Downloads · 30 days
35
12% of all-time downloads
hBERTv1_new_pretrain_w_init__qqp
gokuls/hBERTv1_new_pretrain_w_init__qqp
hBERTv1_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
294
Public
Repo size
8.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin481 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- hybridbert
- Access
- Public
- Created
- May 31, 2023
- Updated
- Jun 6, 2023
- SHA
- de06f6c9
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. -->
hBERTv1_new_pretrain_w_init__qqp
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.3996
- Accuracy: 0.8135
- F1: 0.7339
- 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 |
|---|---|---|---|---|---|---|
| 0.5075 | 1.0 | 2843 | 0.4451 | 0.7864 | 0.7172 | 0.7518 |
| 0.4118 | 2.0 | 5686 | 0.4144 | 0.8052 | 0.7377 | 0.7715 |
| 0.3583 | 3.0 | 8529 | 0.3996 | 0.8135 | 0.7339 | 0.7737 |
| 0.3174 | 4.0 | 11372 | 0.4160 | 0.8195 | 0.7566 | 0.7880 |
| 0.2918 | 5.0 | 14215 | 0.4424 | 0.8142 | 0.7633 | 0.7888 |
| 0.2769 | 6.0 | 17058 | 0.4765 | 0.8195 | 0.7583 | 0.7889 |
| 0.2576 | 7.0 | 19901 | 0.4033 | 0.8237 | 0.7675 | 0.7956 |
| 0.2327 | 8.0 | 22744 | 0.4414 | 0.8279 | 0.7682 | 0.7981 |
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
- May 31, 2023
- Updated
- Jun 6, 2023