{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.20011168718338013,
      "learning_rate": 9.928057553956835e-05,
      "loss": 1.5743,
      "step": 10
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.410460501909256,
      "learning_rate": 9.784172661870504e-05,
      "loss": 1.1382,
      "step": 20
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.24360999464988708,
      "learning_rate": 9.640287769784174e-05,
      "loss": 0.587,
      "step": 30
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.07866887748241425,
      "learning_rate": 9.496402877697842e-05,
      "loss": 0.4484,
      "step": 40
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.1024688109755516,
      "learning_rate": 9.35251798561151e-05,
      "loss": 0.3484,
      "step": 50
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.07728195190429688,
      "learning_rate": 9.20863309352518e-05,
      "loss": 0.3599,
      "step": 60
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.07939107716083527,
      "learning_rate": 9.06474820143885e-05,
      "loss": 0.353,
      "step": 70
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.07889492064714432,
      "learning_rate": 8.920863309352519e-05,
      "loss": 0.3237,
      "step": 80
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.08044611662626266,
      "learning_rate": 8.776978417266187e-05,
      "loss": 0.3519,
      "step": 90
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.08084924519062042,
      "learning_rate": 8.633093525179857e-05,
      "loss": 0.354,
      "step": 100
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.08062956482172012,
      "learning_rate": 8.489208633093527e-05,
      "loss": 0.3886,
      "step": 110
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.07981599122285843,
      "learning_rate": 8.345323741007195e-05,
      "loss": 0.3534,
      "step": 120
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.09865035861730576,
      "learning_rate": 8.201438848920863e-05,
      "loss": 0.3536,
      "step": 130
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.08893056213855743,
      "learning_rate": 8.057553956834533e-05,
      "loss": 0.3326,
      "step": 140
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.07679039984941483,
      "learning_rate": 7.913669064748202e-05,
      "loss": 0.3531,
      "step": 150
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.07035951316356659,
      "learning_rate": 7.769784172661872e-05,
      "loss": 0.3239,
      "step": 160
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 0.09360262006521225,
      "learning_rate": 7.62589928057554e-05,
      "loss": 0.3305,
      "step": 170
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.10175589472055435,
      "learning_rate": 7.48201438848921e-05,
      "loss": 0.3384,
      "step": 180
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 0.15438881516456604,
      "learning_rate": 7.338129496402878e-05,
      "loss": 0.3191,
      "step": 190
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.09196078777313232,
      "learning_rate": 7.194244604316547e-05,
      "loss": 0.2944,
      "step": 200
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.0951504111289978,
      "learning_rate": 7.050359712230215e-05,
      "loss": 0.3055,
      "step": 210
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.09340916574001312,
      "learning_rate": 6.906474820143886e-05,
      "loss": 0.3222,
      "step": 220
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 0.08794793486595154,
      "learning_rate": 6.762589928057555e-05,
      "loss": 0.3395,
      "step": 230
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.09506211429834366,
      "learning_rate": 6.618705035971223e-05,
      "loss": 0.3386,
      "step": 240
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.09224151074886322,
      "learning_rate": 6.474820143884892e-05,
      "loss": 0.3389,
      "step": 250
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.10331781953573227,
      "learning_rate": 6.330935251798561e-05,
      "loss": 0.2951,
      "step": 260
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.10871120542287827,
      "learning_rate": 6.187050359712231e-05,
      "loss": 0.3382,
      "step": 270
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.08793390542268753,
      "learning_rate": 6.0431654676258996e-05,
      "loss": 0.3221,
      "step": 280
    },
    {
      "epoch": 2.0714285714285716,
      "grad_norm": 0.10244260728359222,
      "learning_rate": 5.899280575539569e-05,
      "loss": 0.3054,
      "step": 290
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.08769655227661133,
      "learning_rate": 5.755395683453237e-05,
      "loss": 0.28,
      "step": 300
    },
    {
      "epoch": 2.2142857142857144,
      "grad_norm": 0.10015639662742615,
      "learning_rate": 5.611510791366906e-05,
      "loss": 0.324,
      "step": 310
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.11067729443311691,
      "learning_rate": 5.467625899280576e-05,
      "loss": 0.329,
      "step": 320
    },
    {
      "epoch": 2.357142857142857,
      "grad_norm": 0.10012146830558777,
      "learning_rate": 5.323741007194245e-05,
      "loss": 0.2767,
      "step": 330
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.11153287440538406,
      "learning_rate": 5.179856115107914e-05,
      "loss": 0.3377,
      "step": 340
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.11222545802593231,
      "learning_rate": 5.035971223021583e-05,
      "loss": 0.3123,
      "step": 350
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.11043631285429001,
      "learning_rate": 4.892086330935252e-05,
      "loss": 0.3232,
      "step": 360
    },
    {
      "epoch": 2.642857142857143,
      "grad_norm": 0.11605663597583771,
      "learning_rate": 4.748201438848921e-05,
      "loss": 0.299,
      "step": 370
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.1168583557009697,
      "learning_rate": 4.60431654676259e-05,
      "loss": 0.3057,
      "step": 380
    },
    {
      "epoch": 2.7857142857142856,
      "grad_norm": 0.1063845306634903,
      "learning_rate": 4.460431654676259e-05,
      "loss": 0.2892,
      "step": 390
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.1153399869799614,
      "learning_rate": 4.3165467625899284e-05,
      "loss": 0.2884,
      "step": 400
    },
    {
      "epoch": 2.928571428571429,
      "grad_norm": 0.11235486716032028,
      "learning_rate": 4.1726618705035975e-05,
      "loss": 0.2879,
      "step": 410
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.14575359225273132,
      "learning_rate": 4.0287769784172666e-05,
      "loss": 0.3107,
      "step": 420
    },
    {
      "epoch": 3.0714285714285716,
      "grad_norm": 0.11519063264131546,
      "learning_rate": 3.884892086330936e-05,
      "loss": 0.2878,
      "step": 430
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 0.13909830152988434,
      "learning_rate": 3.741007194244605e-05,
      "loss": 0.2743,
      "step": 440
    },
    {
      "epoch": 3.2142857142857144,
      "grad_norm": 0.1268688589334488,
      "learning_rate": 3.597122302158273e-05,
      "loss": 0.2827,
      "step": 450
    },
    {
      "epoch": 3.2857142857142856,
      "grad_norm": 0.13879084587097168,
      "learning_rate": 3.453237410071943e-05,
      "loss": 0.3196,
      "step": 460
    },
    {
      "epoch": 3.357142857142857,
      "grad_norm": 0.13855186104774475,
      "learning_rate": 3.3093525179856116e-05,
      "loss": 0.2846,
      "step": 470
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 0.13305865228176117,
      "learning_rate": 3.165467625899281e-05,
      "loss": 0.2998,
      "step": 480
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.13443267345428467,
      "learning_rate": 3.0215827338129498e-05,
      "loss": 0.2742,
      "step": 490
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 0.1269126534461975,
      "learning_rate": 2.8776978417266186e-05,
      "loss": 0.2608,
      "step": 500
    },
    {
      "epoch": 3.642857142857143,
      "grad_norm": 0.1363735795021057,
      "learning_rate": 2.733812949640288e-05,
      "loss": 0.2744,
      "step": 510
    },
    {
      "epoch": 3.7142857142857144,
      "grad_norm": 0.1578550785779953,
      "learning_rate": 2.589928057553957e-05,
      "loss": 0.2922,
      "step": 520
    },
    {
      "epoch": 3.7857142857142856,
      "grad_norm": 0.1330137997865677,
      "learning_rate": 2.446043165467626e-05,
      "loss": 0.2932,
      "step": 530
    },
    {
      "epoch": 3.857142857142857,
      "grad_norm": 0.14818449318408966,
      "learning_rate": 2.302158273381295e-05,
      "loss": 0.2587,
      "step": 540
    },
    {
      "epoch": 3.928571428571429,
      "grad_norm": 0.14131690561771393,
      "learning_rate": 2.1582733812949642e-05,
      "loss": 0.2999,
      "step": 550
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.14016275107860565,
      "learning_rate": 2.0143884892086333e-05,
      "loss": 0.2941,
      "step": 560
    },
    {
      "epoch": 4.071428571428571,
      "grad_norm": 0.13414789736270905,
      "learning_rate": 1.8705035971223024e-05,
      "loss": 0.2685,
      "step": 570
    },
    {
      "epoch": 4.142857142857143,
      "grad_norm": 0.1517314612865448,
      "learning_rate": 1.7266187050359716e-05,
      "loss": 0.2555,
      "step": 580
    },
    {
      "epoch": 4.214285714285714,
      "grad_norm": 0.16656886041164398,
      "learning_rate": 1.5827338129496403e-05,
      "loss": 0.2492,
      "step": 590
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 0.14459213614463806,
      "learning_rate": 1.4388489208633093e-05,
      "loss": 0.2538,
      "step": 600
    },
    {
      "epoch": 4.357142857142857,
      "grad_norm": 0.17722781002521515,
      "learning_rate": 1.2949640287769784e-05,
      "loss": 0.2882,
      "step": 610
    },
    {
      "epoch": 4.428571428571429,
      "grad_norm": 0.17217843234539032,
      "learning_rate": 1.1510791366906475e-05,
      "loss": 0.2996,
      "step": 620
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.14222589135169983,
      "learning_rate": 1.0071942446043167e-05,
      "loss": 0.262,
      "step": 630
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 0.17444641888141632,
      "learning_rate": 8.633093525179858e-06,
      "loss": 0.2721,
      "step": 640
    },
    {
      "epoch": 4.642857142857143,
      "grad_norm": 0.18322263658046722,
      "learning_rate": 7.1942446043165465e-06,
      "loss": 0.2818,
      "step": 650
    },
    {
      "epoch": 4.714285714285714,
      "grad_norm": 0.1895478367805481,
      "learning_rate": 5.755395683453238e-06,
      "loss": 0.262,
      "step": 660
    },
    {
      "epoch": 4.785714285714286,
      "grad_norm": 0.1996978223323822,
      "learning_rate": 4.316546762589929e-06,
      "loss": 0.2836,
      "step": 670
    },
    {
      "epoch": 4.857142857142857,
      "grad_norm": 0.2018844485282898,
      "learning_rate": 2.877697841726619e-06,
      "loss": 0.2655,
      "step": 680
    },
    {
      "epoch": 4.928571428571429,
      "grad_norm": 0.18131566047668457,
      "learning_rate": 1.4388489208633094e-06,
      "loss": 0.2839,
      "step": 690
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.1565731167793274,
      "learning_rate": 0.0,
      "loss": 0.2389,
      "step": 700
    }
  ],
  "logging_steps": 10,
  "max_steps": 700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 3.5798886346653696e+17,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}