{
  "best_metric": 0.8585572838783264,
  "best_model_checkpoint": "./results/run-37598087/checkpoint-344",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 1376,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029069767441860465,
      "grad_norm": 1.1999566555023193,
      "learning_rate": 3.2681368723557635e-05,
      "loss": 1.0968,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.6239361242297824,
      "eval_loss": 0.8585572838783264,
      "eval_runtime": 1.1693,
      "eval_samples_per_second": 1566.772,
      "eval_steps_per_second": 195.846,
      "step": 344
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.6482640943501118,
      "eval_loss": 0.9017149806022644,
      "eval_runtime": 1.1788,
      "eval_samples_per_second": 1554.158,
      "eval_steps_per_second": 194.27,
      "step": 688
    },
    {
      "epoch": 2.9069767441860463,
      "grad_norm": 10.886157989501953,
      "learning_rate": 8.93686882913285e-06,
      "loss": 0.5554,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.649741833511255,
      "eval_loss": 1.2939248085021973,
      "eval_runtime": 1.1859,
      "eval_samples_per_second": 1544.754,
      "eval_steps_per_second": 193.094,
      "step": 1032
    },
    {
      "epoch": 4.0,
      "eval_f1": 0.6436338860188018,
      "eval_loss": 1.5838754177093506,
      "eval_runtime": 1.1543,
      "eval_samples_per_second": 1587.073,
      "eval_steps_per_second": 198.384,
      "step": 1376
    }
  ],
  "logging_steps": 1000,
  "max_steps": 1376,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4202973734787072.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.270513699172022e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 16,
    "warmup_steps": 0,
    "weight_decay": 0.07303439372733585
  }
}