{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0038322741353431482,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012774247117810494,
      "eval_loss": 4.265748977661133,
      "eval_runtime": 183.8203,
      "eval_samples_per_second": 17.936,
      "eval_steps_per_second": 8.971,
      "step": 1
    },
    {
      "epoch": 0.00038322741353431485,
      "grad_norm": 8.271459579467773,
      "learning_rate": 6e-05,
      "loss": 14.7209,
      "step": 3
    },
    {
      "epoch": 0.0007664548270686297,
      "grad_norm": 15.851831436157227,
      "learning_rate": 0.00012,
      "loss": 22.904,
      "step": 6
    },
    {
      "epoch": 0.0010219397694248395,
      "eval_loss": 2.6914103031158447,
      "eval_runtime": 183.7092,
      "eval_samples_per_second": 17.947,
      "eval_steps_per_second": 8.976,
      "step": 8
    },
    {
      "epoch": 0.0011496822406029444,
      "grad_norm": 14.430719375610352,
      "learning_rate": 0.00018,
      "loss": 11.3893,
      "step": 9
    },
    {
      "epoch": 0.0015329096541372594,
      "grad_norm": 11.2367525100708,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.6279,
      "step": 12
    },
    {
      "epoch": 0.0019161370676715741,
      "grad_norm": 9.639863014221191,
      "learning_rate": 0.00017071067811865476,
      "loss": 4.6616,
      "step": 15
    },
    {
      "epoch": 0.002043879538849679,
      "eval_loss": 1.1346616744995117,
      "eval_runtime": 184.0071,
      "eval_samples_per_second": 17.918,
      "eval_steps_per_second": 8.962,
      "step": 16
    },
    {
      "epoch": 0.002299364481205889,
      "grad_norm": 7.165860176086426,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.3663,
      "step": 18
    },
    {
      "epoch": 0.0026825918947402036,
      "grad_norm": 9.319868087768555,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.7561,
      "step": 21
    },
    {
      "epoch": 0.0030658193082745188,
      "grad_norm": 7.558574199676514,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.6226,
      "step": 24
    },
    {
      "epoch": 0.0030658193082745188,
      "eval_loss": 0.8786661624908447,
      "eval_runtime": 183.5815,
      "eval_samples_per_second": 17.959,
      "eval_steps_per_second": 8.982,
      "step": 24
    },
    {
      "epoch": 0.0034490467218088335,
      "grad_norm": 27.973899841308594,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.2881,
      "step": 27
    },
    {
      "epoch": 0.0038322741353431482,
      "grad_norm": 6.591433048248291,
      "learning_rate": 0.0,
      "loss": 3.661,
      "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": 9801873028546560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}