{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0408163265306123,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02040816326530612,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.02040816326530612,
      "eval_loss": NaN,
      "eval_runtime": 5.1593,
      "eval_samples_per_second": 8.141,
      "eval_steps_per_second": 1.163,
      "step": 1
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.1836734693877551,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.1836734693877551,
      "eval_loss": NaN,
      "eval_runtime": 4.7497,
      "eval_samples_per_second": 8.843,
      "eval_steps_per_second": 1.263,
      "step": 9
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.22448979591836735,
      "grad_norm": NaN,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.2653061224489796,
      "grad_norm": NaN,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": NaN,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.3469387755102041,
      "grad_norm": NaN,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.3673469387755102,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.3673469387755102,
      "eval_loss": NaN,
      "eval_runtime": 4.7676,
      "eval_samples_per_second": 8.809,
      "eval_steps_per_second": 1.258,
      "step": 18
    },
    {
      "epoch": 0.3877551020408163,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": NaN,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.4489795918367347,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.46938775510204084,
      "grad_norm": NaN,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": NaN,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.5306122448979592,
      "grad_norm": NaN,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.5510204081632653,
      "grad_norm": NaN,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.5510204081632653,
      "eval_loss": NaN,
      "eval_runtime": 4.7615,
      "eval_samples_per_second": 8.821,
      "eval_steps_per_second": 1.26,
      "step": 27
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.5918367346938775,
      "grad_norm": NaN,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.6326530612244898,
      "grad_norm": NaN,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": NaN,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.673469387755102,
      "grad_norm": NaN,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.6938775510204082,
      "grad_norm": NaN,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.7346938775510204,
      "grad_norm": NaN,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.7346938775510204,
      "eval_loss": NaN,
      "eval_runtime": 4.7613,
      "eval_samples_per_second": 8.821,
      "eval_steps_per_second": 1.26,
      "step": 36
    },
    {
      "epoch": 0.7551020408163265,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.7755102040816326,
      "grad_norm": NaN,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.7959183673469388,
      "grad_norm": NaN,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.8367346938775511,
      "grad_norm": NaN,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": NaN,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.8775510204081632,
      "grad_norm": NaN,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.8979591836734694,
      "grad_norm": NaN,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.9183673469387755,
      "eval_loss": NaN,
      "eval_runtime": 4.7739,
      "eval_samples_per_second": 8.798,
      "eval_steps_per_second": 1.257,
      "step": 45
    },
    {
      "epoch": 0.9387755102040817,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.9591836734693877,
      "grad_norm": NaN,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": NaN,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 1.0,
      "grad_norm": NaN,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 1.0204081632653061,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 1.0408163265306123,
      "grad_norm": NaN,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 1.0612244897959184,
      "grad_norm": NaN,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 1.0816326530612246,
      "grad_norm": NaN,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 1.1020408163265305,
      "grad_norm": NaN,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 1.1020408163265305,
      "eval_loss": NaN,
      "eval_runtime": 4.7828,
      "eval_samples_per_second": 8.782,
      "eval_steps_per_second": 1.255,
      "step": 54
    },
    {
      "epoch": 1.1224489795918366,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": NaN,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 1.163265306122449,
      "grad_norm": NaN,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 1.183673469387755,
      "grad_norm": NaN,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 1.2040816326530612,
      "grad_norm": NaN,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 1.2244897959183674,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 1.2448979591836735,
      "grad_norm": NaN,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 1.2653061224489797,
      "grad_norm": NaN,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": NaN,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 1.2857142857142856,
      "eval_loss": NaN,
      "eval_runtime": 4.7771,
      "eval_samples_per_second": 8.792,
      "eval_steps_per_second": 1.256,
      "step": 63
    },
    {
      "epoch": 1.306122448979592,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 1.3265306122448979,
      "grad_norm": NaN,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 1.346938775510204,
      "grad_norm": NaN,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 1.3673469387755102,
      "grad_norm": NaN,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 1.3877551020408163,
      "grad_norm": NaN,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 1.4081632653061225,
      "grad_norm": NaN,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 1.4489795918367347,
      "grad_norm": NaN,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 1.469387755102041,
      "grad_norm": NaN,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 1.469387755102041,
      "eval_loss": NaN,
      "eval_runtime": 4.7764,
      "eval_samples_per_second": 8.793,
      "eval_steps_per_second": 1.256,
      "step": 72
    },
    {
      "epoch": 1.489795918367347,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 1.510204081632653,
      "grad_norm": NaN,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 1.5306122448979593,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 1.5510204081632653,
      "grad_norm": NaN,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": NaN,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 1.5918367346938775,
      "grad_norm": NaN,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 1.6122448979591837,
      "grad_norm": NaN,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 1.6326530612244898,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 1.6530612244897958,
      "grad_norm": NaN,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 1.6530612244897958,
      "eval_loss": NaN,
      "eval_runtime": 4.772,
      "eval_samples_per_second": 8.801,
      "eval_steps_per_second": 1.257,
      "step": 81
    },
    {
      "epoch": 1.6734693877551021,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 1.693877551020408,
      "grad_norm": NaN,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": NaN,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 1.7346938775510203,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 1.7551020408163265,
      "grad_norm": NaN,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 1.7755102040816326,
      "grad_norm": NaN,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 1.7959183673469388,
      "grad_norm": NaN,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 1.816326530612245,
      "grad_norm": NaN,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 1.836734693877551,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 1.836734693877551,
      "eval_loss": NaN,
      "eval_runtime": 4.7727,
      "eval_samples_per_second": 8.8,
      "eval_steps_per_second": 1.257,
      "step": 90
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 1.8775510204081631,
      "grad_norm": NaN,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 1.8979591836734695,
      "grad_norm": NaN,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 1.9183673469387754,
      "grad_norm": NaN,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 1.9387755102040818,
      "grad_norm": NaN,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 1.9591836734693877,
      "grad_norm": NaN,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 1.9795918367346939,
      "grad_norm": NaN,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 2.0,
      "grad_norm": NaN,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 2.020408163265306,
      "grad_norm": NaN,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 2.020408163265306,
      "eval_loss": NaN,
      "eval_runtime": 4.7731,
      "eval_samples_per_second": 8.799,
      "eval_steps_per_second": 1.257,
      "step": 99
    },
    {
      "epoch": 2.0408163265306123,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.400325653515469e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}