genSoftQwen2.5MathRM72Bth0.5pair4NoGT_1.5B_dpo_ebs32_lr5e-07_beta1.5_epoch8.0_42

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the YuchenLi01/MATH_Qwen2.5-1.5BInstruct_Soft_DPO_Qwen2.5MathRM72B_th0.5_pair4NoGT dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1130
  • Rewards/chosen: -0.4448
  • Rewards/rejected: -5.8140
  • Rewards/accuracies: 0.7622
  • Rewards/margins: 5.3692
  • Logps/rejected: -51.3617
  • Logps/chosen: -37.6017
  • Logits/rejected: -2.4410
  • Logits/chosen: -2.6351

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: 5e-07
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 32
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 8.0

Training results

Training Loss Epoch Step Validation Loss Rewards/chosen Rewards/rejected Rewards/accuracies Rewards/margins Logps/rejected Logps/chosen Logits/rejected Logits/chosen
0.7928 0.0287 20 0.7514 -0.0078 -0.0175 0.4878 0.0097 -47.4973 -37.3104 -2.1647 -2.3055
0.731 0.0573 40 0.7643 -0.0306 0.0115 0.4756 -0.0421 -47.4780 -37.3256 -2.1637 -2.3045
0.7496 0.0860 60 0.7537 -0.0234 -0.0266 0.4939 0.0031 -47.5034 -37.3208 -2.1630 -2.3030
0.7762 0.1146 80 0.7601 0.0130 -0.0070 0.5366 0.0200 -47.4903 -37.2965 -2.1612 -2.3012
0.6473 0.1433 100 0.7580 0.0273 -0.0027 0.5366 0.0300 -47.4875 -37.2870 -2.1657 -2.3065
0.7257 0.1719 120 0.7473 -0.0380 0.0161 0.4329 -0.0541 -47.4749 -37.3305 -2.1671 -2.3080
0.8268 0.2006 140 0.7495 -0.0581 -0.0707 0.4939 0.0126 -47.5328 -37.3439 -2.1631 -2.3039
0.7202 0.2292 160 0.7365 -0.0103 -0.1378 0.5549 0.1275 -47.5775 -37.3120 -2.1625 -2.3030
0.6835 0.2579 180 0.7315 -0.0179 -0.1123 0.5793 0.0945 -47.5606 -37.3171 -2.1630 -2.3034
0.7214 0.2865 200 0.7199 0.0580 -0.0883 0.5732 0.1463 -47.5445 -37.2665 -2.1617 -2.3024
0.7425 0.3152 220 0.7150 -0.0271 -0.2070 0.5183 0.1800 -47.6237 -37.3232 -2.1603 -2.3014
0.8579 0.3438 240 0.7096 -0.1333 -0.3021 0.5549 0.1688 -47.6871 -37.3940 -2.1521 -2.2929
0.7338 0.3725 260 0.7003 -0.1719 -0.3421 0.6098 0.1702 -47.7138 -37.4198 -2.1585 -2.3011
0.7376 0.4011 280 0.6751 -0.1860 -0.3819 0.5854 0.1959 -47.7403 -37.4292 -2.1537 -2.2968
0.6339 0.4298 300 0.6785 -0.2004 -0.4422 0.6098 0.2418 -47.7805 -37.4388 -2.1518 -2.2945
0.6225 0.4585 320 0.6674 -0.1704 -0.4729 0.6463 0.3025 -47.8010 -37.4188 -2.1541 -2.2974
0.579 0.4871 340 0.6474 -0.1687 -0.4939 0.6402 0.3251 -47.8149 -37.4177 -2.1566 -2.3012
0.6451 0.5158 360 0.6410 0.0118 -0.3711 0.6220 0.3829 -47.7331 -37.2973 -2.1662 -2.3121
0.6538 0.5444 380 0.6364 -0.0017 -0.4015 0.6220 0.3999 -47.7534 -37.3063 -2.1613 -2.3063
0.8197 0.5731 400 0.6280 0.2083 -0.3317 0.6524 0.5400 -47.7068 -37.1663 -2.1787 -2.3252
0.7057 0.6017 420 0.6240 0.2479 -0.3546 0.6890 0.6025 -47.7221 -37.1399 -2.1832 -2.3308
0.6017 0.6304 440 0.6256 0.2469 -0.3383 0.6951 0.5852 -47.7112 -37.1406 -2.1756 -2.3217
0.5999 0.6590 460 0.6262 0.1867 -0.4060 0.6951 0.5928 -47.7564 -37.1807 -2.1749 -2.3230
0.7107 0.6877 480 0.6079 0.2263 -0.4225 0.6951 0.6488 -47.7673 -37.1543 -2.1770 -2.3259
0.6802 0.7163 500 0.6210 0.0788 -0.5335 0.6829 0.6123 -47.8414 -37.2527 -2.1671 -2.3160
0.5559 0.7450 520 0.5969 0.1966 -0.4291 0.6402 0.6256 -47.7717 -37.1741 -2.1742 -2.3240
0.4405 0.7736 540 0.6161 0.2357 -0.3912 0.6280 0.6270 -47.7465 -37.1480 -2.1724 -2.3215
0.7618 0.8023 560 0.6139 0.0737 -0.6811 0.6646 0.7548 -47.9398 -37.2561 -2.1725 -2.3245
0.6474 0.8309 580 0.6280 -0.1066 -0.9227 0.6585 0.8161 -48.1008 -37.3762 -2.1516 -2.3023
0.5268 0.8596 600 0.6122 0.0132 -0.7545 0.6585 0.7677 -47.9887 -37.2964 -2.1594 -2.3114
0.6057 0.8883 620 0.6149 0.2543 -0.5146 0.6220 0.7689 -47.8287 -37.1356 -2.1755 -2.3278
0.7815 0.9169 640 0.5993 0.5243 -0.3617 0.6951 0.8860 -47.7268 -36.9557 -2.1886 -2.3420
0.6002 0.9456 660 0.6021 0.3025 -0.5777 0.6829 0.8802 -47.8708 -37.1035 -2.1748 -2.3288
0.4714 0.9742 680 0.6061 0.3065 -0.5966 0.6829 0.9031 -47.8834 -37.1009 -2.1779 -2.3328
0.4473 1.0029 700 0.5906 0.1890 -0.7219 0.7012 0.9109 -47.9670 -37.1792 -2.1747 -2.3296
0.6104 1.0315 720 0.5983 0.2820 -0.6438 0.6707 0.9257 -47.9149 -37.1172 -2.1731 -2.3283
0.247 1.0602 740 0.6153 0.2211 -0.7089 0.6768 0.9300 -47.9583 -37.1578 -2.1696 -2.3247
0.2829 1.0888 760 0.5967 0.5021 -0.5021 0.7073 1.0042 -47.8204 -36.9704 -2.1858 -2.3419
0.7007 1.1175 780 0.5845 0.4472 -0.6834 0.7012 1.1306 -47.9413 -37.0070 -2.1841 -2.3406
0.4195 1.1461 800 0.5889 0.3344 -0.7400 0.6646 1.0743 -47.9790 -37.0823 -2.1829 -2.3402
0.5674 1.1748 820 0.6098 0.1958 -0.8943 0.6890 1.0901 -48.0819 -37.1747 -2.1825 -2.3397
0.3761 1.2034 840 0.5986 0.0432 -0.9917 0.6585 1.0348 -48.1468 -37.2764 -2.1704 -2.3282
0.3679 1.2321 860 0.6030 0.0566 -1.0274 0.6585 1.0841 -48.1706 -37.2674 -2.1725 -2.3296
0.5377 1.2607 880 0.6021 0.1168 -0.9839 0.6768 1.1007 -48.1416 -37.2273 -2.1751 -2.3331
0.3405 1.2894 900 0.6064 0.2970 -0.8893 0.7256 1.1864 -48.0786 -37.1072 -2.1883 -2.3479
0.1659 1.3181 920 0.6314 0.1824 -0.8912 0.6524 1.0736 -48.0798 -37.1836 -2.1828 -2.3415
0.4237 1.3467 940 0.6102 0.2663 -0.9341 0.7134 1.2004 -48.1084 -37.1276 -2.1804 -2.3382
0.3987 1.3754 960 0.6131 0.4488 -0.8216 0.6768 1.2705 -48.0334 -37.0060 -2.1947 -2.3527
0.2087 1.4040 980 0.5906 0.4733 -0.9328 0.7256 1.4061 -48.1076 -36.9896 -2.2024 -2.3630
0.3061 1.4327 1000 0.6170 0.1882 -1.0420 0.7012 1.2302 -48.1803 -37.1797 -2.1883 -2.3474
0.2672 1.4613 1020 0.6116 0.1180 -1.1792 0.7012 1.2972 -48.2719 -37.2265 -2.1890 -2.3493
0.3562 1.4900 1040 0.6018 0.2854 -1.0265 0.6951 1.3119 -48.1700 -37.1149 -2.2012 -2.3613
0.3363 1.5186 1060 0.6195 0.3778 -0.8765 0.6768 1.2543 -48.0700 -37.0533 -2.2075 -2.3676
0.3844 1.5473 1080 0.6089 0.1947 -1.1531 0.7195 1.3478 -48.2544 -37.1754 -2.1980 -2.3588
0.4012 1.5759 1100 0.5956 0.1228 -1.1446 0.6951 1.2675 -48.2488 -37.2233 -2.1951 -2.3560
0.327 1.6046 1120 0.6081 0.2826 -1.0557 0.6646 1.3384 -48.1895 -37.1168 -2.1960 -2.3551
0.2342 1.6332 1140 0.6209 0.0370 -1.3406 0.7073 1.3776 -48.3794 -37.2805 -2.1911 -2.3520
0.2669 1.6619 1160 0.6203 0.2179 -1.2507 0.7012 1.4686 -48.3195 -37.1599 -2.2000 -2.3610
0.6199 1.6905 1180 0.6189 0.4441 -0.9714 0.7073 1.4155 -48.1333 -37.0091 -2.2058 -2.3658
0.3065 1.7192 1200 0.6199 0.0421 -1.3445 0.7073 1.3866 -48.3820 -37.2771 -2.1932 -2.3535
0.4585 1.7479 1220 0.6250 0.1468 -1.1685 0.7012 1.3153 -48.2647 -37.2073 -2.1939 -2.3526
0.1956 1.7765 1240 0.6335 0.0356 -1.3259 0.6951 1.3614 -48.3696 -37.2815 -2.1912 -2.3505
0.3968 1.8052 1260 0.6243 -0.0324 -1.3457 0.6829 1.3133 -48.3828 -37.3268 -2.1853 -2.3448
0.3171 1.8338 1280 0.6281 0.0291 -1.3772 0.7195 1.4063 -48.4038 -37.2858 -2.1849 -2.3447
0.3697 1.8625 1300 0.6468 -0.4073 -1.8934 0.6951 1.4860 -48.7479 -37.5767 -2.1688 -2.3294
0.6919 1.8911 1320 0.6367 0.0682 -1.3252 0.6890 1.3934 -48.3691 -37.2597 -2.1928 -2.3533
0.1672 1.9198 1340 0.6425 0.0594 -1.2842 0.6585 1.3436 -48.3418 -37.2656 -2.1903 -2.3514
0.6577 1.9484 1360 0.6240 0.0020 -1.4207 0.7195 1.4227 -48.4328 -37.3038 -2.1917 -2.3529
0.5993 1.9771 1380 0.6220 0.1529 -1.2681 0.6951 1.4210 -48.3311 -37.2033 -2.1972 -2.3576
0.0986 2.0057 1400 0.6307 0.2365 -1.1349 0.6585 1.3714 -48.2423 -37.1475 -2.2010 -2.3613
0.0338 2.0344 1420 0.6335 -0.2288 -1.7656 0.6951 1.5367 -48.6627 -37.4577 -2.1787 -2.3406
0.063 2.0630 1440 0.6207 -0.2477 -1.8723 0.7195 1.6246 -48.7339 -37.4703 -2.1821 -2.3447
0.0372 2.0917 1460 0.6302 0.3317 -1.3680 0.7012 1.6997 -48.3977 -37.0840 -2.2163 -2.3790
0.0561 2.1203 1480 0.6379 0.0407 -1.7830 0.7622 1.8238 -48.6744 -37.2780 -2.1988 -2.3621
0.0777 2.1490 1500 0.6513 0.1493 -1.7175 0.75 1.8668 -48.6307 -37.2057 -2.2097 -2.3739
0.0742 2.1777 1520 0.6372 0.3690 -1.5756 0.7134 1.9446 -48.5361 -37.0592 -2.2211 -2.3851
0.1014 2.2063 1540 0.6605 -0.0006 -1.8407 0.7012 1.8401 -48.7128 -37.3056 -2.2063 -2.3723
0.0559 2.2350 1560 0.6647 -0.0007 -1.9446 0.7134 1.9439 -48.7821 -37.3057 -2.2099 -2.3759
0.2224 2.2636 1580 0.6734 0.1503 -1.7687 0.7073 1.9189 -48.6648 -37.2050 -2.2196 -2.3861
0.0762 2.2923 1600 0.6678 0.2905 -1.6954 0.6951 1.9859 -48.6160 -37.1116 -2.2357 -2.4033
0.2452 2.3209 1620 0.6795 0.4962 -1.5076 0.7317 2.0038 -48.4907 -36.9744 -2.2440 -2.4112
0.0354 2.3496 1640 0.6843 0.4023 -1.6671 0.7134 2.0693 -48.5971 -37.0370 -2.2475 -2.4154
0.1987 2.3782 1660 0.6911 0.4904 -1.6030 0.7073 2.0934 -48.5544 -36.9782 -2.2530 -2.4212
0.1498 2.4069 1680 0.7020 0.2536 -1.8520 0.7195 2.1056 -48.7204 -37.1361 -2.2406 -2.4096
0.0617 2.4355 1700 0.7078 0.1642 -2.0151 0.7012 2.1793 -48.8291 -37.1957 -2.2341 -2.4027
0.0721 2.4642 1720 0.7118 -0.0325 -2.0697 0.6707 2.0372 -48.8655 -37.3268 -2.2306 -2.3997
0.0521 2.4928 1740 0.7055 -0.3331 -2.4476 0.7073 2.1145 -49.1174 -37.5273 -2.2059 -2.3751
0.055 2.5215 1760 0.6997 -0.3667 -2.5408 0.7134 2.1741 -49.1796 -37.5496 -2.2166 -2.3868
0.0903 2.5501 1780 0.7113 -0.2858 -2.4486 0.7439 2.1628 -49.1181 -37.4957 -2.2138 -2.3836
0.0453 2.5788 1800 0.7051 0.2785 -1.9874 0.75 2.2659 -48.8106 -37.1195 -2.2511 -2.4217
0.1064 2.6074 1820 0.7095 0.2406 -1.9493 0.7439 2.1899 -48.7852 -37.1448 -2.2445 -2.4146
0.0386 2.6361 1840 0.7283 -0.0103 -2.1669 0.7439 2.1567 -48.9303 -37.3120 -2.2272 -2.3986
0.3008 2.6648 1860 0.7347 -0.1451 -2.3757 0.7378 2.2306 -49.0695 -37.4019 -2.2140 -2.3856
0.0656 2.6934 1880 0.7283 0.2229 -2.0668 0.75 2.2897 -48.8635 -37.1566 -2.2324 -2.4039
0.0723 2.7221 1900 0.7282 -0.1779 -2.5250 0.7195 2.3471 -49.1690 -37.4238 -2.2098 -2.3811
0.1359 2.7507 1920 0.7192 -0.0838 -2.4250 0.75 2.3412 -49.1024 -37.3610 -2.2228 -2.3953
0.1302 2.7794 1940 0.7274 -0.0127 -2.4967 0.75 2.4840 -49.1501 -37.3137 -2.2322 -2.4044
0.1229 2.8080 1960 0.7108 0.0211 -2.4790 0.7439 2.5001 -49.1383 -37.2911 -2.2375 -2.4091
0.1202 2.8367 1980 0.7250 0.1294 -2.2904 0.7561 2.4199 -49.0126 -37.2189 -2.2409 -2.4113
0.057 2.8653 2000 0.7071 0.2988 -2.1859 0.7439 2.4847 -48.9429 -37.1060 -2.2570 -2.4290
0.0959 2.8940 2020 0.7210 0.3411 -2.0084 0.7561 2.3494 -48.8246 -37.0778 -2.2583 -2.4303
0.2817 2.9226 2040 0.7216 0.1300 -2.2967 0.7378 2.4266 -49.0168 -37.2185 -2.2406 -2.4125
0.6541 2.9513 2060 0.7282 0.0017 -2.4450 0.7378 2.4468 -49.1157 -37.3041 -2.2387 -2.4101
0.042 2.9799 2080 0.7077 0.0490 -2.5035 0.7439 2.5525 -49.1547 -37.2725 -2.2465 -2.4188
0.0089 3.0086 2100 0.7133 -0.0381 -2.5231 0.75 2.4850 -49.1677 -37.3306 -2.2352 -2.4069
0.0721 3.0372 2120 0.7310 -0.1357 -2.6555 0.7195 2.5197 -49.2560 -37.3957 -2.2350 -2.4075
0.0125 3.0659 2140 0.7289 0.1899 -2.4457 0.7622 2.6356 -49.1161 -37.1786 -2.2545 -2.4279
0.0297 3.0946 2160 0.7484 0.0728 -2.6560 0.7439 2.7288 -49.2563 -37.2566 -2.2537 -2.4276
0.0237 3.1232 2180 0.7679 0.2225 -2.5259 0.7378 2.7484 -49.1696 -37.1568 -2.2724 -2.4466
0.0084 3.1519 2200 0.7743 0.0334 -2.7988 0.7317 2.8321 -49.3515 -37.2830 -2.2704 -2.4455
0.0071 3.1805 2220 0.7777 0.1805 -2.7171 0.7622 2.8976 -49.2971 -37.1849 -2.2821 -2.4573
0.019 3.2092 2240 0.7602 0.1961 -2.7390 0.7622 2.9350 -49.3117 -37.1745 -2.2839 -2.4598
0.0053 3.2378 2260 0.7749 0.4526 -2.6596 0.7683 3.1122 -49.2587 -37.0034 -2.3020 -2.4783
0.0164 3.2665 2280 0.7822 0.3732 -2.6889 0.7744 3.0621 -49.2783 -37.0564 -2.3030 -2.4798
0.0068 3.2951 2300 0.7899 0.0399 -3.1333 0.7439 3.1732 -49.5745 -37.2786 -2.2989 -2.4764
0.0077 3.3238 2320 0.7887 0.1155 -2.9342 0.7561 3.0497 -49.4418 -37.2282 -2.2970 -2.4759
0.0231 3.3524 2340 0.7947 0.1411 -2.8551 0.7439 2.9963 -49.3891 -37.2111 -2.3068 -2.4853
0.0549 3.3811 2360 0.8034 0.2132 -2.9557 0.7805 3.1689 -49.4562 -37.1630 -2.3121 -2.4900
0.0814 3.4097 2380 0.7907 0.2118 -2.9652 0.7378 3.1770 -49.4625 -37.1640 -2.3046 -2.4826
0.0135 3.4384 2400 0.7899 0.0287 -3.1253 0.7622 3.1540 -49.5692 -37.2860 -2.2945 -2.4723
0.0862 3.4670 2420 0.7882 -0.3170 -3.6215 0.7622 3.3045 -49.9000 -37.5165 -2.2759 -2.4542
0.0149 3.4957 2440 0.8006 -0.5581 -3.7738 0.7561 3.2157 -50.0015 -37.6772 -2.2578 -2.4357
0.0191 3.5244 2460 0.7836 -0.4308 -3.6489 0.7561 3.2181 -49.9183 -37.5924 -2.2620 -2.4399
0.0161 3.5530 2480 0.8380 -0.1969 -3.3682 0.7378 3.1712 -49.7311 -37.4365 -2.2813 -2.4603
0.0934 3.5817 2500 0.8258 -0.0412 -3.3281 0.7439 3.2869 -49.7044 -37.3326 -2.2867 -2.4660
0.0169 3.6103 2520 0.8328 0.1485 -3.1268 0.7439 3.2753 -49.5702 -37.2062 -2.2883 -2.4670
0.0831 3.6390 2540 0.8336 -0.0808 -3.2812 0.7317 3.2004 -49.6731 -37.3591 -2.2800 -2.4587
0.2622 3.6676 2560 0.8307 0.2177 -3.0623 0.7378 3.2800 -49.5272 -37.1601 -2.2951 -2.4736
0.0038 3.6963 2580 0.8253 0.1987 -3.0051 0.75 3.2038 -49.4891 -37.1727 -2.2973 -2.4753
0.173 3.7249 2600 0.8292 0.1861 -3.0668 0.7195 3.2529 -49.5302 -37.1811 -2.3006 -2.4795
0.1305 3.7536 2620 0.8336 -0.2786 -3.5522 0.7561 3.2735 -49.8538 -37.4909 -2.2721 -2.4511
0.0884 3.7822 2640 0.8450 -0.4424 -3.6805 0.7439 3.2381 -49.9394 -37.6001 -2.2600 -2.4389
0.0045 3.8109 2660 0.8323 -0.2425 -3.6836 0.7561 3.4412 -49.9414 -37.4668 -2.2674 -2.4463
0.0152 3.8395 2680 0.8460 0.0591 -3.2821 0.7683 3.3412 -49.6738 -37.2658 -2.2876 -2.4676
0.0079 3.8682 2700 0.8276 -0.0039 -3.4071 0.7439 3.4032 -49.7571 -37.3078 -2.2765 -2.4552
0.1328 3.8968 2720 0.8264 -0.0002 -3.3186 0.7378 3.3184 -49.6981 -37.3053 -2.2873 -2.4683
0.0312 3.9255 2740 0.8063 -0.0827 -3.4566 0.7561 3.3739 -49.7901 -37.3603 -2.2762 -2.4554
0.0038 3.9542 2760 0.8245 0.0086 -3.3572 0.75 3.3658 -49.7238 -37.2994 -2.2894 -2.4694
0.0096 3.9828 2780 0.8281 -0.2458 -3.5377 0.7439 3.2920 -49.8442 -37.4690 -2.2806 -2.4604
0.0019 4.0115 2800 0.8470 -0.1289 -3.4632 0.7561 3.3343 -49.7945 -37.3911 -2.2872 -2.4679
0.0037 4.0401 2820 0.8506 -0.0267 -3.5451 0.7622 3.5183 -49.8491 -37.3230 -2.2949 -2.4761
0.0041 4.0688 2840 0.8633 -0.2368 -3.8138 0.7317 3.5770 -50.0282 -37.4631 -2.2923 -2.4749
0.0013 4.0974 2860 0.8747 -0.3139 -3.9316 0.7561 3.6177 -50.1067 -37.5144 -2.2942 -2.4760
0.0027 4.1261 2880 0.8936 -0.5221 -4.1944 0.75 3.6724 -50.2820 -37.6532 -2.2923 -2.4744
0.0028 4.1547 2900 0.8900 -0.4697 -4.2019 0.75 3.7322 -50.2870 -37.6183 -2.2950 -2.4776
0.0026 4.1834 2920 0.8899 -0.5699 -4.3045 0.7256 3.7346 -50.3554 -37.6851 -2.3000 -2.4839
0.004 4.2120 2940 0.8926 -0.4792 -4.2045 0.75 3.7253 -50.2887 -37.6247 -2.3152 -2.4986
0.0022 4.2407 2960 0.9133 -0.1876 -4.0201 0.7378 3.8326 -50.1658 -37.4302 -2.3286 -2.5117
0.0015 4.2693 2980 0.9147 -0.1140 -3.9325 0.7622 3.8185 -50.1073 -37.3812 -2.3393 -2.5221
0.002 4.2980 3000 0.9264 -0.1440 -4.0713 0.7378 3.9274 -50.1999 -37.4012 -2.3416 -2.5263
0.0027 4.3266 3020 0.9465 -0.2334 -4.1554 0.7683 3.9220 -50.2560 -37.4608 -2.3426 -2.5273
0.0128 4.3553 3040 0.9607 -0.3812 -4.3053 0.75 3.9241 -50.3559 -37.5593 -2.3323 -2.5168
0.0092 4.3840 3060 0.9387 -0.6329 -4.7010 0.7622 4.0681 -50.6197 -37.7271 -2.3207 -2.5059
0.0009 4.4126 3080 0.9478 -0.6562 -4.7956 0.7561 4.1394 -50.6827 -37.7427 -2.3221 -2.5068
0.0047 4.4413 3100 0.9456 -0.3176 -4.6057 0.7561 4.2881 -50.5561 -37.5169 -2.3561 -2.5425
0.0033 4.4699 3120 0.9556 -0.2730 -4.4728 0.75 4.1998 -50.4676 -37.4872 -2.3550 -2.5408
0.0017 4.4986 3140 0.9745 -0.3027 -4.5593 0.75 4.2565 -50.5252 -37.5070 -2.3487 -2.5341
0.0009 4.5272 3160 0.9731 -0.3404 -4.5470 0.7561 4.2067 -50.5170 -37.5321 -2.3525 -2.5386
0.1341 4.5559 3180 0.9740 -0.2885 -4.5137 0.7805 4.2252 -50.4948 -37.4975 -2.3507 -2.5355
0.0139 4.5845 3200 0.9846 -0.4084 -4.6203 0.7439 4.2119 -50.5659 -37.5775 -2.3554 -2.5410
0.001 4.6132 3220 0.9964 -0.4146 -4.5785 0.7683 4.1639 -50.5380 -37.5816 -2.3523 -2.5390
0.0019 4.6418 3240 0.9914 -0.3992 -4.6578 0.7744 4.2586 -50.5909 -37.5713 -2.3588 -2.5460
0.0003 4.6705 3260 0.9859 -0.4765 -4.6712 0.7561 4.1947 -50.5998 -37.6229 -2.3567 -2.5430
0.0022 4.6991 3280 0.9858 -0.5399 -4.8405 0.75 4.3006 -50.7127 -37.6651 -2.3437 -2.5302
0.0016 4.7278 3300 0.9901 -0.3900 -4.7788 0.7561 4.3888 -50.6715 -37.5652 -2.3604 -2.5482
0.0015 4.7564 3320 0.9915 -0.4472 -4.7529 0.7439 4.3057 -50.6543 -37.6033 -2.3556 -2.5419
0.0068 4.7851 3340 1.0009 -0.6228 -4.8092 0.7683 4.1864 -50.6918 -37.7204 -2.3566 -2.5435
0.0435 4.8138 3360 0.9982 -0.3929 -4.6009 0.7561 4.2080 -50.5529 -37.5671 -2.3650 -2.5530
0.0041 4.8424 3380 1.0030 -0.4106 -4.7219 0.7378 4.3113 -50.6336 -37.5790 -2.3571 -2.5437
0.0031 4.8711 3400 0.9665 -0.2183 -4.4817 0.7683 4.2634 -50.4735 -37.4507 -2.3633 -2.5496
0.0008 4.8997 3420 0.9724 -0.3910 -4.5774 0.7622 4.1864 -50.5373 -37.5659 -2.3572 -2.5446
0.0019 4.9284 3440 0.9784 -0.3079 -4.5903 0.75 4.2823 -50.5459 -37.5105 -2.3559 -2.5432
0.0004 4.9570 3460 0.9802 -0.4062 -4.6542 0.7622 4.2479 -50.5885 -37.5760 -2.3582 -2.5461
0.0063 4.9857 3480 0.9698 -0.3503 -4.7231 0.75 4.3728 -50.6344 -37.5387 -2.3594 -2.5471
0.0013 5.0143 3500 0.9783 -0.0355 -4.3472 0.7439 4.3116 -50.3838 -37.3289 -2.3741 -2.5616
0.0051 5.0430 3520 0.9935 -0.2275 -4.5304 0.75 4.3029 -50.5060 -37.4569 -2.3734 -2.5612
0.0014 5.0716 3540 0.9793 -0.4280 -4.7133 0.7561 4.2854 -50.6279 -37.5905 -2.3615 -2.5493
0.0009 5.1003 3560 0.9986 -0.5060 -4.9080 0.7561 4.4020 -50.7577 -37.6425 -2.3665 -2.5552
0.0004 5.1289 3580 0.9914 -0.5134 -4.8579 0.7683 4.3445 -50.7243 -37.6474 -2.3756 -2.5645
0.0001 5.1576 3600 1.0033 -0.2291 -4.6954 0.75 4.4663 -50.6160 -37.4580 -2.3894 -2.5772
0.0009 5.1862 3620 1.0033 -0.2055 -4.7371 0.7683 4.5316 -50.6438 -37.4422 -2.3936 -2.5816
0.0008 5.2149 3640 1.0176 -0.3229 -4.8411 0.7439 4.5181 -50.7131 -37.5205 -2.3866 -2.5744
0.0005 5.2436 3660 1.0224 -0.4097 -4.9712 0.7622 4.5615 -50.7998 -37.5783 -2.3865 -2.5749
0.0003 5.2722 3680 1.0403 -0.5507 -5.1750 0.7744 4.6243 -50.9357 -37.6723 -2.3794 -2.5682
0.0005 5.3009 3700 1.0228 -0.4905 -5.1947 0.7805 4.7042 -50.9488 -37.6322 -2.3795 -2.5682
0.0006 5.3295 3720 1.0378 -0.6007 -5.2590 0.7683 4.6584 -50.9917 -37.7056 -2.3796 -2.5696
0.0005 5.3582 3740 1.0296 -0.4368 -5.1702 0.7622 4.7334 -50.9325 -37.5964 -2.3879 -2.5789
0.0007 5.3868 3760 1.0324 -0.4259 -5.1876 0.7683 4.7617 -50.9441 -37.5891 -2.3880 -2.5777
0.0072 5.4155 3780 1.0398 -0.4193 -5.1073 0.7683 4.6879 -50.8905 -37.5847 -2.3883 -2.5773
0.0002 5.4441 3800 1.0492 -0.2759 -5.0575 0.7805 4.7816 -50.8574 -37.4891 -2.4041 -2.5945
0.0002 5.4728 3820 1.0587 -0.3267 -5.1022 0.7622 4.7754 -50.8871 -37.5230 -2.4098 -2.6004
0.0005 5.5014 3840 1.0631 -0.2539 -5.1368 0.7561 4.8829 -50.9102 -37.4744 -2.4090 -2.5992
0.0002 5.5301 3860 1.0372 -0.4144 -5.2424 0.7744 4.8280 -50.9807 -37.5815 -2.4013 -2.5924
0.0004 5.5587 3880 1.0495 -0.4714 -5.3312 0.7561 4.8597 -51.0398 -37.6195 -2.3924 -2.5821
0.001 5.5874 3900 1.0486 -0.4782 -5.3662 0.7805 4.8880 -51.0631 -37.6240 -2.3974 -2.5880
0.001 5.6160 3920 1.0506 -0.3607 -5.2072 0.7744 4.8465 -50.9571 -37.5456 -2.4071 -2.5976
0.0006 5.6447 3940 1.0483 -0.3132 -5.1293 0.7378 4.8161 -50.9052 -37.5140 -2.4116 -2.6014
0.0005 5.6734 3960 1.0553 -0.3917 -5.2145 0.7439 4.8228 -50.9620 -37.5664 -2.4092 -2.5993
0.0013 5.7020 3980 1.0599 -0.4594 -5.3379 0.7805 4.8785 -51.0443 -37.6115 -2.4045 -2.5949
0.0005 5.7307 4000 1.0585 -0.6683 -5.4484 0.7683 4.7802 -51.1180 -37.7507 -2.3965 -2.5871
0.0051 5.7593 4020 1.0491 -0.7331 -5.5061 0.7744 4.7730 -51.1564 -37.7939 -2.4022 -2.5943
0.0011 5.7880 4040 1.0520 -0.5599 -5.5201 0.7683 4.9602 -51.1657 -37.6785 -2.4005 -2.5917
0.0013 5.8166 4060 1.0609 -0.5051 -5.4035 0.75 4.8985 -51.0880 -37.6419 -2.4058 -2.5975
0.0018 5.8453 4080 1.0655 -0.5281 -5.4475 0.7683 4.9194 -51.1173 -37.6572 -2.4031 -2.5946
0.0005 5.8739 4100 1.0503 -0.4433 -5.3728 0.75 4.9295 -51.0676 -37.6007 -2.4080 -2.6002
0.0002 5.9026 4120 1.0647 -0.5539 -5.4257 0.7744 4.8718 -51.1028 -37.6744 -2.4030 -2.5951
0.0003 5.9312 4140 1.0795 -0.6022 -5.4344 0.7622 4.8321 -51.1086 -37.7067 -2.3998 -2.5919
0.0006 5.9599 4160 1.0599 -0.5806 -5.4356 0.7622 4.8550 -51.1094 -37.6923 -2.3980 -2.5898
0.0008 5.9885 4180 1.0733 -0.4986 -5.4546 0.7561 4.9560 -51.1221 -37.6376 -2.4061 -2.5986
0.0002 6.0172 4200 1.0704 -0.5107 -5.4161 0.7622 4.9054 -51.0964 -37.6457 -2.4134 -2.6052
0.0001 6.0458 4220 1.0739 -0.5080 -5.4632 0.75 4.9552 -51.1278 -37.6439 -2.4164 -2.6087
0.0006 6.0745 4240 1.0734 -0.4802 -5.4571 0.7622 4.9769 -51.1237 -37.6253 -2.4160 -2.6087
0.0003 6.1032 4260 1.0684 -0.4813 -5.4922 0.7622 5.0109 -51.1472 -37.6260 -2.4203 -2.6129
0.0001 6.1318 4280 1.0806 -0.4602 -5.5021 0.7439 5.0419 -51.1538 -37.6120 -2.4205 -2.6129
0.0003 6.1605 4300 1.0743 -0.4804 -5.4534 0.7439 4.9730 -51.1213 -37.6255 -2.4226 -2.6156
0.0002 6.1891 4320 1.0910 -0.4338 -5.4512 0.7805 5.0173 -51.1198 -37.5944 -2.4259 -2.6187
0.0002 6.2178 4340 1.1028 -0.4035 -5.4744 0.7561 5.0709 -51.1353 -37.5742 -2.4228 -2.6155
0.0002 6.2464 4360 1.0730 -0.3543 -5.4536 0.7683 5.0993 -51.1214 -37.5414 -2.4284 -2.6212
0.0002 6.2751 4380 1.0913 -0.3756 -5.4334 0.7378 5.0578 -51.1079 -37.5556 -2.4294 -2.6227
0.0002 6.3037 4400 1.0897 -0.4736 -5.5099 0.7378 5.0363 -51.1590 -37.6209 -2.4300 -2.6230
0.0003 6.3324 4420 1.1019 -0.5148 -5.5269 0.7439 5.0122 -51.1703 -37.6484 -2.4225 -2.6153
0.0001 6.3610 4440 1.0869 -0.4746 -5.6385 0.7744 5.1639 -51.2447 -37.6216 -2.4261 -2.6193
0.0002 6.3897 4460 1.0844 -0.4900 -5.6492 0.7561 5.1592 -51.2518 -37.6318 -2.4273 -2.6204
0.0001 6.4183 4480 1.0832 -0.4725 -5.6053 0.7622 5.1328 -51.2226 -37.6202 -2.4249 -2.6183
0.0001 6.4470 4500 1.0951 -0.4556 -5.6636 0.7683 5.2080 -51.2614 -37.6089 -2.4292 -2.6222
0.0 6.4756 4520 1.0866 -0.5072 -5.6601 0.7805 5.1529 -51.2591 -37.6433 -2.4246 -2.6164
0.0002 6.5043 4540 1.0916 -0.4715 -5.7196 0.7683 5.2481 -51.2988 -37.6195 -2.4297 -2.6236
0.0009 6.5330 4560 1.0964 -0.4816 -5.6407 0.7622 5.1591 -51.2461 -37.6263 -2.4245 -2.6171
0.0002 6.5616 4580 1.1214 -0.4599 -5.6562 0.7561 5.1962 -51.2565 -37.6118 -2.4333 -2.6261
0.0002 6.5903 4600 1.1098 -0.4649 -5.7015 0.7744 5.2366 -51.2867 -37.6151 -2.4341 -2.6274
0.0004 6.6189 4620 1.1121 -0.5644 -5.7521 0.7622 5.1877 -51.3204 -37.6815 -2.4334 -2.6263
0.0 6.6476 4640 1.1109 -0.4577 -5.6589 0.7622 5.2012 -51.2583 -37.6103 -2.4342 -2.6273
0.0004 6.6762 4660 1.1142 -0.4737 -5.6591 0.7561 5.1854 -51.2584 -37.6210 -2.4339 -2.6276
0.0002 6.7049 4680 1.1061 -0.5055 -5.7155 0.7561 5.2100 -51.2960 -37.6422 -2.4306 -2.6235
0.0002 6.7335 4700 1.0880 -0.4853 -5.6204 0.75 5.1352 -51.2326 -37.6287 -2.4356 -2.6296
0.0002 6.7622 4720 1.1035 -0.5173 -5.6735 0.7622 5.1563 -51.2680 -37.6500 -2.4328 -2.6259
0.0003 6.7908 4740 1.1121 -0.4845 -5.6930 0.7439 5.2086 -51.2810 -37.6282 -2.4305 -2.6240
0.0002 6.8195 4760 1.1118 -0.4717 -5.6904 0.7378 5.2187 -51.2793 -37.6197 -2.4357 -2.6295
0.0005 6.8481 4780 1.1005 -0.5040 -5.7272 0.7866 5.2232 -51.3038 -37.6412 -2.4367 -2.6293
0.0015 6.8768 4800 1.1215 -0.5113 -5.7074 0.7561 5.1961 -51.2906 -37.6460 -2.4320 -2.6248
0.0004 6.9054 4820 1.1107 -0.4717 -5.6918 0.7561 5.2200 -51.2802 -37.6197 -2.4320 -2.6256
0.0003 6.9341 4840 1.1153 -0.5086 -5.7519 0.75 5.2433 -51.3203 -37.6442 -2.4312 -2.6243
0.0005 6.9628 4860 1.1147 -0.5398 -5.7740 0.7561 5.2341 -51.3350 -37.6651 -2.4292 -2.6225
0.0003 6.9914 4880 1.1151 -0.4804 -5.7762 0.7683 5.2958 -51.3365 -37.6255 -2.4291 -2.6220
0.0001 7.0201 4900 1.1117 -0.5175 -5.7645 0.7439 5.2469 -51.3287 -37.6502 -2.4347 -2.6280
0.0002 7.0487 4920 1.1236 -0.5374 -5.8409 0.7561 5.3035 -51.3796 -37.6634 -2.4315 -2.6250
0.0002 7.0774 4940 1.1032 -0.5376 -5.7386 0.7561 5.2010 -51.3114 -37.6636 -2.4378 -2.6317
0.0001 7.1060 4960 1.1131 -0.5442 -5.8413 0.75 5.2971 -51.3799 -37.6680 -2.4334 -2.6275
0.0001 7.1347 4980 1.1208 -0.5429 -5.7231 0.7683 5.1802 -51.3011 -37.6671 -2.4385 -2.6326
0.0003 7.1633 5000 1.0966 -0.5211 -5.7483 0.7561 5.2273 -51.3179 -37.6526 -2.4344 -2.6286
0.0001 7.1920 5020 1.1016 -0.5223 -5.7960 0.7561 5.2737 -51.3497 -37.6534 -2.4340 -2.6274
0.0003 7.2206 5040 1.1043 -0.4846 -5.8107 0.7622 5.3261 -51.3595 -37.6283 -2.4340 -2.6278
0.0001 7.2493 5060 1.1027 -0.5569 -5.8161 0.7439 5.2592 -51.3631 -37.6765 -2.4315 -2.6248
0.0002 7.2779 5080 1.1172 -0.5091 -5.6916 0.7622 5.1825 -51.2801 -37.6446 -2.4367 -2.6307
0.0001 7.3066 5100 1.1024 -0.4273 -5.7785 0.75 5.3512 -51.3380 -37.5901 -2.4370 -2.6312
0.0001 7.3352 5120 1.1125 -0.5374 -5.7627 0.7744 5.2253 -51.3275 -37.6634 -2.4369 -2.6304
0.0001 7.3639 5140 1.1132 -0.5510 -5.7399 0.75 5.1889 -51.3123 -37.6725 -2.4394 -2.6336
0.0002 7.3926 5160 1.1260 -0.5236 -5.7101 0.7622 5.1865 -51.2924 -37.6542 -2.4368 -2.6302
0.0001 7.4212 5180 1.1230 -0.5582 -5.7407 0.7622 5.1825 -51.3128 -37.6773 -2.4317 -2.6248
0.0002 7.4499 5200 1.1276 -0.4874 -5.7521 0.7561 5.2648 -51.3204 -37.6301 -2.4420 -2.6360
0.0002 7.4785 5220 1.1213 -0.5305 -5.7599 0.75 5.2294 -51.3256 -37.6589 -2.4400 -2.6343
0.0002 7.5072 5240 1.1124 -0.5311 -5.8026 0.7561 5.2716 -51.3541 -37.6592 -2.4364 -2.6296
0.0002 7.5358 5260 1.0987 -0.5151 -5.8600 0.7683 5.3449 -51.3924 -37.6486 -2.4374 -2.6315
0.0003 7.5645 5280 1.1274 -0.5296 -5.7695 0.7683 5.2399 -51.3320 -37.6583 -2.4365 -2.6296
0.0001 7.5931 5300 1.1037 -0.5168 -5.8267 0.75 5.3099 -51.3701 -37.6497 -2.4417 -2.6353
0.0002 7.6218 5320 1.1130 -0.5122 -5.7933 0.7622 5.2811 -51.3479 -37.6467 -2.4371 -2.6304
0.0001 7.6504 5340 1.1096 -0.5304 -5.8626 0.7622 5.3322 -51.3941 -37.6588 -2.4390 -2.6329
0.0002 7.6791 5360 1.1134 -0.5563 -5.7787 0.7683 5.2225 -51.3382 -37.6761 -2.4387 -2.6325
0.0001 7.7077 5380 1.1191 -0.4964 -5.7361 0.7805 5.2397 -51.3098 -37.6361 -2.4442 -2.6387
0.0001 7.7364 5400 1.1221 -0.5278 -5.8344 0.7561 5.3066 -51.3753 -37.6571 -2.4389 -2.6327
0.0001 7.7650 5420 1.1255 -0.4974 -5.7959 0.7439 5.2986 -51.3496 -37.6368 -2.4378 -2.6311
0.0002 7.7937 5440 1.1317 -0.5313 -5.8578 0.7683 5.3266 -51.3909 -37.6594 -2.4405 -2.6341
0.0002 7.8223 5460 1.1171 -0.5022 -5.7745 0.75 5.2723 -51.3353 -37.6400 -2.4417 -2.6355
0.0001 7.8510 5480 1.1041 -0.5059 -5.8136 0.7683 5.3077 -51.3614 -37.6424 -2.4416 -2.6356
0.0001 7.8797 5500 1.1202 -0.4504 -5.6939 0.7561 5.2434 -51.2816 -37.6055 -2.4399 -2.6339
0.0001 7.9083 5520 1.1202 -0.5155 -5.7020 0.7561 5.1865 -51.2870 -37.6488 -2.4392 -2.6333
0.0002 7.9370 5540 1.1255 -0.4878 -5.8076 0.7683 5.3198 -51.3574 -37.6304 -2.4410 -2.6350
0.0001 7.9656 5560 1.1222 -0.4668 -5.8181 0.7683 5.3513 -51.3644 -37.6164 -2.4407 -2.6347
0.0008 7.9943 5580 1.1130 -0.4448 -5.8140 0.7622 5.3692 -51.3617 -37.6017 -2.4410 -2.6351

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.5.1+cu121
  • Datasets 3.5.0
  • Tokenizers 0.20.3
Downloads last month
2
Safetensors
Model size
2B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for YuchenLi01/genSoftQwen2.5MathRM72Bth0.5pair4NoGT_1.5B_dpo_ebs32_lr5e-07_beta1.5_epoch8.0_42

Finetuned
(1506)
this model