whisper-lora-641
This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3466
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- 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: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4188 | 0.5674 | 10 | 1.3683 |
| 1.3084 | 1.1135 | 20 | 1.3669 |
| 1.3747 | 1.6809 | 30 | 1.3646 |
| 1.3357 | 2.2270 | 40 | 1.3638 |
| 1.3503 | 2.7943 | 50 | 1.3617 |
| 1.3659 | 3.3404 | 60 | 1.3597 |
| 1.3663 | 3.9078 | 70 | 1.3525 |
| 1.2646 | 4.4539 | 80 | 1.3499 |
| 1.3585 | 5.0 | 90 | 1.3466 |
Framework versions
- PEFT 0.16.0
- Transformers 4.53.2
- Pytorch 2.7.1+cu118
- Datasets 3.1.0
- Tokenizers 0.21.2
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Jeff13680/whisper-lora-641
Base model
openai/whisper-large-v3