Downloads · 30 days
1
6% of all-time downloads
mdberta
MrKlaxen/mdberta
mdberta is a text classification model from MrKlaxen. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
18
Public
Parameters
184M
6.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors738 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- May 7, 2025
- Updated
- May 8, 2025
- SHA
- 8fd11de9
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. -->
mdberta
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5351
- Accuracy: 0.9056
- Precision: 0.9077
- Recall: 0.9030
- F1: 0.9054
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: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2926 | 1.0 | 1563 | 0.2550 | 0.8988 | 0.8854 | 0.9163 | 0.9006 |
| 0.2119 | 2.0 | 3126 | 0.2359 | 0.9092 | 0.9220 | 0.8939 | 0.9078 |
| 0.1672 | 3.0 | 4689 | 0.2632 | 0.9076 | 0.9240 | 0.8883 | 0.9058 |
| 0.1281 | 4.0 | 6252 | 0.2913 | 0.9098 | 0.9187 | 0.8992 | 0.9088 |
| 0.101 | 5.0 | 7815 | 0.3063 | 0.9075 | 0.9101 | 0.9043 | 0.9072 |
| 0.0793 | 6.0 | 9378 | 0.3577 | 0.9010 | 0.8897 | 0.9154 | 0.9024 |
| 0.0616 | 7.0 | 10941 | 0.4586 | 0.9051 | 0.9001 | 0.9114 | 0.9057 |
| 0.0492 | 8.0 | 12504 | 0.4240 | 0.9075 | 0.9093 | 0.9052 | 0.9073 |
| 0.0402 | 9.0 | 14067 | 0.5017 | 0.9064 | 0.9076 | 0.9050 | 0.9063 |
| 0.0328 | 10.0 | 15630 | 0.5351 | 0.9056 | 0.9077 | 0.9030 | 0.9054 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Task
- Text Classification
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Created
- May 7, 2025
- Updated
- May 8, 2025