Downloads · 30 days
11
34% of all-time downloads
hBERTv2_data_aug_stsb
gokuls/hBERTv2_data_aug_stsb
hBERTv2_data_aug_stsb 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
32
Public
Repo size
2.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin420 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- hybridbert
- Access
- Public
- Created
- Mar 5, 2023
- Updated
- Mar 5, 2023
- SHA
- f46642b0
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_data_aug_stsb
This model is a fine-tuned version of gokuls/bert_12_layer_model_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 2.1357
- Pearson: 0.5181
- Spearmanr: 0.5131
- Combined Score: 0.5156
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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 0.6302 | 1.0 | 1259 | 2.1357 | 0.5181 | 0.5131 | 0.5156 |
| 0.0973 | 2.0 | 2518 | 2.4678 | 0.4495 | 0.4283 | 0.4389 |
| 0.0514 | 3.0 | 3777 | 2.3102 | 0.4101 | 0.3922 | 0.4011 |
| 0.0384 | 4.0 | 5036 | 2.5410 | 0.4446 | 0.4376 | 0.4411 |
| 0.031 | 5.0 | 6295 | 2.4586 | 0.4091 | 0.3917 | 0.4004 |
| 0.0255 | 6.0 | 7554 | 2.5981 | 0.3998 | 0.3874 | 0.3936 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.10.1
- Tokenizers 0.13.2
- Task
- Text Classification
- Library
- transformers
- Type
- hybridbert
- Languages
- en
- Created
- Mar 5, 2023
- Updated
- Mar 5, 2023