| --- |
| library_name: peft |
| base_model: voidful/llm-codec-abl-sa |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: llmcodec-librispeech-abl-sa |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # llmcodec-librispeech-abl-sa |
|
|
| This model is a fine-tuned version of [voidful/llm-codec-abl-sa](https://huggingface.co/voidful/llm-codec-abl-sa) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 8.4431 |
|
|
| ## Model description |
|
|
| More information needed |
|
|
| ## Intended uses & limitations |
|
|
| More information needed |
|
|
| ## Training and evaluation data |
|
|
| More information needed |
|
|
| ## Training procedure |
|
|
| ### Training hyperparameters |
|
|
| The following hyperparameters were used during training: |
| - learning_rate: 0.0001 |
| - train_batch_size: 1 |
| - eval_batch_size: 1 |
| - seed: 42 |
| - gradient_accumulation_steps: 8 |
| - total_train_batch_size: 8 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_ratio: 0.1 |
| - num_epochs: 3 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:------:|:---------------:| |
| | 8.5968 | 1.0 | 35156 | 8.7275 | |
| | 8.3714 | 2.0 | 70312 | 8.5016 | |
| | 8.3344 | 3.0 | 105468 | 8.4431 | |
|
|
|
|
| ### Framework versions |
|
|
| - PEFT 0.15.0 |
| - Transformers 4.57.3 |
| - Pytorch 2.8.0+cu126 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.0 |
