{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.2526315789473683,
  "eval_steps": 25,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 1.790313482284546,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.6345,
      "step": 1
    },
    {
      "epoch": 0.16842105263157894,
      "eval_loss": 5.683742523193359,
      "eval_runtime": 1.1876,
      "eval_samples_per_second": 33.681,
      "eval_steps_per_second": 4.21,
      "step": 1
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 1.7789044380187988,
      "learning_rate": 9.698463103929542e-05,
      "loss": 5.4727,
      "step": 2
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 1.455612063407898,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.2738,
      "step": 3
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 1.2226887941360474,
      "learning_rate": 8.83022221559489e-05,
      "loss": 5.0603,
      "step": 4
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 1.5110059976577759,
      "learning_rate": 8.213938048432697e-05,
      "loss": 5.1348,
      "step": 5
    },
    {
      "epoch": 1.0842105263157895,
      "grad_norm": 1.8657609224319458,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.5326,
      "step": 6
    },
    {
      "epoch": 1.2526315789473683,
      "grad_norm": 0.957495927810669,
      "learning_rate": 6.710100716628344e-05,
      "loss": 3.7847,
      "step": 7
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 0.8734927177429199,
      "learning_rate": 5.868240888334653e-05,
      "loss": 3.2414,
      "step": 8
    },
    {
      "epoch": 1.5894736842105264,
      "grad_norm": 1.333768367767334,
      "learning_rate": 5e-05,
      "loss": 5.1393,
      "step": 9
    },
    {
      "epoch": 1.7578947368421054,
      "grad_norm": 1.515599250793457,
      "learning_rate": 4.131759111665349e-05,
      "loss": 5.3362,
      "step": 10
    },
    {
      "epoch": 1.9263157894736842,
      "grad_norm": 1.4267529249191284,
      "learning_rate": 3.289899283371657e-05,
      "loss": 5.5935,
      "step": 11
    },
    {
      "epoch": 2.168421052631579,
      "grad_norm": 0.8411449193954468,
      "learning_rate": 2.500000000000001e-05,
      "loss": 4.0428,
      "step": 12
    },
    {
      "epoch": 2.336842105263158,
      "grad_norm": 0.8417137861251831,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 4.0572,
      "step": 13
    },
    {
      "epoch": 2.5052631578947366,
      "grad_norm": 0.8732736706733704,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 4.0247,
      "step": 14
    },
    {
      "epoch": 2.6736842105263157,
      "grad_norm": 0.9625438451766968,
      "learning_rate": 6.698729810778065e-06,
      "loss": 4.0893,
      "step": 15
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 1.3134748935699463,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 4.1622,
      "step": 16
    },
    {
      "epoch": 3.0842105263157893,
      "grad_norm": 1.6211005449295044,
      "learning_rate": 7.596123493895991e-07,
      "loss": 6.4519,
      "step": 17
    },
    {
      "epoch": 3.2526315789473683,
      "grad_norm": 1.026520848274231,
      "learning_rate": 0.0,
      "loss": 3.2888,
      "step": 18
    }
  ],
  "logging_steps": 1,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8932788789405286e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}