Downloads · 30 days
11
26% of all-time downloads
tinybert_base_train_book_ent_15p_s_init_kd_complete_mnli
gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init_kd_complete_mnli
tinybert_base_train_book_ent_15p_s_init_kd_complete_mnli 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
42
Public
Parameters
28.8M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors115 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jun 15, 2025
- Updated
- Jun 15, 2025
- SHA
- fea9f051
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_base_train_book_ent_15p_s_init_kd_complete_mnli
This model is a fine-tuned version of gokulsrinivasagan/tinybert_base_train_book_ent_15p_s_init_kd_complete on the GLUE MNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.5911
- Accuracy: 0.7631
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 | Accuracy |
|---|---|---|---|---|
| 0.7566 | 1.0 | 1534 | 0.6799 | 0.7186 |
| 0.6322 | 2.0 | 3068 | 0.6413 | 0.7379 |
| 0.5681 | 3.0 | 4602 | 0.6223 | 0.7451 |
| 0.5157 | 4.0 | 6136 | 0.6184 | 0.7565 |
| 0.4699 | 5.0 | 7670 | 0.6115 | 0.7620 |
| 0.4266 | 6.0 | 9204 | 0.6486 | 0.7614 |
| 0.3871 | 7.0 | 10738 | 0.6570 | 0.7572 |
| 0.3532 | 8.0 | 12272 | 0.7183 | 0.7556 |
| 0.3191 | 9.0 | 13806 | 0.7695 | 0.7533 |
| 0.2903 | 10.0 | 15340 | 0.7822 | 0.7545 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- en
- Created
- Jun 15, 2025
- Updated
- Jun 15, 2025