From a65016e23e6c829d61c63a68e27b24abf86e926a Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 四月 2024 10:09:03 +0800
Subject: [PATCH] Dev gzf exp (#1618)
---
funasr/train_utils/trainer.py | 13 +++++++------
1 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/funasr/train_utils/trainer.py b/funasr/train_utils/trainer.py
index 27856fb..35a266f 100644
--- a/funasr/train_utils/trainer.py
+++ b/funasr/train_utils/trainer.py
@@ -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]
@@ -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()]}, "
--
Gitblit v1.9.1