|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.10031347962382445, |
|
"eval_steps": 500, |
|
"global_step": 128, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2e-05, |
|
"loss": 0.7469, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 4e-05, |
|
"loss": 0.7617, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 6e-05, |
|
"loss": 0.8527, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 8e-05, |
|
"loss": 0.7475, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.0001, |
|
"loss": 0.7094, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00012, |
|
"loss": 0.6652, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00014, |
|
"loss": 0.5645, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00016, |
|
"loss": 0.5129, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00018, |
|
"loss": 0.3689, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0002, |
|
"loss": 0.4651, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00019996456111234527, |
|
"loss": 0.3466, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0001998582695676762, |
|
"loss": 0.288, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.000199681200703075, |
|
"loss": 0.2641, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00019943348002101371, |
|
"loss": 0.1956, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00019911528310040074, |
|
"loss": 0.2055, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00019872683547213446, |
|
"loss": 0.2808, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00019826841245925212, |
|
"loss": 0.2246, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00019774033898178667, |
|
"loss": 0.2667, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.00019714298932647098, |
|
"loss": 0.2157, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0001964767868814516, |
|
"loss": 0.2702, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00019574220383620055, |
|
"loss": 0.3036, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00019493976084683813, |
|
"loss": 0.2306, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00019407002666710336, |
|
"loss": 0.2523, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00019313361774523385, |
|
"loss": 0.1678, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00019213119778704128, |
|
"loss": 0.1514, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00019106347728549135, |
|
"loss": 0.2651, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00018993121301712193, |
|
"loss": 0.2442, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00018873520750565718, |
|
"loss": 0.2395, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.00018747630845319612, |
|
"loss": 0.1471, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0001861554081393806, |
|
"loss": 0.2239, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0001847734427889671, |
|
"loss": 0.176, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0001833313919082515, |
|
"loss": 0.2475, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0001818302775908169, |
|
"loss": 0.286, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00018027116379309638, |
|
"loss": 0.0994, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00017865515558026428, |
|
"loss": 0.1781, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00017698339834299061, |
|
"loss": 0.2149, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00017525707698561385, |
|
"loss": 0.1176, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00017347741508630672, |
|
"loss": 0.2308, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00017164567402983152, |
|
"loss": 0.1913, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0001697631521134985, |
|
"loss": 0.1527, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00016783118362696163, |
|
"loss": 0.1628, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00016585113790650388, |
|
"loss": 0.1501, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00016382441836448202, |
|
"loss": 0.1326, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0001617524614946192, |
|
"loss": 0.1057, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00015963673585385016, |
|
"loss": 0.1666, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0001574787410214407, |
|
"loss": 0.1454, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00015528000653611935, |
|
"loss": 0.2029, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00015304209081197425, |
|
"loss": 0.2525, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.000150766580033884, |
|
"loss": 0.2038, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00014845508703326504, |
|
"loss": 0.2174, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0001461092501449326, |
|
"loss": 0.204, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00014373073204588556, |
|
"loss": 0.159, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00014132121857683783, |
|
"loss": 0.2731, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00013888241754733208, |
|
"loss": 0.1232, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00013641605752528224, |
|
"loss": 0.1696, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.00013392388661180303, |
|
"loss": 0.2264, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0001314076712021949, |
|
"loss": 0.2123, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0001288691947339621, |
|
"loss": 0.1561, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00012631025642275212, |
|
"loss": 0.1864, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0001237326699871115, |
|
"loss": 0.2353, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00012113826236296244, |
|
"loss": 0.2863, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00011852887240871145, |
|
"loss": 0.2241, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00011590634960190721, |
|
"loss": 0.1076, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00011327255272837221, |
|
"loss": 0.0993, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00011062934856473655, |
|
"loss": 0.2469, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00010797861055530831, |
|
"loss": 0.1613, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00010532221748421787, |
|
"loss": 0.2165, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00010266205214377748, |
|
"loss": 0.1614, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2062, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.733794785622253e-05, |
|
"loss": 0.2491, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 9.467778251578217e-05, |
|
"loss": 0.1994, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 9.202138944469168e-05, |
|
"loss": 0.1555, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 8.937065143526347e-05, |
|
"loss": 0.0907, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 8.672744727162781e-05, |
|
"loss": 0.0849, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 8.409365039809281e-05, |
|
"loss": 0.1289, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 8.147112759128859e-05, |
|
"loss": 0.1881, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 7.886173763703757e-05, |
|
"loss": 0.09, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 7.626733001288851e-05, |
|
"loss": 0.3259, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 7.368974357724789e-05, |
|
"loss": 0.1752, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 7.113080526603792e-05, |
|
"loss": 0.2569, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 6.859232879780515e-05, |
|
"loss": 0.118, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 6.607611338819697e-05, |
|
"loss": 0.1885, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 6.358394247471778e-05, |
|
"loss": 0.1382, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 6.111758245266794e-05, |
|
"loss": 0.0643, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 5.867878142316221e-05, |
|
"loss": 0.2721, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 5.626926795411447e-05, |
|
"loss": 0.1497, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 5.38907498550674e-05, |
|
"loss": 0.1311, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 5.1544912966734994e-05, |
|
"loss": 0.1305, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.9233419966116036e-05, |
|
"loss": 0.1846, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.695790918802576e-05, |
|
"loss": 0.2248, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.47199934638807e-05, |
|
"loss": 0.2505, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.252125897855932e-05, |
|
"loss": 0.1422, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.036326414614985e-05, |
|
"loss": 0.2374, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 3.824753850538082e-05, |
|
"loss": 0.083, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 3.617558163551802e-05, |
|
"loss": 0.1934, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 3.414886209349615e-05, |
|
"loss": 0.1593, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 3.216881637303839e-05, |
|
"loss": 0.1621, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 3.0236847886501542e-05, |
|
"loss": 0.2919, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2.8354325970168484e-05, |
|
"loss": 0.1741, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2.6522584913693294e-05, |
|
"loss": 0.0845, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2.4742923014386156e-05, |
|
"loss": 0.2681, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2.301660165700936e-05, |
|
"loss": 0.1332, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2.1344844419735755e-05, |
|
"loss": 0.1809, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.9728836206903656e-05, |
|
"loss": 0.2586, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.8169722409183097e-05, |
|
"loss": 0.1661, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.6668608091748495e-05, |
|
"loss": 0.2437, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.522655721103291e-05, |
|
"loss": 0.1746, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 1.3844591860619383e-05, |
|
"loss": 0.2686, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.2523691546803873e-05, |
|
"loss": 0.2711, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.1264792494342857e-05, |
|
"loss": 0.2428, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.0068786982878087e-05, |
|
"loss": 0.2276, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 8.936522714508678e-06, |
|
"loss": 0.2001, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 7.868802212958703e-06, |
|
"loss": 0.2749, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 6.866382254766157e-06, |
|
"loss": 0.2148, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 5.929973332896677e-06, |
|
"loss": 0.1606, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 5.060239153161872e-06, |
|
"loss": 0.1503, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.257796163799455e-06, |
|
"loss": 0.1724, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 3.5232131185484076e-06, |
|
"loss": 0.1867, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 2.857010673529015e-06, |
|
"loss": 0.3419, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 2.259661018213333e-06, |
|
"loss": 0.3071, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.7315875407479032e-06, |
|
"loss": 0.117, |
|
"step": 121 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.2731645278655445e-06, |
|
"loss": 0.2245, |
|
"step": 122 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 8.847168995992916e-07, |
|
"loss": 0.0688, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 5.665199789862907e-07, |
|
"loss": 0.1772, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 3.1879929692498757e-07, |
|
"loss": 0.1484, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.4173043232380557e-07, |
|
"loss": 0.133, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 3.5438887654737355e-08, |
|
"loss": 0.1682, |
|
"step": 127 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0, |
|
"loss": 0.1149, |
|
"step": 128 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 128, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"total_flos": 5.921036416707461e+17, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|