{
  "best_metric": 0.889345109462738,
  "best_model_checkpoint": "output/finetune/llama-3.1-8b/mbpp/2e-5-3epoch-mbpp-v1/checkpoint-4",
  "epoch": 3.0,
  "eval_steps": 1,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "eval_loss": 2.062755823135376,
      "eval_runtime": 0.1446,
      "eval_samples_per_second": 297.286,
      "eval_steps_per_second": 13.827,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1295955181121826,
      "eval_runtime": 0.1329,
      "eval_samples_per_second": 323.473,
      "eval_steps_per_second": 15.045,
      "step": 2
    },
    {
      "epoch": 1.5,
      "eval_loss": 0.9314517378807068,
      "eval_runtime": 0.1323,
      "eval_samples_per_second": 325.101,
      "eval_steps_per_second": 15.121,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.889345109462738,
      "eval_runtime": 0.1313,
      "eval_samples_per_second": 327.454,
      "eval_steps_per_second": 15.23,
      "step": 4
    },
    {
      "epoch": 2.5,
      "grad_norm": 24.375,
      "learning_rate": 4.000000000000001e-06,
      "loss": 5.2411,
      "step": 5
    },
    {
      "epoch": 2.5,
      "eval_loss": 0.8952356576919556,
      "eval_runtime": 0.109,
      "eval_samples_per_second": 394.377,
      "eval_steps_per_second": 18.343,
      "step": 5
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.8954342007637024,
      "eval_runtime": 0.1323,
      "eval_samples_per_second": 324.91,
      "eval_steps_per_second": 15.112,
      "step": 6
    },
    {
      "epoch": 3.0,
      "step": 6,
      "total_flos": 1872868942020608.0,
      "train_loss": 4.762929121653239,
      "train_runtime": 490.1592,
      "train_samples_per_second": 0.734,
      "train_steps_per_second": 0.012
    }
  ],
  "logging_steps": 5,
  "max_steps": 6,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1872868942020608.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}