sujayC66's picture
End of training
e855e70 verified
metadata
license: apache-2.0
base_model: google-t5/t5-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: t5-base-finetuned-stocknews_2000_longshort_100
    results: []

t5-base-finetuned-stocknews_2000_longshort_100

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

  • Loss: 1.2433
  • Rouge1: 47.379
  • Rouge2: 37.1581
  • Rougel: 44.4701
  • Rougelsum: 44.9076
  • Gen Len: 18.9725

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: 150
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 200 0.9141 38.5343 24.2777 34.8367 35.2768 18.93
No log 2.0 400 0.8487 40.3489 26.7081 36.8437 37.2973 18.905
0.9964 3.0 600 0.8132 40.5675 26.9863 37.1398 37.6554 18.92
0.9964 4.0 800 0.7866 40.9242 27.5104 37.3596 37.8172 18.9175
0.7772 5.0 1000 0.7671 42.9708 29.7805 39.4356 39.9334 18.925
0.7772 6.0 1200 0.7591 43.3101 30.5015 39.8299 40.3437 18.9225
0.7772 7.0 1400 0.7478 43.3538 30.7684 40.0205 40.4603 18.915
0.6424 8.0 1600 0.7443 43.691 31.528 40.5718 41.0246 18.94
0.6424 9.0 1800 0.7403 44.2767 32.1741 40.9753 41.4431 18.935
0.5559 10.0 2000 0.7445 44.2641 32.2749 41.238 41.6911 18.9325
0.5559 11.0 2200 0.7402 44.9439 33.2834 41.8866 42.3044 18.9375
0.5559 12.0 2400 0.7453 44.8006 33.0754 41.69 42.1809 18.94
0.4838 13.0 2600 0.7466 45.861 34.1523 42.8088 43.2566 18.9425
0.4838 14.0 2800 0.7469 45.5954 34.1822 42.7063 43.1481 18.9425
0.4255 15.0 3000 0.7520 45.6216 34.4968 42.7157 43.1601 18.9425
0.4255 16.0 3200 0.7630 45.8129 34.5464 42.8766 43.3734 18.9425
0.4255 17.0 3400 0.7691 45.5398 34.1635 42.7054 43.2133 18.9475
0.374 18.0 3600 0.7794 45.956 34.9695 43.2425 43.7921 18.9475
0.374 19.0 3800 0.7858 46.3277 35.375 43.5397 44.0538 18.95
0.3378 20.0 4000 0.7908 45.7738 34.8592 43.0466 43.5114 18.97
0.3378 21.0 4200 0.8030 46.4438 35.484 43.5796 43.9963 18.9725
0.3378 22.0 4400 0.8122 46.3839 35.5331 43.5935 44.0138 18.97
0.2962 23.0 4600 0.8170 46.1935 35.3128 43.3188 43.7615 18.9475
0.2962 24.0 4800 0.8259 46.7935 35.9441 43.7662 44.2772 18.95
0.2696 25.0 5000 0.8331 46.6253 35.8821 43.727 44.1886 18.9525
0.2696 26.0 5200 0.8374 46.5525 35.9618 43.7777 44.1759 18.9525
0.2696 27.0 5400 0.8538 46.4477 35.7819 43.5644 43.9848 18.9525
0.2399 28.0 5600 0.8612 46.7679 36.2854 44.1508 44.5167 18.9525
0.2399 29.0 5800 0.8620 46.7708 36.1656 43.9684 44.3859 18.9525
0.218 30.0 6000 0.8781 46.93 36.5689 44.4382 44.8294 18.9525
0.218 31.0 6200 0.8809 46.9622 36.5912 44.2164 44.6975 18.9525
0.218 32.0 6400 0.8909 46.9908 36.4725 44.145 44.6297 18.9725
0.1979 33.0 6600 0.9007 47.0094 36.5598 44.1484 44.6246 18.9725
0.1979 34.0 6800 0.9032 47.0099 36.4015 43.9565 44.511 18.9525
0.1803 35.0 7000 0.9113 47.0771 36.4655 44.0139 44.4934 18.9525
0.1803 36.0 7200 0.9193 47.0419 36.6874 44.1141 44.5545 18.9525
0.1803 37.0 7400 0.9276 47.0573 36.7703 44.2841 44.7604 18.9525
0.1619 38.0 7600 0.9363 47.3043 37.0269 44.4301 44.8272 18.9525
0.1619 39.0 7800 0.9370 47.015 36.6241 44.1216 44.4495 18.9525
0.1516 40.0 8000 0.9524 47.2931 36.7869 44.356 44.7442 18.9525
0.1516 41.0 8200 0.9585 47.1871 36.7163 44.2597 44.6574 18.9525
0.1516 42.0 8400 0.9633 47.2776 36.7057 44.336 44.7328 18.9525
0.1374 43.0 8600 0.9690 47.2502 36.759 44.4381 44.8798 18.9525
0.1374 44.0 8800 0.9791 47.3719 36.8917 44.577 44.9546 18.9525
0.1258 45.0 9000 0.9796 47.3306 36.9041 44.4739 44.8264 18.9725
0.1258 46.0 9200 0.9824 47.1484 36.847 44.2686 44.6887 18.9525
0.1258 47.0 9400 1.0006 47.1981 36.8111 44.3574 44.7138 18.9525
0.1179 48.0 9600 0.9993 47.314 36.7132 44.0765 44.5151 18.9525
0.1179 49.0 9800 1.0100 47.0527 36.7627 44.1905 44.5119 18.9525
0.1095 50.0 10000 1.0155 47.127 36.773 44.3325 44.6517 18.9525
0.1095 51.0 10200 1.0182 47.1701 36.7509 44.2938 44.6916 18.9725
0.1095 52.0 10400 1.0242 47.2623 36.8327 44.4037 44.7943 18.9725
0.1004 53.0 10600 1.0275 47.5715 37.1557 44.6796 45.0297 18.9725
0.1004 54.0 10800 1.0359 47.3342 36.9982 44.469 44.8337 18.9525
0.0936 55.0 11000 1.0366 47.6092 37.1985 44.7346 45.0989 18.9725
0.0936 56.0 11200 1.0535 47.6625 37.2267 44.6937 45.0813 18.9525
0.0936 57.0 11400 1.0434 47.1472 36.736 44.3177 44.641 18.9525
0.0868 58.0 11600 1.0535 47.1669 36.63 44.3785 44.7253 18.9525
0.0868 59.0 11800 1.0524 47.0978 36.46 44.1152 44.4164 18.9525
0.0816 60.0 12000 1.0629 46.9521 36.4969 44.0844 44.4438 18.9725
0.0816 61.0 12200 1.0650 47.2896 36.9284 44.4427 44.8343 18.9725
0.0816 62.0 12400 1.0756 47.2056 36.6007 44.2689 44.6388 18.9725
0.0763 63.0 12600 1.0757 47.2394 36.8165 44.256 44.561 18.9725
0.0763 64.0 12800 1.0808 47.2861 36.8009 44.3111 44.6663 18.9725
0.0739 65.0 13000 1.0871 47.0393 36.4886 44.108 44.4587 18.9725
0.0739 66.0 13200 1.0935 47.0034 36.6509 43.99 44.3965 18.9525
0.0739 67.0 13400 1.0916 47.0806 36.6237 44.0661 44.5176 18.9725
0.068 68.0 13600 1.1006 47.1444 36.5177 44.2365 44.6788 18.9725
0.068 69.0 13800 1.1053 47.0907 36.4401 44.1416 44.5535 18.9725
0.0643 70.0 14000 1.1006 47.2846 36.7274 44.3121 44.7264 18.9725
0.0643 71.0 14200 1.1139 47.4036 36.9528 44.5044 44.9003 18.9725
0.0643 72.0 14400 1.1099 47.3805 37.0484 44.5352 44.935 18.9725
0.0623 73.0 14600 1.1126 47.2923 36.7686 44.3123 44.717 18.9725
0.0623 74.0 14800 1.1197 47.316 36.8541 44.3815 44.8115 18.9725
0.0581 75.0 15000 1.1175 47.3956 36.9679 44.3779 44.8287 18.9725
0.0581 76.0 15200 1.1334 47.0912 36.6596 44.2089 44.6322 18.9725
0.0581 77.0 15400 1.1302 47.3066 36.8107 44.4113 44.8553 18.9725
0.0548 78.0 15600 1.1360 47.3241 36.9129 44.5069 44.922 18.9725
0.0548 79.0 15800 1.1353 47.2705 37.0027 44.4539 44.8693 18.9725
0.0525 80.0 16000 1.1394 47.2088 36.8393 44.3551 44.7349 18.9725
0.0525 81.0 16200 1.1467 47.1913 36.7994 44.3602 44.7693 18.9725
0.0525 82.0 16400 1.1516 47.0243 36.6827 44.2269 44.5925 18.9725
0.0499 83.0 16600 1.1481 47.2883 36.7582 44.5134 44.8985 18.9725
0.0499 84.0 16800 1.1481 47.2414 36.8938 44.4629 44.8504 18.9725
0.0488 85.0 17000 1.1659 47.0325 36.7187 44.1609 44.574 18.9725
0.0488 86.0 17200 1.1608 47.0348 36.7733 44.2843 44.755 18.9725
0.0488 87.0 17400 1.1620 47.289 36.957 44.3967 44.833 18.9725
0.0459 88.0 17600 1.1640 47.2488 37.0562 44.4618 44.8901 18.9725
0.0459 89.0 17800 1.1611 47.253 36.8942 44.3236 44.7534 18.9725
0.0433 90.0 18000 1.1713 47.0768 36.7887 44.1503 44.6221 18.9725
0.0433 91.0 18200 1.1760 47.2611 36.91 44.3145 44.7267 18.9725
0.0433 92.0 18400 1.1742 47.1569 36.8205 44.1965 44.6291 18.9725
0.0429 93.0 18600 1.1802 47.1488 36.8472 44.2746 44.7273 18.9725
0.0429 94.0 18800 1.1776 47.1428 36.8405 44.2248 44.677 18.9725
0.0406 95.0 19000 1.1787 47.2424 37.0243 44.3605 44.8277 18.9725
0.0406 96.0 19200 1.1888 46.9867 36.8466 44.138 44.6028 18.9725
0.0406 97.0 19400 1.1842 47.221 36.9451 44.3828 44.8279 18.9725
0.0402 98.0 19600 1.1931 47.3532 36.9798 44.4183 44.8908 18.9725
0.0402 99.0 19800 1.1910 47.3024 37.0443 44.4254 44.8128 18.9725
0.0379 100.0 20000 1.1866 47.0876 36.7997 44.2002 44.5963 18.9725
0.0379 101.0 20200 1.1954 47.3442 36.8921 44.5062 44.9326 18.9725
0.0379 102.0 20400 1.1932 47.3439 36.9949 44.4978 44.9289 18.9725
0.0371 103.0 20600 1.1995 47.4909 37.1924 44.627 44.9876 18.9725
0.0371 104.0 20800 1.1873 47.3608 37.1436 44.5186 44.8913 18.9725
0.0371 105.0 21000 1.2004 47.2225 36.947 44.2986 44.7392 18.9725
0.0371 106.0 21200 1.2038 47.3322 37.1391 44.4508 44.8944 18.9725
0.0371 107.0 21400 1.2032 47.4927 37.2393 44.5274 44.9546 18.9725
0.0351 108.0 21600 1.2088 47.1914 36.9084 44.2846 44.6942 18.9725
0.0351 109.0 21800 1.2055 47.1807 37.0308 44.2609 44.6812 18.9725
0.0342 110.0 22000 1.2033 47.3249 37.188 44.4933 44.9173 18.9725
0.0342 111.0 22200 1.2109 47.3209 37.2169 44.43 44.8419 18.9725
0.0342 112.0 22400 1.2112 47.2884 37.0231 44.4526 44.8678 18.9725
0.0339 113.0 22600 1.2122 47.4514 37.1338 44.5042 44.9023 18.9725
0.0339 114.0 22800 1.2133 47.4942 37.2246 44.6414 45.0367 18.9725
0.0319 115.0 23000 1.2188 47.3496 37.07 44.4763 44.8769 18.9725
0.0319 116.0 23200 1.2196 47.3476 37.0494 44.4154 44.8526 18.9725
0.0319 117.0 23400 1.2184 47.3939 37.0739 44.4843 44.8791 18.9725
0.0318 118.0 23600 1.2153 47.297 37.1253 44.4336 44.8667 18.9725
0.0318 119.0 23800 1.2204 47.2655 37.0161 44.315 44.7425 18.9725
0.031 120.0 24000 1.2300 47.1659 36.9164 44.2885 44.6854 18.9725
0.031 121.0 24200 1.2244 47.2323 37.0646 44.3231 44.7741 18.9725
0.031 122.0 24400 1.2246 47.2887 37.1099 44.4102 44.8013 18.9725
0.0314 123.0 24600 1.2227 47.2844 37.1004 44.477 44.8791 18.9725
0.0314 124.0 24800 1.2261 47.4595 37.182 44.525 44.9282 18.9725
0.0299 125.0 25000 1.2250 47.4474 37.1837 44.4691 44.8932 18.9725
0.0299 126.0 25200 1.2270 47.3974 37.1118 44.4632 44.8601 18.9725
0.0299 127.0 25400 1.2268 47.4627 37.1918 44.5778 45.0057 18.9725
0.0304 128.0 25600 1.2300 47.5374 37.3058 44.5345 44.9816 18.9725
0.0304 129.0 25800 1.2320 47.5205 37.2863 44.5928 44.9842 18.9725
0.0283 130.0 26000 1.2337 47.3531 37.2235 44.538 44.9476 18.9725
0.0283 131.0 26200 1.2374 47.3214 37.0934 44.5008 44.897 18.9725
0.0283 132.0 26400 1.2372 47.3673 37.0916 44.4828 44.9017 18.9725
0.0292 133.0 26600 1.2376 47.3677 37.065 44.4243 44.8378 18.9725
0.0292 134.0 26800 1.2361 47.3707 37.1482 44.4561 44.8555 18.9725
0.0277 135.0 27000 1.2375 47.1611 37.016 44.2671 44.7125 18.9725
0.0277 136.0 27200 1.2408 47.2849 37.0969 44.4603 44.8522 18.9725
0.0277 137.0 27400 1.2387 47.3732 37.1009 44.4399 44.8788 18.9725
0.0287 138.0 27600 1.2379 47.3887 37.1236 44.4965 44.946 18.9725
0.0287 139.0 27800 1.2413 47.2686 37.0526 44.4412 44.8908 18.9725
0.0275 140.0 28000 1.2436 47.1805 36.9982 44.2954 44.7762 18.9725
0.0275 141.0 28200 1.2419 47.3737 37.1899 44.5507 45.0069 18.9725
0.0275 142.0 28400 1.2420 47.3535 37.1088 44.4099 44.8821 18.9725
0.0275 143.0 28600 1.2417 47.3146 37.0719 44.3936 44.8605 18.9725
0.0275 144.0 28800 1.2416 47.2858 37.0775 44.4035 44.8692 18.9725
0.0277 145.0 29000 1.2418 47.3574 37.1278 44.4706 44.9182 18.9725
0.0277 146.0 29200 1.2423 47.4899 37.2542 44.5283 44.9664 18.9725
0.0277 147.0 29400 1.2426 47.3521 37.1389 44.434 44.8793 18.9725
0.0276 148.0 29600 1.2428 47.3361 37.1177 44.4202 44.8607 18.9725
0.0276 149.0 29800 1.2431 47.3633 37.1581 44.4518 44.8961 18.9725
0.0272 150.0 30000 1.2433 47.379 37.1581 44.4701 44.9076 18.9725

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.1.2
  • Datasets 2.1.0
  • Tokenizers 0.15.2