{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0101010101010102,
  "eval_steps": 150,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020202020202020204,
      "eval_loss": 0.7936934232711792,
      "eval_runtime": 4.8495,
      "eval_samples_per_second": 17.322,
      "eval_steps_per_second": 4.33,
      "step": 1
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 9.893560409545898,
      "learning_rate": 2e-05,
      "loss": 2.4426,
      "step": 10
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 6.190565586090088,
      "learning_rate": 4e-05,
      "loss": 1.5465,
      "step": 20
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 6.172042369842529,
      "learning_rate": 6e-05,
      "loss": 1.3086,
      "step": 30
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 5.878918647766113,
      "learning_rate": 8e-05,
      "loss": 1.1168,
      "step": 40
    },
    {
      "epoch": 1.0101010101010102,
      "grad_norm": 5.348450660705566,
      "learning_rate": 0.0001,
      "loss": 0.9049,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 150,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.330695504055501e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}