{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.2679738562091503,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_f1": 0.0,
      "eval_f1_sklearn": 0.9551506074222,
      "eval_loss": 0.20079144835472107,
      "eval_precision": 0.0,
      "eval_precision_sklearn": 0.9551506074222,
      "eval_recall": 0.0,
      "eval_recall_sklearn": 0.9551506074222,
      "eval_runtime": 4.2829,
      "eval_samples_per_second": 95.262,
      "eval_steps_per_second": 23.815,
      "step": 153
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.0,
      "eval_f1_sklearn": 0.9551506074222,
      "eval_loss": 0.200123593211174,
      "eval_precision": 0.0,
      "eval_precision_sklearn": 0.9551506074222,
      "eval_recall": 0.0,
      "eval_recall_sklearn": 0.9551506074222,
      "eval_runtime": 3.972,
      "eval_samples_per_second": 102.72,
      "eval_steps_per_second": 25.68,
      "step": 306
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.0,
      "eval_f1_sklearn": 0.9551506074222,
      "eval_loss": 0.19927753508090973,
      "eval_precision": 0.0,
      "eval_precision_sklearn": 0.9551506074222,
      "eval_recall": 0.0,
      "eval_recall_sklearn": 0.9551506074222,
      "eval_runtime": 3.9795,
      "eval_samples_per_second": 102.524,
      "eval_steps_per_second": 25.631,
      "step": 459
    },
    {
      "epoch": 3.2679738562091503,
      "grad_norm": 0.3564257025718689,
      "learning_rate": 0.00017320261437908497,
      "loss": 0.1991,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 765,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 418074507767664.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "_wandb": {},
    "assignments": {},
    "learning_rate": 0.0005,
    "metric": "eval/loss",
    "per_device_train_batch_size": 8
  }
}