metadata
base_model: csebuetnlp/banglat5
tags:
- generated_from_trainer
model-index:
- name: filtered_annotated94k_banglat5
results: []
filtered_annotated94k_banglat5
This model is a fine-tuned version of csebuetnlp/banglat5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1241
- Val accuracy: 0.9387
- Gen Len: 2.6493
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: 300
- eval_batch_size: 32
- 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 | Val accuracy | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 253 | 0.1969 | 0.8979 | 2.6679 |
| 1.0947 | 2.0 | 506 | 0.1400 | 0.924 | 2.6558 |
| 1.0947 | 3.0 | 759 | 0.1280 | 0.9324 | 2.653 |
| 0.1281 | 4.0 | 1012 | 0.1250 | 0.9359 | 2.6522 |
| 0.1281 | 5.0 | 1265 | 0.1241 | 0.9387 | 2.6493 |
Framework versions
- Transformers 4.35.2
- Pytorch 1.13.1+cu117
- Datasets 2.17.0
- Tokenizers 0.15.1