{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006587615283267457,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013175230566534913,
      "grad_norm": 3.8656578063964844,
      "learning_rate": 1e-05,
      "loss": 12.9996,
      "step": 1
    },
    {
      "epoch": 0.00013175230566534913,
      "eval_loss": 12.650906562805176,
      "eval_runtime": 101.0889,
      "eval_samples_per_second": 126.463,
      "eval_steps_per_second": 63.231,
      "step": 1
    },
    {
      "epoch": 0.00026350461133069827,
      "grad_norm": 3.4676733016967773,
      "learning_rate": 2e-05,
      "loss": 12.3484,
      "step": 2
    },
    {
      "epoch": 0.00026350461133069827,
      "eval_loss": 12.615131378173828,
      "eval_runtime": 71.202,
      "eval_samples_per_second": 179.546,
      "eval_steps_per_second": 89.773,
      "step": 2
    },
    {
      "epoch": 0.0003952569169960474,
      "grad_norm": 3.372246026992798,
      "learning_rate": 3e-05,
      "loss": 12.5158,
      "step": 3
    },
    {
      "epoch": 0.0005270092226613965,
      "grad_norm": 3.524444580078125,
      "learning_rate": 4e-05,
      "loss": 12.2846,
      "step": 4
    },
    {
      "epoch": 0.0005270092226613965,
      "eval_loss": 12.575155258178711,
      "eval_runtime": 99.7735,
      "eval_samples_per_second": 128.13,
      "eval_steps_per_second": 64.065,
      "step": 4
    },
    {
      "epoch": 0.0006587615283267457,
      "grad_norm": 3.934224843978882,
      "learning_rate": 5e-05,
      "loss": 12.8298,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 108879165259776.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}