{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 0.0,
      "loss": 1.8458,
      "step": 1
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00012618595071429146,
      "loss": 1.3338,
      "step": 2
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.4449,
      "step": 3
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.2432,
      "step": 4
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.1334,
      "step": 5
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.0409,
      "step": 6
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.995,
      "step": 7
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.8637,
      "step": 8
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.8986,
      "step": 9
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.014405369758606,
      "eval_runtime": 5.2246,
      "eval_samples_per_second": 9.57,
      "eval_steps_per_second": 0.383,
      "step": 9
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.6907,
      "step": 10
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.5098,
      "step": 11
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.4846,
      "step": 12
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 0.5445,
      "step": 13
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 0.4899,
      "step": 14
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 0.4685,
      "step": 15
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 0.3165,
      "step": 16
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 0.2817,
      "step": 17
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 0.2358,
      "step": 18
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.116402268409729,
      "eval_runtime": 5.3145,
      "eval_samples_per_second": 9.408,
      "eval_steps_per_second": 0.376,
      "step": 18
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002,
      "loss": 0.1739,
      "step": 19
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0002,
      "loss": 0.1121,
      "step": 20
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0002,
      "loss": 0.1148,
      "step": 21
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0002,
      "loss": 0.1308,
      "step": 22
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0002,
      "loss": 0.0877,
      "step": 23
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0002,
      "loss": 0.0622,
      "step": 24
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0002,
      "loss": 0.0994,
      "step": 25
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0002,
      "loss": 0.0978,
      "step": 26
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0002,
      "loss": 0.0721,
      "step": 27
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.1953805685043335,
      "eval_runtime": 5.3566,
      "eval_samples_per_second": 9.334,
      "eval_steps_per_second": 0.373,
      "step": 27
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0002,
      "loss": 0.0396,
      "step": 28
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.0002,
      "loss": 0.0378,
      "step": 29
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0002,
      "loss": 0.0381,
      "step": 30
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0002,
      "loss": 0.0245,
      "step": 31
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0002,
      "loss": 0.0375,
      "step": 32
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0002,
      "loss": 0.0384,
      "step": 33
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.0002,
      "loss": 0.0327,
      "step": 34
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.0002,
      "loss": 0.0447,
      "step": 35
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0002,
      "loss": 0.0289,
      "step": 36
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.3896456956863403,
      "eval_runtime": 5.3385,
      "eval_samples_per_second": 9.366,
      "eval_steps_per_second": 0.375,
      "step": 36
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0002,
      "loss": 0.0104,
      "step": 37
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.0002,
      "loss": 0.0176,
      "step": 38
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0002,
      "loss": 0.0143,
      "step": 39
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0002,
      "loss": 0.013,
      "step": 40
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0002,
      "loss": 0.0091,
      "step": 41
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.0002,
      "loss": 0.0153,
      "step": 42
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.0002,
      "loss": 0.0223,
      "step": 43
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0002,
      "loss": 0.0145,
      "step": 44
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0002,
      "loss": 0.0089,
      "step": 45
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.474170207977295,
      "eval_runtime": 5.3872,
      "eval_samples_per_second": 9.281,
      "eval_steps_per_second": 0.371,
      "step": 45
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.0002,
      "loss": 0.0073,
      "step": 46
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.0002,
      "loss": 0.0103,
      "step": 47
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.0002,
      "loss": 0.0093,
      "step": 48
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.0002,
      "loss": 0.0105,
      "step": 49
    },
    {
      "epoch": 5.56,
      "learning_rate": 0.0002,
      "loss": 0.0062,
      "step": 50
    },
    {
      "epoch": 5.67,
      "learning_rate": 0.0002,
      "loss": 0.0161,
      "step": 51
    },
    {
      "epoch": 5.78,
      "learning_rate": 0.0002,
      "loss": 0.0069,
      "step": 52
    },
    {
      "epoch": 5.89,
      "learning_rate": 0.0002,
      "loss": 0.0086,
      "step": 53
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.0002,
      "loss": 0.0073,
      "step": 54
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.4845446348190308,
      "eval_runtime": 5.395,
      "eval_samples_per_second": 9.268,
      "eval_steps_per_second": 0.371,
      "step": 54
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.0002,
      "loss": 0.0061,
      "step": 55
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.0002,
      "loss": 0.0048,
      "step": 56
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.0002,
      "loss": 0.0088,
      "step": 57
    },
    {
      "epoch": 6.44,
      "learning_rate": 0.0002,
      "loss": 0.007,
      "step": 58
    },
    {
      "epoch": 6.56,
      "learning_rate": 0.0002,
      "loss": 0.0096,
      "step": 59
    },
    {
      "epoch": 6.67,
      "learning_rate": 0.0002,
      "loss": 0.003,
      "step": 60
    },
    {
      "epoch": 6.78,
      "learning_rate": 0.0002,
      "loss": 0.0064,
      "step": 61
    },
    {
      "epoch": 6.89,
      "learning_rate": 0.0002,
      "loss": 0.0041,
      "step": 62
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.0002,
      "loss": 0.0051,
      "step": 63
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.5378952026367188,
      "eval_runtime": 5.3409,
      "eval_samples_per_second": 9.362,
      "eval_steps_per_second": 0.374,
      "step": 63
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.0002,
      "loss": 0.0094,
      "step": 64
    },
    {
      "epoch": 7.22,
      "learning_rate": 0.0002,
      "loss": 0.0038,
      "step": 65
    },
    {
      "epoch": 7.33,
      "learning_rate": 0.0002,
      "loss": 0.0025,
      "step": 66
    },
    {
      "epoch": 7.44,
      "learning_rate": 0.0002,
      "loss": 0.0043,
      "step": 67
    },
    {
      "epoch": 7.56,
      "learning_rate": 0.0002,
      "loss": 0.0039,
      "step": 68
    },
    {
      "epoch": 7.67,
      "learning_rate": 0.0002,
      "loss": 0.0019,
      "step": 69
    },
    {
      "epoch": 7.78,
      "learning_rate": 0.0002,
      "loss": 0.0039,
      "step": 70
    },
    {
      "epoch": 7.89,
      "learning_rate": 0.0002,
      "loss": 0.0043,
      "step": 71
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.0002,
      "loss": 0.0012,
      "step": 72
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.5768710374832153,
      "eval_runtime": 5.3401,
      "eval_samples_per_second": 9.363,
      "eval_steps_per_second": 0.375,
      "step": 72
    },
    {
      "epoch": 8.11,
      "learning_rate": 0.0002,
      "loss": 0.0012,
      "step": 73
    },
    {
      "epoch": 8.22,
      "learning_rate": 0.0002,
      "loss": 0.0021,
      "step": 74
    },
    {
      "epoch": 8.33,
      "learning_rate": 0.0002,
      "loss": 0.003,
      "step": 75
    },
    {
      "epoch": 8.44,
      "learning_rate": 0.0002,
      "loss": 0.001,
      "step": 76
    },
    {
      "epoch": 8.56,
      "learning_rate": 0.0002,
      "loss": 0.0022,
      "step": 77
    },
    {
      "epoch": 8.67,
      "learning_rate": 0.0002,
      "loss": 0.0069,
      "step": 78
    },
    {
      "epoch": 8.78,
      "learning_rate": 0.0002,
      "loss": 0.0012,
      "step": 79
    },
    {
      "epoch": 8.89,
      "learning_rate": 0.0002,
      "loss": 0.0011,
      "step": 80
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.0002,
      "loss": 0.0015,
      "step": 81
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.6410647630691528,
      "eval_runtime": 5.3143,
      "eval_samples_per_second": 9.409,
      "eval_steps_per_second": 0.376,
      "step": 81
    },
    {
      "epoch": 9.11,
      "learning_rate": 0.0002,
      "loss": 0.002,
      "step": 82
    },
    {
      "epoch": 9.22,
      "learning_rate": 0.0002,
      "loss": 0.0007,
      "step": 83
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.0002,
      "loss": 0.0018,
      "step": 84
    },
    {
      "epoch": 9.44,
      "learning_rate": 0.0002,
      "loss": 0.0018,
      "step": 85
    },
    {
      "epoch": 9.56,
      "learning_rate": 0.0002,
      "loss": 0.0023,
      "step": 86
    },
    {
      "epoch": 9.67,
      "learning_rate": 0.0002,
      "loss": 0.0035,
      "step": 87
    },
    {
      "epoch": 9.78,
      "learning_rate": 0.0002,
      "loss": 0.0007,
      "step": 88
    },
    {
      "epoch": 9.89,
      "learning_rate": 0.0002,
      "loss": 0.0038,
      "step": 89
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0002,
      "loss": 0.0005,
      "step": 90
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.6346640586853027,
      "eval_runtime": 5.3194,
      "eval_samples_per_second": 9.4,
      "eval_steps_per_second": 0.376,
      "step": 90
    },
    {
      "epoch": 10.0,
      "step": 90,
      "total_flos": 1.6878235281679974e+17,
      "train_loss": 0.1825528386579309,
      "train_runtime": 634.3775,
      "train_samples_per_second": 4.461,
      "train_steps_per_second": 0.142
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 90,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 50000,
  "total_flos": 1.6878235281679974e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}