{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14715349949415985,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00036788374873539964,
      "eval_loss": 2.4577674865722656,
      "eval_runtime": 112.2373,
      "eval_samples_per_second": 10.202,
      "eval_steps_per_second": 5.105,
      "step": 1
    },
    {
      "epoch": 0.001839418743676998,
      "grad_norm": 0.8280420303344727,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 9.5252,
      "step": 5
    },
    {
      "epoch": 0.003678837487353996,
      "grad_norm": 0.9618687033653259,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 9.5181,
      "step": 10
    },
    {
      "epoch": 0.005518256231030994,
      "grad_norm": 1.3654139041900635,
      "learning_rate": 5e-05,
      "loss": 9.7815,
      "step": 15
    },
    {
      "epoch": 0.007357674974707992,
      "grad_norm": 1.9203743934631348,
      "learning_rate": 6.666666666666667e-05,
      "loss": 9.3567,
      "step": 20
    },
    {
      "epoch": 0.00919709371838499,
      "grad_norm": 1.9197553396224976,
      "learning_rate": 8.333333333333334e-05,
      "loss": 8.4937,
      "step": 25
    },
    {
      "epoch": 0.011036512462061988,
      "grad_norm": 2.091545343399048,
      "learning_rate": 0.0001,
      "loss": 8.1682,
      "step": 30
    },
    {
      "epoch": 0.012875931205738987,
      "grad_norm": 3.067678928375244,
      "learning_rate": 9.995494831023409e-05,
      "loss": 7.3596,
      "step": 35
    },
    {
      "epoch": 0.014715349949415984,
      "grad_norm": 2.219508409500122,
      "learning_rate": 9.981987442712633e-05,
      "loss": 6.8717,
      "step": 40
    },
    {
      "epoch": 0.016554768693092983,
      "grad_norm": 2.6248016357421875,
      "learning_rate": 9.959502176294383e-05,
      "loss": 6.4147,
      "step": 45
    },
    {
      "epoch": 0.01839418743676998,
      "grad_norm": 4.349789619445801,
      "learning_rate": 9.928079551738543e-05,
      "loss": 5.7112,
      "step": 50
    },
    {
      "epoch": 0.020233606180446978,
      "grad_norm": 2.7610251903533936,
      "learning_rate": 9.887776194738432e-05,
      "loss": 7.0983,
      "step": 55
    },
    {
      "epoch": 0.022073024924123975,
      "grad_norm": 2.097891092300415,
      "learning_rate": 9.838664734667495e-05,
      "loss": 6.49,
      "step": 60
    },
    {
      "epoch": 0.023912443667800976,
      "grad_norm": 2.097975730895996,
      "learning_rate": 9.780833673696254e-05,
      "loss": 6.3915,
      "step": 65
    },
    {
      "epoch": 0.025751862411477974,
      "grad_norm": 2.758938789367676,
      "learning_rate": 9.714387227305422e-05,
      "loss": 6.1658,
      "step": 70
    },
    {
      "epoch": 0.02759128115515497,
      "grad_norm": 2.5158843994140625,
      "learning_rate": 9.639445136482548e-05,
      "loss": 5.973,
      "step": 75
    },
    {
      "epoch": 0.02943069989883197,
      "grad_norm": 2.327061414718628,
      "learning_rate": 9.55614245194068e-05,
      "loss": 5.8564,
      "step": 80
    },
    {
      "epoch": 0.03127011864250897,
      "grad_norm": 2.72761869430542,
      "learning_rate": 9.464629290747842e-05,
      "loss": 5.6626,
      "step": 85
    },
    {
      "epoch": 0.03310953738618597,
      "grad_norm": 2.809091091156006,
      "learning_rate": 9.365070565805941e-05,
      "loss": 5.759,
      "step": 90
    },
    {
      "epoch": 0.034948956129862964,
      "grad_norm": 3.292855978012085,
      "learning_rate": 9.257645688666556e-05,
      "loss": 5.6545,
      "step": 95
    },
    {
      "epoch": 0.03678837487353996,
      "grad_norm": 4.276185512542725,
      "learning_rate": 9.142548246219212e-05,
      "loss": 5.5527,
      "step": 100
    },
    {
      "epoch": 0.03678837487353996,
      "eval_loss": 1.4643136262893677,
      "eval_runtime": 113.5811,
      "eval_samples_per_second": 10.081,
      "eval_steps_per_second": 5.045,
      "step": 100
    },
    {
      "epoch": 0.03862779361721696,
      "grad_norm": 2.679311752319336,
      "learning_rate": 9.019985651834703e-05,
      "loss": 6.2604,
      "step": 105
    },
    {
      "epoch": 0.040467212360893956,
      "grad_norm": 2.35363507270813,
      "learning_rate": 8.890178771592199e-05,
      "loss": 5.8234,
      "step": 110
    },
    {
      "epoch": 0.04230663110457095,
      "grad_norm": 2.542659044265747,
      "learning_rate": 8.753361526263621e-05,
      "loss": 5.7194,
      "step": 115
    },
    {
      "epoch": 0.04414604984824795,
      "grad_norm": 3.0282368659973145,
      "learning_rate": 8.609780469772623e-05,
      "loss": 5.759,
      "step": 120
    },
    {
      "epoch": 0.045985468591924955,
      "grad_norm": 2.7836074829101562,
      "learning_rate": 8.459694344887732e-05,
      "loss": 5.7397,
      "step": 125
    },
    {
      "epoch": 0.04782488733560195,
      "grad_norm": 3.0715341567993164,
      "learning_rate": 8.303373616950408e-05,
      "loss": 5.5474,
      "step": 130
    },
    {
      "epoch": 0.04966430607927895,
      "grad_norm": 2.9016990661621094,
      "learning_rate": 8.141099986478212e-05,
      "loss": 5.5474,
      "step": 135
    },
    {
      "epoch": 0.05150372482295595,
      "grad_norm": 3.3964619636535645,
      "learning_rate": 7.973165881521434e-05,
      "loss": 5.3662,
      "step": 140
    },
    {
      "epoch": 0.053343143566632945,
      "grad_norm": 3.3130300045013428,
      "learning_rate": 7.799873930687978e-05,
      "loss": 5.3101,
      "step": 145
    },
    {
      "epoch": 0.05518256231030994,
      "grad_norm": 4.319330215454102,
      "learning_rate": 7.621536417786159e-05,
      "loss": 4.9975,
      "step": 150
    },
    {
      "epoch": 0.05702198105398694,
      "grad_norm": 3.213869094848633,
      "learning_rate": 7.438474719068173e-05,
      "loss": 6.1274,
      "step": 155
    },
    {
      "epoch": 0.05886139979766394,
      "grad_norm": 2.622100353240967,
      "learning_rate": 7.251018724088367e-05,
      "loss": 5.7882,
      "step": 160
    },
    {
      "epoch": 0.060700818541340934,
      "grad_norm": 3.130568504333496,
      "learning_rate": 7.059506241219965e-05,
      "loss": 5.9381,
      "step": 165
    },
    {
      "epoch": 0.06254023728501794,
      "grad_norm": 2.869192361831665,
      "learning_rate": 6.864282388901544e-05,
      "loss": 5.5488,
      "step": 170
    },
    {
      "epoch": 0.06437965602869493,
      "grad_norm": 3.0501046180725098,
      "learning_rate": 6.665698973710288e-05,
      "loss": 5.5089,
      "step": 175
    },
    {
      "epoch": 0.06621907477237193,
      "grad_norm": 2.932879686355591,
      "learning_rate": 6.464113856382752e-05,
      "loss": 5.2593,
      "step": 180
    },
    {
      "epoch": 0.06805849351604892,
      "grad_norm": 3.290214776992798,
      "learning_rate": 6.259890306925627e-05,
      "loss": 5.361,
      "step": 185
    },
    {
      "epoch": 0.06989791225972593,
      "grad_norm": 3.387301206588745,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 5.0956,
      "step": 190
    },
    {
      "epoch": 0.07173733100340292,
      "grad_norm": 3.709397554397583,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 5.2804,
      "step": 195
    },
    {
      "epoch": 0.07357674974707992,
      "grad_norm": 3.7642862796783447,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 5.0599,
      "step": 200
    },
    {
      "epoch": 0.07357674974707992,
      "eval_loss": 1.37430739402771,
      "eval_runtime": 113.5636,
      "eval_samples_per_second": 10.082,
      "eval_steps_per_second": 5.046,
      "step": 200
    },
    {
      "epoch": 0.07541616849075693,
      "grad_norm": 3.2448863983154297,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 5.7563,
      "step": 205
    },
    {
      "epoch": 0.07725558723443392,
      "grad_norm": 2.951735496520996,
      "learning_rate": 5.212206015980742e-05,
      "loss": 5.6391,
      "step": 210
    },
    {
      "epoch": 0.07909500597811092,
      "grad_norm": 3.1694722175598145,
      "learning_rate": 5e-05,
      "loss": 5.6285,
      "step": 215
    },
    {
      "epoch": 0.08093442472178791,
      "grad_norm": 3.165539026260376,
      "learning_rate": 4.78779398401926e-05,
      "loss": 5.3206,
      "step": 220
    },
    {
      "epoch": 0.08277384346546492,
      "grad_norm": 3.699326515197754,
      "learning_rate": 4.575970377622456e-05,
      "loss": 5.3481,
      "step": 225
    },
    {
      "epoch": 0.0846132622091419,
      "grad_norm": 3.6325888633728027,
      "learning_rate": 4.364910901265606e-05,
      "loss": 5.4734,
      "step": 230
    },
    {
      "epoch": 0.08645268095281891,
      "grad_norm": 3.2507312297821045,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 5.3317,
      "step": 235
    },
    {
      "epoch": 0.0882920996964959,
      "grad_norm": 3.554300308227539,
      "learning_rate": 3.94660365002137e-05,
      "loss": 5.002,
      "step": 240
    },
    {
      "epoch": 0.0901315184401729,
      "grad_norm": 4.213696002960205,
      "learning_rate": 3.740109693074375e-05,
      "loss": 4.9878,
      "step": 245
    },
    {
      "epoch": 0.09197093718384991,
      "grad_norm": 5.890469551086426,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 4.804,
      "step": 250
    },
    {
      "epoch": 0.0938103559275269,
      "grad_norm": 4.224252223968506,
      "learning_rate": 3.334301026289712e-05,
      "loss": 5.7972,
      "step": 255
    },
    {
      "epoch": 0.0956497746712039,
      "grad_norm": 3.418585777282715,
      "learning_rate": 3.135717611098458e-05,
      "loss": 5.6721,
      "step": 260
    },
    {
      "epoch": 0.0974891934148809,
      "grad_norm": 3.128255844116211,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 5.5736,
      "step": 265
    },
    {
      "epoch": 0.0993286121585579,
      "grad_norm": 3.1626009941101074,
      "learning_rate": 2.748981275911633e-05,
      "loss": 5.4318,
      "step": 270
    },
    {
      "epoch": 0.10116803090223489,
      "grad_norm": 3.325432538986206,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 5.5074,
      "step": 275
    },
    {
      "epoch": 0.1030074496459119,
      "grad_norm": 3.587782144546509,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 5.1664,
      "step": 280
    },
    {
      "epoch": 0.10484686838958888,
      "grad_norm": 3.5791549682617188,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 5.3143,
      "step": 285
    },
    {
      "epoch": 0.10668628713326589,
      "grad_norm": 3.5152134895324707,
      "learning_rate": 2.026834118478567e-05,
      "loss": 5.1506,
      "step": 290
    },
    {
      "epoch": 0.10852570587694288,
      "grad_norm": 3.811131000518799,
      "learning_rate": 1.858900013521788e-05,
      "loss": 4.8958,
      "step": 295
    },
    {
      "epoch": 0.11036512462061988,
      "grad_norm": 5.474424362182617,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 4.7134,
      "step": 300
    },
    {
      "epoch": 0.11036512462061988,
      "eval_loss": 1.3311870098114014,
      "eval_runtime": 113.5734,
      "eval_samples_per_second": 10.082,
      "eval_steps_per_second": 5.045,
      "step": 300
    },
    {
      "epoch": 0.11220454336429689,
      "grad_norm": 3.599816083908081,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 5.7563,
      "step": 305
    },
    {
      "epoch": 0.11404396210797388,
      "grad_norm": 3.3748738765716553,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 5.7474,
      "step": 310
    },
    {
      "epoch": 0.11588338085165088,
      "grad_norm": 3.2355871200561523,
      "learning_rate": 1.246638473736378e-05,
      "loss": 5.7403,
      "step": 315
    },
    {
      "epoch": 0.11772279959532787,
      "grad_norm": 3.1642491817474365,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 5.5903,
      "step": 320
    },
    {
      "epoch": 0.11956221833900488,
      "grad_norm": 3.0514121055603027,
      "learning_rate": 9.800143481652979e-06,
      "loss": 5.4359,
      "step": 325
    },
    {
      "epoch": 0.12140163708268187,
      "grad_norm": 3.2304811477661133,
      "learning_rate": 8.574517537807897e-06,
      "loss": 5.2602,
      "step": 330
    },
    {
      "epoch": 0.12324105582635887,
      "grad_norm": 3.596357583999634,
      "learning_rate": 7.423543113334436e-06,
      "loss": 5.2125,
      "step": 335
    },
    {
      "epoch": 0.12508047457003588,
      "grad_norm": 3.4694998264312744,
      "learning_rate": 6.349294341940593e-06,
      "loss": 4.9665,
      "step": 340
    },
    {
      "epoch": 0.12691989331371287,
      "grad_norm": 4.421322345733643,
      "learning_rate": 5.353707092521582e-06,
      "loss": 5.0172,
      "step": 345
    },
    {
      "epoch": 0.12875931205738986,
      "grad_norm": 7.54664421081543,
      "learning_rate": 4.43857548059321e-06,
      "loss": 5.004,
      "step": 350
    },
    {
      "epoch": 0.13059873080106688,
      "grad_norm": 3.203753709793091,
      "learning_rate": 3.605548635174533e-06,
      "loss": 5.4771,
      "step": 355
    },
    {
      "epoch": 0.13243814954474387,
      "grad_norm": 3.195307970046997,
      "learning_rate": 2.85612772694579e-06,
      "loss": 5.6448,
      "step": 360
    },
    {
      "epoch": 0.13427756828842086,
      "grad_norm": 3.1105239391326904,
      "learning_rate": 2.191663263037458e-06,
      "loss": 5.4492,
      "step": 365
    },
    {
      "epoch": 0.13611698703209785,
      "grad_norm": 3.306166648864746,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 5.2933,
      "step": 370
    },
    {
      "epoch": 0.13795640577577487,
      "grad_norm": 3.3269877433776855,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 5.2259,
      "step": 375
    },
    {
      "epoch": 0.13979582451945186,
      "grad_norm": 3.450143814086914,
      "learning_rate": 7.192044826145771e-07,
      "loss": 5.2903,
      "step": 380
    },
    {
      "epoch": 0.14163524326312885,
      "grad_norm": 3.320021867752075,
      "learning_rate": 4.049782370561583e-07,
      "loss": 5.322,
      "step": 385
    },
    {
      "epoch": 0.14347466200680584,
      "grad_norm": 3.6967437267303467,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 5.1866,
      "step": 390
    },
    {
      "epoch": 0.14531408075048285,
      "grad_norm": 3.773526668548584,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 5.2132,
      "step": 395
    },
    {
      "epoch": 0.14715349949415985,
      "grad_norm": 6.1009931564331055,
      "learning_rate": 0.0,
      "loss": 4.8495,
      "step": 400
    },
    {
      "epoch": 0.14715349949415985,
      "eval_loss": 1.319486141204834,
      "eval_runtime": 113.5557,
      "eval_samples_per_second": 10.083,
      "eval_steps_per_second": 5.046,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.302999393632256e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}