Downloads · 30 days
11
3% of all-time downloads
classifier-clinc-MBbase-distilled
Mathildeholst/classifier-clinc-MBbase-distilled
classifier-clinc-MBbase-distilled is a text classification model from Mathildeholst. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
358
Public
Parameters
150M
124 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt51.5 GB · 66%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- modernbert
- Access
- Public
- Created
- Oct 10, 2025
- Updated
- Oct 23, 2025
- SHA
- b7cd3f52
Try a prompt
Base models
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. -->
classifier-clinc-MBbase-distilled
This model is a fine-tuned version of answerdotai/ModernBERT-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7808
- Accuracy: 0.9506
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 313 | 2.9367 | 0.8661 |
| 6.6903 | 2.0 | 626 | 1.1788 | 0.9284 |
| 6.6903 | 3.0 | 939 | 0.9195 | 0.9432 |
| 0.7702 | 4.0 | 1252 | 0.8179 | 0.9471 |
| 0.387 | 5.0 | 1565 | 0.7808 | 0.9506 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Task
- Text Classification
- Library
- transformers
- Type
- modernbert
- License
- apache-2.0
- Created
- Oct 10, 2025
- Updated
- Oct 23, 2025