GPT训练完文件夹没文件

[HSJDZNM]

trafficstars

C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\pytorch_lightning\loops\fit_loop.py:293: The number of training batches (17) is smaller than the logging interval Trainer(log_every_n_steps=50). Set a lower value for log_every_n_steps if you want to see logs for the training epoch. Trainer.fit stopped: max_epochs=15 reached. C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\transformers\utils\generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\transformers\utils\generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\transformers\utils\generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\transformers\utils\generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( "C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\python.exe" GPT_SoVITS/s1_train.py --config_file "C:\Users\dell\Desktop\GPT-SoVITS-beta0306\TEMP/tmp_s1.yaml" C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\transformers\utils\generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( Seed set to 1234 Using 16bit Automatic Mixed Precision (AMP) GPU available: True (cuda), used: True TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU available: False, using: 0 HPUs <All keys matched successfully> ckpt_path: logs\KoBy\logs_s1\ckpt\epoch=14-step=60.ckpt [rank: 0] Seed set to 1234 Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/1 [W socket.cpp:697] [c10d] The client socket has failed to connect to [DESKTOP-FUHLA6V]:52405 (system error: 10049 - 在其上下文中，该请求的地址无效。).

distributed_backend=gloo All distributed processes registered. Starting with 1 processes

semantic_data_len: 44 phoneme_data_len: 44 item_name semantic_audio 0 vocal_man.wav.reformatted.wav_10.wav_000002304... 520 486 486 486 486 486 486 486 486 486 72 704... 1 vocal_man.wav.reformatted.wav_10.wav_000069664... 774 647 774 953 565 192 747 973 940 940 526 67... 2 vocal_man.wav.reformatted.wav_10.wav_000131552... 1005 263 263 581 581 185 496 774 263 263 263 5... & 语言文件........ & deleted 34 audios who's phoneme/sec are bigger than 25 or smaller than 3 dataset.len(): 100 C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\pytorch_lightning\callbacks\model_checkpoint.py:639: Checkpoint directory C:\Users\dell\Desktop\GPT-SoVITS-beta0306\logs\KoBy\logs_s1\ckpt exists and is not empty. Restoring states from the checkpoint path at logs\KoBy\logs_s1\ckpt\epoch=14-step=60.ckpt LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

| Name | Type | Params

0 | model | Text2SemanticDecoder | 77.5 M

77.5 M Trainable params 0 Non-trainable params 77.5 M Total params 309.975 Total estimated model params size (MB) Restored all states from the checkpoint at logs\KoBy\logs_s1\ckpt\epoch=14-step=60.ckpt C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\pytorch_lightning\loops\fit_loop.py:293: The number of training batches (17) is smaller than the logging interval Trainer(log_every_n_steps=50). Set a lower value for log_every_n_steps if you want to see logs for the training epoch. Trainer.fit stopped: max_epochs=15 reached. C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\transformers\utils\generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\transformers\utils\generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\transformers\utils\generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node( C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\transformers\utils\generic.py:441: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. _torch_pytree._register_pytree_node(

[SapphireLab]

你这个...粘贴日志之前还是整理一下格式为好.

关键句:

C:\Users\dell\Desktop\GPT-SoVITS-beta0306\runtime\lib\site-packages\pytorch_lightning\callbacks\model_checkpoint.py:639:
Checkpoint directory C:\Users\dell\Desktop\GPT-SoVITS-beta0306\logs\KoBy\logs_s1\ckpt exists and is not empty.
Restoring states from the checkpoint path at logs\KoBy\logs_s1\ckpt\epoch=14-step=60.ckpt

看起来是之前用实验名 KoBy 训练过, 并且 logs 下的文件夹没有清除, 读取到了相应模型, 其训练的 epoch 数已经达到上限, 所以没有继续训练. 请考虑清除 logs/KoBy 文件夹或者重新设置实验名.