{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 13,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 0.3934652805328369,
      "learning_rate": 0.0,
      "loss": 1.41943359375,
      "step": 1
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.27814722061157227,
      "learning_rate": 2.5e-05,
      "loss": 1.28857421875,
      "step": 2
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 0.2720669209957123,
      "learning_rate": 5e-05,
      "loss": 1.368408203125,
      "step": 3
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.15397290885448456,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.302978515625,
      "step": 4
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.10039743036031723,
      "learning_rate": 0.0001,
      "loss": 1.13818359375,
      "step": 5
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.08535437285900116,
      "learning_rate": 9.99474502074547e-05,
      "loss": 1.09423828125,
      "step": 6
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.11014275997877121,
      "learning_rate": 9.978992356229419e-05,
      "loss": 1.20263671875,
      "step": 7
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.11600128561258316,
      "learning_rate": 9.95277879752973e-05,
      "loss": 1.2470703125,
      "step": 8
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.10469289124011993,
      "learning_rate": 9.916165567627362e-05,
      "loss": 1.08837890625,
      "step": 9
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.06072447448968887,
      "learning_rate": 9.869238178417235e-05,
      "loss": 0.966064453125,
      "step": 10
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.08861712366342545,
      "learning_rate": 9.812106230991248e-05,
      "loss": 1.07470703125,
      "step": 11
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.06396962702274323,
      "learning_rate": 9.744903159659843e-05,
      "loss": 1.0478515625,
      "step": 12
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.07080996781587601,
      "learning_rate": 9.667785920309994e-05,
      "loss": 0.9302978515625,
      "step": 13
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.06746376305818558,
      "learning_rate": 9.580934623827455e-05,
      "loss": 1.043212890625,
      "step": 14
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.08017799258232117,
      "learning_rate": 9.484552115439445e-05,
      "loss": 0.8516845703125,
      "step": 15
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.07284124940633774,
      "learning_rate": 9.378863500960222e-05,
      "loss": 0.83984375,
      "step": 16
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 0.07209096848964691,
      "learning_rate": 9.26411562104602e-05,
      "loss": 0.964599609375,
      "step": 17
    },
    {
      "epoch": 0.7391304347826086,
      "eval_loss": 0.94384765625,
      "eval_runtime": 6.4026,
      "eval_samples_per_second": 1.093,
      "eval_steps_per_second": 0.156,
      "step": 17
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.06006007641553879,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.91156005859375,
      "step": 18
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.06638667732477188,
      "learning_rate": 9.008534593284501e-05,
      "loss": 0.958984375,
      "step": 19
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.05720623955130577,
      "learning_rate": 8.868298366769954e-05,
      "loss": 0.95166015625,
      "step": 20
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.05189875140786171,
      "learning_rate": 8.720195323348545e-05,
      "loss": 0.88525390625,
      "step": 21
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.0865139439702034,
      "learning_rate": 8.564571364540588e-05,
      "loss": 0.55859375,
      "step": 22
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.06380347907543182,
      "learning_rate": 8.401789957312768e-05,
      "loss": 0.900146484375,
      "step": 23
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.055657561868429184,
      "learning_rate": 8.232231285184201e-05,
      "loss": 0.849853515625,
      "step": 24
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 0.059652525931596756,
      "learning_rate": 8.056291360290201e-05,
      "loss": 0.853759765625,
      "step": 25
    },
    {
      "epoch": 1.1304347826086956,
      "grad_norm": 0.060650426894426346,
      "learning_rate": 7.874381098477599e-05,
      "loss": 0.8466796875,
      "step": 26
    },
    {
      "epoch": 1.1739130434782608,
      "grad_norm": 0.06352933496236801,
      "learning_rate": 7.686925359591727e-05,
      "loss": 0.851806640625,
      "step": 27
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 0.05915879085659981,
      "learning_rate": 7.494361955196587e-05,
      "loss": 0.8531494140625,
      "step": 28
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 0.06083173677325249,
      "learning_rate": 7.29714062604563e-05,
      "loss": 0.81640625,
      "step": 29
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 0.05808182805776596,
      "learning_rate": 7.095721991691411e-05,
      "loss": 0.953125,
      "step": 30
    },
    {
      "epoch": 1.3043478260869565,
      "eval_loss": 0.8916015625,
      "eval_runtime": 6.4036,
      "eval_samples_per_second": 1.093,
      "eval_steps_per_second": 0.156,
      "step": 30
    },
    {
      "epoch": 1.3478260869565217,
      "grad_norm": 0.06193830072879791,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.9913330078125,
      "step": 31
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.06262914091348648,
      "learning_rate": 6.682183201893642e-05,
      "loss": 0.82470703125,
      "step": 32
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 0.04759113863110542,
      "learning_rate": 6.471028885455128e-05,
      "loss": 0.8173828125,
      "step": 33
    },
    {
      "epoch": 1.4782608695652173,
      "grad_norm": 0.066951222717762,
      "learning_rate": 6.257606686061673e-05,
      "loss": 0.83984375,
      "step": 34
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 0.06664830446243286,
      "learning_rate": 6.042415061148954e-05,
      "loss": 0.844482421875,
      "step": 35
    },
    {
      "epoch": 1.5652173913043477,
      "grad_norm": 0.06117849424481392,
      "learning_rate": 5.825956600727932e-05,
      "loss": 0.730712890625,
      "step": 36
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 0.057094771414995193,
      "learning_rate": 5.608736853562596e-05,
      "loss": 0.886474609375,
      "step": 37
    },
    {
      "epoch": 1.6521739130434783,
      "grad_norm": 0.06637031584978104,
      "learning_rate": 5.3912631464374064e-05,
      "loss": 0.66357421875,
      "step": 38
    },
    {
      "epoch": 1.6956521739130435,
      "grad_norm": 0.05959177389740944,
      "learning_rate": 5.1740433992720704e-05,
      "loss": 0.669677734375,
      "step": 39
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.06861241906881332,
      "learning_rate": 4.9575849388510473e-05,
      "loss": 0.806884765625,
      "step": 40
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 0.0767131820321083,
      "learning_rate": 4.742393313938327e-05,
      "loss": 0.805206298828125,
      "step": 41
    },
    {
      "epoch": 1.8260869565217392,
      "grad_norm": 0.08656497299671173,
      "learning_rate": 4.5289711145448735e-05,
      "loss": 0.8193359375,
      "step": 42
    },
    {
      "epoch": 1.8695652173913042,
      "grad_norm": 0.0569748617708683,
      "learning_rate": 4.317816798106359e-05,
      "loss": 0.8310546875,
      "step": 43
    },
    {
      "epoch": 1.8695652173913042,
      "eval_loss": 0.8701171875,
      "eval_runtime": 6.3906,
      "eval_samples_per_second": 1.095,
      "eval_steps_per_second": 0.156,
      "step": 43
    },
    {
      "epoch": 1.9130434782608696,
      "grad_norm": 0.05252943933010101,
      "learning_rate": 4.109423525312738e-05,
      "loss": 0.772705078125,
      "step": 44
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 0.046744897961616516,
      "learning_rate": 3.904278008308589e-05,
      "loss": 0.4869384765625,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.07318034023046494,
      "learning_rate": 3.7028593739543715e-05,
      "loss": 0.7264404296875,
      "step": 46
    },
    {
      "epoch": 2.0434782608695654,
      "grad_norm": 0.10306981950998306,
      "learning_rate": 3.5056380448034144e-05,
      "loss": 0.6920166015625,
      "step": 47
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.13271251320838928,
      "learning_rate": 3.313074640408273e-05,
      "loss": 0.7445068359375,
      "step": 48
    },
    {
      "epoch": 2.130434782608696,
      "grad_norm": 0.06118979677557945,
      "learning_rate": 3.1256189015224025e-05,
      "loss": 0.728515625,
      "step": 49
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 0.06570016592741013,
      "learning_rate": 2.9437086397097995e-05,
      "loss": 0.736328125,
      "step": 50
    },
    {
      "epoch": 2.217391304347826,
      "grad_norm": 0.07529520988464355,
      "learning_rate": 2.7677687148157998e-05,
      "loss": 0.7554931640625,
      "step": 51
    },
    {
      "epoch": 2.260869565217391,
      "grad_norm": 0.06760681420564651,
      "learning_rate": 2.5982100426872337e-05,
      "loss": 0.708984375,
      "step": 52
    },
    {
      "epoch": 2.3043478260869565,
      "grad_norm": 0.06175344064831734,
      "learning_rate": 2.4354286354594124e-05,
      "loss": 0.8507080078125,
      "step": 53
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.07249287515878677,
      "learning_rate": 2.2798046766514558e-05,
      "loss": 0.88232421875,
      "step": 54
    },
    {
      "epoch": 2.391304347826087,
      "grad_norm": 0.07413790374994278,
      "learning_rate": 2.1317016332300447e-05,
      "loss": 0.704833984375,
      "step": 55
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.05818796530365944,
      "learning_rate": 1.9914654067154996e-05,
      "loss": 0.75341796875,
      "step": 56
    },
    {
      "epoch": 2.4347826086956523,
      "eval_loss": 0.862548828125,
      "eval_runtime": 6.4067,
      "eval_samples_per_second": 1.093,
      "eval_steps_per_second": 0.156,
      "step": 56
    },
    {
      "epoch": 2.4782608695652173,
      "grad_norm": 0.07730214297771454,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 0.7138671875,
      "step": 57
    },
    {
      "epoch": 2.5217391304347827,
      "grad_norm": 0.07291872054338455,
      "learning_rate": 1.7358843789539798e-05,
      "loss": 0.7332763671875,
      "step": 58
    },
    {
      "epoch": 2.5652173913043477,
      "grad_norm": 0.07213034480810165,
      "learning_rate": 1.6211364990397783e-05,
      "loss": 0.6407470703125,
      "step": 59
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.07417318224906921,
      "learning_rate": 1.515447884560556e-05,
      "loss": 0.803466796875,
      "step": 60
    },
    {
      "epoch": 2.6521739130434785,
      "grad_norm": 0.07352118194103241,
      "learning_rate": 1.4190653761725458e-05,
      "loss": 0.5760498046875,
      "step": 61
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 0.06771689653396606,
      "learning_rate": 1.3322140796900066e-05,
      "loss": 0.5888671875,
      "step": 62
    },
    {
      "epoch": 2.7391304347826084,
      "grad_norm": 0.08380644768476486,
      "learning_rate": 1.2550968403401558e-05,
      "loss": 0.708984375,
      "step": 63
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.05968998745083809,
      "learning_rate": 1.1878937690087522e-05,
      "loss": 0.74993896484375,
      "step": 64
    },
    {
      "epoch": 2.8260869565217392,
      "grad_norm": 0.07142704725265503,
      "learning_rate": 1.130761821582766e-05,
      "loss": 0.74267578125,
      "step": 65
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 0.07036396116018295,
      "learning_rate": 1.0838344323726395e-05,
      "loss": 0.76318359375,
      "step": 66
    },
    {
      "epoch": 2.9130434782608696,
      "grad_norm": 0.06523539125919342,
      "learning_rate": 1.04722120247027e-05,
      "loss": 0.719970703125,
      "step": 67
    },
    {
      "epoch": 2.9565217391304346,
      "grad_norm": 0.04794224724173546,
      "learning_rate": 1.0210076437705812e-05,
      "loss": 0.4503173828125,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.07751081883907318,
      "learning_rate": 1.0052549792545301e-05,
      "loss": 0.624755859375,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.860595703125,
      "eval_runtime": 6.4167,
      "eval_samples_per_second": 1.091,
      "eval_steps_per_second": 0.156,
      "step": 69
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 69,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9863300003908813e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}