{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004914004914004914,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.914004914004914e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 8.6388,
      "step": 1
    },
    {
      "epoch": 4.914004914004914e-05,
      "eval_loss": 8.530080795288086,
      "eval_runtime": 623.7918,
      "eval_samples_per_second": 27.472,
      "eval_steps_per_second": 6.869,
      "step": 1
    },
    {
      "epoch": 9.828009828009828e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.1814,
      "step": 2
    },
    {
      "epoch": 0.00014742014742014743,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.1088,
      "step": 3
    },
    {
      "epoch": 0.00014742014742014743,
      "eval_loss": 8.530080795288086,
      "eval_runtime": 622.7663,
      "eval_samples_per_second": 27.518,
      "eval_steps_per_second": 6.881,
      "step": 3
    },
    {
      "epoch": 0.00019656019656019656,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.3909,
      "step": 4
    },
    {
      "epoch": 0.0002457002457002457,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.206,
      "step": 5
    },
    {
      "epoch": 0.00029484029484029485,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 8.0766,
      "step": 6
    },
    {
      "epoch": 0.00029484029484029485,
      "eval_loss": 8.530080795288086,
      "eval_runtime": 625.557,
      "eval_samples_per_second": 27.395,
      "eval_steps_per_second": 6.85,
      "step": 6
    },
    {
      "epoch": 0.00034398034398034396,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.4326,
      "step": 7
    },
    {
      "epoch": 0.0003931203931203931,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 12.6011,
      "step": 8
    },
    {
      "epoch": 0.0004422604422604423,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 7.9906,
      "step": 9
    },
    {
      "epoch": 0.0004422604422604423,
      "eval_loss": 8.530080795288086,
      "eval_runtime": 623.4456,
      "eval_samples_per_second": 27.488,
      "eval_steps_per_second": 6.873,
      "step": 9
    },
    {
      "epoch": 0.0004914004914004914,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 10.3592,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.47552863256576e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}