{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.998864926220204,
  "global_step": 1760,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4856970986003244,
      "eval_loss": 3.856384515762329,
      "eval_runtime": 5.67,
      "eval_samples_per_second": 16.049,
      "eval_steps_per_second": 8.113,
      "step": 220
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6095839644226742,
      "eval_loss": 2.7515063285827637,
      "eval_runtime": 5.6811,
      "eval_samples_per_second": 16.018,
      "eval_steps_per_second": 8.097,
      "step": 440
    },
    {
      "epoch": 2.27,
      "learning_rate": 7.181818181818182e-06,
      "loss": 4.1568,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6779671940962263,
      "eval_loss": 2.2462902069091797,
      "eval_runtime": 5.6846,
      "eval_samples_per_second": 16.008,
      "eval_steps_per_second": 8.092,
      "step": 660
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7152310055535862,
      "eval_loss": 1.981738567352295,
      "eval_runtime": 5.6899,
      "eval_samples_per_second": 15.993,
      "eval_steps_per_second": 8.084,
      "step": 880
    },
    {
      "epoch": 4.54,
      "learning_rate": 4.340909090909091e-06,
      "loss": 2.2818,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7353184449958643,
      "eval_loss": 1.8277500867843628,
      "eval_runtime": 5.6901,
      "eval_samples_per_second": 15.993,
      "eval_steps_per_second": 8.084,
      "step": 1100
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7485740066385228,
      "eval_loss": 1.7312932014465332,
      "eval_runtime": 5.683,
      "eval_samples_per_second": 16.013,
      "eval_steps_per_second": 8.094,
      "step": 1320
    },
    {
      "epoch": 6.82,
      "learning_rate": 1.5e-06,
      "loss": 1.8444,
      "step": 1500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7553092069221101,
      "eval_loss": 1.6847076416015625,
      "eval_runtime": 5.6791,
      "eval_samples_per_second": 16.024,
      "eval_steps_per_second": 8.1,
      "step": 1540
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.75708162804937,
      "eval_loss": 1.669904112815857,
      "eval_runtime": 5.9939,
      "eval_samples_per_second": 15.182,
      "eval_steps_per_second": 7.674,
      "step": 1760
    },
    {
      "epoch": 8.0,
      "step": 1760,
      "total_flos": 6.134202859152998e+16,
      "train_loss": 2.6170630194924094,
      "train_runtime": 2594.3652,
      "train_samples_per_second": 5.433,
      "train_steps_per_second": 0.678
    }
  ],
  "max_steps": 1760,
  "num_train_epochs": 8,
  "total_flos": 6.134202859152998e+16,
  "trial_name": null,
  "trial_params": null
}