Downloads · 30 days
1
4% of all-time downloads
4_BiasDetctor_HTW_ANG.KI
Ghazi-nak/4_BiasDetctor_HTW_ANG.KI
4_BiasDetctor_HTW_ANG.KI is a text classification model from Ghazi-nak. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
25
Public
Parameters
355M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Apr 29, 2025
- Updated
- Apr 29, 2025
- SHA
- 1f39cdb4
Try a prompt
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. -->
4_BiasDetctor_HTW_ANG.KI
This model is a fine-tuned version of roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6007
- Accuracy: 0.9018
- F1: 0.9023
- Precision: 0.9047
- Recall: 0.9018
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- 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: cosine
- lr_scheduler_warmup_steps: 300
- num_epochs: 15
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 1.0644 | 0.1 | 250 | 0.8163 | 0.8038 | 0.8074 | 0.8311 | 0.8038 |
| 0.8034 | 0.2 | 500 | 0.7662 | 0.8178 | 0.8188 | 0.8319 | 0.8178 |
| 0.7396 | 0.3 | 750 | 0.7053 | 0.8502 | 0.8506 | 0.8529 | 0.8502 |
| 0.6945 | 0.4 | 1000 | 0.6885 | 0.8657 | 0.8670 | 0.8747 | 0.8657 |
| 0.6836 | 0.5 | 1250 | 0.6513 | 0.8772 | 0.8782 | 0.8832 | 0.8772 |
| 0.6412 | 0.6 | 1500 | 0.6437 | 0.8873 | 0.8879 | 0.8900 | 0.8873 |
| 0.6363 | 0.7 | 1750 | 0.6284 | 0.8895 | 0.8899 | 0.8913 | 0.8895 |
| 0.6388 | 0.8 | 2000 | 0.6370 | 0.8866 | 0.8871 | 0.8912 | 0.8866 |
| 0.6547 | 0.9 | 2250 | 0.6280 | 0.8936 | 0.8945 | 0.8999 | 0.8936 |
| 0.6239 | 1.0 | 2500 | 0.6007 | 0.9018 | 0.9023 | 0.9047 | 0.9018 |
| 0.5927 | 1.1 | 2750 | 0.6481 | 0.8986 | 0.8994 | 0.9040 | 0.8986 |
| 0.5956 | 1.2 | 3000 | 0.6580 | 0.8921 | 0.8923 | 0.8981 | 0.8921 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.5.1
- Tokenizers 0.21.1
more info
TrainOutput(global_step=3000, training_loss=0.7137984479268392, metrics={'train_runtime': 1499.0616, 'train_samples_per_second': 400.25, 'train_steps_per_second': 25.016, 'total_flos': 1.1183289716736e+16, 'train_loss': 0.7137984479268392, 'epoch': 1.2})
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- Created
- Apr 29, 2025
- Updated
- Apr 29, 2025