{
  "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": 0.21007585525512695,
      "learning_rate": 0.0,
      "loss": 1.655029296875,
      "step": 1
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.17798976600170135,
      "learning_rate": 2.5e-05,
      "loss": 1.575439453125,
      "step": 2
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 0.2259913980960846,
      "learning_rate": 5e-05,
      "loss": 1.564697265625,
      "step": 3
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.09690755605697632,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0810546875,
      "step": 4
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.08801790326833725,
      "learning_rate": 0.0001,
      "loss": 1.2662353515625,
      "step": 5
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.10510177165269852,
      "learning_rate": 9.861538461538462e-05,
      "loss": 1.2568359375,
      "step": 6
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.1348714828491211,
      "learning_rate": 9.723076923076924e-05,
      "loss": 1.3818359375,
      "step": 7
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.1032116636633873,
      "learning_rate": 9.584615384615385e-05,
      "loss": 1.34033203125,
      "step": 8
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.05139140784740448,
      "learning_rate": 9.446153846153846e-05,
      "loss": 0.979248046875,
      "step": 9
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.05326853692531586,
      "learning_rate": 9.307692307692309e-05,
      "loss": 1.3447265625,
      "step": 10
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.05313504859805107,
      "learning_rate": 9.16923076923077e-05,
      "loss": 1.3134765625,
      "step": 11
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.059753868728876114,
      "learning_rate": 9.030769230769232e-05,
      "loss": 1.1787109375,
      "step": 12
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.04527796804904938,
      "learning_rate": 8.892307692307693e-05,
      "loss": 0.904296875,
      "step": 13
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.060468655079603195,
      "learning_rate": 8.753846153846154e-05,
      "loss": 1.244384765625,
      "step": 14
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.05863908305764198,
      "learning_rate": 8.615384615384615e-05,
      "loss": 1.039794921875,
      "step": 15
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.0608099065721035,
      "learning_rate": 8.476923076923078e-05,
      "loss": 1.2816162109375,
      "step": 16
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 0.059380367398262024,
      "learning_rate": 8.338461538461538e-05,
      "loss": 1.2283935546875,
      "step": 17
    },
    {
      "epoch": 0.7391304347826086,
      "eval_loss": 1.0439453125,
      "eval_runtime": 7.3287,
      "eval_samples_per_second": 1.092,
      "eval_steps_per_second": 0.136,
      "step": 17
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.049521345645189285,
      "learning_rate": 8.200000000000001e-05,
      "loss": 1.2255859375,
      "step": 18
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.06924596428871155,
      "learning_rate": 8.061538461538461e-05,
      "loss": 1.214111328125,
      "step": 19
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.04814432933926582,
      "learning_rate": 7.923076923076924e-05,
      "loss": 1.140625,
      "step": 20
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.047830354422330856,
      "learning_rate": 7.784615384615385e-05,
      "loss": 1.1376953125,
      "step": 21
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.047462135553359985,
      "learning_rate": 7.646153846153847e-05,
      "loss": 1.09326171875,
      "step": 22
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.06260090321302414,
      "learning_rate": 7.507692307692308e-05,
      "loss": 1.1416015625,
      "step": 23
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.05586949363350868,
      "learning_rate": 7.36923076923077e-05,
      "loss": 1.1619873046875,
      "step": 24
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 0.055030837655067444,
      "learning_rate": 7.23076923076923e-05,
      "loss": 1.12841796875,
      "step": 25
    },
    {
      "epoch": 1.1304347826086956,
      "grad_norm": 0.061410631984472275,
      "learning_rate": 7.092307692307693e-05,
      "loss": 1.0794677734375,
      "step": 26
    },
    {
      "epoch": 1.1739130434782608,
      "grad_norm": 0.036529239267110825,
      "learning_rate": 6.953846153846154e-05,
      "loss": 0.8125,
      "step": 27
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 0.06471265107393265,
      "learning_rate": 6.815384615384615e-05,
      "loss": 1.003662109375,
      "step": 28
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 0.05256718769669533,
      "learning_rate": 6.676923076923078e-05,
      "loss": 1.02978515625,
      "step": 29
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 0.061083290725946426,
      "learning_rate": 6.538461538461539e-05,
      "loss": 1.098388671875,
      "step": 30
    },
    {
      "epoch": 1.3043478260869565,
      "eval_loss": 0.99755859375,
      "eval_runtime": 7.2801,
      "eval_samples_per_second": 1.099,
      "eval_steps_per_second": 0.137,
      "step": 30
    },
    {
      "epoch": 1.3478260869565217,
      "grad_norm": 0.055687159299850464,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.09130859375,
      "step": 31
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.04101266339421272,
      "learning_rate": 6.261538461538462e-05,
      "loss": 0.8245849609375,
      "step": 32
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 0.06126929074525833,
      "learning_rate": 6.123076923076923e-05,
      "loss": 1.140380859375,
      "step": 33
    },
    {
      "epoch": 1.4782608695652173,
      "grad_norm": 0.1110447347164154,
      "learning_rate": 5.984615384615385e-05,
      "loss": 1.115478515625,
      "step": 34
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 0.04907373711466789,
      "learning_rate": 5.846153846153847e-05,
      "loss": 1.0115966796875,
      "step": 35
    },
    {
      "epoch": 1.5652173913043477,
      "grad_norm": 0.042174968868494034,
      "learning_rate": 5.7076923076923086e-05,
      "loss": 0.78759765625,
      "step": 36
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 0.06539176404476166,
      "learning_rate": 5.5692307692307696e-05,
      "loss": 1.0634765625,
      "step": 37
    },
    {
      "epoch": 1.6521739130434783,
      "grad_norm": 0.06267675757408142,
      "learning_rate": 5.4307692307692314e-05,
      "loss": 0.8946533203125,
      "step": 38
    },
    {
      "epoch": 1.6956521739130435,
      "grad_norm": 0.061865441501140594,
      "learning_rate": 5.292307692307693e-05,
      "loss": 1.1124267578125,
      "step": 39
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.07024873048067093,
      "learning_rate": 5.153846153846155e-05,
      "loss": 1.05615234375,
      "step": 40
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 0.06368125230073929,
      "learning_rate": 5.015384615384616e-05,
      "loss": 1.0770263671875,
      "step": 41
    },
    {
      "epoch": 1.8260869565217392,
      "grad_norm": 0.07061440497636795,
      "learning_rate": 4.876923076923078e-05,
      "loss": 1.017822265625,
      "step": 42
    },
    {
      "epoch": 1.8695652173913042,
      "grad_norm": 0.05024050921201706,
      "learning_rate": 4.7384615384615396e-05,
      "loss": 1.0234375,
      "step": 43
    },
    {
      "epoch": 1.8695652173913042,
      "eval_loss": 0.971923828125,
      "eval_runtime": 7.3334,
      "eval_samples_per_second": 1.091,
      "eval_steps_per_second": 0.136,
      "step": 43
    },
    {
      "epoch": 1.9130434782608696,
      "grad_norm": 0.061272069811820984,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.010009765625,
      "step": 44
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 0.05659634247422218,
      "learning_rate": 4.4615384615384625e-05,
      "loss": 0.977783203125,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0683118924498558,
      "learning_rate": 4.323076923076924e-05,
      "loss": 0.9609375,
      "step": 46
    },
    {
      "epoch": 2.0434782608695654,
      "grad_norm": 0.06508132070302963,
      "learning_rate": 4.1846153846153846e-05,
      "loss": 0.982666015625,
      "step": 47
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.06541179120540619,
      "learning_rate": 4.0461538461538464e-05,
      "loss": 0.995361328125,
      "step": 48
    },
    {
      "epoch": 2.130434782608696,
      "grad_norm": 0.07752222567796707,
      "learning_rate": 3.9076923076923075e-05,
      "loss": 0.9139404296875,
      "step": 49
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 0.05275733023881912,
      "learning_rate": 3.769230769230769e-05,
      "loss": 0.727294921875,
      "step": 50
    },
    {
      "epoch": 2.217391304347826,
      "grad_norm": 0.06840420514345169,
      "learning_rate": 3.630769230769231e-05,
      "loss": 0.90020751953125,
      "step": 51
    },
    {
      "epoch": 2.260869565217391,
      "grad_norm": 0.06666186451911926,
      "learning_rate": 3.492307692307693e-05,
      "loss": 0.923095703125,
      "step": 52
    },
    {
      "epoch": 2.3043478260869565,
      "grad_norm": 0.09174983948469162,
      "learning_rate": 3.353846153846154e-05,
      "loss": 0.93115234375,
      "step": 53
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.08284027874469757,
      "learning_rate": 3.215384615384616e-05,
      "loss": 0.94482421875,
      "step": 54
    },
    {
      "epoch": 2.391304347826087,
      "grad_norm": 0.05585809051990509,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.7435302734375,
      "step": 55
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.07766841351985931,
      "learning_rate": 2.938461538461539e-05,
      "loss": 1.013671875,
      "step": 56
    },
    {
      "epoch": 2.4347826086956523,
      "eval_loss": 0.965576171875,
      "eval_runtime": 7.2901,
      "eval_samples_per_second": 1.097,
      "eval_steps_per_second": 0.137,
      "step": 56
    },
    {
      "epoch": 2.4782608695652173,
      "grad_norm": 0.0812578797340393,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.9970703125,
      "step": 57
    },
    {
      "epoch": 2.5217391304347827,
      "grad_norm": 0.0702136754989624,
      "learning_rate": 2.661538461538462e-05,
      "loss": 0.90185546875,
      "step": 58
    },
    {
      "epoch": 2.5652173913043477,
      "grad_norm": 0.05338814854621887,
      "learning_rate": 2.5230769230769235e-05,
      "loss": 0.7076416015625,
      "step": 59
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.0778580904006958,
      "learning_rate": 2.384615384615385e-05,
      "loss": 0.93701171875,
      "step": 60
    },
    {
      "epoch": 2.6521739130434785,
      "grad_norm": 0.0665515884757042,
      "learning_rate": 2.2461538461538464e-05,
      "loss": 0.78955078125,
      "step": 61
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 0.08628246933221817,
      "learning_rate": 2.1076923076923078e-05,
      "loss": 0.991455078125,
      "step": 62
    },
    {
      "epoch": 2.7391304347826084,
      "grad_norm": 0.08580964058637619,
      "learning_rate": 1.9692307692307692e-05,
      "loss": 0.917236328125,
      "step": 63
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.07817274332046509,
      "learning_rate": 1.830769230769231e-05,
      "loss": 0.961669921875,
      "step": 64
    },
    {
      "epoch": 2.8260869565217392,
      "grad_norm": 0.09753349423408508,
      "learning_rate": 1.6923076923076924e-05,
      "loss": 0.842041015625,
      "step": 65
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 0.08620236814022064,
      "learning_rate": 1.5538461538461542e-05,
      "loss": 0.94287109375,
      "step": 66
    },
    {
      "epoch": 2.9130434782608696,
      "grad_norm": 0.09718054533004761,
      "learning_rate": 1.4153846153846156e-05,
      "loss": 0.91259765625,
      "step": 67
    },
    {
      "epoch": 2.9565217391304346,
      "grad_norm": 0.08040907979011536,
      "learning_rate": 1.2769230769230769e-05,
      "loss": 0.8974609375,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.09266524761915207,
      "learning_rate": 1.1384615384615385e-05,
      "loss": 0.798095703125,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.966064453125,
      "eval_runtime": 7.2916,
      "eval_samples_per_second": 1.097,
      "eval_steps_per_second": 0.137,
      "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": 2.0858247646386586e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}