Downloads · 30 days
7
8% of all-time downloads
iter2-diacritized
lazymonster/iter2-diacritized
iter2-diacritized is a text classification model from lazymonster. 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
90
Public
Parameters
16.1M
516 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors64.5 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Dec 4, 2025
- Updated
- Dec 4, 2025
- SHA
- a4c667cb
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. -->
iter2-diacritized
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1624
- Accuracy: 0.6403
- F1 Macro: 0.6342
- Composite Score: 0.6338
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: 3e-05
- train_batch_size: 32
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Composite Score |
|---|---|---|---|---|---|---|
| 1.059 | 1.0 | 1601 | 1.2371 | 0.3785 | 0.2823 | 0.2366 |
| 0.6954 | 2.0 | 3202 | 1.0196 | 0.6226 | 0.6144 | 0.6144 |
| 0.6009 | 3.0 | 4803 | 1.0371 | 0.6468 | 0.6450 | 0.6450 |
| 0.5632 | 4.0 | 6404 | 1.0776 | 0.6479 | 0.6484 | 0.6484 |
| 0.5458 | 5.0 | 8005 | 1.1058 | 0.6524 | 0.6498 | 0.6498 |
| 0.5341 | 6.0 | 9606 | 1.1441 | 0.6468 | 0.6441 | 0.6441 |
| 0.5237 | 7.0 | 11207 | 1.1527 | 0.6464 | 0.6465 | 0.6465 |
| 0.5218 | 8.0 | 12808 | 1.1624 | 0.6403 | 0.6342 | 0.6338 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.4.1
- Tokenizers 0.21.2
- Task
- Text Classification
- Library
- transformers
- Type
- roberta
- License
- mit
- Created
- Dec 4, 2025
- Updated
- Dec 4, 2025