Downloads · 30 days
8
22% of all-time downloads
distilbert_km_20_v1_qqp
Hartunka/distilbert_km_20_v1_qqp
distilbert_km_20_v1_qqp is a text classification model from Hartunka. 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
36
Public
Parameters
67M
1.9 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
- Apr 15, 2025
- Updated
- Apr 15, 2025
- SHA
- b30b9fce
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_km_20_v1_qqp
This model is a fine-tuned version of Hartunka/distilbert_km_20_v1 on the GLUE QQP dataset. It achieves the following results on the evaluation set:
- Loss: 0.3983
- Accuracy: 0.8152
- F1: 0.7476
- Combined Score: 0.7814
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 | F1 | Combined Score |
|---|---|---|---|---|---|---|
| 0.485 | 1.0 | 1422 | 0.4343 | 0.7906 | 0.6921 | 0.7413 |
| 0.3809 | 2.0 | 2844 | 0.3983 | 0.8152 | 0.7476 | 0.7814 |
| 0.307 | 3.0 | 4266 | 0.3997 | 0.8230 | 0.7683 | 0.7957 |
| 0.2452 | 4.0 | 5688 | 0.4376 | 0.8293 | 0.7561 | 0.7927 |
| 0.1961 | 5.0 | 7110 | 0.4592 | 0.8329 | 0.7672 | 0.8001 |
| 0.1568 | 6.0 | 8532 | 0.5182 | 0.8240 | 0.7739 | 0.7989 |
| 0.1273 | 7.0 | 9954 | 0.5558 | 0.8324 | 0.7772 | 0.8048 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- Languages
- en
- Created
- Apr 15, 2025
- Updated
- Apr 15, 2025