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: 1.2532
- Rouge1: 58.505
- Rouge2: 40.7585
- Rougel: 58.4653
- Rougelsum: 58.4037
- Gen Len: 17.199
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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 76 | 3.6488 | 18.0544 | 10.1314 | 17.9969 | 17.9364 | 18.9555 |
| No log | 2.0 | 152 | 2.8655 | 20.8947 | 12.1663 | 20.8942 | 20.7913 | 17.2592 |
| No log | 3.0 | 228 | 2.5441 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| No log | 4.0 | 304 | 2.1197 | 24.8779 | 13.8464 | 24.8679 | 24.7943 | 16.6361 |
| No log | 5.0 | 380 | 1.9142 | 32.7885 | 18.308 | 32.7168 | 32.6032 | 16.0026 |
| No log | 6.0 | 456 | 1.8132 | 42.6762 | 24.9808 | 42.7653 | 42.6814 | 16.4372 |
| 4.0412 | 7.0 | 532 | 1.7578 | 47.0516 | 28.9154 | 47.0625 | 46.8679 | 16.5497 |
| 4.0412 | 8.0 | 608 | 1.7036 | 48.5544 | 30.6663 | 48.4878 | 48.2941 | 16.712 |
| 4.0412 | 9.0 | 684 | 1.6619 | 49.0281 | 30.913 | 48.9624 | 48.8024 | 16.7932 |
| 4.0412 | 10.0 | 760 | 1.6264 | 50.4718 | 31.3769 | 50.4991 | 50.3001 | 16.8298 |
| 4.0412 | 11.0 | 836 | 1.5929 | 51.8768 | 32.8966 | 51.8764 | 51.6971 | 16.9241 |
| 4.0412 | 12.0 | 912 | 1.5674 | 52.805 | 33.7597 | 52.814 | 52.6762 | 17.0393 |
| 4.0412 | 13.0 | 988 | 1.5385 | 53.3014 | 34.7227 | 53.2522 | 53.1391 | 16.9686 |
| 2.3621 | 14.0 | 1064 | 1.5161 | 53.4211 | 34.5845 | 53.3523 | 53.2309 | 17.0654 |
| 2.3621 | 15.0 | 1140 | 1.4950 | 54.0068 | 35.364 | 53.9636 | 53.8528 | 17.0471 |
| 2.3621 | 16.0 | 1216 | 1.4740 | 54.9014 | 35.7748 | 54.793 | 54.7219 | 17.0681 |
| 2.3621 | 17.0 | 1292 | 1.4592 | 55.0288 | 36.4521 | 54.8815 | 54.8354 | 17.1466 |
| 2.3621 | 18.0 | 1368 | 1.4400 | 55.1504 | 36.5607 | 55.0743 | 55.0264 | 17.1178 |
| 2.3621 | 19.0 | 1444 | 1.4189 | 55.3705 | 36.7609 | 55.2619 | 55.1529 | 17.0942 |
| 2.0838 | 20.0 | 1520 | 1.4100 | 55.6045 | 36.6921 | 55.4813 | 55.3633 | 17.144 |
| 2.0838 | 21.0 | 1596 | 1.4001 | 55.716 | 36.8504 | 55.5929 | 55.5 | 17.1754 |
| 2.0838 | 22.0 | 1672 | 1.3874 | 55.4707 | 36.6502 | 55.3258 | 55.3038 | 17.1728 |
| 2.0838 | 23.0 | 1748 | 1.3732 | 55.5138 | 36.6722 | 55.4043 | 55.3049 | 17.1649 |
| 2.0838 | 24.0 | 1824 | 1.3640 | 55.6384 | 37.131 | 55.5682 | 55.5184 | 17.1806 |
| 2.0838 | 25.0 | 1900 | 1.3516 | 55.9776 | 37.4206 | 55.8968 | 55.8347 | 17.1754 |
| 2.0838 | 26.0 | 1976 | 1.3466 | 55.9109 | 37.3492 | 55.8212 | 55.7707 | 17.2147 |
| 1.9303 | 27.0 | 2052 | 1.3335 | 56.1628 | 37.5711 | 56.0569 | 56.037 | 17.1911 |
| 1.9303 | 28.0 | 2128 | 1.3308 | 56.3832 | 38.1769 | 56.2915 | 56.2485 | 17.2251 |
| 1.9303 | 29.0 | 2204 | 1.3193 | 56.5538 | 38.0494 | 56.4529 | 56.3879 | 17.199 |
| 1.9303 | 30.0 | 2280 | 1.3143 | 56.8915 | 38.4523 | 56.8172 | 56.7577 | 17.2251 |
| 1.9303 | 31.0 | 2356 | 1.3055 | 57.2079 | 38.7956 | 57.1173 | 57.0803 | 17.233 |
| 1.9303 | 32.0 | 2432 | 1.3016 | 57.2978 | 38.8335 | 57.2228 | 57.1916 | 17.2277 |
| 1.837 | 33.0 | 2508 | 1.2959 | 57.2382 | 39.3425 | 57.2579 | 57.1906 | 17.2225 |
| 1.837 | 34.0 | 2584 | 1.2885 | 57.5746 | 39.8412 | 57.5268 | 57.4536 | 17.1937 |
| 1.837 | 35.0 | 2660 | 1.2848 | 57.5721 | 39.5468 | 57.5542 | 57.4642 | 17.1937 |
| 1.837 | 36.0 | 2736 | 1.2829 | 57.7334 | 39.6824 | 57.7178 | 57.6337 | 17.1754 |
| 1.837 | 37.0 | 2812 | 1.2768 | 58.0261 | 40.335 | 58.0649 | 57.9859 | 17.1754 |
| 1.837 | 38.0 | 2888 | 1.2736 | 57.9739 | 40.2252 | 57.9272 | 57.8891 | 17.2016 |
| 1.837 | 39.0 | 2964 | 1.2693 | 58.1793 | 40.4482 | 58.1415 | 58.1187 | 17.178 |
| 1.7809 | 40.0 | 3040 | 1.2671 | 57.9545 | 40.3069 | 57.9214 | 57.9091 | 17.1806 |
| 1.7809 | 41.0 | 3116 | 1.2651 | 58.0546 | 40.4009 | 58.0387 | 57.9956 | 17.1911 |
| 1.7809 | 42.0 | 3192 | 1.2616 | 58.1469 | 40.4112 | 58.1098 | 58.0618 | 17.2042 |
| 1.7809 | 43.0 | 3268 | 1.2616 | 58.2348 | 40.5331 | 58.2115 | 58.1603 | 17.2068 |
| 1.7809 | 44.0 | 3344 | 1.2584 | 58.3018 | 40.5296 | 58.2795 | 58.2452 | 17.1963 |
| 1.7809 | 45.0 | 3420 | 1.2564 | 58.2935 | 40.478 | 58.2611 | 58.2192 | 17.1911 |
| 1.7809 | 46.0 | 3496 | 1.2550 | 58.2928 | 40.4315 | 58.2823 | 58.2234 | 17.1937 |
| 1.7469 | 47.0 | 3572 | 1.2541 | 58.2963 | 40.4214 | 58.2831 | 58.2164 | 17.1963 |
| 1.7469 | 48.0 | 3648 | 1.2538 | 58.4422 | 40.6293 | 58.4285 | 58.3755 | 17.1963 |
| 1.7469 | 49.0 | 3724 | 1.2534 | 58.505 | 40.7585 | 58.4653 | 58.4037 | 17.199 |
| 1.7469 | 50.0 | 3800 | 1.2532 | 58.505 | 40.7585 | 58.4653 | 58.4037 | 17.199 |
Framework versions
- Transformers 4.36.2
- Pytorch 1.13.1
- Datasets 2.16.1
- Tokenizers 0.15.0