metadata
library_name: peft
base_model: voidful/llm-codec-abl-ftp
tags:
- generated_from_trainer
model-index:
- name: llmcodec-librispeech-abl-ftp
results: []
llmcodec-librispeech-abl-ftp
This model is a fine-tuned version of voidful/llm-codec-abl-ftp on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 8.5615
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 |
|---|---|---|---|
| 8.7126 | 1.0 | 35156 | 8.8477 |
| 8.3702 | 2.0 | 70312 | 8.6207 |
| 8.4569 | 3.0 | 105468 | 8.5615 |
Framework versions
- PEFT 0.15.0
- Transformers 4.57.3
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0