{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.716981132075472,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.61,
      "eval_loss": 0.2181043028831482,
      "eval_runtime": 5.4585,
      "eval_samples_per_second": 567.924,
      "eval_steps_per_second": 11.908,
      "step": 318
    },
    {
      "epoch": 1.5723270440251573,
      "grad_norm": 0.5552464127540588,
      "learning_rate": 1.685534591194969e-05,
      "loss": 0.3513,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8335483870967741,
      "eval_loss": 0.10069030523300171,
      "eval_runtime": 5.463,
      "eval_samples_per_second": 567.458,
      "eval_steps_per_second": 11.898,
      "step": 636
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8880645161290323,
      "eval_loss": 0.06445235759019852,
      "eval_runtime": 5.3929,
      "eval_samples_per_second": 574.829,
      "eval_steps_per_second": 12.053,
      "step": 954
    },
    {
      "epoch": 3.1446540880503147,
      "grad_norm": 0.47348132729530334,
      "learning_rate": 1.371069182389937e-05,
      "loss": 0.1174,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9025806451612903,
      "eval_loss": 0.04838454723358154,
      "eval_runtime": 5.5851,
      "eval_samples_per_second": 555.047,
      "eval_steps_per_second": 11.638,
      "step": 1272
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.31585973501205444,
      "learning_rate": 1.0566037735849058e-05,
      "loss": 0.0719,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 3180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 391368939443328.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.435413568517991,
    "num_train_epochs": 10,
    "temperature": 6
  }
}