{
  "best_global_step": 1268,
  "best_metric": 72.25401951388476,
  "best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-18/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": 5.808117389678955,
      "learning_rate": 0.0002375118861037853,
      "loss": 3.0843448097397475,
      "step": 634
    },
    {
      "epoch": 1.0,
      "eval_exact_match": 54.24,
      "eval_f1": 68.71297045089493,
      "eval_loss": 1.490488052368164,
      "eval_runtime": 7.8716,
      "eval_samples_per_second": 160.705,
      "eval_steps_per_second": 10.163,
      "step": 634
    },
    {
      "epoch": 2.0,
      "grad_norm": 5.10264253616333,
      "learning_rate": 0.0001781573193754448,
      "loss": 1.4483898656225356,
      "step": 1268
    },
    {
      "epoch": 2.0,
      "eval_exact_match": 57.44,
      "eval_f1": 72.25401951388476,
      "eval_loss": 1.3791934251785278,
      "eval_runtime": 7.7741,
      "eval_samples_per_second": 162.719,
      "eval_steps_per_second": 10.291,
      "step": 1268
    }
  ],
  "logging_steps": 500,
  "max_steps": 3170,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 0.0002670955502775323,
    "lora_alpha": 64,
    "lora_dropout": 0.05890421094449804,
    "lora_r": 256,
    "num_train_epochs": 5,
    "weight_decay": 0.04632596783403071
  }
}