{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.0,
      "loss": 1.4966,
      "step": 1
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.613531161467861e-05,
      "loss": 1.0914,
      "step": 2
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00013652123889719707,
      "loss": 1.1815,
      "step": 3
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017227062322935723,
      "loss": 1.1374,
      "step": 4
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 1.0049,
      "step": 5
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.9757,
      "step": 6
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.9526,
      "step": 7
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.8746,
      "step": 8
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.7538,
      "step": 9
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.7817,
      "step": 10
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.7263,
      "step": 11
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.6033,
      "step": 12
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.582,
      "step": 13
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.4256,
      "step": 14
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.3590076267719269,
      "eval_runtime": 27.2669,
      "eval_samples_per_second": 15.587,
      "eval_steps_per_second": 0.513,
      "step": 14
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.2531,
      "step": 15
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.3431,
      "step": 16
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.2548,
      "step": 17
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 0.2814,
      "step": 18
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 0.1958,
      "step": 19
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 0.2286,
      "step": 20
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 0.2332,
      "step": 21
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.1755,
      "step": 22
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 0.1312,
      "step": 23
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 0.0845,
      "step": 24
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 0.1214,
      "step": 25
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 0.0884,
      "step": 26
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 0.1381,
      "step": 27
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 0.0643,
      "step": 28
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.07109997421503067,
      "eval_runtime": 27.4843,
      "eval_samples_per_second": 15.463,
      "eval_steps_per_second": 0.509,
      "step": 28
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0002,
      "loss": 0.0533,
      "step": 29
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0002,
      "loss": 0.0566,
      "step": 30
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0002,
      "loss": 0.0457,
      "step": 31
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0002,
      "loss": 0.041,
      "step": 32
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0002,
      "loss": 0.0447,
      "step": 33
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0002,
      "loss": 0.0206,
      "step": 34
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0002,
      "loss": 0.0221,
      "step": 35
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0002,
      "loss": 0.0541,
      "step": 36
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0002,
      "loss": 0.0274,
      "step": 37
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0002,
      "loss": 0.0169,
      "step": 38
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0002,
      "loss": 0.0358,
      "step": 39
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0002,
      "loss": 0.0375,
      "step": 40
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0002,
      "loss": 0.0233,
      "step": 41
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0002,
      "loss": 0.0114,
      "step": 42
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.01424238458275795,
      "eval_runtime": 27.4614,
      "eval_samples_per_second": 15.476,
      "eval_steps_per_second": 0.51,
      "step": 42
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0002,
      "loss": 0.0095,
      "step": 43
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0002,
      "loss": 0.0093,
      "step": 44
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.0002,
      "loss": 0.0068,
      "step": 45
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.0002,
      "loss": 0.0069,
      "step": 46
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0002,
      "loss": 0.0067,
      "step": 47
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0002,
      "loss": 0.0161,
      "step": 48
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0002,
      "loss": 0.0123,
      "step": 49
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.0002,
      "loss": 0.0074,
      "step": 50
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.0002,
      "loss": 0.0052,
      "step": 51
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0002,
      "loss": 0.0088,
      "step": 52
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.0002,
      "loss": 0.0147,
      "step": 53
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0002,
      "loss": 0.008,
      "step": 54
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0002,
      "loss": 0.0062,
      "step": 55
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0002,
      "loss": 0.0089,
      "step": 56
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.006587002892047167,
      "eval_runtime": 27.6072,
      "eval_samples_per_second": 15.395,
      "eval_steps_per_second": 0.507,
      "step": 56
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.0002,
      "loss": 0.0047,
      "step": 57
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0002,
      "loss": 0.0043,
      "step": 58
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0002,
      "loss": 0.0061,
      "step": 59
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0002,
      "loss": 0.0036,
      "step": 60
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.0002,
      "loss": 0.0019,
      "step": 61
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.0002,
      "loss": 0.0032,
      "step": 62
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0002,
      "loss": 0.0056,
      "step": 63
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0002,
      "loss": 0.0063,
      "step": 64
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0002,
      "loss": 0.002,
      "step": 65
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0002,
      "loss": 0.0057,
      "step": 66
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0002,
      "loss": 0.0031,
      "step": 67
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.0002,
      "loss": 0.0065,
      "step": 68
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.0002,
      "loss": 0.0022,
      "step": 69
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0002,
      "loss": 0.0021,
      "step": 70
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.0026798362378031015,
      "eval_runtime": 27.5909,
      "eval_samples_per_second": 15.404,
      "eval_steps_per_second": 0.507,
      "step": 70
    },
    {
      "epoch": 5.07,
      "learning_rate": 0.0002,
      "loss": 0.0009,
      "step": 71
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.0002,
      "loss": 0.0013,
      "step": 72
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.0002,
      "loss": 0.0024,
      "step": 73
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.0002,
      "loss": 0.0011,
      "step": 74
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.0002,
      "loss": 0.0008,
      "step": 75
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.0002,
      "loss": 0.0019,
      "step": 76
    },
    {
      "epoch": 5.5,
      "learning_rate": 0.0002,
      "loss": 0.0009,
      "step": 77
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.0002,
      "loss": 0.0016,
      "step": 78
    },
    {
      "epoch": 5.64,
      "learning_rate": 0.0002,
      "loss": 0.0021,
      "step": 79
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.0002,
      "loss": 0.0017,
      "step": 80
    },
    {
      "epoch": 5.79,
      "learning_rate": 0.0002,
      "loss": 0.0028,
      "step": 81
    },
    {
      "epoch": 5.86,
      "learning_rate": 0.0002,
      "loss": 0.0028,
      "step": 82
    },
    {
      "epoch": 5.93,
      "learning_rate": 0.0002,
      "loss": 0.0013,
      "step": 83
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.0002,
      "loss": 0.0012,
      "step": 84
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.0026673530228435993,
      "eval_runtime": 27.6491,
      "eval_samples_per_second": 15.371,
      "eval_steps_per_second": 0.506,
      "step": 84
    },
    {
      "epoch": 6.07,
      "learning_rate": 0.0002,
      "loss": 0.0027,
      "step": 85
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.0002,
      "loss": 0.0037,
      "step": 86
    },
    {
      "epoch": 6.21,
      "learning_rate": 0.0002,
      "loss": 0.0022,
      "step": 87
    },
    {
      "epoch": 6.29,
      "learning_rate": 0.0002,
      "loss": 0.002,
      "step": 88
    },
    {
      "epoch": 6.36,
      "learning_rate": 0.0002,
      "loss": 0.0004,
      "step": 89
    },
    {
      "epoch": 6.43,
      "learning_rate": 0.0002,
      "loss": 0.0009,
      "step": 90
    },
    {
      "epoch": 6.5,
      "learning_rate": 0.0002,
      "loss": 0.0009,
      "step": 91
    },
    {
      "epoch": 6.57,
      "learning_rate": 0.0002,
      "loss": 0.0014,
      "step": 92
    },
    {
      "epoch": 6.64,
      "learning_rate": 0.0002,
      "loss": 0.0014,
      "step": 93
    },
    {
      "epoch": 6.71,
      "learning_rate": 0.0002,
      "loss": 0.002,
      "step": 94
    },
    {
      "epoch": 6.79,
      "learning_rate": 0.0002,
      "loss": 0.001,
      "step": 95
    },
    {
      "epoch": 6.86,
      "learning_rate": 0.0002,
      "loss": 0.0005,
      "step": 96
    },
    {
      "epoch": 6.93,
      "learning_rate": 0.0002,
      "loss": 0.0031,
      "step": 97
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.0002,
      "loss": 0.0008,
      "step": 98
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.0014789514243602753,
      "eval_runtime": 27.6117,
      "eval_samples_per_second": 15.392,
      "eval_steps_per_second": 0.507,
      "step": 98
    },
    {
      "epoch": 7.07,
      "learning_rate": 0.0002,
      "loss": 0.0005,
      "step": 99
    },
    {
      "epoch": 7.14,
      "learning_rate": 0.0002,
      "loss": 0.0003,
      "step": 100
    },
    {
      "epoch": 7.21,
      "learning_rate": 0.0002,
      "loss": 0.0011,
      "step": 101
    },
    {
      "epoch": 7.29,
      "learning_rate": 0.0002,
      "loss": 0.0005,
      "step": 102
    },
    {
      "epoch": 7.36,
      "learning_rate": 0.0002,
      "loss": 0.0005,
      "step": 103
    },
    {
      "epoch": 7.43,
      "learning_rate": 0.0002,
      "loss": 0.0003,
      "step": 104
    },
    {
      "epoch": 7.5,
      "learning_rate": 0.0002,
      "loss": 0.0004,
      "step": 105
    },
    {
      "epoch": 7.57,
      "learning_rate": 0.0002,
      "loss": 0.0003,
      "step": 106
    },
    {
      "epoch": 7.64,
      "learning_rate": 0.0002,
      "loss": 0.002,
      "step": 107
    },
    {
      "epoch": 7.71,
      "learning_rate": 0.0002,
      "loss": 0.001,
      "step": 108
    },
    {
      "epoch": 7.79,
      "learning_rate": 0.0002,
      "loss": 0.0005,
      "step": 109
    },
    {
      "epoch": 7.86,
      "learning_rate": 0.0002,
      "loss": 0.0025,
      "step": 110
    },
    {
      "epoch": 7.93,
      "learning_rate": 0.0002,
      "loss": 0.0005,
      "step": 111
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 112
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.0006328822346404195,
      "eval_runtime": 27.661,
      "eval_samples_per_second": 15.365,
      "eval_steps_per_second": 0.506,
      "step": 112
    },
    {
      "epoch": 8.07,
      "learning_rate": 0.0002,
      "loss": 0.0007,
      "step": 113
    },
    {
      "epoch": 8.14,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 114
    },
    {
      "epoch": 8.21,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 115
    },
    {
      "epoch": 8.29,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 116
    },
    {
      "epoch": 8.36,
      "learning_rate": 0.0002,
      "loss": 0.0005,
      "step": 117
    },
    {
      "epoch": 8.43,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 118
    },
    {
      "epoch": 8.5,
      "learning_rate": 0.0002,
      "loss": 0.0007,
      "step": 119
    },
    {
      "epoch": 8.57,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 120
    },
    {
      "epoch": 8.64,
      "learning_rate": 0.0002,
      "loss": 0.0025,
      "step": 121
    },
    {
      "epoch": 8.71,
      "learning_rate": 0.0002,
      "loss": 0.0008,
      "step": 122
    },
    {
      "epoch": 8.79,
      "learning_rate": 0.0002,
      "loss": 0.0012,
      "step": 123
    },
    {
      "epoch": 8.86,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 124
    },
    {
      "epoch": 8.93,
      "learning_rate": 0.0002,
      "loss": 0.0003,
      "step": 125
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 126
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.0004491883155424148,
      "eval_runtime": 27.6221,
      "eval_samples_per_second": 15.386,
      "eval_steps_per_second": 0.507,
      "step": 126
    },
    {
      "epoch": 9.07,
      "learning_rate": 0.0002,
      "loss": 0.0004,
      "step": 127
    },
    {
      "epoch": 9.14,
      "learning_rate": 0.0002,
      "loss": 0.0001,
      "step": 128
    },
    {
      "epoch": 9.21,
      "learning_rate": 0.0002,
      "loss": 0.0001,
      "step": 129
    },
    {
      "epoch": 9.29,
      "learning_rate": 0.0002,
      "loss": 0.0003,
      "step": 130
    },
    {
      "epoch": 9.36,
      "learning_rate": 0.0002,
      "loss": 0.0011,
      "step": 131
    },
    {
      "epoch": 9.43,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 132
    },
    {
      "epoch": 9.5,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 133
    },
    {
      "epoch": 9.57,
      "learning_rate": 0.0002,
      "loss": 0.0007,
      "step": 134
    },
    {
      "epoch": 9.64,
      "learning_rate": 0.0002,
      "loss": 0.0022,
      "step": 135
    },
    {
      "epoch": 9.71,
      "learning_rate": 0.0002,
      "loss": 0.0016,
      "step": 136
    },
    {
      "epoch": 9.79,
      "learning_rate": 0.0002,
      "loss": 0.0001,
      "step": 137
    },
    {
      "epoch": 9.86,
      "learning_rate": 0.0002,
      "loss": 0.0001,
      "step": 138
    },
    {
      "epoch": 9.93,
      "learning_rate": 0.0002,
      "loss": 0.0003,
      "step": 139
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0002,
      "loss": 0.0005,
      "step": 140
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.00029718142468482256,
      "eval_runtime": 27.6542,
      "eval_samples_per_second": 15.368,
      "eval_steps_per_second": 0.506,
      "step": 140
    },
    {
      "epoch": 10.0,
      "step": 140,
      "total_flos": 4.2897933864638874e+17,
      "train_loss": 0.11377025729951648,
      "train_runtime": 2129.3536,
      "train_samples_per_second": 1.996,
      "train_steps_per_second": 0.066
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 50000,
  "total_flos": 4.2897933864638874e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}