mt5-lora

This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.3226
  • Rouge1: 7.8216
  • Rouge2: 1.0545
  • Rougel: 6.1432
  • Rougelsum: 6.1446

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
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 6

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum
23.4174 0.0160 5 11.5276 0.5512 0.0509 0.5083 0.5105
20.8541 0.0319 10 11.3887 0.5208 0.0420 0.4838 0.4806
19.7415 0.0479 15 11.2833 0.5674 0.0379 0.5039 0.5039
22.3202 0.0639 20 11.1524 0.6424 0.0488 0.5638 0.5599
19.664 0.0799 25 11.0473 0.6588 0.0387 0.5976 0.5910
19.8018 0.0958 30 11.0452 0.6368 0.0306 0.5833 0.5773
19.3572 0.1118 35 11.0515 0.7488 0.0299 0.6835 0.6747
20.8368 0.1278 40 11.0434 0.8070 0.0621 0.7082 0.7025
22.0695 0.1438 45 10.9605 0.7058 0.0380 0.6236 0.6165
20.6973 0.1597 50 10.9030 0.7250 0.0346 0.6444 0.6367
20.2663 0.1757 55 10.7690 0.8067 0.0531 0.7106 0.7034
22.5977 0.1917 60 10.6166 0.8258 0.0646 0.7409 0.7427
17.239 0.2077 65 10.4542 0.8013 0.0736 0.7240 0.7238
19.9696 0.2236 70 10.2183 0.8306 0.0737 0.7532 0.7495
15.8901 0.2396 75 10.0682 0.8198 0.0683 0.7315 0.7295
15.3968 0.2556 80 9.9389 0.8226 0.0519 0.7350 0.7343
21.1744 0.2716 85 9.8182 0.8582 0.0829 0.7680 0.7633
19.8718 0.2875 90 9.7245 0.8604 0.0792 0.7585 0.7592
16.4366 0.3035 95 9.6151 0.8401 0.0741 0.7469 0.7479
17.3532 0.3195 100 9.5204 0.8644 0.0742 0.7623 0.7632
17.0363 0.3355 105 9.4045 0.9015 0.0792 0.8096 0.8049
18.5648 0.3514 110 9.2755 0.9620 0.0864 0.8438 0.8439
16.616 0.3674 115 9.1327 0.9881 0.0735 0.8607 0.8568
14.493 0.3834 120 8.9794 0.9963 0.0696 0.8583 0.8565
14.9013 0.3994 125 8.8291 1.0745 0.0856 0.9557 0.9567
13.4762 0.4153 130 8.6996 1.0927 0.1052 0.9579 0.9509
14.4945 0.4313 135 8.5736 1.1429 0.1006 1.0144 1.0141
13.5679 0.4473 140 8.4425 1.1295 0.0912 0.9998 0.9994
15.0019 0.4633 145 8.2860 1.1883 0.0962 1.0700 1.0662
14.1212 0.4792 150 8.1218 1.3312 0.1006 1.1960 1.1942
12.7002 0.4952 155 7.9539 1.4626 0.1199 1.2780 1.2770
13.1474 0.5112 160 7.7965 1.3940 0.1190 1.2474 1.2436
14.5109 0.5272 165 7.6643 1.6103 0.1058 1.4796 1.4798
12.6913 0.5431 170 7.5470 1.7523 0.1230 1.5815 1.5751
11.4756 0.5591 175 7.4656 1.9158 0.1608 1.7088 1.7119
11.9234 0.5751 180 7.3834 1.9540 0.1774 1.7611 1.7598
11.0724 0.5911 185 7.2629 1.9871 0.1552 1.7926 1.7887
11.6507 0.6070 190 7.1034 1.9782 0.1410 1.7966 1.7902
11.9906 0.6230 195 6.9759 2.2038 0.1563 1.9806 1.9726
10.8749 0.6390 200 6.8845 2.2981 0.1679 2.0372 2.0295
10.6337 0.6550 205 6.8046 2.3401 0.1510 2.0842 2.0849
10.4566 0.6709 210 6.7251 2.4901 0.1521 2.2305 2.2257
10.3598 0.6869 215 6.6457 2.7227 0.1648 2.4467 2.4454
9.4165 0.7029 220 6.5906 2.8052 0.1248 2.5173 2.5198
9.4989 0.7188 225 6.5359 3.1011 0.1626 2.8119 2.8119
9.1349 0.7348 230 6.4783 3.2991 0.2224 2.9851 2.9873
9.7813 0.7508 235 6.4346 3.2898 0.1813 2.9987 3.0018
8.7862 0.7668 240 6.3906 3.2366 0.1717 2.9376 2.9315
8.5808 0.7827 245 6.3494 3.4441 0.1838 3.1485 3.1404
8.3688 0.7987 250 6.3160 3.4652 0.2120 3.0932 3.0858
7.8728 0.8147 255 6.1939 3.5126 0.2161 3.1197 3.1101
7.7791 0.8307 260 6.0422 3.5680 0.2148 3.2478 3.2502
7.6755 0.8466 265 5.9109 3.4946 0.2339 3.1731 3.1703
7.4162 0.8626 270 5.8052 3.5776 0.2309 3.2148 3.2215
7.2342 0.8786 275 5.7194 3.3818 0.1998 3.0493 3.0476
7.1504 0.8946 280 5.6598 3.1740 0.1684 2.8844 2.8834
7.0159 0.9105 285 5.6208 2.9711 0.1415 2.7126 2.7104
7.1424 0.9265 290 5.5964 2.7683 0.0634 2.5813 2.5837
6.7451 0.9425 295 5.5818 2.7456 0.0568 2.5982 2.5947
6.7401 0.9585 300 5.5601 2.6545 0.0280 2.5506 2.5347
6.7725 0.9744 305 5.5474 2.6375 0.0225 2.5254 2.5062
6.6 0.9904 310 5.5262 2.6241 0.0318 2.5260 2.5160
6.7553 1.0064 315 5.5075 2.7581 0.0752 2.6420 2.6236
6.7118 1.0224 320 5.4911 2.8034 0.0704 2.6557 2.6419
6.5138 1.0383 325 5.4664 2.8934 0.0729 2.7440 2.7363
6.3071 1.0543 330 5.4398 2.9828 0.0718 2.8381 2.8348
6.2783 1.0703 335 5.4021 3.0171 0.0941 2.8712 2.8618
6.1266 1.0863 340 5.3589 3.1202 0.1625 2.9845 2.9727
6.1881 1.1022 345 5.3167 3.3116 0.2156 3.1289 3.1196
6.2642 1.1182 350 5.2739 3.4642 0.2852 3.2263 3.2161
6.146 1.1342 355 5.2336 3.5524 0.2905 3.2935 3.2832
6.1432 1.1502 360 5.1949 3.6599 0.2973 3.4063 3.3878
5.9649 1.1661 365 5.1552 3.7014 0.3259 3.4428 3.4269
6.2828 1.1821 370 5.1219 3.8202 0.3492 3.5719 3.5633
5.9083 1.1981 375 5.0893 4.0190 0.3812 3.7140 3.7099
5.9194 1.2141 380 5.0534 4.2639 0.4082 3.9475 3.9430
5.8114 1.2300 385 5.0187 4.4058 0.4498 4.0691 4.0584
5.9099 1.2460 390 4.9859 4.6188 0.4248 4.2003 4.1816
6.9239 1.2620 395 4.9597 4.6864 0.3851 4.2822 4.2767
5.8784 1.2780 400 4.9367 4.7774 0.4615 4.3299 4.3268
5.6944 1.2939 405 4.9154 4.7518 0.4225 4.2943 4.2835
5.7841 1.3099 410 4.8942 5.0763 0.5001 4.5626 4.5506
5.4959 1.3259 415 4.8727 5.1974 0.4848 4.6204 4.6136
5.7918 1.3419 420 4.8514 5.3658 0.5150 4.7269 4.7229
5.564 1.3578 425 4.8315 5.4525 0.5188 4.7995 4.7949
5.7502 1.3738 430 4.8120 5.5823 0.5460 4.8396 4.8402
5.7183 1.3898 435 4.7962 5.6605 0.5128 4.9291 4.9355
5.6075 1.4058 440 4.7827 5.8504 0.5399 5.0957 5.0945
5.4517 1.4217 445 4.7698 5.9596 0.5882 5.0729 5.0818
5.5904 1.4377 450 4.7567 6.3422 0.6041 5.3449 5.3427
5.5302 1.4537 455 4.7425 6.5357 0.6688 5.4570 5.4494
5.4474 1.4696 460 4.7274 6.6389 0.6350 5.5574 5.5418
5.5081 1.4856 465 4.7142 6.7687 0.7230 5.6597 5.6488
5.7388 1.5016 470 4.7033 6.7877 0.6756 5.6965 5.6844
5.7518 1.5176 475 4.6940 6.7742 0.6820 5.6947 5.6833
5.9692 1.5335 480 4.6832 6.7753 0.6728 5.7376 5.7326
5.5493 1.5495 485 4.6752 6.7782 0.6779 5.7264 5.7236
5.4517 1.5655 490 4.6660 6.7433 0.6677 5.6678 5.6627
5.4072 1.5815 495 4.6544 6.7451 0.6685 5.6435 5.6459
5.3341 1.5974 500 4.6415 6.7146 0.6591 5.6348 5.6298
5.5638 1.6134 505 4.6278 6.9514 0.7494 5.7740 5.7623
5.4438 1.6294 510 4.6193 6.9315 0.7450 5.8160 5.8072
5.2225 1.6454 515 4.6121 7.0183 0.7255 5.8563 5.8436
5.3059 1.6613 520 4.6048 7.0723 0.7431 5.9316 5.9195
5.249 1.6773 525 4.5995 7.1713 0.7601 6.0056 5.9905
5.4208 1.6933 530 4.5945 7.2201 0.7667 5.9700 5.9527
5.8052 1.7093 535 4.5898 7.2075 0.7749 5.9898 5.9838
5.5609 1.7252 540 4.5833 7.2178 0.8101 5.9825 5.9742
5.3695 1.7412 545 4.5759 7.1889 0.8046 5.9291 5.9202
5.3855 1.7572 550 4.5688 7.2416 0.8298 6.0218 6.0193
5.2254 1.7732 555 4.5620 7.1364 0.7926 5.9165 5.9173
5.2946 1.7891 560 4.5562 7.1300 0.8436 5.8809 5.8734
5.1469 1.8051 565 4.5523 7.0630 0.8550 5.8875 5.8791
5.4316 1.8211 570 4.5476 7.1515 0.8185 5.8968 5.9001
5.4154 1.8371 575 4.5434 7.0949 0.8109 5.8768 5.8783
5.3236 1.8530 580 4.5393 7.0200 0.8220 5.8357 5.8337
5.3977 1.8690 585 4.5353 6.8813 0.7518 5.7547 5.7480
5.231 1.8850 590 4.5306 6.9975 0.8231 5.8376 5.8361
5.1977 1.9010 595 4.5253 6.9867 0.7840 5.7865 5.7865
5.1508 1.9169 600 4.5183 6.9963 0.7654 5.7866 5.7769
5.3122 1.9329 605 4.5135 7.0253 0.7531 5.8269 5.8236
5.2965 1.9489 610 4.5090 7.1005 0.7956 5.8740 5.8678
5.2763 1.9649 615 4.5049 7.2127 0.8061 5.9695 5.9634
5.197 1.9808 620 4.5003 7.2466 0.8646 5.9926 5.9920
5.06 1.9968 625 4.4960 7.1826 0.8737 5.9518 5.9560
5.197 2.0128 630 4.4950 7.1843 0.8755 5.9126 5.9132
5.1263 2.0288 635 4.4935 7.2493 0.8757 5.9768 5.9753
5.2239 2.0447 640 4.4904 7.1220 0.8488 5.8750 5.8761
5.4354 2.0607 645 4.4874 7.1138 0.8524 5.8486 5.8486
5.8528 2.0767 650 4.4851 7.1801 0.8384 5.9110 5.9093
5.1073 2.0927 655 4.4841 7.1465 0.8200 5.8586 5.8598
5.2021 2.1086 660 4.4827 7.1738 0.8648 5.9139 5.9107
5.2228 2.1246 665 4.4818 7.1615 0.8452 5.8823 5.8806
5.1512 2.1406 670 4.4792 7.2016 0.8799 5.9256 5.9243
5.0959 2.1565 675 4.4749 7.2563 0.8906 5.9145 5.9190
5.0816 2.1725 680 4.4706 7.2635 0.9198 5.9403 5.9434
5.2325 2.1885 685 4.4672 7.2539 0.8930 5.9365 5.9373
5.2439 2.2045 690 4.4647 7.1329 0.8859 5.8597 5.8618
5.3669 2.2204 695 4.4639 7.1435 0.8830 5.8719 5.8697
5.1739 2.2364 700 4.4615 7.1627 0.8747 5.9314 5.9293
5.1589 2.2524 705 4.4581 7.1976 0.8329 5.9189 5.9181
5.0201 2.2684 710 4.4548 7.1503 0.8330 5.8295 5.8288
5.1782 2.2843 715 4.4524 7.0478 0.8211 5.7872 5.7877
5.4161 2.3003 720 4.4512 7.0227 0.8004 5.7695 5.7741
5.2066 2.3163 725 4.4483 7.0058 0.8090 5.7595 5.7571
5.2428 2.3323 730 4.4456 6.9623 0.8100 5.7154 5.7128
5.2263 2.3482 735 4.4429 7.0183 0.8002 5.7599 5.7542
5.1332 2.3642 740 4.4402 7.1283 0.8214 5.8456 5.8473
5.2223 2.3802 745 4.4370 7.1333 0.8331 5.8713 5.8781
5.0942 2.3962 750 4.4358 7.2237 0.8484 5.9213 5.9230
5.1686 2.4121 755 4.4354 7.2068 0.8469 5.9262 5.9210
5.1731 2.4281 760 4.4340 7.2619 0.8603 5.9468 5.9409
5.1303 2.4441 765 4.4309 7.2012 0.8455 5.8986 5.8969
4.9487 2.4601 770 4.4286 7.1008 0.8057 5.8042 5.8038
5.0781 2.4760 775 4.4271 7.0506 0.7662 5.7615 5.7577
5.1239 2.4920 780 4.4255 7.0936 0.8019 5.8001 5.7966
5.0973 2.5080 785 4.4233 7.1104 0.8471 5.8333 5.8377
5.047 2.5240 790 4.4226 7.1011 0.8421 5.8017 5.8025
5.1145 2.5399 795 4.4214 7.1758 0.8452 5.8921 5.8885
5.1569 2.5559 800 4.4199 7.2287 0.8429 5.9401 5.9358
5.0929 2.5719 805 4.4186 7.2605 0.8465 5.9684 5.9706
4.9979 2.5879 810 4.4167 7.2952 0.8723 5.9564 5.9586
5.2416 2.6038 815 4.4148 7.3345 0.8723 5.9941 5.9916
5.1275 2.6198 820 4.4122 7.3157 0.8731 5.9902 5.9799
5.0442 2.6358 825 4.4109 7.3031 0.8777 5.9888 5.9800
5.02 2.6518 830 4.4111 7.3503 0.8800 6.0046 5.9926
5.0734 2.6677 835 4.4122 7.3183 0.8784 5.9362 5.9262
5.078 2.6837 840 4.4128 7.3182 0.8817 5.9506 5.9443
4.9815 2.6997 845 4.4116 7.2872 0.9068 5.9426 5.9339
4.9768 2.7157 850 4.4089 7.3339 0.8839 6.0006 5.9917
5.032 2.7316 855 4.4048 7.3529 0.8972 6.0608 6.0543
5.025 2.7476 860 4.4027 7.3729 0.9448 6.0690 6.0629
5.0341 2.7636 865 4.4008 7.2963 0.9054 6.0141 6.0132
4.9091 2.7796 870 4.4007 7.2958 0.8849 6.0324 6.0364
5.0662 2.7955 875 4.4016 7.3117 0.8884 6.0305 6.0244
5.2129 2.8115 880 4.4022 7.2543 0.8930 5.9937 5.9829
5.1673 2.8275 885 4.4010 7.3243 0.8953 6.0491 6.0441
5.0533 2.8435 890 4.3979 7.2927 0.8748 6.0153 6.0086
5.0917 2.8594 895 4.3944 7.3091 0.9064 6.0178 6.0094
5.2621 2.8754 900 4.3935 7.2308 0.8968 5.9607 5.9525
4.9642 2.8914 905 4.3933 7.2551 0.8896 5.9743 5.9692
5.013 2.9073 910 4.3922 7.2437 0.8894 5.9721 5.9652
5.0455 2.9233 915 4.3906 7.2870 0.9207 5.9824 5.9747
5.1566 2.9393 920 4.3894 7.3241 0.9130 6.0086 5.9984
5.1624 2.9553 925 4.3892 7.3109 0.9082 5.9725 5.9633
4.9393 2.9712 930 4.3880 7.3367 0.9046 5.9947 5.9904
5.0442 2.9872 935 4.3868 7.3301 0.8972 5.9785 5.9684
5.1003 3.0032 940 4.3850 7.2628 0.8845 5.9464 5.9399
5.0953 3.0192 945 4.3836 7.2418 0.8976 5.9284 5.9251
5.0498 3.0351 950 4.3827 7.2159 0.8875 5.8910 5.8869
4.9049 3.0511 955 4.3810 7.2497 0.9309 5.9163 5.9116
5.1671 3.0671 960 4.3788 7.2706 0.9297 5.9437 5.9386
5.039 3.0831 965 4.3772 7.2784 0.9169 5.9150 5.9039
4.9631 3.0990 970 4.3764 7.2486 0.9009 5.8804 5.8762
5.0452 3.1150 975 4.3759 7.2401 0.8922 5.8692 5.8657
5.0414 3.1310 980 4.3750 7.2768 0.8755 5.9131 5.9067
5.0543 3.1470 985 4.3746 7.3163 0.9281 5.9206 5.9190
5.0062 3.1629 990 4.3747 7.4349 0.9639 6.0304 6.0215
5.0441 3.1789 995 4.3762 7.4030 0.9699 6.0210 6.0136
5.0549 3.1949 1000 4.3763 7.4348 0.9795 6.0078 6.0003
4.8066 3.2109 1005 4.3762 7.3923 0.9642 5.9953 5.9818
4.9398 3.2268 1010 4.3762 7.3906 0.9577 5.9968 5.9852
4.9251 3.2428 1015 4.3758 7.4300 0.9411 6.0545 6.0482
4.9915 3.2588 1020 4.3758 7.4863 0.9828 6.0976 6.0841
5.0957 3.2748 1025 4.3752 7.4985 0.9803 6.1357 6.1216
5.1146 3.2907 1030 4.3740 7.5046 0.9575 6.1345 6.1203
5.1074 3.3067 1035 4.3727 7.5027 0.9469 6.0929 6.0845
4.88 3.3227 1040 4.3711 7.4661 0.9356 6.0458 6.0364
4.922 3.3387 1045 4.3693 7.4812 0.9686 6.0729 6.0572
5.0247 3.3546 1050 4.3667 7.4387 0.9287 6.0286 6.0156
4.9925 3.3706 1055 4.3645 7.4062 0.9259 5.9774 5.9694
5.0598 3.3866 1060 4.3631 7.4506 0.9642 5.9859 5.9719
5.1107 3.4026 1065 4.3620 7.4497 0.9831 5.9838 5.9676
5.9375 3.4185 1070 4.3621 7.4267 0.9827 5.9516 5.9419
5.0654 3.4345 1075 4.3630 7.4204 0.9749 5.9540 5.9443
5.0002 3.4505 1080 4.3650 7.4044 0.9337 5.9603 5.9516
4.9958 3.4665 1085 4.3672 7.4358 0.9545 5.9941 5.9836
4.9601 3.4824 1090 4.3681 7.4650 0.9612 6.0129 6.0008
5.0984 3.4984 1095 4.3687 7.3706 0.9345 5.9709 5.9548
5.0266 3.5144 1100 4.3684 7.3913 0.9382 5.9680 5.9598
4.8365 3.5304 1105 4.3686 7.3994 0.9509 5.9680 5.9572
4.8761 3.5463 1110 4.3675 7.4688 0.9509 5.9876 5.9789
4.9711 3.5623 1115 4.3662 7.4356 0.9500 5.9815 5.9745
5.027 3.5783 1120 4.3660 7.4089 0.9309 5.9851 5.9710
4.8545 3.5942 1125 4.3662 7.4501 0.9371 6.0094 5.9983
4.8711 3.6102 1130 4.3666 7.4912 0.9437 6.0361 6.0276
4.9593 3.6262 1135 4.3661 7.5101 0.9449 6.0638 6.0620
5.0499 3.6422 1140 4.3654 7.5779 0.9641 6.0859 6.0758
5.1807 3.6581 1145 4.3647 7.6076 0.9619 6.0981 6.0904
4.9862 3.6741 1150 4.3630 7.6010 0.9717 6.0660 6.0576
4.8606 3.6901 1155 4.3617 7.5719 0.9763 6.0416 6.0323
5.1017 3.7061 1160 4.3609 7.5500 0.9730 6.0361 6.0249
5.145 3.7220 1165 4.3596 7.5079 0.9484 5.9961 5.9835
5.0378 3.7380 1170 4.3590 7.4708 0.9639 5.9879 5.9769
5.1457 3.7540 1175 4.3584 7.4506 0.9670 5.9667 5.9589
4.8238 3.7700 1180 4.3572 7.5186 0.9703 5.9893 5.9760
5.0649 3.7859 1185 4.3552 7.5171 0.9449 5.9562 5.9513
5.2019 3.8019 1190 4.3540 7.5922 0.9901 6.0043 5.9924
4.9544 3.8179 1195 4.3534 7.6158 0.9749 5.9965 5.9857
5.0737 3.8339 1200 4.3523 7.6583 0.9888 6.0326 6.0217
5.0164 3.8498 1205 4.3516 7.6724 0.9962 6.0160 6.0052
5.0842 3.8658 1210 4.3509 7.5698 0.9960 5.9851 5.9752
4.8723 3.8818 1215 4.3501 7.5539 0.9918 5.9883 5.9771
4.9591 3.8978 1220 4.3497 7.4666 0.9714 5.9291 5.9206
4.9407 3.9137 1225 4.3491 7.4850 0.9716 5.9482 5.9378
4.9529 3.9297 1230 4.3488 7.4749 0.9759 5.9510 5.9453
4.7896 3.9457 1235 4.3486 7.4730 0.9514 5.9567 5.9470
4.9939 3.9617 1240 4.3479 7.4929 0.9907 5.9980 5.9886
4.9954 3.9776 1245 4.3468 7.5651 1.0185 6.0080 6.0022
5.0677 3.9936 1250 4.3460 7.5604 1.0443 6.0228 6.0100
4.8667 4.0096 1255 4.3460 7.5730 1.0380 6.0162 6.0022
4.9784 4.0256 1260 4.3454 7.5657 1.0282 5.9908 5.9860
4.8794 4.0415 1265 4.3447 7.5704 1.0411 5.9863 5.9772
4.9753 4.0575 1270 4.3439 7.5492 0.9916 5.9362 5.9300
4.8115 4.0735 1275 4.3434 7.5454 0.9888 5.9454 5.9433
4.9679 4.0895 1280 4.3421 7.5914 1.0105 5.9620 5.9625
4.9535 4.1054 1285 4.3412 7.6417 1.0420 5.9848 5.9852
5.0465 4.1214 1290 4.3410 7.6500 1.0408 5.9770 5.9797
4.9678 4.1374 1295 4.3407 7.6556 1.0283 5.9699 5.9734
4.8975 4.1534 1300 4.3408 7.6201 1.0222 5.9561 5.9589
5.073 4.1693 1305 4.3405 7.6351 1.0144 5.9511 5.9503
5.0291 4.1853 1310 4.3398 7.6253 1.0094 5.9875 5.9866
4.7808 4.2013 1315 4.3404 7.6265 1.0080 5.9924 5.9872
5.0118 4.2173 1320 4.3406 7.6036 1.0131 5.9951 5.9944
4.9147 4.2332 1325 4.3408 7.6478 1.0060 5.9993 5.9963
5.2196 4.2492 1330 4.3409 7.6920 1.0183 6.0359 6.0368
4.7923 4.2652 1335 4.3402 7.7291 1.0206 6.0770 6.0775
5.2416 4.2812 1340 4.3389 7.7189 1.0336 6.0734 6.0690
4.9129 4.2971 1345 4.3371 7.7187 1.0641 6.0790 6.0741
4.8426 4.3131 1350 4.3360 7.7236 1.0619 6.0650 6.0600
4.9097 4.3291 1355 4.3350 7.7200 1.0503 6.0460 6.0423
4.812 4.3450 1360 4.3344 7.7144 1.0565 6.0526 6.0517
5.01 4.3610 1365 4.3338 7.7116 1.0388 6.0731 6.0710
4.8906 4.3770 1370 4.3326 7.7511 1.0446 6.0964 6.0925
4.9873 4.3930 1375 4.3326 7.7392 1.0728 6.0972 6.0944
4.8922 4.4089 1380 4.3326 7.6930 1.0453 6.0528 6.0544
5.0074 4.4249 1385 4.3323 7.6723 1.0509 6.0698 6.0709
4.9939 4.4409 1390 4.3318 7.6901 1.0595 6.0942 6.0909
5.023 4.4569 1395 4.3318 7.7283 1.0458 6.1093 6.1050
4.8076 4.4728 1400 4.3317 7.6976 1.0719 6.0941 6.0859
5.1418 4.4888 1405 4.3321 7.7327 1.0791 6.0838 6.0748
4.8614 4.5048 1410 4.3321 7.5965 1.0139 6.0089 6.0025
4.8516 4.5208 1415 4.3322 7.6741 1.0467 6.0436 6.0375
5.1611 4.5367 1420 4.3331 7.6540 1.0297 6.0385 6.0298
4.8864 4.5527 1425 4.3332 7.6279 1.0335 6.0205 6.0106
5.0181 4.5687 1430 4.3328 7.6939 1.0702 6.0759 6.0756
5.1197 4.5847 1435 4.3319 7.7408 1.0965 6.1116 6.1082
5.03 4.6006 1440 4.3315 7.7497 1.0758 6.1203 6.1149
4.8272 4.6166 1445 4.3318 7.7247 1.0643 6.1007 6.0937
4.8669 4.6326 1450 4.3319 7.7556 1.0908 6.1252 6.1205
4.9243 4.6486 1455 4.3316 7.7401 1.0920 6.1078 6.1052
4.9354 4.6645 1460 4.3311 7.7599 1.0710 6.1272 6.1201
4.9087 4.6805 1465 4.3312 7.7357 1.0748 6.1100 6.1019
5.0466 4.6965 1470 4.3313 7.7241 1.0440 6.0772 6.0712
4.987 4.7125 1475 4.3311 7.6894 1.0217 6.0663 6.0653
5.0424 4.7284 1480 4.3312 7.7028 1.0257 6.0607 6.0603
4.9104 4.7444 1485 4.3314 7.7049 1.0382 6.0579 6.0566
5.4987 4.7604 1490 4.3316 7.7122 1.0360 6.0474 6.0392
4.9413 4.7764 1495 4.3316 7.7498 1.0150 6.0863 6.0798
4.9124 4.7923 1500 4.3321 7.7538 1.0291 6.0791 6.0753
4.8853 4.8083 1505 4.3328 7.7532 1.0170 6.0938 6.0888
4.9113 4.8243 1510 4.3325 7.7311 1.0010 6.0658 6.0632
5.1313 4.8403 1515 4.3322 7.7341 0.9924 6.0552 6.0545
4.9934 4.8562 1520 4.3313 7.7445 1.0359 6.0700 6.0630
4.9148 4.8722 1525 4.3303 7.7310 1.0531 6.0620 6.0601
4.9555 4.8882 1530 4.3295 7.7469 1.0705 6.0964 6.0910
4.7897 4.9042 1535 4.3290 7.7583 1.0816 6.0907 6.0861
5.2209 4.9201 1540 4.3291 7.6943 1.0308 6.0188 6.0216
5.1329 4.9361 1545 4.3293 7.7375 1.0413 6.0539 6.0509
4.9242 4.9521 1550 4.3295 7.7516 1.0480 6.0517 6.0544
4.8293 4.9681 1555 4.3290 7.7303 1.0457 6.0352 6.0299
4.9005 4.9840 1560 4.3285 7.7264 1.0352 6.0264 6.0187
4.9146 5.0 1565 4.3283 7.7195 1.0331 6.0371 6.0316
5.0743 5.0160 1570 4.3279 7.7183 1.0703 6.0462 6.0352
4.8564 5.0319 1575 4.3276 7.7294 1.0774 6.0553 6.0465
4.927 5.0479 1580 4.3274 7.7478 1.0915 6.0644 6.0530
4.7846 5.0639 1585 4.3270 7.7938 1.1112 6.1027 6.0903
5.0363 5.0799 1590 4.3270 7.8152 1.1145 6.1205 6.1103
4.8218 5.0958 1595 4.3269 7.7887 1.1122 6.1028 6.0912
4.9988 5.1118 1600 4.3264 7.7989 1.0866 6.1238 6.1106
5.0564 5.1278 1605 4.3260 7.7916 1.0738 6.1174 6.1035
4.9796 5.1438 1610 4.3261 7.7909 1.0695 6.1230 6.1167
4.9055 5.1597 1615 4.3263 7.7884 1.0694 6.1194 6.1151
5.0426 5.1757 1620 4.3266 7.8154 1.0780 6.1596 6.1528
4.8726 5.1917 1625 4.3268 7.8710 1.0926 6.2040 6.1981
4.9214 5.2077 1630 4.3268 7.8670 1.0880 6.2140 6.2059
4.7925 5.2236 1635 4.3270 7.8478 1.0920 6.1588 6.1562
4.8974 5.2396 1640 4.3270 7.8261 1.1046 6.1584 6.1575
4.942 5.2556 1645 4.3269 7.7903 1.0984 6.1120 6.1089
4.8275 5.2716 1650 4.3267 7.8096 1.0926 6.1156 6.1118
5.2443 5.2875 1655 4.3266 7.8066 1.0915 6.1225 6.1208
4.9792 5.3035 1660 4.3265 7.8421 1.0884 6.1384 6.1326
5.0446 5.3195 1665 4.3264 7.8426 1.0842 6.1409 6.1384
4.9313 5.3355 1670 4.3265 7.8642 1.0807 6.1659 6.1570
4.7981 5.3514 1675 4.3262 7.8241 1.0759 6.1698 6.1630
4.8056 5.3674 1680 4.3258 7.8492 1.0877 6.1975 6.1891
4.9503 5.3834 1685 4.3257 7.8797 1.0971 6.2128 6.2035
4.9289 5.3994 1690 4.3256 7.8831 1.1095 6.2021 6.1947
4.9398 5.4153 1695 4.3256 7.8577 1.1025 6.1788 6.1690
4.8135 5.4313 1700 4.3255 7.8440 1.0957 6.1659 6.1589
4.9993 5.4473 1705 4.3255 7.7802 1.0757 6.1289 6.1246
4.9389 5.4633 1710 4.3253 7.7995 1.0852 6.1398 6.1318
5.1666 5.4792 1715 4.3248 7.7675 1.0663 6.1302 6.1217
4.9146 5.4952 1720 4.3246 7.7542 1.0510 6.1118 6.1048
4.8464 5.5112 1725 4.3245 7.7685 1.0458 6.1273 6.1173
4.9564 5.5272 1730 4.3246 7.7701 1.0553 6.1174 6.1098
4.9375 5.5431 1735 4.3247 7.8109 1.0601 6.1367 6.1313
4.8133 5.5591 1740 4.3249 7.8305 1.0728 6.1654 6.1590
4.912 5.5751 1745 4.3251 7.8129 1.0629 6.1426 6.1365
4.8319 5.5911 1750 4.3251 7.8199 1.0698 6.1581 6.1561
4.9121 5.6070 1755 4.3251 7.8372 1.0657 6.1785 6.1737
4.9906 5.6230 1760 4.3249 7.8071 1.0540 6.1744 6.1683
4.954 5.6390 1765 4.3248 7.7878 1.0540 6.1538 6.1520
5.4461 5.6550 1770 4.3246 7.7997 1.0543 6.1591 6.1566
5.0082 5.6709 1775 4.3242 7.8102 1.0602 6.1712 6.1660
4.7876 5.6869 1780 4.3240 7.7923 1.0579 6.1640 6.1587
4.9822 5.7029 1785 4.3238 7.8041 1.0695 6.1665 6.1598
4.9743 5.7188 1790 4.3238 7.8227 1.0672 6.1718 6.1658
4.7794 5.7348 1795 4.3238 7.8236 1.0587 6.1678 6.1618
4.887 5.7508 1800 4.3238 7.8118 1.0493 6.1490 6.1430
4.9724 5.7668 1805 4.3237 7.8100 1.0490 6.1387 6.1352
4.9202 5.7827 1810 4.3234 7.8060 1.0534 6.1295 6.1289
4.9347 5.7987 1815 4.3232 7.8086 1.0454 6.1371 6.1370
4.8149 5.8147 1820 4.3230 7.8131 1.0503 6.1413 6.1411
4.9697 5.8307 1825 4.3230 7.8132 1.0503 6.1416 6.1414
4.9892 5.8466 1830 4.3229 7.8132 1.0503 6.1416 6.1414
4.8792 5.8626 1835 4.3229 7.8264 1.0503 6.1416 6.1413
4.929 5.8786 1840 4.3228 7.8286 1.0578 6.1372 6.1368
4.9375 5.8946 1845 4.3228 7.8286 1.0578 6.1383 6.1387
4.8564 5.9105 1850 4.3228 7.8423 1.0575 6.1429 6.1443
5.0988 5.9265 1855 4.3227 7.8423 1.0575 6.1429 6.1443
5.0853 5.9425 1860 4.3227 7.8217 1.0502 6.1385 6.1409
5.1103 5.9585 1865 4.3227 7.8216 1.0545 6.1432 6.1446
4.8901 5.9744 1870 4.3227 7.8216 1.0545 6.1432 6.1446
4.8509 5.9904 1875 4.3226 7.8216 1.0545 6.1432 6.1446

Framework versions

  • PEFT 0.14.0
  • Transformers 4.49.0
  • Pytorch 2.6.0+cu124
  • Datasets 3.3.2
  • Tokenizers 0.21.0
Downloads last month
0
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for benitoals/mt5-lora

Base model

google/mt5-small
Adapter
(13)
this model