sciqqa_noaugs_llama_lora

This model is a fine-tuned version of Daewon0808/prm800k_llama_fulltune on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1472
  • Prm accuracy: 0.9127
  • Prm precision: 0.9364
  • Prm recall: 0.9626
  • Prm specificty: 0.6316
  • Prm npv: 0.75
  • Prm f1: 0.9493
  • Prm f1 neg: 0.6857
  • Prm f1 auc: 0.7971
  • Prm f1 auc (fixed): 0.9653

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: 2
  • eval_batch_size: 4
  • seed: 908932403
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • total_eval_batch_size: 32
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Prm accuracy Prm precision Prm recall Prm specificty Prm npv Prm f1 Prm f1 neg Prm f1 auc Prm f1 auc (fixed)
No log 0 0 0.3535 0.8333 0.8772 0.9346 0.2632 0.4167 0.9050 0.3226 0.5989 0.8195
0.3328 0.0038 5 0.3544 0.8333 0.8772 0.9346 0.2632 0.4167 0.9050 0.3226 0.5989 0.8202
0.3139 0.0076 10 0.3526 0.8413 0.8783 0.9439 0.2632 0.4545 0.9099 0.3333 0.6035 0.8160
0.375 0.0113 15 0.3438 0.8413 0.8718 0.9533 0.2105 0.4444 0.9107 0.2857 0.5819 0.8224
0.2172 0.0151 20 0.3504 0.8492 0.8667 0.9720 0.1579 0.5 0.9163 0.24 0.5649 0.8325
0.2049 0.0189 25 0.3833 0.8492 0.8548 0.9907 0.0526 0.5 0.9177 0.0952 0.5216 0.8478
0.3257 0.0227 30 0.3566 0.8413 0.8595 0.9720 0.1053 0.4 0.9123 0.1667 0.5386 0.8377
0.2205 0.0264 35 0.3307 0.8492 0.8667 0.9720 0.1579 0.5 0.9163 0.24 0.5649 0.8308
0.2519 0.0302 40 0.3368 0.8492 0.8607 0.9813 0.1053 0.5 0.9170 0.1739 0.5433 0.8355
0.2338 0.0340 45 0.3614 0.8571 0.8618 0.9907 0.1053 0.6667 0.9217 0.1818 0.5480 0.8362
0.2385 0.0378 50 0.3127 0.8571 0.8618 0.9907 0.1053 0.6667 0.9217 0.1818 0.5480 0.8460
0.2242 0.0415 55 0.2820 0.8492 0.8729 0.9626 0.2105 0.5 0.9156 0.2963 0.5866 0.8623
0.2156 0.0453 60 0.3156 0.8571 0.8618 0.9907 0.1053 0.6667 0.9217 0.1818 0.5480 0.8829
0.2999 0.0491 65 0.3628 0.8651 0.8629 1.0 0.1053 1.0 0.9264 0.1905 0.5526 0.8901
0.2272 0.0529 70 0.2806 0.8571 0.8678 0.9813 0.1579 0.6 0.9211 0.25 0.5696 0.8785
0.2181 0.0566 75 0.2671 0.8492 0.8729 0.9626 0.2105 0.5 0.9156 0.2963 0.5866 0.8910
0.1718 0.0604 80 0.2746 0.8492 0.8729 0.9626 0.2105 0.5 0.9156 0.2963 0.5866 0.8987
0.166 0.0642 85 0.2832 0.8571 0.8739 0.9720 0.2105 0.5714 0.9204 0.3077 0.5912 0.8851
0.2396 0.0680 90 0.2847 0.8730 0.8824 0.9813 0.2632 0.7143 0.9292 0.3846 0.6222 0.8760
0.159 0.0717 95 0.2758 0.8810 0.8898 0.9813 0.3158 0.75 0.9333 0.4444 0.6485 0.8918
0.218 0.0755 100 0.3285 0.8730 0.8760 0.9907 0.2105 0.8 0.9298 0.3333 0.6006 0.8997
0.1849 0.0793 105 0.2451 0.8889 0.9043 0.9720 0.4211 0.7273 0.9369 0.5333 0.6965 0.9196
0.218 0.0831 110 0.2453 0.8810 0.9182 0.9439 0.5263 0.625 0.9309 0.5714 0.7351 0.9142
0.1904 0.0868 115 0.2721 0.8651 0.875 0.9813 0.2105 0.6667 0.9251 0.32 0.5959 0.9097
0.1325 0.0906 120 0.2901 0.8730 0.8760 0.9907 0.2105 0.8 0.9298 0.3333 0.6006 0.8938
0.1312 0.0944 125 0.2664 0.8810 0.8966 0.9720 0.3684 0.7 0.9327 0.4828 0.6702 0.8977
0.2058 0.0982 130 0.2557 0.8730 0.8957 0.9626 0.3684 0.6364 0.9279 0.4667 0.6655 0.9120
0.094 0.1019 135 0.3045 0.8651 0.8814 0.9720 0.2632 0.625 0.9244 0.3704 0.6176 0.9139
0.0851 0.1057 140 0.2504 0.8810 0.8966 0.9720 0.3684 0.7 0.9327 0.4828 0.6702 0.9154
0.269 0.1095 145 0.2434 0.8651 0.8947 0.9533 0.3684 0.5833 0.9231 0.4516 0.6608 0.9156
0.1326 0.1133 150 0.2458 0.8571 0.8870 0.9533 0.3158 0.5455 0.9189 0.4 0.6345 0.9164
0.1725 0.1170 155 0.2634 0.8651 0.8689 0.9907 0.1579 0.75 0.9258 0.2609 0.5743 0.9186
0.1548 0.1208 160 0.2368 0.8889 0.9043 0.9720 0.4211 0.7273 0.9369 0.5333 0.6965 0.9196
0.1057 0.1246 165 0.2501 0.9048 0.9204 0.9720 0.5263 0.7692 0.9455 0.625 0.7491 0.9144
0.064 0.1284 170 0.2487 0.8810 0.9182 0.9439 0.5263 0.625 0.9309 0.5714 0.7351 0.9127
0.1817 0.1321 175 0.2658 0.8651 0.9018 0.9439 0.4211 0.5714 0.9224 0.4848 0.6825 0.9112
0.1152 0.1359 180 0.2613 0.8651 0.8947 0.9533 0.3684 0.5833 0.9231 0.4516 0.6608 0.9001
0.0887 0.1397 185 0.2633 0.8571 0.8803 0.9626 0.2632 0.5556 0.9196 0.3571 0.6129 0.9058
0.0815 0.1435 190 0.2483 0.8810 0.9107 0.9533 0.4737 0.6429 0.9315 0.5455 0.7135 0.9166
0.1135 0.1472 195 0.2790 0.8730 0.9027 0.9533 0.4211 0.6154 0.9273 0.5 0.6872 0.9166
0.133 0.1510 200 0.2879 0.8810 0.9107 0.9533 0.4737 0.6429 0.9315 0.5455 0.7135 0.9137
0.2139 0.1548 205 0.2979 0.8571 0.8870 0.9533 0.3158 0.5455 0.9189 0.4 0.6345 0.9144
0.1917 0.1586 210 0.2744 0.8651 0.8814 0.9720 0.2632 0.625 0.9244 0.3704 0.6176 0.9154
0.1653 0.1623 215 0.2709 0.8730 0.9174 0.9346 0.5263 0.5882 0.9259 0.5556 0.7304 0.9156
0.172 0.1661 220 0.2612 0.8810 0.9259 0.9346 0.5789 0.6111 0.9302 0.5946 0.7568 0.9213
0.2033 0.1699 225 0.2521 0.8810 0.9259 0.9346 0.5789 0.6111 0.9302 0.5946 0.7568 0.9218
0.154 0.1737 230 0.2831 0.8889 0.9043 0.9720 0.4211 0.7273 0.9369 0.5333 0.6965 0.9095
0.082 0.1774 235 0.2823 0.8651 0.9018 0.9439 0.4211 0.5714 0.9224 0.4848 0.6825 0.9048
0.2339 0.1812 240 0.2823 0.8571 0.9009 0.9346 0.4211 0.5333 0.9174 0.4706 0.6778 0.9063
0.067 0.1850 245 0.2531 0.8730 0.9252 0.9252 0.5789 0.5789 0.9252 0.5789 0.7521 0.9097
0.1571 0.1888 250 0.2622 0.8810 0.9182 0.9439 0.5263 0.625 0.9309 0.5714 0.7351 0.9127
0.1248 0.1925 255 0.2788 0.8810 0.9035 0.9626 0.4211 0.6667 0.9321 0.5161 0.6918 0.9092
0.1479 0.1963 260 0.2751 0.8413 0.9223 0.8879 0.5789 0.4783 0.9048 0.5238 0.7334 0.8957
0.1505 0.2001 265 0.2907 0.8413 0.9065 0.9065 0.4737 0.4737 0.9065 0.4737 0.6901 0.8849
0.1007 0.2039 270 0.2753 0.8492 0.9 0.9252 0.4211 0.5 0.9124 0.4571 0.6731 0.8977
0.1106 0.2076 275 0.2560 0.8810 0.9340 0.9252 0.6316 0.6 0.9296 0.6154 0.7784 0.9083
0.1668 0.2114 280 0.2426 0.8810 0.9340 0.9252 0.6316 0.6 0.9296 0.6154 0.7784 0.9137
0.1225 0.2152 285 0.2420 0.8810 0.9340 0.9252 0.6316 0.6 0.9296 0.6154 0.7784 0.9061
0.1254 0.2190 290 0.2428 0.8730 0.9174 0.9346 0.5263 0.5882 0.9259 0.5556 0.7304 0.9056
0.1312 0.2227 295 0.2397 0.8968 0.9352 0.9439 0.6316 0.6667 0.9395 0.6486 0.7878 0.9139
0.1072 0.2265 300 0.2506 0.8810 0.9107 0.9533 0.4737 0.6429 0.9315 0.5455 0.7135 0.9092
0.0867 0.2303 305 0.2505 0.8889 0.9189 0.9533 0.5263 0.6667 0.9358 0.5882 0.7398 0.9088
0.0724 0.2341 310 0.2786 0.8810 0.9107 0.9533 0.4737 0.6429 0.9315 0.5455 0.7135 0.9073
0.0652 0.2378 315 0.2687 0.8810 0.9182 0.9439 0.5263 0.625 0.9309 0.5714 0.7351 0.9137
0.1312 0.2416 320 0.2643 0.8810 0.9340 0.9252 0.6316 0.6 0.9296 0.6154 0.7784 0.9124
0.1099 0.2454 325 0.2628 0.8651 0.8947 0.9533 0.3684 0.5833 0.9231 0.4516 0.6608 0.9183
0.1619 0.2492 330 0.2544 0.8571 0.8870 0.9533 0.3158 0.5455 0.9189 0.4 0.6345 0.9274
0.102 0.2529 335 0.2188 0.8889 0.9515 0.9159 0.7368 0.6087 0.9333 0.6667 0.8264 0.9306
0.1485 0.2567 340 0.2155 0.8968 0.9519 0.9252 0.7368 0.6364 0.9384 0.6829 0.8310 0.9397
0.1597 0.2605 345 0.2593 0.8651 0.875 0.9813 0.2105 0.6667 0.9251 0.32 0.5959 0.9469
0.1184 0.2643 350 0.2033 0.8968 0.9273 0.9533 0.5789 0.6875 0.9401 0.6286 0.7661 0.9511
0.1541 0.2680 355 0.2162 0.8571 0.8938 0.9439 0.3684 0.5385 0.9182 0.4375 0.6562 0.9429
0.1596 0.2718 360 0.2390 0.8730 0.8889 0.9720 0.3158 0.6667 0.9286 0.4286 0.6439 0.9375
0.0735 0.2756 365 0.1968 0.8730 0.9174 0.9346 0.5263 0.5882 0.9259 0.5556 0.7304 0.9417
0.1558 0.2794 370 0.2021 0.8889 0.9429 0.9252 0.6842 0.6190 0.9340 0.65 0.8047 0.9405
0.126 0.2831 375 0.2101 0.9127 0.9528 0.9439 0.7368 0.7 0.9484 0.7179 0.8404 0.9375
0.107 0.2869 380 0.2047 0.8968 0.9434 0.9346 0.6842 0.65 0.9390 0.6667 0.8094 0.9412
0.141 0.2907 385 0.1959 0.8889 0.9266 0.9439 0.5789 0.6471 0.9352 0.6111 0.7614 0.9429
0.0626 0.2945 390 0.1993 0.8651 0.8947 0.9533 0.3684 0.5833 0.9231 0.4516 0.6608 0.9405
0.102 0.2982 395 0.1938 0.8889 0.9266 0.9439 0.5789 0.6471 0.9352 0.6111 0.7614 0.9484
0.0902 0.3020 400 0.2072 0.8889 0.9266 0.9439 0.5789 0.6471 0.9352 0.6111 0.7614 0.9496
0.1481 0.3058 405 0.1849 0.8968 0.9434 0.9346 0.6842 0.65 0.9390 0.6667 0.8094 0.9535
0.0708 0.3096 410 0.1873 0.9286 0.99 0.9252 0.9474 0.6923 0.9565 0.8 0.9363 0.9547
0.0674 0.3133 415 0.1972 0.8889 0.9266 0.9439 0.5789 0.6471 0.9352 0.6111 0.7614 0.9442
0.127 0.3171 420 0.1969 0.8810 0.9182 0.9439 0.5263 0.625 0.9309 0.5714 0.7351 0.9456
0.0974 0.3209 425 0.1775 0.9127 0.9706 0.9252 0.8421 0.6667 0.9474 0.7442 0.8837 0.9520
0.0755 0.3247 430 0.1804 0.8810 0.9182 0.9439 0.5263 0.625 0.9309 0.5714 0.7351 0.9525
0.0827 0.3284 435 0.1958 0.8730 0.9027 0.9533 0.4211 0.6154 0.9273 0.5 0.6872 0.9513
0.1017 0.3322 440 0.1831 0.8730 0.9174 0.9346 0.5263 0.5882 0.9259 0.5556 0.7304 0.9498
0.1285 0.3360 445 0.1775 0.8889 0.9429 0.9252 0.6842 0.6190 0.9340 0.65 0.8047 0.9508
0.1479 0.3398 450 0.1726 0.8810 0.9259 0.9346 0.5789 0.6111 0.9302 0.5946 0.7568 0.9538
0.1136 0.3435 455 0.1952 0.8968 0.9123 0.9720 0.4737 0.75 0.9412 0.5806 0.7228 0.9533
0.1274 0.3473 460 0.1664 0.8968 0.9352 0.9439 0.6316 0.6667 0.9395 0.6486 0.7878 0.9602
0.1065 0.3511 465 0.1619 0.9127 0.9615 0.9346 0.7895 0.6818 0.9479 0.7317 0.8620 0.9658
0.0507 0.3549 470 0.1597 0.8968 0.9352 0.9439 0.6316 0.6667 0.9395 0.6486 0.7878 0.9670
0.1417 0.3586 475 0.1675 0.8889 0.9189 0.9533 0.5263 0.6667 0.9358 0.5882 0.7398 0.9643
0.0947 0.3624 480 0.1604 0.8968 0.9352 0.9439 0.6316 0.6667 0.9395 0.6486 0.7878 0.9651
0.1216 0.3662 485 0.1596 0.9127 0.9615 0.9346 0.7895 0.6818 0.9479 0.7317 0.8620 0.9651
0.0979 0.3700 490 0.1581 0.9127 0.9615 0.9346 0.7895 0.6818 0.9479 0.7317 0.8620 0.9668
0.0764 0.3737 495 0.1578 0.9127 0.9528 0.9439 0.7368 0.7 0.9484 0.7179 0.8404 0.9673
0.1232 0.3775 500 0.1794 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9643
0.1159 0.3813 505 0.1724 0.9127 0.9528 0.9439 0.7368 0.7 0.9484 0.7179 0.8404 0.9570
0.1331 0.3851 510 0.1781 0.9127 0.9615 0.9346 0.7895 0.6818 0.9479 0.7317 0.8620 0.9523
0.1576 0.3888 515 0.1919 0.9048 0.9358 0.9533 0.6316 0.7059 0.9444 0.6667 0.7924 0.9511
0.1924 0.3926 520 0.1898 0.9048 0.9439 0.9439 0.6842 0.6842 0.9439 0.6842 0.8141 0.9498
0.0823 0.3964 525 0.1968 0.9048 0.9612 0.9252 0.7895 0.6522 0.9429 0.7143 0.8574 0.9484
0.0995 0.4002 530 0.2065 0.8968 0.9352 0.9439 0.6316 0.6667 0.9395 0.6486 0.7878 0.9469
0.0421 0.4039 535 0.2086 0.8968 0.9352 0.9439 0.6316 0.6667 0.9395 0.6486 0.7878 0.9491
0.0818 0.4077 540 0.2006 0.8968 0.9434 0.9346 0.6842 0.65 0.9390 0.6667 0.8094 0.9511
0.1179 0.4115 545 0.1960 0.8968 0.9434 0.9346 0.6842 0.65 0.9390 0.6667 0.8094 0.9491
0.1114 0.4153 550 0.2115 0.8968 0.9273 0.9533 0.5789 0.6875 0.9401 0.6286 0.7661 0.9464
0.1148 0.4190 555 0.2243 0.8968 0.9123 0.9720 0.4737 0.75 0.9412 0.5806 0.7228 0.9437
0.0433 0.4228 560 0.2189 0.9048 0.9358 0.9533 0.6316 0.7059 0.9444 0.6667 0.7924 0.9422
0.125 0.4266 565 0.2168 0.8810 0.9340 0.9252 0.6316 0.6 0.9296 0.6154 0.7784 0.9405
0.0984 0.4304 570 0.2065 0.8730 0.9333 0.9159 0.6316 0.5714 0.9245 0.6 0.7737 0.9380
0.158 0.4341 575 0.2048 0.8810 0.9423 0.9159 0.6842 0.5909 0.9289 0.6341 0.8000 0.9356
0.1386 0.4379 580 0.2135 0.8810 0.9340 0.9252 0.6316 0.6 0.9296 0.6154 0.7784 0.9306
0.0898 0.4417 585 0.2219 0.8810 0.9259 0.9346 0.5789 0.6111 0.9302 0.5946 0.7568 0.9331
0.1216 0.4455 590 0.2122 0.8968 0.9519 0.9252 0.7368 0.6364 0.9384 0.6829 0.8310 0.9356
0.0644 0.4492 595 0.2139 0.8889 0.9346 0.9346 0.6316 0.6316 0.9346 0.6316 0.7831 0.9400
0.097 0.4530 600 0.2089 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9484
0.1183 0.4568 605 0.1958 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9528
0.0851 0.4606 610 0.1928 0.9127 0.9444 0.9533 0.6842 0.7222 0.9488 0.7027 0.8187 0.9528
0.1627 0.4643 615 0.2013 0.9048 0.9358 0.9533 0.6316 0.7059 0.9444 0.6667 0.7924 0.9508
0.0585 0.4681 620 0.2076 0.9048 0.9358 0.9533 0.6316 0.7059 0.9444 0.6667 0.7924 0.9486
0.1332 0.4719 625 0.2182 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9515
0.1214 0.4757 630 0.2251 0.8889 0.9043 0.9720 0.4211 0.7273 0.9369 0.5333 0.6965 0.9511
0.1882 0.4794 635 0.2115 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9481
0.0529 0.4832 640 0.1852 0.9127 0.9615 0.9346 0.7895 0.6818 0.9479 0.7317 0.8620 0.9481
0.1455 0.4870 645 0.1816 0.8889 0.9115 0.9626 0.4737 0.6923 0.9364 0.5625 0.7182 0.9506
0.0429 0.4908 650 0.1788 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9543
0.0726 0.4945 655 0.1764 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9584
0.1361 0.4983 660 0.1776 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9636
0.1765 0.5021 665 0.1727 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9666
0.1026 0.5059 670 0.1571 0.9127 0.9444 0.9533 0.6842 0.7222 0.9488 0.7027 0.8187 0.9668
0.115 0.5096 675 0.1594 0.8968 0.9434 0.9346 0.6842 0.65 0.9390 0.6667 0.8094 0.9666
0.0842 0.5134 680 0.1778 0.8889 0.9115 0.9626 0.4737 0.6923 0.9364 0.5625 0.7182 0.9636
0.087 0.5172 685 0.1745 0.8810 0.9035 0.9626 0.4211 0.6667 0.9321 0.5161 0.6918 0.9626
0.0934 0.5210 690 0.1644 0.8968 0.9352 0.9439 0.6316 0.6667 0.9395 0.6486 0.7878 0.9611
0.0995 0.5247 695 0.1624 0.9206 0.9619 0.9439 0.7895 0.7143 0.9528 0.75 0.8667 0.9626
0.1695 0.5285 700 0.1615 0.9127 0.9528 0.9439 0.7368 0.7 0.9484 0.7179 0.8404 0.9614
0.0854 0.5323 705 0.1576 0.8968 0.9352 0.9439 0.6316 0.6667 0.9395 0.6486 0.7878 0.9616
0.1292 0.5361 710 0.1582 0.8889 0.9266 0.9439 0.5789 0.6471 0.9352 0.6111 0.7614 0.9611
0.08 0.5398 715 0.1609 0.9048 0.9439 0.9439 0.6842 0.6842 0.9439 0.6842 0.8141 0.9599
0.095 0.5436 720 0.1642 0.9206 0.9619 0.9439 0.7895 0.7143 0.9528 0.75 0.8667 0.9584
0.0972 0.5474 725 0.1703 0.9206 0.9709 0.9346 0.8421 0.6957 0.9524 0.7619 0.8883 0.9567
0.0595 0.5512 730 0.1770 0.9048 0.9439 0.9439 0.6842 0.6842 0.9439 0.6842 0.8141 0.9597
0.079 0.5549 735 0.1840 0.8810 0.9182 0.9439 0.5263 0.625 0.9309 0.5714 0.7351 0.9582
0.082 0.5587 740 0.1893 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9584
0.1311 0.5625 745 0.1913 0.8889 0.9115 0.9626 0.4737 0.6923 0.9364 0.5625 0.7182 0.9606
0.0682 0.5663 750 0.1636 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9666
0.1597 0.5700 755 0.1570 0.9286 0.9712 0.9439 0.8421 0.7273 0.9573 0.7805 0.8930 0.9673
0.0498 0.5738 760 0.1601 0.9286 0.9712 0.9439 0.8421 0.7273 0.9573 0.7805 0.8930 0.9641
0.075 0.5776 765 0.1764 0.9048 0.9204 0.9720 0.5263 0.7692 0.9455 0.625 0.7491 0.9638
0.1459 0.5814 770 0.1904 0.8968 0.9123 0.9720 0.4737 0.75 0.9412 0.5806 0.7228 0.9616
0.1514 0.5851 775 0.1837 0.8968 0.9123 0.9720 0.4737 0.75 0.9412 0.5806 0.7228 0.9606
0.1923 0.5889 780 0.1733 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9592
0.0993 0.5927 785 0.1634 0.9048 0.9439 0.9439 0.6842 0.6842 0.9439 0.6842 0.8141 0.9587
0.1239 0.5965 790 0.1659 0.9048 0.9439 0.9439 0.6842 0.6842 0.9439 0.6842 0.8141 0.9582
0.0799 0.6002 795 0.1700 0.8889 0.9189 0.9533 0.5263 0.6667 0.9358 0.5882 0.7398 0.9592
0.0693 0.6040 800 0.1810 0.8968 0.9123 0.9720 0.4737 0.75 0.9412 0.5806 0.7228 0.9592
0.1315 0.6078 805 0.1771 0.8968 0.9123 0.9720 0.4737 0.75 0.9412 0.5806 0.7228 0.9575
0.0627 0.6116 810 0.1738 0.8889 0.9115 0.9626 0.4737 0.6923 0.9364 0.5625 0.7182 0.9582
0.1457 0.6153 815 0.1703 0.8889 0.9189 0.9533 0.5263 0.6667 0.9358 0.5882 0.7398 0.9584
0.1184 0.6191 820 0.1644 0.9048 0.9439 0.9439 0.6842 0.6842 0.9439 0.6842 0.8141 0.9597
0.1293 0.6229 825 0.1602 0.9127 0.9528 0.9439 0.7368 0.7 0.9484 0.7179 0.8404 0.9606
0.0869 0.6267 830 0.1647 0.9127 0.9444 0.9533 0.6842 0.7222 0.9488 0.7027 0.8187 0.9604
0.0974 0.6304 835 0.1736 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9597
0.1035 0.6342 840 0.1775 0.9048 0.9439 0.9439 0.6842 0.6842 0.9439 0.6842 0.8141 0.9567
0.1022 0.6380 845 0.1833 0.9127 0.9615 0.9346 0.7895 0.6818 0.9479 0.7317 0.8620 0.9570
0.0759 0.6418 850 0.1859 0.9127 0.9615 0.9346 0.7895 0.6818 0.9479 0.7317 0.8620 0.9545
0.0555 0.6455 855 0.1818 0.9206 0.9533 0.9533 0.7368 0.7368 0.9533 0.7368 0.8451 0.9555
0.1063 0.6493 860 0.1793 0.9048 0.9358 0.9533 0.6316 0.7059 0.9444 0.6667 0.7924 0.9575
0.1168 0.6531 865 0.1761 0.8968 0.9273 0.9533 0.5789 0.6875 0.9401 0.6286 0.7661 0.9592
0.0726 0.6569 870 0.1706 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9606
0.1218 0.6606 875 0.1643 0.9206 0.9533 0.9533 0.7368 0.7368 0.9533 0.7368 0.8451 0.9636
0.1684 0.6644 880 0.1619 0.9286 0.9712 0.9439 0.8421 0.7273 0.9573 0.7805 0.8930 0.9626
0.1613 0.6682 885 0.1564 0.9286 0.9712 0.9439 0.8421 0.7273 0.9573 0.7805 0.8930 0.9653
0.1801 0.6720 890 0.1575 0.9127 0.9528 0.9439 0.7368 0.7 0.9484 0.7179 0.8404 0.9643
0.0906 0.6757 895 0.1551 0.9127 0.9528 0.9439 0.7368 0.7 0.9484 0.7179 0.8404 0.9646
0.1181 0.6795 900 0.1553 0.8889 0.9266 0.9439 0.5789 0.6471 0.9352 0.6111 0.7614 0.9656
0.1126 0.6833 905 0.1560 0.8968 0.9273 0.9533 0.5789 0.6875 0.9401 0.6286 0.7661 0.9658
0.1097 0.6871 910 0.1575 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9648
0.088 0.6908 915 0.1570 0.8968 0.9273 0.9533 0.5789 0.6875 0.9401 0.6286 0.7661 0.9648
0.0694 0.6946 920 0.1638 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9653
0.1506 0.6984 925 0.1628 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9643
0.2068 0.7022 930 0.1644 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9634
0.0779 0.7059 935 0.1682 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9624
0.0573 0.7097 940 0.1702 0.8968 0.9196 0.9626 0.5263 0.7143 0.9406 0.6061 0.7445 0.9606
0.0821 0.7135 945 0.1750 0.8968 0.9123 0.9720 0.4737 0.75 0.9412 0.5806 0.7228 0.9616
0.087 0.7173 950 0.1783 0.8968 0.9123 0.9720 0.4737 0.75 0.9412 0.5806 0.7228 0.9611
0.0905 0.7210 955 0.1774 0.8968 0.9123 0.9720 0.4737 0.75 0.9412 0.5806 0.7228 0.9616
0.0823 0.7248 960 0.1666 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9611
0.0569 0.7286 965 0.1585 0.9206 0.9533 0.9533 0.7368 0.7368 0.9533 0.7368 0.8451 0.9638
0.0598 0.7324 970 0.1576 0.9127 0.9615 0.9346 0.7895 0.6818 0.9479 0.7317 0.8620 0.9641
0.0971 0.7361 975 0.1578 0.9127 0.9528 0.9439 0.7368 0.7 0.9484 0.7179 0.8404 0.9648
0.066 0.7399 980 0.1563 0.9206 0.9533 0.9533 0.7368 0.7368 0.9533 0.7368 0.8451 0.9648
0.0816 0.7437 985 0.1555 0.9206 0.9533 0.9533 0.7368 0.7368 0.9533 0.7368 0.8451 0.9648
0.0998 0.7475 990 0.1570 0.9286 0.9537 0.9626 0.7368 0.7778 0.9581 0.7568 0.8497 0.9641
0.076 0.7512 995 0.1587 0.9206 0.9450 0.9626 0.6842 0.7647 0.9537 0.7222 0.8234 0.9638
0.0439 0.7550 1000 0.1594 0.9206 0.9450 0.9626 0.6842 0.7647 0.9537 0.7222 0.8234 0.9643
0.0497 0.7588 1005 0.1571 0.9286 0.9537 0.9626 0.7368 0.7778 0.9581 0.7568 0.8497 0.9643
0.0671 0.7626 1010 0.1569 0.9286 0.9537 0.9626 0.7368 0.7778 0.9581 0.7568 0.8497 0.9641
0.1369 0.7663 1015 0.1604 0.9206 0.9450 0.9626 0.6842 0.7647 0.9537 0.7222 0.8234 0.9636
0.1011 0.7701 1020 0.1599 0.9206 0.9450 0.9626 0.6842 0.7647 0.9537 0.7222 0.8234 0.9631
0.0758 0.7739 1025 0.1546 0.9206 0.9450 0.9626 0.6842 0.7647 0.9537 0.7222 0.8234 0.9641
0.1426 0.7777 1030 0.1514 0.9286 0.9537 0.9626 0.7368 0.7778 0.9581 0.7568 0.8497 0.9648
0.0784 0.7814 1035 0.1505 0.9286 0.9537 0.9626 0.7368 0.7778 0.9581 0.7568 0.8497 0.9656
0.0685 0.7852 1040 0.1505 0.9365 0.9626 0.9626 0.7895 0.7895 0.9626 0.7895 0.8760 0.9646
0.0983 0.7890 1045 0.1489 0.9365 0.9626 0.9626 0.7895 0.7895 0.9626 0.7895 0.8760 0.9661
0.1238 0.7928 1050 0.1488 0.9444 0.9717 0.9626 0.8421 0.8 0.9671 0.8205 0.9024 0.9656
0.1614 0.7965 1055 0.1502 0.9444 0.9717 0.9626 0.8421 0.8 0.9671 0.8205 0.9024 0.9658
0.1288 0.8003 1060 0.1482 0.9444 0.9717 0.9626 0.8421 0.8 0.9671 0.8205 0.9024 0.9666
0.0675 0.8041 1065 0.1484 0.9365 0.9714 0.9533 0.8421 0.7619 0.9623 0.8 0.8977 0.9661
0.1533 0.8079 1070 0.1480 0.9365 0.9714 0.9533 0.8421 0.7619 0.9623 0.8 0.8977 0.9663
0.0876 0.8116 1075 0.1477 0.9365 0.9626 0.9626 0.7895 0.7895 0.9626 0.7895 0.8760 0.9670
0.0713 0.8154 1080 0.1502 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9670
0.0925 0.8192 1085 0.1509 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9670
0.0835 0.8230 1090 0.1506 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9653
0.0653 0.8267 1095 0.1522 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9663
0.0807 0.8305 1100 0.1551 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9646
0.1001 0.8343 1105 0.1581 0.9127 0.9211 0.9813 0.5263 0.8333 0.9502 0.6452 0.7538 0.9641
0.1085 0.8381 1110 0.1568 0.9127 0.9211 0.9813 0.5263 0.8333 0.9502 0.6452 0.7538 0.9636
0.0751 0.8418 1115 0.1570 0.9127 0.9211 0.9813 0.5263 0.8333 0.9502 0.6452 0.7538 0.9636
0.0711 0.8456 1120 0.1546 0.9048 0.9204 0.9720 0.5263 0.7692 0.9455 0.625 0.7491 0.9641
0.148 0.8494 1125 0.1505 0.9048 0.9358 0.9533 0.6316 0.7059 0.9444 0.6667 0.7924 0.9651
0.0592 0.8532 1130 0.1484 0.9127 0.9444 0.9533 0.6842 0.7222 0.9488 0.7027 0.8187 0.9653
0.1196 0.8569 1135 0.1476 0.9206 0.9533 0.9533 0.7368 0.7368 0.9533 0.7368 0.8451 0.9668
0.0801 0.8607 1140 0.1471 0.9127 0.9444 0.9533 0.6842 0.7222 0.9488 0.7027 0.8187 0.9658
0.1064 0.8645 1145 0.1471 0.9206 0.9533 0.9533 0.7368 0.7368 0.9533 0.7368 0.8451 0.9673
0.1343 0.8683 1150 0.1473 0.9206 0.9533 0.9533 0.7368 0.7368 0.9533 0.7368 0.8451 0.9663
0.0945 0.8720 1155 0.1476 0.9206 0.9533 0.9533 0.7368 0.7368 0.9533 0.7368 0.8451 0.9661
0.1215 0.8758 1160 0.1477 0.9206 0.9533 0.9533 0.7368 0.7368 0.9533 0.7368 0.8451 0.9666
0.1187 0.8796 1165 0.1473 0.9048 0.9358 0.9533 0.6316 0.7059 0.9444 0.6667 0.7924 0.9670
0.083 0.8834 1170 0.1485 0.9048 0.9358 0.9533 0.6316 0.7059 0.9444 0.6667 0.7924 0.9651
0.0841 0.8871 1175 0.1507 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9666
0.104 0.8909 1180 0.1500 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9668
0.0895 0.8947 1185 0.1497 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9666
0.1156 0.8985 1190 0.1486 0.9127 0.9286 0.9720 0.5789 0.7857 0.9498 0.6667 0.7755 0.9673
0.1089 0.9022 1195 0.1497 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9668
0.0877 0.9060 1200 0.1493 0.9048 0.9279 0.9626 0.5789 0.7333 0.9450 0.6471 0.7708 0.9673
0.1283 0.9098 1205 0.1498 0.9127 0.9286 0.9720 0.5789 0.7857 0.9498 0.6667 0.7755 0.9663
0.1218 0.9136 1210 0.1480 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9673
0.077 0.9173 1215 0.1467 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9688
0.1762 0.9211 1220 0.1480 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9675
0.061 0.9249 1225 0.1479 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9663
0.0721 0.9287 1230 0.1469 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9661
0.0713 0.9324 1235 0.1467 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9668
0.0472 0.9362 1240 0.1468 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9673
0.0743 0.9400 1245 0.1475 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9675
0.068 0.9438 1250 0.1474 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9666
0.0789 0.9475 1255 0.1478 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9663
0.0882 0.9513 1260 0.1465 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9673
0.0997 0.9551 1265 0.1471 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9670
0.0615 0.9589 1270 0.1466 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9661
0.0874 0.9626 1275 0.1470 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9675
0.0864 0.9664 1280 0.1460 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9675
0.066 0.9702 1285 0.1459 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9668
0.0599 0.9740 1290 0.1458 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9673
0.0672 0.9777 1295 0.1466 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9668
0.1481 0.9815 1300 0.1472 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9661
0.0763 0.9853 1305 0.1468 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9666
0.109 0.9891 1310 0.1465 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9668
0.0481 0.9928 1315 0.1460 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9670
0.0744 0.9966 1320 0.1472 0.9127 0.9364 0.9626 0.6316 0.75 0.9493 0.6857 0.7971 0.9653

Framework versions

  • PEFT 0.12.0
  • Transformers 4.46.0
  • Pytorch 2.4.0+cu118
  • Datasets 3.0.0
  • Tokenizers 0.20.1
Downloads last month
9
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for Daewon0808/sciqqa_noaugs_llama_lora