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
results: []
idt5-base-qaqg
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: 1.9747
- Rouge1: 0.4128
- Rouge2: 0.2269
- Rougel: 0.3823
- Rougelsum: 0.3837
- Bleu: 0.1804
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 |
|---|---|---|---|---|---|---|---|---|
| 0.771 | 1.0 | 6000 | 1.3605 | 0.4130 | 0.2293 | 0.3840 | 0.3851 | 0.1819 |
| 0.4904 | 2.0 | 12000 | 1.5539 | 0.4183 | 0.2330 | 0.3885 | 0.3897 | 0.1837 |
| 0.3432 | 3.0 | 18000 | 1.7444 | 0.4093 | 0.2249 | 0.3797 | 0.3810 | 0.1768 |
| 0.2608 | 4.0 | 24000 | 1.8966 | 0.4149 | 0.2270 | 0.3834 | 0.3848 | 0.1805 |
| 0.2215 | 5.0 | 30000 | 1.9747 | 0.4128 | 0.2269 | 0.3823 | 0.3837 | 0.1804 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
- Datasets 3.0.2
- Tokenizers 0.20.1