ht-stmini-cls-v6_ftis_noPretrain-cssl

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

  • Loss: 47.6574
  • Accuracy: 0.9233
  • Macro F1: 0.8216

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
1018.9662 0.0013 174 886.7844 0.0198 0.0149
260.1557 1.0013 348 169.5858 0.0300 0.0189
92.2633 2.0013 522 209.2763 0.0964 0.0395
76.7039 3.0013 696 233.4833 0.2778 0.0855
67.6178 4.0013 870 260.0321 0.3898 0.1045
63.425 5.0013 1044 272.0145 0.4480 0.1135
58.8917 6.0012 1218 236.8830 0.4785 0.1198
56.2551 7.0012 1392 252.6676 0.5018 0.1256
52.6558 8.0012 1566 247.7189 0.5149 0.1278
50.3825 9.0012 1740 231.8936 0.5282 0.1305
46.9564 10.0012 1914 209.5309 0.5358 0.1327
45.2095 11.0012 2088 168.8359 0.5424 0.1347
43.9985 12.0012 2262 155.1590 0.5501 0.1369
41.8779 13.0012 2436 145.9534 0.5555 0.1394
40.0768 14.0012 2610 127.8282 0.5675 0.1431
38.1067 15.0012 2784 121.9314 0.5652 0.1444
36.2789 16.0012 2958 116.3356 0.5808 0.1483
34.7069 17.0012 3132 113.5115 0.5841 0.1514
32.6285 18.0012 3306 100.3720 0.5823 0.1540
31.0395 19.0012 3480 96.5261 0.6127 0.1615
29.2644 20.0011 3654 87.1805 0.5916 0.1618
27.4652 21.0011 3828 87.9615 0.6149 0.1702
25.9325 22.0011 4002 83.6003 0.6226 0.1741
25.0002 23.0011 4176 76.7922 0.6275 0.1788
23.2397 24.0011 4350 73.2350 0.6334 0.1863
21.1748 25.0011 4524 69.9598 0.6515 0.1928
20.4036 26.0011 4698 69.3483 0.6560 0.2018
19.0807 27.0011 4872 65.5320 0.6733 0.2106
17.8389 28.0011 5046 68.3772 0.6597 0.2107
16.805 29.0011 5220 67.2978 0.6870 0.2337
15.8108 30.0011 5394 67.1013 0.6967 0.2429
14.6479 31.0011 5568 64.9705 0.7008 0.2507
14.6249 32.0011 5742 66.2467 0.7024 0.2705
12.8522 33.0010 5916 60.0096 0.7198 0.2823
12.2158 34.0010 6090 64.3605 0.7142 0.2945
11.0809 35.0010 6264 71.1757 0.7257 0.3146
10.6067 36.0010 6438 59.0718 0.7378 0.3307
9.5373 37.0010 6612 60.7505 0.7385 0.3389
9.2151 38.0010 6786 70.1060 0.7321 0.3431
8.4569 39.0010 6960 69.4160 0.7619 0.3835
7.6876 40.0010 7134 65.8783 0.7604 0.3925
7.2987 41.0010 7308 73.3103 0.7494 0.3927
6.8534 42.0010 7482 69.7635 0.7646 0.4074
6.2614 43.0010 7656 77.1677 0.7687 0.4313
5.8958 44.0010 7830 79.1795 0.7785 0.4380
5.4359 45.0010 8004 77.5591 0.7811 0.4430
4.8526 46.0010 8178 74.7853 0.7747 0.4194
4.6859 47.0009 8352 85.4596 0.7758 0.4579
4.2142 48.0009 8526 80.1337 0.7917 0.4642
3.9637 49.0009 8700 92.6560 0.7928 0.4744
3.616 50.0009 8874 83.4114 0.7932 0.4823
3.907 51.0009 9048 88.3556 0.7927 0.4862
3.3069 52.0009 9222 97.5112 0.7945 0.4893
2.9136 53.0009 9396 84.7138 0.8026 0.4982
2.8066 54.0009 9570 92.7946 0.8064 0.5016
2.6243 55.0009 9744 87.0662 0.8031 0.5100
2.252 56.0009 9918 74.2636 0.8148 0.5241
2.0999 57.0009 10092 82.0390 0.8102 0.5277
2.0915 58.0009 10266 83.4555 0.8153 0.5365
1.8435 59.0009 10440 87.2845 0.8143 0.5337
1.7772 60.0008 10614 86.3610 0.8204 0.5417
1.6551 61.0008 10788 86.5665 0.8192 0.5464
1.526 62.0008 10962 90.3210 0.8207 0.5448
1.4244 63.0008 11136 84.8928 0.8213 0.5564
1.2992 64.0008 11310 82.9842 0.8253 0.5623
1.2884 65.0008 11484 84.0504 0.8264 0.5622
1.0592 66.0008 11658 85.8088 0.8356 0.5733
1.0429 67.0008 11832 85.2289 0.8348 0.5739
0.7873 68.0008 12006 83.6686 0.8404 0.5699
0.7001 69.0008 12180 69.0753 0.8337 0.5714
0.6209 70.0008 12354 65.6049 0.8415 0.5875
0.5815 71.0008 12528 69.6665 0.8515 0.5974
0.6008 72.0008 12702 78.5241 0.8495 0.5992
0.471 73.0007 12876 80.9271 0.8516 0.6029
0.4406 74.0007 13050 73.7751 0.8528 0.6024
0.384 75.0007 13224 89.1608 0.8631 0.6266
0.3868 76.0007 13398 71.3697 0.8610 0.6194
0.3662 77.0007 13572 75.9505 0.8658 0.6328
0.3217 78.0007 13746 84.1621 0.8623 0.6345
0.3074 79.0007 13920 69.1188 0.8655 0.6450
0.3098 80.0007 14094 71.0890 0.8680 0.6409
0.2844 81.0007 14268 70.1989 0.8749 0.6595
0.2717 82.0007 14442 70.0522 0.8752 0.6564
0.2496 83.0007 14616 64.5729 0.8755 0.6640
0.2294 84.0007 14790 61.5465 0.8755 0.6682
0.2291 85.0007 14964 56.7459 0.8805 0.6778
0.2295 86.0007 15138 56.1958 0.8812 0.6786
0.22 87.0006 15312 55.2968 0.8788 0.6768
0.1854 88.0006 15486 50.3378 0.8834 0.6815
0.1919 89.0006 15660 47.6849 0.8834 0.6840
0.1852 90.0006 15834 51.5832 0.8868 0.6925
0.1956 91.0006 16008 47.1593 0.8878 0.6984
0.1871 92.0006 16182 44.7734 0.8905 0.6984
0.1706 93.0006 16356 45.7976 0.8920 0.7014
0.1783 94.0006 16530 45.5912 0.8908 0.7038
0.163 95.0006 16704 35.9449 0.8885 0.7011
0.1581 96.0006 16878 40.0306 0.8924 0.7110
0.1619 97.0006 17052 42.5047 0.8923 0.7122
0.1498 98.0006 17226 38.5984 0.8968 0.7146
0.1374 99.0006 17400 38.8074 0.8930 0.7116
0.1274 100.0005 17574 35.9301 0.8975 0.7236
0.1614 101.0005 17748 37.7465 0.8959 0.7198
0.1359 102.0005 17922 34.5807 0.8969 0.7246
0.1243 103.0005 18096 35.3724 0.8991 0.7226
0.1155 104.0005 18270 35.3707 0.8981 0.7280
0.1165 105.0005 18444 32.1560 0.8946 0.7285
0.1131 106.0005 18618 34.4429 0.9002 0.7321
0.1178 107.0005 18792 36.3275 0.8980 0.7288
0.1174 108.0005 18966 34.7116 0.8996 0.7387
0.1105 109.0005 19140 29.4596 0.8997 0.7354
0.1067 110.0005 19314 28.7954 0.9019 0.7360
0.1084 111.0005 19488 29.3049 0.9032 0.7322
0.0922 112.0005 19662 33.5139 0.9019 0.7330
0.0938 113.0005 19836 29.6300 0.9004 0.7424
0.0932 114.0004 20010 32.2453 0.8982 0.7416
0.1128 115.0004 20184 30.7392 0.9026 0.7419
0.0947 116.0004 20358 32.1838 0.9067 0.7483
0.0913 117.0004 20532 31.4314 0.9044 0.7433
0.1027 118.0004 20706 31.9996 0.9073 0.7509
0.0846 119.0004 20880 30.2339 0.9040 0.7532
0.0969 120.0004 21054 27.6715 0.9065 0.7493
0.0764 121.0004 21228 28.2749 0.9052 0.7509
0.0786 122.0004 21402 30.4559 0.9045 0.7545
0.0799 123.0004 21576 27.7721 0.9093 0.7487
0.0765 124.0004 21750 27.8817 0.9085 0.7560
0.0705 125.0004 21924 28.9301 0.9065 0.7548
0.0766 126.0004 22098 27.5768 0.9064 0.7547
0.0709 127.0003 22272 27.0074 0.9095 0.7620
0.0694 128.0003 22446 28.1529 0.9046 0.7559
0.0731 129.0003 22620 30.0155 0.9042 0.7558
0.0793 130.0003 22794 30.4234 0.9090 0.7628
0.0666 131.0003 22968 27.7200 0.9115 0.7698
0.0672 132.0003 23142 28.2346 0.9027 0.7510
0.0691 133.0003 23316 25.5206 0.9064 0.7607
0.0638 134.0003 23490 27.0041 0.9054 0.7622
0.0619 135.0003 23664 25.9758 0.9081 0.7585
0.0631 136.0003 23838 29.3851 0.9062 0.7625
0.0625 137.0003 24012 30.1125 0.9075 0.7694
0.0664 138.0003 24186 29.4815 0.9090 0.7627
0.0562 139.0003 24360 27.7964 0.9067 0.7625
0.0618 140.0003 24534 26.7068 0.9084 0.7650
0.0541 141.0002 24708 29.7151 0.9095 0.7704
0.0566 142.0002 24882 29.1786 0.9095 0.7639
0.0521 143.0002 25056 24.2856 0.9118 0.7683
0.0622 144.0002 25230 26.6733 0.9102 0.7719
0.0567 145.0002 25404 24.7187 0.9095 0.7693
0.0605 146.0002 25578 28.7627 0.9115 0.7729
0.0537 147.0002 25752 27.2667 0.9107 0.7698
0.0563 148.0002 25926 24.9834 0.9113 0.7752
0.0559 149.0002 26100 27.6179 0.9088 0.7680
0.0561 150.0002 26274 31.0997 0.9127 0.7795
0.0474 151.0002 26448 28.2782 0.9127 0.7747
0.0514 152.0002 26622 30.3161 0.9107 0.7700
0.0471 153.0002 26796 29.9901 0.9119 0.7692
0.0505 154.0001 26970 28.5633 0.9091 0.7680
0.0451 155.0001 27144 31.1368 0.9112 0.7730
0.0495 156.0001 27318 28.4080 0.9156 0.7784
0.0483 157.0001 27492 27.6302 0.9122 0.7780
0.0472 158.0001 27666 27.4289 0.9114 0.7825
0.0439 159.0001 27840 29.3186 0.9116 0.7799
0.0423 160.0001 28014 34.0200 0.9116 0.7818
0.0474 161.0001 28188 30.2252 0.9139 0.7812
0.0467 162.0001 28362 28.8594 0.9150 0.7851
0.0445 163.0001 28536 30.7785 0.9118 0.7759
0.0398 164.0001 28710 29.3775 0.9130 0.7846
0.0424 165.0001 28884 30.7597 0.9135 0.7771
0.0408 166.0001 29058 32.2907 0.9116 0.7854
0.0374 167.0001 29232 32.4651 0.9123 0.7838
0.0421 168.0000 29406 30.2800 0.9166 0.7906
0.0384 169.0000 29580 30.0484 0.9110 0.7801
0.0425 170.0000 29754 30.1615 0.9170 0.7799
0.0357 171.0000 29928 30.4271 0.9155 0.7893
0.0357 172.0000 30102 36.2971 0.9132 0.7877
0.0403 173.0000 30276 31.1155 0.9157 0.7844
0.0412 173.0013 30450 30.9512 0.9156 0.7928
0.0401 174.0013 30624 33.7072 0.9167 0.7895
0.0371 175.0013 30798 31.9823 0.9118 0.7831
0.0384 176.0013 30972 31.5748 0.9162 0.7860
0.0374 177.0013 31146 35.0625 0.9153 0.7867
0.0381 178.0013 31320 30.2533 0.9124 0.7873
0.0374 179.0013 31494 32.2868 0.9100 0.7824
0.0394 180.0012 31668 30.0325 0.9180 0.7956
0.0343 181.0012 31842 35.9215 0.9141 0.7845
0.0331 182.0012 32016 38.9509 0.9152 0.7924
0.0412 183.0012 32190 37.0806 0.9146 0.7939
0.0361 184.0012 32364 34.1683 0.9160 0.7873
0.0341 185.0012 32538 36.9450 0.9132 0.7893
0.0355 186.0012 32712 35.5289 0.9113 0.7881
0.0319 187.0012 32886 32.0215 0.9133 0.7887
0.0323 188.0012 33060 38.2136 0.9174 0.7893
0.0334 189.0012 33234 33.9702 0.9174 0.7868
0.0339 190.0012 33408 32.3623 0.9167 0.7915
0.031 191.0012 33582 35.9899 0.9189 0.7942
0.0333 192.0012 33756 30.8882 0.9123 0.7835
0.0313 193.0012 33930 29.3838 0.9154 0.7903
0.0357 194.0011 34104 31.5153 0.9146 0.7895
0.0297 195.0011 34278 36.7306 0.9171 0.8001
0.03 196.0011 34452 44.4969 0.9161 0.7955
0.031 197.0011 34626 37.9926 0.9156 0.7920
0.0312 198.0011 34800 35.3609 0.9112 0.7848
0.0267 199.0011 34974 34.6034 0.9171 0.7988
0.032 200.0011 35148 39.7821 0.9159 0.7945
0.0289 201.0011 35322 37.0427 0.9133 0.7964
0.029 202.0011 35496 32.8827 0.9150 0.7924
0.0292 203.0011 35670 43.9328 0.9155 0.7953
0.03 204.0011 35844 34.9994 0.9175 0.7929
0.0314 205.0011 36018 34.2457 0.9148 0.7877
0.03 206.0011 36192 35.2586 0.9163 0.7940
0.0301 207.0010 36366 42.5431 0.9175 0.8021
0.0299 208.0010 36540 37.2172 0.9194 0.8027
0.0277 209.0010 36714 37.7206 0.9177 0.7987
0.0285 210.0010 36888 37.0854 0.9143 0.7873
0.0291 211.0010 37062 36.8426 0.9164 0.7952
0.0351 212.0010 37236 35.1683 0.9188 0.8020
0.0288 213.0010 37410 36.8758 0.9195 0.8033
0.0266 214.0010 37584 38.5491 0.9178 0.8033
0.0226 215.0010 37758 39.0585 0.9159 0.7992
0.0266 216.0010 37932 39.5026 0.9169 0.8002
0.0244 217.0010 38106 42.3005 0.9191 0.7980
0.0335 218.0010 38280 47.1153 0.9181 0.7921
0.022 219.0010 38454 43.6929 0.9160 0.7975
0.0258 220.0010 38628 39.3755 0.9182 0.7927
0.0279 221.0009 38802 45.8714 0.9204 0.8051
0.025 222.0009 38976 43.5941 0.9167 0.7987
0.0256 223.0009 39150 43.9527 0.9176 0.8017
0.0258 224.0009 39324 45.6563 0.9205 0.8059
0.0281 225.0009 39498 40.4796 0.9195 0.7980
0.0225 226.0009 39672 41.8142 0.9179 0.8017
0.0248 227.0009 39846 43.5486 0.9173 0.8023
0.0228 228.0009 40020 45.3256 0.9212 0.8097
0.0217 229.0009 40194 45.3866 0.9176 0.8017
0.0247 230.0009 40368 42.5377 0.9221 0.8121
0.0235 231.0009 40542 37.5438 0.9184 0.8069
0.0235 232.0009 40716 40.0287 0.9184 0.8022
0.0246 233.0009 40890 42.5155 0.9177 0.8001
0.0255 234.0008 41064 42.7117 0.9195 0.8100
0.0206 235.0008 41238 48.3968 0.9174 0.8090
0.0232 236.0008 41412 51.0763 0.9152 0.8032
0.0234 237.0008 41586 39.4386 0.9198 0.8055
0.0233 238.0008 41760 44.5458 0.9217 0.8080
0.0238 239.0008 41934 48.2213 0.9191 0.7976
0.02 240.0008 42108 44.2605 0.9200 0.8129
0.0199 241.0008 42282 47.5592 0.9200 0.8082
0.0219 242.0008 42456 42.3564 0.9199 0.8075
0.0241 243.0008 42630 43.6339 0.9207 0.8045
0.0219 244.0008 42804 35.1476 0.9180 0.7980
0.0236 245.0008 42978 46.1355 0.9168 0.7999
0.0198 246.0008 43152 42.6001 0.9193 0.8004
0.0203 247.0007 43326 47.3434 0.9212 0.8086
0.0231 248.0007 43500 39.7633 0.9167 0.8017
0.0221 249.0007 43674 44.7583 0.9197 0.8025
0.021 250.0007 43848 50.2212 0.9221 0.8132
0.0202 251.0007 44022 47.9243 0.9136 0.8054
0.0185 252.0007 44196 46.0769 0.9194 0.8104
0.0189 253.0007 44370 52.2120 0.9174 0.8008
0.0179 254.0007 44544 45.7492 0.9195 0.8024
0.0216 255.0007 44718 47.2048 0.9215 0.8085
0.0212 256.0007 44892 44.5182 0.9215 0.8097
0.021 257.0007 45066 46.1859 0.9189 0.8010
0.0198 258.0007 45240 48.1614 0.9209 0.8078
0.0187 259.0007 45414 52.2066 0.9209 0.8036
0.0195 260.0007 45588 44.0922 0.9224 0.8086
0.0165 261.0006 45762 45.9520 0.9168 0.8043
0.0163 262.0006 45936 43.2828 0.9206 0.8072
0.0211 263.0006 46110 42.8789 0.9209 0.8048
0.017 264.0006 46284 41.3356 0.9233 0.8106
0.0161 265.0006 46458 48.6635 0.9185 0.8040
0.0209 266.0006 46632 46.9325 0.9235 0.8150
0.0184 267.0006 46806 50.3337 0.9230 0.8148
0.0198 268.0006 46980 50.8222 0.9197 0.8113
0.0163 269.0006 47154 46.9500 0.9213 0.8150
0.0162 270.0006 47328 45.6510 0.9233 0.8216
0.0187 271.0006 47502 37.2923 0.9231 0.8113
0.0177 272.0006 47676 45.4361 0.9181 0.8162
0.0184 273.0006 47850 46.4800 0.9248 0.8137
0.0155 274.0005 48024 46.2687 0.9192 0.8066
0.0165 275.0005 48198 47.8882 0.9231 0.8131
0.0153 276.0005 48372 50.2584 0.9220 0.8121
0.0251 277.0005 48546 48.6829 0.9223 0.8104
0.0173 278.0005 48720 48.3648 0.9210 0.8120
0.0169 279.0005 48894 51.1578 0.9214 0.8124
0.018 280.0005 49068 45.1408 0.9234 0.8181
0.0156 281.0005 49242 47.3514 0.9203 0.8069
0.0197 282.0005 49416 44.1649 0.9281 0.8109
0.0148 283.0005 49590 51.4681 0.9229 0.8156
0.0175 284.0005 49764 47.8627 0.9260 0.8087
0.0167 285.0005 49938 53.6919 0.9232 0.8115
0.0166 286.0005 50112 45.2318 0.9257 0.8214
0.0145 287.0005 50286 48.3413 0.9214 0.8159
0.0227 288.0004 50460 55.2927 0.9210 0.8151
0.0178 289.0004 50634 46.7973 0.9229 0.8156
0.0167 290.0004 50808 45.8350 0.9266 0.8207

Framework versions

  • Transformers 4.46.0
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.20.1
Downloads last month
3
Safetensors
Model size
31.2M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support