metadata
license: apache-2.0
base_model: google/t5-efficient-tiny
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: denoice-finetuned-xsum
results: []
denoice-finetuned-xsum
This model is a fine-tuned version of google/t5-efficient-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0564
- Rouge1: 63.8802
- Rouge2: 45.4086
- Rougel: 63.8882
- Rougelsum: 63.8316
- Gen Len: 17.2016
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: 500
- eval_batch_size: 500
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 76 | 1.1573 | 62.0366 | 43.6573 | 62.0258 | 61.9691 | 17.2068 |
| No log | 2.0 | 152 | 1.1458 | 61.7366 | 43.5997 | 61.7261 | 61.6638 | 17.2408 |
| No log | 3.0 | 228 | 1.1342 | 62.8021 | 44.3773 | 62.8168 | 62.7397 | 17.178 |
| No log | 4.0 | 304 | 1.1221 | 62.5511 | 44.4096 | 62.3775 | 62.3239 | 17.1518 |
| No log | 5.0 | 380 | 1.1177 | 63.0909 | 44.9863 | 62.9819 | 62.9072 | 17.1702 |
| No log | 6.0 | 456 | 1.1123 | 62.5334 | 44.2764 | 62.4559 | 62.4037 | 17.2173 |
| 1.5445 | 7.0 | 532 | 1.1073 | 62.8456 | 44.711 | 62.7463 | 62.7041 | 17.2016 |
| 1.5445 | 8.0 | 608 | 1.0983 | 63.0763 | 44.9468 | 62.9522 | 62.9795 | 17.2147 |
| 1.5445 | 9.0 | 684 | 1.0952 | 62.9383 | 44.9129 | 62.8777 | 62.8081 | 17.2487 |
| 1.5445 | 10.0 | 760 | 1.0947 | 62.8263 | 44.5132 | 62.7596 | 62.7362 | 17.233 |
| 1.5445 | 11.0 | 836 | 1.0801 | 63.0087 | 44.8035 | 63.0091 | 62.9498 | 17.1806 |
| 1.5445 | 12.0 | 912 | 1.0781 | 62.9718 | 44.6364 | 62.881 | 62.8786 | 17.1832 |
| 1.5445 | 13.0 | 988 | 1.0767 | 63.0711 | 44.7516 | 62.9967 | 62.9834 | 17.199 |
| 1.4815 | 14.0 | 1064 | 1.0722 | 63.1128 | 44.8069 | 63.0483 | 63.0151 | 17.2068 |
| 1.4815 | 15.0 | 1140 | 1.0719 | 63.2282 | 44.9567 | 63.2052 | 63.1787 | 17.2147 |
| 1.4815 | 16.0 | 1216 | 1.0684 | 63.3222 | 44.916 | 63.322 | 63.2505 | 17.199 |
| 1.4815 | 17.0 | 1292 | 1.0668 | 63.1931 | 44.9734 | 63.1833 | 63.114 | 17.2251 |
| 1.4815 | 18.0 | 1368 | 1.0640 | 63.5689 | 45.1652 | 63.62 | 63.5671 | 17.1806 |
| 1.4815 | 19.0 | 1444 | 1.0600 | 63.5552 | 45.2046 | 63.5795 | 63.5295 | 17.199 |
| 1.4452 | 20.0 | 1520 | 1.0593 | 63.5801 | 45.2453 | 63.5856 | 63.5245 | 17.199 |
| 1.4452 | 21.0 | 1596 | 1.0594 | 63.6291 | 45.1114 | 63.6412 | 63.5951 | 17.2042 |
| 1.4452 | 22.0 | 1672 | 1.0571 | 63.9129 | 45.3688 | 63.914 | 63.8618 | 17.1702 |
| 1.4452 | 23.0 | 1748 | 1.0573 | 63.8608 | 45.3548 | 63.857 | 63.8156 | 17.2042 |
| 1.4452 | 24.0 | 1824 | 1.0571 | 63.875 | 45.3997 | 63.8858 | 63.8202 | 17.2094 |
| 1.4452 | 25.0 | 1900 | 1.0564 | 63.8802 | 45.4086 | 63.8882 | 63.8316 | 17.2016 |
Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1
- Datasets 2.16.1
- Tokenizers 0.15.0