Downloads · 30 days
5
19% of all-time downloads
bert_base_km_50_v2_mrpc
Hartunka/bert_base_km_50_v2_mrpc
bert_base_km_50_v2_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
27
Public
Parameters
109M
1.8 GB 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
- Apr 23, 2025
- Updated
- Apr 23, 2025
- SHA
- 7854855a
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_km_50_v2_mrpc
This model is a fine-tuned version of Hartunka/bert_base_km_50_v2 on the GLUE MRPC dataset. It achieves the following results on the evaluation set:
- Loss: 0.5949
- Accuracy: 0.7132
- F1: 0.8208
- Combined Score: 0.7670
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 |
|---|---|---|---|---|---|---|
| 0.6303 | 1.0 | 15 | 0.6091 | 0.6838 | 0.7988 | 0.7413 |
| 0.5743 | 2.0 | 30 | 0.5949 | 0.7132 | 0.8208 | 0.7670 |
| 0.5186 | 3.0 | 45 | 0.6003 | 0.7010 | 0.8117 | 0.7564 |
| 0.4417 | 4.0 | 60 | 0.6426 | 0.6765 | 0.7724 | 0.7244 |
| 0.3244 | 5.0 | 75 | 0.7228 | 0.6691 | 0.7532 | 0.7112 |
| 0.2037 | 6.0 | 90 | 0.8417 | 0.6789 | 0.7665 | 0.7227 |
| 0.1058 | 7.0 | 105 | 1.0139 | 0.6716 | 0.7607 | 0.7161 |
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 23, 2025
- Updated
- Apr 23, 2025