metadata
library_name: transformers
license: apache-2.0
base_model: muchad/idt5-base
tags:
- generated_from_trainer
metrics:
- rouge
- bleu
model-index:
- name: idt5-base-qaqg_v3
results: []
idt5-base-qaqg_v3
This model is a fine-tuned version of muchad/idt5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3062
- Rouge1: 0.3601
- Rouge2: 0.1916
- Rougel: 0.3400
- Rougelsum: 0.3400
- Bleu: 0.1048
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu |
|---|---|---|---|---|---|---|---|---|
| 1.5911 | 1.0 | 4695 | 1.4095 | 0.3387 | 0.1717 | 0.3191 | 0.3191 | 0.0946 |
| 1.3763 | 2.0 | 9390 | 1.3437 | 0.3500 | 0.1839 | 0.3305 | 0.3304 | 0.1004 |
| 1.2634 | 3.0 | 14085 | 1.3158 | 0.3576 | 0.1892 | 0.3385 | 0.3385 | 0.1024 |
| 1.1552 | 4.0 | 18780 | 1.2977 | 0.3589 | 0.1889 | 0.3390 | 0.3391 | 0.1010 |
| 1.1018 | 5.0 | 23475 | 1.3062 | 0.3601 | 0.1916 | 0.3400 | 0.3400 | 0.1048 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
- Datasets 3.0.2
- Tokenizers 0.20.1