src/nli/training.py [768:812]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            r_dict = dict()
            # Eval loop:
            for i in range(len(eval_data_name)):
                cur_eval_data_name = eval_data_name[i]
                cur_eval_data_list = eval_data_list[i]
                cur_eval_dataloader = eval_data_loaders[i]
                # cur_eval_raw_data_list = eval_raw_data_list[i]

                evaluation_dataset(args, cur_eval_dataloader, cur_eval_data_list, model, r_dict,
                                   eval_name=cur_eval_data_name)

            # saving checkpoints
            current_checkpoint_filename = \
                f'e({epoch})|i({global_step})'

            for i in range(len(eval_data_name)):
                cur_eval_data_name = eval_data_name[i]
                current_checkpoint_filename += \
                    f'|{cur_eval_data_name}#({round(r_dict[cur_eval_data_name]["acc"], 4)})'

            if not args.debug_mode:
                # save model:
                model_output_dir = checkpoints_path / current_checkpoint_filename
                if not model_output_dir.exists():
                    model_output_dir.mkdir()
                model_to_save = (
                    model.module if hasattr(model, "module") else model
                )  # Take care of distributed/parallel training

                torch.save(model_to_save.state_dict(), str(model_output_dir / "model.pt"))
                torch.save(optimizer.state_dict(), str(model_output_dir / "optimizer.pt"))
                torch.save(scheduler.state_dict(), str(model_output_dir / "scheduler.pt"))

            # save prediction:
            if not args.debug_mode and args.save_prediction:
                cur_results_path = prediction_path / current_checkpoint_filename
                if not cur_results_path.exists():
                    cur_results_path.mkdir(parents=True)
                for key, item in r_dict.items():
                    common.save_jsonl(item['predictions'], cur_results_path / f"{key}.jsonl")

                # avoid saving too many things
                for key, item in r_dict.items():
                    del r_dict[key]['predictions']
                common.save_json(r_dict, cur_results_path / "results_dict.json", indent=2)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/nli/training_extra.py [757:801]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            r_dict = dict()
            # Eval loop:
            for i in range(len(eval_data_name)):
                cur_eval_data_name = eval_data_name[i]
                cur_eval_data_list = eval_data_list[i]
                cur_eval_dataloader = eval_data_loaders[i]
                # cur_eval_raw_data_list = eval_raw_data_list[i]

                evaluation_dataset(args, cur_eval_dataloader, cur_eval_data_list, model, r_dict,
                                   eval_name=cur_eval_data_name)

            # saving checkpoints
            current_checkpoint_filename = \
                f'e({epoch})|i({global_step})'

            for i in range(len(eval_data_name)):
                cur_eval_data_name = eval_data_name[i]
                current_checkpoint_filename += \
                    f'|{cur_eval_data_name}#({round(r_dict[cur_eval_data_name]["acc"], 4)})'

            if not args.debug_mode:
                # save model:
                model_output_dir = checkpoints_path / current_checkpoint_filename
                if not model_output_dir.exists():
                    model_output_dir.mkdir()
                model_to_save = (
                    model.module if hasattr(model, "module") else model
                )  # Take care of distributed/parallel training

                torch.save(model_to_save.state_dict(), str(model_output_dir / "model.pt"))
                torch.save(optimizer.state_dict(), str(model_output_dir / "optimizer.pt"))
                torch.save(scheduler.state_dict(), str(model_output_dir / "scheduler.pt"))

            # save prediction:
            if not args.debug_mode and args.save_prediction:
                cur_results_path = prediction_path / current_checkpoint_filename
                if not cur_results_path.exists():
                    cur_results_path.mkdir(parents=True)
                for key, item in r_dict.items():
                    common.save_jsonl(item['predictions'], cur_results_path / f"{key}.jsonl")

                # avoid saving too many things
                for key, item in r_dict.items():
                    del r_dict[key]['predictions']
                common.save_json(r_dict, cur_results_path / "results_dict.json", indent=2)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -