Downloads · 30 days
3
18% of all-time downloads
combined_model_4class
levshechter/combined_model_4class
combined_model_4class is a token classification model from levshechter. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
17
Public
Parameters
177M
5.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Sep 16, 2025
- Updated
- Sep 16, 2025
- SHA
- d3c73106
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. -->
combined_model_4class
This model is a fine-tuned version of OMRIDRORI/mbert-tibetan-continual-unicode-240k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3992
- Accuracy: 0.8837
- Proximity F1: 0.0493
- Proximity Recall: 0.1713
- Proximity Precision: 0.0319
- Exact Matches: 0.3643
- Missed Switches: 0.0310
- False Switches: 6.6667
- Matches At 1 Words: 0.0
- Matches At 2 Words: 0.0
- Matches At 3 Words: 0.0
- Matches At 4 Words: 0.0
- Matches At 5 Words: 0.0078
- Matches At 6 Words: 0.0
- Matches At 7 Words: 0.0
- Matches At 8 Words: 0.0
- Matches At 9 Words: 0.0
- Matches At 10 Words: 0.0
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Proximity F1 | Proximity Recall | Proximity Precision | Exact Matches | Missed Switches | False Switches | Matches At 1 Words | Matches At 2 Words | Matches At 3 Words | Matches At 4 Words | Matches At 5 Words | Matches At 6 Words | Matches At 7 Words | Matches At 8 Words | Matches At 9 Words | Matches At 10 Words |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.1158 | 4.8193 | 200 | 0.5707 | 0.9129 | 0.0374 | 0.0297 | 0.0646 | 0.0698 | 0.3333 | 0.2093 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.533 | 9.6386 | 400 | 0.3992 | 0.8837 | 0.0493 | 0.1713 | 0.0319 | 0.3643 | 0.0310 | 6.6667 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0078 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Sep 16, 2025
- Updated
- Sep 16, 2025