{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10084033613445378,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03361344537815126,
      "grad_norm": 21.339550018310547,
      "learning_rate": 2e-05,
      "loss": 3.109,
      "step": 1
    },
    {
      "epoch": 0.03361344537815126,
      "eval_loss": 0.8350883722305298,
      "eval_runtime": 1.1724,
      "eval_samples_per_second": 11.088,
      "eval_steps_per_second": 5.971,
      "step": 1
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": 36.52603530883789,
      "learning_rate": 4e-05,
      "loss": 3.4425,
      "step": 2
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": 26.741819381713867,
      "learning_rate": 6e-05,
      "loss": 3.1212,
      "step": 3
    },
    {
      "epoch": 0.10084033613445378,
      "eval_loss": 0.8261054754257202,
      "eval_runtime": 0.2039,
      "eval_samples_per_second": 63.746,
      "eval_steps_per_second": 34.325,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 26318569734144.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}