{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9031256614689903,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.22578141536724758,
      "grad_norm": 0.5844059586524963,
      "learning_rate": 9.247214694369166e-05,
      "loss": 690550.208,
      "step": 500
    },
    {
      "epoch": 0.45156283073449516,
      "grad_norm": 0.8188964128494263,
      "learning_rate": 8.494429388738332e-05,
      "loss": 165964.512,
      "step": 1000
    },
    {
      "epoch": 0.6773442461017427,
      "grad_norm": 0.9122233390808105,
      "learning_rate": 7.741644083107498e-05,
      "loss": 95503.16,
      "step": 1500
    },
    {
      "epoch": 0.9031256614689903,
      "grad_norm": 0.3017164468765259,
      "learning_rate": 6.988858777476665e-05,
      "loss": 428021.44,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 6642,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.4198393918420956e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}