checkpoint-200/trainer_state.json

{
  "best_metric": 0.5658872723579407,
  "best_model_checkpoint": "/kaggle/output/checkpoint-200",
  "epoch": 0.4132231404958678,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.6979,
      "step": 1
    },
    {
      "epoch": 0.1,
      "eval_accuracy": 0.75,
      "eval_loss": 0.6723740696907043,
      "eval_runtime": 28.903,
      "eval_samples_per_second": 40.965,
      "eval_steps_per_second": 20.482,
      "step": 50
    },
    {
      "epoch": 0.21,
      "eval_accuracy": 0.75,
      "eval_loss": 0.6272028088569641,
      "eval_runtime": 28.756,
      "eval_samples_per_second": 41.174,
      "eval_steps_per_second": 20.587,
      "step": 100
    },
    {
      "epoch": 0.31,
      "eval_accuracy": 0.75,
      "eval_loss": 0.5726658701896667,
      "eval_runtime": 28.7791,
      "eval_samples_per_second": 41.141,
      "eval_steps_per_second": 20.57,
      "step": 150
    },
    {
      "epoch": 0.41,
      "eval_accuracy": 0.75,
      "eval_loss": 0.5658872723579407,
      "eval_runtime": 28.8005,
      "eval_samples_per_second": 41.11,
      "eval_steps_per_second": 20.555,
      "step": 200
    }
  ],
  "logging_steps": 1000,
  "max_steps": 1000,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 648800331133968.0,
  "trial_name": null,
  "trial_params": null
}