{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006898573719883414,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.898573719883414e-05,
      "grad_norm": 0.017506157979369164,
      "learning_rate": 2e-05,
      "loss": 10.3796,
      "step": 1
    },
    {
      "epoch": 6.898573719883414e-05,
      "eval_loss": 10.378271102905273,
      "eval_runtime": 18.3905,
      "eval_samples_per_second": 331.911,
      "eval_steps_per_second": 165.956,
      "step": 1
    },
    {
      "epoch": 0.00013797147439766828,
      "grad_norm": 0.013643925078213215,
      "learning_rate": 4e-05,
      "loss": 10.3707,
      "step": 2
    },
    {
      "epoch": 0.00020695721159650244,
      "grad_norm": 0.020240245386958122,
      "learning_rate": 6e-05,
      "loss": 10.3798,
      "step": 3
    },
    {
      "epoch": 0.00020695721159650244,
      "eval_loss": 10.378259658813477,
      "eval_runtime": 18.4647,
      "eval_samples_per_second": 330.576,
      "eval_steps_per_second": 165.288,
      "step": 3
    },
    {
      "epoch": 0.00027594294879533656,
      "grad_norm": 0.018379218876361847,
      "learning_rate": 8e-05,
      "loss": 10.3793,
      "step": 4
    },
    {
      "epoch": 0.0003449286859941707,
      "grad_norm": 0.01751578599214554,
      "learning_rate": 0.0001,
      "loss": 10.3787,
      "step": 5
    },
    {
      "epoch": 0.00041391442319300487,
      "grad_norm": 0.01601172611117363,
      "learning_rate": 0.00012,
      "loss": 10.3794,
      "step": 6
    },
    {
      "epoch": 0.00041391442319300487,
      "eval_loss": 10.378188133239746,
      "eval_runtime": 18.7162,
      "eval_samples_per_second": 326.134,
      "eval_steps_per_second": 163.067,
      "step": 6
    },
    {
      "epoch": 0.000482900160391839,
      "grad_norm": 0.01772220991551876,
      "learning_rate": 0.00014,
      "loss": 10.3793,
      "step": 7
    },
    {
      "epoch": 0.0005518858975906731,
      "grad_norm": 0.020962320268154144,
      "learning_rate": 0.00016,
      "loss": 10.3765,
      "step": 8
    },
    {
      "epoch": 0.0006208716347895073,
      "grad_norm": 0.018440164625644684,
      "learning_rate": 0.00018,
      "loss": 10.3788,
      "step": 9
    },
    {
      "epoch": 0.0006208716347895073,
      "eval_loss": 10.378067016601562,
      "eval_runtime": 18.8897,
      "eval_samples_per_second": 323.138,
      "eval_steps_per_second": 161.569,
      "step": 9
    },
    {
      "epoch": 0.0006898573719883414,
      "grad_norm": 0.012787417508661747,
      "learning_rate": 0.0002,
      "loss": 10.3822,
      "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": 242454528000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}