<!-- 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. -->
punjab_bert
This model is a fine-tuned version of l3cube-pune/punjabi-bert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.7311
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: 0.0005
- 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: 7
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.8977 | 1.0 | 998 | 3.7757 |
3.7502 | 2.0 | 1996 | 3.7404 |
3.7475 | 3.0 | 2994 | 3.7493 |
3.7423 | 4.0 | 3992 | 3.7376 |
3.731 | 5.0 | 4990 | 3.7338 |
3.7254 | 6.0 | 5988 | 3.7195 |
3.7213 | 7.0 | 6986 | 3.7129 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3