{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 107,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009345794392523364,
      "grad_norm": NaN,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.9667,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": NaN,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.06542056074766354,
      "grad_norm": NaN,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": NaN,
      "learning_rate": 9e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.102803738317757,
      "grad_norm": NaN,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": NaN,
      "learning_rate": 1.2e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.12149532710280374,
      "grad_norm": NaN,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": NaN,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": NaN,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.1588785046728972,
      "grad_norm": NaN,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": NaN,
      "learning_rate": 1.8e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.17757009345794392,
      "grad_norm": NaN,
      "learning_rate": 1.9e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": NaN,
      "learning_rate": 2.1e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": NaN,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.21495327102803738,
      "grad_norm": NaN,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": NaN,
      "learning_rate": 2.4e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.24299065420560748,
      "grad_norm": NaN,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.2523364485981308,
      "grad_norm": NaN,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": NaN,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.27102803738317754,
      "grad_norm": NaN,
      "learning_rate": 2.9e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.2897196261682243,
      "grad_norm": NaN,
      "learning_rate": 3.1e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": NaN,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.308411214953271,
      "grad_norm": NaN,
      "learning_rate": 3.3e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.3177570093457944,
      "grad_norm": NaN,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.32710280373831774,
      "grad_norm": NaN,
      "learning_rate": 3.5e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": NaN,
      "learning_rate": 3.6e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.34579439252336447,
      "grad_norm": NaN,
      "learning_rate": 3.7e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.35514018691588783,
      "grad_norm": NaN,
      "learning_rate": 3.8e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.3644859813084112,
      "grad_norm": NaN,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.38317757009345793,
      "grad_norm": NaN,
      "learning_rate": 4.1e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.3925233644859813,
      "grad_norm": NaN,
      "learning_rate": 4.2e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.40186915887850466,
      "grad_norm": NaN,
      "learning_rate": 4.3e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.411214953271028,
      "grad_norm": NaN,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.4205607476635514,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.42990654205607476,
      "grad_norm": NaN,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.4392523364485981,
      "grad_norm": NaN,
      "learning_rate": 4.7e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": NaN,
      "learning_rate": 4.8e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.45794392523364486,
      "grad_norm": NaN,
      "learning_rate": 4.9e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.4766355140186916,
      "grad_norm": NaN,
      "learning_rate": 5.1000000000000006e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.48598130841121495,
      "grad_norm": NaN,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.4953271028037383,
      "grad_norm": NaN,
      "learning_rate": 5.300000000000001e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.5046728971962616,
      "grad_norm": NaN,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.514018691588785,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.5233644859813084,
      "grad_norm": NaN,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.5327102803738317,
      "grad_norm": NaN,
      "learning_rate": 5.6999999999999996e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.5420560747663551,
      "grad_norm": NaN,
      "learning_rate": 5.8e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.5514018691588785,
      "grad_norm": NaN,
      "learning_rate": 5.9e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.5700934579439252,
      "grad_norm": NaN,
      "learning_rate": 6.1e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.5794392523364486,
      "grad_norm": NaN,
      "learning_rate": 6.2e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.5887850467289719,
      "grad_norm": NaN,
      "learning_rate": 6.3e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": NaN,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.6074766355140186,
      "grad_norm": NaN,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.616822429906542,
      "grad_norm": NaN,
      "learning_rate": 6.6e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.6261682242990654,
      "grad_norm": NaN,
      "learning_rate": 6.7e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.6355140186915887,
      "grad_norm": NaN,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.6448598130841121,
      "grad_norm": NaN,
      "learning_rate": 6.9e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.6542056074766355,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.6635514018691588,
      "grad_norm": NaN,
      "learning_rate": 7.1e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": NaN,
      "learning_rate": 7.2e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.6822429906542056,
      "grad_norm": NaN,
      "learning_rate": 7.3e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.6915887850467289,
      "grad_norm": NaN,
      "learning_rate": 7.4e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.7009345794392523,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.7102803738317757,
      "grad_norm": NaN,
      "learning_rate": 7.6e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.719626168224299,
      "grad_norm": NaN,
      "learning_rate": 7.7e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.7289719626168224,
      "grad_norm": NaN,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.7383177570093458,
      "grad_norm": NaN,
      "learning_rate": 7.900000000000001e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.7570093457943925,
      "grad_norm": NaN,
      "learning_rate": 8.1e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.7663551401869159,
      "grad_norm": NaN,
      "learning_rate": 8.2e-05,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.7757009345794392,
      "grad_norm": NaN,
      "learning_rate": 8.3e-05,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.7850467289719626,
      "grad_norm": NaN,
      "learning_rate": 8.4e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.794392523364486,
      "grad_norm": NaN,
      "learning_rate": 8.5e-05,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.8037383177570093,
      "grad_norm": NaN,
      "learning_rate": 8.6e-05,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.8130841121495327,
      "grad_norm": NaN,
      "learning_rate": 8.7e-05,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.822429906542056,
      "grad_norm": NaN,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.8317757009345794,
      "grad_norm": NaN,
      "learning_rate": 8.900000000000001e-05,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.8504672897196262,
      "grad_norm": NaN,
      "learning_rate": 9.1e-05,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.8598130841121495,
      "grad_norm": NaN,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.8691588785046729,
      "grad_norm": NaN,
      "learning_rate": 9.300000000000001e-05,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.8785046728971962,
      "grad_norm": NaN,
      "learning_rate": 9.4e-05,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.8878504672897196,
      "grad_norm": NaN,
      "learning_rate": 9.5e-05,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": NaN,
      "learning_rate": 9.6e-05,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.9065420560747663,
      "grad_norm": NaN,
      "learning_rate": 9.7e-05,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.9158878504672897,
      "grad_norm": NaN,
      "learning_rate": 9.8e-05,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.9252336448598131,
      "grad_norm": NaN,
      "learning_rate": 9.900000000000001e-05,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.9439252336448598,
      "grad_norm": NaN,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.0,
      "step": 101
    },
    {
      "epoch": 0.9532710280373832,
      "grad_norm": NaN,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.9626168224299065,
      "grad_norm": NaN,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0,
      "step": 103
    },
    {
      "epoch": 0.9719626168224299,
      "grad_norm": NaN,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0,
      "step": 104
    },
    {
      "epoch": 0.9813084112149533,
      "grad_norm": NaN,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.9906542056074766,
      "grad_norm": NaN,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0,
      "step": 106
    },
    {
      "epoch": 1.0,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 107
    }
  ],
  "logging_steps": 1,
  "max_steps": 107,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 239,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.615331368861696e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}