distilbert-base-multilingual-cased-indic_glue
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2873
- Precision: 0.8099
- Recall: 0.8251
- F1: 0.8175
- Accuracy: 0.9114
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 |
|---|---|---|---|---|---|---|---|
| 0.6012 | 0.31 | 200 | 0.3849 | 0.7566 | 0.7108 | 0.7330 | 0.8722 |
| 0.377 | 0.62 | 400 | 0.3365 | 0.7696 | 0.7837 | 0.7766 | 0.8886 |
| 0.3205 | 0.94 | 600 | 0.3093 | 0.7875 | 0.7864 | 0.7869 | 0.8961 |
| 0.2517 | 1.25 | 800 | 0.3050 | 0.8039 | 0.8131 | 0.8085 | 0.9050 |
| 0.2034 | 1.56 | 1000 | 0.2950 | 0.8129 | 0.8130 | 0.8130 | 0.9098 |
| 0.1968 | 1.88 | 1200 | 0.2873 | 0.8099 | 0.8251 | 0.8175 | 0.9114 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3