{
  "best_global_step": 1902,
  "best_metric": 75.7524410049227,
  "best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-21/checkpoint-1902",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1902,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 6.722503662109375,
      "learning_rate": 0.0003114394251761509,
      "loss": 3.015302303085568,
      "step": 634
    },
    {
      "epoch": 1.0,
      "eval_exact_match": 56.0,
      "eval_f1": 70.22942126963311,
      "eval_loss": 1.4306745529174805,
      "eval_runtime": 7.817,
      "eval_samples_per_second": 161.826,
      "eval_steps_per_second": 10.234,
      "step": 634
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.973718166351318,
      "learning_rate": 0.0002491711831194875,
      "loss": 1.4158356964400138,
      "step": 1268
    },
    {
      "epoch": 2.0,
      "eval_exact_match": 58.88,
      "eval_f1": 73.16707373350391,
      "eval_loss": 1.3502248525619507,
      "eval_runtime": 7.7856,
      "eval_samples_per_second": 162.48,
      "eval_steps_per_second": 10.275,
      "step": 1268
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.4416329860687256,
      "learning_rate": 0.0001869029410628241,
      "loss": 1.1203439995317428,
      "step": 1902
    },
    {
      "epoch": 3.0,
      "eval_exact_match": 61.28,
      "eval_f1": 75.7524410049227,
      "eval_loss": 1.2547671794891357,
      "eval_runtime": 7.7254,
      "eval_samples_per_second": 163.745,
      "eval_steps_per_second": 10.355,
      "step": 1902
    }
  ],
  "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": 9271487193486336.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 0.00033618957817028213,
    "lora_alpha": 64,
    "lora_dropout": 0.10918859508364355,
    "lora_r": 256,
    "num_train_epochs": 6,
    "weight_decay": 0.09817847608832152
  }
}