<!-- 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. -->
TaNER-500-indic_glue
This model is a fine-tuned version of livinNector/tabert-500 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2608
- Precision: 0.8035
- Recall: 0.8304
- F1: 0.8167
- Accuracy: 0.9169
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.5439 | 0.31 | 200 | 0.3597 | 0.7357 | 0.7286 | 0.7321 | 0.8817 |
0.3655 | 0.62 | 400 | 0.3258 | 0.7377 | 0.7877 | 0.7619 | 0.8928 |
0.3036 | 0.94 | 600 | 0.2912 | 0.7764 | 0.7973 | 0.7867 | 0.9049 |
0.2322 | 1.25 | 800 | 0.2731 | 0.7884 | 0.8205 | 0.8041 | 0.9114 |
0.1851 | 1.56 | 1000 | 0.2622 | 0.8005 | 0.8214 | 0.8109 | 0.9159 |
0.1773 | 1.88 | 1200 | 0.2608 | 0.8035 | 0.8304 | 0.8167 | 0.9169 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3