fish-speech
fish-speech copied to clipboard
while training full or warnings and errors, the weights are not loaded
Self Checks
- [X] This template is only for bug reports. For questions, please visit Discussions.
- [X] I have thoroughly reviewed the project documentation (installation, training, inference) but couldn't find information to solve my problem. English 中文 日本語 Portuguese (Brazil)
- [X] I have searched for existing issues, including closed ones. Search issues
- [X] I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
- [X] [FOR CHINESE USERS] 请务必使用英文提交 Issue,否则会被关闭。谢谢!:)
- [X] Please do not modify this template and fill in all required fields.
Cloud or Self Hosted
Cloud
Environment Details
linux vm
Steps to Reproduce
while trainind
✔️ Expected Behavior
runs without error and arning, loading correct pretrained weights, i have downloaded the pretrained weights and the path is correct
❌ Actual Behavior
2024-11-08 15:55:29,094][fish_speech.models.text2semantic.llama][INFO] - [rank: 0] Loaded weights with error: _IncompatibleKeys(missing_keys=['embeddings.lora_A', 'embeddings.lora_B', 'codebook_embeddings.lora_A', 'codebook_embeddings.lora_B', 'layers.0.attention.wqkv.lora_A', 'layers.0.attention.wqkv.lora_B', 'layers.0.attention.wo.lora_A', 'layers.0.attention.wo.lora_B', 'layers.0.feed_forward.w1.lora_A', 'layers.0.feed_forward.w1.lora_B', 'layers.0.feed_forward.w3.lora_A', 'layers.0.feed_forward.w3.lora_B', 'layers.0.feed_forward.w2.lora_A', 'layers.0.feed_forward.w2.lora_B', 'layers.1.attention.wqkv.lora_A', 'layers.1.attention.wqkv.lora_B', 'layers.1.attention.wo.lora_A', 'layers.1.attention.wo.lora_B', 'layers.1.feed_forward.w1.lora_A', 'layers.1.feed_forward.w1.lora_B', 'layers.1.feed_forward.w3.lora_A', 'layers.1.feed_forward.w3.lora_B', 'layers.1.feed_forward.w2.lora_A', 'layers.1.feed_forward.w2.lora_B', 'layers.2.attention.wqkv.lora_A', 'layers.2.attention.wqkv.lora_B', 'layers.2.attention.wo.lora_A', 'layers.2.attention.wo.lora_B', 'layers.2.feed_forward.w1.lora_A', 'layers.2.feed_forward.w1.lora_B', 'layers.2.feed_forward.w3.lora_A', 'layers.2.feed_forward.w3.lora_B', 'layers.2.feed_forward.w2.lora_A', 'layers.2.feed_forward.w2.lora_B', 'layers.3.attention.wqkv.lora_A', 'layers.3.attention.wqkv.lora_B', 'layers.3.attention.wo.lora_A', 'layers.3.attention.wo.lora_B', 'layers.3.feed_forward.w1.lora_A', 'layers.3.feed_forward.w1.lora_B', 'layers.3.feed_forward.w3.lora_A', 'layers.3.feed_forward.w3.lora_B', 'layers.3.feed_forward.w2.lora_A', 'layers.3.feed_forward.w2.lora_B', 'layers.4.attention.wqkv.lora_A', 'layers.4.attention.wqkv.lora_B', 'layers.4.attention.wo.lora_A', 'layers.4.attention.wo.lora_B', 'layers.4.feed_forward.w1.lora_A', 'layers.4.feed_forward.w1.lora_B', 'layers.4.feed_forward.w3.lora_A', 'layers.4.feed_forward.w3.lora_B', 'layers.4.feed_forward.w2.lora_A', 'layers.4.feed_forward.w2.lora_B', 'layers.5.attention.wqkv.lora_A', 'layers.5.attention.wqkv.lora_B', 'layers.5.attention.wo.lora_A', 'layers.5.attention.wo.lora_B', 'layers.5.feed_forward.w1.lora_A', 'layers.5.feed_forward.w1.lora_B', 'layers.5.feed_forward.w3.lora_A', 'layers.5.feed_forward.w3.lora_B', 'layers.5.feed_forward.w2.lora_A', 'layers.5.feed_forward.w2.lora_B', 'layers.6.attention.wqkv.lora_A', 'layers.6.attention.wqkv.lora_B', 'layers.6.attention.wo.lora_A', 'layers.6.attention.wo.lora_B', 'layers.6.feed_forward.w1.lora_A', 'layers.6.feed_forward.w1.lora_B', 'layers.6.feed_forward.w3.lora_A', 'layers.6.feed_forward.w3.lora_B', 'layers.6.feed_forward.w2.lora_A', 'layers.6.feed_forward.w2.lora_B', 'layers.7.attention.wqkv.lora_A', 'layers.7.attention.wqkv.lora_B', 'layers.7.attention.wo.lora_A', 'layers.7.attention.wo.lora_B', 'layers.7.feed_forward.w1.lora_A', 'layers.7.feed_forward.w1.lora_B', 'layers.7.feed_forward.w3.lora_A', 'layers.7.feed_forward.w3.lora_B', 'layers.7.feed_forward.w2.lora_A', 'layers.7.feed_forward.w2.lora_B', 'layers.8.attention.wqkv.lora_A', 'layers.8.attention.wqkv.lora_B', 'layers.8.attention.wo.lora_A', 'layers.8.attention.wo.lora_B', 'layers.8.feed_forward.w1.lora_A', 'layers.8.feed_forward.w1.lora_B', 'layers.8.feed_forward.w3.lora_A', 'layers.8.feed_forward.w3.lora_B', 'layers.8.feed_forward.w2.lora_A', 'layers.8.feed_forward.w2.lora_B', 'layers.9.attention.wqkv.lora_A', 'layers.9.attention.wqkv.lora_B', 'layers.9.attention.wo.lora_A', 'layers.9.attention.wo.lora_B', 'layers.9.feed_forward.w1.lora_A', 'layers.9.feed_forward.w1.lora_B', 'layers.9.feed_forward.w3.lora_A', 'layers.9.feed_forward.w3.lora_B', 'layers.9.feed_forward.w2.lora_A', 'layers.9.feed_forward.w2.lora_B', 'layers.10.attention.wqkv.lora_A', 'layers.10.attention.wqkv.lora_B', 'layers.10.attention.wo.lora_A', 'layers.10.attention.wo.lora_B', 'layers.10.feed_forward.w1.lora_A', 'layers.10.feed_forward.w1.lora_B', 'layers.10.feed_forward.w3.lora_A', 'layers.10.feed_forward.w3.lora_B', 'layers.10.feed_forward.w2.lora_A', 'layers.10.feed_forward.w2.lora_B', 'layers.11.attention.wqkv.lora_A', 'layers.11.attention.wqkv.lora_B', 'layers.11.attention.wo.lora_A', 'layers.11.attention.wo.lora_B', 'layers.11.feed_forward.w1.lora_A', 'layers.11.feed_forward.w1.lora_B', 'layers.11.feed_forward.w3.lora_A', 'layers.11.feed_forward.w3.lora_B', 'layers.11.feed_forward.w2.lora_A', 'layers.11.feed_forward.w2.lora_B', 'layers.12.attention.wqkv.lora_A', 'layers.12.attention.wqkv.lora_B', 'layers.12.attention.wo.lora_A', 'layers.12.attention.wo.lora_B', 'layers.12.feed_forward.w1.lora_A', 'layers.12.feed_forward.w1.lora_B', 'layers.12.feed_forward.w3.lora_A', 'layers.12.feed_forward.w3.lora_B', 'layers.12.feed_forward.w2.lora_A', 'layers.12.feed_forward.w2.lora_B', 'layers.13.attention.wqkv.lora_A', 'layers.13.attention.wqkv.lora_B', 'layers.13.attention.wo.lora_A', 'layers.13.attention.wo.lora_B', 'layers.13.feed_forward.w1.lora_A', 'layers.13.feed_forward.w1.lora_B', 'layers.13.feed_forward.w3.lora_A', 'layers.13.feed_forward.w3.lora_B', 'layers.13.feed_forward.w2.lora_A', 'layers.13.feed_forward.w2.lora_B', 'layers.14.attention.wqkv.lora_A', 'layers.14.attention.wqkv.lora_B', 'layers.14.attention.wo.lora_A', 'layers.14.attention.wo.lora_B', 'layers.14.feed_forward.w1.lora_A', 'layers.14.feed_forward.w1.lora_B', 'layers.14.feed_forward.w3.lora_A', 'layers.14.feed_forward.w3.lora_B', 'layers.14.feed_forward.w2.lora_A', 'layers.14.feed_forward.w2.lora_B', 'layers.15.attention.wqkv.lora_A', 'layers.15.attention.wqkv.lora_B', 'layers.15.attention.wo.lora_A', 'layers.15.attention.wo.lora_B', 'layers.15.feed_forward.w1.lora_A', 'layers.15.feed_forward.w1.lora_B', 'layers.15.feed_forward.w3.lora_A', 'layers.15.feed_forward.w3.lora_B', 'layers.15.feed_forward.w2.lora_A', 'layers.15.feed_forward.w2.lora_B', 'layers.16.attention.wqkv.lora_A', 'layers.16.attention.wqkv.lora_B', 'layers.16.attention.wo.lora_A', 'layers.16.attention.wo.lora_B', 'layers.16.feed_forward.w1.lora_A', 'layers.16.feed_forward.w1.lora_B', 'layers.16.feed_forward.w3.lora_A', 'layers.16.feed_forward.w3.lora_B', 'layers.16.feed_forward.w2.lora_A', 'layers.16.feed_forward.w2.lora_B', 'layers.17.attention.wqkv.lora_A', 'layers.17.attention.wqkv.lora_B', 'layers.17.attention.wo.lora_A', 'layers.17.attention.wo.lora_B', 'layers.17.feed_forward.w1.lora_A', 'layers.17.feed_forward.w1.lora_B', 'layers.17.feed_forward.w3.lora_A', 'layers.17.feed_forward.w3.lora_B', 'layers.17.feed_forward.w2.lora_A', 'layers.17.feed_forward.w2.lora_B', 'layers.18.attention.wqkv.lora_A', 'layers.18.attention.wqkv.lora_B', 'layers.18.attention.wo.lora_A', 'layers.18.attention.wo.lora_B', 'layers.18.feed_forward.w1.lora_A', 'layers.18.feed_forward.w1.lora_B', 'layers.18.feed_forward.w3.lora_A', 'layers.18.feed_forward.w3.lora_B', 'layers.18.feed_forward.w2.lora_A', 'layers.18.feed_forward.w2.lora_B', 'layers.19.attention.wqkv.lora_A', 'layers.19.attention.wqkv.lora_B', 'layers.19.attention.wo.lora_A', 'layers.19.attention.wo.lora_B', 'layers.19.feed_forward.w1.lora_A', 'layers.19.feed_forward.w1.lora_B', 'layers.19.feed_forward.w3.lora_A', 'layers.19.feed_forward.w3.lora_B', 'layers.19.feed_forward.w2.lora_A', 'layers.19.feed_forward.w2.lora_B', 'layers.20.attention.wqkv.lora_A', 'layers.20.attention.wqkv.lora_B', 'layers.20.attention.wo.lora_A', 'layers.20.attention.wo.lora_B', 'layers.20.feed_forward.w1.lora_A', 'layers.20.feed_forward.w1.lora_B', 'layers.20.feed_forward.w3.lora_A', 'layers.20.feed_forward.w3.lora_B', 'layers.20.feed_forward.w2.lora_A', 'layers.20.feed_forward.w2.lora_B', 'layers.21.attention.wqkv.lora_A', 'layers.21.attention.wqkv.lora_B', 'layers.21.attention.wo.lora_A', 'layers.21.attention.wo.lora_B', 'layers.21.feed_forward.w1.lora_A', 'layers.21.feed_forward.w1.lora_B', 'layers.21.feed_forward.w3.lora_A', 'layers.21.feed_forward.w3.lora_B', 'layers.21.feed_forward.w2.lora_A', 'layers.21.feed_forward.w2.lora_B', 'layers.22.attention.wqkv.lora_A', 'layers.22.attention.wqkv.lora_B', 'layers.22.attention.wo.lora_A', 'layers.22.attention.wo.lora_B', 'layers.22.feed_forward.w1.lora_A', 'layers.22.feed_forward.w1.lora_B', 'layers.22.feed_forward.w3.lora_A', 'layers.22.feed_forward.w3.lora_B', 'layers.22.feed_forward.w2.lora_A', 'layers.22.feed_forward.w2.lora_B', 'layers.23.attention.wqkv.lora_A', 'layers.23.attention.wqkv.lora_B', 'layers.23.attention.wo.lora_A', 'layers.23.attention.wo.lora_B', 'layers.23.feed_forward.w1.lora_A', 'layers.23.feed_forward.w1.lora_B', 'layers.23.feed_forward.w3.lora_A', 'layers.23.feed_forward.w3.lora_B', 'layers.23.feed_forward.w2.lora_A', 'layers.23.feed_forward.w2.lora_B', 'output.lora_A', 'output.lora_B', 'fast_embeddings.lora_A', 'fast_embeddings.lora_B', 'fast_layers.0.attention.wqkv.lora_A', 'fast_layers.0.attention.wqkv.lora_B', 'fast_layers.0.attention.wo.lora_A', 'fast_layers.0.attention.wo.lora_B', 'fast_layers.0.feed_forward.w1.lora_A', 'fast_layers.0.feed_forward.w1.lora_B', 'fast_layers.0.feed_forward.w3.lora_A', 'fast_layers.0.feed_forward.w3.lora_B', 'fast_layers.0.feed_forward.w2.lora_A', 'fast_layers.0.feed_forward.w2.lora_B', 'fast_layers.1.attention.wqkv.lora_A', 'fast_layers.1.attention.wqkv.lora_B', 'fast_layers.1.attention.wo.lora_A', 'fast_layers.1.attention.wo.lora_B', 'fast_layers.1.feed_forward.w1.lora_A', 'fast_layers.1.feed_forward.w1.lora_B', 'fast_layers.1.feed_forward.w3.lora_A', 'fast_layers.1.feed_forward.w3.lora_B', 'fast_layers.1.feed_forward.w2.lora_A', 'fast_layers.1.feed_forward.w2.lora_B', 'fast_layers.2.attention.wqkv.lora_A', 'fast_layers.2.attention.wqkv.lora_B', 'fast_layers.2.attention.wo.lora_A', 'fast_layers.2.attention.wo.lora_B', 'fast_layers.2.feed_forward.w1.lora_A', 'fast_layers.2.feed_forward.w1.lora_B', 'fast_layers.2.feed_forward.w3.lora_A', 'fast_layers.2.feed_forward.w3.lora_B', 'fast_layers.2.feed_forward.w2.lora_A', 'fast_layers.2.feed_forward.w2.lora_B', 'fast_layers.3.attention.wqkv.lora_A', 'fast_layers.3.attention.wqkv.lora_B', 'fast_layers.3.attention.wo.lora_A', 'fast_layers.3.attention.wo.lora_B', 'fast_layers.3.feed_forward.w1.lora_A', 'fast_layers.3.feed_forward.w1.lora_B', 'fast_layers.3.feed_forward.w3.lora_A', 'fast_layers.3.feed_forward.w3.lora_B', 'fast_layers.3.feed_forward.w2.lora_A', 'fast_layers.3.feed_forward.w2.lora_B', 'fast_output.lora_A', 'fast_output.lora_B'], unexpected_keys=[])
[2024-11-08 15:55:29,099][main][INFO] - [rank: 0] Instantiating callbacks...
[2024-11-08 15:55:29,099][fish_speech.utils.instantiators][INFO] - [rank: 0] Instantiating callback <lightning.pytorch.callbacks.ModelCheckpoint>
[2024-11-08 15:55:29,103][fish_speech.utils.instantiators][INFO] - [rank: 0] Instantiating callback <lightning.pytorch.callbacks.ModelSummary>
[2024-11-08 15:55:29,104][fish_speech.utils.instantiators][INFO] - [rank: 0] Instantiating callback <lightning.pytorch.callbacks.LearningRateMonitor>
[2024-11-08 15:55:29,104][fish_speech.utils.instantiators][INFO] - [rank: 0] Instantiating callback <fish_speech.callbacks.GradNormMonitor>
[2024-11-08 15:55:29,109][main][INFO] - [rank: 0] Instantiating loggers...
[2024-11-08 15:55:29,109][fish_speech.utils.instantiators][INFO] - [rank: 0] Instantiating logger <lightning.pytorch.loggers.tensorboard.TensorBoardLogger>
[2024-11-08 15:55:29,113][main][INFO] - [rank: 0] Instantiating trainer <lightning.pytorch.trainer.Trainer>
[2024-11-08 15:55:29,150][pytorch_lightning.utilities.rank_zero][INFO] - Trainer already configured with model summary callbacks: [<class 'lightning.pytorch.callbacks.model_summary.ModelSummary'>]. Skipping setting a default ModelSummary
callback.
[2024-11-08 15:55:29,195][pytorch_lightning.utilities.rank_zero][INFO] - GPU available: True (cuda), used: True
[2024-11-08 15:55:29,196][pytorch_lightning.utilities.rank_zero][INFO] - TPU available: False, using: 0 TPU cores
[2024-11-08 15:55:29,196][pytorch_lightning.utilities.rank_zero][INFO] - HPU available: False, using: 0 HPUs
[2024-11-08 15:55:29,197][main][INFO] - [rank: 0] Logging hyperparameters!
[2024-11-08 15:55:42,725][main][INFO] - [rank: 0] Starting training!
INFO: Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/2
[2024-11-08 15:55:42,798][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/2
[2024-11-08 15:55:48,877][numexpr.utils][INFO] - NumExpr defaulting to 4 threads.
[2024-11-08 15:55:49,063][datasets][INFO] - PyTorch version 2.4.1 available.
[2024-11-08 15:55:49,065][datasets][INFO] - Polars version 1.9.0 available.
[2024-11-08 15:55:49,066][datasets][INFO] - TensorFlow version 2.16.1 available.
[2024-11-08 15:55:49,068][datasets][INFO] - JAX version 0.4.26 available.
2024-11-08 15:56:06.023 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for embeddings.lora_A
2024-11-08 15:56:06.023 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for embeddings.lora_B
2024-11-08 15:56:06.023 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for codebook_embeddings.lora_A
2024-11-08 15:56:06.023 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for codebook_embeddings.lora_B
2024-11-08 15:56:06.023 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.0.attention.wqkv.lora_A
2024-11-08 15:56:06.024 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.0.attention.wqkv.lora_B
2024-11-08 15:56:06.024 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.0.attention.wo.lora_A
2024-11-08 15:56:06.024 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.0.attention.wo.lora_B
2024-11-08 15:56:06.024 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.0.feed_forward.w1.lora_A
2024-11-08 15:56:06.024 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.0.feed_forward.w1.lora_B
2024-11-08 15:56:06.024 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.0.feed_forward.w3.lora_A
2024-11-08 15:56:06.024 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.0.feed_forward.w3.lora_B
2024-11-08 15:56:06.024 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.0.feed_forward.w2.lora_A
2024-11-08 15:56:06.024 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.0.feed_forward.w2.lora_B
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.1.attention.wqkv.lora_A
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.1.attention.wqkv.lora_B
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.1.attention.wo.lora_A
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.1.attention.wo.lora_B
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.1.feed_forward.w1.lora_A
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.1.feed_forward.w1.lora_B
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.1.feed_forward.w3.lora_A
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.1.feed_forward.w3.lora_B
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.1.feed_forward.w2.lora_A
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.1.feed_forward.w2.lora_B
2024-11-08 15:56:06.025 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.2.attention.wqkv.lora_A
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.2.attention.wqkv.lora_B
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.2.attention.wo.lora_A
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.2.attention.wo.lora_B
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.2.feed_forward.w1.lora_A
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.2.feed_forward.w1.lora_B
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.2.feed_forward.w3.lora_A
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.2.feed_forward.w3.lora_B
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.2.feed_forward.w2.lora_A
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.2.feed_forward.w2.lora_B
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.3.attention.wqkv.lora_A
2024-11-08 15:56:06.026 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.3.attention.wqkv.lora_B
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.3.attention.wo.lora_A
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.3.attention.wo.lora_B
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.3.feed_forward.w1.lora_A
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.3.feed_forward.w1.lora_B
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.3.feed_forward.w3.lora_A
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.3.feed_forward.w3.lora_B
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.3.feed_forward.w2.lora_A
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.3.feed_forward.w2.lora_B
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.4.attention.wqkv.lora_A
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.4.attention.wqkv.lora_B
2024-11-08 15:56:06.027 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.4.attention.wo.lora_A
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.4.attention.wo.lora_B
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.4.feed_forward.w1.lora_A
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.4.feed_forward.w1.lora_B
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.4.feed_forward.w3.lora_A
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.4.feed_forward.w3.lora_B
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.4.feed_forward.w2.lora_A
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.4.feed_forward.w2.lora_B
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.5.attention.wqkv.lora_A
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.5.attention.wqkv.lora_B
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.5.attention.wo.lora_A
2024-11-08 15:56:06.028 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.5.attention.wo.lora_B
2024-11-08 15:56:06.029 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.5.feed_forward.w1.lora_A
2024-11-08 15:56:06.029 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.5.feed_forward.w1.lora_B
2024-11-08 15:56:06.029 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.5.feed_forward.w3.lora_A
2024-11-08 15:56:06.029 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.5.feed_forward.w3.lora_B
2024-11-08 15:56:06.029 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.5.feed_forward.w2.lora_A
2024-11-08 15:56:06.029 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.5.feed_forward.w2.lora_B
2024-11-08 15:56:06.029 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.6.attention.wqkv.lora_A
2024-11-08 15:56:06.029 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.6.attention.wqkv.lora_B
2024-11-08 15:56:06.029 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.6.attention.wo.lora_A
2024-11-08 15:56:06.029 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.6.attention.wo.lora_B
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.6.feed_forward.w1.lora_A
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.6.feed_forward.w1.lora_B
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.6.feed_forward.w3.lora_A
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.6.feed_forward.w3.lora_B
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.6.feed_forward.w2.lora_A
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.6.feed_forward.w2.lora_B
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.7.attention.wqkv.lora_A
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.7.attention.wqkv.lora_B
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.7.attention.wo.lora_A
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.7.attention.wo.lora_B
2024-11-08 15:56:06.030 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.7.feed_forward.w1.lora_A
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.7.feed_forward.w1.lora_B
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.7.feed_forward.w3.lora_A
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.7.feed_forward.w3.lora_B
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.7.feed_forward.w2.lora_A
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.7.feed_forward.w2.lora_B
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.8.attention.wqkv.lora_A
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.8.attention.wqkv.lora_B
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.8.attention.wo.lora_A
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.8.attention.wo.lora_B
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.8.feed_forward.w1.lora_A
2024-11-08 15:56:06.031 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.8.feed_forward.w1.lora_B
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.8.feed_forward.w3.lora_A
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.8.feed_forward.w3.lora_B
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.8.feed_forward.w2.lora_A
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.8.feed_forward.w2.lora_B
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.9.attention.wqkv.lora_A
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.9.attention.wqkv.lora_B
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.9.attention.wo.lora_A
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.9.attention.wo.lora_B
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.9.feed_forward.w1.lora_A
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.9.feed_forward.w1.lora_B
2024-11-08 15:56:06.032 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.9.feed_forward.w3.lora_A
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.9.feed_forward.w3.lora_B
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.9.feed_forward.w2.lora_A
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.9.feed_forward.w2.lora_B
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.10.attention.wqkv.lora_A
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.10.attention.wqkv.lora_B
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.10.attention.wo.lora_A
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.10.attention.wo.lora_B
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.10.feed_forward.w1.lora_A
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.10.feed_forward.w1.lora_B
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.10.feed_forward.w3.lora_A
2024-11-08 15:56:06.033 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.10.feed_forward.w3.lora_B
2024-11-08 15:56:06.034 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.10.feed_forward.w2.lora_A
2024-11-08 15:56:06.034 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.10.feed_forward.w2.lora_B
2024-11-08 15:56:06.034 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.11.attention.wqkv.lora_A
2024-11-08 15:56:06.034 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.11.attention.wqkv.lora_B
2024-11-08 15:56:06.034 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.11.attention.wo.lora_A
2024-11-08 15:56:06.034 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.11.attention.wo.lora_B
2024-11-08 15:56:06.034 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.11.feed_forward.w1.lora_A
2024-11-08 15:56:06.034 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.11.feed_forward.w1.lora_B
2024-11-08 15:56:06.034 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.11.feed_forward.w3.lora_A
2024-11-08 15:56:06.034 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.11.feed_forward.w3.lora_B
2024-11-08 15:56:06.035 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.11.feed_forward.w2.lora_A
2024-11-08 15:56:06.035 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.11.feed_forward.w2.lora_B
2024-11-08 15:56:06.035 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.12.attention.wqkv.lora_A
2024-11-08 15:56:06.035 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.12.attention.wqkv.lora_B
2024-11-08 15:56:06.035 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.12.attention.wo.lora_A
2024-11-08 15:56:06.035 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.12.attention.wo.lora_B
2024-11-08 15:56:06.035 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.12.feed_forward.w1.lora_A
2024-11-08 15:56:06.035 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.12.feed_forward.w1.lora_B
2024-11-08 15:56:06.035 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.12.feed_forward.w3.lora_A
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.12.feed_forward.w3.lora_B
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.12.feed_forward.w2.lora_A
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.12.feed_forward.w2.lora_B
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.13.attention.wqkv.lora_A
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.13.attention.wqkv.lora_B
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.13.attention.wo.lora_A
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.13.attention.wo.lora_B
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.13.feed_forward.w1.lora_A
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.13.feed_forward.w1.lora_B
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.13.feed_forward.w3.lora_A
2024-11-08 15:56:06.036 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.13.feed_forward.w3.lora_B
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.13.feed_forward.w2.lora_A
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.13.feed_forward.w2.lora_B
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.14.attention.wqkv.lora_A
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.14.attention.wqkv.lora_B
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.14.attention.wo.lora_A
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.14.attention.wo.lora_B
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.14.feed_forward.w1.lora_A
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.14.feed_forward.w1.lora_B
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.14.feed_forward.w3.lora_A
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.14.feed_forward.w3.lora_B
2024-11-08 15:56:06.037 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.14.feed_forward.w2.lora_A
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.14.feed_forward.w2.lora_B
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.15.attention.wqkv.lora_A
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.15.attention.wqkv.lora_B
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.15.attention.wo.lora_A
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.15.attention.wo.lora_B
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.15.feed_forward.w1.lora_A
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.15.feed_forward.w1.lora_B
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.15.feed_forward.w3.lora_A
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.15.feed_forward.w3.lora_B
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.15.feed_forward.w2.lora_A
2024-11-08 15:56:06.038 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.15.feed_forward.w2.lora_B
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.16.attention.wqkv.lora_A
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.16.attention.wqkv.lora_B
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.16.attention.wo.lora_A
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.16.attention.wo.lora_B
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.16.feed_forward.w1.lora_A
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.16.feed_forward.w1.lora_B
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.16.feed_forward.w3.lora_A
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.16.feed_forward.w3.lora_B
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.16.feed_forward.w2.lora_A
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.16.feed_forward.w2.lora_B
2024-11-08 15:56:06.039 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.17.attention.wqkv.lora_A
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.17.attention.wqkv.lora_B
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.17.attention.wo.lora_A
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.17.attention.wo.lora_B
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.17.feed_forward.w1.lora_A
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.17.feed_forward.w1.lora_B
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.17.feed_forward.w3.lora_A
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.17.feed_forward.w3.lora_B
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.17.feed_forward.w2.lora_A
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.17.feed_forward.w2.lora_B
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.18.attention.wqkv.lora_A
2024-11-08 15:56:06.040 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.18.attention.wqkv.lora_B
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.18.attention.wo.lora_A
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.18.attention.wo.lora_B
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.18.feed_forward.w1.lora_A
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.18.feed_forward.w1.lora_B
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.18.feed_forward.w3.lora_A
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.18.feed_forward.w3.lora_B
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.18.feed_forward.w2.lora_A
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.18.feed_forward.w2.lora_B
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.19.attention.wqkv.lora_A
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.19.attention.wqkv.lora_B
2024-11-08 15:56:06.041 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.19.attention.wo.lora_A
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.19.attention.wo.lora_B
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.19.feed_forward.w1.lora_A
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.19.feed_forward.w1.lora_B
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.19.feed_forward.w3.lora_A
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.19.feed_forward.w3.lora_B
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.19.feed_forward.w2.lora_A
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.19.feed_forward.w2.lora_B
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.20.attention.wqkv.lora_A
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.20.attention.wqkv.lora_B
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.20.attention.wo.lora_A
2024-11-08 15:56:06.042 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.20.attention.wo.lora_B
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.20.feed_forward.w1.lora_A
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.20.feed_forward.w1.lora_B
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.20.feed_forward.w3.lora_A
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.20.feed_forward.w3.lora_B
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.20.feed_forward.w2.lora_A
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.20.feed_forward.w2.lora_B
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.21.attention.wqkv.lora_A
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.21.attention.wqkv.lora_B
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.21.attention.wo.lora_A
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.21.attention.wo.lora_B
2024-11-08 15:56:06.043 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.21.feed_forward.w1.lora_A
2024-11-08 15:56:06.044 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.21.feed_forward.w1.lora_B
2024-11-08 15:56:06.044 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.21.feed_forward.w3.lora_A
2024-11-08 15:56:06.044 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.21.feed_forward.w3.lora_B
2024-11-08 15:56:06.044 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.21.feed_forward.w2.lora_A
2024-11-08 15:56:06.044 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.21.feed_forward.w2.lora_B
2024-11-08 15:56:06.044 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.22.attention.wqkv.lora_A
2024-11-08 15:56:06.044 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.22.attention.wqkv.lora_B
2024-11-08 15:56:06.044 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.22.attention.wo.lora_A
2024-11-08 15:56:06.044 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.22.attention.wo.lora_B
2024-11-08 15:56:06.045 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.22.feed_forward.w1.lora_A
2024-11-08 15:56:06.045 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.22.feed_forward.w1.lora_B
2024-11-08 15:56:06.045 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.22.feed_forward.w3.lora_A
2024-11-08 15:56:06.045 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.22.feed_forward.w3.lora_B
2024-11-08 15:56:06.045 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.22.feed_forward.w2.lora_A
2024-11-08 15:56:06.045 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.22.feed_forward.w2.lora_B
2024-11-08 15:56:06.045 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.23.attention.wqkv.lora_A
2024-11-08 15:56:06.045 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.23.attention.wqkv.lora_B
2024-11-08 15:56:06.045 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.23.attention.wo.lora_A
2024-11-08 15:56:06.045 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.23.attention.wo.lora_B
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.23.feed_forward.w1.lora_A
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.23.feed_forward.w1.lora_B
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.23.feed_forward.w3.lora_A
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.23.feed_forward.w3.lora_B
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.23.feed_forward.w2.lora_A
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for layers.23.feed_forward.w2.lora_B
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for output.lora_A
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for output.lora_B
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_embeddings.lora_A
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_embeddings.lora_B
2024-11-08 15:56:06.046 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.0.attention.wqkv.lora_A
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.0.attention.wqkv.lora_B
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.0.attention.wo.lora_A
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.0.attention.wo.lora_B
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.0.feed_forward.w1.lora_A
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.0.feed_forward.w1.lora_B
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.0.feed_forward.w3.lora_A
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.0.feed_forward.w3.lora_B
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.0.feed_forward.w2.lora_A
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.0.feed_forward.w2.lora_B
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.1.attention.wqkv.lora_A
2024-11-08 15:56:06.047 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.1.attention.wqkv.lora_B
2024-11-08 15:56:06.048 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.1.attention.wo.lora_A
2024-11-08 15:56:06.048 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.1.attention.wo.lora_B
2024-11-08 15:56:06.048 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.1.feed_forward.w1.lora_A
2024-11-08 15:56:06.048 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.1.feed_forward.w1.lora_B
2024-11-08 15:56:06.048 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.1.feed_forward.w3.lora_A
2024-11-08 15:56:06.048 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.1.feed_forward.w3.lora_B
2024-11-08 15:56:06.048 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.1.feed_forward.w2.lora_A
2024-11-08 15:56:06.048 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.1.feed_forward.w2.lora_B
2024-11-08 15:56:06.048 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.2.attention.wqkv.lora_A
2024-11-08 15:56:06.049 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.2.attention.wqkv.lora_B
2024-11-08 15:56:06.049 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.2.attention.wo.lora_A
2024-11-08 15:56:06.049 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.2.attention.wo.lora_B
2024-11-08 15:56:06.049 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.2.feed_forward.w1.lora_A
2024-11-08 15:56:06.049 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.2.feed_forward.w1.lora_B
2024-11-08 15:56:06.049 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.2.feed_forward.w3.lora_A
2024-11-08 15:56:06.049 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.2.feed_forward.w3.lora_B
2024-11-08 15:56:06.049 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.2.feed_forward.w2.lora_A
2024-11-08 15:56:06.050 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.2.feed_forward.w2.lora_B
2024-11-08 15:56:06.050 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.3.attention.wqkv.lora_A
2024-11-08 15:56:06.050 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.3.attention.wqkv.lora_B
2024-11-08 15:56:06.050 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.3.attention.wo.lora_A
2024-11-08 15:56:06.050 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.3.attention.wo.lora_B
2024-11-08 15:56:06.050 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.3.feed_forward.w1.lora_A
2024-11-08 15:56:06.050 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.3.feed_forward.w1.lora_B
2024-11-08 15:56:06.051 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.3.feed_forward.w3.lora_A
2024-11-08 15:56:06.051 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.3.feed_forward.w3.lora_B
2024-11-08 15:56:06.051 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.3.feed_forward.w2.lora_A
2024-11-08 15:56:06.051 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_layers.3.feed_forward.w2.lora_B
2024-11-08 15:56:06.051 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_output.lora_A
2024-11-08 15:56:06.051 | WARNING | fish_speech.models.text2semantic.llama:from_pretrained:424 - No weight for fast_output.lora_B
INFO: Initializing distributed: GLOBAL_RANK: 1, MEMBER: 2/2
[2024-11-08 15:56:06,333][lightning.fabric.utilities.distributed][INFO] - Initializing distributed: GLOBAL_RANK: 1, MEMBER: 2/2
[W1108 15:56:06.706582522 CUDAAllocatorConfig.h:28] Warning: expandable_segments not supported on this platform (function operator())
[W1108 15:56:06.715281420 CUDAAllocatorConfig.h:28] Warning: expandable_segments not supported on this platform (function operator())
[2024-11-08 15:56:06,345][pytorch_lightning.utilities.rank_zero][INFO] - ----------------------------------------------------------------------------------------------------
distributed_backend=nccl
All distributed processes registered. Starting with 2 processes
INFO: LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1] INFO: LOCAL_RANK: 1 - CUDA_VISIBLE_DEVICES: [0,1] [2024-11-08 15:56:07,062][lightning.pytorch.accelerators.cuda][INFO] - LOCAL_RANK: 1 - CUDA_VISIBLE_DEVICES: [0,1] [2024-11-08 15:56:07,062][lightning.pytorch.accelerators.cuda][INFO] - LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1] [2024-11-08 15:56:17,373][fish_speech.models.text2semantic.lit_module][INFO] - [rank: 0] Set weight decay: 0 for 432 parameters [2024-11-08 15:56:17,373][fish_speech.models.text2semantic.lit_module][INFO] - [rank: 0] Set weight decay: 0.0 for 61 parameters INFO: | Name | Type | Params | Mode
0 | model | DualARTransformer | 499 M | train 1 | model.embeddings | Embedding | 33.0 M | train 2 | model.codebook_embeddings | Embedding | 8.5 M | train 3 | model.layers | ModuleList | 362 M | train 4 | model.norm | RMSNorm | 1.0 K | train 5 | model.output | Linear | 33.0 M | train 6 | model.fast_project_in | Identity | 0 | train 7 | model.fast_embeddings | Embedding | 1.1 M | train 8 | model.fast_layers | ModuleList | 60.4 M | train 9 | model.fast_norm | RMSNorm | 1.0 K | train 10 | model.fast_output | Linear | 1.1 M | train
5.1 M Trainable params 494 M Non-trainable params 499 M Total params 1,998.053 Total estimated model params size (MB) 433 Modules in train mode 0 Modules in eval mode