{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00436316971446904,
  "eval_steps": 17,
  "global_step": 17,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025665704202759064,
      "eval_loss": 2.767350435256958,
      "eval_runtime": 491.4277,
      "eval_samples_per_second": 13.355,
      "eval_steps_per_second": 1.671,
      "step": 1
    },
    {
      "epoch": 0.0007699711260827719,
      "grad_norm": 0.3417242467403412,
      "learning_rate": 3e-05,
      "loss": 2.6769,
      "step": 3
    },
    {
      "epoch": 0.0015399422521655437,
      "grad_norm": 0.35272517800331116,
      "learning_rate": 6e-05,
      "loss": 2.7375,
      "step": 6
    },
    {
      "epoch": 0.0023099133782483157,
      "grad_norm": 0.350046306848526,
      "learning_rate": 9e-05,
      "loss": 2.6718,
      "step": 9
    },
    {
      "epoch": 0.0030798845043310875,
      "grad_norm": 0.3014596104621887,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.5993,
      "step": 12
    },
    {
      "epoch": 0.0038498556304138597,
      "grad_norm": 0.3522738218307495,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.5303,
      "step": 15
    },
    {
      "epoch": 0.00436316971446904,
      "eval_loss": 2.5289151668548584,
      "eval_runtime": 493.8022,
      "eval_samples_per_second": 13.291,
      "eval_steps_per_second": 1.663,
      "step": 17
    }
  ],
  "logging_steps": 3,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4391533604110336e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}