{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6330365974282888,
  "eval_steps": 500.0,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003165182987141444,
      "grad_norm": 424.0,
      "learning_rate": 3.79746835443038e-08,
      "loss": 12.429935455322266,
      "step": 1,
      "token_acc": 0.3053435114503817
    },
    {
      "epoch": 0.1582591493570722,
      "grad_norm": 0.84375,
      "learning_rate": 5.8099004948061835e-06,
      "loss": 1.251413960733968,
      "step": 500,
      "token_acc": 0.9084568173857424
    },
    {
      "epoch": 0.3165182987141444,
      "grad_norm": 0.5390625,
      "learning_rate": 4.908786401724081e-06,
      "loss": 0.010874405860900879,
      "step": 1000,
      "token_acc": 0.9976750193748385
    },
    {
      "epoch": 0.47477744807121663,
      "grad_norm": 0.09326171875,
      "learning_rate": 3.4968801808609607e-06,
      "loss": 0.009071314811706543,
      "step": 1500,
      "token_acc": 0.998050890042789
    },
    {
      "epoch": 0.6330365974282888,
      "grad_norm": 0.09326171875,
      "learning_rate": 1.952008592786012e-06,
      "loss": 0.006442168235778809,
      "step": 2000,
      "token_acc": 0.9988140489584917
    }
  ],
  "logging_steps": 500,
  "max_steps": 3160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.332279735076086e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}