Downloads · 30 days
14
42% of all-time downloads
tinybert_train_book_v2_stsb
gokulsrinivasagan/tinybert_train_book_v2_stsb
tinybert_train_book_v2_stsb is a text classification model from gokulsrinivasagan. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
33
Public
Parameters
33M
659 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors132 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Jan 30, 2025
- Updated
- Jan 30, 2025
- SHA
- 388d48cf
Try a prompt
Base models
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. -->
tinybert_train_book_v2_stsb
This model is a fine-tuned version of gokulsrinivasagan/tinybert_train_book_v2 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 0.7733
- Pearson: 0.8119
- Spearmanr: 0.8095
- Combined Score: 0.8107
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
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Spearmanr | Combined Score |
|---|---|---|---|---|---|---|
| 3.0445 | 1.0 | 23 | 2.5260 | 0.0890 | 0.0888 | 0.0889 |
| 1.861 | 2.0 | 46 | 1.7447 | 0.5276 | 0.5175 | 0.5225 |
| 1.1901 | 3.0 | 69 | 1.1124 | 0.7331 | 0.7380 | 0.7356 |
| 0.8584 | 4.0 | 92 | 0.8622 | 0.7888 | 0.7846 | 0.7867 |
| 0.6948 | 5.0 | 115 | 0.9176 | 0.7912 | 0.7941 | 0.7927 |
| 0.5835 | 6.0 | 138 | 0.7733 | 0.8119 | 0.8095 | 0.8107 |
| 0.4936 | 7.0 | 161 | 0.8153 | 0.8118 | 0.8101 | 0.8110 |
| 0.4288 | 8.0 | 184 | 0.8134 | 0.8042 | 0.8021 | 0.8031 |
| 0.3747 | 9.0 | 207 | 0.8136 | 0.8064 | 0.8050 | 0.8057 |
| 0.3202 | 10.0 | 230 | 0.7878 | 0.8144 | 0.8125 | 0.8134 |
| 0.3003 | 11.0 | 253 | 0.8023 | 0.8134 | 0.8114 | 0.8124 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Languages
- en
- Created
- Jan 30, 2025
- Updated
- Jan 30, 2025