{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.8202524504618856, "eval_steps": 500, "global_step": 5000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01128270220717862, "grad_norm": 684.0, "learning_rate": 1.1875e-06, "loss": 42.923, "step": 20 }, { "epoch": 0.02256540441435724, "grad_norm": 378.0, "learning_rate": 2.4375e-06, "loss": 41.9073, "step": 40 }, { "epoch": 0.03384810662153586, "grad_norm": 322.0, "learning_rate": 3.6875000000000007e-06, "loss": 39.9877, "step": 60 }, { "epoch": 0.04513080882871448, "grad_norm": 280.0, "learning_rate": 4.937500000000001e-06, "loss": 38.0747, "step": 80 }, { "epoch": 0.056413511035893094, "grad_norm": 1328.0, "learning_rate": 6.1875000000000005e-06, "loss": 36.2999, "step": 100 }, { "epoch": 0.06769621324307172, "grad_norm": 212.0, "learning_rate": 7.437500000000001e-06, "loss": 35.0646, "step": 120 }, { "epoch": 0.07897891545025033, "grad_norm": 208.0, "learning_rate": 8.687500000000001e-06, "loss": 34.4917, "step": 140 }, { "epoch": 0.09026161765742896, "grad_norm": 180.0, "learning_rate": 9.937500000000001e-06, "loss": 34.5205, "step": 160 }, { "epoch": 0.10154431986460757, "grad_norm": 213.0, "learning_rate": 9.96317115720101e-06, "loss": 33.3244, "step": 180 }, { "epoch": 0.11282702207178619, "grad_norm": 174.0, "learning_rate": 9.9244039542547e-06, "loss": 33.6509, "step": 200 }, { "epoch": 0.12410972427896481, "grad_norm": 234.0, "learning_rate": 9.885636751308394e-06, "loss": 34.1064, "step": 220 }, { "epoch": 0.13539242648614344, "grad_norm": 176.0, "learning_rate": 9.846869548362087e-06, "loss": 34.0945, "step": 240 }, { "epoch": 0.14667512869332205, "grad_norm": 222.0, "learning_rate": 9.80810234541578e-06, "loss": 33.8671, "step": 260 }, { "epoch": 0.15795783090050067, "grad_norm": 164.0, "learning_rate": 9.769335142469472e-06, "loss": 33.4257, "step": 280 }, { "epoch": 0.16924053310767928, "grad_norm": 185.0, "learning_rate": 9.730567939523164e-06, "loss": 33.4832, "step": 300 }, { "epoch": 0.18052323531485792, "grad_norm": 188.0, "learning_rate": 9.691800736576857e-06, "loss": 33.4079, "step": 320 }, { "epoch": 0.19180593752203653, "grad_norm": 195.0, "learning_rate": 9.65303353363055e-06, "loss": 34.1975, "step": 340 }, { "epoch": 0.20308863972921515, "grad_norm": 186.0, "learning_rate": 9.614266330684242e-06, "loss": 33.3613, "step": 360 }, { "epoch": 0.21437134193639376, "grad_norm": 172.0, "learning_rate": 9.575499127737934e-06, "loss": 32.6162, "step": 380 }, { "epoch": 0.22565404414357237, "grad_norm": 170.0, "learning_rate": 9.536731924791627e-06, "loss": 33.3925, "step": 400 }, { "epoch": 0.23693674635075102, "grad_norm": 168.0, "learning_rate": 9.49796472184532e-06, "loss": 33.4435, "step": 420 }, { "epoch": 0.24821944855792963, "grad_norm": 197.0, "learning_rate": 9.459197518899013e-06, "loss": 32.9941, "step": 440 }, { "epoch": 0.25950215076510824, "grad_norm": 190.0, "learning_rate": 9.420430315952704e-06, "loss": 33.2245, "step": 460 }, { "epoch": 0.2707848529722869, "grad_norm": 185.0, "learning_rate": 9.381663113006397e-06, "loss": 33.2802, "step": 480 }, { "epoch": 0.28206755517946547, "grad_norm": 201.0, "learning_rate": 9.34289591006009e-06, "loss": 33.3563, "step": 500 }, { "epoch": 0.2933502573866441, "grad_norm": 160.0, "learning_rate": 9.304128707113782e-06, "loss": 32.8094, "step": 520 }, { "epoch": 0.3046329595938227, "grad_norm": 171.0, "learning_rate": 9.265361504167476e-06, "loss": 33.967, "step": 540 }, { "epoch": 0.31591566180100134, "grad_norm": 185.0, "learning_rate": 9.226594301221168e-06, "loss": 33.9071, "step": 560 }, { "epoch": 0.32719836400818, "grad_norm": 168.0, "learning_rate": 9.18782709827486e-06, "loss": 33.5103, "step": 580 }, { "epoch": 0.33848106621535856, "grad_norm": 185.0, "learning_rate": 9.149059895328553e-06, "loss": 33.2943, "step": 600 }, { "epoch": 0.3497637684225372, "grad_norm": 235.0, "learning_rate": 9.110292692382246e-06, "loss": 33.8674, "step": 620 }, { "epoch": 0.36104647062971584, "grad_norm": 171.0, "learning_rate": 9.071525489435938e-06, "loss": 34.1437, "step": 640 }, { "epoch": 0.37232917283689443, "grad_norm": 176.0, "learning_rate": 9.03275828648963e-06, "loss": 32.9577, "step": 660 }, { "epoch": 0.38361187504407307, "grad_norm": 179.0, "learning_rate": 8.993991083543323e-06, "loss": 33.5755, "step": 680 }, { "epoch": 0.39489457725125165, "grad_norm": 187.0, "learning_rate": 8.955223880597016e-06, "loss": 34.03, "step": 700 }, { "epoch": 0.4061772794584303, "grad_norm": 175.0, "learning_rate": 8.916456677650708e-06, "loss": 34.0341, "step": 720 }, { "epoch": 0.41745998166560894, "grad_norm": 184.0, "learning_rate": 8.8776894747044e-06, "loss": 34.1199, "step": 740 }, { "epoch": 0.4287426838727875, "grad_norm": 214.0, "learning_rate": 8.838922271758093e-06, "loss": 34.5299, "step": 760 }, { "epoch": 0.44002538607996616, "grad_norm": 187.0, "learning_rate": 8.800155068811787e-06, "loss": 33.6687, "step": 780 }, { "epoch": 0.45130808828714475, "grad_norm": 207.0, "learning_rate": 8.761387865865478e-06, "loss": 33.4913, "step": 800 }, { "epoch": 0.4625907904943234, "grad_norm": 199.0, "learning_rate": 8.72262066291917e-06, "loss": 34.6043, "step": 820 }, { "epoch": 0.47387349270150203, "grad_norm": 308.0, "learning_rate": 8.683853459972865e-06, "loss": 34.1107, "step": 840 }, { "epoch": 0.4851561949086806, "grad_norm": 219.0, "learning_rate": 8.645086257026555e-06, "loss": 33.5659, "step": 860 }, { "epoch": 0.49643889711585926, "grad_norm": 184.0, "learning_rate": 8.60631905408025e-06, "loss": 34.6702, "step": 880 }, { "epoch": 0.5077215993230378, "grad_norm": 188.0, "learning_rate": 8.567551851133942e-06, "loss": 33.9021, "step": 900 }, { "epoch": 0.5190043015302165, "grad_norm": 189.0, "learning_rate": 8.528784648187633e-06, "loss": 33.8139, "step": 920 }, { "epoch": 0.5302870037373951, "grad_norm": 202.0, "learning_rate": 8.490017445241327e-06, "loss": 33.9562, "step": 940 }, { "epoch": 0.5415697059445738, "grad_norm": 184.0, "learning_rate": 8.45125024229502e-06, "loss": 34.1304, "step": 960 }, { "epoch": 0.5528524081517523, "grad_norm": 210.0, "learning_rate": 8.412483039348712e-06, "loss": 34.3385, "step": 980 }, { "epoch": 0.5641351103589309, "grad_norm": 167.0, "learning_rate": 8.373715836402404e-06, "loss": 34.2957, "step": 1000 }, { "epoch": 0.5754178125661096, "grad_norm": 197.0, "learning_rate": 8.334948633456097e-06, "loss": 34.701, "step": 1020 }, { "epoch": 0.5867005147732882, "grad_norm": 220.0, "learning_rate": 8.29618143050979e-06, "loss": 34.1251, "step": 1040 }, { "epoch": 0.5979832169804669, "grad_norm": 199.0, "learning_rate": 8.257414227563482e-06, "loss": 34.2395, "step": 1060 }, { "epoch": 0.6092659191876454, "grad_norm": 210.0, "learning_rate": 8.218647024617174e-06, "loss": 33.7562, "step": 1080 }, { "epoch": 0.620548621394824, "grad_norm": 213.0, "learning_rate": 8.179879821670867e-06, "loss": 35.2014, "step": 1100 }, { "epoch": 0.6318313236020027, "grad_norm": 214.0, "learning_rate": 8.14111261872456e-06, "loss": 33.6772, "step": 1120 }, { "epoch": 0.6431140258091813, "grad_norm": 220.0, "learning_rate": 8.102345415778252e-06, "loss": 34.0573, "step": 1140 }, { "epoch": 0.65439672801636, "grad_norm": 162.0, "learning_rate": 8.063578212831944e-06, "loss": 34.1778, "step": 1160 }, { "epoch": 0.6656794302235386, "grad_norm": 171.0, "learning_rate": 8.024811009885637e-06, "loss": 34.7704, "step": 1180 }, { "epoch": 0.6769621324307171, "grad_norm": 192.0, "learning_rate": 7.98604380693933e-06, "loss": 34.5073, "step": 1200 }, { "epoch": 0.6882448346378958, "grad_norm": 199.0, "learning_rate": 7.947276603993023e-06, "loss": 35.1462, "step": 1220 }, { "epoch": 0.6995275368450744, "grad_norm": 194.0, "learning_rate": 7.908509401046716e-06, "loss": 35.0324, "step": 1240 }, { "epoch": 0.710810239052253, "grad_norm": 180.0, "learning_rate": 7.869742198100407e-06, "loss": 34.4355, "step": 1260 }, { "epoch": 0.7220929412594317, "grad_norm": 171.0, "learning_rate": 7.8309749951541e-06, "loss": 34.3484, "step": 1280 }, { "epoch": 0.7333756434666102, "grad_norm": 234.0, "learning_rate": 7.792207792207793e-06, "loss": 34.3537, "step": 1300 }, { "epoch": 0.7446583456737889, "grad_norm": 217.0, "learning_rate": 7.753440589261486e-06, "loss": 34.4467, "step": 1320 }, { "epoch": 0.7559410478809675, "grad_norm": 183.0, "learning_rate": 7.714673386315178e-06, "loss": 34.5935, "step": 1340 }, { "epoch": 0.7672237500881461, "grad_norm": 167.0, "learning_rate": 7.67590618336887e-06, "loss": 34.1833, "step": 1360 }, { "epoch": 0.7785064522953248, "grad_norm": 182.0, "learning_rate": 7.637138980422563e-06, "loss": 34.5052, "step": 1380 }, { "epoch": 0.7897891545025033, "grad_norm": 170.0, "learning_rate": 7.598371777476256e-06, "loss": 34.5334, "step": 1400 }, { "epoch": 0.801071856709682, "grad_norm": 181.0, "learning_rate": 7.559604574529948e-06, "loss": 34.1411, "step": 1420 }, { "epoch": 0.8123545589168606, "grad_norm": 163.0, "learning_rate": 7.5208373715836415e-06, "loss": 34.7683, "step": 1440 }, { "epoch": 0.8236372611240392, "grad_norm": 176.0, "learning_rate": 7.482070168637333e-06, "loss": 34.7674, "step": 1460 }, { "epoch": 0.8349199633312179, "grad_norm": 165.0, "learning_rate": 7.4433029656910264e-06, "loss": 34.7617, "step": 1480 }, { "epoch": 0.8462026655383964, "grad_norm": 194.0, "learning_rate": 7.404535762744719e-06, "loss": 34.7591, "step": 1500 }, { "epoch": 0.857485367745575, "grad_norm": 175.0, "learning_rate": 7.3657685597984105e-06, "loss": 34.0827, "step": 1520 }, { "epoch": 0.8687680699527537, "grad_norm": 179.0, "learning_rate": 7.327001356852104e-06, "loss": 34.5944, "step": 1540 }, { "epoch": 0.8800507721599323, "grad_norm": 198.0, "learning_rate": 7.288234153905796e-06, "loss": 35.1967, "step": 1560 }, { "epoch": 0.891333474367111, "grad_norm": 192.0, "learning_rate": 7.249466950959488e-06, "loss": 35.0658, "step": 1580 }, { "epoch": 0.9026161765742895, "grad_norm": 207.0, "learning_rate": 7.210699748013181e-06, "loss": 34.9624, "step": 1600 }, { "epoch": 0.9138988787814681, "grad_norm": 195.0, "learning_rate": 7.171932545066874e-06, "loss": 34.5503, "step": 1620 }, { "epoch": 0.9251815809886468, "grad_norm": 187.0, "learning_rate": 7.133165342120567e-06, "loss": 34.6947, "step": 1640 }, { "epoch": 0.9364642831958254, "grad_norm": 178.0, "learning_rate": 7.094398139174259e-06, "loss": 34.7273, "step": 1660 }, { "epoch": 0.9477469854030041, "grad_norm": 195.0, "learning_rate": 7.055630936227952e-06, "loss": 35.1698, "step": 1680 }, { "epoch": 0.9590296876101826, "grad_norm": 194.0, "learning_rate": 7.0168637332816445e-06, "loss": 34.8608, "step": 1700 }, { "epoch": 0.9703123898173612, "grad_norm": 209.0, "learning_rate": 6.978096530335336e-06, "loss": 34.3997, "step": 1720 }, { "epoch": 0.9815950920245399, "grad_norm": 142.0, "learning_rate": 6.9393293273890295e-06, "loss": 34.856, "step": 1740 }, { "epoch": 0.9928777942317185, "grad_norm": 186.0, "learning_rate": 6.900562124442722e-06, "loss": 34.3359, "step": 1760 }, { "epoch": 1.0039489457725126, "grad_norm": 169.0, "learning_rate": 6.8617949214964145e-06, "loss": 33.62, "step": 1780 }, { "epoch": 1.0152316479796912, "grad_norm": 189.0, "learning_rate": 6.823027718550107e-06, "loss": 33.4374, "step": 1800 }, { "epoch": 1.0265143501868697, "grad_norm": 191.0, "learning_rate": 6.7842605156038e-06, "loss": 32.8082, "step": 1820 }, { "epoch": 1.0377970523940483, "grad_norm": 151.0, "learning_rate": 6.745493312657493e-06, "loss": 33.2524, "step": 1840 }, { "epoch": 1.049079754601227, "grad_norm": 153.0, "learning_rate": 6.706726109711184e-06, "loss": 32.7946, "step": 1860 }, { "epoch": 1.0603624568084056, "grad_norm": 190.0, "learning_rate": 6.667958906764878e-06, "loss": 34.0579, "step": 1880 }, { "epoch": 1.0716451590155842, "grad_norm": 169.0, "learning_rate": 6.62919170381857e-06, "loss": 33.6604, "step": 1900 }, { "epoch": 1.0829278612227629, "grad_norm": 203.0, "learning_rate": 6.590424500872263e-06, "loss": 33.566, "step": 1920 }, { "epoch": 1.0942105634299415, "grad_norm": 166.0, "learning_rate": 6.551657297925955e-06, "loss": 32.8621, "step": 1940 }, { "epoch": 1.1054932656371201, "grad_norm": 190.0, "learning_rate": 6.5128900949796484e-06, "loss": 32.7915, "step": 1960 }, { "epoch": 1.1167759678442988, "grad_norm": 159.0, "learning_rate": 6.47412289203334e-06, "loss": 32.8263, "step": 1980 }, { "epoch": 1.1280586700514774, "grad_norm": 213.0, "learning_rate": 6.4353556890870326e-06, "loss": 33.4649, "step": 2000 }, { "epoch": 1.1393413722586558, "grad_norm": 170.0, "learning_rate": 6.396588486140726e-06, "loss": 33.0993, "step": 2020 }, { "epoch": 1.1506240744658345, "grad_norm": 178.0, "learning_rate": 6.3578212831944175e-06, "loss": 32.8403, "step": 2040 }, { "epoch": 1.1619067766730131, "grad_norm": 192.0, "learning_rate": 6.31905408024811e-06, "loss": 33.212, "step": 2060 }, { "epoch": 1.1731894788801918, "grad_norm": 177.0, "learning_rate": 6.280286877301803e-06, "loss": 32.9688, "step": 2080 }, { "epoch": 1.1844721810873704, "grad_norm": 176.0, "learning_rate": 6.241519674355496e-06, "loss": 33.0461, "step": 2100 }, { "epoch": 1.195754883294549, "grad_norm": 191.0, "learning_rate": 6.202752471409188e-06, "loss": 33.4505, "step": 2120 }, { "epoch": 1.2070375855017277, "grad_norm": 165.0, "learning_rate": 6.163985268462881e-06, "loss": 33.6436, "step": 2140 }, { "epoch": 1.2183202877089063, "grad_norm": 177.0, "learning_rate": 6.125218065516574e-06, "loss": 32.9951, "step": 2160 }, { "epoch": 1.229602989916085, "grad_norm": 181.0, "learning_rate": 6.086450862570266e-06, "loss": 34.0142, "step": 2180 }, { "epoch": 1.2408856921232636, "grad_norm": 174.0, "learning_rate": 6.047683659623958e-06, "loss": 33.6973, "step": 2200 }, { "epoch": 1.2521683943304422, "grad_norm": 160.0, "learning_rate": 6.0089164566776515e-06, "loss": 32.4556, "step": 2220 }, { "epoch": 1.2634510965376209, "grad_norm": 165.0, "learning_rate": 5.970149253731343e-06, "loss": 33.3473, "step": 2240 }, { "epoch": 1.2747337987447993, "grad_norm": 192.0, "learning_rate": 5.9313820507850365e-06, "loss": 32.9415, "step": 2260 }, { "epoch": 1.286016500951978, "grad_norm": 169.0, "learning_rate": 5.892614847838729e-06, "loss": 33.7312, "step": 2280 }, { "epoch": 1.2972992031591566, "grad_norm": 172.0, "learning_rate": 5.853847644892422e-06, "loss": 33.2523, "step": 2300 }, { "epoch": 1.3085819053663352, "grad_norm": 166.0, "learning_rate": 5.815080441946114e-06, "loss": 33.4629, "step": 2320 }, { "epoch": 1.3198646075735139, "grad_norm": 220.0, "learning_rate": 5.776313238999806e-06, "loss": 33.6943, "step": 2340 }, { "epoch": 1.3311473097806925, "grad_norm": 163.0, "learning_rate": 5.7375460360535e-06, "loss": 33.2026, "step": 2360 }, { "epoch": 1.3424300119878712, "grad_norm": 227.0, "learning_rate": 5.698778833107191e-06, "loss": 33.3166, "step": 2380 }, { "epoch": 1.3537127141950498, "grad_norm": 198.0, "learning_rate": 5.660011630160885e-06, "loss": 33.5236, "step": 2400 }, { "epoch": 1.3649954164022282, "grad_norm": 178.0, "learning_rate": 5.621244427214577e-06, "loss": 33.3746, "step": 2420 }, { "epoch": 1.3762781186094069, "grad_norm": 182.0, "learning_rate": 5.582477224268269e-06, "loss": 33.2293, "step": 2440 }, { "epoch": 1.3875608208165855, "grad_norm": 232.0, "learning_rate": 5.543710021321962e-06, "loss": 34.0862, "step": 2460 }, { "epoch": 1.3988435230237641, "grad_norm": 175.0, "learning_rate": 5.5049428183756546e-06, "loss": 33.4116, "step": 2480 }, { "epoch": 1.4101262252309428, "grad_norm": 198.0, "learning_rate": 5.466175615429348e-06, "loss": 32.8442, "step": 2500 }, { "epoch": 1.4214089274381214, "grad_norm": 162.0, "learning_rate": 5.4274084124830395e-06, "loss": 33.7111, "step": 2520 }, { "epoch": 1.4326916296453, "grad_norm": 208.0, "learning_rate": 5.388641209536732e-06, "loss": 33.0033, "step": 2540 }, { "epoch": 1.4439743318524787, "grad_norm": 192.0, "learning_rate": 5.349874006590425e-06, "loss": 33.8201, "step": 2560 }, { "epoch": 1.4552570340596573, "grad_norm": 169.0, "learning_rate": 5.311106803644117e-06, "loss": 32.9213, "step": 2580 }, { "epoch": 1.466539736266836, "grad_norm": 181.0, "learning_rate": 5.27233960069781e-06, "loss": 33.9638, "step": 2600 }, { "epoch": 1.4778224384740146, "grad_norm": 173.0, "learning_rate": 5.233572397751503e-06, "loss": 33.5811, "step": 2620 }, { "epoch": 1.4891051406811933, "grad_norm": 190.0, "learning_rate": 5.194805194805194e-06, "loss": 33.8197, "step": 2640 }, { "epoch": 1.500387842888372, "grad_norm": 197.0, "learning_rate": 5.156037991858888e-06, "loss": 33.6394, "step": 2660 }, { "epoch": 1.5116705450955505, "grad_norm": 290.0, "learning_rate": 5.11727078891258e-06, "loss": 33.2235, "step": 2680 }, { "epoch": 1.522953247302729, "grad_norm": 148.0, "learning_rate": 5.0785035859662735e-06, "loss": 33.6943, "step": 2700 }, { "epoch": 1.5342359495099076, "grad_norm": 183.0, "learning_rate": 5.039736383019965e-06, "loss": 33.5758, "step": 2720 }, { "epoch": 1.5455186517170862, "grad_norm": 175.0, "learning_rate": 5.0009691800736585e-06, "loss": 34.077, "step": 2740 }, { "epoch": 1.5568013539242649, "grad_norm": 178.0, "learning_rate": 4.96220197712735e-06, "loss": 33.2421, "step": 2760 }, { "epoch": 1.5680840561314435, "grad_norm": 169.0, "learning_rate": 4.9234347741810434e-06, "loss": 34.0267, "step": 2780 }, { "epoch": 1.579366758338622, "grad_norm": 171.0, "learning_rate": 4.884667571234736e-06, "loss": 33.5599, "step": 2800 }, { "epoch": 1.5906494605458006, "grad_norm": 206.0, "learning_rate": 4.845900368288428e-06, "loss": 33.7535, "step": 2820 }, { "epoch": 1.6019321627529792, "grad_norm": 168.0, "learning_rate": 4.807133165342121e-06, "loss": 33.4231, "step": 2840 }, { "epoch": 1.6132148649601579, "grad_norm": 208.0, "learning_rate": 4.768365962395813e-06, "loss": 33.1695, "step": 2860 }, { "epoch": 1.6244975671673365, "grad_norm": 213.0, "learning_rate": 4.729598759449507e-06, "loss": 33.2739, "step": 2880 }, { "epoch": 1.6357802693745152, "grad_norm": 177.0, "learning_rate": 4.690831556503198e-06, "loss": 33.3967, "step": 2900 }, { "epoch": 1.6470629715816938, "grad_norm": 234.0, "learning_rate": 4.652064353556891e-06, "loss": 34.2787, "step": 2920 }, { "epoch": 1.6583456737888724, "grad_norm": 163.0, "learning_rate": 4.613297150610584e-06, "loss": 34.1793, "step": 2940 }, { "epoch": 1.669628375996051, "grad_norm": 192.0, "learning_rate": 4.574529947664277e-06, "loss": 33.67, "step": 2960 }, { "epoch": 1.6809110782032297, "grad_norm": 188.0, "learning_rate": 4.535762744717969e-06, "loss": 34.1299, "step": 2980 }, { "epoch": 1.6921937804104084, "grad_norm": 210.0, "learning_rate": 4.4969955417716615e-06, "loss": 33.6063, "step": 3000 }, { "epoch": 1.703476482617587, "grad_norm": 222.0, "learning_rate": 4.458228338825354e-06, "loss": 33.864, "step": 3020 }, { "epoch": 1.7147591848247656, "grad_norm": 167.0, "learning_rate": 4.4194611358790465e-06, "loss": 33.9385, "step": 3040 }, { "epoch": 1.7260418870319443, "grad_norm": 201.0, "learning_rate": 4.380693932932739e-06, "loss": 33.4324, "step": 3060 }, { "epoch": 1.737324589239123, "grad_norm": 171.0, "learning_rate": 4.341926729986432e-06, "loss": 33.6625, "step": 3080 }, { "epoch": 1.7486072914463013, "grad_norm": 166.0, "learning_rate": 4.303159527040125e-06, "loss": 33.1414, "step": 3100 }, { "epoch": 1.75988999365348, "grad_norm": 151.0, "learning_rate": 4.264392324093816e-06, "loss": 34.045, "step": 3120 }, { "epoch": 1.7711726958606586, "grad_norm": 179.0, "learning_rate": 4.22562512114751e-06, "loss": 33.642, "step": 3140 }, { "epoch": 1.7824553980678373, "grad_norm": 204.0, "learning_rate": 4.186857918201202e-06, "loss": 33.6747, "step": 3160 }, { "epoch": 1.793738100275016, "grad_norm": 156.0, "learning_rate": 4.148090715254895e-06, "loss": 33.6803, "step": 3180 }, { "epoch": 1.8050208024821943, "grad_norm": 181.0, "learning_rate": 4.109323512308587e-06, "loss": 33.9288, "step": 3200 }, { "epoch": 1.816303504689373, "grad_norm": 167.0, "learning_rate": 4.07055630936228e-06, "loss": 33.6484, "step": 3220 }, { "epoch": 1.8275862068965516, "grad_norm": 179.0, "learning_rate": 4.031789106415972e-06, "loss": 33.5411, "step": 3240 }, { "epoch": 1.8388689091037302, "grad_norm": 202.0, "learning_rate": 3.993021903469665e-06, "loss": 33.7925, "step": 3260 }, { "epoch": 1.8501516113109089, "grad_norm": 211.0, "learning_rate": 3.954254700523358e-06, "loss": 34.3101, "step": 3280 }, { "epoch": 1.8614343135180875, "grad_norm": 187.0, "learning_rate": 3.91548749757705e-06, "loss": 33.674, "step": 3300 }, { "epoch": 1.8727170157252662, "grad_norm": 186.0, "learning_rate": 3.876720294630743e-06, "loss": 34.4049, "step": 3320 }, { "epoch": 1.8839997179324448, "grad_norm": 170.0, "learning_rate": 3.837953091684435e-06, "loss": 33.3274, "step": 3340 }, { "epoch": 1.8952824201396234, "grad_norm": 239.0, "learning_rate": 3.799185888738128e-06, "loss": 33.1375, "step": 3360 }, { "epoch": 1.906565122346802, "grad_norm": 178.0, "learning_rate": 3.7604186857918207e-06, "loss": 34.1163, "step": 3380 }, { "epoch": 1.9178478245539807, "grad_norm": 185.0, "learning_rate": 3.7216514828455132e-06, "loss": 34.4329, "step": 3400 }, { "epoch": 1.9291305267611594, "grad_norm": 195.0, "learning_rate": 3.6828842798992053e-06, "loss": 33.4928, "step": 3420 }, { "epoch": 1.940413228968338, "grad_norm": 162.0, "learning_rate": 3.644117076952898e-06, "loss": 34.0265, "step": 3440 }, { "epoch": 1.9516959311755167, "grad_norm": 195.0, "learning_rate": 3.6053498740065907e-06, "loss": 33.9424, "step": 3460 }, { "epoch": 1.9629786333826953, "grad_norm": 185.0, "learning_rate": 3.5665826710602836e-06, "loss": 34.3252, "step": 3480 }, { "epoch": 1.974261335589874, "grad_norm": 195.0, "learning_rate": 3.527815468113976e-06, "loss": 34.5225, "step": 3500 }, { "epoch": 1.9855440377970524, "grad_norm": 214.0, "learning_rate": 3.489048265167668e-06, "loss": 34.5155, "step": 3520 }, { "epoch": 1.996826740004231, "grad_norm": 182.0, "learning_rate": 3.450281062221361e-06, "loss": 34.1097, "step": 3540 }, { "epoch": 2.007897891545025, "grad_norm": 164.0, "learning_rate": 3.4115138592750535e-06, "loss": 33.4037, "step": 3560 }, { "epoch": 2.019180593752204, "grad_norm": 164.0, "learning_rate": 3.3727466563287464e-06, "loss": 33.2511, "step": 3580 }, { "epoch": 2.0304632959593825, "grad_norm": 228.0, "learning_rate": 3.333979453382439e-06, "loss": 33.3459, "step": 3600 }, { "epoch": 2.041745998166561, "grad_norm": 201.0, "learning_rate": 3.2952122504361313e-06, "loss": 33.6336, "step": 3620 }, { "epoch": 2.0530287003737393, "grad_norm": 243.0, "learning_rate": 3.2564450474898242e-06, "loss": 33.4227, "step": 3640 }, { "epoch": 2.064311402580918, "grad_norm": 188.0, "learning_rate": 3.2176778445435163e-06, "loss": 33.9483, "step": 3660 }, { "epoch": 2.0755941047880966, "grad_norm": 177.0, "learning_rate": 3.1789106415972088e-06, "loss": 32.5607, "step": 3680 }, { "epoch": 2.0868768069952752, "grad_norm": 195.0, "learning_rate": 3.1401434386509017e-06, "loss": 33.2094, "step": 3700 }, { "epoch": 2.098159509202454, "grad_norm": 194.0, "learning_rate": 3.101376235704594e-06, "loss": 32.5983, "step": 3720 }, { "epoch": 2.1094422114096325, "grad_norm": 171.0, "learning_rate": 3.062609032758287e-06, "loss": 33.4583, "step": 3740 }, { "epoch": 2.120724913616811, "grad_norm": 196.0, "learning_rate": 3.023841829811979e-06, "loss": 33.2525, "step": 3760 }, { "epoch": 2.13200761582399, "grad_norm": 185.0, "learning_rate": 2.9850746268656716e-06, "loss": 32.8658, "step": 3780 }, { "epoch": 2.1432903180311684, "grad_norm": 211.0, "learning_rate": 2.9463074239193645e-06, "loss": 33.584, "step": 3800 }, { "epoch": 2.154573020238347, "grad_norm": 177.0, "learning_rate": 2.907540220973057e-06, "loss": 32.7506, "step": 3820 }, { "epoch": 2.1658557224455257, "grad_norm": 201.0, "learning_rate": 2.86877301802675e-06, "loss": 33.6909, "step": 3840 }, { "epoch": 2.1771384246527044, "grad_norm": 187.0, "learning_rate": 2.8300058150804423e-06, "loss": 32.9226, "step": 3860 }, { "epoch": 2.188421126859883, "grad_norm": 186.0, "learning_rate": 2.7912386121341344e-06, "loss": 33.2277, "step": 3880 }, { "epoch": 2.1997038290670616, "grad_norm": 198.0, "learning_rate": 2.7524714091878273e-06, "loss": 32.8508, "step": 3900 }, { "epoch": 2.2109865312742403, "grad_norm": 186.0, "learning_rate": 2.7137042062415198e-06, "loss": 33.2497, "step": 3920 }, { "epoch": 2.222269233481419, "grad_norm": 222.0, "learning_rate": 2.6749370032952127e-06, "loss": 33.5576, "step": 3940 }, { "epoch": 2.2335519356885976, "grad_norm": 161.0, "learning_rate": 2.636169800348905e-06, "loss": 33.4056, "step": 3960 }, { "epoch": 2.244834637895776, "grad_norm": 163.0, "learning_rate": 2.597402597402597e-06, "loss": 33.0674, "step": 3980 }, { "epoch": 2.256117340102955, "grad_norm": 177.0, "learning_rate": 2.55863539445629e-06, "loss": 32.9768, "step": 4000 }, { "epoch": 2.2674000423101335, "grad_norm": 220.0, "learning_rate": 2.5198681915099826e-06, "loss": 33.1559, "step": 4020 }, { "epoch": 2.2786827445173117, "grad_norm": 175.0, "learning_rate": 2.481100988563675e-06, "loss": 33.5091, "step": 4040 }, { "epoch": 2.2899654467244908, "grad_norm": 180.0, "learning_rate": 2.442333785617368e-06, "loss": 33.3984, "step": 4060 }, { "epoch": 2.301248148931669, "grad_norm": 192.0, "learning_rate": 2.4035665826710604e-06, "loss": 33.3091, "step": 4080 }, { "epoch": 2.3125308511388476, "grad_norm": 200.0, "learning_rate": 2.3647993797247533e-06, "loss": 33.9978, "step": 4100 }, { "epoch": 2.3238135533460262, "grad_norm": 202.0, "learning_rate": 2.3260321767784454e-06, "loss": 33.4988, "step": 4120 }, { "epoch": 2.335096255553205, "grad_norm": 220.0, "learning_rate": 2.2872649738321383e-06, "loss": 32.5648, "step": 4140 }, { "epoch": 2.3463789577603835, "grad_norm": 188.0, "learning_rate": 2.2484977708858308e-06, "loss": 33.3508, "step": 4160 }, { "epoch": 2.357661659967562, "grad_norm": 166.0, "learning_rate": 2.2097305679395232e-06, "loss": 33.5085, "step": 4180 }, { "epoch": 2.368944362174741, "grad_norm": 192.0, "learning_rate": 2.170963364993216e-06, "loss": 33.5222, "step": 4200 }, { "epoch": 2.3802270643819194, "grad_norm": 168.0, "learning_rate": 2.132196162046908e-06, "loss": 33.5567, "step": 4220 }, { "epoch": 2.391509766589098, "grad_norm": 189.0, "learning_rate": 2.093428959100601e-06, "loss": 32.6794, "step": 4240 }, { "epoch": 2.4027924687962767, "grad_norm": 208.0, "learning_rate": 2.0546617561542936e-06, "loss": 33.1244, "step": 4260 }, { "epoch": 2.4140751710034554, "grad_norm": 222.0, "learning_rate": 2.015894553207986e-06, "loss": 33.2899, "step": 4280 }, { "epoch": 2.425357873210634, "grad_norm": 165.0, "learning_rate": 1.977127350261679e-06, "loss": 33.3089, "step": 4300 }, { "epoch": 2.4366405754178126, "grad_norm": 186.0, "learning_rate": 1.9383601473153714e-06, "loss": 33.8634, "step": 4320 }, { "epoch": 2.4479232776249913, "grad_norm": 189.0, "learning_rate": 1.899592944369064e-06, "loss": 33.6295, "step": 4340 }, { "epoch": 2.45920597983217, "grad_norm": 194.0, "learning_rate": 1.8608257414227566e-06, "loss": 33.7899, "step": 4360 }, { "epoch": 2.4704886820393486, "grad_norm": 176.0, "learning_rate": 1.822058538476449e-06, "loss": 33.4224, "step": 4380 }, { "epoch": 2.481771384246527, "grad_norm": 178.0, "learning_rate": 1.7832913355301418e-06, "loss": 33.2276, "step": 4400 }, { "epoch": 2.493054086453706, "grad_norm": 204.0, "learning_rate": 1.744524132583834e-06, "loss": 33.7431, "step": 4420 }, { "epoch": 2.5043367886608845, "grad_norm": 195.0, "learning_rate": 1.7057569296375267e-06, "loss": 33.1986, "step": 4440 }, { "epoch": 2.5156194908680627, "grad_norm": 191.0, "learning_rate": 1.6669897266912194e-06, "loss": 33.1506, "step": 4460 }, { "epoch": 2.5269021930752418, "grad_norm": 193.0, "learning_rate": 1.6282225237449121e-06, "loss": 33.1911, "step": 4480 }, { "epoch": 2.53818489528242, "grad_norm": 230.0, "learning_rate": 1.5894553207986044e-06, "loss": 33.6828, "step": 4500 }, { "epoch": 2.5494675974895986, "grad_norm": 219.0, "learning_rate": 1.550688117852297e-06, "loss": 33.9657, "step": 4520 }, { "epoch": 2.5607502996967773, "grad_norm": 197.0, "learning_rate": 1.5119209149059895e-06, "loss": 33.2005, "step": 4540 }, { "epoch": 2.572033001903956, "grad_norm": 214.0, "learning_rate": 1.4731537119596822e-06, "loss": 33.5472, "step": 4560 }, { "epoch": 2.5833157041111345, "grad_norm": 167.0, "learning_rate": 1.434386509013375e-06, "loss": 34.237, "step": 4580 }, { "epoch": 2.594598406318313, "grad_norm": 162.0, "learning_rate": 1.3956193060670672e-06, "loss": 34.3779, "step": 4600 }, { "epoch": 2.605881108525492, "grad_norm": 240.0, "learning_rate": 1.3568521031207599e-06, "loss": 33.7256, "step": 4620 }, { "epoch": 2.6171638107326705, "grad_norm": 187.0, "learning_rate": 1.3180849001744526e-06, "loss": 32.9692, "step": 4640 }, { "epoch": 2.628446512939849, "grad_norm": 164.0, "learning_rate": 1.279317697228145e-06, "loss": 33.8773, "step": 4660 }, { "epoch": 2.6397292151470277, "grad_norm": 188.0, "learning_rate": 1.2405504942818375e-06, "loss": 33.5338, "step": 4680 }, { "epoch": 2.6510119173542064, "grad_norm": 185.0, "learning_rate": 1.2017832913355302e-06, "loss": 33.9084, "step": 4700 }, { "epoch": 2.662294619561385, "grad_norm": 190.0, "learning_rate": 1.1630160883892227e-06, "loss": 33.0886, "step": 4720 }, { "epoch": 2.6735773217685637, "grad_norm": 169.0, "learning_rate": 1.1242488854429154e-06, "loss": 33.0422, "step": 4740 }, { "epoch": 2.6848600239757423, "grad_norm": 185.0, "learning_rate": 1.085481682496608e-06, "loss": 33.4596, "step": 4760 }, { "epoch": 2.696142726182921, "grad_norm": 169.0, "learning_rate": 1.0467144795503006e-06, "loss": 33.3788, "step": 4780 }, { "epoch": 2.7074254283900996, "grad_norm": 214.0, "learning_rate": 1.007947276603993e-06, "loss": 33.6668, "step": 4800 }, { "epoch": 2.7187081305972782, "grad_norm": 170.0, "learning_rate": 9.691800736576857e-07, "loss": 33.1791, "step": 4820 }, { "epoch": 2.7299908328044564, "grad_norm": 192.0, "learning_rate": 9.304128707113783e-07, "loss": 33.7457, "step": 4840 }, { "epoch": 2.7412735350116355, "grad_norm": 171.0, "learning_rate": 8.916456677650709e-07, "loss": 33.7942, "step": 4860 }, { "epoch": 2.7525562372188137, "grad_norm": 164.0, "learning_rate": 8.528784648187634e-07, "loss": 33.0871, "step": 4880 }, { "epoch": 2.763838939425993, "grad_norm": 179.0, "learning_rate": 8.141112618724561e-07, "loss": 33.5948, "step": 4900 }, { "epoch": 2.775121641633171, "grad_norm": 197.0, "learning_rate": 7.753440589261485e-07, "loss": 33.451, "step": 4920 }, { "epoch": 2.7864043438403496, "grad_norm": 176.0, "learning_rate": 7.365768559798411e-07, "loss": 33.3747, "step": 4940 }, { "epoch": 2.7976870460475283, "grad_norm": 221.0, "learning_rate": 6.978096530335336e-07, "loss": 33.7778, "step": 4960 }, { "epoch": 2.808969748254707, "grad_norm": 198.0, "learning_rate": 6.590424500872263e-07, "loss": 33.2167, "step": 4980 }, { "epoch": 2.8202524504618856, "grad_norm": 208.0, "learning_rate": 6.202752471409188e-07, "loss": 33.0164, "step": 5000 } ], "logging_steps": 20, "max_steps": 5319, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }