Downloads · 30 days
6
29% of all-time downloads
distilbert_km_5_v1_mrpc
Hartunka/distilbert_km_5_v1_mrpc
distilbert_km_5_v1_mrpc 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
21
Public
Parameters
67M
804 MB 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 14, 2025
- Updated
- Apr 14, 2025
- SHA
- 37783b26
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_5_v1_mrpc
This model is a fine-tuned version of Hartunka/distilbert_km_5_v1 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5909
- Accuracy: 0.6838
- F1: 0.7956
- Combined Score: 0.7397
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 |
|---|---|---|---|---|---|---|
| 0.625 | 1.0 | 15 | 0.6060 | 0.6936 | 0.7961 | 0.7449 |
| 0.5537 | 2.0 | 30 | 0.5909 | 0.6838 | 0.7956 | 0.7397 |
| 0.4677 | 3.0 | 45 | 0.6478 | 0.7083 | 0.8065 | 0.7574 |
| 0.3598 | 4.0 | 60 | 0.7725 | 0.6544 | 0.7496 | 0.7020 |
| 0.2154 | 5.0 | 75 | 1.0573 | 0.5882 | 0.6842 | 0.6362 |
| 0.1138 | 6.0 | 90 | 1.1863 | 0.6691 | 0.7676 | 0.7184 |
| 0.0656 | 7.0 | 105 | 1.4887 | 0.6225 | 0.7354 | 0.6790 |
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 14, 2025
- Updated
- Apr 14, 2025