<!-- 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. -->
pegasus-xsum-prei-7k
This model is a fine-tuned version of google/pegasus-xsum on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5504
- Rouge2 Precision: 0.0
- Rouge2 Recall: 0.0
- Rouge2 Fmeasure: 0.0
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: 0.0005
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adafactor
- lr_scheduler_type: linear
- num_epochs: 50
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
|---|---|---|---|---|---|---|
| No log | 1.0 | 1 | 2.0548 | 0.0 | 0.0 | 0.0 |
| No log | 2.0 | 2 | 1.8220 | 0.0082 | 0.0093 | 0.0087 |
| No log | 3.0 | 3 | 1.6844 | 0.0082 | 0.0093 | 0.0087 |
| No log | 4.0 | 4 | 1.8011 | 0.0082 | 0.0093 | 0.0087 |
| No log | 5.0 | 5 | 1.7271 | 0.0 | 0.0 | 0.0 |
| No log | 6.0 | 6 | 1.7730 | 0.0082 | 0.0093 | 0.0087 |
| No log | 7.0 | 7 | 1.7311 | 0.0 | 0.0 | 0.0 |
| No log | 8.0 | 8 | 1.7311 | 0.0 | 0.0 | 0.0 |
| No log | 9.0 | 9 | 1.7030 | 0.0249 | 0.0293 | 0.0269 |
| No log | 10.0 | 10 | 1.7071 | 0.0082 | 0.0093 | 0.0087 |
| No log | 11.0 | 11 | 1.6465 | 0.0 | 0.0 | 0.0 |
| No log | 12.0 | 12 | 1.6520 | 0.0082 | 0.0093 | 0.0087 |
| No log | 13.0 | 13 | 1.6619 | 0.0 | 0.0 | 0.0 |
| No log | 14.0 | 14 | 1.6257 | 0.0167 | 0.02 | 0.0182 |
| No log | 15.0 | 15 | 1.7339 | 0.0249 | 0.0293 | 0.0269 |
| No log | 16.0 | 16 | 1.6232 | 0.0 | 0.0 | 0.0 |
| No log | 17.0 | 17 | 1.7218 | 0.0082 | 0.0093 | 0.0087 |
| No log | 18.0 | 18 | 1.6056 | 0.0082 | 0.0093 | 0.0087 |
| No log | 19.0 | 19 | 1.7079 | 0.0167 | 0.02 | 0.0182 |
| No log | 20.0 | 20 | 1.6044 | 0.0 | 0.0 | 0.0 |
| No log | 21.0 | 21 | 1.6766 | 0.0167 | 0.02 | 0.0182 |
| No log | 22.0 | 22 | 1.6000 | 0.0 | 0.0 | 0.0 |
| No log | 23.0 | 23 | 1.6677 | 0.0249 | 0.0293 | 0.0269 |
| No log | 24.0 | 24 | 1.5932 | 0.0 | 0.0 | 0.0 |
| No log | 25.0 | 25 | 1.6530 | 0.0 | 0.0 | 0.0 |
| No log | 26.0 | 26 | 1.5875 | 0.0 | 0.0 | 0.0 |
| No log | 27.0 | 27 | 1.6486 | 0.0082 | 0.0093 | 0.0087 |
| No log | 28.0 | 28 | 1.5865 | 0.0 | 0.0 | 0.0 |
| No log | 29.0 | 29 | 1.6243 | 0.0 | 0.0 | 0.0 |
| No log | 30.0 | 30 | 1.5793 | 0.0 | 0.0 | 0.0 |
| No log | 31.0 | 31 | 1.6170 | 0.0 | 0.0 | 0.0 |
| No log | 32.0 | 32 | 1.5761 | 0.0 | 0.0 | 0.0 |
| No log | 33.0 | 33 | 1.6046 | 0.0 | 0.0 | 0.0 |
| No log | 34.0 | 34 | 1.5709 | 0.0167 | 0.02 | 0.0182 |
| No log | 35.0 | 35 | 1.5966 | 0.0 | 0.0 | 0.0 |
| No log | 36.0 | 36 | 1.5656 | 0.0 | 0.0 | 0.0 |
| No log | 37.0 | 37 | 1.5690 | 0.0 | 0.0 | 0.0 |
| No log | 38.0 | 38 | 1.5817 | 0.0082 | 0.0093 | 0.0087 |
| No log | 39.0 | 39 | 1.5770 | 0.0082 | 0.0093 | 0.0087 |
| No log | 40.0 | 40 | 1.5600 | 0.0082 | 0.0093 | 0.0087 |
| No log | 41.0 | 41 | 1.5688 | 0.0 | 0.0 | 0.0 |
| No log | 42.0 | 42 | 1.5603 | 0.0 | 0.0 | 0.0 |
| No log | 43.0 | 43 | 1.5546 | 0.0 | 0.0 | 0.0 |
| No log | 44.0 | 44 | 1.5728 | 0.0 | 0.0 | 0.0 |
| No log | 45.0 | 45 | 1.5515 | 0.0 | 0.0 | 0.0 |
| No log | 46.0 | 46 | 1.5510 | 0.0 | 0.0 | 0.0 |
| No log | 47.0 | 47 | 1.5524 | 0.0 | 0.0 | 0.0 |
| No log | 48.0 | 48 | 1.5521 | 0.0 | 0.0 | 0.0 |
| No log | 49.0 | 49 | 1.5512 | 0.0 | 0.0 | 0.0 |
| No log | 50.0 | 50 | 1.5504 | 0.0 | 0.0 | 0.0 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
