metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: openai/whisper-small
model-index:
- name: Whisper-small-L2Arctic
results: []
Whisper-small-L2Arctic
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6319
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: 0.001
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5321 | 1.0 | 450 | 0.5247 |
| 0.4321 | 2.0 | 900 | 0.5136 |
| 0.3659 | 3.0 | 1350 | 0.4786 |
| 0.313 | 4.0 | 1800 | 0.4708 |
| 0.2468 | 5.0 | 2250 | 0.4729 |
| 0.189 | 6.0 | 2700 | 0.5010 |
| 0.1223 | 7.0 | 3150 | 0.5433 |
| 0.0729 | 8.0 | 3600 | 0.5775 |
| 0.0363 | 9.0 | 4050 | 0.6103 |
| 0.0182 | 10.0 | 4500 | 0.6319 |
Framework versions
- PEFT 0.8.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1