{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.4071550255536627,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8517887563884157,
      "grad_norm": 0.07218749076128006,
      "learning_rate": 4.6128232925507207e-05,
      "loss": 1.4771,
      "step": 500
    },
    {
      "epoch": 1.7035775127768313,
      "grad_norm": 3.5773040779618626e-11,
      "learning_rate": 4.2256465851014404e-05,
      "loss": 0.6892,
      "step": 1000
    },
    {
      "epoch": 2.555366269165247,
      "grad_norm": 1.4907100549597627e-18,
      "learning_rate": 3.838469877652161e-05,
      "loss": 0.391,
      "step": 1500
    },
    {
      "epoch": 3.4071550255536627,
      "grad_norm": 8.450392385839223e-09,
      "learning_rate": 3.4512931702028805e-05,
      "loss": 0.0828,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 6457,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 11,
  "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": 6640298805288960.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}