update seaco finetune

维石

2024-04-17 149063ced4d2d5269f0472677228eadfcb4a4d8a

 funasr/train_utils/trainer.py

@@ -79,7 +79,7 @@
        self.validate_interval = kwargs.get("validate_interval", 5000)
        self.keep_nbest_models = kwargs.get("keep_nbest_models", 500)
        self.avg_keep_nbest_models_type = kwargs.get("avg_keep_nbest_models_type", "acc")
        self.avg_nbest_model = kwargs.get("avg_nbest_model", 5)
        self.avg_nbest_model = kwargs.get("avg_nbest_model", 10)
        self.accum_grad = kwargs.get("accum_grad", 1)
        self.grad_clip = kwargs.get("grad_clip", 10.0)
        self.grad_clip_type = kwargs.get("grad_clip_type", 2.0)
@@ -134,7 +134,7 @@
                "val_acc_step_or_eoch": self.val_acc_step_or_eoch,
                "val_loss_step_or_eoch": self.val_loss_step_or_eoch,
                "best_step_or_epoch": self.best_step_or_epoch,
                "avg_keep_nbest_models_type": slef.avg_keep_nbest_models_type,
                "avg_keep_nbest_models_type": self.avg_keep_nbest_models_type,
            }
            if hasattr(model, "module"):
                state["state_dict"] = model.module.state_dict()
@@ -161,17 +161,17 @@
                    self.best_step_or_epoch = ckpt_name
                    best_ckpt = Path(os.path.join(self.output_dir, f'model.pt.best'))
                    torch.save(state, best_ckpt)
                    logging.info(f"Update best acc: {self.val_acc_step_or_eoch[self.best_step_or_epoch]}, {best_ckpt}")
                    logging.info(f"Update best acc: {self.val_acc_step_or_eoch[self.best_step_or_epoch]:.4f}, {best_ckpt}")
                else:
                    logging.info(f"No improvement in acc: {self.val_acc_step_or_eoch[ckpt_name]} < {self.val_acc_step_or_eoch[self.best_step_or_epoch]}")
                    logging.info(f"No improvement in acc: {self.val_acc_step_or_eoch[ckpt_name]:.4f} < {self.val_acc_step_or_eoch[self.best_step_or_epoch]:.4f}")
            elif self.avg_keep_nbest_models_type == "loss":
                if self.val_loss_step_or_eoch[ckpt_name] <= self.val_loss_step_or_eoch[self.best_step_or_epoch]:
                    self.best_step_or_epoch = ckpt_name
                    best_ckpt = Path(os.path.join(self.output_dir, f'model.pt.best'))
                    torch.save(state, best_ckpt)
                    logging.info(f"Update best loss: {self.val_loss_step_or_eoch[self.best_step_or_epoch]}, {best_ckpt}")
                    logging.info(f"Update best loss: {self.val_loss_step_or_eoch[self.best_step_or_epoch]:.4f}, {best_ckpt}")
                else:
                    logging.info(f"No improvement in loss: {self.val_loss_step_or_eoch[ckpt_name]} > {self.val_loss_step_or_eoch[self.best_step_or_epoch]}")
                    logging.info(f"No improvement in loss: {self.val_loss_step_or_eoch[ckpt_name]:.4f} > {self.val_loss_step_or_eoch[self.best_step_or_epoch]:.4f}")
            else:
                print("Undo")
            self.saved_ckpts[ckpt_name] = getattr(self, f"val_{self.avg_keep_nbest_models_type}_step_or_eoch")[ckpt_name]
@@ -233,7 +233,7 @@
                self.saved_ckpts = checkpoint["saved_ckpts"]
                self.val_acc_step_or_eoch = checkpoint["val_acc_step_or_eoch"] if "val_acc_step_or_eoch" in checkpoint else {}
                self.val_loss_step_or_eoch = checkpoint["val_loss_step_or_eoch"] if "val_loss_step_or_eoch" in checkpoint else {}
                self.val_loss_step_or_eoch = checkpoint["best_step_or_epoch"] if "best_step_or_epoch" in checkpoint else ""
                self.best_step_or_epoch = checkpoint["best_step_or_epoch"] if "best_step_or_epoch" in checkpoint else ""
                model.to(self.device)
                print(f"Checkpoint loaded successfully from '{ckpt}'")
            else:
@@ -377,7 +377,8 @@
                    model=model,
                    dataloader_val=dataloader_val,
                    epoch=epoch,
                    writer=writer
                    writer=writer,
                    step=batch_idx+1,
                )

            if (batch_idx+1) % self.save_checkpoint_interval == 0:
@@ -523,7 +524,7 @@
                f"step: {batch_idx + 1}/{batch_num_epoch}, total step: {self.batch_total}, "
                f"(loss_avg_rank: {loss:.3f}), "
                f"(loss_avg_epoch: {loss_avg_epoch:.3f}), "
                f"(ppl_avg_epoch: {math.exp(loss_avg_epoch):.3f}), "
                f"(ppl_avg_epoch: {math.exp(loss_avg_epoch):.3e}), "
                f"(acc_avg_epoch: {acc_avg_epoch:.3f}), "
                f"(lr: {lr:.3e}), "
                f"{[(k, round(v.detach().cpu().item(), 3)) for k, v in stats.items()]}, "