Downloads · 30 days
11
5% of all-time downloads
hBERTv2_new_pretrain_w_init__qqp
gokuls/hBERTv2_new_pretrain_w_init__qqp
hBERTv2_new_pretrain_w_init__qqp is a text classification model from gokuls. 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
220
Public
Repo size
5.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin477 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- hybridbert
- Access
- Public
- Created
- Jun 6, 2023
- Updated
- Jun 6, 2023
- SHA
- 4e821cee
Try a prompt
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. -->
hBERTv2_new_pretrain_w_init__qqp
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_wt_init on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.4228
- Accuracy: 0.8043
- F1: 0.7431
- Combined Score: 0.7737
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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.6243 | 1.0 | 2843 | 0.5630 | 0.7026 | 0.6300 | 0.6663 |
| 0.5301 | 2.0 | 5686 | 0.5110 | 0.7516 | 0.6346 | 0.6931 |
| 0.4804 | 3.0 | 8529 | 0.4928 | 0.7635 | 0.6780 | 0.7208 |
| 0.4419 | 4.0 | 11372 | 0.4610 | 0.7756 | 0.7173 | 0.7465 |
| 0.4105 | 5.0 | 14215 | 0.4441 | 0.7889 | 0.7347 | 0.7618 |
| 0.3819 | 6.0 | 17058 | 0.4336 | 0.8018 | 0.7207 | 0.7613 |
| 0.3534 | 7.0 | 19901 | 0.4228 | 0.8043 | 0.7431 | 0.7737 |
| 0.33 | 8.0 | 22744 | 0.4429 | 0.8062 | 0.7445 | 0.7754 |
| 0.3098 | 9.0 | 25587 | 0.4296 | 0.8104 | 0.7511 | 0.7807 |
| 0.2912 | 10.0 | 28430 | 0.4386 | 0.8086 | 0.7554 | 0.7820 |
| 0.275 | 11.0 | 31273 | 0.4551 | 0.8143 | 0.7575 | 0.7859 |
| 0.2575 | 12.0 | 34116 | 0.4742 | 0.8160 | 0.7491 | 0.7825 |
Framework versions
- Transformers 4.29.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- hybridbert
- Languages
- en
- Created
- Jun 6, 2023
- Updated
- Jun 6, 2023