{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.028815478028198, "eval_steps": 2500, "global_step": 2500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004116496861171143, "grad_norm": 722.9849266591084, "learning_rate": 1.0000000000000001e-07, "loss": 79.4593, "step": 10 }, { "epoch": 0.008232993722342286, "grad_norm": 713.4423322869009, "learning_rate": 2.1111111111111113e-07, "loss": 79.3183, "step": 20 }, { "epoch": 0.01234949058351343, "grad_norm": 619.0335944754007, "learning_rate": 3.2222222222222227e-07, "loss": 78.0929, "step": 30 }, { "epoch": 0.016465987444684572, "grad_norm": 439.772626183607, "learning_rate": 4.333333333333334e-07, "loss": 75.0743, "step": 40 }, { "epoch": 0.020582484305855717, "grad_norm": 281.08070517386403, "learning_rate": 5.444444444444444e-07, "loss": 69.3428, "step": 50 }, { "epoch": 0.02469898116702686, "grad_norm": 238.72306538307805, "learning_rate": 6.555555555555556e-07, "loss": 64.8186, "step": 60 }, { "epoch": 0.028815478028198005, "grad_norm": 265.61586056265025, "learning_rate": 7.666666666666667e-07, "loss": 59.6238, "step": 70 }, { "epoch": 0.032931974889369144, "grad_norm": 92.19312055336448, "learning_rate": 8.777777777777778e-07, "loss": 52.8731, "step": 80 }, { "epoch": 0.03704847175054029, "grad_norm": 45.48770884961453, "learning_rate": 9.88888888888889e-07, "loss": 49.676, "step": 90 }, { "epoch": 0.041164968611711435, "grad_norm": 27.08086194848908, "learning_rate": 1.1e-06, "loss": 48.4892, "step": 100 }, { "epoch": 0.04528146547288258, "grad_norm": 19.32379182470467, "learning_rate": 1.2111111111111111e-06, "loss": 48.0497, "step": 110 }, { "epoch": 0.04939796233405372, "grad_norm": 16.380874066084196, "learning_rate": 1.3222222222222222e-06, "loss": 47.7781, "step": 120 }, { "epoch": 0.053514459195224864, "grad_norm": 15.371140813384557, "learning_rate": 1.4333333333333335e-06, "loss": 47.5811, "step": 130 }, { "epoch": 0.05763095605639601, "grad_norm": 15.84809592222176, "learning_rate": 1.5444444444444446e-06, "loss": 47.4215, "step": 140 }, { "epoch": 0.06174745291756715, "grad_norm": 16.994317821440845, "learning_rate": 1.6555555555555559e-06, "loss": 47.2557, "step": 150 }, { "epoch": 0.06586394977873829, "grad_norm": 18.743638967461997, "learning_rate": 1.7666666666666668e-06, "loss": 47.0796, "step": 160 }, { "epoch": 0.06998044663990943, "grad_norm": 20.92550528148297, "learning_rate": 1.8777777777777778e-06, "loss": 46.8693, "step": 170 }, { "epoch": 0.07409694350108058, "grad_norm": 23.935804629158547, "learning_rate": 1.988888888888889e-06, "loss": 46.6118, "step": 180 }, { "epoch": 0.07821344036225172, "grad_norm": 28.229572692610986, "learning_rate": 2.1000000000000002e-06, "loss": 46.267, "step": 190 }, { "epoch": 0.08232993722342287, "grad_norm": 34.37693332521861, "learning_rate": 2.2111111111111113e-06, "loss": 45.7269, "step": 200 }, { "epoch": 0.08644643408459401, "grad_norm": 43.4433932596704, "learning_rate": 2.3222222222222224e-06, "loss": 44.9702, "step": 210 }, { "epoch": 0.09056293094576516, "grad_norm": 58.28038941283432, "learning_rate": 2.4333333333333335e-06, "loss": 43.7522, "step": 220 }, { "epoch": 0.09467942780693629, "grad_norm": 71.69823530504809, "learning_rate": 2.5444444444444446e-06, "loss": 41.9094, "step": 230 }, { "epoch": 0.09879592466810744, "grad_norm": 69.78057028859453, "learning_rate": 2.6555555555555556e-06, "loss": 39.6286, "step": 240 }, { "epoch": 0.10291242152927858, "grad_norm": 65.2702064062225, "learning_rate": 2.766666666666667e-06, "loss": 37.279, "step": 250 }, { "epoch": 0.10702891839044973, "grad_norm": 62.147050273188626, "learning_rate": 2.8777777777777782e-06, "loss": 34.8486, "step": 260 }, { "epoch": 0.11114541525162087, "grad_norm": 58.3163917534024, "learning_rate": 2.988888888888889e-06, "loss": 32.3669, "step": 270 }, { "epoch": 0.11526191211279202, "grad_norm": 73.8699537282808, "learning_rate": 3.1000000000000004e-06, "loss": 29.9582, "step": 280 }, { "epoch": 0.11937840897396315, "grad_norm": 59.22493609025033, "learning_rate": 3.2111111111111115e-06, "loss": 27.8124, "step": 290 }, { "epoch": 0.1234949058351343, "grad_norm": 42.636994581457614, "learning_rate": 3.322222222222222e-06, "loss": 25.908, "step": 300 }, { "epoch": 0.12761140269630544, "grad_norm": 36.81511952341932, "learning_rate": 3.4333333333333336e-06, "loss": 24.4843, "step": 310 }, { "epoch": 0.13172789955747657, "grad_norm": 27.381915904890327, "learning_rate": 3.5444444444444447e-06, "loss": 23.4653, "step": 320 }, { "epoch": 0.13584439641864773, "grad_norm": 23.598517571067614, "learning_rate": 3.6555555555555562e-06, "loss": 22.7909, "step": 330 }, { "epoch": 0.13996089327981887, "grad_norm": 23.294478325249578, "learning_rate": 3.766666666666667e-06, "loss": 22.3688, "step": 340 }, { "epoch": 0.14407739014099002, "grad_norm": 20.093643447034683, "learning_rate": 3.877777777777778e-06, "loss": 22.0982, "step": 350 }, { "epoch": 0.14819388700216116, "grad_norm": 19.394487535911193, "learning_rate": 3.9888888888888895e-06, "loss": 21.9086, "step": 360 }, { "epoch": 0.15231038386333232, "grad_norm": 18.119665979499104, "learning_rate": 4.1e-06, "loss": 21.7863, "step": 370 }, { "epoch": 0.15642688072450345, "grad_norm": 17.07344526731236, "learning_rate": 4.211111111111112e-06, "loss": 21.6972, "step": 380 }, { "epoch": 0.16054337758567458, "grad_norm": 17.2895867054574, "learning_rate": 4.322222222222223e-06, "loss": 21.6276, "step": 390 }, { "epoch": 0.16465987444684574, "grad_norm": 18.055980258041934, "learning_rate": 4.433333333333334e-06, "loss": 21.5774, "step": 400 }, { "epoch": 0.16877637130801687, "grad_norm": 17.602944740266267, "learning_rate": 4.544444444444445e-06, "loss": 21.5305, "step": 410 }, { "epoch": 0.17289286816918803, "grad_norm": 17.047319458414727, "learning_rate": 4.655555555555556e-06, "loss": 21.4996, "step": 420 }, { "epoch": 0.17700936503035916, "grad_norm": 17.326432935336033, "learning_rate": 4.766666666666667e-06, "loss": 21.4706, "step": 430 }, { "epoch": 0.18112586189153032, "grad_norm": 17.554696739458905, "learning_rate": 4.877777777777778e-06, "loss": 21.4449, "step": 440 }, { "epoch": 0.18524235875270145, "grad_norm": 16.57900811727561, "learning_rate": 4.988888888888889e-06, "loss": 21.4242, "step": 450 }, { "epoch": 0.18935885561387258, "grad_norm": 16.41658497950142, "learning_rate": 5.1e-06, "loss": 21.4136, "step": 460 }, { "epoch": 0.19347535247504374, "grad_norm": 14.851397065124416, "learning_rate": 5.211111111111111e-06, "loss": 21.3904, "step": 470 }, { "epoch": 0.19759184933621488, "grad_norm": 16.86165644628761, "learning_rate": 5.322222222222223e-06, "loss": 21.3748, "step": 480 }, { "epoch": 0.20170834619738603, "grad_norm": 16.021934417394476, "learning_rate": 5.4333333333333335e-06, "loss": 21.3649, "step": 490 }, { "epoch": 0.20582484305855717, "grad_norm": 16.71987330752045, "learning_rate": 5.544444444444445e-06, "loss": 21.357, "step": 500 }, { "epoch": 0.2099413399197283, "grad_norm": 16.033384348770003, "learning_rate": 5.6555555555555566e-06, "loss": 21.345, "step": 510 }, { "epoch": 0.21405783678089946, "grad_norm": 16.503614387128653, "learning_rate": 5.766666666666667e-06, "loss": 21.3308, "step": 520 }, { "epoch": 0.2181743336420706, "grad_norm": 16.5197017811903, "learning_rate": 5.877777777777778e-06, "loss": 21.3167, "step": 530 }, { "epoch": 0.22229083050324175, "grad_norm": 18.609397075134556, "learning_rate": 5.98888888888889e-06, "loss": 21.2952, "step": 540 }, { "epoch": 0.22640732736441288, "grad_norm": 18.044456751597316, "learning_rate": 6.1e-06, "loss": 21.2694, "step": 550 }, { "epoch": 0.23052382422558404, "grad_norm": 18.440050806349944, "learning_rate": 6.211111111111111e-06, "loss": 21.2149, "step": 560 }, { "epoch": 0.23464032108675517, "grad_norm": 36.12491809597436, "learning_rate": 6.322222222222223e-06, "loss": 21.1566, "step": 570 }, { "epoch": 0.2387568179479263, "grad_norm": 17.843619309609803, "learning_rate": 6.433333333333333e-06, "loss": 21.0841, "step": 580 }, { "epoch": 0.24287331480909746, "grad_norm": 18.299191738513812, "learning_rate": 6.544444444444445e-06, "loss": 20.9708, "step": 590 }, { "epoch": 0.2469898116702686, "grad_norm": 18.056905789458586, "learning_rate": 6.655555555555556e-06, "loss": 20.8825, "step": 600 }, { "epoch": 0.2511063085314397, "grad_norm": 44.82326463049171, "learning_rate": 6.7666666666666665e-06, "loss": 20.8147, "step": 610 }, { "epoch": 0.2552228053926109, "grad_norm": 27.094157559455603, "learning_rate": 6.8777777777777785e-06, "loss": 20.7548, "step": 620 }, { "epoch": 0.25933930225378204, "grad_norm": 27.88387397100189, "learning_rate": 6.9888888888888895e-06, "loss": 20.6822, "step": 630 }, { "epoch": 0.26345579911495315, "grad_norm": 31.290911839762394, "learning_rate": 7.100000000000001e-06, "loss": 20.5884, "step": 640 }, { "epoch": 0.2675722959761243, "grad_norm": 24.27245501884365, "learning_rate": 7.211111111111112e-06, "loss": 20.5162, "step": 650 }, { "epoch": 0.27168879283729547, "grad_norm": 23.89703899570296, "learning_rate": 7.322222222222223e-06, "loss": 20.4592, "step": 660 }, { "epoch": 0.2758052896984666, "grad_norm": 57.249160956506614, "learning_rate": 7.433333333333334e-06, "loss": 20.3787, "step": 670 }, { "epoch": 0.27992178655963773, "grad_norm": 44.42291899504958, "learning_rate": 7.544444444444445e-06, "loss": 20.207, "step": 680 }, { "epoch": 0.2840382834208089, "grad_norm": 91.55863776649939, "learning_rate": 7.655555555555556e-06, "loss": 20.143, "step": 690 }, { "epoch": 0.28815478028198005, "grad_norm": 57.092128520356646, "learning_rate": 7.766666666666666e-06, "loss": 19.9418, "step": 700 }, { "epoch": 0.29227127714315115, "grad_norm": 37.42956925364744, "learning_rate": 7.877777777777778e-06, "loss": 19.6662, "step": 710 }, { "epoch": 0.2963877740043223, "grad_norm": 24.54779334825758, "learning_rate": 7.98888888888889e-06, "loss": 19.4289, "step": 720 }, { "epoch": 0.3005042708654935, "grad_norm": 20.193177185866038, "learning_rate": 8.1e-06, "loss": 19.2373, "step": 730 }, { "epoch": 0.30462076772666463, "grad_norm": 60.48422812921962, "learning_rate": 8.211111111111112e-06, "loss": 19.173, "step": 740 }, { "epoch": 0.30873726458783574, "grad_norm": 27.558098824852753, "learning_rate": 8.322222222222223e-06, "loss": 18.9043, "step": 750 }, { "epoch": 0.3128537614490069, "grad_norm": 29.51167246824426, "learning_rate": 8.433333333333334e-06, "loss": 18.6651, "step": 760 }, { "epoch": 0.31697025831017805, "grad_norm": 21.93310893699215, "learning_rate": 8.544444444444445e-06, "loss": 18.4818, "step": 770 }, { "epoch": 0.32108675517134916, "grad_norm": 51.99252088836799, "learning_rate": 8.655555555555557e-06, "loss": 18.4864, "step": 780 }, { "epoch": 0.3252032520325203, "grad_norm": 35.01362198000449, "learning_rate": 8.766666666666669e-06, "loss": 18.205, "step": 790 }, { "epoch": 0.3293197488936915, "grad_norm": 30.09623662803406, "learning_rate": 8.877777777777779e-06, "loss": 18.0342, "step": 800 }, { "epoch": 0.33343624575486264, "grad_norm": 55.16314161967726, "learning_rate": 8.988888888888889e-06, "loss": 17.8646, "step": 810 }, { "epoch": 0.33755274261603374, "grad_norm": 33.375878351461154, "learning_rate": 9.100000000000001e-06, "loss": 17.6275, "step": 820 }, { "epoch": 0.3416692394772049, "grad_norm": 27.20030408565347, "learning_rate": 9.211111111111111e-06, "loss": 17.53, "step": 830 }, { "epoch": 0.34578573633837606, "grad_norm": 44.94165316928541, "learning_rate": 9.322222222222223e-06, "loss": 17.4118, "step": 840 }, { "epoch": 0.34990223319954716, "grad_norm": 51.21107811701123, "learning_rate": 9.433333333333335e-06, "loss": 17.2221, "step": 850 }, { "epoch": 0.3540187300607183, "grad_norm": 48.69081492082153, "learning_rate": 9.544444444444445e-06, "loss": 17.0648, "step": 860 }, { "epoch": 0.3581352269218895, "grad_norm": 59.568062971869644, "learning_rate": 9.655555555555556e-06, "loss": 16.9709, "step": 870 }, { "epoch": 0.36225172378306064, "grad_norm": 48.20595634997982, "learning_rate": 9.766666666666667e-06, "loss": 16.7922, "step": 880 }, { "epoch": 0.36636822064423175, "grad_norm": 38.89100659846126, "learning_rate": 9.877777777777778e-06, "loss": 16.5606, "step": 890 }, { "epoch": 0.3704847175054029, "grad_norm": 55.476242446929724, "learning_rate": 9.98888888888889e-06, "loss": 16.5196, "step": 900 }, { "epoch": 0.37460121436657406, "grad_norm": 33.8871713799869, "learning_rate": 9.996907216494847e-06, "loss": 16.2859, "step": 910 }, { "epoch": 0.37871771122774517, "grad_norm": 48.67199287721736, "learning_rate": 9.993470790378008e-06, "loss": 16.1253, "step": 920 }, { "epoch": 0.38283420808891633, "grad_norm": 53.10677273121955, "learning_rate": 9.99003436426117e-06, "loss": 16.1184, "step": 930 }, { "epoch": 0.3869507049500875, "grad_norm": 36.47115886963749, "learning_rate": 9.986597938144331e-06, "loss": 15.8454, "step": 940 }, { "epoch": 0.3910672018112586, "grad_norm": 46.9950180770148, "learning_rate": 9.983161512027493e-06, "loss": 15.7934, "step": 950 }, { "epoch": 0.39518369867242975, "grad_norm": 41.780425293570616, "learning_rate": 9.979725085910654e-06, "loss": 15.7013, "step": 960 }, { "epoch": 0.3993001955336009, "grad_norm": 61.01443519953337, "learning_rate": 9.976288659793816e-06, "loss": 15.5447, "step": 970 }, { "epoch": 0.40341669239477207, "grad_norm": 37.005722827889784, "learning_rate": 9.972852233676977e-06, "loss": 15.4402, "step": 980 }, { "epoch": 0.4075331892559432, "grad_norm": 34.50549181078069, "learning_rate": 9.969415807560139e-06, "loss": 15.3771, "step": 990 }, { "epoch": 0.41164968611711433, "grad_norm": 43.56802220640922, "learning_rate": 9.965979381443299e-06, "loss": 15.1859, "step": 1000 }, { "epoch": 0.4157661829782855, "grad_norm": 44.27192419759802, "learning_rate": 9.96254295532646e-06, "loss": 15.1377, "step": 1010 }, { "epoch": 0.4198826798394566, "grad_norm": 54.39835842981886, "learning_rate": 9.959106529209622e-06, "loss": 15.0264, "step": 1020 }, { "epoch": 0.42399917670062776, "grad_norm": 39.41791238776903, "learning_rate": 9.955670103092783e-06, "loss": 14.9343, "step": 1030 }, { "epoch": 0.4281156735617989, "grad_norm": 33.82937492863744, "learning_rate": 9.952233676975945e-06, "loss": 14.7589, "step": 1040 }, { "epoch": 0.4322321704229701, "grad_norm": 40.479975837330905, "learning_rate": 9.948797250859106e-06, "loss": 14.6838, "step": 1050 }, { "epoch": 0.4363486672841412, "grad_norm": 49.56506719825334, "learning_rate": 9.945360824742268e-06, "loss": 14.5806, "step": 1060 }, { "epoch": 0.44046516414531234, "grad_norm": 43.92728436690805, "learning_rate": 9.94192439862543e-06, "loss": 14.5519, "step": 1070 }, { "epoch": 0.4445816610064835, "grad_norm": 38.083124431784405, "learning_rate": 9.938487972508592e-06, "loss": 14.4566, "step": 1080 }, { "epoch": 0.4486981578676546, "grad_norm": 40.83368623786197, "learning_rate": 9.935051546391754e-06, "loss": 14.4637, "step": 1090 }, { "epoch": 0.45281465472882576, "grad_norm": 39.888961137074325, "learning_rate": 9.931615120274915e-06, "loss": 14.2926, "step": 1100 }, { "epoch": 0.4569311515899969, "grad_norm": 52.98917099950452, "learning_rate": 9.928178694158077e-06, "loss": 14.2284, "step": 1110 }, { "epoch": 0.4610476484511681, "grad_norm": 39.86769855717651, "learning_rate": 9.924742268041238e-06, "loss": 14.1538, "step": 1120 }, { "epoch": 0.4651641453123392, "grad_norm": 41.47546966771517, "learning_rate": 9.9213058419244e-06, "loss": 14.1268, "step": 1130 }, { "epoch": 0.46928064217351034, "grad_norm": 43.66832808351295, "learning_rate": 9.917869415807561e-06, "loss": 14.0239, "step": 1140 }, { "epoch": 0.4733971390346815, "grad_norm": 38.15090916854303, "learning_rate": 9.914432989690723e-06, "loss": 13.9388, "step": 1150 }, { "epoch": 0.4775136358958526, "grad_norm": 34.56956210917117, "learning_rate": 9.910996563573884e-06, "loss": 13.911, "step": 1160 }, { "epoch": 0.48163013275702377, "grad_norm": 33.31934413400173, "learning_rate": 9.907560137457046e-06, "loss": 13.8416, "step": 1170 }, { "epoch": 0.4857466296181949, "grad_norm": 37.93411062451452, "learning_rate": 9.904123711340207e-06, "loss": 13.8095, "step": 1180 }, { "epoch": 0.4898631264793661, "grad_norm": 38.20924261082129, "learning_rate": 9.900687285223369e-06, "loss": 13.7295, "step": 1190 }, { "epoch": 0.4939796233405372, "grad_norm": 53.63569573152946, "learning_rate": 9.89725085910653e-06, "loss": 13.6506, "step": 1200 }, { "epoch": 0.49809612020170835, "grad_norm": 43.14530877212232, "learning_rate": 9.893814432989692e-06, "loss": 13.6186, "step": 1210 }, { "epoch": 0.5022126170628795, "grad_norm": 49.03916689519157, "learning_rate": 9.890378006872853e-06, "loss": 13.6416, "step": 1220 }, { "epoch": 0.5063291139240507, "grad_norm": 36.49026973775023, "learning_rate": 9.886941580756015e-06, "loss": 13.574, "step": 1230 }, { "epoch": 0.5104456107852218, "grad_norm": 32.76071554080421, "learning_rate": 9.883505154639176e-06, "loss": 13.4854, "step": 1240 }, { "epoch": 0.5145621076463929, "grad_norm": 36.789924557345806, "learning_rate": 9.880068728522338e-06, "loss": 13.3827, "step": 1250 }, { "epoch": 0.5186786045075641, "grad_norm": 28.079567041126435, "learning_rate": 9.8766323024055e-06, "loss": 13.3305, "step": 1260 }, { "epoch": 0.5227951013687352, "grad_norm": 43.55514700081209, "learning_rate": 9.87319587628866e-06, "loss": 13.33, "step": 1270 }, { "epoch": 0.5269115982299063, "grad_norm": 28.76115488681788, "learning_rate": 9.869759450171822e-06, "loss": 13.2651, "step": 1280 }, { "epoch": 0.5310280950910775, "grad_norm": 37.358128749691296, "learning_rate": 9.866323024054984e-06, "loss": 13.2312, "step": 1290 }, { "epoch": 0.5351445919522486, "grad_norm": 44.992288758478345, "learning_rate": 9.862886597938145e-06, "loss": 13.1897, "step": 1300 }, { "epoch": 0.5392610888134198, "grad_norm": 28.47379704494871, "learning_rate": 9.859450171821307e-06, "loss": 13.1063, "step": 1310 }, { "epoch": 0.5433775856745909, "grad_norm": 31.796429799283633, "learning_rate": 9.856013745704468e-06, "loss": 13.0747, "step": 1320 }, { "epoch": 0.547494082535762, "grad_norm": 39.38678551108492, "learning_rate": 9.85257731958763e-06, "loss": 13.0861, "step": 1330 }, { "epoch": 0.5516105793969333, "grad_norm": 38.812099741482996, "learning_rate": 9.849140893470791e-06, "loss": 13.046, "step": 1340 }, { "epoch": 0.5557270762581044, "grad_norm": 34.79929463071014, "learning_rate": 9.845704467353953e-06, "loss": 13.0339, "step": 1350 }, { "epoch": 0.5598435731192755, "grad_norm": 36.095752723061416, "learning_rate": 9.842268041237114e-06, "loss": 12.9433, "step": 1360 }, { "epoch": 0.5639600699804467, "grad_norm": 36.27956418944883, "learning_rate": 9.838831615120276e-06, "loss": 12.907, "step": 1370 }, { "epoch": 0.5680765668416178, "grad_norm": 35.72628600227518, "learning_rate": 9.835395189003437e-06, "loss": 12.91, "step": 1380 }, { "epoch": 0.5721930637027889, "grad_norm": 36.2974491311879, "learning_rate": 9.831958762886599e-06, "loss": 12.8805, "step": 1390 }, { "epoch": 0.5763095605639601, "grad_norm": 38.753865801889205, "learning_rate": 9.82852233676976e-06, "loss": 12.8487, "step": 1400 }, { "epoch": 0.5804260574251312, "grad_norm": 37.15806127726735, "learning_rate": 9.825085910652922e-06, "loss": 12.8255, "step": 1410 }, { "epoch": 0.5845425542863023, "grad_norm": 31.930169790036125, "learning_rate": 9.821649484536083e-06, "loss": 12.7318, "step": 1420 }, { "epoch": 0.5886590511474735, "grad_norm": 46.704762225618985, "learning_rate": 9.818213058419245e-06, "loss": 12.8322, "step": 1430 }, { "epoch": 0.5927755480086446, "grad_norm": 33.776587810887825, "learning_rate": 9.814776632302406e-06, "loss": 12.7815, "step": 1440 }, { "epoch": 0.5968920448698158, "grad_norm": 29.58229351266127, "learning_rate": 9.811340206185568e-06, "loss": 12.7486, "step": 1450 }, { "epoch": 0.601008541730987, "grad_norm": 33.63398991455025, "learning_rate": 9.80790378006873e-06, "loss": 12.6896, "step": 1460 }, { "epoch": 0.605125038592158, "grad_norm": 36.832689858066715, "learning_rate": 9.804467353951891e-06, "loss": 12.6699, "step": 1470 }, { "epoch": 0.6092415354533293, "grad_norm": 37.43208595185383, "learning_rate": 9.801030927835052e-06, "loss": 12.5471, "step": 1480 }, { "epoch": 0.6133580323145004, "grad_norm": 33.7941307098917, "learning_rate": 9.797594501718214e-06, "loss": 12.6142, "step": 1490 }, { "epoch": 0.6174745291756715, "grad_norm": 31.9466158932975, "learning_rate": 9.794158075601375e-06, "loss": 12.5338, "step": 1500 }, { "epoch": 0.6215910260368427, "grad_norm": 38.30578087105521, "learning_rate": 9.790721649484537e-06, "loss": 12.4764, "step": 1510 }, { "epoch": 0.6257075228980138, "grad_norm": 32.61697454595358, "learning_rate": 9.787285223367698e-06, "loss": 12.4952, "step": 1520 }, { "epoch": 0.6298240197591849, "grad_norm": 40.16758133155219, "learning_rate": 9.78384879725086e-06, "loss": 12.4546, "step": 1530 }, { "epoch": 0.6339405166203561, "grad_norm": 48.80638115137875, "learning_rate": 9.780412371134021e-06, "loss": 12.4843, "step": 1540 }, { "epoch": 0.6380570134815272, "grad_norm": 37.475171347455756, "learning_rate": 9.776975945017183e-06, "loss": 12.4931, "step": 1550 }, { "epoch": 0.6421735103426983, "grad_norm": 33.28595513208406, "learning_rate": 9.773539518900344e-06, "loss": 12.4005, "step": 1560 }, { "epoch": 0.6462900072038695, "grad_norm": 31.086866920620285, "learning_rate": 9.770103092783506e-06, "loss": 12.3441, "step": 1570 }, { "epoch": 0.6504065040650406, "grad_norm": 39.3394583771368, "learning_rate": 9.766666666666667e-06, "loss": 12.2734, "step": 1580 }, { "epoch": 0.6545230009262117, "grad_norm": 32.802912711135214, "learning_rate": 9.763230240549829e-06, "loss": 12.3482, "step": 1590 }, { "epoch": 0.658639497787383, "grad_norm": 37.29399518826948, "learning_rate": 9.75979381443299e-06, "loss": 12.3565, "step": 1600 }, { "epoch": 0.6627559946485541, "grad_norm": 31.346208761120682, "learning_rate": 9.756357388316152e-06, "loss": 12.2918, "step": 1610 }, { "epoch": 0.6668724915097253, "grad_norm": 32.38506378128921, "learning_rate": 9.752920962199313e-06, "loss": 12.2984, "step": 1620 }, { "epoch": 0.6709889883708964, "grad_norm": 37.55618381493301, "learning_rate": 9.749484536082475e-06, "loss": 12.2223, "step": 1630 }, { "epoch": 0.6751054852320675, "grad_norm": 30.159408332251935, "learning_rate": 9.746048109965636e-06, "loss": 12.2059, "step": 1640 }, { "epoch": 0.6792219820932387, "grad_norm": 33.64269413817189, "learning_rate": 9.742611683848798e-06, "loss": 12.1934, "step": 1650 }, { "epoch": 0.6833384789544098, "grad_norm": 33.350706787266056, "learning_rate": 9.73917525773196e-06, "loss": 12.2187, "step": 1660 }, { "epoch": 0.6874549758155809, "grad_norm": 33.39405862288003, "learning_rate": 9.735738831615121e-06, "loss": 12.163, "step": 1670 }, { "epoch": 0.6915714726767521, "grad_norm": 33.41635090076034, "learning_rate": 9.732302405498283e-06, "loss": 12.1662, "step": 1680 }, { "epoch": 0.6956879695379232, "grad_norm": 30.14281470411853, "learning_rate": 9.728865979381444e-06, "loss": 12.2065, "step": 1690 }, { "epoch": 0.6998044663990943, "grad_norm": 30.467396684661566, "learning_rate": 9.725429553264606e-06, "loss": 12.1291, "step": 1700 }, { "epoch": 0.7039209632602655, "grad_norm": 30.441530111439768, "learning_rate": 9.721993127147767e-06, "loss": 12.0492, "step": 1710 }, { "epoch": 0.7080374601214366, "grad_norm": 28.49347966966388, "learning_rate": 9.718556701030929e-06, "loss": 12.0813, "step": 1720 }, { "epoch": 0.7121539569826077, "grad_norm": 30.721181306779684, "learning_rate": 9.71512027491409e-06, "loss": 12.0821, "step": 1730 }, { "epoch": 0.716270453843779, "grad_norm": 29.129251982891667, "learning_rate": 9.711683848797252e-06, "loss": 12.0637, "step": 1740 }, { "epoch": 0.7203869507049501, "grad_norm": 29.95019721435932, "learning_rate": 9.708247422680413e-06, "loss": 11.9994, "step": 1750 }, { "epoch": 0.7245034475661213, "grad_norm": 32.81918337349151, "learning_rate": 9.704810996563575e-06, "loss": 12.024, "step": 1760 }, { "epoch": 0.7286199444272924, "grad_norm": 39.5144099446638, "learning_rate": 9.701374570446736e-06, "loss": 12.0285, "step": 1770 }, { "epoch": 0.7327364412884635, "grad_norm": 31.653909615694747, "learning_rate": 9.697938144329898e-06, "loss": 11.9479, "step": 1780 }, { "epoch": 0.7368529381496347, "grad_norm": 33.40571679023385, "learning_rate": 9.694501718213059e-06, "loss": 11.9523, "step": 1790 }, { "epoch": 0.7409694350108058, "grad_norm": 37.473942426771224, "learning_rate": 9.69106529209622e-06, "loss": 11.9416, "step": 1800 }, { "epoch": 0.7450859318719769, "grad_norm": 36.94155127706317, "learning_rate": 9.687628865979382e-06, "loss": 12.0463, "step": 1810 }, { "epoch": 0.7492024287331481, "grad_norm": 37.68814388273857, "learning_rate": 9.684192439862544e-06, "loss": 11.8785, "step": 1820 }, { "epoch": 0.7533189255943192, "grad_norm": 28.366410820050916, "learning_rate": 9.680756013745705e-06, "loss": 11.8984, "step": 1830 }, { "epoch": 0.7574354224554903, "grad_norm": 32.286183742630165, "learning_rate": 9.677319587628867e-06, "loss": 11.7795, "step": 1840 }, { "epoch": 0.7615519193166616, "grad_norm": 34.20137530626946, "learning_rate": 9.673883161512028e-06, "loss": 11.7833, "step": 1850 }, { "epoch": 0.7656684161778327, "grad_norm": 26.974205102100083, "learning_rate": 9.67044673539519e-06, "loss": 11.8231, "step": 1860 }, { "epoch": 0.7697849130390038, "grad_norm": 30.78227640084708, "learning_rate": 9.667010309278351e-06, "loss": 11.839, "step": 1870 }, { "epoch": 0.773901409900175, "grad_norm": 32.775223259236476, "learning_rate": 9.663573883161513e-06, "loss": 11.7576, "step": 1880 }, { "epoch": 0.7780179067613461, "grad_norm": 32.09910452344205, "learning_rate": 9.660137457044674e-06, "loss": 11.8203, "step": 1890 }, { "epoch": 0.7821344036225172, "grad_norm": 34.679912416674696, "learning_rate": 9.656701030927836e-06, "loss": 11.7395, "step": 1900 }, { "epoch": 0.7862509004836884, "grad_norm": 41.08474046950697, "learning_rate": 9.653264604810997e-06, "loss": 11.7656, "step": 1910 }, { "epoch": 0.7903673973448595, "grad_norm": 43.79171589552821, "learning_rate": 9.649828178694159e-06, "loss": 11.7157, "step": 1920 }, { "epoch": 0.7944838942060307, "grad_norm": 32.06890784949689, "learning_rate": 9.64639175257732e-06, "loss": 11.7633, "step": 1930 }, { "epoch": 0.7986003910672018, "grad_norm": 33.88840596948513, "learning_rate": 9.642955326460482e-06, "loss": 11.7696, "step": 1940 }, { "epoch": 0.8027168879283729, "grad_norm": 43.3525380610554, "learning_rate": 9.639518900343643e-06, "loss": 11.6768, "step": 1950 }, { "epoch": 0.8068333847895441, "grad_norm": 29.03141895521922, "learning_rate": 9.636082474226805e-06, "loss": 11.6438, "step": 1960 }, { "epoch": 0.8109498816507152, "grad_norm": 31.577350376305315, "learning_rate": 9.632646048109966e-06, "loss": 11.648, "step": 1970 }, { "epoch": 0.8150663785118863, "grad_norm": 29.395462355828993, "learning_rate": 9.629209621993128e-06, "loss": 11.5621, "step": 1980 }, { "epoch": 0.8191828753730576, "grad_norm": 36.070659840431695, "learning_rate": 9.625773195876289e-06, "loss": 11.6605, "step": 1990 }, { "epoch": 0.8232993722342287, "grad_norm": 40.63936989861702, "learning_rate": 9.62233676975945e-06, "loss": 11.6847, "step": 2000 }, { "epoch": 0.8274158690953998, "grad_norm": 28.74096555707873, "learning_rate": 9.618900343642612e-06, "loss": 11.5951, "step": 2010 }, { "epoch": 0.831532365956571, "grad_norm": 26.857379564051325, "learning_rate": 9.615463917525774e-06, "loss": 11.5425, "step": 2020 }, { "epoch": 0.8356488628177421, "grad_norm": 34.26526481929795, "learning_rate": 9.612027491408935e-06, "loss": 11.5395, "step": 2030 }, { "epoch": 0.8397653596789132, "grad_norm": 39.61591003341877, "learning_rate": 9.608591065292097e-06, "loss": 11.5239, "step": 2040 }, { "epoch": 0.8438818565400844, "grad_norm": 32.799457497612636, "learning_rate": 9.605154639175258e-06, "loss": 11.5221, "step": 2050 }, { "epoch": 0.8479983534012555, "grad_norm": 30.46702989419665, "learning_rate": 9.60171821305842e-06, "loss": 11.5188, "step": 2060 }, { "epoch": 0.8521148502624267, "grad_norm": 36.16227939472805, "learning_rate": 9.598281786941581e-06, "loss": 11.5045, "step": 2070 }, { "epoch": 0.8562313471235978, "grad_norm": 35.47038057679002, "learning_rate": 9.594845360824743e-06, "loss": 11.5307, "step": 2080 }, { "epoch": 0.8603478439847689, "grad_norm": 32.257372818520146, "learning_rate": 9.591408934707904e-06, "loss": 11.523, "step": 2090 }, { "epoch": 0.8644643408459401, "grad_norm": 29.92970511160102, "learning_rate": 9.587972508591066e-06, "loss": 11.5006, "step": 2100 }, { "epoch": 0.8685808377071113, "grad_norm": 31.548453221760763, "learning_rate": 9.584536082474227e-06, "loss": 11.4492, "step": 2110 }, { "epoch": 0.8726973345682824, "grad_norm": 34.57267127412313, "learning_rate": 9.581099656357389e-06, "loss": 11.4804, "step": 2120 }, { "epoch": 0.8768138314294536, "grad_norm": 34.17219698271619, "learning_rate": 9.57766323024055e-06, "loss": 11.4529, "step": 2130 }, { "epoch": 0.8809303282906247, "grad_norm": 29.479641794210973, "learning_rate": 9.574226804123712e-06, "loss": 11.3922, "step": 2140 }, { "epoch": 0.8850468251517958, "grad_norm": 32.38400767680429, "learning_rate": 9.570790378006873e-06, "loss": 11.394, "step": 2150 }, { "epoch": 0.889163322012967, "grad_norm": 32.32981900594448, "learning_rate": 9.567353951890035e-06, "loss": 11.3841, "step": 2160 }, { "epoch": 0.8932798188741381, "grad_norm": 33.61678562259265, "learning_rate": 9.563917525773196e-06, "loss": 11.3688, "step": 2170 }, { "epoch": 0.8973963157353092, "grad_norm": 32.71587409986399, "learning_rate": 9.560481099656358e-06, "loss": 11.3808, "step": 2180 }, { "epoch": 0.9015128125964804, "grad_norm": 29.54893232627574, "learning_rate": 9.55704467353952e-06, "loss": 11.3336, "step": 2190 }, { "epoch": 0.9056293094576515, "grad_norm": 32.06137522253644, "learning_rate": 9.55360824742268e-06, "loss": 11.3034, "step": 2200 }, { "epoch": 0.9097458063188227, "grad_norm": 36.467602001920255, "learning_rate": 9.550171821305842e-06, "loss": 11.3092, "step": 2210 }, { "epoch": 0.9138623031799938, "grad_norm": 36.697441519061755, "learning_rate": 9.546735395189004e-06, "loss": 11.3535, "step": 2220 }, { "epoch": 0.9179788000411649, "grad_norm": 29.195704697132054, "learning_rate": 9.543298969072165e-06, "loss": 11.2906, "step": 2230 }, { "epoch": 0.9220952969023362, "grad_norm": 28.12150721519504, "learning_rate": 9.539862542955327e-06, "loss": 11.2277, "step": 2240 }, { "epoch": 0.9262117937635073, "grad_norm": 28.28187759539184, "learning_rate": 9.536426116838488e-06, "loss": 11.2413, "step": 2250 }, { "epoch": 0.9303282906246784, "grad_norm": 38.194498763414195, "learning_rate": 9.53298969072165e-06, "loss": 11.2062, "step": 2260 }, { "epoch": 0.9344447874858496, "grad_norm": 30.60316989712369, "learning_rate": 9.529553264604811e-06, "loss": 11.2868, "step": 2270 }, { "epoch": 0.9385612843470207, "grad_norm": 32.2566760579608, "learning_rate": 9.526116838487973e-06, "loss": 11.3455, "step": 2280 }, { "epoch": 0.9426777812081918, "grad_norm": 29.363121550952414, "learning_rate": 9.522680412371134e-06, "loss": 11.2271, "step": 2290 }, { "epoch": 0.946794278069363, "grad_norm": 34.44659489587604, "learning_rate": 9.519243986254296e-06, "loss": 11.2572, "step": 2300 }, { "epoch": 0.9509107749305341, "grad_norm": 38.421619327615275, "learning_rate": 9.515807560137457e-06, "loss": 11.2059, "step": 2310 }, { "epoch": 0.9550272717917052, "grad_norm": 28.45314623909409, "learning_rate": 9.512371134020619e-06, "loss": 11.2005, "step": 2320 }, { "epoch": 0.9591437686528764, "grad_norm": 33.71882176291607, "learning_rate": 9.50893470790378e-06, "loss": 11.1696, "step": 2330 }, { "epoch": 0.9632602655140475, "grad_norm": 40.284639005118564, "learning_rate": 9.505498281786942e-06, "loss": 11.1289, "step": 2340 }, { "epoch": 0.9673767623752186, "grad_norm": 29.578038874639823, "learning_rate": 9.502061855670103e-06, "loss": 11.1945, "step": 2350 }, { "epoch": 0.9714932592363899, "grad_norm": 30.78279090155006, "learning_rate": 9.498625429553265e-06, "loss": 11.1547, "step": 2360 }, { "epoch": 0.975609756097561, "grad_norm": 32.32491917371623, "learning_rate": 9.495189003436426e-06, "loss": 11.1499, "step": 2370 }, { "epoch": 0.9797262529587322, "grad_norm": 33.912601882090534, "learning_rate": 9.491752577319588e-06, "loss": 11.0843, "step": 2380 }, { "epoch": 0.9838427498199033, "grad_norm": 33.636974029662824, "learning_rate": 9.48831615120275e-06, "loss": 11.0857, "step": 2390 }, { "epoch": 0.9879592466810744, "grad_norm": 28.479925241415103, "learning_rate": 9.48487972508591e-06, "loss": 11.117, "step": 2400 }, { "epoch": 0.9920757435422456, "grad_norm": 32.19633310187057, "learning_rate": 9.481443298969072e-06, "loss": 11.1586, "step": 2410 }, { "epoch": 0.9961922404034167, "grad_norm": 30.24939985897427, "learning_rate": 9.478006872852234e-06, "loss": 11.0449, "step": 2420 }, { "epoch": 1.0, "grad_norm": 27.59918285796063, "learning_rate": 9.474570446735395e-06, "loss": 10.2576, "step": 2430 }, { "epoch": 1.004116496861171, "grad_norm": 29.145692709878713, "learning_rate": 9.471134020618557e-06, "loss": 10.9205, "step": 2440 }, { "epoch": 1.0082329937223422, "grad_norm": 34.22402623391047, "learning_rate": 9.467697594501718e-06, "loss": 10.8674, "step": 2450 }, { "epoch": 1.0123494905835135, "grad_norm": 31.116476736190727, "learning_rate": 9.46426116838488e-06, "loss": 10.9685, "step": 2460 }, { "epoch": 1.0164659874446846, "grad_norm": 31.010011036576245, "learning_rate": 9.460824742268041e-06, "loss": 10.8758, "step": 2470 }, { "epoch": 1.0205824843058557, "grad_norm": 33.554395898942225, "learning_rate": 9.457388316151203e-06, "loss": 10.8832, "step": 2480 }, { "epoch": 1.0246989811670268, "grad_norm": 33.7710211448291, "learning_rate": 9.453951890034366e-06, "loss": 10.8374, "step": 2490 }, { "epoch": 1.028815478028198, "grad_norm": 36.176567342791, "learning_rate": 9.450515463917528e-06, "loss": 10.8073, "step": 2500 }, { "epoch": 1.028815478028198, "eval_loss": 3.158303737640381, "eval_runtime": 3671.6298, "eval_samples_per_second": 149.924, "eval_steps_per_second": 0.293, "step": 2500 } ], "logging_steps": 10, "max_steps": 30000, "num_input_tokens_seen": 0, "num_train_epochs": 13, "save_steps": 2500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3776084605665280.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }