{
  "best_global_step": 1268,
  "best_metric": 72.45242535630264,
  "best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-13/checkpoint-1268",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1268,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 4.9004082679748535,
      "learning_rate": 0.0004602578021214701,
      "loss": 2.8550773163323147,
      "step": 634
    },
    {
      "epoch": 1.0,
      "eval_exact_match": 55.12,
      "eval_f1": 69.72068460360381,
      "eval_loss": 1.4229457378387451,
      "eval_runtime": 7.8179,
      "eval_samples_per_second": 161.808,
      "eval_steps_per_second": 10.233,
      "step": 634
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.626029968261719,
      "learning_rate": 0.00036823527088684005,
      "loss": 1.3960553960469242,
      "step": 1268
    },
    {
      "epoch": 2.0,
      "eval_exact_match": 57.68,
      "eval_f1": 72.45242535630264,
      "eval_loss": 1.3469899892807007,
      "eval_runtime": 7.7359,
      "eval_samples_per_second": 163.524,
      "eval_steps_per_second": 10.341,
      "step": 1268
    }
  ],
  "logging_steps": 500,
  "max_steps": 3804,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 6180991462324224.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 0.0004968345810980108,
    "lora_alpha": 64,
    "lora_dropout": 0.17487061368186463,
    "lora_r": 256,
    "num_train_epochs": 6,
    "weight_decay": 0.03656091062669907
  }
}