No index file generated after training the model

[SpawnerF]

So basically after completing 350 epochs, it did generate the .pth file along with config json, but .index is no where to be seen, here is the logs :

2023-04-29 14:39:38,916	mymodel	INFO	{'train': {'log_interval': 200, 'seed': 1234, 'epochs': 20000, 'learning_rate': 0.0001, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 14, 'fp16_run': True, 'lr_decay': 0.999875, 'segment_size': 12800, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'max_wav_value': 32768.0, 'sampling_rate': 40000, 'filter_length': 2048, 'hop_length': 400, 'win_length': 2048, 'n_mel_channels': 125, 'mel_fmin': 0.0, 'mel_fmax': None, 'training_files': './logs/mymodel/filelist.txt'}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [10, 10, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'use_spectral_norm': False, 'gin_channels': 256, 'spk_embed_dim': 109}, 'model_dir': './logs/mymodel', 'experiment_dir': './logs/mymodel', 'save_every_epoch': 50, 'name': 'mymodel', 'total_epoch': 350, 'pretrainG': 'pretrained/f0G40k.pth', 'pretrainD': 'pretrained/f0D40k.pth', 'gpus': '0', 'sample_rate': '40k', 'if_f0': 1, 'if_latest': 1, 'if_cache_data_in_gpu': 0}

2023-04-29 16:02:55,997	mymodel	INFO	Saving model and optimizer state at epoch 350 to ./logs/mymodel/G_2333333.pth
2023-04-29 16:02:57,467	mymodel	INFO	Saving model and optimizer state at epoch 350 to ./logs/mymodel/D_2333333.pth
2023-04-29 16:03:00,090	mymodel	INFO	====> Epoch: 350
2023-04-29 16:03:00,090	mymodel	INFO	Training is done. The program is closed.
2023-04-29 16:03:00,352	mymodel	INFO	saving final ckpt:Success.

[mr-segfault]

Duplicate of: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/167

[RVC-Boss]

So basically after completing 350 epochs, it did generate the .pth file along with config json, but .index is no where to be seen, here is the logs :

2023-04-29 14:39:38,916	mymodel	INFO	{'train': {'log_interval': 200, 'seed': 1234, 'epochs': 20000, 'learning_rate': 0.0001, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 14, 'fp16_run': True, 'lr_decay': 0.999875, 'segment_size': 12800, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'max_wav_value': 32768.0, 'sampling_rate': 40000, 'filter_length': 2048, 'hop_length': 400, 'win_length': 2048, 'n_mel_channels': 125, 'mel_fmin': 0.0, 'mel_fmax': None, 'training_files': './logs/mymodel/filelist.txt'}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [10, 10, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'use_spectral_norm': False, 'gin_channels': 256, 'spk_embed_dim': 109}, 'model_dir': './logs/mymodel', 'experiment_dir': './logs/mymodel', 'save_every_epoch': 50, 'name': 'mymodel', 'total_epoch': 350, 'pretrainG': 'pretrained/f0G40k.pth', 'pretrainD': 'pretrained/f0D40k.pth', 'gpus': '0', 'sample_rate': '40k', 'if_f0': 1, 'if_latest': 1, 'if_cache_data_in_gpu': 0}

2023-04-29 16:02:55,997	mymodel	INFO	Saving model and optimizer state at epoch 350 to ./logs/mymodel/G_2333333.pth
2023-04-29 16:02:57,467	mymodel	INFO	Saving model and optimizer state at epoch 350 to ./logs/mymodel/D_2333333.pth
2023-04-29 16:03:00,090	mymodel	INFO	====> Epoch: 350
2023-04-29 16:03:00,090	mymodel	INFO	Training is done. The program is closed.
2023-04-29 16:03:00,352	mymodel	INFO	saving final ckpt:Success.

Your GPU is, 10xx, 16xx, P40, or others?

[SpawnerF]

I'm using Google colab free version as I still can't run rvc locally on M1.

GPU Name : GPU 0: Tesla T4

[eliasnassar]

I am facing the same problem +1

[shivanishimpi]

I am stuck with the same problem, can someone direct me to a solution to the same?

[Acrivec]

I have the same problem - 100 epochs training completed, no GPU, no index file.

[himalooo]

any updates how to fix it

[skillslasher]

Same problem with index file. After training the model, it's gone. Has anyone found a solution?

[github-actions[bot]]

This issue was closed because it has been inactive for 15 days since being marked as stale.