{
  "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": 1.8683,
      "step": 1
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00012618595071429146,
      "loss": 1.3271,
      "step": 2
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.4466,
      "step": 3
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.2395,
      "step": 4
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.1324,
      "step": 5
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.0393,
      "step": 6
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.9908,
      "step": 7
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.8564,
      "step": 8
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.8953,
      "step": 9
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0183672904968262,
      "eval_runtime": 5.4699,
      "eval_samples_per_second": 9.141,
      "eval_steps_per_second": 0.366,
      "step": 9
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.6845,
      "step": 10
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.5012,
      "step": 11
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.4781,
      "step": 12
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 0.537,
      "step": 13
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 0.4819,
      "step": 14
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 0.4597,
      "step": 15
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 0.311,
      "step": 16
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 0.2765,
      "step": 17
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 0.2243,
      "step": 18
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.1205252408981323,
      "eval_runtime": 5.3424,
      "eval_samples_per_second": 9.359,
      "eval_steps_per_second": 0.374,
      "step": 18
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002,
      "loss": 0.1638,
      "step": 19
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0002,
      "loss": 0.1098,
      "step": 20
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0002,
      "loss": 0.1072,
      "step": 21
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0002,
      "loss": 0.1314,
      "step": 22
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0002,
      "loss": 0.0875,
      "step": 23
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0002,
      "loss": 0.0577,
      "step": 24
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0002,
      "loss": 0.0921,
      "step": 25
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0002,
      "loss": 0.0993,
      "step": 26
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0002,
      "loss": 0.0751,
      "step": 27
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.1984949111938477,
      "eval_runtime": 5.5175,
      "eval_samples_per_second": 9.062,
      "eval_steps_per_second": 0.362,
      "step": 27
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0002,
      "loss": 0.0364,
      "step": 28
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.0002,
      "loss": 0.0341,
      "step": 29
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0002,
      "loss": 0.0429,
      "step": 30
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0002,
      "loss": 0.025,
      "step": 31
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0002,
      "loss": 0.0339,
      "step": 32
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0002,
      "loss": 0.0348,
      "step": 33
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.0002,
      "loss": 0.0313,
      "step": 34
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.0002,
      "loss": 0.0379,
      "step": 35
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0002,
      "loss": 0.0279,
      "step": 36
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.3922247886657715,
      "eval_runtime": 5.3112,
      "eval_samples_per_second": 9.414,
      "eval_steps_per_second": 0.377,
      "step": 36
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0002,
      "loss": 0.0094,
      "step": 37
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.0002,
      "loss": 0.0163,
      "step": 38
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0002,
      "loss": 0.0119,
      "step": 39
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0002,
      "loss": 0.0108,
      "step": 40
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0002,
      "loss": 0.008,
      "step": 41
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.0002,
      "loss": 0.0164,
      "step": 42
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.0002,
      "loss": 0.0187,
      "step": 43
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0002,
      "loss": 0.01,
      "step": 44
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0002,
      "loss": 0.0093,
      "step": 45
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.5086246728897095,
      "eval_runtime": 5.3535,
      "eval_samples_per_second": 9.34,
      "eval_steps_per_second": 0.374,
      "step": 45
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.0002,
      "loss": 0.0057,
      "step": 46
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.0002,
      "loss": 0.0068,
      "step": 47
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.0002,
      "loss": 0.0066,
      "step": 48
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.0002,
      "loss": 0.0114,
      "step": 49
    },
    {
      "epoch": 5.56,
      "learning_rate": 0.0002,
      "loss": 0.008,
      "step": 50
    },
    {
      "epoch": 5.67,
      "learning_rate": 0.0002,
      "loss": 0.0146,
      "step": 51
    },
    {
      "epoch": 5.78,
      "learning_rate": 0.0002,
      "loss": 0.0095,
      "step": 52
    },
    {
      "epoch": 5.89,
      "learning_rate": 0.0002,
      "loss": 0.0051,
      "step": 53
    },
    {
      "epoch": 6.0,
      "learning_rate": 0.0002,
      "loss": 0.0114,
      "step": 54
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.4457488059997559,
      "eval_runtime": 5.3478,
      "eval_samples_per_second": 9.35,
      "eval_steps_per_second": 0.374,
      "step": 54
    },
    {
      "epoch": 6.11,
      "learning_rate": 0.0002,
      "loss": 0.0052,
      "step": 55
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.0002,
      "loss": 0.0057,
      "step": 56
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.0002,
      "loss": 0.0115,
      "step": 57
    },
    {
      "epoch": 6.44,
      "learning_rate": 0.0002,
      "loss": 0.0067,
      "step": 58
    },
    {
      "epoch": 6.56,
      "learning_rate": 0.0002,
      "loss": 0.0064,
      "step": 59
    },
    {
      "epoch": 6.67,
      "learning_rate": 0.0002,
      "loss": 0.0069,
      "step": 60
    },
    {
      "epoch": 6.78,
      "learning_rate": 0.0002,
      "loss": 0.0074,
      "step": 61
    },
    {
      "epoch": 6.89,
      "learning_rate": 0.0002,
      "loss": 0.0042,
      "step": 62
    },
    {
      "epoch": 7.0,
      "learning_rate": 0.0002,
      "loss": 0.003,
      "step": 63
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.4304248094558716,
      "eval_runtime": 5.3914,
      "eval_samples_per_second": 9.274,
      "eval_steps_per_second": 0.371,
      "step": 63
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.0002,
      "loss": 0.0032,
      "step": 64
    },
    {
      "epoch": 7.22,
      "learning_rate": 0.0002,
      "loss": 0.0026,
      "step": 65
    },
    {
      "epoch": 7.33,
      "learning_rate": 0.0002,
      "loss": 0.0052,
      "step": 66
    },
    {
      "epoch": 7.44,
      "learning_rate": 0.0002,
      "loss": 0.0042,
      "step": 67
    },
    {
      "epoch": 7.56,
      "learning_rate": 0.0002,
      "loss": 0.0055,
      "step": 68
    },
    {
      "epoch": 7.67,
      "learning_rate": 0.0002,
      "loss": 0.004,
      "step": 69
    },
    {
      "epoch": 7.78,
      "learning_rate": 0.0002,
      "loss": 0.0037,
      "step": 70
    },
    {
      "epoch": 7.89,
      "learning_rate": 0.0002,
      "loss": 0.0061,
      "step": 71
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.0002,
      "loss": 0.0028,
      "step": 72
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.4950295686721802,
      "eval_runtime": 5.4012,
      "eval_samples_per_second": 9.257,
      "eval_steps_per_second": 0.37,
      "step": 72
    },
    {
      "epoch": 8.11,
      "learning_rate": 0.0002,
      "loss": 0.0021,
      "step": 73
    },
    {
      "epoch": 8.22,
      "learning_rate": 0.0002,
      "loss": 0.0025,
      "step": 74
    },
    {
      "epoch": 8.33,
      "learning_rate": 0.0002,
      "loss": 0.0112,
      "step": 75
    },
    {
      "epoch": 8.44,
      "learning_rate": 0.0002,
      "loss": 0.0013,
      "step": 76
    },
    {
      "epoch": 8.56,
      "learning_rate": 0.0002,
      "loss": 0.0009,
      "step": 77
    },
    {
      "epoch": 8.67,
      "learning_rate": 0.0002,
      "loss": 0.0019,
      "step": 78
    },
    {
      "epoch": 8.78,
      "learning_rate": 0.0002,
      "loss": 0.0021,
      "step": 79
    },
    {
      "epoch": 8.89,
      "learning_rate": 0.0002,
      "loss": 0.0047,
      "step": 80
    },
    {
      "epoch": 9.0,
      "learning_rate": 0.0002,
      "loss": 0.0011,
      "step": 81
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.5274981260299683,
      "eval_runtime": 5.3505,
      "eval_samples_per_second": 9.345,
      "eval_steps_per_second": 0.374,
      "step": 81
    },
    {
      "epoch": 9.11,
      "learning_rate": 0.0002,
      "loss": 0.0011,
      "step": 82
    },
    {
      "epoch": 9.22,
      "learning_rate": 0.0002,
      "loss": 0.0004,
      "step": 83
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.0002,
      "loss": 0.0018,
      "step": 84
    },
    {
      "epoch": 9.44,
      "learning_rate": 0.0002,
      "loss": 0.001,
      "step": 85
    },
    {
      "epoch": 9.56,
      "learning_rate": 0.0002,
      "loss": 0.0006,
      "step": 86
    },
    {
      "epoch": 9.67,
      "learning_rate": 0.0002,
      "loss": 0.0009,
      "step": 87
    },
    {
      "epoch": 9.78,
      "learning_rate": 0.0002,
      "loss": 0.0031,
      "step": 88
    },
    {
      "epoch": 9.89,
      "learning_rate": 0.0002,
      "loss": 0.0008,
      "step": 89
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0002,
      "loss": 0.0011,
      "step": 90
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.5826122760772705,
      "eval_runtime": 5.3744,
      "eval_samples_per_second": 9.303,
      "eval_steps_per_second": 0.372,
      "step": 90
    },
    {
      "epoch": 10.0,
      "step": 90,
      "total_flos": 1.694918922857349e+17,
      "train_loss": 0.18111829615146335,
      "train_runtime": 635.413,
      "train_samples_per_second": 4.454,
      "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": 1.694918922857349e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}