Downloads · 30 days
4
25% of all-time downloads
langtok-mt5small
emmabedna/langtok-mt5small
langtok-mt5small is a token classification model from emmabedna. 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
16
Public
Parameters
172M
4.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors689 MB · 97%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- mt5
- Access
- Public
- Created
- Oct 8, 2025
- Updated
- Oct 8, 2025
- SHA
- 97f21d52
Try a prompt
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. -->
langtok-mt5small
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1115
- Precision: 0.5238
- Recall: 0.5227
- F1: 0.5233
- Accuracy: 0.9686
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.6198 | 1.0 | 1708 | 0.2441 | 0.3706 | 0.3268 | 0.3473 | 0.9504 |
| 0.2093 | 2.0 | 3416 | 0.1294 | 0.4930 | 0.4829 | 0.4879 | 0.9653 |
| 0.1574 | 3.0 | 5124 | 0.1115 | 0.5238 | 0.5227 | 0.5233 | 0.9686 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.7.1+cu126
- Datasets 3.0.1
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- mt5
- Created
- Oct 8, 2025
- Updated
- Oct 8, 2025