{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9952038369304557,
  "eval_steps": 500,
  "global_step": 208,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009592326139088728,
      "grad_norm": 22.080848693847656,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 7.4477,
      "step": 1
    },
    {
      "epoch": 0.9976019184652278,
      "grad_norm": 4.235527038574219,
      "learning_rate": 1.3164556962025317e-05,
      "loss": 6.4196,
      "step": 104
    },
    {
      "epoch": 1.9952038369304557,
      "grad_norm": 5.404126167297363,
      "learning_rate": 0.0,
      "loss": 5.713,
      "step": 208
    }
  ],
  "logging_steps": 2,
  "max_steps": 208,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9439352575352832.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}