ht-stmini-cls-v6_ftis_noPretrain-cssl-msm-bml

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

  • Loss: 16.6821
  • Accuracy: 0.9045
  • Macro F1: 0.7674

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: 8
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 6733
  • training_steps: 134674

Training results

Training Loss Epoch Step Validation Loss Accuracy Macro F1
11715.2213 0.0013 174 10727.4766 0.0638 0.0283
8436.0012 1.0013 348 6992.4492 0.0706 0.0296
5873.0413 2.0013 522 3689.1555 0.0970 0.0358
2780.7009 3.0013 696 1901.4088 0.2850 0.0661
1096.5327 4.0013 870 828.9574 0.3923 0.0909
640.5421 5.0013 1044 513.9333 0.4514 0.1113
423.0914 6.0012 1218 396.2117 0.4752 0.1182
337.1574 7.0012 1392 330.5453 0.4958 0.1237
257.1514 8.0012 1566 264.8556 0.5144 0.1272
216.2928 9.0012 1740 216.6899 0.5206 0.1298
209.9206 10.0012 1914 184.6555 0.5321 0.1322
170.8291 11.0012 2088 159.6617 0.5371 0.1341
160.7261 12.0012 2262 145.2256 0.5420 0.1362
143.5558 13.0012 2436 130.5261 0.5432 0.1376
124.9779 14.0012 2610 121.6776 0.5549 0.1402
114.6333 15.0012 2784 114.0393 0.5567 0.1425
104.1651 16.0012 2958 105.7749 0.5675 0.1442
96.692 17.0012 3132 102.6569 0.5627 0.1446
89.7748 18.0012 3306 97.5948 0.5745 0.1468
89.4558 19.0012 3480 93.5582 0.5859 0.1512
80.687 20.0011 3654 88.2421 0.5775 0.1530
76.154 21.0011 3828 90.8190 0.5704 0.1501
73.2332 22.0011 4002 84.4550 0.5805 0.1565
71.9891 23.0011 4176 80.8633 0.5902 0.1596
70.2947 24.0011 4350 80.1923 0.5893 0.1611
67.5285 25.0011 4524 78.1419 0.5917 0.1608
66.9792 26.0011 4698 73.2892 0.6081 0.1703
65.348 27.0011 4872 70.4800 0.6047 0.1695
62.3904 28.0011 5046 76.0858 0.5940 0.1689
61.1992 29.0011 5220 67.9268 0.6100 0.1782
58.0391 30.0011 5394 64.8750 0.6191 0.1802
54.2658 31.0011 5568 64.0972 0.6239 0.1935
53.7429 32.0011 5742 61.6177 0.6336 0.1981
49.5539 33.0010 5916 63.4825 0.6351 0.1983
48.5641 34.0010 6090 59.5909 0.6448 0.2138
45.7779 35.0010 6264 58.3350 0.6224 0.2105
43.3097 36.0010 6438 55.5437 0.6561 0.2252
39.4661 37.0010 6612 54.4594 0.6593 0.2360
38.7875 38.0010 6786 51.2408 0.6655 0.2373
36.1766 39.0010 6960 50.7226 0.6749 0.2522
34.0581 40.0010 7134 51.9902 0.6780 0.2654
32.973 41.0010 7308 49.4649 0.6819 0.2732
31.9436 42.0010 7482 47.4678 0.6925 0.2859
29.808 43.0010 7656 47.4288 0.7010 0.2986
28.988 44.0010 7830 47.9734 0.7017 0.3069
28.5465 45.0010 8004 47.5173 0.7051 0.3021
25.2834 46.0010 8178 46.4361 0.7089 0.3154
26.4334 47.0009 8352 49.4728 0.7098 0.3195
23.5124 48.0009 8526 48.7914 0.7116 0.3339
23.1348 49.0009 8700 47.3581 0.7207 0.3396
21.6129 50.0009 8874 46.1953 0.7296 0.3557
22.9044 51.0009 9048 43.5262 0.7335 0.3583
21.2048 52.0009 9222 51.1645 0.6949 0.3454
18.3862 53.0009 9396 47.1605 0.7434 0.3746
18.8145 54.0009 9570 50.5842 0.7187 0.3316
17.9621 55.0009 9744 46.3175 0.7326 0.3595
15.6122 56.0009 9918 46.0008 0.7439 0.3860
14.9198 57.0009 10092 49.5679 0.7436 0.3994
15.1845 58.0009 10266 44.8107 0.7499 0.4040
14.2785 59.0009 10440 48.7127 0.7415 0.4033
14.1863 60.0008 10614 47.7495 0.7532 0.4077
14.0713 61.0008 10788 49.2214 0.7579 0.4159
14.7541 62.0008 10962 53.5513 0.7477 0.3994
13.3041 63.0008 11136 44.9118 0.7552 0.4194
11.6473 64.0008 11310 49.2335 0.7627 0.4315
11.2095 65.0008 11484 46.2891 0.7675 0.4325
10.2987 66.0008 11658 53.1796 0.7624 0.4306
11.346 67.0008 11832 51.8456 0.7657 0.4339
9.3548 68.0008 12006 50.8765 0.7678 0.4403
9.3037 69.0008 12180 55.0888 0.7714 0.4477
8.9857 70.0008 12354 50.0248 0.7628 0.4440
8.7682 71.0008 12528 50.6941 0.7770 0.4619
9.1196 72.0008 12702 46.8410 0.7684 0.4584
8.3427 73.0007 12876 50.8483 0.7652 0.4536
7.8778 74.0007 13050 46.3875 0.7793 0.4660
6.9879 75.0007 13224 45.0568 0.7834 0.4688
7.5269 76.0007 13398 46.9041 0.7858 0.4689
6.9116 77.0007 13572 48.1086 0.7663 0.4703
6.9254 78.0007 13746 47.4047 0.7879 0.4844
6.2481 79.0007 13920 44.9859 0.7813 0.4757
6.6851 80.0007 14094 38.6904 0.7850 0.4852
5.97 81.0007 14268 42.5499 0.7882 0.4812
6.1771 82.0007 14442 38.4021 0.7928 0.4936
5.1963 83.0007 14616 42.9896 0.7939 0.4888
7.9398 84.0007 14790 40.9555 0.7838 0.4915
5.3613 85.0007 14964 42.9515 0.7908 0.5045
6.7202 86.0007 15138 39.7180 0.7864 0.4951
4.6764 87.0006 15312 38.2246 0.7937 0.5101
4.2945 88.0006 15486 38.6347 0.7956 0.5087
4.1892 89.0006 15660 35.4375 0.7958 0.5055
4.1461 90.0006 15834 44.9172 0.7964 0.5127
4.2493 91.0006 16008 35.8057 0.7935 0.5037
4.7168 92.0006 16182 37.1874 0.8039 0.5202
3.7186 93.0006 16356 34.5887 0.7948 0.5243
3.9092 94.0006 16530 34.3659 0.8049 0.5224
3.4922 95.0006 16704 38.1849 0.7997 0.5176
3.293 96.0006 16878 33.7994 0.8127 0.5347
3.294 97.0006 17052 31.2770 0.8034 0.5267
2.8844 98.0006 17226 32.2301 0.8153 0.5347
2.8165 99.0006 17400 37.9324 0.7940 0.5233
2.6399 100.0005 17574 31.1739 0.8110 0.5344
2.686 101.0005 17748 35.2568 0.8088 0.5258
2.406 102.0005 17922 32.8968 0.8139 0.5458
2.799 103.0005 18096 25.1094 0.8134 0.5300
1.9403 104.0005 18270 24.3377 0.8120 0.5341
1.8998 105.0005 18444 26.6559 0.8116 0.5427
1.6745 106.0005 18618 21.0844 0.8184 0.5326
1.5847 107.0005 18792 30.5684 0.8138 0.5412
1.539 108.0005 18966 29.5075 0.8157 0.5621
1.5605 109.0005 19140 26.9982 0.8164 0.5514
1.4464 110.0005 19314 22.9506 0.8223 0.5683
1.4368 111.0005 19488 27.1973 0.8284 0.5693
1.3086 112.0005 19662 32.0884 0.8116 0.5541
1.3881 113.0005 19836 19.1791 0.8306 0.5773
1.316 114.0004 20010 27.2289 0.8293 0.5661
1.3519 115.0004 20184 25.0924 0.8373 0.5942
1.3086 116.0004 20358 25.9505 0.8431 0.5962
1.2558 117.0004 20532 20.9844 0.8427 0.6016
1.3284 118.0004 20706 22.0272 0.8413 0.5966
1.2293 119.0004 20880 25.0141 0.8435 0.6093
1.1877 120.0004 21054 20.0948 0.8421 0.5953
1.1295 121.0004 21228 19.8363 0.8276 0.5805
1.1163 122.0004 21402 21.4298 0.8490 0.6072
1.0742 123.0004 21576 20.9026 0.8480 0.6119
1.0389 124.0004 21750 20.7149 0.8366 0.6152
1.0495 125.0004 21924 25.3593 0.8510 0.6198
1.1515 126.0004 22098 17.9324 0.8443 0.6120
1.0378 127.0003 22272 22.3808 0.8535 0.6271
1.0459 128.0003 22446 19.1860 0.8384 0.6144
0.9204 129.0003 22620 20.5149 0.8564 0.6272
0.961 130.0003 22794 19.8676 0.8573 0.6349
0.9265 131.0003 22968 22.2702 0.8543 0.6308
1.156 132.0003 23142 25.0896 0.8532 0.6203
1.0723 133.0003 23316 12.4057 0.8546 0.6243
0.9053 134.0003 23490 16.2697 0.8589 0.6356
0.8414 135.0003 23664 18.2528 0.8594 0.6376
0.9563 136.0003 23838 18.9026 0.8606 0.6404
0.8713 137.0003 24012 20.1320 0.8659 0.6426
0.886 138.0003 24186 21.3480 0.8577 0.6253
0.8638 139.0003 24360 19.3888 0.8645 0.6429
0.841 140.0003 24534 19.2783 0.8650 0.6474
0.8303 141.0002 24708 19.9639 0.8597 0.6464
0.8369 142.0002 24882 11.9309 0.8621 0.6514
0.715 143.0002 25056 13.8198 0.8681 0.6544
0.849 144.0002 25230 10.8690 0.8619 0.6375
0.8585 145.0002 25404 10.9302 0.8658 0.6518
0.7652 146.0002 25578 15.6227 0.8729 0.6648
0.7047 147.0002 25752 17.5963 0.8691 0.6607
0.7735 148.0002 25926 15.9798 0.8699 0.6584
0.7502 149.0002 26100 16.9661 0.8721 0.6640
0.6434 150.0002 26274 18.8849 0.8607 0.6547
0.7066 151.0002 26448 17.9607 0.8724 0.6668
0.6763 152.0002 26622 21.1410 0.8661 0.6678
0.6306 153.0002 26796 22.4174 0.8637 0.6507
0.6913 154.0001 26970 19.5015 0.8711 0.6677
0.6406 155.0001 27144 19.9176 0.8712 0.6669
0.7159 156.0001 27318 13.8663 0.8693 0.6673
0.7575 157.0001 27492 16.8359 0.8713 0.6741
0.6609 158.0001 27666 15.3045 0.8712 0.6728
0.6315 159.0001 27840 17.4548 0.8665 0.6735
0.6101 160.0001 28014 20.8768 0.8704 0.6730
0.64 161.0001 28188 18.5729 0.8765 0.6720
0.623 162.0001 28362 20.3598 0.8792 0.6778
0.5812 163.0001 28536 13.9977 0.8784 0.6792
0.5705 164.0001 28710 16.8151 0.8766 0.6763
0.584 165.0001 28884 18.1551 0.8797 0.6880
0.5394 166.0001 29058 17.7883 0.8784 0.6792
0.5432 167.0001 29232 19.1870 0.8770 0.6836
0.6009 168.0000 29406 16.1470 0.8818 0.6899
0.5492 169.0000 29580 16.3520 0.8801 0.6826
0.5594 170.0000 29754 15.6605 0.8777 0.6853
0.5397 171.0000 29928 17.4010 0.8783 0.6873
0.4919 172.0000 30102 18.0559 0.8848 0.6951
0.53 173.0000 30276 14.1754 0.8822 0.6955
0.5522 173.0013 30450 14.0451 0.8741 0.6914
0.5484 174.0013 30624 16.6871 0.8801 0.6916
0.5278 175.0013 30798 15.2314 0.8824 0.6921
0.4913 176.0013 30972 16.4353 0.8809 0.6945
0.52 177.0013 31146 18.0517 0.8868 0.7032
0.5637 178.0013 31320 16.3400 0.8423 0.6632
0.5497 179.0013 31494 14.6085 0.8776 0.6914
0.4954 180.0012 31668 14.8209 0.8848 0.7004
0.48 181.0012 31842 17.6260 0.8836 0.6990
0.6265 182.0012 32016 10.3516 0.8797 0.6926
0.4802 183.0012 32190 12.9974 0.8857 0.6996
0.4944 184.0012 32364 13.7040 0.8835 0.7034
0.5148 185.0012 32538 15.6512 0.8823 0.6999
0.4609 186.0012 32712 16.7489 0.8856 0.6994
0.4298 187.0012 32886 13.6762 0.8844 0.7002
0.4083 188.0012 33060 17.2014 0.8841 0.7030
0.5683 189.0012 33234 14.0504 0.8500 0.6427
0.4913 190.0012 33408 13.4722 0.8826 0.6992
0.4486 191.0012 33582 14.0649 0.8867 0.7038
0.4617 192.0012 33756 14.5238 0.8866 0.7051
0.4362 193.0012 33930 15.3280 0.8863 0.7062
0.4396 194.0011 34104 14.3054 0.8856 0.7045
0.3991 195.0011 34278 16.1425 0.8871 0.7053
0.3911 196.0011 34452 16.3227 0.8872 0.7150
0.4021 197.0011 34626 15.9223 0.8907 0.7169
0.4325 198.0011 34800 16.4887 0.8871 0.7072
0.4289 199.0011 34974 13.0254 0.8877 0.7120
0.4118 200.0011 35148 14.3179 0.8889 0.7133
0.3828 201.0011 35322 15.9050 0.8898 0.7142
0.399 202.0011 35496 15.5794 0.8930 0.7183
0.3962 203.0011 35670 23.9086 0.8873 0.7071
0.4236 204.0011 35844 14.5871 0.8892 0.7151
0.4175 205.0011 36018 13.0064 0.8888 0.7143
0.4509 206.0011 36192 14.4157 0.8907 0.7151
0.3698 207.0010 36366 16.9400 0.8911 0.7209
0.3959 208.0010 36540 11.6492 0.8919 0.7223
0.3722 209.0010 36714 10.6274 0.8906 0.7213
0.3643 210.0010 36888 13.9021 0.8901 0.7212
0.3607 211.0010 37062 16.8761 0.8906 0.7100
0.3781 212.0010 37236 14.9723 0.8920 0.7246
0.3774 213.0010 37410 16.4877 0.8887 0.7216
0.4089 214.0010 37584 14.8110 0.8910 0.7227
0.3354 215.0010 37758 15.7290 0.8931 0.7241
0.3453 216.0010 37932 17.8587 0.8930 0.7262
0.3855 217.0010 38106 16.6364 0.8923 0.7205
0.3547 218.0010 38280 15.0288 0.8902 0.7262
0.3944 219.0010 38454 15.1244 0.8928 0.7267
0.3322 220.0010 38628 15.5708 0.8974 0.7308
0.5656 221.0009 38802 15.3676 0.8853 0.7131
0.3659 222.0009 38976 7.9423 0.8845 0.7166
0.3521 223.0009 39150 13.7582 0.8929 0.7277
0.3583 224.0009 39324 14.8325 0.8933 0.7351
0.3265 225.0009 39498 15.1472 0.8937 0.7340
0.3049 226.0009 39672 14.5932 0.8885 0.7246
0.336 227.0009 39846 14.2317 0.8925 0.7312
0.3057 228.0009 40020 16.1414 0.8932 0.7360
0.3329 229.0009 40194 15.2193 0.8920 0.7296
0.2967 230.0009 40368 16.3685 0.8949 0.7350
0.3154 231.0009 40542 15.8833 0.8973 0.7380
0.3414 232.0009 40716 11.7715 0.8954 0.7344
0.3231 233.0009 40890 13.7687 0.8964 0.7366
0.3277 234.0008 41064 16.5868 0.8933 0.7321
0.3384 235.0008 41238 14.9357 0.8951 0.7408
0.3358 236.0008 41412 16.2438 0.8969 0.7389
0.2861 237.0008 41586 13.7728 0.8858 0.7211
0.3149 238.0008 41760 16.2031 0.8964 0.7378
0.3268 239.0008 41934 13.5356 0.8984 0.7366
0.3158 240.0008 42108 16.0668 0.8983 0.7363
0.288 241.0008 42282 16.6506 0.8969 0.7388
0.2693 242.0008 42456 15.0677 0.8951 0.7397
0.2793 243.0008 42630 16.6893 0.8964 0.7415
0.2718 244.0008 42804 17.5266 0.8981 0.7434
0.2792 245.0008 42978 16.0863 0.8937 0.7354
0.3232 246.0008 43152 18.1412 0.8959 0.7379
0.2769 247.0007 43326 18.2384 0.8975 0.7482
0.2967 248.0007 43500 15.9407 0.8972 0.7458
0.3054 249.0007 43674 16.6762 0.8957 0.7415
0.2838 250.0007 43848 16.8079 0.8988 0.7406
0.2707 251.0007 44022 16.9714 0.8952 0.7420
0.4811 252.0007 44196 9.5724 0.8906 0.7180
0.3373 253.0007 44370 11.0438 0.8960 0.7408
0.2654 254.0007 44544 14.4336 0.8971 0.7454
0.3087 255.0007 44718 14.2193 0.8973 0.7442
0.257 256.0007 44892 15.4050 0.8977 0.7428
0.2951 257.0007 45066 16.0725 0.8952 0.7405
0.25 258.0007 45240 17.0912 0.9012 0.7467
0.2637 259.0007 45414 15.3124 0.8975 0.7474
0.2375 260.0007 45588 14.8288 0.8974 0.7481
0.2269 261.0006 45762 16.0601 0.8986 0.7459
0.2742 262.0006 45936 14.0432 0.8977 0.7442
0.271 263.0006 46110 16.4956 0.8985 0.7466
0.3463 264.0006 46284 15.3674 0.8992 0.7449
0.2848 265.0006 46458 14.0978 0.9003 0.7483
0.2487 266.0006 46632 14.9997 0.8964 0.7437
0.2619 267.0006 46806 13.5976 0.8982 0.7492
0.2388 268.0006 46980 14.3842 0.8983 0.7478
0.2354 269.0006 47154 13.7162 0.8976 0.7481
0.2466 270.0006 47328 12.8044 0.9018 0.7484
0.2399 271.0006 47502 13.4347 0.8993 0.7506
0.4447 272.0006 47676 9.7105 0.9009 0.7438
0.261 273.0006 47850 12.8051 0.8953 0.7429
0.2415 274.0005 48024 14.9494 0.9013 0.7553
0.243 275.0005 48198 12.9017 0.9011 0.7557
0.2873 276.0005 48372 12.4695 0.9018 0.7545
0.3073 277.0005 48546 12.9455 0.9025 0.7533
0.2429 278.0005 48720 12.1919 0.9012 0.7548
0.2311 279.0005 48894 15.6412 0.9015 0.7576
0.3222 280.0005 49068 13.7687 0.8931 0.7480
0.2178 281.0005 49242 16.8131 0.8974 0.7473
0.2413 282.0005 49416 13.5668 0.9030 0.7568
0.2337 283.0005 49590 15.5167 0.9008 0.7509
0.2513 284.0005 49764 16.4551 0.8979 0.7481
0.2399 285.0005 49938 13.4715 0.9032 0.7578
0.2308 286.0005 50112 14.5640 0.9040 0.7604
0.3765 287.0005 50286 13.2947 0.8803 0.7446
0.2562 288.0004 50460 16.2386 0.8987 0.7529
0.2337 289.0004 50634 16.6809 0.9031 0.7574
0.2278 290.0004 50808 14.7238 0.8995 0.7506
0.2222 291.0004 50982 17.9847 0.8992 0.7488
0.2202 292.0004 51156 12.6368 0.9008 0.7505
0.2145 293.0004 51330 13.8875 0.9025 0.7545
0.2409 294.0004 51504 14.1272 0.9022 0.7581
0.2281 295.0004 51678 14.1585 0.9023 0.7568
0.2312 296.0004 51852 14.0201 0.9006 0.7487
0.2131 297.0004 52026 15.6053 0.9005 0.7523
0.2297 298.0004 52200 13.9298 0.9053 0.7579
0.2197 299.0004 52374 15.9253 0.9036 0.7602
0.2383 300.0004 52548 12.9275 0.9027 0.7574
0.2153 301.0003 52722 16.5673 0.9047 0.7617
0.1957 302.0003 52896 19.4735 0.9031 0.7586
0.1985 303.0003 53070 15.1224 0.9049 0.7613
0.1922 304.0003 53244 17.6586 0.9027 0.7601
0.2092 305.0003 53418 16.8100 0.9045 0.7674
0.2035 306.0003 53592 17.3255 0.9023 0.7621
0.247 307.0003 53766 14.9393 0.9015 0.7579
0.2209 308.0003 53940 17.7670 0.9018 0.7616
0.21 309.0003 54114 17.3934 0.9042 0.7635
0.2049 310.0003 54288 19.5490 0.9007 0.7545
0.2023 311.0003 54462 16.2449 0.9038 0.7566
0.3726 312.0003 54636 10.4166 0.8765 0.7226
0.2432 313.0003 54810 11.6401 0.9034 0.7608
0.2181 314.0003 54984 14.3938 0.9044 0.7654
0.2029 315.0002 55158 15.7325 0.9019 0.7607
0.2003 316.0002 55332 17.3243 0.9023 0.7618
0.1899 317.0002 55506 14.7359 0.9040 0.7672
0.1948 318.0002 55680 15.1991 0.9049 0.7664
0.2076 319.0002 55854 15.9182 0.8995 0.7574
0.2239 320.0002 56028 12.1547 0.9031 0.7585
0.1866 321.0002 56202 15.7659 0.9037 0.7624
0.1721 322.0002 56376 16.8787 0.9054 0.7635
0.1717 323.0002 56550 15.8258 0.9025 0.7619
0.1908 324.0002 56724 18.5532 0.9037 0.7618
0.1968 325.0002 56898 18.5373 0.9060 0.7662

Framework versions

  • Transformers 4.46.0
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.20.1
Downloads last month
2
Safetensors
Model size
31.5M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support