|
--- |
|
license: apache-2.0 |
|
base_model: t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: my_awesome_opus_books_model |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# my_awesome_opus_books_model |
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co./t5-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.2918 |
|
- Bleu: 0.006 |
|
- 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 100 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| |
|
| No log | 1.0 | 15 | 6.5275 | 0.0014 | 19.0 | |
|
| No log | 2.0 | 30 | 5.6262 | 0.0017 | 18.9333 | |
|
| No log | 3.0 | 45 | 5.3621 | 0.0012 | 19.0 | |
|
| No log | 4.0 | 60 | 5.1888 | 0.0003 | 19.0 | |
|
| No log | 5.0 | 75 | 5.0467 | 0.0005 | 19.0 | |
|
| No log | 6.0 | 90 | 4.9398 | 0.0004 | 19.0 | |
|
| No log | 7.0 | 105 | 4.8270 | 0.0004 | 19.0 | |
|
| No log | 8.0 | 120 | 4.7307 | 0.0004 | 19.0 | |
|
| No log | 9.0 | 135 | 4.6413 | 0.0006 | 19.0 | |
|
| No log | 10.0 | 150 | 4.5564 | 0.001 | 19.0 | |
|
| No log | 11.0 | 165 | 4.4810 | 0.0068 | 19.0 | |
|
| No log | 12.0 | 180 | 4.4120 | 0.0102 | 19.0 | |
|
| No log | 13.0 | 195 | 4.3472 | 0.0072 | 19.0 | |
|
| No log | 14.0 | 210 | 4.2857 | 0.0038 | 19.0 | |
|
| No log | 15.0 | 225 | 4.2197 | 0.0037 | 19.0 | |
|
| No log | 16.0 | 240 | 4.1564 | 0.0028 | 19.0 | |
|
| No log | 17.0 | 255 | 4.0921 | 0.0018 | 19.0 | |
|
| No log | 18.0 | 270 | 4.0299 | 0.0018 | 19.0 | |
|
| No log | 19.0 | 285 | 3.9678 | 0.0019 | 19.0 | |
|
| No log | 20.0 | 300 | 3.9072 | 0.0007 | 19.0 | |
|
| No log | 21.0 | 315 | 3.8477 | 0.0043 | 19.0 | |
|
| No log | 22.0 | 330 | 3.7894 | 0.0024 | 19.0 | |
|
| No log | 23.0 | 345 | 3.7494 | 0.0 | 19.0 | |
|
| No log | 24.0 | 360 | 3.7120 | 0.0 | 19.0 | |
|
| No log | 25.0 | 375 | 3.6799 | 0.0007 | 19.0 | |
|
| No log | 26.0 | 390 | 3.6512 | 0.0 | 19.0 | |
|
| No log | 27.0 | 405 | 3.6272 | 0.0 | 19.0 | |
|
| No log | 28.0 | 420 | 3.6106 | 0.0 | 19.0 | |
|
| No log | 29.0 | 435 | 3.5992 | 0.0059 | 19.0 | |
|
| No log | 30.0 | 450 | 3.5872 | 0.0007 | 19.0 | |
|
| No log | 31.0 | 465 | 3.5728 | 0.0004 | 19.0 | |
|
| No log | 32.0 | 480 | 3.5575 | 0.0004 | 19.0 | |
|
| No log | 33.0 | 495 | 3.5474 | 0.001 | 19.0 | |
|
| 4.6099 | 34.0 | 510 | 3.5393 | 0.001 | 19.0 | |
|
| 4.6099 | 35.0 | 525 | 3.5271 | 0.0009 | 19.0 | |
|
| 4.6099 | 36.0 | 540 | 3.5240 | 0.0015 | 19.0 | |
|
| 4.6099 | 37.0 | 555 | 3.5154 | 0.0011 | 18.8833 | |
|
| 4.6099 | 38.0 | 570 | 3.5015 | 0.0005 | 18.85 | |
|
| 4.6099 | 39.0 | 585 | 3.4891 | 0.0005 | 18.8 | |
|
| 4.6099 | 40.0 | 600 | 3.4856 | 0.0005 | 18.8 | |
|
| 4.6099 | 41.0 | 615 | 3.4791 | 0.0005 | 18.8 | |
|
| 4.6099 | 42.0 | 630 | 3.4646 | 0.0004 | 18.8 | |
|
| 4.6099 | 43.0 | 645 | 3.4589 | 0.0004 | 18.8 | |
|
| 4.6099 | 44.0 | 660 | 3.4497 | 0.0005 | 18.8 | |
|
| 4.6099 | 45.0 | 675 | 3.4436 | 0.0005 | 18.8 | |
|
| 4.6099 | 46.0 | 690 | 3.4382 | 0.0005 | 18.8 | |
|
| 4.6099 | 47.0 | 705 | 3.4330 | 0.0005 | 18.8 | |
|
| 4.6099 | 48.0 | 720 | 3.4217 | 0.0005 | 18.8 | |
|
| 4.6099 | 49.0 | 735 | 3.4135 | 0.0005 | 18.8 | |
|
| 4.6099 | 50.0 | 750 | 3.4096 | 0.0006 | 18.8 | |
|
| 4.6099 | 51.0 | 765 | 3.4013 | 0.0007 | 18.8 | |
|
| 4.6099 | 52.0 | 780 | 3.3969 | 0.0007 | 18.8 | |
|
| 4.6099 | 53.0 | 795 | 3.3906 | 0.0006 | 18.8 | |
|
| 4.6099 | 54.0 | 810 | 3.3819 | 0.0008 | 18.8 | |
|
| 4.6099 | 55.0 | 825 | 3.3799 | 0.0009 | 18.8 | |
|
| 4.6099 | 56.0 | 840 | 3.3753 | 0.001 | 18.8 | |
|
| 4.6099 | 57.0 | 855 | 3.3742 | 0.0012 | 18.8 | |
|
| 4.6099 | 58.0 | 870 | 3.3641 | 0.0008 | 18.8 | |
|
| 4.6099 | 59.0 | 885 | 3.3604 | 0.0009 | 18.8 | |
|
| 4.6099 | 60.0 | 900 | 3.3554 | 0.0009 | 18.8 | |
|
| 4.6099 | 61.0 | 915 | 3.3522 | 0.0016 | 18.8 | |
|
| 4.6099 | 62.0 | 930 | 3.3494 | 0.001 | 18.8 | |
|
| 4.6099 | 63.0 | 945 | 3.3454 | 0.0022 | 19.0 | |
|
| 4.6099 | 64.0 | 960 | 3.3441 | 0.003 | 19.0 | |
|
| 4.6099 | 65.0 | 975 | 3.3391 | 0.0035 | 18.8 | |
|
| 4.6099 | 66.0 | 990 | 3.3366 | 0.0022 | 18.8 | |
|
| 3.4904 | 67.0 | 1005 | 3.3340 | 0.0018 | 18.8 | |
|
| 3.4904 | 68.0 | 1020 | 3.3303 | 0.0023 | 19.0 | |
|
| 3.4904 | 69.0 | 1035 | 3.3304 | 0.0024 | 19.0 | |
|
| 3.4904 | 70.0 | 1050 | 3.3284 | 0.0019 | 19.0 | |
|
| 3.4904 | 71.0 | 1065 | 3.3260 | 0.0032 | 19.0 | |
|
| 3.4904 | 72.0 | 1080 | 3.3246 | 0.0021 | 19.0 | |
|
| 3.4904 | 73.0 | 1095 | 3.3186 | 0.0022 | 19.0 | |
|
| 3.4904 | 74.0 | 1110 | 3.3150 | 0.0021 | 19.0 | |
|
| 3.4904 | 75.0 | 1125 | 3.3144 | 0.0022 | 19.0 | |
|
| 3.4904 | 76.0 | 1140 | 3.3121 | 0.0026 | 19.0 | |
|
| 3.4904 | 77.0 | 1155 | 3.3131 | 0.0024 | 19.0 | |
|
| 3.4904 | 78.0 | 1170 | 3.3118 | 0.0021 | 19.0 | |
|
| 3.4904 | 79.0 | 1185 | 3.3092 | 0.0025 | 19.0 | |
|
| 3.4904 | 80.0 | 1200 | 3.3095 | 0.0022 | 19.0 | |
|
| 3.4904 | 81.0 | 1215 | 3.3059 | 0.003 | 19.0 | |
|
| 3.4904 | 82.0 | 1230 | 3.3015 | 0.0016 | 19.0 | |
|
| 3.4904 | 83.0 | 1245 | 3.3004 | 0.0024 | 19.0 | |
|
| 3.4904 | 84.0 | 1260 | 3.3002 | 0.0018 | 19.0 | |
|
| 3.4904 | 85.0 | 1275 | 3.2994 | 0.0021 | 19.0 | |
|
| 3.4904 | 86.0 | 1290 | 3.2979 | 0.002 | 19.0 | |
|
| 3.4904 | 87.0 | 1305 | 3.2955 | 0.0019 | 19.0 | |
|
| 3.4904 | 88.0 | 1320 | 3.2940 | 0.003 | 19.0 | |
|
| 3.4904 | 89.0 | 1335 | 3.2942 | 0.0021 | 19.0 | |
|
| 3.4904 | 90.0 | 1350 | 3.2948 | 0.0023 | 19.0 | |
|
| 3.4904 | 91.0 | 1365 | 3.2939 | 0.0024 | 19.0 | |
|
| 3.4904 | 92.0 | 1380 | 3.2934 | 0.004 | 19.0 | |
|
| 3.4904 | 93.0 | 1395 | 3.2928 | 0.0032 | 19.0 | |
|
| 3.4904 | 94.0 | 1410 | 3.2925 | 0.0059 | 19.0 | |
|
| 3.4904 | 95.0 | 1425 | 3.2922 | 0.004 | 19.0 | |
|
| 3.4904 | 96.0 | 1440 | 3.2920 | 0.0047 | 19.0 | |
|
| 3.4904 | 97.0 | 1455 | 3.2920 | 0.0052 | 19.0 | |
|
| 3.4904 | 98.0 | 1470 | 3.2918 | 0.0062 | 19.0 | |
|
| 3.4904 | 99.0 | 1485 | 3.2918 | 0.0076 | 19.0 | |
|
| 3.2991 | 100.0 | 1500 | 3.2918 | 0.006 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.2 |
|
|
