{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00555971346092163,
  "eval_steps": 10,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004276702662247407,
      "eval_loss": 3.4804275035858154,
      "eval_runtime": 15.2889,
      "eval_samples_per_second": 64.426,
      "eval_steps_per_second": 32.246,
      "step": 1
    },
    {
      "epoch": 0.0021383513311237037,
      "grad_norm": 0.7456838488578796,
      "learning_rate": 5e-05,
      "loss": 3.6062,
      "step": 5
    },
    {
      "epoch": 0.004276702662247407,
      "grad_norm": 1.261491060256958,
      "learning_rate": 0.0001,
      "loss": 3.4641,
      "step": 10
    },
    {
      "epoch": 0.004276702662247407,
      "eval_loss": 3.438182830810547,
      "eval_runtime": 15.358,
      "eval_samples_per_second": 64.136,
      "eval_steps_per_second": 32.1,
      "step": 10
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 44580445618176.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}