duplicated block id: 1 size: 132 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (374:572) - trl/trainer/orpo_trainer.py (349:547) duplicated block id: 2 size: 116 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (920:1109) - trl/trainer/orpo_trainer.py (899:1086) duplicated block id: 3 size: 109 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1364:1536) - trl/trainer/kto_trainer.py (1557:1729) duplicated block id: 4 size: 108 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1229:1360) - trl/trainer/kto_trainer.py (1421:1553) duplicated block id: 5 size: 68 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (401:498) - trl/trainer/kto_trainer.py (386:483) duplicated block id: 6 size: 61 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (208:281) - trl/trainer/kto_trainer.py (200:273) duplicated block id: 7 size: 55 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (145:226) - trl/trainer/orpo_trainer.py (149:230) duplicated block id: 8 size: 53 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (730:813) - trl/trainer/rloo_trainer.py (623:709) duplicated block id: 9 size: 48 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (465:544) - trl/trainer/xpo_trainer.py (511:588) duplicated block id: 10 size: 47 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (382:458) - trl/trainer/ddpo_trainer.py (584:662) duplicated block id: 11 size: 46 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (574:642) - trl/trainer/orpo_trainer.py (559:627) duplicated block id: 12 size: 44 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (86:130) - trl/trainer/kto_config.py (93:137) duplicated block id: 13 size: 43 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (158:220) - trl/trainer/kto_trainer.py (402:464) duplicated block id: 14 size: 43 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (402:464) - trl/trainer/orpo_trainer.py (162:224) duplicated block id: 15 size: 43 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (417:479) - trl/trainer/orpo_trainer.py (162:224) duplicated block id: 16 size: 43 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (417:479) - trl/trainer/cpo_trainer.py (158:220) duplicated block id: 17 size: 42 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (733:787) - trl/trainer/orpo_trainer.py (697:751) duplicated block id: 18 size: 42 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (23:126) - trl/trainer/orpo_config.py (23:111) duplicated block id: 19 size: 40 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1854:1923) - trl/trainer/kto_trainer.py (1664:1729) duplicated block id: 20 size: 40 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (93:133) - trl/trainer/orpo_config.py (71:111) duplicated block id: 21 size: 40 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1471:1536) - trl/trainer/dpo_trainer.py (1854:1923) duplicated block id: 22 size: 38 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:458) - trl/trainer/online_dpo_trainer.py (741:802) duplicated block id: 23 size: 38 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1536) - trl/trainer/cpo_trainer.py (1046:1109) duplicated block id: 24 size: 38 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1536) - trl/trainer/orpo_trainer.py (1025:1086) duplicated block id: 25 size: 38 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1858:1923) - trl/trainer/grpo_trainer.py (1516:1580) duplicated block id: 26 size: 38 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:458) - trl/trainer/grpo_trainer.py (1516:1580) duplicated block id: 27 size: 38 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:662) - trl/trainer/ppo_trainer.py (752:813) duplicated block id: 28 size: 38 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1536) - trl/trainer/ddpo_trainer.py (599:662) duplicated block id: 29 size: 38 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1858:1923) - trl/trainer/online_dpo_trainer.py (741:802) duplicated block id: 30 size: 38 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1516:1580) - trl/trainer/kto_trainer.py (1668:1729) duplicated block id: 31 size: 38 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (741:802) - trl/trainer/ppo_trainer.py (752:813) duplicated block id: 32 size: 38 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (1025:1086) - trl/trainer/rloo_trainer.py (645:709) duplicated block id: 33 size: 38 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (1025:1086) - trl/trainer/ppo_trainer.py (752:813) duplicated block id: 34 size: 38 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1516:1580) - trl/trainer/ppo_trainer.py (752:813) duplicated block id: 35 size: 38 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:458) - trl/trainer/rloo_trainer.py (645:709) duplicated block id: 36 size: 38 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1668:1729) - trl/trainer/ppo_trainer.py (752:813) duplicated block id: 37 size: 38 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1858:1923) - trl/trainer/ppo_trainer.py (752:813) duplicated block id: 38 size: 38 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (741:802) - trl/trainer/orpo_trainer.py (1025:1086) duplicated block id: 39 size: 38 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1516:1580) - trl/trainer/rloo_trainer.py (645:709) duplicated block id: 40 size: 38 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1536) - trl/trainer/rloo_trainer.py (645:709) duplicated block id: 41 size: 38 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:662) - trl/trainer/orpo_trainer.py (1025:1086) duplicated block id: 42 size: 38 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:458) - trl/trainer/kto_trainer.py (1668:1729) duplicated block id: 43 size: 38 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:458) - trl/trainer/cpo_trainer.py (1046:1109) duplicated block id: 44 size: 38 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:662) - trl/trainer/grpo_trainer.py (1516:1580) duplicated block id: 45 size: 38 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (741:802) - trl/trainer/rloo_trainer.py (645:709) duplicated block id: 46 size: 38 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1109) - trl/trainer/ddpo_trainer.py (599:662) duplicated block id: 47 size: 38 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:662) - trl/trainer/rloo_trainer.py (645:709) duplicated block id: 48 size: 38 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1536) - trl/trainer/grpo_trainer.py (1516:1580) duplicated block id: 49 size: 38 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:662) - trl/trainer/dpo_trainer.py (1858:1923) duplicated block id: 50 size: 38 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1668:1729) - trl/trainer/orpo_trainer.py (1025:1086) duplicated block id: 51 size: 38 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1858:1923) - trl/trainer/orpo_trainer.py (1025:1086) duplicated block id: 52 size: 38 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1668:1729) - trl/trainer/rloo_trainer.py (645:709) duplicated block id: 53 size: 38 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1109) - trl/trainer/rloo_trainer.py (645:709) duplicated block id: 54 size: 38 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:458) - trl/trainer/ppo_trainer.py (752:813) duplicated block id: 55 size: 38 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:458) - trl/trainer/bco_trainer.py (1475:1536) duplicated block id: 56 size: 38 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1516:1580) - trl/trainer/orpo_trainer.py (1025:1086) duplicated block id: 57 size: 38 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1109) - trl/trainer/kto_trainer.py (1668:1729) duplicated block id: 58 size: 38 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1109) - trl/trainer/dpo_trainer.py (1858:1923) duplicated block id: 59 size: 38 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1109) - trl/trainer/grpo_trainer.py (1516:1580) duplicated block id: 60 size: 38 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1536) - trl/trainer/online_dpo_trainer.py (741:802) duplicated block id: 61 size: 38 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1109) - trl/trainer/online_dpo_trainer.py (741:802) duplicated block id: 62 size: 38 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:662) - trl/trainer/online_dpo_trainer.py (741:802) duplicated block id: 63 size: 38 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1858:1923) - trl/trainer/rloo_trainer.py (645:709) duplicated block id: 64 size: 38 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1536) - trl/trainer/ppo_trainer.py (752:813) duplicated block id: 65 size: 38 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1516:1580) - trl/trainer/online_dpo_trainer.py (741:802) duplicated block id: 66 size: 38 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1668:1729) - trl/trainer/online_dpo_trainer.py (741:802) duplicated block id: 67 size: 38 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (118:170) - trl/trainer/ddpo_trainer.py (121:173) duplicated block id: 68 size: 38 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:458) - trl/trainer/orpo_trainer.py (1025:1086) duplicated block id: 69 size: 38 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1109) - trl/trainer/ppo_trainer.py (752:813) duplicated block id: 70 size: 38 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:458) - trl/trainer/dpo_trainer.py (1858:1923) duplicated block id: 71 size: 38 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:662) - trl/trainer/kto_trainer.py (1668:1729) duplicated block id: 72 size: 37 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1108) - trl/trainer/prm_trainer.py (307:367) duplicated block id: 73 size: 37 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:457) - trl/trainer/prm_trainer.py (307:367) duplicated block id: 74 size: 37 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1516:1579) - trl/trainer/prm_trainer.py (307:367) duplicated block id: 75 size: 37 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (1025:1085) - trl/trainer/prm_trainer.py (307:367) duplicated block id: 76 size: 37 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:661) - trl/trainer/prm_trainer.py (307:367) duplicated block id: 77 size: 37 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1668:1728) - trl/trainer/prm_trainer.py (307:367) duplicated block id: 78 size: 37 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1858:1922) - trl/trainer/prm_trainer.py (307:367) duplicated block id: 79 size: 37 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (307:367) - trl/trainer/rloo_trainer.py (645:708) duplicated block id: 80 size: 37 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (752:812) - trl/trainer/prm_trainer.py (307:367) duplicated block id: 81 size: 37 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (741:801) - trl/trainer/prm_trainer.py (307:367) duplicated block id: 82 size: 37 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1535) - trl/trainer/prm_trainer.py (307:367) duplicated block id: 83 size: 36 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (467:520) - trl/trainer/reward_trainer.py (373:426) duplicated block id: 84 size: 36 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (669:715) - trl/trainer/kto_trainer.py (736:782) duplicated block id: 85 size: 36 cleaned lines of code in 2 files: - trl/trainer/callbacks.py (313:354) - trl/trainer/callbacks.py (376:417) duplicated block id: 86 size: 35 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1240:1290) - trl/trainer/dpo_trainer.py (1438:1493) duplicated block id: 87 size: 35 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1058:1099) - trl/trainer/kto_trainer.py (1052:1093) duplicated block id: 88 size: 34 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (97:147) - trl/trainer/kto_trainer.py (99:149) duplicated block id: 89 size: 33 cleaned lines of code in 2 files: - trl/trainer/reward_trainer.py (373:423) - trl/trainer/sft_trainer.py (880:930) duplicated block id: 90 size: 33 cleaned lines of code in 2 files: - trl/mergekit_utils.py (131:166) - trl/mergekit_utils.py (175:210) duplicated block id: 91 size: 33 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (467:517) - trl/trainer/sft_trainer.py (880:930) duplicated block id: 92 size: 32 cleaned lines of code in 2 files: - trl/trainer/reward_trainer.py (367:417) - trl/trainer/rloo_trainer.py (639:689) duplicated block id: 93 size: 32 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (746:796) - trl/trainer/reward_trainer.py (367:417) duplicated block id: 94 size: 31 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1483:1536) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 95 size: 31 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (607:662) - trl/trainer/nash_md_trainer.py (489:544) duplicated block id: 96 size: 31 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (405:458) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 97 size: 31 cleaned lines of code in 2 files: - trl/trainer/rloo_trainer.py (653:709) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 98 size: 31 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:362) - trl/trainer/orpo_trainer.py (1033:1086) duplicated block id: 99 size: 31 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1866:1923) - trl/trainer/gkd_trainer.py (307:362) duplicated block id: 100 size: 31 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:362) - trl/trainer/ppo_trainer.py (760:813) duplicated block id: 101 size: 31 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (489:544) - trl/trainer/orpo_trainer.py (1033:1086) duplicated block id: 102 size: 31 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (284:320) - trl/trainer/ddpo_trainer.py (396:432) duplicated block id: 103 size: 31 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:362) - trl/trainer/kto_trainer.py (1676:1729) duplicated block id: 104 size: 31 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:362) - trl/trainer/rloo_trainer.py (653:709) duplicated block id: 105 size: 31 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (607:662) - trl/trainer/gkd_trainer.py (307:362) duplicated block id: 106 size: 31 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (405:458) - trl/trainer/gkd_trainer.py (307:362) duplicated block id: 107 size: 31 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (760:813) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 108 size: 31 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (607:662) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 109 size: 31 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1866:1923) - trl/trainer/nash_md_trainer.py (489:544) duplicated block id: 110 size: 31 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (405:458) - trl/trainer/nash_md_trainer.py (489:544) duplicated block id: 111 size: 31 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1524:1580) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 112 size: 31 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (749:802) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 113 size: 31 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (489:544) - trl/trainer/ppo_trainer.py (760:813) duplicated block id: 114 size: 31 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1483:1536) - trl/trainer/nash_md_trainer.py (489:544) duplicated block id: 115 size: 31 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1866:1923) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 116 size: 31 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (1033:1086) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 117 size: 31 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1054:1109) - trl/trainer/nash_md_trainer.py (489:544) duplicated block id: 118 size: 31 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:362) - trl/trainer/grpo_trainer.py (1524:1580) duplicated block id: 119 size: 31 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1676:1729) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 120 size: 31 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1524:1580) - trl/trainer/nash_md_trainer.py (489:544) duplicated block id: 121 size: 31 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:362) - trl/trainer/nash_md_trainer.py (489:544) duplicated block id: 122 size: 31 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (489:544) - trl/trainer/online_dpo_trainer.py (749:802) duplicated block id: 123 size: 31 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1054:1109) - trl/trainer/gkd_trainer.py (307:362) duplicated block id: 124 size: 31 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:362) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 125 size: 31 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1676:1729) - trl/trainer/nash_md_trainer.py (489:544) duplicated block id: 126 size: 31 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (489:544) - trl/trainer/rloo_trainer.py (653:709) duplicated block id: 127 size: 31 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:362) - trl/trainer/online_dpo_trainer.py (749:802) duplicated block id: 128 size: 31 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1483:1536) - trl/trainer/gkd_trainer.py (307:362) duplicated block id: 129 size: 31 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1054:1109) - trl/trainer/xpo_trainer.py (535:588) duplicated block id: 130 size: 30 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (489:543) - trl/trainer/prm_trainer.py (315:367) duplicated block id: 131 size: 30 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:361) - trl/trainer/prm_trainer.py (315:367) duplicated block id: 132 size: 30 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (315:367) - trl/trainer/xpo_trainer.py (535:587) duplicated block id: 133 size: 30 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (97:128) - trl/trainer/reward_trainer.py (91:158) duplicated block id: 134 size: 29 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (64:97) - trl/trainer/ddpo_trainer.py (62:95) duplicated block id: 135 size: 28 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (467:511) - trl/trainer/online_dpo_trainer.py (741:785) duplicated block id: 136 size: 28 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1519) - trl/trainer/reward_trainer.py (373:417) duplicated block id: 137 size: 28 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:643) - trl/trainer/iterative_sft_trainer.py (467:511) duplicated block id: 138 size: 28 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1090) - trl/trainer/iterative_sft_trainer.py (467:511) duplicated block id: 139 size: 28 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:643) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 140 size: 28 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1519) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 141 size: 28 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1858:1902) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 142 size: 28 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (1025:1069) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 143 size: 28 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1668:1712) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 144 size: 28 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (599:643) - trl/trainer/reward_trainer.py (373:417) duplicated block id: 145 size: 28 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1668:1712) - trl/trainer/reward_trainer.py (373:417) duplicated block id: 146 size: 28 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (307:351) - trl/trainer/reward_trainer.py (373:417) duplicated block id: 147 size: 28 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (741:785) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 148 size: 28 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1516:1560) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 149 size: 28 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (467:511) - trl/trainer/rloo_trainer.py (645:689) duplicated block id: 150 size: 28 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1516:1560) - trl/trainer/reward_trainer.py (373:417) duplicated block id: 151 size: 28 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1516:1560) - trl/trainer/iterative_sft_trainer.py (467:511) duplicated block id: 152 size: 28 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:441) - trl/trainer/iterative_sft_trainer.py (467:511) duplicated block id: 153 size: 28 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1090) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 154 size: 28 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (467:511) - trl/trainer/prm_trainer.py (307:351) duplicated block id: 155 size: 28 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (307:351) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 156 size: 28 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (467:511) - trl/trainer/orpo_trainer.py (1025:1069) duplicated block id: 157 size: 28 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1858:1902) - trl/trainer/reward_trainer.py (373:417) duplicated block id: 158 size: 28 cleaned lines of code in 2 files: - trl/trainer/rloo_trainer.py (645:689) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 159 size: 28 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (752:796) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 160 size: 28 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1858:1902) - trl/trainer/iterative_sft_trainer.py (467:511) duplicated block id: 161 size: 28 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1475:1519) - trl/trainer/iterative_sft_trainer.py (467:511) duplicated block id: 162 size: 28 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (467:511) - trl/trainer/ppo_trainer.py (752:796) duplicated block id: 163 size: 28 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:441) - trl/trainer/sft_trainer.py (880:924) duplicated block id: 164 size: 28 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1046:1090) - trl/trainer/reward_trainer.py (373:417) duplicated block id: 165 size: 28 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (1025:1069) - trl/trainer/reward_trainer.py (373:417) duplicated block id: 166 size: 28 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (741:785) - trl/trainer/reward_trainer.py (373:417) duplicated block id: 167 size: 28 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (397:441) - trl/trainer/reward_trainer.py (373:417) duplicated block id: 168 size: 28 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (467:511) - trl/trainer/kto_trainer.py (1668:1712) duplicated block id: 169 size: 26 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (232:262) - trl/trainer/rloo_trainer.py (162:193) duplicated block id: 170 size: 26 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (884:919) - trl/trainer/orpo_trainer.py (858:893) duplicated block id: 171 size: 25 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1010:1057) - trl/trainer/kto_trainer.py (1001:1049) duplicated block id: 172 size: 25 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (940:978) - trl/trainer/dpo_trainer.py (1772:1810) duplicated block id: 173 size: 25 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1772:1810) - trl/trainer/orpo_trainer.py (919:957) duplicated block id: 174 size: 24 cleaned lines of code in 2 files: - trl/trainer/prm_config.py (56:80) - trl/trainer/reward_config.py (51:75) duplicated block id: 175 size: 24 cleaned lines of code in 2 files: - trl/trainer/prm_config.py (54:77) - trl/trainer/sft_config.py (102:125) duplicated block id: 176 size: 24 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (406:429) - trl/trainer/grpo_config.py (486:509) duplicated block id: 177 size: 24 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (157:204) - trl/trainer/kto_trainer.py (149:196) duplicated block id: 178 size: 24 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (262:291) - trl/trainer/orpo_trainer.py (261:290) duplicated block id: 179 size: 23 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (106:128) - scripts/generate_zen_dataset.py (271:293) duplicated block id: 180 size: 23 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (873:905) - trl/trainer/kto_trainer.py (809:841) duplicated block id: 181 size: 23 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (682:706) - trl/trainer/rloo_trainer.py (563:587) duplicated block id: 182 size: 22 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (442:463) - scripts/generate_zen_dataset.py (607:628) duplicated block id: 183 size: 22 cleaned lines of code in 2 files: - trl/trainer/reward_config.py (51:72) - trl/trainer/sft_config.py (104:125) duplicated block id: 184 size: 21 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (442:462) - scripts/generate_zen_dataset.py (490:510) duplicated block id: 185 size: 21 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (415:435) - scripts/generate_zen_dataset.py (442:462) duplicated block id: 186 size: 21 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:343) - trl/trainer/iterative_sft_trainer.py (475:511) duplicated block id: 187 size: 21 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (106:126) - scripts/generate_zen_dataset.py (154:174) duplicated block id: 188 size: 21 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (415:435) - scripts/generate_zen_dataset.py (607:627) duplicated block id: 189 size: 21 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (490:510) - scripts/generate_zen_dataset.py (607:627) duplicated block id: 190 size: 21 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (415:435) - scripts/generate_zen_dataset.py (490:510) duplicated block id: 191 size: 21 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (79:99) - scripts/generate_zen_dataset.py (271:291) duplicated block id: 192 size: 21 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (35:203) - trl/trainer/kto_config.py (23:111) duplicated block id: 193 size: 21 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (79:99) - scripts/generate_zen_dataset.py (154:174) duplicated block id: 194 size: 21 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (353:376) - trl/trainer/rloo_trainer.py (251:274) duplicated block id: 195 size: 21 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (475:511) - trl/trainer/nash_md_trainer.py (489:525) duplicated block id: 196 size: 21 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (79:99) - scripts/generate_zen_dataset.py (106:126) duplicated block id: 197 size: 21 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (489:525) - trl/trainer/sft_trainer.py (888:924) duplicated block id: 198 size: 21 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (489:525) - trl/trainer/reward_trainer.py (381:417) duplicated block id: 199 size: 21 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (154:174) - scripts/generate_zen_dataset.py (271:291) duplicated block id: 200 size: 21 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (475:511) - trl/trainer/xpo_trainer.py (535:571) duplicated block id: 201 size: 21 cleaned lines of code in 2 files: - trl/trainer/reward_trainer.py (381:417) - trl/trainer/xpo_trainer.py (535:571) duplicated block id: 202 size: 21 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:343) - trl/trainer/sft_trainer.py (888:924) duplicated block id: 203 size: 21 cleaned lines of code in 2 files: - trl/trainer/sft_trainer.py (888:924) - trl/trainer/xpo_trainer.py (535:571) duplicated block id: 204 size: 21 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (307:343) - trl/trainer/reward_trainer.py (381:417) duplicated block id: 205 size: 20 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (158:177) - trl/trainer/orpo_config.py (119:138) duplicated block id: 206 size: 20 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (354:380) - trl/trainer/kto_trainer.py (738:764) duplicated block id: 207 size: 20 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (464:483) - scripts/generate_zen_dataset.py (512:531) duplicated block id: 208 size: 20 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (211:232) - trl/trainer/orpo_config.py (68:89) duplicated block id: 209 size: 20 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (53:72) - scripts/generate_zen_dataset.py (224:243) duplicated block id: 210 size: 20 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (265:292) - trl/trainer/rloo_trainer.py (197:224) duplicated block id: 211 size: 20 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (83:104) - trl/trainer/grpo_config.py (211:232) duplicated block id: 212 size: 20 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (128:147) - scripts/generate_zen_dataset.py (176:195) duplicated block id: 213 size: 20 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (671:697) - trl/trainer/cpo_trainer.py (354:380) duplicated block id: 214 size: 19 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (86:104) - trl/trainer/dpo_config.py (185:203) duplicated block id: 215 size: 19 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (452:480) - trl/trainer/kto_trainer.py (749:777) duplicated block id: 216 size: 19 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (913:936) - trl/trainer/dpo_trainer.py (1745:1768) duplicated block id: 217 size: 19 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (682:710) - trl/trainer/dpo_trainer.py (452:480) duplicated block id: 218 size: 19 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (185:203) - trl/trainer/grpo_config.py (214:232) duplicated block id: 219 size: 19 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (185:203) - trl/trainer/orpo_config.py (71:89) duplicated block id: 220 size: 19 cleaned lines of code in 2 files: - scripts/generate_zen_dataset.py (390:408) - scripts/generate_zen_dataset.py (561:579) duplicated block id: 221 size: 19 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (189:209) - trl/trainer/iterative_sft_config.py (54:74) duplicated block id: 222 size: 19 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (214:232) - trl/trainer/kto_config.py (93:111) duplicated block id: 223 size: 18 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (157:174) - trl/trainer/orpo_config.py (125:142) duplicated block id: 224 size: 18 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (409:430) - trl/trainer/xpo_trainer.py (446:467) duplicated block id: 225 size: 17 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (95:111) - trl/trainer/prm_config.py (54:70) duplicated block id: 226 size: 17 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:100) - trl/trainer/cpo_config.py (90:107) duplicated block id: 227 size: 17 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (95:111) - trl/trainer/sft_config.py (102:118) duplicated block id: 228 size: 17 cleaned lines of code in 2 files: - trl/trainer/orpo_config.py (73:89) - trl/trainer/prm_config.py (54:70) duplicated block id: 229 size: 17 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (95:111) - trl/trainer/online_dpo_config.py (79:95) duplicated block id: 230 size: 17 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (187:203) - trl/trainer/sft_config.py (102:118) duplicated block id: 231 size: 17 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (216:232) - trl/trainer/sft_config.py (102:118) duplicated block id: 232 size: 17 cleaned lines of code in 2 files: - trl/models/modeling_value_head.py (108:137) - trl/models/modeling_value_head.py (382:403) duplicated block id: 233 size: 17 cleaned lines of code in 2 files: - trl/trainer/online_dpo_config.py (79:95) - trl/trainer/orpo_config.py (73:89) duplicated block id: 234 size: 17 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:100) - trl/trainer/kto_config.py (97:114) duplicated block id: 235 size: 17 cleaned lines of code in 2 files: - trl/trainer/orpo_config.py (73:89) - trl/trainer/sft_config.py (102:118) duplicated block id: 236 size: 17 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (187:203) - trl/trainer/online_dpo_config.py (79:95) duplicated block id: 237 size: 17 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (187:203) - trl/trainer/prm_config.py (54:70) duplicated block id: 238 size: 17 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (88:104) - trl/trainer/sft_config.py (102:118) duplicated block id: 239 size: 17 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (387:404) - trl/trainer/rloo_trainer.py (284:301) duplicated block id: 240 size: 17 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:100) - trl/trainer/orpo_config.py (75:92) duplicated block id: 241 size: 17 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (216:232) - trl/trainer/prm_config.py (54:70) duplicated block id: 242 size: 17 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (815:833) - trl/trainer/orpo_trainer.py (785:803) duplicated block id: 243 size: 17 cleaned lines of code in 2 files: - trl/trainer/online_dpo_config.py (79:95) - trl/trainer/sft_config.py (102:118) duplicated block id: 244 size: 17 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (88:104) - trl/trainer/online_dpo_config.py (79:95) duplicated block id: 245 size: 17 cleaned lines of code in 2 files: - trl/trainer/online_dpo_config.py (79:95) - trl/trainer/prm_config.py (54:70) duplicated block id: 246 size: 17 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (216:232) - trl/trainer/online_dpo_config.py (79:95) duplicated block id: 247 size: 17 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (915:948) - trl/trainer/kto_trainer.py (861:894) duplicated block id: 248 size: 17 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (88:104) - trl/trainer/prm_config.py (54:70) duplicated block id: 249 size: 16 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (467:487) - trl/trainer/online_dpo_trainer.py (674:695) duplicated block id: 250 size: 16 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (191:209) - trl/trainer/reward_trainer.py (245:263) duplicated block id: 251 size: 16 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (536:553) - trl/trainer/rloo_trainer.py (443:462) duplicated block id: 252 size: 16 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (913:930) - trl/trainer/kto_trainer.py (1537:1553) duplicated block id: 253 size: 16 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (989:1020) - trl/trainer/dpo_trainer.py (1824:1855) duplicated block id: 254 size: 16 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1344:1360) - trl/trainer/cpo_trainer.py (913:930) duplicated block id: 255 size: 16 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1824:1855) - trl/trainer/orpo_trainer.py (968:999) duplicated block id: 256 size: 16 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (674:695) - trl/trainer/xpo_trainer.py (513:533) duplicated block id: 257 size: 16 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1745:1762) - trl/trainer/kto_trainer.py (1537:1553) duplicated block id: 258 size: 16 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (958:978) - trl/trainer/kto_trainer.py (913:933) duplicated block id: 259 size: 16 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1344:1360) - trl/trainer/dpo_trainer.py (1745:1762) duplicated block id: 260 size: 16 cleaned lines of code in 2 files: - trl/trainer/reward_config.py (23:65) - trl/trainer/utils.py (1014:1092) duplicated block id: 261 size: 16 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (118:133) - trl/trainer/orpo_trainer.py (122:137) duplicated block id: 262 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (623:639) - trl/trainer/kto_trainer.py (632:649) duplicated block id: 263 size: 15 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (90:104) - trl/trainer/iterative_sft_config.py (54:68) duplicated block id: 264 size: 15 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_config.py (54:68) - trl/trainer/prm_config.py (56:70) duplicated block id: 265 size: 15 cleaned lines of code in 2 files: - trl/trainer/sft_config.py (104:118) - trl/trainer/utils.py (1078:1092) duplicated block id: 266 size: 15 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_config.py (54:68) - trl/trainer/reward_config.py (51:65) duplicated block id: 267 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:97) - trl/trainer/grpo_config.py (218:232) duplicated block id: 268 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:97) - trl/trainer/online_dpo_config.py (81:95) duplicated block id: 269 size: 15 cleaned lines of code in 2 files: - trl/models/modeling_value_head.py (220:239) - trl/models/modeling_value_head.py (307:326) duplicated block id: 270 size: 15 cleaned lines of code in 2 files: - trl/models/modeling_sd_base.py (333:347) - trl/models/modeling_sd_base.py (546:560) duplicated block id: 271 size: 15 cleaned lines of code in 2 files: - trl/trainer/orpo_config.py (75:89) - trl/trainer/reward_config.py (51:65) duplicated block id: 272 size: 15 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (864:881) - trl/trainer/orpo_trainer.py (835:852) duplicated block id: 273 size: 15 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (90:104) - trl/trainer/utils.py (1078:1092) duplicated block id: 274 size: 15 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (90:104) - trl/trainer/reward_config.py (51:65) duplicated block id: 275 size: 15 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (176:192) - trl/trainer/orpo_config.py (147:163) duplicated block id: 276 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (521:538) - trl/trainer/kto_trainer.py (506:523) duplicated block id: 277 size: 15 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (97:111) - trl/trainer/reward_config.py (51:65) duplicated block id: 278 size: 15 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (117:131) - trl/trainer/xpo_trainer.py (117:131) duplicated block id: 279 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:97) - trl/trainer/utils.py (1078:1092) duplicated block id: 280 size: 15 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (44:70) - trl/trainer/orpo_trainer.py (45:71) duplicated block id: 281 size: 15 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_config.py (54:68) - trl/trainer/online_dpo_config.py (81:95) duplicated block id: 282 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:97) - trl/trainer/sft_config.py (104:118) duplicated block id: 283 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:97) - trl/trainer/dpo_config.py (189:203) duplicated block id: 284 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1421:1450) - trl/trainer/cpo_trainer.py (986:1015) duplicated block id: 285 size: 15 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_config.py (54:68) - trl/trainer/utils.py (1078:1092) duplicated block id: 286 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1421:1450) - trl/trainer/orpo_trainer.py (965:994) duplicated block id: 287 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:97) - trl/trainer/iterative_sft_config.py (54:68) duplicated block id: 288 size: 15 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (189:203) - trl/trainer/utils.py (1078:1092) duplicated block id: 289 size: 15 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (334:350) - trl/trainer/prm_trainer.py (193:209) duplicated block id: 290 size: 15 cleaned lines of code in 2 files: - trl/trainer/online_dpo_config.py (81:95) - trl/trainer/reward_config.py (51:65) duplicated block id: 291 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (125:139) - trl/trainer/kto_config.py (157:171) duplicated block id: 292 size: 15 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_config.py (54:68) - trl/trainer/kto_config.py (97:111) duplicated block id: 293 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:97) - trl/trainer/prm_config.py (56:70) duplicated block id: 294 size: 15 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (218:232) - trl/trainer/iterative_sft_config.py (54:68) duplicated block id: 295 size: 15 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (189:203) - trl/trainer/reward_config.py (51:65) duplicated block id: 296 size: 15 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1674:1692) - trl/trainer/orpo_trainer.py (840:860) duplicated block id: 297 size: 15 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (986:1015) - trl/trainer/kto_trainer.py (1614:1643) duplicated block id: 298 size: 15 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (334:350) - trl/trainer/reward_trainer.py (247:263) duplicated block id: 299 size: 15 cleaned lines of code in 2 files: - trl/trainer/online_dpo_config.py (81:95) - trl/trainer/utils.py (1078:1092) duplicated block id: 300 size: 15 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1614:1643) - trl/trainer/orpo_trainer.py (965:994) duplicated block id: 301 size: 15 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (97:111) - trl/trainer/utils.py (1078:1092) duplicated block id: 302 size: 15 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (83:97) - trl/trainer/reward_config.py (51:65) duplicated block id: 303 size: 15 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (218:232) - trl/trainer/utils.py (1078:1092) duplicated block id: 304 size: 15 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_config.py (54:68) - trl/trainer/orpo_config.py (75:89) duplicated block id: 305 size: 15 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_config.py (54:68) - trl/trainer/sft_config.py (104:118) duplicated block id: 306 size: 15 cleaned lines of code in 2 files: - trl/trainer/prm_config.py (56:70) - trl/trainer/utils.py (1078:1092) duplicated block id: 307 size: 15 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (218:232) - trl/trainer/reward_config.py (51:65) duplicated block id: 308 size: 15 cleaned lines of code in 2 files: - trl/trainer/orpo_config.py (75:89) - trl/trainer/utils.py (1078:1092) duplicated block id: 309 size: 14 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (697:728) - trl/trainer/orpo_trainer.py (661:692) duplicated block id: 310 size: 14 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (337:350) - trl/trainer/kto_trainer.py (329:342) duplicated block id: 311 size: 14 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1257:1273) - trl/trainer/cpo_trainer.py (864:880) duplicated block id: 312 size: 14 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (669:683) - trl/trainer/reward_trainer.py (245:259) duplicated block id: 313 size: 14 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1382:1406) - trl/trainer/cpo_trainer.py (954:978) duplicated block id: 314 size: 14 cleaned lines of code in 2 files: - trl/models/modeling_sd_base.py (418:433) - trl/models/modeling_sd_base.py (655:670) duplicated block id: 315 size: 14 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (126:139) - trl/trainer/orpo_config.py (119:132) duplicated block id: 316 size: 14 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (34:57) - trl/trainer/rloo_trainer.py (33:53) duplicated block id: 317 size: 14 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1382:1406) - trl/trainer/dpo_trainer.py (1786:1810) duplicated block id: 318 size: 14 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1786:1810) - trl/trainer/kto_trainer.py (1575:1599) duplicated block id: 319 size: 14 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (157:170) - trl/trainer/kto_config.py (164:177) duplicated block id: 320 size: 14 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (864:880) - trl/trainer/kto_trainer.py (1449:1465) duplicated block id: 321 size: 14 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1575:1599) - trl/trainer/orpo_trainer.py (933:957) duplicated block id: 322 size: 14 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1257:1273) - trl/trainer/orpo_trainer.py (835:851) duplicated block id: 323 size: 14 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (954:978) - trl/trainer/kto_trainer.py (1575:1599) duplicated block id: 324 size: 14 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (669:683) - trl/trainer/prm_trainer.py (191:205) duplicated block id: 325 size: 14 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (352:366) - trl/trainer/orpo_trainer.py (332:346) duplicated block id: 326 size: 14 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (736:750) - trl/trainer/prm_trainer.py (191:205) duplicated block id: 327 size: 14 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (685:702) - trl/trainer/dpo_trainer.py (720:737) duplicated block id: 328 size: 14 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (736:750) - trl/trainer/reward_trainer.py (245:259) duplicated block id: 329 size: 14 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1449:1465) - trl/trainer/orpo_trainer.py (835:851) duplicated block id: 330 size: 14 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1382:1406) - trl/trainer/orpo_trainer.py (933:957) duplicated block id: 331 size: 13 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (429:442) - trl/trainer/rloo_trainer.py (323:337) duplicated block id: 332 size: 13 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (177:189) - trl/trainer/kto_config.py (206:218) duplicated block id: 333 size: 13 cleaned lines of code in 2 files: - trl/mergekit_utils.py (195:210) - trl/mergekit_utils.py (234:249) duplicated block id: 334 size: 13 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (31:62) - trl/trainer/xpo_trainer.py (32:62) duplicated block id: 335 size: 13 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (354:366) - trl/trainer/reward_trainer.py (247:259) duplicated block id: 336 size: 13 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (671:683) - trl/trainer/orpo_trainer.py (334:346) duplicated block id: 337 size: 13 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1010:1038) - trl/trainer/orpo_trainer.py (661:691) duplicated block id: 338 size: 13 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (354:366) - trl/trainer/prm_trainer.py (193:205) duplicated block id: 339 size: 13 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (697:727) - trl/trainer/kto_trainer.py (1001:1030) duplicated block id: 340 size: 13 cleaned lines of code in 2 files: - trl/__init__.py (195:213) - trl/models/__init__.py (58:72) duplicated block id: 341 size: 13 cleaned lines of code in 2 files: - trl/trainer/ppo_config.py (86:98) - trl/trainer/rloo_config.py (70:82) duplicated block id: 342 size: 13 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (623:635) - trl/trainer/rloo_trainer.py (526:538) duplicated block id: 343 size: 13 cleaned lines of code in 2 files: - trl/mergekit_utils.py (151:166) - trl/mergekit_utils.py (234:249) duplicated block id: 344 size: 13 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1001:1030) - trl/trainer/orpo_trainer.py (661:691) duplicated block id: 345 size: 13 cleaned lines of code in 2 files: - trl/models/modeling_value_head.py (199:218) - trl/models/modeling_value_head.py (361:380) duplicated block id: 346 size: 13 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (738:750) - trl/trainer/orpo_trainer.py (334:346) duplicated block id: 347 size: 13 cleaned lines of code in 2 files: - trl/accelerate_configs/multi_gpu.yaml (4:16) - trl/accelerate_configs/single_gpu.yaml (4:16) duplicated block id: 348 size: 13 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1010:1038) - trl/trainer/cpo_trainer.py (697:727) duplicated block id: 349 size: 13 cleaned lines of code in 2 files: - trl/accelerate_configs/zero1.yaml (8:20) - trl/accelerate_configs/zero2.yaml (9:21) duplicated block id: 350 size: 12 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (134:145) - trl/trainer/xpo_trainer.py (134:145) duplicated block id: 351 size: 12 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (869:881) - trl/trainer/dpo_trainer.py (1674:1685) duplicated block id: 352 size: 12 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (130:147) - trl/trainer/reward_trainer.py (161:178) duplicated block id: 353 size: 12 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1752:1768) - trl/trainer/orpo_trainer.py (899:915) duplicated block id: 354 size: 12 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (873:885) - trl/trainer/dpo_trainer.py (865:877) duplicated block id: 355 size: 12 cleaned lines of code in 2 files: - scripts/generate_toolcall_dataset.py (22:44) - scripts/generate_zen_dataset.py (21:43) duplicated block id: 356 size: 12 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1824:1850) - trl/trainer/kto_trainer.py (1617:1643) duplicated block id: 357 size: 12 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1424:1450) - trl/trainer/dpo_trainer.py (1824:1850) duplicated block id: 358 size: 12 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (865:877) - trl/trainer/kto_trainer.py (809:821) duplicated block id: 359 size: 11 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (591:605) - trl/trainer/sft_trainer.py (612:626) duplicated block id: 360 size: 11 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp2.yaml (15:25) - trl/accelerate_configs/zero3.yaml (12:22) duplicated block id: 361 size: 11 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1494:1505) - trl/trainer/orpo_trainer.py (869:880) duplicated block id: 362 size: 11 cleaned lines of code in 2 files: - trl/accelerate_configs/single_gpu.yaml (6:16) - trl/accelerate_configs/zero1.yaml (10:20) duplicated block id: 363 size: 11 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (572:582) - trl/trainer/orpo_trainer.py (293:303) duplicated block id: 364 size: 11 cleaned lines of code in 2 files: - trl/accelerate_configs/multi_gpu.yaml (6:16) - trl/accelerate_configs/zero1.yaml (10:20) duplicated block id: 365 size: 11 cleaned lines of code in 2 files: - trl/scripts/kto.py (104:120) - trl/scripts/sft.py (122:137) duplicated block id: 366 size: 11 cleaned lines of code in 2 files: - trl/scripts/grpo.py (104:120) - trl/scripts/sft.py (122:137) duplicated block id: 367 size: 11 cleaned lines of code in 2 files: - trl/accelerate_configs/multi_gpu.yaml (6:16) - trl/accelerate_configs/zero2.yaml (11:21) duplicated block id: 368 size: 11 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1302:1312) - trl/trainer/orpo_trainer.py (869:880) duplicated block id: 369 size: 11 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (895:906) - trl/trainer/kto_trainer.py (1494:1505) duplicated block id: 370 size: 11 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp1.yaml (18:28) - trl/accelerate_configs/zero3.yaml (12:22) duplicated block id: 371 size: 11 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp1.yaml (18:28) - trl/accelerate_configs/fsdp2.yaml (15:25) duplicated block id: 372 size: 11 cleaned lines of code in 2 files: - trl/trainer/alignprop_config.py (181:192) - trl/trainer/ddpo_config.py (288:299) duplicated block id: 373 size: 11 cleaned lines of code in 2 files: - trl/accelerate_configs/single_gpu.yaml (6:16) - trl/accelerate_configs/zero2.yaml (11:21) duplicated block id: 374 size: 11 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1262:1273) - trl/trainer/dpo_trainer.py (1674:1684) duplicated block id: 375 size: 11 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1302:1312) - trl/trainer/cpo_trainer.py (895:906) duplicated block id: 376 size: 11 cleaned lines of code in 2 files: - trl/scripts/grpo.py (104:120) - trl/scripts/kto.py (104:120) duplicated block id: 377 size: 11 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1674:1684) - trl/trainer/kto_trainer.py (1454:1465) duplicated block id: 378 size: 11 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (616:628) - trl/trainer/bco_trainer.py (644:656) duplicated block id: 379 size: 10 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (36:45) - trl/trainer/dpo_trainer.py (38:47) duplicated block id: 380 size: 10 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (164:176) - trl/trainer/dpo_trainer.py (555:567) duplicated block id: 381 size: 10 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (423:435) - trl/trainer/dpo_trainer.py (555:567) duplicated block id: 382 size: 10 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (555:567) - trl/trainer/kto_trainer.py (408:420) duplicated block id: 383 size: 10 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (227:238) - trl/trainer/xpo_trainer.py (212:223) duplicated block id: 384 size: 10 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (555:567) - trl/trainer/orpo_trainer.py (168:180) duplicated block id: 385 size: 10 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (441:450) - trl/trainer/online_dpo_trainer.py (298:307) duplicated block id: 386 size: 10 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1297:1310) - trl/trainer/dpo_trainer.py (1697:1711) duplicated block id: 387 size: 10 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (62:75) - trl/trainer/cpo_trainer.py (56:70) duplicated block id: 388 size: 10 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1052:1061) - trl/trainer/kto_trainer.py (1236:1245) duplicated block id: 389 size: 10 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (62:75) - trl/trainer/orpo_trainer.py (57:71) duplicated block id: 390 size: 10 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (230:241) - trl/trainer/ddpo_trainer.py (535:544) duplicated block id: 391 size: 10 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (260:272) - trl/trainer/kto_trainer.py (511:523) duplicated block id: 392 size: 10 cleaned lines of code in 2 files: - trl/trainer/xpo_trainer.py (332:343) - trl/trainer/xpo_trainer.py (393:404) duplicated block id: 393 size: 10 cleaned lines of code in 2 files: - trl/models/modeling_value_head.py (174:197) - trl/models/modeling_value_head.py (419:434) duplicated block id: 394 size: 10 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (308:317) - trl/trainer/kto_trainer.py (567:576) duplicated block id: 395 size: 10 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (308:317) - trl/trainer/orpo_trainer.py (294:303) duplicated block id: 396 size: 10 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (415:425) - trl/trainer/orpo_trainer.py (295:305) duplicated block id: 397 size: 10 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1058:1067) - trl/trainer/kto_trainer.py (1236:1245) duplicated block id: 398 size: 10 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (526:538) - trl/trainer/cpo_trainer.py (260:272) duplicated block id: 399 size: 10 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (567:576) - trl/trainer/orpo_trainer.py (294:303) duplicated block id: 400 size: 10 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (573:582) - trl/trainer/kto_trainer.py (567:576) duplicated block id: 401 size: 10 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (210:221) - trl/trainer/rloo_trainer.py (139:148) duplicated block id: 402 size: 10 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (540:552) - trl/trainer/kto_trainer.py (525:537) duplicated block id: 403 size: 10 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (573:582) - trl/trainer/cpo_trainer.py (308:317) duplicated block id: 404 size: 10 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1697:1711) - trl/trainer/kto_trainer.py (1489:1503) duplicated block id: 405 size: 9 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (365:380) - trl/trainer/dpo_trainer.py (452:467) duplicated block id: 406 size: 9 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (219:227) - trl/trainer/ppo_config.py (78:86) duplicated block id: 407 size: 9 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (35:43) - trl/trainer/orpo_trainer.py (35:43) duplicated block id: 408 size: 9 cleaned lines of code in 2 files: - trl/trainer/online_dpo_config.py (169:177) - trl/trainer/rloo_config.py (106:114) duplicated block id: 409 size: 9 cleaned lines of code in 2 files: - trl/trainer/ppo_config.py (24:78) - trl/trainer/rloo_config.py (23:70) duplicated block id: 410 size: 9 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (199:207) - trl/trainer/orpo_config.py (146:154) duplicated block id: 411 size: 9 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (309:317) - trl/trainer/dpo_trainer.py (415:423) duplicated block id: 412 size: 9 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (513:523) - trl/trainer/orpo_trainer.py (261:271) duplicated block id: 413 size: 9 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (415:423) - trl/trainer/kto_trainer.py (568:576) duplicated block id: 414 size: 9 cleaned lines of code in 2 files: - trl/trainer/online_dpo_config.py (169:177) - trl/trainer/ppo_config.py (127:135) duplicated block id: 415 size: 9 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (574:582) - trl/trainer/dpo_trainer.py (415:423) duplicated block id: 416 size: 9 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (390:399) - trl/trainer/kto_trainer.py (375:384) duplicated block id: 417 size: 9 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1544:1553) - trl/trainer/orpo_trainer.py (899:909) duplicated block id: 418 size: 9 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (365:374) - trl/trainer/ddpo_trainer.py (464:473) duplicated block id: 419 size: 9 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (340:348) - trl/trainer/kto_config.py (222:230) duplicated block id: 420 size: 9 cleaned lines of code in 2 files: - trl/models/modeling_sd_base.py (444:452) - trl/models/modeling_sd_base.py (683:691) duplicated block id: 421 size: 9 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (528:538) - trl/trainer/orpo_trainer.py (261:271) duplicated block id: 422 size: 9 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1702:1711) - trl/trainer/orpo_trainer.py (869:878) duplicated block id: 423 size: 9 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (185:197) - trl/trainer/rloo_trainer.py (116:128) duplicated block id: 424 size: 9 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (984:993) - trl/trainer/kto_trainer.py (952:960) duplicated block id: 425 size: 9 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1351:1360) - trl/trainer/orpo_trainer.py (899:909) duplicated block id: 426 size: 9 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1195:1203) - trl/trainer/kto_trainer.py (1390:1398) duplicated block id: 427 size: 9 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (376:384) - trl/trainer/sft_trainer.py (403:411) duplicated block id: 428 size: 9 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (118:126) - trl/trainer/dpo_config.py (347:355) duplicated block id: 429 size: 9 cleaned lines of code in 2 files: - trl/trainer/online_dpo_config.py (124:132) - trl/trainer/utils.py (1141:1149) duplicated block id: 430 size: 9 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (86:94) - trl/trainer/online_dpo_trainer.py (300:308) duplicated block id: 431 size: 9 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (895:904) - trl/trainer/dpo_trainer.py (1702:1711) duplicated block id: 432 size: 9 cleaned lines of code in 2 files: - trl/trainer/ppo_config.py (127:135) - trl/trainer/rloo_config.py (106:114) duplicated block id: 433 size: 9 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (36:44) - trl/trainer/sft_trainer.py (31:39) duplicated block id: 434 size: 9 cleaned lines of code in 2 files: - trl/models/modeling_sd_base.py (461:469) - trl/models/modeling_sd_base.py (700:708) duplicated block id: 435 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (38:45) - trl/trainer/orpo_trainer.py (35:42) duplicated block id: 436 size: 8 cleaned lines of code in 2 files: - trl/trainer/callbacks.py (365:372) - trl/trainer/callbacks.py (481:488) duplicated block id: 437 size: 8 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1573:1580) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 438 size: 8 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (806:813) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 439 size: 8 cleaned lines of code in 2 files: - trl/trainer/orpo_config.py (154:163) - trl/trainer/prm_config.py (105:114) duplicated block id: 440 size: 8 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (718:726) - trl/trainer/rloo_trainer.py (599:607) duplicated block id: 441 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp1.yaml (21:28) - trl/accelerate_configs/zero2.yaml (14:21) duplicated block id: 442 size: 8 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (30:37) - trl/trainer/sft_trainer.py (35:42) duplicated block id: 443 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (901:909) - trl/trainer/kto_trainer.py (1522:1530) duplicated block id: 444 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1329:1337) - trl/trainer/orpo_trainer.py (875:883) duplicated block id: 445 size: 8 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (537:546) - trl/trainer/orpo_trainer.py (157:166) duplicated block id: 446 size: 8 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1160:1169) - trl/trainer/dpo_trainer.py (1407:1416) duplicated block id: 447 size: 8 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1916:1923) - trl/trainer/iterative_sft_trainer.py (513:520) duplicated block id: 448 size: 8 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (451:458) - trl/trainer/iterative_sft_trainer.py (513:520) duplicated block id: 449 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/single_gpu.yaml (9:16) - trl/accelerate_configs/zero3.yaml (15:22) duplicated block id: 450 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (38:45) - trl/trainer/cpo_trainer.py (35:42) duplicated block id: 451 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (511:519) - trl/trainer/kto_trainer.py (496:504) duplicated block id: 452 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (274:284) - trl/trainer/kto_trainer.py (525:535) duplicated block id: 453 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (915:936) - trl/trainer/dpo_trainer.py (808:829) duplicated block id: 454 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/zero2.yaml (14:21) - trl/accelerate_configs/zero3.yaml (15:22) duplicated block id: 455 size: 8 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (357:365) - trl/trainer/orpo_trainer.py (139:147) duplicated block id: 456 size: 8 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (513:520) - trl/trainer/ppo_trainer.py (806:813) duplicated block id: 457 size: 8 cleaned lines of code in 2 files: - trl/mergekit_utils.py (175:182) - trl/mergekit_utils.py (220:227) duplicated block id: 458 size: 8 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1916:1923) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 459 size: 8 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (279:286) - trl/trainer/sft_config.py (194:201) duplicated block id: 460 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp2.yaml (18:25) - trl/accelerate_configs/single_gpu.yaml (9:16) duplicated block id: 461 size: 8 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (355:362) - trl/trainer/iterative_sft_trainer.py (513:520) duplicated block id: 462 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (39:46) - trl/trainer/sft_trainer.py (33:40) duplicated block id: 463 size: 8 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1476:1487) - trl/trainer/sft_trainer.py (866:877) duplicated block id: 464 size: 8 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (513:520) - trl/trainer/kto_trainer.py (1722:1729) duplicated block id: 465 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp1.yaml (21:28) - trl/accelerate_configs/single_gpu.yaml (9:16) duplicated block id: 466 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/multi_gpu.yaml (9:16) - trl/accelerate_configs/zero3.yaml (15:22) duplicated block id: 467 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (998:1006) - trl/trainer/kto_trainer.py (978:986) duplicated block id: 468 size: 8 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (513:520) - trl/trainer/xpo_trainer.py (581:588) duplicated block id: 469 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (231:238) - trl/trainer/orpo_trainer.py (235:242) duplicated block id: 470 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (153:162) - trl/trainer/dpo_trainer.py (537:546) duplicated block id: 471 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (183:192) - trl/trainer/prm_config.py (105:114) duplicated block id: 472 size: 8 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (59:66) - trl/trainer/orpo_trainer.py (57:64) duplicated block id: 473 size: 8 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (443:450) - trl/trainer/gkd_trainer.py (86:93) duplicated block id: 474 size: 8 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (37:44) - trl/trainer/orpo_trainer.py (35:42) duplicated block id: 475 size: 8 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (38:45) - trl/trainer/orpo_trainer.py (36:43) duplicated block id: 476 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (372:380) - trl/trainer/orpo_trainer.py (139:147) duplicated block id: 477 size: 8 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (655:662) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 478 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp1.yaml (21:28) - trl/accelerate_configs/zero1.yaml (13:20) duplicated block id: 479 size: 8 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (513:520) - trl/trainer/nash_md_trainer.py (537:544) duplicated block id: 480 size: 8 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (342:350) - trl/trainer/ddpo_trainer.py (454:461) duplicated block id: 481 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp2.yaml (18:25) - trl/accelerate_configs/multi_gpu.yaml (9:16) duplicated block id: 482 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (176:183) - trl/trainer/kto_config.py (200:207) duplicated block id: 483 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (540:550) - trl/trainer/orpo_trainer.py (273:283) duplicated block id: 484 size: 8 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (592:599) - trl/trainer/rloo_trainer.py (498:505) duplicated block id: 485 size: 8 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (537:544) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 486 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (38:45) - trl/trainer/kto_trainer.py (37:44) duplicated block id: 487 size: 8 cleaned lines of code in 2 files: - trl/trainer/reward_trainer.py (419:426) - trl/trainer/rloo_trainer.py (702:709) duplicated block id: 488 size: 8 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (512:519) - trl/trainer/sft_trainer.py (527:534) duplicated block id: 489 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (286:293) - trl/trainer/kto_trainer.py (540:547) duplicated block id: 490 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (35:42) - trl/trainer/kto_trainer.py (37:44) duplicated block id: 491 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (132:139) - trl/trainer/cpo_config.py (157:164) duplicated block id: 492 size: 8 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (355:362) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 493 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1329:1337) - trl/trainer/cpo_trainer.py (901:909) duplicated block id: 494 size: 8 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (1573:1580) - trl/trainer/iterative_sft_trainer.py (513:520) duplicated block id: 495 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (135:143) - trl/trainer/orpo_trainer.py (139:147) duplicated block id: 496 size: 8 cleaned lines of code in 2 files: - trl/trainer/reward_trainer.py (419:426) - trl/trainer/xpo_trainer.py (581:588) duplicated block id: 497 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (372:380) - trl/trainer/kto_trainer.py (357:365) duplicated block id: 498 size: 8 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (513:520) - trl/trainer/orpo_trainer.py (1079:1086) duplicated block id: 499 size: 8 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1522:1530) - trl/trainer/orpo_trainer.py (875:883) duplicated block id: 500 size: 8 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (282:289) - trl/trainer/xpo_trainer.py (268:275) duplicated block id: 501 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp1.yaml (21:28) - trl/accelerate_configs/multi_gpu.yaml (9:16) duplicated block id: 502 size: 8 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (525:535) - trl/trainer/orpo_trainer.py (273:283) duplicated block id: 503 size: 8 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (764:772) - trl/trainer/online_dpo_trainer.py (367:375) duplicated block id: 504 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1102:1109) - trl/trainer/iterative_sft_trainer.py (513:520) duplicated block id: 505 size: 8 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (513:520) - trl/trainer/rloo_trainer.py (702:709) duplicated block id: 506 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp2.yaml (18:25) - trl/accelerate_configs/zero1.yaml (13:20) duplicated block id: 507 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (1102:1109) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 508 size: 8 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (199:206) - trl/trainer/rloo_trainer.py (132:139) duplicated block id: 509 size: 8 cleaned lines of code in 2 files: - trl/trainer/ddpo_trainer.py (655:662) - trl/trainer/iterative_sft_trainer.py (513:520) duplicated block id: 510 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (372:380) - trl/trainer/cpo_trainer.py (135:143) duplicated block id: 511 size: 8 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (182:189) - trl/trainer/orpo_config.py (140:147) duplicated block id: 512 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1529:1536) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 513 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/zero1.yaml (13:20) - trl/accelerate_configs/zero3.yaml (15:22) duplicated block id: 514 size: 8 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (513:520) - trl/trainer/online_dpo_trainer.py (795:802) duplicated block id: 515 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp2.yaml (18:25) - trl/accelerate_configs/zero2.yaml (14:21) duplicated block id: 516 size: 8 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (451:458) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 517 size: 8 cleaned lines of code in 2 files: - trl/trainer/grpo_trainer.py (416:423) - trl/trainer/sft_trainer.py (527:534) duplicated block id: 518 size: 8 cleaned lines of code in 2 files: - trl/models/utils.py (218:225) - trl/models/utils.py (251:258) duplicated block id: 519 size: 8 cleaned lines of code in 2 files: - trl/trainer/callbacks.py (143:153) - trl/trainer/callbacks.py (204:211) duplicated block id: 520 size: 8 cleaned lines of code in 2 files: - trl/accelerate_configs/fsdp1.yaml (1:8) - trl/accelerate_configs/fsdp2.yaml (2:9) duplicated block id: 521 size: 8 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (795:802) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 522 size: 8 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1722:1729) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 523 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (62:69) - trl/trainer/kto_trainer.py (59:66) duplicated block id: 524 size: 8 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (512:519) - trl/trainer/grpo_trainer.py (416:423) duplicated block id: 525 size: 8 cleaned lines of code in 2 files: - trl/mergekit_utils.py (131:138) - trl/mergekit_utils.py (220:227) duplicated block id: 526 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (540:550) - trl/trainer/cpo_trainer.py (274:284) duplicated block id: 527 size: 8 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (1079:1086) - trl/trainer/reward_trainer.py (419:426) duplicated block id: 528 size: 8 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (808:829) - trl/trainer/kto_trainer.py (861:882) duplicated block id: 529 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (135:143) - trl/trainer/kto_trainer.py (357:365) duplicated block id: 530 size: 8 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1529:1536) - trl/trainer/iterative_sft_trainer.py (513:520) duplicated block id: 531 size: 8 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (56:63) - trl/trainer/kto_trainer.py (59:66) duplicated block id: 532 size: 7 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (305:313) - trl/trainer/orpo_trainer.py (342:350) duplicated block id: 533 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (363:370) - trl/trainer/kto_trainer.py (348:355) duplicated block id: 534 size: 7 cleaned lines of code in 2 files: - trl/models/__init__.py (32:39) - trl/trainer/__init__.py (83:89) duplicated block id: 535 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (441:447) - trl/trainer/kto_trainer.py (738:744) duplicated block id: 536 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (501:508) - trl/trainer/kto_trainer.py (486:493) duplicated block id: 537 size: 7 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (193:199) - trl/trainer/sft_trainer.py (498:504) duplicated block id: 538 size: 7 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (298:304) - trl/trainer/reward_trainer.py (247:253) duplicated block id: 539 size: 7 cleaned lines of code in 2 files: - trl/trainer/utils.py (520:526) - trl/trainer/utils.py (537:543) duplicated block id: 540 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (457:466) - trl/trainer/cpo_trainer.py (177:186) duplicated block id: 541 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (671:677) - trl/trainer/online_dpo_trainer.py (298:304) duplicated block id: 542 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (457:466) - trl/trainer/kto_trainer.py (421:430) duplicated block id: 543 size: 7 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (122:128) - trl/trainer/prm_trainer.py (97:103) duplicated block id: 544 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (36:42) - trl/trainer/reward_trainer.py (30:36) duplicated block id: 545 size: 7 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (26:32) - trl/trainer/online_dpo_trainer.py (32:38) duplicated block id: 546 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (728:738) - trl/trainer/kto_trainer.py (1035:1045) duplicated block id: 547 size: 7 cleaned lines of code in 2 files: - trl/models/activation_offloading.py (194:202) - trl/models/activation_offloading.py (229:237) duplicated block id: 548 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1205:1211) - trl/trainer/dpo_trainer.py (1220:1226) duplicated block id: 549 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (436:445) - trl/trainer/kto_trainer.py (442:451) duplicated block id: 550 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (486:493) - trl/trainer/grpo_trainer.py (713:720) duplicated block id: 551 size: 7 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (122:128) - trl/trainer/reward_trainer.py (91:97) duplicated block id: 552 size: 7 cleaned lines of code in 2 files: - trl/scripts/grpo.py (124:132) - trl/scripts/kto.py (124:132) duplicated block id: 553 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (671:677) - trl/trainer/sft_trainer.py (498:504) duplicated block id: 554 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1537:1543) - trl/trainer/orpo_trainer.py (887:893) duplicated block id: 555 size: 7 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (840:846) - trl/trainer/reward_trainer.py (265:271) duplicated block id: 556 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (436:445) - trl/trainer/orpo_trainer.py (202:211) duplicated block id: 557 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (38:44) - trl/trainer/kto_trainer.py (38:44) duplicated block id: 558 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (436:445) - trl/trainer/cpo_trainer.py (198:207) duplicated block id: 559 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (441:447) - trl/trainer/prm_trainer.py (193:199) duplicated block id: 560 size: 7 cleaned lines of code in 2 files: - trl/trainer/reward_trainer.py (30:36) - trl/trainer/sft_trainer.py (33:39) duplicated block id: 561 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (457:466) - trl/trainer/orpo_trainer.py (181:190) duplicated block id: 562 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (36:42) - trl/trainer/sft_trainer.py (33:39) duplicated block id: 563 size: 7 cleaned lines of code in 2 files: - scripts/generate_tiny_models.py (150:156) - scripts/generate_tiny_models.py (162:168) duplicated block id: 564 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1262:1268) - trl/trainer/reward_trainer.py (265:271) duplicated block id: 565 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (177:186) - trl/trainer/orpo_trainer.py (202:211) duplicated block id: 566 size: 7 cleaned lines of code in 2 files: - trl/trainer/reward_trainer.py (247:253) - trl/trainer/sft_trainer.py (498:504) duplicated block id: 567 size: 7 cleaned lines of code in 2 files: - trl/scripts/dpo.py (153:161) - trl/scripts/grpo.py (124:132) duplicated block id: 568 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (436:445) - trl/trainer/bco_trainer.py (457:466) duplicated block id: 569 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1062:1069) - trl/trainer/orpo_trainer.py (723:731) duplicated block id: 570 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (118:124) - trl/trainer/reward_trainer.py (91:97) duplicated block id: 571 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (815:822) - trl/trainer/dpo_trainer.py (1606:1613) duplicated block id: 572 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1606:1613) - trl/trainer/orpo_trainer.py (785:792) duplicated block id: 573 size: 7 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (298:304) - trl/trainer/sft_trainer.py (498:504) duplicated block id: 574 size: 7 cleaned lines of code in 2 files: - trl/__init__.py (101:108) - trl/models/__init__.py (32:39) duplicated block id: 575 size: 7 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (416:422) - trl/trainer/rloo_trainer.py (309:315) duplicated block id: 576 size: 7 cleaned lines of code in 2 files: - trl/trainer/utils.py (153:159) - trl/trainer/utils.py (180:186) duplicated block id: 577 size: 7 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (361:367) - trl/trainer/reward_trainer.py (419:425) duplicated block id: 578 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (843:849) - trl/trainer/dpo_trainer.py (1644:1650) duplicated block id: 579 size: 7 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (298:304) - trl/trainer/prm_trainer.py (193:199) duplicated block id: 580 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (671:677) - trl/trainer/dpo_trainer.py (441:447) duplicated block id: 581 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (421:430) - trl/trainer/kto_trainer.py (442:451) duplicated block id: 582 size: 7 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (637:643) - trl/trainer/rloo_trainer.py (539:545) duplicated block id: 583 size: 7 cleaned lines of code in 2 files: - trl/__init__.py (101:108) - trl/trainer/__init__.py (83:89) duplicated block id: 584 size: 7 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (305:313) - trl/trainer/reward_trainer.py (255:263) duplicated block id: 585 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (360:367) - trl/trainer/kto_trainer.py (379:386) duplicated block id: 586 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1745:1751) - trl/trainer/orpo_trainer.py (887:893) duplicated block id: 587 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (341:347) - trl/trainer/orpo_trainer.py (325:331) duplicated block id: 588 size: 7 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (708:714) - trl/trainer/rloo_trainer.py (589:595) duplicated block id: 589 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (822:828) - trl/trainer/bco_trainer.py (895:901) duplicated block id: 590 size: 7 cleaned lines of code in 2 files: - trl/models/modeling_base.py (220:226) - trl/models/modeling_base.py (233:239) duplicated block id: 591 size: 7 cleaned lines of code in 2 files: - trl/trainer/callbacks.py (304:310) - trl/trainer/callbacks.py (482:488) duplicated block id: 592 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1454:1460) - trl/trainer/reward_trainer.py (265:271) duplicated block id: 593 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (759:767) - trl/trainer/kto_trainer.py (1056:1063) duplicated block id: 594 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (354:360) - trl/trainer/sft_trainer.py (498:504) duplicated block id: 595 size: 7 cleaned lines of code in 2 files: - trl/trainer/callbacks.py (304:310) - trl/trainer/callbacks.py (366:372) duplicated block id: 596 size: 7 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (181:190) - trl/trainer/orpo_trainer.py (202:211) duplicated block id: 597 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (198:207) - trl/trainer/orpo_trainer.py (181:190) duplicated block id: 598 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1056:1063) - trl/trainer/orpo_trainer.py (723:731) duplicated block id: 599 size: 7 cleaned lines of code in 2 files: - trl/models/modeling_sd_base.py (516:523) - trl/models/modeling_sd_base.py (780:787) duplicated block id: 600 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1344:1350) - trl/trainer/orpo_trainer.py (887:893) duplicated block id: 601 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (421:430) - trl/trainer/orpo_trainer.py (202:211) duplicated block id: 602 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1043:1053) - trl/trainer/cpo_trainer.py (728:738) duplicated block id: 603 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (441:447) - trl/trainer/orpo_trainer.py (334:340) duplicated block id: 604 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (39:45) - trl/trainer/dpo_trainer.py (38:44) duplicated block id: 605 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (441:447) - trl/trainer/sft_trainer.py (498:504) duplicated block id: 606 size: 7 cleaned lines of code in 2 files: - trl/__init__.py (195:204) - trl/trainer/__init__.py (151:160) duplicated block id: 607 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (38:44) - trl/trainer/reward_trainer.py (30:36) duplicated block id: 608 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (38:44) - trl/trainer/reward_trainer.py (30:36) duplicated block id: 609 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (554:560) - trl/trainer/cpo_trainer.py (286:292) duplicated block id: 610 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (442:451) - trl/trainer/orpo_trainer.py (181:190) duplicated block id: 611 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (354:360) - trl/trainer/online_dpo_trainer.py (298:304) duplicated block id: 612 size: 7 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (36:42) - trl/trainer/sft_trainer.py (33:39) duplicated block id: 613 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (869:875) - trl/trainer/reward_trainer.py (265:271) duplicated block id: 614 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (375:382) - trl/trainer/bco_trainer.py (394:401) duplicated block id: 615 size: 7 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (169:175) - trl/trainer/prm_trainer.py (185:191) duplicated block id: 616 size: 7 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (334:340) - trl/trainer/sft_trainer.py (498:504) duplicated block id: 617 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (39:45) - trl/trainer/reward_trainer.py (30:36) duplicated block id: 618 size: 7 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (298:304) - trl/trainer/orpo_trainer.py (334:340) duplicated block id: 619 size: 7 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (305:313) - trl/trainer/prm_trainer.py (201:209) duplicated block id: 620 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1601:1609) - trl/trainer/kto_trainer.py (1337:1345) duplicated block id: 621 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (198:207) - trl/trainer/kto_trainer.py (421:430) duplicated block id: 622 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (777:783) - trl/trainer/dpo_trainer.py (831:837) duplicated block id: 623 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (354:360) - trl/trainer/dpo_trainer.py (441:447) duplicated block id: 624 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (38:44) - trl/trainer/sft_trainer.py (33:39) duplicated block id: 625 size: 7 cleaned lines of code in 2 files: - trl/scripts/dpo.py (153:161) - trl/scripts/kto.py (124:132) duplicated block id: 626 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1674:1680) - trl/trainer/reward_trainer.py (265:271) duplicated block id: 627 size: 7 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (36:42) - trl/trainer/reward_trainer.py (30:36) duplicated block id: 628 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (738:744) - trl/trainer/sft_trainer.py (498:504) duplicated block id: 629 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (322:340) - trl/trainer/orpo_trainer.py (305:323) duplicated block id: 630 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (822:828) - trl/trainer/kto_trainer.py (831:837) duplicated block id: 631 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1062:1069) - trl/trainer/cpo_trainer.py (759:767) duplicated block id: 632 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (177:186) - trl/trainer/cpo_trainer.py (198:207) duplicated block id: 633 size: 7 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (554:560) - trl/trainer/kto_trainer.py (540:546) duplicated block id: 634 size: 7 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (738:744) - trl/trainer/online_dpo_trainer.py (298:304) duplicated block id: 635 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (177:186) - trl/trainer/kto_trainer.py (442:451) duplicated block id: 636 size: 7 cleaned lines of code in 2 files: - trl/trainer/prm_trainer.py (31:37) - trl/trainer/reward_trainer.py (32:38) duplicated block id: 637 size: 7 cleaned lines of code in 2 files: - scripts/generate_tiny_models.py (135:141) - scripts/generate_tiny_models.py (179:185) duplicated block id: 638 size: 7 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (448:456) - trl/trainer/rloo_trainer.py (339:347) duplicated block id: 639 size: 7 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_trainer.py (513:519) - trl/trainer/prm_trainer.py (361:367) duplicated block id: 640 size: 7 cleaned lines of code in 2 files: - trl/models/__init__.py (58:65) - trl/trainer/__init__.py (151:160) duplicated block id: 641 size: 7 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (441:447) - trl/trainer/reward_trainer.py (247:253) duplicated block id: 642 size: 7 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (118:124) - trl/trainer/prm_trainer.py (97:103) duplicated block id: 643 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1344:1349) - trl/trainer/reward_trainer.py (298:303) duplicated block id: 644 size: 6 cleaned lines of code in 2 files: - trl/trainer/iterative_sft_config.py (67:74) - trl/trainer/sft_config.py (124:131) duplicated block id: 645 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (423:430) - trl/trainer/sft_trainer.py (612:619) duplicated block id: 646 size: 6 cleaned lines of code in 2 files: - trl/models/modeling_value_head.py (156:163) - trl/models/modeling_value_head.py (404:410) duplicated block id: 647 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (438:445) - trl/trainer/dpo_trainer.py (591:598) duplicated block id: 648 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1745:1750) - trl/trainer/reward_trainer.py (298:303) duplicated block id: 649 size: 6 cleaned lines of code in 2 files: - trl/__init__.py (199:204) - trl/models/__init__.py (34:39) duplicated block id: 650 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (845:852) - trl/trainer/kto_trainer.py (898:905) duplicated block id: 651 size: 6 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (183:190) - trl/trainer/sft_trainer.py (612:619) duplicated block id: 652 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (937:942) - trl/trainer/kto_trainer.py (964:969) duplicated block id: 653 size: 6 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (67:72) - trl/trainer/prm_trainer.py (97:102) duplicated block id: 654 size: 6 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (276:281) - trl/trainer/online_dpo_config.py (169:174) duplicated block id: 655 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1537:1542) - trl/trainer/reward_trainer.py (298:303) duplicated block id: 656 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (901:906) - trl/trainer/kto_trainer.py (1514:1519) duplicated block id: 657 size: 6 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (157:162) - trl/trainer/xpo_trainer.py (159:165) duplicated block id: 658 size: 6 cleaned lines of code in 2 files: - trl/scripts/dpo.py (127:132) - trl/scripts/kto.py (102:107) duplicated block id: 659 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (444:451) - trl/trainer/sft_trainer.py (612:619) duplicated block id: 660 size: 6 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (67:72) - trl/trainer/reward_trainer.py (91:96) duplicated block id: 661 size: 6 cleaned lines of code in 2 files: - trl/trainer/callbacks.py (345:350) - trl/trainer/callbacks.py (399:404) duplicated block id: 662 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1307:1312) - trl/trainer/kto_trainer.py (1514:1519) duplicated block id: 663 size: 6 cleaned lines of code in 2 files: - trl/models/__init__.py (34:39) - trl/trainer/__init__.py (155:160) duplicated block id: 664 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1307:1312) - trl/trainer/kto_trainer.py (1522:1527) duplicated block id: 665 size: 6 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (481:486) - trl/trainer/rloo_trainer.py (378:383) duplicated block id: 666 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (184:189) - trl/trainer/orpo_config.py (153:158) duplicated block id: 667 size: 6 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (306:313) - trl/trainer/xpo_trainer.py (292:299) duplicated block id: 668 size: 6 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (276:281) - trl/trainer/ppo_config.py (127:132) duplicated block id: 669 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (200:207) - trl/trainer/dpo_trainer.py (591:598) duplicated block id: 670 size: 6 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (123:128) - trl/trainer/online_dpo_trainer.py (149:154) duplicated block id: 671 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (182:187) - trl/trainer/dpo_config.py (245:252) duplicated block id: 672 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1205:1210) - trl/trainer/kto_trainer.py (1401:1406) duplicated block id: 673 size: 6 cleaned lines of code in 2 files: - trl/trainer/grpo_config.py (276:281) - trl/trainer/rloo_config.py (106:111) duplicated block id: 674 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (913:918) - trl/trainer/reward_trainer.py (298:303) duplicated block id: 675 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (233:238) - trl/trainer/reward_config.py (79:84) duplicated block id: 676 size: 6 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (596:601) - trl/trainer/orpo_trainer.py (606:611) duplicated block id: 677 size: 6 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (474:479) - trl/trainer/rloo_trainer.py (370:375) duplicated block id: 678 size: 6 cleaned lines of code in 2 files: - trl/models/__init__.py (34:39) - trl/models/__init__.py (60:65) duplicated block id: 679 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (184:189) - trl/trainer/dpo_config.py (245:252) duplicated block id: 680 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (213:218) - trl/trainer/online_dpo_config.py (147:152) duplicated block id: 681 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (978:984) - trl/trainer/kto_trainer.py (941:946) duplicated block id: 682 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (182:187) - trl/trainer/kto_config.py (213:218) duplicated block id: 683 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (343:348) - trl/trainer/orpo_trainer.py (128:133) duplicated block id: 684 size: 6 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (289:294) - trl/trainer/gkd_trainer.py (297:302) duplicated block id: 685 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1514:1519) - trl/trainer/kto_trainer.py (1522:1527) duplicated block id: 686 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (974:980) - trl/trainer/bco_trainer.py (989:995) duplicated block id: 687 size: 6 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (174:180) - trl/trainer/ddpo_trainer.py (183:189) duplicated block id: 688 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (179:186) - trl/trainer/dpo_trainer.py (591:598) duplicated block id: 689 size: 6 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (204:211) - trl/trainer/sft_trainer.py (612:619) duplicated block id: 690 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1321:1326) - trl/trainer/orpo_trainer.py (875:880) duplicated block id: 691 size: 6 cleaned lines of code in 2 files: - trl/trainer/callbacks.py (336:341) - trl/trainer/callbacks.py (408:413) duplicated block id: 692 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1708:1713) - trl/trainer/dpo_trainer.py (1730:1735) duplicated block id: 693 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1708:1713) - trl/trainer/dpo_trainer.py (1722:1727) duplicated block id: 694 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (461:467) - trl/trainer/orpo_trainer.py (349:355) duplicated block id: 695 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (140:145) - trl/trainer/orpo_config.py (114:119) duplicated block id: 696 size: 6 cleaned lines of code in 2 files: - trl/models/modeling_sd_base.py (483:488) - trl/models/modeling_sd_base.py (731:736) duplicated block id: 697 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (939:946) - trl/trainer/dpo_trainer.py (833:840) duplicated block id: 698 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1329:1334) - trl/trainer/kto_trainer.py (1500:1505) duplicated block id: 699 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1329:1334) - trl/trainer/kto_trainer.py (1514:1519) duplicated block id: 700 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (184:189) - trl/trainer/sft_config.py (155:160) duplicated block id: 701 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (200:207) - trl/trainer/sft_trainer.py (612:619) duplicated block id: 702 size: 6 cleaned lines of code in 2 files: - trl/trainer/orpo_config.py (153:158) - trl/trainer/sft_config.py (155:160) duplicated block id: 703 size: 6 cleaned lines of code in 2 files: - trl/trainer/callbacks.py (336:341) - trl/trainer/callbacks.py (345:350) duplicated block id: 704 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (202:209) - trl/trainer/sft_config.py (124:131) duplicated block id: 705 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1307:1312) - trl/trainer/bco_trainer.py (1329:1334) duplicated block id: 706 size: 6 cleaned lines of code in 2 files: - trl/__init__.py (103:108) - trl/models/__init__.py (60:65) duplicated block id: 707 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1307:1312) - trl/trainer/bco_trainer.py (1321:1326) duplicated block id: 708 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (179:186) - trl/trainer/sft_trainer.py (612:619) duplicated block id: 709 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (540:545) - trl/trainer/orpo_trainer.py (285:290) duplicated block id: 710 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (296:301) - trl/trainer/dpo_trainer.py (402:407) duplicated block id: 711 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (343:348) - trl/trainer/cpo_trainer.py (124:129) duplicated block id: 712 size: 6 cleaned lines of code in 2 files: - trl/scripts/dpo.py (101:106) - trl/scripts/kto.py (87:94) duplicated block id: 713 size: 6 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (149:154) - trl/trainer/xpo_trainer.py (123:128) duplicated block id: 714 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (184:189) - trl/trainer/cpo_config.py (182:187) duplicated block id: 715 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (897:904) - trl/trainer/dpo_trainer.py (779:786) duplicated block id: 716 size: 6 cleaned lines of code in 2 files: - trl/trainer/nash_md_trainer.py (25:30) - trl/trainer/xpo_trainer.py (25:30) duplicated block id: 717 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (651:656) - trl/trainer/kto_trainer.py (632:637) duplicated block id: 718 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1240:1245) - trl/trainer/orpo_trainer.py (723:729) duplicated block id: 719 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (591:598) - trl/trainer/kto_trainer.py (444:451) duplicated block id: 720 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (591:598) - trl/trainer/kto_trainer.py (423:430) duplicated block id: 721 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (118:123) - trl/trainer/gkd_trainer.py (67:72) duplicated block id: 722 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (245:252) - trl/trainer/orpo_config.py (153:158) duplicated block id: 723 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (213:218) - trl/trainer/orpo_config.py (153:158) duplicated block id: 724 size: 6 cleaned lines of code in 2 files: - trl/models/modeling_value_head.py (86:92) - trl/models/modeling_value_head.py (282:288) duplicated block id: 725 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (184:189) - trl/trainer/online_dpo_config.py (147:152) duplicated block id: 726 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (448:453) - trl/trainer/sft_trainer.py (506:511) duplicated block id: 727 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (233:238) - trl/trainer/prm_config.py (92:97) duplicated block id: 728 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (611:616) - trl/trainer/orpo_trainer.py (606:611) duplicated block id: 729 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (438:445) - trl/trainer/sft_trainer.py (612:619) duplicated block id: 730 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (611:616) - trl/trainer/cpo_trainer.py (621:626) duplicated block id: 731 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (182:187) - trl/trainer/sft_config.py (155:160) duplicated block id: 732 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (833:840) - trl/trainer/kto_trainer.py (885:892) duplicated block id: 733 size: 6 cleaned lines of code in 2 files: - trl/trainer/orpo_trainer.py (887:892) - trl/trainer/reward_trainer.py (298:303) duplicated block id: 734 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (143:148) - trl/trainer/prm_config.py (92:97) duplicated block id: 735 size: 6 cleaned lines of code in 2 files: - trl/trainer/__init__.py (84:89) - trl/trainer/__init__.py (155:160) duplicated block id: 736 size: 6 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (378:385) - trl/trainer/rloo_trainer.py (275:282) duplicated block id: 737 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (245:252) - trl/trainer/kto_config.py (213:218) duplicated block id: 738 size: 6 cleaned lines of code in 2 files: - trl/trainer/gkd_trainer.py (67:72) - trl/trainer/orpo_trainer.py (122:127) duplicated block id: 739 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (759:765) - trl/trainer/kto_trainer.py (1240:1245) duplicated block id: 740 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (591:598) - trl/trainer/orpo_trainer.py (204:211) duplicated block id: 741 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (591:598) - trl/trainer/orpo_trainer.py (183:190) duplicated block id: 742 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (382:388) - trl/trainer/kto_trainer.py (367:373) duplicated block id: 743 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (459:466) - trl/trainer/sft_trainer.py (612:619) duplicated block id: 744 size: 6 cleaned lines of code in 2 files: - trl/mergekit_utils.py (86:91) - trl/mergekit_utils.py (93:98) duplicated block id: 745 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (335:340) - trl/trainer/orpo_trainer.py (128:133) duplicated block id: 746 size: 6 cleaned lines of code in 2 files: - trl/models/__init__.py (60:65) - trl/trainer/__init__.py (84:89) duplicated block id: 747 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1178:1183) - trl/trainer/kto_trainer.py (1368:1373) duplicated block id: 748 size: 6 cleaned lines of code in 2 files: - trl/trainer/online_dpo_config.py (147:152) - trl/trainer/sft_config.py (155:160) duplicated block id: 749 size: 6 cleaned lines of code in 2 files: - trl/trainer/online_dpo_config.py (147:152) - trl/trainer/orpo_config.py (153:158) duplicated block id: 750 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (321:327) - trl/trainer/kto_trainer.py (470:476) duplicated block id: 751 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1321:1326) - trl/trainer/bco_trainer.py (1329:1334) duplicated block id: 752 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (657:662) - trl/trainer/kto_trainer.py (656:661) duplicated block id: 753 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (485:491) - trl/trainer/dpo_trainer.py (321:327) duplicated block id: 754 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (143:148) - trl/trainer/dpo_config.py (233:238) duplicated block id: 755 size: 6 cleaned lines of code in 2 files: - trl/__init__.py (103:108) - trl/__init__.py (199:204) duplicated block id: 756 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (41:46) - trl/trainer/iterative_sft_trainer.py (30:35) duplicated block id: 757 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (312:319) - trl/trainer/online_dpo_config.py (140:145) duplicated block id: 758 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (779:786) - trl/trainer/kto_trainer.py (833:840) duplicated block id: 759 size: 6 cleaned lines of code in 2 files: - trl/trainer/ppo_trainer.py (558:563) - trl/trainer/rloo_trainer.py (466:473) duplicated block id: 760 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (554:559) - trl/trainer/orpo_trainer.py (285:290) duplicated block id: 761 size: 6 cleaned lines of code in 2 files: - trl/trainer/alignprop_trainer.py (182:187) - trl/trainer/ddpo_trainer.py (194:199) duplicated block id: 762 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (929:935) - trl/trainer/kto_trainer.py (956:962) duplicated block id: 763 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1321:1326) - trl/trainer/cpo_trainer.py (901:906) duplicated block id: 764 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (182:187) - trl/trainer/online_dpo_config.py (147:152) duplicated block id: 765 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (245:252) - trl/trainer/sft_config.py (155:160) duplicated block id: 766 size: 6 cleaned lines of code in 2 files: - trl/trainer/callbacks.py (399:404) - trl/trainer/callbacks.py (408:413) duplicated block id: 767 size: 6 cleaned lines of code in 2 files: - trl/trainer/online_dpo_trainer.py (238:243) - trl/trainer/xpo_trainer.py (157:162) duplicated block id: 768 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (758:764) - trl/trainer/orpo_trainer.py (349:355) duplicated block id: 769 size: 6 cleaned lines of code in 2 files: - trl/__init__.py (199:204) - trl/trainer/__init__.py (84:89) duplicated block id: 770 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (614:621) - trl/trainer/kto_trainer.py (624:630) duplicated block id: 771 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (213:218) - trl/trainer/sft_config.py (155:160) duplicated block id: 772 size: 6 cleaned lines of code in 2 files: - trl/trainer/prm_config.py (92:97) - trl/trainer/reward_config.py (79:84) duplicated block id: 773 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (459:466) - trl/trainer/dpo_trainer.py (591:598) duplicated block id: 774 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_config.py (245:252) - trl/trainer/online_dpo_config.py (147:152) duplicated block id: 775 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (240:245) - trl/trainer/orpo_trainer.py (244:249) duplicated block id: 776 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_config.py (143:148) - trl/trainer/reward_config.py (79:84) duplicated block id: 777 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (1722:1727) - trl/trainer/dpo_trainer.py (1730:1735) duplicated block id: 778 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1500:1505) - trl/trainer/kto_trainer.py (1522:1527) duplicated block id: 779 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1500:1505) - trl/trainer/kto_trainer.py (1514:1519) duplicated block id: 780 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1514:1519) - trl/trainer/orpo_trainer.py (875:880) duplicated block id: 781 size: 6 cleaned lines of code in 2 files: - trl/accelerate_configs/zero2.yaml (1:6) - trl/accelerate_configs/zero3.yaml (1:6) duplicated block id: 782 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (691:697) - trl/trainer/orpo_trainer.py (349:355) duplicated block id: 783 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1321:1326) - trl/trainer/kto_trainer.py (1500:1505) duplicated block id: 784 size: 6 cleaned lines of code in 2 files: - trl/trainer/bco_trainer.py (1321:1326) - trl/trainer/kto_trainer.py (1522:1527) duplicated block id: 785 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (621:626) - trl/trainer/orpo_trainer.py (596:601) duplicated block id: 786 size: 6 cleaned lines of code in 2 files: - trl/trainer/dpo_trainer.py (791:796) - trl/trainer/dpo_trainer.py (845:850) duplicated block id: 787 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_trainer.py (1394:1399) - trl/trainer/kto_trainer.py (1402:1407) duplicated block id: 788 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_trainer.py (124:129) - trl/trainer/kto_trainer.py (335:340) duplicated block id: 789 size: 6 cleaned lines of code in 2 files: - trl/__init__.py (103:108) - trl/trainer/__init__.py (155:160) duplicated block id: 790 size: 6 cleaned lines of code in 2 files: - trl/trainer/kto_config.py (188:193) - trl/trainer/orpo_config.py (114:119) duplicated block id: 791 size: 6 cleaned lines of code in 2 files: - trl/trainer/cpo_config.py (140:145) - trl/trainer/kto_config.py (188:193)