Downloads · 30 days
6
11% of all-time downloads
distilbert_lda_100_v1_stsb
gokulsrinivasagan/distilbert_lda_100_v1_stsb
distilbert_lda_100_v1_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
55
Public
Parameters
67M
1.3 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
- Nov 26, 2024
- Updated
- Dec 4, 2024
- SHA
- d9193250
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_stsb
This model is a fine-tuned version of gokulsrinivasagan/distilbert_lda_100_v1 on the GLUE STSB dataset. It achieves the following results on the evaluation set:
- Loss: 0.9153
- Pearson: 0.7758
- Spearmanr: 0.7704
- Combined Score: 0.7731
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 |
|---|---|---|---|---|---|---|
| 2.622 | 1.0 | 23 | 2.5298 | 0.1011 | 0.0891 | 0.0951 |
| 1.8404 | 2.0 | 46 | 2.3343 | 0.4642 | 0.4648 | 0.4645 |
| 1.3143 | 3.0 | 69 | 1.2509 | 0.6736 | 0.6670 | 0.6703 |
| 0.8809 | 4.0 | 92 | 1.3874 | 0.7172 | 0.7254 | 0.7213 |
| 0.6317 | 5.0 | 115 | 1.5835 | 0.7091 | 0.7238 | 0.7164 |
| 0.5139 | 6.0 | 138 | 1.2793 | 0.7443 | 0.7470 | 0.7456 |
| 0.3919 | 7.0 | 161 | 1.0238 | 0.7576 | 0.7535 | 0.7556 |
| 0.3125 | 8.0 | 184 | 1.4519 | 0.7331 | 0.7349 | 0.7340 |
| 0.281 | 9.0 | 207 | 1.2564 | 0.7390 | 0.7374 | 0.7382 |
| 0.2395 | 10.0 | 230 | 0.9153 | 0.7758 | 0.7704 | 0.7731 |
| 0.2219 | 11.0 | 253 | 1.2411 | 0.7509 | 0.7509 | 0.7509 |
| 0.1923 | 12.0 | 276 | 1.5144 | 0.7429 | 0.7444 | 0.7436 |
| 0.1688 | 13.0 | 299 | 1.0667 | 0.7518 | 0.7468 | 0.7493 |
| 0.1494 | 14.0 | 322 | 1.2371 | 0.7502 | 0.7483 | 0.7493 |
| 0.1498 | 15.0 | 345 | 1.1066 | 0.7473 | 0.7433 | 0.7453 |
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 26, 2024
- Updated
- Dec 4, 2024