segformer-b1-from-scratch-run5
This model is a fine-tuned version of on the samitizerxu/kelp_data_rgbaa_swin_nir dataset. It achieves the following results on the evaluation set:
- Iou Kelp: 0.2882
- Loss: 0.7179
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: 22
- eval_batch_size: 22
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 80
Training results
Training Loss | Epoch | Step | Iou Kelp | Validation Loss |
---|---|---|---|---|
1.0 | 0.15 | 30 | 0.0113 | 0.9806 |
0.9993 | 0.29 | 60 | 0.0159 | 0.9691 |
0.9692 | 0.44 | 90 | 0.0179 | 0.9640 |
0.9912 | 0.59 | 120 | 0.0204 | 0.9532 |
0.9902 | 0.73 | 150 | 0.0099 | 0.9747 |
0.9912 | 0.88 | 180 | 0.0262 | 0.9330 |
0.9741 | 1.02 | 210 | 0.0155 | 0.9581 |
0.9737 | 1.17 | 240 | 0.0199 | 0.9319 |
0.9805 | 1.32 | 270 | 0.0233 | 0.9140 |
0.9574 | 1.46 | 300 | 0.0234 | 0.8942 |
0.8296 | 1.61 | 330 | 0.0119 | 0.9535 |
0.8707 | 1.76 | 360 | 0.0233 | 0.9085 |
0.976 | 1.9 | 390 | 0.0367 | 0.8714 |
0.9776 | 2.05 | 420 | 0.0424 | 0.8187 |
0.9663 | 2.2 | 450 | 0.0376 | 0.8124 |
0.9994 | 2.34 | 480 | 0.0323 | 0.8721 |
0.946 | 2.49 | 510 | 0.0466 | 0.8020 |
0.9993 | 2.63 | 540 | 0.0382 | 0.8266 |
0.9805 | 2.78 | 570 | 0.0249 | 0.9105 |
0.9506 | 2.93 | 600 | 0.0286 | 0.9019 |
0.9739 | 3.07 | 630 | 0.0267 | 0.9255 |
0.9843 | 3.22 | 660 | 0.0380 | 0.8543 |
0.9563 | 3.37 | 690 | 0.0339 | 0.8385 |
0.9353 | 3.51 | 720 | 0.0396 | 0.8547 |
0.9492 | 3.66 | 750 | 0.0392 | 0.7916 |
0.953 | 3.8 | 780 | 0.0445 | 0.7976 |
0.9752 | 3.95 | 810 | 0.0165 | 0.9435 |
0.9769 | 4.1 | 840 | 0.0536 | 0.7686 |
1.0 | 4.24 | 870 | 0.0238 | 0.9143 |
0.9739 | 4.39 | 900 | 0.0213 | 0.8626 |
0.9086 | 4.54 | 930 | 0.0415 | 0.8102 |
0.9557 | 4.68 | 960 | 0.0385 | 0.8055 |
1.0 | 4.83 | 990 | 0.0540 | 0.8136 |
1.0 | 4.98 | 1020 | 0.0258 | 0.8799 |
1.0 | 5.12 | 1050 | 0.0507 | 0.7994 |
0.9086 | 5.27 | 1080 | 0.0451 | 0.8493 |
0.9297 | 5.41 | 1110 | 0.0311 | 0.9036 |
0.963 | 5.56 | 1140 | 0.0549 | 0.7996 |
0.9109 | 5.71 | 1170 | 0.0461 | 0.7831 |
0.9822 | 5.85 | 1200 | 0.0306 | 0.8125 |
0.9447 | 6.0 | 1230 | 0.0151 | 0.9378 |
0.9725 | 6.15 | 1260 | 0.0192 | 0.8890 |
0.9619 | 6.29 | 1290 | 0.0401 | 0.8039 |
0.9653 | 6.44 | 1320 | 0.0457 | 0.7751 |
0.9357 | 6.59 | 1350 | 0.0498 | 0.7531 |
1.0 | 6.73 | 1380 | 0.0497 | 0.7618 |
0.9841 | 6.88 | 1410 | 0.0509 | 0.8379 |
1.0 | 7.02 | 1440 | 0.0223 | 0.9015 |
0.9479 | 7.17 | 1470 | 0.0827 | 0.8138 |
0.9955 | 7.32 | 1500 | 0.0177 | 0.8841 |
0.9758 | 7.46 | 1530 | 0.0217 | 0.9615 |
0.9912 | 7.61 | 1560 | 0.0395 | 0.7983 |
0.9923 | 7.76 | 1590 | 0.0205 | 0.8603 |
0.9387 | 7.9 | 1620 | 0.0489 | 0.7513 |
0.928 | 8.05 | 1650 | 0.0400 | 0.8886 |
0.9157 | 8.2 | 1680 | 0.0448 | 0.7630 |
0.9896 | 8.34 | 1710 | 0.0388 | 0.7792 |
0.9032 | 8.49 | 1740 | 0.0533 | 0.7399 |
0.9841 | 8.63 | 1770 | 0.0580 | 0.8018 |
0.969 | 8.78 | 1800 | 0.0576 | 0.7661 |
0.9661 | 8.93 | 1830 | 0.0486 | 0.7812 |
0.9758 | 9.07 | 1860 | 0.0491 | 0.7958 |
0.8972 | 9.22 | 1890 | 0.0392 | 0.7631 |
0.9413 | 9.37 | 1920 | 0.0467 | 0.8068 |
0.88 | 9.51 | 1950 | 0.0374 | 0.8465 |
0.9017 | 9.66 | 1980 | 0.0412 | 0.7847 |
0.9079 | 9.8 | 2010 | 0.0473 | 0.9055 |
0.8876 | 9.95 | 2040 | 0.0488 | 0.7668 |
0.9484 | 10.1 | 2070 | 0.0456 | 0.7815 |
0.9387 | 10.24 | 2100 | 0.0328 | 0.8699 |
1.0 | 10.39 | 2130 | 0.0403 | 0.7867 |
0.9391 | 10.54 | 2160 | 0.0797 | 0.9083 |
0.9452 | 10.68 | 2190 | 0.0460 | 0.8210 |
0.8905 | 10.83 | 2220 | 0.0407 | 0.7891 |
0.895 | 10.98 | 2250 | 0.0361 | 0.7920 |
0.9687 | 11.12 | 2280 | 0.0537 | 0.7589 |
0.9743 | 11.27 | 2310 | 0.0471 | 0.7990 |
0.9809 | 11.41 | 2340 | 0.0497 | 0.7483 |
0.9844 | 11.56 | 2370 | 0.0231 | 0.8341 |
0.9677 | 11.71 | 2400 | 0.0355 | 0.8333 |
0.9875 | 11.85 | 2430 | 0.0475 | 0.7670 |
0.8915 | 12.0 | 2460 | 0.0685 | 0.9265 |
1.0 | 12.15 | 2490 | 0.0460 | 0.7805 |
0.9952 | 12.29 | 2520 | 0.0452 | 0.7596 |
0.968 | 12.44 | 2550 | 0.0476 | 0.8224 |
0.9221 | 12.59 | 2580 | 0.0270 | 0.8552 |
1.0 | 12.73 | 2610 | 0.0482 | 0.8761 |
0.9677 | 12.88 | 2640 | 0.0233 | 0.9088 |
0.9399 | 13.02 | 2670 | 0.0155 | 0.8832 |
0.9534 | 13.17 | 2700 | 0.0445 | 0.7967 |
0.9264 | 13.32 | 2730 | 0.0687 | 0.7580 |
0.9594 | 13.46 | 2760 | 0.0649 | 0.7650 |
0.9733 | 13.61 | 2790 | 0.1277 | 0.7837 |
0.9397 | 13.76 | 2820 | 0.0871 | 0.7793 |
0.9999 | 13.9 | 2850 | 0.1863 | 0.7651 |
0.9368 | 14.05 | 2880 | 0.0573 | 0.8260 |
0.9296 | 14.2 | 2910 | 0.1523 | 0.8077 |
0.9407 | 14.34 | 2940 | 0.0486 | 0.7525 |
0.9448 | 14.49 | 2970 | 0.1615 | 0.8279 |
0.9695 | 14.63 | 3000 | 0.1231 | 0.8339 |
1.0 | 14.78 | 3030 | 0.0798 | 0.7823 |
0.9565 | 14.93 | 3060 | 0.2063 | 0.7564 |
0.9434 | 15.07 | 3090 | 0.2314 | 0.7536 |
0.978 | 15.22 | 3120 | 0.2240 | 0.7475 |
0.9401 | 15.37 | 3150 | 0.1385 | 0.7721 |
0.9665 | 15.51 | 3180 | 0.1396 | 0.7992 |
0.9607 | 15.66 | 3210 | 0.0736 | 0.7447 |
0.9512 | 15.8 | 3240 | 0.1348 | 0.7992 |
0.9181 | 15.95 | 3270 | 0.0985 | 0.7430 |
0.9417 | 16.1 | 3300 | 0.0462 | 0.7904 |
0.9385 | 16.24 | 3330 | 0.1473 | 0.8078 |
0.9384 | 16.39 | 3360 | 0.0561 | 0.7395 |
0.9326 | 16.54 | 3390 | 0.2212 | 0.7423 |
0.9799 | 16.68 | 3420 | 0.1509 | 0.8205 |
0.8899 | 16.83 | 3450 | 0.0716 | 0.7786 |
0.9754 | 16.98 | 3480 | 0.2254 | 0.7361 |
0.9647 | 17.12 | 3510 | 0.1768 | 0.8012 |
0.9362 | 17.27 | 3540 | 0.1584 | 0.8134 |
0.9779 | 17.41 | 3570 | 0.1196 | 0.7518 |
0.9326 | 17.56 | 3600 | 0.1921 | 0.7676 |
0.9614 | 17.71 | 3630 | 0.2033 | 0.7342 |
0.9622 | 17.85 | 3660 | 0.1299 | 0.7386 |
0.8703 | 18.0 | 3690 | 0.1533 | 0.8180 |
0.9459 | 18.15 | 3720 | 0.1504 | 0.7256 |
0.9859 | 18.29 | 3750 | 0.1865 | 0.7652 |
1.0 | 18.44 | 3780 | 0.1511 | 0.8045 |
0.9593 | 18.59 | 3810 | 0.2293 | 0.7607 |
0.9583 | 18.73 | 3840 | 0.1890 | 0.7308 |
0.9058 | 18.88 | 3870 | 0.1851 | 0.7870 |
0.953 | 19.02 | 3900 | 0.2030 | 0.7624 |
0.924 | 19.17 | 3930 | 0.1239 | 0.7849 |
0.9019 | 19.32 | 3960 | 0.2305 | 0.7485 |
0.9314 | 19.46 | 3990 | 0.1032 | 0.7293 |
0.8895 | 19.61 | 4020 | 0.1637 | 0.7956 |
0.9486 | 19.76 | 4050 | 0.0799 | 0.9128 |
0.8784 | 19.9 | 4080 | 0.0754 | 0.7671 |
0.9142 | 20.05 | 4110 | 0.1488 | 0.7567 |
1.0 | 20.2 | 4140 | 0.2080 | 0.7380 |
0.9176 | 20.34 | 4170 | 0.1782 | 0.7515 |
0.9215 | 20.49 | 4200 | 0.0930 | 0.7288 |
0.963 | 20.63 | 4230 | 0.1857 | 0.7506 |
0.9146 | 20.78 | 4260 | 0.2212 | 0.7408 |
0.9294 | 20.93 | 4290 | 0.2064 | 0.7323 |
0.8854 | 21.07 | 4320 | 0.2075 | 0.7473 |
0.9865 | 21.22 | 4350 | 0.1653 | 0.8171 |
0.9438 | 21.37 | 4380 | 0.1411 | 0.7523 |
0.9429 | 21.51 | 4410 | 0.2108 | 0.7613 |
0.9502 | 21.66 | 4440 | 0.2271 | 0.7374 |
0.9093 | 21.8 | 4470 | 0.1920 | 0.7653 |
0.9336 | 21.95 | 4500 | 0.0891 | 0.7500 |
0.9152 | 22.1 | 4530 | 0.1585 | 0.8189 |
0.9153 | 22.24 | 4560 | 0.2616 | 0.7239 |
0.8398 | 22.39 | 4590 | 0.2169 | 0.7510 |
0.9471 | 22.54 | 4620 | 0.2007 | 0.7289 |
0.9388 | 22.68 | 4650 | 0.2111 | 0.7689 |
0.9369 | 22.83 | 4680 | 0.2244 | 0.7177 |
0.9456 | 22.98 | 4710 | 0.1363 | 0.8247 |
0.9103 | 23.12 | 4740 | 0.2565 | 0.7335 |
1.0 | 23.27 | 4770 | 0.2031 | 0.7671 |
1.0 | 23.41 | 4800 | 0.1743 | 0.7442 |
0.879 | 23.56 | 4830 | 0.2156 | 0.7588 |
0.9668 | 23.71 | 4860 | 0.1453 | 0.8305 |
0.9327 | 23.85 | 4890 | 0.2714 | 0.7287 |
0.9298 | 24.0 | 4920 | 0.1491 | 0.8436 |
0.8313 | 24.15 | 4950 | 0.2105 | 0.7345 |
1.0 | 24.29 | 4980 | 0.1543 | 0.7511 |
0.9413 | 24.44 | 5010 | 0.1346 | 0.8504 |
0.9714 | 24.59 | 5040 | 0.2286 | 0.7357 |
0.9781 | 24.73 | 5070 | 0.1691 | 0.7408 |
0.9206 | 24.88 | 5100 | 0.1191 | 0.8582 |
0.9842 | 25.02 | 5130 | 0.1090 | 0.8746 |
0.9483 | 25.17 | 5160 | 0.1126 | 0.8713 |
0.8986 | 25.32 | 5190 | 0.0498 | 0.8127 |
0.9028 | 25.46 | 5220 | 0.2617 | 0.7342 |
1.0 | 25.61 | 5250 | 0.1516 | 0.7367 |
0.9594 | 25.76 | 5280 | 0.1723 | 0.7631 |
0.9518 | 25.9 | 5310 | 0.2255 | 0.7521 |
0.9613 | 26.05 | 5340 | 0.2086 | 0.7372 |
0.9985 | 26.2 | 5370 | 0.0610 | 0.8180 |
0.9332 | 26.34 | 5400 | 0.1802 | 0.7751 |
0.9743 | 26.49 | 5430 | 0.0532 | 0.8143 |
0.9815 | 26.63 | 5460 | 0.2184 | 0.7518 |
0.9564 | 26.78 | 5490 | 0.2248 | 0.7409 |
1.0 | 26.93 | 5520 | 0.1170 | 0.7504 |
0.9314 | 27.07 | 5550 | 0.2421 | 0.7435 |
0.9167 | 27.22 | 5580 | 0.2353 | 0.7439 |
0.9736 | 27.37 | 5610 | 0.1749 | 0.7347 |
0.9719 | 27.51 | 5640 | 0.1793 | 0.8076 |
1.0 | 27.66 | 5670 | 0.1879 | 0.7665 |
0.9733 | 27.8 | 5700 | 0.1642 | 0.7411 |
0.9041 | 27.95 | 5730 | 0.2878 | 0.7266 |
0.9057 | 28.1 | 5760 | 0.1770 | 0.8027 |
0.9485 | 28.24 | 5790 | 0.2226 | 0.7363 |
0.9641 | 28.39 | 5820 | 0.1740 | 0.8032 |
0.902 | 28.54 | 5850 | 0.2688 | 0.7523 |
0.9047 | 28.68 | 5880 | 0.2600 | 0.7308 |
0.997 | 28.83 | 5910 | 0.2428 | 0.7456 |
0.9589 | 28.98 | 5940 | 0.1723 | 0.7825 |
0.9256 | 29.12 | 5970 | 0.2057 | 0.7671 |
1.0 | 29.27 | 6000 | 0.2344 | 0.7409 |
0.9693 | 29.41 | 6030 | 0.1468 | 0.7332 |
0.9322 | 29.56 | 6060 | 0.1429 | 0.8253 |
0.9293 | 29.71 | 6090 | 0.2103 | 0.7393 |
0.9505 | 29.85 | 6120 | 0.1712 | 0.7898 |
0.9734 | 30.0 | 6150 | 0.2007 | 0.7613 |
0.9671 | 30.15 | 6180 | 0.2440 | 0.7532 |
1.0 | 30.29 | 6210 | 0.2503 | 0.7384 |
0.9586 | 30.44 | 6240 | 0.2954 | 0.7336 |
1.0 | 30.59 | 6270 | 0.2176 | 0.7586 |
0.9319 | 30.73 | 6300 | 0.1855 | 0.7958 |
0.8779 | 30.88 | 6330 | 0.1568 | 0.8000 |
0.8768 | 31.02 | 6360 | 0.2701 | 0.7234 |
1.0 | 31.17 | 6390 | 0.0853 | 0.9075 |
0.9749 | 31.32 | 6420 | 0.1562 | 0.7665 |
0.944 | 31.46 | 6450 | 0.1985 | 0.7785 |
0.9689 | 31.61 | 6480 | 0.2687 | 0.7234 |
0.9315 | 31.76 | 6510 | 0.2228 | 0.7221 |
0.9432 | 31.9 | 6540 | 0.1555 | 0.8126 |
0.9546 | 32.05 | 6570 | 0.1912 | 0.7635 |
0.9304 | 32.2 | 6600 | 0.2084 | 0.7409 |
0.9279 | 32.34 | 6630 | 0.2351 | 0.7482 |
0.9695 | 32.49 | 6660 | 0.2192 | 0.7500 |
0.9107 | 32.63 | 6690 | 0.2510 | 0.7437 |
1.0 | 32.78 | 6720 | 0.1856 | 0.7742 |
0.9125 | 32.93 | 6750 | 0.2278 | 0.7341 |
0.9135 | 33.07 | 6780 | 0.2615 | 0.7241 |
0.9368 | 33.22 | 6810 | 0.2067 | 0.7403 |
0.9319 | 33.37 | 6840 | 0.1821 | 0.7769 |
0.9346 | 33.51 | 6870 | 0.2333 | 0.7359 |
0.924 | 33.66 | 6900 | 0.2411 | 0.7335 |
0.906 | 33.8 | 6930 | 0.2797 | 0.7204 |
0.9535 | 33.95 | 6960 | 0.2573 | 0.7397 |
1.0 | 34.1 | 6990 | 0.2879 | 0.7343 |
0.954 | 34.24 | 7020 | 0.2346 | 0.7485 |
1.0 | 34.39 | 7050 | 0.2236 | 0.7693 |
0.9394 | 34.54 | 7080 | 0.1759 | 0.8031 |
0.9565 | 34.68 | 7110 | 0.2617 | 0.7312 |
0.8503 | 34.83 | 7140 | 0.2641 | 0.7242 |
0.972 | 34.98 | 7170 | 0.1391 | 0.8332 |
0.9649 | 35.12 | 7200 | 0.2151 | 0.7580 |
0.8979 | 35.27 | 7230 | 0.2225 | 0.7461 |
1.0 | 35.41 | 7260 | 0.2244 | 0.7377 |
0.991 | 35.56 | 7290 | 0.2535 | 0.7342 |
0.9386 | 35.71 | 7320 | 0.2251 | 0.7418 |
0.9713 | 35.85 | 7350 | 0.2228 | 0.7413 |
0.9144 | 36.0 | 7380 | 0.2504 | 0.7246 |
0.9671 | 36.15 | 7410 | 0.2861 | 0.7296 |
0.9592 | 36.29 | 7440 | 0.2213 | 0.7549 |
0.9221 | 36.44 | 7470 | 0.2016 | 0.7553 |
0.9356 | 36.59 | 7500 | 0.2195 | 0.7601 |
0.9307 | 36.73 | 7530 | 0.2693 | 0.7245 |
0.9438 | 36.88 | 7560 | 0.2046 | 0.7261 |
0.9795 | 37.02 | 7590 | 0.2259 | 0.7469 |
0.968 | 37.17 | 7620 | 0.2694 | 0.7147 |
1.0 | 37.32 | 7650 | 0.2124 | 0.7730 |
0.9625 | 37.46 | 7680 | 0.2393 | 0.7445 |
0.9369 | 37.61 | 7710 | 0.2405 | 0.7297 |
0.9485 | 37.76 | 7740 | 0.2747 | 0.7195 |
0.9435 | 37.9 | 7770 | 0.2444 | 0.7238 |
0.8679 | 38.05 | 7800 | 0.2206 | 0.7571 |
0.9141 | 38.2 | 7830 | 0.2558 | 0.7293 |
0.9181 | 38.34 | 7860 | 0.2639 | 0.7231 |
0.9758 | 38.49 | 7890 | 0.2669 | 0.7359 |
0.8926 | 38.63 | 7920 | 0.2901 | 0.7186 |
0.9481 | 38.78 | 7950 | 0.2450 | 0.7468 |
0.9166 | 38.93 | 7980 | 0.2456 | 0.7255 |
0.9843 | 39.07 | 8010 | 0.2393 | 0.7301 |
0.9967 | 39.22 | 8040 | 0.2511 | 0.7281 |
0.9758 | 39.37 | 8070 | 0.1683 | 0.8029 |
0.9653 | 39.51 | 8100 | 0.2242 | 0.7202 |
0.9674 | 39.66 | 8130 | 0.2313 | 0.7519 |
0.969 | 39.8 | 8160 | 0.1742 | 0.8009 |
0.9378 | 39.95 | 8190 | 0.2418 | 0.7351 |
0.9701 | 40.1 | 8220 | 0.1953 | 0.7794 |
0.9354 | 40.24 | 8250 | 0.2204 | 0.7590 |
0.9513 | 40.39 | 8280 | 0.2566 | 0.7284 |
0.9694 | 40.54 | 8310 | 0.2831 | 0.7253 |
0.9387 | 40.68 | 8340 | 0.2340 | 0.7466 |
1.0 | 40.83 | 8370 | 0.2740 | 0.7188 |
0.9896 | 40.98 | 8400 | 0.2137 | 0.7603 |
0.9121 | 41.12 | 8430 | 0.2520 | 0.7363 |
0.9439 | 41.27 | 8460 | 0.2480 | 0.7289 |
0.9783 | 41.41 | 8490 | 0.3102 | 0.7184 |
0.9649 | 41.56 | 8520 | 0.2420 | 0.7474 |
0.8501 | 41.71 | 8550 | 0.2764 | 0.7276 |
0.933 | 41.85 | 8580 | 0.2677 | 0.7236 |
0.9667 | 42.0 | 8610 | 0.2438 | 0.7404 |
0.9402 | 42.15 | 8640 | 0.2467 | 0.7377 |
0.8646 | 42.29 | 8670 | 0.2617 | 0.7296 |
0.9862 | 42.44 | 8700 | 0.1372 | 0.8366 |
0.9906 | 42.59 | 8730 | 0.2985 | 0.7230 |
0.9926 | 42.73 | 8760 | 0.2264 | 0.7557 |
0.99 | 42.88 | 8790 | 0.2942 | 0.7208 |
0.8906 | 43.02 | 8820 | 0.2748 | 0.7257 |
0.8935 | 43.17 | 8850 | 0.2368 | 0.7472 |
0.9676 | 43.32 | 8880 | 0.2767 | 0.7245 |
0.9665 | 43.46 | 8910 | 0.1487 | 0.8215 |
0.9117 | 43.61 | 8940 | 0.2589 | 0.7253 |
0.9734 | 43.76 | 8970 | 0.2316 | 0.7457 |
0.9331 | 43.9 | 9000 | 0.2410 | 0.7375 |
0.9791 | 44.05 | 9030 | 0.2859 | 0.7256 |
0.9654 | 44.2 | 9060 | 0.2524 | 0.7349 |
0.9711 | 44.34 | 9090 | 0.2870 | 0.7174 |
0.8592 | 44.49 | 9120 | 0.1605 | 0.8222 |
0.9246 | 44.63 | 9150 | 0.2367 | 0.7370 |
0.9544 | 44.78 | 9180 | 0.2447 | 0.7372 |
0.9318 | 44.93 | 9210 | 0.1873 | 0.7707 |
0.9579 | 45.07 | 9240 | 0.2717 | 0.7123 |
0.9325 | 45.22 | 9270 | 0.2947 | 0.7169 |
0.9246 | 45.37 | 9300 | 0.2441 | 0.7357 |
0.9772 | 45.51 | 9330 | 0.2280 | 0.7449 |
0.8828 | 45.66 | 9360 | 0.1924 | 0.7817 |
1.0 | 45.8 | 9390 | 0.1880 | 0.7764 |
0.965 | 45.95 | 9420 | 0.2047 | 0.7718 |
0.8838 | 46.1 | 9450 | 0.3006 | 0.7133 |
0.9389 | 46.24 | 9480 | 0.3049 | 0.7202 |
1.0 | 46.39 | 9510 | 0.2433 | 0.7447 |
0.8744 | 46.54 | 9540 | 0.2295 | 0.7597 |
0.9409 | 46.68 | 9570 | 0.3002 | 0.7158 |
0.9968 | 46.83 | 9600 | 0.3180 | 0.7143 |
0.9477 | 46.98 | 9630 | 0.2468 | 0.7354 |
0.9456 | 47.12 | 9660 | 0.2122 | 0.7599 |
0.9736 | 47.27 | 9690 | 0.1841 | 0.7891 |
1.0 | 47.41 | 9720 | 0.2437 | 0.7326 |
0.962 | 47.56 | 9750 | 0.2870 | 0.7117 |
0.9701 | 47.71 | 9780 | 0.2834 | 0.7185 |
0.9076 | 47.85 | 9810 | 0.2544 | 0.7319 |
0.9523 | 48.0 | 9840 | 0.2267 | 0.7449 |
0.9756 | 48.15 | 9870 | 0.2744 | 0.7278 |
0.9834 | 48.29 | 9900 | 0.2268 | 0.7490 |
0.9497 | 48.44 | 9930 | 0.2304 | 0.7419 |
0.9165 | 48.59 | 9960 | 0.2443 | 0.7343 |
0.9806 | 48.73 | 9990 | 0.2997 | 0.7207 |
0.9385 | 48.88 | 10020 | 0.2309 | 0.7585 |
0.9478 | 49.02 | 10050 | 0.2892 | 0.7166 |
0.8437 | 49.17 | 10080 | 0.2779 | 0.7271 |
0.9555 | 49.32 | 10110 | 0.2222 | 0.7608 |
0.9454 | 49.46 | 10140 | 0.3031 | 0.7174 |
0.9652 | 49.61 | 10170 | 0.2557 | 0.7330 |
0.9245 | 49.76 | 10200 | 0.2834 | 0.7204 |
1.0 | 49.9 | 10230 | 0.2456 | 0.7373 |
0.9409 | 50.05 | 10260 | 0.2573 | 0.7292 |
0.9049 | 50.2 | 10290 | 0.2108 | 0.7541 |
0.9896 | 50.34 | 10320 | 0.2984 | 0.7091 |
0.9276 | 50.49 | 10350 | 0.2964 | 0.7121 |
0.9667 | 50.63 | 10380 | 0.2647 | 0.7291 |
1.0 | 50.78 | 10410 | 0.2924 | 0.7133 |
0.953 | 50.93 | 10440 | 0.2362 | 0.7387 |
0.9264 | 51.07 | 10470 | 0.2518 | 0.7360 |
0.9296 | 51.22 | 10500 | 0.2864 | 0.7140 |
0.9208 | 51.37 | 10530 | 0.2373 | 0.7532 |
0.9694 | 51.51 | 10560 | 0.2979 | 0.7149 |
0.967 | 51.66 | 10590 | 0.2769 | 0.7216 |
0.9104 | 51.8 | 10620 | 0.2801 | 0.7152 |
0.9527 | 51.95 | 10650 | 0.2503 | 0.7264 |
0.9278 | 52.1 | 10680 | 0.2726 | 0.7268 |
0.8901 | 52.24 | 10710 | 0.2575 | 0.7256 |
0.9937 | 52.39 | 10740 | 0.2722 | 0.7199 |
0.9339 | 52.54 | 10770 | 0.2886 | 0.7134 |
0.9213 | 52.68 | 10800 | 0.2749 | 0.7174 |
0.906 | 52.83 | 10830 | 0.2202 | 0.7493 |
0.9951 | 52.98 | 10860 | 0.2620 | 0.7222 |
0.9361 | 53.12 | 10890 | 0.2363 | 0.7350 |
0.9203 | 53.27 | 10920 | 0.1988 | 0.7694 |
0.9692 | 53.41 | 10950 | 0.2775 | 0.7180 |
0.9276 | 53.56 | 10980 | 0.2771 | 0.7177 |
0.9969 | 53.71 | 11010 | 0.2272 | 0.7428 |
0.9394 | 53.85 | 11040 | 0.2408 | 0.7346 |
0.9047 | 54.0 | 11070 | 0.2492 | 0.7222 |
0.9347 | 54.15 | 11100 | 0.2611 | 0.7305 |
0.897 | 54.29 | 11130 | 0.2466 | 0.7344 |
0.962 | 54.44 | 11160 | 0.2592 | 0.7253 |
0.9222 | 54.59 | 11190 | 0.2809 | 0.7191 |
0.9178 | 54.73 | 11220 | 0.2713 | 0.7226 |
0.9096 | 54.88 | 11250 | 0.2551 | 0.7270 |
0.9233 | 55.02 | 11280 | 0.2410 | 0.7422 |
0.9365 | 55.17 | 11310 | 0.3120 | 0.7069 |
0.9768 | 55.32 | 11340 | 0.2473 | 0.7372 |
0.9893 | 55.46 | 11370 | 0.2216 | 0.7537 |
0.9699 | 55.61 | 11400 | 0.2307 | 0.7431 |
0.9793 | 55.76 | 11430 | 0.2926 | 0.7134 |
1.0 | 55.9 | 11460 | 0.2622 | 0.7226 |
0.9781 | 56.05 | 11490 | 0.2244 | 0.7454 |
0.9388 | 56.2 | 11520 | 0.2631 | 0.7280 |
0.9066 | 56.34 | 11550 | 0.2486 | 0.7369 |
0.9717 | 56.49 | 11580 | 0.2524 | 0.7297 |
0.9385 | 56.63 | 11610 | 0.2806 | 0.7155 |
0.9443 | 56.78 | 11640 | 0.2134 | 0.7768 |
0.951 | 56.93 | 11670 | 0.2856 | 0.7134 |
0.9419 | 57.07 | 11700 | 0.3246 | 0.7086 |
0.9639 | 57.22 | 11730 | 0.3028 | 0.7070 |
0.9031 | 57.37 | 11760 | 0.2565 | 0.7317 |
0.9709 | 57.51 | 11790 | 0.2863 | 0.7257 |
0.9698 | 57.66 | 11820 | 0.3146 | 0.7110 |
0.9678 | 57.8 | 11850 | 0.2709 | 0.7236 |
0.8802 | 57.95 | 11880 | 0.2832 | 0.7182 |
0.9881 | 58.1 | 11910 | 0.2397 | 0.7376 |
0.9417 | 58.24 | 11940 | 0.2842 | 0.7126 |
1.0 | 58.39 | 11970 | 0.2598 | 0.7271 |
0.9558 | 58.54 | 12000 | 0.2954 | 0.7106 |
0.9581 | 58.68 | 12030 | 0.2863 | 0.7150 |
0.975 | 58.83 | 12060 | 0.2503 | 0.7396 |
0.8941 | 58.98 | 12090 | 0.3105 | 0.7083 |
0.9497 | 59.12 | 12120 | 0.2750 | 0.7273 |
0.9427 | 59.27 | 12150 | 0.2863 | 0.7192 |
0.9784 | 59.41 | 12180 | 0.2806 | 0.7193 |
0.9475 | 59.56 | 12210 | 0.2807 | 0.7195 |
0.8317 | 59.71 | 12240 | 0.2774 | 0.7245 |
0.9697 | 59.85 | 12270 | 0.2771 | 0.7228 |
0.9692 | 60.0 | 12300 | 0.2914 | 0.7155 |
0.9834 | 60.15 | 12330 | 0.2790 | 0.7221 |
0.8969 | 60.29 | 12360 | 0.2851 | 0.7178 |
0.9812 | 60.44 | 12390 | 0.2558 | 0.7320 |
0.8812 | 60.59 | 12420 | 0.2558 | 0.7304 |
0.9679 | 60.73 | 12450 | 0.2966 | 0.7115 |
0.839 | 60.88 | 12480 | 0.2884 | 0.7135 |
0.9388 | 61.02 | 12510 | 0.3028 | 0.7106 |
0.9713 | 61.17 | 12540 | 0.3106 | 0.7115 |
0.907 | 61.32 | 12570 | 0.2940 | 0.7130 |
0.8798 | 61.46 | 12600 | 0.3048 | 0.7087 |
0.9661 | 61.61 | 12630 | 0.2852 | 0.7155 |
0.8974 | 61.76 | 12660 | 0.2835 | 0.7172 |
0.9523 | 61.9 | 12690 | 0.2897 | 0.7153 |
0.9747 | 62.05 | 12720 | 0.2649 | 0.7262 |
1.0 | 62.2 | 12750 | 0.2828 | 0.7170 |
0.9701 | 62.34 | 12780 | 0.2471 | 0.7406 |
0.9084 | 62.49 | 12810 | 0.2735 | 0.7241 |
0.9404 | 62.63 | 12840 | 0.2667 | 0.7271 |
0.9866 | 62.78 | 12870 | 0.2522 | 0.7383 |
0.911 | 62.93 | 12900 | 0.2566 | 0.7334 |
0.9561 | 63.07 | 12930 | 0.3086 | 0.7067 |
1.0 | 63.22 | 12960 | 0.2825 | 0.7172 |
0.9011 | 63.37 | 12990 | 0.2818 | 0.7161 |
0.971 | 63.51 | 13020 | 0.2675 | 0.7287 |
0.9452 | 63.66 | 13050 | 0.3012 | 0.7075 |
0.9689 | 63.8 | 13080 | 0.3054 | 0.7071 |
0.8509 | 63.95 | 13110 | 0.2755 | 0.7193 |
0.9464 | 64.1 | 13140 | 0.2613 | 0.7269 |
0.8899 | 64.24 | 13170 | 0.2685 | 0.7216 |
0.9468 | 64.39 | 13200 | 0.2877 | 0.7116 |
0.968 | 64.54 | 13230 | 0.2873 | 0.7159 |
0.9616 | 64.68 | 13260 | 0.2841 | 0.7149 |
0.9487 | 64.83 | 13290 | 0.2798 | 0.7165 |
0.9479 | 64.98 | 13320 | 0.2840 | 0.7135 |
0.9099 | 65.12 | 13350 | 0.2594 | 0.7313 |
0.8809 | 65.27 | 13380 | 0.2758 | 0.7177 |
0.9643 | 65.41 | 13410 | 0.3070 | 0.7063 |
0.9287 | 65.56 | 13440 | 0.2868 | 0.7142 |
0.9509 | 65.71 | 13470 | 0.2747 | 0.7185 |
0.9495 | 65.85 | 13500 | 0.2450 | 0.7375 |
0.8864 | 66.0 | 13530 | 0.2709 | 0.7233 |
0.9703 | 66.15 | 13560 | 0.2661 | 0.7300 |
0.9289 | 66.29 | 13590 | 0.2732 | 0.7249 |
0.9736 | 66.44 | 13620 | 0.2927 | 0.7135 |
0.9569 | 66.59 | 13650 | 0.2860 | 0.7182 |
0.9636 | 66.73 | 13680 | 0.2636 | 0.7287 |
0.9668 | 66.88 | 13710 | 0.2694 | 0.7231 |
0.8278 | 67.02 | 13740 | 0.2912 | 0.7118 |
0.9101 | 67.17 | 13770 | 0.3011 | 0.7095 |
0.9701 | 67.32 | 13800 | 0.2967 | 0.7109 |
0.9373 | 67.46 | 13830 | 0.2961 | 0.7108 |
0.9626 | 67.61 | 13860 | 0.2806 | 0.7148 |
0.9618 | 67.76 | 13890 | 0.2870 | 0.7129 |
0.9522 | 67.9 | 13920 | 0.2679 | 0.7235 |
0.9013 | 68.05 | 13950 | 0.2906 | 0.7134 |
0.9284 | 68.2 | 13980 | 0.2956 | 0.7137 |
1.0 | 68.34 | 14010 | 0.2874 | 0.7199 |
0.9377 | 68.49 | 14040 | 0.2857 | 0.7191 |
0.9778 | 68.63 | 14070 | 0.2841 | 0.7191 |
0.9189 | 68.78 | 14100 | 0.2869 | 0.7189 |
0.9416 | 68.93 | 14130 | 0.2784 | 0.7224 |
0.8688 | 69.07 | 14160 | 0.2864 | 0.7187 |
0.9559 | 69.22 | 14190 | 0.2796 | 0.7229 |
0.9967 | 69.37 | 14220 | 0.2831 | 0.7202 |
0.9331 | 69.51 | 14250 | 0.2996 | 0.7146 |
0.8874 | 69.66 | 14280 | 0.2989 | 0.7145 |
0.9949 | 69.8 | 14310 | 0.3045 | 0.7119 |
0.9415 | 69.95 | 14340 | 0.3014 | 0.7126 |
0.9696 | 70.1 | 14370 | 0.2985 | 0.7150 |
0.9685 | 70.24 | 14400 | 0.2933 | 0.7168 |
0.919 | 70.39 | 14430 | 0.2898 | 0.7175 |
0.9707 | 70.54 | 14460 | 0.2823 | 0.7201 |
0.9462 | 70.68 | 14490 | 0.2843 | 0.7195 |
0.85 | 70.83 | 14520 | 0.2899 | 0.7176 |
0.9442 | 70.98 | 14550 | 0.2917 | 0.7160 |
0.8982 | 71.12 | 14580 | 0.2885 | 0.7180 |
0.9435 | 71.27 | 14610 | 0.2866 | 0.7199 |
0.9786 | 71.41 | 14640 | 0.2839 | 0.7208 |
0.8984 | 71.56 | 14670 | 0.2809 | 0.7225 |
0.9419 | 71.71 | 14700 | 0.2902 | 0.7179 |
0.9325 | 71.85 | 14730 | 0.2931 | 0.7157 |
1.0 | 72.0 | 14760 | 0.3010 | 0.7121 |
1.0 | 72.15 | 14790 | 0.3040 | 0.7111 |
0.942 | 72.29 | 14820 | 0.3027 | 0.7122 |
0.955 | 72.44 | 14850 | 0.2971 | 0.7135 |
0.9204 | 72.59 | 14880 | 0.2830 | 0.7211 |
0.9359 | 72.73 | 14910 | 0.2871 | 0.7189 |
0.9656 | 72.88 | 14940 | 0.2920 | 0.7164 |
0.894 | 73.02 | 14970 | 0.2935 | 0.7158 |
0.9308 | 73.17 | 15000 | 0.2901 | 0.7179 |
0.9698 | 73.32 | 15030 | 0.2937 | 0.7154 |
0.9481 | 73.46 | 15060 | 0.2961 | 0.7142 |
0.8752 | 73.61 | 15090 | 0.2926 | 0.7154 |
0.9822 | 73.76 | 15120 | 0.2941 | 0.7142 |
0.8797 | 73.9 | 15150 | 0.2936 | 0.7153 |
1.0 | 74.05 | 15180 | 0.2867 | 0.7178 |
0.9081 | 74.2 | 15210 | 0.2901 | 0.7171 |
0.894 | 74.34 | 15240 | 0.2810 | 0.7220 |
0.9254 | 74.49 | 15270 | 0.2791 | 0.7218 |
0.9925 | 74.63 | 15300 | 0.2806 | 0.7212 |
0.9774 | 74.78 | 15330 | 0.2751 | 0.7237 |
0.9542 | 74.93 | 15360 | 0.2804 | 0.7206 |
0.9294 | 75.07 | 15390 | 0.2848 | 0.7184 |
0.9539 | 75.22 | 15420 | 0.2828 | 0.7203 |
0.9277 | 75.37 | 15450 | 0.2838 | 0.7201 |
1.0 | 75.51 | 15480 | 0.2790 | 0.7223 |
0.9104 | 75.66 | 15510 | 0.2835 | 0.7206 |
0.9232 | 75.8 | 15540 | 0.2823 | 0.7213 |
0.9011 | 75.95 | 15570 | 0.2880 | 0.7175 |
0.9345 | 76.1 | 15600 | 0.2819 | 0.7213 |
0.9263 | 76.24 | 15630 | 0.2850 | 0.7186 |
0.917 | 76.39 | 15660 | 0.2829 | 0.7206 |
0.9744 | 76.54 | 15690 | 0.2906 | 0.7161 |
0.9647 | 76.68 | 15720 | 0.2846 | 0.7202 |
0.9842 | 76.83 | 15750 | 0.2864 | 0.7192 |
0.9 | 76.98 | 15780 | 0.2855 | 0.7189 |
0.9378 | 77.12 | 15810 | 0.2848 | 0.7191 |
0.9141 | 77.27 | 15840 | 0.2875 | 0.7181 |
0.8811 | 77.41 | 15870 | 0.2855 | 0.7194 |
0.9341 | 77.56 | 15900 | 0.2885 | 0.7175 |
0.87 | 77.71 | 15930 | 0.2898 | 0.7161 |
0.9022 | 77.85 | 15960 | 0.2843 | 0.7198 |
0.9914 | 78.0 | 15990 | 0.2853 | 0.7197 |
0.9486 | 78.15 | 16020 | 0.2858 | 0.7185 |
0.9524 | 78.29 | 16050 | 0.2912 | 0.7158 |
0.9248 | 78.44 | 16080 | 0.2873 | 0.7183 |
0.9667 | 78.59 | 16110 | 0.2861 | 0.7193 |
0.9646 | 78.73 | 16140 | 0.2884 | 0.7176 |
0.9311 | 78.88 | 16170 | 0.2893 | 0.7171 |
0.9647 | 79.02 | 16200 | 0.2826 | 0.7207 |
1.0 | 79.17 | 16230 | 0.2860 | 0.7189 |
1.0 | 79.32 | 16260 | 0.2878 | 0.7186 |
0.9798 | 79.46 | 16290 | 0.2874 | 0.7180 |
0.9361 | 79.61 | 16320 | 0.2874 | 0.7184 |
0.8783 | 79.76 | 16350 | 0.2906 | 0.7160 |
0.9166 | 79.9 | 16380 | 0.2882 | 0.7179 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.