{
  "best_global_step": 177,
  "best_metric": 0.0004340429150033742,
  "best_model_checkpoint": "./fine-tuned-model-8\\checkpoint-177",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 177,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.847457627118644,
      "grad_norm": 0.404996782541275,
      "learning_rate": 3.932203389830509e-05,
      "loss": 0.6388,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.06650885194540024,
      "eval_runtime": 8.3615,
      "eval_samples_per_second": 12.558,
      "eval_steps_per_second": 0.837,
      "step": 59
    },
    {
      "epoch": 1.694915254237288,
      "grad_norm": 0.7748989462852478,
      "learning_rate": 3.8644067796610175e-05,
      "loss": 0.0458,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0008016377687454224,
      "eval_runtime": 8.629,
      "eval_samples_per_second": 12.168,
      "eval_steps_per_second": 0.811,
      "step": 118
    },
    {
      "epoch": 2.542372881355932,
      "grad_norm": 0.007611678447574377,
      "learning_rate": 3.796610169491526e-05,
      "loss": 0.002,
      "step": 150
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.0004340429150033742,
      "eval_runtime": 8.5685,
      "eval_samples_per_second": 12.254,
      "eval_steps_per_second": 0.817,
      "step": 177
    }
  ],
  "logging_steps": 50,
  "max_steps": 2950,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5570596939235328.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}