Heisen0928's picture
Upload folder using huggingface_hub
184f0af verified
Raw
History Blame Contribute Delete
41.1 kB
{"global_step": 10, "epoch": 0.004116496861171143, "loss": 79.4593, "grad_norm": 722.9849266591084, "learning_rate": 1.0000000000000001e-07}
{"global_step": 20, "epoch": 0.008232993722342286, "loss": 79.3183, "grad_norm": 713.4423322869009, "learning_rate": 2.1111111111111113e-07}
{"global_step": 30, "epoch": 0.01234949058351343, "loss": 78.0929, "grad_norm": 619.0335944754007, "learning_rate": 3.2222222222222227e-07}
{"global_step": 40, "epoch": 0.016465987444684572, "loss": 75.0743, "grad_norm": 439.772626183607, "learning_rate": 4.333333333333334e-07}
{"global_step": 50, "epoch": 0.020582484305855717, "loss": 69.3428, "grad_norm": 281.08070517386403, "learning_rate": 5.444444444444444e-07}
{"global_step": 60, "epoch": 0.02469898116702686, "loss": 64.8186, "grad_norm": 238.72306538307805, "learning_rate": 6.555555555555556e-07}
{"global_step": 70, "epoch": 0.028815478028198005, "loss": 59.6238, "grad_norm": 265.61586056265025, "learning_rate": 7.666666666666667e-07}
{"global_step": 80, "epoch": 0.032931974889369144, "loss": 52.8731, "grad_norm": 92.19312055336448, "learning_rate": 8.777777777777778e-07}
{"global_step": 90, "epoch": 0.03704847175054029, "loss": 49.676, "grad_norm": 45.48770884961453, "learning_rate": 9.88888888888889e-07}
{"global_step": 100, "epoch": 0.041164968611711435, "loss": 48.4892, "grad_norm": 27.08086194848908, "learning_rate": 1.1e-06}
{"global_step": 110, "epoch": 0.04528146547288258, "loss": 48.0497, "grad_norm": 19.32379182470467, "learning_rate": 1.2111111111111111e-06}
{"global_step": 120, "epoch": 0.04939796233405372, "loss": 47.7781, "grad_norm": 16.380874066084196, "learning_rate": 1.3222222222222222e-06}
{"global_step": 130, "epoch": 0.053514459195224864, "loss": 47.5811, "grad_norm": 15.371140813384557, "learning_rate": 1.4333333333333335e-06}
{"global_step": 140, "epoch": 0.05763095605639601, "loss": 47.4215, "grad_norm": 15.84809592222176, "learning_rate": 1.5444444444444446e-06}
{"global_step": 150, "epoch": 0.06174745291756715, "loss": 47.2557, "grad_norm": 16.994317821440845, "learning_rate": 1.6555555555555559e-06}
{"global_step": 160, "epoch": 0.06586394977873829, "loss": 47.0796, "grad_norm": 18.743638967461997, "learning_rate": 1.7666666666666668e-06}
{"global_step": 170, "epoch": 0.06998044663990943, "loss": 46.8693, "grad_norm": 20.92550528148297, "learning_rate": 1.8777777777777778e-06}
{"global_step": 180, "epoch": 0.07409694350108058, "loss": 46.6118, "grad_norm": 23.935804629158547, "learning_rate": 1.988888888888889e-06}
{"global_step": 190, "epoch": 0.07821344036225172, "loss": 46.267, "grad_norm": 28.229572692610986, "learning_rate": 2.1000000000000002e-06}
{"global_step": 200, "epoch": 0.08232993722342287, "loss": 45.7269, "grad_norm": 34.37693332521861, "learning_rate": 2.2111111111111113e-06}
{"global_step": 210, "epoch": 0.08644643408459401, "loss": 44.9702, "grad_norm": 43.4433932596704, "learning_rate": 2.3222222222222224e-06}
{"global_step": 220, "epoch": 0.09056293094576516, "loss": 43.7522, "grad_norm": 58.28038941283432, "learning_rate": 2.4333333333333335e-06}
{"global_step": 230, "epoch": 0.09467942780693629, "loss": 41.9094, "grad_norm": 71.69823530504809, "learning_rate": 2.5444444444444446e-06}
{"global_step": 240, "epoch": 0.09879592466810744, "loss": 39.6286, "grad_norm": 69.78057028859453, "learning_rate": 2.6555555555555556e-06}
{"global_step": 250, "epoch": 0.10291242152927858, "loss": 37.279, "grad_norm": 65.2702064062225, "learning_rate": 2.766666666666667e-06}
{"global_step": 260, "epoch": 0.10702891839044973, "loss": 34.8486, "grad_norm": 62.147050273188626, "learning_rate": 2.8777777777777782e-06}
{"global_step": 270, "epoch": 0.11114541525162087, "loss": 32.3669, "grad_norm": 58.3163917534024, "learning_rate": 2.988888888888889e-06}
{"global_step": 280, "epoch": 0.11526191211279202, "loss": 29.9582, "grad_norm": 73.8699537282808, "learning_rate": 3.1000000000000004e-06}
{"global_step": 290, "epoch": 0.11937840897396315, "loss": 27.8124, "grad_norm": 59.22493609025033, "learning_rate": 3.2111111111111115e-06}
{"global_step": 300, "epoch": 0.1234949058351343, "loss": 25.908, "grad_norm": 42.636994581457614, "learning_rate": 3.322222222222222e-06}
{"global_step": 310, "epoch": 0.12761140269630544, "loss": 24.4843, "grad_norm": 36.81511952341932, "learning_rate": 3.4333333333333336e-06}
{"global_step": 320, "epoch": 0.13172789955747657, "loss": 23.4653, "grad_norm": 27.381915904890327, "learning_rate": 3.5444444444444447e-06}
{"global_step": 330, "epoch": 0.13584439641864773, "loss": 22.7909, "grad_norm": 23.598517571067614, "learning_rate": 3.6555555555555562e-06}
{"global_step": 340, "epoch": 0.13996089327981887, "loss": 22.3688, "grad_norm": 23.294478325249578, "learning_rate": 3.766666666666667e-06}
{"global_step": 350, "epoch": 0.14407739014099002, "loss": 22.0982, "grad_norm": 20.093643447034683, "learning_rate": 3.877777777777778e-06}
{"global_step": 360, "epoch": 0.14819388700216116, "loss": 21.9086, "grad_norm": 19.394487535911193, "learning_rate": 3.9888888888888895e-06}
{"global_step": 370, "epoch": 0.15231038386333232, "loss": 21.7863, "grad_norm": 18.119665979499104, "learning_rate": 4.1e-06}
{"global_step": 380, "epoch": 0.15642688072450345, "loss": 21.6972, "grad_norm": 17.07344526731236, "learning_rate": 4.211111111111112e-06}
{"global_step": 390, "epoch": 0.16054337758567458, "loss": 21.6276, "grad_norm": 17.2895867054574, "learning_rate": 4.322222222222223e-06}
{"global_step": 400, "epoch": 0.16465987444684574, "loss": 21.5774, "grad_norm": 18.055980258041934, "learning_rate": 4.433333333333334e-06}
{"global_step": 410, "epoch": 0.16877637130801687, "loss": 21.5305, "grad_norm": 17.602944740266267, "learning_rate": 4.544444444444445e-06}
{"global_step": 420, "epoch": 0.17289286816918803, "loss": 21.4996, "grad_norm": 17.047319458414727, "learning_rate": 4.655555555555556e-06}
{"global_step": 430, "epoch": 0.17700936503035916, "loss": 21.4706, "grad_norm": 17.326432935336033, "learning_rate": 4.766666666666667e-06}
{"global_step": 440, "epoch": 0.18112586189153032, "loss": 21.4449, "grad_norm": 17.554696739458905, "learning_rate": 4.877777777777778e-06}
{"global_step": 450, "epoch": 0.18524235875270145, "loss": 21.4242, "grad_norm": 16.57900811727561, "learning_rate": 4.988888888888889e-06}
{"global_step": 460, "epoch": 0.18935885561387258, "loss": 21.4136, "grad_norm": 16.41658497950142, "learning_rate": 5.1e-06}
{"global_step": 470, "epoch": 0.19347535247504374, "loss": 21.3904, "grad_norm": 14.851397065124416, "learning_rate": 5.211111111111111e-06}
{"global_step": 480, "epoch": 0.19759184933621488, "loss": 21.3748, "grad_norm": 16.86165644628761, "learning_rate": 5.322222222222223e-06}
{"global_step": 490, "epoch": 0.20170834619738603, "loss": 21.3649, "grad_norm": 16.021934417394476, "learning_rate": 5.4333333333333335e-06}
{"global_step": 500, "epoch": 0.20582484305855717, "loss": 21.357, "grad_norm": 16.71987330752045, "learning_rate": 5.544444444444445e-06}
{"global_step": 510, "epoch": 0.2099413399197283, "loss": 21.345, "grad_norm": 16.033384348770003, "learning_rate": 5.6555555555555566e-06}
{"global_step": 520, "epoch": 0.21405783678089946, "loss": 21.3308, "grad_norm": 16.503614387128653, "learning_rate": 5.766666666666667e-06}
{"global_step": 530, "epoch": 0.2181743336420706, "loss": 21.3167, "grad_norm": 16.5197017811903, "learning_rate": 5.877777777777778e-06}
{"global_step": 540, "epoch": 0.22229083050324175, "loss": 21.2952, "grad_norm": 18.609397075134556, "learning_rate": 5.98888888888889e-06}
{"global_step": 550, "epoch": 0.22640732736441288, "loss": 21.2694, "grad_norm": 18.044456751597316, "learning_rate": 6.1e-06}
{"global_step": 560, "epoch": 0.23052382422558404, "loss": 21.2149, "grad_norm": 18.440050806349944, "learning_rate": 6.211111111111111e-06}
{"global_step": 570, "epoch": 0.23464032108675517, "loss": 21.1566, "grad_norm": 36.12491809597436, "learning_rate": 6.322222222222223e-06}
{"global_step": 580, "epoch": 0.2387568179479263, "loss": 21.0841, "grad_norm": 17.843619309609803, "learning_rate": 6.433333333333333e-06}
{"global_step": 590, "epoch": 0.24287331480909746, "loss": 20.9708, "grad_norm": 18.299191738513812, "learning_rate": 6.544444444444445e-06}
{"global_step": 600, "epoch": 0.2469898116702686, "loss": 20.8825, "grad_norm": 18.056905789458586, "learning_rate": 6.655555555555556e-06}
{"global_step": 610, "epoch": 0.2511063085314397, "loss": 20.8147, "grad_norm": 44.82326463049171, "learning_rate": 6.7666666666666665e-06}
{"global_step": 620, "epoch": 0.2552228053926109, "loss": 20.7548, "grad_norm": 27.094157559455603, "learning_rate": 6.8777777777777785e-06}
{"global_step": 630, "epoch": 0.25933930225378204, "loss": 20.6822, "grad_norm": 27.88387397100189, "learning_rate": 6.9888888888888895e-06}
{"global_step": 640, "epoch": 0.26345579911495315, "loss": 20.5884, "grad_norm": 31.290911839762394, "learning_rate": 7.100000000000001e-06}
{"global_step": 650, "epoch": 0.2675722959761243, "loss": 20.5162, "grad_norm": 24.27245501884365, "learning_rate": 7.211111111111112e-06}
{"global_step": 660, "epoch": 0.27168879283729547, "loss": 20.4592, "grad_norm": 23.89703899570296, "learning_rate": 7.322222222222223e-06}
{"global_step": 670, "epoch": 0.2758052896984666, "loss": 20.3787, "grad_norm": 57.249160956506614, "learning_rate": 7.433333333333334e-06}
{"global_step": 680, "epoch": 0.27992178655963773, "loss": 20.207, "grad_norm": 44.42291899504958, "learning_rate": 7.544444444444445e-06}
{"global_step": 690, "epoch": 0.2840382834208089, "loss": 20.143, "grad_norm": 91.55863776649939, "learning_rate": 7.655555555555556e-06}
{"global_step": 700, "epoch": 0.28815478028198005, "loss": 19.9418, "grad_norm": 57.092128520356646, "learning_rate": 7.766666666666666e-06}
{"global_step": 710, "epoch": 0.29227127714315115, "loss": 19.6662, "grad_norm": 37.42956925364744, "learning_rate": 7.877777777777778e-06}
{"global_step": 720, "epoch": 0.2963877740043223, "loss": 19.4289, "grad_norm": 24.54779334825758, "learning_rate": 7.98888888888889e-06}
{"global_step": 730, "epoch": 0.3005042708654935, "loss": 19.2373, "grad_norm": 20.193177185866038, "learning_rate": 8.1e-06}
{"global_step": 740, "epoch": 0.30462076772666463, "loss": 19.173, "grad_norm": 60.48422812921962, "learning_rate": 8.211111111111112e-06}
{"global_step": 750, "epoch": 0.30873726458783574, "loss": 18.9043, "grad_norm": 27.558098824852753, "learning_rate": 8.322222222222223e-06}
{"global_step": 760, "epoch": 0.3128537614490069, "loss": 18.6651, "grad_norm": 29.51167246824426, "learning_rate": 8.433333333333334e-06}
{"global_step": 770, "epoch": 0.31697025831017805, "loss": 18.4818, "grad_norm": 21.93310893699215, "learning_rate": 8.544444444444445e-06}
{"global_step": 780, "epoch": 0.32108675517134916, "loss": 18.4864, "grad_norm": 51.99252088836799, "learning_rate": 8.655555555555557e-06}
{"global_step": 790, "epoch": 0.3252032520325203, "loss": 18.205, "grad_norm": 35.01362198000449, "learning_rate": 8.766666666666669e-06}
{"global_step": 800, "epoch": 0.3293197488936915, "loss": 18.0342, "grad_norm": 30.09623662803406, "learning_rate": 8.877777777777779e-06}
{"global_step": 810, "epoch": 0.33343624575486264, "loss": 17.8646, "grad_norm": 55.16314161967726, "learning_rate": 8.988888888888889e-06}
{"global_step": 820, "epoch": 0.33755274261603374, "loss": 17.6275, "grad_norm": 33.375878351461154, "learning_rate": 9.100000000000001e-06}
{"global_step": 830, "epoch": 0.3416692394772049, "loss": 17.53, "grad_norm": 27.20030408565347, "learning_rate": 9.211111111111111e-06}
{"global_step": 840, "epoch": 0.34578573633837606, "loss": 17.4118, "grad_norm": 44.94165316928541, "learning_rate": 9.322222222222223e-06}
{"global_step": 850, "epoch": 0.34990223319954716, "loss": 17.2221, "grad_norm": 51.21107811701123, "learning_rate": 9.433333333333335e-06}
{"global_step": 860, "epoch": 0.3540187300607183, "loss": 17.0648, "grad_norm": 48.69081492082153, "learning_rate": 9.544444444444445e-06}
{"global_step": 870, "epoch": 0.3581352269218895, "loss": 16.9709, "grad_norm": 59.568062971869644, "learning_rate": 9.655555555555556e-06}
{"global_step": 880, "epoch": 0.36225172378306064, "loss": 16.7922, "grad_norm": 48.20595634997982, "learning_rate": 9.766666666666667e-06}
{"global_step": 890, "epoch": 0.36636822064423175, "loss": 16.5606, "grad_norm": 38.89100659846126, "learning_rate": 9.877777777777778e-06}
{"global_step": 900, "epoch": 0.3704847175054029, "loss": 16.5196, "grad_norm": 55.476242446929724, "learning_rate": 9.98888888888889e-06}
{"global_step": 910, "epoch": 0.37460121436657406, "loss": 16.2859, "grad_norm": 33.8871713799869, "learning_rate": 9.996907216494847e-06}
{"global_step": 920, "epoch": 0.37871771122774517, "loss": 16.1253, "grad_norm": 48.67199287721736, "learning_rate": 9.993470790378008e-06}
{"global_step": 930, "epoch": 0.38283420808891633, "loss": 16.1184, "grad_norm": 53.10677273121955, "learning_rate": 9.99003436426117e-06}
{"global_step": 940, "epoch": 0.3869507049500875, "loss": 15.8454, "grad_norm": 36.47115886963749, "learning_rate": 9.986597938144331e-06}
{"global_step": 950, "epoch": 0.3910672018112586, "loss": 15.7934, "grad_norm": 46.9950180770148, "learning_rate": 9.983161512027493e-06}
{"global_step": 960, "epoch": 0.39518369867242975, "loss": 15.7013, "grad_norm": 41.780425293570616, "learning_rate": 9.979725085910654e-06}
{"global_step": 970, "epoch": 0.3993001955336009, "loss": 15.5447, "grad_norm": 61.01443519953337, "learning_rate": 9.976288659793816e-06}
{"global_step": 980, "epoch": 0.40341669239477207, "loss": 15.4402, "grad_norm": 37.005722827889784, "learning_rate": 9.972852233676977e-06}
{"global_step": 990, "epoch": 0.4075331892559432, "loss": 15.3771, "grad_norm": 34.50549181078069, "learning_rate": 9.969415807560139e-06}
{"global_step": 1000, "epoch": 0.41164968611711433, "loss": 15.1859, "grad_norm": 43.56802220640922, "learning_rate": 9.965979381443299e-06}
{"global_step": 1010, "epoch": 0.4157661829782855, "loss": 15.1377, "grad_norm": 44.27192419759802, "learning_rate": 9.96254295532646e-06}
{"global_step": 1020, "epoch": 0.4198826798394566, "loss": 15.0264, "grad_norm": 54.39835842981886, "learning_rate": 9.959106529209622e-06}
{"global_step": 1030, "epoch": 0.42399917670062776, "loss": 14.9343, "grad_norm": 39.41791238776903, "learning_rate": 9.955670103092783e-06}
{"global_step": 1040, "epoch": 0.4281156735617989, "loss": 14.7589, "grad_norm": 33.82937492863744, "learning_rate": 9.952233676975945e-06}
{"global_step": 1050, "epoch": 0.4322321704229701, "loss": 14.6838, "grad_norm": 40.479975837330905, "learning_rate": 9.948797250859106e-06}
{"global_step": 1060, "epoch": 0.4363486672841412, "loss": 14.5806, "grad_norm": 49.56506719825334, "learning_rate": 9.945360824742268e-06}
{"global_step": 1070, "epoch": 0.44046516414531234, "loss": 14.5519, "grad_norm": 43.92728436690805, "learning_rate": 9.94192439862543e-06}
{"global_step": 1080, "epoch": 0.4445816610064835, "loss": 14.4566, "grad_norm": 38.083124431784405, "learning_rate": 9.938487972508592e-06}
{"global_step": 1090, "epoch": 0.4486981578676546, "loss": 14.4637, "grad_norm": 40.83368623786197, "learning_rate": 9.935051546391754e-06}
{"global_step": 1100, "epoch": 0.45281465472882576, "loss": 14.2926, "grad_norm": 39.888961137074325, "learning_rate": 9.931615120274915e-06}
{"global_step": 1110, "epoch": 0.4569311515899969, "loss": 14.2284, "grad_norm": 52.98917099950452, "learning_rate": 9.928178694158077e-06}
{"global_step": 1120, "epoch": 0.4610476484511681, "loss": 14.1538, "grad_norm": 39.86769855717651, "learning_rate": 9.924742268041238e-06}
{"global_step": 1130, "epoch": 0.4651641453123392, "loss": 14.1268, "grad_norm": 41.47546966771517, "learning_rate": 9.9213058419244e-06}
{"global_step": 1140, "epoch": 0.46928064217351034, "loss": 14.0239, "grad_norm": 43.66832808351295, "learning_rate": 9.917869415807561e-06}
{"global_step": 1150, "epoch": 0.4733971390346815, "loss": 13.9388, "grad_norm": 38.15090916854303, "learning_rate": 9.914432989690723e-06}
{"global_step": 1160, "epoch": 0.4775136358958526, "loss": 13.911, "grad_norm": 34.56956210917117, "learning_rate": 9.910996563573884e-06}
{"global_step": 1170, "epoch": 0.48163013275702377, "loss": 13.8416, "grad_norm": 33.31934413400173, "learning_rate": 9.907560137457046e-06}
{"global_step": 1180, "epoch": 0.4857466296181949, "loss": 13.8095, "grad_norm": 37.93411062451452, "learning_rate": 9.904123711340207e-06}
{"global_step": 1190, "epoch": 0.4898631264793661, "loss": 13.7295, "grad_norm": 38.20924261082129, "learning_rate": 9.900687285223369e-06}
{"global_step": 1200, "epoch": 0.4939796233405372, "loss": 13.6506, "grad_norm": 53.63569573152946, "learning_rate": 9.89725085910653e-06}
{"global_step": 1210, "epoch": 0.49809612020170835, "loss": 13.6186, "grad_norm": 43.14530877212232, "learning_rate": 9.893814432989692e-06}
{"global_step": 1220, "epoch": 0.5022126170628795, "loss": 13.6416, "grad_norm": 49.03916689519157, "learning_rate": 9.890378006872853e-06}
{"global_step": 1230, "epoch": 0.5063291139240507, "loss": 13.574, "grad_norm": 36.49026973775023, "learning_rate": 9.886941580756015e-06}
{"global_step": 1240, "epoch": 0.5104456107852218, "loss": 13.4854, "grad_norm": 32.76071554080421, "learning_rate": 9.883505154639176e-06}
{"global_step": 1250, "epoch": 0.5145621076463929, "loss": 13.3827, "grad_norm": 36.789924557345806, "learning_rate": 9.880068728522338e-06}
{"global_step": 1260, "epoch": 0.5186786045075641, "loss": 13.3305, "grad_norm": 28.079567041126435, "learning_rate": 9.8766323024055e-06}
{"global_step": 1270, "epoch": 0.5227951013687352, "loss": 13.33, "grad_norm": 43.55514700081209, "learning_rate": 9.87319587628866e-06}
{"global_step": 1280, "epoch": 0.5269115982299063, "loss": 13.2651, "grad_norm": 28.76115488681788, "learning_rate": 9.869759450171822e-06}
{"global_step": 1290, "epoch": 0.5310280950910775, "loss": 13.2312, "grad_norm": 37.358128749691296, "learning_rate": 9.866323024054984e-06}
{"global_step": 1300, "epoch": 0.5351445919522486, "loss": 13.1897, "grad_norm": 44.992288758478345, "learning_rate": 9.862886597938145e-06}
{"global_step": 1310, "epoch": 0.5392610888134198, "loss": 13.1063, "grad_norm": 28.47379704494871, "learning_rate": 9.859450171821307e-06}
{"global_step": 1320, "epoch": 0.5433775856745909, "loss": 13.0747, "grad_norm": 31.796429799283633, "learning_rate": 9.856013745704468e-06}
{"global_step": 1330, "epoch": 0.547494082535762, "loss": 13.0861, "grad_norm": 39.38678551108492, "learning_rate": 9.85257731958763e-06}
{"global_step": 1340, "epoch": 0.5516105793969333, "loss": 13.046, "grad_norm": 38.812099741482996, "learning_rate": 9.849140893470791e-06}
{"global_step": 1350, "epoch": 0.5557270762581044, "loss": 13.0339, "grad_norm": 34.79929463071014, "learning_rate": 9.845704467353953e-06}
{"global_step": 1360, "epoch": 0.5598435731192755, "loss": 12.9433, "grad_norm": 36.095752723061416, "learning_rate": 9.842268041237114e-06}
{"global_step": 1370, "epoch": 0.5639600699804467, "loss": 12.907, "grad_norm": 36.27956418944883, "learning_rate": 9.838831615120276e-06}
{"global_step": 1380, "epoch": 0.5680765668416178, "loss": 12.91, "grad_norm": 35.72628600227518, "learning_rate": 9.835395189003437e-06}
{"global_step": 1390, "epoch": 0.5721930637027889, "loss": 12.8805, "grad_norm": 36.2974491311879, "learning_rate": 9.831958762886599e-06}
{"global_step": 1400, "epoch": 0.5763095605639601, "loss": 12.8487, "grad_norm": 38.753865801889205, "learning_rate": 9.82852233676976e-06}
{"global_step": 1410, "epoch": 0.5804260574251312, "loss": 12.8255, "grad_norm": 37.15806127726735, "learning_rate": 9.825085910652922e-06}
{"global_step": 1420, "epoch": 0.5845425542863023, "loss": 12.7318, "grad_norm": 31.930169790036125, "learning_rate": 9.821649484536083e-06}
{"global_step": 1430, "epoch": 0.5886590511474735, "loss": 12.8322, "grad_norm": 46.704762225618985, "learning_rate": 9.818213058419245e-06}
{"global_step": 1440, "epoch": 0.5927755480086446, "loss": 12.7815, "grad_norm": 33.776587810887825, "learning_rate": 9.814776632302406e-06}
{"global_step": 1450, "epoch": 0.5968920448698158, "loss": 12.7486, "grad_norm": 29.58229351266127, "learning_rate": 9.811340206185568e-06}
{"global_step": 1460, "epoch": 0.601008541730987, "loss": 12.6896, "grad_norm": 33.63398991455025, "learning_rate": 9.80790378006873e-06}
{"global_step": 1470, "epoch": 0.605125038592158, "loss": 12.6699, "grad_norm": 36.832689858066715, "learning_rate": 9.804467353951891e-06}
{"global_step": 1480, "epoch": 0.6092415354533293, "loss": 12.5471, "grad_norm": 37.43208595185383, "learning_rate": 9.801030927835052e-06}
{"global_step": 1490, "epoch": 0.6133580323145004, "loss": 12.6142, "grad_norm": 33.7941307098917, "learning_rate": 9.797594501718214e-06}
{"global_step": 1500, "epoch": 0.6174745291756715, "loss": 12.5338, "grad_norm": 31.9466158932975, "learning_rate": 9.794158075601375e-06}
{"global_step": 1510, "epoch": 0.6215910260368427, "loss": 12.4764, "grad_norm": 38.30578087105521, "learning_rate": 9.790721649484537e-06}
{"global_step": 1520, "epoch": 0.6257075228980138, "loss": 12.4952, "grad_norm": 32.61697454595358, "learning_rate": 9.787285223367698e-06}
{"global_step": 1530, "epoch": 0.6298240197591849, "loss": 12.4546, "grad_norm": 40.16758133155219, "learning_rate": 9.78384879725086e-06}
{"global_step": 1540, "epoch": 0.6339405166203561, "loss": 12.4843, "grad_norm": 48.80638115137875, "learning_rate": 9.780412371134021e-06}
{"global_step": 1550, "epoch": 0.6380570134815272, "loss": 12.4931, "grad_norm": 37.475171347455756, "learning_rate": 9.776975945017183e-06}
{"global_step": 1560, "epoch": 0.6421735103426983, "loss": 12.4005, "grad_norm": 33.28595513208406, "learning_rate": 9.773539518900344e-06}
{"global_step": 1570, "epoch": 0.6462900072038695, "loss": 12.3441, "grad_norm": 31.086866920620285, "learning_rate": 9.770103092783506e-06}
{"global_step": 1580, "epoch": 0.6504065040650406, "loss": 12.2734, "grad_norm": 39.3394583771368, "learning_rate": 9.766666666666667e-06}
{"global_step": 1590, "epoch": 0.6545230009262117, "loss": 12.3482, "grad_norm": 32.802912711135214, "learning_rate": 9.763230240549829e-06}
{"global_step": 1600, "epoch": 0.658639497787383, "loss": 12.3565, "grad_norm": 37.29399518826948, "learning_rate": 9.75979381443299e-06}
{"global_step": 1610, "epoch": 0.6627559946485541, "loss": 12.2918, "grad_norm": 31.346208761120682, "learning_rate": 9.756357388316152e-06}
{"global_step": 1620, "epoch": 0.6668724915097253, "loss": 12.2984, "grad_norm": 32.38506378128921, "learning_rate": 9.752920962199313e-06}
{"global_step": 1630, "epoch": 0.6709889883708964, "loss": 12.2223, "grad_norm": 37.55618381493301, "learning_rate": 9.749484536082475e-06}
{"global_step": 1640, "epoch": 0.6751054852320675, "loss": 12.2059, "grad_norm": 30.159408332251935, "learning_rate": 9.746048109965636e-06}
{"global_step": 1650, "epoch": 0.6792219820932387, "loss": 12.1934, "grad_norm": 33.64269413817189, "learning_rate": 9.742611683848798e-06}
{"global_step": 1660, "epoch": 0.6833384789544098, "loss": 12.2187, "grad_norm": 33.350706787266056, "learning_rate": 9.73917525773196e-06}
{"global_step": 1670, "epoch": 0.6874549758155809, "loss": 12.163, "grad_norm": 33.39405862288003, "learning_rate": 9.735738831615121e-06}
{"global_step": 1680, "epoch": 0.6915714726767521, "loss": 12.1662, "grad_norm": 33.41635090076034, "learning_rate": 9.732302405498283e-06}
{"global_step": 1690, "epoch": 0.6956879695379232, "loss": 12.2065, "grad_norm": 30.14281470411853, "learning_rate": 9.728865979381444e-06}
{"global_step": 1700, "epoch": 0.6998044663990943, "loss": 12.1291, "grad_norm": 30.467396684661566, "learning_rate": 9.725429553264606e-06}
{"global_step": 1710, "epoch": 0.7039209632602655, "loss": 12.0492, "grad_norm": 30.441530111439768, "learning_rate": 9.721993127147767e-06}
{"global_step": 1720, "epoch": 0.7080374601214366, "loss": 12.0813, "grad_norm": 28.49347966966388, "learning_rate": 9.718556701030929e-06}
{"global_step": 1730, "epoch": 0.7121539569826077, "loss": 12.0821, "grad_norm": 30.721181306779684, "learning_rate": 9.71512027491409e-06}
{"global_step": 1740, "epoch": 0.716270453843779, "loss": 12.0637, "grad_norm": 29.129251982891667, "learning_rate": 9.711683848797252e-06}
{"global_step": 1750, "epoch": 0.7203869507049501, "loss": 11.9994, "grad_norm": 29.95019721435932, "learning_rate": 9.708247422680413e-06}
{"global_step": 1760, "epoch": 0.7245034475661213, "loss": 12.024, "grad_norm": 32.81918337349151, "learning_rate": 9.704810996563575e-06}
{"global_step": 1770, "epoch": 0.7286199444272924, "loss": 12.0285, "grad_norm": 39.5144099446638, "learning_rate": 9.701374570446736e-06}
{"global_step": 1780, "epoch": 0.7327364412884635, "loss": 11.9479, "grad_norm": 31.653909615694747, "learning_rate": 9.697938144329898e-06}
{"global_step": 1790, "epoch": 0.7368529381496347, "loss": 11.9523, "grad_norm": 33.40571679023385, "learning_rate": 9.694501718213059e-06}
{"global_step": 1800, "epoch": 0.7409694350108058, "loss": 11.9416, "grad_norm": 37.473942426771224, "learning_rate": 9.69106529209622e-06}
{"global_step": 1810, "epoch": 0.7450859318719769, "loss": 12.0463, "grad_norm": 36.94155127706317, "learning_rate": 9.687628865979382e-06}
{"global_step": 1820, "epoch": 0.7492024287331481, "loss": 11.8785, "grad_norm": 37.68814388273857, "learning_rate": 9.684192439862544e-06}
{"global_step": 1830, "epoch": 0.7533189255943192, "loss": 11.8984, "grad_norm": 28.366410820050916, "learning_rate": 9.680756013745705e-06}
{"global_step": 1840, "epoch": 0.7574354224554903, "loss": 11.7795, "grad_norm": 32.286183742630165, "learning_rate": 9.677319587628867e-06}
{"global_step": 1850, "epoch": 0.7615519193166616, "loss": 11.7833, "grad_norm": 34.20137530626946, "learning_rate": 9.673883161512028e-06}
{"global_step": 1860, "epoch": 0.7656684161778327, "loss": 11.8231, "grad_norm": 26.974205102100083, "learning_rate": 9.67044673539519e-06}
{"global_step": 1870, "epoch": 0.7697849130390038, "loss": 11.839, "grad_norm": 30.78227640084708, "learning_rate": 9.667010309278351e-06}
{"global_step": 1880, "epoch": 0.773901409900175, "loss": 11.7576, "grad_norm": 32.775223259236476, "learning_rate": 9.663573883161513e-06}
{"global_step": 1890, "epoch": 0.7780179067613461, "loss": 11.8203, "grad_norm": 32.09910452344205, "learning_rate": 9.660137457044674e-06}
{"global_step": 1900, "epoch": 0.7821344036225172, "loss": 11.7395, "grad_norm": 34.679912416674696, "learning_rate": 9.656701030927836e-06}
{"global_step": 1910, "epoch": 0.7862509004836884, "loss": 11.7656, "grad_norm": 41.08474046950697, "learning_rate": 9.653264604810997e-06}
{"global_step": 1920, "epoch": 0.7903673973448595, "loss": 11.7157, "grad_norm": 43.79171589552821, "learning_rate": 9.649828178694159e-06}
{"global_step": 1930, "epoch": 0.7944838942060307, "loss": 11.7633, "grad_norm": 32.06890784949689, "learning_rate": 9.64639175257732e-06}
{"global_step": 1940, "epoch": 0.7986003910672018, "loss": 11.7696, "grad_norm": 33.88840596948513, "learning_rate": 9.642955326460482e-06}
{"global_step": 1950, "epoch": 0.8027168879283729, "loss": 11.6768, "grad_norm": 43.3525380610554, "learning_rate": 9.639518900343643e-06}
{"global_step": 1960, "epoch": 0.8068333847895441, "loss": 11.6438, "grad_norm": 29.03141895521922, "learning_rate": 9.636082474226805e-06}
{"global_step": 1970, "epoch": 0.8109498816507152, "loss": 11.648, "grad_norm": 31.577350376305315, "learning_rate": 9.632646048109966e-06}
{"global_step": 1980, "epoch": 0.8150663785118863, "loss": 11.5621, "grad_norm": 29.395462355828993, "learning_rate": 9.629209621993128e-06}
{"global_step": 1990, "epoch": 0.8191828753730576, "loss": 11.6605, "grad_norm": 36.070659840431695, "learning_rate": 9.625773195876289e-06}
{"global_step": 2000, "epoch": 0.8232993722342287, "loss": 11.6847, "grad_norm": 40.63936989861702, "learning_rate": 9.62233676975945e-06}
{"global_step": 2010, "epoch": 0.8274158690953998, "loss": 11.5951, "grad_norm": 28.74096555707873, "learning_rate": 9.618900343642612e-06}
{"global_step": 2020, "epoch": 0.831532365956571, "loss": 11.5425, "grad_norm": 26.857379564051325, "learning_rate": 9.615463917525774e-06}
{"global_step": 2030, "epoch": 0.8356488628177421, "loss": 11.5395, "grad_norm": 34.26526481929795, "learning_rate": 9.612027491408935e-06}
{"global_step": 2040, "epoch": 0.8397653596789132, "loss": 11.5239, "grad_norm": 39.61591003341877, "learning_rate": 9.608591065292097e-06}
{"global_step": 2050, "epoch": 0.8438818565400844, "loss": 11.5221, "grad_norm": 32.799457497612636, "learning_rate": 9.605154639175258e-06}
{"global_step": 2060, "epoch": 0.8479983534012555, "loss": 11.5188, "grad_norm": 30.46702989419665, "learning_rate": 9.60171821305842e-06}
{"global_step": 2070, "epoch": 0.8521148502624267, "loss": 11.5045, "grad_norm": 36.16227939472805, "learning_rate": 9.598281786941581e-06}
{"global_step": 2080, "epoch": 0.8562313471235978, "loss": 11.5307, "grad_norm": 35.47038057679002, "learning_rate": 9.594845360824743e-06}
{"global_step": 2090, "epoch": 0.8603478439847689, "loss": 11.523, "grad_norm": 32.257372818520146, "learning_rate": 9.591408934707904e-06}
{"global_step": 2100, "epoch": 0.8644643408459401, "loss": 11.5006, "grad_norm": 29.92970511160102, "learning_rate": 9.587972508591066e-06}
{"global_step": 2110, "epoch": 0.8685808377071113, "loss": 11.4492, "grad_norm": 31.548453221760763, "learning_rate": 9.584536082474227e-06}
{"global_step": 2120, "epoch": 0.8726973345682824, "loss": 11.4804, "grad_norm": 34.57267127412313, "learning_rate": 9.581099656357389e-06}
{"global_step": 2130, "epoch": 0.8768138314294536, "loss": 11.4529, "grad_norm": 34.17219698271619, "learning_rate": 9.57766323024055e-06}
{"global_step": 2140, "epoch": 0.8809303282906247, "loss": 11.3922, "grad_norm": 29.479641794210973, "learning_rate": 9.574226804123712e-06}
{"global_step": 2150, "epoch": 0.8850468251517958, "loss": 11.394, "grad_norm": 32.38400767680429, "learning_rate": 9.570790378006873e-06}
{"global_step": 2160, "epoch": 0.889163322012967, "loss": 11.3841, "grad_norm": 32.32981900594448, "learning_rate": 9.567353951890035e-06}
{"global_step": 2170, "epoch": 0.8932798188741381, "loss": 11.3688, "grad_norm": 33.61678562259265, "learning_rate": 9.563917525773196e-06}
{"global_step": 2180, "epoch": 0.8973963157353092, "loss": 11.3808, "grad_norm": 32.71587409986399, "learning_rate": 9.560481099656358e-06}
{"global_step": 2190, "epoch": 0.9015128125964804, "loss": 11.3336, "grad_norm": 29.54893232627574, "learning_rate": 9.55704467353952e-06}
{"global_step": 2200, "epoch": 0.9056293094576515, "loss": 11.3034, "grad_norm": 32.06137522253644, "learning_rate": 9.55360824742268e-06}
{"global_step": 2210, "epoch": 0.9097458063188227, "loss": 11.3092, "grad_norm": 36.467602001920255, "learning_rate": 9.550171821305842e-06}
{"global_step": 2220, "epoch": 0.9138623031799938, "loss": 11.3535, "grad_norm": 36.697441519061755, "learning_rate": 9.546735395189004e-06}
{"global_step": 2230, "epoch": 0.9179788000411649, "loss": 11.2906, "grad_norm": 29.195704697132054, "learning_rate": 9.543298969072165e-06}
{"global_step": 2240, "epoch": 0.9220952969023362, "loss": 11.2277, "grad_norm": 28.12150721519504, "learning_rate": 9.539862542955327e-06}
{"global_step": 2250, "epoch": 0.9262117937635073, "loss": 11.2413, "grad_norm": 28.28187759539184, "learning_rate": 9.536426116838488e-06}
{"global_step": 2260, "epoch": 0.9303282906246784, "loss": 11.2062, "grad_norm": 38.194498763414195, "learning_rate": 9.53298969072165e-06}
{"global_step": 2270, "epoch": 0.9344447874858496, "loss": 11.2868, "grad_norm": 30.60316989712369, "learning_rate": 9.529553264604811e-06}
{"global_step": 2280, "epoch": 0.9385612843470207, "loss": 11.3455, "grad_norm": 32.2566760579608, "learning_rate": 9.526116838487973e-06}
{"global_step": 2290, "epoch": 0.9426777812081918, "loss": 11.2271, "grad_norm": 29.363121550952414, "learning_rate": 9.522680412371134e-06}
{"global_step": 2300, "epoch": 0.946794278069363, "loss": 11.2572, "grad_norm": 34.44659489587604, "learning_rate": 9.519243986254296e-06}
{"global_step": 2310, "epoch": 0.9509107749305341, "loss": 11.2059, "grad_norm": 38.421619327615275, "learning_rate": 9.515807560137457e-06}
{"global_step": 2320, "epoch": 0.9550272717917052, "loss": 11.2005, "grad_norm": 28.45314623909409, "learning_rate": 9.512371134020619e-06}
{"global_step": 2330, "epoch": 0.9591437686528764, "loss": 11.1696, "grad_norm": 33.71882176291607, "learning_rate": 9.50893470790378e-06}
{"global_step": 2340, "epoch": 0.9632602655140475, "loss": 11.1289, "grad_norm": 40.284639005118564, "learning_rate": 9.505498281786942e-06}
{"global_step": 2350, "epoch": 0.9673767623752186, "loss": 11.1945, "grad_norm": 29.578038874639823, "learning_rate": 9.502061855670103e-06}
{"global_step": 2360, "epoch": 0.9714932592363899, "loss": 11.1547, "grad_norm": 30.78279090155006, "learning_rate": 9.498625429553265e-06}
{"global_step": 2370, "epoch": 0.975609756097561, "loss": 11.1499, "grad_norm": 32.32491917371623, "learning_rate": 9.495189003436426e-06}
{"global_step": 2380, "epoch": 0.9797262529587322, "loss": 11.0843, "grad_norm": 33.912601882090534, "learning_rate": 9.491752577319588e-06}
{"global_step": 2390, "epoch": 0.9838427498199033, "loss": 11.0857, "grad_norm": 33.636974029662824, "learning_rate": 9.48831615120275e-06}
{"global_step": 2400, "epoch": 0.9879592466810744, "loss": 11.117, "grad_norm": 28.479925241415103, "learning_rate": 9.48487972508591e-06}
{"global_step": 2410, "epoch": 0.9920757435422456, "loss": 11.1586, "grad_norm": 32.19633310187057, "learning_rate": 9.481443298969072e-06}
{"global_step": 2420, "epoch": 0.9961922404034167, "loss": 11.0449, "grad_norm": 30.24939985897427, "learning_rate": 9.478006872852234e-06}
{"global_step": 2430, "epoch": 1.0, "loss": 10.2576, "grad_norm": 27.59918285796063, "learning_rate": 9.474570446735395e-06}
{"global_step": 2440, "epoch": 1.004116496861171, "loss": 10.9205, "grad_norm": 29.145692709878713, "learning_rate": 9.471134020618557e-06}
{"global_step": 2450, "epoch": 1.0082329937223422, "loss": 10.8674, "grad_norm": 34.22402623391047, "learning_rate": 9.467697594501718e-06}
{"global_step": 2460, "epoch": 1.0123494905835135, "loss": 10.9685, "grad_norm": 31.116476736190727, "learning_rate": 9.46426116838488e-06}
{"global_step": 2470, "epoch": 1.0164659874446846, "loss": 10.8758, "grad_norm": 31.010011036576245, "learning_rate": 9.460824742268041e-06}
{"global_step": 2480, "epoch": 1.0205824843058557, "loss": 10.8832, "grad_norm": 33.554395898942225, "learning_rate": 9.457388316151203e-06}
{"global_step": 2490, "epoch": 1.0246989811670268, "loss": 10.8374, "grad_norm": 33.7710211448291, "learning_rate": 9.453951890034366e-06}
{"global_step": 2500, "epoch": 1.028815478028198, "loss": 10.8073, "grad_norm": 36.176567342791, "learning_rate": 9.450515463917528e-06}
{"global_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}
{"global_step": 2510, "epoch": 1.032931974889369, "loss": 10.8554, "grad_norm": 33.415438706038195, "learning_rate": 9.447079037800689e-06}
{"global_step": 2520, "epoch": 1.0370484717505404, "loss": 10.844, "grad_norm": 33.56857491605213, "learning_rate": 9.44364261168385e-06}
{"global_step": 2530, "epoch": 1.0411649686117115, "loss": 10.9254, "grad_norm": 28.692610292751354, "learning_rate": 9.440206185567012e-06}
{"global_step": 2540, "epoch": 1.0452814654728826, "loss": 10.8743, "grad_norm": 37.71077640271992, "learning_rate": 9.436769759450174e-06}
{"global_step": 2550, "epoch": 1.0493979623340537, "loss": 10.884, "grad_norm": 39.50450285467682, "learning_rate": 9.433333333333335e-06}
{"global_step": 2560, "epoch": 1.0535144591952248, "loss": 10.8537, "grad_norm": 33.57213304521402, "learning_rate": 9.429896907216497e-06}
{"global_step": 2570, "epoch": 1.057630956056396, "loss": 10.8328, "grad_norm": 32.59962115413462, "learning_rate": 9.426460481099658e-06}
{"global_step": 2580, "epoch": 1.0617474529175672, "loss": 10.8917, "grad_norm": 34.910436921816675, "learning_rate": 9.42302405498282e-06}
{"global_step": 2590, "epoch": 1.0658639497787383, "loss": 10.8385, "grad_norm": 27.303722252736947, "learning_rate": 9.419587628865981e-06}
{"global_step": 2600, "epoch": 1.0699804466399094, "loss": 10.8006, "grad_norm": 31.339676779439166, "learning_rate": 9.416151202749143e-06}
{"global_step": 2610, "epoch": 1.0740969435010805, "loss": 10.7646, "grad_norm": 31.406463331327124, "learning_rate": 9.412714776632304e-06}
{"global_step": 2620, "epoch": 1.0782134403622516, "loss": 10.7957, "grad_norm": 34.52313243956516, "learning_rate": 9.409278350515466e-06}
{"global_step": 2630, "epoch": 1.082329937223423, "loss": 10.824, "grad_norm": 34.82551474227616, "learning_rate": 9.405841924398627e-06}
{"global_step": 2640, "epoch": 1.086446434084594, "loss": 10.7844, "grad_norm": 35.0844939375081, "learning_rate": 9.402405498281789e-06}
{"global_step": 2650, "epoch": 1.0905629309457652, "loss": 10.7582, "grad_norm": 33.8646318867766, "learning_rate": 9.39896907216495e-06}
{"global_step": 2660, "epoch": 1.0946794278069363, "loss": 10.7714, "grad_norm": 30.267226879030765, "learning_rate": 9.395532646048112e-06}
{"global_step": 2670, "epoch": 1.0987959246681074, "loss": 10.7044, "grad_norm": 32.65500459467302, "learning_rate": 9.392096219931273e-06}
{"global_step": 2680, "epoch": 1.1029124215292785, "loss": 10.7325, "grad_norm": 29.90355585105674, "learning_rate": 9.388659793814435e-06}
{"global_step": 2690, "epoch": 1.1070289183904498, "loss": 10.7143, "grad_norm": 28.569571173298087, "learning_rate": 9.385223367697596e-06}
{"global_step": 2700, "epoch": 1.111145415251621, "loss": 10.7198, "grad_norm": 34.54223606254732, "learning_rate": 9.381786941580758e-06}
{"global_step": 2710, "epoch": 1.115261912112792, "loss": 10.7134, "grad_norm": 41.65988359943903, "learning_rate": 9.378350515463919e-06}
{"global_step": 2720, "epoch": 1.1193784089739631, "loss": 10.7478, "grad_norm": 31.147728489757004, "learning_rate": 9.37491408934708e-06}
{"global_step": 2730, "epoch": 1.1234949058351342, "loss": 10.7194, "grad_norm": 34.35653519254494, "learning_rate": 9.371477663230242e-06}
{"global_step": 2740, "epoch": 1.1276114026963056, "loss": 10.709, "grad_norm": 28.753608820035986, "learning_rate": 9.368041237113404e-06}
{"global_step": 2750, "epoch": 1.1317278995574767, "loss": 10.6483, "grad_norm": 33.40825861778074, "learning_rate": 9.364604810996565e-06}
{"global_step": 2760, "epoch": 1.1358443964186478, "loss": 10.6871, "grad_norm": 35.80091959274697, "learning_rate": 9.361168384879727e-06}
{"global_step": 2770, "epoch": 1.1399608932798189, "loss": 10.6778, "grad_norm": 29.44549475248084, "learning_rate": 9.357731958762888e-06}
{"global_step": 2780, "epoch": 1.14407739014099, "loss": 10.594, "grad_norm": 30.257547070006492, "learning_rate": 9.35429553264605e-06}
{"global_step": 2790, "epoch": 1.148193887002161, "loss": 10.621, "grad_norm": 32.02247706651434, "learning_rate": 9.350859106529211e-06}
{"global_step": 2800, "epoch": 1.1523103838633324, "loss": 10.6492, "grad_norm": 29.489438810378612, "learning_rate": 9.347422680412373e-06}
{"global_step": 2810, "epoch": 1.1564268807245035, "loss": 10.578, "grad_norm": 29.232020772768045, "learning_rate": 9.343986254295534e-06}
{"global_step": 2820, "epoch": 1.1605433775856746, "loss": 10.6208, "grad_norm": 34.113466181093656, "learning_rate": 9.340549828178694e-06}
{"global_step": 2830, "epoch": 1.1646598744468457, "loss": 10.6177, "grad_norm": 28.652154767647808, "learning_rate": 9.337113402061855e-06}
{"global_step": 2840, "epoch": 1.1687763713080168, "loss": 10.6009, "grad_norm": 30.199419083823177, "learning_rate": 9.333676975945017e-06}
{"global_step": 2850, "epoch": 1.1728928681691881, "loss": 10.6318, "grad_norm": 30.560648700009178, "learning_rate": 9.330240549828178e-06}
{"global_step": 2860, "epoch": 1.1770093650303592, "loss": 10.6573, "grad_norm": 39.61531783787058, "learning_rate": 9.32680412371134e-06}
{"global_step": 2870, "epoch": 1.1811258618915303, "loss": 10.5804, "grad_norm": 32.38846280563923, "learning_rate": 9.323367697594501e-06}
{"global_step": 2880, "epoch": 1.1852423587527015, "loss": 10.618, "grad_norm": 28.914675084096515, "learning_rate": 9.319931271477663e-06}
{"global_step": 2890, "epoch": 1.1893588556138726, "loss": 10.5063, "grad_norm": 30.757441625032715, "learning_rate": 9.316494845360825e-06}
{"global_step": 2900, "epoch": 1.1934753524750437, "loss": 10.5521, "grad_norm": 31.287565569939332, "learning_rate": 9.313058419243986e-06}
{"global_step": 2910, "epoch": 1.1975918493362148, "loss": 10.5292, "grad_norm": 28.929871208415086, "learning_rate": 9.309621993127148e-06}
{"global_step": 2920, "epoch": 1.201708346197386, "loss": 10.5852, "grad_norm": 31.229185761150184, "learning_rate": 9.306185567010309e-06}
{"global_step": 2930, "epoch": 1.2058248430585572, "loss": 10.5663, "grad_norm": 33.338469531453924, "learning_rate": 9.30274914089347e-06}