generated_from_trainer

<!-- 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. -->

t5-v1_1-large-fce-e8-b16

This model is a fine-tuned version of google/t5-v1_1-large on the None dataset. It achieves the following results on the evaluation set:

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:

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
3.325 0.06 100 0.7775 76.9422 69.1942 76.3689 76.3852 14.7545
0.9422 0.11 200 0.4327 85.6522 77.1791 85.0843 85.0849 15.0315
0.535 0.17 300 0.4081 85.8265 77.0897 85.2547 85.2421 14.8745
0.5003 0.23 400 0.4104 85.847 77.3884 85.3678 85.3536 14.8257
0.4734 0.28 500 0.3830 86.3501 78.2006 85.824 85.8541 14.8613
0.4439 0.34 600 0.3652 86.5106 78.4301 85.9794 85.9871 14.8644
0.4399 0.4 700 0.3656 86.3955 78.2086 85.8592 85.8785 14.8562
0.4259 0.45 800 0.3925 85.6654 77.0925 85.1468 85.1547 14.9142
0.4092 0.51 900 0.3720 86.317 78.3141 85.8151 85.7907 14.8859
0.4143 0.56 1000 0.3761 86.5432 78.4572 85.9424 85.9234 14.8763
0.4184 0.62 1100 0.3487 86.4053 78.5526 85.8508 85.8745 14.8909
0.4025 0.68 1200 0.3556 86.2418 78.2845 85.7291 85.7379 14.8603
0.4014 0.73 1300 0.3657 86.6544 78.9722 86.1314 86.1446 14.8257
0.379 0.79 1400 0.3512 86.6622 79.1939 86.1521 86.1383 14.8955
0.3898 0.85 1500 0.3517 86.1483 78.4144 85.5986 85.6256 14.8955
0.373 0.9 1600 0.3565 86.6775 79.0902 86.1475 86.156 14.8946
0.3685 0.96 1700 0.3500 86.8048 79.2231 86.2842 86.2602 14.8658
0.3353 1.02 1800 0.3547 86.7966 79.1526 86.2624 86.2769 14.8895
0.2323 1.07 1900 0.3529 86.6715 79.0832 86.1451 86.143 14.9119
0.2458 1.13 2000 0.3699 86.9553 79.3124 86.3906 86.4162 14.8987
0.2349 1.19 2100 0.3640 86.4161 78.4111 85.8783 85.8807 14.9420
0.2358 1.24 2200 0.3598 86.7842 79.1199 86.2164 86.2259 14.8932
0.2229 1.3 2300 0.3610 86.7032 79.0013 86.168 86.1807 14.8827
0.2502 1.35 2400 0.3527 86.5423 78.9113 86.0423 86.0465 14.8946
0.2466 1.41 2500 0.3575 86.512 78.7998 85.9795 85.9899 14.9142
0.2457 1.47 2600 0.3463 86.5376 78.7642 86.0019 85.993 14.8964
0.2429 1.52 2700 0.3480 86.5911 78.9802 86.0235 86.0303 14.9169
0.2657 1.58 2800 0.3423 86.6139 79.1659 86.0999 86.1034 14.8905
0.2542 1.64 2900 0.3439 86.4731 78.8656 86.0285 86.0336 14.8955
0.2529 1.69 3000 0.3491 86.7686 79.2799 86.2783 86.2663 14.8891
0.2475 1.75 3100 0.3460 86.0511 77.837 85.5557 85.56 14.8868
0.2472 1.81 3200 0.3375 86.6711 79.1718 86.1627 86.1402 14.8809
0.2432 1.86 3300 0.3349 86.6648 79.4505 86.1654 86.1549 14.9105
0.2467 1.92 3400 0.3383 86.867 79.7251 86.3823 86.3811 14.9014
0.2416 1.98 3500 0.3404 86.8577 79.4128 86.3474 86.3386 14.8909
0.1816 2.03 3600 0.3590 86.7414 79.4138 86.2395 86.2415 14.9283
0.1344 2.09 3700 0.3806 86.9318 79.5175 86.4098 86.4209 14.9238
0.134 2.14 3800 0.3704 86.733 79.2709 86.2066 86.2083 14.9379
0.1301 2.2 3900 0.3788 86.7622 79.4039 86.2608 86.2514 14.9133
0.1417 2.26 4000 0.3658 87.0002 79.8067 86.4663 86.4604 14.9105
0.1256 2.31 4100 0.3728 86.6691 79.3081 86.1154 86.1184 14.9119
0.1393 2.37 4200 0.3666 86.7525 79.3901 86.223 86.2348 14.9046
0.1542 2.43 4300 0.3740 86.6779 79.5336 86.1667 86.1716 14.9283
0.133 2.48 4400 0.3790 86.7692 79.6713 86.2335 86.2394 14.9457
0.1389 2.54 4500 0.3717 86.4853 79.3114 85.9253 85.9128 14.9434
0.1489 2.6 4600 0.3724 86.2107 78.63 85.6539 85.6792 14.9311
0.1522 2.65 4700 0.3647 86.8659 79.8 86.3545 86.3676 14.9160
0.1439 2.71 4800 0.3672 86.0554 78.1382 85.5587 85.5362 14.9297
0.1406 2.77 4900 0.3637 86.4054 78.9406 85.8958 85.9036 14.9069
0.1522 2.82 5000 0.3715 86.7402 79.6515 86.2414 86.2416 14.9201
0.1577 2.88 5100 0.3531 86.5905 79.2319 86.0746 86.0661 14.9174
0.1427 2.93 5200 0.3693 86.4955 79.0202 86.0034 85.9923 14.9014
0.1489 2.99 5300 0.3671 86.6285 79.2982 86.1429 86.1239 14.9366
0.0874 3.05 5400 0.4117 86.7939 79.6444 86.2987 86.292 14.9311
0.0824 3.1 5500 0.4056 86.7504 79.5265 86.2525 86.2509 14.9069
0.0815 3.16 5600 0.4064 86.9102 79.8072 86.4 86.3798 14.9188
0.0761 3.22 5700 0.4061 86.7759 79.4944 86.2642 86.2638 14.9156
0.0858 3.27 5800 0.4104 86.9783 79.7005 86.4405 86.4279 14.9206
0.0774 3.33 5900 0.4043 86.7749 79.4813 86.2355 86.2441 14.9010
0.0841 3.39 6000 0.4033 86.915 79.7145 86.3878 86.3809 14.9060
0.0885 3.44 6100 0.4066 86.761 79.3294 86.202 86.2041 14.8973
0.0794 3.5 6200 0.3987 86.699 79.2133 86.1431 86.1571 14.9083
0.0845 3.56 6300 0.4225 86.8629 79.4052 86.3102 86.32 14.9169
0.0869 3.61 6400 0.4033 86.8748 79.5928 86.3421 86.3564 14.8987
0.0791 3.67 6500 0.4055 86.9491 79.6876 86.4205 86.4281 14.9115
0.0849 3.72 6600 0.4068 86.7855 79.4848 86.2791 86.2945 14.9192
0.0865 3.78 6700 0.4069 86.7864 79.5128 86.2844 86.3027 14.9092
0.086 3.84 6800 0.3989 86.9556 79.6203 86.4463 86.4673 14.9083
0.0811 3.89 6900 0.3913 86.9815 79.7108 86.4913 86.4905 14.9073
0.0812 3.95 7000 0.4022 86.819 79.5024 86.313 86.336 14.9261
0.087 4.01 7100 0.4238 87.0628 79.8276 86.5385 86.5444 14.9133
0.0484 4.06 7200 0.4301 87.0455 79.7775 86.5274 86.5298 14.9023
0.0481 4.12 7300 0.4715 87.0629 79.9823 86.5676 86.5615 14.9073
0.0522 4.18 7400 0.4379 86.983 79.7011 86.4659 86.4906 14.9174
0.0463 4.23 7500 0.4574 87.047 79.6937 86.5243 86.5252 14.9133
0.0559 4.29 7600 0.4275 86.8511 79.4707 86.3482 86.3463 14.9270
0.0484 4.35 7700 0.4426 86.8238 79.4779 86.3242 86.3224 14.9178
0.0468 4.4 7800 0.4565 86.9331 79.7622 86.4253 86.433 14.9174
0.0501 4.46 7900 0.4506 86.884 79.7917 86.4025 86.4082 14.9160
0.0538 4.51 8000 0.4290 86.95 79.7812 86.4425 86.4387 14.9092
0.0499 4.57 8100 0.4366 87.1034 80.0115 86.6029 86.6075 14.9137
0.051 4.63 8200 0.4472 86.8904 79.6413 86.4313 86.4236 14.9078
0.0546 4.68 8300 0.4299 86.8704 79.6621 86.3474 86.3699 14.9055
0.049 4.74 8400 0.4601 87.0006 79.7754 86.4831 86.484 14.9073
0.0474 4.8 8500 0.4481 86.9629 79.7888 86.452 86.4605 14.9069
0.0509 4.85 8600 0.4329 86.9177 79.6544 86.4178 86.4215 14.9124
0.0521 4.91 8700 0.4323 86.8574 79.6029 86.3347 86.3477 14.9169
0.0458 4.97 8800 0.4563 87.0021 79.754 86.4522 86.4517 14.9105
0.0411 5.02 8900 0.4707 86.884 79.6339 86.3403 86.3413 14.9178
0.0283 5.08 9000 0.4809 86.9403 79.8934 86.4149 86.4145 14.9183
0.029 5.14 9100 0.4799 86.8942 79.7148 86.3502 86.3571 14.9064
0.0268 5.19 9200 0.4910 86.9841 79.8403 86.4605 86.4683 14.9233
0.0294 5.25 9300 0.4838 86.9494 79.9215 86.4508 86.4474 14.9151
0.028 5.3 9400 0.5042 87.1362 80.0747 86.6251 86.6238 14.9169
0.0291 5.36 9500 0.4997 87.0858 80.036 86.5966 86.5908 14.9087
0.0291 5.42 9600 0.4983 87.0756 79.9726 86.5872 86.5865 14.9037
0.0282 5.47 9700 0.5073 87.0901 79.8924 86.5942 86.595 14.8982
0.0299 5.53 9800 0.4945 87.145 79.9289 86.6143 86.6206 14.8987
0.0278 5.59 9900 0.5187 86.9691 79.7553 86.4589 86.4624 14.9051
0.0237 5.64 10000 0.5246 86.9827 79.7671 86.4783 86.4701 14.9119
0.03 5.7 10100 0.4944 87.0292 79.8105 86.4909 86.5016 14.9119
0.0289 5.76 10200 0.5131 87.0028 79.8731 86.5042 86.5187 14.9137
0.0296 5.81 10300 0.4963 87.1329 79.9334 86.6172 86.6194 14.9128
0.0287 5.87 10400 0.4893 87.0761 79.9902 86.5448 86.5427 14.9174
0.029 5.93 10500 0.4880 87.0082 79.8738 86.4987 86.4864 14.9105
0.0281 5.98 10600 0.4928 87.0415 79.8243 86.5291 86.5279 14.9206
0.0236 6.04 10700 0.5026 86.9936 79.8109 86.4741 86.4771 14.9165
0.0172 6.09 10800 0.5242 87.0859 80.0264 86.5787 86.5684 14.9178
0.0157 6.15 10900 0.5386 87.0647 80.1227 86.5723 86.5658 14.9197
0.0175 6.21 11000 0.5222 87.034 80.051 86.525 86.5177 14.9160
0.0155 6.26 11100 0.5445 87.0634 79.9564 86.5556 86.5507 14.9101
0.0147 6.32 11200 0.5602 87.0164 79.9748 86.505 86.4928 14.9105
0.0156 6.38 11300 0.5587 87.1387 79.9561 86.6298 86.6329 14.9137
0.0157 6.43 11400 0.5655 87.1027 80.1466 86.6023 86.5983 14.9201
0.0139 6.49 11500 0.5773 87.1318 80.1543 86.5965 86.6127 14.9251
0.0152 6.55 11600 0.5748 87.2417 80.2155 86.7204 86.7277 14.9128
0.0169 6.6 11700 0.5558 87.2049 80.1632 86.7078 86.7198 14.9042
0.0158 6.66 11800 0.5452 87.0358 79.9864 86.5181 86.5149 14.9151
0.0169 6.72 11900 0.5411 87.0557 79.9435 86.5372 86.5375 14.9087
0.0127 6.77 12000 0.5564 87.0617 80.0711 86.5398 86.5645 14.9051
0.0158 6.83 12100 0.5545 87.0269 80.0081 86.4936 86.5004 14.9247
0.0142 6.88 12200 0.5520 87.1107 80.1457 86.5775 86.5851 14.9192
0.0142 6.94 12300 0.5590 87.152 80.1378 86.604 86.6048 14.9178
0.0146 7.0 12400 0.5633 87.1416 80.1493 86.6109 86.6128 14.9178
0.0087 7.05 12500 0.5928 87.1881 80.1549 86.6642 86.6747 14.9133
0.0094 7.11 12600 0.5998 87.2084 80.2571 86.7023 86.6967 14.9042
0.0082 7.17 12700 0.6086 87.1567 80.204 86.6479 86.6462 14.9147
0.0096 7.22 12800 0.6106 87.173 80.1732 86.658 86.6586 14.9156
0.0084 7.28 12900 0.6318 87.1298 80.1264 86.6351 86.638 14.9174
0.0079 7.34 13000 0.6363 87.1628 80.1184 86.6548 86.6486 14.9174
0.0091 7.39 13100 0.6313 87.241 80.2331 86.7437 86.7435 14.9156
0.0088 7.45 13200 0.6376 87.1652 80.1422 86.661 86.6599 14.9142
0.0091 7.51 13300 0.6364 87.1554 80.1285 86.6576 86.6553 14.9147
0.0081 7.56 13400 0.6372 87.2418 80.192 86.7178 86.7199 14.9188
0.0103 7.62 13500 0.6369 87.1754 80.1347 86.666 86.666 14.9133
0.0094 7.67 13600 0.6382 87.1611 80.1066 86.6541 86.6488 14.9142
0.0081 7.73 13700 0.6371 87.1836 80.0865 86.6575 86.6538 14.9151
0.0076 7.79 13800 0.6377 87.1652 80.0572 86.6498 86.6569 14.9142
0.0092 7.84 13900 0.6354 87.1638 80.0867 86.6563 86.6536 14.9142
0.0076 7.9 14000 0.6346 87.1814 80.1212 86.6698 86.6683 14.9137
0.0063 7.96 14100 0.6373 87.1913 80.1322 86.6793 86.6765 14.9128

Framework versions