{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.304932735426009,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 3.7037037037037036e-07,
      "loss": 0.6848,
      "step": 2
    },
    {
      "epoch": 0.14,
      "learning_rate": 7.407407407407407e-07,
      "loss": 0.6805,
      "step": 4
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.6842,
      "step": 6
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.4814814814814815e-06,
      "loss": 0.6893,
      "step": 8
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.6787,
      "step": 10
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.6789,
      "step": 12
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.5925925925925925e-06,
      "loss": 0.685,
      "step": 14
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.962962962962963e-06,
      "loss": 0.6823,
      "step": 16
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.6836,
      "step": 18
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.6756,
      "step": 20
    },
    {
      "epoch": 0.72,
      "eval_accuracy": 0.5419999957084656,
      "eval_average_score": 0.5289427638053894,
      "eval_label_positive_rate": 0.47600001096725464,
      "eval_loss": 0.6793817281723022,
      "eval_runtime": 8.697,
      "eval_samples_per_second": 57.491,
      "eval_steps_per_second": 7.244,
      "step": 20
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.074074074074074e-06,
      "loss": 0.6845,
      "step": 22
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.6837,
      "step": 24
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.814814814814815e-06,
      "loss": 0.6743,
      "step": 26
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.185185185185185e-06,
      "loss": 0.6718,
      "step": 28
    },
    {
      "epoch": 1.08,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.6777,
      "step": 30
    },
    {
      "epoch": 1.15,
      "learning_rate": 5.925925925925926e-06,
      "loss": 0.6702,
      "step": 32
    },
    {
      "epoch": 1.22,
      "learning_rate": 6.296296296296297e-06,
      "loss": 0.6743,
      "step": 34
    },
    {
      "epoch": 1.29,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.6722,
      "step": 36
    },
    {
      "epoch": 1.36,
      "learning_rate": 7.0370370370370375e-06,
      "loss": 0.6697,
      "step": 38
    },
    {
      "epoch": 1.43,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.6654,
      "step": 40
    },
    {
      "epoch": 1.43,
      "eval_accuracy": 0.7080000042915344,
      "eval_average_score": 0.4319504201412201,
      "eval_label_positive_rate": 0.47600001096725464,
      "eval_loss": 0.6608079075813293,
      "eval_runtime": 8.6968,
      "eval_samples_per_second": 57.492,
      "eval_steps_per_second": 7.244,
      "step": 40
    },
    {
      "epoch": 1.51,
      "learning_rate": 7.77777777777778e-06,
      "loss": 0.6572,
      "step": 42
    },
    {
      "epoch": 1.58,
      "learning_rate": 8.148148148148148e-06,
      "loss": 0.6621,
      "step": 44
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.518518518518519e-06,
      "loss": 0.6575,
      "step": 46
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.6455,
      "step": 48
    },
    {
      "epoch": 1.79,
      "learning_rate": 9.25925925925926e-06,
      "loss": 0.6367,
      "step": 50
    },
    {
      "epoch": 1.87,
      "learning_rate": 9.62962962962963e-06,
      "loss": 0.64,
      "step": 52
    },
    {
      "epoch": 1.94,
      "learning_rate": 1e-05,
      "loss": 0.6316,
      "step": 54
    },
    {
      "epoch": 2.01,
      "learning_rate": 1e-05,
      "loss": 0.6121,
      "step": 56
    },
    {
      "epoch": 2.08,
      "learning_rate": 1e-05,
      "loss": 0.6104,
      "step": 58
    },
    {
      "epoch": 2.15,
      "learning_rate": 1e-05,
      "loss": 0.5916,
      "step": 60
    },
    {
      "epoch": 2.15,
      "eval_accuracy": 0.9419999718666077,
      "eval_average_score": 0.13356663286685944,
      "eval_label_positive_rate": 0.47600001096725464,
      "eval_loss": 0.5838245153427124,
      "eval_runtime": 8.6962,
      "eval_samples_per_second": 57.496,
      "eval_steps_per_second": 7.245,
      "step": 60
    },
    {
      "epoch": 2.22,
      "learning_rate": 1e-05,
      "loss": 0.5801,
      "step": 62
    },
    {
      "epoch": 2.3,
      "learning_rate": 1e-05,
      "loss": 0.5677,
      "step": 64
    },
    {
      "epoch": 2.37,
      "learning_rate": 1e-05,
      "loss": 0.5472,
      "step": 66
    },
    {
      "epoch": 2.44,
      "learning_rate": 1e-05,
      "loss": 0.5267,
      "step": 68
    },
    {
      "epoch": 2.51,
      "learning_rate": 1e-05,
      "loss": 0.5224,
      "step": 70
    },
    {
      "epoch": 2.58,
      "learning_rate": 1e-05,
      "loss": 0.49,
      "step": 72
    },
    {
      "epoch": 2.65,
      "learning_rate": 1e-05,
      "loss": 0.4607,
      "step": 74
    },
    {
      "epoch": 2.73,
      "learning_rate": 1e-05,
      "loss": 0.4295,
      "step": 76
    },
    {
      "epoch": 2.8,
      "learning_rate": 1e-05,
      "loss": 0.393,
      "step": 78
    },
    {
      "epoch": 2.87,
      "learning_rate": 1e-05,
      "loss": 0.3463,
      "step": 80
    },
    {
      "epoch": 2.87,
      "eval_accuracy": 0.9800000190734863,
      "eval_average_score": -0.13676369190216064,
      "eval_label_positive_rate": 0.47600001096725464,
      "eval_loss": 0.30906087160110474,
      "eval_runtime": 8.6996,
      "eval_samples_per_second": 57.474,
      "eval_steps_per_second": 7.242,
      "step": 80
    },
    {
      "epoch": 2.94,
      "learning_rate": 1e-05,
      "loss": 0.3167,
      "step": 82
    },
    {
      "epoch": 3.01,
      "learning_rate": 1e-05,
      "loss": 0.2559,
      "step": 84
    },
    {
      "epoch": 3.09,
      "learning_rate": 1e-05,
      "loss": 0.2119,
      "step": 86
    },
    {
      "epoch": 3.16,
      "learning_rate": 1e-05,
      "loss": 0.1874,
      "step": 88
    },
    {
      "epoch": 3.23,
      "learning_rate": 1e-05,
      "loss": 0.1407,
      "step": 90
    },
    {
      "epoch": 3.3,
      "learning_rate": 1e-05,
      "loss": 0.1037,
      "step": 92
    },
    {
      "epoch": 3.37,
      "learning_rate": 1e-05,
      "loss": 0.0717,
      "step": 94
    },
    {
      "epoch": 3.44,
      "learning_rate": 1e-05,
      "loss": 0.0692,
      "step": 96
    },
    {
      "epoch": 3.52,
      "learning_rate": 1e-05,
      "loss": 0.0708,
      "step": 98
    },
    {
      "epoch": 3.59,
      "learning_rate": 1e-05,
      "loss": 0.0426,
      "step": 100
    },
    {
      "epoch": 3.59,
      "eval_accuracy": 0.9879999756813049,
      "eval_average_score": -0.7325789332389832,
      "eval_label_positive_rate": 0.47600001096725464,
      "eval_loss": 0.03151561692357063,
      "eval_runtime": 8.708,
      "eval_samples_per_second": 57.418,
      "eval_steps_per_second": 7.235,
      "step": 100
    },
    {
      "epoch": 3.66,
      "learning_rate": 1e-05,
      "loss": 0.0315,
      "step": 102
    },
    {
      "epoch": 3.73,
      "learning_rate": 1e-05,
      "loss": 0.0227,
      "step": 104
    },
    {
      "epoch": 3.8,
      "learning_rate": 1e-05,
      "loss": 0.0272,
      "step": 106
    },
    {
      "epoch": 3.87,
      "learning_rate": 1e-05,
      "loss": 0.0203,
      "step": 108
    },
    {
      "epoch": 3.95,
      "learning_rate": 1e-05,
      "loss": 0.0151,
      "step": 110
    },
    {
      "epoch": 4.02,
      "learning_rate": 1e-05,
      "loss": 0.0199,
      "step": 112
    },
    {
      "epoch": 4.09,
      "learning_rate": 1e-05,
      "loss": 0.0171,
      "step": 114
    },
    {
      "epoch": 4.16,
      "learning_rate": 1e-05,
      "loss": 0.0094,
      "step": 116
    },
    {
      "epoch": 4.23,
      "learning_rate": 1e-05,
      "loss": 0.0166,
      "step": 118
    },
    {
      "epoch": 4.3,
      "learning_rate": 1e-05,
      "loss": 0.0079,
      "step": 120
    },
    {
      "epoch": 4.3,
      "eval_accuracy": 1.0,
      "eval_average_score": -1.2080471515655518,
      "eval_label_positive_rate": 0.47600001096725464,
      "eval_loss": 0.009560000151395798,
      "eval_runtime": 8.7049,
      "eval_samples_per_second": 57.439,
      "eval_steps_per_second": 7.237,
      "step": 120
    }
  ],
  "max_steps": 270,
  "num_train_epochs": 10,
  "total_flos": 3.914291024788193e+17,
  "trial_name": null,
  "trial_params": null
}