{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0025320729237002025,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.440243079000676e-05,
      "eval_loss": NaN,
      "eval_runtime": 1081.8789,
      "eval_samples_per_second": 4.611,
      "eval_steps_per_second": 2.306,
      "step": 1
    },
    {
      "epoch": 0.00025320729237002026,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005064145847400405,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0006752194463200541,
      "eval_loss": NaN,
      "eval_runtime": 1081.1677,
      "eval_samples_per_second": 4.614,
      "eval_steps_per_second": 2.308,
      "step": 8
    },
    {
      "epoch": 0.0007596218771100607,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.001012829169480081,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0012660364618501012,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0013504388926401081,
      "eval_loss": NaN,
      "eval_runtime": 1081.0401,
      "eval_samples_per_second": 4.615,
      "eval_steps_per_second": 2.308,
      "step": 16
    },
    {
      "epoch": 0.0015192437542201215,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0017724510465901419,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.002025658338960162,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.002025658338960162,
      "eval_loss": NaN,
      "eval_runtime": 1081.7437,
      "eval_samples_per_second": 4.612,
      "eval_steps_per_second": 2.306,
      "step": 24
    },
    {
      "epoch": 0.0022788656313301823,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0025320729237002025,
      "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": 1.054695455981568e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}