Downloads · 30 days
7
21% of all-time downloads
find_tune_bert_output
seriouspark/find_tune_bert_output
find_tune_bert_output is a token classification model from seriouspark. 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
34
Public
Parameters
14.1M
56.3 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors56.3 MB · 98%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- electra
- Access
- Public
- Created
- Mar 23, 2024
- Updated
- Mar 23, 2024
- SHA
- a21af785
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. -->
find_tune_bert_output
This model is a fine-tuned version of monologg/koelectra-small-v3-discriminator on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2110
- Overall Precision: 0.8468
- Overall Recall: 0.8561
- Overall F1: 0.8514
- Overall Accuracy: 0.9405
- Loc F1: 0.9090
- Org F1: 0.7685
- Per F1: 0.8477
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Loc F1 | Org F1 | Per F1 |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.2146 | 0.8 | 1000 | 0.2903 | 0.7632 | 0.8340 | 0.7970 | 0.9175 | 0.8729 | 0.6812 | 0.7966 |
| 0.2538 | 1.6 | 2000 | 0.2374 | 0.8183 | 0.8290 | 0.8236 | 0.9299 | 0.8940 | 0.7187 | 0.8178 |
| 0.2192 | 2.4 | 3000 | 0.2265 | 0.8246 | 0.8437 | 0.8340 | 0.9340 | 0.8956 | 0.7403 | 0.8322 |
| 0.1967 | 3.2 | 4000 | 0.2206 | 0.8261 | 0.8529 | 0.8393 | 0.9354 | 0.9047 | 0.7499 | 0.8290 |
| 0.1814 | 4.0 | 5000 | 0.2169 | 0.8371 | 0.8538 | 0.8453 | 0.9379 | 0.9057 | 0.7605 | 0.8388 |
| 0.1661 | 4.8 | 6000 | 0.2169 | 0.8403 | 0.8490 | 0.8446 | 0.9382 | 0.9050 | 0.7583 | 0.8378 |
| 0.1577 | 5.6 | 7000 | 0.2116 | 0.8413 | 0.8604 | 0.8507 | 0.9401 | 0.9088 | 0.7670 | 0.8472 |
| 0.1544 | 6.4 | 8000 | 0.2110 | 0.8468 | 0.8561 | 0.8514 | 0.9405 | 0.9090 | 0.7685 | 0.8477 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Token Classification
- Library
- transformers
- Type
- electra
- Created
- Mar 23, 2024
- Updated
- Mar 23, 2024