hing-mbert-finetuned-TRAC-DS
This model is a fine-tuned version of l3cube-pune/hing-mbert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3580
- Accuracy: 0.7018
- Precision: 0.6759
- Recall: 0.6722
- F1: 0.6737
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: 2.824279936868144e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 43
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.7111 | 2.0 | 1224 | 0.7772 | 0.6683 | 0.6695 | 0.6793 | 0.6558 |
0.3026 | 3.99 | 2448 | 1.3580 | 0.7018 | 0.6759 | 0.6722 | 0.6737 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.10.1+cu111
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 2