Downloads · 30 days
6
3% of all-time downloads
hBERTv1_new_pretrain_48_emb_com_qqp
gokuls/hBERTv1_new_pretrain_48_emb_com_qqp
hBERTv1_new_pretrain_48_emb_com_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
206
Public
Repo size
4.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin402 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- hybridbert
- Access
- Public
- Created
- Jun 14, 2023
- Updated
- Jun 15, 2023
- SHA
- 8dd1afce
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_48_emb_com_qqp
This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_emb_compress_48 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.4383
- Accuracy: 0.7895
- F1: 0.7288
- Combined Score: 0.7591
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 |
|---|---|---|---|---|---|---|
| 0.5492 | 1.0 | 2843 | 0.5130 | 0.7537 | 0.6393 | 0.6965 |
| 0.4928 | 2.0 | 5686 | 0.4971 | 0.7602 | 0.6526 | 0.7064 |
| 0.4578 | 3.0 | 8529 | 0.4656 | 0.7775 | 0.6825 | 0.7300 |
| 0.4346 | 4.0 | 11372 | 0.4565 | 0.7804 | 0.6744 | 0.7274 |
| 0.4146 | 5.0 | 14215 | 0.4783 | 0.7812 | 0.7078 | 0.7445 |
| 0.3952 | 6.0 | 17058 | 0.4675 | 0.7899 | 0.7042 | 0.7470 |
| 0.3747 | 7.0 | 19901 | 0.4383 | 0.7895 | 0.7288 | 0.7591 |
| 0.355 | 8.0 | 22744 | 0.4455 | 0.7948 | 0.7053 | 0.7500 |
| 0.3362 | 9.0 | 25587 | 0.4483 | 0.7935 | 0.7334 | 0.7635 |
| 0.3185 | 10.0 | 28430 | 0.4480 | 0.7956 | 0.7388 | 0.7672 |
| 0.301 | 11.0 | 31273 | 0.4630 | 0.8055 | 0.7236 | 0.7646 |
| 0.2848 | 12.0 | 34116 | 0.4850 | 0.8062 | 0.7352 | 0.7707 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- hybridbert
- Languages
- en
- Created
- Jun 14, 2023
- Updated
- Jun 15, 2023