{
  "best_global_step": 1200,
  "best_metric": 2.1439664363861084,
  "best_model_checkpoint": "./results/checkpoint-1200",
  "epoch": 0.4,
  "eval_steps": 600,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 1.328125,
      "learning_rate": 0.00018033388981636062,
      "loss": 0.5064,
      "step": 600
    },
    {
      "epoch": 0.2,
      "eval_loss": 2.144320249557495,
      "eval_runtime": 183.765,
      "eval_samples_per_second": 65.301,
      "eval_steps_per_second": 16.325,
      "step": 600
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.478515625,
      "learning_rate": 0.00016030050083472454,
      "loss": 0.244,
      "step": 1200
    },
    {
      "epoch": 0.4,
      "eval_loss": 2.1439664363861084,
      "eval_runtime": 201.3005,
      "eval_samples_per_second": 59.612,
      "eval_steps_per_second": 14.903,
      "step": 1200
    }
  ],
  "logging_steps": 600,
  "max_steps": 6000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 600,
  "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": 2.004344603816755e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}