metadata
base_model: ka05ar/Banglat5_Dx1
tags:
- generated_from_trainer
model-index:
- name: wsdbanglat5_F2e4
results: []
wsdbanglat5_F2e4
This model is a fine-tuned version of ka05ar/Banglat5_Dx1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0006
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0439 | 1.0 | 1481 | 0.0486 |
| 0.0166 | 2.0 | 2962 | 0.3209 |
| 0.0088 | 3.0 | 4443 | 0.0056 |
| 0.0048 | 4.0 | 5924 | 0.0020 |
| 0.0023 | 5.0 | 7405 | 0.0011 |
| 0.0017 | 6.0 | 8886 | 0.0007 |
| 0.0011 | 7.0 | 10367 | 0.0007 |
| 0.0022 | 8.0 | 11848 | 0.0007 |
| 0.0007 | 9.0 | 13329 | 0.0006 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1