{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005054653440323498,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6848844801078327e-05,
      "eval_loss": 1.987382411956787,
      "eval_runtime": 1447.1215,
      "eval_samples_per_second": 17.269,
      "eval_steps_per_second": 8.634,
      "step": 1
    },
    {
      "epoch": 5.0546534403234975e-05,
      "grad_norm": 1.5325778722763062,
      "learning_rate": 6e-05,
      "loss": 2.0113,
      "step": 3
    },
    {
      "epoch": 0.00010109306880646995,
      "grad_norm": 1.345590591430664,
      "learning_rate": 0.00012,
      "loss": 1.9332,
      "step": 6
    },
    {
      "epoch": 0.00013479075840862662,
      "eval_loss": 1.7950469255447388,
      "eval_runtime": 1444.9887,
      "eval_samples_per_second": 17.294,
      "eval_steps_per_second": 8.647,
      "step": 8
    },
    {
      "epoch": 0.00015163960320970494,
      "grad_norm": 0.911850094795227,
      "learning_rate": 0.00018,
      "loss": 1.7152,
      "step": 9
    },
    {
      "epoch": 0.0002021861376129399,
      "grad_norm": 0.8572914600372314,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.7502,
      "step": 12
    },
    {
      "epoch": 0.0002527326720161749,
      "grad_norm": 0.6948115229606628,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.8149,
      "step": 15
    },
    {
      "epoch": 0.00026958151681725324,
      "eval_loss": 1.6598775386810303,
      "eval_runtime": 1444.8346,
      "eval_samples_per_second": 17.296,
      "eval_steps_per_second": 8.648,
      "step": 16
    },
    {
      "epoch": 0.0003032792064194099,
      "grad_norm": 0.846465528011322,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.6647,
      "step": 18
    },
    {
      "epoch": 0.00035382574082264487,
      "grad_norm": 1.2150896787643433,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.5905,
      "step": 21
    },
    {
      "epoch": 0.0004043722752258798,
      "grad_norm": 0.6084617972373962,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.5145,
      "step": 24
    },
    {
      "epoch": 0.0004043722752258798,
      "eval_loss": 1.6232589483261108,
      "eval_runtime": 1445.6994,
      "eval_samples_per_second": 17.286,
      "eval_steps_per_second": 8.643,
      "step": 24
    },
    {
      "epoch": 0.0004549188096291148,
      "grad_norm": 0.9218605756759644,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.6509,
      "step": 27
    },
    {
      "epoch": 0.0005054653440323498,
      "grad_norm": 0.8422278165817261,
      "learning_rate": 0.0,
      "loss": 1.7086,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}