fix
This commit is contained in:
erenup
parent
eb2f7062f1
commit
783874049b
|
|
@ -957,76 +957,11 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"execution_count": null,
|
||||
"source": [
|
||||
"trainer.train()"
|
||||
],
|
||||
"outputs": [
|
||||
{
|
||||
"output_type": "stream",
|
||||
"name": "stderr",
|
||||
"text": [
|
||||
" 1%|▏ | 500/38145 [1:05:10<91:20:54, 8.74s/it]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"output_type": "stream",
|
||||
"name": "stdout",
|
||||
"text": [
|
||||
"{'loss': 0.8588, 'learning_rate': 1.973784244330843e-05, 'epoch': 0.01}\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"output_type": "stream",
|
||||
"name": "stderr",
|
||||
"text": [
|
||||
" 3%|▎ | 1000/38145 [2:09:32<73:56:07, 7.17s/it]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"output_type": "stream",
|
||||
"name": "stdout",
|
||||
"text": [
|
||||
"{'loss': 0.8343, 'learning_rate': 1.947568488661686e-05, 'epoch': 0.03}\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"output_type": "stream",
|
||||
"name": "stderr",
|
||||
"text": [
|
||||
" 4%|▍ | 1500/38145 [3:03:53<57:17:10, 5.63s/it]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"output_type": "stream",
|
||||
"name": "stdout",
|
||||
"text": [
|
||||
"{'loss': 0.8246, 'learning_rate': 1.9213527329925285e-05, 'epoch': 0.04}\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"output_type": "stream",
|
||||
"name": "stderr",
|
||||
"text": [
|
||||
" 5%|▌ | 1980/38145 [3:52:54<67:46:36, 6.75s/it]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"output_type": "error",
|
||||
"ename": "KeyboardInterrupt",
|
||||
"evalue": "",
|
||||
"traceback": [
|
||||
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
||||
"\u001b[0;32m/var/folders/2k/x3py0v857kgcwqvvl00xxhxw0000gn/T/ipykernel_15169/4032920361.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mtrainer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
|
||||
"\u001b[0;32m~/Desktop/zhihu/learn-nlp-with-transformers/venv/lib/python3.8/site-packages/transformers/trainer.py\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(self, resume_from_checkpoint, trial, **kwargs)\u001b[0m\n\u001b[1;32m 1079\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1080\u001b[0m \u001b[0;31m# Revert to normal clipping otherwise, handling Apex or full precision\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1081\u001b[0;31m torch.nn.utils.clip_grad_norm_(\n\u001b[0m\u001b[1;32m 1082\u001b[0m \u001b[0mamp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmaster_params\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moptimizer\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muse_apex\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparameters\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1083\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmax_grad_norm\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||||
"\u001b[0;32m~/Desktop/zhihu/learn-nlp-with-transformers/venv/lib/python3.8/site-packages/torch/nn/utils/clip_grad.py\u001b[0m in \u001b[0;36mclip_grad_norm_\u001b[0;34m(parameters, max_norm, norm_type, error_if_nonfinite)\u001b[0m\n\u001b[1;32m 40\u001b[0m \u001b[0mtotal_norm\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnorms\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnorms\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m1\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmax\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstack\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnorms\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 41\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 42\u001b[0;31m \u001b[0mtotal_norm\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnorm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstack\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnorm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgrad\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdetach\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnorm_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mp\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnorm_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 43\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtotal_norm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misnan\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mtotal_norm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misinf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 44\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0merror_if_nonfinite\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||||
"\u001b[0;32m~/Desktop/zhihu/learn-nlp-with-transformers/venv/lib/python3.8/site-packages/torch/nn/utils/clip_grad.py\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 40\u001b[0m \u001b[0mtotal_norm\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnorms\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnorms\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m1\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmax\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstack\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnorms\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 41\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 42\u001b[0;31m \u001b[0mtotal_norm\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnorm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstack\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnorm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgrad\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdetach\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnorm_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mp\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnorm_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 43\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mtotal_norm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misnan\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mtotal_norm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misinf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 44\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0merror_if_nonfinite\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||||
"\u001b[0;32m~/Desktop/zhihu/learn-nlp-with-transformers/venv/lib/python3.8/site-packages/torch/functional.py\u001b[0m in \u001b[0;36mnorm\u001b[0;34m(input, p, dim, keepdim, out, dtype)\u001b[0m\n\u001b[1;32m 1310\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1311\u001b[0m \u001b[0m_dim\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mndim\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;31m# noqa: C416 TODO: rewrite as list(range(m))\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1312\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0m_VF\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnorm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mp\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdim\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0m_dim\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkeepdim\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mkeepdim\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore[attr-defined]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1313\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1314\u001b[0m \u001b[0;31m# TODO: when https://github.com/pytorch/pytorch/issues/33782 is fixed\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
|
||||
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
|
||||
]
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"metadata": {
|
||||
"id": "uNx5pyRlIrJh",
|
||||
"scrolled": false
|
||||
|
|
|
|||
|
|
@ -486,67 +486,6 @@ trainer = Seq2SeqTrainer(
|
|||
trainer.train()
|
||||
```
|
||||
|
||||
1%|▏ | 500/38145 [1:05:10<91:20:54, 8.74s/it]
|
||||
|
||||
{'loss': 0.8588, 'learning_rate': 1.973784244330843e-05, 'epoch': 0.01}
|
||||
|
||||
|
||||
3%|▎ | 1000/38145 [2:09:32<73:56:07, 7.17s/it]
|
||||
|
||||
{'loss': 0.8343, 'learning_rate': 1.947568488661686e-05, 'epoch': 0.03}
|
||||
|
||||
|
||||
4%|▍ | 1500/38145 [3:03:53<57:17:10, 5.63s/it]
|
||||
|
||||
{'loss': 0.8246, 'learning_rate': 1.9213527329925285e-05, 'epoch': 0.04}
|
||||
|
||||
|
||||
5%|▌ | 1980/38145 [3:52:54<67:46:36, 6.75s/it]
|
||||
|
||||
|
||||
---------------------------------------------------------------------------
|
||||
|
||||
KeyboardInterrupt Traceback (most recent call last)
|
||||
|
||||
/var/folders/2k/x3py0v857kgcwqvvl00xxhxw0000gn/T/ipykernel_15169/4032920361.py in <module>
|
||||
----> 1 trainer.train()
|
||||
|
||||
|
||||
~/Desktop/zhihu/learn-nlp-with-transformers/venv/lib/python3.8/site-packages/transformers/trainer.py in train(self, resume_from_checkpoint, trial, **kwargs)
|
||||
1079 else:
|
||||
1080 # Revert to normal clipping otherwise, handling Apex or full precision
|
||||
-> 1081 torch.nn.utils.clip_grad_norm_(
|
||||
1082 amp.master_params(self.optimizer) if self.use_apex else model.parameters(),
|
||||
1083 self.args.max_grad_norm,
|
||||
|
||||
|
||||
~/Desktop/zhihu/learn-nlp-with-transformers/venv/lib/python3.8/site-packages/torch/nn/utils/clip_grad.py in clip_grad_norm_(parameters, max_norm, norm_type, error_if_nonfinite)
|
||||
40 total_norm = norms[0] if len(norms) == 1 else torch.max(torch.stack(norms))
|
||||
41 else:
|
||||
---> 42 total_norm = torch.norm(torch.stack([torch.norm(p.grad.detach(), norm_type).to(device) for p in parameters]), norm_type)
|
||||
43 if total_norm.isnan() or total_norm.isinf():
|
||||
44 if error_if_nonfinite:
|
||||
|
||||
|
||||
~/Desktop/zhihu/learn-nlp-with-transformers/venv/lib/python3.8/site-packages/torch/nn/utils/clip_grad.py in <listcomp>(.0)
|
||||
40 total_norm = norms[0] if len(norms) == 1 else torch.max(torch.stack(norms))
|
||||
41 else:
|
||||
---> 42 total_norm = torch.norm(torch.stack([torch.norm(p.grad.detach(), norm_type).to(device) for p in parameters]), norm_type)
|
||||
43 if total_norm.isnan() or total_norm.isinf():
|
||||
44 if error_if_nonfinite:
|
||||
|
||||
|
||||
~/Desktop/zhihu/learn-nlp-with-transformers/venv/lib/python3.8/site-packages/torch/functional.py in norm(input, p, dim, keepdim, out, dtype)
|
||||
1310 if not isinstance(p, str):
|
||||
1311 _dim = [i for i in range(ndim)] # noqa: C416 TODO: rewrite as list(range(m))
|
||||
-> 1312 return _VF.norm(input, p, dim=_dim, keepdim=keepdim) # type: ignore[attr-defined]
|
||||
1313
|
||||
1314 # TODO: when https://github.com/pytorch/pytorch/issues/33782 is fixed
|
||||
|
||||
|
||||
KeyboardInterrupt:
|
||||
|
||||
|
||||
最后别忘了，查看如何上传模型 ，上传模型到](https://huggingface.co/transformers/model_sharing.html) 到[🤗 Model Hub](https://huggingface.co/models)。随后您就可以像这个notebook一开始一样，直接用模型名字就能使用您的模型啦。
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue