{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9998676022772408,
  "eval_steps": 500,
  "global_step": 236,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004236727128293393,
      "grad_norm": 7.9786027295219055,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 1.4409,
      "step": 1
    },
    {
      "epoch": 0.9998676022772408,
      "eval_loss": 1.2675002813339233,
      "eval_runtime": 349.7638,
      "eval_samples_per_second": 38.237,
      "eval_steps_per_second": 9.561,
      "step": 236
    },
    {
      "epoch": 0.9998676022772408,
      "step": 236,
      "total_flos": 215124962967552.0,
      "train_loss": 1.2779299263226784,
      "train_runtime": 6035.0093,
      "train_samples_per_second": 20.024,
      "train_steps_per_second": 0.039
    }
  ],
  "logging_steps": 100000000,
  "max_steps": 236,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100000000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 215124962967552.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}