metadata
base_model: csebuetnlp/banglat5
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: banglat5-finetuned-headlineBT5_1000
results: []
banglat5-finetuned-headlineBT5_1000
This model is a fine-tuned version of csebuetnlp/banglat5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.4004
- Rouge1: 0.0
- Rouge2: 0.0
- Rougel: 0.0
- Rougelsum: 0.0
- Gen Len: 8.3188
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: 2e-05
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 160 | 8.7729 | 0.0 | 0.0 | 0.0 | 0.0 | 16.7688 |
| No log | 2.0 | 320 | 6.8254 | 0.0 | 0.0 | 0.0 | 0.0 | 13.6312 |
| No log | 3.0 | 480 | 5.8745 | 0.0 | 0.0 | 0.0 | 0.0 | 8.65 |
| 10.9912 | 4.0 | 640 | 5.4995 | 0.0 | 0.0 | 0.0 | 0.0 | 8.4625 |
| 10.9912 | 5.0 | 800 | 5.4004 | 0.0 | 0.0 | 0.0 | 0.0 | 8.3188 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2