trainer_state.json

{
  "best_metric": 0.12190821766853333,
  "best_model_checkpoint": "multilabel_classification/checkpoint-239",
  "epoch": 0.5,
  "eval_steps": 500,
  "global_step": 239,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "eval_f1_macro": 0.0,
      "eval_f1_micro": 0.0,
      "eval_f1_weighted": 0.0,
      "eval_loss": 0.12190821766853333,
      "eval_runtime": 157.5442,
      "eval_samples_per_second": 2.729,
      "eval_steps_per_second": 0.343,
      "step": 239
    }
  ],
  "logging_steps": 500,
  "max_steps": 239,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 6318616510660608.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}