spellcorrector_11_02_050_1_per_word_v6
This model is a fine-tuned version of Buseak/spellcorrector_11_02_050_1_per_word_v5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0149
- Precision: 1.0
- Recall: 1.0
- F1: 1.0
- Accuracy: 0.9955
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: 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 |
---|---|---|---|---|---|---|---|
0.0704 | 1.0 | 967 | 0.0434 | 0.9946 | 0.9936 | 0.9941 | 0.9866 |
0.0636 | 2.0 | 1934 | 0.0385 | 0.9930 | 0.9941 | 0.9936 | 0.9881 |
0.0575 | 3.0 | 2901 | 0.0343 | 0.9979 | 0.9973 | 0.9976 | 0.9894 |
0.051 | 4.0 | 3868 | 0.0288 | 0.9984 | 0.9984 | 0.9984 | 0.9910 |
0.0473 | 5.0 | 4835 | 0.0243 | 0.9995 | 0.9995 | 0.9995 | 0.9922 |
0.043 | 6.0 | 5802 | 0.0223 | 0.9995 | 0.9995 | 0.9995 | 0.9931 |
0.0393 | 7.0 | 6769 | 0.0190 | 1.0 | 0.9984 | 0.9992 | 0.9941 |
0.0366 | 8.0 | 7736 | 0.0181 | 1.0 | 0.9989 | 0.9995 | 0.9945 |
0.0336 | 9.0 | 8703 | 0.0150 | 1.0 | 0.9995 | 0.9997 | 0.9954 |
0.0325 | 10.0 | 9670 | 0.0149 | 1.0 | 1.0 | 1.0 | 0.9955 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1
- Downloads last month
- 1
Inference API (serverless) is not available, repository is disabled.
Model tree for Buseak/spellcorrector_11_02_050_1_per_word_v6
Base model
google/canine-s
Finetuned
this model