run-0/checkpoint-5/trainer_state.json

{
  "best_metric": 0.70751953125,
  "best_model_checkpoint": "test_trainer\\run-0\\checkpoint-3",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 5,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.7080078125,
      "eval_runtime": 0.1741,
      "eval_samples_per_second": 5.744,
      "eval_steps_per_second": 5.744,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.7080078125,
      "eval_runtime": 0.1514,
      "eval_samples_per_second": 6.605,
      "eval_steps_per_second": 6.605,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.70751953125,
      "eval_runtime": 0.1497,
      "eval_samples_per_second": 6.681,
      "eval_steps_per_second": 6.681,
      "step": 3
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.70751953125,
      "eval_runtime": 0.1815,
      "eval_samples_per_second": 5.51,
      "eval_steps_per_second": 5.51,
      "step": 4
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.70751953125,
      "eval_runtime": 0.1768,
      "eval_samples_per_second": 5.657,
      "eval_steps_per_second": 5.657,
      "step": 5
    }
  ],
  "logging_steps": 500,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "gradient_accumulation_steps": 8,
    "learning_rate": 7.543213106016258e-06,
    "num_train_epochs": 5,
    "optimizer": "AdamW",
    "seed": 48,
    "warmup_ratio": 0.2668631355210866,
    "warmup_steps": 204,
    "weight_decay": 0.4761015845296048
  }
}