metadata
base_model: csebuetnlp/banglat5
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: banglat5-headline-trial-with-ES-batch16-2e-4-ep10
results: []
banglat5-headline-trial-with-ES-batch16-2e-4-ep10
This model is a fine-tuned version of csebuetnlp/banglat5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.8411
- Rouge1: 0.0
- Rouge2: 0.0
- Rougel: 0.0
- Rougelsum: 0.0
- Gen Len: 8.995
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
3.9163 | 1.0 | 202 | 3.1831 | 0.0 | 0.0 | 0.0 | 0.0 | 9.6873 |
3.0764 | 2.0 | 404 | 2.9729 | 0.0 | 0.0 | 0.0 | 0.0 | 8.273 |
2.763 | 3.0 | 606 | 2.8976 | 0.0 | 0.0 | 0.0 | 0.0 | 9.1266 |
2.3236 | 4.0 | 808 | 2.8411 | 0.0 | 0.0 | 0.0 | 0.0 | 8.995 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2