Downloads · 30 days
5
14% of all-time downloads
bert_uncased_L-2_H-256_A-4_stsb
gokulsrinivasagan/bert_uncased_L-2_H-256_A-4_stsb
bert_uncased_L-2_H-256_A-4_stsb is a text classification model from gokulsrinivasagan. 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
37
Public
Parameters
9.6M
422 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors38.4 MB · 97%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Dec 4, 2024
- Updated
- Dec 4, 2024
- SHA
- 567bef93
Try a prompt
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. -->
bert_uncased_L-2_H-256_A-4_stsb
This model is a fine-tuned version of google/bert_uncased_L-2_H-256_A-4 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 0.6440
- Pearson: 0.8507
- Spearmanr: 0.8479
- Combined Score: 0.8493
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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- 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
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 6.8258 | 1.0 | 23 | 3.3322 | 0.1922 | 0.1781 | 0.1851 |
| 3.0892 | 2.0 | 46 | 2.2069 | 0.6152 | 0.5994 | 0.6073 |
| 2.0898 | 3.0 | 69 | 1.7703 | 0.7189 | 0.6773 | 0.6981 |
| 1.4102 | 4.0 | 92 | 1.0357 | 0.7469 | 0.7387 | 0.7428 |
| 0.984 | 5.0 | 115 | 0.9263 | 0.7887 | 0.8082 | 0.7985 |
| 0.8202 | 6.0 | 138 | 0.7993 | 0.8138 | 0.8193 | 0.8166 |
| 0.7105 | 7.0 | 161 | 0.8494 | 0.8163 | 0.8249 | 0.8206 |
| 0.6584 | 8.0 | 184 | 0.7529 | 0.8301 | 0.8352 | 0.8327 |
| 0.6204 | 9.0 | 207 | 0.7247 | 0.8368 | 0.8399 | 0.8383 |
| 0.5581 | 10.0 | 230 | 0.6988 | 0.8414 | 0.8430 | 0.8422 |
| 0.532 | 11.0 | 253 | 0.8075 | 0.8374 | 0.8422 | 0.8398 |
| 0.5051 | 12.0 | 276 | 0.7243 | 0.8421 | 0.8431 | 0.8426 |
| 0.4731 | 13.0 | 299 | 0.6760 | 0.8458 | 0.8438 | 0.8448 |
| 0.445 | 14.0 | 322 | 0.7161 | 0.8459 | 0.8452 | 0.8455 |
| 0.4192 | 15.0 | 345 | 0.6626 | 0.8489 | 0.8468 | 0.8478 |
| 0.405 | 16.0 | 368 | 0.7449 | 0.8458 | 0.8463 | 0.8460 |
| 0.3962 | 17.0 | 391 | 0.6440 | 0.8507 | 0.8479 | 0.8493 |
| 0.3683 | 18.0 | 414 | 0.6780 | 0.8490 | 0.8468 | 0.8479 |
| 0.3479 | 19.0 | 437 | 0.6729 | 0.8492 | 0.8466 | 0.8479 |
| 0.3434 | 20.0 | 460 | 0.6733 | 0.8486 | 0.8453 | 0.8470 |
| 0.3471 | 21.0 | 483 | 0.6503 | 0.8488 | 0.8450 | 0.8469 |
| 0.3221 | 22.0 | 506 | 0.6581 | 0.8497 | 0.8467 | 0.8482 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- en
- Created
- Dec 4, 2024
- Updated
- Dec 4, 2024