<!-- 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. -->
t5-paraphraser_nocomparative
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0388
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.2391 | 0.31 | 10 | 1.0103 |
1.215 | 0.61 | 20 | 0.9655 |
0.9575 | 0.92 | 30 | 0.9410 |
0.798 | 1.22 | 40 | 0.9410 |
0.7554 | 1.53 | 50 | 0.9753 |
0.928 | 1.83 | 60 | 0.9211 |
0.6989 | 2.14 | 70 | 0.9141 |
0.7275 | 2.44 | 80 | 0.9579 |
0.7135 | 2.75 | 90 | 0.9969 |
0.6 | 3.05 | 100 | 1.0139 |
0.5888 | 3.36 | 110 | 1.0635 |
0.6075 | 3.66 | 120 | 1.0409 |
0.5833 | 3.97 | 130 | 0.9971 |
0.5383 | 4.27 | 140 | 1.0357 |
0.4872 | 4.58 | 150 | 1.0439 |
0.6166 | 4.89 | 160 | 1.0497 |
0.4339 | 5.19 | 170 | 1.0362 |
0.6023 | 5.5 | 180 | 1.0405 |
0.5324 | 5.8 | 190 | 1.0377 |
0.5492 | 6.11 | 200 | 1.0300 |
0.4499 | 6.41 | 210 | 1.0324 |
0.4604 | 6.72 | 220 | 1.0388 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3