| | --- |
| | base_model: csebuetnlp/banglat5 |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - bleu |
| | model-index: |
| | - name: working |
| | results: [] |
| | --- |
| | |
| | <!-- 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. --> |
| |
|
| | # working |
| |
|
| | This model is a fine-tuned version of [csebuetnlp/banglat5](https://huggingface.co/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 |
| |
|
