{
    "epoch": 3.84,
    "global_step": 9600,
    "max_steps": 12500,
    "logging_steps": 5,
    "eval_steps": 300,
    "save_steps": 0,
    "train_batch_size": 32,
    "num_train_epochs": 5,
    "num_input_tokens_seen": 0,
    "total_flos": 3.63748104290304e+16,
    "log_history": [
        {
            "loss": 2.5268,
            "grad_norm": 16.133350372314453,
            "learning_rate": 3.2e-08,
            "epoch": 0.002,
            "step": 5
        },
        {
            "loss": 2.5161,
            "grad_norm": 14.84888744354248,
            "learning_rate": 6.4e-08,
            "epoch": 0.004,
            "step": 10
        },
        {
            "loss": 2.5155,
            "grad_norm": 15.398407936096191,
            "learning_rate": 9.6e-08,
            "epoch": 0.006,
            "step": 15
        },
        {
            "loss": 2.5163,
            "grad_norm": 15.783890724182129,
            "learning_rate": 1.28e-07,
            "epoch": 0.008,
            "step": 20
        },
        {
            "loss": 2.5075,
            "grad_norm": 15.233412742614746,
            "learning_rate": 1.6e-07,
            "epoch": 0.01,
            "step": 25
        },
        {
            "loss": 2.517,
            "grad_norm": 16.014202117919922,
            "learning_rate": 1.92e-07,
            "epoch": 0.012,
            "step": 30
        },
        {
            "loss": 2.5128,
            "grad_norm": 15.242566108703613,
            "learning_rate": 2.24e-07,
            "epoch": 0.014,
            "step": 35
        },
        {
            "loss": 2.502,
            "grad_norm": 15.127752304077148,
            "learning_rate": 2.56e-07,
            "epoch": 0.016,
            "step": 40
        },
        {
            "loss": 2.4916,
            "grad_norm": 15.18114948272705,
            "learning_rate": 2.88e-07,
            "epoch": 0.018,
            "step": 45
        },
        {
            "loss": 2.4734,
            "grad_norm": 15.798980712890625,
            "learning_rate": 3.2e-07,
            "epoch": 0.02,
            "step": 50
        },
        {
            "loss": 2.4783,
            "grad_norm": 15.849250793457031,
            "learning_rate": 3.52e-07,
            "epoch": 0.022,
            "step": 55
        },
        {
            "loss": 2.4663,
            "grad_norm": 15.577946662902832,
            "learning_rate": 3.84e-07,
            "epoch": 0.024,
            "step": 60
        },
        {
            "loss": 2.4544,
            "grad_norm": 15.798593521118164,
            "learning_rate": 4.1599999999999997e-07,
            "epoch": 0.026,
            "step": 65
        },
        {
            "loss": 2.4422,
            "grad_norm": 15.301485061645508,
            "learning_rate": 4.48e-07,
            "epoch": 0.028,
            "step": 70
        },
        {
            "loss": 2.4251,
            "grad_norm": 15.569108963012695,
            "learning_rate": 4.8e-07,
            "epoch": 0.03,
            "step": 75
        },
        {
            "loss": 2.4175,
            "grad_norm": 15.294572830200195,
            "learning_rate": 5.12e-07,
            "epoch": 0.032,
            "step": 80
        },
        {
            "loss": 2.3908,
            "grad_norm": 14.963807106018066,
            "learning_rate": 5.44e-07,
            "epoch": 0.034,
            "step": 85
        },
        {
            "loss": 2.3822,
            "grad_norm": 15.635550498962402,
            "learning_rate": 5.76e-07,
            "epoch": 0.036,
            "step": 90
        },
        {
            "loss": 2.3725,
            "grad_norm": 15.150557518005371,
            "learning_rate": 6.079999999999999e-07,
            "epoch": 0.038,
            "step": 95
        },
        {
            "loss": 2.3445,
            "grad_norm": 15.063860893249512,
            "learning_rate": 6.4e-07,
            "epoch": 0.04,
            "step": 100
        },
        {
            "loss": 2.3278,
            "grad_norm": 15.137476921081543,
            "learning_rate": 6.72e-07,
            "epoch": 0.042,
            "step": 105
        },
        {
            "loss": 2.3031,
            "grad_norm": 14.787077903747559,
            "learning_rate": 7.04e-07,
            "epoch": 0.044,
            "step": 110
        },
        {
            "loss": 2.2727,
            "grad_norm": 15.38878059387207,
            "learning_rate": 7.359999999999999e-07,
            "epoch": 0.046,
            "step": 115
        },
        {
            "loss": 2.2556,
            "grad_norm": 15.348287582397461,
            "learning_rate": 7.68e-07,
            "epoch": 0.048,
            "step": 120
        },
        {
            "loss": 2.2295,
            "grad_norm": 14.54725456237793,
            "learning_rate": 8e-07,
            "epoch": 0.05,
            "step": 125
        },
        {
            "loss": 2.1979,
            "grad_norm": 15.238685607910156,
            "learning_rate": 8.319999999999999e-07,
            "epoch": 0.052,
            "step": 130
        },
        {
            "loss": 2.1635,
            "grad_norm": 14.70527458190918,
            "learning_rate": 8.639999999999999e-07,
            "epoch": 0.054,
            "step": 135
        },
        {
            "loss": 2.1285,
            "grad_norm": 14.510773658752441,
            "learning_rate": 8.96e-07,
            "epoch": 0.056,
            "step": 140
        },
        {
            "loss": 2.0941,
            "grad_norm": 15.0075101852417,
            "learning_rate": 9.28e-07,
            "epoch": 0.058,
            "step": 145
        },
        {
            "loss": 2.0416,
            "grad_norm": 14.339794158935547,
            "learning_rate": 9.6e-07,
            "epoch": 0.06,
            "step": 150
        },
        {
            "loss": 1.9913,
            "grad_norm": 14.906635284423828,
            "learning_rate": 9.92e-07,
            "epoch": 0.062,
            "step": 155
        },
        {
            "loss": 1.9468,
            "grad_norm": 14.263531684875488,
            "learning_rate": 1.024e-06,
            "epoch": 0.064,
            "step": 160
        },
        {
            "loss": 1.8718,
            "grad_norm": 14.663393020629883,
            "learning_rate": 1.056e-06,
            "epoch": 0.066,
            "step": 165
        },
        {
            "loss": 1.8186,
            "grad_norm": 14.615333557128906,
            "learning_rate": 1.088e-06,
            "epoch": 0.068,
            "step": 170
        },
        {
            "loss": 1.725,
            "grad_norm": 14.633109092712402,
            "learning_rate": 1.12e-06,
            "epoch": 0.07,
            "step": 175
        },
        {
            "loss": 1.6146,
            "grad_norm": 15.169989585876465,
            "learning_rate": 1.152e-06,
            "epoch": 0.072,
            "step": 180
        },
        {
            "loss": 1.4998,
            "grad_norm": 15.033684730529785,
            "learning_rate": 1.1839999999999998e-06,
            "epoch": 0.074,
            "step": 185
        },
        {
            "loss": 1.301,
            "grad_norm": 15.551471710205078,
            "learning_rate": 1.2159999999999999e-06,
            "epoch": 0.076,
            "step": 190
        },
        {
            "loss": 1.0338,
            "grad_norm": 15.359707832336426,
            "learning_rate": 1.248e-06,
            "epoch": 0.078,
            "step": 195
        },
        {
            "loss": 0.806,
            "grad_norm": 7.907179832458496,
            "learning_rate": 1.28e-06,
            "epoch": 0.08,
            "step": 200
        },
        {
            "loss": 0.7207,
            "grad_norm": 3.2169458866119385,
            "learning_rate": 1.312e-06,
            "epoch": 0.082,
            "step": 205
        },
        {
            "loss": 0.5559,
            "grad_norm": 1.8723922967910767,
            "learning_rate": 1.344e-06,
            "epoch": 0.084,
            "step": 210
        },
        {
            "loss": 0.5757,
            "grad_norm": 1.5876153707504272,
            "learning_rate": 1.3759999999999998e-06,
            "epoch": 0.086,
            "step": 215
        },
        {
            "loss": 0.5581,
            "grad_norm": 1.9984169006347656,
            "learning_rate": 1.408e-06,
            "epoch": 0.088,
            "step": 220
        },
        {
            "loss": 0.5586,
            "grad_norm": 2.7533481121063232,
            "learning_rate": 1.44e-06,
            "epoch": 0.09,
            "step": 225
        },
        {
            "loss": 0.5814,
            "grad_norm": 1.501729130744934,
            "learning_rate": 1.4719999999999998e-06,
            "epoch": 0.092,
            "step": 230
        },
        {
            "loss": 0.5214,
            "grad_norm": 1.4177746772766113,
            "learning_rate": 1.504e-06,
            "epoch": 0.094,
            "step": 235
        },
        {
            "loss": 0.5143,
            "grad_norm": 1.4111453294754028,
            "learning_rate": 1.536e-06,
            "epoch": 0.096,
            "step": 240
        },
        {
            "loss": 0.4862,
            "grad_norm": 2.962812662124634,
            "learning_rate": 1.568e-06,
            "epoch": 0.098,
            "step": 245
        },
        {
            "loss": 0.4822,
            "grad_norm": 2.2985591888427734,
            "learning_rate": 1.6e-06,
            "epoch": 0.1,
            "step": 250
        },
        {
            "loss": 0.4687,
            "grad_norm": 1.5222264528274536,
            "learning_rate": 1.6319999999999998e-06,
            "epoch": 0.102,
            "step": 255
        },
        {
            "loss": 0.5013,
            "grad_norm": 2.4972426891326904,
            "learning_rate": 1.6639999999999999e-06,
            "epoch": 0.104,
            "step": 260
        },
        {
            "loss": 0.3939,
            "grad_norm": 1.4573918581008911,
            "learning_rate": 1.696e-06,
            "epoch": 0.106,
            "step": 265
        },
        {
            "loss": 0.4413,
            "grad_norm": 2.337775468826294,
            "learning_rate": 1.7279999999999998e-06,
            "epoch": 0.108,
            "step": 270
        },
        {
            "loss": 0.4228,
            "grad_norm": 1.4672980308532715,
            "learning_rate": 1.7599999999999999e-06,
            "epoch": 0.11,
            "step": 275
        },
        {
            "loss": 0.4029,
            "grad_norm": 1.662713646888733,
            "learning_rate": 1.792e-06,
            "epoch": 0.112,
            "step": 280
        },
        {
            "loss": 0.3813,
            "grad_norm": 1.564231038093567,
            "learning_rate": 1.824e-06,
            "epoch": 0.114,
            "step": 285
        },
        {
            "loss": 0.408,
            "grad_norm": 2.164536237716675,
            "learning_rate": 1.856e-06,
            "epoch": 0.116,
            "step": 290
        },
        {
            "loss": 0.3692,
            "grad_norm": 1.7828514575958252,
            "learning_rate": 1.8879999999999998e-06,
            "epoch": 0.118,
            "step": 295
        },
        {
            "loss": 0.3728,
            "grad_norm": 1.4622581005096436,
            "learning_rate": 1.92e-06,
            "epoch": 0.12,
            "step": 300
        },
        {
            "eval_loss": 0.3354146480560303,
            "eval_f1": 0.00487408610885459,
            "eval_recall": 0.0028364323983611725,
            "eval_accuracy": 0.8979505610285702,
            "eval_precision": 0.01730769230769231,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.0,
                    "recall": 0.0,
                    "f1-score": 0.0,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.0,
                    "recall": 0.0,
                    "f1-score": 0.0,
                    "support": 876
                },
                "PER": {
                    "precision": 0.017324350336862367,
                    "recall": 0.005122367672168469,
                    "f1-score": 0.007906874588183616,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.0,
                    "recall": 0.0,
                    "f1-score": 0.0,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.01730769230769231,
                    "recall": 0.0028364323983611725,
                    "f1-score": 0.00487408610885459,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.004331087584215592,
                    "recall": 0.0012805919180421173,
                    "f1-score": 0.001976718647045904,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.009593092827566083,
                    "recall": 0.0028364323983611725,
                    "f1-score": 0.00437831032191573,
                    "support": 6346
                }
            },
            "eval_runtime": 4.5783,
            "eval_samples_per_second": 894.652,
            "eval_steps_per_second": 6.989,
            "epoch": 0.12,
            "step": 300
        },
        {
            "loss": 0.3304,
            "grad_norm": 1.6962974071502686,
            "learning_rate": 1.9519999999999997e-06,
            "epoch": 0.122,
            "step": 305
        },
        {
            "loss": 0.3458,
            "grad_norm": 1.308433175086975,
            "learning_rate": 1.984e-06,
            "epoch": 0.124,
            "step": 310
        },
        {
            "loss": 0.3442,
            "grad_norm": 2.2314276695251465,
            "learning_rate": 2.016e-06,
            "epoch": 0.126,
            "step": 315
        },
        {
            "loss": 0.3696,
            "grad_norm": 1.9199355840682983,
            "learning_rate": 2.048e-06,
            "epoch": 0.128,
            "step": 320
        },
        {
            "loss": 0.3166,
            "grad_norm": 1.6935266256332397,
            "learning_rate": 2.08e-06,
            "epoch": 0.13,
            "step": 325
        },
        {
            "loss": 0.346,
            "grad_norm": 1.811660885810852,
            "learning_rate": 2.112e-06,
            "epoch": 0.132,
            "step": 330
        },
        {
            "loss": 0.3657,
            "grad_norm": 1.5775116682052612,
            "learning_rate": 2.144e-06,
            "epoch": 0.134,
            "step": 335
        },
        {
            "loss": 0.2938,
            "grad_norm": 1.6461272239685059,
            "learning_rate": 2.176e-06,
            "epoch": 0.136,
            "step": 340
        },
        {
            "loss": 0.3306,
            "grad_norm": 1.7531514167785645,
            "learning_rate": 2.2080000000000003e-06,
            "epoch": 0.138,
            "step": 345
        },
        {
            "loss": 0.3464,
            "grad_norm": 1.6555029153823853,
            "learning_rate": 2.24e-06,
            "epoch": 0.14,
            "step": 350
        },
        {
            "loss": 0.2953,
            "grad_norm": 1.4035905599594116,
            "learning_rate": 2.2719999999999996e-06,
            "epoch": 0.142,
            "step": 355
        },
        {
            "loss": 0.3325,
            "grad_norm": 2.567598581314087,
            "learning_rate": 2.304e-06,
            "epoch": 0.144,
            "step": 360
        },
        {
            "loss": 0.3082,
            "grad_norm": 2.6436054706573486,
            "learning_rate": 2.3359999999999997e-06,
            "epoch": 0.146,
            "step": 365
        },
        {
            "loss": 0.2998,
            "grad_norm": 1.9194581508636475,
            "learning_rate": 2.3679999999999996e-06,
            "epoch": 0.148,
            "step": 370
        },
        {
            "loss": 0.316,
            "grad_norm": 1.3982847929000854,
            "learning_rate": 2.4e-06,
            "epoch": 0.15,
            "step": 375
        },
        {
            "loss": 0.3,
            "grad_norm": 1.6546880006790161,
            "learning_rate": 2.4319999999999998e-06,
            "epoch": 0.152,
            "step": 380
        },
        {
            "loss": 0.2655,
            "grad_norm": 2.259777069091797,
            "learning_rate": 2.464e-06,
            "epoch": 0.154,
            "step": 385
        },
        {
            "loss": 0.2699,
            "grad_norm": 1.7673263549804688,
            "learning_rate": 2.496e-06,
            "epoch": 0.156,
            "step": 390
        },
        {
            "loss": 0.2811,
            "grad_norm": 3.892162322998047,
            "learning_rate": 2.5279999999999998e-06,
            "epoch": 0.158,
            "step": 395
        },
        {
            "loss": 0.2772,
            "grad_norm": 1.8219752311706543,
            "learning_rate": 2.56e-06,
            "epoch": 0.16,
            "step": 400
        },
        {
            "loss": 0.2781,
            "grad_norm": 1.3643286228179932,
            "learning_rate": 2.592e-06,
            "epoch": 0.162,
            "step": 405
        },
        {
            "loss": 0.2373,
            "grad_norm": 1.9395954608917236,
            "learning_rate": 2.624e-06,
            "epoch": 0.164,
            "step": 410
        },
        {
            "loss": 0.2706,
            "grad_norm": 1.9215404987335205,
            "learning_rate": 2.656e-06,
            "epoch": 0.166,
            "step": 415
        },
        {
            "loss": 0.2366,
            "grad_norm": 1.8311808109283447,
            "learning_rate": 2.688e-06,
            "epoch": 0.168,
            "step": 420
        },
        {
            "loss": 0.2439,
            "grad_norm": 4.7104315757751465,
            "learning_rate": 2.7200000000000002e-06,
            "epoch": 0.17,
            "step": 425
        },
        {
            "loss": 0.2652,
            "grad_norm": 1.6695914268493652,
            "learning_rate": 2.7519999999999997e-06,
            "epoch": 0.172,
            "step": 430
        },
        {
            "loss": 0.2686,
            "grad_norm": 3.2596871852874756,
            "learning_rate": 2.7839999999999995e-06,
            "epoch": 0.174,
            "step": 435
        },
        {
            "loss": 0.2503,
            "grad_norm": 1.2396231889724731,
            "learning_rate": 2.816e-06,
            "epoch": 0.176,
            "step": 440
        },
        {
            "loss": 0.2437,
            "grad_norm": 1.248783826828003,
            "learning_rate": 2.8479999999999997e-06,
            "epoch": 0.178,
            "step": 445
        },
        {
            "loss": 0.2865,
            "grad_norm": 2.0188465118408203,
            "learning_rate": 2.88e-06,
            "epoch": 0.18,
            "step": 450
        },
        {
            "loss": 0.2787,
            "grad_norm": 1.6038897037506104,
            "learning_rate": 2.912e-06,
            "epoch": 0.182,
            "step": 455
        },
        {
            "loss": 0.2642,
            "grad_norm": 2.3539955615997314,
            "learning_rate": 2.9439999999999997e-06,
            "epoch": 0.184,
            "step": 460
        },
        {
            "loss": 0.2714,
            "grad_norm": 2.066349983215332,
            "learning_rate": 2.976e-06,
            "epoch": 0.186,
            "step": 465
        },
        {
            "loss": 0.2159,
            "grad_norm": 1.4786362648010254,
            "learning_rate": 3.008e-06,
            "epoch": 0.188,
            "step": 470
        },
        {
            "loss": 0.2233,
            "grad_norm": 2.180941581726074,
            "learning_rate": 3.0399999999999997e-06,
            "epoch": 0.19,
            "step": 475
        },
        {
            "loss": 0.2266,
            "grad_norm": 1.6064552068710327,
            "learning_rate": 3.072e-06,
            "epoch": 0.192,
            "step": 480
        },
        {
            "loss": 0.2394,
            "grad_norm": 1.6990272998809814,
            "learning_rate": 3.104e-06,
            "epoch": 0.194,
            "step": 485
        },
        {
            "loss": 0.2153,
            "grad_norm": 1.6439210176467896,
            "learning_rate": 3.136e-06,
            "epoch": 0.196,
            "step": 490
        },
        {
            "loss": 0.2308,
            "grad_norm": 1.447668433189392,
            "learning_rate": 3.168e-06,
            "epoch": 0.198,
            "step": 495
        },
        {
            "loss": 0.2481,
            "grad_norm": 2.030056953430176,
            "learning_rate": 3.2e-06,
            "epoch": 0.2,
            "step": 500
        },
        {
            "loss": 0.2139,
            "grad_norm": 1.6460680961608887,
            "learning_rate": 3.232e-06,
            "epoch": 0.202,
            "step": 505
        },
        {
            "loss": 0.2504,
            "grad_norm": 2.0557398796081543,
            "learning_rate": 3.2639999999999996e-06,
            "epoch": 0.204,
            "step": 510
        },
        {
            "loss": 0.2418,
            "grad_norm": 1.8461668491363525,
            "learning_rate": 3.296e-06,
            "epoch": 0.206,
            "step": 515
        },
        {
            "loss": 0.2451,
            "grad_norm": 1.7242536544799805,
            "learning_rate": 3.3279999999999997e-06,
            "epoch": 0.208,
            "step": 520
        },
        {
            "loss": 0.2008,
            "grad_norm": 2.204143524169922,
            "learning_rate": 3.3599999999999996e-06,
            "epoch": 0.21,
            "step": 525
        },
        {
            "loss": 0.2119,
            "grad_norm": 1.5572588443756104,
            "learning_rate": 3.392e-06,
            "epoch": 0.212,
            "step": 530
        },
        {
            "loss": 0.2313,
            "grad_norm": 2.58699893951416,
            "learning_rate": 3.4239999999999997e-06,
            "epoch": 0.214,
            "step": 535
        },
        {
            "loss": 0.1838,
            "grad_norm": 1.5217881202697754,
            "learning_rate": 3.4559999999999996e-06,
            "epoch": 0.216,
            "step": 540
        },
        {
            "loss": 0.2088,
            "grad_norm": 3.143136978149414,
            "learning_rate": 3.488e-06,
            "epoch": 0.218,
            "step": 545
        },
        {
            "loss": 0.1968,
            "grad_norm": 2.258408546447754,
            "learning_rate": 3.5199999999999998e-06,
            "epoch": 0.22,
            "step": 550
        },
        {
            "loss": 0.1955,
            "grad_norm": 3.3416690826416016,
            "learning_rate": 3.552e-06,
            "epoch": 0.222,
            "step": 555
        },
        {
            "loss": 0.2105,
            "grad_norm": 2.335618495941162,
            "learning_rate": 3.584e-06,
            "epoch": 0.224,
            "step": 560
        },
        {
            "loss": 0.2072,
            "grad_norm": 2.2555360794067383,
            "learning_rate": 3.6159999999999998e-06,
            "epoch": 0.226,
            "step": 565
        },
        {
            "loss": 0.1885,
            "grad_norm": 1.5827440023422241,
            "learning_rate": 3.648e-06,
            "epoch": 0.228,
            "step": 570
        },
        {
            "loss": 0.1588,
            "grad_norm": 1.7830958366394043,
            "learning_rate": 3.68e-06,
            "epoch": 0.23,
            "step": 575
        },
        {
            "loss": 0.1897,
            "grad_norm": 1.719193935394287,
            "learning_rate": 3.712e-06,
            "epoch": 0.232,
            "step": 580
        },
        {
            "loss": 0.1882,
            "grad_norm": 2.1949222087860107,
            "learning_rate": 3.744e-06,
            "epoch": 0.234,
            "step": 585
        },
        {
            "loss": 0.1854,
            "grad_norm": 2.689244508743286,
            "learning_rate": 3.7759999999999995e-06,
            "epoch": 0.236,
            "step": 590
        },
        {
            "loss": 0.187,
            "grad_norm": 1.785309076309204,
            "learning_rate": 3.808e-06,
            "epoch": 0.238,
            "step": 595
        },
        {
            "loss": 0.1883,
            "grad_norm": 3.2251055240631104,
            "learning_rate": 3.84e-06,
            "epoch": 0.24,
            "step": 600
        },
        {
            "eval_loss": 0.18151065707206726,
            "eval_f1": 0.4366562479217929,
            "eval_recall": 0.5173337535455405,
            "eval_accuracy": 0.9406186824118346,
            "eval_precision": 0.3777470946956622,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.17842876165113183,
                    "recall": 0.2607003891050584,
                    "f1-score": 0.21185770750988145,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.06685768863419293,
                    "recall": 0.07990867579908675,
                    "f1-score": 0.07280291211648467,
                    "support": 876
                },
                "PER": {
                    "precision": 0.5522388059701493,
                    "recall": 0.8212862834376778,
                    "f1-score": 0.6604118993135011,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.06441048034934498,
                    "recall": 0.06357758620689655,
                    "f1-score": 0.06399132321041215,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.3777470946956622,
                    "recall": 0.5173337535455405,
                    "f1-score": 0.4366562479217929,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.21548393415120473,
                    "recall": 0.30636823363717985,
                    "f1-score": 0.25226596053756983,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.35334575987460026,
                    "recall": 0.5173337535455405,
                    "f1-score": 0.41941954561315853,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4851,
            "eval_samples_per_second": 913.248,
            "eval_steps_per_second": 7.135,
            "epoch": 0.24,
            "step": 600
        },
        {
            "loss": 0.1854,
            "grad_norm": 1.8407150506973267,
            "learning_rate": 3.8719999999999995e-06,
            "epoch": 0.242,
            "step": 605
        },
        {
            "loss": 0.1912,
            "grad_norm": 2.229262113571167,
            "learning_rate": 3.903999999999999e-06,
            "epoch": 0.244,
            "step": 610
        },
        {
            "loss": 0.1727,
            "grad_norm": 1.8601970672607422,
            "learning_rate": 3.936e-06,
            "epoch": 0.246,
            "step": 615
        },
        {
            "loss": 0.1858,
            "grad_norm": 2.8779358863830566,
            "learning_rate": 3.968e-06,
            "epoch": 0.248,
            "step": 620
        },
        {
            "loss": 0.1805,
            "grad_norm": 1.9415929317474365,
            "learning_rate": 4e-06,
            "epoch": 0.25,
            "step": 625
        },
        {
            "loss": 0.1696,
            "grad_norm": 2.7695600986480713,
            "learning_rate": 4.032e-06,
            "epoch": 0.252,
            "step": 630
        },
        {
            "loss": 0.2183,
            "grad_norm": 2.749915361404419,
            "learning_rate": 4.0639999999999995e-06,
            "epoch": 0.254,
            "step": 635
        },
        {
            "loss": 0.1987,
            "grad_norm": 2.4085581302642822,
            "learning_rate": 4.096e-06,
            "epoch": 0.256,
            "step": 640
        },
        {
            "loss": 0.1799,
            "grad_norm": 2.114816665649414,
            "learning_rate": 4.128e-06,
            "epoch": 0.258,
            "step": 645
        },
        {
            "loss": 0.163,
            "grad_norm": 2.882733106613159,
            "learning_rate": 4.16e-06,
            "epoch": 0.26,
            "step": 650
        },
        {
            "loss": 0.1647,
            "grad_norm": 1.5387121438980103,
            "learning_rate": 4.192e-06,
            "epoch": 0.262,
            "step": 655
        },
        {
            "loss": 0.1612,
            "grad_norm": 1.6238993406295776,
            "learning_rate": 4.224e-06,
            "epoch": 0.264,
            "step": 660
        },
        {
            "loss": 0.2001,
            "grad_norm": 3.3563082218170166,
            "learning_rate": 4.256e-06,
            "epoch": 0.266,
            "step": 665
        },
        {
            "loss": 0.1908,
            "grad_norm": 2.149529457092285,
            "learning_rate": 4.288e-06,
            "epoch": 0.268,
            "step": 670
        },
        {
            "loss": 0.2101,
            "grad_norm": 2.43994402885437,
            "learning_rate": 4.32e-06,
            "epoch": 0.27,
            "step": 675
        },
        {
            "loss": 0.1859,
            "grad_norm": 1.7799561023712158,
            "learning_rate": 4.352e-06,
            "epoch": 0.272,
            "step": 680
        },
        {
            "loss": 0.1977,
            "grad_norm": 2.3376314640045166,
            "learning_rate": 4.384e-06,
            "epoch": 0.274,
            "step": 685
        },
        {
            "loss": 0.1719,
            "grad_norm": 2.0569114685058594,
            "learning_rate": 4.416000000000001e-06,
            "epoch": 0.276,
            "step": 690
        },
        {
            "loss": 0.163,
            "grad_norm": 3.003807544708252,
            "learning_rate": 4.4480000000000004e-06,
            "epoch": 0.278,
            "step": 695
        },
        {
            "loss": 0.1912,
            "grad_norm": 5.920291900634766,
            "learning_rate": 4.48e-06,
            "epoch": 0.28,
            "step": 700
        },
        {
            "loss": 0.1656,
            "grad_norm": 1.8108654022216797,
            "learning_rate": 4.511999999999999e-06,
            "epoch": 0.282,
            "step": 705
        },
        {
            "loss": 0.1802,
            "grad_norm": 2.667088031768799,
            "learning_rate": 4.543999999999999e-06,
            "epoch": 0.284,
            "step": 710
        },
        {
            "loss": 0.1512,
            "grad_norm": 3.99697208404541,
            "learning_rate": 4.575999999999999e-06,
            "epoch": 0.286,
            "step": 715
        },
        {
            "loss": 0.2039,
            "grad_norm": 3.946279287338257,
            "learning_rate": 4.608e-06,
            "epoch": 0.288,
            "step": 720
        },
        {
            "loss": 0.1578,
            "grad_norm": 2.7749242782592773,
            "learning_rate": 4.64e-06,
            "epoch": 0.29,
            "step": 725
        },
        {
            "loss": 0.1573,
            "grad_norm": 2.427551031112671,
            "learning_rate": 4.6719999999999995e-06,
            "epoch": 0.292,
            "step": 730
        },
        {
            "loss": 0.1581,
            "grad_norm": 1.6226930618286133,
            "learning_rate": 4.703999999999999e-06,
            "epoch": 0.294,
            "step": 735
        },
        {
            "loss": 0.1703,
            "grad_norm": 3.0467660427093506,
            "learning_rate": 4.735999999999999e-06,
            "epoch": 0.296,
            "step": 740
        },
        {
            "loss": 0.1682,
            "grad_norm": 2.1693990230560303,
            "learning_rate": 4.768e-06,
            "epoch": 0.298,
            "step": 745
        },
        {
            "loss": 0.1414,
            "grad_norm": 3.378171443939209,
            "learning_rate": 4.8e-06,
            "epoch": 0.3,
            "step": 750
        },
        {
            "loss": 0.1554,
            "grad_norm": 2.861342430114746,
            "learning_rate": 4.832e-06,
            "epoch": 0.302,
            "step": 755
        },
        {
            "loss": 0.1555,
            "grad_norm": 4.578545093536377,
            "learning_rate": 4.8639999999999995e-06,
            "epoch": 0.304,
            "step": 760
        },
        {
            "loss": 0.1528,
            "grad_norm": 1.9380147457122803,
            "learning_rate": 4.895999999999999e-06,
            "epoch": 0.306,
            "step": 765
        },
        {
            "loss": 0.1553,
            "grad_norm": 2.095710515975952,
            "learning_rate": 4.928e-06,
            "epoch": 0.308,
            "step": 770
        },
        {
            "loss": 0.1469,
            "grad_norm": 2.028012275695801,
            "learning_rate": 4.96e-06,
            "epoch": 0.31,
            "step": 775
        },
        {
            "loss": 0.1387,
            "grad_norm": 3.573380470275879,
            "learning_rate": 4.992e-06,
            "epoch": 0.312,
            "step": 780
        },
        {
            "loss": 0.1502,
            "grad_norm": 3.8040242195129395,
            "learning_rate": 5.024e-06,
            "epoch": 0.314,
            "step": 785
        },
        {
            "loss": 0.1723,
            "grad_norm": 2.9107425212860107,
            "learning_rate": 5.0559999999999995e-06,
            "epoch": 0.316,
            "step": 790
        },
        {
            "loss": 0.1469,
            "grad_norm": 2.459500551223755,
            "learning_rate": 5.088e-06,
            "epoch": 0.318,
            "step": 795
        },
        {
            "loss": 0.1527,
            "grad_norm": 2.3761110305786133,
            "learning_rate": 5.12e-06,
            "epoch": 0.32,
            "step": 800
        },
        {
            "loss": 0.135,
            "grad_norm": 2.6900863647460938,
            "learning_rate": 5.152e-06,
            "epoch": 0.322,
            "step": 805
        },
        {
            "loss": 0.1239,
            "grad_norm": 2.9080264568328857,
            "learning_rate": 5.184e-06,
            "epoch": 0.324,
            "step": 810
        },
        {
            "loss": 0.1462,
            "grad_norm": 1.5792351961135864,
            "learning_rate": 5.216e-06,
            "epoch": 0.326,
            "step": 815
        },
        {
            "loss": 0.1381,
            "grad_norm": 2.521165609359741,
            "learning_rate": 5.248e-06,
            "epoch": 0.328,
            "step": 820
        },
        {
            "loss": 0.1103,
            "grad_norm": 1.9186408519744873,
            "learning_rate": 5.28e-06,
            "epoch": 0.33,
            "step": 825
        },
        {
            "loss": 0.1603,
            "grad_norm": 1.647247076034546,
            "learning_rate": 5.312e-06,
            "epoch": 0.332,
            "step": 830
        },
        {
            "loss": 0.1587,
            "grad_norm": 4.094577789306641,
            "learning_rate": 5.344e-06,
            "epoch": 0.334,
            "step": 835
        },
        {
            "loss": 0.1399,
            "grad_norm": 2.6570229530334473,
            "learning_rate": 5.376e-06,
            "epoch": 0.336,
            "step": 840
        },
        {
            "loss": 0.148,
            "grad_norm": 2.2654404640197754,
            "learning_rate": 5.408e-06,
            "epoch": 0.338,
            "step": 845
        },
        {
            "loss": 0.1497,
            "grad_norm": 2.284410238265991,
            "learning_rate": 5.4400000000000004e-06,
            "epoch": 0.34,
            "step": 850
        },
        {
            "loss": 0.1446,
            "grad_norm": 4.6466474533081055,
            "learning_rate": 5.472e-06,
            "epoch": 0.342,
            "step": 855
        },
        {
            "loss": 0.1516,
            "grad_norm": 2.8773186206817627,
            "learning_rate": 5.503999999999999e-06,
            "epoch": 0.344,
            "step": 860
        },
        {
            "loss": 0.1452,
            "grad_norm": 2.2973082065582275,
            "learning_rate": 5.535999999999999e-06,
            "epoch": 0.346,
            "step": 865
        },
        {
            "loss": 0.176,
            "grad_norm": 2.536414384841919,
            "learning_rate": 5.567999999999999e-06,
            "epoch": 0.348,
            "step": 870
        },
        {
            "loss": 0.1305,
            "grad_norm": 2.7103326320648193,
            "learning_rate": 5.6e-06,
            "epoch": 0.35,
            "step": 875
        },
        {
            "loss": 0.1333,
            "grad_norm": 2.1574366092681885,
            "learning_rate": 5.632e-06,
            "epoch": 0.352,
            "step": 880
        },
        {
            "loss": 0.1558,
            "grad_norm": 2.3346569538116455,
            "learning_rate": 5.6639999999999995e-06,
            "epoch": 0.354,
            "step": 885
        },
        {
            "loss": 0.1442,
            "grad_norm": 2.2171738147735596,
            "learning_rate": 5.695999999999999e-06,
            "epoch": 0.356,
            "step": 890
        },
        {
            "loss": 0.1283,
            "grad_norm": 1.5601425170898438,
            "learning_rate": 5.727999999999999e-06,
            "epoch": 0.358,
            "step": 895
        },
        {
            "loss": 0.1506,
            "grad_norm": 2.4185307025909424,
            "learning_rate": 5.76e-06,
            "epoch": 0.36,
            "step": 900
        },
        {
            "eval_loss": 0.1293565332889557,
            "eval_f1": 0.6398730830248545,
            "eval_recall": 0.6673495115033091,
            "eval_accuracy": 0.9566152167634695,
            "eval_precision": 0.6145697286315484,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.46348962336664107,
                    "recall": 0.5865758754863813,
                    "f1-score": 0.5178188063546586,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.48459715639810425,
                    "recall": 0.4668949771689498,
                    "f1-score": 0.47558139534883714,
                    "support": 876
                },
                "PER": {
                    "precision": 0.7338183642749624,
                    "recall": 0.8323847467273762,
                    "f1-score": 0.7799999999999999,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.39210526315789473,
                    "recall": 0.32112068965517243,
                    "f1-score": 0.3530805687203792,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.6145697286315484,
                    "recall": 0.6673495115033091,
                    "f1-score": 0.6398730830248545,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.5185026017994006,
                    "recall": 0.55174407225947,
                    "f1-score": 0.5316201926059687,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.6056548783640704,
                    "recall": 0.6673495115033091,
                    "f1-score": 0.6330768677955692,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4874,
            "eval_samples_per_second": 912.787,
            "eval_steps_per_second": 7.131,
            "epoch": 0.36,
            "step": 900
        },
        {
            "loss": 0.1455,
            "grad_norm": 4.152116298675537,
            "learning_rate": 5.792e-06,
            "epoch": 0.362,
            "step": 905
        },
        {
            "loss": 0.1346,
            "grad_norm": 3.55926775932312,
            "learning_rate": 5.824e-06,
            "epoch": 0.364,
            "step": 910
        },
        {
            "loss": 0.1156,
            "grad_norm": 2.7267816066741943,
            "learning_rate": 5.8559999999999995e-06,
            "epoch": 0.366,
            "step": 915
        },
        {
            "loss": 0.1302,
            "grad_norm": 2.0737144947052,
            "learning_rate": 5.887999999999999e-06,
            "epoch": 0.368,
            "step": 920
        },
        {
            "loss": 0.145,
            "grad_norm": 2.326054811477661,
            "learning_rate": 5.92e-06,
            "epoch": 0.37,
            "step": 925
        },
        {
            "loss": 0.1295,
            "grad_norm": 3.610700845718384,
            "learning_rate": 5.952e-06,
            "epoch": 0.372,
            "step": 930
        },
        {
            "loss": 0.1418,
            "grad_norm": 3.3352484703063965,
            "learning_rate": 5.984e-06,
            "epoch": 0.374,
            "step": 935
        },
        {
            "loss": 0.1374,
            "grad_norm": 2.08766508102417,
            "learning_rate": 6.016e-06,
            "epoch": 0.376,
            "step": 940
        },
        {
            "loss": 0.1405,
            "grad_norm": 2.5608620643615723,
            "learning_rate": 6.0479999999999995e-06,
            "epoch": 0.378,
            "step": 945
        },
        {
            "loss": 0.1348,
            "grad_norm": 2.067394971847534,
            "learning_rate": 6.079999999999999e-06,
            "epoch": 0.38,
            "step": 950
        },
        {
            "loss": 0.1478,
            "grad_norm": 2.299405813217163,
            "learning_rate": 6.112e-06,
            "epoch": 0.382,
            "step": 955
        },
        {
            "loss": 0.1486,
            "grad_norm": 2.649480104446411,
            "learning_rate": 6.144e-06,
            "epoch": 0.384,
            "step": 960
        },
        {
            "loss": 0.1359,
            "grad_norm": 2.1568503379821777,
            "learning_rate": 6.176e-06,
            "epoch": 0.386,
            "step": 965
        },
        {
            "loss": 0.1205,
            "grad_norm": 1.940739393234253,
            "learning_rate": 6.208e-06,
            "epoch": 0.388,
            "step": 970
        },
        {
            "loss": 0.1559,
            "grad_norm": 6.96638298034668,
            "learning_rate": 6.2399999999999995e-06,
            "epoch": 0.39,
            "step": 975
        },
        {
            "loss": 0.1356,
            "grad_norm": 3.2226979732513428,
            "learning_rate": 6.272e-06,
            "epoch": 0.392,
            "step": 980
        },
        {
            "loss": 0.1342,
            "grad_norm": 2.922348976135254,
            "learning_rate": 6.304e-06,
            "epoch": 0.394,
            "step": 985
        },
        {
            "loss": 0.1375,
            "grad_norm": 3.6619770526885986,
            "learning_rate": 6.336e-06,
            "epoch": 0.396,
            "step": 990
        },
        {
            "loss": 0.1362,
            "grad_norm": 2.7726478576660156,
            "learning_rate": 6.368e-06,
            "epoch": 0.398,
            "step": 995
        },
        {
            "loss": 0.116,
            "grad_norm": 2.9028987884521484,
            "learning_rate": 6.4e-06,
            "epoch": 0.4,
            "step": 1000
        },
        {
            "loss": 0.1602,
            "grad_norm": 3.2052741050720215,
            "learning_rate": 6.432e-06,
            "epoch": 0.402,
            "step": 1005
        },
        {
            "loss": 0.1416,
            "grad_norm": 4.2089643478393555,
            "learning_rate": 6.464e-06,
            "epoch": 0.404,
            "step": 1010
        },
        {
            "loss": 0.1306,
            "grad_norm": 1.9934160709381104,
            "learning_rate": 6.496e-06,
            "epoch": 0.406,
            "step": 1015
        },
        {
            "loss": 0.1332,
            "grad_norm": 2.8803083896636963,
            "learning_rate": 6.527999999999999e-06,
            "epoch": 0.408,
            "step": 1020
        },
        {
            "loss": 0.1242,
            "grad_norm": 3.181933641433716,
            "learning_rate": 6.559999999999999e-06,
            "epoch": 0.41,
            "step": 1025
        },
        {
            "loss": 0.1359,
            "grad_norm": 3.336484432220459,
            "learning_rate": 6.592e-06,
            "epoch": 0.412,
            "step": 1030
        },
        {
            "loss": 0.1167,
            "grad_norm": 1.918241024017334,
            "learning_rate": 6.624e-06,
            "epoch": 0.414,
            "step": 1035
        },
        {
            "loss": 0.1093,
            "grad_norm": 2.4218132495880127,
            "learning_rate": 6.6559999999999995e-06,
            "epoch": 0.416,
            "step": 1040
        },
        {
            "loss": 0.1484,
            "grad_norm": 4.516479015350342,
            "learning_rate": 6.687999999999999e-06,
            "epoch": 0.418,
            "step": 1045
        },
        {
            "loss": 0.1175,
            "grad_norm": 3.450985908508301,
            "learning_rate": 6.719999999999999e-06,
            "epoch": 0.42,
            "step": 1050
        },
        {
            "loss": 0.1358,
            "grad_norm": 2.617156982421875,
            "learning_rate": 6.751999999999999e-06,
            "epoch": 0.422,
            "step": 1055
        },
        {
            "loss": 0.1341,
            "grad_norm": 2.4724085330963135,
            "learning_rate": 6.784e-06,
            "epoch": 0.424,
            "step": 1060
        },
        {
            "loss": 0.1223,
            "grad_norm": 2.672679901123047,
            "learning_rate": 6.816e-06,
            "epoch": 0.426,
            "step": 1065
        },
        {
            "loss": 0.1003,
            "grad_norm": 1.9279921054840088,
            "learning_rate": 6.8479999999999995e-06,
            "epoch": 0.428,
            "step": 1070
        },
        {
            "loss": 0.1416,
            "grad_norm": 2.6067376136779785,
            "learning_rate": 6.879999999999999e-06,
            "epoch": 0.43,
            "step": 1075
        },
        {
            "loss": 0.1197,
            "grad_norm": 1.941898226737976,
            "learning_rate": 6.911999999999999e-06,
            "epoch": 0.432,
            "step": 1080
        },
        {
            "loss": 0.1112,
            "grad_norm": 2.3376991748809814,
            "learning_rate": 6.944e-06,
            "epoch": 0.434,
            "step": 1085
        },
        {
            "loss": 0.1322,
            "grad_norm": 2.3963701725006104,
            "learning_rate": 6.976e-06,
            "epoch": 0.436,
            "step": 1090
        },
        {
            "loss": 0.1105,
            "grad_norm": 3.066112995147705,
            "learning_rate": 7.008e-06,
            "epoch": 0.438,
            "step": 1095
        },
        {
            "loss": 0.1212,
            "grad_norm": 1.8004413843154907,
            "learning_rate": 7.0399999999999995e-06,
            "epoch": 0.44,
            "step": 1100
        },
        {
            "loss": 0.1165,
            "grad_norm": 2.7130348682403564,
            "learning_rate": 7.071999999999999e-06,
            "epoch": 0.442,
            "step": 1105
        },
        {
            "loss": 0.1143,
            "grad_norm": 1.7246865034103394,
            "learning_rate": 7.104e-06,
            "epoch": 0.444,
            "step": 1110
        },
        {
            "loss": 0.1056,
            "grad_norm": 1.9137200117111206,
            "learning_rate": 7.136e-06,
            "epoch": 0.446,
            "step": 1115
        },
        {
            "loss": 0.1242,
            "grad_norm": 2.081324338912964,
            "learning_rate": 7.168e-06,
            "epoch": 0.448,
            "step": 1120
        },
        {
            "loss": 0.1481,
            "grad_norm": 3.1608314514160156,
            "learning_rate": 7.2e-06,
            "epoch": 0.45,
            "step": 1125
        },
        {
            "loss": 0.1147,
            "grad_norm": 1.478460669517517,
            "learning_rate": 7.2319999999999995e-06,
            "epoch": 0.452,
            "step": 1130
        },
        {
            "loss": 0.1202,
            "grad_norm": 1.8189239501953125,
            "learning_rate": 7.264e-06,
            "epoch": 0.454,
            "step": 1135
        },
        {
            "loss": 0.122,
            "grad_norm": 2.241744041442871,
            "learning_rate": 7.296e-06,
            "epoch": 0.456,
            "step": 1140
        },
        {
            "loss": 0.1057,
            "grad_norm": 1.4779651165008545,
            "learning_rate": 7.328e-06,
            "epoch": 0.458,
            "step": 1145
        },
        {
            "loss": 0.1199,
            "grad_norm": 5.8651604652404785,
            "learning_rate": 7.36e-06,
            "epoch": 0.46,
            "step": 1150
        },
        {
            "loss": 0.1272,
            "grad_norm": 2.5674874782562256,
            "learning_rate": 7.392e-06,
            "epoch": 0.462,
            "step": 1155
        },
        {
            "loss": 0.1321,
            "grad_norm": 1.700770616531372,
            "learning_rate": 7.424e-06,
            "epoch": 0.464,
            "step": 1160
        },
        {
            "loss": 0.1305,
            "grad_norm": 2.1846227645874023,
            "learning_rate": 7.456e-06,
            "epoch": 0.466,
            "step": 1165
        },
        {
            "loss": 0.0947,
            "grad_norm": 2.0733227729797363,
            "learning_rate": 7.488e-06,
            "epoch": 0.468,
            "step": 1170
        },
        {
            "loss": 0.1157,
            "grad_norm": 2.285745859146118,
            "learning_rate": 7.519999999999999e-06,
            "epoch": 0.47,
            "step": 1175
        },
        {
            "loss": 0.1494,
            "grad_norm": 4.178990364074707,
            "learning_rate": 7.551999999999999e-06,
            "epoch": 0.472,
            "step": 1180
        },
        {
            "loss": 0.0886,
            "grad_norm": 1.7573225498199463,
            "learning_rate": 7.583999999999999e-06,
            "epoch": 0.474,
            "step": 1185
        },
        {
            "loss": 0.1392,
            "grad_norm": 2.660471200942993,
            "learning_rate": 7.616e-06,
            "epoch": 0.476,
            "step": 1190
        },
        {
            "loss": 0.1181,
            "grad_norm": 1.673506736755371,
            "learning_rate": 7.647999999999999e-06,
            "epoch": 0.478,
            "step": 1195
        },
        {
            "loss": 0.1254,
            "grad_norm": 2.3451597690582275,
            "learning_rate": 7.68e-06,
            "epoch": 0.48,
            "step": 1200
        },
        {
            "eval_loss": 0.11651310324668884,
            "eval_f1": 0.6772621635804784,
            "eval_recall": 0.7117869524109676,
            "eval_accuracy": 0.9599578560044497,
            "eval_precision": 0.645931645931646,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.5070318282753515,
                    "recall": 0.6663424124513618,
                    "f1-score": 0.5758722152164775,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.5165775401069519,
                    "recall": 0.5513698630136986,
                    "f1-score": 0.5334069574820541,
                    "support": 876
                },
                "PER": {
                    "precision": 0.7578576816696002,
                    "recall": 0.8577120091064314,
                    "f1-score": 0.8046989720998531,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.4589041095890411,
                    "recall": 0.3609913793103448,
                    "f1-score": 0.4041013268998793,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.645931645931646,
                    "recall": 0.7117869524109676,
                    "f1-score": 0.6772621635804784,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.5600927899102361,
                    "recall": 0.6091039159704591,
                    "f1-score": 0.579519867924566,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.6402025766918306,
                    "recall": 0.7117869524109676,
                    "f1-score": 0.671600906290386,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4538,
            "eval_samples_per_second": 919.671,
            "eval_steps_per_second": 7.185,
            "epoch": 0.48,
            "step": 1200
        },
        {
            "loss": 0.1205,
            "grad_norm": 1.8473345041275024,
            "learning_rate": 7.712e-06,
            "epoch": 0.482,
            "step": 1205
        },
        {
            "loss": 0.1214,
            "grad_norm": 2.8123273849487305,
            "learning_rate": 7.743999999999999e-06,
            "epoch": 0.484,
            "step": 1210
        },
        {
            "loss": 0.1198,
            "grad_norm": 2.7720494270324707,
            "learning_rate": 7.776e-06,
            "epoch": 0.486,
            "step": 1215
        },
        {
            "loss": 0.1357,
            "grad_norm": 2.757894277572632,
            "learning_rate": 7.807999999999999e-06,
            "epoch": 0.488,
            "step": 1220
        },
        {
            "loss": 0.0963,
            "grad_norm": 1.808860182762146,
            "learning_rate": 7.84e-06,
            "epoch": 0.49,
            "step": 1225
        },
        {
            "loss": 0.1208,
            "grad_norm": 2.6157824993133545,
            "learning_rate": 7.872e-06,
            "epoch": 0.492,
            "step": 1230
        },
        {
            "loss": 0.1211,
            "grad_norm": 2.5180656909942627,
            "learning_rate": 7.904e-06,
            "epoch": 0.494,
            "step": 1235
        },
        {
            "loss": 0.1496,
            "grad_norm": 3.3822121620178223,
            "learning_rate": 7.936e-06,
            "epoch": 0.496,
            "step": 1240
        },
        {
            "loss": 0.1511,
            "grad_norm": 2.526564359664917,
            "learning_rate": 7.967999999999999e-06,
            "epoch": 0.498,
            "step": 1245
        },
        {
            "loss": 0.1283,
            "grad_norm": 2.005441665649414,
            "learning_rate": 8e-06,
            "epoch": 0.5,
            "step": 1250
        },
        {
            "loss": 0.1216,
            "grad_norm": 1.9142677783966064,
            "learning_rate": 8e-06,
            "epoch": 0.502,
            "step": 1255
        },
        {
            "loss": 0.1174,
            "grad_norm": 2.765774965286255,
            "learning_rate": 8e-06,
            "epoch": 0.504,
            "step": 1260
        },
        {
            "loss": 0.1148,
            "grad_norm": 4.123652458190918,
            "learning_rate": 8e-06,
            "epoch": 0.506,
            "step": 1265
        },
        {
            "loss": 0.1244,
            "grad_norm": 2.268881320953369,
            "learning_rate": 8e-06,
            "epoch": 0.508,
            "step": 1270
        },
        {
            "loss": 0.1156,
            "grad_norm": 2.2551679611206055,
            "learning_rate": 8e-06,
            "epoch": 0.51,
            "step": 1275
        },
        {
            "loss": 0.1382,
            "grad_norm": 2.7823495864868164,
            "learning_rate": 8e-06,
            "epoch": 0.512,
            "step": 1280
        },
        {
            "loss": 0.1286,
            "grad_norm": 1.9663594961166382,
            "learning_rate": 8e-06,
            "epoch": 0.514,
            "step": 1285
        },
        {
            "loss": 0.1356,
            "grad_norm": 1.8923016786575317,
            "learning_rate": 8e-06,
            "epoch": 0.516,
            "step": 1290
        },
        {
            "loss": 0.1129,
            "grad_norm": 2.858227014541626,
            "learning_rate": 8e-06,
            "epoch": 0.518,
            "step": 1295
        },
        {
            "loss": 0.1125,
            "grad_norm": 2.718233346939087,
            "learning_rate": 8e-06,
            "epoch": 0.52,
            "step": 1300
        },
        {
            "loss": 0.1526,
            "grad_norm": 2.312448501586914,
            "learning_rate": 8e-06,
            "epoch": 0.522,
            "step": 1305
        },
        {
            "loss": 0.1309,
            "grad_norm": 3.582595109939575,
            "learning_rate": 8e-06,
            "epoch": 0.524,
            "step": 1310
        },
        {
            "loss": 0.1019,
            "grad_norm": 1.7062674760818481,
            "learning_rate": 8e-06,
            "epoch": 0.526,
            "step": 1315
        },
        {
            "loss": 0.1082,
            "grad_norm": 1.8148196935653687,
            "learning_rate": 8e-06,
            "epoch": 0.528,
            "step": 1320
        },
        {
            "loss": 0.1051,
            "grad_norm": 1.7100651264190674,
            "learning_rate": 8e-06,
            "epoch": 0.53,
            "step": 1325
        },
        {
            "loss": 0.0986,
            "grad_norm": 1.4712669849395752,
            "learning_rate": 8e-06,
            "epoch": 0.532,
            "step": 1330
        },
        {
            "loss": 0.0984,
            "grad_norm": 1.6358044147491455,
            "learning_rate": 8e-06,
            "epoch": 0.534,
            "step": 1335
        },
        {
            "loss": 0.1124,
            "grad_norm": 3.1934499740600586,
            "learning_rate": 8e-06,
            "epoch": 0.536,
            "step": 1340
        },
        {
            "loss": 0.1149,
            "grad_norm": 1.7618718147277832,
            "learning_rate": 8e-06,
            "epoch": 0.538,
            "step": 1345
        },
        {
            "loss": 0.1169,
            "grad_norm": 1.7664477825164795,
            "learning_rate": 8e-06,
            "epoch": 0.54,
            "step": 1350
        },
        {
            "loss": 0.1037,
            "grad_norm": 2.9790565967559814,
            "learning_rate": 8e-06,
            "epoch": 0.542,
            "step": 1355
        },
        {
            "loss": 0.1166,
            "grad_norm": 2.352510929107666,
            "learning_rate": 8e-06,
            "epoch": 0.544,
            "step": 1360
        },
        {
            "loss": 0.1078,
            "grad_norm": 2.114887237548828,
            "learning_rate": 8e-06,
            "epoch": 0.546,
            "step": 1365
        },
        {
            "loss": 0.1073,
            "grad_norm": 2.677525758743286,
            "learning_rate": 8e-06,
            "epoch": 0.548,
            "step": 1370
        },
        {
            "loss": 0.1027,
            "grad_norm": 1.9252755641937256,
            "learning_rate": 8e-06,
            "epoch": 0.55,
            "step": 1375
        },
        {
            "loss": 0.0969,
            "grad_norm": 1.5352263450622559,
            "learning_rate": 8e-06,
            "epoch": 0.552,
            "step": 1380
        },
        {
            "loss": 0.1056,
            "grad_norm": 2.4699230194091797,
            "learning_rate": 8e-06,
            "epoch": 0.554,
            "step": 1385
        },
        {
            "loss": 0.1146,
            "grad_norm": 2.246919631958008,
            "learning_rate": 8e-06,
            "epoch": 0.556,
            "step": 1390
        },
        {
            "loss": 0.115,
            "grad_norm": 2.030308723449707,
            "learning_rate": 8e-06,
            "epoch": 0.558,
            "step": 1395
        },
        {
            "loss": 0.0984,
            "grad_norm": 2.4233415126800537,
            "learning_rate": 8e-06,
            "epoch": 0.56,
            "step": 1400
        },
        {
            "loss": 0.0957,
            "grad_norm": 2.0604140758514404,
            "learning_rate": 8e-06,
            "epoch": 0.562,
            "step": 1405
        },
        {
            "loss": 0.1015,
            "grad_norm": 2.132284641265869,
            "learning_rate": 8e-06,
            "epoch": 0.564,
            "step": 1410
        },
        {
            "loss": 0.13,
            "grad_norm": 2.437201738357544,
            "learning_rate": 8e-06,
            "epoch": 0.566,
            "step": 1415
        },
        {
            "loss": 0.0916,
            "grad_norm": 4.739233493804932,
            "learning_rate": 8e-06,
            "epoch": 0.568,
            "step": 1420
        },
        {
            "loss": 0.0997,
            "grad_norm": 1.8776425123214722,
            "learning_rate": 8e-06,
            "epoch": 0.57,
            "step": 1425
        },
        {
            "loss": 0.0979,
            "grad_norm": 3.126708984375,
            "learning_rate": 8e-06,
            "epoch": 0.572,
            "step": 1430
        },
        {
            "loss": 0.1226,
            "grad_norm": 1.9385004043579102,
            "learning_rate": 8e-06,
            "epoch": 0.574,
            "step": 1435
        },
        {
            "loss": 0.1078,
            "grad_norm": 2.135901689529419,
            "learning_rate": 8e-06,
            "epoch": 0.576,
            "step": 1440
        },
        {
            "loss": 0.1268,
            "grad_norm": 2.6939914226531982,
            "learning_rate": 8e-06,
            "epoch": 0.578,
            "step": 1445
        },
        {
            "loss": 0.1172,
            "grad_norm": 2.7349302768707275,
            "learning_rate": 8e-06,
            "epoch": 0.58,
            "step": 1450
        },
        {
            "loss": 0.1202,
            "grad_norm": 4.490180492401123,
            "learning_rate": 8e-06,
            "epoch": 0.582,
            "step": 1455
        },
        {
            "loss": 0.097,
            "grad_norm": 2.778078556060791,
            "learning_rate": 8e-06,
            "epoch": 0.584,
            "step": 1460
        },
        {
            "loss": 0.1391,
            "grad_norm": 2.0595037937164307,
            "learning_rate": 8e-06,
            "epoch": 0.586,
            "step": 1465
        },
        {
            "loss": 0.1123,
            "grad_norm": 1.9643030166625977,
            "learning_rate": 8e-06,
            "epoch": 0.588,
            "step": 1470
        },
        {
            "loss": 0.1017,
            "grad_norm": 1.6642616987228394,
            "learning_rate": 8e-06,
            "epoch": 0.59,
            "step": 1475
        },
        {
            "loss": 0.1078,
            "grad_norm": 1.896048665046692,
            "learning_rate": 8e-06,
            "epoch": 0.592,
            "step": 1480
        },
        {
            "loss": 0.127,
            "grad_norm": 2.3617284297943115,
            "learning_rate": 8e-06,
            "epoch": 0.594,
            "step": 1485
        },
        {
            "loss": 0.117,
            "grad_norm": 1.414752721786499,
            "learning_rate": 8e-06,
            "epoch": 0.596,
            "step": 1490
        },
        {
            "loss": 0.1362,
            "grad_norm": 3.3731861114501953,
            "learning_rate": 8e-06,
            "epoch": 0.598,
            "step": 1495
        },
        {
            "loss": 0.1,
            "grad_norm": 3.5915513038635254,
            "learning_rate": 8e-06,
            "epoch": 0.6,
            "step": 1500
        },
        {
            "eval_loss": 0.10783616453409195,
            "eval_f1": 0.6989263126930432,
            "eval_recall": 0.7488181531673496,
            "eval_accuracy": 0.9622201542427451,
            "eval_precision": 0.6552675124103695,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.5716768027801912,
                    "recall": 0.6400778210116731,
                    "f1-score": 0.603946764570904,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.5397489539748954,
                    "recall": 0.589041095890411,
                    "f1-score": 0.5633187772925764,
                    "support": 876
                },
                "PER": {
                    "precision": 0.7672862453531598,
                    "recall": 0.8810472396129767,
                    "f1-score": 0.8202410915353026,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.43423423423423424,
                    "recall": 0.5193965517241379,
                    "f1-score": 0.4730127576054956,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.6552675124103695,
                    "recall": 0.7488181531673496,
                    "f1-score": 0.6989263126930432,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.5782365590856202,
                    "recall": 0.6573906770597997,
                    "f1-score": 0.6151298477510696,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.6554864595777526,
                    "recall": 0.7488181531673496,
                    "f1-score": 0.6989611657107059,
                    "support": 6346
                }
            },
            "eval_runtime": 5.6387,
            "eval_samples_per_second": 726.414,
            "eval_steps_per_second": 5.675,
            "epoch": 0.6,
            "step": 1500
        },
        {
            "loss": 0.1181,
            "grad_norm": 1.2604758739471436,
            "learning_rate": 8e-06,
            "epoch": 0.602,
            "step": 1505
        },
        {
            "loss": 0.1034,
            "grad_norm": 2.244868755340576,
            "learning_rate": 8e-06,
            "epoch": 0.604,
            "step": 1510
        },
        {
            "loss": 0.1065,
            "grad_norm": 2.9435572624206543,
            "learning_rate": 8e-06,
            "epoch": 0.606,
            "step": 1515
        },
        {
            "loss": 0.1023,
            "grad_norm": 2.3951878547668457,
            "learning_rate": 8e-06,
            "epoch": 0.608,
            "step": 1520
        },
        {
            "loss": 0.116,
            "grad_norm": 1.918272614479065,
            "learning_rate": 8e-06,
            "epoch": 0.61,
            "step": 1525
        },
        {
            "loss": 0.1179,
            "grad_norm": 3.313293218612671,
            "learning_rate": 8e-06,
            "epoch": 0.612,
            "step": 1530
        },
        {
            "loss": 0.1203,
            "grad_norm": 2.390363931655884,
            "learning_rate": 8e-06,
            "epoch": 0.614,
            "step": 1535
        },
        {
            "loss": 0.1209,
            "grad_norm": 3.174931526184082,
            "learning_rate": 8e-06,
            "epoch": 0.616,
            "step": 1540
        },
        {
            "loss": 0.1145,
            "grad_norm": 3.1557910442352295,
            "learning_rate": 8e-06,
            "epoch": 0.618,
            "step": 1545
        },
        {
            "loss": 0.119,
            "grad_norm": 6.000813007354736,
            "learning_rate": 8e-06,
            "epoch": 0.62,
            "step": 1550
        },
        {
            "loss": 0.1172,
            "grad_norm": 2.176056385040283,
            "learning_rate": 8e-06,
            "epoch": 0.622,
            "step": 1555
        },
        {
            "loss": 0.1028,
            "grad_norm": 2.1561827659606934,
            "learning_rate": 8e-06,
            "epoch": 0.624,
            "step": 1560
        },
        {
            "loss": 0.1292,
            "grad_norm": 1.817461371421814,
            "learning_rate": 8e-06,
            "epoch": 0.626,
            "step": 1565
        },
        {
            "loss": 0.1042,
            "grad_norm": 1.366830587387085,
            "learning_rate": 8e-06,
            "epoch": 0.628,
            "step": 1570
        },
        {
            "loss": 0.1242,
            "grad_norm": 2.524897813796997,
            "learning_rate": 8e-06,
            "epoch": 0.63,
            "step": 1575
        },
        {
            "loss": 0.1239,
            "grad_norm": 3.5279176235198975,
            "learning_rate": 8e-06,
            "epoch": 0.632,
            "step": 1580
        },
        {
            "loss": 0.0968,
            "grad_norm": 2.1919798851013184,
            "learning_rate": 8e-06,
            "epoch": 0.634,
            "step": 1585
        },
        {
            "loss": 0.1058,
            "grad_norm": 2.7044196128845215,
            "learning_rate": 8e-06,
            "epoch": 0.636,
            "step": 1590
        },
        {
            "loss": 0.096,
            "grad_norm": 1.741538405418396,
            "learning_rate": 8e-06,
            "epoch": 0.638,
            "step": 1595
        },
        {
            "loss": 0.1086,
            "grad_norm": 1.6264333724975586,
            "learning_rate": 8e-06,
            "epoch": 0.64,
            "step": 1600
        },
        {
            "loss": 0.1014,
            "grad_norm": 1.291340708732605,
            "learning_rate": 8e-06,
            "epoch": 0.642,
            "step": 1605
        },
        {
            "loss": 0.1022,
            "grad_norm": 3.0790889263153076,
            "learning_rate": 8e-06,
            "epoch": 0.644,
            "step": 1610
        },
        {
            "loss": 0.1237,
            "grad_norm": 2.736382246017456,
            "learning_rate": 8e-06,
            "epoch": 0.646,
            "step": 1615
        },
        {
            "loss": 0.1192,
            "grad_norm": 2.7508342266082764,
            "learning_rate": 8e-06,
            "epoch": 0.648,
            "step": 1620
        },
        {
            "loss": 0.1323,
            "grad_norm": 2.456146478652954,
            "learning_rate": 8e-06,
            "epoch": 0.65,
            "step": 1625
        },
        {
            "loss": 0.102,
            "grad_norm": 2.2447190284729004,
            "learning_rate": 8e-06,
            "epoch": 0.652,
            "step": 1630
        },
        {
            "loss": 0.0961,
            "grad_norm": 2.0763468742370605,
            "learning_rate": 8e-06,
            "epoch": 0.654,
            "step": 1635
        },
        {
            "loss": 0.1023,
            "grad_norm": 2.0788025856018066,
            "learning_rate": 8e-06,
            "epoch": 0.656,
            "step": 1640
        },
        {
            "loss": 0.1182,
            "grad_norm": 1.4793463945388794,
            "learning_rate": 8e-06,
            "epoch": 0.658,
            "step": 1645
        },
        {
            "loss": 0.1246,
            "grad_norm": 1.6473404169082642,
            "learning_rate": 8e-06,
            "epoch": 0.66,
            "step": 1650
        },
        {
            "loss": 0.1294,
            "grad_norm": 2.6154377460479736,
            "learning_rate": 8e-06,
            "epoch": 0.662,
            "step": 1655
        },
        {
            "loss": 0.1029,
            "grad_norm": 2.1304848194122314,
            "learning_rate": 8e-06,
            "epoch": 0.664,
            "step": 1660
        },
        {
            "loss": 0.1111,
            "grad_norm": 1.5652196407318115,
            "learning_rate": 8e-06,
            "epoch": 0.666,
            "step": 1665
        },
        {
            "loss": 0.1068,
            "grad_norm": 1.7295061349868774,
            "learning_rate": 8e-06,
            "epoch": 0.668,
            "step": 1670
        },
        {
            "loss": 0.0959,
            "grad_norm": 2.026042938232422,
            "learning_rate": 8e-06,
            "epoch": 0.67,
            "step": 1675
        },
        {
            "loss": 0.1202,
            "grad_norm": 2.580071210861206,
            "learning_rate": 8e-06,
            "epoch": 0.672,
            "step": 1680
        },
        {
            "loss": 0.1016,
            "grad_norm": 1.917648434638977,
            "learning_rate": 8e-06,
            "epoch": 0.674,
            "step": 1685
        },
        {
            "loss": 0.0998,
            "grad_norm": 5.012639999389648,
            "learning_rate": 8e-06,
            "epoch": 0.676,
            "step": 1690
        },
        {
            "loss": 0.0962,
            "grad_norm": 2.429553270339966,
            "learning_rate": 8e-06,
            "epoch": 0.678,
            "step": 1695
        },
        {
            "loss": 0.1035,
            "grad_norm": 1.8783029317855835,
            "learning_rate": 8e-06,
            "epoch": 0.68,
            "step": 1700
        },
        {
            "loss": 0.14,
            "grad_norm": 3.922071933746338,
            "learning_rate": 8e-06,
            "epoch": 0.682,
            "step": 1705
        },
        {
            "loss": 0.0897,
            "grad_norm": 1.953321933746338,
            "learning_rate": 8e-06,
            "epoch": 0.684,
            "step": 1710
        },
        {
            "loss": 0.0921,
            "grad_norm": 4.774768829345703,
            "learning_rate": 8e-06,
            "epoch": 0.686,
            "step": 1715
        },
        {
            "loss": 0.1121,
            "grad_norm": 2.7971770763397217,
            "learning_rate": 8e-06,
            "epoch": 0.688,
            "step": 1720
        },
        {
            "loss": 0.0887,
            "grad_norm": 1.632091760635376,
            "learning_rate": 8e-06,
            "epoch": 0.69,
            "step": 1725
        },
        {
            "loss": 0.1215,
            "grad_norm": 1.99653160572052,
            "learning_rate": 8e-06,
            "epoch": 0.692,
            "step": 1730
        },
        {
            "loss": 0.1077,
            "grad_norm": 1.8965474367141724,
            "learning_rate": 8e-06,
            "epoch": 0.694,
            "step": 1735
        },
        {
            "loss": 0.1077,
            "grad_norm": 2.297473907470703,
            "learning_rate": 8e-06,
            "epoch": 0.696,
            "step": 1740
        },
        {
            "loss": 0.1204,
            "grad_norm": 4.623359203338623,
            "learning_rate": 8e-06,
            "epoch": 0.698,
            "step": 1745
        },
        {
            "loss": 0.1144,
            "grad_norm": 1.398749828338623,
            "learning_rate": 8e-06,
            "epoch": 0.7,
            "step": 1750
        },
        {
            "loss": 0.1116,
            "grad_norm": 2.044412851333618,
            "learning_rate": 8e-06,
            "epoch": 0.702,
            "step": 1755
        },
        {
            "loss": 0.1153,
            "grad_norm": 2.719938278198242,
            "learning_rate": 8e-06,
            "epoch": 0.704,
            "step": 1760
        },
        {
            "loss": 0.1219,
            "grad_norm": 2.9993155002593994,
            "learning_rate": 8e-06,
            "epoch": 0.706,
            "step": 1765
        },
        {
            "loss": 0.1037,
            "grad_norm": 2.1006362438201904,
            "learning_rate": 8e-06,
            "epoch": 0.708,
            "step": 1770
        },
        {
            "loss": 0.0878,
            "grad_norm": 3.399524688720703,
            "learning_rate": 8e-06,
            "epoch": 0.71,
            "step": 1775
        },
        {
            "loss": 0.1037,
            "grad_norm": 1.7821229696273804,
            "learning_rate": 8e-06,
            "epoch": 0.712,
            "step": 1780
        },
        {
            "loss": 0.1091,
            "grad_norm": 3.391005516052246,
            "learning_rate": 8e-06,
            "epoch": 0.714,
            "step": 1785
        },
        {
            "loss": 0.1269,
            "grad_norm": 3.1656627655029297,
            "learning_rate": 8e-06,
            "epoch": 0.716,
            "step": 1790
        },
        {
            "loss": 0.0923,
            "grad_norm": 1.6307140588760376,
            "learning_rate": 8e-06,
            "epoch": 0.718,
            "step": 1795
        },
        {
            "loss": 0.099,
            "grad_norm": 1.692694067955017,
            "learning_rate": 8e-06,
            "epoch": 0.72,
            "step": 1800
        },
        {
            "eval_loss": 0.10066167265176773,
            "eval_f1": 0.7141826344904995,
            "eval_recall": 0.7018594390167034,
            "eval_accuracy": 0.9656804543850078,
            "eval_precision": 0.7269463032479191,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.5970561177552898,
                    "recall": 0.6313229571984436,
                    "f1-score": 0.6137115839243499,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6269633507853403,
                    "recall": 0.5468036529680366,
                    "f1-score": 0.5841463414634146,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8387278356318604,
                    "recall": 0.8480364257256687,
                    "f1-score": 0.8433564454506863,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.4785615491009682,
                    "recall": 0.3728448275862069,
                    "f1-score": 0.41913991520290733,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7269463032479191,
                    "recall": 0.7018594390167034,
                    "f1-score": 0.7141826344904995,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6353272133183647,
                    "recall": 0.599751965869589,
                    "f1-score": 0.6150885715103395,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.717678587506532,
                    "recall": 0.7018594390167034,
                    "f1-score": 0.7083397563848398,
                    "support": 6346
                }
            },
            "eval_runtime": 4.5097,
            "eval_samples_per_second": 908.268,
            "eval_steps_per_second": 7.096,
            "epoch": 0.72,
            "step": 1800
        },
        {
            "loss": 0.1345,
            "grad_norm": 4.213858604431152,
            "learning_rate": 8e-06,
            "epoch": 0.722,
            "step": 1805
        },
        {
            "loss": 0.1138,
            "grad_norm": 2.7535576820373535,
            "learning_rate": 8e-06,
            "epoch": 0.724,
            "step": 1810
        },
        {
            "loss": 0.1084,
            "grad_norm": 5.392453193664551,
            "learning_rate": 8e-06,
            "epoch": 0.726,
            "step": 1815
        },
        {
            "loss": 0.1206,
            "grad_norm": 1.9903637170791626,
            "learning_rate": 8e-06,
            "epoch": 0.728,
            "step": 1820
        },
        {
            "loss": 0.0945,
            "grad_norm": 1.5198200941085815,
            "learning_rate": 8e-06,
            "epoch": 0.73,
            "step": 1825
        },
        {
            "loss": 0.108,
            "grad_norm": 2.369828462600708,
            "learning_rate": 8e-06,
            "epoch": 0.732,
            "step": 1830
        },
        {
            "loss": 0.1071,
            "grad_norm": 1.620745301246643,
            "learning_rate": 8e-06,
            "epoch": 0.734,
            "step": 1835
        },
        {
            "loss": 0.1065,
            "grad_norm": 3.1889514923095703,
            "learning_rate": 8e-06,
            "epoch": 0.736,
            "step": 1840
        },
        {
            "loss": 0.1115,
            "grad_norm": 2.053093194961548,
            "learning_rate": 8e-06,
            "epoch": 0.738,
            "step": 1845
        },
        {
            "loss": 0.0971,
            "grad_norm": 2.0912253856658936,
            "learning_rate": 8e-06,
            "epoch": 0.74,
            "step": 1850
        },
        {
            "loss": 0.1166,
            "grad_norm": 2.168764352798462,
            "learning_rate": 8e-06,
            "epoch": 0.742,
            "step": 1855
        },
        {
            "loss": 0.1138,
            "grad_norm": 1.9431016445159912,
            "learning_rate": 8e-06,
            "epoch": 0.744,
            "step": 1860
        },
        {
            "loss": 0.1109,
            "grad_norm": 1.3536930084228516,
            "learning_rate": 8e-06,
            "epoch": 0.746,
            "step": 1865
        },
        {
            "loss": 0.0964,
            "grad_norm": 1.4992367029190063,
            "learning_rate": 8e-06,
            "epoch": 0.748,
            "step": 1870
        },
        {
            "loss": 0.0951,
            "grad_norm": 2.0224592685699463,
            "learning_rate": 8e-06,
            "epoch": 0.75,
            "step": 1875
        },
        {
            "loss": 0.1311,
            "grad_norm": 2.0972347259521484,
            "learning_rate": 8e-06,
            "epoch": 0.752,
            "step": 1880
        },
        {
            "loss": 0.1239,
            "grad_norm": 2.3813929557800293,
            "learning_rate": 8e-06,
            "epoch": 0.754,
            "step": 1885
        },
        {
            "loss": 0.1013,
            "grad_norm": 2.6182994842529297,
            "learning_rate": 8e-06,
            "epoch": 0.756,
            "step": 1890
        },
        {
            "loss": 0.1149,
            "grad_norm": 1.6200709342956543,
            "learning_rate": 8e-06,
            "epoch": 0.758,
            "step": 1895
        },
        {
            "loss": 0.0957,
            "grad_norm": 3.850557804107666,
            "learning_rate": 8e-06,
            "epoch": 0.76,
            "step": 1900
        },
        {
            "loss": 0.1056,
            "grad_norm": 2.4268243312835693,
            "learning_rate": 8e-06,
            "epoch": 0.762,
            "step": 1905
        },
        {
            "loss": 0.1058,
            "grad_norm": 2.1716701984405518,
            "learning_rate": 8e-06,
            "epoch": 0.764,
            "step": 1910
        },
        {
            "loss": 0.0995,
            "grad_norm": 2.202430486679077,
            "learning_rate": 8e-06,
            "epoch": 0.766,
            "step": 1915
        },
        {
            "loss": 0.0971,
            "grad_norm": 1.3137474060058594,
            "learning_rate": 8e-06,
            "epoch": 0.768,
            "step": 1920
        },
        {
            "loss": 0.1037,
            "grad_norm": 2.269815444946289,
            "learning_rate": 8e-06,
            "epoch": 0.77,
            "step": 1925
        },
        {
            "loss": 0.1038,
            "grad_norm": 6.890628814697266,
            "learning_rate": 8e-06,
            "epoch": 0.772,
            "step": 1930
        },
        {
            "loss": 0.1083,
            "grad_norm": 2.773165464401245,
            "learning_rate": 8e-06,
            "epoch": 0.774,
            "step": 1935
        },
        {
            "loss": 0.117,
            "grad_norm": 1.54208242893219,
            "learning_rate": 8e-06,
            "epoch": 0.776,
            "step": 1940
        },
        {
            "loss": 0.1098,
            "grad_norm": 2.0637564659118652,
            "learning_rate": 8e-06,
            "epoch": 0.778,
            "step": 1945
        },
        {
            "loss": 0.1022,
            "grad_norm": 2.086134433746338,
            "learning_rate": 8e-06,
            "epoch": 0.78,
            "step": 1950
        },
        {
            "loss": 0.089,
            "grad_norm": 1.3135778903961182,
            "learning_rate": 8e-06,
            "epoch": 0.782,
            "step": 1955
        },
        {
            "loss": 0.1007,
            "grad_norm": 1.6700270175933838,
            "learning_rate": 8e-06,
            "epoch": 0.784,
            "step": 1960
        },
        {
            "loss": 0.1038,
            "grad_norm": 2.4169046878814697,
            "learning_rate": 8e-06,
            "epoch": 0.786,
            "step": 1965
        },
        {
            "loss": 0.0768,
            "grad_norm": 1.6238781213760376,
            "learning_rate": 8e-06,
            "epoch": 0.788,
            "step": 1970
        },
        {
            "loss": 0.1124,
            "grad_norm": 1.6280595064163208,
            "learning_rate": 8e-06,
            "epoch": 0.79,
            "step": 1975
        },
        {
            "loss": 0.1241,
            "grad_norm": 1.728705644607544,
            "learning_rate": 8e-06,
            "epoch": 0.792,
            "step": 1980
        },
        {
            "loss": 0.1157,
            "grad_norm": 2.7153706550598145,
            "learning_rate": 8e-06,
            "epoch": 0.794,
            "step": 1985
        },
        {
            "loss": 0.0985,
            "grad_norm": 3.5251948833465576,
            "learning_rate": 8e-06,
            "epoch": 0.796,
            "step": 1990
        },
        {
            "loss": 0.1032,
            "grad_norm": 2.4613757133483887,
            "learning_rate": 8e-06,
            "epoch": 0.798,
            "step": 1995
        },
        {
            "loss": 0.1176,
            "grad_norm": 3.4476537704467773,
            "learning_rate": 8e-06,
            "epoch": 0.8,
            "step": 2000
        },
        {
            "loss": 0.0914,
            "grad_norm": 1.8241450786590576,
            "learning_rate": 8e-06,
            "epoch": 0.802,
            "step": 2005
        },
        {
            "loss": 0.106,
            "grad_norm": 2.4217545986175537,
            "learning_rate": 8e-06,
            "epoch": 0.804,
            "step": 2010
        },
        {
            "loss": 0.0971,
            "grad_norm": 1.317046046257019,
            "learning_rate": 8e-06,
            "epoch": 0.806,
            "step": 2015
        },
        {
            "loss": 0.0945,
            "grad_norm": 1.5175155401229858,
            "learning_rate": 8e-06,
            "epoch": 0.808,
            "step": 2020
        },
        {
            "loss": 0.1056,
            "grad_norm": 1.6594090461730957,
            "learning_rate": 8e-06,
            "epoch": 0.81,
            "step": 2025
        },
        {
            "loss": 0.1162,
            "grad_norm": 2.219998598098755,
            "learning_rate": 8e-06,
            "epoch": 0.812,
            "step": 2030
        },
        {
            "loss": 0.1065,
            "grad_norm": 2.0362367630004883,
            "learning_rate": 8e-06,
            "epoch": 0.814,
            "step": 2035
        },
        {
            "loss": 0.1187,
            "grad_norm": 1.5633361339569092,
            "learning_rate": 8e-06,
            "epoch": 0.816,
            "step": 2040
        },
        {
            "loss": 0.1129,
            "grad_norm": 3.0103328227996826,
            "learning_rate": 8e-06,
            "epoch": 0.818,
            "step": 2045
        },
        {
            "loss": 0.1,
            "grad_norm": 2.361574649810791,
            "learning_rate": 8e-06,
            "epoch": 0.82,
            "step": 2050
        },
        {
            "loss": 0.1129,
            "grad_norm": 2.4421870708465576,
            "learning_rate": 8e-06,
            "epoch": 0.822,
            "step": 2055
        },
        {
            "loss": 0.1024,
            "grad_norm": 1.3809490203857422,
            "learning_rate": 8e-06,
            "epoch": 0.824,
            "step": 2060
        },
        {
            "loss": 0.0963,
            "grad_norm": 3.0031931400299072,
            "learning_rate": 8e-06,
            "epoch": 0.826,
            "step": 2065
        },
        {
            "loss": 0.0911,
            "grad_norm": 1.8818169832229614,
            "learning_rate": 8e-06,
            "epoch": 0.828,
            "step": 2070
        },
        {
            "loss": 0.0913,
            "grad_norm": 3.190126419067383,
            "learning_rate": 8e-06,
            "epoch": 0.83,
            "step": 2075
        },
        {
            "loss": 0.1045,
            "grad_norm": 1.5629044771194458,
            "learning_rate": 8e-06,
            "epoch": 0.832,
            "step": 2080
        },
        {
            "loss": 0.0932,
            "grad_norm": 2.4516923427581787,
            "learning_rate": 8e-06,
            "epoch": 0.834,
            "step": 2085
        },
        {
            "loss": 0.0931,
            "grad_norm": 2.4912900924682617,
            "learning_rate": 8e-06,
            "epoch": 0.836,
            "step": 2090
        },
        {
            "loss": 0.091,
            "grad_norm": 2.6029093265533447,
            "learning_rate": 8e-06,
            "epoch": 0.838,
            "step": 2095
        },
        {
            "loss": 0.1,
            "grad_norm": 3.914865493774414,
            "learning_rate": 8e-06,
            "epoch": 0.84,
            "step": 2100
        },
        {
            "eval_loss": 0.0948529839515686,
            "eval_f1": 0.7252347773401998,
            "eval_recall": 0.7544910179640718,
            "eval_accuracy": 0.9664399020205585,
            "eval_precision": 0.6981627296587927,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.5696784073506891,
                    "recall": 0.7237354085603113,
                    "f1-score": 0.6375321336760926,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6586466165413534,
                    "recall": 0.5,
                    "f1-score": 0.5684620376378975,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8230563002680965,
                    "recall": 0.8736482640865111,
                    "f1-score": 0.8475980121479846,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.46326707000864303,
                    "recall": 0.5775862068965517,
                    "f1-score": 0.5141486810551559,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.6981627296587927,
                    "recall": 0.7544910179640718,
                    "f1-score": 0.7252347773401998,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6286620985421955,
                    "recall": 0.6687424698858435,
                    "f1-score": 0.6419352161292826,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7067027291139057,
                    "recall": 0.7544910179640718,
                    "f1-score": 0.7262756333276117,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4675,
            "eval_samples_per_second": 916.853,
            "eval_steps_per_second": 7.163,
            "epoch": 0.84,
            "step": 2100
        },
        {
            "loss": 0.1148,
            "grad_norm": 2.962674856185913,
            "learning_rate": 8e-06,
            "epoch": 0.842,
            "step": 2105
        },
        {
            "loss": 0.1142,
            "grad_norm": 2.6428966522216797,
            "learning_rate": 8e-06,
            "epoch": 0.844,
            "step": 2110
        },
        {
            "loss": 0.1322,
            "grad_norm": 2.1754729747772217,
            "learning_rate": 8e-06,
            "epoch": 0.846,
            "step": 2115
        },
        {
            "loss": 0.0816,
            "grad_norm": 1.5457775592803955,
            "learning_rate": 8e-06,
            "epoch": 0.848,
            "step": 2120
        },
        {
            "loss": 0.0947,
            "grad_norm": 0.9276325702667236,
            "learning_rate": 8e-06,
            "epoch": 0.85,
            "step": 2125
        },
        {
            "loss": 0.1139,
            "grad_norm": 2.0984833240509033,
            "learning_rate": 8e-06,
            "epoch": 0.852,
            "step": 2130
        },
        {
            "loss": 0.1079,
            "grad_norm": 2.5297398567199707,
            "learning_rate": 8e-06,
            "epoch": 0.854,
            "step": 2135
        },
        {
            "loss": 0.1073,
            "grad_norm": 1.9774534702301025,
            "learning_rate": 8e-06,
            "epoch": 0.856,
            "step": 2140
        },
        {
            "loss": 0.115,
            "grad_norm": 2.224738597869873,
            "learning_rate": 8e-06,
            "epoch": 0.858,
            "step": 2145
        },
        {
            "loss": 0.0942,
            "grad_norm": 1.606993317604065,
            "learning_rate": 8e-06,
            "epoch": 0.86,
            "step": 2150
        },
        {
            "loss": 0.1035,
            "grad_norm": 2.161098003387451,
            "learning_rate": 8e-06,
            "epoch": 0.862,
            "step": 2155
        },
        {
            "loss": 0.0983,
            "grad_norm": 1.6656678915023804,
            "learning_rate": 8e-06,
            "epoch": 0.864,
            "step": 2160
        },
        {
            "loss": 0.096,
            "grad_norm": 2.3000805377960205,
            "learning_rate": 8e-06,
            "epoch": 0.866,
            "step": 2165
        },
        {
            "loss": 0.1037,
            "grad_norm": 2.57238507270813,
            "learning_rate": 8e-06,
            "epoch": 0.868,
            "step": 2170
        },
        {
            "loss": 0.1157,
            "grad_norm": 2.408168315887451,
            "learning_rate": 8e-06,
            "epoch": 0.87,
            "step": 2175
        },
        {
            "loss": 0.1028,
            "grad_norm": 1.3032737970352173,
            "learning_rate": 8e-06,
            "epoch": 0.872,
            "step": 2180
        },
        {
            "loss": 0.0926,
            "grad_norm": 2.1990020275115967,
            "learning_rate": 8e-06,
            "epoch": 0.874,
            "step": 2185
        },
        {
            "loss": 0.1003,
            "grad_norm": 2.0016491413116455,
            "learning_rate": 8e-06,
            "epoch": 0.876,
            "step": 2190
        },
        {
            "loss": 0.0813,
            "grad_norm": 1.8834952116012573,
            "learning_rate": 8e-06,
            "epoch": 0.878,
            "step": 2195
        },
        {
            "loss": 0.1037,
            "grad_norm": 1.660363793373108,
            "learning_rate": 8e-06,
            "epoch": 0.88,
            "step": 2200
        },
        {
            "loss": 0.0803,
            "grad_norm": 1.6013151407241821,
            "learning_rate": 8e-06,
            "epoch": 0.882,
            "step": 2205
        },
        {
            "loss": 0.0892,
            "grad_norm": 2.4268202781677246,
            "learning_rate": 8e-06,
            "epoch": 0.884,
            "step": 2210
        },
        {
            "loss": 0.0973,
            "grad_norm": 2.4953036308288574,
            "learning_rate": 8e-06,
            "epoch": 0.886,
            "step": 2215
        },
        {
            "loss": 0.1006,
            "grad_norm": 2.3615450859069824,
            "learning_rate": 8e-06,
            "epoch": 0.888,
            "step": 2220
        },
        {
            "loss": 0.1022,
            "grad_norm": 2.0057294368743896,
            "learning_rate": 8e-06,
            "epoch": 0.89,
            "step": 2225
        },
        {
            "loss": 0.1184,
            "grad_norm": 2.737046003341675,
            "learning_rate": 8e-06,
            "epoch": 0.892,
            "step": 2230
        },
        {
            "loss": 0.102,
            "grad_norm": 1.573883056640625,
            "learning_rate": 8e-06,
            "epoch": 0.894,
            "step": 2235
        },
        {
            "loss": 0.1063,
            "grad_norm": 2.040607452392578,
            "learning_rate": 8e-06,
            "epoch": 0.896,
            "step": 2240
        },
        {
            "loss": 0.0965,
            "grad_norm": 1.7376033067703247,
            "learning_rate": 8e-06,
            "epoch": 0.898,
            "step": 2245
        },
        {
            "loss": 0.0944,
            "grad_norm": 1.714582085609436,
            "learning_rate": 8e-06,
            "epoch": 0.9,
            "step": 2250
        },
        {
            "loss": 0.0849,
            "grad_norm": 1.719523310661316,
            "learning_rate": 8e-06,
            "epoch": 0.902,
            "step": 2255
        },
        {
            "loss": 0.0787,
            "grad_norm": 2.0248682498931885,
            "learning_rate": 8e-06,
            "epoch": 0.904,
            "step": 2260
        },
        {
            "loss": 0.0906,
            "grad_norm": 1.362322449684143,
            "learning_rate": 8e-06,
            "epoch": 0.906,
            "step": 2265
        },
        {
            "loss": 0.0678,
            "grad_norm": 2.2854971885681152,
            "learning_rate": 8e-06,
            "epoch": 0.908,
            "step": 2270
        },
        {
            "loss": 0.0811,
            "grad_norm": 1.838706612586975,
            "learning_rate": 8e-06,
            "epoch": 0.91,
            "step": 2275
        },
        {
            "loss": 0.1037,
            "grad_norm": 2.097517728805542,
            "learning_rate": 8e-06,
            "epoch": 0.912,
            "step": 2280
        },
        {
            "loss": 0.1118,
            "grad_norm": 2.0900723934173584,
            "learning_rate": 8e-06,
            "epoch": 0.914,
            "step": 2285
        },
        {
            "loss": 0.0825,
            "grad_norm": 2.761448621749878,
            "learning_rate": 8e-06,
            "epoch": 0.916,
            "step": 2290
        },
        {
            "loss": 0.1175,
            "grad_norm": 2.014038562774658,
            "learning_rate": 8e-06,
            "epoch": 0.918,
            "step": 2295
        },
        {
            "loss": 0.0824,
            "grad_norm": 2.505511522293091,
            "learning_rate": 8e-06,
            "epoch": 0.92,
            "step": 2300
        },
        {
            "loss": 0.0858,
            "grad_norm": 1.9412996768951416,
            "learning_rate": 8e-06,
            "epoch": 0.922,
            "step": 2305
        },
        {
            "loss": 0.1238,
            "grad_norm": 2.4698023796081543,
            "learning_rate": 8e-06,
            "epoch": 0.924,
            "step": 2310
        },
        {
            "loss": 0.0882,
            "grad_norm": 1.474888563156128,
            "learning_rate": 8e-06,
            "epoch": 0.926,
            "step": 2315
        },
        {
            "loss": 0.0741,
            "grad_norm": 1.3064391613006592,
            "learning_rate": 8e-06,
            "epoch": 0.928,
            "step": 2320
        },
        {
            "loss": 0.1058,
            "grad_norm": 1.598344087600708,
            "learning_rate": 8e-06,
            "epoch": 0.93,
            "step": 2325
        },
        {
            "loss": 0.0831,
            "grad_norm": 0.6924474835395813,
            "learning_rate": 8e-06,
            "epoch": 0.932,
            "step": 2330
        },
        {
            "loss": 0.0836,
            "grad_norm": 2.598015069961548,
            "learning_rate": 8e-06,
            "epoch": 0.934,
            "step": 2335
        },
        {
            "loss": 0.105,
            "grad_norm": 2.3260750770568848,
            "learning_rate": 8e-06,
            "epoch": 0.936,
            "step": 2340
        },
        {
            "loss": 0.0974,
            "grad_norm": 3.8303189277648926,
            "learning_rate": 8e-06,
            "epoch": 0.938,
            "step": 2345
        },
        {
            "loss": 0.0973,
            "grad_norm": 1.9160821437835693,
            "learning_rate": 8e-06,
            "epoch": 0.94,
            "step": 2350
        },
        {
            "loss": 0.1167,
            "grad_norm": 2.69177508354187,
            "learning_rate": 8e-06,
            "epoch": 0.942,
            "step": 2355
        },
        {
            "loss": 0.1165,
            "grad_norm": 2.8532042503356934,
            "learning_rate": 8e-06,
            "epoch": 0.944,
            "step": 2360
        },
        {
            "loss": 0.0797,
            "grad_norm": 1.063161849975586,
            "learning_rate": 8e-06,
            "epoch": 0.946,
            "step": 2365
        },
        {
            "loss": 0.0931,
            "grad_norm": 2.647063970565796,
            "learning_rate": 8e-06,
            "epoch": 0.948,
            "step": 2370
        },
        {
            "loss": 0.1063,
            "grad_norm": 2.3484230041503906,
            "learning_rate": 8e-06,
            "epoch": 0.95,
            "step": 2375
        },
        {
            "loss": 0.0889,
            "grad_norm": 2.8344171047210693,
            "learning_rate": 8e-06,
            "epoch": 0.952,
            "step": 2380
        },
        {
            "loss": 0.0916,
            "grad_norm": 1.2836601734161377,
            "learning_rate": 8e-06,
            "epoch": 0.954,
            "step": 2385
        },
        {
            "loss": 0.0866,
            "grad_norm": 1.3982932567596436,
            "learning_rate": 8e-06,
            "epoch": 0.956,
            "step": 2390
        },
        {
            "loss": 0.1001,
            "grad_norm": 2.317309856414795,
            "learning_rate": 8e-06,
            "epoch": 0.958,
            "step": 2395
        },
        {
            "loss": 0.1151,
            "grad_norm": 2.5597691535949707,
            "learning_rate": 8e-06,
            "epoch": 0.96,
            "step": 2400
        },
        {
            "eval_loss": 0.09212032705545425,
            "eval_f1": 0.7315705735282976,
            "eval_recall": 0.7607942010715412,
            "eval_accuracy": 0.9677876541625218,
            "eval_precision": 0.7045089741718955,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.5693261037955074,
                    "recall": 0.7149805447470817,
                    "f1-score": 0.6338939197930142,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6458055925432756,
                    "recall": 0.5536529680365296,
                    "f1-score": 0.5961893054701906,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8149699031667103,
                    "recall": 0.8861696072851452,
                    "f1-score": 0.849079754601227,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.498989898989899,
                    "recall": 0.5323275862068966,
                    "f1-score": 0.5151199165797705,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7045089741718955,
                    "recall": 0.7607942010715412,
                    "f1-score": 0.7315705735282976,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6322728746238481,
                    "recall": 0.6717826765689132,
                    "f1-score": 0.6485707241110505,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7056192561865958,
                    "recall": 0.7607942010715412,
                    "f1-score": 0.7304762561288756,
                    "support": 6346
                }
            },
            "eval_runtime": 5.7858,
            "eval_samples_per_second": 707.941,
            "eval_steps_per_second": 5.531,
            "epoch": 0.96,
            "step": 2400
        },
        {
            "loss": 0.0924,
            "grad_norm": 1.7065337896347046,
            "learning_rate": 8e-06,
            "epoch": 0.962,
            "step": 2405
        },
        {
            "loss": 0.0791,
            "grad_norm": 1.943071961402893,
            "learning_rate": 8e-06,
            "epoch": 0.964,
            "step": 2410
        },
        {
            "loss": 0.0944,
            "grad_norm": 1.4317870140075684,
            "learning_rate": 8e-06,
            "epoch": 0.966,
            "step": 2415
        },
        {
            "loss": 0.0904,
            "grad_norm": 1.650014877319336,
            "learning_rate": 8e-06,
            "epoch": 0.968,
            "step": 2420
        },
        {
            "loss": 0.1182,
            "grad_norm": 2.1704814434051514,
            "learning_rate": 8e-06,
            "epoch": 0.97,
            "step": 2425
        },
        {
            "loss": 0.1087,
            "grad_norm": 2.165372371673584,
            "learning_rate": 8e-06,
            "epoch": 0.972,
            "step": 2430
        },
        {
            "loss": 0.0965,
            "grad_norm": 1.9209121465682983,
            "learning_rate": 8e-06,
            "epoch": 0.974,
            "step": 2435
        },
        {
            "loss": 0.1293,
            "grad_norm": 1.0325933694839478,
            "learning_rate": 8e-06,
            "epoch": 0.976,
            "step": 2440
        },
        {
            "loss": 0.097,
            "grad_norm": 1.339850902557373,
            "learning_rate": 8e-06,
            "epoch": 0.978,
            "step": 2445
        },
        {
            "loss": 0.1262,
            "grad_norm": 3.2699124813079834,
            "learning_rate": 8e-06,
            "epoch": 0.98,
            "step": 2450
        },
        {
            "loss": 0.1061,
            "grad_norm": 3.834474563598633,
            "learning_rate": 8e-06,
            "epoch": 0.982,
            "step": 2455
        },
        {
            "loss": 0.1165,
            "grad_norm": 2.3430044651031494,
            "learning_rate": 8e-06,
            "epoch": 0.984,
            "step": 2460
        },
        {
            "loss": 0.1145,
            "grad_norm": 2.573155403137207,
            "learning_rate": 8e-06,
            "epoch": 0.986,
            "step": 2465
        },
        {
            "loss": 0.1108,
            "grad_norm": 1.3619855642318726,
            "learning_rate": 8e-06,
            "epoch": 0.988,
            "step": 2470
        },
        {
            "loss": 0.1167,
            "grad_norm": 1.7598576545715332,
            "learning_rate": 8e-06,
            "epoch": 0.99,
            "step": 2475
        },
        {
            "loss": 0.0706,
            "grad_norm": 1.5276695489883423,
            "learning_rate": 8e-06,
            "epoch": 0.992,
            "step": 2480
        },
        {
            "loss": 0.096,
            "grad_norm": 1.9719339609146118,
            "learning_rate": 8e-06,
            "epoch": 0.994,
            "step": 2485
        },
        {
            "loss": 0.0799,
            "grad_norm": 2.2132861614227295,
            "learning_rate": 8e-06,
            "epoch": 0.996,
            "step": 2490
        },
        {
            "loss": 0.0876,
            "grad_norm": 1.6263560056686401,
            "learning_rate": 8e-06,
            "epoch": 0.998,
            "step": 2495
        },
        {
            "loss": 0.0787,
            "grad_norm": 2.4338204860687256,
            "learning_rate": 8e-06,
            "epoch": 1.0,
            "step": 2500
        },
        {
            "loss": 0.1087,
            "grad_norm": 2.094555377960205,
            "learning_rate": 8e-06,
            "epoch": 1.002,
            "step": 2505
        },
        {
            "loss": 0.0948,
            "grad_norm": 1.5327783823013306,
            "learning_rate": 8e-06,
            "epoch": 1.004,
            "step": 2510
        },
        {
            "loss": 0.0889,
            "grad_norm": 2.0043179988861084,
            "learning_rate": 8e-06,
            "epoch": 1.006,
            "step": 2515
        },
        {
            "loss": 0.0955,
            "grad_norm": 2.1117453575134277,
            "learning_rate": 8e-06,
            "epoch": 1.008,
            "step": 2520
        },
        {
            "loss": 0.1034,
            "grad_norm": 3.245856285095215,
            "learning_rate": 8e-06,
            "epoch": 1.01,
            "step": 2525
        },
        {
            "loss": 0.1008,
            "grad_norm": 1.5075653791427612,
            "learning_rate": 8e-06,
            "epoch": 1.012,
            "step": 2530
        },
        {
            "loss": 0.0907,
            "grad_norm": 1.709066390991211,
            "learning_rate": 8e-06,
            "epoch": 1.014,
            "step": 2535
        },
        {
            "loss": 0.0781,
            "grad_norm": 1.7726372480392456,
            "learning_rate": 8e-06,
            "epoch": 1.016,
            "step": 2540
        },
        {
            "loss": 0.1063,
            "grad_norm": 2.5633091926574707,
            "learning_rate": 8e-06,
            "epoch": 1.018,
            "step": 2545
        },
        {
            "loss": 0.1035,
            "grad_norm": 1.2038917541503906,
            "learning_rate": 8e-06,
            "epoch": 1.02,
            "step": 2550
        },
        {
            "loss": 0.0897,
            "grad_norm": 2.283512592315674,
            "learning_rate": 8e-06,
            "epoch": 1.022,
            "step": 2555
        },
        {
            "loss": 0.0898,
            "grad_norm": 1.8333004713058472,
            "learning_rate": 8e-06,
            "epoch": 1.024,
            "step": 2560
        },
        {
            "loss": 0.0879,
            "grad_norm": 2.4193239212036133,
            "learning_rate": 8e-06,
            "epoch": 1.026,
            "step": 2565
        },
        {
            "loss": 0.0726,
            "grad_norm": 1.1462633609771729,
            "learning_rate": 8e-06,
            "epoch": 1.028,
            "step": 2570
        },
        {
            "loss": 0.0834,
            "grad_norm": 1.3149166107177734,
            "learning_rate": 8e-06,
            "epoch": 1.03,
            "step": 2575
        },
        {
            "loss": 0.0929,
            "grad_norm": 1.7227773666381836,
            "learning_rate": 8e-06,
            "epoch": 1.032,
            "step": 2580
        },
        {
            "loss": 0.0776,
            "grad_norm": 1.8107072114944458,
            "learning_rate": 8e-06,
            "epoch": 1.034,
            "step": 2585
        },
        {
            "loss": 0.0743,
            "grad_norm": 1.706870198249817,
            "learning_rate": 8e-06,
            "epoch": 1.036,
            "step": 2590
        },
        {
            "loss": 0.0871,
            "grad_norm": 1.8850386142730713,
            "learning_rate": 8e-06,
            "epoch": 1.038,
            "step": 2595
        },
        {
            "loss": 0.0823,
            "grad_norm": 2.4460742473602295,
            "learning_rate": 8e-06,
            "epoch": 1.04,
            "step": 2600
        },
        {
            "loss": 0.0771,
            "grad_norm": 2.0006229877471924,
            "learning_rate": 8e-06,
            "epoch": 1.042,
            "step": 2605
        },
        {
            "loss": 0.0754,
            "grad_norm": 2.3141613006591797,
            "learning_rate": 8e-06,
            "epoch": 1.044,
            "step": 2610
        },
        {
            "loss": 0.0874,
            "grad_norm": 2.500019073486328,
            "learning_rate": 8e-06,
            "epoch": 1.046,
            "step": 2615
        },
        {
            "loss": 0.0992,
            "grad_norm": 2.1803324222564697,
            "learning_rate": 8e-06,
            "epoch": 1.048,
            "step": 2620
        },
        {
            "loss": 0.0771,
            "grad_norm": 1.6438238620758057,
            "learning_rate": 8e-06,
            "epoch": 1.05,
            "step": 2625
        },
        {
            "loss": 0.0852,
            "grad_norm": 8.317742347717285,
            "learning_rate": 8e-06,
            "epoch": 1.052,
            "step": 2630
        },
        {
            "loss": 0.0725,
            "grad_norm": 1.9858851432800293,
            "learning_rate": 8e-06,
            "epoch": 1.054,
            "step": 2635
        },
        {
            "loss": 0.0927,
            "grad_norm": 1.603283405303955,
            "learning_rate": 8e-06,
            "epoch": 1.056,
            "step": 2640
        },
        {
            "loss": 0.0879,
            "grad_norm": 2.1322410106658936,
            "learning_rate": 8e-06,
            "epoch": 1.058,
            "step": 2645
        },
        {
            "loss": 0.0917,
            "grad_norm": 1.663830280303955,
            "learning_rate": 8e-06,
            "epoch": 1.06,
            "step": 2650
        },
        {
            "loss": 0.0797,
            "grad_norm": 2.6469333171844482,
            "learning_rate": 8e-06,
            "epoch": 1.062,
            "step": 2655
        },
        {
            "loss": 0.0824,
            "grad_norm": 2.4851632118225098,
            "learning_rate": 8e-06,
            "epoch": 1.064,
            "step": 2660
        },
        {
            "loss": 0.0867,
            "grad_norm": 1.7993645668029785,
            "learning_rate": 8e-06,
            "epoch": 1.066,
            "step": 2665
        },
        {
            "loss": 0.0904,
            "grad_norm": 3.168592929840088,
            "learning_rate": 8e-06,
            "epoch": 1.068,
            "step": 2670
        },
        {
            "loss": 0.0989,
            "grad_norm": 2.004182815551758,
            "learning_rate": 8e-06,
            "epoch": 1.07,
            "step": 2675
        },
        {
            "loss": 0.0744,
            "grad_norm": 1.7511309385299683,
            "learning_rate": 8e-06,
            "epoch": 1.072,
            "step": 2680
        },
        {
            "loss": 0.1093,
            "grad_norm": 2.9921319484710693,
            "learning_rate": 8e-06,
            "epoch": 1.074,
            "step": 2685
        },
        {
            "loss": 0.097,
            "grad_norm": 1.6885356903076172,
            "learning_rate": 8e-06,
            "epoch": 1.076,
            "step": 2690
        },
        {
            "loss": 0.0871,
            "grad_norm": 1.2935689687728882,
            "learning_rate": 8e-06,
            "epoch": 1.078,
            "step": 2695
        },
        {
            "loss": 0.0776,
            "grad_norm": 1.6937687397003174,
            "learning_rate": 8e-06,
            "epoch": 1.08,
            "step": 2700
        },
        {
            "eval_loss": 0.08921021223068237,
            "eval_f1": 0.7471832072850748,
            "eval_recall": 0.7628427355814686,
            "eval_accuracy": 0.969172843863984,
            "eval_precision": 0.7321536600120992,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6268656716417911,
                    "recall": 0.6945525291828794,
                    "f1-score": 0.6589755422242732,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6313823163138231,
                    "recall": 0.5787671232876712,
                    "f1-score": 0.6039309112567004,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8338255033557047,
                    "recall": 0.883892999430848,
                    "f1-score": 0.8581295759082745,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5439153439153439,
                    "recall": 0.5538793103448276,
                    "f1-score": 0.5488521089161773,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7321536600120992,
                    "recall": 0.7628427355814686,
                    "f1-score": 0.7471832072850748,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6589972088066657,
                    "recall": 0.6777729905615566,
                    "f1-score": 0.6674720345763565,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7299598294175947,
                    "recall": 0.7628427355814686,
                    "f1-score": 0.7455519102558008,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4611,
            "eval_samples_per_second": 918.15,
            "eval_steps_per_second": 7.173,
            "epoch": 1.08,
            "step": 2700
        },
        {
            "loss": 0.0915,
            "grad_norm": 2.1813206672668457,
            "learning_rate": 8e-06,
            "epoch": 1.082,
            "step": 2705
        },
        {
            "loss": 0.0832,
            "grad_norm": 0.9442950487136841,
            "learning_rate": 8e-06,
            "epoch": 1.084,
            "step": 2710
        },
        {
            "loss": 0.0908,
            "grad_norm": 2.044844150543213,
            "learning_rate": 8e-06,
            "epoch": 1.086,
            "step": 2715
        },
        {
            "loss": 0.0931,
            "grad_norm": 2.1138663291931152,
            "learning_rate": 8e-06,
            "epoch": 1.088,
            "step": 2720
        },
        {
            "loss": 0.1136,
            "grad_norm": 5.280987739562988,
            "learning_rate": 8e-06,
            "epoch": 1.09,
            "step": 2725
        },
        {
            "loss": 0.0877,
            "grad_norm": 1.5456572771072388,
            "learning_rate": 8e-06,
            "epoch": 1.092,
            "step": 2730
        },
        {
            "loss": 0.1,
            "grad_norm": 2.771561622619629,
            "learning_rate": 8e-06,
            "epoch": 1.094,
            "step": 2735
        },
        {
            "loss": 0.1058,
            "grad_norm": 1.8419712781906128,
            "learning_rate": 8e-06,
            "epoch": 1.096,
            "step": 2740
        },
        {
            "loss": 0.1019,
            "grad_norm": 1.6091111898422241,
            "learning_rate": 8e-06,
            "epoch": 1.098,
            "step": 2745
        },
        {
            "loss": 0.0928,
            "grad_norm": 2.1653358936309814,
            "learning_rate": 8e-06,
            "epoch": 1.1,
            "step": 2750
        },
        {
            "loss": 0.1157,
            "grad_norm": 2.2329907417297363,
            "learning_rate": 8e-06,
            "epoch": 1.102,
            "step": 2755
        },
        {
            "loss": 0.0862,
            "grad_norm": 2.2551684379577637,
            "learning_rate": 8e-06,
            "epoch": 1.104,
            "step": 2760
        },
        {
            "loss": 0.101,
            "grad_norm": 2.5450034141540527,
            "learning_rate": 8e-06,
            "epoch": 1.106,
            "step": 2765
        },
        {
            "loss": 0.085,
            "grad_norm": 1.220986247062683,
            "learning_rate": 8e-06,
            "epoch": 1.108,
            "step": 2770
        },
        {
            "loss": 0.105,
            "grad_norm": 1.1395474672317505,
            "learning_rate": 8e-06,
            "epoch": 1.11,
            "step": 2775
        },
        {
            "loss": 0.082,
            "grad_norm": 1.7989983558654785,
            "learning_rate": 8e-06,
            "epoch": 1.112,
            "step": 2780
        },
        {
            "loss": 0.0907,
            "grad_norm": 2.363970994949341,
            "learning_rate": 8e-06,
            "epoch": 1.114,
            "step": 2785
        },
        {
            "loss": 0.0999,
            "grad_norm": 2.0103321075439453,
            "learning_rate": 8e-06,
            "epoch": 1.116,
            "step": 2790
        },
        {
            "loss": 0.1114,
            "grad_norm": 3.9405438899993896,
            "learning_rate": 8e-06,
            "epoch": 1.1179999999999999,
            "step": 2795
        },
        {
            "loss": 0.0879,
            "grad_norm": 2.227370262145996,
            "learning_rate": 8e-06,
            "epoch": 1.12,
            "step": 2800
        },
        {
            "loss": 0.0955,
            "grad_norm": 2.247675895690918,
            "learning_rate": 8e-06,
            "epoch": 1.1219999999999999,
            "step": 2805
        },
        {
            "loss": 0.0782,
            "grad_norm": 2.3396973609924316,
            "learning_rate": 8e-06,
            "epoch": 1.124,
            "step": 2810
        },
        {
            "loss": 0.0734,
            "grad_norm": 2.2284469604492188,
            "learning_rate": 8e-06,
            "epoch": 1.126,
            "step": 2815
        },
        {
            "loss": 0.0811,
            "grad_norm": 3.0049989223480225,
            "learning_rate": 8e-06,
            "epoch": 1.1280000000000001,
            "step": 2820
        },
        {
            "loss": 0.088,
            "grad_norm": 2.456244945526123,
            "learning_rate": 8e-06,
            "epoch": 1.13,
            "step": 2825
        },
        {
            "loss": 0.0649,
            "grad_norm": 1.1116385459899902,
            "learning_rate": 8e-06,
            "epoch": 1.1320000000000001,
            "step": 2830
        },
        {
            "loss": 0.0937,
            "grad_norm": 2.047569751739502,
            "learning_rate": 8e-06,
            "epoch": 1.134,
            "step": 2835
        },
        {
            "loss": 0.0994,
            "grad_norm": 3.432607889175415,
            "learning_rate": 8e-06,
            "epoch": 1.1360000000000001,
            "step": 2840
        },
        {
            "loss": 0.0788,
            "grad_norm": 3.2721669673919678,
            "learning_rate": 8e-06,
            "epoch": 1.138,
            "step": 2845
        },
        {
            "loss": 0.0893,
            "grad_norm": 2.3681375980377197,
            "learning_rate": 8e-06,
            "epoch": 1.1400000000000001,
            "step": 2850
        },
        {
            "loss": 0.0832,
            "grad_norm": 1.7820907831192017,
            "learning_rate": 8e-06,
            "epoch": 1.142,
            "step": 2855
        },
        {
            "loss": 0.0777,
            "grad_norm": 1.1003997325897217,
            "learning_rate": 8e-06,
            "epoch": 1.144,
            "step": 2860
        },
        {
            "loss": 0.1001,
            "grad_norm": 2.955970525741577,
            "learning_rate": 8e-06,
            "epoch": 1.146,
            "step": 2865
        },
        {
            "loss": 0.082,
            "grad_norm": 1.565207600593567,
            "learning_rate": 8e-06,
            "epoch": 1.148,
            "step": 2870
        },
        {
            "loss": 0.0809,
            "grad_norm": 1.5165148973464966,
            "learning_rate": 8e-06,
            "epoch": 1.15,
            "step": 2875
        },
        {
            "loss": 0.0809,
            "grad_norm": 2.046414613723755,
            "learning_rate": 8e-06,
            "epoch": 1.152,
            "step": 2880
        },
        {
            "loss": 0.0842,
            "grad_norm": 1.8639721870422363,
            "learning_rate": 8e-06,
            "epoch": 1.154,
            "step": 2885
        },
        {
            "loss": 0.0809,
            "grad_norm": 2.5630087852478027,
            "learning_rate": 8e-06,
            "epoch": 1.156,
            "step": 2890
        },
        {
            "loss": 0.0923,
            "grad_norm": 1.88362455368042,
            "learning_rate": 8e-06,
            "epoch": 1.158,
            "step": 2895
        },
        {
            "loss": 0.102,
            "grad_norm": 1.9933149814605713,
            "learning_rate": 8e-06,
            "epoch": 1.16,
            "step": 2900
        },
        {
            "loss": 0.0915,
            "grad_norm": 1.9965647459030151,
            "learning_rate": 8e-06,
            "epoch": 1.162,
            "step": 2905
        },
        {
            "loss": 0.0758,
            "grad_norm": 4.019878387451172,
            "learning_rate": 8e-06,
            "epoch": 1.164,
            "step": 2910
        },
        {
            "loss": 0.0771,
            "grad_norm": 1.551666498184204,
            "learning_rate": 8e-06,
            "epoch": 1.166,
            "step": 2915
        },
        {
            "loss": 0.1103,
            "grad_norm": 3.8637349605560303,
            "learning_rate": 8e-06,
            "epoch": 1.168,
            "step": 2920
        },
        {
            "loss": 0.0904,
            "grad_norm": 1.6173635721206665,
            "learning_rate": 8e-06,
            "epoch": 1.17,
            "step": 2925
        },
        {
            "loss": 0.084,
            "grad_norm": 2.2009122371673584,
            "learning_rate": 8e-06,
            "epoch": 1.172,
            "step": 2930
        },
        {
            "loss": 0.0841,
            "grad_norm": 1.963370442390442,
            "learning_rate": 8e-06,
            "epoch": 1.174,
            "step": 2935
        },
        {
            "loss": 0.0889,
            "grad_norm": 2.0058987140655518,
            "learning_rate": 8e-06,
            "epoch": 1.176,
            "step": 2940
        },
        {
            "loss": 0.0957,
            "grad_norm": 2.1079087257385254,
            "learning_rate": 8e-06,
            "epoch": 1.178,
            "step": 2945
        },
        {
            "loss": 0.0809,
            "grad_norm": 1.261217474937439,
            "learning_rate": 8e-06,
            "epoch": 1.18,
            "step": 2950
        },
        {
            "loss": 0.0872,
            "grad_norm": 2.0628490447998047,
            "learning_rate": 8e-06,
            "epoch": 1.182,
            "step": 2955
        },
        {
            "loss": 0.0869,
            "grad_norm": 1.8191113471984863,
            "learning_rate": 8e-06,
            "epoch": 1.184,
            "step": 2960
        },
        {
            "loss": 0.0836,
            "grad_norm": 1.681555986404419,
            "learning_rate": 8e-06,
            "epoch": 1.186,
            "step": 2965
        },
        {
            "loss": 0.0928,
            "grad_norm": 2.140772581100464,
            "learning_rate": 8e-06,
            "epoch": 1.188,
            "step": 2970
        },
        {
            "loss": 0.1017,
            "grad_norm": 1.6262438297271729,
            "learning_rate": 8e-06,
            "epoch": 1.19,
            "step": 2975
        },
        {
            "loss": 0.1085,
            "grad_norm": 2.08590030670166,
            "learning_rate": 8e-06,
            "epoch": 1.192,
            "step": 2980
        },
        {
            "loss": 0.0864,
            "grad_norm": 2.325618267059326,
            "learning_rate": 8e-06,
            "epoch": 1.194,
            "step": 2985
        },
        {
            "loss": 0.0893,
            "grad_norm": 3.1603991985321045,
            "learning_rate": 8e-06,
            "epoch": 1.196,
            "step": 2990
        },
        {
            "loss": 0.0806,
            "grad_norm": 1.7369579076766968,
            "learning_rate": 8e-06,
            "epoch": 1.198,
            "step": 2995
        },
        {
            "loss": 0.0759,
            "grad_norm": 1.1727640628814697,
            "learning_rate": 8e-06,
            "epoch": 1.2,
            "step": 3000
        },
        {
            "eval_loss": 0.08949017524719238,
            "eval_f1": 0.7534685165421557,
            "eval_recall": 0.7787582729278285,
            "eval_accuracy": 0.9691514509728417,
            "eval_precision": 0.7297696396928529,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6059152677857714,
                    "recall": 0.7373540856031129,
                    "f1-score": 0.6652040368582712,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6529850746268657,
                    "recall": 0.5993150684931506,
                    "f1-score": 0.6250000000000001,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8271702071859428,
                    "recall": 0.8975526465566306,
                    "f1-score": 0.8609253446158046,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5586283185840708,
                    "recall": 0.5441810344827587,
                    "f1-score": 0.5513100436681223,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7297696396928529,
                    "recall": 0.7787582729278285,
                    "f1-score": 0.7534685165421557,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6611747170456627,
                    "recall": 0.6946007087839132,
                    "f1-score": 0.6756098562855496,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7280143410580409,
                    "recall": 0.7787582729278285,
                    "f1-score": 0.7513767934753007,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4463,
            "eval_samples_per_second": 921.22,
            "eval_steps_per_second": 7.197,
            "epoch": 1.2,
            "step": 3000
        },
        {
            "loss": 0.0889,
            "grad_norm": 1.192557692527771,
            "learning_rate": 8e-06,
            "epoch": 1.202,
            "step": 3005
        },
        {
            "loss": 0.0917,
            "grad_norm": 2.861600160598755,
            "learning_rate": 8e-06,
            "epoch": 1.204,
            "step": 3010
        },
        {
            "loss": 0.086,
            "grad_norm": 1.5992927551269531,
            "learning_rate": 8e-06,
            "epoch": 1.206,
            "step": 3015
        },
        {
            "loss": 0.0889,
            "grad_norm": 2.007841110229492,
            "learning_rate": 8e-06,
            "epoch": 1.208,
            "step": 3020
        },
        {
            "loss": 0.0891,
            "grad_norm": 1.457335352897644,
            "learning_rate": 8e-06,
            "epoch": 1.21,
            "step": 3025
        },
        {
            "loss": 0.094,
            "grad_norm": 2.2553551197052,
            "learning_rate": 8e-06,
            "epoch": 1.212,
            "step": 3030
        },
        {
            "loss": 0.0885,
            "grad_norm": 1.7530649900436401,
            "learning_rate": 8e-06,
            "epoch": 1.214,
            "step": 3035
        },
        {
            "loss": 0.1019,
            "grad_norm": 3.254007577896118,
            "learning_rate": 8e-06,
            "epoch": 1.216,
            "step": 3040
        },
        {
            "loss": 0.0784,
            "grad_norm": 2.569369077682495,
            "learning_rate": 8e-06,
            "epoch": 1.218,
            "step": 3045
        },
        {
            "loss": 0.0903,
            "grad_norm": 2.3850581645965576,
            "learning_rate": 8e-06,
            "epoch": 1.22,
            "step": 3050
        },
        {
            "loss": 0.0771,
            "grad_norm": 1.4471362829208374,
            "learning_rate": 8e-06,
            "epoch": 1.222,
            "step": 3055
        },
        {
            "loss": 0.0714,
            "grad_norm": 1.6642720699310303,
            "learning_rate": 8e-06,
            "epoch": 1.224,
            "step": 3060
        },
        {
            "loss": 0.0818,
            "grad_norm": 1.5619250535964966,
            "learning_rate": 8e-06,
            "epoch": 1.226,
            "step": 3065
        },
        {
            "loss": 0.0806,
            "grad_norm": 1.7066279649734497,
            "learning_rate": 8e-06,
            "epoch": 1.228,
            "step": 3070
        },
        {
            "loss": 0.081,
            "grad_norm": 1.4788118600845337,
            "learning_rate": 8e-06,
            "epoch": 1.23,
            "step": 3075
        },
        {
            "loss": 0.0742,
            "grad_norm": 1.4609308242797852,
            "learning_rate": 8e-06,
            "epoch": 1.232,
            "step": 3080
        },
        {
            "loss": 0.0928,
            "grad_norm": 0.935118556022644,
            "learning_rate": 8e-06,
            "epoch": 1.234,
            "step": 3085
        },
        {
            "loss": 0.1021,
            "grad_norm": 1.3960094451904297,
            "learning_rate": 8e-06,
            "epoch": 1.236,
            "step": 3090
        },
        {
            "loss": 0.0837,
            "grad_norm": 1.5411620140075684,
            "learning_rate": 8e-06,
            "epoch": 1.238,
            "step": 3095
        },
        {
            "loss": 0.0896,
            "grad_norm": 2.064812660217285,
            "learning_rate": 8e-06,
            "epoch": 1.24,
            "step": 3100
        },
        {
            "loss": 0.081,
            "grad_norm": 1.8426328897476196,
            "learning_rate": 8e-06,
            "epoch": 1.242,
            "step": 3105
        },
        {
            "loss": 0.1018,
            "grad_norm": 2.584106922149658,
            "learning_rate": 8e-06,
            "epoch": 1.244,
            "step": 3110
        },
        {
            "loss": 0.0868,
            "grad_norm": 1.7109880447387695,
            "learning_rate": 8e-06,
            "epoch": 1.246,
            "step": 3115
        },
        {
            "loss": 0.0883,
            "grad_norm": 2.2373952865600586,
            "learning_rate": 8e-06,
            "epoch": 1.248,
            "step": 3120
        },
        {
            "loss": 0.0935,
            "grad_norm": 1.890869140625,
            "learning_rate": 8e-06,
            "epoch": 1.25,
            "step": 3125
        },
        {
            "loss": 0.0795,
            "grad_norm": 1.3910471200942993,
            "learning_rate": 8e-06,
            "epoch": 1.252,
            "step": 3130
        },
        {
            "loss": 0.0732,
            "grad_norm": 1.5978306531906128,
            "learning_rate": 8e-06,
            "epoch": 1.254,
            "step": 3135
        },
        {
            "loss": 0.0846,
            "grad_norm": 1.921636700630188,
            "learning_rate": 8e-06,
            "epoch": 1.256,
            "step": 3140
        },
        {
            "loss": 0.0791,
            "grad_norm": 2.21860933303833,
            "learning_rate": 8e-06,
            "epoch": 1.258,
            "step": 3145
        },
        {
            "loss": 0.0847,
            "grad_norm": 2.1913938522338867,
            "learning_rate": 8e-06,
            "epoch": 1.26,
            "step": 3150
        },
        {
            "loss": 0.0709,
            "grad_norm": 2.0978829860687256,
            "learning_rate": 8e-06,
            "epoch": 1.262,
            "step": 3155
        },
        {
            "loss": 0.0723,
            "grad_norm": 1.7183048725128174,
            "learning_rate": 8e-06,
            "epoch": 1.264,
            "step": 3160
        },
        {
            "loss": 0.0844,
            "grad_norm": 1.2543994188308716,
            "learning_rate": 8e-06,
            "epoch": 1.266,
            "step": 3165
        },
        {
            "loss": 0.0681,
            "grad_norm": 1.3639894723892212,
            "learning_rate": 8e-06,
            "epoch": 1.268,
            "step": 3170
        },
        {
            "loss": 0.0793,
            "grad_norm": 1.8830009698867798,
            "learning_rate": 8e-06,
            "epoch": 1.27,
            "step": 3175
        },
        {
            "loss": 0.0751,
            "grad_norm": 2.5669820308685303,
            "learning_rate": 8e-06,
            "epoch": 1.272,
            "step": 3180
        },
        {
            "loss": 0.0878,
            "grad_norm": 4.726340293884277,
            "learning_rate": 8e-06,
            "epoch": 1.274,
            "step": 3185
        },
        {
            "loss": 0.0741,
            "grad_norm": 1.2281980514526367,
            "learning_rate": 8e-06,
            "epoch": 1.276,
            "step": 3190
        },
        {
            "loss": 0.0842,
            "grad_norm": 1.745344877243042,
            "learning_rate": 8e-06,
            "epoch": 1.278,
            "step": 3195
        },
        {
            "loss": 0.0926,
            "grad_norm": 2.890878915786743,
            "learning_rate": 8e-06,
            "epoch": 1.28,
            "step": 3200
        },
        {
            "loss": 0.0883,
            "grad_norm": 1.5412535667419434,
            "learning_rate": 8e-06,
            "epoch": 1.282,
            "step": 3205
        },
        {
            "loss": 0.0785,
            "grad_norm": 1.50885808467865,
            "learning_rate": 8e-06,
            "epoch": 1.284,
            "step": 3210
        },
        {
            "loss": 0.0968,
            "grad_norm": 1.3099855184555054,
            "learning_rate": 8e-06,
            "epoch": 1.286,
            "step": 3215
        },
        {
            "loss": 0.0814,
            "grad_norm": 1.3573116064071655,
            "learning_rate": 8e-06,
            "epoch": 1.288,
            "step": 3220
        },
        {
            "loss": 0.082,
            "grad_norm": 1.821215271949768,
            "learning_rate": 8e-06,
            "epoch": 1.29,
            "step": 3225
        },
        {
            "loss": 0.1001,
            "grad_norm": 2.0144784450531006,
            "learning_rate": 8e-06,
            "epoch": 1.292,
            "step": 3230
        },
        {
            "loss": 0.0729,
            "grad_norm": 1.2380242347717285,
            "learning_rate": 8e-06,
            "epoch": 1.294,
            "step": 3235
        },
        {
            "loss": 0.0719,
            "grad_norm": 2.204129219055176,
            "learning_rate": 8e-06,
            "epoch": 1.296,
            "step": 3240
        },
        {
            "loss": 0.1046,
            "grad_norm": 1.894843339920044,
            "learning_rate": 8e-06,
            "epoch": 1.298,
            "step": 3245
        },
        {
            "loss": 0.0819,
            "grad_norm": 1.612225890159607,
            "learning_rate": 8e-06,
            "epoch": 1.3,
            "step": 3250
        },
        {
            "loss": 0.0968,
            "grad_norm": 1.2606414556503296,
            "learning_rate": 8e-06,
            "epoch": 1.302,
            "step": 3255
        },
        {
            "loss": 0.0899,
            "grad_norm": 2.0871033668518066,
            "learning_rate": 8e-06,
            "epoch": 1.304,
            "step": 3260
        },
        {
            "loss": 0.0799,
            "grad_norm": 1.886413812637329,
            "learning_rate": 8e-06,
            "epoch": 1.306,
            "step": 3265
        },
        {
            "loss": 0.1027,
            "grad_norm": 2.1651813983917236,
            "learning_rate": 8e-06,
            "epoch": 1.308,
            "step": 3270
        },
        {
            "loss": 0.0647,
            "grad_norm": 3.022395372390747,
            "learning_rate": 8e-06,
            "epoch": 1.31,
            "step": 3275
        },
        {
            "loss": 0.0936,
            "grad_norm": 2.0828847885131836,
            "learning_rate": 8e-06,
            "epoch": 1.312,
            "step": 3280
        },
        {
            "loss": 0.1053,
            "grad_norm": 1.0117254257202148,
            "learning_rate": 8e-06,
            "epoch": 1.314,
            "step": 3285
        },
        {
            "loss": 0.0815,
            "grad_norm": 1.7354812622070312,
            "learning_rate": 8e-06,
            "epoch": 1.316,
            "step": 3290
        },
        {
            "loss": 0.0754,
            "grad_norm": 1.6243014335632324,
            "learning_rate": 8e-06,
            "epoch": 1.318,
            "step": 3295
        },
        {
            "loss": 0.0926,
            "grad_norm": 1.885732650756836,
            "learning_rate": 8e-06,
            "epoch": 1.32,
            "step": 3300
        },
        {
            "eval_loss": 0.08793383836746216,
            "eval_f1": 0.7514416236051823,
            "eval_recall": 0.7905767412543334,
            "eval_accuracy": 0.9691621474184129,
            "eval_precision": 0.7159982874268589,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6021671826625387,
                    "recall": 0.7568093385214008,
                    "f1-score": 0.6706896551724137,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.654275092936803,
                    "recall": 0.6027397260273972,
                    "f1-score": 0.6274509803921569,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8380797396257119,
                    "recall": 0.8793397837222539,
                    "f1-score": 0.8582141369254269,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5085995085995086,
                    "recall": 0.6691810344827587,
                    "f1-score": 0.5779432294090274,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7159982874268589,
                    "recall": 0.7905767412543334,
                    "f1-score": 0.7514416236051823,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6507803809561405,
                    "recall": 0.7270174706884527,
                    "f1-score": 0.6835745004747562,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7263103363086707,
                    "recall": 0.7905767412543334,
                    "f1-score": 0.7549971349493064,
                    "support": 6346
                }
            },
            "eval_runtime": 5.6138,
            "eval_samples_per_second": 729.636,
            "eval_steps_per_second": 5.7,
            "epoch": 1.32,
            "step": 3300
        },
        {
            "loss": 0.0693,
            "grad_norm": 1.5597200393676758,
            "learning_rate": 8e-06,
            "epoch": 1.322,
            "step": 3305
        },
        {
            "loss": 0.0897,
            "grad_norm": 2.206671953201294,
            "learning_rate": 8e-06,
            "epoch": 1.324,
            "step": 3310
        },
        {
            "loss": 0.0823,
            "grad_norm": 1.5785690546035767,
            "learning_rate": 8e-06,
            "epoch": 1.326,
            "step": 3315
        },
        {
            "loss": 0.0801,
            "grad_norm": 1.8500458002090454,
            "learning_rate": 8e-06,
            "epoch": 1.328,
            "step": 3320
        },
        {
            "loss": 0.0943,
            "grad_norm": 2.389836549758911,
            "learning_rate": 8e-06,
            "epoch": 1.33,
            "step": 3325
        },
        {
            "loss": 0.0863,
            "grad_norm": 1.5967286825180054,
            "learning_rate": 8e-06,
            "epoch": 1.332,
            "step": 3330
        },
        {
            "loss": 0.0905,
            "grad_norm": 2.7995100021362305,
            "learning_rate": 8e-06,
            "epoch": 1.334,
            "step": 3335
        },
        {
            "loss": 0.084,
            "grad_norm": 2.379472494125366,
            "learning_rate": 8e-06,
            "epoch": 1.336,
            "step": 3340
        },
        {
            "loss": 0.0732,
            "grad_norm": 1.4096511602401733,
            "learning_rate": 8e-06,
            "epoch": 1.338,
            "step": 3345
        },
        {
            "loss": 0.0772,
            "grad_norm": 2.8414270877838135,
            "learning_rate": 8e-06,
            "epoch": 1.34,
            "step": 3350
        },
        {
            "loss": 0.0755,
            "grad_norm": 1.3646994829177856,
            "learning_rate": 8e-06,
            "epoch": 1.342,
            "step": 3355
        },
        {
            "loss": 0.0965,
            "grad_norm": 2.0139803886413574,
            "learning_rate": 8e-06,
            "epoch": 1.3439999999999999,
            "step": 3360
        },
        {
            "loss": 0.0677,
            "grad_norm": 1.3450729846954346,
            "learning_rate": 8e-06,
            "epoch": 1.346,
            "step": 3365
        },
        {
            "loss": 0.0774,
            "grad_norm": 1.850787878036499,
            "learning_rate": 8e-06,
            "epoch": 1.3479999999999999,
            "step": 3370
        },
        {
            "loss": 0.1017,
            "grad_norm": 1.7837886810302734,
            "learning_rate": 8e-06,
            "epoch": 1.35,
            "step": 3375
        },
        {
            "loss": 0.0878,
            "grad_norm": 1.5627564191818237,
            "learning_rate": 8e-06,
            "epoch": 1.3519999999999999,
            "step": 3380
        },
        {
            "loss": 0.0795,
            "grad_norm": 1.7162724733352661,
            "learning_rate": 8e-06,
            "epoch": 1.354,
            "step": 3385
        },
        {
            "loss": 0.0832,
            "grad_norm": 1.4134622812271118,
            "learning_rate": 8e-06,
            "epoch": 1.3559999999999999,
            "step": 3390
        },
        {
            "loss": 0.0925,
            "grad_norm": 2.253948926925659,
            "learning_rate": 8e-06,
            "epoch": 1.358,
            "step": 3395
        },
        {
            "loss": 0.0988,
            "grad_norm": 2.0299627780914307,
            "learning_rate": 8e-06,
            "epoch": 1.3599999999999999,
            "step": 3400
        },
        {
            "loss": 0.0762,
            "grad_norm": 0.9964221119880676,
            "learning_rate": 8e-06,
            "epoch": 1.362,
            "step": 3405
        },
        {
            "loss": 0.0865,
            "grad_norm": 1.4537701606750488,
            "learning_rate": 8e-06,
            "epoch": 1.3639999999999999,
            "step": 3410
        },
        {
            "loss": 0.1034,
            "grad_norm": 1.5038058757781982,
            "learning_rate": 8e-06,
            "epoch": 1.366,
            "step": 3415
        },
        {
            "loss": 0.0916,
            "grad_norm": 2.0742297172546387,
            "learning_rate": 8e-06,
            "epoch": 1.3679999999999999,
            "step": 3420
        },
        {
            "loss": 0.0881,
            "grad_norm": 1.5191285610198975,
            "learning_rate": 8e-06,
            "epoch": 1.37,
            "step": 3425
        },
        {
            "loss": 0.0789,
            "grad_norm": 1.2934892177581787,
            "learning_rate": 8e-06,
            "epoch": 1.3719999999999999,
            "step": 3430
        },
        {
            "loss": 0.0722,
            "grad_norm": 2.1492512226104736,
            "learning_rate": 8e-06,
            "epoch": 1.374,
            "step": 3435
        },
        {
            "loss": 0.0947,
            "grad_norm": 1.9278557300567627,
            "learning_rate": 8e-06,
            "epoch": 1.376,
            "step": 3440
        },
        {
            "loss": 0.0808,
            "grad_norm": 2.0927507877349854,
            "learning_rate": 8e-06,
            "epoch": 1.3780000000000001,
            "step": 3445
        },
        {
            "loss": 0.0883,
            "grad_norm": 2.3299899101257324,
            "learning_rate": 8e-06,
            "epoch": 1.38,
            "step": 3450
        },
        {
            "loss": 0.0953,
            "grad_norm": 2.123443841934204,
            "learning_rate": 8e-06,
            "epoch": 1.3820000000000001,
            "step": 3455
        },
        {
            "loss": 0.0783,
            "grad_norm": 1.488665223121643,
            "learning_rate": 8e-06,
            "epoch": 1.384,
            "step": 3460
        },
        {
            "loss": 0.0871,
            "grad_norm": 1.6600313186645508,
            "learning_rate": 8e-06,
            "epoch": 1.3860000000000001,
            "step": 3465
        },
        {
            "loss": 0.0831,
            "grad_norm": 1.790525197982788,
            "learning_rate": 8e-06,
            "epoch": 1.388,
            "step": 3470
        },
        {
            "loss": 0.0822,
            "grad_norm": 2.0680456161499023,
            "learning_rate": 8e-06,
            "epoch": 1.3900000000000001,
            "step": 3475
        },
        {
            "loss": 0.0901,
            "grad_norm": 0.869941234588623,
            "learning_rate": 8e-06,
            "epoch": 1.392,
            "step": 3480
        },
        {
            "loss": 0.0835,
            "grad_norm": 3.7660624980926514,
            "learning_rate": 8e-06,
            "epoch": 1.3940000000000001,
            "step": 3485
        },
        {
            "loss": 0.0834,
            "grad_norm": 1.6872613430023193,
            "learning_rate": 8e-06,
            "epoch": 1.396,
            "step": 3490
        },
        {
            "loss": 0.073,
            "grad_norm": 0.9286977052688599,
            "learning_rate": 8e-06,
            "epoch": 1.3980000000000001,
            "step": 3495
        },
        {
            "loss": 0.1023,
            "grad_norm": 2.1689939498901367,
            "learning_rate": 8e-06,
            "epoch": 1.4,
            "step": 3500
        },
        {
            "loss": 0.0979,
            "grad_norm": 2.602993965148926,
            "learning_rate": 8e-06,
            "epoch": 1.4020000000000001,
            "step": 3505
        },
        {
            "loss": 0.0712,
            "grad_norm": 1.8331382274627686,
            "learning_rate": 8e-06,
            "epoch": 1.404,
            "step": 3510
        },
        {
            "loss": 0.0787,
            "grad_norm": 1.8316572904586792,
            "learning_rate": 8e-06,
            "epoch": 1.4060000000000001,
            "step": 3515
        },
        {
            "loss": 0.0948,
            "grad_norm": 1.3218051195144653,
            "learning_rate": 8e-06,
            "epoch": 1.408,
            "step": 3520
        },
        {
            "loss": 0.0763,
            "grad_norm": 1.4546324014663696,
            "learning_rate": 8e-06,
            "epoch": 1.41,
            "step": 3525
        },
        {
            "loss": 0.0722,
            "grad_norm": 1.633030891418457,
            "learning_rate": 8e-06,
            "epoch": 1.412,
            "step": 3530
        },
        {
            "loss": 0.0782,
            "grad_norm": 1.6665209531784058,
            "learning_rate": 8e-06,
            "epoch": 1.414,
            "step": 3535
        },
        {
            "loss": 0.094,
            "grad_norm": 2.9263885021209717,
            "learning_rate": 8e-06,
            "epoch": 1.416,
            "step": 3540
        },
        {
            "loss": 0.0835,
            "grad_norm": 2.137140989303589,
            "learning_rate": 8e-06,
            "epoch": 1.418,
            "step": 3545
        },
        {
            "loss": 0.0807,
            "grad_norm": 2.082080841064453,
            "learning_rate": 8e-06,
            "epoch": 1.42,
            "step": 3550
        },
        {
            "loss": 0.0964,
            "grad_norm": 2.4824836254119873,
            "learning_rate": 8e-06,
            "epoch": 1.422,
            "step": 3555
        },
        {
            "loss": 0.0779,
            "grad_norm": 2.3590879440307617,
            "learning_rate": 8e-06,
            "epoch": 1.424,
            "step": 3560
        },
        {
            "loss": 0.0898,
            "grad_norm": 2.3054323196411133,
            "learning_rate": 8e-06,
            "epoch": 1.426,
            "step": 3565
        },
        {
            "loss": 0.0913,
            "grad_norm": 1.992417335510254,
            "learning_rate": 8e-06,
            "epoch": 1.428,
            "step": 3570
        },
        {
            "loss": 0.1003,
            "grad_norm": 1.9136306047439575,
            "learning_rate": 8e-06,
            "epoch": 1.43,
            "step": 3575
        },
        {
            "loss": 0.0865,
            "grad_norm": 1.5182067155838013,
            "learning_rate": 8e-06,
            "epoch": 1.432,
            "step": 3580
        },
        {
            "loss": 0.0819,
            "grad_norm": 1.4642199277877808,
            "learning_rate": 8e-06,
            "epoch": 1.434,
            "step": 3585
        },
        {
            "loss": 0.0936,
            "grad_norm": 1.8935976028442383,
            "learning_rate": 8e-06,
            "epoch": 1.436,
            "step": 3590
        },
        {
            "loss": 0.0761,
            "grad_norm": 1.4622349739074707,
            "learning_rate": 8e-06,
            "epoch": 1.438,
            "step": 3595
        },
        {
            "loss": 0.0913,
            "grad_norm": 1.497562050819397,
            "learning_rate": 8e-06,
            "epoch": 1.44,
            "step": 3600
        },
        {
            "eval_loss": 0.08709558844566345,
            "eval_f1": 0.7580354460799039,
            "eval_recall": 0.7953041285849354,
            "eval_accuracy": 0.9695739605729016,
            "eval_precision": 0.724103299856528,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6224,
                    "recall": 0.7568093385214008,
                    "f1-score": 0.6830553116769096,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6431137724550898,
                    "recall": 0.613013698630137,
                    "f1-score": 0.6277030976037405,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8310562270099843,
                    "recall": 0.9001138303927149,
                    "f1-score": 0.8642076502732241,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5273401297497683,
                    "recall": 0.6131465517241379,
                    "f1-score": 0.5670154459392126,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.724103299856528,
                    "recall": 0.7953041285849354,
                    "f1-score": 0.7580354460799039,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6559775323037106,
                    "recall": 0.7207708548170976,
                    "f1-score": 0.6854953763732717,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7268985324285421,
                    "recall": 0.7953041285849354,
                    "f1-score": 0.7587558762679545,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4551,
            "eval_samples_per_second": 919.4,
            "eval_steps_per_second": 7.183,
            "epoch": 1.44,
            "step": 3600
        },
        {
            "loss": 0.085,
            "grad_norm": 2.4866440296173096,
            "learning_rate": 8e-06,
            "epoch": 1.442,
            "step": 3605
        },
        {
            "loss": 0.1168,
            "grad_norm": 2.423072099685669,
            "learning_rate": 8e-06,
            "epoch": 1.444,
            "step": 3610
        },
        {
            "loss": 0.0652,
            "grad_norm": 1.3679779767990112,
            "learning_rate": 8e-06,
            "epoch": 1.446,
            "step": 3615
        },
        {
            "loss": 0.0748,
            "grad_norm": 1.9603455066680908,
            "learning_rate": 8e-06,
            "epoch": 1.448,
            "step": 3620
        },
        {
            "loss": 0.0788,
            "grad_norm": 1.2541165351867676,
            "learning_rate": 8e-06,
            "epoch": 1.45,
            "step": 3625
        },
        {
            "loss": 0.0827,
            "grad_norm": 2.4596054553985596,
            "learning_rate": 8e-06,
            "epoch": 1.452,
            "step": 3630
        },
        {
            "loss": 0.0948,
            "grad_norm": 3.6045901775360107,
            "learning_rate": 8e-06,
            "epoch": 1.454,
            "step": 3635
        },
        {
            "loss": 0.1007,
            "grad_norm": 3.592435598373413,
            "learning_rate": 8e-06,
            "epoch": 1.456,
            "step": 3640
        },
        {
            "loss": 0.0896,
            "grad_norm": 2.175860643386841,
            "learning_rate": 8e-06,
            "epoch": 1.458,
            "step": 3645
        },
        {
            "loss": 0.0754,
            "grad_norm": 1.8911582231521606,
            "learning_rate": 8e-06,
            "epoch": 1.46,
            "step": 3650
        },
        {
            "loss": 0.0601,
            "grad_norm": 1.6625245809555054,
            "learning_rate": 8e-06,
            "epoch": 1.462,
            "step": 3655
        },
        {
            "loss": 0.0753,
            "grad_norm": 2.0409300327301025,
            "learning_rate": 8e-06,
            "epoch": 1.464,
            "step": 3660
        },
        {
            "loss": 0.0765,
            "grad_norm": 1.144038438796997,
            "learning_rate": 8e-06,
            "epoch": 1.466,
            "step": 3665
        },
        {
            "loss": 0.0869,
            "grad_norm": 1.5845837593078613,
            "learning_rate": 8e-06,
            "epoch": 1.468,
            "step": 3670
        },
        {
            "loss": 0.0923,
            "grad_norm": 2.0097620487213135,
            "learning_rate": 8e-06,
            "epoch": 1.47,
            "step": 3675
        },
        {
            "loss": 0.0815,
            "grad_norm": 1.8257272243499756,
            "learning_rate": 8e-06,
            "epoch": 1.472,
            "step": 3680
        },
        {
            "loss": 0.0924,
            "grad_norm": 1.7181577682495117,
            "learning_rate": 8e-06,
            "epoch": 1.474,
            "step": 3685
        },
        {
            "loss": 0.0822,
            "grad_norm": 1.270491361618042,
            "learning_rate": 8e-06,
            "epoch": 1.476,
            "step": 3690
        },
        {
            "loss": 0.0988,
            "grad_norm": 1.5403469800949097,
            "learning_rate": 8e-06,
            "epoch": 1.478,
            "step": 3695
        },
        {
            "loss": 0.0786,
            "grad_norm": 3.301100969314575,
            "learning_rate": 8e-06,
            "epoch": 1.48,
            "step": 3700
        },
        {
            "loss": 0.0919,
            "grad_norm": 2.1680102348327637,
            "learning_rate": 8e-06,
            "epoch": 1.482,
            "step": 3705
        },
        {
            "loss": 0.0772,
            "grad_norm": 3.3601222038269043,
            "learning_rate": 8e-06,
            "epoch": 1.484,
            "step": 3710
        },
        {
            "loss": 0.0843,
            "grad_norm": 2.282194137573242,
            "learning_rate": 8e-06,
            "epoch": 1.486,
            "step": 3715
        },
        {
            "loss": 0.0734,
            "grad_norm": 1.963431477546692,
            "learning_rate": 8e-06,
            "epoch": 1.488,
            "step": 3720
        },
        {
            "loss": 0.0711,
            "grad_norm": 1.6504247188568115,
            "learning_rate": 8e-06,
            "epoch": 1.49,
            "step": 3725
        },
        {
            "loss": 0.0713,
            "grad_norm": 1.6872142553329468,
            "learning_rate": 8e-06,
            "epoch": 1.492,
            "step": 3730
        },
        {
            "loss": 0.086,
            "grad_norm": 1.3204140663146973,
            "learning_rate": 8e-06,
            "epoch": 1.494,
            "step": 3735
        },
        {
            "loss": 0.073,
            "grad_norm": 1.5206447839736938,
            "learning_rate": 8e-06,
            "epoch": 1.496,
            "step": 3740
        },
        {
            "loss": 0.0941,
            "grad_norm": 1.7424460649490356,
            "learning_rate": 8e-06,
            "epoch": 1.498,
            "step": 3745
        },
        {
            "loss": 0.0867,
            "grad_norm": 1.8891993761062622,
            "learning_rate": 8e-06,
            "epoch": 1.5,
            "step": 3750
        },
        {
            "loss": 0.0881,
            "grad_norm": 1.932795763015747,
            "learning_rate": 8e-06,
            "epoch": 1.502,
            "step": 3755
        },
        {
            "loss": 0.0763,
            "grad_norm": 2.50638747215271,
            "learning_rate": 8e-06,
            "epoch": 1.504,
            "step": 3760
        },
        {
            "loss": 0.0977,
            "grad_norm": 2.8946168422698975,
            "learning_rate": 8e-06,
            "epoch": 1.506,
            "step": 3765
        },
        {
            "loss": 0.0733,
            "grad_norm": 1.8435226678848267,
            "learning_rate": 8e-06,
            "epoch": 1.508,
            "step": 3770
        },
        {
            "loss": 0.1064,
            "grad_norm": 1.9253838062286377,
            "learning_rate": 8e-06,
            "epoch": 1.51,
            "step": 3775
        },
        {
            "loss": 0.0855,
            "grad_norm": 1.4757670164108276,
            "learning_rate": 8e-06,
            "epoch": 1.512,
            "step": 3780
        },
        {
            "loss": 0.0732,
            "grad_norm": 1.516099214553833,
            "learning_rate": 8e-06,
            "epoch": 1.514,
            "step": 3785
        },
        {
            "loss": 0.0871,
            "grad_norm": 1.5101583003997803,
            "learning_rate": 8e-06,
            "epoch": 1.516,
            "step": 3790
        },
        {
            "loss": 0.0873,
            "grad_norm": 1.6248359680175781,
            "learning_rate": 8e-06,
            "epoch": 1.518,
            "step": 3795
        },
        {
            "loss": 0.0936,
            "grad_norm": 1.6492527723312378,
            "learning_rate": 8e-06,
            "epoch": 1.52,
            "step": 3800
        },
        {
            "loss": 0.0894,
            "grad_norm": 1.9346810579299927,
            "learning_rate": 8e-06,
            "epoch": 1.522,
            "step": 3805
        },
        {
            "loss": 0.0935,
            "grad_norm": 1.3690080642700195,
            "learning_rate": 8e-06,
            "epoch": 1.524,
            "step": 3810
        },
        {
            "loss": 0.0873,
            "grad_norm": 2.17598819732666,
            "learning_rate": 8e-06,
            "epoch": 1.526,
            "step": 3815
        },
        {
            "loss": 0.0921,
            "grad_norm": 2.183689594268799,
            "learning_rate": 8e-06,
            "epoch": 1.528,
            "step": 3820
        },
        {
            "loss": 0.0723,
            "grad_norm": 1.9970979690551758,
            "learning_rate": 8e-06,
            "epoch": 1.53,
            "step": 3825
        },
        {
            "loss": 0.0898,
            "grad_norm": 2.708585739135742,
            "learning_rate": 8e-06,
            "epoch": 1.532,
            "step": 3830
        },
        {
            "loss": 0.0718,
            "grad_norm": 1.1575881242752075,
            "learning_rate": 8e-06,
            "epoch": 1.534,
            "step": 3835
        },
        {
            "loss": 0.0702,
            "grad_norm": 1.1524685621261597,
            "learning_rate": 8e-06,
            "epoch": 1.536,
            "step": 3840
        },
        {
            "loss": 0.0714,
            "grad_norm": 1.4655202627182007,
            "learning_rate": 8e-06,
            "epoch": 1.538,
            "step": 3845
        },
        {
            "loss": 0.0915,
            "grad_norm": 1.6392251253128052,
            "learning_rate": 8e-06,
            "epoch": 1.54,
            "step": 3850
        },
        {
            "loss": 0.0832,
            "grad_norm": 1.4799299240112305,
            "learning_rate": 8e-06,
            "epoch": 1.542,
            "step": 3855
        },
        {
            "loss": 0.0938,
            "grad_norm": 1.6101644039154053,
            "learning_rate": 8e-06,
            "epoch": 1.544,
            "step": 3860
        },
        {
            "loss": 0.0747,
            "grad_norm": 1.3023031949996948,
            "learning_rate": 8e-06,
            "epoch": 1.546,
            "step": 3865
        },
        {
            "loss": 0.0812,
            "grad_norm": 2.2888240814208984,
            "learning_rate": 8e-06,
            "epoch": 1.548,
            "step": 3870
        },
        {
            "loss": 0.0906,
            "grad_norm": 2.2639172077178955,
            "learning_rate": 8e-06,
            "epoch": 1.55,
            "step": 3875
        },
        {
            "loss": 0.0759,
            "grad_norm": 2.5550034046173096,
            "learning_rate": 8e-06,
            "epoch": 1.552,
            "step": 3880
        },
        {
            "loss": 0.0802,
            "grad_norm": 2.673090696334839,
            "learning_rate": 8e-06,
            "epoch": 1.554,
            "step": 3885
        },
        {
            "loss": 0.0865,
            "grad_norm": 1.8726561069488525,
            "learning_rate": 8e-06,
            "epoch": 1.556,
            "step": 3890
        },
        {
            "loss": 0.0885,
            "grad_norm": 2.329512596130371,
            "learning_rate": 8e-06,
            "epoch": 1.558,
            "step": 3895
        },
        {
            "loss": 0.0737,
            "grad_norm": 3.3645689487457275,
            "learning_rate": 8e-06,
            "epoch": 1.56,
            "step": 3900
        },
        {
            "eval_loss": 0.08458419889211655,
            "eval_f1": 0.7630182293669717,
            "eval_recall": 0.7815947053261897,
            "eval_accuracy": 0.9706649980211576,
            "eval_precision": 0.7453042824943651,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6345826235093697,
                    "recall": 0.7247081712062257,
                    "f1-score": 0.6766575840145324,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6741293532338308,
                    "recall": 0.6187214611872146,
                    "f1-score": 0.6452380952380953,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8309859154929577,
                    "recall": 0.9066590779738191,
                    "f1-score": 0.8671747414262384,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5776986951364176,
                    "recall": 0.5247844827586207,
                    "f1-score": 0.5499717673630717,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7453042824943651,
                    "recall": 0.7815947053261897,
                    "f1-score": 0.7630182293669717,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.679349146843144,
                    "recall": 0.6937182982814699,
                    "f1-score": 0.6847605470104845,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7404785922674626,
                    "recall": 0.7815947053261897,
                    "f1-score": 0.7592906412354621,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4491,
            "eval_samples_per_second": 920.641,
            "eval_steps_per_second": 7.193,
            "epoch": 1.56,
            "step": 3900
        },
        {
            "loss": 0.0929,
            "grad_norm": 2.2930798530578613,
            "learning_rate": 8e-06,
            "epoch": 1.562,
            "step": 3905
        },
        {
            "loss": 0.0821,
            "grad_norm": 1.572696328163147,
            "learning_rate": 8e-06,
            "epoch": 1.564,
            "step": 3910
        },
        {
            "loss": 0.089,
            "grad_norm": 1.8538520336151123,
            "learning_rate": 8e-06,
            "epoch": 1.5659999999999998,
            "step": 3915
        },
        {
            "loss": 0.0847,
            "grad_norm": 2.0858941078186035,
            "learning_rate": 8e-06,
            "epoch": 1.568,
            "step": 3920
        },
        {
            "loss": 0.0769,
            "grad_norm": 1.0743093490600586,
            "learning_rate": 8e-06,
            "epoch": 1.5699999999999998,
            "step": 3925
        },
        {
            "loss": 0.0761,
            "grad_norm": 2.1181881427764893,
            "learning_rate": 8e-06,
            "epoch": 1.572,
            "step": 3930
        },
        {
            "loss": 0.0913,
            "grad_norm": 2.1447536945343018,
            "learning_rate": 8e-06,
            "epoch": 1.5739999999999998,
            "step": 3935
        },
        {
            "loss": 0.0741,
            "grad_norm": 1.672751784324646,
            "learning_rate": 8e-06,
            "epoch": 1.576,
            "step": 3940
        },
        {
            "loss": 0.0832,
            "grad_norm": 2.036849021911621,
            "learning_rate": 8e-06,
            "epoch": 1.5779999999999998,
            "step": 3945
        },
        {
            "loss": 0.0747,
            "grad_norm": 1.863664150238037,
            "learning_rate": 8e-06,
            "epoch": 1.58,
            "step": 3950
        },
        {
            "loss": 0.0743,
            "grad_norm": 1.1926816701889038,
            "learning_rate": 8e-06,
            "epoch": 1.5819999999999999,
            "step": 3955
        },
        {
            "loss": 0.0804,
            "grad_norm": 0.8053627610206604,
            "learning_rate": 8e-06,
            "epoch": 1.584,
            "step": 3960
        },
        {
            "loss": 0.0879,
            "grad_norm": 1.6511119604110718,
            "learning_rate": 8e-06,
            "epoch": 1.5859999999999999,
            "step": 3965
        },
        {
            "loss": 0.0846,
            "grad_norm": 0.9771901965141296,
            "learning_rate": 8e-06,
            "epoch": 1.588,
            "step": 3970
        },
        {
            "loss": 0.0754,
            "grad_norm": 2.487807273864746,
            "learning_rate": 8e-06,
            "epoch": 1.5899999999999999,
            "step": 3975
        },
        {
            "loss": 0.0831,
            "grad_norm": 1.1327435970306396,
            "learning_rate": 8e-06,
            "epoch": 1.592,
            "step": 3980
        },
        {
            "loss": 0.0807,
            "grad_norm": 2.907038450241089,
            "learning_rate": 8e-06,
            "epoch": 1.5939999999999999,
            "step": 3985
        },
        {
            "loss": 0.1001,
            "grad_norm": 2.5251030921936035,
            "learning_rate": 8e-06,
            "epoch": 1.596,
            "step": 3990
        },
        {
            "loss": 0.0851,
            "grad_norm": 1.6762030124664307,
            "learning_rate": 8e-06,
            "epoch": 1.5979999999999999,
            "step": 3995
        },
        {
            "loss": 0.0906,
            "grad_norm": 2.047257661819458,
            "learning_rate": 8e-06,
            "epoch": 1.6,
            "step": 4000
        },
        {
            "loss": 0.0868,
            "grad_norm": 2.0957038402557373,
            "learning_rate": 8e-06,
            "epoch": 1.6019999999999999,
            "step": 4005
        },
        {
            "loss": 0.0704,
            "grad_norm": 1.2201881408691406,
            "learning_rate": 8e-06,
            "epoch": 1.604,
            "step": 4010
        },
        {
            "loss": 0.101,
            "grad_norm": 1.856491208076477,
            "learning_rate": 8e-06,
            "epoch": 1.6059999999999999,
            "step": 4015
        },
        {
            "loss": 0.1151,
            "grad_norm": 2.1119353771209717,
            "learning_rate": 8e-06,
            "epoch": 1.608,
            "step": 4020
        },
        {
            "loss": 0.0816,
            "grad_norm": 3.5525214672088623,
            "learning_rate": 8e-06,
            "epoch": 1.6099999999999999,
            "step": 4025
        },
        {
            "loss": 0.0785,
            "grad_norm": 1.385134220123291,
            "learning_rate": 8e-06,
            "epoch": 1.612,
            "step": 4030
        },
        {
            "loss": 0.0852,
            "grad_norm": 1.8294153213500977,
            "learning_rate": 8e-06,
            "epoch": 1.6139999999999999,
            "step": 4035
        },
        {
            "loss": 0.0758,
            "grad_norm": 1.1270880699157715,
            "learning_rate": 8e-06,
            "epoch": 1.616,
            "step": 4040
        },
        {
            "loss": 0.0972,
            "grad_norm": 3.90352725982666,
            "learning_rate": 8e-06,
            "epoch": 1.6179999999999999,
            "step": 4045
        },
        {
            "loss": 0.0631,
            "grad_norm": 2.5311167240142822,
            "learning_rate": 8e-06,
            "epoch": 1.62,
            "step": 4050
        },
        {
            "loss": 0.0544,
            "grad_norm": 1.5862138271331787,
            "learning_rate": 8e-06,
            "epoch": 1.6219999999999999,
            "step": 4055
        },
        {
            "loss": 0.0861,
            "grad_norm": 2.020814895629883,
            "learning_rate": 8e-06,
            "epoch": 1.624,
            "step": 4060
        },
        {
            "loss": 0.1125,
            "grad_norm": 2.6049492359161377,
            "learning_rate": 8e-06,
            "epoch": 1.626,
            "step": 4065
        },
        {
            "loss": 0.0743,
            "grad_norm": 1.789648413658142,
            "learning_rate": 8e-06,
            "epoch": 1.6280000000000001,
            "step": 4070
        },
        {
            "loss": 0.0933,
            "grad_norm": 1.929592490196228,
            "learning_rate": 8e-06,
            "epoch": 1.63,
            "step": 4075
        },
        {
            "loss": 0.0897,
            "grad_norm": 1.4197399616241455,
            "learning_rate": 8e-06,
            "epoch": 1.6320000000000001,
            "step": 4080
        },
        {
            "loss": 0.0695,
            "grad_norm": 2.1227831840515137,
            "learning_rate": 8e-06,
            "epoch": 1.634,
            "step": 4085
        },
        {
            "loss": 0.1122,
            "grad_norm": 2.6838815212249756,
            "learning_rate": 8e-06,
            "epoch": 1.6360000000000001,
            "step": 4090
        },
        {
            "loss": 0.0833,
            "grad_norm": 1.7261425256729126,
            "learning_rate": 8e-06,
            "epoch": 1.638,
            "step": 4095
        },
        {
            "loss": 0.0923,
            "grad_norm": 2.1506998538970947,
            "learning_rate": 8e-06,
            "epoch": 1.6400000000000001,
            "step": 4100
        },
        {
            "loss": 0.0709,
            "grad_norm": 1.6237051486968994,
            "learning_rate": 8e-06,
            "epoch": 1.642,
            "step": 4105
        },
        {
            "loss": 0.0674,
            "grad_norm": 1.961130142211914,
            "learning_rate": 8e-06,
            "epoch": 1.6440000000000001,
            "step": 4110
        },
        {
            "loss": 0.0885,
            "grad_norm": 1.6567693948745728,
            "learning_rate": 8e-06,
            "epoch": 1.646,
            "step": 4115
        },
        {
            "loss": 0.0949,
            "grad_norm": 2.405735731124878,
            "learning_rate": 8e-06,
            "epoch": 1.6480000000000001,
            "step": 4120
        },
        {
            "loss": 0.0988,
            "grad_norm": 2.5615103244781494,
            "learning_rate": 8e-06,
            "epoch": 1.65,
            "step": 4125
        },
        {
            "loss": 0.0774,
            "grad_norm": 1.7441389560699463,
            "learning_rate": 8e-06,
            "epoch": 1.6520000000000001,
            "step": 4130
        },
        {
            "loss": 0.0745,
            "grad_norm": 2.7019295692443848,
            "learning_rate": 8e-06,
            "epoch": 1.654,
            "step": 4135
        },
        {
            "loss": 0.0826,
            "grad_norm": 1.5788123607635498,
            "learning_rate": 8e-06,
            "epoch": 1.6560000000000001,
            "step": 4140
        },
        {
            "loss": 0.0887,
            "grad_norm": 3.116400718688965,
            "learning_rate": 8e-06,
            "epoch": 1.658,
            "step": 4145
        },
        {
            "loss": 0.0772,
            "grad_norm": 1.1376745700836182,
            "learning_rate": 8e-06,
            "epoch": 1.6600000000000001,
            "step": 4150
        },
        {
            "loss": 0.0684,
            "grad_norm": 1.4985822439193726,
            "learning_rate": 8e-06,
            "epoch": 1.662,
            "step": 4155
        },
        {
            "loss": 0.1044,
            "grad_norm": 2.1057190895080566,
            "learning_rate": 8e-06,
            "epoch": 1.6640000000000001,
            "step": 4160
        },
        {
            "loss": 0.0991,
            "grad_norm": 2.7834959030151367,
            "learning_rate": 8e-06,
            "epoch": 1.666,
            "step": 4165
        },
        {
            "loss": 0.0898,
            "grad_norm": 2.5300896167755127,
            "learning_rate": 8e-06,
            "epoch": 1.6680000000000001,
            "step": 4170
        },
        {
            "loss": 0.0707,
            "grad_norm": 1.5817674398422241,
            "learning_rate": 8e-06,
            "epoch": 1.67,
            "step": 4175
        },
        {
            "loss": 0.0731,
            "grad_norm": 2.2029688358306885,
            "learning_rate": 8e-06,
            "epoch": 1.6720000000000002,
            "step": 4180
        },
        {
            "loss": 0.0859,
            "grad_norm": 1.721802830696106,
            "learning_rate": 8e-06,
            "epoch": 1.674,
            "step": 4185
        },
        {
            "loss": 0.0772,
            "grad_norm": 1.917983055114746,
            "learning_rate": 8e-06,
            "epoch": 1.6760000000000002,
            "step": 4190
        },
        {
            "loss": 0.087,
            "grad_norm": 2.0751254558563232,
            "learning_rate": 8e-06,
            "epoch": 1.678,
            "step": 4195
        },
        {
            "loss": 0.0649,
            "grad_norm": 1.5130926370620728,
            "learning_rate": 8e-06,
            "epoch": 1.6800000000000002,
            "step": 4200
        },
        {
            "eval_loss": 0.0831230878829956,
            "eval_f1": 0.7643312101910829,
            "eval_recall": 0.7847462968799244,
            "eval_accuracy": 0.9713281776465681,
            "eval_precision": 0.7449513836948392,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6471119133574007,
                    "recall": 0.6974708171206225,
                    "f1-score": 0.6713483146067415,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6233766233766234,
                    "recall": 0.6575342465753424,
                    "f1-score": 0.64,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8567914730800765,
                    "recall": 0.892145702902675,
                    "f1-score": 0.8741112505227938,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5553319919517102,
                    "recall": 0.5948275862068966,
                    "f1-score": 0.5744016649323622,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7449513836948392,
                    "recall": 0.7847462968799244,
                    "f1-score": 0.7643312101910829,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6706530004414527,
                    "recall": 0.7104945882013842,
                    "f1-score": 0.6899653075154744,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7465210044033889,
                    "recall": 0.7847462968799244,
                    "f1-score": 0.7651209812180996,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4564,
            "eval_samples_per_second": 919.126,
            "eval_steps_per_second": 7.181,
            "epoch": 1.6800000000000002,
            "step": 4200
        },
        {
            "loss": 0.0803,
            "grad_norm": 1.5767217874526978,
            "learning_rate": 8e-06,
            "epoch": 1.682,
            "step": 4205
        },
        {
            "loss": 0.0708,
            "grad_norm": 2.478666305541992,
            "learning_rate": 8e-06,
            "epoch": 1.6840000000000002,
            "step": 4210
        },
        {
            "loss": 0.0657,
            "grad_norm": 2.314206600189209,
            "learning_rate": 8e-06,
            "epoch": 1.686,
            "step": 4215
        },
        {
            "loss": 0.0899,
            "grad_norm": 1.638214349746704,
            "learning_rate": 8e-06,
            "epoch": 1.688,
            "step": 4220
        },
        {
            "loss": 0.0796,
            "grad_norm": 1.9549816846847534,
            "learning_rate": 8e-06,
            "epoch": 1.69,
            "step": 4225
        },
        {
            "loss": 0.0843,
            "grad_norm": 2.1924641132354736,
            "learning_rate": 8e-06,
            "epoch": 1.692,
            "step": 4230
        },
        {
            "loss": 0.093,
            "grad_norm": 2.5645861625671387,
            "learning_rate": 8e-06,
            "epoch": 1.694,
            "step": 4235
        },
        {
            "loss": 0.0987,
            "grad_norm": 3.024087905883789,
            "learning_rate": 8e-06,
            "epoch": 1.696,
            "step": 4240
        },
        {
            "loss": 0.0822,
            "grad_norm": 1.0954530239105225,
            "learning_rate": 8e-06,
            "epoch": 1.698,
            "step": 4245
        },
        {
            "loss": 0.0909,
            "grad_norm": 1.5792206525802612,
            "learning_rate": 8e-06,
            "epoch": 1.7,
            "step": 4250
        },
        {
            "loss": 0.0902,
            "grad_norm": 2.7375142574310303,
            "learning_rate": 8e-06,
            "epoch": 1.702,
            "step": 4255
        },
        {
            "loss": 0.1052,
            "grad_norm": 1.9460357427597046,
            "learning_rate": 8e-06,
            "epoch": 1.704,
            "step": 4260
        },
        {
            "loss": 0.0806,
            "grad_norm": 1.6596564054489136,
            "learning_rate": 8e-06,
            "epoch": 1.706,
            "step": 4265
        },
        {
            "loss": 0.0851,
            "grad_norm": 2.8823728561401367,
            "learning_rate": 8e-06,
            "epoch": 1.708,
            "step": 4270
        },
        {
            "loss": 0.0639,
            "grad_norm": 0.8543097376823425,
            "learning_rate": 8e-06,
            "epoch": 1.71,
            "step": 4275
        },
        {
            "loss": 0.0786,
            "grad_norm": 1.6336305141448975,
            "learning_rate": 8e-06,
            "epoch": 1.712,
            "step": 4280
        },
        {
            "loss": 0.08,
            "grad_norm": 1.4719345569610596,
            "learning_rate": 8e-06,
            "epoch": 1.714,
            "step": 4285
        },
        {
            "loss": 0.0872,
            "grad_norm": 1.7954950332641602,
            "learning_rate": 8e-06,
            "epoch": 1.716,
            "step": 4290
        },
        {
            "loss": 0.0856,
            "grad_norm": 2.2179136276245117,
            "learning_rate": 8e-06,
            "epoch": 1.718,
            "step": 4295
        },
        {
            "loss": 0.0859,
            "grad_norm": 2.056745767593384,
            "learning_rate": 8e-06,
            "epoch": 1.72,
            "step": 4300
        },
        {
            "loss": 0.0893,
            "grad_norm": 2.1485402584075928,
            "learning_rate": 8e-06,
            "epoch": 1.722,
            "step": 4305
        },
        {
            "loss": 0.0838,
            "grad_norm": 1.5262163877487183,
            "learning_rate": 8e-06,
            "epoch": 1.724,
            "step": 4310
        },
        {
            "loss": 0.0939,
            "grad_norm": 2.631493330001831,
            "learning_rate": 8e-06,
            "epoch": 1.726,
            "step": 4315
        },
        {
            "loss": 0.0804,
            "grad_norm": 1.5657718181610107,
            "learning_rate": 8e-06,
            "epoch": 1.728,
            "step": 4320
        },
        {
            "loss": 0.0888,
            "grad_norm": 1.393547534942627,
            "learning_rate": 8e-06,
            "epoch": 1.73,
            "step": 4325
        },
        {
            "loss": 0.0787,
            "grad_norm": 1.6395312547683716,
            "learning_rate": 8e-06,
            "epoch": 1.732,
            "step": 4330
        },
        {
            "loss": 0.08,
            "grad_norm": 1.3212580680847168,
            "learning_rate": 8e-06,
            "epoch": 1.734,
            "step": 4335
        },
        {
            "loss": 0.073,
            "grad_norm": 1.6193777322769165,
            "learning_rate": 8e-06,
            "epoch": 1.736,
            "step": 4340
        },
        {
            "loss": 0.069,
            "grad_norm": 1.2587904930114746,
            "learning_rate": 8e-06,
            "epoch": 1.738,
            "step": 4345
        },
        {
            "loss": 0.0902,
            "grad_norm": 1.7939785718917847,
            "learning_rate": 8e-06,
            "epoch": 1.74,
            "step": 4350
        },
        {
            "loss": 0.0703,
            "grad_norm": 2.074793577194214,
            "learning_rate": 8e-06,
            "epoch": 1.742,
            "step": 4355
        },
        {
            "loss": 0.0672,
            "grad_norm": 2.0146853923797607,
            "learning_rate": 8e-06,
            "epoch": 1.744,
            "step": 4360
        },
        {
            "loss": 0.0863,
            "grad_norm": 2.607942819595337,
            "learning_rate": 8e-06,
            "epoch": 1.746,
            "step": 4365
        },
        {
            "loss": 0.0768,
            "grad_norm": 1.1778024435043335,
            "learning_rate": 8e-06,
            "epoch": 1.748,
            "step": 4370
        },
        {
            "loss": 0.0643,
            "grad_norm": 1.5599111318588257,
            "learning_rate": 8e-06,
            "epoch": 1.75,
            "step": 4375
        },
        {
            "loss": 0.0775,
            "grad_norm": 1.5436519384384155,
            "learning_rate": 8e-06,
            "epoch": 1.752,
            "step": 4380
        },
        {
            "loss": 0.0942,
            "grad_norm": 2.195523500442505,
            "learning_rate": 8e-06,
            "epoch": 1.754,
            "step": 4385
        },
        {
            "loss": 0.08,
            "grad_norm": 1.5974839925765991,
            "learning_rate": 8e-06,
            "epoch": 1.756,
            "step": 4390
        },
        {
            "loss": 0.0893,
            "grad_norm": 2.372723340988159,
            "learning_rate": 8e-06,
            "epoch": 1.758,
            "step": 4395
        },
        {
            "loss": 0.084,
            "grad_norm": 2.3500800132751465,
            "learning_rate": 8e-06,
            "epoch": 1.76,
            "step": 4400
        },
        {
            "loss": 0.065,
            "grad_norm": 1.9229398965835571,
            "learning_rate": 8e-06,
            "epoch": 1.762,
            "step": 4405
        },
        {
            "loss": 0.0818,
            "grad_norm": 1.3183350563049316,
            "learning_rate": 8e-06,
            "epoch": 1.764,
            "step": 4410
        },
        {
            "loss": 0.0964,
            "grad_norm": 1.6061151027679443,
            "learning_rate": 8e-06,
            "epoch": 1.766,
            "step": 4415
        },
        {
            "loss": 0.0718,
            "grad_norm": 1.8282115459442139,
            "learning_rate": 8e-06,
            "epoch": 1.768,
            "step": 4420
        },
        {
            "loss": 0.1049,
            "grad_norm": 1.909293293952942,
            "learning_rate": 8e-06,
            "epoch": 1.77,
            "step": 4425
        },
        {
            "loss": 0.0759,
            "grad_norm": 1.632448434829712,
            "learning_rate": 8e-06,
            "epoch": 1.772,
            "step": 4430
        },
        {
            "loss": 0.0737,
            "grad_norm": 1.1754827499389648,
            "learning_rate": 8e-06,
            "epoch": 1.774,
            "step": 4435
        },
        {
            "loss": 0.0715,
            "grad_norm": 1.850757122039795,
            "learning_rate": 8e-06,
            "epoch": 1.776,
            "step": 4440
        },
        {
            "loss": 0.0745,
            "grad_norm": 2.3938746452331543,
            "learning_rate": 8e-06,
            "epoch": 1.778,
            "step": 4445
        },
        {
            "loss": 0.091,
            "grad_norm": 2.252285957336426,
            "learning_rate": 8e-06,
            "epoch": 1.78,
            "step": 4450
        },
        {
            "loss": 0.0784,
            "grad_norm": 2.053720474243164,
            "learning_rate": 8e-06,
            "epoch": 1.782,
            "step": 4455
        },
        {
            "loss": 0.0792,
            "grad_norm": 1.9878182411193848,
            "learning_rate": 8e-06,
            "epoch": 1.784,
            "step": 4460
        },
        {
            "loss": 0.0534,
            "grad_norm": 1.4189457893371582,
            "learning_rate": 8e-06,
            "epoch": 1.786,
            "step": 4465
        },
        {
            "loss": 0.0759,
            "grad_norm": 1.7159192562103271,
            "learning_rate": 8e-06,
            "epoch": 1.788,
            "step": 4470
        },
        {
            "loss": 0.0838,
            "grad_norm": 2.1645431518554688,
            "learning_rate": 8e-06,
            "epoch": 1.79,
            "step": 4475
        },
        {
            "loss": 0.0812,
            "grad_norm": 2.971859931945801,
            "learning_rate": 8e-06,
            "epoch": 1.792,
            "step": 4480
        },
        {
            "loss": 0.086,
            "grad_norm": 1.999100923538208,
            "learning_rate": 8e-06,
            "epoch": 1.794,
            "step": 4485
        },
        {
            "loss": 0.0936,
            "grad_norm": 1.9757349491119385,
            "learning_rate": 8e-06,
            "epoch": 1.796,
            "step": 4490
        },
        {
            "loss": 0.0744,
            "grad_norm": 1.2670925855636597,
            "learning_rate": 8e-06,
            "epoch": 1.798,
            "step": 4495
        },
        {
            "loss": 0.0958,
            "grad_norm": 2.797227382659912,
            "learning_rate": 8e-06,
            "epoch": 1.8,
            "step": 4500
        },
        {
            "eval_loss": 0.08477164804935455,
            "eval_f1": 0.7663946811725597,
            "eval_recall": 0.7992436180271036,
            "eval_accuracy": 0.970386890436308,
            "eval_precision": 0.7361393323657475,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6122448979591837,
                    "recall": 0.7587548638132295,
                    "f1-score": 0.6776715899218071,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6553341148886284,
                    "recall": 0.6381278538812786,
                    "f1-score": 0.6466165413533834,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8457418318157471,
                    "recall": 0.8986909504837791,
                    "f1-score": 0.8714128035320088,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5587949465500486,
                    "recall": 0.6196120689655172,
                    "f1-score": 0.5876341338783853,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7361393323657475,
                    "recall": 0.7992436180271036,
                    "f1-score": 0.7663946811725597,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.668028947803402,
                    "recall": 0.7287964342859511,
                    "f1-score": 0.6958337671713961,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7396720685697227,
                    "recall": 0.7992436180271036,
                    "f1-score": 0.7674994567468959,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4652,
            "eval_samples_per_second": 917.307,
            "eval_steps_per_second": 7.166,
            "epoch": 1.8,
            "step": 4500
        },
        {
            "loss": 0.0664,
            "grad_norm": 1.5839214324951172,
            "learning_rate": 8e-06,
            "epoch": 1.802,
            "step": 4505
        },
        {
            "loss": 0.0846,
            "grad_norm": 2.8396291732788086,
            "learning_rate": 8e-06,
            "epoch": 1.804,
            "step": 4510
        },
        {
            "loss": 0.072,
            "grad_norm": 2.812471866607666,
            "learning_rate": 8e-06,
            "epoch": 1.806,
            "step": 4515
        },
        {
            "loss": 0.0752,
            "grad_norm": 2.5706632137298584,
            "learning_rate": 8e-06,
            "epoch": 1.808,
            "step": 4520
        },
        {
            "loss": 0.0966,
            "grad_norm": 1.8899390697479248,
            "learning_rate": 8e-06,
            "epoch": 1.81,
            "step": 4525
        },
        {
            "loss": 0.0739,
            "grad_norm": 1.0509426593780518,
            "learning_rate": 8e-06,
            "epoch": 1.812,
            "step": 4530
        },
        {
            "loss": 0.0974,
            "grad_norm": 1.8153026103973389,
            "learning_rate": 8e-06,
            "epoch": 1.814,
            "step": 4535
        },
        {
            "loss": 0.0614,
            "grad_norm": 1.5334410667419434,
            "learning_rate": 8e-06,
            "epoch": 1.8159999999999998,
            "step": 4540
        },
        {
            "loss": 0.1074,
            "grad_norm": 2.2708680629730225,
            "learning_rate": 8e-06,
            "epoch": 1.818,
            "step": 4545
        },
        {
            "loss": 0.0808,
            "grad_norm": 1.8838120698928833,
            "learning_rate": 8e-06,
            "epoch": 1.8199999999999998,
            "step": 4550
        },
        {
            "loss": 0.0764,
            "grad_norm": 1.7701873779296875,
            "learning_rate": 8e-06,
            "epoch": 1.822,
            "step": 4555
        },
        {
            "loss": 0.0815,
            "grad_norm": 1.742060899734497,
            "learning_rate": 8e-06,
            "epoch": 1.8239999999999998,
            "step": 4560
        },
        {
            "loss": 0.0841,
            "grad_norm": 1.8581641912460327,
            "learning_rate": 8e-06,
            "epoch": 1.826,
            "step": 4565
        },
        {
            "loss": 0.0754,
            "grad_norm": 1.8008826971054077,
            "learning_rate": 8e-06,
            "epoch": 1.8279999999999998,
            "step": 4570
        },
        {
            "loss": 0.0726,
            "grad_norm": 2.33091139793396,
            "learning_rate": 8e-06,
            "epoch": 1.83,
            "step": 4575
        },
        {
            "loss": 0.0709,
            "grad_norm": 2.293073892593384,
            "learning_rate": 8e-06,
            "epoch": 1.8319999999999999,
            "step": 4580
        },
        {
            "loss": 0.0797,
            "grad_norm": 1.7442444562911987,
            "learning_rate": 8e-06,
            "epoch": 1.834,
            "step": 4585
        },
        {
            "loss": 0.0705,
            "grad_norm": 1.5901288986206055,
            "learning_rate": 8e-06,
            "epoch": 1.8359999999999999,
            "step": 4590
        },
        {
            "loss": 0.0788,
            "grad_norm": 1.6212064027786255,
            "learning_rate": 8e-06,
            "epoch": 1.838,
            "step": 4595
        },
        {
            "loss": 0.0799,
            "grad_norm": 1.9443702697753906,
            "learning_rate": 8e-06,
            "epoch": 1.8399999999999999,
            "step": 4600
        },
        {
            "loss": 0.078,
            "grad_norm": 2.543562412261963,
            "learning_rate": 8e-06,
            "epoch": 1.842,
            "step": 4605
        },
        {
            "loss": 0.0713,
            "grad_norm": 1.60332453250885,
            "learning_rate": 8e-06,
            "epoch": 1.8439999999999999,
            "step": 4610
        },
        {
            "loss": 0.0527,
            "grad_norm": 0.9988309741020203,
            "learning_rate": 8e-06,
            "epoch": 1.846,
            "step": 4615
        },
        {
            "loss": 0.0661,
            "grad_norm": 1.3677080869674683,
            "learning_rate": 8e-06,
            "epoch": 1.8479999999999999,
            "step": 4620
        },
        {
            "loss": 0.0698,
            "grad_norm": 1.349312424659729,
            "learning_rate": 8e-06,
            "epoch": 1.85,
            "step": 4625
        },
        {
            "loss": 0.076,
            "grad_norm": 2.438589334487915,
            "learning_rate": 8e-06,
            "epoch": 1.8519999999999999,
            "step": 4630
        },
        {
            "loss": 0.1023,
            "grad_norm": 2.102405548095703,
            "learning_rate": 8e-06,
            "epoch": 1.854,
            "step": 4635
        },
        {
            "loss": 0.0741,
            "grad_norm": 1.6295207738876343,
            "learning_rate": 8e-06,
            "epoch": 1.8559999999999999,
            "step": 4640
        },
        {
            "loss": 0.0673,
            "grad_norm": 2.2553110122680664,
            "learning_rate": 8e-06,
            "epoch": 1.858,
            "step": 4645
        },
        {
            "loss": 0.0781,
            "grad_norm": 2.09378719329834,
            "learning_rate": 8e-06,
            "epoch": 1.8599999999999999,
            "step": 4650
        },
        {
            "loss": 0.0737,
            "grad_norm": 2.0351040363311768,
            "learning_rate": 8e-06,
            "epoch": 1.862,
            "step": 4655
        },
        {
            "loss": 0.0826,
            "grad_norm": 1.9075145721435547,
            "learning_rate": 8e-06,
            "epoch": 1.8639999999999999,
            "step": 4660
        },
        {
            "loss": 0.0709,
            "grad_norm": 1.3182653188705444,
            "learning_rate": 8e-06,
            "epoch": 1.866,
            "step": 4665
        },
        {
            "loss": 0.1014,
            "grad_norm": 2.208664894104004,
            "learning_rate": 8e-06,
            "epoch": 1.8679999999999999,
            "step": 4670
        },
        {
            "loss": 0.0829,
            "grad_norm": 1.0819579362869263,
            "learning_rate": 8e-06,
            "epoch": 1.87,
            "step": 4675
        },
        {
            "loss": 0.0707,
            "grad_norm": 1.3027503490447998,
            "learning_rate": 8e-06,
            "epoch": 1.8719999999999999,
            "step": 4680
        },
        {
            "loss": 0.0779,
            "grad_norm": 1.221472978591919,
            "learning_rate": 8e-06,
            "epoch": 1.874,
            "step": 4685
        },
        {
            "loss": 0.0819,
            "grad_norm": 1.7872675657272339,
            "learning_rate": 8e-06,
            "epoch": 1.876,
            "step": 4690
        },
        {
            "loss": 0.0691,
            "grad_norm": 1.9194060564041138,
            "learning_rate": 8e-06,
            "epoch": 1.8780000000000001,
            "step": 4695
        },
        {
            "loss": 0.0765,
            "grad_norm": 1.7084579467773438,
            "learning_rate": 8e-06,
            "epoch": 1.88,
            "step": 4700
        },
        {
            "loss": 0.09,
            "grad_norm": 2.821483612060547,
            "learning_rate": 8e-06,
            "epoch": 1.8820000000000001,
            "step": 4705
        },
        {
            "loss": 0.0748,
            "grad_norm": 1.453945279121399,
            "learning_rate": 8e-06,
            "epoch": 1.884,
            "step": 4710
        },
        {
            "loss": 0.0878,
            "grad_norm": 2.0933761596679688,
            "learning_rate": 8e-06,
            "epoch": 1.8860000000000001,
            "step": 4715
        },
        {
            "loss": 0.0856,
            "grad_norm": 1.9581583738327026,
            "learning_rate": 8e-06,
            "epoch": 1.888,
            "step": 4720
        },
        {
            "loss": 0.0835,
            "grad_norm": 2.658473014831543,
            "learning_rate": 8e-06,
            "epoch": 1.8900000000000001,
            "step": 4725
        },
        {
            "loss": 0.0741,
            "grad_norm": 1.4347758293151855,
            "learning_rate": 8e-06,
            "epoch": 1.892,
            "step": 4730
        },
        {
            "loss": 0.0879,
            "grad_norm": 1.8370131254196167,
            "learning_rate": 8e-06,
            "epoch": 1.8940000000000001,
            "step": 4735
        },
        {
            "loss": 0.0767,
            "grad_norm": 1.2555227279663086,
            "learning_rate": 8e-06,
            "epoch": 1.896,
            "step": 4740
        },
        {
            "loss": 0.0904,
            "grad_norm": 2.258507013320923,
            "learning_rate": 8e-06,
            "epoch": 1.8980000000000001,
            "step": 4745
        },
        {
            "loss": 0.082,
            "grad_norm": 1.8350958824157715,
            "learning_rate": 8e-06,
            "epoch": 1.9,
            "step": 4750
        },
        {
            "loss": 0.0839,
            "grad_norm": 1.2753959894180298,
            "learning_rate": 8e-06,
            "epoch": 1.9020000000000001,
            "step": 4755
        },
        {
            "loss": 0.0887,
            "grad_norm": 1.0550404787063599,
            "learning_rate": 8e-06,
            "epoch": 1.904,
            "step": 4760
        },
        {
            "loss": 0.0791,
            "grad_norm": 1.890140175819397,
            "learning_rate": 8e-06,
            "epoch": 1.9060000000000001,
            "step": 4765
        },
        {
            "loss": 0.0718,
            "grad_norm": 1.862311601638794,
            "learning_rate": 8e-06,
            "epoch": 1.908,
            "step": 4770
        },
        {
            "loss": 0.0775,
            "grad_norm": 1.8739173412322998,
            "learning_rate": 8e-06,
            "epoch": 1.9100000000000001,
            "step": 4775
        },
        {
            "loss": 0.0923,
            "grad_norm": 1.1710866689682007,
            "learning_rate": 8e-06,
            "epoch": 1.912,
            "step": 4780
        },
        {
            "loss": 0.1001,
            "grad_norm": 2.5947365760803223,
            "learning_rate": 8e-06,
            "epoch": 1.9140000000000001,
            "step": 4785
        },
        {
            "loss": 0.0861,
            "grad_norm": 2.169424295425415,
            "learning_rate": 8e-06,
            "epoch": 1.916,
            "step": 4790
        },
        {
            "loss": 0.085,
            "grad_norm": 0.9919788837432861,
            "learning_rate": 8e-06,
            "epoch": 1.9180000000000001,
            "step": 4795
        },
        {
            "loss": 0.0754,
            "grad_norm": 2.121422529220581,
            "learning_rate": 8e-06,
            "epoch": 1.92,
            "step": 4800
        },
        {
            "eval_loss": 0.08149135857820511,
            "eval_f1": 0.7699780633030398,
            "eval_recall": 0.7743460447526,
            "eval_accuracy": 0.9713067847554258,
            "eval_precision": 0.7656590838267373,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.655536028119508,
                    "recall": 0.72568093385214,
                    "f1-score": 0.6888273314866113,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.7175141242937854,
                    "recall": 0.5799086757990868,
                    "f1-score": 0.6414141414141415,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8586717892425906,
                    "recall": 0.8904382470119522,
                    "f1-score": 0.8742665549036043,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.572198275862069,
                    "recall": 0.572198275862069,
                    "f1-score": 0.572198275862069,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7656590838267373,
                    "recall": 0.7743460447526,
                    "f1-score": 0.7699780633030398,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.7009800543794882,
                    "recall": 0.692056533131312,
                    "f1-score": 0.6941765759166065,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7643879730833081,
                    "recall": 0.7743460447526,
                    "f1-score": 0.7679114337501245,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4616,
            "eval_samples_per_second": 918.063,
            "eval_steps_per_second": 7.172,
            "epoch": 1.92,
            "step": 4800
        },
        {
            "loss": 0.0867,
            "grad_norm": 1.6722311973571777,
            "learning_rate": 8e-06,
            "epoch": 1.9220000000000002,
            "step": 4805
        },
        {
            "loss": 0.0796,
            "grad_norm": 1.8381457328796387,
            "learning_rate": 8e-06,
            "epoch": 1.924,
            "step": 4810
        },
        {
            "loss": 0.0827,
            "grad_norm": 2.4064767360687256,
            "learning_rate": 8e-06,
            "epoch": 1.9260000000000002,
            "step": 4815
        },
        {
            "loss": 0.0596,
            "grad_norm": 1.713552713394165,
            "learning_rate": 8e-06,
            "epoch": 1.928,
            "step": 4820
        },
        {
            "loss": 0.0806,
            "grad_norm": 1.2551277875900269,
            "learning_rate": 8e-06,
            "epoch": 1.9300000000000002,
            "step": 4825
        },
        {
            "loss": 0.0807,
            "grad_norm": 1.5893667936325073,
            "learning_rate": 8e-06,
            "epoch": 1.932,
            "step": 4830
        },
        {
            "loss": 0.0792,
            "grad_norm": 2.729285955429077,
            "learning_rate": 8e-06,
            "epoch": 1.9340000000000002,
            "step": 4835
        },
        {
            "loss": 0.0959,
            "grad_norm": 1.7766679525375366,
            "learning_rate": 8e-06,
            "epoch": 1.936,
            "step": 4840
        },
        {
            "loss": 0.0774,
            "grad_norm": 2.0147287845611572,
            "learning_rate": 8e-06,
            "epoch": 1.938,
            "step": 4845
        },
        {
            "loss": 0.0858,
            "grad_norm": 1.8140957355499268,
            "learning_rate": 8e-06,
            "epoch": 1.94,
            "step": 4850
        },
        {
            "loss": 0.0681,
            "grad_norm": 1.3121507167816162,
            "learning_rate": 8e-06,
            "epoch": 1.942,
            "step": 4855
        },
        {
            "loss": 0.0742,
            "grad_norm": 1.6998246908187866,
            "learning_rate": 8e-06,
            "epoch": 1.944,
            "step": 4860
        },
        {
            "loss": 0.0702,
            "grad_norm": 1.308337926864624,
            "learning_rate": 8e-06,
            "epoch": 1.946,
            "step": 4865
        },
        {
            "loss": 0.068,
            "grad_norm": 1.289541482925415,
            "learning_rate": 8e-06,
            "epoch": 1.948,
            "step": 4870
        },
        {
            "loss": 0.1058,
            "grad_norm": 1.6464645862579346,
            "learning_rate": 8e-06,
            "epoch": 1.95,
            "step": 4875
        },
        {
            "loss": 0.0687,
            "grad_norm": 1.975448727607727,
            "learning_rate": 8e-06,
            "epoch": 1.952,
            "step": 4880
        },
        {
            "loss": 0.071,
            "grad_norm": 1.1790046691894531,
            "learning_rate": 8e-06,
            "epoch": 1.954,
            "step": 4885
        },
        {
            "loss": 0.0826,
            "grad_norm": 1.6079002618789673,
            "learning_rate": 8e-06,
            "epoch": 1.956,
            "step": 4890
        },
        {
            "loss": 0.0779,
            "grad_norm": 2.0401816368103027,
            "learning_rate": 8e-06,
            "epoch": 1.958,
            "step": 4895
        },
        {
            "loss": 0.0733,
            "grad_norm": 1.7419495582580566,
            "learning_rate": 8e-06,
            "epoch": 1.96,
            "step": 4900
        },
        {
            "loss": 0.0853,
            "grad_norm": 2.7807817459106445,
            "learning_rate": 8e-06,
            "epoch": 1.962,
            "step": 4905
        },
        {
            "loss": 0.0744,
            "grad_norm": 2.1707053184509277,
            "learning_rate": 8e-06,
            "epoch": 1.964,
            "step": 4910
        },
        {
            "loss": 0.0892,
            "grad_norm": 3.6735785007476807,
            "learning_rate": 8e-06,
            "epoch": 1.966,
            "step": 4915
        },
        {
            "loss": 0.0721,
            "grad_norm": 1.0367029905319214,
            "learning_rate": 8e-06,
            "epoch": 1.968,
            "step": 4920
        },
        {
            "loss": 0.0842,
            "grad_norm": 2.0966131687164307,
            "learning_rate": 8e-06,
            "epoch": 1.97,
            "step": 4925
        },
        {
            "loss": 0.101,
            "grad_norm": 2.0314016342163086,
            "learning_rate": 8e-06,
            "epoch": 1.972,
            "step": 4930
        },
        {
            "loss": 0.0907,
            "grad_norm": 1.2148834466934204,
            "learning_rate": 8e-06,
            "epoch": 1.974,
            "step": 4935
        },
        {
            "loss": 0.0927,
            "grad_norm": 1.7404437065124512,
            "learning_rate": 8e-06,
            "epoch": 1.976,
            "step": 4940
        },
        {
            "loss": 0.089,
            "grad_norm": 1.6712653636932373,
            "learning_rate": 8e-06,
            "epoch": 1.978,
            "step": 4945
        },
        {
            "loss": 0.0652,
            "grad_norm": 2.053269147872925,
            "learning_rate": 8e-06,
            "epoch": 1.98,
            "step": 4950
        },
        {
            "loss": 0.0676,
            "grad_norm": 2.0243144035339355,
            "learning_rate": 8e-06,
            "epoch": 1.982,
            "step": 4955
        },
        {
            "loss": 0.0682,
            "grad_norm": 1.825394868850708,
            "learning_rate": 8e-06,
            "epoch": 1.984,
            "step": 4960
        },
        {
            "loss": 0.1014,
            "grad_norm": 2.002345561981201,
            "learning_rate": 8e-06,
            "epoch": 1.986,
            "step": 4965
        },
        {
            "loss": 0.0796,
            "grad_norm": 1.9747087955474854,
            "learning_rate": 8e-06,
            "epoch": 1.988,
            "step": 4970
        },
        {
            "loss": 0.0751,
            "grad_norm": 2.926936626434326,
            "learning_rate": 8e-06,
            "epoch": 1.99,
            "step": 4975
        },
        {
            "loss": 0.074,
            "grad_norm": 1.7890509366989136,
            "learning_rate": 8e-06,
            "epoch": 1.992,
            "step": 4980
        },
        {
            "loss": 0.0817,
            "grad_norm": 3.0640170574188232,
            "learning_rate": 8e-06,
            "epoch": 1.994,
            "step": 4985
        },
        {
            "loss": 0.0714,
            "grad_norm": 1.4577277898788452,
            "learning_rate": 8e-06,
            "epoch": 1.996,
            "step": 4990
        },
        {
            "loss": 0.0775,
            "grad_norm": 1.1370892524719238,
            "learning_rate": 8e-06,
            "epoch": 1.998,
            "step": 4995
        },
        {
            "loss": 0.0842,
            "grad_norm": 2.710001230239868,
            "learning_rate": 8e-06,
            "epoch": 2.0,
            "step": 5000
        },
        {
            "loss": 0.0671,
            "grad_norm": 1.1735267639160156,
            "learning_rate": 8e-06,
            "epoch": 2.002,
            "step": 5005
        },
        {
            "loss": 0.0558,
            "grad_norm": 1.2049776315689087,
            "learning_rate": 8e-06,
            "epoch": 2.004,
            "step": 5010
        },
        {
            "loss": 0.0732,
            "grad_norm": 1.596998929977417,
            "learning_rate": 8e-06,
            "epoch": 2.006,
            "step": 5015
        },
        {
            "loss": 0.0645,
            "grad_norm": 2.1448974609375,
            "learning_rate": 8e-06,
            "epoch": 2.008,
            "step": 5020
        },
        {
            "loss": 0.0681,
            "grad_norm": 2.122743606567383,
            "learning_rate": 8e-06,
            "epoch": 2.01,
            "step": 5025
        },
        {
            "loss": 0.0838,
            "grad_norm": 2.48150634765625,
            "learning_rate": 8e-06,
            "epoch": 2.012,
            "step": 5030
        },
        {
            "loss": 0.0742,
            "grad_norm": 1.6750376224517822,
            "learning_rate": 8e-06,
            "epoch": 2.014,
            "step": 5035
        },
        {
            "loss": 0.0616,
            "grad_norm": 0.6567020416259766,
            "learning_rate": 8e-06,
            "epoch": 2.016,
            "step": 5040
        },
        {
            "loss": 0.0779,
            "grad_norm": 1.0679494142532349,
            "learning_rate": 8e-06,
            "epoch": 2.018,
            "step": 5045
        },
        {
            "loss": 0.0723,
            "grad_norm": 2.0321507453918457,
            "learning_rate": 8e-06,
            "epoch": 2.02,
            "step": 5050
        },
        {
            "loss": 0.0773,
            "grad_norm": 1.974700689315796,
            "learning_rate": 8e-06,
            "epoch": 2.022,
            "step": 5055
        },
        {
            "loss": 0.0536,
            "grad_norm": 1.2842592000961304,
            "learning_rate": 8e-06,
            "epoch": 2.024,
            "step": 5060
        },
        {
            "loss": 0.0609,
            "grad_norm": 1.7530572414398193,
            "learning_rate": 8e-06,
            "epoch": 2.026,
            "step": 5065
        },
        {
            "loss": 0.0718,
            "grad_norm": 2.4305508136749268,
            "learning_rate": 8e-06,
            "epoch": 2.028,
            "step": 5070
        },
        {
            "loss": 0.0695,
            "grad_norm": 2.104219675064087,
            "learning_rate": 8e-06,
            "epoch": 2.03,
            "step": 5075
        },
        {
            "loss": 0.0788,
            "grad_norm": 2.4942402839660645,
            "learning_rate": 8e-06,
            "epoch": 2.032,
            "step": 5080
        },
        {
            "loss": 0.0734,
            "grad_norm": 2.4591751098632812,
            "learning_rate": 8e-06,
            "epoch": 2.034,
            "step": 5085
        },
        {
            "loss": 0.067,
            "grad_norm": 1.6005585193634033,
            "learning_rate": 8e-06,
            "epoch": 2.036,
            "step": 5090
        },
        {
            "loss": 0.0655,
            "grad_norm": 2.9200713634490967,
            "learning_rate": 8e-06,
            "epoch": 2.038,
            "step": 5095
        },
        {
            "loss": 0.0838,
            "grad_norm": 1.6534920930862427,
            "learning_rate": 8e-06,
            "epoch": 2.04,
            "step": 5100
        },
        {
            "eval_loss": 0.08375908434391022,
            "eval_f1": 0.7703274322418926,
            "eval_recall": 0.7748187834856602,
            "eval_accuracy": 0.9714458385478506,
            "eval_precision": 0.7658878504672897,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6551724137931034,
                    "recall": 0.7208171206225681,
                    "f1-score": 0.6864289022695692,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6828609986504723,
                    "recall": 0.5776255707762558,
                    "f1-score": 0.6258503401360543,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8532358516111562,
                    "recall": 0.8966989186112692,
                    "f1-score": 0.874427639794644,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.6070175438596491,
                    "recall": 0.5592672413793104,
                    "f1-score": 0.5821648906337634,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7658878504672897,
                    "recall": 0.7748187834856602,
                    "f1-score": 0.7703274322418926,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6995717019785953,
                    "recall": 0.6886022128473509,
                    "f1-score": 0.6922179432085077,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7616272517271481,
                    "recall": 0.7748187834856602,
                    "f1-score": 0.7669211399682969,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4411,
            "eval_samples_per_second": 922.293,
            "eval_steps_per_second": 7.205,
            "epoch": 2.04,
            "step": 5100
        },
        {
            "loss": 0.0693,
            "grad_norm": 1.8126423358917236,
            "learning_rate": 8e-06,
            "epoch": 2.042,
            "step": 5105
        },
        {
            "loss": 0.0822,
            "grad_norm": 1.9415088891983032,
            "learning_rate": 8e-06,
            "epoch": 2.044,
            "step": 5110
        },
        {
            "loss": 0.0857,
            "grad_norm": 1.9547300338745117,
            "learning_rate": 8e-06,
            "epoch": 2.046,
            "step": 5115
        },
        {
            "loss": 0.0639,
            "grad_norm": 1.4740625619888306,
            "learning_rate": 8e-06,
            "epoch": 2.048,
            "step": 5120
        },
        {
            "loss": 0.057,
            "grad_norm": 1.462734341621399,
            "learning_rate": 8e-06,
            "epoch": 2.05,
            "step": 5125
        },
        {
            "loss": 0.0893,
            "grad_norm": 1.7724378108978271,
            "learning_rate": 8e-06,
            "epoch": 2.052,
            "step": 5130
        },
        {
            "loss": 0.0731,
            "grad_norm": 1.64137601852417,
            "learning_rate": 8e-06,
            "epoch": 2.054,
            "step": 5135
        },
        {
            "loss": 0.0735,
            "grad_norm": 3.7789502143859863,
            "learning_rate": 8e-06,
            "epoch": 2.056,
            "step": 5140
        },
        {
            "loss": 0.0943,
            "grad_norm": 1.198384165763855,
            "learning_rate": 8e-06,
            "epoch": 2.058,
            "step": 5145
        },
        {
            "loss": 0.0603,
            "grad_norm": 1.2977964878082275,
            "learning_rate": 8e-06,
            "epoch": 2.06,
            "step": 5150
        },
        {
            "loss": 0.0882,
            "grad_norm": 1.2623950242996216,
            "learning_rate": 8e-06,
            "epoch": 2.062,
            "step": 5155
        },
        {
            "loss": 0.0688,
            "grad_norm": 3.096648693084717,
            "learning_rate": 8e-06,
            "epoch": 2.064,
            "step": 5160
        },
        {
            "loss": 0.0678,
            "grad_norm": 1.4856210947036743,
            "learning_rate": 8e-06,
            "epoch": 2.066,
            "step": 5165
        },
        {
            "loss": 0.0789,
            "grad_norm": 4.3737897872924805,
            "learning_rate": 8e-06,
            "epoch": 2.068,
            "step": 5170
        },
        {
            "loss": 0.0604,
            "grad_norm": 0.9314009547233582,
            "learning_rate": 8e-06,
            "epoch": 2.07,
            "step": 5175
        },
        {
            "loss": 0.0741,
            "grad_norm": 2.0018062591552734,
            "learning_rate": 8e-06,
            "epoch": 2.072,
            "step": 5180
        },
        {
            "loss": 0.0637,
            "grad_norm": 1.6208444833755493,
            "learning_rate": 8e-06,
            "epoch": 2.074,
            "step": 5185
        },
        {
            "loss": 0.0633,
            "grad_norm": 2.362640380859375,
            "learning_rate": 8e-06,
            "epoch": 2.076,
            "step": 5190
        },
        {
            "loss": 0.0608,
            "grad_norm": 1.2321702241897583,
            "learning_rate": 8e-06,
            "epoch": 2.078,
            "step": 5195
        },
        {
            "loss": 0.0735,
            "grad_norm": 1.5446884632110596,
            "learning_rate": 8e-06,
            "epoch": 2.08,
            "step": 5200
        },
        {
            "loss": 0.0831,
            "grad_norm": 1.5735018253326416,
            "learning_rate": 8e-06,
            "epoch": 2.082,
            "step": 5205
        },
        {
            "loss": 0.0519,
            "grad_norm": 2.4089691638946533,
            "learning_rate": 8e-06,
            "epoch": 2.084,
            "step": 5210
        },
        {
            "loss": 0.0765,
            "grad_norm": 2.502044200897217,
            "learning_rate": 8e-06,
            "epoch": 2.086,
            "step": 5215
        },
        {
            "loss": 0.0773,
            "grad_norm": 2.7446861267089844,
            "learning_rate": 8e-06,
            "epoch": 2.088,
            "step": 5220
        },
        {
            "loss": 0.0554,
            "grad_norm": 1.3121671676635742,
            "learning_rate": 8e-06,
            "epoch": 2.09,
            "step": 5225
        },
        {
            "loss": 0.0634,
            "grad_norm": 1.2000455856323242,
            "learning_rate": 8e-06,
            "epoch": 2.092,
            "step": 5230
        },
        {
            "loss": 0.0745,
            "grad_norm": 1.2651928663253784,
            "learning_rate": 8e-06,
            "epoch": 2.094,
            "step": 5235
        },
        {
            "loss": 0.078,
            "grad_norm": 2.7945830821990967,
            "learning_rate": 8e-06,
            "epoch": 2.096,
            "step": 5240
        },
        {
            "loss": 0.0643,
            "grad_norm": 1.3196104764938354,
            "learning_rate": 8e-06,
            "epoch": 2.098,
            "step": 5245
        },
        {
            "loss": 0.0632,
            "grad_norm": 1.40666663646698,
            "learning_rate": 8e-06,
            "epoch": 2.1,
            "step": 5250
        },
        {
            "loss": 0.0958,
            "grad_norm": 1.9376022815704346,
            "learning_rate": 8e-06,
            "epoch": 2.102,
            "step": 5255
        },
        {
            "loss": 0.0663,
            "grad_norm": 2.3697924613952637,
            "learning_rate": 8e-06,
            "epoch": 2.104,
            "step": 5260
        },
        {
            "loss": 0.0702,
            "grad_norm": 2.2652668952941895,
            "learning_rate": 8e-06,
            "epoch": 2.106,
            "step": 5265
        },
        {
            "loss": 0.0714,
            "grad_norm": 1.1760812997817993,
            "learning_rate": 8e-06,
            "epoch": 2.108,
            "step": 5270
        },
        {
            "loss": 0.0793,
            "grad_norm": 2.335463762283325,
            "learning_rate": 8e-06,
            "epoch": 2.11,
            "step": 5275
        },
        {
            "loss": 0.0642,
            "grad_norm": 1.7582536935806274,
            "learning_rate": 8e-06,
            "epoch": 2.112,
            "step": 5280
        },
        {
            "loss": 0.0645,
            "grad_norm": 1.05707585811615,
            "learning_rate": 8e-06,
            "epoch": 2.114,
            "step": 5285
        },
        {
            "loss": 0.0875,
            "grad_norm": 1.7205647230148315,
            "learning_rate": 8e-06,
            "epoch": 2.116,
            "step": 5290
        },
        {
            "loss": 0.071,
            "grad_norm": 2.275991678237915,
            "learning_rate": 8e-06,
            "epoch": 2.118,
            "step": 5295
        },
        {
            "loss": 0.0668,
            "grad_norm": 2.1619341373443604,
            "learning_rate": 8e-06,
            "epoch": 2.12,
            "step": 5300
        },
        {
            "loss": 0.0677,
            "grad_norm": 2.344557285308838,
            "learning_rate": 8e-06,
            "epoch": 2.122,
            "step": 5305
        },
        {
            "loss": 0.0809,
            "grad_norm": 2.2454893589019775,
            "learning_rate": 8e-06,
            "epoch": 2.124,
            "step": 5310
        },
        {
            "loss": 0.0731,
            "grad_norm": 2.110347032546997,
            "learning_rate": 8e-06,
            "epoch": 2.126,
            "step": 5315
        },
        {
            "loss": 0.0829,
            "grad_norm": 2.27894926071167,
            "learning_rate": 8e-06,
            "epoch": 2.128,
            "step": 5320
        },
        {
            "loss": 0.0746,
            "grad_norm": 1.4773190021514893,
            "learning_rate": 8e-06,
            "epoch": 2.13,
            "step": 5325
        },
        {
            "loss": 0.0681,
            "grad_norm": 2.529496431350708,
            "learning_rate": 8e-06,
            "epoch": 2.132,
            "step": 5330
        },
        {
            "loss": 0.0688,
            "grad_norm": 1.364312767982483,
            "learning_rate": 8e-06,
            "epoch": 2.134,
            "step": 5335
        },
        {
            "loss": 0.0709,
            "grad_norm": 2.2978315353393555,
            "learning_rate": 8e-06,
            "epoch": 2.136,
            "step": 5340
        },
        {
            "loss": 0.0707,
            "grad_norm": 2.264289379119873,
            "learning_rate": 8e-06,
            "epoch": 2.138,
            "step": 5345
        },
        {
            "loss": 0.0543,
            "grad_norm": 2.466801166534424,
            "learning_rate": 8e-06,
            "epoch": 2.14,
            "step": 5350
        },
        {
            "loss": 0.0725,
            "grad_norm": 2.0405187606811523,
            "learning_rate": 8e-06,
            "epoch": 2.142,
            "step": 5355
        },
        {
            "loss": 0.0736,
            "grad_norm": 1.5795954465866089,
            "learning_rate": 8e-06,
            "epoch": 2.144,
            "step": 5360
        },
        {
            "loss": 0.0719,
            "grad_norm": 2.319472074508667,
            "learning_rate": 8e-06,
            "epoch": 2.146,
            "step": 5365
        },
        {
            "loss": 0.096,
            "grad_norm": 3.9601943492889404,
            "learning_rate": 8e-06,
            "epoch": 2.148,
            "step": 5370
        },
        {
            "loss": 0.0846,
            "grad_norm": 1.6001394987106323,
            "learning_rate": 8e-06,
            "epoch": 2.15,
            "step": 5375
        },
        {
            "loss": 0.0777,
            "grad_norm": 1.5867778062820435,
            "learning_rate": 8e-06,
            "epoch": 2.152,
            "step": 5380
        },
        {
            "loss": 0.0658,
            "grad_norm": 1.5618113279342651,
            "learning_rate": 8e-06,
            "epoch": 2.154,
            "step": 5385
        },
        {
            "loss": 0.0672,
            "grad_norm": 1.9043043851852417,
            "learning_rate": 8e-06,
            "epoch": 2.156,
            "step": 5390
        },
        {
            "loss": 0.0868,
            "grad_norm": 2.1186065673828125,
            "learning_rate": 8e-06,
            "epoch": 2.158,
            "step": 5395
        },
        {
            "loss": 0.0673,
            "grad_norm": 1.1335450410842896,
            "learning_rate": 8e-06,
            "epoch": 2.16,
            "step": 5400
        },
        {
            "eval_loss": 0.0800337940454483,
            "eval_f1": 0.7779500697782602,
            "eval_recall": 0.7905767412543334,
            "eval_accuracy": 0.9721999379606157,
            "eval_precision": 0.7657203907203908,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6798917944093779,
                    "recall": 0.7334630350194552,
                    "f1-score": 0.7056621431913898,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.7021822849807445,
                    "recall": 0.6244292237442922,
                    "f1-score": 0.6610271903323263,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8524015110631409,
                    "recall": 0.8989755264655663,
                    "f1-score": 0.8750692520775624,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.581419624217119,
                    "recall": 0.6002155172413793,
                    "f1-score": 0.5906680805938495,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7657203907203908,
                    "recall": 0.7905767412543334,
                    "f1-score": 0.7779500697782602,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.7039738036675955,
                    "recall": 0.7142708256176733,
                    "f1-score": 0.708106666548782,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7640934080437026,
                    "recall": 0.7905767412543334,
                    "f1-score": 0.7764913067323532,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4843,
            "eval_samples_per_second": 913.408,
            "eval_steps_per_second": 7.136,
            "epoch": 2.16,
            "step": 5400
        },
        {
            "loss": 0.0692,
            "grad_norm": 1.8934468030929565,
            "learning_rate": 8e-06,
            "epoch": 2.162,
            "step": 5405
        },
        {
            "loss": 0.0628,
            "grad_norm": 1.7565622329711914,
            "learning_rate": 8e-06,
            "epoch": 2.164,
            "step": 5410
        },
        {
            "loss": 0.0786,
            "grad_norm": 2.165438652038574,
            "learning_rate": 8e-06,
            "epoch": 2.166,
            "step": 5415
        },
        {
            "loss": 0.066,
            "grad_norm": 2.420761823654175,
            "learning_rate": 8e-06,
            "epoch": 2.168,
            "step": 5420
        },
        {
            "loss": 0.0714,
            "grad_norm": 1.7825912237167358,
            "learning_rate": 8e-06,
            "epoch": 2.17,
            "step": 5425
        },
        {
            "loss": 0.0653,
            "grad_norm": 1.100364089012146,
            "learning_rate": 8e-06,
            "epoch": 2.172,
            "step": 5430
        },
        {
            "loss": 0.0766,
            "grad_norm": 1.6345465183258057,
            "learning_rate": 8e-06,
            "epoch": 2.174,
            "step": 5435
        },
        {
            "loss": 0.0698,
            "grad_norm": 1.5901751518249512,
            "learning_rate": 8e-06,
            "epoch": 2.176,
            "step": 5440
        },
        {
            "loss": 0.0854,
            "grad_norm": 1.1608340740203857,
            "learning_rate": 8e-06,
            "epoch": 2.178,
            "step": 5445
        },
        {
            "loss": 0.0549,
            "grad_norm": 1.6592341661453247,
            "learning_rate": 8e-06,
            "epoch": 2.18,
            "step": 5450
        },
        {
            "loss": 0.0713,
            "grad_norm": 1.723031759262085,
            "learning_rate": 8e-06,
            "epoch": 2.182,
            "step": 5455
        },
        {
            "loss": 0.0703,
            "grad_norm": 2.5917468070983887,
            "learning_rate": 8e-06,
            "epoch": 2.184,
            "step": 5460
        },
        {
            "loss": 0.0823,
            "grad_norm": 1.7228331565856934,
            "learning_rate": 8e-06,
            "epoch": 2.186,
            "step": 5465
        },
        {
            "loss": 0.0493,
            "grad_norm": 1.8900835514068604,
            "learning_rate": 8e-06,
            "epoch": 2.188,
            "step": 5470
        },
        {
            "loss": 0.0591,
            "grad_norm": 0.7350454330444336,
            "learning_rate": 8e-06,
            "epoch": 2.19,
            "step": 5475
        },
        {
            "loss": 0.0795,
            "grad_norm": 1.3947514295578003,
            "learning_rate": 8e-06,
            "epoch": 2.192,
            "step": 5480
        },
        {
            "loss": 0.0622,
            "grad_norm": 1.995726227760315,
            "learning_rate": 8e-06,
            "epoch": 2.194,
            "step": 5485
        },
        {
            "loss": 0.0658,
            "grad_norm": 1.8504934310913086,
            "learning_rate": 8e-06,
            "epoch": 2.196,
            "step": 5490
        },
        {
            "loss": 0.084,
            "grad_norm": 1.6886248588562012,
            "learning_rate": 8e-06,
            "epoch": 2.198,
            "step": 5495
        },
        {
            "loss": 0.0666,
            "grad_norm": 2.837376356124878,
            "learning_rate": 8e-06,
            "epoch": 2.2,
            "step": 5500
        },
        {
            "loss": 0.0722,
            "grad_norm": 1.3876851797103882,
            "learning_rate": 8e-06,
            "epoch": 2.202,
            "step": 5505
        },
        {
            "loss": 0.0567,
            "grad_norm": 2.557180643081665,
            "learning_rate": 8e-06,
            "epoch": 2.204,
            "step": 5510
        },
        {
            "loss": 0.0651,
            "grad_norm": 1.6563799381256104,
            "learning_rate": 8e-06,
            "epoch": 2.206,
            "step": 5515
        },
        {
            "loss": 0.0739,
            "grad_norm": 2.788484573364258,
            "learning_rate": 8e-06,
            "epoch": 2.208,
            "step": 5520
        },
        {
            "loss": 0.0765,
            "grad_norm": 3.419346570968628,
            "learning_rate": 8e-06,
            "epoch": 2.21,
            "step": 5525
        },
        {
            "loss": 0.0795,
            "grad_norm": 2.2101943492889404,
            "learning_rate": 8e-06,
            "epoch": 2.212,
            "step": 5530
        },
        {
            "loss": 0.0526,
            "grad_norm": 1.5434879064559937,
            "learning_rate": 8e-06,
            "epoch": 2.214,
            "step": 5535
        },
        {
            "loss": 0.0677,
            "grad_norm": 0.995057225227356,
            "learning_rate": 8e-06,
            "epoch": 2.216,
            "step": 5540
        },
        {
            "loss": 0.0803,
            "grad_norm": 3.2104272842407227,
            "learning_rate": 8e-06,
            "epoch": 2.218,
            "step": 5545
        },
        {
            "loss": 0.0682,
            "grad_norm": 1.4938737154006958,
            "learning_rate": 8e-06,
            "epoch": 2.22,
            "step": 5550
        },
        {
            "loss": 0.0556,
            "grad_norm": 1.1753389835357666,
            "learning_rate": 8e-06,
            "epoch": 2.222,
            "step": 5555
        },
        {
            "loss": 0.06,
            "grad_norm": 1.0790467262268066,
            "learning_rate": 8e-06,
            "epoch": 2.224,
            "step": 5560
        },
        {
            "loss": 0.0604,
            "grad_norm": 1.6998093128204346,
            "learning_rate": 8e-06,
            "epoch": 2.226,
            "step": 5565
        },
        {
            "loss": 0.0775,
            "grad_norm": 3.1967906951904297,
            "learning_rate": 8e-06,
            "epoch": 2.228,
            "step": 5570
        },
        {
            "loss": 0.0693,
            "grad_norm": 2.120765447616577,
            "learning_rate": 8e-06,
            "epoch": 2.23,
            "step": 5575
        },
        {
            "loss": 0.0763,
            "grad_norm": 1.78904128074646,
            "learning_rate": 8e-06,
            "epoch": 2.232,
            "step": 5580
        },
        {
            "loss": 0.0804,
            "grad_norm": 1.609783411026001,
            "learning_rate": 8e-06,
            "epoch": 2.234,
            "step": 5585
        },
        {
            "loss": 0.0696,
            "grad_norm": 1.594632863998413,
            "learning_rate": 8e-06,
            "epoch": 2.2359999999999998,
            "step": 5590
        },
        {
            "loss": 0.063,
            "grad_norm": 1.783339262008667,
            "learning_rate": 8e-06,
            "epoch": 2.238,
            "step": 5595
        },
        {
            "loss": 0.07,
            "grad_norm": 2.804853677749634,
            "learning_rate": 8e-06,
            "epoch": 2.24,
            "step": 5600
        },
        {
            "loss": 0.0727,
            "grad_norm": 1.4056936502456665,
            "learning_rate": 8e-06,
            "epoch": 2.242,
            "step": 5605
        },
        {
            "loss": 0.0751,
            "grad_norm": 1.2248584032058716,
            "learning_rate": 8e-06,
            "epoch": 2.2439999999999998,
            "step": 5610
        },
        {
            "loss": 0.0778,
            "grad_norm": 1.4376842975616455,
            "learning_rate": 8e-06,
            "epoch": 2.246,
            "step": 5615
        },
        {
            "loss": 0.0832,
            "grad_norm": 1.3311806917190552,
            "learning_rate": 8e-06,
            "epoch": 2.248,
            "step": 5620
        },
        {
            "loss": 0.0734,
            "grad_norm": 1.5829744338989258,
            "learning_rate": 8e-06,
            "epoch": 2.25,
            "step": 5625
        },
        {
            "loss": 0.0743,
            "grad_norm": 1.6108676195144653,
            "learning_rate": 8e-06,
            "epoch": 2.252,
            "step": 5630
        },
        {
            "loss": 0.0574,
            "grad_norm": 2.1534781455993652,
            "learning_rate": 8e-06,
            "epoch": 2.254,
            "step": 5635
        },
        {
            "loss": 0.0694,
            "grad_norm": 1.8060301542282104,
            "learning_rate": 8e-06,
            "epoch": 2.2560000000000002,
            "step": 5640
        },
        {
            "loss": 0.0719,
            "grad_norm": 2.3013458251953125,
            "learning_rate": 8e-06,
            "epoch": 2.258,
            "step": 5645
        },
        {
            "loss": 0.0816,
            "grad_norm": 2.9612765312194824,
            "learning_rate": 8e-06,
            "epoch": 2.26,
            "step": 5650
        },
        {
            "loss": 0.0826,
            "grad_norm": 2.006572723388672,
            "learning_rate": 8e-06,
            "epoch": 2.262,
            "step": 5655
        },
        {
            "loss": 0.0636,
            "grad_norm": 1.6865205764770508,
            "learning_rate": 8e-06,
            "epoch": 2.2640000000000002,
            "step": 5660
        },
        {
            "loss": 0.0629,
            "grad_norm": 1.3528937101364136,
            "learning_rate": 8e-06,
            "epoch": 2.266,
            "step": 5665
        },
        {
            "loss": 0.0805,
            "grad_norm": 1.8797624111175537,
            "learning_rate": 8e-06,
            "epoch": 2.268,
            "step": 5670
        },
        {
            "loss": 0.0612,
            "grad_norm": 1.7519080638885498,
            "learning_rate": 8e-06,
            "epoch": 2.27,
            "step": 5675
        },
        {
            "loss": 0.0819,
            "grad_norm": 2.049199104309082,
            "learning_rate": 8e-06,
            "epoch": 2.2720000000000002,
            "step": 5680
        },
        {
            "loss": 0.0565,
            "grad_norm": 1.2188210487365723,
            "learning_rate": 8e-06,
            "epoch": 2.274,
            "step": 5685
        },
        {
            "loss": 0.0733,
            "grad_norm": 2.287142038345337,
            "learning_rate": 8e-06,
            "epoch": 2.276,
            "step": 5690
        },
        {
            "loss": 0.0722,
            "grad_norm": 2.9930036067962646,
            "learning_rate": 8e-06,
            "epoch": 2.278,
            "step": 5695
        },
        {
            "loss": 0.0574,
            "grad_norm": 2.3243839740753174,
            "learning_rate": 8e-06,
            "epoch": 2.2800000000000002,
            "step": 5700
        },
        {
            "eval_loss": 0.08188726007938385,
            "eval_f1": 0.778134042386799,
            "eval_recall": 0.7839583989914907,
            "eval_accuracy": 0.9721518039555456,
            "eval_precision": 0.7723955907467784,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.677536231884058,
                    "recall": 0.7276264591439688,
                    "f1-score": 0.701688555347092,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.69221260815822,
                    "recall": 0.639269406392694,
                    "f1-score": 0.6646884272997032,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8582292232482347,
                    "recall": 0.8992601024473534,
                    "f1-score": 0.8782657031684269,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.599290780141844,
                    "recall": 0.5463362068965517,
                    "f1-score": 0.5715896279594138,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7723955907467784,
                    "recall": 0.7839583989914907,
                    "f1-score": 0.778134042386799,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.7068172108580891,
                    "recall": 0.7031230437201419,
                    "f1-score": 0.704058078443659,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7681759889047179,
                    "recall": 0.7839583989914907,
                    "f1-score": 0.7753330842879828,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4771,
            "eval_samples_per_second": 914.877,
            "eval_steps_per_second": 7.147,
            "epoch": 2.2800000000000002,
            "step": 5700
        },
        {
            "loss": 0.0681,
            "grad_norm": 2.9346566200256348,
            "learning_rate": 8e-06,
            "epoch": 2.282,
            "step": 5705
        },
        {
            "loss": 0.0775,
            "grad_norm": 1.1602610349655151,
            "learning_rate": 8e-06,
            "epoch": 2.284,
            "step": 5710
        },
        {
            "loss": 0.069,
            "grad_norm": 2.381728172302246,
            "learning_rate": 8e-06,
            "epoch": 2.286,
            "step": 5715
        },
        {
            "loss": 0.06,
            "grad_norm": 0.8593127131462097,
            "learning_rate": 8e-06,
            "epoch": 2.288,
            "step": 5720
        },
        {
            "loss": 0.0604,
            "grad_norm": 2.344034194946289,
            "learning_rate": 8e-06,
            "epoch": 2.29,
            "step": 5725
        },
        {
            "loss": 0.0619,
            "grad_norm": 1.553518295288086,
            "learning_rate": 8e-06,
            "epoch": 2.292,
            "step": 5730
        },
        {
            "loss": 0.069,
            "grad_norm": 2.925671100616455,
            "learning_rate": 8e-06,
            "epoch": 2.294,
            "step": 5735
        },
        {
            "loss": 0.0635,
            "grad_norm": 1.7347326278686523,
            "learning_rate": 8e-06,
            "epoch": 2.296,
            "step": 5740
        },
        {
            "loss": 0.0782,
            "grad_norm": 2.2523274421691895,
            "learning_rate": 8e-06,
            "epoch": 2.298,
            "step": 5745
        },
        {
            "loss": 0.0797,
            "grad_norm": 1.7338066101074219,
            "learning_rate": 8e-06,
            "epoch": 2.3,
            "step": 5750
        },
        {
            "loss": 0.0595,
            "grad_norm": 1.5514034032821655,
            "learning_rate": 8e-06,
            "epoch": 2.302,
            "step": 5755
        },
        {
            "loss": 0.0718,
            "grad_norm": 3.708470582962036,
            "learning_rate": 8e-06,
            "epoch": 2.304,
            "step": 5760
        },
        {
            "loss": 0.0792,
            "grad_norm": 2.2736918926239014,
            "learning_rate": 8e-06,
            "epoch": 2.306,
            "step": 5765
        },
        {
            "loss": 0.0573,
            "grad_norm": 1.938658595085144,
            "learning_rate": 8e-06,
            "epoch": 2.308,
            "step": 5770
        },
        {
            "loss": 0.066,
            "grad_norm": 3.364190101623535,
            "learning_rate": 8e-06,
            "epoch": 2.31,
            "step": 5775
        },
        {
            "loss": 0.0731,
            "grad_norm": 1.9282273054122925,
            "learning_rate": 8e-06,
            "epoch": 2.312,
            "step": 5780
        },
        {
            "loss": 0.0699,
            "grad_norm": 1.3767348527908325,
            "learning_rate": 8e-06,
            "epoch": 2.314,
            "step": 5785
        },
        {
            "loss": 0.0609,
            "grad_norm": 1.8483394384384155,
            "learning_rate": 8e-06,
            "epoch": 2.316,
            "step": 5790
        },
        {
            "loss": 0.0767,
            "grad_norm": 1.476662039756775,
            "learning_rate": 8e-06,
            "epoch": 2.318,
            "step": 5795
        },
        {
            "loss": 0.0694,
            "grad_norm": 2.0788488388061523,
            "learning_rate": 8e-06,
            "epoch": 2.32,
            "step": 5800
        },
        {
            "loss": 0.0614,
            "grad_norm": 2.5590286254882812,
            "learning_rate": 8e-06,
            "epoch": 2.322,
            "step": 5805
        },
        {
            "loss": 0.0659,
            "grad_norm": 1.5596853494644165,
            "learning_rate": 8e-06,
            "epoch": 2.324,
            "step": 5810
        },
        {
            "loss": 0.0837,
            "grad_norm": 2.3667943477630615,
            "learning_rate": 8e-06,
            "epoch": 2.326,
            "step": 5815
        },
        {
            "loss": 0.0737,
            "grad_norm": 2.4769175052642822,
            "learning_rate": 8e-06,
            "epoch": 2.328,
            "step": 5820
        },
        {
            "loss": 0.0752,
            "grad_norm": 1.8319482803344727,
            "learning_rate": 8e-06,
            "epoch": 2.33,
            "step": 5825
        },
        {
            "loss": 0.0779,
            "grad_norm": 1.2032912969589233,
            "learning_rate": 8e-06,
            "epoch": 2.332,
            "step": 5830
        },
        {
            "loss": 0.0696,
            "grad_norm": 2.1332194805145264,
            "learning_rate": 8e-06,
            "epoch": 2.334,
            "step": 5835
        },
        {
            "loss": 0.0717,
            "grad_norm": 2.0492630004882812,
            "learning_rate": 8e-06,
            "epoch": 2.336,
            "step": 5840
        },
        {
            "loss": 0.0607,
            "grad_norm": 1.6597256660461426,
            "learning_rate": 8e-06,
            "epoch": 2.338,
            "step": 5845
        },
        {
            "loss": 0.0578,
            "grad_norm": 1.7936040163040161,
            "learning_rate": 8e-06,
            "epoch": 2.34,
            "step": 5850
        },
        {
            "loss": 0.0726,
            "grad_norm": 1.0071934461593628,
            "learning_rate": 8e-06,
            "epoch": 2.342,
            "step": 5855
        },
        {
            "loss": 0.0675,
            "grad_norm": 1.6697758436203003,
            "learning_rate": 8e-06,
            "epoch": 2.344,
            "step": 5860
        },
        {
            "loss": 0.0839,
            "grad_norm": 2.1684906482696533,
            "learning_rate": 8e-06,
            "epoch": 2.346,
            "step": 5865
        },
        {
            "loss": 0.0684,
            "grad_norm": 1.8675734996795654,
            "learning_rate": 8e-06,
            "epoch": 2.348,
            "step": 5870
        },
        {
            "loss": 0.0743,
            "grad_norm": 1.2881358861923218,
            "learning_rate": 8e-06,
            "epoch": 2.35,
            "step": 5875
        },
        {
            "loss": 0.0812,
            "grad_norm": 1.6205908060073853,
            "learning_rate": 8e-06,
            "epoch": 2.352,
            "step": 5880
        },
        {
            "loss": 0.0947,
            "grad_norm": 2.782970905303955,
            "learning_rate": 8e-06,
            "epoch": 2.354,
            "step": 5885
        },
        {
            "loss": 0.0735,
            "grad_norm": 2.5378241539001465,
            "learning_rate": 8e-06,
            "epoch": 2.356,
            "step": 5890
        },
        {
            "loss": 0.0819,
            "grad_norm": 1.485276460647583,
            "learning_rate": 8e-06,
            "epoch": 2.358,
            "step": 5895
        },
        {
            "loss": 0.0792,
            "grad_norm": 2.7741858959198,
            "learning_rate": 8e-06,
            "epoch": 2.36,
            "step": 5900
        },
        {
            "loss": 0.0828,
            "grad_norm": 1.274687647819519,
            "learning_rate": 8e-06,
            "epoch": 2.362,
            "step": 5905
        },
        {
            "loss": 0.0567,
            "grad_norm": 1.3811352252960205,
            "learning_rate": 8e-06,
            "epoch": 2.364,
            "step": 5910
        },
        {
            "loss": 0.0588,
            "grad_norm": 1.31446373462677,
            "learning_rate": 8e-06,
            "epoch": 2.366,
            "step": 5915
        },
        {
            "loss": 0.066,
            "grad_norm": 3.14760160446167,
            "learning_rate": 8e-06,
            "epoch": 2.368,
            "step": 5920
        },
        {
            "loss": 0.0486,
            "grad_norm": 0.9160536527633667,
            "learning_rate": 8e-06,
            "epoch": 2.37,
            "step": 5925
        },
        {
            "loss": 0.069,
            "grad_norm": 1.4212514162063599,
            "learning_rate": 8e-06,
            "epoch": 2.372,
            "step": 5930
        },
        {
            "loss": 0.0732,
            "grad_norm": 1.680173635482788,
            "learning_rate": 8e-06,
            "epoch": 2.374,
            "step": 5935
        },
        {
            "loss": 0.0762,
            "grad_norm": 2.2761056423187256,
            "learning_rate": 8e-06,
            "epoch": 2.376,
            "step": 5940
        },
        {
            "loss": 0.0754,
            "grad_norm": 1.6442232131958008,
            "learning_rate": 8e-06,
            "epoch": 2.378,
            "step": 5945
        },
        {
            "loss": 0.0639,
            "grad_norm": 1.0770936012268066,
            "learning_rate": 8e-06,
            "epoch": 2.38,
            "step": 5950
        },
        {
            "loss": 0.0666,
            "grad_norm": 2.9454753398895264,
            "learning_rate": 8e-06,
            "epoch": 2.382,
            "step": 5955
        },
        {
            "loss": 0.0699,
            "grad_norm": 2.6895864009857178,
            "learning_rate": 8e-06,
            "epoch": 2.384,
            "step": 5960
        },
        {
            "loss": 0.0751,
            "grad_norm": 1.078113079071045,
            "learning_rate": 8e-06,
            "epoch": 2.386,
            "step": 5965
        },
        {
            "loss": 0.0662,
            "grad_norm": 1.5649033784866333,
            "learning_rate": 8e-06,
            "epoch": 2.388,
            "step": 5970
        },
        {
            "loss": 0.0562,
            "grad_norm": 2.10102915763855,
            "learning_rate": 8e-06,
            "epoch": 2.39,
            "step": 5975
        },
        {
            "loss": 0.0636,
            "grad_norm": 2.391630172729492,
            "learning_rate": 8e-06,
            "epoch": 2.392,
            "step": 5980
        },
        {
            "loss": 0.0824,
            "grad_norm": 1.667046070098877,
            "learning_rate": 8e-06,
            "epoch": 2.394,
            "step": 5985
        },
        {
            "loss": 0.0759,
            "grad_norm": 1.4064910411834717,
            "learning_rate": 8e-06,
            "epoch": 2.396,
            "step": 5990
        },
        {
            "loss": 0.0878,
            "grad_norm": 1.6835540533065796,
            "learning_rate": 8e-06,
            "epoch": 2.398,
            "step": 5995
        },
        {
            "loss": 0.0694,
            "grad_norm": 2.6536636352539062,
            "learning_rate": 8e-06,
            "epoch": 2.4,
            "step": 6000
        },
        {
            "eval_loss": 0.08277688920497894,
            "eval_f1": 0.7619047619047619,
            "eval_recall": 0.8017648912700914,
            "eval_accuracy": 0.9706382569072297,
            "eval_precision": 0.7258202567760342,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.5694842406876791,
                    "recall": 0.7733463035019456,
                    "f1-score": 0.655940594059406,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6418764302059496,
                    "recall": 0.6404109589041096,
                    "f1-score": 0.6411428571428571,
                    "support": 876
                },
                "PER": {
                    "precision": 0.831948051948052,
                    "recall": 0.9114968696642003,
                    "f1-score": 0.8699076588810429,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5943820224719101,
                    "recall": 0.5700431034482759,
                    "f1-score": 0.5819581958195821,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7258202567760342,
                    "recall": 0.8017648912700914,
                    "f1-score": 0.7619047619047619,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6594226863283976,
                    "recall": 0.7238243088796328,
                    "f1-score": 0.687237326475722,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7284534389673389,
                    "recall": 0.8017648912700914,
                    "f1-score": 0.7615601627133264,
                    "support": 6346
                }
            },
            "eval_runtime": 5.6651,
            "eval_samples_per_second": 723.019,
            "eval_steps_per_second": 5.649,
            "epoch": 2.4,
            "step": 6000
        },
        {
            "loss": 0.0781,
            "grad_norm": 1.8829439878463745,
            "learning_rate": 8e-06,
            "epoch": 2.402,
            "step": 6005
        },
        {
            "loss": 0.071,
            "grad_norm": 1.3135184049606323,
            "learning_rate": 8e-06,
            "epoch": 2.404,
            "step": 6010
        },
        {
            "loss": 0.0561,
            "grad_norm": 1.192928433418274,
            "learning_rate": 8e-06,
            "epoch": 2.406,
            "step": 6015
        },
        {
            "loss": 0.077,
            "grad_norm": 1.323746681213379,
            "learning_rate": 8e-06,
            "epoch": 2.408,
            "step": 6020
        },
        {
            "loss": 0.0742,
            "grad_norm": 2.341524600982666,
            "learning_rate": 8e-06,
            "epoch": 2.41,
            "step": 6025
        },
        {
            "loss": 0.0722,
            "grad_norm": 2.517820119857788,
            "learning_rate": 8e-06,
            "epoch": 2.412,
            "step": 6030
        },
        {
            "loss": 0.0626,
            "grad_norm": 1.2483386993408203,
            "learning_rate": 8e-06,
            "epoch": 2.414,
            "step": 6035
        },
        {
            "loss": 0.0752,
            "grad_norm": 2.5188677310943604,
            "learning_rate": 8e-06,
            "epoch": 2.416,
            "step": 6040
        },
        {
            "loss": 0.082,
            "grad_norm": 2.8307435512542725,
            "learning_rate": 8e-06,
            "epoch": 2.418,
            "step": 6045
        },
        {
            "loss": 0.0748,
            "grad_norm": 2.350684881210327,
            "learning_rate": 8e-06,
            "epoch": 2.42,
            "step": 6050
        },
        {
            "loss": 0.0613,
            "grad_norm": 1.8322186470031738,
            "learning_rate": 8e-06,
            "epoch": 2.422,
            "step": 6055
        },
        {
            "loss": 0.066,
            "grad_norm": 1.7167149782180786,
            "learning_rate": 8e-06,
            "epoch": 2.424,
            "step": 6060
        },
        {
            "loss": 0.0774,
            "grad_norm": 1.229945182800293,
            "learning_rate": 8e-06,
            "epoch": 2.426,
            "step": 6065
        },
        {
            "loss": 0.0769,
            "grad_norm": 1.7560818195343018,
            "learning_rate": 8e-06,
            "epoch": 2.428,
            "step": 6070
        },
        {
            "loss": 0.0891,
            "grad_norm": 1.9582656621932983,
            "learning_rate": 8e-06,
            "epoch": 2.43,
            "step": 6075
        },
        {
            "loss": 0.0788,
            "grad_norm": 1.7396446466445923,
            "learning_rate": 8e-06,
            "epoch": 2.432,
            "step": 6080
        },
        {
            "loss": 0.0753,
            "grad_norm": 1.564461350440979,
            "learning_rate": 8e-06,
            "epoch": 2.434,
            "step": 6085
        },
        {
            "loss": 0.069,
            "grad_norm": 1.7491505146026611,
            "learning_rate": 8e-06,
            "epoch": 2.436,
            "step": 6090
        },
        {
            "loss": 0.0837,
            "grad_norm": 2.532491683959961,
            "learning_rate": 8e-06,
            "epoch": 2.438,
            "step": 6095
        },
        {
            "loss": 0.0758,
            "grad_norm": 1.297455906867981,
            "learning_rate": 8e-06,
            "epoch": 2.44,
            "step": 6100
        },
        {
            "loss": 0.0544,
            "grad_norm": 1.5791606903076172,
            "learning_rate": 8e-06,
            "epoch": 2.442,
            "step": 6105
        },
        {
            "loss": 0.0829,
            "grad_norm": 1.286221981048584,
            "learning_rate": 8e-06,
            "epoch": 2.444,
            "step": 6110
        },
        {
            "loss": 0.076,
            "grad_norm": 1.1497137546539307,
            "learning_rate": 8e-06,
            "epoch": 2.446,
            "step": 6115
        },
        {
            "loss": 0.059,
            "grad_norm": 2.361020565032959,
            "learning_rate": 8e-06,
            "epoch": 2.448,
            "step": 6120
        },
        {
            "loss": 0.0724,
            "grad_norm": 1.8054949045181274,
            "learning_rate": 8e-06,
            "epoch": 2.45,
            "step": 6125
        },
        {
            "loss": 0.0577,
            "grad_norm": 1.178678035736084,
            "learning_rate": 8e-06,
            "epoch": 2.452,
            "step": 6130
        },
        {
            "loss": 0.0581,
            "grad_norm": 1.1044881343841553,
            "learning_rate": 8e-06,
            "epoch": 2.454,
            "step": 6135
        },
        {
            "loss": 0.0744,
            "grad_norm": 3.3837671279907227,
            "learning_rate": 8e-06,
            "epoch": 2.456,
            "step": 6140
        },
        {
            "loss": 0.0811,
            "grad_norm": 3.5469093322753906,
            "learning_rate": 8e-06,
            "epoch": 2.458,
            "step": 6145
        },
        {
            "loss": 0.0586,
            "grad_norm": 1.4242446422576904,
            "learning_rate": 8e-06,
            "epoch": 2.46,
            "step": 6150
        },
        {
            "loss": 0.0665,
            "grad_norm": 2.6378910541534424,
            "learning_rate": 8e-06,
            "epoch": 2.462,
            "step": 6155
        },
        {
            "loss": 0.064,
            "grad_norm": 1.2731393575668335,
            "learning_rate": 8e-06,
            "epoch": 2.464,
            "step": 6160
        },
        {
            "loss": 0.0604,
            "grad_norm": 2.08463191986084,
            "learning_rate": 8e-06,
            "epoch": 2.466,
            "step": 6165
        },
        {
            "loss": 0.0891,
            "grad_norm": 1.923829197883606,
            "learning_rate": 8e-06,
            "epoch": 2.468,
            "step": 6170
        },
        {
            "loss": 0.0649,
            "grad_norm": 1.8594831228256226,
            "learning_rate": 8e-06,
            "epoch": 2.4699999999999998,
            "step": 6175
        },
        {
            "loss": 0.0597,
            "grad_norm": 1.6066774129867554,
            "learning_rate": 8e-06,
            "epoch": 2.472,
            "step": 6180
        },
        {
            "loss": 0.0607,
            "grad_norm": 1.9730322360992432,
            "learning_rate": 8e-06,
            "epoch": 2.474,
            "step": 6185
        },
        {
            "loss": 0.0947,
            "grad_norm": 2.4940686225891113,
            "learning_rate": 8e-06,
            "epoch": 2.476,
            "step": 6190
        },
        {
            "loss": 0.0712,
            "grad_norm": 1.9742729663848877,
            "learning_rate": 8e-06,
            "epoch": 2.4779999999999998,
            "step": 6195
        },
        {
            "loss": 0.0675,
            "grad_norm": 2.1857476234436035,
            "learning_rate": 8e-06,
            "epoch": 2.48,
            "step": 6200
        },
        {
            "loss": 0.0746,
            "grad_norm": 1.5053695440292358,
            "learning_rate": 8e-06,
            "epoch": 2.482,
            "step": 6205
        },
        {
            "loss": 0.0673,
            "grad_norm": 1.2315897941589355,
            "learning_rate": 8e-06,
            "epoch": 2.484,
            "step": 6210
        },
        {
            "loss": 0.0538,
            "grad_norm": 1.0107605457305908,
            "learning_rate": 8e-06,
            "epoch": 2.4859999999999998,
            "step": 6215
        },
        {
            "loss": 0.069,
            "grad_norm": 1.7853130102157593,
            "learning_rate": 8e-06,
            "epoch": 2.488,
            "step": 6220
        },
        {
            "loss": 0.0725,
            "grad_norm": 1.541305422782898,
            "learning_rate": 8e-06,
            "epoch": 2.49,
            "step": 6225
        },
        {
            "loss": 0.0737,
            "grad_norm": 1.1022809743881226,
            "learning_rate": 8e-06,
            "epoch": 2.492,
            "step": 6230
        },
        {
            "loss": 0.0738,
            "grad_norm": 1.9851784706115723,
            "learning_rate": 8e-06,
            "epoch": 2.4939999999999998,
            "step": 6235
        },
        {
            "loss": 0.0666,
            "grad_norm": 2.114854574203491,
            "learning_rate": 8e-06,
            "epoch": 2.496,
            "step": 6240
        },
        {
            "loss": 0.0626,
            "grad_norm": 2.893246650695801,
            "learning_rate": 8e-06,
            "epoch": 2.498,
            "step": 6245
        },
        {
            "loss": 0.0593,
            "grad_norm": 2.4109292030334473,
            "learning_rate": 8e-06,
            "epoch": 2.5,
            "step": 6250
        },
        {
            "loss": 0.0595,
            "grad_norm": 1.8524398803710938,
            "learning_rate": 8e-06,
            "epoch": 2.502,
            "step": 6255
        },
        {
            "loss": 0.0547,
            "grad_norm": 0.8541412353515625,
            "learning_rate": 8e-06,
            "epoch": 2.504,
            "step": 6260
        },
        {
            "loss": 0.0594,
            "grad_norm": 1.2501170635223389,
            "learning_rate": 8e-06,
            "epoch": 2.5060000000000002,
            "step": 6265
        },
        {
            "loss": 0.062,
            "grad_norm": 1.61237370967865,
            "learning_rate": 8e-06,
            "epoch": 2.508,
            "step": 6270
        },
        {
            "loss": 0.0586,
            "grad_norm": 1.851884126663208,
            "learning_rate": 8e-06,
            "epoch": 2.51,
            "step": 6275
        },
        {
            "loss": 0.0654,
            "grad_norm": 1.9194782972335815,
            "learning_rate": 8e-06,
            "epoch": 2.512,
            "step": 6280
        },
        {
            "loss": 0.0726,
            "grad_norm": 1.7718696594238281,
            "learning_rate": 8e-06,
            "epoch": 2.5140000000000002,
            "step": 6285
        },
        {
            "loss": 0.057,
            "grad_norm": 1.5731326341629028,
            "learning_rate": 8e-06,
            "epoch": 2.516,
            "step": 6290
        },
        {
            "loss": 0.0819,
            "grad_norm": 2.6881115436553955,
            "learning_rate": 8e-06,
            "epoch": 2.518,
            "step": 6295
        },
        {
            "loss": 0.0773,
            "grad_norm": 3.4439167976379395,
            "learning_rate": 8e-06,
            "epoch": 2.52,
            "step": 6300
        },
        {
            "eval_loss": 0.08242911100387573,
            "eval_f1": 0.7786618170796393,
            "eval_recall": 0.809643870154428,
            "eval_accuracy": 0.9719057857074094,
            "eval_precision": 0.7499635089767918,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6388443017656501,
                    "recall": 0.77431906614786,
                    "f1-score": 0.7000879507475813,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6990049751243781,
                    "recall": 0.6415525114155252,
                    "f1-score": 0.6690476190476191,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8526965387711296,
                    "recall": 0.9043824701195219,
                    "f1-score": 0.8777793122496893,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5605214152700186,
                    "recall": 0.6487068965517241,
                    "f1-score": 0.6013986013986015,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7499635089767918,
                    "recall": 0.809643870154428,
                    "f1-score": 0.7786618170796393,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6877668077327941,
                    "recall": 0.7422402360586579,
                    "f1-score": 0.7120783708608729,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7541127972008148,
                    "recall": 0.809643870154428,
                    "f1-score": 0.7797652904187736,
                    "support": 6346
                }
            },
            "eval_runtime": 4.1825,
            "eval_samples_per_second": 979.315,
            "eval_steps_per_second": 7.651,
            "epoch": 2.52,
            "step": 6300
        },
        {
            "loss": 0.0799,
            "grad_norm": 1.1966677904129028,
            "learning_rate": 8e-06,
            "epoch": 2.5220000000000002,
            "step": 6305
        },
        {
            "loss": 0.0601,
            "grad_norm": 1.7919189929962158,
            "learning_rate": 8e-06,
            "epoch": 2.524,
            "step": 6310
        },
        {
            "loss": 0.0667,
            "grad_norm": 1.3100509643554688,
            "learning_rate": 8e-06,
            "epoch": 2.526,
            "step": 6315
        },
        {
            "loss": 0.0733,
            "grad_norm": 1.461391568183899,
            "learning_rate": 8e-06,
            "epoch": 2.528,
            "step": 6320
        },
        {
            "loss": 0.0776,
            "grad_norm": 2.0679855346679688,
            "learning_rate": 8e-06,
            "epoch": 2.5300000000000002,
            "step": 6325
        },
        {
            "loss": 0.0693,
            "grad_norm": 1.6368656158447266,
            "learning_rate": 8e-06,
            "epoch": 2.532,
            "step": 6330
        },
        {
            "loss": 0.055,
            "grad_norm": 1.3042922019958496,
            "learning_rate": 8e-06,
            "epoch": 2.534,
            "step": 6335
        },
        {
            "loss": 0.0697,
            "grad_norm": 1.7734087705612183,
            "learning_rate": 8e-06,
            "epoch": 2.536,
            "step": 6340
        },
        {
            "loss": 0.0653,
            "grad_norm": 1.6049072742462158,
            "learning_rate": 8e-06,
            "epoch": 2.5380000000000003,
            "step": 6345
        },
        {
            "loss": 0.0737,
            "grad_norm": 1.2079707384109497,
            "learning_rate": 8e-06,
            "epoch": 2.54,
            "step": 6350
        },
        {
            "loss": 0.0614,
            "grad_norm": 1.6290900707244873,
            "learning_rate": 8e-06,
            "epoch": 2.542,
            "step": 6355
        },
        {
            "loss": 0.0734,
            "grad_norm": 1.4483171701431274,
            "learning_rate": 8e-06,
            "epoch": 2.544,
            "step": 6360
        },
        {
            "loss": 0.0777,
            "grad_norm": 1.2853431701660156,
            "learning_rate": 8e-06,
            "epoch": 2.5460000000000003,
            "step": 6365
        },
        {
            "loss": 0.0721,
            "grad_norm": 1.9787815809249878,
            "learning_rate": 8e-06,
            "epoch": 2.548,
            "step": 6370
        },
        {
            "loss": 0.0702,
            "grad_norm": 1.5077825784683228,
            "learning_rate": 8e-06,
            "epoch": 2.55,
            "step": 6375
        },
        {
            "loss": 0.0886,
            "grad_norm": 1.8213099241256714,
            "learning_rate": 8e-06,
            "epoch": 2.552,
            "step": 6380
        },
        {
            "loss": 0.0628,
            "grad_norm": 2.2267274856567383,
            "learning_rate": 8e-06,
            "epoch": 2.5540000000000003,
            "step": 6385
        },
        {
            "loss": 0.0814,
            "grad_norm": 1.660213828086853,
            "learning_rate": 8e-06,
            "epoch": 2.556,
            "step": 6390
        },
        {
            "loss": 0.0633,
            "grad_norm": 1.6631474494934082,
            "learning_rate": 8e-06,
            "epoch": 2.558,
            "step": 6395
        },
        {
            "loss": 0.0836,
            "grad_norm": 5.124907493591309,
            "learning_rate": 8e-06,
            "epoch": 2.56,
            "step": 6400
        },
        {
            "loss": 0.0833,
            "grad_norm": 1.7845135927200317,
            "learning_rate": 8e-06,
            "epoch": 2.5620000000000003,
            "step": 6405
        },
        {
            "loss": 0.0621,
            "grad_norm": 2.107532501220703,
            "learning_rate": 8e-06,
            "epoch": 2.564,
            "step": 6410
        },
        {
            "loss": 0.0851,
            "grad_norm": 1.7203911542892456,
            "learning_rate": 8e-06,
            "epoch": 2.566,
            "step": 6415
        },
        {
            "loss": 0.0735,
            "grad_norm": 1.7149648666381836,
            "learning_rate": 8e-06,
            "epoch": 2.568,
            "step": 6420
        },
        {
            "loss": 0.0676,
            "grad_norm": 1.755204677581787,
            "learning_rate": 8e-06,
            "epoch": 2.57,
            "step": 6425
        },
        {
            "loss": 0.0605,
            "grad_norm": 2.1887528896331787,
            "learning_rate": 8e-06,
            "epoch": 2.572,
            "step": 6430
        },
        {
            "loss": 0.0745,
            "grad_norm": 1.1531474590301514,
            "learning_rate": 8e-06,
            "epoch": 2.574,
            "step": 6435
        },
        {
            "loss": 0.0765,
            "grad_norm": 1.5162715911865234,
            "learning_rate": 8e-06,
            "epoch": 2.576,
            "step": 6440
        },
        {
            "loss": 0.0701,
            "grad_norm": 1.8207167387008667,
            "learning_rate": 8e-06,
            "epoch": 2.578,
            "step": 6445
        },
        {
            "loss": 0.0617,
            "grad_norm": 1.6479531526565552,
            "learning_rate": 8e-06,
            "epoch": 2.58,
            "step": 6450
        },
        {
            "loss": 0.0569,
            "grad_norm": 1.0048418045043945,
            "learning_rate": 8e-06,
            "epoch": 2.582,
            "step": 6455
        },
        {
            "loss": 0.0592,
            "grad_norm": 1.3792476654052734,
            "learning_rate": 8e-06,
            "epoch": 2.584,
            "step": 6460
        },
        {
            "loss": 0.0832,
            "grad_norm": 2.832638740539551,
            "learning_rate": 8e-06,
            "epoch": 2.586,
            "step": 6465
        },
        {
            "loss": 0.0825,
            "grad_norm": 1.3427882194519043,
            "learning_rate": 8e-06,
            "epoch": 2.588,
            "step": 6470
        },
        {
            "loss": 0.0541,
            "grad_norm": 2.770066976547241,
            "learning_rate": 8e-06,
            "epoch": 2.59,
            "step": 6475
        },
        {
            "loss": 0.0567,
            "grad_norm": 1.5984609127044678,
            "learning_rate": 8e-06,
            "epoch": 2.592,
            "step": 6480
        },
        {
            "loss": 0.0737,
            "grad_norm": 1.6586003303527832,
            "learning_rate": 8e-06,
            "epoch": 2.594,
            "step": 6485
        },
        {
            "loss": 0.0608,
            "grad_norm": 1.4890666007995605,
            "learning_rate": 8e-06,
            "epoch": 2.596,
            "step": 6490
        },
        {
            "loss": 0.0783,
            "grad_norm": 2.52177095413208,
            "learning_rate": 8e-06,
            "epoch": 2.598,
            "step": 6495
        },
        {
            "loss": 0.0605,
            "grad_norm": 0.9725523591041565,
            "learning_rate": 8e-06,
            "epoch": 2.6,
            "step": 6500
        },
        {
            "loss": 0.0601,
            "grad_norm": 1.575479507446289,
            "learning_rate": 8e-06,
            "epoch": 2.602,
            "step": 6505
        },
        {
            "loss": 0.0652,
            "grad_norm": 5.091175079345703,
            "learning_rate": 8e-06,
            "epoch": 2.604,
            "step": 6510
        },
        {
            "loss": 0.0698,
            "grad_norm": 0.9361104965209961,
            "learning_rate": 8e-06,
            "epoch": 2.606,
            "step": 6515
        },
        {
            "loss": 0.0607,
            "grad_norm": 1.5897740125656128,
            "learning_rate": 8e-06,
            "epoch": 2.608,
            "step": 6520
        },
        {
            "loss": 0.064,
            "grad_norm": 1.5193196535110474,
            "learning_rate": 8e-06,
            "epoch": 2.61,
            "step": 6525
        },
        {
            "loss": 0.0624,
            "grad_norm": 1.6479572057724,
            "learning_rate": 8e-06,
            "epoch": 2.612,
            "step": 6530
        },
        {
            "loss": 0.0676,
            "grad_norm": 1.5803968906402588,
            "learning_rate": 8e-06,
            "epoch": 2.614,
            "step": 6535
        },
        {
            "loss": 0.0671,
            "grad_norm": 1.9785692691802979,
            "learning_rate": 8e-06,
            "epoch": 2.616,
            "step": 6540
        },
        {
            "loss": 0.0607,
            "grad_norm": 1.244495153427124,
            "learning_rate": 8e-06,
            "epoch": 2.618,
            "step": 6545
        },
        {
            "loss": 0.0711,
            "grad_norm": 1.9103542566299438,
            "learning_rate": 8e-06,
            "epoch": 2.62,
            "step": 6550
        },
        {
            "loss": 0.0789,
            "grad_norm": 1.079941749572754,
            "learning_rate": 8e-06,
            "epoch": 2.622,
            "step": 6555
        },
        {
            "loss": 0.0775,
            "grad_norm": 2.0589497089385986,
            "learning_rate": 8e-06,
            "epoch": 2.624,
            "step": 6560
        },
        {
            "loss": 0.0631,
            "grad_norm": 2.1336958408355713,
            "learning_rate": 8e-06,
            "epoch": 2.626,
            "step": 6565
        },
        {
            "loss": 0.0568,
            "grad_norm": 0.8881664276123047,
            "learning_rate": 8e-06,
            "epoch": 2.628,
            "step": 6570
        },
        {
            "loss": 0.0677,
            "grad_norm": 1.7090575695037842,
            "learning_rate": 8e-06,
            "epoch": 2.63,
            "step": 6575
        },
        {
            "loss": 0.0809,
            "grad_norm": 1.9867650270462036,
            "learning_rate": 8e-06,
            "epoch": 2.632,
            "step": 6580
        },
        {
            "loss": 0.0811,
            "grad_norm": 2.478883743286133,
            "learning_rate": 8e-06,
            "epoch": 2.634,
            "step": 6585
        },
        {
            "loss": 0.1021,
            "grad_norm": 1.811302661895752,
            "learning_rate": 8e-06,
            "epoch": 2.636,
            "step": 6590
        },
        {
            "loss": 0.0556,
            "grad_norm": 1.1566795110702515,
            "learning_rate": 8e-06,
            "epoch": 2.638,
            "step": 6595
        },
        {
            "loss": 0.0693,
            "grad_norm": 1.370473027229309,
            "learning_rate": 8e-06,
            "epoch": 2.64,
            "step": 6600
        },
        {
            "eval_loss": 0.08131863921880722,
            "eval_f1": 0.7771747323986131,
            "eval_recall": 0.8123227229751024,
            "eval_accuracy": 0.9710661147300752,
            "eval_precision": 0.744942196531792,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6600173460537727,
                    "recall": 0.7402723735408561,
                    "f1-score": 0.69784502521779,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.699748743718593,
                    "recall": 0.6358447488584474,
                    "f1-score": 0.6662679425837321,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8433385992627699,
                    "recall": 0.9114968696642003,
                    "f1-score": 0.87609409190372,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5404944586530265,
                    "recall": 0.6831896551724138,
                    "f1-score": 0.6035221323179439,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.744942196531792,
                    "recall": 0.8123227229751024,
                    "f1-score": 0.7771747323986131,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6858997869220405,
                    "recall": 0.7427009118089793,
                    "f1-score": 0.7109322980057965,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7495348923227463,
                    "recall": 0.8123227229751024,
                    "f1-score": 0.7783956163517115,
                    "support": 6346
                }
            },
            "eval_runtime": 4.3019,
            "eval_samples_per_second": 952.136,
            "eval_steps_per_second": 7.439,
            "epoch": 2.64,
            "step": 6600
        },
        {
            "loss": 0.0598,
            "grad_norm": 1.1263710260391235,
            "learning_rate": 8e-06,
            "epoch": 2.642,
            "step": 6605
        },
        {
            "loss": 0.0566,
            "grad_norm": 1.1804805994033813,
            "learning_rate": 8e-06,
            "epoch": 2.644,
            "step": 6610
        },
        {
            "loss": 0.1001,
            "grad_norm": 2.0802574157714844,
            "learning_rate": 8e-06,
            "epoch": 2.646,
            "step": 6615
        },
        {
            "loss": 0.0766,
            "grad_norm": 1.781795859336853,
            "learning_rate": 8e-06,
            "epoch": 2.648,
            "step": 6620
        },
        {
            "loss": 0.0683,
            "grad_norm": 1.4637380838394165,
            "learning_rate": 8e-06,
            "epoch": 2.65,
            "step": 6625
        },
        {
            "loss": 0.0628,
            "grad_norm": 1.4133729934692383,
            "learning_rate": 8e-06,
            "epoch": 2.652,
            "step": 6630
        },
        {
            "loss": 0.0639,
            "grad_norm": 2.2269234657287598,
            "learning_rate": 8e-06,
            "epoch": 2.654,
            "step": 6635
        },
        {
            "loss": 0.0557,
            "grad_norm": 1.9096084833145142,
            "learning_rate": 8e-06,
            "epoch": 2.656,
            "step": 6640
        },
        {
            "loss": 0.0843,
            "grad_norm": 1.6075165271759033,
            "learning_rate": 8e-06,
            "epoch": 2.658,
            "step": 6645
        },
        {
            "loss": 0.0582,
            "grad_norm": 2.06548810005188,
            "learning_rate": 8e-06,
            "epoch": 2.66,
            "step": 6650
        },
        {
            "loss": 0.0641,
            "grad_norm": 0.9705261588096619,
            "learning_rate": 8e-06,
            "epoch": 2.662,
            "step": 6655
        },
        {
            "loss": 0.0691,
            "grad_norm": 0.7832489609718323,
            "learning_rate": 8e-06,
            "epoch": 2.664,
            "step": 6660
        },
        {
            "loss": 0.0871,
            "grad_norm": 1.8046834468841553,
            "learning_rate": 8e-06,
            "epoch": 2.666,
            "step": 6665
        },
        {
            "loss": 0.0678,
            "grad_norm": 3.309705972671509,
            "learning_rate": 8e-06,
            "epoch": 2.668,
            "step": 6670
        },
        {
            "loss": 0.0572,
            "grad_norm": 1.459825038909912,
            "learning_rate": 8e-06,
            "epoch": 2.67,
            "step": 6675
        },
        {
            "loss": 0.0888,
            "grad_norm": 2.072387218475342,
            "learning_rate": 8e-06,
            "epoch": 2.672,
            "step": 6680
        },
        {
            "loss": 0.0765,
            "grad_norm": 1.5624781847000122,
            "learning_rate": 8e-06,
            "epoch": 2.674,
            "step": 6685
        },
        {
            "loss": 0.0589,
            "grad_norm": 1.4673558473587036,
            "learning_rate": 8e-06,
            "epoch": 2.676,
            "step": 6690
        },
        {
            "loss": 0.0874,
            "grad_norm": 2.3059046268463135,
            "learning_rate": 8e-06,
            "epoch": 2.678,
            "step": 6695
        },
        {
            "loss": 0.0813,
            "grad_norm": 2.3486928939819336,
            "learning_rate": 8e-06,
            "epoch": 2.68,
            "step": 6700
        },
        {
            "loss": 0.0773,
            "grad_norm": 1.9315897226333618,
            "learning_rate": 8e-06,
            "epoch": 2.682,
            "step": 6705
        },
        {
            "loss": 0.0886,
            "grad_norm": 2.2492241859436035,
            "learning_rate": 8e-06,
            "epoch": 2.684,
            "step": 6710
        },
        {
            "loss": 0.0787,
            "grad_norm": 0.9510430097579956,
            "learning_rate": 8e-06,
            "epoch": 2.686,
            "step": 6715
        },
        {
            "loss": 0.0652,
            "grad_norm": 1.8755972385406494,
            "learning_rate": 8e-06,
            "epoch": 2.6879999999999997,
            "step": 6720
        },
        {
            "loss": 0.0702,
            "grad_norm": 1.5175440311431885,
            "learning_rate": 8e-06,
            "epoch": 2.69,
            "step": 6725
        },
        {
            "loss": 0.0701,
            "grad_norm": 2.1031503677368164,
            "learning_rate": 8e-06,
            "epoch": 2.692,
            "step": 6730
        },
        {
            "loss": 0.0695,
            "grad_norm": 2.0955793857574463,
            "learning_rate": 8e-06,
            "epoch": 2.694,
            "step": 6735
        },
        {
            "loss": 0.0691,
            "grad_norm": 5.77532958984375,
            "learning_rate": 8e-06,
            "epoch": 2.6959999999999997,
            "step": 6740
        },
        {
            "loss": 0.0604,
            "grad_norm": 1.6561795473098755,
            "learning_rate": 8e-06,
            "epoch": 2.698,
            "step": 6745
        },
        {
            "loss": 0.07,
            "grad_norm": 1.2469795942306519,
            "learning_rate": 8e-06,
            "epoch": 2.7,
            "step": 6750
        },
        {
            "loss": 0.0758,
            "grad_norm": 3.5328822135925293,
            "learning_rate": 8e-06,
            "epoch": 2.702,
            "step": 6755
        },
        {
            "loss": 0.0521,
            "grad_norm": 1.1253048181533813,
            "learning_rate": 8e-06,
            "epoch": 2.7039999999999997,
            "step": 6760
        },
        {
            "loss": 0.0624,
            "grad_norm": 1.583511471748352,
            "learning_rate": 8e-06,
            "epoch": 2.706,
            "step": 6765
        },
        {
            "loss": 0.0662,
            "grad_norm": 1.6158533096313477,
            "learning_rate": 8e-06,
            "epoch": 2.708,
            "step": 6770
        },
        {
            "loss": 0.0587,
            "grad_norm": 1.3283190727233887,
            "learning_rate": 8e-06,
            "epoch": 2.71,
            "step": 6775
        },
        {
            "loss": 0.0656,
            "grad_norm": 2.294694662094116,
            "learning_rate": 8e-06,
            "epoch": 2.7119999999999997,
            "step": 6780
        },
        {
            "loss": 0.0544,
            "grad_norm": 2.819467782974243,
            "learning_rate": 8e-06,
            "epoch": 2.714,
            "step": 6785
        },
        {
            "loss": 0.0634,
            "grad_norm": 1.4729505777359009,
            "learning_rate": 8e-06,
            "epoch": 2.716,
            "step": 6790
        },
        {
            "loss": 0.0792,
            "grad_norm": 2.3337042331695557,
            "learning_rate": 8e-06,
            "epoch": 2.718,
            "step": 6795
        },
        {
            "loss": 0.0804,
            "grad_norm": 3.6622157096862793,
            "learning_rate": 8e-06,
            "epoch": 2.7199999999999998,
            "step": 6800
        },
        {
            "loss": 0.06,
            "grad_norm": 2.14294171333313,
            "learning_rate": 8e-06,
            "epoch": 2.722,
            "step": 6805
        },
        {
            "loss": 0.066,
            "grad_norm": 4.532078266143799,
            "learning_rate": 8e-06,
            "epoch": 2.724,
            "step": 6810
        },
        {
            "loss": 0.0787,
            "grad_norm": 5.753841876983643,
            "learning_rate": 8e-06,
            "epoch": 2.726,
            "step": 6815
        },
        {
            "loss": 0.0642,
            "grad_norm": 1.5978223085403442,
            "learning_rate": 8e-06,
            "epoch": 2.7279999999999998,
            "step": 6820
        },
        {
            "loss": 0.0508,
            "grad_norm": 2.049849033355713,
            "learning_rate": 8e-06,
            "epoch": 2.73,
            "step": 6825
        },
        {
            "loss": 0.0705,
            "grad_norm": 2.0862483978271484,
            "learning_rate": 8e-06,
            "epoch": 2.732,
            "step": 6830
        },
        {
            "loss": 0.0756,
            "grad_norm": 2.5848159790039062,
            "learning_rate": 8e-06,
            "epoch": 2.734,
            "step": 6835
        },
        {
            "loss": 0.0634,
            "grad_norm": 2.1792469024658203,
            "learning_rate": 8e-06,
            "epoch": 2.7359999999999998,
            "step": 6840
        },
        {
            "loss": 0.0667,
            "grad_norm": 1.5471874475479126,
            "learning_rate": 8e-06,
            "epoch": 2.738,
            "step": 6845
        },
        {
            "loss": 0.0568,
            "grad_norm": 2.0973401069641113,
            "learning_rate": 8e-06,
            "epoch": 2.74,
            "step": 6850
        },
        {
            "loss": 0.0822,
            "grad_norm": 3.117375612258911,
            "learning_rate": 8e-06,
            "epoch": 2.742,
            "step": 6855
        },
        {
            "loss": 0.0633,
            "grad_norm": 1.1974657773971558,
            "learning_rate": 8e-06,
            "epoch": 2.7439999999999998,
            "step": 6860
        },
        {
            "loss": 0.0638,
            "grad_norm": 2.1911661624908447,
            "learning_rate": 8e-06,
            "epoch": 2.746,
            "step": 6865
        },
        {
            "loss": 0.0664,
            "grad_norm": 1.7018791437149048,
            "learning_rate": 8e-06,
            "epoch": 2.748,
            "step": 6870
        },
        {
            "loss": 0.063,
            "grad_norm": 1.8112157583236694,
            "learning_rate": 8e-06,
            "epoch": 2.75,
            "step": 6875
        },
        {
            "loss": 0.083,
            "grad_norm": 2.338540554046631,
            "learning_rate": 8e-06,
            "epoch": 2.752,
            "step": 6880
        },
        {
            "loss": 0.0746,
            "grad_norm": 1.5950676202774048,
            "learning_rate": 8e-06,
            "epoch": 2.754,
            "step": 6885
        },
        {
            "loss": 0.0636,
            "grad_norm": 1.8432954549789429,
            "learning_rate": 8e-06,
            "epoch": 2.7560000000000002,
            "step": 6890
        },
        {
            "loss": 0.069,
            "grad_norm": 1.8332206010818481,
            "learning_rate": 8e-06,
            "epoch": 2.758,
            "step": 6895
        },
        {
            "loss": 0.0638,
            "grad_norm": 2.0233993530273438,
            "learning_rate": 8e-06,
            "epoch": 2.76,
            "step": 6900
        },
        {
            "eval_loss": 0.07947058230638504,
            "eval_f1": 0.7794312426957538,
            "eval_recall": 0.7882130475890324,
            "eval_accuracy": 0.9728738140315973,
            "eval_precision": 0.7708429650177223,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6630824372759857,
                    "recall": 0.7198443579766537,
                    "f1-score": 0.6902985074626866,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6744186046511628,
                    "recall": 0.6621004566210046,
                    "f1-score": 0.6682027649769585,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8712184290868721,
                    "recall": 0.8932840068298236,
                    "f1-score": 0.8821132499648728,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5967032967032967,
                    "recall": 0.5851293103448276,
                    "f1-score": 0.5908596300326442,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7708429650177223,
                    "recall": 0.7882130475890324,
                    "f1-score": 0.7794312426957538,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.7013556919293293,
                    "recall": 0.7150895329430773,
                    "f1-score": 0.7078685381092905,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7701925090365679,
                    "recall": 0.7882130475890324,
                    "f1-score": 0.7789215544970556,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4765,
            "eval_samples_per_second": 915.004,
            "eval_steps_per_second": 7.148,
            "epoch": 2.76,
            "step": 6900
        },
        {
            "loss": 0.0649,
            "grad_norm": 1.2920796871185303,
            "learning_rate": 8e-06,
            "epoch": 2.762,
            "step": 6905
        },
        {
            "loss": 0.0756,
            "grad_norm": 2.305264472961426,
            "learning_rate": 8e-06,
            "epoch": 2.7640000000000002,
            "step": 6910
        },
        {
            "loss": 0.0716,
            "grad_norm": 1.597629427909851,
            "learning_rate": 8e-06,
            "epoch": 2.766,
            "step": 6915
        },
        {
            "loss": 0.0764,
            "grad_norm": 1.436596155166626,
            "learning_rate": 8e-06,
            "epoch": 2.768,
            "step": 6920
        },
        {
            "loss": 0.0637,
            "grad_norm": 1.7159010171890259,
            "learning_rate": 8e-06,
            "epoch": 2.77,
            "step": 6925
        },
        {
            "loss": 0.0537,
            "grad_norm": 0.8144262433052063,
            "learning_rate": 8e-06,
            "epoch": 2.7720000000000002,
            "step": 6930
        },
        {
            "loss": 0.0577,
            "grad_norm": 0.9119420647621155,
            "learning_rate": 8e-06,
            "epoch": 2.774,
            "step": 6935
        },
        {
            "loss": 0.0805,
            "grad_norm": 1.954416036605835,
            "learning_rate": 8e-06,
            "epoch": 2.776,
            "step": 6940
        },
        {
            "loss": 0.0776,
            "grad_norm": 1.7917485237121582,
            "learning_rate": 8e-06,
            "epoch": 2.778,
            "step": 6945
        },
        {
            "loss": 0.0613,
            "grad_norm": 2.6071135997772217,
            "learning_rate": 8e-06,
            "epoch": 2.7800000000000002,
            "step": 6950
        },
        {
            "loss": 0.0626,
            "grad_norm": 1.6080430746078491,
            "learning_rate": 8e-06,
            "epoch": 2.782,
            "step": 6955
        },
        {
            "loss": 0.0769,
            "grad_norm": 2.145181655883789,
            "learning_rate": 8e-06,
            "epoch": 2.784,
            "step": 6960
        },
        {
            "loss": 0.0706,
            "grad_norm": 1.9656941890716553,
            "learning_rate": 8e-06,
            "epoch": 2.786,
            "step": 6965
        },
        {
            "loss": 0.0594,
            "grad_norm": 2.045661211013794,
            "learning_rate": 8e-06,
            "epoch": 2.7880000000000003,
            "step": 6970
        },
        {
            "loss": 0.0561,
            "grad_norm": 2.600101947784424,
            "learning_rate": 8e-06,
            "epoch": 2.79,
            "step": 6975
        },
        {
            "loss": 0.039,
            "grad_norm": 1.5662219524383545,
            "learning_rate": 8e-06,
            "epoch": 2.792,
            "step": 6980
        },
        {
            "loss": 0.0711,
            "grad_norm": 2.4349420070648193,
            "learning_rate": 8e-06,
            "epoch": 2.794,
            "step": 6985
        },
        {
            "loss": 0.0732,
            "grad_norm": 1.617434024810791,
            "learning_rate": 8e-06,
            "epoch": 2.7960000000000003,
            "step": 6990
        },
        {
            "loss": 0.0753,
            "grad_norm": 2.030320644378662,
            "learning_rate": 8e-06,
            "epoch": 2.798,
            "step": 6995
        },
        {
            "loss": 0.0602,
            "grad_norm": 2.2038543224334717,
            "learning_rate": 8e-06,
            "epoch": 2.8,
            "step": 7000
        },
        {
            "loss": 0.0593,
            "grad_norm": 2.330838918685913,
            "learning_rate": 8e-06,
            "epoch": 2.802,
            "step": 7005
        },
        {
            "loss": 0.0564,
            "grad_norm": 3.2118215560913086,
            "learning_rate": 8e-06,
            "epoch": 2.8040000000000003,
            "step": 7010
        },
        {
            "loss": 0.0525,
            "grad_norm": 1.3071149587631226,
            "learning_rate": 8e-06,
            "epoch": 2.806,
            "step": 7015
        },
        {
            "loss": 0.0701,
            "grad_norm": 1.7662557363510132,
            "learning_rate": 8e-06,
            "epoch": 2.808,
            "step": 7020
        },
        {
            "loss": 0.049,
            "grad_norm": 1.4329850673675537,
            "learning_rate": 8e-06,
            "epoch": 2.81,
            "step": 7025
        },
        {
            "loss": 0.0668,
            "grad_norm": 1.9767951965332031,
            "learning_rate": 8e-06,
            "epoch": 2.8120000000000003,
            "step": 7030
        },
        {
            "loss": 0.0794,
            "grad_norm": 2.6724774837493896,
            "learning_rate": 8e-06,
            "epoch": 2.814,
            "step": 7035
        },
        {
            "loss": 0.0854,
            "grad_norm": 2.972694158554077,
            "learning_rate": 8e-06,
            "epoch": 2.816,
            "step": 7040
        },
        {
            "loss": 0.0808,
            "grad_norm": 5.6355695724487305,
            "learning_rate": 8e-06,
            "epoch": 2.818,
            "step": 7045
        },
        {
            "loss": 0.0905,
            "grad_norm": 1.6163212060928345,
            "learning_rate": 8e-06,
            "epoch": 2.82,
            "step": 7050
        },
        {
            "loss": 0.0849,
            "grad_norm": 1.2994393110275269,
            "learning_rate": 8e-06,
            "epoch": 2.822,
            "step": 7055
        },
        {
            "loss": 0.0573,
            "grad_norm": 1.4245305061340332,
            "learning_rate": 8e-06,
            "epoch": 2.824,
            "step": 7060
        },
        {
            "loss": 0.0807,
            "grad_norm": 1.864383339881897,
            "learning_rate": 8e-06,
            "epoch": 2.826,
            "step": 7065
        },
        {
            "loss": 0.0705,
            "grad_norm": 1.8631558418273926,
            "learning_rate": 8e-06,
            "epoch": 2.828,
            "step": 7070
        },
        {
            "loss": 0.0638,
            "grad_norm": 1.7696099281311035,
            "learning_rate": 8e-06,
            "epoch": 2.83,
            "step": 7075
        },
        {
            "loss": 0.055,
            "grad_norm": 1.5155752897262573,
            "learning_rate": 8e-06,
            "epoch": 2.832,
            "step": 7080
        },
        {
            "loss": 0.071,
            "grad_norm": 2.0386011600494385,
            "learning_rate": 8e-06,
            "epoch": 2.834,
            "step": 7085
        },
        {
            "loss": 0.0542,
            "grad_norm": 1.5361720323562622,
            "learning_rate": 8e-06,
            "epoch": 2.836,
            "step": 7090
        },
        {
            "loss": 0.0765,
            "grad_norm": 2.0638694763183594,
            "learning_rate": 8e-06,
            "epoch": 2.838,
            "step": 7095
        },
        {
            "loss": 0.0818,
            "grad_norm": 1.6572251319885254,
            "learning_rate": 8e-06,
            "epoch": 2.84,
            "step": 7100
        },
        {
            "loss": 0.0622,
            "grad_norm": 2.1133289337158203,
            "learning_rate": 8e-06,
            "epoch": 2.842,
            "step": 7105
        },
        {
            "loss": 0.0624,
            "grad_norm": 1.720784068107605,
            "learning_rate": 8e-06,
            "epoch": 2.844,
            "step": 7110
        },
        {
            "loss": 0.071,
            "grad_norm": 2.227137804031372,
            "learning_rate": 8e-06,
            "epoch": 2.846,
            "step": 7115
        },
        {
            "loss": 0.0626,
            "grad_norm": 2.590061664581299,
            "learning_rate": 8e-06,
            "epoch": 2.848,
            "step": 7120
        },
        {
            "loss": 0.0869,
            "grad_norm": 2.8977808952331543,
            "learning_rate": 8e-06,
            "epoch": 2.85,
            "step": 7125
        },
        {
            "loss": 0.0925,
            "grad_norm": 1.1035264730453491,
            "learning_rate": 8e-06,
            "epoch": 2.852,
            "step": 7130
        },
        {
            "loss": 0.0788,
            "grad_norm": 2.9677250385284424,
            "learning_rate": 8e-06,
            "epoch": 2.854,
            "step": 7135
        },
        {
            "loss": 0.0933,
            "grad_norm": 2.3727002143859863,
            "learning_rate": 8e-06,
            "epoch": 2.856,
            "step": 7140
        },
        {
            "loss": 0.0692,
            "grad_norm": 1.4957131147384644,
            "learning_rate": 8e-06,
            "epoch": 2.858,
            "step": 7145
        },
        {
            "loss": 0.0799,
            "grad_norm": 2.0381662845611572,
            "learning_rate": 8e-06,
            "epoch": 2.86,
            "step": 7150
        },
        {
            "loss": 0.0602,
            "grad_norm": 1.1913000345230103,
            "learning_rate": 8e-06,
            "epoch": 2.862,
            "step": 7155
        },
        {
            "loss": 0.0553,
            "grad_norm": 1.827811360359192,
            "learning_rate": 8e-06,
            "epoch": 2.864,
            "step": 7160
        },
        {
            "loss": 0.0638,
            "grad_norm": 1.313844919204712,
            "learning_rate": 8e-06,
            "epoch": 2.866,
            "step": 7165
        },
        {
            "loss": 0.0794,
            "grad_norm": 1.6958441734313965,
            "learning_rate": 8e-06,
            "epoch": 2.868,
            "step": 7170
        },
        {
            "loss": 0.0669,
            "grad_norm": 2.3618381023406982,
            "learning_rate": 8e-06,
            "epoch": 2.87,
            "step": 7175
        },
        {
            "loss": 0.0839,
            "grad_norm": 1.4780547618865967,
            "learning_rate": 8e-06,
            "epoch": 2.872,
            "step": 7180
        },
        {
            "loss": 0.0732,
            "grad_norm": 2.7169899940490723,
            "learning_rate": 8e-06,
            "epoch": 2.874,
            "step": 7185
        },
        {
            "loss": 0.0681,
            "grad_norm": 1.8775625228881836,
            "learning_rate": 8e-06,
            "epoch": 2.876,
            "step": 7190
        },
        {
            "loss": 0.0851,
            "grad_norm": 2.692686080932617,
            "learning_rate": 8e-06,
            "epoch": 2.878,
            "step": 7195
        },
        {
            "loss": 0.0735,
            "grad_norm": 1.9736157655715942,
            "learning_rate": 8e-06,
            "epoch": 2.88,
            "step": 7200
        },
        {
            "eval_loss": 0.07939465343952179,
            "eval_f1": 0.7828217101737732,
            "eval_recall": 0.8057043807122597,
            "eval_accuracy": 0.9727401084619581,
            "eval_precision": 0.7612029179693316,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6413398692810458,
                    "recall": 0.7636186770428015,
                    "f1-score": 0.697158081705151,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6558659217877095,
                    "recall": 0.6700913242009132,
                    "f1-score": 0.6629023150762281,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8723640399556049,
                    "recall": 0.8947068867387592,
                    "f1-score": 0.8833942118572632,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.6006036217303823,
                    "recall": 0.6433189655172413,
                    "f1-score": 0.6212278876170655,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7612029179693316,
                    "recall": 0.8057043807122597,
                    "f1-score": 0.7828217101737732,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6925433631886856,
                    "recall": 0.7429339633749288,
                    "f1-score": 0.716170624063927,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7653141081747146,
                    "recall": 0.8057043807122597,
                    "f1-score": 0.7844512568822456,
                    "support": 6346
                }
            },
            "eval_runtime": 4.5592,
            "eval_samples_per_second": 898.395,
            "eval_steps_per_second": 7.019,
            "epoch": 2.88,
            "step": 7200
        },
        {
            "loss": 0.0722,
            "grad_norm": 1.8013473749160767,
            "learning_rate": 8e-06,
            "epoch": 2.882,
            "step": 7205
        },
        {
            "loss": 0.0642,
            "grad_norm": 1.615976095199585,
            "learning_rate": 8e-06,
            "epoch": 2.884,
            "step": 7210
        },
        {
            "loss": 0.0868,
            "grad_norm": 1.9779208898544312,
            "learning_rate": 8e-06,
            "epoch": 2.886,
            "step": 7215
        },
        {
            "loss": 0.0701,
            "grad_norm": 2.2371153831481934,
            "learning_rate": 8e-06,
            "epoch": 2.888,
            "step": 7220
        },
        {
            "loss": 0.0681,
            "grad_norm": 1.72183096408844,
            "learning_rate": 8e-06,
            "epoch": 2.89,
            "step": 7225
        },
        {
            "loss": 0.0551,
            "grad_norm": 1.8114104270935059,
            "learning_rate": 8e-06,
            "epoch": 2.892,
            "step": 7230
        },
        {
            "loss": 0.0806,
            "grad_norm": 1.4609500169754028,
            "learning_rate": 8e-06,
            "epoch": 2.894,
            "step": 7235
        },
        {
            "loss": 0.077,
            "grad_norm": 2.6986920833587646,
            "learning_rate": 8e-06,
            "epoch": 2.896,
            "step": 7240
        },
        {
            "loss": 0.0782,
            "grad_norm": 1.3295527696609497,
            "learning_rate": 8e-06,
            "epoch": 2.898,
            "step": 7245
        },
        {
            "loss": 0.0641,
            "grad_norm": 2.800112009048462,
            "learning_rate": 8e-06,
            "epoch": 2.9,
            "step": 7250
        },
        {
            "loss": 0.0803,
            "grad_norm": 1.050598382949829,
            "learning_rate": 8e-06,
            "epoch": 2.902,
            "step": 7255
        },
        {
            "loss": 0.0644,
            "grad_norm": 1.764042854309082,
            "learning_rate": 8e-06,
            "epoch": 2.904,
            "step": 7260
        },
        {
            "loss": 0.0669,
            "grad_norm": 2.050962209701538,
            "learning_rate": 8e-06,
            "epoch": 2.906,
            "step": 7265
        },
        {
            "loss": 0.0855,
            "grad_norm": 1.0479813814163208,
            "learning_rate": 8e-06,
            "epoch": 2.908,
            "step": 7270
        },
        {
            "loss": 0.0817,
            "grad_norm": 1.7931886911392212,
            "learning_rate": 8e-06,
            "epoch": 2.91,
            "step": 7275
        },
        {
            "loss": 0.0639,
            "grad_norm": 1.6830390691757202,
            "learning_rate": 8e-06,
            "epoch": 2.912,
            "step": 7280
        },
        {
            "loss": 0.0545,
            "grad_norm": 1.4436495304107666,
            "learning_rate": 8e-06,
            "epoch": 2.914,
            "step": 7285
        },
        {
            "loss": 0.0783,
            "grad_norm": 1.396645426750183,
            "learning_rate": 8e-06,
            "epoch": 2.916,
            "step": 7290
        },
        {
            "loss": 0.0818,
            "grad_norm": 1.763839840888977,
            "learning_rate": 8e-06,
            "epoch": 2.918,
            "step": 7295
        },
        {
            "loss": 0.0594,
            "grad_norm": 1.4163758754730225,
            "learning_rate": 8e-06,
            "epoch": 2.92,
            "step": 7300
        },
        {
            "loss": 0.0663,
            "grad_norm": 2.411884069442749,
            "learning_rate": 8e-06,
            "epoch": 2.922,
            "step": 7305
        },
        {
            "loss": 0.0585,
            "grad_norm": 2.005913019180298,
            "learning_rate": 8e-06,
            "epoch": 2.924,
            "step": 7310
        },
        {
            "loss": 0.0681,
            "grad_norm": 1.7997190952301025,
            "learning_rate": 8e-06,
            "epoch": 2.926,
            "step": 7315
        },
        {
            "loss": 0.0644,
            "grad_norm": 2.115227222442627,
            "learning_rate": 8e-06,
            "epoch": 2.928,
            "step": 7320
        },
        {
            "loss": 0.052,
            "grad_norm": 1.726792573928833,
            "learning_rate": 8e-06,
            "epoch": 2.93,
            "step": 7325
        },
        {
            "loss": 0.0564,
            "grad_norm": 1.2597509622573853,
            "learning_rate": 8e-06,
            "epoch": 2.932,
            "step": 7330
        },
        {
            "loss": 0.0653,
            "grad_norm": 1.547537922859192,
            "learning_rate": 8e-06,
            "epoch": 2.934,
            "step": 7335
        },
        {
            "loss": 0.073,
            "grad_norm": 0.6566094160079956,
            "learning_rate": 8e-06,
            "epoch": 2.936,
            "step": 7340
        },
        {
            "loss": 0.0697,
            "grad_norm": 2.9685287475585938,
            "learning_rate": 8e-06,
            "epoch": 2.9379999999999997,
            "step": 7345
        },
        {
            "loss": 0.0577,
            "grad_norm": 1.3996710777282715,
            "learning_rate": 8e-06,
            "epoch": 2.94,
            "step": 7350
        },
        {
            "loss": 0.0665,
            "grad_norm": 1.3074623346328735,
            "learning_rate": 8e-06,
            "epoch": 2.942,
            "step": 7355
        },
        {
            "loss": 0.0614,
            "grad_norm": 4.111547946929932,
            "learning_rate": 8e-06,
            "epoch": 2.944,
            "step": 7360
        },
        {
            "loss": 0.0896,
            "grad_norm": 3.2397828102111816,
            "learning_rate": 8e-06,
            "epoch": 2.9459999999999997,
            "step": 7365
        },
        {
            "loss": 0.0835,
            "grad_norm": 2.393432855606079,
            "learning_rate": 8e-06,
            "epoch": 2.948,
            "step": 7370
        },
        {
            "loss": 0.075,
            "grad_norm": 1.497036099433899,
            "learning_rate": 8e-06,
            "epoch": 2.95,
            "step": 7375
        },
        {
            "loss": 0.0566,
            "grad_norm": 1.4327598810195923,
            "learning_rate": 8e-06,
            "epoch": 2.952,
            "step": 7380
        },
        {
            "loss": 0.0751,
            "grad_norm": 3.47872257232666,
            "learning_rate": 8e-06,
            "epoch": 2.9539999999999997,
            "step": 7385
        },
        {
            "loss": 0.0752,
            "grad_norm": 1.2681224346160889,
            "learning_rate": 8e-06,
            "epoch": 2.956,
            "step": 7390
        },
        {
            "loss": 0.08,
            "grad_norm": 1.8855258226394653,
            "learning_rate": 8e-06,
            "epoch": 2.958,
            "step": 7395
        },
        {
            "loss": 0.0771,
            "grad_norm": 1.7458757162094116,
            "learning_rate": 8e-06,
            "epoch": 2.96,
            "step": 7400
        },
        {
            "loss": 0.0653,
            "grad_norm": 1.5794506072998047,
            "learning_rate": 8e-06,
            "epoch": 2.9619999999999997,
            "step": 7405
        },
        {
            "loss": 0.0662,
            "grad_norm": 1.8604092597961426,
            "learning_rate": 8e-06,
            "epoch": 2.964,
            "step": 7410
        },
        {
            "loss": 0.0812,
            "grad_norm": 2.962656259536743,
            "learning_rate": 8e-06,
            "epoch": 2.966,
            "step": 7415
        },
        {
            "loss": 0.0838,
            "grad_norm": 2.028225898742676,
            "learning_rate": 8e-06,
            "epoch": 2.968,
            "step": 7420
        },
        {
            "loss": 0.0581,
            "grad_norm": 2.1050732135772705,
            "learning_rate": 8e-06,
            "epoch": 2.9699999999999998,
            "step": 7425
        },
        {
            "loss": 0.0668,
            "grad_norm": 1.9371997117996216,
            "learning_rate": 8e-06,
            "epoch": 2.972,
            "step": 7430
        },
        {
            "loss": 0.0622,
            "grad_norm": 1.4123144149780273,
            "learning_rate": 8e-06,
            "epoch": 2.974,
            "step": 7435
        },
        {
            "loss": 0.0705,
            "grad_norm": 2.647277593612671,
            "learning_rate": 8e-06,
            "epoch": 2.976,
            "step": 7440
        },
        {
            "loss": 0.0754,
            "grad_norm": 1.4660438299179077,
            "learning_rate": 8e-06,
            "epoch": 2.9779999999999998,
            "step": 7445
        },
        {
            "loss": 0.069,
            "grad_norm": 1.704702615737915,
            "learning_rate": 8e-06,
            "epoch": 2.98,
            "step": 7450
        },
        {
            "loss": 0.0579,
            "grad_norm": 2.234325408935547,
            "learning_rate": 8e-06,
            "epoch": 2.982,
            "step": 7455
        },
        {
            "loss": 0.0602,
            "grad_norm": 1.2050659656524658,
            "learning_rate": 8e-06,
            "epoch": 2.984,
            "step": 7460
        },
        {
            "loss": 0.071,
            "grad_norm": 1.1882563829421997,
            "learning_rate": 8e-06,
            "epoch": 2.9859999999999998,
            "step": 7465
        },
        {
            "loss": 0.0774,
            "grad_norm": 1.8264572620391846,
            "learning_rate": 8e-06,
            "epoch": 2.988,
            "step": 7470
        },
        {
            "loss": 0.0758,
            "grad_norm": 2.5301897525787354,
            "learning_rate": 8e-06,
            "epoch": 2.99,
            "step": 7475
        },
        {
            "loss": 0.0698,
            "grad_norm": 1.7562788724899292,
            "learning_rate": 8e-06,
            "epoch": 2.992,
            "step": 7480
        },
        {
            "loss": 0.0823,
            "grad_norm": 1.6565687656402588,
            "learning_rate": 8e-06,
            "epoch": 2.9939999999999998,
            "step": 7485
        },
        {
            "loss": 0.0751,
            "grad_norm": 2.169358730316162,
            "learning_rate": 8e-06,
            "epoch": 2.996,
            "step": 7490
        },
        {
            "loss": 0.078,
            "grad_norm": 1.3640016317367554,
            "learning_rate": 8e-06,
            "epoch": 2.998,
            "step": 7495
        },
        {
            "loss": 0.0874,
            "grad_norm": 2.789052963256836,
            "learning_rate": 8e-06,
            "epoch": 3.0,
            "step": 7500
        },
        {
            "eval_loss": 0.0786023959517479,
            "eval_f1": 0.7818459191456902,
            "eval_recall": 0.8075953356445005,
            "eval_accuracy": 0.9727240637936014,
            "eval_precision": 0.7576877587226494,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6449752883031301,
                    "recall": 0.7616731517509727,
                    "f1-score": 0.6984834968777877,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6670454545454545,
                    "recall": 0.6700913242009132,
                    "f1-score": 0.6685649202733485,
                    "support": 876
                },
                "PER": {
                    "precision": 0.85553772070626,
                    "recall": 0.9100739897552647,
                    "f1-score": 0.8819635962493105,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5976394849785408,
                    "recall": 0.6002155172413793,
                    "f1-score": 0.5989247311827958,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7576877587226494,
                    "recall": 0.8075953356445005,
                    "f1-score": 0.7818459191456902,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.6912994871333464,
                    "recall": 0.7355134957371325,
                    "f1-score": 0.7119841861458106,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7576954628394768,
                    "recall": 0.8075953356445005,
                    "f1-score": 0.7813939698562135,
                    "support": 6346
                }
            },
            "eval_runtime": 4.3742,
            "eval_samples_per_second": 936.41,
            "eval_steps_per_second": 7.316,
            "epoch": 3.0,
            "step": 7500
        },
        {
            "loss": 0.0598,
            "grad_norm": 1.9275978803634644,
            "learning_rate": 8e-06,
            "epoch": 3.002,
            "step": 7505
        },
        {
            "loss": 0.0571,
            "grad_norm": 1.7370985746383667,
            "learning_rate": 8e-06,
            "epoch": 3.004,
            "step": 7510
        },
        {
            "loss": 0.0562,
            "grad_norm": 1.5715522766113281,
            "learning_rate": 8e-06,
            "epoch": 3.006,
            "step": 7515
        },
        {
            "loss": 0.0551,
            "grad_norm": 1.0972830057144165,
            "learning_rate": 8e-06,
            "epoch": 3.008,
            "step": 7520
        },
        {
            "loss": 0.0501,
            "grad_norm": 1.892337441444397,
            "learning_rate": 8e-06,
            "epoch": 3.01,
            "step": 7525
        },
        {
            "loss": 0.0635,
            "grad_norm": 2.049790620803833,
            "learning_rate": 8e-06,
            "epoch": 3.012,
            "step": 7530
        },
        {
            "loss": 0.0671,
            "grad_norm": 1.8435304164886475,
            "learning_rate": 8e-06,
            "epoch": 3.014,
            "step": 7535
        },
        {
            "loss": 0.0503,
            "grad_norm": 1.7112923860549927,
            "learning_rate": 8e-06,
            "epoch": 3.016,
            "step": 7540
        },
        {
            "loss": 0.0635,
            "grad_norm": 3.3512978553771973,
            "learning_rate": 8e-06,
            "epoch": 3.018,
            "step": 7545
        },
        {
            "loss": 0.0651,
            "grad_norm": 2.541895866394043,
            "learning_rate": 8e-06,
            "epoch": 3.02,
            "step": 7550
        },
        {
            "loss": 0.0522,
            "grad_norm": 1.5064723491668701,
            "learning_rate": 8e-06,
            "epoch": 3.022,
            "step": 7555
        },
        {
            "loss": 0.0649,
            "grad_norm": 1.5007935762405396,
            "learning_rate": 8e-06,
            "epoch": 3.024,
            "step": 7560
        },
        {
            "loss": 0.0605,
            "grad_norm": 1.5780285596847534,
            "learning_rate": 8e-06,
            "epoch": 3.026,
            "step": 7565
        },
        {
            "loss": 0.0587,
            "grad_norm": 1.3145517110824585,
            "learning_rate": 8e-06,
            "epoch": 3.028,
            "step": 7570
        },
        {
            "loss": 0.0802,
            "grad_norm": 2.117780923843384,
            "learning_rate": 8e-06,
            "epoch": 3.03,
            "step": 7575
        },
        {
            "loss": 0.0548,
            "grad_norm": 1.5841641426086426,
            "learning_rate": 8e-06,
            "epoch": 3.032,
            "step": 7580
        },
        {
            "loss": 0.0484,
            "grad_norm": 1.8854401111602783,
            "learning_rate": 8e-06,
            "epoch": 3.034,
            "step": 7585
        },
        {
            "loss": 0.0636,
            "grad_norm": 2.264667272567749,
            "learning_rate": 8e-06,
            "epoch": 3.036,
            "step": 7590
        },
        {
            "loss": 0.0406,
            "grad_norm": 0.8167891502380371,
            "learning_rate": 8e-06,
            "epoch": 3.038,
            "step": 7595
        },
        {
            "loss": 0.054,
            "grad_norm": 1.4835176467895508,
            "learning_rate": 8e-06,
            "epoch": 3.04,
            "step": 7600
        },
        {
            "loss": 0.0621,
            "grad_norm": 2.691655158996582,
            "learning_rate": 8e-06,
            "epoch": 3.042,
            "step": 7605
        },
        {
            "loss": 0.0547,
            "grad_norm": 2.1912128925323486,
            "learning_rate": 8e-06,
            "epoch": 3.044,
            "step": 7610
        },
        {
            "loss": 0.0568,
            "grad_norm": 1.17652428150177,
            "learning_rate": 8e-06,
            "epoch": 3.046,
            "step": 7615
        },
        {
            "loss": 0.0567,
            "grad_norm": 1.9101375341415405,
            "learning_rate": 8e-06,
            "epoch": 3.048,
            "step": 7620
        },
        {
            "loss": 0.0563,
            "grad_norm": 1.6223288774490356,
            "learning_rate": 8e-06,
            "epoch": 3.05,
            "step": 7625
        },
        {
            "loss": 0.0603,
            "grad_norm": 2.660374641418457,
            "learning_rate": 8e-06,
            "epoch": 3.052,
            "step": 7630
        },
        {
            "loss": 0.0593,
            "grad_norm": 2.1911377906799316,
            "learning_rate": 8e-06,
            "epoch": 3.054,
            "step": 7635
        },
        {
            "loss": 0.073,
            "grad_norm": 3.0745151042938232,
            "learning_rate": 8e-06,
            "epoch": 3.056,
            "step": 7640
        },
        {
            "loss": 0.0577,
            "grad_norm": 1.344785451889038,
            "learning_rate": 8e-06,
            "epoch": 3.058,
            "step": 7645
        },
        {
            "loss": 0.06,
            "grad_norm": 3.031137466430664,
            "learning_rate": 8e-06,
            "epoch": 3.06,
            "step": 7650
        },
        {
            "loss": 0.0617,
            "grad_norm": 1.4542783498764038,
            "learning_rate": 8e-06,
            "epoch": 3.062,
            "step": 7655
        },
        {
            "loss": 0.0518,
            "grad_norm": 1.4282457828521729,
            "learning_rate": 8e-06,
            "epoch": 3.064,
            "step": 7660
        },
        {
            "loss": 0.0667,
            "grad_norm": 1.4535874128341675,
            "learning_rate": 8e-06,
            "epoch": 3.066,
            "step": 7665
        },
        {
            "loss": 0.0504,
            "grad_norm": 1.3522804975509644,
            "learning_rate": 8e-06,
            "epoch": 3.068,
            "step": 7670
        },
        {
            "loss": 0.0571,
            "grad_norm": 2.0311501026153564,
            "learning_rate": 8e-06,
            "epoch": 3.07,
            "step": 7675
        },
        {
            "loss": 0.0427,
            "grad_norm": 1.362892985343933,
            "learning_rate": 8e-06,
            "epoch": 3.072,
            "step": 7680
        },
        {
            "loss": 0.0543,
            "grad_norm": 0.9493785500526428,
            "learning_rate": 8e-06,
            "epoch": 3.074,
            "step": 7685
        },
        {
            "loss": 0.0571,
            "grad_norm": 1.306753396987915,
            "learning_rate": 8e-06,
            "epoch": 3.076,
            "step": 7690
        },
        {
            "loss": 0.0508,
            "grad_norm": 1.4821546077728271,
            "learning_rate": 8e-06,
            "epoch": 3.078,
            "step": 7695
        },
        {
            "loss": 0.0493,
            "grad_norm": 1.13963782787323,
            "learning_rate": 8e-06,
            "epoch": 3.08,
            "step": 7700
        },
        {
            "loss": 0.051,
            "grad_norm": 2.0684919357299805,
            "learning_rate": 8e-06,
            "epoch": 3.082,
            "step": 7705
        },
        {
            "loss": 0.0599,
            "grad_norm": 2.393254280090332,
            "learning_rate": 8e-06,
            "epoch": 3.084,
            "step": 7710
        },
        {
            "loss": 0.0537,
            "grad_norm": 1.5467740297317505,
            "learning_rate": 8e-06,
            "epoch": 3.086,
            "step": 7715
        },
        {
            "loss": 0.0513,
            "grad_norm": 2.0061841011047363,
            "learning_rate": 8e-06,
            "epoch": 3.088,
            "step": 7720
        },
        {
            "loss": 0.0558,
            "grad_norm": 1.7230349779129028,
            "learning_rate": 8e-06,
            "epoch": 3.09,
            "step": 7725
        },
        {
            "loss": 0.0763,
            "grad_norm": 2.8252148628234863,
            "learning_rate": 8e-06,
            "epoch": 3.092,
            "step": 7730
        },
        {
            "loss": 0.0551,
            "grad_norm": 0.8587589263916016,
            "learning_rate": 8e-06,
            "epoch": 3.094,
            "step": 7735
        },
        {
            "loss": 0.0582,
            "grad_norm": 1.0842533111572266,
            "learning_rate": 8e-06,
            "epoch": 3.096,
            "step": 7740
        },
        {
            "loss": 0.0679,
            "grad_norm": 2.0289597511291504,
            "learning_rate": 8e-06,
            "epoch": 3.098,
            "step": 7745
        },
        {
            "loss": 0.0522,
            "grad_norm": 2.802363395690918,
            "learning_rate": 8e-06,
            "epoch": 3.1,
            "step": 7750
        },
        {
            "loss": 0.0637,
            "grad_norm": 1.4773004055023193,
            "learning_rate": 8e-06,
            "epoch": 3.102,
            "step": 7755
        },
        {
            "loss": 0.0565,
            "grad_norm": 1.6349005699157715,
            "learning_rate": 8e-06,
            "epoch": 3.104,
            "step": 7760
        },
        {
            "loss": 0.0698,
            "grad_norm": 1.261045217514038,
            "learning_rate": 8e-06,
            "epoch": 3.106,
            "step": 7765
        },
        {
            "loss": 0.065,
            "grad_norm": 2.214414119720459,
            "learning_rate": 8e-06,
            "epoch": 3.108,
            "step": 7770
        },
        {
            "loss": 0.0614,
            "grad_norm": 0.9859732389450073,
            "learning_rate": 8e-06,
            "epoch": 3.11,
            "step": 7775
        },
        {
            "loss": 0.0578,
            "grad_norm": 2.3614468574523926,
            "learning_rate": 8e-06,
            "epoch": 3.112,
            "step": 7780
        },
        {
            "loss": 0.0524,
            "grad_norm": 1.6542396545410156,
            "learning_rate": 8e-06,
            "epoch": 3.114,
            "step": 7785
        },
        {
            "loss": 0.0578,
            "grad_norm": 1.52065110206604,
            "learning_rate": 8e-06,
            "epoch": 3.116,
            "step": 7790
        },
        {
            "loss": 0.0558,
            "grad_norm": 1.4347044229507446,
            "learning_rate": 8e-06,
            "epoch": 3.118,
            "step": 7795
        },
        {
            "loss": 0.061,
            "grad_norm": 2.0815412998199463,
            "learning_rate": 8e-06,
            "epoch": 3.12,
            "step": 7800
        },
        {
            "eval_loss": 0.07994288206100464,
            "eval_f1": 0.7838067961916556,
            "eval_recall": 0.797825401827923,
            "eval_accuracy": 0.9735316454342222,
            "eval_precision": 0.7702723261828693,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6851179673321234,
                    "recall": 0.7344357976653697,
                    "f1-score": 0.7089201877934272,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6719636776390465,
                    "recall": 0.6757990867579908,
                    "f1-score": 0.6738759248719408,
                    "support": 876
                },
                "PER": {
                    "precision": 0.871523915461624,
                    "recall": 0.8918611269208879,
                    "f1-score": 0.8815752461322082,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.5855130784708249,
                    "recall": 0.6271551724137931,
                    "f1-score": 0.6056191467221644,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7702723261828693,
                    "recall": 0.797825401827923,
                    "f1-score": 0.7838067961916556,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.7035296597259046,
                    "recall": 0.7323127959395104,
                    "f1-score": 0.7174976263799352,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7719559766439174,
                    "recall": 0.797825401827923,
                    "f1-score": 0.7845816650340706,
                    "support": 6346
                }
            },
            "eval_runtime": 4.5207,
            "eval_samples_per_second": 906.047,
            "eval_steps_per_second": 7.078,
            "epoch": 3.12,
            "step": 7800
        },
        {
            "loss": 0.075,
            "grad_norm": 4.5445427894592285,
            "learning_rate": 8e-06,
            "epoch": 3.122,
            "step": 7805
        },
        {
            "loss": 0.0593,
            "grad_norm": 1.8801742792129517,
            "learning_rate": 8e-06,
            "epoch": 3.124,
            "step": 7810
        },
        {
            "loss": 0.0539,
            "grad_norm": 1.3580029010772705,
            "learning_rate": 8e-06,
            "epoch": 3.126,
            "step": 7815
        },
        {
            "loss": 0.0537,
            "grad_norm": 1.6891025304794312,
            "learning_rate": 8e-06,
            "epoch": 3.128,
            "step": 7820
        },
        {
            "loss": 0.054,
            "grad_norm": 2.297626256942749,
            "learning_rate": 8e-06,
            "epoch": 3.13,
            "step": 7825
        },
        {
            "loss": 0.0547,
            "grad_norm": 2.519568681716919,
            "learning_rate": 8e-06,
            "epoch": 3.132,
            "step": 7830
        },
        {
            "loss": 0.066,
            "grad_norm": 2.1600019931793213,
            "learning_rate": 8e-06,
            "epoch": 3.134,
            "step": 7835
        },
        {
            "loss": 0.0388,
            "grad_norm": 1.4077932834625244,
            "learning_rate": 8e-06,
            "epoch": 3.136,
            "step": 7840
        },
        {
            "loss": 0.0571,
            "grad_norm": 3.3711249828338623,
            "learning_rate": 8e-06,
            "epoch": 3.138,
            "step": 7845
        },
        {
            "loss": 0.06,
            "grad_norm": 1.6148710250854492,
            "learning_rate": 8e-06,
            "epoch": 3.14,
            "step": 7850
        },
        {
            "loss": 0.0427,
            "grad_norm": 1.7283375263214111,
            "learning_rate": 8e-06,
            "epoch": 3.142,
            "step": 7855
        },
        {
            "loss": 0.0669,
            "grad_norm": 2.671191692352295,
            "learning_rate": 8e-06,
            "epoch": 3.144,
            "step": 7860
        },
        {
            "loss": 0.0523,
            "grad_norm": 2.892082929611206,
            "learning_rate": 8e-06,
            "epoch": 3.146,
            "step": 7865
        },
        {
            "loss": 0.051,
            "grad_norm": 1.1051301956176758,
            "learning_rate": 8e-06,
            "epoch": 3.148,
            "step": 7870
        },
        {
            "loss": 0.0676,
            "grad_norm": 2.3762619495391846,
            "learning_rate": 8e-06,
            "epoch": 3.15,
            "step": 7875
        },
        {
            "loss": 0.0558,
            "grad_norm": 2.631073236465454,
            "learning_rate": 8e-06,
            "epoch": 3.152,
            "step": 7880
        },
        {
            "loss": 0.0598,
            "grad_norm": 1.369123935699463,
            "learning_rate": 8e-06,
            "epoch": 3.154,
            "step": 7885
        },
        {
            "loss": 0.069,
            "grad_norm": 2.581331491470337,
            "learning_rate": 8e-06,
            "epoch": 3.156,
            "step": 7890
        },
        {
            "loss": 0.0549,
            "grad_norm": 2.854773759841919,
            "learning_rate": 8e-06,
            "epoch": 3.158,
            "step": 7895
        },
        {
            "loss": 0.0576,
            "grad_norm": 1.8181781768798828,
            "learning_rate": 8e-06,
            "epoch": 3.16,
            "step": 7900
        },
        {
            "loss": 0.0544,
            "grad_norm": 2.22052264213562,
            "learning_rate": 8e-06,
            "epoch": 3.162,
            "step": 7905
        },
        {
            "loss": 0.0627,
            "grad_norm": 3.0869510173797607,
            "learning_rate": 8e-06,
            "epoch": 3.164,
            "step": 7910
        },
        {
            "loss": 0.075,
            "grad_norm": 3.0576155185699463,
            "learning_rate": 8e-06,
            "epoch": 3.166,
            "step": 7915
        },
        {
            "loss": 0.0602,
            "grad_norm": 1.7892483472824097,
            "learning_rate": 8e-06,
            "epoch": 3.168,
            "step": 7920
        },
        {
            "loss": 0.0691,
            "grad_norm": 2.3954122066497803,
            "learning_rate": 8e-06,
            "epoch": 3.17,
            "step": 7925
        },
        {
            "loss": 0.0595,
            "grad_norm": 0.8992685675621033,
            "learning_rate": 8e-06,
            "epoch": 3.172,
            "step": 7930
        },
        {
            "loss": 0.0562,
            "grad_norm": 2.0815887451171875,
            "learning_rate": 8e-06,
            "epoch": 3.174,
            "step": 7935
        },
        {
            "loss": 0.0552,
            "grad_norm": 1.9649169445037842,
            "learning_rate": 8e-06,
            "epoch": 3.176,
            "step": 7940
        },
        {
            "loss": 0.0565,
            "grad_norm": 1.4420647621154785,
            "learning_rate": 8e-06,
            "epoch": 3.178,
            "step": 7945
        },
        {
            "loss": 0.0734,
            "grad_norm": 2.482234239578247,
            "learning_rate": 8e-06,
            "epoch": 3.18,
            "step": 7950
        },
        {
            "loss": 0.0421,
            "grad_norm": 1.698704719543457,
            "learning_rate": 8e-06,
            "epoch": 3.182,
            "step": 7955
        },
        {
            "loss": 0.0532,
            "grad_norm": 3.824493169784546,
            "learning_rate": 8e-06,
            "epoch": 3.184,
            "step": 7960
        },
        {
            "loss": 0.0504,
            "grad_norm": 1.5873934030532837,
            "learning_rate": 8e-06,
            "epoch": 3.186,
            "step": 7965
        },
        {
            "loss": 0.0709,
            "grad_norm": 1.78299081325531,
            "learning_rate": 8e-06,
            "epoch": 3.188,
            "step": 7970
        },
        {
            "loss": 0.0555,
            "grad_norm": 1.755164623260498,
            "learning_rate": 8e-06,
            "epoch": 3.19,
            "step": 7975
        },
        {
            "loss": 0.0609,
            "grad_norm": 2.8747761249542236,
            "learning_rate": 8e-06,
            "epoch": 3.192,
            "step": 7980
        },
        {
            "loss": 0.0566,
            "grad_norm": 1.9421133995056152,
            "learning_rate": 8e-06,
            "epoch": 3.194,
            "step": 7985
        },
        {
            "loss": 0.0617,
            "grad_norm": 2.059926748275757,
            "learning_rate": 8e-06,
            "epoch": 3.196,
            "step": 7990
        },
        {
            "loss": 0.0622,
            "grad_norm": 1.2114022970199585,
            "learning_rate": 8e-06,
            "epoch": 3.198,
            "step": 7995
        },
        {
            "loss": 0.0621,
            "grad_norm": 0.8345400094985962,
            "learning_rate": 8e-06,
            "epoch": 3.2,
            "step": 8000
        },
        {
            "loss": 0.05,
            "grad_norm": 1.0462415218353271,
            "learning_rate": 8e-06,
            "epoch": 3.202,
            "step": 8005
        },
        {
            "loss": 0.0659,
            "grad_norm": 1.5363352298736572,
            "learning_rate": 8e-06,
            "epoch": 3.204,
            "step": 8010
        },
        {
            "loss": 0.0631,
            "grad_norm": 2.37239933013916,
            "learning_rate": 8e-06,
            "epoch": 3.206,
            "step": 8015
        },
        {
            "loss": 0.0569,
            "grad_norm": 2.3328864574432373,
            "learning_rate": 8e-06,
            "epoch": 3.208,
            "step": 8020
        },
        {
            "loss": 0.0528,
            "grad_norm": 2.0102033615112305,
            "learning_rate": 8e-06,
            "epoch": 3.21,
            "step": 8025
        },
        {
            "loss": 0.0513,
            "grad_norm": 0.8346136212348938,
            "learning_rate": 8e-06,
            "epoch": 3.212,
            "step": 8030
        },
        {
            "loss": 0.0636,
            "grad_norm": 1.596662163734436,
            "learning_rate": 8e-06,
            "epoch": 3.214,
            "step": 8035
        },
        {
            "loss": 0.0532,
            "grad_norm": 1.49081552028656,
            "learning_rate": 8e-06,
            "epoch": 3.216,
            "step": 8040
        },
        {
            "loss": 0.0536,
            "grad_norm": 2.007908821105957,
            "learning_rate": 8e-06,
            "epoch": 3.218,
            "step": 8045
        },
        {
            "loss": 0.0569,
            "grad_norm": 1.7553801536560059,
            "learning_rate": 8e-06,
            "epoch": 3.22,
            "step": 8050
        },
        {
            "loss": 0.0626,
            "grad_norm": 1.9947236776351929,
            "learning_rate": 8e-06,
            "epoch": 3.222,
            "step": 8055
        },
        {
            "loss": 0.0434,
            "grad_norm": 1.7276853322982788,
            "learning_rate": 8e-06,
            "epoch": 3.224,
            "step": 8060
        },
        {
            "loss": 0.0586,
            "grad_norm": 3.044273853302002,
            "learning_rate": 8e-06,
            "epoch": 3.226,
            "step": 8065
        },
        {
            "loss": 0.0626,
            "grad_norm": 1.044541835784912,
            "learning_rate": 8e-06,
            "epoch": 3.228,
            "step": 8070
        },
        {
            "loss": 0.0585,
            "grad_norm": 1.4177979230880737,
            "learning_rate": 8e-06,
            "epoch": 3.23,
            "step": 8075
        },
        {
            "loss": 0.0495,
            "grad_norm": 1.1373378038406372,
            "learning_rate": 8e-06,
            "epoch": 3.232,
            "step": 8080
        },
        {
            "loss": 0.0582,
            "grad_norm": 3.1846847534179688,
            "learning_rate": 8e-06,
            "epoch": 3.234,
            "step": 8085
        },
        {
            "loss": 0.0671,
            "grad_norm": 7.788245677947998,
            "learning_rate": 8e-06,
            "epoch": 3.2359999999999998,
            "step": 8090
        },
        {
            "loss": 0.0661,
            "grad_norm": 2.2142364978790283,
            "learning_rate": 8e-06,
            "epoch": 3.238,
            "step": 8095
        },
        {
            "loss": 0.0618,
            "grad_norm": 2.3119606971740723,
            "learning_rate": 8e-06,
            "epoch": 3.24,
            "step": 8100
        },
        {
            "eval_loss": 0.08147256076335907,
            "eval_f1": 0.785394581861013,
            "eval_recall": 0.7880554680113457,
            "eval_accuracy": 0.9730075196012365,
            "eval_precision": 0.7827516043199249,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6932938856015779,
                    "recall": 0.683852140077821,
                    "f1-score": 0.6885406464250735,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6799531066822978,
                    "recall": 0.6621004566210046,
                    "f1-score": 0.6709080393290919,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8754180602006689,
                    "recall": 0.8938531587933979,
                    "f1-score": 0.8845395663193468,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.6177730192719486,
                    "recall": 0.6217672413793104,
                    "f1-score": 0.6197636949516648,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7827516043199249,
                    "recall": 0.7880554680113457,
                    "f1-score": 0.785394581861013,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.7166095179391233,
                    "recall": 0.7153932492178835,
                    "f1-score": 0.7159379867562943,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7812570849797721,
                    "recall": 0.7880554680113457,
                    "f1-score": 0.784580518742293,
                    "support": 6346
                }
            },
            "eval_runtime": 4.3678,
            "eval_samples_per_second": 937.778,
            "eval_steps_per_second": 7.326,
            "epoch": 3.24,
            "step": 8100
        },
        {
            "loss": 0.0707,
            "grad_norm": 1.7246350049972534,
            "learning_rate": 8e-06,
            "epoch": 3.242,
            "step": 8105
        },
        {
            "loss": 0.0495,
            "grad_norm": 1.9905563592910767,
            "learning_rate": 8e-06,
            "epoch": 3.2439999999999998,
            "step": 8110
        },
        {
            "loss": 0.048,
            "grad_norm": 1.4937989711761475,
            "learning_rate": 8e-06,
            "epoch": 3.246,
            "step": 8115
        },
        {
            "loss": 0.0561,
            "grad_norm": 1.2713204622268677,
            "learning_rate": 8e-06,
            "epoch": 3.248,
            "step": 8120
        },
        {
            "loss": 0.045,
            "grad_norm": 1.8541297912597656,
            "learning_rate": 8e-06,
            "epoch": 3.25,
            "step": 8125
        },
        {
            "loss": 0.0645,
            "grad_norm": 1.7588274478912354,
            "learning_rate": 8e-06,
            "epoch": 3.252,
            "step": 8130
        },
        {
            "loss": 0.0657,
            "grad_norm": 1.0561513900756836,
            "learning_rate": 8e-06,
            "epoch": 3.254,
            "step": 8135
        },
        {
            "loss": 0.0524,
            "grad_norm": 1.3065669536590576,
            "learning_rate": 8e-06,
            "epoch": 3.2560000000000002,
            "step": 8140
        },
        {
            "loss": 0.0657,
            "grad_norm": 1.4889991283416748,
            "learning_rate": 8e-06,
            "epoch": 3.258,
            "step": 8145
        },
        {
            "loss": 0.0784,
            "grad_norm": 1.9435447454452515,
            "learning_rate": 8e-06,
            "epoch": 3.26,
            "step": 8150
        },
        {
            "loss": 0.0612,
            "grad_norm": 1.628287672996521,
            "learning_rate": 8e-06,
            "epoch": 3.262,
            "step": 8155
        },
        {
            "loss": 0.0771,
            "grad_norm": 1.7129027843475342,
            "learning_rate": 8e-06,
            "epoch": 3.2640000000000002,
            "step": 8160
        },
        {
            "loss": 0.0608,
            "grad_norm": 0.9670374393463135,
            "learning_rate": 8e-06,
            "epoch": 3.266,
            "step": 8165
        },
        {
            "loss": 0.0508,
            "grad_norm": 1.3291881084442139,
            "learning_rate": 8e-06,
            "epoch": 3.268,
            "step": 8170
        },
        {
            "loss": 0.0545,
            "grad_norm": 1.3769599199295044,
            "learning_rate": 8e-06,
            "epoch": 3.27,
            "step": 8175
        },
        {
            "loss": 0.0623,
            "grad_norm": 2.7208454608917236,
            "learning_rate": 8e-06,
            "epoch": 3.2720000000000002,
            "step": 8180
        },
        {
            "loss": 0.0616,
            "grad_norm": 2.7041842937469482,
            "learning_rate": 8e-06,
            "epoch": 3.274,
            "step": 8185
        },
        {
            "loss": 0.0637,
            "grad_norm": 2.4463696479797363,
            "learning_rate": 8e-06,
            "epoch": 3.276,
            "step": 8190
        },
        {
            "loss": 0.0651,
            "grad_norm": 3.870532989501953,
            "learning_rate": 8e-06,
            "epoch": 3.278,
            "step": 8195
        },
        {
            "loss": 0.0618,
            "grad_norm": 1.2492810487747192,
            "learning_rate": 8e-06,
            "epoch": 3.2800000000000002,
            "step": 8200
        },
        {
            "loss": 0.0764,
            "grad_norm": 1.8642328977584839,
            "learning_rate": 8e-06,
            "epoch": 3.282,
            "step": 8205
        },
        {
            "loss": 0.0533,
            "grad_norm": 1.813428282737732,
            "learning_rate": 8e-06,
            "epoch": 3.284,
            "step": 8210
        },
        {
            "loss": 0.0732,
            "grad_norm": 2.4164655208587646,
            "learning_rate": 8e-06,
            "epoch": 3.286,
            "step": 8215
        },
        {
            "loss": 0.0616,
            "grad_norm": 1.9420292377471924,
            "learning_rate": 8e-06,
            "epoch": 3.288,
            "step": 8220
        },
        {
            "loss": 0.0455,
            "grad_norm": 1.4442543983459473,
            "learning_rate": 8e-06,
            "epoch": 3.29,
            "step": 8225
        },
        {
            "loss": 0.0738,
            "grad_norm": 1.8695507049560547,
            "learning_rate": 8e-06,
            "epoch": 3.292,
            "step": 8230
        },
        {
            "loss": 0.0532,
            "grad_norm": 1.168153166770935,
            "learning_rate": 8e-06,
            "epoch": 3.294,
            "step": 8235
        },
        {
            "loss": 0.0578,
            "grad_norm": 2.0391845703125,
            "learning_rate": 8e-06,
            "epoch": 3.296,
            "step": 8240
        },
        {
            "loss": 0.0575,
            "grad_norm": 1.3823065757751465,
            "learning_rate": 8e-06,
            "epoch": 3.298,
            "step": 8245
        },
        {
            "loss": 0.0641,
            "grad_norm": 1.4073230028152466,
            "learning_rate": 8e-06,
            "epoch": 3.3,
            "step": 8250
        },
        {
            "loss": 0.0529,
            "grad_norm": 1.7022085189819336,
            "learning_rate": 8e-06,
            "epoch": 3.302,
            "step": 8255
        },
        {
            "loss": 0.0562,
            "grad_norm": 2.009066343307495,
            "learning_rate": 8e-06,
            "epoch": 3.304,
            "step": 8260
        },
        {
            "loss": 0.0546,
            "grad_norm": 1.3871334791183472,
            "learning_rate": 8e-06,
            "epoch": 3.306,
            "step": 8265
        },
        {
            "loss": 0.0642,
            "grad_norm": 1.0884206295013428,
            "learning_rate": 8e-06,
            "epoch": 3.308,
            "step": 8270
        },
        {
            "loss": 0.0651,
            "grad_norm": 1.6437311172485352,
            "learning_rate": 8e-06,
            "epoch": 3.31,
            "step": 8275
        },
        {
            "loss": 0.0537,
            "grad_norm": 1.1212939023971558,
            "learning_rate": 8e-06,
            "epoch": 3.312,
            "step": 8280
        },
        {
            "loss": 0.0756,
            "grad_norm": 2.7999138832092285,
            "learning_rate": 8e-06,
            "epoch": 3.314,
            "step": 8285
        },
        {
            "loss": 0.0521,
            "grad_norm": 1.5129097700119019,
            "learning_rate": 8e-06,
            "epoch": 3.316,
            "step": 8290
        },
        {
            "loss": 0.0669,
            "grad_norm": 2.3188130855560303,
            "learning_rate": 8e-06,
            "epoch": 3.318,
            "step": 8295
        },
        {
            "loss": 0.0548,
            "grad_norm": 1.4862446784973145,
            "learning_rate": 8e-06,
            "epoch": 3.32,
            "step": 8300
        },
        {
            "loss": 0.0545,
            "grad_norm": 1.513450264930725,
            "learning_rate": 8e-06,
            "epoch": 3.322,
            "step": 8305
        },
        {
            "loss": 0.0708,
            "grad_norm": 1.860600233078003,
            "learning_rate": 8e-06,
            "epoch": 3.324,
            "step": 8310
        },
        {
            "loss": 0.0789,
            "grad_norm": 2.458388328552246,
            "learning_rate": 8e-06,
            "epoch": 3.326,
            "step": 8315
        },
        {
            "loss": 0.0453,
            "grad_norm": 1.3712499141693115,
            "learning_rate": 8e-06,
            "epoch": 3.328,
            "step": 8320
        },
        {
            "loss": 0.0665,
            "grad_norm": 1.5789800882339478,
            "learning_rate": 8e-06,
            "epoch": 3.33,
            "step": 8325
        },
        {
            "loss": 0.0509,
            "grad_norm": 1.8339914083480835,
            "learning_rate": 8e-06,
            "epoch": 3.332,
            "step": 8330
        },
        {
            "loss": 0.0528,
            "grad_norm": 1.4083598852157593,
            "learning_rate": 8e-06,
            "epoch": 3.334,
            "step": 8335
        },
        {
            "loss": 0.0501,
            "grad_norm": 0.9512283802032471,
            "learning_rate": 8e-06,
            "epoch": 3.336,
            "step": 8340
        },
        {
            "loss": 0.0587,
            "grad_norm": 2.0425944328308105,
            "learning_rate": 8e-06,
            "epoch": 3.338,
            "step": 8345
        },
        {
            "loss": 0.0824,
            "grad_norm": 1.515615463256836,
            "learning_rate": 8e-06,
            "epoch": 3.34,
            "step": 8350
        },
        {
            "loss": 0.0521,
            "grad_norm": 1.113750696182251,
            "learning_rate": 8e-06,
            "epoch": 3.342,
            "step": 8355
        },
        {
            "loss": 0.0496,
            "grad_norm": 2.371227502822876,
            "learning_rate": 8e-06,
            "epoch": 3.344,
            "step": 8360
        },
        {
            "loss": 0.0628,
            "grad_norm": 3.9837634563446045,
            "learning_rate": 8e-06,
            "epoch": 3.346,
            "step": 8365
        },
        {
            "loss": 0.0609,
            "grad_norm": 2.086134672164917,
            "learning_rate": 8e-06,
            "epoch": 3.348,
            "step": 8370
        },
        {
            "loss": 0.0608,
            "grad_norm": 2.391849994659424,
            "learning_rate": 8e-06,
            "epoch": 3.35,
            "step": 8375
        },
        {
            "loss": 0.0576,
            "grad_norm": 1.9155726432800293,
            "learning_rate": 8e-06,
            "epoch": 3.352,
            "step": 8380
        },
        {
            "loss": 0.0698,
            "grad_norm": 1.7786717414855957,
            "learning_rate": 8e-06,
            "epoch": 3.354,
            "step": 8385
        },
        {
            "loss": 0.0458,
            "grad_norm": 2.154423475265503,
            "learning_rate": 8e-06,
            "epoch": 3.356,
            "step": 8390
        },
        {
            "loss": 0.0723,
            "grad_norm": 2.186889171600342,
            "learning_rate": 8e-06,
            "epoch": 3.358,
            "step": 8395
        },
        {
            "loss": 0.0723,
            "grad_norm": 1.8536717891693115,
            "learning_rate": 8e-06,
            "epoch": 3.36,
            "step": 8400
        },
        {
            "eval_loss": 0.08203853666782379,
            "eval_f1": 0.7887821744141377,
            "eval_recall": 0.8088559722659944,
            "eval_accuracy": 0.9732642342949438,
            "eval_precision": 0.769680611785875,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6675213675213675,
                    "recall": 0.7597276264591439,
                    "f1-score": 0.710646041856233,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6855123674911661,
                    "recall": 0.6643835616438356,
                    "f1-score": 0.6747826086956521,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8591360343439763,
                    "recall": 0.9112122936824132,
                    "f1-score": 0.8844082309073333,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.6153846153846154,
                    "recall": 0.6120689655172413,
                    "f1-score": 0.6137223122636413,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.769680611785875,
                    "recall": 0.8088559722659944,
                    "f1-score": 0.7887821744141377,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.7068885961852813,
                    "recall": 0.7368481118256585,
                    "f1-score": 0.7208897984307149,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7684843598323169,
                    "recall": 0.8088559722659944,
                    "f1-score": 0.7877400764945836,
                    "support": 6346
                }
            },
            "eval_runtime": 4.3157,
            "eval_samples_per_second": 949.093,
            "eval_steps_per_second": 7.415,
            "epoch": 3.36,
            "step": 8400
        },
        {
            "loss": 0.0728,
            "grad_norm": 1.3062595129013062,
            "learning_rate": 8e-06,
            "epoch": 3.362,
            "step": 8405
        },
        {
            "loss": 0.0643,
            "grad_norm": 1.9040919542312622,
            "learning_rate": 8e-06,
            "epoch": 3.364,
            "step": 8410
        },
        {
            "loss": 0.0668,
            "grad_norm": 1.7230565547943115,
            "learning_rate": 8e-06,
            "epoch": 3.366,
            "step": 8415
        },
        {
            "loss": 0.0627,
            "grad_norm": 1.9742558002471924,
            "learning_rate": 8e-06,
            "epoch": 3.368,
            "step": 8420
        },
        {
            "loss": 0.064,
            "grad_norm": 1.2454439401626587,
            "learning_rate": 8e-06,
            "epoch": 3.37,
            "step": 8425
        },
        {
            "loss": 0.0487,
            "grad_norm": 1.5588769912719727,
            "learning_rate": 8e-06,
            "epoch": 3.372,
            "step": 8430
        },
        {
            "loss": 0.0663,
            "grad_norm": 1.7079048156738281,
            "learning_rate": 8e-06,
            "epoch": 3.374,
            "step": 8435
        },
        {
            "loss": 0.0629,
            "grad_norm": 1.321677327156067,
            "learning_rate": 8e-06,
            "epoch": 3.376,
            "step": 8440
        },
        {
            "loss": 0.0736,
            "grad_norm": 1.8945026397705078,
            "learning_rate": 8e-06,
            "epoch": 3.378,
            "step": 8445
        },
        {
            "loss": 0.0649,
            "grad_norm": 1.838546872138977,
            "learning_rate": 8e-06,
            "epoch": 3.38,
            "step": 8450
        },
        {
            "loss": 0.0697,
            "grad_norm": 2.3351099491119385,
            "learning_rate": 8e-06,
            "epoch": 3.382,
            "step": 8455
        },
        {
            "loss": 0.0667,
            "grad_norm": 2.1161487102508545,
            "learning_rate": 8e-06,
            "epoch": 3.384,
            "step": 8460
        },
        {
            "loss": 0.053,
            "grad_norm": 2.4105398654937744,
            "learning_rate": 8e-06,
            "epoch": 3.386,
            "step": 8465
        },
        {
            "loss": 0.0522,
            "grad_norm": 1.0069979429244995,
            "learning_rate": 8e-06,
            "epoch": 3.388,
            "step": 8470
        },
        {
            "loss": 0.0556,
            "grad_norm": 2.046985149383545,
            "learning_rate": 8e-06,
            "epoch": 3.39,
            "step": 8475
        },
        {
            "loss": 0.0615,
            "grad_norm": 1.4955238103866577,
            "learning_rate": 8e-06,
            "epoch": 3.392,
            "step": 8480
        },
        {
            "loss": 0.0475,
            "grad_norm": 1.197951078414917,
            "learning_rate": 8e-06,
            "epoch": 3.394,
            "step": 8485
        },
        {
            "loss": 0.0567,
            "grad_norm": 1.4083096981048584,
            "learning_rate": 8e-06,
            "epoch": 3.396,
            "step": 8490
        },
        {
            "loss": 0.0575,
            "grad_norm": 1.6572322845458984,
            "learning_rate": 8e-06,
            "epoch": 3.398,
            "step": 8495
        },
        {
            "loss": 0.0606,
            "grad_norm": 2.4595260620117188,
            "learning_rate": 8e-06,
            "epoch": 3.4,
            "step": 8500
        },
        {
            "loss": 0.0563,
            "grad_norm": 1.2360011339187622,
            "learning_rate": 8e-06,
            "epoch": 3.402,
            "step": 8505
        },
        {
            "loss": 0.0641,
            "grad_norm": 5.187164783477783,
            "learning_rate": 8e-06,
            "epoch": 3.404,
            "step": 8510
        },
        {
            "loss": 0.0572,
            "grad_norm": 1.179909348487854,
            "learning_rate": 8e-06,
            "epoch": 3.406,
            "step": 8515
        },
        {
            "loss": 0.0753,
            "grad_norm": 5.376225471496582,
            "learning_rate": 8e-06,
            "epoch": 3.408,
            "step": 8520
        },
        {
            "loss": 0.0643,
            "grad_norm": 2.0164871215820312,
            "learning_rate": 8e-06,
            "epoch": 3.41,
            "step": 8525
        },
        {
            "loss": 0.0503,
            "grad_norm": 1.2721247673034668,
            "learning_rate": 8e-06,
            "epoch": 3.412,
            "step": 8530
        },
        {
            "loss": 0.0539,
            "grad_norm": 1.4751328229904175,
            "learning_rate": 8e-06,
            "epoch": 3.414,
            "step": 8535
        },
        {
            "loss": 0.0655,
            "grad_norm": 1.6055521965026855,
            "learning_rate": 8e-06,
            "epoch": 3.416,
            "step": 8540
        },
        {
            "loss": 0.0663,
            "grad_norm": 2.497098445892334,
            "learning_rate": 8e-06,
            "epoch": 3.418,
            "step": 8545
        },
        {
            "loss": 0.0744,
            "grad_norm": 1.5186593532562256,
            "learning_rate": 8e-06,
            "epoch": 3.42,
            "step": 8550
        },
        {
            "loss": 0.0547,
            "grad_norm": 1.4651179313659668,
            "learning_rate": 8e-06,
            "epoch": 3.422,
            "step": 8555
        },
        {
            "loss": 0.0527,
            "grad_norm": 1.3586647510528564,
            "learning_rate": 8e-06,
            "epoch": 3.424,
            "step": 8560
        },
        {
            "loss": 0.0707,
            "grad_norm": 3.113377571105957,
            "learning_rate": 8e-06,
            "epoch": 3.426,
            "step": 8565
        },
        {
            "loss": 0.0581,
            "grad_norm": 1.5035123825073242,
            "learning_rate": 8e-06,
            "epoch": 3.428,
            "step": 8570
        },
        {
            "loss": 0.0461,
            "grad_norm": 1.4370678663253784,
            "learning_rate": 8e-06,
            "epoch": 3.43,
            "step": 8575
        },
        {
            "loss": 0.0568,
            "grad_norm": 1.8007874488830566,
            "learning_rate": 8e-06,
            "epoch": 3.432,
            "step": 8580
        },
        {
            "loss": 0.0949,
            "grad_norm": 2.297567844390869,
            "learning_rate": 8e-06,
            "epoch": 3.434,
            "step": 8585
        },
        {
            "loss": 0.0737,
            "grad_norm": 1.9587080478668213,
            "learning_rate": 8e-06,
            "epoch": 3.436,
            "step": 8590
        },
        {
            "loss": 0.0741,
            "grad_norm": 1.4565794467926025,
            "learning_rate": 8e-06,
            "epoch": 3.438,
            "step": 8595
        },
        {
            "loss": 0.0467,
            "grad_norm": 1.8200174570083618,
            "learning_rate": 8e-06,
            "epoch": 3.44,
            "step": 8600
        },
        {
            "loss": 0.0676,
            "grad_norm": 1.6252179145812988,
            "learning_rate": 8e-06,
            "epoch": 3.442,
            "step": 8605
        },
        {
            "loss": 0.0573,
            "grad_norm": 3.037452459335327,
            "learning_rate": 8e-06,
            "epoch": 3.444,
            "step": 8610
        },
        {
            "loss": 0.0352,
            "grad_norm": 1.3261386156082153,
            "learning_rate": 8e-06,
            "epoch": 3.446,
            "step": 8615
        },
        {
            "loss": 0.0743,
            "grad_norm": 1.933951735496521,
            "learning_rate": 8e-06,
            "epoch": 3.448,
            "step": 8620
        },
        {
            "loss": 0.0519,
            "grad_norm": 1.9583613872528076,
            "learning_rate": 8e-06,
            "epoch": 3.45,
            "step": 8625
        },
        {
            "loss": 0.0536,
            "grad_norm": 1.6283670663833618,
            "learning_rate": 8e-06,
            "epoch": 3.452,
            "step": 8630
        },
        {
            "loss": 0.0712,
            "grad_norm": 1.7913377285003662,
            "learning_rate": 8e-06,
            "epoch": 3.454,
            "step": 8635
        },
        {
            "loss": 0.0752,
            "grad_norm": 1.5752465724945068,
            "learning_rate": 8e-06,
            "epoch": 3.456,
            "step": 8640
        },
        {
            "loss": 0.052,
            "grad_norm": 1.488472580909729,
            "learning_rate": 8e-06,
            "epoch": 3.458,
            "step": 8645
        },
        {
            "loss": 0.0544,
            "grad_norm": 1.057573676109314,
            "learning_rate": 8e-06,
            "epoch": 3.46,
            "step": 8650
        },
        {
            "loss": 0.0543,
            "grad_norm": 1.9144024848937988,
            "learning_rate": 8e-06,
            "epoch": 3.462,
            "step": 8655
        },
        {
            "loss": 0.0652,
            "grad_norm": 1.6403056383132935,
            "learning_rate": 8e-06,
            "epoch": 3.464,
            "step": 8660
        },
        {
            "loss": 0.0546,
            "grad_norm": 1.7283471822738647,
            "learning_rate": 8e-06,
            "epoch": 3.466,
            "step": 8665
        },
        {
            "loss": 0.0645,
            "grad_norm": 1.855018973350525,
            "learning_rate": 8e-06,
            "epoch": 3.468,
            "step": 8670
        },
        {
            "loss": 0.0584,
            "grad_norm": 1.9453010559082031,
            "learning_rate": 8e-06,
            "epoch": 3.4699999999999998,
            "step": 8675
        },
        {
            "loss": 0.048,
            "grad_norm": 2.19704270362854,
            "learning_rate": 8e-06,
            "epoch": 3.472,
            "step": 8680
        },
        {
            "loss": 0.0633,
            "grad_norm": 1.440316915512085,
            "learning_rate": 8e-06,
            "epoch": 3.474,
            "step": 8685
        },
        {
            "loss": 0.0675,
            "grad_norm": 3.228910207748413,
            "learning_rate": 8e-06,
            "epoch": 3.476,
            "step": 8690
        },
        {
            "loss": 0.0584,
            "grad_norm": 1.9835097789764404,
            "learning_rate": 8e-06,
            "epoch": 3.4779999999999998,
            "step": 8695
        },
        {
            "loss": 0.0495,
            "grad_norm": 1.7700468301773071,
            "learning_rate": 8e-06,
            "epoch": 3.48,
            "step": 8700
        },
        {
            "eval_loss": 0.08127632737159729,
            "eval_f1": 0.7840408257944793,
            "eval_recall": 0.7989284588717303,
            "eval_accuracy": 0.9731091358341623,
            "eval_precision": 0.7696978897829058,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6608238387379491,
                    "recall": 0.7334630350194552,
                    "f1-score": 0.6952512678653757,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6844059405940595,
                    "recall": 0.6312785388127854,
                    "f1-score": 0.6567695961995249,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8649089426474585,
                    "recall": 0.9055207740466704,
                    "f1-score": 0.8847490615876547,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.6058394160583942,
                    "recall": 0.6260775862068966,
                    "f1-score": 0.6157922628510865,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7696978897829058,
                    "recall": 0.7989284588717303,
                    "f1-score": 0.7840408257944793,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.7039945345094654,
                    "recall": 0.724084983521452,
                    "f1-score": 0.7131405471259105,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7690475122515549,
                    "recall": 0.7989284588717303,
                    "f1-score": 0.7832511648252786,
                    "support": 6346
                }
            },
            "eval_runtime": 4.472,
            "eval_samples_per_second": 915.928,
            "eval_steps_per_second": 7.156,
            "epoch": 3.48,
            "step": 8700
        },
        {
            "loss": 0.062,
            "grad_norm": 2.4190304279327393,
            "learning_rate": 8e-06,
            "epoch": 3.482,
            "step": 8705
        },
        {
            "loss": 0.0579,
            "grad_norm": 1.569366455078125,
            "learning_rate": 8e-06,
            "epoch": 3.484,
            "step": 8710
        },
        {
            "loss": 0.0616,
            "grad_norm": 1.122167706489563,
            "learning_rate": 8e-06,
            "epoch": 3.4859999999999998,
            "step": 8715
        },
        {
            "loss": 0.0487,
            "grad_norm": 1.3975995779037476,
            "learning_rate": 8e-06,
            "epoch": 3.488,
            "step": 8720
        },
        {
            "loss": 0.0561,
            "grad_norm": 1.226738452911377,
            "learning_rate": 8e-06,
            "epoch": 3.49,
            "step": 8725
        },
        {
            "loss": 0.0544,
            "grad_norm": 2.8947229385375977,
            "learning_rate": 8e-06,
            "epoch": 3.492,
            "step": 8730
        },
        {
            "loss": 0.0707,
            "grad_norm": 2.107724905014038,
            "learning_rate": 8e-06,
            "epoch": 3.4939999999999998,
            "step": 8735
        },
        {
            "loss": 0.0717,
            "grad_norm": 2.868443727493286,
            "learning_rate": 8e-06,
            "epoch": 3.496,
            "step": 8740
        },
        {
            "loss": 0.063,
            "grad_norm": 2.9752955436706543,
            "learning_rate": 8e-06,
            "epoch": 3.498,
            "step": 8745
        },
        {
            "loss": 0.0527,
            "grad_norm": 0.7677602171897888,
            "learning_rate": 8e-06,
            "epoch": 3.5,
            "step": 8750
        },
        {
            "loss": 0.0659,
            "grad_norm": 2.2926928997039795,
            "learning_rate": 8e-06,
            "epoch": 3.502,
            "step": 8755
        },
        {
            "loss": 0.0596,
            "grad_norm": 1.1970878839492798,
            "learning_rate": 8e-06,
            "epoch": 3.504,
            "step": 8760
        },
        {
            "loss": 0.064,
            "grad_norm": 1.5327636003494263,
            "learning_rate": 8e-06,
            "epoch": 3.5060000000000002,
            "step": 8765
        },
        {
            "loss": 0.0635,
            "grad_norm": 1.9243823289871216,
            "learning_rate": 8e-06,
            "epoch": 3.508,
            "step": 8770
        },
        {
            "loss": 0.062,
            "grad_norm": 3.4148764610290527,
            "learning_rate": 8e-06,
            "epoch": 3.51,
            "step": 8775
        },
        {
            "loss": 0.0658,
            "grad_norm": 1.5186994075775146,
            "learning_rate": 8e-06,
            "epoch": 3.512,
            "step": 8780
        },
        {
            "loss": 0.0656,
            "grad_norm": 2.5925533771514893,
            "learning_rate": 8e-06,
            "epoch": 3.5140000000000002,
            "step": 8785
        },
        {
            "loss": 0.0576,
            "grad_norm": 1.8713964223861694,
            "learning_rate": 8e-06,
            "epoch": 3.516,
            "step": 8790
        },
        {
            "loss": 0.066,
            "grad_norm": 1.821513056755066,
            "learning_rate": 8e-06,
            "epoch": 3.518,
            "step": 8795
        },
        {
            "loss": 0.0599,
            "grad_norm": 3.020036458969116,
            "learning_rate": 8e-06,
            "epoch": 3.52,
            "step": 8800
        },
        {
            "loss": 0.0513,
            "grad_norm": 2.4372825622558594,
            "learning_rate": 8e-06,
            "epoch": 3.5220000000000002,
            "step": 8805
        },
        {
            "loss": 0.062,
            "grad_norm": 1.4764965772628784,
            "learning_rate": 8e-06,
            "epoch": 3.524,
            "step": 8810
        },
        {
            "loss": 0.0478,
            "grad_norm": 2.9392127990722656,
            "learning_rate": 8e-06,
            "epoch": 3.526,
            "step": 8815
        },
        {
            "loss": 0.0647,
            "grad_norm": 2.084571361541748,
            "learning_rate": 8e-06,
            "epoch": 3.528,
            "step": 8820
        },
        {
            "loss": 0.0561,
            "grad_norm": 1.2860004901885986,
            "learning_rate": 8e-06,
            "epoch": 3.5300000000000002,
            "step": 8825
        },
        {
            "loss": 0.0558,
            "grad_norm": 1.940037488937378,
            "learning_rate": 8e-06,
            "epoch": 3.532,
            "step": 8830
        },
        {
            "loss": 0.0648,
            "grad_norm": 2.482166051864624,
            "learning_rate": 8e-06,
            "epoch": 3.534,
            "step": 8835
        },
        {
            "loss": 0.0528,
            "grad_norm": 2.1710197925567627,
            "learning_rate": 8e-06,
            "epoch": 3.536,
            "step": 8840
        },
        {
            "loss": 0.0652,
            "grad_norm": 2.6305155754089355,
            "learning_rate": 8e-06,
            "epoch": 3.5380000000000003,
            "step": 8845
        },
        {
            "loss": 0.0577,
            "grad_norm": 2.6456785202026367,
            "learning_rate": 8e-06,
            "epoch": 3.54,
            "step": 8850
        },
        {
            "loss": 0.0613,
            "grad_norm": 2.091012477874756,
            "learning_rate": 8e-06,
            "epoch": 3.542,
            "step": 8855
        },
        {
            "loss": 0.0661,
            "grad_norm": 1.8235070705413818,
            "learning_rate": 8e-06,
            "epoch": 3.544,
            "step": 8860
        },
        {
            "loss": 0.0548,
            "grad_norm": 1.7087634801864624,
            "learning_rate": 8e-06,
            "epoch": 3.5460000000000003,
            "step": 8865
        },
        {
            "loss": 0.0748,
            "grad_norm": 2.188114881515503,
            "learning_rate": 8e-06,
            "epoch": 3.548,
            "step": 8870
        },
        {
            "loss": 0.0527,
            "grad_norm": 1.5943806171417236,
            "learning_rate": 8e-06,
            "epoch": 3.55,
            "step": 8875
        },
        {
            "loss": 0.0637,
            "grad_norm": 1.2138746976852417,
            "learning_rate": 8e-06,
            "epoch": 3.552,
            "step": 8880
        },
        {
            "loss": 0.0617,
            "grad_norm": 1.1889370679855347,
            "learning_rate": 8e-06,
            "epoch": 3.5540000000000003,
            "step": 8885
        },
        {
            "loss": 0.0679,
            "grad_norm": 1.6543527841567993,
            "learning_rate": 8e-06,
            "epoch": 3.556,
            "step": 8890
        },
        {
            "loss": 0.07,
            "grad_norm": 2.7229225635528564,
            "learning_rate": 8e-06,
            "epoch": 3.558,
            "step": 8895
        },
        {
            "loss": 0.0609,
            "grad_norm": 1.5556360483169556,
            "learning_rate": 8e-06,
            "epoch": 3.56,
            "step": 8900
        },
        {
            "loss": 0.0759,
            "grad_norm": 2.298935651779175,
            "learning_rate": 8e-06,
            "epoch": 3.5620000000000003,
            "step": 8905
        },
        {
            "loss": 0.0612,
            "grad_norm": 1.987859845161438,
            "learning_rate": 8e-06,
            "epoch": 3.564,
            "step": 8910
        },
        {
            "loss": 0.0741,
            "grad_norm": 3.799887180328369,
            "learning_rate": 8e-06,
            "epoch": 3.566,
            "step": 8915
        },
        {
            "loss": 0.06,
            "grad_norm": 1.2929970026016235,
            "learning_rate": 8e-06,
            "epoch": 3.568,
            "step": 8920
        },
        {
            "loss": 0.0735,
            "grad_norm": 1.5070545673370361,
            "learning_rate": 8e-06,
            "epoch": 3.57,
            "step": 8925
        },
        {
            "loss": 0.0639,
            "grad_norm": 1.6416497230529785,
            "learning_rate": 8e-06,
            "epoch": 3.572,
            "step": 8930
        },
        {
            "loss": 0.0648,
            "grad_norm": 1.2282836437225342,
            "learning_rate": 8e-06,
            "epoch": 3.574,
            "step": 8935
        },
        {
            "loss": 0.0617,
            "grad_norm": 0.948669970035553,
            "learning_rate": 8e-06,
            "epoch": 3.576,
            "step": 8940
        },
        {
            "loss": 0.0568,
            "grad_norm": 1.607196569442749,
            "learning_rate": 8e-06,
            "epoch": 3.578,
            "step": 8945
        },
        {
            "loss": 0.052,
            "grad_norm": 1.4457112550735474,
            "learning_rate": 8e-06,
            "epoch": 3.58,
            "step": 8950
        },
        {
            "loss": 0.0683,
            "grad_norm": 2.2280592918395996,
            "learning_rate": 8e-06,
            "epoch": 3.582,
            "step": 8955
        },
        {
            "loss": 0.0559,
            "grad_norm": 1.487533688545227,
            "learning_rate": 8e-06,
            "epoch": 3.584,
            "step": 8960
        },
        {
            "loss": 0.0628,
            "grad_norm": 1.8714033365249634,
            "learning_rate": 8e-06,
            "epoch": 3.586,
            "step": 8965
        },
        {
            "loss": 0.0575,
            "grad_norm": 1.284734845161438,
            "learning_rate": 8e-06,
            "epoch": 3.588,
            "step": 8970
        },
        {
            "loss": 0.048,
            "grad_norm": 1.857041835784912,
            "learning_rate": 8e-06,
            "epoch": 3.59,
            "step": 8975
        },
        {
            "loss": 0.0643,
            "grad_norm": 1.9718185663223267,
            "learning_rate": 8e-06,
            "epoch": 3.592,
            "step": 8980
        },
        {
            "loss": 0.0593,
            "grad_norm": 1.3883665800094604,
            "learning_rate": 8e-06,
            "epoch": 3.594,
            "step": 8985
        },
        {
            "loss": 0.0683,
            "grad_norm": 1.8098574876785278,
            "learning_rate": 8e-06,
            "epoch": 3.596,
            "step": 8990
        },
        {
            "loss": 0.0763,
            "grad_norm": 2.613100051879883,
            "learning_rate": 8e-06,
            "epoch": 3.598,
            "step": 8995
        },
        {
            "loss": 0.0651,
            "grad_norm": 1.3097673654556274,
            "learning_rate": 8e-06,
            "epoch": 3.6,
            "step": 9000
        },
        {
            "eval_loss": 0.07993094623088837,
            "eval_f1": 0.7911899758736088,
            "eval_recall": 0.8009769933816577,
            "eval_accuracy": 0.9734514220924387,
            "eval_precision": 0.781639243426111,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6749555950266429,
                    "recall": 0.7392996108949417,
                    "f1-score": 0.7056638811513464,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.7037484885126964,
                    "recall": 0.6643835616438356,
                    "f1-score": 0.6834997064004698,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8679142934635204,
                    "recall": 0.910643141718839,
                    "f1-score": 0.8887654492431607,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.626882966396292,
                    "recall": 0.5829741379310345,
                    "f1-score": 0.6041317699609158,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.781639243426111,
                    "recall": 0.8009769933816577,
                    "f1-score": 0.7911899758736088,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.718375335849788,
                    "recall": 0.7243251130471626,
                    "f1-score": 0.7205152016889731,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7787482268627608,
                    "recall": 0.8009769933816577,
                    "f1-score": 0.7891465937274805,
                    "support": 6346
                }
            },
            "eval_runtime": 5.4752,
            "eval_samples_per_second": 748.096,
            "eval_steps_per_second": 5.845,
            "epoch": 3.6,
            "step": 9000
        },
        {
            "loss": 0.0596,
            "grad_norm": 1.9843226671218872,
            "learning_rate": 8e-06,
            "epoch": 3.602,
            "step": 9005
        },
        {
            "loss": 0.0659,
            "grad_norm": 2.0195467472076416,
            "learning_rate": 8e-06,
            "epoch": 3.604,
            "step": 9010
        },
        {
            "loss": 0.0591,
            "grad_norm": 2.4729671478271484,
            "learning_rate": 8e-06,
            "epoch": 3.606,
            "step": 9015
        },
        {
            "loss": 0.0491,
            "grad_norm": 0.9484131336212158,
            "learning_rate": 8e-06,
            "epoch": 3.608,
            "step": 9020
        },
        {
            "loss": 0.0679,
            "grad_norm": 0.9202929735183716,
            "learning_rate": 8e-06,
            "epoch": 3.61,
            "step": 9025
        },
        {
            "loss": 0.0632,
            "grad_norm": 1.896445870399475,
            "learning_rate": 8e-06,
            "epoch": 3.612,
            "step": 9030
        },
        {
            "loss": 0.0669,
            "grad_norm": 1.5597829818725586,
            "learning_rate": 8e-06,
            "epoch": 3.614,
            "step": 9035
        },
        {
            "loss": 0.0406,
            "grad_norm": 1.2635653018951416,
            "learning_rate": 8e-06,
            "epoch": 3.616,
            "step": 9040
        },
        {
            "loss": 0.05,
            "grad_norm": 1.126405954360962,
            "learning_rate": 8e-06,
            "epoch": 3.618,
            "step": 9045
        },
        {
            "loss": 0.0719,
            "grad_norm": 2.622976064682007,
            "learning_rate": 8e-06,
            "epoch": 3.62,
            "step": 9050
        },
        {
            "loss": 0.0625,
            "grad_norm": 1.6710870265960693,
            "learning_rate": 8e-06,
            "epoch": 3.622,
            "step": 9055
        },
        {
            "loss": 0.0623,
            "grad_norm": 2.7407519817352295,
            "learning_rate": 8e-06,
            "epoch": 3.624,
            "step": 9060
        },
        {
            "loss": 0.0582,
            "grad_norm": 0.9846726655960083,
            "learning_rate": 8e-06,
            "epoch": 3.626,
            "step": 9065
        },
        {
            "loss": 0.0605,
            "grad_norm": 1.436699628829956,
            "learning_rate": 8e-06,
            "epoch": 3.628,
            "step": 9070
        },
        {
            "loss": 0.056,
            "grad_norm": 1.6733222007751465,
            "learning_rate": 8e-06,
            "epoch": 3.63,
            "step": 9075
        },
        {
            "loss": 0.0711,
            "grad_norm": 1.4430930614471436,
            "learning_rate": 8e-06,
            "epoch": 3.632,
            "step": 9080
        },
        {
            "loss": 0.0763,
            "grad_norm": 3.8938775062561035,
            "learning_rate": 8e-06,
            "epoch": 3.634,
            "step": 9085
        },
        {
            "loss": 0.067,
            "grad_norm": 1.5136204957962036,
            "learning_rate": 8e-06,
            "epoch": 3.636,
            "step": 9090
        },
        {
            "loss": 0.0479,
            "grad_norm": 1.0665889978408813,
            "learning_rate": 8e-06,
            "epoch": 3.638,
            "step": 9095
        },
        {
            "loss": 0.052,
            "grad_norm": 2.122455358505249,
            "learning_rate": 8e-06,
            "epoch": 3.64,
            "step": 9100
        },
        {
            "loss": 0.0534,
            "grad_norm": 1.5709620714187622,
            "learning_rate": 8e-06,
            "epoch": 3.642,
            "step": 9105
        },
        {
            "loss": 0.0685,
            "grad_norm": 1.5025672912597656,
            "learning_rate": 8e-06,
            "epoch": 3.644,
            "step": 9110
        },
        {
            "loss": 0.053,
            "grad_norm": 1.7206823825836182,
            "learning_rate": 8e-06,
            "epoch": 3.646,
            "step": 9115
        },
        {
            "loss": 0.066,
            "grad_norm": 1.637412428855896,
            "learning_rate": 8e-06,
            "epoch": 3.648,
            "step": 9120
        },
        {
            "loss": 0.0564,
            "grad_norm": 1.8064359426498413,
            "learning_rate": 8e-06,
            "epoch": 3.65,
            "step": 9125
        },
        {
            "loss": 0.0714,
            "grad_norm": 1.839477777481079,
            "learning_rate": 8e-06,
            "epoch": 3.652,
            "step": 9130
        },
        {
            "loss": 0.0524,
            "grad_norm": 2.8026604652404785,
            "learning_rate": 8e-06,
            "epoch": 3.654,
            "step": 9135
        },
        {
            "loss": 0.0613,
            "grad_norm": 1.3419278860092163,
            "learning_rate": 8e-06,
            "epoch": 3.656,
            "step": 9140
        },
        {
            "loss": 0.0572,
            "grad_norm": 1.566048264503479,
            "learning_rate": 8e-06,
            "epoch": 3.658,
            "step": 9145
        },
        {
            "loss": 0.0674,
            "grad_norm": 2.4811923503875732,
            "learning_rate": 8e-06,
            "epoch": 3.66,
            "step": 9150
        },
        {
            "loss": 0.0639,
            "grad_norm": 1.7168813943862915,
            "learning_rate": 8e-06,
            "epoch": 3.662,
            "step": 9155
        },
        {
            "loss": 0.055,
            "grad_norm": 1.4167128801345825,
            "learning_rate": 8e-06,
            "epoch": 3.664,
            "step": 9160
        },
        {
            "loss": 0.0592,
            "grad_norm": 1.157570242881775,
            "learning_rate": 8e-06,
            "epoch": 3.666,
            "step": 9165
        },
        {
            "loss": 0.0647,
            "grad_norm": 1.6890606880187988,
            "learning_rate": 8e-06,
            "epoch": 3.668,
            "step": 9170
        },
        {
            "loss": 0.0683,
            "grad_norm": 2.16872501373291,
            "learning_rate": 8e-06,
            "epoch": 3.67,
            "step": 9175
        },
        {
            "loss": 0.0595,
            "grad_norm": 1.3891710042953491,
            "learning_rate": 8e-06,
            "epoch": 3.672,
            "step": 9180
        },
        {
            "loss": 0.0563,
            "grad_norm": 1.7667551040649414,
            "learning_rate": 8e-06,
            "epoch": 3.674,
            "step": 9185
        },
        {
            "loss": 0.0678,
            "grad_norm": 2.3562090396881104,
            "learning_rate": 8e-06,
            "epoch": 3.676,
            "step": 9190
        },
        {
            "loss": 0.0589,
            "grad_norm": 1.7532329559326172,
            "learning_rate": 8e-06,
            "epoch": 3.678,
            "step": 9195
        },
        {
            "loss": 0.064,
            "grad_norm": 1.7924787998199463,
            "learning_rate": 8e-06,
            "epoch": 3.68,
            "step": 9200
        },
        {
            "loss": 0.0623,
            "grad_norm": 2.6511549949645996,
            "learning_rate": 8e-06,
            "epoch": 3.682,
            "step": 9205
        },
        {
            "loss": 0.072,
            "grad_norm": 2.0434536933898926,
            "learning_rate": 8e-06,
            "epoch": 3.684,
            "step": 9210
        },
        {
            "loss": 0.077,
            "grad_norm": 1.3607088327407837,
            "learning_rate": 8e-06,
            "epoch": 3.686,
            "step": 9215
        },
        {
            "loss": 0.0489,
            "grad_norm": 1.7675492763519287,
            "learning_rate": 8e-06,
            "epoch": 3.6879999999999997,
            "step": 9220
        },
        {
            "loss": 0.057,
            "grad_norm": 2.160468816757202,
            "learning_rate": 8e-06,
            "epoch": 3.69,
            "step": 9225
        },
        {
            "loss": 0.0658,
            "grad_norm": 1.5233378410339355,
            "learning_rate": 8e-06,
            "epoch": 3.692,
            "step": 9230
        },
        {
            "loss": 0.0646,
            "grad_norm": 1.187113642692566,
            "learning_rate": 8e-06,
            "epoch": 3.694,
            "step": 9235
        },
        {
            "loss": 0.0639,
            "grad_norm": 2.3621163368225098,
            "learning_rate": 8e-06,
            "epoch": 3.6959999999999997,
            "step": 9240
        },
        {
            "loss": 0.0645,
            "grad_norm": 1.3223092555999756,
            "learning_rate": 8e-06,
            "epoch": 3.698,
            "step": 9245
        },
        {
            "loss": 0.0764,
            "grad_norm": 1.8085476160049438,
            "learning_rate": 8e-06,
            "epoch": 3.7,
            "step": 9250
        },
        {
            "loss": 0.0475,
            "grad_norm": 1.7277330160140991,
            "learning_rate": 8e-06,
            "epoch": 3.702,
            "step": 9255
        },
        {
            "loss": 0.0665,
            "grad_norm": 1.308441400527954,
            "learning_rate": 8e-06,
            "epoch": 3.7039999999999997,
            "step": 9260
        },
        {
            "loss": 0.0589,
            "grad_norm": 2.3320040702819824,
            "learning_rate": 8e-06,
            "epoch": 3.706,
            "step": 9265
        },
        {
            "loss": 0.0607,
            "grad_norm": 4.2476701736450195,
            "learning_rate": 8e-06,
            "epoch": 3.708,
            "step": 9270
        },
        {
            "loss": 0.0665,
            "grad_norm": 1.3882185220718384,
            "learning_rate": 8e-06,
            "epoch": 3.71,
            "step": 9275
        },
        {
            "loss": 0.068,
            "grad_norm": 1.5096240043640137,
            "learning_rate": 8e-06,
            "epoch": 3.7119999999999997,
            "step": 9280
        },
        {
            "loss": 0.0682,
            "grad_norm": 2.242079257965088,
            "learning_rate": 8e-06,
            "epoch": 3.714,
            "step": 9285
        },
        {
            "loss": 0.0575,
            "grad_norm": 1.2935901880264282,
            "learning_rate": 8e-06,
            "epoch": 3.716,
            "step": 9290
        },
        {
            "loss": 0.0513,
            "grad_norm": 1.2026594877243042,
            "learning_rate": 8e-06,
            "epoch": 3.718,
            "step": 9295
        },
        {
            "loss": 0.0717,
            "grad_norm": 2.5918827056884766,
            "learning_rate": 8e-06,
            "epoch": 3.7199999999999998,
            "step": 9300
        },
        {
            "eval_loss": 0.07929243892431259,
            "eval_f1": 0.7874806800618238,
            "eval_recall": 0.8028679483138985,
            "eval_accuracy": 0.9733711987506551,
            "eval_precision": 0.7726721261753109,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6675369886858138,
                    "recall": 0.7461089494163424,
                    "f1-score": 0.7046394120349104,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6926658905704307,
                    "recall": 0.6792237442922374,
                    "f1-score": 0.6858789625360231,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8693259972489684,
                    "recall": 0.8992601024473534,
                    "f1-score": 0.8840397258357813,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.6025236593059937,
                    "recall": 0.6174568965517241,
                    "f1-score": 0.6098988823842469,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7726721261753109,
                    "recall": 0.8028679483138985,
                    "f1-score": 0.7874806800618238,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.7080131339528015,
                    "recall": 0.7355124231769143,
                    "f1-score": 0.7211142456977404,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7732361888871022,
                    "recall": 0.8028679483138985,
                    "f1-score": 0.7875356202636243,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4569,
            "eval_samples_per_second": 919.031,
            "eval_steps_per_second": 7.18,
            "epoch": 3.7199999999999998,
            "step": 9300
        },
        {
            "loss": 0.05,
            "grad_norm": 2.3970115184783936,
            "learning_rate": 8e-06,
            "epoch": 3.722,
            "step": 9305
        },
        {
            "loss": 0.0656,
            "grad_norm": 1.445888638496399,
            "learning_rate": 8e-06,
            "epoch": 3.724,
            "step": 9310
        },
        {
            "loss": 0.063,
            "grad_norm": 2.908632278442383,
            "learning_rate": 8e-06,
            "epoch": 3.726,
            "step": 9315
        },
        {
            "loss": 0.0632,
            "grad_norm": 1.4150112867355347,
            "learning_rate": 8e-06,
            "epoch": 3.7279999999999998,
            "step": 9320
        },
        {
            "loss": 0.0642,
            "grad_norm": 1.4881550073623657,
            "learning_rate": 8e-06,
            "epoch": 3.73,
            "step": 9325
        },
        {
            "loss": 0.0668,
            "grad_norm": 3.3821842670440674,
            "learning_rate": 8e-06,
            "epoch": 3.732,
            "step": 9330
        },
        {
            "loss": 0.0539,
            "grad_norm": 1.7119593620300293,
            "learning_rate": 8e-06,
            "epoch": 3.734,
            "step": 9335
        },
        {
            "loss": 0.0546,
            "grad_norm": 1.5257060527801514,
            "learning_rate": 8e-06,
            "epoch": 3.7359999999999998,
            "step": 9340
        },
        {
            "loss": 0.0611,
            "grad_norm": 1.5467032194137573,
            "learning_rate": 8e-06,
            "epoch": 3.738,
            "step": 9345
        },
        {
            "loss": 0.0592,
            "grad_norm": 1.3341357707977295,
            "learning_rate": 8e-06,
            "epoch": 3.74,
            "step": 9350
        },
        {
            "loss": 0.0562,
            "grad_norm": 1.4406683444976807,
            "learning_rate": 8e-06,
            "epoch": 3.742,
            "step": 9355
        },
        {
            "loss": 0.059,
            "grad_norm": 1.2769895792007446,
            "learning_rate": 8e-06,
            "epoch": 3.7439999999999998,
            "step": 9360
        },
        {
            "loss": 0.0618,
            "grad_norm": 1.8561174869537354,
            "learning_rate": 8e-06,
            "epoch": 3.746,
            "step": 9365
        },
        {
            "loss": 0.0642,
            "grad_norm": 1.0985785722732544,
            "learning_rate": 8e-06,
            "epoch": 3.748,
            "step": 9370
        },
        {
            "loss": 0.0641,
            "grad_norm": 1.6753166913986206,
            "learning_rate": 8e-06,
            "epoch": 3.75,
            "step": 9375
        },
        {
            "loss": 0.0609,
            "grad_norm": 1.2929069995880127,
            "learning_rate": 8e-06,
            "epoch": 3.752,
            "step": 9380
        },
        {
            "loss": 0.0578,
            "grad_norm": 2.1930458545684814,
            "learning_rate": 8e-06,
            "epoch": 3.754,
            "step": 9385
        },
        {
            "loss": 0.0603,
            "grad_norm": 1.2991464138031006,
            "learning_rate": 8e-06,
            "epoch": 3.7560000000000002,
            "step": 9390
        },
        {
            "loss": 0.0541,
            "grad_norm": 1.7394887208938599,
            "learning_rate": 8e-06,
            "epoch": 3.758,
            "step": 9395
        },
        {
            "loss": 0.0622,
            "grad_norm": 1.9924023151397705,
            "learning_rate": 8e-06,
            "epoch": 3.76,
            "step": 9400
        },
        {
            "loss": 0.061,
            "grad_norm": 1.8349542617797852,
            "learning_rate": 8e-06,
            "epoch": 3.762,
            "step": 9405
        },
        {
            "loss": 0.0505,
            "grad_norm": 1.3267790079116821,
            "learning_rate": 8e-06,
            "epoch": 3.7640000000000002,
            "step": 9410
        },
        {
            "loss": 0.0641,
            "grad_norm": 2.636303424835205,
            "learning_rate": 8e-06,
            "epoch": 3.766,
            "step": 9415
        },
        {
            "loss": 0.0552,
            "grad_norm": 1.2574602365493774,
            "learning_rate": 8e-06,
            "epoch": 3.768,
            "step": 9420
        },
        {
            "loss": 0.0676,
            "grad_norm": 3.1541645526885986,
            "learning_rate": 8e-06,
            "epoch": 3.77,
            "step": 9425
        },
        {
            "loss": 0.0525,
            "grad_norm": 1.8504595756530762,
            "learning_rate": 8e-06,
            "epoch": 3.7720000000000002,
            "step": 9430
        },
        {
            "loss": 0.0523,
            "grad_norm": 1.7444342374801636,
            "learning_rate": 8e-06,
            "epoch": 3.774,
            "step": 9435
        },
        {
            "loss": 0.0604,
            "grad_norm": 1.3693537712097168,
            "learning_rate": 8e-06,
            "epoch": 3.776,
            "step": 9440
        },
        {
            "loss": 0.0525,
            "grad_norm": 1.279012680053711,
            "learning_rate": 8e-06,
            "epoch": 3.778,
            "step": 9445
        },
        {
            "loss": 0.0548,
            "grad_norm": 1.9149588346481323,
            "learning_rate": 8e-06,
            "epoch": 3.7800000000000002,
            "step": 9450
        },
        {
            "loss": 0.0487,
            "grad_norm": 1.25267493724823,
            "learning_rate": 8e-06,
            "epoch": 3.782,
            "step": 9455
        },
        {
            "loss": 0.0485,
            "grad_norm": 2.1233396530151367,
            "learning_rate": 8e-06,
            "epoch": 3.784,
            "step": 9460
        },
        {
            "loss": 0.0569,
            "grad_norm": 3.061711072921753,
            "learning_rate": 8e-06,
            "epoch": 3.786,
            "step": 9465
        },
        {
            "loss": 0.0597,
            "grad_norm": 1.655897617340088,
            "learning_rate": 8e-06,
            "epoch": 3.7880000000000003,
            "step": 9470
        },
        {
            "loss": 0.0641,
            "grad_norm": 1.7936134338378906,
            "learning_rate": 8e-06,
            "epoch": 3.79,
            "step": 9475
        },
        {
            "loss": 0.0653,
            "grad_norm": 2.540442943572998,
            "learning_rate": 8e-06,
            "epoch": 3.792,
            "step": 9480
        },
        {
            "loss": 0.0584,
            "grad_norm": 2.375387191772461,
            "learning_rate": 8e-06,
            "epoch": 3.794,
            "step": 9485
        },
        {
            "loss": 0.0572,
            "grad_norm": 2.1083993911743164,
            "learning_rate": 8e-06,
            "epoch": 3.7960000000000003,
            "step": 9490
        },
        {
            "loss": 0.065,
            "grad_norm": 1.196303367614746,
            "learning_rate": 8e-06,
            "epoch": 3.798,
            "step": 9495
        },
        {
            "loss": 0.0545,
            "grad_norm": 3.649332046508789,
            "learning_rate": 8e-06,
            "epoch": 3.8,
            "step": 9500
        },
        {
            "loss": 0.066,
            "grad_norm": 1.569014310836792,
            "learning_rate": 8e-06,
            "epoch": 3.802,
            "step": 9505
        },
        {
            "loss": 0.0709,
            "grad_norm": 1.9241915941238403,
            "learning_rate": 8e-06,
            "epoch": 3.8040000000000003,
            "step": 9510
        },
        {
            "loss": 0.0505,
            "grad_norm": 0.8684083819389343,
            "learning_rate": 8e-06,
            "epoch": 3.806,
            "step": 9515
        },
        {
            "loss": 0.0696,
            "grad_norm": 4.363123893737793,
            "learning_rate": 8e-06,
            "epoch": 3.808,
            "step": 9520
        },
        {
            "loss": 0.0623,
            "grad_norm": 4.481400966644287,
            "learning_rate": 8e-06,
            "epoch": 3.81,
            "step": 9525
        },
        {
            "loss": 0.0626,
            "grad_norm": 0.8018396496772766,
            "learning_rate": 8e-06,
            "epoch": 3.8120000000000003,
            "step": 9530
        },
        {
            "loss": 0.0409,
            "grad_norm": 1.2935986518859863,
            "learning_rate": 8e-06,
            "epoch": 3.814,
            "step": 9535
        },
        {
            "loss": 0.0721,
            "grad_norm": 1.5226695537567139,
            "learning_rate": 8e-06,
            "epoch": 3.816,
            "step": 9540
        },
        {
            "loss": 0.0712,
            "grad_norm": 2.114611864089966,
            "learning_rate": 8e-06,
            "epoch": 3.818,
            "step": 9545
        },
        {
            "loss": 0.0728,
            "grad_norm": 2.736205816268921,
            "learning_rate": 8e-06,
            "epoch": 3.82,
            "step": 9550
        },
        {
            "loss": 0.0844,
            "grad_norm": 1.632352590560913,
            "learning_rate": 8e-06,
            "epoch": 3.822,
            "step": 9555
        },
        {
            "loss": 0.0677,
            "grad_norm": 2.619251012802124,
            "learning_rate": 8e-06,
            "epoch": 3.824,
            "step": 9560
        },
        {
            "loss": 0.0664,
            "grad_norm": 2.1190075874328613,
            "learning_rate": 8e-06,
            "epoch": 3.826,
            "step": 9565
        },
        {
            "loss": 0.0592,
            "grad_norm": 1.5711067914962769,
            "learning_rate": 8e-06,
            "epoch": 3.828,
            "step": 9570
        },
        {
            "loss": 0.055,
            "grad_norm": 1.7190828323364258,
            "learning_rate": 8e-06,
            "epoch": 3.83,
            "step": 9575
        },
        {
            "loss": 0.0629,
            "grad_norm": 1.5764851570129395,
            "learning_rate": 8e-06,
            "epoch": 3.832,
            "step": 9580
        },
        {
            "loss": 0.0617,
            "grad_norm": 1.5081696510314941,
            "learning_rate": 8e-06,
            "epoch": 3.834,
            "step": 9585
        },
        {
            "loss": 0.052,
            "grad_norm": 1.3117311000823975,
            "learning_rate": 8e-06,
            "epoch": 3.836,
            "step": 9590
        },
        {
            "loss": 0.0606,
            "grad_norm": 1.7069602012634277,
            "learning_rate": 8e-06,
            "epoch": 3.838,
            "step": 9595
        },
        {
            "loss": 0.0697,
            "grad_norm": 1.7236192226409912,
            "learning_rate": 8e-06,
            "epoch": 3.84,
            "step": 9600
        },
        {
            "eval_loss": 0.0778723731637001,
            "eval_f1": 0.7926253001781703,
            "eval_recall": 0.8061771194453199,
            "eval_accuracy": 0.9739274139203543,
            "eval_precision": 0.7795215602620753,
            "eval_classification_report": {
                "LOC": {
                    "precision": 0.6896860986547085,
                    "recall": 0.7480544747081712,
                    "f1-score": 0.7176854876341577,
                    "support": 1028
                },
                "ORG": {
                    "precision": 0.6923076923076923,
                    "recall": 0.678082191780822,
                    "f1-score": 0.685121107266436,
                    "support": 876
                },
                "PER": {
                    "precision": 0.8776758409785933,
                    "recall": 0.898406374501992,
                    "f1-score": 0.8879201237519336,
                    "support": 3514
                },
                "PRD": {
                    "precision": 0.6002014098690835,
                    "recall": 0.6422413793103449,
                    "f1-score": 0.62051015096304,
                    "support": 928
                },
                "micro avg": {
                    "precision": 0.7795215602620753,
                    "recall": 0.8061771194453199,
                    "f1-score": 0.7926253001781703,
                    "support": 6346
                },
                "macro avg": {
                    "precision": 0.7149677604525195,
                    "recall": 0.7416961050753325,
                    "f1-score": 0.7278092174038917,
                    "support": 6346
                },
                "weighted avg": {
                    "precision": 0.7810587238316836,
                    "recall": 0.8061771194453199,
                    "f1-score": 0.7932448008527115,
                    "support": 6346
                }
            },
            "eval_runtime": 4.4594,
            "eval_samples_per_second": 918.517,
            "eval_steps_per_second": 7.176,
            "epoch": 3.84,
            "step": 9600
        }
    ],
    "best_metric": null,
    "best_model_checkpoint": null,
    "is_local_process_zero": true,
    "is_world_process_zero": true,
    "is_hyper_param_search": false,
    "trial_name": null,
    "trial_params": null,
    "stateful_callbacks": {
        "TrainerControl": {
            "args": {
                "should_training_stop": false,
                "should_epoch_stop": false,
                "should_save": false,
                "should_evaluate": false,
                "should_log": false
            },
            "attributes": {}
        }
    }
}