{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003299241174529858,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010997470581766194,
      "eval_loss": 8.646834373474121,
      "eval_runtime": 209.1318,
      "eval_samples_per_second": 18.309,
      "eval_steps_per_second": 9.157,
      "step": 1
    },
    {
      "epoch": 0.0003299241174529858,
      "grad_norm": 34.69627380371094,
      "learning_rate": 6e-05,
      "loss": 8.6076,
      "step": 3
    },
    {
      "epoch": 0.0006598482349059716,
      "grad_norm": 21.912450790405273,
      "learning_rate": 0.00012,
      "loss": 4.8263,
      "step": 6
    },
    {
      "epoch": 0.0008797976465412955,
      "eval_loss": 0.030696555972099304,
      "eval_runtime": 212.4528,
      "eval_samples_per_second": 18.023,
      "eval_steps_per_second": 9.014,
      "step": 8
    },
    {
      "epoch": 0.0009897723523589574,
      "grad_norm": 2.559295892715454,
      "learning_rate": 0.00018,
      "loss": 0.4799,
      "step": 9
    },
    {
      "epoch": 0.0013196964698119432,
      "grad_norm": 0.004662382882088423,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0014,
      "step": 12
    },
    {
      "epoch": 0.001649620587264929,
      "grad_norm": 0.0018161301268264651,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0001,
      "step": 15
    },
    {
      "epoch": 0.001759595293082591,
      "eval_loss": 9.960264833352994e-06,
      "eval_runtime": 213.0234,
      "eval_samples_per_second": 17.975,
      "eval_steps_per_second": 8.99,
      "step": 16
    },
    {
      "epoch": 0.001979544704717915,
      "grad_norm": 0.0035299949813634157,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0023094688221709007,
      "grad_norm": 0.010442993603646755,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0026393929396238865,
      "grad_norm": 0.004692532122135162,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0026393929396238865,
      "eval_loss": 1.1225663001823705e-05,
      "eval_runtime": 211.7665,
      "eval_samples_per_second": 18.081,
      "eval_steps_per_second": 9.043,
      "step": 24
    },
    {
      "epoch": 0.0029693170570768723,
      "grad_norm": 0.0018272201996296644,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.003299241174529858,
      "grad_norm": 0.001389215816743672,
      "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": 2951326036131840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}