{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.034960145434205,
  "eval_steps": 5000,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006992029086841001,
      "grad_norm": 75.90129852294922,
      "learning_rate": 6.780845858091577e-07,
      "loss": 16.865,
      "step": 100
    },
    {
      "epoch": 0.013984058173682002,
      "grad_norm": 71.16612243652344,
      "learning_rate": 1.3771408598392172e-06,
      "loss": 16.1556,
      "step": 200
    },
    {
      "epoch": 0.020976087260523003,
      "grad_norm": 130.67613220214844,
      "learning_rate": 2.0761971338692767e-06,
      "loss": 14.8008,
      "step": 300
    },
    {
      "epoch": 0.027968116347364003,
      "grad_norm": 36.4179801940918,
      "learning_rate": 2.7682628451590356e-06,
      "loss": 12.4025,
      "step": 400
    },
    {
      "epoch": 0.034960145434205,
      "grad_norm": 34.748844146728516,
      "learning_rate": 3.467319119189095e-06,
      "loss": 9.7465,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 28604,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}