{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004904645516745277,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6348818389150925e-05,
      "eval_loss": NaN,
      "eval_runtime": 1449.2181,
      "eval_samples_per_second": 17.772,
      "eval_steps_per_second": 8.886,
      "step": 1
    },
    {
      "epoch": 4.904645516745277e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 9.809291033490554e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0001307905471132074,
      "eval_loss": NaN,
      "eval_runtime": 1449.1167,
      "eval_samples_per_second": 17.773,
      "eval_steps_per_second": 8.887,
      "step": 8
    },
    {
      "epoch": 0.00014713936550235832,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00019618582066981109,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00024523227583726385,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0002615810942264148,
      "eval_loss": NaN,
      "eval_runtime": 1451.4005,
      "eval_samples_per_second": 17.745,
      "eval_steps_per_second": 8.873,
      "step": 16
    },
    {
      "epoch": 0.00029427873100471664,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0003433251861721694,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.00039237164133962217,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.00039237164133962217,
      "eval_loss": NaN,
      "eval_runtime": 1458.697,
      "eval_samples_per_second": 17.656,
      "eval_steps_per_second": 8.828,
      "step": 24
    },
    {
      "epoch": 0.00044141809650707496,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0004904645516745277,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.054694852001792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}