metadata
tags:
- generated_from_trainer
datasets:
- samsum
model-index:
- name: pegasus-samsum
results: []
pegasus-samsum
This model is a fine-tuned version of google/pegasus-cnn_dailymail on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.4251
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1284 | 0.01 | 10 | 2.5960 |
| 3.122 | 0.02 | 20 | 2.5579 |
| 3.0196 | 0.03 | 30 | 2.4983 |
| 2.9803 | 0.04 | 40 | 2.4197 |
| 2.8471 | 0.05 | 50 | 2.3258 |
| 2.7692 | 0.07 | 60 | 2.2438 |
| 2.682 | 0.08 | 70 | 2.1608 |
| 2.3648 | 0.09 | 80 | 2.0838 |
| 2.5696 | 0.1 | 90 | 2.0222 |
| 2.3403 | 0.11 | 100 | 1.9713 |
| 2.2036 | 0.12 | 110 | 1.9199 |
| 2.1998 | 0.13 | 120 | 1.8750 |
| 2.3006 | 0.14 | 130 | 1.8382 |
| 2.1182 | 0.15 | 140 | 1.8050 |
| 2.1493 | 0.16 | 150 | 1.7748 |
| 2.0437 | 0.17 | 160 | 1.7494 |
| 1.9236 | 0.18 | 170 | 1.7289 |
| 2.0114 | 0.2 | 180 | 1.7106 |
| 1.9939 | 0.21 | 190 | 1.6906 |
| 1.928 | 0.22 | 200 | 1.6737 |
| 1.9444 | 0.23 | 210 | 1.6603 |
| 1.9071 | 0.24 | 220 | 1.6485 |
| 1.8314 | 0.25 | 230 | 1.6369 |
| 1.8085 | 0.26 | 240 | 1.6277 |
| 1.7493 | 0.27 | 250 | 1.6203 |
| 1.8539 | 0.28 | 260 | 1.6089 |
| 1.7048 | 0.29 | 270 | 1.5999 |
| 1.7486 | 0.3 | 280 | 1.5921 |
| 1.795 | 0.31 | 290 | 1.5842 |
| 1.6613 | 0.33 | 300 | 1.5815 |
| 1.8163 | 0.34 | 310 | 1.5732 |
| 1.6133 | 0.35 | 320 | 1.5621 |
| 1.8 | 0.36 | 330 | 1.5542 |
| 1.7159 | 0.37 | 340 | 1.5506 |
| 1.8081 | 0.38 | 350 | 1.5483 |
| 1.7365 | 0.39 | 360 | 1.5451 |
| 1.7334 | 0.4 | 370 | 1.5405 |
| 1.7329 | 0.41 | 380 | 1.5334 |
| 1.6923 | 0.42 | 390 | 1.5259 |
| 1.6868 | 0.43 | 400 | 1.5227 |
| 1.7033 | 0.45 | 410 | 1.5163 |
| 1.6805 | 0.46 | 420 | 1.5144 |
| 1.6056 | 0.47 | 430 | 1.5126 |
| 1.7317 | 0.48 | 440 | 1.5086 |
| 1.6303 | 0.49 | 450 | 1.5015 |
| 1.7136 | 0.5 | 460 | 1.4943 |
| 1.534 | 0.51 | 470 | 1.4910 |
| 1.6682 | 0.52 | 480 | 1.4917 |
| 1.6234 | 0.53 | 490 | 1.4885 |
| 1.7103 | 0.54 | 500 | 1.4857 |
| 1.7673 | 0.55 | 510 | 1.4800 |
| 1.6631 | 0.56 | 520 | 1.4776 |
| 1.7073 | 0.58 | 530 | 1.4745 |
| 1.6843 | 0.59 | 540 | 1.4698 |
| 1.6849 | 0.6 | 550 | 1.4679 |
| 1.6054 | 0.61 | 560 | 1.4642 |
| 1.6073 | 0.62 | 570 | 1.4629 |
| 1.5896 | 0.63 | 580 | 1.4591 |
| 1.608 | 0.64 | 590 | 1.4580 |
| 1.58 | 0.65 | 600 | 1.4548 |
| 1.5722 | 0.66 | 610 | 1.4548 |
| 1.5529 | 0.67 | 620 | 1.4542 |
| 1.5948 | 0.68 | 630 | 1.4518 |
| 1.5869 | 0.7 | 640 | 1.4489 |
| 1.577 | 0.71 | 650 | 1.4488 |
| 1.6517 | 0.72 | 660 | 1.4477 |
| 1.5955 | 0.73 | 670 | 1.4436 |
| 1.5678 | 0.74 | 680 | 1.4402 |
| 1.6743 | 0.75 | 690 | 1.4384 |
| 1.5791 | 0.76 | 700 | 1.4374 |
| 1.6397 | 0.77 | 710 | 1.4380 |
| 1.5637 | 0.78 | 720 | 1.4363 |
| 1.5849 | 0.79 | 730 | 1.4356 |
| 1.5815 | 0.8 | 740 | 1.4350 |
| 1.5797 | 0.81 | 750 | 1.4362 |
| 1.5551 | 0.83 | 760 | 1.4354 |
| 1.5486 | 0.84 | 770 | 1.4341 |
| 1.5756 | 0.85 | 780 | 1.4320 |
| 1.5326 | 0.86 | 790 | 1.4300 |
| 1.6198 | 0.87 | 800 | 1.4290 |
| 1.5947 | 0.88 | 810 | 1.4288 |
| 1.6326 | 0.89 | 820 | 1.4291 |
| 1.6231 | 0.9 | 830 | 1.4288 |
| 1.597 | 0.91 | 840 | 1.4281 |
| 1.5781 | 0.92 | 850 | 1.4273 |
| 1.6835 | 0.93 | 860 | 1.4260 |
| 1.5373 | 0.94 | 870 | 1.4257 |
| 1.5458 | 0.96 | 880 | 1.4252 |
| 1.4953 | 0.97 | 890 | 1.4252 |
| 1.5299 | 0.98 | 900 | 1.4252 |
| 1.5853 | 0.99 | 910 | 1.4251 |
| 1.5723 | 1.0 | 920 | 1.4251 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0
- Datasets 1.18.4
- Tokenizers 0.12.1