{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.8179275625786602, "eval_steps": 5000, "global_step": 26000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.006992029086841001, "grad_norm": 75.90129852294922, "learning_rate": 6.780845858091577e-07, "loss": 16.865, "step": 100 }, { "epoch": 0.013984058173682002, "grad_norm": 71.16612243652344, "learning_rate": 1.3771408598392172e-06, "loss": 16.1556, "step": 200 }, { "epoch": 0.020976087260523003, "grad_norm": 130.67613220214844, "learning_rate": 2.0761971338692767e-06, "loss": 14.8008, "step": 300 }, { "epoch": 0.027968116347364003, "grad_norm": 36.4179801940918, "learning_rate": 2.7682628451590356e-06, "loss": 12.4025, "step": 400 }, { "epoch": 0.034960145434205, "grad_norm": 34.748844146728516, "learning_rate": 3.467319119189095e-06, "loss": 9.7465, "step": 500 }, { "epoch": 0.04195217452104601, "grad_norm": 8.039146423339844, "learning_rate": 4.166375393219155e-06, "loss": 8.448, "step": 600 }, { "epoch": 0.04894420360788701, "grad_norm": 10.288451194763184, "learning_rate": 4.865431667249214e-06, "loss": 8.1951, "step": 700 }, { "epoch": 0.05593623269472801, "grad_norm": 6.3236308097839355, "learning_rate": 5.564487941279273e-06, "loss": 8.1093, "step": 800 }, { "epoch": 0.06292826178156902, "grad_norm": 15.230368614196777, "learning_rate": 6.263544215309333e-06, "loss": 8.0567, "step": 900 }, { "epoch": 0.06992029086841, "grad_norm": 5.573168754577637, "learning_rate": 6.962600489339393e-06, "loss": 8.0401, "step": 1000 }, { "epoch": 0.07691231995525101, "grad_norm": 6.7740325927734375, "learning_rate": 7.661656763369451e-06, "loss": 7.9491, "step": 1100 }, { "epoch": 0.08390434904209201, "grad_norm": 6.167610168457031, "learning_rate": 8.360713037399512e-06, "loss": 7.9494, "step": 1200 }, { "epoch": 0.09089637812893302, "grad_norm": 5.53561544418335, "learning_rate": 9.05976931142957e-06, "loss": 7.9386, "step": 1300 }, { "epoch": 0.09788840721577402, "grad_norm": 6.056953430175781, "learning_rate": 9.758825585459631e-06, "loss": 7.9033, "step": 1400 }, { "epoch": 0.10488043630261502, "grad_norm": 5.160706043243408, "learning_rate": 1.045788185948969e-05, "loss": 7.9055, "step": 1500 }, { "epoch": 0.11187246538945601, "grad_norm": 5.525616645812988, "learning_rate": 1.115693813351975e-05, "loss": 7.9203, "step": 1600 }, { "epoch": 0.11886449447629702, "grad_norm": 5.553597927093506, "learning_rate": 1.185599440754981e-05, "loss": 7.8381, "step": 1700 }, { "epoch": 0.12585652356313803, "grad_norm": 4.8832478523254395, "learning_rate": 1.2555050681579868e-05, "loss": 7.8679, "step": 1800 }, { "epoch": 0.13284855264997902, "grad_norm": 5.308164596557617, "learning_rate": 1.3254106955609927e-05, "loss": 7.8686, "step": 1900 }, { "epoch": 0.13984058173682, "grad_norm": 6.790646553039551, "learning_rate": 1.3953163229639988e-05, "loss": 7.8252, "step": 2000 }, { "epoch": 0.14683261082366103, "grad_norm": 5.003779888153076, "learning_rate": 1.4652219503670046e-05, "loss": 7.856, "step": 2100 }, { "epoch": 0.15382463991050202, "grad_norm": 5.0926642417907715, "learning_rate": 1.5351275777700107e-05, "loss": 7.8301, "step": 2200 }, { "epoch": 0.16081666899734304, "grad_norm": 4.154193878173828, "learning_rate": 1.6050332051730168e-05, "loss": 7.8595, "step": 2300 }, { "epoch": 0.16780869808418403, "grad_norm": 4.168135166168213, "learning_rate": 1.6749388325760225e-05, "loss": 7.8138, "step": 2400 }, { "epoch": 0.17480072717102504, "grad_norm": 4.69076681137085, "learning_rate": 1.7448444599790285e-05, "loss": 7.812, "step": 2500 }, { "epoch": 0.18179275625786603, "grad_norm": 4.386991500854492, "learning_rate": 1.8147500873820346e-05, "loss": 7.8261, "step": 2600 }, { "epoch": 0.18878478534470702, "grad_norm": 5.777139186859131, "learning_rate": 1.8846557147850403e-05, "loss": 7.7988, "step": 2700 }, { "epoch": 0.19577681443154804, "grad_norm": 18.3277645111084, "learning_rate": 1.9545613421880464e-05, "loss": 7.7965, "step": 2800 }, { "epoch": 0.20276884351838903, "grad_norm": 4.5356669425964355, "learning_rate": 1.997280814201919e-05, "loss": 7.783, "step": 2900 }, { "epoch": 0.20976087260523005, "grad_norm": 5.4392476081848145, "learning_rate": 1.9895117119216877e-05, "loss": 7.7752, "step": 3000 }, { "epoch": 0.21675290169207104, "grad_norm": 5.365427017211914, "learning_rate": 1.981742609641456e-05, "loss": 7.7715, "step": 3100 }, { "epoch": 0.22374493077891203, "grad_norm": 4.111672401428223, "learning_rate": 1.9739735073612244e-05, "loss": 7.7903, "step": 3200 }, { "epoch": 0.23073695986575304, "grad_norm": 4.107003211975098, "learning_rate": 1.9662044050809928e-05, "loss": 7.7656, "step": 3300 }, { "epoch": 0.23772898895259403, "grad_norm": 4.667971611022949, "learning_rate": 1.9584353028007615e-05, "loss": 7.749, "step": 3400 }, { "epoch": 0.24472101803943505, "grad_norm": 4.010958194732666, "learning_rate": 1.95066620052053e-05, "loss": 7.7662, "step": 3500 }, { "epoch": 0.25171304712627607, "grad_norm": 4.07546329498291, "learning_rate": 1.9428970982402986e-05, "loss": 7.7492, "step": 3600 }, { "epoch": 0.25870507621311706, "grad_norm": 5.414000988006592, "learning_rate": 1.935127995960067e-05, "loss": 7.737, "step": 3700 }, { "epoch": 0.26569710529995805, "grad_norm": 4.4744648933410645, "learning_rate": 1.9273588936798357e-05, "loss": 7.7232, "step": 3800 }, { "epoch": 0.27268913438679904, "grad_norm": 4.141202926635742, "learning_rate": 1.919589791399604e-05, "loss": 7.7616, "step": 3900 }, { "epoch": 0.27968116347364, "grad_norm": 4.493043899536133, "learning_rate": 1.9118206891193724e-05, "loss": 7.7391, "step": 4000 }, { "epoch": 0.28667319256048107, "grad_norm": 4.083165168762207, "learning_rate": 1.904051586839141e-05, "loss": 7.7552, "step": 4100 }, { "epoch": 0.29366522164732206, "grad_norm": 8.303427696228027, "learning_rate": 1.8962824845589095e-05, "loss": 7.7273, "step": 4200 }, { "epoch": 0.30065725073416305, "grad_norm": 4.003914833068848, "learning_rate": 1.888513382278678e-05, "loss": 7.7216, "step": 4300 }, { "epoch": 0.30764927982100404, "grad_norm": 4.859315395355225, "learning_rate": 1.8807442799984462e-05, "loss": 7.7371, "step": 4400 }, { "epoch": 0.31464130890784503, "grad_norm": 4.693440914154053, "learning_rate": 1.872975177718215e-05, "loss": 7.7426, "step": 4500 }, { "epoch": 0.3216333379946861, "grad_norm": 4.81652307510376, "learning_rate": 1.8652060754379833e-05, "loss": 7.7406, "step": 4600 }, { "epoch": 0.32862536708152706, "grad_norm": 3.861663341522217, "learning_rate": 1.8574369731577516e-05, "loss": 7.712, "step": 4700 }, { "epoch": 0.33561739616836805, "grad_norm": 4.218888282775879, "learning_rate": 1.8496678708775203e-05, "loss": 7.7466, "step": 4800 }, { "epoch": 0.34260942525520904, "grad_norm": 8.032899856567383, "learning_rate": 1.8418987685972887e-05, "loss": 7.7058, "step": 4900 }, { "epoch": 0.3496014543420501, "grad_norm": 4.292692184448242, "learning_rate": 1.8342073573398596e-05, "loss": 7.7139, "step": 5000 }, { "epoch": 0.3496014543420501, "eval_loss": 7.6895527839660645, "eval_runtime": 270.2677, "eval_samples_per_second": 1696.499, "eval_steps_per_second": 13.257, "step": 5000 }, { "epoch": 0.3565934834288911, "grad_norm": 4.507449626922607, "learning_rate": 1.826438255059628e-05, "loss": 7.7457, "step": 5100 }, { "epoch": 0.36358551251573207, "grad_norm": 10.12509536743164, "learning_rate": 1.8186691527793966e-05, "loss": 7.7172, "step": 5200 }, { "epoch": 0.37057754160257306, "grad_norm": 4.254384517669678, "learning_rate": 1.810900050499165e-05, "loss": 7.739, "step": 5300 }, { "epoch": 0.37756957068941405, "grad_norm": 6.059901237487793, "learning_rate": 1.8031309482189334e-05, "loss": 7.7259, "step": 5400 }, { "epoch": 0.3845615997762551, "grad_norm": 5.770705223083496, "learning_rate": 1.7953618459387017e-05, "loss": 7.6977, "step": 5500 }, { "epoch": 0.3915536288630961, "grad_norm": 6.927788257598877, "learning_rate": 1.7875927436584705e-05, "loss": 7.7237, "step": 5600 }, { "epoch": 0.39854565794993707, "grad_norm": 4.323265552520752, "learning_rate": 1.7798236413782388e-05, "loss": 7.7118, "step": 5700 }, { "epoch": 0.40553768703677806, "grad_norm": 4.448848247528076, "learning_rate": 1.7720545390980072e-05, "loss": 7.7099, "step": 5800 }, { "epoch": 0.41252971612361905, "grad_norm": 66.31098175048828, "learning_rate": 1.764285436817776e-05, "loss": 7.7142, "step": 5900 }, { "epoch": 0.4195217452104601, "grad_norm": 6.65512228012085, "learning_rate": 1.7565163345375443e-05, "loss": 7.6885, "step": 6000 }, { "epoch": 0.4265137742973011, "grad_norm": 4.743120193481445, "learning_rate": 1.748747232257313e-05, "loss": 7.6799, "step": 6100 }, { "epoch": 0.4335058033841421, "grad_norm": 4.90665864944458, "learning_rate": 1.7409781299770813e-05, "loss": 7.7039, "step": 6200 }, { "epoch": 0.44049783247098306, "grad_norm": 6.465912342071533, "learning_rate": 1.7332090276968497e-05, "loss": 7.6825, "step": 6300 }, { "epoch": 0.44748986155782405, "grad_norm": 3.6341958045959473, "learning_rate": 1.7254399254166184e-05, "loss": 7.6846, "step": 6400 }, { "epoch": 0.4544818906446651, "grad_norm": 3.931257486343384, "learning_rate": 1.7176708231363868e-05, "loss": 7.7078, "step": 6500 }, { "epoch": 0.4614739197315061, "grad_norm": 4.2776665687561035, "learning_rate": 1.709901720856155e-05, "loss": 7.6945, "step": 6600 }, { "epoch": 0.4684659488183471, "grad_norm": 4.510386943817139, "learning_rate": 1.702132618575924e-05, "loss": 7.7017, "step": 6700 }, { "epoch": 0.47545797790518807, "grad_norm": 5.780529975891113, "learning_rate": 1.6943635162956922e-05, "loss": 7.6781, "step": 6800 }, { "epoch": 0.4824500069920291, "grad_norm": 5.802525997161865, "learning_rate": 1.6865944140154606e-05, "loss": 7.6885, "step": 6900 }, { "epoch": 0.4894420360788701, "grad_norm": 5.534703254699707, "learning_rate": 1.6789030027580314e-05, "loss": 7.7426, "step": 7000 }, { "epoch": 0.4964340651657111, "grad_norm": 5.897773742675781, "learning_rate": 1.6711339004778e-05, "loss": 7.6809, "step": 7100 }, { "epoch": 0.5034260942525521, "grad_norm": 5.115645408630371, "learning_rate": 1.6633647981975685e-05, "loss": 7.6977, "step": 7200 }, { "epoch": 0.5104181233393931, "grad_norm": 7.200738430023193, "learning_rate": 1.655595695917337e-05, "loss": 7.6964, "step": 7300 }, { "epoch": 0.5174101524262341, "grad_norm": 5.526965618133545, "learning_rate": 1.6478265936371052e-05, "loss": 7.6834, "step": 7400 }, { "epoch": 0.524402181513075, "grad_norm": 8.350557327270508, "learning_rate": 1.640057491356874e-05, "loss": 7.6593, "step": 7500 }, { "epoch": 0.5313942105999161, "grad_norm": 4.367435455322266, "learning_rate": 1.6322883890766423e-05, "loss": 7.6745, "step": 7600 }, { "epoch": 0.5383862396867571, "grad_norm": 7.726882457733154, "learning_rate": 1.6245192867964107e-05, "loss": 7.6587, "step": 7700 }, { "epoch": 0.5453782687735981, "grad_norm": 5.289243221282959, "learning_rate": 1.6167501845161794e-05, "loss": 7.6389, "step": 7800 }, { "epoch": 0.5523702978604391, "grad_norm": 4.716782093048096, "learning_rate": 1.6089810822359478e-05, "loss": 7.6298, "step": 7900 }, { "epoch": 0.55936232694728, "grad_norm": 4.2459797859191895, "learning_rate": 1.601211979955716e-05, "loss": 7.6693, "step": 8000 }, { "epoch": 0.5663543560341211, "grad_norm": 4.4402594566345215, "learning_rate": 1.5934428776754848e-05, "loss": 7.6454, "step": 8100 }, { "epoch": 0.5733463851209621, "grad_norm": 20.979795455932617, "learning_rate": 1.5856737753952532e-05, "loss": 7.6491, "step": 8200 }, { "epoch": 0.5803384142078031, "grad_norm": 4.494659900665283, "learning_rate": 1.5779046731150216e-05, "loss": 7.661, "step": 8300 }, { "epoch": 0.5873304432946441, "grad_norm": 4.788604736328125, "learning_rate": 1.57013557083479e-05, "loss": 7.6525, "step": 8400 }, { "epoch": 0.5943224723814851, "grad_norm": 4.576944351196289, "learning_rate": 1.5623664685545586e-05, "loss": 7.6669, "step": 8500 }, { "epoch": 0.6013145014683261, "grad_norm": 5.762516498565674, "learning_rate": 1.5545973662743273e-05, "loss": 7.6379, "step": 8600 }, { "epoch": 0.6083065305551671, "grad_norm": 4.864853858947754, "learning_rate": 1.5468282639940957e-05, "loss": 7.6706, "step": 8700 }, { "epoch": 0.6152985596420081, "grad_norm": 11.886726379394531, "learning_rate": 1.539059161713864e-05, "loss": 7.6487, "step": 8800 }, { "epoch": 0.6222905887288491, "grad_norm": 4.3859052658081055, "learning_rate": 1.5312900594336328e-05, "loss": 7.6607, "step": 8900 }, { "epoch": 0.6292826178156901, "grad_norm": 4.877004146575928, "learning_rate": 1.5235209571534011e-05, "loss": 7.6334, "step": 9000 }, { "epoch": 0.6362746469025311, "grad_norm": 10.190913200378418, "learning_rate": 1.5158295458959717e-05, "loss": 7.6891, "step": 9100 }, { "epoch": 0.6432666759893721, "grad_norm": 4.916624546051025, "learning_rate": 1.5080604436157402e-05, "loss": 7.734, "step": 9200 }, { "epoch": 0.6502587050762131, "grad_norm": 5.250345230102539, "learning_rate": 1.5002913413355089e-05, "loss": 7.6283, "step": 9300 }, { "epoch": 0.6572507341630541, "grad_norm": 4.70583963394165, "learning_rate": 1.4925222390552775e-05, "loss": 7.6461, "step": 9400 }, { "epoch": 0.6642427632498952, "grad_norm": 4.943760871887207, "learning_rate": 1.4847531367750458e-05, "loss": 7.623, "step": 9500 }, { "epoch": 0.6712347923367361, "grad_norm": 6.2978715896606445, "learning_rate": 1.4769840344948144e-05, "loss": 7.6251, "step": 9600 }, { "epoch": 0.6782268214235772, "grad_norm": 4.278825759887695, "learning_rate": 1.4692149322145827e-05, "loss": 7.6663, "step": 9700 }, { "epoch": 0.6852188505104181, "grad_norm": 6.855334758758545, "learning_rate": 1.4614458299343513e-05, "loss": 7.6376, "step": 9800 }, { "epoch": 0.6922108795972591, "grad_norm": 9.894013404846191, "learning_rate": 1.4536767276541198e-05, "loss": 7.6834, "step": 9900 }, { "epoch": 0.6992029086841002, "grad_norm": 4.454260349273682, "learning_rate": 1.4459076253738882e-05, "loss": 7.6851, "step": 10000 }, { "epoch": 0.6992029086841002, "eval_loss": 7.6099066734313965, "eval_runtime": 436.4855, "eval_samples_per_second": 1050.456, "eval_steps_per_second": 8.209, "step": 10000 }, { "epoch": 0.7061949377709411, "grad_norm": 5.147873878479004, "learning_rate": 1.4381385230936567e-05, "loss": 7.6034, "step": 10100 }, { "epoch": 0.7131869668577822, "grad_norm": 5.6142964363098145, "learning_rate": 1.430369420813425e-05, "loss": 7.6512, "step": 10200 }, { "epoch": 0.7201789959446231, "grad_norm": 10.30461597442627, "learning_rate": 1.4226003185331936e-05, "loss": 7.6413, "step": 10300 }, { "epoch": 0.7271710250314641, "grad_norm": 6.112381458282471, "learning_rate": 1.4148312162529621e-05, "loss": 7.6083, "step": 10400 }, { "epoch": 0.7341630541183052, "grad_norm": 4.750720977783203, "learning_rate": 1.4070621139727305e-05, "loss": 7.6475, "step": 10500 }, { "epoch": 0.7411550832051461, "grad_norm": 4.715427875518799, "learning_rate": 1.399293011692499e-05, "loss": 7.61, "step": 10600 }, { "epoch": 0.7481471122919872, "grad_norm": 5.024092197418213, "learning_rate": 1.3915239094122674e-05, "loss": 7.6404, "step": 10700 }, { "epoch": 0.7551391413788281, "grad_norm": 7.21763801574707, "learning_rate": 1.383754807132036e-05, "loss": 7.6308, "step": 10800 }, { "epoch": 0.7621311704656691, "grad_norm": 5.111927032470703, "learning_rate": 1.3759857048518043e-05, "loss": 7.638, "step": 10900 }, { "epoch": 0.7691231995525102, "grad_norm": 5.705997467041016, "learning_rate": 1.368216602571573e-05, "loss": 7.5954, "step": 11000 }, { "epoch": 0.7761152286393511, "grad_norm": 5.417977809906006, "learning_rate": 1.3604475002913415e-05, "loss": 7.6037, "step": 11100 }, { "epoch": 0.7831072577261922, "grad_norm": 4.27499532699585, "learning_rate": 1.3527560890339122e-05, "loss": 7.6405, "step": 11200 }, { "epoch": 0.7900992868130331, "grad_norm": 4.530681133270264, "learning_rate": 1.3449869867536806e-05, "loss": 7.6396, "step": 11300 }, { "epoch": 0.7970913158998741, "grad_norm": 6.06285285949707, "learning_rate": 1.3372178844734491e-05, "loss": 7.5898, "step": 11400 }, { "epoch": 0.8040833449867152, "grad_norm": 5.323781490325928, "learning_rate": 1.3294487821932177e-05, "loss": 7.644, "step": 11500 }, { "epoch": 0.8110753740735561, "grad_norm": 5.1687092781066895, "learning_rate": 1.321679679912986e-05, "loss": 7.639, "step": 11600 }, { "epoch": 0.8180674031603972, "grad_norm": 13.228008270263672, "learning_rate": 1.3139105776327546e-05, "loss": 7.6146, "step": 11700 }, { "epoch": 0.8250594322472381, "grad_norm": 14.277410507202148, "learning_rate": 1.3061414753525233e-05, "loss": 7.6076, "step": 11800 }, { "epoch": 0.8320514613340791, "grad_norm": 5.011687755584717, "learning_rate": 1.2983723730722917e-05, "loss": 7.5997, "step": 11900 }, { "epoch": 0.8390434904209202, "grad_norm": 5.056484699249268, "learning_rate": 1.2906032707920602e-05, "loss": 7.6196, "step": 12000 }, { "epoch": 0.8460355195077611, "grad_norm": 5.087393283843994, "learning_rate": 1.2828341685118286e-05, "loss": 7.6139, "step": 12100 }, { "epoch": 0.8530275485946022, "grad_norm": 6.482489109039307, "learning_rate": 1.2750650662315971e-05, "loss": 7.6335, "step": 12200 }, { "epoch": 0.8600195776814431, "grad_norm": 5.367912292480469, "learning_rate": 1.2672959639513656e-05, "loss": 7.6057, "step": 12300 }, { "epoch": 0.8670116067682841, "grad_norm": 5.633285999298096, "learning_rate": 1.259526861671134e-05, "loss": 7.5759, "step": 12400 }, { "epoch": 0.8740036358551252, "grad_norm": 5.425296783447266, "learning_rate": 1.2518354504137047e-05, "loss": 7.6044, "step": 12500 }, { "epoch": 0.8809956649419661, "grad_norm": 5.661762237548828, "learning_rate": 1.2440663481334734e-05, "loss": 7.589, "step": 12600 }, { "epoch": 0.8879876940288072, "grad_norm": 51.0821647644043, "learning_rate": 1.2362972458532418e-05, "loss": 7.5871, "step": 12700 }, { "epoch": 0.8949797231156481, "grad_norm": 12.381628036499023, "learning_rate": 1.2285281435730103e-05, "loss": 7.6161, "step": 12800 }, { "epoch": 0.9019717522024892, "grad_norm": 8.360747337341309, "learning_rate": 1.2207590412927788e-05, "loss": 7.5797, "step": 12900 }, { "epoch": 0.9089637812893302, "grad_norm": 5.329476356506348, "learning_rate": 1.2129899390125472e-05, "loss": 7.6202, "step": 13000 }, { "epoch": 0.9159558103761711, "grad_norm": 10.23351764678955, "learning_rate": 1.2052208367323157e-05, "loss": 7.6116, "step": 13100 }, { "epoch": 0.9229478394630122, "grad_norm": 5.831717491149902, "learning_rate": 1.1974517344520841e-05, "loss": 7.6253, "step": 13200 }, { "epoch": 0.9299398685498532, "grad_norm": 5.673948764801025, "learning_rate": 1.1896826321718526e-05, "loss": 7.5891, "step": 13300 }, { "epoch": 0.9369318976366942, "grad_norm": 4.9491963386535645, "learning_rate": 1.1819135298916212e-05, "loss": 7.5856, "step": 13400 }, { "epoch": 0.9439239267235352, "grad_norm": 10.202159881591797, "learning_rate": 1.1741444276113895e-05, "loss": 7.5824, "step": 13500 }, { "epoch": 0.9509159558103761, "grad_norm": 5.314234256744385, "learning_rate": 1.166375325331158e-05, "loss": 7.6288, "step": 13600 }, { "epoch": 0.9579079848972172, "grad_norm": 6.260787010192871, "learning_rate": 1.1586062230509264e-05, "loss": 7.5653, "step": 13700 }, { "epoch": 0.9649000139840582, "grad_norm": 26.669679641723633, "learning_rate": 1.150837120770695e-05, "loss": 7.6073, "step": 13800 }, { "epoch": 0.9718920430708992, "grad_norm": 6.57592248916626, "learning_rate": 1.1430680184904635e-05, "loss": 7.5958, "step": 13900 }, { "epoch": 0.9788840721577402, "grad_norm": 7.6479363441467285, "learning_rate": 1.1352989162102319e-05, "loss": 7.599, "step": 14000 }, { "epoch": 0.9858761012445811, "grad_norm": 6.408242702484131, "learning_rate": 1.1275298139300004e-05, "loss": 7.5982, "step": 14100 }, { "epoch": 0.9928681303314222, "grad_norm": 5.306247234344482, "learning_rate": 1.1197607116497688e-05, "loss": 7.5634, "step": 14200 }, { "epoch": 0.9998601594182632, "grad_norm": 5.802295684814453, "learning_rate": 1.1119916093695375e-05, "loss": 7.5923, "step": 14300 }, { "epoch": 1.0068521885051043, "grad_norm": 7.27552604675293, "learning_rate": 1.104222507089306e-05, "loss": 7.6072, "step": 14400 }, { "epoch": 1.013844217591945, "grad_norm": 5.475253105163574, "learning_rate": 1.0964534048090744e-05, "loss": 7.5589, "step": 14500 }, { "epoch": 1.0208362466787861, "grad_norm": 5.9576544761657715, "learning_rate": 1.088684302528843e-05, "loss": 7.6, "step": 14600 }, { "epoch": 1.0278282757656272, "grad_norm": 5.9021196365356445, "learning_rate": 1.0809152002486115e-05, "loss": 7.5464, "step": 14700 }, { "epoch": 1.0348203048524682, "grad_norm": 5.77813196182251, "learning_rate": 1.0731460979683798e-05, "loss": 7.5824, "step": 14800 }, { "epoch": 1.0418123339393093, "grad_norm": 6.408592224121094, "learning_rate": 1.0653769956881484e-05, "loss": 7.5528, "step": 14900 }, { "epoch": 1.04880436302615, "grad_norm": 5.504671573638916, "learning_rate": 1.0576078934079167e-05, "loss": 7.568, "step": 15000 }, { "epoch": 1.04880436302615, "eval_loss": 7.561756610870361, "eval_runtime": 277.2921, "eval_samples_per_second": 1653.524, "eval_steps_per_second": 12.921, "step": 15000 }, { "epoch": 1.0557963921129911, "grad_norm": 5.96599817276001, "learning_rate": 1.0498387911276853e-05, "loss": 7.559, "step": 15100 }, { "epoch": 1.0627884211998322, "grad_norm": 17.772111892700195, "learning_rate": 1.0420696888474538e-05, "loss": 7.5555, "step": 15200 }, { "epoch": 1.0697804502866732, "grad_norm": 8.23525333404541, "learning_rate": 1.0343005865672222e-05, "loss": 7.552, "step": 15300 }, { "epoch": 1.0767724793735143, "grad_norm": 5.616782188415527, "learning_rate": 1.0265314842869907e-05, "loss": 7.5851, "step": 15400 }, { "epoch": 1.083764508460355, "grad_norm": 6.9555888175964355, "learning_rate": 1.018762382006759e-05, "loss": 7.5256, "step": 15500 }, { "epoch": 1.0907565375471961, "grad_norm": 6.269557952880859, "learning_rate": 1.0109932797265276e-05, "loss": 7.5683, "step": 15600 }, { "epoch": 1.0977485666340372, "grad_norm": 5.618041038513184, "learning_rate": 1.0032241774462962e-05, "loss": 7.5909, "step": 15700 }, { "epoch": 1.1047405957208782, "grad_norm": 7.424361705780029, "learning_rate": 9.954550751660647e-06, "loss": 7.5655, "step": 15800 }, { "epoch": 1.1117326248077193, "grad_norm": 6.244665622711182, "learning_rate": 9.87685972885833e-06, "loss": 7.5476, "step": 15900 }, { "epoch": 1.11872465389456, "grad_norm": 5.86741304397583, "learning_rate": 9.799168706056016e-06, "loss": 7.5721, "step": 16000 }, { "epoch": 1.1257166829814012, "grad_norm": 6.809812068939209, "learning_rate": 9.721477683253701e-06, "loss": 7.5593, "step": 16100 }, { "epoch": 1.1327087120682422, "grad_norm": 5.530270576477051, "learning_rate": 9.643786660451385e-06, "loss": 7.5783, "step": 16200 }, { "epoch": 1.1397007411550832, "grad_norm": 6.193401336669922, "learning_rate": 9.56609563764907e-06, "loss": 7.5905, "step": 16300 }, { "epoch": 1.1466927702419243, "grad_norm": 6.046769142150879, "learning_rate": 9.488404614846756e-06, "loss": 7.542, "step": 16400 }, { "epoch": 1.153684799328765, "grad_norm": 9.423077583312988, "learning_rate": 9.410713592044441e-06, "loss": 7.5794, "step": 16500 }, { "epoch": 1.1606768284156062, "grad_norm": 6.115114688873291, "learning_rate": 9.333022569242125e-06, "loss": 7.5669, "step": 16600 }, { "epoch": 1.1676688575024472, "grad_norm": 7.971080780029297, "learning_rate": 9.25533154643981e-06, "loss": 7.5738, "step": 16700 }, { "epoch": 1.1746608865892882, "grad_norm": 6.336145877838135, "learning_rate": 9.178417433865517e-06, "loss": 7.5431, "step": 16800 }, { "epoch": 1.1816529156761293, "grad_norm": 29.671520233154297, "learning_rate": 9.100726411063202e-06, "loss": 7.5401, "step": 16900 }, { "epoch": 1.1886449447629701, "grad_norm": 5.954431533813477, "learning_rate": 9.023035388260886e-06, "loss": 7.5629, "step": 17000 }, { "epoch": 1.1956369738498112, "grad_norm": 5.608087062835693, "learning_rate": 8.945344365458573e-06, "loss": 7.5534, "step": 17100 }, { "epoch": 1.2026290029366522, "grad_norm": 6.294321060180664, "learning_rate": 8.867653342656257e-06, "loss": 7.571, "step": 17200 }, { "epoch": 1.2096210320234932, "grad_norm": 7.695574760437012, "learning_rate": 8.789962319853942e-06, "loss": 7.5387, "step": 17300 }, { "epoch": 1.2166130611103343, "grad_norm": 7.697295665740967, "learning_rate": 8.712271297051626e-06, "loss": 7.5596, "step": 17400 }, { "epoch": 1.2236050901971751, "grad_norm": 7.128779411315918, "learning_rate": 8.634580274249311e-06, "loss": 7.5427, "step": 17500 }, { "epoch": 1.2305971192840162, "grad_norm": 5.591519832611084, "learning_rate": 8.556889251446996e-06, "loss": 7.5305, "step": 17600 }, { "epoch": 1.2375891483708572, "grad_norm": 5.650510311126709, "learning_rate": 8.47919822864468e-06, "loss": 7.556, "step": 17700 }, { "epoch": 1.2445811774576983, "grad_norm": 5.732466220855713, "learning_rate": 8.401507205842366e-06, "loss": 7.5442, "step": 17800 }, { "epoch": 1.2515732065445393, "grad_norm": 5.8693952560424805, "learning_rate": 8.32381618304005e-06, "loss": 7.5635, "step": 17900 }, { "epoch": 1.2585652356313801, "grad_norm": 5.428412437438965, "learning_rate": 8.246125160237736e-06, "loss": 7.5675, "step": 18000 }, { "epoch": 1.2655572647182212, "grad_norm": 13.564213752746582, "learning_rate": 8.16843413743542e-06, "loss": 7.5412, "step": 18100 }, { "epoch": 1.2725492938050622, "grad_norm": 6.041943073272705, "learning_rate": 8.090743114633105e-06, "loss": 7.5148, "step": 18200 }, { "epoch": 1.2795413228919033, "grad_norm": 6.719943523406982, "learning_rate": 8.013052091830789e-06, "loss": 7.546, "step": 18300 }, { "epoch": 1.2865333519787443, "grad_norm": 6.333201885223389, "learning_rate": 7.935361069028474e-06, "loss": 7.5608, "step": 18400 }, { "epoch": 1.2935253810655851, "grad_norm": 6.595645427703857, "learning_rate": 7.85767004622616e-06, "loss": 7.5269, "step": 18500 }, { "epoch": 1.3005174101524262, "grad_norm": 68.7165756225586, "learning_rate": 7.779979023423843e-06, "loss": 7.5614, "step": 18600 }, { "epoch": 1.3075094392392672, "grad_norm": 6.356012344360352, "learning_rate": 7.702288000621529e-06, "loss": 7.5276, "step": 18700 }, { "epoch": 1.3145014683261083, "grad_norm": 5.727452754974365, "learning_rate": 7.624596977819214e-06, "loss": 7.5586, "step": 18800 }, { "epoch": 1.3214934974129493, "grad_norm": 6.261607646942139, "learning_rate": 7.5469059550168985e-06, "loss": 7.5783, "step": 18900 }, { "epoch": 1.3284855264997901, "grad_norm": 6.753152847290039, "learning_rate": 7.469214932214584e-06, "loss": 7.5312, "step": 19000 }, { "epoch": 1.3354775555866312, "grad_norm": 6.3251471519470215, "learning_rate": 7.391523909412268e-06, "loss": 7.536, "step": 19100 }, { "epoch": 1.3424695846734722, "grad_norm": 13.632108688354492, "learning_rate": 7.314609796837976e-06, "loss": 7.5497, "step": 19200 }, { "epoch": 1.3494616137603133, "grad_norm": 7.272294044494629, "learning_rate": 7.236918774035661e-06, "loss": 7.5256, "step": 19300 }, { "epoch": 1.3564536428471543, "grad_norm": 5.5204339027404785, "learning_rate": 7.159227751233345e-06, "loss": 7.5364, "step": 19400 }, { "epoch": 1.3634456719339951, "grad_norm": 9.409886360168457, "learning_rate": 7.08153672843103e-06, "loss": 7.5311, "step": 19500 }, { "epoch": 1.3704377010208362, "grad_norm": 5.982423782348633, "learning_rate": 7.003845705628716e-06, "loss": 7.5557, "step": 19600 }, { "epoch": 1.3774297301076772, "grad_norm": 4.965424060821533, "learning_rate": 6.9261546828264005e-06, "loss": 7.5531, "step": 19700 }, { "epoch": 1.3844217591945183, "grad_norm": 6.396183967590332, "learning_rate": 6.848463660024085e-06, "loss": 7.4844, "step": 19800 }, { "epoch": 1.3914137882813593, "grad_norm": 7.028730869293213, "learning_rate": 6.7707726372217695e-06, "loss": 7.5408, "step": 19900 }, { "epoch": 1.3984058173682001, "grad_norm": 7.949461936950684, "learning_rate": 6.693081614419454e-06, "loss": 7.5336, "step": 20000 }, { "epoch": 1.3984058173682001, "eval_loss": 7.509986400604248, "eval_runtime": 277.4571, "eval_samples_per_second": 1652.54, "eval_steps_per_second": 12.914, "step": 20000 }, { "epoch": 1.4053978464550412, "grad_norm": 7.297272205352783, "learning_rate": 6.615390591617139e-06, "loss": 7.524, "step": 20100 }, { "epoch": 1.4123898755418822, "grad_norm": 6.259093284606934, "learning_rate": 6.537699568814824e-06, "loss": 7.5236, "step": 20200 }, { "epoch": 1.4193819046287233, "grad_norm": 11.356688499450684, "learning_rate": 6.460008546012508e-06, "loss": 7.5354, "step": 20300 }, { "epoch": 1.4263739337155643, "grad_norm": 7.6718363761901855, "learning_rate": 6.382317523210193e-06, "loss": 7.5228, "step": 20400 }, { "epoch": 1.4333659628024051, "grad_norm": 8.468694686889648, "learning_rate": 6.304626500407879e-06, "loss": 7.5453, "step": 20500 }, { "epoch": 1.4403579918892462, "grad_norm": 8.101908683776855, "learning_rate": 6.226935477605564e-06, "loss": 7.5492, "step": 20600 }, { "epoch": 1.4473500209760872, "grad_norm": 6.307611465454102, "learning_rate": 6.149244454803248e-06, "loss": 7.5145, "step": 20700 }, { "epoch": 1.4543420500629283, "grad_norm": 5.946073532104492, "learning_rate": 6.071553432000933e-06, "loss": 7.5464, "step": 20800 }, { "epoch": 1.4613340791497693, "grad_norm": 6.155106544494629, "learning_rate": 5.993862409198617e-06, "loss": 7.5377, "step": 20900 }, { "epoch": 1.4683261082366101, "grad_norm": 16.788408279418945, "learning_rate": 5.9161713863963025e-06, "loss": 7.5221, "step": 21000 }, { "epoch": 1.4753181373234512, "grad_norm": 6.25968599319458, "learning_rate": 5.838480363593987e-06, "loss": 7.5793, "step": 21100 }, { "epoch": 1.4823101664102922, "grad_norm": 7.0548248291015625, "learning_rate": 5.7607893407916716e-06, "loss": 7.5234, "step": 21200 }, { "epoch": 1.4893021954971333, "grad_norm": 6.981344223022461, "learning_rate": 5.683098317989357e-06, "loss": 7.4922, "step": 21300 }, { "epoch": 1.4962942245839743, "grad_norm": 6.049755573272705, "learning_rate": 5.605407295187042e-06, "loss": 7.5196, "step": 21400 }, { "epoch": 1.5032862536708151, "grad_norm": 6.19504976272583, "learning_rate": 5.527716272384727e-06, "loss": 7.5265, "step": 21500 }, { "epoch": 1.5102782827576564, "grad_norm": 6.721789360046387, "learning_rate": 5.450025249582411e-06, "loss": 7.5251, "step": 21600 }, { "epoch": 1.5172703118444972, "grad_norm": 7.129571437835693, "learning_rate": 5.372334226780096e-06, "loss": 7.4982, "step": 21700 }, { "epoch": 1.5242623409313383, "grad_norm": 6.069876194000244, "learning_rate": 5.29464320397778e-06, "loss": 7.5225, "step": 21800 }, { "epoch": 1.5312543700181793, "grad_norm": 6.939220905303955, "learning_rate": 5.216952181175466e-06, "loss": 7.5725, "step": 21900 }, { "epoch": 1.5382463991050201, "grad_norm": 8.495509147644043, "learning_rate": 5.13926115837315e-06, "loss": 7.5109, "step": 22000 }, { "epoch": 1.5452384281918614, "grad_norm": 9.123753547668457, "learning_rate": 5.061570135570835e-06, "loss": 7.5382, "step": 22100 }, { "epoch": 1.5522304572787022, "grad_norm": 7.599153995513916, "learning_rate": 4.98387911276852e-06, "loss": 7.5131, "step": 22200 }, { "epoch": 1.5592224863655433, "grad_norm": 8.744050025939941, "learning_rate": 4.906965000194228e-06, "loss": 7.5376, "step": 22300 }, { "epoch": 1.5662145154523843, "grad_norm": 9.72993278503418, "learning_rate": 4.829273977391912e-06, "loss": 7.5373, "step": 22400 }, { "epoch": 1.5732065445392251, "grad_norm": 5.993570804595947, "learning_rate": 4.751582954589598e-06, "loss": 7.5467, "step": 22500 }, { "epoch": 1.5801985736260664, "grad_norm": 6.120882034301758, "learning_rate": 4.673891931787282e-06, "loss": 7.519, "step": 22600 }, { "epoch": 1.5871906027129072, "grad_norm": 6.386423587799072, "learning_rate": 4.596200908984968e-06, "loss": 7.5137, "step": 22700 }, { "epoch": 1.5941826317997483, "grad_norm": 7.490204811096191, "learning_rate": 4.518509886182652e-06, "loss": 7.5511, "step": 22800 }, { "epoch": 1.6011746608865893, "grad_norm": 7.535491943359375, "learning_rate": 4.440818863380337e-06, "loss": 7.5376, "step": 22900 }, { "epoch": 1.6081666899734302, "grad_norm": 6.852174282073975, "learning_rate": 4.363127840578021e-06, "loss": 7.4912, "step": 23000 }, { "epoch": 1.6151587190602714, "grad_norm": 6.470872402191162, "learning_rate": 4.2854368177757065e-06, "loss": 7.5331, "step": 23100 }, { "epoch": 1.6221507481471122, "grad_norm": 7.37431526184082, "learning_rate": 4.207745794973391e-06, "loss": 7.5223, "step": 23200 }, { "epoch": 1.6291427772339533, "grad_norm": 9.51193904876709, "learning_rate": 4.1300547721710756e-06, "loss": 7.5342, "step": 23300 }, { "epoch": 1.6361348063207943, "grad_norm": 6.587790489196777, "learning_rate": 4.052363749368761e-06, "loss": 7.5171, "step": 23400 }, { "epoch": 1.6431268354076352, "grad_norm": 5.792933464050293, "learning_rate": 3.9746727265664454e-06, "loss": 7.5225, "step": 23500 }, { "epoch": 1.6501188644944764, "grad_norm": 6.8659772872924805, "learning_rate": 3.896981703764131e-06, "loss": 7.5273, "step": 23600 }, { "epoch": 1.6571108935813172, "grad_norm": 6.789074420928955, "learning_rate": 3.819290680961815e-06, "loss": 7.5179, "step": 23700 }, { "epoch": 1.6641029226681583, "grad_norm": 6.146234512329102, "learning_rate": 3.7415996581595e-06, "loss": 7.5508, "step": 23800 }, { "epoch": 1.6710949517549993, "grad_norm": 6.709959030151367, "learning_rate": 3.6639086353571848e-06, "loss": 7.5064, "step": 23900 }, { "epoch": 1.6780869808418402, "grad_norm": 6.41048526763916, "learning_rate": 3.5862176125548697e-06, "loss": 7.5008, "step": 24000 }, { "epoch": 1.6850790099286814, "grad_norm": 6.711287498474121, "learning_rate": 3.5085265897525546e-06, "loss": 7.5046, "step": 24100 }, { "epoch": 1.6920710390155222, "grad_norm": 12.106834411621094, "learning_rate": 3.430835566950239e-06, "loss": 7.5295, "step": 24200 }, { "epoch": 1.6990630681023633, "grad_norm": 5.898963451385498, "learning_rate": 3.3531445441479237e-06, "loss": 7.4983, "step": 24300 }, { "epoch": 1.7060550971892043, "grad_norm": 7.358336448669434, "learning_rate": 3.276230431573632e-06, "loss": 7.5451, "step": 24400 }, { "epoch": 1.7130471262760452, "grad_norm": 8.829870223999023, "learning_rate": 3.198539408771317e-06, "loss": 7.5092, "step": 24500 }, { "epoch": 1.7200391553628864, "grad_norm": 6.954072952270508, "learning_rate": 3.1216252961970243e-06, "loss": 7.5434, "step": 24600 }, { "epoch": 1.7270311844497273, "grad_norm": 5.627025604248047, "learning_rate": 3.0439342733947096e-06, "loss": 7.5296, "step": 24700 }, { "epoch": 1.7340232135365683, "grad_norm": 6.21652364730835, "learning_rate": 2.9662432505923946e-06, "loss": 7.5036, "step": 24800 }, { "epoch": 1.7410152426234093, "grad_norm": 6.878439903259277, "learning_rate": 2.888552227790079e-06, "loss": 7.5133, "step": 24900 }, { "epoch": 1.7480072717102502, "grad_norm": 7.0961151123046875, "learning_rate": 2.8108612049877636e-06, "loss": 7.5222, "step": 25000 }, { "epoch": 1.7480072717102502, "eval_loss": 7.498583793640137, "eval_runtime": 273.9346, "eval_samples_per_second": 1673.79, "eval_steps_per_second": 13.08, "step": 25000 }, { "epoch": 1.7549993007970914, "grad_norm": 6.734392166137695, "learning_rate": 2.733170182185449e-06, "loss": 7.4928, "step": 25100 }, { "epoch": 1.7619913298839323, "grad_norm": 7.46415376663208, "learning_rate": 2.6554791593831335e-06, "loss": 7.5338, "step": 25200 }, { "epoch": 1.7689833589707733, "grad_norm": 7.958985328674316, "learning_rate": 2.5777881365808184e-06, "loss": 7.4937, "step": 25300 }, { "epoch": 1.7759753880576143, "grad_norm": 6.51747989654541, "learning_rate": 2.500097113778503e-06, "loss": 7.542, "step": 25400 }, { "epoch": 1.7829674171444552, "grad_norm": 7.316498756408691, "learning_rate": 2.422406090976188e-06, "loss": 7.5296, "step": 25500 }, { "epoch": 1.7899594462312964, "grad_norm": 7.3862528800964355, "learning_rate": 2.3447150681738724e-06, "loss": 7.5069, "step": 25600 }, { "epoch": 1.7969514753181373, "grad_norm": 5.974991321563721, "learning_rate": 2.2670240453715577e-06, "loss": 7.5311, "step": 25700 }, { "epoch": 1.8039435044049783, "grad_norm": 6.846700191497803, "learning_rate": 2.1893330225692422e-06, "loss": 7.5433, "step": 25800 }, { "epoch": 1.8109355334918193, "grad_norm": 6.979272365570068, "learning_rate": 2.111641999766927e-06, "loss": 7.4879, "step": 25900 }, { "epoch": 1.8179275625786602, "grad_norm": 6.944764137268066, "learning_rate": 2.0339509769646117e-06, "loss": 7.5547, "step": 26000 } ], "logging_steps": 100, "max_steps": 28604, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 128, "trial_name": null, "trial_params": null }