Downloads · 30 days
5
14% of all-time downloads
liberta-large_ner
izaitova/liberta-large_ner
liberta-large_ner is a token classification model from izaitova. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as cc-by-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
36
Public
Parameters
336M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- cc-by-4.0
- Model type
- bert
- Access
- Public
- Created
- Sep 10, 2024
- Updated
- Sep 10, 2024
- SHA
- 8be91391
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. -->
liberta-large_ner
This model is a fine-tuned version of Goader/liberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3665
- Precision: 0.9206
- Recall: 0.9363
- F1: 0.9275
- Accuracy: 0.9548
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 438 | 0.2759 | 0.8856 | 0.9109 | 0.8963 | 0.9300 |
| 0.3117 | 2.0 | 876 | 0.2289 | 0.9165 | 0.9251 | 0.9201 | 0.9493 |
| 0.1293 | 3.0 | 1314 | 0.3084 | 0.9111 | 0.9205 | 0.9147 | 0.9465 |
| 0.0687 | 4.0 | 1752 | 0.2430 | 0.9171 | 0.9343 | 0.9249 | 0.9534 |
| 0.0399 | 5.0 | 2190 | 0.2581 | 0.9284 | 0.9334 | 0.9292 | 0.9564 |
| 0.0223 | 6.0 | 2628 | 0.2819 | 0.9258 | 0.9368 | 0.9301 | 0.9563 |
| 0.0149 | 7.0 | 3066 | 0.3421 | 0.9158 | 0.9354 | 0.9252 | 0.9527 |
| 0.005 | 8.0 | 3504 | 0.3694 | 0.9162 | 0.9337 | 0.9238 | 0.9527 |
| 0.005 | 9.0 | 3942 | 0.3357 | 0.9241 | 0.9387 | 0.9308 | 0.9563 |
| 0.0029 | 10.0 | 4380 | 0.3665 | 0.9206 | 0.9363 | 0.9275 | 0.9548 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- cc-by-4.0
- Created
- Sep 10, 2024
- Updated
- Sep 10, 2024