Downloads · 30 days
10
22% of all-time downloads
spellcorrector_17_02_050_qwerty_v4
Buseak/spellcorrector_17_02_050_qwerty_v4
spellcorrector_17_02_050_qwerty_v4 is a token classification model from Buseak. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
46
Public
Parameters
132M
5.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors529 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- canine
- Access
- Public
- Created
- Feb 17, 2024
- Updated
- Feb 17, 2024
- SHA
- 4d507bbc
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. -->
spellcorrector_17_02_050_qwerty_v4
This model is a fine-tuned version of Buseak/spellcorrector_17_02_050_qwerty on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0036
- Precision: 0.9989
- Recall: 0.9995
- F1: 0.9992
- Accuracy: 0.9991
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: 8
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0368 | 1.0 | 967 | 0.0185 | 0.9935 | 0.9903 | 0.9919 | 0.9943 |
| 0.0329 | 2.0 | 1934 | 0.0159 | 0.9935 | 0.9887 | 0.9911 | 0.9952 |
| 0.0283 | 3.0 | 2901 | 0.0136 | 0.9952 | 0.9914 | 0.9933 | 0.9960 |
| 0.024 | 4.0 | 3868 | 0.0103 | 0.9952 | 0.9914 | 0.9933 | 0.9970 |
| 0.0209 | 5.0 | 4835 | 0.0090 | 0.9968 | 0.9936 | 0.9952 | 0.9973 |
| 0.0181 | 6.0 | 5802 | 0.0069 | 0.9978 | 0.9957 | 0.9968 | 0.9980 |
| 0.015 | 7.0 | 6769 | 0.0057 | 0.9989 | 0.9995 | 0.9992 | 0.9984 |
| 0.0132 | 8.0 | 7736 | 0.0045 | 0.9984 | 0.9995 | 0.9989 | 0.9988 |
| 0.0119 | 9.0 | 8703 | 0.0039 | 0.9989 | 0.9995 | 0.9992 | 0.9990 |
| 0.0104 | 10.0 | 9670 | 0.0036 | 0.9989 | 0.9995 | 0.9992 | 0.9991 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Task
- Token Classification
- Library
- transformers
- Type
- canine
- License
- apache-2.0
- Created
- Feb 17, 2024
- Updated
- Feb 17, 2024