run-2/checkpoint-564/trainer_state.json

{
  "best_metric": 0.59608556088931,
  "best_model_checkpoint": "students_scores_model/run-2/checkpoint-564",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 564,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_f1": 0.5542424468942035,
      "eval_loss": 0.9836739301681519,
      "eval_runtime": 37.7933,
      "eval_samples_per_second": 59.534,
      "eval_steps_per_second": 7.462,
      "step": 282
    },
    {
      "epoch": 1.773049645390071,
      "grad_norm": 13.297893524169922,
      "learning_rate": 4.297481786070467e-06,
      "loss": 1.0267,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.59608556088931,
      "eval_loss": 0.9071515798568726,
      "eval_runtime": 37.9029,
      "eval_samples_per_second": 59.362,
      "eval_steps_per_second": 7.44,
      "step": 564
    }
  ],
  "logging_steps": 500,
  "max_steps": 846,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 4203350064691200.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.0507715580969985e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 32,
    "weight_decay": 5.2295860944350256e-05
  }
}