Downloads · 30 days
10
37% of all-time downloads
bert_base_lda_stsb
gokulsrinivasagan/bert_base_lda_stsb
bert_base_lda_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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
27
Public
Parameters
109M
3.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Nov 22, 2024
- Updated
- Dec 4, 2024
- SHA
- 7ee47766
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_base_lda_stsb
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 1.6844
- Pearson: 0.5377
- Spearmanr: 0.5310
- Combined Score: 0.5344
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 |
|---|---|---|---|---|---|---|
| 2.6177 | 1.0 | 23 | 2.5040 | 0.0492 | 0.0656 | 0.0574 |
| 1.9612 | 2.0 | 46 | 2.0348 | 0.3695 | 0.3669 | 0.3682 |
| 1.5453 | 3.0 | 69 | 2.0887 | 0.4294 | 0.4268 | 0.4281 |
| 1.1331 | 4.0 | 92 | 2.0548 | 0.4989 | 0.5093 | 0.5041 |
| 0.8134 | 5.0 | 115 | 1.8755 | 0.4933 | 0.4930 | 0.4931 |
| 0.7478 | 6.0 | 138 | 2.0804 | 0.5093 | 0.5092 | 0.5093 |
| 0.5429 | 7.0 | 161 | 1.9448 | 0.5262 | 0.5261 | 0.5261 |
| 0.4469 | 8.0 | 184 | 1.8867 | 0.5136 | 0.5118 | 0.5127 |
| 0.4011 | 9.0 | 207 | 1.8538 | 0.5243 | 0.5185 | 0.5214 |
| 0.3255 | 10.0 | 230 | 1.8652 | 0.5373 | 0.5320 | 0.5346 |
| 0.271 | 11.0 | 253 | 2.0402 | 0.5128 | 0.5043 | 0.5085 |
| 0.2699 | 12.0 | 276 | 1.8057 | 0.5305 | 0.5241 | 0.5273 |
| 0.2086 | 13.0 | 299 | 1.8275 | 0.5225 | 0.5190 | 0.5207 |
| 0.1951 | 14.0 | 322 | 2.0355 | 0.5140 | 0.5076 | 0.5108 |
| 0.1875 | 15.0 | 345 | 1.7243 | 0.5372 | 0.5323 | 0.5347 |
| 0.17 | 16.0 | 368 | 1.7595 | 0.5392 | 0.5342 | 0.5367 |
| 0.149 | 17.0 | 391 | 1.7326 | 0.5433 | 0.5387 | 0.5410 |
| 0.1476 | 18.0 | 414 | 1.6844 | 0.5377 | 0.5310 | 0.5344 |
| 0.127 | 19.0 | 437 | 1.7534 | 0.5277 | 0.5208 | 0.5242 |
| 0.1217 | 20.0 | 460 | 1.9471 | 0.5275 | 0.5187 | 0.5231 |
| 0.1182 | 21.0 | 483 | 1.8289 | 0.5323 | 0.5242 | 0.5282 |
| 0.0989 | 22.0 | 506 | 1.8270 | 0.5209 | 0.5128 | 0.5168 |
| 0.1017 | 23.0 | 529 | 1.8574 | 0.5309 | 0.5219 | 0.5264 |
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
- distilbert
- Languages
- en
- Created
- Nov 22, 2024
- Updated
- Dec 4, 2024