metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-github-repo-tag-generation
results: []
t5-small-github-repo-tag-generation
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6488
- Rouge1: 25.2912
- Rouge2: 9.5617
- Rougel: 22.6455
- Rougelsum: 22.617
- Gen Len: 19.0
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.7857 | 1.0 | 66 | 1.2317 | 2.609 | 0.0 | 2.5996 | 2.6132 | 19.0 |
| 1.2147 | 2.0 | 132 | 1.0105 | 1.8041 | 0.0866 | 1.7432 | 1.7451 | 18.9848 |
| 1.0625 | 3.0 | 198 | 0.9154 | 2.5794 | 0.5266 | 2.4272 | 2.4305 | 19.0 |
| 0.9849 | 4.0 | 264 | 0.8615 | 19.2823 | 4.6729 | 17.639 | 17.6209 | 19.0 |
| 0.9363 | 5.0 | 330 | 0.8248 | 22.4371 | 5.4177 | 20.0806 | 20.1164 | 19.0 |
| 0.8995 | 6.0 | 396 | 0.7943 | 24.162 | 6.1729 | 21.3733 | 21.3621 | 19.0 |
| 0.8774 | 7.0 | 462 | 0.7736 | 24.0765 | 6.4219 | 21.2588 | 21.2715 | 19.0 |
| 0.8544 | 8.0 | 528 | 0.7558 | 24.4842 | 6.7685 | 21.8275 | 21.8459 | 19.0 |
| 0.8334 | 9.0 | 594 | 0.7416 | 25.009 | 7.8025 | 22.3227 | 22.3454 | 19.0 |
| 0.8212 | 10.0 | 660 | 0.7300 | 24.9532 | 7.9013 | 22.4275 | 22.4138 | 19.0 |
| 0.8118 | 11.0 | 726 | 0.7208 | 25.4191 | 7.8727 | 22.696 | 22.6894 | 19.0 |
| 0.7994 | 12.0 | 792 | 0.7114 | 25.4852 | 8.1776 | 22.4479 | 22.4522 | 19.0 |
| 0.7904 | 13.0 | 858 | 0.7020 | 25.4509 | 8.7603 | 22.7333 | 22.7213 | 19.0 |
| 0.7829 | 14.0 | 924 | 0.6958 | 25.0587 | 8.9197 | 22.6393 | 22.6207 | 19.0 |
| 0.7764 | 15.0 | 990 | 0.6897 | 25.0867 | 9.0392 | 22.6598 | 22.6808 | 19.0 |
| 0.7703 | 16.0 | 1056 | 0.6841 | 25.2402 | 9.3991 | 22.6384 | 22.6226 | 19.0 |
| 0.7633 | 17.0 | 1122 | 0.6781 | 25.7124 | 9.5485 | 23.0809 | 23.0677 | 19.0 |
| 0.7591 | 18.0 | 1188 | 0.6744 | 25.0679 | 9.4176 | 22.5225 | 22.4913 | 19.0 |
| 0.7553 | 19.0 | 1254 | 0.6695 | 25.3046 | 9.2343 | 22.931 | 22.8948 | 19.0 |
| 0.7514 | 20.0 | 1320 | 0.6661 | 25.3134 | 9.3234 | 22.8281 | 22.8198 | 19.0 |
| 0.746 | 21.0 | 1386 | 0.6630 | 25.3837 | 9.2876 | 22.806 | 22.7907 | 19.0 |
| 0.741 | 22.0 | 1452 | 0.6592 | 25.4751 | 9.3792 | 22.9321 | 22.9158 | 19.0 |
| 0.7404 | 23.0 | 1518 | 0.6566 | 25.5734 | 9.4539 | 23.0627 | 23.063 | 19.0 |
| 0.735 | 24.0 | 1584 | 0.6555 | 25.2529 | 9.5285 | 22.6775 | 22.6504 | 19.0 |
| 0.7334 | 25.0 | 1650 | 0.6536 | 25.2281 | 9.4984 | 22.3494 | 22.3364 | 19.0 |
| 0.7352 | 26.0 | 1716 | 0.6514 | 25.3464 | 9.7302 | 22.6918 | 22.6786 | 19.0 |
| 0.7322 | 27.0 | 1782 | 0.6502 | 25.2349 | 9.6516 | 22.6298 | 22.6005 | 19.0 |
| 0.7333 | 28.0 | 1848 | 0.6492 | 25.288 | 9.5646 | 22.6836 | 22.6629 | 19.0 |
| 0.7291 | 29.0 | 1914 | 0.6488 | 25.2912 | 9.5617 | 22.6455 | 22.617 | 19.0 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2