sewd_classifier
This model is a fine-tuned version of asapp/sew-d-tiny-100k-ft-ls100h on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2176
- Accuracy: 0.1578
- Precision: 0.1069
- Recall: 0.1578
- F1: 0.1011
- Binary: 0.4046
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Binary |
---|---|---|---|---|---|---|---|---|
No log | 0.86 | 50 | 4.3363 | 0.0340 | 0.0127 | 0.0340 | 0.0089 | 0.2745 |
4.403 | 1.72 | 100 | 4.0500 | 0.0364 | 0.0076 | 0.0364 | 0.0100 | 0.3073 |
4.1865 | 2.59 | 150 | 3.8094 | 0.0631 | 0.0352 | 0.0631 | 0.0271 | 0.3354 |
3.9457 | 3.45 | 200 | 3.6427 | 0.0777 | 0.0356 | 0.0777 | 0.0312 | 0.3507 |
3.791 | 4.31 | 250 | 3.5282 | 0.0947 | 0.0376 | 0.0947 | 0.0368 | 0.3604 |
3.6663 | 5.17 | 300 | 3.4610 | 0.1044 | 0.0790 | 0.1044 | 0.0529 | 0.3636 |
3.5798 | 6.03 | 350 | 3.3702 | 0.1238 | 0.0834 | 0.1238 | 0.0783 | 0.3801 |
3.5798 | 6.9 | 400 | 3.3180 | 0.1383 | 0.0987 | 0.1383 | 0.0915 | 0.3917 |
3.5087 | 7.76 | 450 | 3.2698 | 0.1578 | 0.1113 | 0.1578 | 0.1070 | 0.4046 |
3.4575 | 8.62 | 500 | 3.2399 | 0.1699 | 0.1264 | 0.1699 | 0.1176 | 0.4124 |
3.4108 | 9.48 | 550 | 3.2176 | 0.1578 | 0.1069 | 0.1578 | 0.1011 | 0.4046 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.15.1
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for fydhfzh/sewd_classifier
Base model
asapp/sew-d-tiny-100k-ft-ls100h
Finetuned
this model