ht-stmini-cls-v6_ftis_noPretrain-cssl-npsNonennsNone
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 12.6679
- Accuracy: 0.9494
- Macro F1: 0.8742
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: 134675
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
---|---|---|---|---|---|
29.0394 | 0.0015 | 202 | 56.7948 | 0.0226 | 0.0157 |
9.9157 | 1.0015 | 404 | 122.1472 | 0.3377 | 0.1028 |
6.8856 | 2.0015 | 606 | 178.4100 | 0.5107 | 0.1300 |
5.6537 | 3.0015 | 808 | 153.1210 | 0.5484 | 0.1359 |
4.8787 | 4.0015 | 1010 | 97.3385 | 0.5825 | 0.1460 |
4.1301 | 5.0015 | 1212 | 58.1262 | 0.6046 | 0.1586 |
3.5358 | 6.0015 | 1414 | 34.0446 | 0.6040 | 0.1614 |
3.2316 | 7.0015 | 1616 | 25.4868 | 0.6264 | 0.1777 |
3.0193 | 8.0015 | 1818 | 20.7106 | 0.6264 | 0.1820 |
2.8551 | 9.0015 | 2020 | 17.6827 | 0.6368 | 0.1996 |
2.6372 | 10.0015 | 2222 | 17.0154 | 0.6291 | 0.2031 |
2.5454 | 11.0015 | 2424 | 13.9989 | 0.6558 | 0.2277 |
2.561 | 12.0015 | 2626 | 11.8079 | 0.6547 | 0.2507 |
2.4346 | 13.0015 | 2828 | 12.7712 | 0.6668 | 0.2715 |
2.3611 | 14.0015 | 3030 | 12.5375 | 0.6641 | 0.2937 |
2.2639 | 15.0015 | 3232 | 13.9663 | 0.6926 | 0.3135 |
2.1008 | 16.0015 | 3434 | 13.9551 | 0.7067 | 0.3581 |
2.1484 | 17.0015 | 3636 | 12.6761 | 0.7163 | 0.3577 |
2.0754 | 18.0015 | 3838 | 11.2040 | 0.7315 | 0.3919 |
1.9875 | 19.0015 | 4040 | 14.8334 | 0.7368 | 0.4078 |
1.8376 | 20.0015 | 4242 | 14.1404 | 0.7367 | 0.4139 |
1.8363 | 21.0015 | 4444 | 14.0238 | 0.7595 | 0.4399 |
1.6386 | 22.0015 | 4646 | 18.6358 | 0.7663 | 0.4558 |
1.5819 | 23.0015 | 4848 | 15.7189 | 0.7811 | 0.4771 |
1.4591 | 24.0015 | 5050 | 15.6616 | 0.7854 | 0.4829 |
1.6291 | 25.0015 | 5252 | 16.8924 | 0.7986 | 0.5067 |
1.4887 | 26.0015 | 5454 | 19.0706 | 0.7969 | 0.5039 |
1.3698 | 27.0015 | 5656 | 18.0771 | 0.8109 | 0.5169 |
1.3326 | 28.0015 | 5858 | 19.9888 | 0.7970 | 0.5028 |
1.3234 | 29.0015 | 6060 | 20.3724 | 0.8171 | 0.5380 |
1.3146 | 30.0015 | 6262 | 21.3991 | 0.8043 | 0.5219 |
1.2217 | 31.0015 | 6464 | 21.1857 | 0.8171 | 0.5545 |
1.1788 | 32.0015 | 6666 | 21.6528 | 0.8259 | 0.5550 |
1.0916 | 33.0015 | 6868 | 22.9352 | 0.8363 | 0.5595 |
1.092 | 34.0015 | 7070 | 24.5454 | 0.8388 | 0.5736 |
1.0218 | 35.0015 | 7272 | 20.6898 | 0.8369 | 0.5987 |
0.9729 | 36.0015 | 7474 | 22.3012 | 0.8507 | 0.6303 |
0.9803 | 37.0015 | 7676 | 19.0813 | 0.8620 | 0.6389 |
0.9151 | 38.0015 | 7878 | 23.1321 | 0.8701 | 0.6532 |
0.8737 | 39.0015 | 8080 | 22.7779 | 0.8710 | 0.6499 |
0.7884 | 40.0015 | 8282 | 27.0817 | 0.8714 | 0.6566 |
0.8056 | 41.0015 | 8484 | 23.3382 | 0.8776 | 0.6637 |
0.7573 | 42.0015 | 8686 | 27.7628 | 0.8805 | 0.6741 |
0.7288 | 43.0015 | 8888 | 29.0170 | 0.8814 | 0.6728 |
0.7195 | 44.0015 | 9090 | 24.4600 | 0.8835 | 0.6883 |
0.6096 | 45.0015 | 9292 | 30.9117 | 0.8891 | 0.6876 |
0.6144 | 46.0015 | 9494 | 25.4158 | 0.8781 | 0.6826 |
0.6163 | 47.0015 | 9696 | 29.8568 | 0.8864 | 0.6955 |
0.563 | 48.0015 | 9898 | 27.0068 | 0.8965 | 0.7118 |
0.5371 | 49.0015 | 10100 | 29.6224 | 0.8984 | 0.7155 |
0.5029 | 50.0015 | 10302 | 29.4799 | 0.8969 | 0.7125 |
0.4862 | 51.0015 | 10504 | 27.6201 | 0.9029 | 0.7203 |
0.4844 | 52.0015 | 10706 | 29.6786 | 0.8996 | 0.7129 |
0.5125 | 53.0015 | 10908 | 28.2789 | 0.9046 | 0.7342 |
0.4465 | 54.0015 | 11110 | 27.8457 | 0.8964 | 0.7208 |
0.4096 | 55.0015 | 11312 | 27.7240 | 0.9091 | 0.7384 |
0.4088 | 56.0015 | 11514 | 30.1158 | 0.9092 | 0.7423 |
0.3907 | 57.0015 | 11716 | 27.8627 | 0.9119 | 0.7494 |
0.3891 | 58.0015 | 11918 | 27.4582 | 0.9127 | 0.7553 |
0.3727 | 59.0015 | 12120 | 29.1156 | 0.9111 | 0.7532 |
0.384 | 60.0015 | 12322 | 29.2815 | 0.9152 | 0.7567 |
0.3557 | 61.0015 | 12524 | 27.7506 | 0.9141 | 0.7560 |
0.3517 | 62.0015 | 12726 | 25.4961 | 0.9111 | 0.7564 |
0.323 | 63.0015 | 12928 | 25.4990 | 0.9190 | 0.7696 |
0.3019 | 64.0015 | 13130 | 26.1274 | 0.9171 | 0.7593 |
0.2987 | 65.0015 | 13332 | 25.9306 | 0.9163 | 0.7667 |
0.2957 | 66.0015 | 13534 | 24.4659 | 0.9168 | 0.7637 |
0.3135 | 67.0015 | 13736 | 24.3262 | 0.9172 | 0.7640 |
0.2885 | 68.0015 | 13938 | 25.1840 | 0.9160 | 0.7640 |
0.2768 | 69.0015 | 14140 | 24.4111 | 0.9202 | 0.7726 |
0.2783 | 70.0015 | 14342 | 24.1955 | 0.9232 | 0.7839 |
0.2528 | 71.0015 | 14544 | 25.2125 | 0.9242 | 0.7850 |
0.2561 | 72.0015 | 14746 | 21.4088 | 0.9249 | 0.7829 |
0.2585 | 73.0015 | 14948 | 21.4207 | 0.9270 | 0.7875 |
0.251 | 74.0015 | 15150 | 19.7941 | 0.9222 | 0.7840 |
0.2555 | 75.0015 | 15352 | 19.4835 | 0.9261 | 0.7850 |
0.246 | 76.0015 | 15554 | 19.2469 | 0.9271 | 0.7986 |
0.2298 | 77.0015 | 15756 | 20.0481 | 0.9265 | 0.7875 |
0.2306 | 78.0015 | 15958 | 19.9456 | 0.9285 | 0.7920 |
0.2197 | 79.0015 | 16160 | 20.9567 | 0.9286 | 0.7968 |
0.2222 | 80.0015 | 16362 | 19.9434 | 0.9281 | 0.7936 |
0.2229 | 81.0015 | 16564 | 20.1175 | 0.9306 | 0.8024 |
0.2122 | 82.0015 | 16766 | 19.1138 | 0.9297 | 0.8071 |
0.21 | 83.0015 | 16968 | 18.6819 | 0.9307 | 0.8073 |
0.195 | 84.0015 | 17170 | 19.0340 | 0.9301 | 0.8015 |
0.1983 | 85.0015 | 17372 | 20.1099 | 0.9338 | 0.8133 |
0.2022 | 86.0015 | 17574 | 19.7204 | 0.9349 | 0.8109 |
0.1938 | 87.0015 | 17776 | 17.8072 | 0.9361 | 0.7960 |
0.1941 | 88.0015 | 17978 | 21.8040 | 0.9305 | 0.8049 |
0.1886 | 89.0015 | 18180 | 18.7756 | 0.9306 | 0.8081 |
0.1911 | 90.0015 | 18382 | 17.2777 | 0.9351 | 0.8151 |
0.1894 | 91.0015 | 18584 | 16.9758 | 0.9337 | 0.8130 |
0.1881 | 92.0015 | 18786 | 19.6362 | 0.9365 | 0.7962 |
0.1834 | 93.0015 | 18988 | 19.4640 | 0.9328 | 0.8181 |
0.1832 | 94.0015 | 19190 | 15.5361 | 0.9359 | 0.8167 |
0.1775 | 95.0015 | 19392 | 19.7958 | 0.9381 | 0.8016 |
0.1736 | 96.0015 | 19594 | 18.7959 | 0.9347 | 0.8024 |
0.1856 | 97.0015 | 19796 | 18.0060 | 0.9384 | 0.8071 |
0.1846 | 98.0015 | 19998 | 16.1659 | 0.9352 | 0.8020 |
0.173 | 99.0015 | 20200 | 19.5335 | 0.9336 | 0.8165 |
0.1611 | 100.0015 | 20402 | 15.6862 | 0.9381 | 0.8049 |
0.1728 | 101.0015 | 20604 | 15.7126 | 0.9389 | 0.8256 |
0.1808 | 102.0015 | 20806 | 14.7838 | 0.9383 | 0.8221 |
0.1692 | 103.0015 | 21008 | 18.6851 | 0.9389 | 0.8276 |
0.165 | 104.0015 | 21210 | 15.8484 | 0.9357 | 0.8261 |
0.1646 | 105.0015 | 21412 | 18.4846 | 0.9375 | 0.8083 |
0.1589 | 106.0015 | 21614 | 17.7613 | 0.9377 | 0.8242 |
0.1618 | 107.0015 | 21816 | 15.7972 | 0.9404 | 0.8341 |
0.1687 | 108.0015 | 22018 | 16.7881 | 0.9376 | 0.8136 |
0.1556 | 109.0015 | 22220 | 16.1685 | 0.9351 | 0.8077 |
0.1549 | 110.0015 | 22422 | 14.2477 | 0.9407 | 0.8363 |
0.1589 | 111.0015 | 22624 | 14.4724 | 0.9393 | 0.8151 |
0.152 | 112.0015 | 22826 | 17.5329 | 0.9375 | 0.8098 |
0.1549 | 113.0015 | 23028 | 16.0460 | 0.9372 | 0.8089 |
0.1494 | 114.0015 | 23230 | 16.4300 | 0.9405 | 0.8162 |
0.1571 | 115.0015 | 23432 | 16.2004 | 0.9398 | 0.8168 |
0.1651 | 116.0015 | 23634 | 16.1755 | 0.9381 | 0.8363 |
0.153 | 117.0015 | 23836 | 16.5582 | 0.9416 | 0.8345 |
0.1589 | 118.0015 | 24038 | 14.0753 | 0.9427 | 0.8211 |
0.1472 | 119.0015 | 24240 | 14.5073 | 0.9368 | 0.8357 |
0.1513 | 120.0015 | 24442 | 16.1945 | 0.9392 | 0.8186 |
0.1489 | 121.0015 | 24644 | 13.4503 | 0.9386 | 0.8162 |
0.1419 | 122.0015 | 24846 | 14.3266 | 0.9397 | 0.8395 |
0.1432 | 123.0015 | 25048 | 16.3798 | 0.9378 | 0.8373 |
0.1451 | 124.0015 | 25250 | 17.0060 | 0.9370 | 0.8131 |
0.1494 | 125.0015 | 25452 | 14.7301 | 0.9382 | 0.8383 |
0.145 | 126.0015 | 25654 | 18.0803 | 0.9411 | 0.8408 |
0.1426 | 127.0015 | 25856 | 16.6812 | 0.9413 | 0.8404 |
0.1398 | 128.0015 | 26058 | 12.7576 | 0.9419 | 0.8456 |
0.1397 | 129.0015 | 26260 | 14.9489 | 0.9354 | 0.8361 |
0.1437 | 130.0015 | 26462 | 16.5700 | 0.9411 | 0.8259 |
0.1429 | 131.0015 | 26664 | 14.8897 | 0.9428 | 0.8488 |
0.1334 | 132.0015 | 26866 | 12.8114 | 0.9434 | 0.8451 |
0.1432 | 133.0015 | 27068 | 14.6515 | 0.9423 | 0.8449 |
0.1462 | 134.0015 | 27270 | 13.9119 | 0.9456 | 0.8496 |
0.1446 | 135.0015 | 27472 | 13.9424 | 0.9399 | 0.8438 |
0.1403 | 136.0015 | 27674 | 14.9839 | 0.9419 | 0.8250 |
0.1386 | 137.0015 | 27876 | 13.4313 | 0.9400 | 0.8431 |
0.1348 | 138.0015 | 28078 | 12.7257 | 0.9424 | 0.8478 |
0.136 | 139.0015 | 28280 | 16.4742 | 0.9409 | 0.8430 |
0.1307 | 140.0015 | 28482 | 15.4253 | 0.9378 | 0.8207 |
0.1353 | 141.0015 | 28684 | 13.6584 | 0.9429 | 0.8499 |
0.1325 | 142.0015 | 28886 | 15.8384 | 0.9415 | 0.8439 |
0.1335 | 143.0015 | 29088 | 14.5212 | 0.9443 | 0.8523 |
0.1382 | 144.0015 | 29290 | 14.9674 | 0.9461 | 0.8514 |
0.1286 | 145.0015 | 29492 | 15.5164 | 0.9426 | 0.8487 |
0.1307 | 146.0015 | 29694 | 16.2832 | 0.9454 | 0.8551 |
0.1352 | 147.0015 | 29896 | 14.5950 | 0.9470 | 0.8555 |
0.1271 | 148.0015 | 30098 | 14.9534 | 0.9436 | 0.8472 |
0.1331 | 149.0015 | 30300 | 15.6851 | 0.9425 | 0.8476 |
0.1249 | 150.0015 | 30502 | 15.0723 | 0.9427 | 0.8525 |
0.1268 | 151.0015 | 30704 | 14.4689 | 0.9395 | 0.8464 |
0.1269 | 152.0015 | 30906 | 16.3796 | 0.9411 | 0.8484 |
0.1302 | 153.0015 | 31108 | 15.4793 | 0.9446 | 0.8583 |
0.1272 | 154.0015 | 31310 | 15.5411 | 0.9416 | 0.8357 |
0.1285 | 155.0015 | 31512 | 14.3161 | 0.9448 | 0.8525 |
0.1311 | 156.0015 | 31714 | 14.2404 | 0.9470 | 0.8577 |
0.126 | 157.0015 | 31916 | 15.5440 | 0.9476 | 0.8604 |
0.1273 | 158.0015 | 32118 | 15.2704 | 0.9476 | 0.8618 |
0.1284 | 159.0015 | 32320 | 15.1091 | 0.9441 | 0.8510 |
0.1248 | 160.0015 | 32522 | 16.2945 | 0.9443 | 0.8329 |
0.1237 | 161.0015 | 32724 | 14.0100 | 0.9424 | 0.8351 |
0.1294 | 162.0015 | 32926 | 14.9275 | 0.9458 | 0.8351 |
0.1257 | 163.0015 | 33128 | 12.6442 | 0.9464 | 0.8619 |
0.1336 | 164.0015 | 33330 | 13.7334 | 0.9468 | 0.8392 |
0.1294 | 165.0015 | 33532 | 13.7117 | 0.9420 | 0.8548 |
0.1308 | 166.0015 | 33734 | 12.1870 | 0.9444 | 0.8542 |
0.131 | 167.0015 | 33936 | 10.8715 | 0.9464 | 0.8551 |
0.1217 | 168.0015 | 34138 | 11.4961 | 0.9445 | 0.8388 |
0.1206 | 169.0015 | 34340 | 14.5135 | 0.9455 | 0.8369 |
0.1199 | 170.0015 | 34542 | 12.3938 | 0.9497 | 0.8437 |
0.1314 | 171.0015 | 34744 | 11.1588 | 0.9437 | 0.8338 |
0.1213 | 172.0015 | 34946 | 14.1750 | 0.9473 | 0.8409 |
0.1225 | 173.0015 | 35148 | 14.6673 | 0.9476 | 0.8421 |
0.1235 | 174.0015 | 35350 | 12.8347 | 0.9464 | 0.8386 |
0.1262 | 175.0015 | 35552 | 13.5715 | 0.9461 | 0.8401 |
0.12 | 176.0015 | 35754 | 11.5484 | 0.9439 | 0.8351 |
0.1178 | 177.0015 | 35956 | 14.8943 | 0.9474 | 0.8619 |
0.117 | 178.0015 | 36158 | 12.6414 | 0.9471 | 0.8640 |
0.1202 | 179.0015 | 36360 | 13.0439 | 0.9454 | 0.8417 |
0.1204 | 180.0015 | 36562 | 13.5738 | 0.9462 | 0.8585 |
0.1192 | 181.0015 | 36764 | 13.2942 | 0.9493 | 0.8643 |
0.1184 | 182.0015 | 36966 | 13.1960 | 0.9475 | 0.8607 |
0.1217 | 183.0015 | 37168 | 12.9831 | 0.9461 | 0.8401 |
0.1241 | 184.0015 | 37370 | 13.4301 | 0.9455 | 0.8579 |
0.12 | 185.0015 | 37572 | 11.6860 | 0.9474 | 0.8400 |
0.1208 | 186.0015 | 37774 | 13.0765 | 0.9487 | 0.8431 |
0.1179 | 187.0015 | 37976 | 12.2556 | 0.9463 | 0.8434 |
0.117 | 188.0015 | 38178 | 13.8460 | 0.9482 | 0.8464 |
0.114 | 189.0015 | 38380 | 13.5448 | 0.9480 | 0.8648 |
0.1158 | 190.0015 | 38582 | 14.1170 | 0.9475 | 0.8645 |
0.1188 | 191.0015 | 38784 | 12.9683 | 0.9459 | 0.8399 |
0.1227 | 192.0015 | 38986 | 14.4439 | 0.9482 | 0.8690 |
0.1109 | 193.0015 | 39188 | 14.1846 | 0.9479 | 0.8663 |
0.1193 | 194.0015 | 39390 | 14.8889 | 0.9507 | 0.8706 |
0.1142 | 195.0015 | 39592 | 12.4464 | 0.9461 | 0.8676 |
0.1148 | 196.0015 | 39794 | 12.4066 | 0.9491 | 0.8506 |
0.1229 | 197.0015 | 39996 | 13.3777 | 0.9477 | 0.8667 |
0.1131 | 198.0015 | 40198 | 12.1973 | 0.9484 | 0.8504 |
0.112 | 199.0015 | 40400 | 13.2975 | 0.9465 | 0.8481 |
0.1194 | 200.0015 | 40602 | 14.7107 | 0.9506 | 0.8709 |
0.1137 | 201.0015 | 40804 | 14.2346 | 0.9507 | 0.8717 |
0.1105 | 202.0015 | 41006 | 13.9265 | 0.9484 | 0.8691 |
0.1168 | 203.0015 | 41208 | 13.5502 | 0.9471 | 0.8469 |
0.114 | 204.0015 | 41410 | 13.2039 | 0.9487 | 0.8692 |
0.1115 | 205.0015 | 41612 | 11.9406 | 0.9491 | 0.8708 |
0.1135 | 206.0015 | 41814 | 14.0135 | 0.9493 | 0.8684 |
0.1137 | 207.0015 | 42016 | 11.2001 | 0.9464 | 0.8627 |
0.1131 | 208.0015 | 42218 | 12.8216 | 0.9494 | 0.8742 |
0.1131 | 209.0015 | 42420 | 12.7724 | 0.9464 | 0.8614 |
0.1133 | 210.0015 | 42622 | 12.0775 | 0.9486 | 0.8679 |
0.1126 | 211.0015 | 42824 | 12.5306 | 0.9474 | 0.8496 |
0.1167 | 212.0015 | 43026 | 11.6678 | 0.9473 | 0.8675 |
0.1172 | 213.0015 | 43228 | 10.8519 | 0.9486 | 0.8531 |
0.1123 | 214.0015 | 43430 | 13.4038 | 0.9463 | 0.8701 |
0.1141 | 215.0015 | 43632 | 13.1214 | 0.9484 | 0.8683 |
0.1169 | 216.0015 | 43834 | 10.6910 | 0.9469 | 0.8641 |
0.114 | 217.0015 | 44036 | 12.7617 | 0.9486 | 0.8713 |
0.1149 | 218.0015 | 44238 | 14.6465 | 0.9495 | 0.8716 |
0.1124 | 219.0015 | 44440 | 11.1635 | 0.9499 | 0.8727 |
0.1088 | 220.0015 | 44642 | 12.3209 | 0.9497 | 0.8700 |
0.113 | 221.0015 | 44844 | 12.8288 | 0.9454 | 0.8643 |
0.1139 | 222.0015 | 45046 | 10.2546 | 0.9468 | 0.8711 |
0.1072 | 223.0015 | 45248 | 11.0588 | 0.9511 | 0.8728 |
0.1107 | 224.0015 | 45450 | 11.9633 | 0.9475 | 0.8709 |
0.1137 | 225.0015 | 45652 | 11.5104 | 0.9489 | 0.8686 |
0.1193 | 226.0015 | 45854 | 10.2138 | 0.9471 | 0.8673 |
0.1082 | 227.0015 | 46056 | 12.0301 | 0.9464 | 0.8700 |
0.108 | 228.0015 | 46258 | 12.1987 | 0.9495 | 0.8711 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.20.1
- Downloads last month
- 6
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support