Downloads · 30 days
4
17% of all-time downloads
KhalsuuTagalog-fineTunedLargeV2-tl-1
zeon8985army/KhalsuuTagalog-fineTunedLargeV2-tl-1
KhalsuuTagalog-fineTunedLargeV2-tl-1 is a machine learning model from zeon8985army. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
24
Public
Repo size
63 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors63 MB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Mar 24, 2024
- Updated
- Mar 24, 2024
- SHA
- 21f1e1ef
Base models
Datasets
Model card
From the Hugging Face model README
<!-- 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. -->
zeon8985army/KhalsuuTagalog-fineTunedLargeV2-tl-1
This model is a fine-tuned version of openai/whisper-large-v2 on the AlistairBegg dataset. It achieves the following results on the evaluation set:
- Loss: 0.2708
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: 6e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 12
- training_steps: 276
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.26 | 0.05 | 12 | 3.5752 |
| 2.9122 | 0.1 | 24 | 2.9222 |
| 2.1061 | 0.15 | 36 | 1.9585 |
| 1.6265 | 0.2 | 48 | 1.5771 |
| 1.3155 | 0.25 | 60 | 1.3177 |
| 1.1793 | 0.3 | 72 | 1.1780 |
| 1.0208 | 0.35 | 84 | 1.0613 |
| 0.9111 | 0.4 | 96 | 0.9361 |
| 0.8078 | 0.44 | 108 | 0.7634 |
| 0.6103 | 0.49 | 120 | 0.4794 |
| 0.3911 | 0.54 | 132 | 0.2857 |
| 0.324 | 0.59 | 144 | 0.2915 |
| 0.3228 | 0.64 | 156 | 0.2858 |
| 0.3103 | 0.69 | 168 | 0.2778 |
| 0.3458 | 0.74 | 180 | 0.2750 |
| 0.3283 | 0.79 | 192 | 0.2738 |
| 0.394 | 0.84 | 204 | 0.2728 |
| 0.3181 | 0.89 | 216 | 0.2711 |
| 0.3201 | 0.94 | 228 | 0.2704 |
| 0.3291 | 0.99 | 240 | 0.2705 |
| 0.3084 | 1.04 | 252 | 0.2709 |
| 0.32 | 1.09 | 264 | 0.2711 |
| 0.363 | 1.14 | 276 | 0.2708 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- peft
- License
- apache-2.0
- Languages
- id
- Created
- Mar 24, 2024
- Updated
- Mar 24, 2024