{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.8412291933418694,
  "eval_steps": 1000,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2804097311139564,
      "grad_norm": 6.089337348937988,
      "learning_rate": 4.560090771673174e-06,
      "loss": 0.27634707641601564,
      "step": 1000
    },
    {
      "epoch": 2.560819462227913,
      "grad_norm": 9.166674613952637,
      "learning_rate": 3.319169141307007e-06,
      "loss": 0.195736083984375,
      "step": 2000
    },
    {
      "epoch": 3.8412291933418694,
      "grad_norm": 9.20052433013916,
      "learning_rate": 1.7592143190904068e-06,
      "loss": 0.13768116760253907,
      "step": 3000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 1000,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}