Downloads · 30 days
8
20% of all-time downloads
herbert-large-cased_ner
izaitova/herbert-large-cased_ner
herbert-large-cased_ner is a machine learning model from izaitova. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
40
Public
Parameters
354M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- License
- cc-by-4.0
- Model type
- bert
- Access
- Public
- Created
- Aug 9, 2024
- Updated
- Aug 9, 2024
- SHA
- a091d9ac
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. -->
herbert-large-cased_ner
This model is a fine-tuned version of allegro/herbert-large-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3281
- Precision: 0.9354
- Recall: 0.9326
- F1: 0.9337
- Accuracy: 0.9598
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 | 0.2556 | 0.8915 | 0.8923 | 0.8918 | 0.9369 |
| 0.311 | 2.0 | 876 | 0.1920 | 0.9101 | 0.9107 | 0.9102 | 0.9473 |
| 0.1466 | 3.0 | 1314 | 0.2481 | 0.9050 | 0.9058 | 0.9048 | 0.9442 |
| 0.093 | 4.0 | 1752 | 0.2565 | 0.9187 | 0.9276 | 0.9229 | 0.9537 |
| 0.0584 | 5.0 | 2190 | 0.2620 | 0.9216 | 0.9306 | 0.9260 | 0.9543 |
| 0.037 | 6.0 | 2628 | 0.2891 | 0.9263 | 0.9310 | 0.9282 | 0.9533 |
| 0.0169 | 7.0 | 3066 | 0.3159 | 0.9288 | 0.9314 | 0.9300 | 0.9564 |
| 0.0123 | 8.0 | 3504 | 0.3317 | 0.9359 | 0.9348 | 0.9345 | 0.9606 |
| 0.0123 | 9.0 | 3942 | 0.3097 | 0.9357 | 0.9305 | 0.9327 | 0.9594 |
| 0.0048 | 10.0 | 4380 | 0.3281 | 0.9354 | 0.9326 | 0.9337 | 0.9598 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Type
- bert
- License
- cc-by-4.0
- Created
- Aug 9, 2024
- Updated
- Aug 9, 2024