{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.39269681566490244, "eval_steps": 1000000, "global_step": 44963, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0043668885046027, "grad_norm": 1.5252772569656372, "learning_rate": 9.99956331114954e-06, "loss": 3.1092, "step": 500 }, { "epoch": 0.0087337770092054, "grad_norm": 1.5550904273986816, "learning_rate": 9.99912662229908e-06, "loss": 3.1137, "step": 1000 }, { "epoch": 0.013100665513808101, "grad_norm": 1.6027861833572388, "learning_rate": 9.99868993344862e-06, "loss": 3.1103, "step": 1500 }, { "epoch": 0.0174675540184108, "grad_norm": 1.5541950464248657, "learning_rate": 9.99825324459816e-06, "loss": 3.1174, "step": 2000 }, { "epoch": 0.021834442523013503, "grad_norm": 1.5546715259552002, "learning_rate": 9.9978165557477e-06, "loss": 3.1136, "step": 2500 }, { "epoch": 0.026201331027616202, "grad_norm": 1.5220922231674194, "learning_rate": 9.997379866897238e-06, "loss": 3.1103, "step": 3000 }, { "epoch": 0.030568219532218905, "grad_norm": 1.5199161767959595, "learning_rate": 9.996943178046778e-06, "loss": 3.1157, "step": 3500 }, { "epoch": 0.0349351080368216, "grad_norm": 1.5355709791183472, "learning_rate": 9.996506489196318e-06, "loss": 3.1172, "step": 4000 }, { "epoch": 0.03930199654142431, "grad_norm": 1.5802912712097168, "learning_rate": 9.996069800345858e-06, "loss": 3.1136, "step": 4500 }, { "epoch": 0.043668885046027006, "grad_norm": 1.5675339698791504, "learning_rate": 9.995633111495399e-06, "loss": 3.1132, "step": 5000 }, { "epoch": 0.048035773550629705, "grad_norm": 1.5897544622421265, "learning_rate": 9.995196422644939e-06, "loss": 3.1113, "step": 5500 }, { "epoch": 0.052402662055232405, "grad_norm": 1.5565438270568848, "learning_rate": 9.994759733794479e-06, "loss": 3.1105, "step": 6000 }, { "epoch": 0.056769550559835104, "grad_norm": 1.5703555345535278, "learning_rate": 9.994323044944017e-06, "loss": 3.1029, "step": 6500 }, { "epoch": 0.06113643906443781, "grad_norm": 1.7245922088623047, "learning_rate": 9.993886356093557e-06, "loss": 3.1136, "step": 7000 }, { "epoch": 0.06550332756904051, "grad_norm": 1.5329172611236572, "learning_rate": 9.993449667243097e-06, "loss": 3.1085, "step": 7500 }, { "epoch": 0.0698702160736432, "grad_norm": 1.582455039024353, "learning_rate": 9.993012978392636e-06, "loss": 3.1097, "step": 8000 }, { "epoch": 0.07423710457824591, "grad_norm": 1.5983030796051025, "learning_rate": 9.992576289542176e-06, "loss": 3.1121, "step": 8500 }, { "epoch": 0.07860399308284861, "grad_norm": 1.57261323928833, "learning_rate": 9.992139600691716e-06, "loss": 3.1019, "step": 9000 }, { "epoch": 0.0829708815874513, "grad_norm": 1.6313079595565796, "learning_rate": 9.991702911841256e-06, "loss": 3.103, "step": 9500 }, { "epoch": 0.08733777009205401, "grad_norm": 1.641048789024353, "learning_rate": 9.991266222990796e-06, "loss": 3.1067, "step": 10000 }, { "epoch": 0.0917046585966567, "grad_norm": 1.5543872117996216, "learning_rate": 9.990829534140335e-06, "loss": 3.1154, "step": 10500 }, { "epoch": 0.09607154710125941, "grad_norm": 1.600199818611145, "learning_rate": 9.990392845289875e-06, "loss": 3.1125, "step": 11000 }, { "epoch": 0.10043843560586212, "grad_norm": 1.5695594549179077, "learning_rate": 9.989956156439415e-06, "loss": 3.1062, "step": 11500 }, { "epoch": 0.10480532411046481, "grad_norm": 1.567922830581665, "learning_rate": 9.989519467588953e-06, "loss": 3.0928, "step": 12000 }, { "epoch": 0.10917221261506752, "grad_norm": 1.5480656623840332, "learning_rate": 9.989082778738493e-06, "loss": 3.1059, "step": 12500 }, { "epoch": 0.11353910111967021, "grad_norm": 1.5923876762390137, "learning_rate": 9.988646089888033e-06, "loss": 3.1054, "step": 13000 }, { "epoch": 0.11790598962427291, "grad_norm": 1.5641125440597534, "learning_rate": 9.988209401037573e-06, "loss": 3.1064, "step": 13500 }, { "epoch": 0.12227287812887562, "grad_norm": 1.556784749031067, "learning_rate": 9.987772712187114e-06, "loss": 3.0991, "step": 14000 }, { "epoch": 0.1266397666334783, "grad_norm": 1.5843846797943115, "learning_rate": 9.987336023336654e-06, "loss": 3.1074, "step": 14500 }, { "epoch": 0.13100665513808102, "grad_norm": 1.5881807804107666, "learning_rate": 9.986899334486194e-06, "loss": 3.1025, "step": 15000 }, { "epoch": 0.13537354364268372, "grad_norm": 1.592093825340271, "learning_rate": 9.986462645635732e-06, "loss": 3.1079, "step": 15500 }, { "epoch": 0.1397404321472864, "grad_norm": 1.563472867012024, "learning_rate": 9.986025956785272e-06, "loss": 3.0971, "step": 16000 }, { "epoch": 0.1441073206518891, "grad_norm": 1.5815701484680176, "learning_rate": 9.985589267934812e-06, "loss": 3.1064, "step": 16500 }, { "epoch": 0.14847420915649182, "grad_norm": 1.5487664937973022, "learning_rate": 9.985152579084352e-06, "loss": 3.0966, "step": 17000 }, { "epoch": 0.15284109766109452, "grad_norm": 1.5602947473526, "learning_rate": 9.984715890233891e-06, "loss": 3.0976, "step": 17500 }, { "epoch": 0.15720798616569723, "grad_norm": 1.6305474042892456, "learning_rate": 9.984279201383431e-06, "loss": 3.0978, "step": 18000 }, { "epoch": 0.1615748746702999, "grad_norm": 1.5489692687988281, "learning_rate": 9.983842512532971e-06, "loss": 3.1058, "step": 18500 }, { "epoch": 0.1659417631749026, "grad_norm": 1.575688362121582, "learning_rate": 9.98340582368251e-06, "loss": 3.1003, "step": 19000 }, { "epoch": 0.17030865167950532, "grad_norm": 1.5600476264953613, "learning_rate": 9.98296913483205e-06, "loss": 3.0998, "step": 19500 }, { "epoch": 0.17467554018410802, "grad_norm": 1.5841790437698364, "learning_rate": 9.98253244598159e-06, "loss": 3.107, "step": 20000 }, { "epoch": 0.17904242868871073, "grad_norm": 1.5500739812850952, "learning_rate": 9.982095757131129e-06, "loss": 3.0954, "step": 20500 }, { "epoch": 0.1834093171933134, "grad_norm": 1.5601614713668823, "learning_rate": 9.981659068280668e-06, "loss": 3.1056, "step": 21000 }, { "epoch": 0.18777620569791612, "grad_norm": 1.555240273475647, "learning_rate": 9.981222379430208e-06, "loss": 3.0972, "step": 21500 }, { "epoch": 0.19214309420251882, "grad_norm": 1.5079368352890015, "learning_rate": 9.980785690579748e-06, "loss": 3.1027, "step": 22000 }, { "epoch": 0.19650998270712153, "grad_norm": 1.5824594497680664, "learning_rate": 9.980349001729288e-06, "loss": 3.0981, "step": 22500 }, { "epoch": 0.20087687121172423, "grad_norm": 1.577149748802185, "learning_rate": 9.97991231287883e-06, "loss": 3.1016, "step": 23000 }, { "epoch": 0.2052437597163269, "grad_norm": 1.6186203956604004, "learning_rate": 9.97947562402837e-06, "loss": 3.1016, "step": 23500 }, { "epoch": 0.20961064822092962, "grad_norm": 1.5544419288635254, "learning_rate": 9.979038935177907e-06, "loss": 3.0976, "step": 24000 }, { "epoch": 0.21397753672553232, "grad_norm": 1.6665992736816406, "learning_rate": 9.978602246327447e-06, "loss": 3.0911, "step": 24500 }, { "epoch": 0.21834442523013503, "grad_norm": 1.5559765100479126, "learning_rate": 9.978165557476987e-06, "loss": 3.0948, "step": 25000 }, { "epoch": 0.22271131373473774, "grad_norm": 1.529869794845581, "learning_rate": 9.977728868626527e-06, "loss": 3.093, "step": 25500 }, { "epoch": 0.22707820223934042, "grad_norm": 1.584752082824707, "learning_rate": 9.977292179776067e-06, "loss": 3.1008, "step": 26000 }, { "epoch": 0.23144509074394312, "grad_norm": 1.5647708177566528, "learning_rate": 9.976855490925607e-06, "loss": 3.0945, "step": 26500 }, { "epoch": 0.23581197924854583, "grad_norm": 1.6644014120101929, "learning_rate": 9.976418802075146e-06, "loss": 3.0912, "step": 27000 }, { "epoch": 0.24017886775314853, "grad_norm": 1.5621744394302368, "learning_rate": 9.975982113224686e-06, "loss": 3.1016, "step": 27500 }, { "epoch": 0.24454575625775124, "grad_norm": 1.5438135862350464, "learning_rate": 9.975545424374226e-06, "loss": 3.096, "step": 28000 }, { "epoch": 0.24891264476235392, "grad_norm": 1.5466731786727905, "learning_rate": 9.975108735523766e-06, "loss": 3.0926, "step": 28500 }, { "epoch": 0.2532795332669566, "grad_norm": 1.525607943534851, "learning_rate": 9.974672046673306e-06, "loss": 3.0944, "step": 29000 }, { "epoch": 0.25764642177155933, "grad_norm": 1.591401219367981, "learning_rate": 9.974235357822844e-06, "loss": 3.0821, "step": 29500 }, { "epoch": 0.26201331027616204, "grad_norm": 1.5637773275375366, "learning_rate": 9.973798668972384e-06, "loss": 3.0952, "step": 30000 }, { "epoch": 0.26638019878076474, "grad_norm": 1.5488028526306152, "learning_rate": 9.973361980121923e-06, "loss": 3.0971, "step": 30500 }, { "epoch": 0.27074708728536745, "grad_norm": 1.6777000427246094, "learning_rate": 9.972925291271463e-06, "loss": 3.0917, "step": 31000 }, { "epoch": 0.27511397578997016, "grad_norm": 1.5693696737289429, "learning_rate": 9.972488602421003e-06, "loss": 3.0882, "step": 31500 }, { "epoch": 0.2794808642945728, "grad_norm": 1.5437135696411133, "learning_rate": 9.972051913570545e-06, "loss": 3.0858, "step": 32000 }, { "epoch": 0.2838477527991755, "grad_norm": 1.5495877265930176, "learning_rate": 9.971615224720084e-06, "loss": 3.0899, "step": 32500 }, { "epoch": 0.2882146413037782, "grad_norm": 1.5247818231582642, "learning_rate": 9.971178535869623e-06, "loss": 3.0817, "step": 33000 }, { "epoch": 0.2925815298083809, "grad_norm": 1.5017340183258057, "learning_rate": 9.970741847019162e-06, "loss": 3.0843, "step": 33500 }, { "epoch": 0.29694841831298363, "grad_norm": 1.5877747535705566, "learning_rate": 9.970305158168702e-06, "loss": 3.0843, "step": 34000 }, { "epoch": 0.30131530681758634, "grad_norm": 1.5751012563705444, "learning_rate": 9.969868469318242e-06, "loss": 3.0924, "step": 34500 }, { "epoch": 0.30568219532218904, "grad_norm": 1.595236897468567, "learning_rate": 9.969431780467782e-06, "loss": 3.0881, "step": 35000 }, { "epoch": 0.31004908382679175, "grad_norm": 1.5716018676757812, "learning_rate": 9.968995091617322e-06, "loss": 3.0831, "step": 35500 }, { "epoch": 0.31441597233139446, "grad_norm": 1.5730674266815186, "learning_rate": 9.968558402766862e-06, "loss": 3.0827, "step": 36000 }, { "epoch": 0.31878286083599716, "grad_norm": 1.5956414937973022, "learning_rate": 9.968121713916401e-06, "loss": 3.0827, "step": 36500 }, { "epoch": 0.3231497493405998, "grad_norm": 1.6128644943237305, "learning_rate": 9.967685025065941e-06, "loss": 3.083, "step": 37000 }, { "epoch": 0.3275166378452025, "grad_norm": 1.5318771600723267, "learning_rate": 9.967248336215481e-06, "loss": 3.0863, "step": 37500 }, { "epoch": 0.3318835263498052, "grad_norm": 1.502213716506958, "learning_rate": 9.96681164736502e-06, "loss": 3.0843, "step": 38000 }, { "epoch": 0.33625041485440793, "grad_norm": 1.5129969120025635, "learning_rate": 9.966374958514559e-06, "loss": 3.0866, "step": 38500 }, { "epoch": 0.34061730335901064, "grad_norm": 1.5595052242279053, "learning_rate": 9.965938269664099e-06, "loss": 3.0832, "step": 39000 }, { "epoch": 0.34498419186361334, "grad_norm": 1.5708823204040527, "learning_rate": 9.965501580813639e-06, "loss": 3.0844, "step": 39500 }, { "epoch": 0.34935108036821605, "grad_norm": 1.5758161544799805, "learning_rate": 9.965064891963178e-06, "loss": 3.0802, "step": 40000 }, { "epoch": 0.35371796887281876, "grad_norm": 1.5559204816818237, "learning_rate": 9.964628203112718e-06, "loss": 3.0809, "step": 40500 }, { "epoch": 0.35808485737742146, "grad_norm": 1.5634359121322632, "learning_rate": 9.96419151426226e-06, "loss": 3.0848, "step": 41000 }, { "epoch": 0.36245174588202417, "grad_norm": 1.5033336877822876, "learning_rate": 9.9637548254118e-06, "loss": 3.0803, "step": 41500 }, { "epoch": 0.3668186343866268, "grad_norm": 1.5312292575836182, "learning_rate": 9.963318136561338e-06, "loss": 3.0818, "step": 42000 }, { "epoch": 0.3711855228912295, "grad_norm": 1.5678232908248901, "learning_rate": 9.962881447710878e-06, "loss": 3.0764, "step": 42500 }, { "epoch": 0.37555241139583223, "grad_norm": 1.5265424251556396, "learning_rate": 9.962444758860417e-06, "loss": 3.0803, "step": 43000 }, { "epoch": 0.37991929990043494, "grad_norm": 1.6095571517944336, "learning_rate": 9.962008070009957e-06, "loss": 3.0829, "step": 43500 }, { "epoch": 0.38428618840503764, "grad_norm": 1.5414340496063232, "learning_rate": 9.961571381159497e-06, "loss": 3.0768, "step": 44000 }, { "epoch": 0.38865307690964035, "grad_norm": 1.529461145401001, "learning_rate": 9.961134692309037e-06, "loss": 3.0716, "step": 44500 }, { "epoch": 0.39269681566490244, "step": 44963, "total_flos": 1.1278534630535332e+18, "train_loss": 3.096997114293975, "train_runtime": 46795.6115, "train_samples_per_second": 11744.405, "train_steps_per_second": 244.677 } ], "logging_steps": 500, "max_steps": 11449800, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 1000000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.1278534630535332e+18, "train_batch_size": 48, "trial_name": null, "trial_params": null }