working
This model is a fine-tuned version of csebuetnlp/banglat5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7567
- Bleu: 16.8754
- Gen Len: 11.7975
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: 16
- eval_batch_size: 16
- seed: 42
- 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 | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 450 | 1.7403 | 14.5679 | 11.9038 |
| 2.1563 | 2.0 | 900 | 1.6685 | 15.1417 | 11.7188 |
| 1.5765 | 3.0 | 1350 | 1.6712 | 16.0438 | 11.7525 |
| 1.2297 | 4.0 | 1800 | 1.7176 | 16.9394 | 11.8238 |
| 1.0072 | 5.0 | 2250 | 1.7567 | 16.8754 | 11.7975 |
Framework versions
- Transformers 4.37.0
- Pytorch 1.13.1+cu117
- Datasets 2.1.0
- Tokenizers 0.15.1
- Downloads last month
- 106
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for rabby33/working
Base model
csebuetnlp/banglat5