Downloads · 30 days
14
29% of all-time downloads
hBERTv2_new_pretrain_w_init_48_qqp
gokuls/hBERTv2_new_pretrain_w_init_48_qqp
hBERTv2_new_pretrain_w_init_48_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
49
Public
Repo size
4.8 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
- 949d461c
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_48_qqp
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2_complete_training_new_wt_init_48 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.4082
- Accuracy: 0.8219
- F1: 0.7658
- Combined Score: 0.7939
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 |
|---|---|---|---|---|---|---|
| 0.5585 | 1.0 | 2843 | 0.5073 | 0.7522 | 0.6429 | 0.6976 |
| 0.4735 | 2.0 | 5686 | 0.4584 | 0.7848 | 0.6963 | 0.7405 |
| 0.4044 | 3.0 | 8529 | 0.4140 | 0.8074 | 0.7234 | 0.7654 |
| 0.3583 | 4.0 | 11372 | 0.4206 | 0.8058 | 0.7602 | 0.7830 |
| 0.3271 | 5.0 | 14215 | 0.4082 | 0.8219 | 0.7658 | 0.7939 |
| 0.2987 | 6.0 | 17058 | 0.4203 | 0.8177 | 0.7666 | 0.7921 |
| 0.3287 | 7.0 | 19901 | 0.4641 | 0.8124 | 0.7209 | 0.7667 |
| 0.3594 | 8.0 | 22744 | 0.4493 | 0.8010 | 0.7246 | 0.7628 |
| 0.3729 | 9.0 | 25587 | 0.4443 | 0.8047 | 0.7388 | 0.7718 |
| 0.3314 | 10.0 | 28430 | 0.4196 | 0.8132 | 0.7411 | 0.7771 |
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