{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.255813953488372,
  "eval_steps": 1,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 21.3430233001709,
      "learning_rate": 1e-05,
      "loss": 9.8559,
      "step": 1
    },
    {
      "epoch": 0.37209302325581395,
      "eval_loss": 9.7179536819458,
      "eval_runtime": 136.3079,
      "eval_samples_per_second": 0.037,
      "eval_steps_per_second": 0.022,
      "step": 1
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 20.012374877929688,
      "learning_rate": 2e-05,
      "loss": 9.6493,
      "step": 2
    },
    {
      "epoch": 0.7441860465116279,
      "eval_loss": 9.398591995239258,
      "eval_runtime": 0.3741,
      "eval_samples_per_second": 13.366,
      "eval_steps_per_second": 8.019,
      "step": 2
    },
    {
      "epoch": 1.255813953488372,
      "grad_norm": 34.39786911010742,
      "learning_rate": 3e-05,
      "loss": 15.866,
      "step": 3
    },
    {
      "epoch": 1.255813953488372,
      "eval_loss": 8.760246276855469,
      "eval_runtime": 0.3773,
      "eval_samples_per_second": 13.253,
      "eval_steps_per_second": 7.952,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 3,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2462872340791296.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}