{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.972644376899696,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.48632218844984804,
      "grad_norm": 128.50929260253906,
      "learning_rate": 5e-06,
      "loss": 1.2407,
      "step": 10
    },
    {
      "epoch": 0.9726443768996961,
      "grad_norm": 6.158934116363525,
      "learning_rate": 1e-05,
      "loss": 0.5547,
      "step": 20
    },
    {
      "epoch": 1.486322188449848,
      "grad_norm": 6.566050052642822,
      "learning_rate": 1.5e-05,
      "loss": 0.4024,
      "step": 30
    },
    {
      "epoch": 1.9726443768996962,
      "grad_norm": 5.034642696380615,
      "learning_rate": 2e-05,
      "loss": 0.1755,
      "step": 40
    },
    {
      "epoch": 2.486322188449848,
      "grad_norm": 1.5557312965393066,
      "learning_rate": 2.5e-05,
      "loss": 0.0485,
      "step": 50
    },
    {
      "epoch": 2.972644376899696,
      "grad_norm": 0.319848895072937,
      "learning_rate": 3e-05,
      "loss": 0.0346,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5194827497472.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}