{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007415647015202077,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007415647015202076,
      "eval_loss": 2.5420961380004883,
      "eval_runtime": 79.8279,
      "eval_samples_per_second": 7.115,
      "eval_steps_per_second": 3.558,
      "step": 1
    },
    {
      "epoch": 0.002224694104560623,
      "grad_norm": 5.313490867614746,
      "learning_rate": 6e-05,
      "loss": 10.1044,
      "step": 3
    },
    {
      "epoch": 0.004449388209121246,
      "grad_norm": 7.235334873199463,
      "learning_rate": 0.00012,
      "loss": 9.4141,
      "step": 6
    },
    {
      "epoch": 0.005932517612161661,
      "eval_loss": 1.5158597230911255,
      "eval_runtime": 81.2804,
      "eval_samples_per_second": 6.988,
      "eval_steps_per_second": 3.494,
      "step": 8
    },
    {
      "epoch": 0.006674082313681869,
      "grad_norm": 10.101544380187988,
      "learning_rate": 0.00018,
      "loss": 7.9929,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3267323221770240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}