{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.028731504094239333,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007182876023559833,
      "grad_norm": 102.55565643310547,
      "learning_rate": 3.339317773788151e-07,
      "loss": 4.51,
      "step": 100
    },
    {
      "epoch": 0.014365752047119667,
      "grad_norm": 20.52243995666504,
      "learning_rate": 6.929982046678636e-07,
      "loss": 1.306,
      "step": 200
    },
    {
      "epoch": 0.0215486280706795,
      "grad_norm": 19.479808807373047,
      "learning_rate": 1.0520646319569122e-06,
      "loss": 0.767,
      "step": 300
    },
    {
      "epoch": 0.028731504094239333,
      "grad_norm": 9.521651268005371,
      "learning_rate": 1.4111310592459606e-06,
      "loss": 0.6409,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 27844,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}