Downloads · 30 days
6
16% of all-time downloads
bert_base_lda_100_wnli
gokulsrinivasagan/bert_base_lda_100_wnli
bert_base_lda_100_wnli 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
37
Public
Parameters
109M
876 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Nov 22, 2024
- Updated
- Nov 22, 2024
- SHA
- 4abf9b97
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. -->
bert_base_lda_100_wnli
This model is a fine-tuned version of gokulsrinivasagan/bert_base_lda_100 on the GLUE WNLI dataset. It achieves the following results on the evaluation set:
- Loss: 0.6841
- Accuracy: 0.5634
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: 0.001
- 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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1124 | 1.0 | 3 | 2.0924 | 0.5634 |
| 1.427 | 2.0 | 6 | 0.8691 | 0.5634 |
| 0.8115 | 3.0 | 9 | 0.7052 | 0.4366 |
| 0.7439 | 4.0 | 12 | 0.7183 | 0.5634 |
| 0.7195 | 5.0 | 15 | 0.8258 | 0.4366 |
| 0.7442 | 6.0 | 18 | 0.6925 | 0.5634 |
| 0.7511 | 7.0 | 21 | 0.6906 | 0.5634 |
| 0.6954 | 8.0 | 24 | 0.7698 | 0.4366 |
| 0.7343 | 9.0 | 27 | 0.7089 | 0.4366 |
| 0.7013 | 10.0 | 30 | 0.6874 | 0.5634 |
| 0.6997 | 11.0 | 33 | 0.6966 | 0.4366 |
| 0.7026 | 12.0 | 36 | 0.7131 | 0.4366 |
| 0.6988 | 13.0 | 39 | 0.6886 | 0.5634 |
| 0.6934 | 14.0 | 42 | 0.6841 | 0.5634 |
| 0.701 | 15.0 | 45 | 0.6867 | 0.5634 |
| 0.6928 | 16.0 | 48 | 0.6945 | 0.4366 |
| 0.6941 | 17.0 | 51 | 0.6947 | 0.4366 |
| 0.6949 | 18.0 | 54 | 0.6901 | 0.5634 |
| 0.6932 | 19.0 | 57 | 0.6904 | 0.5634 |
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
- Languages
- en
- Created
- Nov 22, 2024
- Updated
- Nov 22, 2024