{
  "best_metric": 1.0949230194091797,
  "best_model_checkpoint": "/kaggle/output/checkpoint-8000",
  "epoch": 0.3666883963494133,
  "eval_steps": 1000,
  "global_step": 9000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.7777777777777777e-11,
      "loss": 1.1065,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.7750000000000004e-08,
      "loss": 1.1586,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.32954091816367265,
      "eval_loss": 1.1065887212753296,
      "eval_runtime": 54.4372,
      "eval_samples_per_second": 92.033,
      "eval_steps_per_second": 11.518,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.5527777777777784e-08,
      "loss": 1.1259,
      "step": 2000
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.3435129740518962,
      "eval_loss": 1.1045255661010742,
      "eval_runtime": 54.458,
      "eval_samples_per_second": 91.997,
      "eval_steps_per_second": 11.513,
      "step": 2000
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.327777777777778e-08,
      "loss": 1.1229,
      "step": 3000
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.3441117764471058,
      "eval_loss": 1.1050777435302734,
      "eval_runtime": 54.349,
      "eval_samples_per_second": 92.182,
      "eval_steps_per_second": 11.537,
      "step": 3000
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.1105555555555557e-07,
      "loss": 1.1237,
      "step": 4000
    },
    {
      "epoch": 0.16,
      "eval_accuracy": 0.3411177644710579,
      "eval_loss": 1.1015312671661377,
      "eval_runtime": 54.4388,
      "eval_samples_per_second": 92.03,
      "eval_steps_per_second": 11.518,
      "step": 4000
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.3883333333333335e-07,
      "loss": 1.1202,
      "step": 5000
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.3405189620758483,
      "eval_loss": 1.1006112098693848,
      "eval_runtime": 54.4109,
      "eval_samples_per_second": 92.077,
      "eval_steps_per_second": 11.523,
      "step": 5000
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.6658333333333335e-07,
      "loss": 1.1182,
      "step": 6000
    },
    {
      "epoch": 0.24,
      "eval_accuracy": 0.35489021956087824,
      "eval_loss": 1.0982259511947632,
      "eval_runtime": 54.3841,
      "eval_samples_per_second": 92.123,
      "eval_steps_per_second": 11.529,
      "step": 6000
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9436111111111112e-07,
      "loss": 1.1125,
      "step": 7000
    },
    {
      "epoch": 0.29,
      "eval_accuracy": 0.35748502994011977,
      "eval_loss": 1.0954252481460571,
      "eval_runtime": 54.3975,
      "eval_samples_per_second": 92.1,
      "eval_steps_per_second": 11.526,
      "step": 7000
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.2213888888888891e-07,
      "loss": 1.1096,
      "step": 8000
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.3664670658682635,
      "eval_loss": 1.0949230194091797,
      "eval_runtime": 54.3263,
      "eval_samples_per_second": 92.221,
      "eval_steps_per_second": 11.541,
      "step": 8000
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.4988888888888893e-07,
      "loss": 1.1057,
      "step": 9000
    },
    {
      "epoch": 0.37,
      "eval_accuracy": 0.34890219560878244,
      "eval_loss": 1.1037237644195557,
      "eval_runtime": 54.3657,
      "eval_samples_per_second": 92.154,
      "eval_steps_per_second": 11.533,
      "step": 9000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 10000000,
  "num_train_epochs": 408,
  "save_steps": 1000,
  "total_flos": 1.8813196173312e+16,
  "trial_name": null,
  "trial_params": null
}