Downloads · 30 days
3
16% of all-time downloads
bert-hinglish-shared-task
FarhanAmin0068/bert-hinglish-shared-task
bert-hinglish-shared-task is a text classification model from FarhanAmin0068. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
19
Public
Parameters
167M
6.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors669 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 30, 2025
- Updated
- Mar 30, 2025
- SHA
- f4514c95
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. -->
bert-hinglish-shared-task
This model is a fine-tuned version of sam34738/bert-hinglish on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8893
- Precision: 0.6678
- Recall: 0.6626
- Accuracy: 0.7581
- F1: 0.6651
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use 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: 95
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1 |
|---|---|---|---|---|---|---|---|
| 0.6933 | 1.0 | 96 | 0.6847 | 0.5491 | 0.5642 | 0.5984 | 0.5396 |
| 0.6811 | 2.0 | 192 | 0.6201 | 0.6221 | 0.6581 | 0.6738 | 0.6220 |
| 0.5608 | 3.0 | 288 | 0.6682 | 0.6712 | 0.6402 | 0.7659 | 0.6509 |
| 0.4541 | 4.0 | 384 | 0.7216 | 0.6662 | 0.6355 | 0.7630 | 0.6459 |
| 0.3868 | 5.0 | 480 | 0.7191 | 0.6447 | 0.6698 | 0.7209 | 0.6521 |
| 0.2764 | 6.0 | 576 | 0.8893 | 0.6678 | 0.6626 | 0.7581 | 0.6651 |
| 0.2117 | 7.0 | 672 | 1.1178 | 0.6814 | 0.6510 | 0.7718 | 0.6619 |
| 0.168 | 8.0 | 768 | 1.3503 | 0.6904 | 0.6287 | 0.7777 | 0.6437 |
| 0.1117 | 9.0 | 864 | 1.4231 | 0.6607 | 0.6343 | 0.7591 | 0.6437 |
| 0.0967 | 10.0 | 960 | 1.4876 | 0.6621 | 0.6350 | 0.7600 | 0.6445 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Mar 30, 2025
- Updated
- Mar 30, 2025