pargraphs_titlesV1.1
This model is a fine-tuned version of AhmedTaha012/pargraphs_titlesV1.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2229
- Rouge1: 84.2042
- Rouge2: 76.5359
- Rougel: 84.1153
- Rougelsum: 84.1486
- Gen Len: 175797120.0
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: 2
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 40
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.272 | 0.99 | 39 | 0.2272 | 84.1593 | 76.3536 | 84.0811 | 84.1075 | 175797120.0 |
| 0.2515 | 2.0 | 79 | 0.2257 | 83.9867 | 76.2626 | 83.9091 | 83.8999 | 175797120.0 |
| 0.2481 | 2.99 | 118 | 0.2242 | 84.0786 | 76.436 | 84.0015 | 84.0158 | 175797119.0 |
| 0.2364 | 4.0 | 158 | 0.2232 | 84.198 | 76.5543 | 84.1214 | 84.1279 | 175797119.0 |
| 0.2369 | 4.99 | 197 | 0.2229 | 84.2428 | 76.5359 | 84.1617 | 84.188 | 175797120.0 |
| 0.2317 | 5.92 | 234 | 0.2229 | 84.2042 | 76.5359 | 84.1153 | 84.1486 | 175797120.0 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0