<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
parrot_paraphraser_on_T5-finetuned-xsum-v0
This model is a fine-tuned version of prithivida/parrot_paraphraser_on_T5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4418
- Rouge1: 79.364
- Rouge2: 74.776
- Rougel: 78.997
- Rougelsum: 78.7013
- Gen Len: 18.6789
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 216 | 0.5427 | 79.4586 | 74.9115 | 78.8483 | 78.6557 | 18.6972 |
| No log | 2.0 | 432 | 0.4922 | 79.5229 | 74.8555 | 78.7762 | 78.5797 | 18.6881 |
| 0.5974 | 3.0 | 648 | 0.4628 | 79.4743 | 74.7622 | 78.7621 | 78.5631 | 18.6881 |
| 0.5974 | 4.0 | 864 | 0.4517 | 79.6842 | 75.2876 | 79.3457 | 79.0682 | 18.6881 |
| 0.4292 | 5.0 | 1080 | 0.4451 | 79.6571 | 75.2248 | 79.2939 | 79.0412 | 18.6881 |
| 0.4292 | 6.0 | 1296 | 0.4409 | 79.3363 | 74.6763 | 78.9595 | 78.7335 | 18.6789 |
| 0.3367 | 7.0 | 1512 | 0.4398 | 79.364 | 74.776 | 78.997 | 78.7013 | 18.6789 |
| 0.3367 | 8.0 | 1728 | 0.4407 | 79.364 | 74.776 | 78.997 | 78.7013 | 18.6789 |
| 0.3367 | 9.0 | 1944 | 0.4413 | 79.364 | 74.776 | 78.997 | 78.7013 | 18.6789 |
| 0.3012 | 10.0 | 2160 | 0.4418 | 79.364 | 74.776 | 78.997 | 78.7013 | 18.6789 |
Framework versions
- Transformers 4.22.0
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
