{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02302025782688766,
  "eval_steps": 1000,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 3.6137,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 3.4233,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 3.3927,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016,
      "loss": 2.8163,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.4858,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019789473684210526,
      "loss": 1.9139,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019578947368421054,
      "loss": 2.0399,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001936842105263158,
      "loss": 1.9175,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00019157894736842104,
      "loss": 2.2095,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018947368421052632,
      "loss": 1.9044,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001873684210526316,
      "loss": 2.013,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018526315789473685,
      "loss": 2.1313,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001831578947368421,
      "loss": 1.9865,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018105263157894739,
      "loss": 1.7398,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017894736842105264,
      "loss": 1.693,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001768421052631579,
      "loss": 1.6588,
      "step": 16
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017473684210526317,
      "loss": 1.989,
      "step": 17
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017263157894736842,
      "loss": 1.9944,
      "step": 18
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001705263157894737,
      "loss": 1.7393,
      "step": 19
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016842105263157895,
      "loss": 1.7573,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016631578947368423,
      "loss": 1.546,
      "step": 21
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016421052631578948,
      "loss": 1.6286,
      "step": 22
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016210526315789473,
      "loss": 1.61,
      "step": 23
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016,
      "loss": 1.7942,
      "step": 24
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015789473684210527,
      "loss": 1.4316,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015578947368421052,
      "loss": 1.5606,
      "step": 26
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001536842105263158,
      "loss": 1.7435,
      "step": 27
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015157894736842108,
      "loss": 1.2904,
      "step": 28
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014947368421052633,
      "loss": 1.7799,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014736842105263158,
      "loss": 1.3407,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014526315789473686,
      "loss": 1.7537,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001431578947368421,
      "loss": 1.6549,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014105263157894736,
      "loss": 1.8332,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00013894736842105264,
      "loss": 1.4519,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001368421052631579,
      "loss": 1.7497,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00013473684210526317,
      "loss": 1.8566,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00013263157894736842,
      "loss": 1.5518,
      "step": 37
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001305263157894737,
      "loss": 1.2759,
      "step": 38
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012842105263157895,
      "loss": 1.5634,
      "step": 39
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001263157894736842,
      "loss": 1.3718,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012421052631578949,
      "loss": 1.2056,
      "step": 41
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012210526315789474,
      "loss": 1.3365,
      "step": 42
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012,
      "loss": 1.5912,
      "step": 43
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00011789473684210525,
      "loss": 1.5067,
      "step": 44
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00011578947368421053,
      "loss": 1.8345,
      "step": 45
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001136842105263158,
      "loss": 1.5727,
      "step": 46
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00011157894736842105,
      "loss": 1.5058,
      "step": 47
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010947368421052633,
      "loss": 1.5746,
      "step": 48
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010736842105263158,
      "loss": 1.4634,
      "step": 49
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010526315789473685,
      "loss": 1.6622,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010315789473684211,
      "loss": 1.7978,
      "step": 51
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00010105263157894738,
      "loss": 1.6079,
      "step": 52
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.894736842105263e-05,
      "loss": 1.3305,
      "step": 53
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.68421052631579e-05,
      "loss": 1.0298,
      "step": 54
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.473684210526316e-05,
      "loss": 1.5233,
      "step": 55
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.263157894736843e-05,
      "loss": 1.8328,
      "step": 56
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.052631578947369e-05,
      "loss": 0.8634,
      "step": 57
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.842105263157894e-05,
      "loss": 1.5285,
      "step": 58
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.631578947368421e-05,
      "loss": 1.3395,
      "step": 59
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.421052631578948e-05,
      "loss": 1.1776,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.210526315789474e-05,
      "loss": 1.3302,
      "step": 61
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 1.2749,
      "step": 62
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.789473684210526e-05,
      "loss": 1.4488,
      "step": 63
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.578947368421054e-05,
      "loss": 1.7981,
      "step": 64
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.368421052631579e-05,
      "loss": 1.2097,
      "step": 65
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.157894736842105e-05,
      "loss": 1.5589,
      "step": 66
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.947368421052632e-05,
      "loss": 1.5017,
      "step": 67
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.736842105263159e-05,
      "loss": 1.5159,
      "step": 68
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.526315789473685e-05,
      "loss": 1.4459,
      "step": 69
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.31578947368421e-05,
      "loss": 1.5433,
      "step": 70
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.105263157894737e-05,
      "loss": 1.8857,
      "step": 71
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.894736842105263e-05,
      "loss": 1.6394,
      "step": 72
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.68421052631579e-05,
      "loss": 1.3062,
      "step": 73
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.4736842105263165e-05,
      "loss": 1.5015,
      "step": 74
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 1.647,
      "step": 75
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.052631578947369e-05,
      "loss": 1.6026,
      "step": 76
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.842105263157895e-05,
      "loss": 1.4526,
      "step": 77
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.6315789473684214e-05,
      "loss": 1.5979,
      "step": 78
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.421052631578947e-05,
      "loss": 1.4417,
      "step": 79
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.210526315789474e-05,
      "loss": 1.619,
      "step": 80
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 1.1932,
      "step": 81
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.789473684210527e-05,
      "loss": 1.563,
      "step": 82
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.578947368421053e-05,
      "loss": 1.4538,
      "step": 83
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.368421052631579e-05,
      "loss": 1.226,
      "step": 84
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.157894736842105e-05,
      "loss": 1.3118,
      "step": 85
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.9473684210526314e-05,
      "loss": 1.4562,
      "step": 86
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.7368421052631583e-05,
      "loss": 1.2999,
      "step": 87
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.5263157894736845e-05,
      "loss": 1.6079,
      "step": 88
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.3157894736842107e-05,
      "loss": 1.3978,
      "step": 89
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.105263157894737e-05,
      "loss": 1.334,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.8947368421052634e-05,
      "loss": 1.8286,
      "step": 91
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.6842105263157896e-05,
      "loss": 1.2721,
      "step": 92
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.4736842105263157e-05,
      "loss": 1.6883,
      "step": 93
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.2631578947368422e-05,
      "loss": 1.9406,
      "step": 94
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 1.4372,
      "step": 95
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.421052631578948e-06,
      "loss": 1.4428,
      "step": 96
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.315789473684211e-06,
      "loss": 1.696,
      "step": 97
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.210526315789474e-06,
      "loss": 1.1901,
      "step": 98
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.105263157894737e-06,
      "loss": 1.574,
      "step": 99
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 1.4564,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 2031145737289728.0,
  "trial_name": null,
  "trial_params": null
}