Downloads · 30 days
21
42% of all-time downloads
distilbert_lda_100_v1_book_stsb
gokulsrinivasagan/distilbert_lda_100_v1_book_stsb
distilbert_lda_100_v1_book_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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
50
Public
Parameters
67M
1.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors268 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Dec 9, 2024
- Updated
- Dec 9, 2024
- SHA
- 1cbc8dfd
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. -->
distilbert_lda_100_v1_book_stsb
This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_100_v1_book on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 0.7981
- Pearson: 0.8060
- Spearmanr: 0.8014
- Combined Score: 0.8037
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 OptimizerNames.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 |
|---|---|---|---|---|---|---|
| 3.1376 | 1.0 | 23 | 2.3444 | 0.1800 | 0.1657 | 0.1729 |
| 1.571 | 2.0 | 46 | 1.4977 | 0.6469 | 0.6552 | 0.6511 |
| 1.0298 | 3.0 | 69 | 0.9940 | 0.7483 | 0.7462 | 0.7472 |
| 0.8795 | 4.0 | 92 | 1.0649 | 0.7622 | 0.7710 | 0.7666 |
| 0.6951 | 5.0 | 115 | 1.5036 | 0.7508 | 0.7848 | 0.7678 |
| 0.5558 | 6.0 | 138 | 0.9067 | 0.7878 | 0.7914 | 0.7896 |
| 0.4306 | 7.0 | 161 | 0.8333 | 0.8051 | 0.8039 | 0.8045 |
| 0.3592 | 8.0 | 184 | 0.9582 | 0.7967 | 0.7975 | 0.7971 |
| 0.2847 | 9.0 | 207 | 1.0402 | 0.7929 | 0.7954 | 0.7942 |
| 0.2689 | 10.0 | 230 | 0.7981 | 0.8060 | 0.8014 | 0.8037 |
| 0.2368 | 11.0 | 253 | 0.8628 | 0.8101 | 0.8083 | 0.8092 |
| 0.2088 | 12.0 | 276 | 1.0529 | 0.7991 | 0.8011 | 0.8001 |
| 0.1912 | 13.0 | 299 | 0.8878 | 0.8011 | 0.8013 | 0.8012 |
| 0.1618 | 14.0 | 322 | 0.8757 | 0.7959 | 0.7943 | 0.7951 |
| 0.1557 | 15.0 | 345 | 0.8971 | 0.8001 | 0.7979 | 0.7990 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.2.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- Languages
- en
- Created
- Dec 9, 2024
- Updated
- Dec 9, 2024