{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7001983895437041,
  "eval_steps": 250,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2333994631812347,
      "grad_norm": 0.6670471429824829,
      "learning_rate": 8.959847237666421e-05,
      "loss": 0.3298,
      "step": 250
    },
    {
      "epoch": 0.2333994631812347,
      "eval_loss": 0.20243076980113983,
      "eval_runtime": 18.0166,
      "eval_samples_per_second": 4.829,
      "eval_steps_per_second": 4.829,
      "step": 250
    },
    {
      "epoch": 0.4667989263624694,
      "grad_norm": 0.3776451051235199,
      "learning_rate": 5.783666949486448e-05,
      "loss": 0.1479,
      "step": 500
    },
    {
      "epoch": 0.4667989263624694,
      "eval_loss": 0.14761479198932648,
      "eval_runtime": 17.9702,
      "eval_samples_per_second": 4.841,
      "eval_steps_per_second": 4.841,
      "step": 500
    },
    {
      "epoch": 0.7001983895437041,
      "grad_norm": 0.4652869701385498,
      "learning_rate": 2.179828363456768e-05,
      "loss": 0.1232,
      "step": 750
    },
    {
      "epoch": 0.7001983895437041,
      "eval_loss": 0.1344834417104721,
      "eval_runtime": 18.0431,
      "eval_samples_per_second": 4.822,
      "eval_steps_per_second": 4.822,
      "step": 750
    }
  ],
  "logging_steps": 250,
  "max_steps": 1071,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.58275327536128e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}