Downloads · 30 days
2
7% of all-time downloads
mms-oral-cancer
kpushpender/mms-oral-cancer
mms-oral-cancer is a machine learning model from kpushpender. 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 cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
30
Public
Repo size
402 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt63.1 MB · 50%
At a glance
- Library
- peft
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Apr 27, 2025
- Updated
- Apr 27, 2025
- SHA
- 8a73857f
Base models
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. -->
mms-oral-cancer
This model is a fine-tuned version of facebook/mms-1b-all on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7417
- Wer: 0.2858
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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- 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: 40
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.0596 | 0.9825 | 28 | 0.8590 | 0.3343 |
| 0.9545 | 1.9825 | 56 | 0.8381 | 0.3381 |
| 0.8534 | 2.9825 | 84 | 0.7718 | 0.3218 |
| 0.7965 | 3.9825 | 112 | 0.7800 | 0.3149 |
| 0.7944 | 4.9825 | 140 | 0.7759 | 0.3138 |
| 0.739 | 5.9825 | 168 | 0.7685 | 0.3017 |
| 0.7291 | 6.9825 | 196 | 0.7520 | 0.3055 |
| 0.7172 | 7.9825 | 224 | 0.7571 | 0.3024 |
| 0.6872 | 8.9825 | 252 | 0.7567 | 0.3007 |
| 0.66 | 9.9825 | 280 | 0.7533 | 0.2982 |
| 0.6916 | 10.9825 | 308 | 0.7458 | 0.2975 |
| 0.691 | 11.9825 | 336 | 0.7394 | 0.2979 |
| 0.6707 | 12.9825 | 364 | 0.7424 | 0.2920 |
| 0.6381 | 13.9825 | 392 | 0.7444 | 0.2885 |
| 0.6899 | 14.9825 | 420 | 0.7437 | 0.2889 |
| 0.6292 | 15.9825 | 448 | 0.7520 | 0.2899 |
| 0.6549 | 16.9825 | 476 | 0.7436 | 0.2837 |
| 0.6341 | 17.9825 | 504 | 0.7386 | 0.2847 |
| 0.6768 | 18.9825 | 532 | 0.7424 | 0.2854 |
| 0.637 | 19.9825 | 560 | 0.7417 | 0.2858 |
Framework versions
- PEFT 0.14.0
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0
- Library
- peft
- License
- cc-by-nc-4.0
- Created
- Apr 27, 2025
- Updated
- Apr 27, 2025