hing-mbert-finetuned-ours-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: 1.1569
- Accuracy: 0.71
- Precision: 0.6665
- Recall: 0.6668
- F1: 0.6658
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 |
---|---|---|---|---|---|---|---|
0.7704 | 1.99 | 199 | 0.7093 | 0.68 | 0.6679 | 0.6463 | 0.6309 |
0.2597 | 3.98 | 398 | 1.1569 | 0.71 | 0.6665 | 0.6668 | 0.6658 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.10.1+cu111
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 2