mBART-07-TextSimp-LT-BatchSize4-lr1e-4
This model is a fine-tuned version of facebook/mbart-large-50 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0969
- Rouge1: 0.7532
- Rouge2: 0.597
- Rougel: 0.7486
- Sacrebleu: 52.2073
- Gen Len: 36.8624
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Sacrebleu | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 14.7859 | 0.03 | 10 | 13.1919 | 0.3128 | 0.203 | 0.296 | 6.4046 | 512.0 |
| 12.8117 | 0.06 | 20 | 11.9552 | 0.2352 | 0.1537 | 0.2202 | 9.4123 | 512.0 |
| 11.6948 | 0.09 | 30 | 11.1898 | 0.3066 | 0.2046 | 0.2889 | 3.1466 | 512.0 |
| 11.0142 | 0.12 | 40 | 10.4292 | 0.42 | 0.273 | 0.392 | 10.2095 | 512.0 |
| 10.2023 | 0.15 | 50 | 9.5371 | 0.2941 | 0.1894 | 0.2741 | 7.5189 | 512.0 |
| 9.4656 | 0.18 | 60 | 8.6433 | 0.0885 | 0.0565 | 0.0834 | 2.9693 | 512.0 |
| 8.4662 | 0.21 | 70 | 7.7409 | 0.0481 | 0.0293 | 0.0456 | 2.0228 | 512.0 |
| 7.5674 | 0.24 | 80 | 6.7421 | 0.2868 | 0.191 | 0.2754 | 11.5576 | 506.5661 |
| 6.5888 | 0.27 | 90 | 5.6548 | 0.5541 | 0.3894 | 0.5413 | 33.1887 | 65.7196 |
| 5.4845 | 0.3 | 100 | 4.4588 | 0.6149 | 0.4296 | 0.5976 | 35.8204 | 38.9206 |
| 4.2194 | 0.33 | 110 | 3.1654 | 0.6209 | 0.4384 | 0.6068 | 36.664 | 38.1746 |
| 2.9043 | 0.36 | 120 | 1.8555 | 0.6259 | 0.4444 | 0.6157 | 37.0135 | 37.7778 |
| 1.634 | 0.39 | 130 | 0.8079 | 0.6271 | 0.4449 | 0.6186 | 36.9351 | 37.0741 |
| 0.6974 | 0.42 | 140 | 0.3299 | 0.6326 | 0.4486 | 0.6213 | 37.5302 | 36.8677 |
| 0.3001 | 0.45 | 150 | 0.2071 | 0.6385 | 0.4579 | 0.6304 | 38.5749 | 36.8624 |
| 0.2017 | 0.48 | 160 | 0.1785 | 0.6332 | 0.4663 | 0.6259 | 38.7054 | 36.8624 |
| 0.1912 | 0.51 | 170 | 0.1621 | 0.6222 | 0.4441 | 0.6139 | 37.1654 | 36.8624 |
| 0.1654 | 0.54 | 180 | 0.1432 | 0.6242 | 0.4455 | 0.614 | 37.8602 | 36.8677 |
| 0.148 | 0.57 | 190 | 0.1288 | 0.6309 | 0.4619 | 0.6198 | 39.1955 | 36.8624 |
| 0.1253 | 0.6 | 200 | 0.1201 | 0.6284 | 0.4639 | 0.6213 | 39.0881 | 36.8677 |
| 0.1193 | 0.63 | 210 | 0.1107 | 0.6371 | 0.4688 | 0.628 | 40.2517 | 36.8677 |
| 0.1157 | 0.66 | 220 | 0.1036 | 0.6333 | 0.4618 | 0.6253 | 37.952 | 36.8624 |
| 0.1201 | 0.69 | 230 | 0.1002 | 0.6412 | 0.4725 | 0.6357 | 40.6338 | 36.8624 |
| 0.1271 | 0.72 | 240 | 0.0997 | 0.6297 | 0.4528 | 0.623 | 39.4846 | 36.8624 |
| 0.1007 | 0.75 | 250 | 0.0997 | 0.6373 | 0.4672 | 0.6284 | 39.5872 | 36.8624 |
| 0.1053 | 0.78 | 260 | 0.0969 | 0.6468 | 0.4809 | 0.6394 | 41.4503 | 36.8624 |
| 0.1113 | 0.81 | 270 | 0.0926 | 0.6476 | 0.4726 | 0.6373 | 40.325 | 36.8624 |
| 0.1286 | 0.84 | 280 | 0.0910 | 0.6602 | 0.4939 | 0.6532 | 42.0454 | 36.8624 |
| 0.117 | 0.87 | 290 | 0.0911 | 0.645 | 0.4697 | 0.6361 | 40.2852 | 36.8624 |
| 0.1101 | 0.9 | 300 | 0.0919 | 0.6367 | 0.4708 | 0.6309 | 41.2572 | 36.8624 |
| 0.1049 | 0.93 | 310 | 0.0927 | 0.6409 | 0.4708 | 0.633 | 40.4421 | 36.8677 |
| 0.1056 | 0.96 | 320 | 0.0900 | 0.6486 | 0.4728 | 0.6378 | 39.8952 | 36.873 |
| 0.0938 | 0.99 | 330 | 0.0887 | 0.6534 | 0.48 | 0.6458 | 41.5663 | 36.8624 |
| 0.0752 | 1.02 | 340 | 0.0892 | 0.6521 | 0.4803 | 0.6444 | 42.2437 | 36.8624 |
| 0.0755 | 1.05 | 350 | 0.0865 | 0.6576 | 0.4872 | 0.6516 | 42.9283 | 36.8624 |
| 0.0742 | 1.08 | 360 | 0.0860 | 0.6605 | 0.4929 | 0.6546 | 42.836 | 36.8624 |
| 0.0943 | 1.11 | 370 | 0.0839 | 0.6619 | 0.4974 | 0.655 | 43.4383 | 36.8624 |
| 0.0828 | 1.14 | 380 | 0.0864 | 0.6534 | 0.4868 | 0.6468 | 42.0519 | 36.8624 |
| 0.086 | 1.17 | 390 | 0.0863 | 0.647 | 0.4754 | 0.6399 | 42.2711 | 36.8624 |
| 0.0936 | 1.2 | 400 | 0.0851 | 0.6468 | 0.4713 | 0.6403 | 41.1584 | 36.8624 |
| 0.0679 | 1.23 | 410 | 0.0887 | 0.6477 | 0.4785 | 0.64 | 42.3848 | 36.8624 |
| 0.0837 | 1.26 | 420 | 0.0859 | 0.6474 | 0.4794 | 0.6399 | 41.7297 | 36.8624 |
| 0.0734 | 1.29 | 430 | 0.0851 | 0.6431 | 0.4748 | 0.6368 | 39.308 | 36.8624 |
| 0.0783 | 1.32 | 440 | 0.0850 | 0.6517 | 0.4818 | 0.6433 | 41.8024 | 36.8624 |
| 0.0827 | 1.35 | 450 | 0.0869 | 0.6533 | 0.4879 | 0.6458 | 42.4777 | 36.8624 |
| 0.0752 | 1.38 | 460 | 0.0856 | 0.6517 | 0.4848 | 0.6439 | 42.3615 | 36.8624 |
| 0.1051 | 1.41 | 470 | 0.0862 | 0.6563 | 0.4749 | 0.647 | 40.4435 | 36.8624 |
| 0.0955 | 1.44 | 480 | 1.2108 | 0.5138 | 0.3383 | 0.4955 | 22.1136 | 48.9841 |
| 0.3603 | 1.47 | 490 | 0.1833 | 0.6042 | 0.4171 | 0.5868 | 32.7718 | 37.8413 |
| 0.1637 | 1.5 | 500 | 0.1536 | 0.6031 | 0.4203 | 0.591 | 32.4129 | 36.8995 |
| 0.1396 | 1.53 | 510 | 0.1007 | 0.6333 | 0.4598 | 0.6243 | 39.7844 | 36.9206 |
| 0.0957 | 1.56 | 520 | 0.0904 | 0.6367 | 0.4627 | 0.631 | 40.8284 | 36.8624 |
| 0.0884 | 1.59 | 530 | 0.0912 | 0.6448 | 0.4797 | 0.6368 | 41.3376 | 36.8624 |
| 0.0892 | 1.62 | 540 | 0.0840 | 0.6891 | 0.5061 | 0.6809 | 40.3068 | 36.8624 |
| 0.0921 | 1.65 | 550 | 0.0814 | 0.6911 | 0.5109 | 0.6815 | 41.431 | 36.8624 |
| 0.0828 | 1.68 | 560 | 0.0767 | 0.7093 | 0.5277 | 0.7 | 43.3709 | 36.8624 |
| 0.091 | 1.71 | 570 | 0.0763 | 0.7026 | 0.5223 | 0.6943 | 42.9239 | 36.8624 |
| 0.0695 | 1.74 | 580 | 0.0789 | 0.7048 | 0.5284 | 0.6968 | 43.9802 | 36.8624 |
| 0.0748 | 1.77 | 590 | 0.0760 | 0.6954 | 0.5078 | 0.6871 | 43.3337 | 36.8624 |
| 0.0898 | 1.8 | 600 | 0.0755 | 0.6956 | 0.5141 | 0.6896 | 43.3296 | 36.8624 |
| 0.0694 | 1.83 | 610 | 0.0750 | 0.7123 | 0.5298 | 0.705 | 44.0335 | 36.8624 |
| 0.0655 | 1.86 | 620 | 0.0774 | 0.7056 | 0.527 | 0.698 | 43.7464 | 36.8624 |
| 0.0839 | 1.89 | 630 | 0.0744 | 0.7069 | 0.5227 | 0.6982 | 43.2583 | 36.8624 |
| 0.0568 | 1.92 | 640 | 0.0766 | 0.7024 | 0.5233 | 0.6946 | 42.8289 | 36.8624 |
| 0.0899 | 1.95 | 650 | 0.0756 | 0.6944 | 0.5102 | 0.6885 | 42.4079 | 36.8624 |
| 0.0711 | 1.98 | 660 | 0.0749 | 0.7197 | 0.5414 | 0.7127 | 45.3782 | 36.8624 |
| 0.0624 | 2.01 | 670 | 0.0735 | 0.7072 | 0.5332 | 0.7007 | 44.9704 | 36.8624 |
| 0.046 | 2.04 | 680 | 0.0765 | 0.705 | 0.5254 | 0.6991 | 43.4195 | 36.8624 |
| 0.0496 | 2.07 | 690 | 0.0753 | 0.6946 | 0.5345 | 0.6871 | 46.0032 | 36.8624 |
| 0.0495 | 2.1 | 700 | 0.0752 | 0.7219 | 0.5522 | 0.7147 | 46.518 | 36.8624 |
| 0.0424 | 2.13 | 710 | 0.0743 | 0.7202 | 0.5475 | 0.7138 | 45.6772 | 36.8624 |
| 0.0445 | 2.16 | 720 | 0.0717 | 0.729 | 0.561 | 0.7235 | 46.9056 | 36.8624 |
| 0.0364 | 2.19 | 730 | 0.0737 | 0.7318 | 0.5652 | 0.7256 | 47.2385 | 36.8624 |
| 0.0453 | 2.22 | 740 | 0.0732 | 0.7238 | 0.5563 | 0.7175 | 46.1528 | 36.8624 |
| 0.0475 | 2.25 | 750 | 0.0726 | 0.7249 | 0.5569 | 0.7207 | 46.1736 | 36.8624 |
| 0.0457 | 2.28 | 760 | 0.0734 | 0.7334 | 0.565 | 0.727 | 47.3347 | 36.8624 |
| 0.0376 | 2.31 | 770 | 0.0752 | 0.7221 | 0.5509 | 0.7153 | 46.8081 | 36.8624 |
| 0.0408 | 2.34 | 780 | 0.0748 | 0.7276 | 0.5531 | 0.7196 | 46.6557 | 36.8624 |
| 0.0473 | 2.37 | 790 | 0.0722 | 0.732 | 0.5585 | 0.725 | 46.7713 | 36.8624 |
| 0.0458 | 2.4 | 800 | 0.0728 | 0.7369 | 0.5725 | 0.7297 | 47.404 | 36.8624 |
| 0.0439 | 2.43 | 810 | 0.0744 | 0.7376 | 0.5681 | 0.7307 | 46.9208 | 36.8624 |
| 0.0459 | 2.46 | 820 | 0.0743 | 0.7349 | 0.5747 | 0.7275 | 47.9425 | 36.8624 |
| 0.0468 | 2.49 | 830 | 0.0761 | 0.7272 | 0.5542 | 0.7191 | 46.0289 | 36.8624 |
| 0.0546 | 2.51 | 840 | 0.0731 | 0.7205 | 0.5531 | 0.7144 | 47.9148 | 36.8624 |
| 0.0543 | 2.54 | 850 | 0.0717 | 0.7212 | 0.5554 | 0.7155 | 47.4989 | 36.8624 |
| 0.0607 | 2.57 | 860 | 0.0729 | 0.7233 | 0.5506 | 0.7151 | 46.7833 | 36.8624 |
| 0.0513 | 2.6 | 870 | 0.0750 | 0.7287 | 0.5585 | 0.7227 | 48.1438 | 36.8624 |
| 0.0409 | 2.63 | 880 | 0.0732 | 0.73 | 0.5603 | 0.7216 | 47.4183 | 36.8624 |
| 0.0591 | 2.66 | 890 | 0.0735 | 0.7262 | 0.547 | 0.7181 | 46.2204 | 36.8624 |
| 0.0496 | 2.69 | 900 | 0.0734 | 0.7208 | 0.5483 | 0.7149 | 46.2148 | 36.8624 |
| 0.0415 | 2.72 | 910 | 0.0712 | 0.7255 | 0.5529 | 0.7176 | 46.6695 | 36.8624 |
| 0.0611 | 2.75 | 920 | 0.0706 | 0.7256 | 0.554 | 0.7194 | 46.8234 | 36.8624 |
| 0.0393 | 2.78 | 930 | 0.0710 | 0.7299 | 0.5661 | 0.7251 | 48.0862 | 36.8624 |
| 0.0437 | 2.81 | 940 | 0.0714 | 0.7284 | 0.5646 | 0.7223 | 48.1591 | 36.8624 |
| 0.0394 | 2.84 | 950 | 0.0711 | 0.7346 | 0.5685 | 0.728 | 48.2561 | 36.8624 |
| 0.0476 | 2.87 | 960 | 0.0705 | 0.7299 | 0.5583 | 0.7239 | 46.812 | 36.8624 |
| 0.049 | 2.9 | 970 | 0.0716 | 0.7302 | 0.5607 | 0.7237 | 47.2608 | 36.8624 |
| 0.0442 | 2.93 | 980 | 0.0701 | 0.7334 | 0.5621 | 0.7253 | 47.3573 | 36.8624 |
| 0.0498 | 2.96 | 990 | 0.0710 | 0.7319 | 0.5574 | 0.7251 | 47.6192 | 36.8624 |
| 0.0392 | 2.99 | 1000 | 0.0714 | 0.7347 | 0.565 | 0.7269 | 48.0873 | 36.8624 |
| 0.0352 | 3.02 | 1010 | 0.0702 | 0.7401 | 0.5722 | 0.7301 | 48.2069 | 36.8624 |
| 0.023 | 3.05 | 1020 | 0.0754 | 0.7379 | 0.5742 | 0.7312 | 48.5603 | 36.8624 |
| 0.0258 | 3.08 | 1030 | 0.0766 | 0.7401 | 0.5723 | 0.733 | 49.2376 | 36.8624 |
| 0.0239 | 3.11 | 1040 | 0.0753 | 0.7358 | 0.565 | 0.7294 | 49.1768 | 36.8624 |
| 0.0267 | 3.14 | 1050 | 0.0729 | 0.7255 | 0.5525 | 0.7189 | 48.0582 | 36.8624 |
| 0.0283 | 3.17 | 1060 | 0.0745 | 0.7359 | 0.569 | 0.7284 | 48.0218 | 36.8624 |
| 0.0194 | 3.2 | 1070 | 0.0764 | 0.7347 | 0.5648 | 0.7248 | 47.8116 | 36.8624 |
| 0.0242 | 3.23 | 1080 | 0.0757 | 0.7281 | 0.553 | 0.7204 | 47.0052 | 36.8624 |
| 0.0309 | 3.26 | 1090 | 0.0746 | 0.7311 | 0.5631 | 0.7245 | 48.0906 | 36.8624 |
| 0.0222 | 3.29 | 1100 | 0.0758 | 0.7344 | 0.5631 | 0.7266 | 48.4209 | 36.8624 |
| 0.0269 | 3.32 | 1110 | 0.0747 | 0.7335 | 0.5676 | 0.7264 | 48.5228 | 36.8624 |
| 0.0278 | 3.35 | 1120 | 0.0762 | 0.7369 | 0.5717 | 0.7316 | 49.1179 | 36.8624 |
| 0.0252 | 3.38 | 1130 | 0.0735 | 0.7398 | 0.5708 | 0.7344 | 48.7544 | 36.8624 |
| 0.023 | 3.41 | 1140 | 0.0741 | 0.743 | 0.5755 | 0.7363 | 48.9395 | 36.8624 |
| 0.0243 | 3.44 | 1150 | 0.0731 | 0.7497 | 0.5869 | 0.7426 | 49.6457 | 36.8624 |
| 0.0257 | 3.47 | 1160 | 0.0722 | 0.7455 | 0.5854 | 0.7395 | 49.6377 | 36.8624 |
| 0.0235 | 3.5 | 1170 | 0.0730 | 0.7437 | 0.5782 | 0.7356 | 48.4684 | 36.8624 |
| 0.0271 | 3.53 | 1180 | 0.0738 | 0.7458 | 0.5851 | 0.7389 | 48.8971 | 36.8624 |
| 0.0245 | 3.56 | 1190 | 0.0733 | 0.7396 | 0.5699 | 0.7335 | 48.0606 | 36.8624 |
| 0.0271 | 3.59 | 1200 | 0.0739 | 0.7373 | 0.5655 | 0.73 | 48.0489 | 36.8624 |
| 0.0233 | 3.62 | 1210 | 0.0755 | 0.7417 | 0.5748 | 0.7349 | 49.7122 | 36.8624 |
| 0.0215 | 3.65 | 1220 | 0.0740 | 0.7345 | 0.5633 | 0.7278 | 48.8137 | 36.8624 |
| 0.0267 | 3.68 | 1230 | 0.0720 | 0.7324 | 0.559 | 0.7244 | 48.391 | 36.8624 |
| 0.0314 | 3.71 | 1240 | 0.0716 | 0.7414 | 0.5755 | 0.7329 | 49.7737 | 36.8624 |
| 0.0197 | 3.74 | 1250 | 0.0741 | 0.7427 | 0.582 | 0.7346 | 49.904 | 36.8624 |
| 0.0218 | 3.77 | 1260 | 0.0733 | 0.7445 | 0.5777 | 0.7363 | 49.6828 | 36.8624 |
| 0.0213 | 3.8 | 1270 | 0.0748 | 0.7433 | 0.5812 | 0.7354 | 49.4005 | 36.8624 |
| 0.027 | 3.83 | 1280 | 0.0734 | 0.7427 | 0.5823 | 0.7365 | 49.6604 | 36.8624 |
| 0.0227 | 3.86 | 1290 | 0.0728 | 0.7435 | 0.5891 | 0.7379 | 49.7843 | 36.8624 |
| 0.0277 | 3.89 | 1300 | 0.0733 | 0.7455 | 0.5887 | 0.7394 | 51.0555 | 36.8624 |
| 0.0302 | 3.92 | 1310 | 0.0743 | 0.7495 | 0.5961 | 0.742 | 50.1856 | 36.8624 |
| 0.0333 | 3.95 | 1320 | 0.0724 | 0.7432 | 0.5811 | 0.7376 | 49.1899 | 36.8624 |
| 0.0296 | 3.98 | 1330 | 0.0735 | 0.7384 | 0.5716 | 0.7326 | 49.092 | 36.8624 |
| 0.0235 | 4.01 | 1340 | 0.0744 | 0.7309 | 0.5603 | 0.7242 | 47.5228 | 36.8624 |
| 0.0156 | 4.04 | 1350 | 0.0793 | 0.7288 | 0.5544 | 0.7201 | 48.2541 | 36.8624 |
| 0.0152 | 4.07 | 1360 | 0.0812 | 0.7396 | 0.571 | 0.731 | 50.2477 | 36.8624 |
| 0.013 | 4.1 | 1370 | 0.0820 | 0.7443 | 0.5727 | 0.7365 | 49.8545 | 36.8624 |
| 0.0158 | 4.13 | 1380 | 0.0790 | 0.7427 | 0.5756 | 0.7358 | 49.1009 | 36.8624 |
| 0.013 | 4.16 | 1390 | 0.0788 | 0.745 | 0.5838 | 0.7389 | 49.5321 | 36.8624 |
| 0.0155 | 4.19 | 1400 | 0.0804 | 0.7452 | 0.5766 | 0.7386 | 49.9997 | 36.8624 |
| 0.014 | 4.22 | 1410 | 0.0801 | 0.7507 | 0.5835 | 0.7423 | 50.5687 | 36.8624 |
| 0.0148 | 4.25 | 1420 | 0.0803 | 0.7486 | 0.5834 | 0.7413 | 49.6783 | 36.8624 |
| 0.0156 | 4.28 | 1430 | 0.0810 | 0.7467 | 0.5789 | 0.7393 | 49.539 | 36.8624 |
| 0.0177 | 4.31 | 1440 | 0.0797 | 0.7455 | 0.5778 | 0.7397 | 49.7474 | 36.8624 |
| 0.0127 | 4.34 | 1450 | 0.0797 | 0.7494 | 0.5877 | 0.7441 | 50.3975 | 36.8624 |
| 0.0157 | 4.37 | 1460 | 0.0803 | 0.7512 | 0.5886 | 0.7443 | 50.7034 | 36.8624 |
| 0.0156 | 4.4 | 1470 | 0.0776 | 0.7477 | 0.586 | 0.7406 | 50.6352 | 36.8624 |
| 0.0134 | 4.43 | 1480 | 0.0785 | 0.7478 | 0.5868 | 0.7422 | 50.7212 | 36.8624 |
| 0.0179 | 4.46 | 1490 | 0.0787 | 0.7425 | 0.5743 | 0.7364 | 49.7374 | 36.8624 |
| 0.0141 | 4.49 | 1500 | 0.0787 | 0.7473 | 0.5805 | 0.7409 | 49.5875 | 36.8624 |
| 0.018 | 4.52 | 1510 | 0.0780 | 0.7442 | 0.5787 | 0.7377 | 49.8008 | 36.8624 |
| 0.0168 | 4.55 | 1520 | 0.0759 | 0.7436 | 0.58 | 0.738 | 50.2142 | 36.8624 |
| 0.0143 | 4.58 | 1530 | 0.0781 | 0.747 | 0.582 | 0.7409 | 50.4379 | 36.8624 |
| 0.0168 | 4.61 | 1540 | 0.0805 | 0.7485 | 0.5828 | 0.7425 | 50.4126 | 36.8624 |
| 0.0137 | 4.64 | 1550 | 0.0795 | 0.7548 | 0.5943 | 0.7493 | 51.0014 | 36.8624 |
| 0.0151 | 4.67 | 1560 | 0.0806 | 0.7511 | 0.592 | 0.7452 | 50.7105 | 36.8624 |
| 0.0151 | 4.7 | 1570 | 0.0810 | 0.7496 | 0.5851 | 0.744 | 49.794 | 36.8624 |
| 0.015 | 4.73 | 1580 | 0.0805 | 0.7452 | 0.5803 | 0.7404 | 50.0951 | 36.8624 |
| 0.0174 | 4.76 | 1590 | 0.0776 | 0.7473 | 0.5865 | 0.7427 | 51.0089 | 36.8624 |
| 0.0168 | 4.79 | 1600 | 0.0773 | 0.748 | 0.5909 | 0.7428 | 50.9827 | 36.8624 |
| 0.0121 | 4.82 | 1610 | 0.0796 | 0.747 | 0.5908 | 0.7409 | 50.3291 | 36.8624 |
| 0.016 | 4.85 | 1620 | 0.0798 | 0.7484 | 0.59 | 0.7427 | 51.2771 | 36.8624 |
| 0.0189 | 4.88 | 1630 | 0.0792 | 0.7389 | 0.5749 | 0.7325 | 49.6217 | 36.8624 |
| 0.014 | 4.91 | 1640 | 0.0796 | 0.7446 | 0.5822 | 0.7391 | 50.3355 | 36.8624 |
| 0.0159 | 4.94 | 1650 | 0.0797 | 0.7447 | 0.5797 | 0.7394 | 50.0605 | 36.8624 |
| 0.0151 | 4.97 | 1660 | 0.0784 | 0.7396 | 0.5727 | 0.7321 | 49.5799 | 36.8624 |
| 0.0162 | 5.0 | 1670 | 0.0786 | 0.7396 | 0.5737 | 0.7348 | 49.5808 | 36.8624 |
| 0.0089 | 5.03 | 1680 | 0.0831 | 0.7405 | 0.5771 | 0.7355 | 49.9631 | 36.8624 |
| 0.0085 | 5.06 | 1690 | 0.0847 | 0.7469 | 0.5841 | 0.7411 | 50.409 | 36.8624 |
| 0.0093 | 5.09 | 1700 | 0.0844 | 0.7494 | 0.5878 | 0.7445 | 51.0126 | 36.8624 |
| 0.0083 | 5.12 | 1710 | 0.0825 | 0.7465 | 0.5819 | 0.7423 | 50.7735 | 36.8624 |
| 0.0077 | 5.15 | 1720 | 0.0832 | 0.7479 | 0.584 | 0.7428 | 50.1036 | 36.8624 |
| 0.0099 | 5.18 | 1730 | 0.0853 | 0.7509 | 0.5862 | 0.746 | 50.3001 | 36.8624 |
| 0.0112 | 5.21 | 1740 | 0.0851 | 0.7445 | 0.5783 | 0.7393 | 50.1143 | 36.8624 |
| 0.0087 | 5.24 | 1750 | 0.0857 | 0.7495 | 0.5881 | 0.7441 | 50.4766 | 36.8624 |
| 0.0077 | 5.27 | 1760 | 0.0883 | 0.7488 | 0.585 | 0.7434 | 50.4424 | 36.8624 |
| 0.0095 | 5.3 | 1770 | 0.0871 | 0.7455 | 0.5773 | 0.7403 | 49.888 | 36.8624 |
| 0.009 | 5.33 | 1780 | 0.0862 | 0.7423 | 0.5751 | 0.7388 | 50.7529 | 36.8624 |
| 0.0121 | 5.36 | 1790 | 0.0843 | 0.7486 | 0.5869 | 0.7441 | 50.8254 | 36.8624 |
| 0.0093 | 5.39 | 1800 | 0.0849 | 0.7505 | 0.5899 | 0.7462 | 50.4965 | 36.8624 |
| 0.0095 | 5.42 | 1810 | 0.0843 | 0.7525 | 0.5914 | 0.7467 | 50.9595 | 36.8624 |
| 0.0107 | 5.45 | 1820 | 0.0832 | 0.757 | 0.5956 | 0.7499 | 51.3853 | 36.8624 |
| 0.0086 | 5.48 | 1830 | 0.0822 | 0.7565 | 0.5932 | 0.7498 | 51.057 | 36.8624 |
| 0.01 | 5.51 | 1840 | 0.0803 | 0.7576 | 0.5971 | 0.7517 | 51.5254 | 36.8624 |
| 0.0103 | 5.54 | 1850 | 0.0813 | 0.7575 | 0.5978 | 0.7518 | 50.906 | 36.8624 |
| 0.0071 | 5.57 | 1860 | 0.0845 | 0.7502 | 0.5907 | 0.7444 | 50.8391 | 36.8624 |
| 0.0092 | 5.6 | 1870 | 0.0859 | 0.7559 | 0.5956 | 0.7504 | 50.9358 | 36.8624 |
| 0.011 | 5.63 | 1880 | 0.0842 | 0.7546 | 0.5921 | 0.7489 | 50.9914 | 36.8624 |
| 0.0098 | 5.66 | 1890 | 0.0817 | 0.7536 | 0.5951 | 0.7487 | 50.8027 | 36.8624 |
| 0.0092 | 5.69 | 1900 | 0.0838 | 0.7571 | 0.5986 | 0.7517 | 51.0588 | 36.8624 |
| 0.0089 | 5.72 | 1910 | 0.0850 | 0.7572 | 0.5981 | 0.7514 | 51.6142 | 36.8624 |
| 0.0108 | 5.75 | 1920 | 0.0859 | 0.7584 | 0.6011 | 0.7543 | 51.9107 | 36.8624 |
| 0.0098 | 5.78 | 1930 | 0.0863 | 0.7548 | 0.5962 | 0.7502 | 52.0843 | 36.8624 |
| 0.0096 | 5.81 | 1940 | 0.0852 | 0.7559 | 0.5947 | 0.7515 | 51.8232 | 36.8624 |
| 0.011 | 5.84 | 1950 | 0.0836 | 0.7514 | 0.5911 | 0.7475 | 51.5465 | 36.8624 |
| 0.0094 | 5.87 | 1960 | 0.0832 | 0.7497 | 0.5892 | 0.745 | 51.6388 | 36.8624 |
| 0.0094 | 5.9 | 1970 | 0.0848 | 0.7517 | 0.5945 | 0.7463 | 51.607 | 36.8624 |
| 0.0101 | 5.93 | 1980 | 0.0838 | 0.7547 | 0.5942 | 0.7493 | 51.8503 | 36.8624 |
| 0.0096 | 5.96 | 1990 | 0.0822 | 0.7537 | 0.5917 | 0.7476 | 51.6551 | 36.8624 |
| 0.0086 | 5.99 | 2000 | 0.0820 | 0.7526 | 0.5905 | 0.7461 | 51.3715 | 36.8624 |
| 0.0057 | 6.02 | 2010 | 0.0839 | 0.753 | 0.593 | 0.7467 | 51.3697 | 36.8624 |
| 0.0051 | 6.05 | 2020 | 0.0871 | 0.7521 | 0.5917 | 0.7455 | 51.1542 | 36.8624 |
| 0.0049 | 6.08 | 2030 | 0.0896 | 0.7571 | 0.6024 | 0.7515 | 51.388 | 36.8624 |
| 0.0056 | 6.11 | 2040 | 0.0917 | 0.7589 | 0.6041 | 0.7532 | 51.4198 | 36.8624 |
| 0.0044 | 6.14 | 2050 | 0.0933 | 0.7556 | 0.5964 | 0.7503 | 51.5014 | 36.8624 |
| 0.0042 | 6.17 | 2060 | 0.0939 | 0.7577 | 0.5987 | 0.7531 | 51.5153 | 36.8624 |
| 0.0055 | 6.2 | 2070 | 0.0933 | 0.7579 | 0.5971 | 0.7529 | 51.8076 | 36.8624 |
| 0.004 | 6.23 | 2080 | 0.0922 | 0.7541 | 0.5929 | 0.7499 | 51.5442 | 36.8624 |
| 0.0053 | 6.26 | 2090 | 0.0919 | 0.7555 | 0.5948 | 0.7508 | 51.5497 | 36.8624 |
| 0.0052 | 6.29 | 2100 | 0.0923 | 0.7496 | 0.5842 | 0.7445 | 50.9919 | 36.8624 |
| 0.0076 | 6.32 | 2110 | 0.0924 | 0.7518 | 0.5869 | 0.7464 | 50.8457 | 36.8624 |
| 0.006 | 6.35 | 2120 | 0.0920 | 0.7521 | 0.5887 | 0.7472 | 51.101 | 36.8624 |
| 0.0053 | 6.38 | 2130 | 0.0900 | 0.7536 | 0.5935 | 0.748 | 51.1847 | 36.8624 |
| 0.007 | 6.41 | 2140 | 0.0887 | 0.751 | 0.5898 | 0.7461 | 51.0116 | 36.8624 |
| 0.0054 | 6.44 | 2150 | 0.0875 | 0.7487 | 0.5865 | 0.7454 | 51.1587 | 36.8624 |
| 0.005 | 6.47 | 2160 | 0.0880 | 0.7455 | 0.5801 | 0.7412 | 50.6007 | 36.8624 |
| 0.0076 | 6.5 | 2170 | 0.0887 | 0.7491 | 0.5831 | 0.7444 | 50.6703 | 36.8624 |
| 0.0055 | 6.53 | 2180 | 0.0878 | 0.7476 | 0.5799 | 0.7418 | 50.6029 | 36.8624 |
| 0.0059 | 6.56 | 2190 | 0.0874 | 0.7492 | 0.5812 | 0.744 | 50.917 | 36.8624 |
| 0.0064 | 6.59 | 2200 | 0.0876 | 0.7524 | 0.5877 | 0.7466 | 51.2942 | 36.8624 |
| 0.0065 | 6.62 | 2210 | 0.0876 | 0.7544 | 0.5916 | 0.7491 | 51.7458 | 36.8624 |
| 0.0054 | 6.65 | 2220 | 0.0879 | 0.7548 | 0.5926 | 0.7494 | 51.7378 | 36.8624 |
| 0.0069 | 6.68 | 2230 | 0.0884 | 0.7556 | 0.5941 | 0.7504 | 51.6726 | 36.8624 |
| 0.0053 | 6.71 | 2240 | 0.0882 | 0.7529 | 0.5901 | 0.7486 | 51.6491 | 36.8624 |
| 0.0065 | 6.74 | 2250 | 0.0881 | 0.753 | 0.5914 | 0.7481 | 51.5642 | 36.8624 |
| 0.006 | 6.77 | 2260 | 0.0886 | 0.7535 | 0.5946 | 0.7492 | 51.9183 | 36.8624 |
| 0.0054 | 6.8 | 2270 | 0.0888 | 0.7539 | 0.5939 | 0.7484 | 51.7298 | 36.8624 |
| 0.0073 | 6.83 | 2280 | 0.0889 | 0.7548 | 0.5953 | 0.7495 | 51.8818 | 36.8624 |
| 0.0065 | 6.86 | 2290 | 0.0867 | 0.754 | 0.5944 | 0.7492 | 51.9493 | 36.8624 |
| 0.0065 | 6.89 | 2300 | 0.0858 | 0.7539 | 0.5923 | 0.7492 | 52.0167 | 36.8624 |
| 0.005 | 6.92 | 2310 | 0.0865 | 0.75 | 0.5905 | 0.7452 | 51.8096 | 36.8624 |
| 0.0078 | 6.95 | 2320 | 0.0865 | 0.7482 | 0.5898 | 0.7442 | 51.9398 | 36.8624 |
| 0.0084 | 6.98 | 2330 | 0.0863 | 0.7474 | 0.5867 | 0.7428 | 51.6422 | 36.8624 |
| 0.0055 | 7.01 | 2340 | 0.0864 | 0.7503 | 0.5899 | 0.7457 | 51.7704 | 36.8624 |
| 0.003 | 7.04 | 2350 | 0.0881 | 0.7493 | 0.5893 | 0.7453 | 51.4226 | 36.8624 |
| 0.0035 | 7.07 | 2360 | 0.0903 | 0.7521 | 0.5927 | 0.7479 | 51.4198 | 36.8624 |
| 0.0025 | 7.1 | 2370 | 0.0924 | 0.7511 | 0.5933 | 0.7467 | 51.6316 | 36.8624 |
| 0.0027 | 7.13 | 2380 | 0.0937 | 0.7521 | 0.5938 | 0.7479 | 51.8972 | 36.8624 |
| 0.004 | 7.16 | 2390 | 0.0943 | 0.756 | 0.5993 | 0.752 | 52.2357 | 36.8624 |
| 0.0034 | 7.19 | 2400 | 0.0946 | 0.7553 | 0.598 | 0.7508 | 52.2234 | 36.8624 |
| 0.0037 | 7.22 | 2410 | 0.0951 | 0.7536 | 0.596 | 0.7501 | 52.1319 | 36.8624 |
| 0.0024 | 7.25 | 2420 | 0.0957 | 0.7531 | 0.5955 | 0.7498 | 52.1583 | 36.8624 |
| 0.0031 | 7.28 | 2430 | 0.0965 | 0.7498 | 0.5901 | 0.7455 | 51.9043 | 36.8624 |
| 0.0033 | 7.31 | 2440 | 0.0966 | 0.7506 | 0.5919 | 0.7465 | 51.9556 | 36.8624 |
| 0.0032 | 7.34 | 2450 | 0.0969 | 0.7514 | 0.5934 | 0.7469 | 51.9301 | 36.8624 |
| 0.0037 | 7.37 | 2460 | 0.0972 | 0.7519 | 0.5946 | 0.7474 | 51.9706 | 36.8624 |
| 0.0027 | 7.4 | 2470 | 0.0973 | 0.7528 | 0.5965 | 0.748 | 52.1252 | 36.8624 |
| 0.0033 | 7.43 | 2480 | 0.0969 | 0.7514 | 0.5956 | 0.7474 | 52.0514 | 36.8624 |
| 0.0025 | 7.46 | 2490 | 0.0972 | 0.7535 | 0.5982 | 0.7488 | 52.0402 | 36.8624 |
| 0.0042 | 7.49 | 2500 | 0.0974 | 0.7528 | 0.597 | 0.7479 | 51.9109 | 36.8624 |
| 0.003 | 7.51 | 2510 | 0.0978 | 0.7543 | 0.5989 | 0.7498 | 51.9823 | 36.8624 |
| 0.0041 | 7.54 | 2520 | 0.0980 | 0.7526 | 0.5952 | 0.7479 | 51.7125 | 36.8624 |
| 0.0033 | 7.57 | 2530 | 0.0977 | 0.7523 | 0.5956 | 0.7473 | 51.703 | 36.8624 |
| 0.0035 | 7.6 | 2540 | 0.0972 | 0.7518 | 0.5968 | 0.7476 | 51.8299 | 36.8624 |
| 0.0046 | 7.63 | 2550 | 0.0969 | 0.7518 | 0.5964 | 0.7475 | 51.8676 | 36.8624 |
| 0.0031 | 7.66 | 2560 | 0.0967 | 0.752 | 0.5958 | 0.7479 | 51.9726 | 36.8624 |
| 0.0031 | 7.69 | 2570 | 0.0968 | 0.7511 | 0.594 | 0.7469 | 51.8623 | 36.8624 |
| 0.0035 | 7.72 | 2580 | 0.0968 | 0.752 | 0.5947 | 0.7479 | 51.9229 | 36.8624 |
| 0.0039 | 7.75 | 2590 | 0.0966 | 0.7524 | 0.5949 | 0.748 | 51.8871 | 36.8624 |
| 0.004 | 7.78 | 2600 | 0.0966 | 0.7529 | 0.5962 | 0.7484 | 52.042 | 36.8624 |
| 0.0038 | 7.81 | 2610 | 0.0966 | 0.7529 | 0.5964 | 0.7483 | 52.0266 | 36.8624 |
| 0.004 | 7.84 | 2620 | 0.0967 | 0.7533 | 0.5967 | 0.7485 | 52.134 | 36.8624 |
| 0.0035 | 7.87 | 2630 | 0.0968 | 0.7529 | 0.5966 | 0.7483 | 52.2201 | 36.8624 |
| 0.0038 | 7.9 | 2640 | 0.0968 | 0.7534 | 0.5972 | 0.7489 | 52.2577 | 36.8624 |
| 0.0028 | 7.93 | 2650 | 0.0969 | 0.7533 | 0.597 | 0.7487 | 52.2073 | 36.8624 |
| 0.0036 | 7.96 | 2660 | 0.0969 | 0.7533 | 0.597 | 0.7487 | 52.2073 | 36.8624 |
| 0.0037 | 7.99 | 2670 | 0.0969 | 0.7532 | 0.597 | 0.7486 | 52.2073 | 36.8624 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.1.2+cu121
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- -
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for eglkan1/mBART-07-TextSimp-LT-BatchSize4-lr1e-4
Base model
facebook/mbart-large-50