{
  "best_metric": 1.1033366918563843,
  "best_model_checkpoint": "/kaggle/output/checkpoint-2000",
  "epoch": 0.12222946544980444,
  "eval_steps": 1000,
  "global_step": 3000,
  "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": 1.0722,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.7750000000000004e-08,
      "loss": 1.1407,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.32914171656686625,
      "eval_loss": 1.1048731803894043,
      "eval_runtime": 57.3781,
      "eval_samples_per_second": 87.316,
      "eval_steps_per_second": 10.928,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.5527777777777784e-08,
      "loss": 1.1253,
      "step": 2000
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.3377245508982036,
      "eval_loss": 1.1033366918563843,
      "eval_runtime": 57.3237,
      "eval_samples_per_second": 87.398,
      "eval_steps_per_second": 10.938,
      "step": 2000
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.327777777777778e-08,
      "loss": 1.1179,
      "step": 3000
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.3502994011976048,
      "eval_loss": 1.104222059249878,
      "eval_runtime": 57.4527,
      "eval_samples_per_second": 87.202,
      "eval_steps_per_second": 10.913,
      "step": 3000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 10000000,
  "num_train_epochs": 408,
  "save_steps": 1000,
  "total_flos": 6271065391104000.0,
  "trial_name": null,
  "trial_params": null
}