Hugging Face's logo

GuysTrans
/
t5-base-finetuned-ehealth

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
1
t5-base-finetuned-ehealth / README.md
GuysTrans's picture
GuysTrans
update model card README.md
73e298d
preview code
|
raw
history blame
11.6 kB
metadata
license: apache-2.0
base_model: t5-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: t5-base-finetuned-ehealth
    results: []

t5-base-finetuned-ehealth

This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3953
  • Rouge1: 16.9989
  • Rouge2: 4.8395
  • Rougel: 13.1702
  • Rougelsum: 15.6472
  • 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: 100

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 22 4.2413 9.137 1.2333 6.9806 8.1957 18.6901
No log 2.0 44 3.5352 9.5584 1.2176 7.2081 8.5048 18.8187
No log 3.0 66 3.3124 9.9504 1.2105 7.4652 8.7962 18.8187
No log 4.0 88 3.2065 10.3375 1.1847 7.7904 9.1801 18.8947
No log 5.0 110 3.1208 10.777 1.326 8.1305 9.6488 18.8947
No log 6.0 132 3.0495 11.1502 1.4947 8.4386 9.9076 18.924
No log 7.0 154 2.9851 11.1759 1.5744 8.4744 9.9534 18.924
No log 8.0 176 2.9232 10.5745 1.5079 8.1888 9.4731 18.8363
No log 9.0 198 2.8663 10.3156 1.452 8.1662 9.385 18.8947
No log 10.0 220 2.8110 10.5445 1.6067 8.3821 9.6755 18.8538
No log 11.0 242 2.7625 11.0628 1.6957 8.7832 10.1425 18.8947
No log 12.0 264 2.7129 10.9152 1.8386 8.7865 10.0545 18.8538
No log 13.0 286 2.6680 10.8689 1.9024 8.6892 9.883 18.8889
No log 14.0 308 2.6235 10.4118 1.9101 8.2442 9.4505 18.8947
No log 15.0 330 2.5810 11.2578 2.0742 8.7641 10.2349 18.8947
No log 16.0 352 2.5412 11.815 2.1727 9.2403 10.6655 18.9591
No log 17.0 374 2.5056 11.8324 2.1849 9.2089 10.7361 18.9649
No log 18.0 396 2.4710 11.4611 2.1406 8.9329 10.4319 18.8246
No log 19.0 418 2.4365 12.0309 2.4387 9.3966 11.0327 18.8655
No log 20.0 440 2.4039 11.9636 2.4332 9.3448 11.0055 18.8363
No log 21.0 462 2.3734 12.709 2.6945 9.8722 11.572 18.7602
No log 22.0 484 2.3414 13.2227 2.6249 10.1069 11.968 18.7895
3.1829 23.0 506 2.3132 13.3682 2.6082 10.1546 12.0317 18.8246
3.1829 24.0 528 2.2861 14.3195 3.0288 10.8036 12.8973 18.8713
3.1829 25.0 550 2.2592 14.1227 2.6271 10.6826 12.7174 18.9064
3.1829 26.0 572 2.2324 14.3697 2.8314 10.9239 13.0199 18.9064
3.1829 27.0 594 2.2054 14.4512 2.9546 11.0853 13.1193 18.9474
3.1829 28.0 616 2.1810 15.12 3.3732 11.5842 13.6805 18.9474
3.1829 29.0 638 2.1563 14.8242 3.2998 11.2467 13.3076 18.9474
3.1829 30.0 660 2.1333 15.0384 3.3988 11.4676 13.6825 18.9123
3.1829 31.0 682 2.1102 14.9877 3.3844 11.4417 13.5657 18.9591
3.1829 32.0 704 2.0884 14.9699 3.4128 11.4893 13.6109 18.9591
3.1829 33.0 726 2.0646 14.7391 3.0552 11.2351 13.3809 18.9591
3.1829 34.0 748 2.0419 14.9203 3.1074 11.2239 13.4966 18.9591
3.1829 35.0 770 2.0203 15.1875 3.2249 11.3843 13.8011 18.9591
3.1829 36.0 792 1.9988 15.1457 3.1865 11.5238 13.7114 18.9591
3.1829 37.0 814 1.9786 15.2334 3.3739 11.6124 13.8956 18.9591
3.1829 38.0 836 1.9580 15.7105 3.4331 11.8577 14.2217 18.9474
3.1829 39.0 858 1.9387 15.6612 3.5588 12.0279 14.2183 18.9474
3.1829 40.0 880 1.9210 15.8692 3.5665 12.0078 14.3505 18.9591
3.1829 41.0 902 1.9041 15.9888 3.6914 12.0342 14.3375 18.9591
3.1829 42.0 924 1.8834 15.9551 3.6863 12.0562 14.5444 18.9591
3.1829 43.0 946 1.8648 15.9107 3.9128 12.1663 14.5029 18.9591
3.1829 44.0 968 1.8468 15.9831 3.8588 12.196 14.5114 18.9591
3.1829 45.0 990 1.8290 15.9072 3.6844 12.1007 14.5031 18.9591
2.4484 46.0 1012 1.8127 15.9918 3.792 12.2569 14.5287 18.9591
2.4484 47.0 1034 1.7959 15.9685 3.7664 12.1033 14.473 18.9591
2.4484 48.0 1056 1.7799 15.7128 3.505 11.9947 14.216 18.9591
2.4484 49.0 1078 1.7636 15.8033 3.6874 12.1043 14.37 18.9591
2.4484 50.0 1100 1.7487 15.914 3.758 12.1635 14.4603 18.9591
2.4484 51.0 1122 1.7338 15.7088 3.7272 11.951 14.2862 18.9591
2.4484 52.0 1144 1.7202 15.7231 3.6274 12.0492 14.3036 18.9591
2.4484 53.0 1166 1.7081 15.6734 3.5837 11.9265 14.2674 18.9591
2.4484 54.0 1188 1.6935 15.6501 3.5574 11.8579 14.2387 18.9591
2.4484 55.0 1210 1.6793 15.8984 3.8029 12.0981 14.3888 18.9591
2.4484 56.0 1232 1.6666 15.7263 3.6691 12.0325 14.3152 18.9591
2.4484 57.0 1254 1.6516 15.8016 3.6151 12.0349 14.3556 18.9591
2.4484 58.0 1276 1.6385 15.8773 3.7501 12.1887 14.456 18.9591
2.4484 59.0 1298 1.6266 16.0252 3.8027 12.3099 14.5017 18.9591
2.4484 60.0 1320 1.6151 16.29 3.9544 12.5391 14.7691 18.9591
2.4484 61.0 1342 1.6034 16.2891 4.0512 12.5053 14.8155 18.9591
2.4484 62.0 1364 1.5925 16.1871 4.0482 12.4821 14.6986 18.9591
2.4484 63.0 1386 1.5812 16.1774 3.9903 12.4861 14.7798 18.9591
2.4484 64.0 1408 1.5716 16.1663 3.9399 12.4316 14.7449 18.9591
2.4484 65.0 1430 1.5623 16.4455 4.2777 12.7206 14.9193 18.9591
2.4484 66.0 1452 1.5517 16.466 4.2148 12.7613 15.052 18.9591
2.4484 67.0 1474 1.5414 16.5696 4.193 12.6949 15.1064 18.9591
2.4484 68.0 1496 1.5347 16.7602 4.4803 12.938 15.3339 18.9649
2.1379 69.0 1518 1.5278 16.6684 4.3943 12.9152 15.2626 18.9649
2.1379 70.0 1540 1.5193 16.7462 4.4151 12.9251 15.3619 18.9649
2.1379 71.0 1562 1.5104 16.658 4.4187 12.8792 15.2538 18.9591
2.1379 72.0 1584 1.5026 16.8475 4.481 13.0381 15.4041 18.9591
2.1379 73.0 1606 1.4944 16.9066 4.6433 13.1838 15.489 18.9591
2.1379 74.0 1628 1.4864 16.9434 4.6401 13.0527 15.4966 18.9591
2.1379 75.0 1650 1.4801 16.9744 4.694 13.1585 15.5739 19.0
2.1379 76.0 1672 1.4733 17.0546 4.6971 13.0968 15.633 19.0
2.1379 77.0 1694 1.4668 17.1603 4.7771 13.2896 15.7112 19.0
2.1379 78.0 1716 1.4607 17.086 4.7411 13.2587 15.6842 19.0
2.1379 79.0 1738 1.4552 17.0322 4.7652 13.2693 15.711 19.0
2.1379 80.0 1760 1.4493 17.1045 4.8492 13.2752 15.7876 19.0
2.1379 81.0 1782 1.4445 17.0275 4.8688 13.2621 15.7825 19.0
2.1379 82.0 1804 1.4392 17.0985 4.8148 13.2498 15.7718 19.0
2.1379 83.0 1826 1.4337 17.1395 4.8482 13.357 15.8122 19.0
2.1379 84.0 1848 1.4294 17.0411 4.8237 13.3126 15.7736 19.0
2.1379 85.0 1870 1.4254 17.1265 4.8691 13.3033 15.81 19.0
2.1379 86.0 1892 1.4212 16.9899 4.7712 13.1785 15.6416 19.0
2.1379 87.0 1914 1.4176 17.0389 4.7936 13.219 15.7048 19.0
2.1379 88.0 1936 1.4141 17.2266 4.9339 13.3935 15.8629 19.0
2.1379 89.0 1958 1.4108 17.0176 4.8752 13.2829 15.7145 19.0
2.1379 90.0 1980 1.4084 17.154 4.9912 13.3718 15.8255 19.0
1.9718 91.0 2002 1.4061 17.0783 4.9171 13.2617 15.7864 19.0
1.9718 92.0 2024 1.4037 17.0967 4.9393 13.2608 15.8054 19.0
1.9718 93.0 2046 1.4020 17.1524 4.995 13.332 15.8315 19.0
1.9718 94.0 2068 1.4001 17.1357 4.9699 13.3064 15.7932 19.0
1.9718 95.0 2090 1.3988 17.0758 4.8899 13.2231 15.7124 19.0
1.9718 96.0 2112 1.3976 16.9842 4.8395 13.173 15.653 19.0
1.9718 97.0 2134 1.3967 17.0425 4.8395 13.2243 15.6976 19.0
1.9718 98.0 2156 1.3960 16.9842 4.8395 13.173 15.653 19.0
1.9718 99.0 2178 1.3955 16.9842 4.8395 13.173 15.653 19.0
1.9718 100.0 2200 1.3953 16.9989 4.8395 13.1702 15.6472 19.0

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.1
  • Tokenizers 0.13.3