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_v2
results: []
idt5-base-qaqg_v2
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: 1.4556
- Rouge1: 0.3955
- Rouge2: 0.2208
- Rougel: 0.3775
- Rougelsum: 0.3775
- Bleu: 0.1803
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 |
|---|---|---|---|---|---|---|---|---|
| 1.7409 | 1.0 | 6000 | 1.5167 | 0.3688 | 0.1975 | 0.3508 | 0.3508 | 0.1743 |
| 1.5199 | 2.0 | 12000 | 1.4764 | 0.3828 | 0.2118 | 0.3658 | 0.3659 | 0.1656 |
| 1.4226 | 3.0 | 18000 | 1.4606 | 0.3837 | 0.2107 | 0.3661 | 0.3663 | 0.1704 |
| 1.2556 | 4.0 | 24000 | 1.4559 | 0.3955 | 0.2214 | 0.3778 | 0.3777 | 0.1816 |
| 1.2196 | 5.0 | 30000 | 1.4556 | 0.3955 | 0.2208 | 0.3775 | 0.3775 | 0.1803 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
- Datasets 3.0.2
- Tokenizers 0.20.1