run-1/checkpoint-563/trainer_state.json

{
  "best_metric": 0.5710981943306789,
  "best_model_checkpoint": "students_scores_model/run-1/checkpoint-563",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 563,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8880994671403197,
      "grad_norm": 33.513973236083984,
      "learning_rate": 6.5983988623305475e-06,
      "loss": 1.0854,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.5710981943306789,
      "eval_loss": 0.9620336294174194,
      "eval_runtime": 37.4093,
      "eval_samples_per_second": 60.146,
      "eval_steps_per_second": 7.538,
      "step": 563
    }
  ],
  "logging_steps": 500,
  "max_steps": 1126,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2104964038656000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.1868685493584978e-05,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 16,
    "weight_decay": 0.002134803775236508
  }
}