mrq/ai-voice-cloning
31
74
Fork 43
Code Issues 222 Pull Requests 5 Packages Projects Releases Wiki Activity

Update 'Training'

mrq 2023-03-03 04:59:06 +00:00
parent da17c022ad
commit c85a30fc7a
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
Training.md

@ -104,10 +104,13 @@ I have not tested if this is feasible, but I have tested that you can finetune f
After preparing your dataset and configuration file, you are ready to train. Simply select a generated configuration file, click train, then keep an eye on either the console window to the right for output, or console output in your terminal/command prompt. After preparing your dataset and configuration file, you are ready to train. Simply select a generated configuration file, click train, then keep an eye on either the console window to the right for output, or console output in your terminal/command prompt.
If you check `Verbose Console Output`, *all* output from the training process gets forwarded to the console window on the right. This output is buffered, up to the `Console Buffer Size` specified (for example, the last eight lines if 8). If you check `Verbose Console Output`, *all* output from the training process gets forwarded to the console window on the right until training starts. This output is buffered, up to the `Console Buffer Size` specified (for example, the last eight lines if 8).
If you bump up the `Keep X Previous States` above 0, it will keep the last X number of saved models and training states, and clean up the rest on training start, and every save. **!**NOTE**!** I did not extensively test this, only on test data, and it did not nuke my saves. I don't expect it to happen, but be wary. If you bump up the `Keep X Previous States` above 0, it will keep the last X number of saved models and training states, and clean up the rest on training start, and every save. **!**NOTE**!** I did not extensively test this, only on test data, and it did not nuke my saves. I don't expect it to happen, but be wary.
**!**Linux only**!**: If you're looking to use multiple GPUs, set how many GPUs you have in the `GPUs` field, and it will leverage distrubted training.
* **!**NOTE**!**: this is experimental. It seems to train so far, and both my 6800XTs have a load on them, but I'm not too sure of the exact specifics.
If everything is done right, you'll see a progress bar and some helpful metrics. Below that, is a graph of the total GPT loss rate. If everything is done right, you'll see a progress bar and some helpful metrics. Below that, is a graph of the total GPT loss rate.
After every `print rate` iterations, the loss rate will update and get reported back to you. This will update the graph below with the current loss rate. This is useful to see how "ready" your model/finetune is. The general rule of thumb is the lower, the better. I used to swear by values around `0.15` and `0.1`, but I've had nicer results when it's lower. But be wary, as this *may* be grounds for overfitment, as is the usual problem with training/finetuning. After every `print rate` iterations, the loss rate will update and get reported back to you. This will update the graph below with the current loss rate. This is useful to see how "ready" your model/finetune is. The general rule of thumb is the lower, the better. I used to swear by values around `0.15` and `0.1`, but I've had nicer results when it's lower. But be wary, as this *may* be grounds for overfitment, as is the usual problem with training/finetuning.