{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 500, "global_step": 1896, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.004219409282700422, "grad_norm": 14.796709060668945, "learning_rate": 1.0526315789473685e-07, "loss": 2.2001190185546875, "step": 2 }, { "epoch": 0.008438818565400843, "grad_norm": 12.265758514404297, "learning_rate": 3.1578947368421055e-07, "loss": 1.779880166053772, "step": 4 }, { "epoch": 0.012658227848101266, "grad_norm": 2.612766981124878, "learning_rate": 5.263157894736843e-07, "loss": 1.936652660369873, "step": 6 }, { "epoch": 0.016877637130801686, "grad_norm": 6.059353828430176, "learning_rate": 7.368421052631579e-07, "loss": 1.9397815465927124, "step": 8 }, { "epoch": 0.02109704641350211, "grad_norm": 8.950942993164062, "learning_rate": 9.473684210526317e-07, "loss": 1.832364559173584, "step": 10 }, { "epoch": 0.02531645569620253, "grad_norm": 2.104597568511963, "learning_rate": 1.1578947368421053e-06, "loss": 1.299726963043213, "step": 12 }, { "epoch": 0.029535864978902954, "grad_norm": 5.877243518829346, "learning_rate": 1.3684210526315791e-06, "loss": 1.6087231636047363, "step": 14 }, { "epoch": 0.03375527426160337, "grad_norm": 17.939144134521484, "learning_rate": 1.5789473684210526e-06, "loss": 1.916496992111206, "step": 16 }, { "epoch": 0.0379746835443038, "grad_norm": 4.548720359802246, "learning_rate": 1.7894736842105265e-06, "loss": 1.6948615312576294, "step": 18 }, { "epoch": 0.04219409282700422, "grad_norm": 2.9824883937835693, "learning_rate": 2.0000000000000003e-06, "loss": 1.785215973854065, "step": 20 }, { "epoch": 0.046413502109704644, "grad_norm": 2.4866232872009277, "learning_rate": 2.2105263157894738e-06, "loss": 1.4187462329864502, "step": 22 }, { "epoch": 0.05063291139240506, "grad_norm": 3.0071780681610107, "learning_rate": 2.4210526315789477e-06, "loss": 1.5432785749435425, "step": 24 }, { "epoch": 0.05485232067510549, "grad_norm": 3.789935827255249, "learning_rate": 2.631578947368421e-06, "loss": 1.2725498676300049, "step": 26 }, { "epoch": 0.05907172995780591, "grad_norm": 2.851421356201172, "learning_rate": 2.842105263157895e-06, "loss": 1.6877858638763428, "step": 28 }, { "epoch": 0.06329113924050633, "grad_norm": 3.9432740211486816, "learning_rate": 3.052631578947369e-06, "loss": 1.2713236808776855, "step": 30 }, { "epoch": 0.06751054852320675, "grad_norm": 4.447280406951904, "learning_rate": 3.2631578947368423e-06, "loss": 1.5127506256103516, "step": 32 }, { "epoch": 0.07172995780590717, "grad_norm": 4.750420093536377, "learning_rate": 3.473684210526316e-06, "loss": 0.9343477487564087, "step": 34 }, { "epoch": 0.0759493670886076, "grad_norm": 1.6804695129394531, "learning_rate": 3.6842105263157896e-06, "loss": 1.5261802673339844, "step": 36 }, { "epoch": 0.08016877637130802, "grad_norm": 6.685342311859131, "learning_rate": 3.894736842105263e-06, "loss": 1.0748982429504395, "step": 38 }, { "epoch": 0.08438818565400844, "grad_norm": 2.0393264293670654, "learning_rate": 4.105263157894737e-06, "loss": 1.481238842010498, "step": 40 }, { "epoch": 0.08860759493670886, "grad_norm": 5.862325668334961, "learning_rate": 4.315789473684211e-06, "loss": 1.0220767259597778, "step": 42 }, { "epoch": 0.09282700421940929, "grad_norm": 4.788952350616455, "learning_rate": 4.526315789473685e-06, "loss": 1.7615070343017578, "step": 44 }, { "epoch": 0.0970464135021097, "grad_norm": 5.775977611541748, "learning_rate": 4.736842105263158e-06, "loss": 1.6437275409698486, "step": 46 }, { "epoch": 0.10126582278481013, "grad_norm": 1.8969275951385498, "learning_rate": 4.947368421052632e-06, "loss": 1.508329153060913, "step": 48 }, { "epoch": 0.10548523206751055, "grad_norm": 3.841172933578491, "learning_rate": 5.157894736842106e-06, "loss": 0.7547962665557861, "step": 50 }, { "epoch": 0.10970464135021098, "grad_norm": 3.9220786094665527, "learning_rate": 5.36842105263158e-06, "loss": 0.8425694704055786, "step": 52 }, { "epoch": 0.11392405063291139, "grad_norm": 3.563117027282715, "learning_rate": 5.578947368421052e-06, "loss": 0.7532248497009277, "step": 54 }, { "epoch": 0.11814345991561181, "grad_norm": 2.2374536991119385, "learning_rate": 5.789473684210527e-06, "loss": 1.3675358295440674, "step": 56 }, { "epoch": 0.12236286919831224, "grad_norm": 7.060910701751709, "learning_rate": 6e-06, "loss": 0.6351418495178223, "step": 58 }, { "epoch": 0.12658227848101267, "grad_norm": 2.427926540374756, "learning_rate": 6.2105263157894745e-06, "loss": 1.4213347434997559, "step": 60 }, { "epoch": 0.1308016877637131, "grad_norm": 1.9487240314483643, "learning_rate": 6.421052631578948e-06, "loss": 1.440359115600586, "step": 62 }, { "epoch": 0.1350210970464135, "grad_norm": 1.6167141199111938, "learning_rate": 6.631578947368421e-06, "loss": 1.0675294399261475, "step": 64 }, { "epoch": 0.13924050632911392, "grad_norm": 21.33095932006836, "learning_rate": 6.842105263157896e-06, "loss": 0.8040838241577148, "step": 66 }, { "epoch": 0.14345991561181434, "grad_norm": 2.555996894836426, "learning_rate": 7.052631578947369e-06, "loss": 1.0836315155029297, "step": 68 }, { "epoch": 0.14767932489451477, "grad_norm": 5.857820510864258, "learning_rate": 7.263157894736843e-06, "loss": 0.9692027568817139, "step": 70 }, { "epoch": 0.1518987341772152, "grad_norm": 3.2739601135253906, "learning_rate": 7.473684210526316e-06, "loss": 1.2618093490600586, "step": 72 }, { "epoch": 0.15611814345991562, "grad_norm": 19.56288719177246, "learning_rate": 7.68421052631579e-06, "loss": 0.9988642930984497, "step": 74 }, { "epoch": 0.16033755274261605, "grad_norm": 2.945552349090576, "learning_rate": 7.894736842105265e-06, "loss": 0.8282591700553894, "step": 76 }, { "epoch": 0.16455696202531644, "grad_norm": 2.6892292499542236, "learning_rate": 8.105263157894736e-06, "loss": 1.3316826820373535, "step": 78 }, { "epoch": 0.16877637130801687, "grad_norm": 1.9552457332611084, "learning_rate": 8.315789473684212e-06, "loss": 1.3196454048156738, "step": 80 }, { "epoch": 0.1729957805907173, "grad_norm": 3.197690963745117, "learning_rate": 8.526315789473685e-06, "loss": 1.365312933921814, "step": 82 }, { "epoch": 0.17721518987341772, "grad_norm": 4.744936943054199, "learning_rate": 8.736842105263158e-06, "loss": 0.7329152822494507, "step": 84 }, { "epoch": 0.18143459915611815, "grad_norm": 2.6648192405700684, "learning_rate": 8.947368421052632e-06, "loss": 1.1085330247879028, "step": 86 }, { "epoch": 0.18565400843881857, "grad_norm": 4.029935359954834, "learning_rate": 9.157894736842105e-06, "loss": 1.2805731296539307, "step": 88 }, { "epoch": 0.189873417721519, "grad_norm": 4.609519004821777, "learning_rate": 9.36842105263158e-06, "loss": 0.6164019703865051, "step": 90 }, { "epoch": 0.1940928270042194, "grad_norm": 3.3423967361450195, "learning_rate": 9.578947368421054e-06, "loss": 1.6728312969207764, "step": 92 }, { "epoch": 0.19831223628691982, "grad_norm": 2.728170156478882, "learning_rate": 9.789473684210527e-06, "loss": 0.9535161256790161, "step": 94 }, { "epoch": 0.20253164556962025, "grad_norm": 2.532789468765259, "learning_rate": 1e-05, "loss": 1.4083621501922607, "step": 96 }, { "epoch": 0.20675105485232068, "grad_norm": 2.1286873817443848, "learning_rate": 9.999972614896371e-06, "loss": 1.4605371952056885, "step": 98 }, { "epoch": 0.2109704641350211, "grad_norm": 4.27150297164917, "learning_rate": 9.999890459918794e-06, "loss": 1.2393274307250977, "step": 100 }, { "epoch": 0.21518987341772153, "grad_norm": 2.2042596340179443, "learning_rate": 9.999753536067186e-06, "loss": 1.0684850215911865, "step": 102 }, { "epoch": 0.21940928270042195, "grad_norm": 1.7670625448226929, "learning_rate": 9.999561845008071e-06, "loss": 0.9878345131874084, "step": 104 }, { "epoch": 0.22362869198312235, "grad_norm": 5.494508266448975, "learning_rate": 9.999315389074552e-06, "loss": 0.9988884925842285, "step": 106 }, { "epoch": 0.22784810126582278, "grad_norm": 2.658101797103882, "learning_rate": 9.999014171266281e-06, "loss": 0.9694901704788208, "step": 108 }, { "epoch": 0.2320675105485232, "grad_norm": 2.4063663482666016, "learning_rate": 9.99865819524943e-06, "loss": 1.0466890335083008, "step": 110 }, { "epoch": 0.23628691983122363, "grad_norm": 2.1014139652252197, "learning_rate": 9.998247465356636e-06, "loss": 1.3706598281860352, "step": 112 }, { "epoch": 0.24050632911392406, "grad_norm": 2.564980983734131, "learning_rate": 9.997781986586959e-06, "loss": 1.277064323425293, "step": 114 }, { "epoch": 0.24472573839662448, "grad_norm": 4.788301944732666, "learning_rate": 9.997261764605815e-06, "loss": 1.5967435836791992, "step": 116 }, { "epoch": 0.2489451476793249, "grad_norm": 2.3070454597473145, "learning_rate": 9.996686805744904e-06, "loss": 1.2567627429962158, "step": 118 }, { "epoch": 0.25316455696202533, "grad_norm": 1.0532585382461548, "learning_rate": 9.996057117002143e-06, "loss": 1.0196549892425537, "step": 120 }, { "epoch": 0.25738396624472576, "grad_norm": 8.361696243286133, "learning_rate": 9.995372706041573e-06, "loss": 1.2531507015228271, "step": 122 }, { "epoch": 0.2616033755274262, "grad_norm": 2.194535732269287, "learning_rate": 9.994633581193267e-06, "loss": 1.2669099569320679, "step": 124 }, { "epoch": 0.26582278481012656, "grad_norm": 2.4402058124542236, "learning_rate": 9.993839751453232e-06, "loss": 1.3583405017852783, "step": 126 }, { "epoch": 0.270042194092827, "grad_norm": 2.2905256748199463, "learning_rate": 9.992991226483287e-06, "loss": 0.82753986120224, "step": 128 }, { "epoch": 0.2742616033755274, "grad_norm": 2.5970890522003174, "learning_rate": 9.992088016610973e-06, "loss": 1.1481742858886719, "step": 130 }, { "epoch": 0.27848101265822783, "grad_norm": 3.0564959049224854, "learning_rate": 9.991130132829391e-06, "loss": 1.1982448101043701, "step": 132 }, { "epoch": 0.28270042194092826, "grad_norm": 5.393448352813721, "learning_rate": 9.990117586797098e-06, "loss": 0.727470874786377, "step": 134 }, { "epoch": 0.2869198312236287, "grad_norm": 2.3638343811035156, "learning_rate": 9.989050390837953e-06, "loss": 0.895744800567627, "step": 136 }, { "epoch": 0.2911392405063291, "grad_norm": 3.3893914222717285, "learning_rate": 9.987928557940963e-06, "loss": 1.3559479713439941, "step": 138 }, { "epoch": 0.29535864978902954, "grad_norm": 3.2452614307403564, "learning_rate": 9.986752101760134e-06, "loss": 0.9385012984275818, "step": 140 }, { "epoch": 0.29957805907172996, "grad_norm": 3.2762651443481445, "learning_rate": 9.985521036614299e-06, "loss": 1.2601220607757568, "step": 142 }, { "epoch": 0.3037974683544304, "grad_norm": 4.821110725402832, "learning_rate": 9.984235377486942e-06, "loss": 1.0670866966247559, "step": 144 }, { "epoch": 0.3080168776371308, "grad_norm": 2.521937847137451, "learning_rate": 9.982895140026027e-06, "loss": 1.3791577816009521, "step": 146 }, { "epoch": 0.31223628691983124, "grad_norm": 3.367048501968384, "learning_rate": 9.981500340543795e-06, "loss": 1.323941707611084, "step": 148 }, { "epoch": 0.31645569620253167, "grad_norm": 3.1904475688934326, "learning_rate": 9.980050996016565e-06, "loss": 1.2417033910751343, "step": 150 }, { "epoch": 0.3206751054852321, "grad_norm": 2.3574581146240234, "learning_rate": 9.97854712408454e-06, "loss": 1.2712074518203735, "step": 152 }, { "epoch": 0.32489451476793246, "grad_norm": 1.9460793733596802, "learning_rate": 9.97698874305158e-06, "loss": 1.454709768295288, "step": 154 }, { "epoch": 0.3291139240506329, "grad_norm": 2.3965163230895996, "learning_rate": 9.97537587188499e-06, "loss": 1.2456231117248535, "step": 156 }, { "epoch": 0.3333333333333333, "grad_norm": 1.6391736268997192, "learning_rate": 9.973708530215275e-06, "loss": 1.3097188472747803, "step": 158 }, { "epoch": 0.33755274261603374, "grad_norm": 2.726836919784546, "learning_rate": 9.97198673833591e-06, "loss": 1.2852942943572998, "step": 160 }, { "epoch": 0.34177215189873417, "grad_norm": 5.805649757385254, "learning_rate": 9.970210517203099e-06, "loss": 0.8796916007995605, "step": 162 }, { "epoch": 0.3459915611814346, "grad_norm": 3.217100143432617, "learning_rate": 9.968379888435508e-06, "loss": 1.2225377559661865, "step": 164 }, { "epoch": 0.350210970464135, "grad_norm": 4.207212448120117, "learning_rate": 9.966494874314004e-06, "loss": 0.8519747257232666, "step": 166 }, { "epoch": 0.35443037974683544, "grad_norm": 8.152425765991211, "learning_rate": 9.964555497781395e-06, "loss": 1.2175066471099854, "step": 168 }, { "epoch": 0.35864978902953587, "grad_norm": 6.639067649841309, "learning_rate": 9.962561782442133e-06, "loss": 1.3038749694824219, "step": 170 }, { "epoch": 0.3628691983122363, "grad_norm": 5.139934062957764, "learning_rate": 9.960513752562044e-06, "loss": 1.198750376701355, "step": 172 }, { "epoch": 0.3670886075949367, "grad_norm": 2.051300287246704, "learning_rate": 9.95841143306802e-06, "loss": 1.0111594200134277, "step": 174 }, { "epoch": 0.37130801687763715, "grad_norm": 2.477222442626953, "learning_rate": 9.956254849547721e-06, "loss": 1.3064699172973633, "step": 176 }, { "epoch": 0.3755274261603376, "grad_norm": 8.377769470214844, "learning_rate": 9.954044028249269e-06, "loss": 1.3081631660461426, "step": 178 }, { "epoch": 0.379746835443038, "grad_norm": 1.8243556022644043, "learning_rate": 9.95177899608091e-06, "loss": 0.9942997694015503, "step": 180 }, { "epoch": 0.38396624472573837, "grad_norm": 3.0251100063323975, "learning_rate": 9.949459780610714e-06, "loss": 1.2624611854553223, "step": 182 }, { "epoch": 0.3881856540084388, "grad_norm": 3.9718830585479736, "learning_rate": 9.94708641006621e-06, "loss": 1.266221284866333, "step": 184 }, { "epoch": 0.3924050632911392, "grad_norm": 4.708130836486816, "learning_rate": 9.94465891333407e-06, "loss": 0.5301458835601807, "step": 186 }, { "epoch": 0.39662447257383965, "grad_norm": 1.4348413944244385, "learning_rate": 9.942177319959733e-06, "loss": 0.9555749297142029, "step": 188 }, { "epoch": 0.4008438818565401, "grad_norm": 1.6812728643417358, "learning_rate": 9.939641660147067e-06, "loss": 1.0481868982315063, "step": 190 }, { "epoch": 0.4050632911392405, "grad_norm": 1.8171874284744263, "learning_rate": 9.937051964757982e-06, "loss": 1.2823535203933716, "step": 192 }, { "epoch": 0.4092827004219409, "grad_norm": 4.415493965148926, "learning_rate": 9.93440826531207e-06, "loss": 1.057572364807129, "step": 194 }, { "epoch": 0.41350210970464135, "grad_norm": 4.561761379241943, "learning_rate": 9.93171059398621e-06, "loss": 1.257936716079712, "step": 196 }, { "epoch": 0.4177215189873418, "grad_norm": 2.030771255493164, "learning_rate": 9.928958983614187e-06, "loss": 1.0273797512054443, "step": 198 }, { "epoch": 0.4219409282700422, "grad_norm": 2.385207414627075, "learning_rate": 9.926153467686282e-06, "loss": 1.1045024394989014, "step": 200 }, { "epoch": 0.42616033755274263, "grad_norm": 3.4092116355895996, "learning_rate": 9.92329408034887e-06, "loss": 1.1284656524658203, "step": 202 }, { "epoch": 0.43037974683544306, "grad_norm": 3.4495861530303955, "learning_rate": 9.920380856404002e-06, "loss": 0.8900959491729736, "step": 204 }, { "epoch": 0.4345991561181435, "grad_norm": 1.822981834411621, "learning_rate": 9.917413831308988e-06, "loss": 1.3355131149291992, "step": 206 }, { "epoch": 0.4388185654008439, "grad_norm": 7.878076076507568, "learning_rate": 9.914393041175954e-06, "loss": 0.7409433126449585, "step": 208 }, { "epoch": 0.4430379746835443, "grad_norm": 1.9715880155563354, "learning_rate": 9.911318522771414e-06, "loss": 1.2606409788131714, "step": 210 }, { "epoch": 0.4472573839662447, "grad_norm": 7.459953308105469, "learning_rate": 9.90819031351581e-06, "loss": 0.8054428100585938, "step": 212 }, { "epoch": 0.45147679324894513, "grad_norm": 2.934112548828125, "learning_rate": 9.905008451483075e-06, "loss": 1.1959190368652344, "step": 214 }, { "epoch": 0.45569620253164556, "grad_norm": 2.4072892665863037, "learning_rate": 9.901772975400147e-06, "loss": 1.236368179321289, "step": 216 }, { "epoch": 0.459915611814346, "grad_norm": 7.378908634185791, "learning_rate": 9.898483924646516e-06, "loss": 1.2715609073638916, "step": 218 }, { "epoch": 0.4641350210970464, "grad_norm": 1.8914843797683716, "learning_rate": 9.895141339253733e-06, "loss": 1.236929178237915, "step": 220 }, { "epoch": 0.46835443037974683, "grad_norm": 9.663741111755371, "learning_rate": 9.891745259904935e-06, "loss": 1.206599473953247, "step": 222 }, { "epoch": 0.47257383966244726, "grad_norm": 3.8827295303344727, "learning_rate": 9.888295727934333e-06, "loss": 0.9914872646331787, "step": 224 }, { "epoch": 0.4767932489451477, "grad_norm": 1.755597710609436, "learning_rate": 9.884792785326725e-06, "loss": 1.2610862255096436, "step": 226 }, { "epoch": 0.4810126582278481, "grad_norm": 3.596493721008301, "learning_rate": 9.881236474716976e-06, "loss": 0.79889976978302, "step": 228 }, { "epoch": 0.48523206751054854, "grad_norm": 6.4674272537231445, "learning_rate": 9.877626839389501e-06, "loss": 0.9121121168136597, "step": 230 }, { "epoch": 0.48945147679324896, "grad_norm": 11.841682434082031, "learning_rate": 9.873963923277737e-06, "loss": 0.892866849899292, "step": 232 }, { "epoch": 0.4936708860759494, "grad_norm": 3.1085312366485596, "learning_rate": 9.870247770963616e-06, "loss": 1.2593913078308105, "step": 234 }, { "epoch": 0.4978902953586498, "grad_norm": 2.6649982929229736, "learning_rate": 9.866478427677009e-06, "loss": 1.3058339357376099, "step": 236 }, { "epoch": 0.5021097046413502, "grad_norm": 14.443163871765137, "learning_rate": 9.862655939295184e-06, "loss": 0.9796797633171082, "step": 238 }, { "epoch": 0.5063291139240507, "grad_norm": 7.0072736740112305, "learning_rate": 9.858780352342252e-06, "loss": 0.4604620039463043, "step": 240 }, { "epoch": 0.510548523206751, "grad_norm": 2.8164477348327637, "learning_rate": 9.854851713988588e-06, "loss": 1.4089837074279785, "step": 242 }, { "epoch": 0.5147679324894515, "grad_norm": 14.343058586120605, "learning_rate": 9.850870072050268e-06, "loss": 0.8732689619064331, "step": 244 }, { "epoch": 0.5189873417721519, "grad_norm": 2.6711764335632324, "learning_rate": 9.846835474988482e-06, "loss": 1.4676425457000732, "step": 246 }, { "epoch": 0.5232067510548524, "grad_norm": 2.603074073791504, "learning_rate": 9.842747971908943e-06, "loss": 1.1767747402191162, "step": 248 }, { "epoch": 0.5274261603375527, "grad_norm": 2.371072292327881, "learning_rate": 9.838607612561295e-06, "loss": 1.2963995933532715, "step": 250 }, { "epoch": 0.5316455696202531, "grad_norm": 4.966698169708252, "learning_rate": 9.834414447338503e-06, "loss": 1.10191810131073, "step": 252 }, { "epoch": 0.5358649789029536, "grad_norm": 1.7062257528305054, "learning_rate": 9.830168527276238e-06, "loss": 1.213578462600708, "step": 254 }, { "epoch": 0.540084388185654, "grad_norm": 2.720341205596924, "learning_rate": 9.825869904052261e-06, "loss": 1.1875674724578857, "step": 256 }, { "epoch": 0.5443037974683544, "grad_norm": 4.728967666625977, "learning_rate": 9.821518629985793e-06, "loss": 1.0267858505249023, "step": 258 }, { "epoch": 0.5485232067510548, "grad_norm": 8.80720043182373, "learning_rate": 9.817114758036874e-06, "loss": 0.9614678621292114, "step": 260 }, { "epoch": 0.5527426160337553, "grad_norm": 3.104877471923828, "learning_rate": 9.81265834180572e-06, "loss": 1.2562415599822998, "step": 262 }, { "epoch": 0.5569620253164557, "grad_norm": 4.452579021453857, "learning_rate": 9.80814943553207e-06, "loss": 1.2715522050857544, "step": 264 }, { "epoch": 0.5611814345991561, "grad_norm": 3.438886880874634, "learning_rate": 9.80358809409454e-06, "loss": 1.223157286643982, "step": 266 }, { "epoch": 0.5654008438818565, "grad_norm": 2.3886618614196777, "learning_rate": 9.798974373009924e-06, "loss": 1.496765375137329, "step": 268 }, { "epoch": 0.569620253164557, "grad_norm": 6.245704650878906, "learning_rate": 9.794308328432554e-06, "loss": 1.045867681503296, "step": 270 }, { "epoch": 0.5738396624472574, "grad_norm": 3.181368350982666, "learning_rate": 9.789590017153587e-06, "loss": 1.2988061904907227, "step": 272 }, { "epoch": 0.5780590717299579, "grad_norm": 3.332742214202881, "learning_rate": 9.784819496600333e-06, "loss": 1.091325283050537, "step": 274 }, { "epoch": 0.5822784810126582, "grad_norm": 1.8129675388336182, "learning_rate": 9.77999682483555e-06, "loss": 1.2422319650650024, "step": 276 }, { "epoch": 0.5864978902953587, "grad_norm": 3.06986141204834, "learning_rate": 9.775122060556729e-06, "loss": 1.3887534141540527, "step": 278 }, { "epoch": 0.5907172995780591, "grad_norm": 1.7186170816421509, "learning_rate": 9.770195263095396e-06, "loss": 0.9554907083511353, "step": 280 }, { "epoch": 0.5949367088607594, "grad_norm": 2.0644567012786865, "learning_rate": 9.765216492416375e-06, "loss": 1.312037467956543, "step": 282 }, { "epoch": 0.5991561181434599, "grad_norm": 4.419807434082031, "learning_rate": 9.760185809117065e-06, "loss": 1.5302636623382568, "step": 284 }, { "epoch": 0.6033755274261603, "grad_norm": 0.8416258692741394, "learning_rate": 9.755103274426709e-06, "loss": 1.1195366382598877, "step": 286 }, { "epoch": 0.6075949367088608, "grad_norm": 2.3922317028045654, "learning_rate": 9.74996895020563e-06, "loss": 1.2402794361114502, "step": 288 }, { "epoch": 0.6118143459915611, "grad_norm": 11.831677436828613, "learning_rate": 9.744782898944496e-06, "loss": 0.8071295022964478, "step": 290 }, { "epoch": 0.6160337552742616, "grad_norm": 1.879852533340454, "learning_rate": 9.739545183763554e-06, "loss": 0.6571891903877258, "step": 292 }, { "epoch": 0.620253164556962, "grad_norm": 1.9062740802764893, "learning_rate": 9.734255868411857e-06, "loss": 1.2200584411621094, "step": 294 }, { "epoch": 0.6244725738396625, "grad_norm": 6.911993026733398, "learning_rate": 9.728915017266494e-06, "loss": 0.704890787601471, "step": 296 }, { "epoch": 0.6286919831223629, "grad_norm": 4.08508825302124, "learning_rate": 9.723522695331806e-06, "loss": 0.6586240530014038, "step": 298 }, { "epoch": 0.6329113924050633, "grad_norm": 3.476318120956421, "learning_rate": 9.718078968238584e-06, "loss": 1.7605481147766113, "step": 300 }, { "epoch": 0.6371308016877637, "grad_norm": 1.758302927017212, "learning_rate": 9.712583902243294e-06, "loss": 1.2581803798675537, "step": 302 }, { "epoch": 0.6413502109704642, "grad_norm": 4.694915771484375, "learning_rate": 9.707037564227244e-06, "loss": 0.8604925870895386, "step": 304 }, { "epoch": 0.6455696202531646, "grad_norm": 6.87870979309082, "learning_rate": 9.701440021695784e-06, "loss": 1.006733775138855, "step": 306 }, { "epoch": 0.6497890295358649, "grad_norm": 2.047752857208252, "learning_rate": 9.69579134277749e-06, "loss": 1.249037504196167, "step": 308 }, { "epoch": 0.6540084388185654, "grad_norm": 1.755350947380066, "learning_rate": 9.690091596223315e-06, "loss": 1.1914235353469849, "step": 310 }, { "epoch": 0.6582278481012658, "grad_norm": 10.775752067565918, "learning_rate": 9.684340851405771e-06, "loss": 1.0019190311431885, "step": 312 }, { "epoch": 0.6624472573839663, "grad_norm": 1.2793184518814087, "learning_rate": 9.678539178318078e-06, "loss": 1.2022016048431396, "step": 314 }, { "epoch": 0.6666666666666666, "grad_norm": 2.473740339279175, "learning_rate": 9.672686647573312e-06, "loss": 1.0890239477157593, "step": 316 }, { "epoch": 0.6708860759493671, "grad_norm": 1.8484349250793457, "learning_rate": 9.666783330403543e-06, "loss": 1.0760843753814697, "step": 318 }, { "epoch": 0.6751054852320675, "grad_norm": 10.745168685913086, "learning_rate": 9.660829298658972e-06, "loss": 1.0726282596588135, "step": 320 }, { "epoch": 0.679324894514768, "grad_norm": 2.6519157886505127, "learning_rate": 9.654824624807057e-06, "loss": 0.8642212152481079, "step": 322 }, { "epoch": 0.6835443037974683, "grad_norm": 1.717992901802063, "learning_rate": 9.648769381931627e-06, "loss": 0.8955992460250854, "step": 324 }, { "epoch": 0.6877637130801688, "grad_norm": 13.16799259185791, "learning_rate": 9.642663643731993e-06, "loss": 0.8464986085891724, "step": 326 }, { "epoch": 0.6919831223628692, "grad_norm": 3.0998640060424805, "learning_rate": 9.636507484522054e-06, "loss": 0.8659808039665222, "step": 328 }, { "epoch": 0.6962025316455697, "grad_norm": 4.811046123504639, "learning_rate": 9.630300979229393e-06, "loss": 1.558638334274292, "step": 330 }, { "epoch": 0.70042194092827, "grad_norm": 10.04901123046875, "learning_rate": 9.62404420339436e-06, "loss": 1.074096441268921, "step": 332 }, { "epoch": 0.7046413502109705, "grad_norm": 2.525545358657837, "learning_rate": 9.617737233169157e-06, "loss": 1.3383584022521973, "step": 334 }, { "epoch": 0.7088607594936709, "grad_norm": 1.9381195306777954, "learning_rate": 9.611380145316913e-06, "loss": 1.251182198524475, "step": 336 }, { "epoch": 0.7130801687763713, "grad_norm": 2.814554452896118, "learning_rate": 9.60497301721074e-06, "loss": 1.275946021080017, "step": 338 }, { "epoch": 0.7172995780590717, "grad_norm": 5.958861351013184, "learning_rate": 9.598515926832803e-06, "loss": 1.2431640625, "step": 340 }, { "epoch": 0.7215189873417721, "grad_norm": 2.43070912361145, "learning_rate": 9.59200895277336e-06, "loss": 1.2416553497314453, "step": 342 }, { "epoch": 0.7257383966244726, "grad_norm": 2.6783525943756104, "learning_rate": 9.58545217422982e-06, "loss": 1.0711673498153687, "step": 344 }, { "epoch": 0.729957805907173, "grad_norm": 10.548710823059082, "learning_rate": 9.578845671005764e-06, "loss": 0.9235292673110962, "step": 346 }, { "epoch": 0.7341772151898734, "grad_norm": 1.4020512104034424, "learning_rate": 9.57218952350998e-06, "loss": 1.2332313060760498, "step": 348 }, { "epoch": 0.7383966244725738, "grad_norm": 8.172940254211426, "learning_rate": 9.565483812755484e-06, "loss": 1.1720128059387207, "step": 350 }, { "epoch": 0.7426160337552743, "grad_norm": 10.901153564453125, "learning_rate": 9.558728620358539e-06, "loss": 1.0871388912200928, "step": 352 }, { "epoch": 0.7468354430379747, "grad_norm": 8.735403060913086, "learning_rate": 9.55192402853765e-06, "loss": 0.6521060466766357, "step": 354 }, { "epoch": 0.7510548523206751, "grad_norm": 4.4896111488342285, "learning_rate": 9.545070120112574e-06, "loss": 1.047936201095581, "step": 356 }, { "epoch": 0.7552742616033755, "grad_norm": 4.880589962005615, "learning_rate": 9.538166978503311e-06, "loss": 1.0152819156646729, "step": 358 }, { "epoch": 0.759493670886076, "grad_norm": 1.5919607877731323, "learning_rate": 9.531214687729078e-06, "loss": 1.206318974494934, "step": 360 }, { "epoch": 0.7637130801687764, "grad_norm": 3.057582139968872, "learning_rate": 9.524213332407304e-06, "loss": 0.987231969833374, "step": 362 }, { "epoch": 0.7679324894514767, "grad_norm": 4.207955837249756, "learning_rate": 9.517162997752577e-06, "loss": 1.5653212070465088, "step": 364 }, { "epoch": 0.7721518987341772, "grad_norm": 8.507241249084473, "learning_rate": 9.510063769575636e-06, "loss": 0.7021949887275696, "step": 366 }, { "epoch": 0.7763713080168776, "grad_norm": 3.0806355476379395, "learning_rate": 9.5029157342823e-06, "loss": 1.1647017002105713, "step": 368 }, { "epoch": 0.7805907172995781, "grad_norm": 2.6495301723480225, "learning_rate": 9.49571897887243e-06, "loss": 1.4708654880523682, "step": 370 }, { "epoch": 0.7848101265822784, "grad_norm": 37.14263153076172, "learning_rate": 9.488473590938865e-06, "loss": 0.9860970973968506, "step": 372 }, { "epoch": 0.7890295358649789, "grad_norm": 14.923946380615234, "learning_rate": 9.481179658666365e-06, "loss": 1.0486998558044434, "step": 374 }, { "epoch": 0.7932489451476793, "grad_norm": 2.270437002182007, "learning_rate": 9.473837270830521e-06, "loss": 1.156338095664978, "step": 376 }, { "epoch": 0.7974683544303798, "grad_norm": 0.96358722448349, "learning_rate": 9.466446516796692e-06, "loss": 1.11653733253479, "step": 378 }, { "epoch": 0.8016877637130801, "grad_norm": 2.3207335472106934, "learning_rate": 9.459007486518909e-06, "loss": 0.7127337455749512, "step": 380 }, { "epoch": 0.8059071729957806, "grad_norm": 3.06595778465271, "learning_rate": 9.451520270538775e-06, "loss": 1.2675938606262207, "step": 382 }, { "epoch": 0.810126582278481, "grad_norm": 23.335262298583984, "learning_rate": 9.443984959984375e-06, "loss": 0.9875625371932983, "step": 384 }, { "epoch": 0.8143459915611815, "grad_norm": 6.709965229034424, "learning_rate": 9.436401646569154e-06, "loss": 1.2390447854995728, "step": 386 }, { "epoch": 0.8185654008438819, "grad_norm": 3.7535672187805176, "learning_rate": 9.428770422590817e-06, "loss": 0.9481120109558105, "step": 388 }, { "epoch": 0.8227848101265823, "grad_norm": 2.276607036590576, "learning_rate": 9.421091380930187e-06, "loss": 1.2161517143249512, "step": 390 }, { "epoch": 0.8270042194092827, "grad_norm": 3.2340142726898193, "learning_rate": 9.413364615050088e-06, "loss": 0.984723687171936, "step": 392 }, { "epoch": 0.8312236286919831, "grad_norm": 10.801681518554688, "learning_rate": 9.4055902189942e-06, "loss": 0.9216404557228088, "step": 394 }, { "epoch": 0.8354430379746836, "grad_norm": 1.5393396615982056, "learning_rate": 9.397768287385923e-06, "loss": 1.2234981060028076, "step": 396 }, { "epoch": 0.8396624472573839, "grad_norm": 0.5070556402206421, "learning_rate": 9.389898915427213e-06, "loss": 1.0872011184692383, "step": 398 }, { "epoch": 0.8438818565400844, "grad_norm": 1.8275169134140015, "learning_rate": 9.381982198897434e-06, "loss": 0.9712474942207336, "step": 400 }, { "epoch": 0.8481012658227848, "grad_norm": 5.140311241149902, "learning_rate": 9.374018234152187e-06, "loss": 0.7062616348266602, "step": 402 }, { "epoch": 0.8523206751054853, "grad_norm": 2.3650052547454834, "learning_rate": 9.366007118122138e-06, "loss": 1.2058610916137695, "step": 404 }, { "epoch": 0.8565400843881856, "grad_norm": 3.8125803470611572, "learning_rate": 9.35794894831184e-06, "loss": 0.9518964290618896, "step": 406 }, { "epoch": 0.8607594936708861, "grad_norm": 1.838995099067688, "learning_rate": 9.349843822798546e-06, "loss": 0.975111722946167, "step": 408 }, { "epoch": 0.8649789029535865, "grad_norm": 6.433191776275635, "learning_rate": 9.341691840231008e-06, "loss": 1.2284657955169678, "step": 410 }, { "epoch": 0.869198312236287, "grad_norm": 7.83781623840332, "learning_rate": 9.333493099828292e-06, "loss": 0.8631826639175415, "step": 412 }, { "epoch": 0.8734177215189873, "grad_norm": 3.201695680618286, "learning_rate": 9.325247701378553e-06, "loss": 1.2114286422729492, "step": 414 }, { "epoch": 0.8776371308016878, "grad_norm": 4.142547130584717, "learning_rate": 9.316955745237833e-06, "loss": 1.0667777061462402, "step": 416 }, { "epoch": 0.8818565400843882, "grad_norm": 3.4035725593566895, "learning_rate": 9.308617332328829e-06, "loss": 1.1613843441009521, "step": 418 }, { "epoch": 0.8860759493670886, "grad_norm": 1.754526972770691, "learning_rate": 9.300232564139681e-06, "loss": 0.9515656232833862, "step": 420 }, { "epoch": 0.890295358649789, "grad_norm": 2.32590389251709, "learning_rate": 9.29180154272272e-06, "loss": 1.3403286933898926, "step": 422 }, { "epoch": 0.8945147679324894, "grad_norm": 24.669382095336914, "learning_rate": 9.28332437069323e-06, "loss": 0.9794604778289795, "step": 424 }, { "epoch": 0.8987341772151899, "grad_norm": 3.3824493885040283, "learning_rate": 9.274801151228203e-06, "loss": 1.1777677536010742, "step": 426 }, { "epoch": 0.9029535864978903, "grad_norm": 2.9143404960632324, "learning_rate": 9.266231988065084e-06, "loss": 1.0401194095611572, "step": 428 }, { "epoch": 0.9071729957805907, "grad_norm": 4.955803394317627, "learning_rate": 9.257616985500508e-06, "loss": 1.0083619356155396, "step": 430 }, { "epoch": 0.9113924050632911, "grad_norm": 3.7971105575561523, "learning_rate": 9.24895624838902e-06, "loss": 1.0804749727249146, "step": 432 }, { "epoch": 0.9156118143459916, "grad_norm": 2.0953335762023926, "learning_rate": 9.240249882141818e-06, "loss": 1.2387405633926392, "step": 434 }, { "epoch": 0.919831223628692, "grad_norm": 3.6870739459991455, "learning_rate": 9.23149799272545e-06, "loss": 0.9250370860099792, "step": 436 }, { "epoch": 0.9240506329113924, "grad_norm": 2.7028815746307373, "learning_rate": 9.222700686660537e-06, "loss": 1.197579026222229, "step": 438 }, { "epoch": 0.9282700421940928, "grad_norm": 2.6510417461395264, "learning_rate": 9.213858071020477e-06, "loss": 0.9849317073822021, "step": 440 }, { "epoch": 0.9324894514767933, "grad_norm": 10.135645866394043, "learning_rate": 9.204970253430134e-06, "loss": 0.960978627204895, "step": 442 }, { "epoch": 0.9367088607594937, "grad_norm": 35.18146514892578, "learning_rate": 9.19603734206453e-06, "loss": 1.0912028551101685, "step": 444 }, { "epoch": 0.9409282700421941, "grad_norm": 4.102611064910889, "learning_rate": 9.187059445647537e-06, "loss": 1.2960188388824463, "step": 446 }, { "epoch": 0.9451476793248945, "grad_norm": 1.38564133644104, "learning_rate": 9.17803667345054e-06, "loss": 1.0068583488464355, "step": 448 }, { "epoch": 0.9493670886075949, "grad_norm": 5.884424209594727, "learning_rate": 9.16896913529112e-06, "loss": 0.9411823153495789, "step": 450 }, { "epoch": 0.9535864978902954, "grad_norm": 1.8418949842453003, "learning_rate": 9.159856941531707e-06, "loss": 1.2834553718566895, "step": 452 }, { "epoch": 0.9578059071729957, "grad_norm": 3.745450258255005, "learning_rate": 9.150700203078245e-06, "loss": 0.9945646524429321, "step": 454 }, { "epoch": 0.9620253164556962, "grad_norm": 3.2759759426116943, "learning_rate": 9.141499031378836e-06, "loss": 1.1481308937072754, "step": 456 }, { "epoch": 0.9662447257383966, "grad_norm": 1.9661576747894287, "learning_rate": 9.132253538422389e-06, "loss": 0.8864379525184631, "step": 458 }, { "epoch": 0.9704641350210971, "grad_norm": 65.71759796142578, "learning_rate": 9.12296383673725e-06, "loss": 0.7265732288360596, "step": 460 }, { "epoch": 0.9746835443037974, "grad_norm": 32.50619888305664, "learning_rate": 9.113630039389835e-06, "loss": 0.9014446139335632, "step": 462 }, { "epoch": 0.9789029535864979, "grad_norm": 2.8576433658599854, "learning_rate": 9.104252259983264e-06, "loss": 1.1646841764450073, "step": 464 }, { "epoch": 0.9831223628691983, "grad_norm": 3.739401340484619, "learning_rate": 9.094830612655961e-06, "loss": 0.7757707834243774, "step": 466 }, { "epoch": 0.9873417721518988, "grad_norm": 4.484866619110107, "learning_rate": 9.085365212080279e-06, "loss": 1.3110108375549316, "step": 468 }, { "epoch": 0.9915611814345991, "grad_norm": 7.396069049835205, "learning_rate": 9.075856173461094e-06, "loss": 0.8946552276611328, "step": 470 }, { "epoch": 0.9957805907172996, "grad_norm": 4.264477729797363, "learning_rate": 9.06630361253441e-06, "loss": 1.205096960067749, "step": 472 }, { "epoch": 1.0, "grad_norm": 1.8571966886520386, "learning_rate": 9.056707645565946e-06, "loss": 1.2512152194976807, "step": 474 }, { "epoch": 1.0042194092827004, "grad_norm": 6.815761089324951, "learning_rate": 9.047068389349729e-06, "loss": 0.9597331285476685, "step": 476 }, { "epoch": 1.0084388185654007, "grad_norm": 1.808717966079712, "learning_rate": 9.037385961206654e-06, "loss": 1.174092173576355, "step": 478 }, { "epoch": 1.0126582278481013, "grad_norm": 2.1455905437469482, "learning_rate": 9.027660478983082e-06, "loss": 1.1470932960510254, "step": 480 }, { "epoch": 1.0168776371308017, "grad_norm": 3.2191596031188965, "learning_rate": 9.01789206104938e-06, "loss": 0.7979065179824829, "step": 482 }, { "epoch": 1.021097046413502, "grad_norm": 3.9754693508148193, "learning_rate": 9.008080826298504e-06, "loss": 1.0781121253967285, "step": 484 }, { "epoch": 1.0253164556962024, "grad_norm": 4.9864935874938965, "learning_rate": 8.99822689414453e-06, "loss": 0.4800400137901306, "step": 486 }, { "epoch": 1.029535864978903, "grad_norm": 3.4104604721069336, "learning_rate": 8.988330384521218e-06, "loss": 0.9883596897125244, "step": 488 }, { "epoch": 1.0337552742616034, "grad_norm": 3.7277843952178955, "learning_rate": 8.978391417880539e-06, "loss": 0.7610245943069458, "step": 490 }, { "epoch": 1.0379746835443038, "grad_norm": 2.2768747806549072, "learning_rate": 8.96841011519122e-06, "loss": 1.0762301683425903, "step": 492 }, { "epoch": 1.0421940928270041, "grad_norm": 12.251036643981934, "learning_rate": 8.958386597937265e-06, "loss": 0.8438637852668762, "step": 494 }, { "epoch": 1.0464135021097047, "grad_norm": 3.5397419929504395, "learning_rate": 8.948320988116476e-06, "loss": 0.944114089012146, "step": 496 }, { "epoch": 1.0506329113924051, "grad_norm": 2.6761462688446045, "learning_rate": 8.938213408238973e-06, "loss": 1.2203458547592163, "step": 498 }, { "epoch": 1.0548523206751055, "grad_norm": 2.7123825550079346, "learning_rate": 8.928063981325702e-06, "loss": 1.0190808773040771, "step": 500 }, { "epoch": 1.0590717299578059, "grad_norm": 2.3714678287506104, "learning_rate": 8.917872830906929e-06, "loss": 1.081365704536438, "step": 502 }, { "epoch": 1.0632911392405062, "grad_norm": 2.278714418411255, "learning_rate": 8.907640081020748e-06, "loss": 1.2078616619110107, "step": 504 }, { "epoch": 1.0675105485232068, "grad_norm": 2.820486545562744, "learning_rate": 8.897365856211569e-06, "loss": 0.7916339635848999, "step": 506 }, { "epoch": 1.0717299578059072, "grad_norm": 2.414914846420288, "learning_rate": 8.887050281528595e-06, "loss": 1.0088075399398804, "step": 508 }, { "epoch": 1.0759493670886076, "grad_norm": 1.745826005935669, "learning_rate": 8.876693482524306e-06, "loss": 1.0888729095458984, "step": 510 }, { "epoch": 1.080168776371308, "grad_norm": 21.646360397338867, "learning_rate": 8.866295585252932e-06, "loss": 0.9575265049934387, "step": 512 }, { "epoch": 1.0843881856540085, "grad_norm": 4.113856315612793, "learning_rate": 8.855856716268915e-06, "loss": 1.0966126918792725, "step": 514 }, { "epoch": 1.0886075949367089, "grad_norm": 1.6279631853103638, "learning_rate": 8.845377002625369e-06, "loss": 1.0514793395996094, "step": 516 }, { "epoch": 1.0928270042194093, "grad_norm": 2.829108715057373, "learning_rate": 8.834856571872536e-06, "loss": 0.9625022411346436, "step": 518 }, { "epoch": 1.0970464135021096, "grad_norm": 5.274242877960205, "learning_rate": 8.824295552056231e-06, "loss": 0.9224317073822021, "step": 520 }, { "epoch": 1.1012658227848102, "grad_norm": 5.897571563720703, "learning_rate": 8.81369407171629e-06, "loss": 0.860292911529541, "step": 522 }, { "epoch": 1.1054852320675106, "grad_norm": 3.6628153324127197, "learning_rate": 8.803052259884993e-06, "loss": 1.0431971549987793, "step": 524 }, { "epoch": 1.109704641350211, "grad_norm": 7.019797325134277, "learning_rate": 8.792370246085504e-06, "loss": 0.8758162260055542, "step": 526 }, { "epoch": 1.1139240506329113, "grad_norm": 2.6283745765686035, "learning_rate": 8.781648160330295e-06, "loss": 1.3205974102020264, "step": 528 }, { "epoch": 1.1181434599156117, "grad_norm": 3.340432643890381, "learning_rate": 8.770886133119553e-06, "loss": 1.201941967010498, "step": 530 }, { "epoch": 1.1223628691983123, "grad_norm": 6.343982219696045, "learning_rate": 8.760084295439606e-06, "loss": 0.6695289611816406, "step": 532 }, { "epoch": 1.1265822784810127, "grad_norm": 2.7600579261779785, "learning_rate": 8.749242778761317e-06, "loss": 0.899500846862793, "step": 534 }, { "epoch": 1.130801687763713, "grad_norm": 2.929830312728882, "learning_rate": 8.738361715038488e-06, "loss": 1.0471978187561035, "step": 536 }, { "epoch": 1.1350210970464134, "grad_norm": 6.021061420440674, "learning_rate": 8.727441236706258e-06, "loss": 0.8244039416313171, "step": 538 }, { "epoch": 1.139240506329114, "grad_norm": 25.114166259765625, "learning_rate": 8.716481476679482e-06, "loss": 0.7538343667984009, "step": 540 }, { "epoch": 1.1434599156118144, "grad_norm": 1.8386493921279907, "learning_rate": 8.705482568351128e-06, "loss": 0.7804465293884277, "step": 542 }, { "epoch": 1.1476793248945147, "grad_norm": 2.374969005584717, "learning_rate": 8.69444464559063e-06, "loss": 0.8303866982460022, "step": 544 }, { "epoch": 1.1518987341772151, "grad_norm": 4.5004472732543945, "learning_rate": 8.683367842742285e-06, "loss": 1.0070552825927734, "step": 546 }, { "epoch": 1.1561181434599157, "grad_norm": 3.439532518386841, "learning_rate": 8.6722522946236e-06, "loss": 1.0979628562927246, "step": 548 }, { "epoch": 1.160337552742616, "grad_norm": 4.995817184448242, "learning_rate": 8.661098136523663e-06, "loss": 0.8778022527694702, "step": 550 }, { "epoch": 1.1645569620253164, "grad_norm": 2.827592134475708, "learning_rate": 8.649905504201478e-06, "loss": 1.2798807621002197, "step": 552 }, { "epoch": 1.1687763713080168, "grad_norm": 2.2903850078582764, "learning_rate": 8.638674533884338e-06, "loss": 1.164045810699463, "step": 554 }, { "epoch": 1.1729957805907172, "grad_norm": 5.9755940437316895, "learning_rate": 8.627405362266142e-06, "loss": 0.6177074313163757, "step": 556 }, { "epoch": 1.1772151898734178, "grad_norm": 2.224170446395874, "learning_rate": 8.616098126505755e-06, "loss": 0.9453469514846802, "step": 558 }, { "epoch": 1.1814345991561181, "grad_norm": 5.611544132232666, "learning_rate": 8.604752964225315e-06, "loss": 0.760279655456543, "step": 560 }, { "epoch": 1.1856540084388185, "grad_norm": 1.3615453243255615, "learning_rate": 8.593370013508582e-06, "loss": 0.633928656578064, "step": 562 }, { "epoch": 1.189873417721519, "grad_norm": 3.9796786308288574, "learning_rate": 8.581949412899233e-06, "loss": 1.188035488128662, "step": 564 }, { "epoch": 1.1940928270042195, "grad_norm": 4.539784908294678, "learning_rate": 8.570491301399192e-06, "loss": 1.0750675201416016, "step": 566 }, { "epoch": 1.1983122362869199, "grad_norm": 15.827986717224121, "learning_rate": 8.558995818466941e-06, "loss": 0.7490755915641785, "step": 568 }, { "epoch": 1.2025316455696202, "grad_norm": 2.076904296875, "learning_rate": 8.547463104015805e-06, "loss": 0.9767062664031982, "step": 570 }, { "epoch": 1.2067510548523206, "grad_norm": 4.681002616882324, "learning_rate": 8.535893298412262e-06, "loss": 1.0443482398986816, "step": 572 }, { "epoch": 1.2109704641350212, "grad_norm": 2.2652556896209717, "learning_rate": 8.524286542474239e-06, "loss": 1.0343825817108154, "step": 574 }, { "epoch": 1.2151898734177216, "grad_norm": 2.5286481380462646, "learning_rate": 8.512642977469386e-06, "loss": 0.935553252696991, "step": 576 }, { "epoch": 1.219409282700422, "grad_norm": 3.3003175258636475, "learning_rate": 8.50096274511336e-06, "loss": 0.6356152296066284, "step": 578 }, { "epoch": 1.2236286919831223, "grad_norm": 1.7909246683120728, "learning_rate": 8.489245987568107e-06, "loss": 0.9054712653160095, "step": 580 }, { "epoch": 1.2278481012658227, "grad_norm": 26.543872833251953, "learning_rate": 8.477492847440124e-06, "loss": 0.8610569834709167, "step": 582 }, { "epoch": 1.2320675105485233, "grad_norm": 3.908242702484131, "learning_rate": 8.465703467778728e-06, "loss": 0.7942756414413452, "step": 584 }, { "epoch": 1.2362869198312236, "grad_norm": 21.777339935302734, "learning_rate": 8.453877992074308e-06, "loss": 0.9873848557472229, "step": 586 }, { "epoch": 1.240506329113924, "grad_norm": 3.280397415161133, "learning_rate": 8.442016564256594e-06, "loss": 0.8189821243286133, "step": 588 }, { "epoch": 1.2447257383966246, "grad_norm": 2.035757303237915, "learning_rate": 8.43011932869288e-06, "loss": 1.0073659420013428, "step": 590 }, { "epoch": 1.248945147679325, "grad_norm": 2.6660571098327637, "learning_rate": 8.418186430186298e-06, "loss": 0.5638909935951233, "step": 592 }, { "epoch": 1.2531645569620253, "grad_norm": 1.3088264465332031, "learning_rate": 8.406218013974023e-06, "loss": 0.8390307426452637, "step": 594 }, { "epoch": 1.2573839662447257, "grad_norm": 4.299382209777832, "learning_rate": 8.394214225725537e-06, "loss": 0.6718566417694092, "step": 596 }, { "epoch": 1.261603375527426, "grad_norm": 5.391160488128662, "learning_rate": 8.38217521154083e-06, "loss": 0.6240211725234985, "step": 598 }, { "epoch": 1.2658227848101267, "grad_norm": 2.576371908187866, "learning_rate": 8.370101117948636e-06, "loss": 0.8396421670913696, "step": 600 }, { "epoch": 1.270042194092827, "grad_norm": 5.660943984985352, "learning_rate": 8.357992091904644e-06, "loss": 1.346001148223877, "step": 602 }, { "epoch": 1.2742616033755274, "grad_norm": 3.395664930343628, "learning_rate": 8.345848280789716e-06, "loss": 1.0721639394760132, "step": 604 }, { "epoch": 1.2784810126582278, "grad_norm": 3.3266537189483643, "learning_rate": 8.333669832408086e-06, "loss": 0.7810955047607422, "step": 606 }, { "epoch": 1.2827004219409281, "grad_norm": 3.665830135345459, "learning_rate": 8.321456894985564e-06, "loss": 0.8056845664978027, "step": 608 }, { "epoch": 1.2869198312236287, "grad_norm": 3.8954124450683594, "learning_rate": 8.309209617167727e-06, "loss": 0.8474479913711548, "step": 610 }, { "epoch": 1.2911392405063291, "grad_norm": 14.83908462524414, "learning_rate": 8.29692814801812e-06, "loss": 0.6019803285598755, "step": 612 }, { "epoch": 1.2953586497890295, "grad_norm": 1.7662218809127808, "learning_rate": 8.284612637016435e-06, "loss": 0.6540454626083374, "step": 614 }, { "epoch": 1.29957805907173, "grad_norm": 2.633075475692749, "learning_rate": 8.272263234056692e-06, "loss": 1.0802154541015625, "step": 616 }, { "epoch": 1.3037974683544304, "grad_norm": 2.6692678928375244, "learning_rate": 8.259880089445414e-06, "loss": 1.1146447658538818, "step": 618 }, { "epoch": 1.3080168776371308, "grad_norm": 2.178652286529541, "learning_rate": 8.247463353899802e-06, "loss": 0.670699954032898, "step": 620 }, { "epoch": 1.3122362869198312, "grad_norm": 4.32629919052124, "learning_rate": 8.235013178545896e-06, "loss": 0.7013387680053711, "step": 622 }, { "epoch": 1.3164556962025316, "grad_norm": 2.2110602855682373, "learning_rate": 8.222529714916733e-06, "loss": 0.8648394346237183, "step": 624 }, { "epoch": 1.3206751054852321, "grad_norm": 2.262147903442383, "learning_rate": 8.210013114950516e-06, "loss": 1.0324323177337646, "step": 626 }, { "epoch": 1.3248945147679325, "grad_norm": 10.206827163696289, "learning_rate": 8.197463530988747e-06, "loss": 1.4822674989700317, "step": 628 }, { "epoch": 1.3291139240506329, "grad_norm": 3.9082746505737305, "learning_rate": 8.18488111577439e-06, "loss": 0.8351543545722961, "step": 630 }, { "epoch": 1.3333333333333333, "grad_norm": 2.0968756675720215, "learning_rate": 8.17226602244999e-06, "loss": 0.9663413763046265, "step": 632 }, { "epoch": 1.3375527426160336, "grad_norm": 0.9584253430366516, "learning_rate": 8.159618404555836e-06, "loss": 0.7414358854293823, "step": 634 }, { "epoch": 1.3417721518987342, "grad_norm": 5.462522029876709, "learning_rate": 8.146938416028071e-06, "loss": 0.6039226055145264, "step": 636 }, { "epoch": 1.3459915611814346, "grad_norm": 16.680879592895508, "learning_rate": 8.13422621119683e-06, "loss": 0.8345423936843872, "step": 638 }, { "epoch": 1.350210970464135, "grad_norm": 2.430999755859375, "learning_rate": 8.121481944784356e-06, "loss": 1.1797393560409546, "step": 640 }, { "epoch": 1.3544303797468356, "grad_norm": 2.486576557159424, "learning_rate": 8.108705771903118e-06, "loss": 0.767329216003418, "step": 642 }, { "epoch": 1.358649789029536, "grad_norm": 1.574285626411438, "learning_rate": 8.095897848053922e-06, "loss": 1.2056798934936523, "step": 644 }, { "epoch": 1.3628691983122363, "grad_norm": 1.8294974565505981, "learning_rate": 8.083058329124026e-06, "loss": 1.173051118850708, "step": 646 }, { "epoch": 1.3670886075949367, "grad_norm": 27.29816246032715, "learning_rate": 8.070187371385228e-06, "loss": 0.8690171241760254, "step": 648 }, { "epoch": 1.371308016877637, "grad_norm": 2.3717832565307617, "learning_rate": 8.057285131491982e-06, "loss": 1.2316193580627441, "step": 650 }, { "epoch": 1.3755274261603376, "grad_norm": 2.37094783782959, "learning_rate": 8.044351766479478e-06, "loss": 1.0938432216644287, "step": 652 }, { "epoch": 1.379746835443038, "grad_norm": 3.792268753051758, "learning_rate": 8.03138743376173e-06, "loss": 0.7728132009506226, "step": 654 }, { "epoch": 1.3839662447257384, "grad_norm": 2.5651471614837646, "learning_rate": 8.018392291129672e-06, "loss": 1.1373931169509888, "step": 656 }, { "epoch": 1.3881856540084387, "grad_norm": 4.154591083526611, "learning_rate": 8.005366496749228e-06, "loss": 0.6223584413528442, "step": 658 }, { "epoch": 1.3924050632911391, "grad_norm": 2.3023734092712402, "learning_rate": 7.992310209159386e-06, "loss": 1.056243658065796, "step": 660 }, { "epoch": 1.3966244725738397, "grad_norm": 3.571608543395996, "learning_rate": 7.979223587270276e-06, "loss": 0.7067603468894958, "step": 662 }, { "epoch": 1.40084388185654, "grad_norm": 1.450181484222412, "learning_rate": 7.966106790361228e-06, "loss": 1.1153264045715332, "step": 664 }, { "epoch": 1.4050632911392404, "grad_norm": 1.3550797700881958, "learning_rate": 7.952959978078842e-06, "loss": 0.660108208656311, "step": 666 }, { "epoch": 1.409282700421941, "grad_norm": 3.615280866622925, "learning_rate": 7.939783310435036e-06, "loss": 1.0421502590179443, "step": 668 }, { "epoch": 1.4135021097046414, "grad_norm": 1.5363960266113281, "learning_rate": 7.9265769478051e-06, "loss": 1.0815043449401855, "step": 670 }, { "epoch": 1.4177215189873418, "grad_norm": 3.13627290725708, "learning_rate": 7.913341050925752e-06, "loss": 1.2361657619476318, "step": 672 }, { "epoch": 1.4219409282700421, "grad_norm": 1.9106669425964355, "learning_rate": 7.90007578089317e-06, "loss": 0.6243915557861328, "step": 674 }, { "epoch": 1.4261603375527425, "grad_norm": 3.255790948867798, "learning_rate": 7.886781299161044e-06, "loss": 0.6714270710945129, "step": 676 }, { "epoch": 1.4303797468354431, "grad_norm": 5.642148971557617, "learning_rate": 7.873457767538598e-06, "loss": 0.9618281126022339, "step": 678 }, { "epoch": 1.4345991561181435, "grad_norm": 5.4728169441223145, "learning_rate": 7.860105348188632e-06, "loss": 0.9934682846069336, "step": 680 }, { "epoch": 1.4388185654008439, "grad_norm": 1.8310091495513916, "learning_rate": 7.84672420362554e-06, "loss": 0.7535367012023926, "step": 682 }, { "epoch": 1.4430379746835442, "grad_norm": 2.71402645111084, "learning_rate": 7.83331449671333e-06, "loss": 1.1184730529785156, "step": 684 }, { "epoch": 1.4472573839662446, "grad_norm": 2.721883535385132, "learning_rate": 7.819876390663661e-06, "loss": 0.7760183215141296, "step": 686 }, { "epoch": 1.4514767932489452, "grad_norm": 3.989455223083496, "learning_rate": 7.806410049033829e-06, "loss": 0.7684187889099121, "step": 688 }, { "epoch": 1.4556962025316456, "grad_norm": 11.97647762298584, "learning_rate": 7.792915635724796e-06, "loss": 1.0284794569015503, "step": 690 }, { "epoch": 1.459915611814346, "grad_norm": 3.3579699993133545, "learning_rate": 7.779393314979184e-06, "loss": 0.6289864778518677, "step": 692 }, { "epoch": 1.4641350210970465, "grad_norm": 2.3317904472351074, "learning_rate": 7.765843251379288e-06, "loss": 1.1673097610473633, "step": 694 }, { "epoch": 1.4683544303797469, "grad_norm": 2.0161025524139404, "learning_rate": 7.752265609845061e-06, "loss": 0.6799832582473755, "step": 696 }, { "epoch": 1.4725738396624473, "grad_norm": 3.269385814666748, "learning_rate": 7.738660555632112e-06, "loss": 1.1176059246063232, "step": 698 }, { "epoch": 1.4767932489451476, "grad_norm": 2.476309061050415, "learning_rate": 7.72502825432969e-06, "loss": 1.1369357109069824, "step": 700 }, { "epoch": 1.481012658227848, "grad_norm": 5.302575588226318, "learning_rate": 7.711368871858685e-06, "loss": 0.9875307083129883, "step": 702 }, { "epoch": 1.4852320675105486, "grad_norm": 3.4655697345733643, "learning_rate": 7.69768257446958e-06, "loss": 0.8226287364959717, "step": 704 }, { "epoch": 1.489451476793249, "grad_norm": 1.595177412033081, "learning_rate": 7.683969528740454e-06, "loss": 1.0780549049377441, "step": 706 }, { "epoch": 1.4936708860759493, "grad_norm": 1.7033662796020508, "learning_rate": 7.670229901574946e-06, "loss": 1.1031169891357422, "step": 708 }, { "epoch": 1.49789029535865, "grad_norm": 1.2602566480636597, "learning_rate": 7.656463860200212e-06, "loss": 1.0011460781097412, "step": 710 }, { "epoch": 1.50210970464135, "grad_norm": 1.3341336250305176, "learning_rate": 7.642671572164907e-06, "loss": 0.47382962703704834, "step": 712 }, { "epoch": 1.5063291139240507, "grad_norm": 1.314199447631836, "learning_rate": 7.628853205337138e-06, "loss": 1.0233845710754395, "step": 714 }, { "epoch": 1.510548523206751, "grad_norm": 4.115900039672852, "learning_rate": 7.615008927902416e-06, "loss": 1.0157133340835571, "step": 716 }, { "epoch": 1.5147679324894514, "grad_norm": 2.439666509628296, "learning_rate": 7.601138908361621e-06, "loss": 1.021757960319519, "step": 718 }, { "epoch": 1.518987341772152, "grad_norm": 3.328108310699463, "learning_rate": 7.58724331552894e-06, "loss": 0.9978505373001099, "step": 720 }, { "epoch": 1.5232067510548524, "grad_norm": 4.225017070770264, "learning_rate": 7.573322318529818e-06, "loss": 1.0947837829589844, "step": 722 }, { "epoch": 1.5274261603375527, "grad_norm": 2.2315995693206787, "learning_rate": 7.559376086798894e-06, "loss": 1.1927165985107422, "step": 724 }, { "epoch": 1.5316455696202531, "grad_norm": 6.273666858673096, "learning_rate": 7.5454047900779495e-06, "loss": 0.5769215226173401, "step": 726 }, { "epoch": 1.5358649789029535, "grad_norm": 8.556334495544434, "learning_rate": 7.531408598413832e-06, "loss": 0.36240071058273315, "step": 728 }, { "epoch": 1.540084388185654, "grad_norm": 1.8587615489959717, "learning_rate": 7.5173876821563905e-06, "loss": 0.8379468321800232, "step": 730 }, { "epoch": 1.5443037974683544, "grad_norm": 1.8504387140274048, "learning_rate": 7.503342211956398e-06, "loss": 0.9457059502601624, "step": 732 }, { "epoch": 1.5485232067510548, "grad_norm": 2.1898131370544434, "learning_rate": 7.4892723587634845e-06, "loss": 1.1538609266281128, "step": 734 }, { "epoch": 1.5527426160337554, "grad_norm": 2.036227226257324, "learning_rate": 7.475178293824038e-06, "loss": 0.7996088266372681, "step": 736 }, { "epoch": 1.5569620253164556, "grad_norm": 3.042924642562866, "learning_rate": 7.461060188679143e-06, "loss": 0.8761364221572876, "step": 738 }, { "epoch": 1.5611814345991561, "grad_norm": 2.043531894683838, "learning_rate": 7.446918215162474e-06, "loss": 1.0147826671600342, "step": 740 }, { "epoch": 1.5654008438818565, "grad_norm": 1.6727322340011597, "learning_rate": 7.432752545398215e-06, "loss": 0.7132784128189087, "step": 742 }, { "epoch": 1.5696202531645569, "grad_norm": 25.195526123046875, "learning_rate": 7.418563351798959e-06, "loss": 0.5593595504760742, "step": 744 }, { "epoch": 1.5738396624472575, "grad_norm": 2.1481964588165283, "learning_rate": 7.40435080706361e-06, "loss": 0.765815258026123, "step": 746 }, { "epoch": 1.5780590717299579, "grad_norm": 3.1862220764160156, "learning_rate": 7.390115084175283e-06, "loss": 0.6900704503059387, "step": 748 }, { "epoch": 1.5822784810126582, "grad_norm": 3.530600070953369, "learning_rate": 7.375856356399201e-06, "loss": 1.1243162155151367, "step": 750 }, { "epoch": 1.5864978902953588, "grad_norm": 1.4450992345809937, "learning_rate": 7.36157479728058e-06, "loss": 0.5915750861167908, "step": 752 }, { "epoch": 1.590717299578059, "grad_norm": 1.6920042037963867, "learning_rate": 7.347270580642521e-06, "loss": 0.6169447302818298, "step": 754 }, { "epoch": 1.5949367088607596, "grad_norm": 1.833289384841919, "learning_rate": 7.332943880583892e-06, "loss": 0.6001879572868347, "step": 756 }, { "epoch": 1.59915611814346, "grad_norm": 1.8371257781982422, "learning_rate": 7.318594871477209e-06, "loss": 0.802247166633606, "step": 758 }, { "epoch": 1.6033755274261603, "grad_norm": 5.851796627044678, "learning_rate": 7.304223727966523e-06, "loss": 1.079378604888916, "step": 760 }, { "epoch": 1.6075949367088609, "grad_norm": 0.8718931674957275, "learning_rate": 7.289830624965275e-06, "loss": 0.7386890649795532, "step": 762 }, { "epoch": 1.611814345991561, "grad_norm": 1.774277925491333, "learning_rate": 7.275415737654185e-06, "loss": 1.0444384813308716, "step": 764 }, { "epoch": 1.6160337552742616, "grad_norm": 6.020558834075928, "learning_rate": 7.260979241479113e-06, "loss": 0.9992208480834961, "step": 766 }, { "epoch": 1.620253164556962, "grad_norm": 0.6516086459159851, "learning_rate": 7.246521312148924e-06, "loss": 0.8042000532150269, "step": 768 }, { "epoch": 1.6244725738396624, "grad_norm": 2.825258255004883, "learning_rate": 7.232042125633345e-06, "loss": 1.0829482078552246, "step": 770 }, { "epoch": 1.628691983122363, "grad_norm": 1.8748855590820312, "learning_rate": 7.217541858160834e-06, "loss": 1.1436506509780884, "step": 772 }, { "epoch": 1.6329113924050633, "grad_norm": 1.5475397109985352, "learning_rate": 7.203020686216422e-06, "loss": 1.0624109506607056, "step": 774 }, { "epoch": 1.6371308016877637, "grad_norm": 1.7471731901168823, "learning_rate": 7.188478786539579e-06, "loss": 1.0815238952636719, "step": 776 }, { "epoch": 1.6413502109704643, "grad_norm": 1.9459524154663086, "learning_rate": 7.173916336122049e-06, "loss": 0.7794762253761292, "step": 778 }, { "epoch": 1.6455696202531644, "grad_norm": 29.665868759155273, "learning_rate": 7.159333512205703e-06, "loss": 0.3798883557319641, "step": 780 }, { "epoch": 1.649789029535865, "grad_norm": 4.934221267700195, "learning_rate": 7.144730492280387e-06, "loss": 0.9985687732696533, "step": 782 }, { "epoch": 1.6540084388185654, "grad_norm": 3.7234246730804443, "learning_rate": 7.1301074540817496e-06, "loss": 0.8303778171539307, "step": 784 }, { "epoch": 1.6582278481012658, "grad_norm": 2.013413429260254, "learning_rate": 7.1154645755890875e-06, "loss": 1.084949016571045, "step": 786 }, { "epoch": 1.6624472573839664, "grad_norm": 2.8456227779388428, "learning_rate": 7.1008020350231745e-06, "loss": 0.5425201654434204, "step": 788 }, { "epoch": 1.6666666666666665, "grad_norm": 1.1652889251708984, "learning_rate": 7.086120010844097e-06, "loss": 1.0671439170837402, "step": 790 }, { "epoch": 1.6708860759493671, "grad_norm": 41.040802001953125, "learning_rate": 7.071418681749081e-06, "loss": 0.46648311614990234, "step": 792 }, { "epoch": 1.6751054852320675, "grad_norm": 0.44625580310821533, "learning_rate": 7.056698226670312e-06, "loss": 0.7891093492507935, "step": 794 }, { "epoch": 1.6793248945147679, "grad_norm": 1.4371800422668457, "learning_rate": 7.041958824772761e-06, "loss": 1.0508965253829956, "step": 796 }, { "epoch": 1.6835443037974684, "grad_norm": 9.063414573669434, "learning_rate": 7.027200655452007e-06, "loss": 0.8341038227081299, "step": 798 }, { "epoch": 1.6877637130801688, "grad_norm": 2.466891050338745, "learning_rate": 7.012423898332048e-06, "loss": 1.18134343624115, "step": 800 }, { "epoch": 1.6919831223628692, "grad_norm": 30.642555236816406, "learning_rate": 6.997628733263118e-06, "loss": 0.6166775822639465, "step": 802 }, { "epoch": 1.6962025316455698, "grad_norm": 2.0624189376831055, "learning_rate": 6.9828153403194945e-06, "loss": 1.1642102003097534, "step": 804 }, { "epoch": 1.70042194092827, "grad_norm": 1.4250247478485107, "learning_rate": 6.967983899797311e-06, "loss": 1.0424535274505615, "step": 806 }, { "epoch": 1.7046413502109705, "grad_norm": 6.845149040222168, "learning_rate": 6.953134592212363e-06, "loss": 0.8005964159965515, "step": 808 }, { "epoch": 1.7088607594936709, "grad_norm": 3.294389247894287, "learning_rate": 6.938267598297906e-06, "loss": 0.8661649227142334, "step": 810 }, { "epoch": 1.7130801687763713, "grad_norm": 1.8415154218673706, "learning_rate": 6.923383099002462e-06, "loss": 1.0995922088623047, "step": 812 }, { "epoch": 1.7172995780590719, "grad_norm": 4.381662845611572, "learning_rate": 6.9084812754876055e-06, "loss": 1.423997402191162, "step": 814 }, { "epoch": 1.721518987341772, "grad_norm": 2.0566799640655518, "learning_rate": 6.893562309125778e-06, "loss": 1.056745171546936, "step": 816 }, { "epoch": 1.7257383966244726, "grad_norm": 7.664315223693848, "learning_rate": 6.8786263814980625e-06, "loss": 0.7872004508972168, "step": 818 }, { "epoch": 1.729957805907173, "grad_norm": 12.006627082824707, "learning_rate": 6.863673674391981e-06, "loss": 0.3891472816467285, "step": 820 }, { "epoch": 1.7341772151898733, "grad_norm": 2.845207691192627, "learning_rate": 6.848704369799282e-06, "loss": 0.6111759543418884, "step": 822 }, { "epoch": 1.738396624472574, "grad_norm": 2.202544689178467, "learning_rate": 6.833718649913725e-06, "loss": 0.734418511390686, "step": 824 }, { "epoch": 1.7426160337552743, "grad_norm": 3.080443859100342, "learning_rate": 6.8187166971288595e-06, "loss": 0.9128053784370422, "step": 826 }, { "epoch": 1.7468354430379747, "grad_norm": 7.824685096740723, "learning_rate": 6.803698694035812e-06, "loss": 0.9317350387573242, "step": 828 }, { "epoch": 1.7510548523206753, "grad_norm": 1.6106356382369995, "learning_rate": 6.788664823421061e-06, "loss": 1.0445291996002197, "step": 830 }, { "epoch": 1.7552742616033754, "grad_norm": 2.2015790939331055, "learning_rate": 6.773615268264205e-06, "loss": 1.0102322101593018, "step": 832 }, { "epoch": 1.759493670886076, "grad_norm": 2.6845500469207764, "learning_rate": 6.75855021173575e-06, "loss": 0.8290532827377319, "step": 834 }, { "epoch": 1.7637130801687764, "grad_norm": 2.9580721855163574, "learning_rate": 6.74346983719486e-06, "loss": 1.049426555633545, "step": 836 }, { "epoch": 1.7679324894514767, "grad_norm": 2.179271697998047, "learning_rate": 6.728374328187149e-06, "loss": 0.8503140807151794, "step": 838 }, { "epoch": 1.7721518987341773, "grad_norm": 5.178153038024902, "learning_rate": 6.7132638684424286e-06, "loss": 0.7234880924224854, "step": 840 }, { "epoch": 1.7763713080168775, "grad_norm": 2.214745044708252, "learning_rate": 6.698138641872478e-06, "loss": 0.9172013401985168, "step": 842 }, { "epoch": 1.780590717299578, "grad_norm": 0.7265772819519043, "learning_rate": 6.6829988325688066e-06, "loss": 0.4127024710178375, "step": 844 }, { "epoch": 1.7848101265822784, "grad_norm": 1.3983646631240845, "learning_rate": 6.667844624800414e-06, "loss": 0.6767317056655884, "step": 846 }, { "epoch": 1.7890295358649788, "grad_norm": 3.5831058025360107, "learning_rate": 6.652676203011545e-06, "loss": 0.6544051766395569, "step": 848 }, { "epoch": 1.7932489451476794, "grad_norm": 6.102690696716309, "learning_rate": 6.6374937518194445e-06, "loss": 0.7576239109039307, "step": 850 }, { "epoch": 1.7974683544303798, "grad_norm": 1.593667984008789, "learning_rate": 6.622297456012114e-06, "loss": 1.0734498500823975, "step": 852 }, { "epoch": 1.8016877637130801, "grad_norm": 5.819282531738281, "learning_rate": 6.607087500546055e-06, "loss": 1.3928203582763672, "step": 854 }, { "epoch": 1.8059071729957807, "grad_norm": 0.5333048701286316, "learning_rate": 6.591864070544029e-06, "loss": 0.7620506882667542, "step": 856 }, { "epoch": 1.810126582278481, "grad_norm": 3.399226427078247, "learning_rate": 6.57662735129279e-06, "loss": 0.9754884243011475, "step": 858 }, { "epoch": 1.8143459915611815, "grad_norm": 1.6153955459594727, "learning_rate": 6.561377528240851e-06, "loss": 0.6267217397689819, "step": 860 }, { "epoch": 1.8185654008438819, "grad_norm": 2.8977577686309814, "learning_rate": 6.546114786996198e-06, "loss": 1.0711944103240967, "step": 862 }, { "epoch": 1.8227848101265822, "grad_norm": 1.3970896005630493, "learning_rate": 6.530839313324058e-06, "loss": 0.9198905825614929, "step": 864 }, { "epoch": 1.8270042194092828, "grad_norm": 3.1014037132263184, "learning_rate": 6.51555129314462e-06, "loss": 0.9234670996665955, "step": 866 }, { "epoch": 1.831223628691983, "grad_norm": 32.24216842651367, "learning_rate": 6.500250912530779e-06, "loss": 0.8945643305778503, "step": 868 }, { "epoch": 1.8354430379746836, "grad_norm": 2.4129698276519775, "learning_rate": 6.4849383577058746e-06, "loss": 1.0561885833740234, "step": 870 }, { "epoch": 1.839662447257384, "grad_norm": 15.151080131530762, "learning_rate": 6.469613815041417e-06, "loss": 0.7155804634094238, "step": 872 }, { "epoch": 1.8438818565400843, "grad_norm": 9.897340774536133, "learning_rate": 6.454277471054824e-06, "loss": 0.9214745163917542, "step": 874 }, { "epoch": 1.8481012658227849, "grad_norm": 2.1503212451934814, "learning_rate": 6.438929512407148e-06, "loss": 1.0825152397155762, "step": 876 }, { "epoch": 1.8523206751054853, "grad_norm": 3.1753077507019043, "learning_rate": 6.423570125900807e-06, "loss": 0.7228461503982544, "step": 878 }, { "epoch": 1.8565400843881856, "grad_norm": 6.838200569152832, "learning_rate": 6.408199498477307e-06, "loss": 0.7321918606758118, "step": 880 }, { "epoch": 1.8607594936708862, "grad_norm": 2.482978105545044, "learning_rate": 6.392817817214972e-06, "loss": 0.853125810623169, "step": 882 }, { "epoch": 1.8649789029535864, "grad_norm": 2.1994502544403076, "learning_rate": 6.377425269326659e-06, "loss": 0.8759280443191528, "step": 884 }, { "epoch": 1.869198312236287, "grad_norm": 7.824670791625977, "learning_rate": 6.362022042157491e-06, "loss": 0.7490097284317017, "step": 886 }, { "epoch": 1.8734177215189873, "grad_norm": 1.9435874223709106, "learning_rate": 6.346608323182564e-06, "loss": 1.030540943145752, "step": 888 }, { "epoch": 1.8776371308016877, "grad_norm": 4.0743408203125, "learning_rate": 6.331184300004677e-06, "loss": 0.3893578052520752, "step": 890 }, { "epoch": 1.8818565400843883, "grad_norm": 2.1779346466064453, "learning_rate": 6.315750160352036e-06, "loss": 0.6705051064491272, "step": 892 }, { "epoch": 1.8860759493670884, "grad_norm": 3.5976054668426514, "learning_rate": 6.300306092075985e-06, "loss": 1.0589570999145508, "step": 894 }, { "epoch": 1.890295358649789, "grad_norm": 1.8958508968353271, "learning_rate": 6.284852283148705e-06, "loss": 1.225637435913086, "step": 896 }, { "epoch": 1.8945147679324894, "grad_norm": 13.482898712158203, "learning_rate": 6.269388921660931e-06, "loss": 0.7953962683677673, "step": 898 }, { "epoch": 1.8987341772151898, "grad_norm": 2.315037250518799, "learning_rate": 6.2539161958196695e-06, "loss": 0.9806903600692749, "step": 900 }, { "epoch": 1.9029535864978904, "grad_norm": 1.977565050125122, "learning_rate": 6.238434293945895e-06, "loss": 1.1328575611114502, "step": 902 }, { "epoch": 1.9071729957805907, "grad_norm": 6.948404788970947, "learning_rate": 6.222943404472272e-06, "loss": 0.9575637578964233, "step": 904 }, { "epoch": 1.9113924050632911, "grad_norm": 1.308288335800171, "learning_rate": 6.207443715940847e-06, "loss": 1.2435095310211182, "step": 906 }, { "epoch": 1.9156118143459917, "grad_norm": 3.5493340492248535, "learning_rate": 6.191935417000771e-06, "loss": 0.43752309679985046, "step": 908 }, { "epoch": 1.9198312236286919, "grad_norm": 3.865103244781494, "learning_rate": 6.176418696405981e-06, "loss": 1.0318211317062378, "step": 910 }, { "epoch": 1.9240506329113924, "grad_norm": 7.21782112121582, "learning_rate": 6.160893743012927e-06, "loss": 0.7834182977676392, "step": 912 }, { "epoch": 1.9282700421940928, "grad_norm": 2.4316694736480713, "learning_rate": 6.145360745778255e-06, "loss": 1.1165027618408203, "step": 914 }, { "epoch": 1.9324894514767932, "grad_norm": 2.239809513092041, "learning_rate": 6.129819893756516e-06, "loss": 0.7559670209884644, "step": 916 }, { "epoch": 1.9367088607594938, "grad_norm": 2.101334571838379, "learning_rate": 6.1142713760978615e-06, "loss": 1.0124273300170898, "step": 918 }, { "epoch": 1.9409282700421941, "grad_norm": 2.6619949340820312, "learning_rate": 6.098715382045745e-06, "loss": 0.4279465675354004, "step": 920 }, { "epoch": 1.9451476793248945, "grad_norm": 1.2926506996154785, "learning_rate": 6.0831521009346135e-06, "loss": 1.0157091617584229, "step": 922 }, { "epoch": 1.9493670886075949, "grad_norm": 4.153886795043945, "learning_rate": 6.067581722187609e-06, "loss": 1.1203033924102783, "step": 924 }, { "epoch": 1.9535864978902953, "grad_norm": 2.1800642013549805, "learning_rate": 6.0520044353142585e-06, "loss": 0.893081545829773, "step": 926 }, { "epoch": 1.9578059071729959, "grad_norm": 1.6266523599624634, "learning_rate": 6.0364204299081665e-06, "loss": 0.7595791220664978, "step": 928 }, { "epoch": 1.9620253164556962, "grad_norm": 2.508669853210449, "learning_rate": 6.0208298956447155e-06, "loss": 1.0534107685089111, "step": 930 }, { "epoch": 1.9662447257383966, "grad_norm": 8.25910758972168, "learning_rate": 6.005233022278744e-06, "loss": 0.8808714151382446, "step": 932 }, { "epoch": 1.9704641350210972, "grad_norm": 2.152791738510132, "learning_rate": 5.9896299996422546e-06, "loss": 1.2055463790893555, "step": 934 }, { "epoch": 1.9746835443037973, "grad_norm": 2.116642475128174, "learning_rate": 5.974021017642084e-06, "loss": 1.1175028085708618, "step": 936 }, { "epoch": 1.978902953586498, "grad_norm": 2.1793270111083984, "learning_rate": 5.958406266257607e-06, "loss": 0.6490421891212463, "step": 938 }, { "epoch": 1.9831223628691983, "grad_norm": 1.7029622793197632, "learning_rate": 5.942785935538415e-06, "loss": 1.0587456226348877, "step": 940 }, { "epoch": 1.9873417721518987, "grad_norm": 6.407623767852783, "learning_rate": 5.927160215602009e-06, "loss": 0.9026035070419312, "step": 942 }, { "epoch": 1.9915611814345993, "grad_norm": 1.9148080348968506, "learning_rate": 5.9115292966314855e-06, "loss": 0.7156428098678589, "step": 944 }, { "epoch": 1.9957805907172996, "grad_norm": 2.6921048164367676, "learning_rate": 5.895893368873212e-06, "loss": 1.0681915283203125, "step": 946 }, { "epoch": 2.0, "grad_norm": 10.341744422912598, "learning_rate": 5.880252622634524e-06, "loss": 0.565343976020813, "step": 948 }, { "epoch": 2.0042194092827006, "grad_norm": 2.4585750102996826, "learning_rate": 5.864607248281401e-06, "loss": 0.797762930393219, "step": 950 }, { "epoch": 2.0084388185654007, "grad_norm": 4.021915912628174, "learning_rate": 5.848957436236156e-06, "loss": 0.5289384722709656, "step": 952 }, { "epoch": 2.0126582278481013, "grad_norm": 2.4470012187957764, "learning_rate": 5.833303376975109e-06, "loss": 0.7827356457710266, "step": 954 }, { "epoch": 2.0168776371308015, "grad_norm": 1.2545971870422363, "learning_rate": 5.8176452610262756e-06, "loss": 0.9084755182266235, "step": 956 }, { "epoch": 2.021097046413502, "grad_norm": 8.951279640197754, "learning_rate": 5.8019832789670476e-06, "loss": 0.6672205924987793, "step": 958 }, { "epoch": 2.0253164556962027, "grad_norm": 7.998170852661133, "learning_rate": 5.7863176214218676e-06, "loss": 0.719889760017395, "step": 960 }, { "epoch": 2.029535864978903, "grad_norm": 2.303816556930542, "learning_rate": 5.770648479059918e-06, "loss": 0.9447646141052246, "step": 962 }, { "epoch": 2.0337552742616034, "grad_norm": 1.663718342781067, "learning_rate": 5.754976042592791e-06, "loss": 0.720722496509552, "step": 964 }, { "epoch": 2.037974683544304, "grad_norm": 2.7137224674224854, "learning_rate": 5.739300502772177e-06, "loss": 0.6178973913192749, "step": 966 }, { "epoch": 2.042194092827004, "grad_norm": 3.8692123889923096, "learning_rate": 5.723622050387533e-06, "loss": 0.6272182464599609, "step": 968 }, { "epoch": 2.0464135021097047, "grad_norm": 2.5525665283203125, "learning_rate": 5.707940876263767e-06, "loss": 0.928709089756012, "step": 970 }, { "epoch": 2.050632911392405, "grad_norm": 5.327123165130615, "learning_rate": 5.6922571712589145e-06, "loss": 0.8047610521316528, "step": 972 }, { "epoch": 2.0548523206751055, "grad_norm": 1.6276748180389404, "learning_rate": 5.676571126261814e-06, "loss": 0.7803731560707092, "step": 974 }, { "epoch": 2.059071729957806, "grad_norm": 3.2204136848449707, "learning_rate": 5.660882932189783e-06, "loss": 0.6810506582260132, "step": 976 }, { "epoch": 2.0632911392405062, "grad_norm": 1.2158677577972412, "learning_rate": 5.6451927799863e-06, "loss": 0.6252305507659912, "step": 978 }, { "epoch": 2.067510548523207, "grad_norm": 1.7296432256698608, "learning_rate": 5.629500860618673e-06, "loss": 0.5727726221084595, "step": 980 }, { "epoch": 2.071729957805907, "grad_norm": 3.264876127243042, "learning_rate": 5.613807365075716e-06, "loss": 0.9008371829986572, "step": 982 }, { "epoch": 2.0759493670886076, "grad_norm": 3.087449073791504, "learning_rate": 5.5981124843654335e-06, "loss": 0.8526220321655273, "step": 984 }, { "epoch": 2.080168776371308, "grad_norm": 2.4998385906219482, "learning_rate": 5.582416409512682e-06, "loss": 0.894225537776947, "step": 986 }, { "epoch": 2.0843881856540083, "grad_norm": 3.378431558609009, "learning_rate": 5.566719331556858e-06, "loss": 0.8582086563110352, "step": 988 }, { "epoch": 2.088607594936709, "grad_norm": 5.549224853515625, "learning_rate": 5.5510214415495635e-06, "loss": 0.4567492604255676, "step": 990 }, { "epoch": 2.0928270042194095, "grad_norm": 2.0450949668884277, "learning_rate": 5.535322930552283e-06, "loss": 0.47975513339042664, "step": 992 }, { "epoch": 2.0970464135021096, "grad_norm": 1.8305095434188843, "learning_rate": 5.519623989634065e-06, "loss": 0.9532815217971802, "step": 994 }, { "epoch": 2.1012658227848102, "grad_norm": 2.025418519973755, "learning_rate": 5.503924809869186e-06, "loss": 0.9890322089195251, "step": 996 }, { "epoch": 2.1054852320675104, "grad_norm": 0.5560290813446045, "learning_rate": 5.488225582334826e-06, "loss": 0.5471876859664917, "step": 998 }, { "epoch": 2.109704641350211, "grad_norm": 1.7783093452453613, "learning_rate": 5.472526498108756e-06, "loss": 1.0171313285827637, "step": 1000 }, { "epoch": 2.1139240506329116, "grad_norm": 3.2962849140167236, "learning_rate": 5.456827748266995e-06, "loss": 0.8569251298904419, "step": 1002 }, { "epoch": 2.1181434599156117, "grad_norm": 2.183375835418701, "learning_rate": 5.441129523881496e-06, "loss": 0.9041435718536377, "step": 1004 }, { "epoch": 2.1223628691983123, "grad_norm": 1.0837674140930176, "learning_rate": 5.425432016017814e-06, "loss": 0.6107112169265747, "step": 1006 }, { "epoch": 2.1265822784810124, "grad_norm": 1.717499852180481, "learning_rate": 5.409735415732784e-06, "loss": 0.6214268207550049, "step": 1008 }, { "epoch": 2.130801687763713, "grad_norm": 2.559298038482666, "learning_rate": 5.394039914072198e-06, "loss": 0.6848146915435791, "step": 1010 }, { "epoch": 2.1350210970464136, "grad_norm": 18.754873275756836, "learning_rate": 5.37834570206847e-06, "loss": 0.8150510787963867, "step": 1012 }, { "epoch": 2.1392405063291138, "grad_norm": 8.957157135009766, "learning_rate": 5.362652970738321e-06, "loss": 0.9707658290863037, "step": 1014 }, { "epoch": 2.1434599156118144, "grad_norm": 4.546601295471191, "learning_rate": 5.346961911080453e-06, "loss": 0.5670202970504761, "step": 1016 }, { "epoch": 2.147679324894515, "grad_norm": 1.743969440460205, "learning_rate": 5.3312727140732175e-06, "loss": 0.7976697683334351, "step": 1018 }, { "epoch": 2.151898734177215, "grad_norm": 2.410522699356079, "learning_rate": 5.315585570672298e-06, "loss": 0.7055184841156006, "step": 1020 }, { "epoch": 2.1561181434599157, "grad_norm": 4.874363899230957, "learning_rate": 5.299900671808382e-06, "loss": 0.7655179500579834, "step": 1022 }, { "epoch": 2.160337552742616, "grad_norm": 5.135618686676025, "learning_rate": 5.284218208384839e-06, "loss": 0.6614477038383484, "step": 1024 }, { "epoch": 2.1645569620253164, "grad_norm": 1.5275734663009644, "learning_rate": 5.268538371275396e-06, "loss": 0.8715944886207581, "step": 1026 }, { "epoch": 2.168776371308017, "grad_norm": 2.547562837600708, "learning_rate": 5.252861351321815e-06, "loss": 0.9230575561523438, "step": 1028 }, { "epoch": 2.172995780590717, "grad_norm": 1.4855462312698364, "learning_rate": 5.237187339331567e-06, "loss": 0.8314052820205688, "step": 1030 }, { "epoch": 2.1772151898734178, "grad_norm": 2.356966733932495, "learning_rate": 5.2215165260755205e-06, "loss": 0.9557764530181885, "step": 1032 }, { "epoch": 2.181434599156118, "grad_norm": 2.985762119293213, "learning_rate": 5.205849102285603e-06, "loss": 0.8720968961715698, "step": 1034 }, { "epoch": 2.1856540084388185, "grad_norm": 4.336760520935059, "learning_rate": 5.190185258652494e-06, "loss": 0.9139829277992249, "step": 1036 }, { "epoch": 2.189873417721519, "grad_norm": 2.284707546234131, "learning_rate": 5.1745251858232935e-06, "loss": 0.9164941906929016, "step": 1038 }, { "epoch": 2.1940928270042193, "grad_norm": 3.3554375171661377, "learning_rate": 5.158869074399211e-06, "loss": 1.0291779041290283, "step": 1040 }, { "epoch": 2.19831223628692, "grad_norm": 4.926438808441162, "learning_rate": 5.143217114933239e-06, "loss": 0.24929910898208618, "step": 1042 }, { "epoch": 2.2025316455696204, "grad_norm": 1.7740081548690796, "learning_rate": 5.127569497927837e-06, "loss": 0.8818829655647278, "step": 1044 }, { "epoch": 2.2067510548523206, "grad_norm": 8.643919944763184, "learning_rate": 5.111926413832609e-06, "loss": 0.5833356976509094, "step": 1046 }, { "epoch": 2.210970464135021, "grad_norm": 2.8281774520874023, "learning_rate": 5.096288053041992e-06, "loss": 0.8073537349700928, "step": 1048 }, { "epoch": 2.2151898734177213, "grad_norm": 8.114171981811523, "learning_rate": 5.080654605892931e-06, "loss": 0.9253809452056885, "step": 1050 }, { "epoch": 2.219409282700422, "grad_norm": 7.827826976776123, "learning_rate": 5.065026262662572e-06, "loss": 0.8310404419898987, "step": 1052 }, { "epoch": 2.2236286919831225, "grad_norm": 17.488344192504883, "learning_rate": 5.049403213565932e-06, "loss": 0.8019734025001526, "step": 1054 }, { "epoch": 2.2278481012658227, "grad_norm": 2.1192474365234375, "learning_rate": 5.0337856487536e-06, "loss": 0.7308956384658813, "step": 1056 }, { "epoch": 2.2320675105485233, "grad_norm": 4.875123500823975, "learning_rate": 5.018173758309411e-06, "loss": 0.4857543110847473, "step": 1058 }, { "epoch": 2.2362869198312234, "grad_norm": 1.333125352859497, "learning_rate": 5.002567732248137e-06, "loss": 0.7932926416397095, "step": 1060 }, { "epoch": 2.240506329113924, "grad_norm": 0.7726789712905884, "learning_rate": 4.986967760513176e-06, "loss": 0.5164146423339844, "step": 1062 }, { "epoch": 2.2447257383966246, "grad_norm": 3.1366655826568604, "learning_rate": 4.971374032974233e-06, "loss": 0.4894426763057709, "step": 1064 }, { "epoch": 2.2489451476793247, "grad_norm": 1.9511240720748901, "learning_rate": 4.9557867394250194e-06, "loss": 0.8222055435180664, "step": 1066 }, { "epoch": 2.2531645569620253, "grad_norm": 2.5273797512054443, "learning_rate": 4.940206069580932e-06, "loss": 1.0261657238006592, "step": 1068 }, { "epoch": 2.257383966244726, "grad_norm": 2.3411054611206055, "learning_rate": 4.924632213076754e-06, "loss": 0.9490532875061035, "step": 1070 }, { "epoch": 2.261603375527426, "grad_norm": 3.8541409969329834, "learning_rate": 4.9090653594643404e-06, "loss": 0.9570581912994385, "step": 1072 }, { "epoch": 2.2658227848101267, "grad_norm": 4.605185031890869, "learning_rate": 4.893505698210313e-06, "loss": 1.1807842254638672, "step": 1074 }, { "epoch": 2.270042194092827, "grad_norm": 1.5088281631469727, "learning_rate": 4.877953418693755e-06, "loss": 0.8157051801681519, "step": 1076 }, { "epoch": 2.2742616033755274, "grad_norm": 0.785092830657959, "learning_rate": 4.862408710203904e-06, "loss": 0.5877640247344971, "step": 1078 }, { "epoch": 2.278481012658228, "grad_norm": 5.871740341186523, "learning_rate": 4.8468717619378515e-06, "loss": 0.6630680561065674, "step": 1080 }, { "epoch": 2.282700421940928, "grad_norm": 3.791898727416992, "learning_rate": 4.831342762998233e-06, "loss": 0.2969897389411926, "step": 1082 }, { "epoch": 2.2869198312236287, "grad_norm": 19.624292373657227, "learning_rate": 4.81582190239094e-06, "loss": 0.6159294247627258, "step": 1084 }, { "epoch": 2.291139240506329, "grad_norm": 0.5075086951255798, "learning_rate": 4.800309369022803e-06, "loss": 0.47266829013824463, "step": 1086 }, { "epoch": 2.2953586497890295, "grad_norm": 3.045797824859619, "learning_rate": 4.784805351699306e-06, "loss": 0.47493693232536316, "step": 1088 }, { "epoch": 2.29957805907173, "grad_norm": 7.199693202972412, "learning_rate": 4.769310039122278e-06, "loss": 0.4261780083179474, "step": 1090 }, { "epoch": 2.3037974683544302, "grad_norm": 3.732618808746338, "learning_rate": 4.753823619887606e-06, "loss": 0.7672412395477295, "step": 1092 }, { "epoch": 2.308016877637131, "grad_norm": 2.0005836486816406, "learning_rate": 4.738346282482932e-06, "loss": 0.5544326305389404, "step": 1094 }, { "epoch": 2.3122362869198314, "grad_norm": 8.313835144042969, "learning_rate": 4.722878215285362e-06, "loss": 0.37466931343078613, "step": 1096 }, { "epoch": 2.3164556962025316, "grad_norm": 2.707016944885254, "learning_rate": 4.707419606559172e-06, "loss": 0.8995563387870789, "step": 1098 }, { "epoch": 2.320675105485232, "grad_norm": 2.018192768096924, "learning_rate": 4.691970644453521e-06, "loss": 0.6780773401260376, "step": 1100 }, { "epoch": 2.3248945147679323, "grad_norm": 2.0068483352661133, "learning_rate": 4.676531517000152e-06, "loss": 0.8397384881973267, "step": 1102 }, { "epoch": 2.329113924050633, "grad_norm": 1.778388500213623, "learning_rate": 4.661102412111113e-06, "loss": 1.01942777633667, "step": 1104 }, { "epoch": 2.3333333333333335, "grad_norm": 79.84559631347656, "learning_rate": 4.645683517576465e-06, "loss": 0.7264695167541504, "step": 1106 }, { "epoch": 2.3375527426160336, "grad_norm": 5.002988338470459, "learning_rate": 4.630275021061994e-06, "loss": 0.47009116411209106, "step": 1108 }, { "epoch": 2.3417721518987342, "grad_norm": 7.156156063079834, "learning_rate": 4.614877110106936e-06, "loss": 0.8979440331459045, "step": 1110 }, { "epoch": 2.3459915611814344, "grad_norm": 2.5135679244995117, "learning_rate": 4.599489972121685e-06, "loss": 0.939918577671051, "step": 1112 }, { "epoch": 2.350210970464135, "grad_norm": 1.773421049118042, "learning_rate": 4.584113794385514e-06, "loss": 1.0033924579620361, "step": 1114 }, { "epoch": 2.3544303797468356, "grad_norm": 0.7761349081993103, "learning_rate": 4.568748764044301e-06, "loss": 0.4906420111656189, "step": 1116 }, { "epoch": 2.3586497890295357, "grad_norm": 10.869142532348633, "learning_rate": 4.553395068108244e-06, "loss": 0.7896329760551453, "step": 1118 }, { "epoch": 2.3628691983122363, "grad_norm": 2.278578519821167, "learning_rate": 4.538052893449589e-06, "loss": 0.5544410943984985, "step": 1120 }, { "epoch": 2.367088607594937, "grad_norm": 7.019713401794434, "learning_rate": 4.522722426800357e-06, "loss": 0.8139508962631226, "step": 1122 }, { "epoch": 2.371308016877637, "grad_norm": 2.1097123622894287, "learning_rate": 4.507403854750065e-06, "loss": 0.6513611078262329, "step": 1124 }, { "epoch": 2.3755274261603376, "grad_norm": 3.794123888015747, "learning_rate": 4.492097363743461e-06, "loss": 0.6482852101325989, "step": 1126 }, { "epoch": 2.379746835443038, "grad_norm": 2.7359893321990967, "learning_rate": 4.476803140078253e-06, "loss": 0.8722869157791138, "step": 1128 }, { "epoch": 2.3839662447257384, "grad_norm": 6.382290363311768, "learning_rate": 4.4615213699028426e-06, "loss": 0.4258735179901123, "step": 1130 }, { "epoch": 2.388185654008439, "grad_norm": 6.051519870758057, "learning_rate": 4.446252239214055e-06, "loss": 0.34600162506103516, "step": 1132 }, { "epoch": 2.392405063291139, "grad_norm": 5.8614630699157715, "learning_rate": 4.43099593385488e-06, "loss": 0.4541134238243103, "step": 1134 }, { "epoch": 2.3966244725738397, "grad_norm": 2.699312210083008, "learning_rate": 4.4157526395122076e-06, "loss": 0.4782767593860626, "step": 1136 }, { "epoch": 2.40084388185654, "grad_norm": 2.0531277656555176, "learning_rate": 4.400522541714569e-06, "loss": 0.9564571380615234, "step": 1138 }, { "epoch": 2.4050632911392404, "grad_norm": 4.856972694396973, "learning_rate": 4.385305825829878e-06, "loss": 0.7016127705574036, "step": 1140 }, { "epoch": 2.409282700421941, "grad_norm": 3.4981300830841064, "learning_rate": 4.370102677063176e-06, "loss": 0.25484469532966614, "step": 1142 }, { "epoch": 2.413502109704641, "grad_norm": 1.5144480466842651, "learning_rate": 4.354913280454376e-06, "loss": 0.7090221643447876, "step": 1144 }, { "epoch": 2.4177215189873418, "grad_norm": 3.7478628158569336, "learning_rate": 4.339737820876011e-06, "loss": 0.8909446597099304, "step": 1146 }, { "epoch": 2.4219409282700424, "grad_norm": 8.819247245788574, "learning_rate": 4.324576483030984e-06, "loss": 0.7027132511138916, "step": 1148 }, { "epoch": 2.4261603375527425, "grad_norm": 2.4419357776641846, "learning_rate": 4.309429451450323e-06, "loss": 0.969456672668457, "step": 1150 }, { "epoch": 2.430379746835443, "grad_norm": 7.102992057800293, "learning_rate": 4.294296910490927e-06, "loss": 0.5980501174926758, "step": 1152 }, { "epoch": 2.4345991561181437, "grad_norm": 7.420240879058838, "learning_rate": 4.279179044333334e-06, "loss": 0.922325611114502, "step": 1154 }, { "epoch": 2.438818565400844, "grad_norm": 3.1395161151885986, "learning_rate": 4.264076036979465e-06, "loss": 0.3183514475822449, "step": 1156 }, { "epoch": 2.4430379746835444, "grad_norm": 1.9260720014572144, "learning_rate": 4.2489880722503984e-06, "loss": 0.5928694009780884, "step": 1158 }, { "epoch": 2.4472573839662446, "grad_norm": 3.5315332412719727, "learning_rate": 4.233915333784125e-06, "loss": 0.8913297057151794, "step": 1160 }, { "epoch": 2.451476793248945, "grad_norm": 2.6884663105010986, "learning_rate": 4.2188580050333125e-06, "loss": 0.549304723739624, "step": 1162 }, { "epoch": 2.4556962025316453, "grad_norm": 2.063899517059326, "learning_rate": 4.203816269263076e-06, "loss": 0.876154899597168, "step": 1164 }, { "epoch": 2.459915611814346, "grad_norm": 2.011545181274414, "learning_rate": 4.188790309548745e-06, "loss": 0.8603496551513672, "step": 1166 }, { "epoch": 2.4641350210970465, "grad_norm": 1.0937695503234863, "learning_rate": 4.173780308773638e-06, "loss": 0.5272076725959778, "step": 1168 }, { "epoch": 2.4683544303797467, "grad_norm": 1.507976770401001, "learning_rate": 4.158786449626832e-06, "loss": 0.8220661878585815, "step": 1170 }, { "epoch": 2.4725738396624473, "grad_norm": 1.6173585653305054, "learning_rate": 4.1438089146009444e-06, "loss": 0.9008454084396362, "step": 1172 }, { "epoch": 2.476793248945148, "grad_norm": 1.8765454292297363, "learning_rate": 4.128847885989907e-06, "loss": 0.8743375539779663, "step": 1174 }, { "epoch": 2.481012658227848, "grad_norm": 1.9079874753952026, "learning_rate": 4.113903545886753e-06, "loss": 0.6790565848350525, "step": 1176 }, { "epoch": 2.4852320675105486, "grad_norm": 3.8118598461151123, "learning_rate": 4.098976076181391e-06, "loss": 0.349514365196228, "step": 1178 }, { "epoch": 2.489451476793249, "grad_norm": 6.48369026184082, "learning_rate": 4.084065658558404e-06, "loss": 0.6549777984619141, "step": 1180 }, { "epoch": 2.4936708860759493, "grad_norm": 3.4311490058898926, "learning_rate": 4.0691724744948255e-06, "loss": 0.6928924918174744, "step": 1182 }, { "epoch": 2.49789029535865, "grad_norm": 4.259927272796631, "learning_rate": 4.054296705257941e-06, "loss": 0.4243977665901184, "step": 1184 }, { "epoch": 2.50210970464135, "grad_norm": 1.0532008409500122, "learning_rate": 4.039438531903077e-06, "loss": 0.2592931091785431, "step": 1186 }, { "epoch": 2.5063291139240507, "grad_norm": 1.4878853559494019, "learning_rate": 4.024598135271394e-06, "loss": 0.5979218482971191, "step": 1188 }, { "epoch": 2.510548523206751, "grad_norm": 2.2561726570129395, "learning_rate": 4.009775695987694e-06, "loss": 0.9713151454925537, "step": 1190 }, { "epoch": 2.5147679324894514, "grad_norm": 30.54766845703125, "learning_rate": 3.994971394458214e-06, "loss": 0.42932742834091187, "step": 1192 }, { "epoch": 2.518987341772152, "grad_norm": 6.2397236824035645, "learning_rate": 3.980185410868436e-06, "loss": 1.1364171504974365, "step": 1194 }, { "epoch": 2.523206751054852, "grad_norm": 1.8887968063354492, "learning_rate": 3.965417925180889e-06, "loss": 0.9718483686447144, "step": 1196 }, { "epoch": 2.5274261603375527, "grad_norm": 2.0869195461273193, "learning_rate": 3.950669117132961e-06, "loss": 0.8501858711242676, "step": 1198 }, { "epoch": 2.5316455696202533, "grad_norm": 2.8297433853149414, "learning_rate": 3.935939166234716e-06, "loss": 0.610925018787384, "step": 1200 }, { "epoch": 2.5358649789029535, "grad_norm": 3.1504592895507812, "learning_rate": 3.9212282517667e-06, "loss": 0.6660202741622925, "step": 1202 }, { "epoch": 2.540084388185654, "grad_norm": 3.2236862182617188, "learning_rate": 3.9065365527777645e-06, "loss": 0.6265650987625122, "step": 1204 }, { "epoch": 2.5443037974683547, "grad_norm": 2.154318332672119, "learning_rate": 3.891864248082887e-06, "loss": 0.7999696135520935, "step": 1206 }, { "epoch": 2.548523206751055, "grad_norm": 3.641517400741577, "learning_rate": 3.877211516260996e-06, "loss": 0.6511145830154419, "step": 1208 }, { "epoch": 2.5527426160337554, "grad_norm": 2.169196605682373, "learning_rate": 3.862578535652789e-06, "loss": 0.9868561029434204, "step": 1210 }, { "epoch": 2.5569620253164556, "grad_norm": 2.188295841217041, "learning_rate": 3.847965484358577e-06, "loss": 0.9202408194541931, "step": 1212 }, { "epoch": 2.561181434599156, "grad_norm": 5.334817409515381, "learning_rate": 3.833372540236103e-06, "loss": 0.22011728584766388, "step": 1214 }, { "epoch": 2.5654008438818563, "grad_norm": 7.0658159255981445, "learning_rate": 3.818799880898383e-06, "loss": 0.7272290587425232, "step": 1216 }, { "epoch": 2.569620253164557, "grad_norm": 2.094721794128418, "learning_rate": 3.804247683711544e-06, "loss": 0.8370944261550903, "step": 1218 }, { "epoch": 2.5738396624472575, "grad_norm": 4.289225101470947, "learning_rate": 3.789716125792665e-06, "loss": 0.5495480298995972, "step": 1220 }, { "epoch": 2.5780590717299576, "grad_norm": 3.338582754135132, "learning_rate": 3.7752053840076207e-06, "loss": 0.8071571588516235, "step": 1222 }, { "epoch": 2.5822784810126582, "grad_norm": 7.826380729675293, "learning_rate": 3.7607156349689333e-06, "loss": 0.6407029628753662, "step": 1224 }, { "epoch": 2.586497890295359, "grad_norm": 3.921565055847168, "learning_rate": 3.7462470550336115e-06, "loss": 0.5933206081390381, "step": 1226 }, { "epoch": 2.590717299578059, "grad_norm": 2.518813371658325, "learning_rate": 3.7317998203010188e-06, "loss": 0.8569338917732239, "step": 1228 }, { "epoch": 2.5949367088607596, "grad_norm": 3.106778144836426, "learning_rate": 3.7173741066107184e-06, "loss": 0.887120246887207, "step": 1230 }, { "epoch": 2.59915611814346, "grad_norm": 2.3412606716156006, "learning_rate": 3.7029700895403386e-06, "loss": 0.9088625907897949, "step": 1232 }, { "epoch": 2.6033755274261603, "grad_norm": 5.6442975997924805, "learning_rate": 3.6885879444034355e-06, "loss": 0.30501505732536316, "step": 1234 }, { "epoch": 2.607594936708861, "grad_norm": 3.3387961387634277, "learning_rate": 3.674227846247358e-06, "loss": 0.9569495916366577, "step": 1236 }, { "epoch": 2.611814345991561, "grad_norm": 4.308297157287598, "learning_rate": 3.659889969851118e-06, "loss": 1.1148781776428223, "step": 1238 }, { "epoch": 2.6160337552742616, "grad_norm": 2.3547513484954834, "learning_rate": 3.6455744897232615e-06, "loss": 0.6341689229011536, "step": 1240 }, { "epoch": 2.620253164556962, "grad_norm": 3.895256280899048, "learning_rate": 3.631281580099749e-06, "loss": 0.8243012428283691, "step": 1242 }, { "epoch": 2.6244725738396624, "grad_norm": 2.837615966796875, "learning_rate": 3.6170114149418277e-06, "loss": 0.3667352795600891, "step": 1244 }, { "epoch": 2.628691983122363, "grad_norm": 2.2860302925109863, "learning_rate": 3.602764167933921e-06, "loss": 0.6914593577384949, "step": 1246 }, { "epoch": 2.632911392405063, "grad_norm": 5.512315273284912, "learning_rate": 3.588540012481514e-06, "loss": 1.3394896984100342, "step": 1248 }, { "epoch": 2.6371308016877637, "grad_norm": 6.311371326446533, "learning_rate": 3.574339121709035e-06, "loss": 0.7868828177452087, "step": 1250 }, { "epoch": 2.6413502109704643, "grad_norm": 4.537491321563721, "learning_rate": 3.5601616684577587e-06, "loss": 0.8604764938354492, "step": 1252 }, { "epoch": 2.6455696202531644, "grad_norm": 5.187697410583496, "learning_rate": 3.546007825283697e-06, "loss": 0.3737580478191376, "step": 1254 }, { "epoch": 2.649789029535865, "grad_norm": 4.532652854919434, "learning_rate": 3.5318777644555024e-06, "loss": 0.48380380868911743, "step": 1256 }, { "epoch": 2.6540084388185656, "grad_norm": 1.964828372001648, "learning_rate": 3.5177716579523602e-06, "loss": 0.6129435896873474, "step": 1258 }, { "epoch": 2.6582278481012658, "grad_norm": 1.9946211576461792, "learning_rate": 3.5036896774619135e-06, "loss": 0.8307033181190491, "step": 1260 }, { "epoch": 2.6624472573839664, "grad_norm": 1.8517165184020996, "learning_rate": 3.489631994378161e-06, "loss": 0.7911721467971802, "step": 1262 }, { "epoch": 2.6666666666666665, "grad_norm": 0.8536872863769531, "learning_rate": 3.47559877979937e-06, "loss": 0.4675355553627014, "step": 1264 }, { "epoch": 2.670886075949367, "grad_norm": 3.4769389629364014, "learning_rate": 3.461590204526002e-06, "loss": 0.7507180571556091, "step": 1266 }, { "epoch": 2.6751054852320673, "grad_norm": 2.2950754165649414, "learning_rate": 3.4476064390586282e-06, "loss": 0.6631865501403809, "step": 1268 }, { "epoch": 2.679324894514768, "grad_norm": 2.4555985927581787, "learning_rate": 3.433647653595858e-06, "loss": 0.39027154445648193, "step": 1270 }, { "epoch": 2.6835443037974684, "grad_norm": 1.4601293802261353, "learning_rate": 3.4197140180322595e-06, "loss": 0.9111906290054321, "step": 1272 }, { "epoch": 2.6877637130801686, "grad_norm": 8.525717735290527, "learning_rate": 3.405805701956303e-06, "loss": 0.6194537281990051, "step": 1274 }, { "epoch": 2.691983122362869, "grad_norm": 9.036405563354492, "learning_rate": 3.391922874648289e-06, "loss": 0.791827917098999, "step": 1276 }, { "epoch": 2.6962025316455698, "grad_norm": 0.7543266415596008, "learning_rate": 3.3780657050782937e-06, "loss": 0.24154594540596008, "step": 1278 }, { "epoch": 2.70042194092827, "grad_norm": 13.835355758666992, "learning_rate": 3.364234361904101e-06, "loss": 0.7848366498947144, "step": 1280 }, { "epoch": 2.7046413502109705, "grad_norm": 1.945225715637207, "learning_rate": 3.350429013469164e-06, "loss": 0.9365730285644531, "step": 1282 }, { "epoch": 2.708860759493671, "grad_norm": 2.163625955581665, "learning_rate": 3.336649827800551e-06, "loss": 0.3155820071697235, "step": 1284 }, { "epoch": 2.7130801687763713, "grad_norm": 4.400462627410889, "learning_rate": 3.3228969726068928e-06, "loss": 0.49820569157600403, "step": 1286 }, { "epoch": 2.717299578059072, "grad_norm": 0.7554141879081726, "learning_rate": 3.3091706152763524e-06, "loss": 0.4683424234390259, "step": 1288 }, { "epoch": 2.721518987341772, "grad_norm": 0.437103807926178, "learning_rate": 3.295470922874583e-06, "loss": 0.5541238784790039, "step": 1290 }, { "epoch": 2.7257383966244726, "grad_norm": 1.4348374605178833, "learning_rate": 3.281798062142696e-06, "loss": 0.9304251670837402, "step": 1292 }, { "epoch": 2.7299578059071727, "grad_norm": 1.729076862335205, "learning_rate": 3.2681521994952236e-06, "loss": 0.33364760875701904, "step": 1294 }, { "epoch": 2.7341772151898733, "grad_norm": 2.3923468589782715, "learning_rate": 3.2545335010181077e-06, "loss": 0.9474711418151855, "step": 1296 }, { "epoch": 2.738396624472574, "grad_norm": 1.7852957248687744, "learning_rate": 3.2409421324666674e-06, "loss": 0.8929038047790527, "step": 1298 }, { "epoch": 2.742616033755274, "grad_norm": 1.7237015962600708, "learning_rate": 3.227378259263587e-06, "loss": 0.6056531071662903, "step": 1300 }, { "epoch": 2.7468354430379747, "grad_norm": 25.181434631347656, "learning_rate": 3.213842046496896e-06, "loss": 1.0674147605895996, "step": 1302 }, { "epoch": 2.7510548523206753, "grad_norm": 1.6333428621292114, "learning_rate": 3.200333658917969e-06, "loss": 0.4792153835296631, "step": 1304 }, { "epoch": 2.7552742616033754, "grad_norm": 2.7477095127105713, "learning_rate": 3.1868532609395165e-06, "loss": 1.003921389579773, "step": 1306 }, { "epoch": 2.759493670886076, "grad_norm": 3.8744804859161377, "learning_rate": 3.173401016633577e-06, "loss": 0.8779037594795227, "step": 1308 }, { "epoch": 2.7637130801687766, "grad_norm": 11.91277027130127, "learning_rate": 3.159977089729532e-06, "loss": 0.7732213735580444, "step": 1310 }, { "epoch": 2.7679324894514767, "grad_norm": 2.143440008163452, "learning_rate": 3.1465816436121055e-06, "loss": 0.8764097690582275, "step": 1312 }, { "epoch": 2.7721518987341773, "grad_norm": 2.330604314804077, "learning_rate": 3.1332148413193796e-06, "loss": 0.9291867017745972, "step": 1314 }, { "epoch": 2.7763713080168775, "grad_norm": 2.0408952236175537, "learning_rate": 3.1198768455408023e-06, "loss": 0.525703489780426, "step": 1316 }, { "epoch": 2.780590717299578, "grad_norm": 1.3256192207336426, "learning_rate": 3.1065678186152186e-06, "loss": 0.5235413312911987, "step": 1318 }, { "epoch": 2.7848101265822782, "grad_norm": 6.275982856750488, "learning_rate": 3.093287922528886e-06, "loss": 0.926974892616272, "step": 1320 }, { "epoch": 2.789029535864979, "grad_norm": 1.0807502269744873, "learning_rate": 3.0800373189135096e-06, "loss": 0.4855602979660034, "step": 1322 }, { "epoch": 2.7932489451476794, "grad_norm": 2.983281135559082, "learning_rate": 3.0668161690442656e-06, "loss": 0.9527076482772827, "step": 1324 }, { "epoch": 2.7974683544303796, "grad_norm": 8.031917572021484, "learning_rate": 3.0536246338378466e-06, "loss": 0.6917911171913147, "step": 1326 }, { "epoch": 2.80168776371308, "grad_norm": 6.182270050048828, "learning_rate": 3.040462873850503e-06, "loss": 0.5612431764602661, "step": 1328 }, { "epoch": 2.8059071729957807, "grad_norm": 8.575065612792969, "learning_rate": 3.027331049276085e-06, "loss": 0.9485000967979431, "step": 1330 }, { "epoch": 2.810126582278481, "grad_norm": 1.673999309539795, "learning_rate": 3.0142293199440907e-06, "loss": 0.6850672960281372, "step": 1332 }, { "epoch": 2.8143459915611815, "grad_norm": 3.2237377166748047, "learning_rate": 3.001157845317727e-06, "loss": 0.45476678013801575, "step": 1334 }, { "epoch": 2.818565400843882, "grad_norm": 0.8414680361747742, "learning_rate": 2.9881167844919683e-06, "loss": 0.5721867680549622, "step": 1336 }, { "epoch": 2.8227848101265822, "grad_norm": 1.7673283815383911, "learning_rate": 2.9751062961916146e-06, "loss": 0.7035523653030396, "step": 1338 }, { "epoch": 2.827004219409283, "grad_norm": 2.5279760360717773, "learning_rate": 2.962126538769362e-06, "loss": 0.7710987329483032, "step": 1340 }, { "epoch": 2.831223628691983, "grad_norm": 1.56592857837677, "learning_rate": 2.949177670203883e-06, "loss": 0.8627204895019531, "step": 1342 }, { "epoch": 2.8354430379746836, "grad_norm": 2.0604681968688965, "learning_rate": 2.9362598480978867e-06, "loss": 1.017736792564392, "step": 1344 }, { "epoch": 2.8396624472573837, "grad_norm": 5.791495323181152, "learning_rate": 2.9233732296762173e-06, "loss": 0.6497881412506104, "step": 1346 }, { "epoch": 2.8438818565400843, "grad_norm": 1.8422337770462036, "learning_rate": 2.9105179717839353e-06, "loss": 0.5331912040710449, "step": 1348 }, { "epoch": 2.848101265822785, "grad_norm": 2.184656858444214, "learning_rate": 2.897694230884405e-06, "loss": 0.8780800104141235, "step": 1350 }, { "epoch": 2.852320675105485, "grad_norm": 2.416750192642212, "learning_rate": 2.88490216305739e-06, "loss": 0.6759881973266602, "step": 1352 }, { "epoch": 2.8565400843881856, "grad_norm": 2.956289768218994, "learning_rate": 2.8721419239971582e-06, "loss": 0.6248071789741516, "step": 1354 }, { "epoch": 2.8607594936708862, "grad_norm": 10.1500244140625, "learning_rate": 2.8594136690105867e-06, "loss": 0.49903178215026855, "step": 1356 }, { "epoch": 2.8649789029535864, "grad_norm": 1.8450100421905518, "learning_rate": 2.846717553015268e-06, "loss": 0.9704467058181763, "step": 1358 }, { "epoch": 2.869198312236287, "grad_norm": 2.6187939643859863, "learning_rate": 2.834053730537622e-06, "loss": 0.7015703916549683, "step": 1360 }, { "epoch": 2.8734177215189876, "grad_norm": 2.2264678478240967, "learning_rate": 2.821422355711024e-06, "loss": 0.6270128488540649, "step": 1362 }, { "epoch": 2.8776371308016877, "grad_norm": 4.2144317626953125, "learning_rate": 2.8088235822739253e-06, "loss": 0.787007212638855, "step": 1364 }, { "epoch": 2.8818565400843883, "grad_norm": 35.89679718017578, "learning_rate": 2.796257563567973e-06, "loss": 0.8314931988716125, "step": 1366 }, { "epoch": 2.8860759493670884, "grad_norm": 1.8338404893875122, "learning_rate": 2.7837244525361573e-06, "loss": 0.9905785322189331, "step": 1368 }, { "epoch": 2.890295358649789, "grad_norm": 2.268563747406006, "learning_rate": 2.771224401720942e-06, "loss": 0.8372758626937866, "step": 1370 }, { "epoch": 2.894514767932489, "grad_norm": 10.391646385192871, "learning_rate": 2.7587575632624143e-06, "loss": 0.3632681965827942, "step": 1372 }, { "epoch": 2.8987341772151898, "grad_norm": 2.6048460006713867, "learning_rate": 2.7463240888964184e-06, "loss": 0.5810360908508301, "step": 1374 }, { "epoch": 2.9029535864978904, "grad_norm": 1.5397313833236694, "learning_rate": 2.733924129952727e-06, "loss": 0.9394367933273315, "step": 1376 }, { "epoch": 2.9071729957805905, "grad_norm": 5.535853385925293, "learning_rate": 2.7215578373531905e-06, "loss": 0.7054976224899292, "step": 1378 }, { "epoch": 2.911392405063291, "grad_norm": 2.1562106609344482, "learning_rate": 2.709225361609901e-06, "loss": 0.9327753782272339, "step": 1380 }, { "epoch": 2.9156118143459917, "grad_norm": 5.5289740562438965, "learning_rate": 2.6969268528233545e-06, "loss": 0.44913023710250854, "step": 1382 }, { "epoch": 2.919831223628692, "grad_norm": 4.448686122894287, "learning_rate": 2.6846624606806372e-06, "loss": 0.602470338344574, "step": 1384 }, { "epoch": 2.9240506329113924, "grad_norm": 1.980410099029541, "learning_rate": 2.6724323344535953e-06, "loss": 0.47563230991363525, "step": 1386 }, { "epoch": 2.928270042194093, "grad_norm": 1.3847795724868774, "learning_rate": 2.6602366229970137e-06, "loss": 0.836935818195343, "step": 1388 }, { "epoch": 2.932489451476793, "grad_norm": 2.2000951766967773, "learning_rate": 2.6480754747468153e-06, "loss": 0.8829624652862549, "step": 1390 }, { "epoch": 2.9367088607594938, "grad_norm": 2.444465398788452, "learning_rate": 2.635949037718246e-06, "loss": 0.49294620752334595, "step": 1392 }, { "epoch": 2.9409282700421944, "grad_norm": 2.679212808609009, "learning_rate": 2.623857459504078e-06, "loss": 0.44655460119247437, "step": 1394 }, { "epoch": 2.9451476793248945, "grad_norm": 2.4174611568450928, "learning_rate": 2.6118008872728095e-06, "loss": 0.943430483341217, "step": 1396 }, { "epoch": 2.9493670886075947, "grad_norm": 0.6074979901313782, "learning_rate": 2.5997794677668746e-06, "loss": 0.7827745676040649, "step": 1398 }, { "epoch": 2.9535864978902953, "grad_norm": 2.3790440559387207, "learning_rate": 2.587793347300861e-06, "loss": 0.8486776351928711, "step": 1400 }, { "epoch": 2.957805907172996, "grad_norm": 8.990431785583496, "learning_rate": 2.5758426717597257e-06, "loss": 0.4565354585647583, "step": 1402 }, { "epoch": 2.962025316455696, "grad_norm": 6.847982883453369, "learning_rate": 2.563927586597017e-06, "loss": 0.84642493724823, "step": 1404 }, { "epoch": 2.9662447257383966, "grad_norm": 3.296928882598877, "learning_rate": 2.552048236833109e-06, "loss": 0.809276819229126, "step": 1406 }, { "epoch": 2.970464135021097, "grad_norm": 1.1968058347702026, "learning_rate": 2.5402047670534375e-06, "loss": 0.4831066131591797, "step": 1408 }, { "epoch": 2.9746835443037973, "grad_norm": 4.178463459014893, "learning_rate": 2.528397321406731e-06, "loss": 0.7795858383178711, "step": 1410 }, { "epoch": 2.978902953586498, "grad_norm": 1.707894206047058, "learning_rate": 2.5166260436032686e-06, "loss": 0.9426555633544922, "step": 1412 }, { "epoch": 2.9831223628691985, "grad_norm": 4.879833221435547, "learning_rate": 2.504891076913121e-06, "loss": 0.8021796345710754, "step": 1414 }, { "epoch": 2.9873417721518987, "grad_norm": 2.0400021076202393, "learning_rate": 2.493192564164415e-06, "loss": 0.7935506701469421, "step": 1416 }, { "epoch": 2.9915611814345993, "grad_norm": 1.5087887048721313, "learning_rate": 2.4815306477415843e-06, "loss": 0.8384319543838501, "step": 1418 }, { "epoch": 2.9957805907173, "grad_norm": 5.154513359069824, "learning_rate": 2.469905469583648e-06, "loss": 0.9012800455093384, "step": 1420 }, { "epoch": 3.0, "grad_norm": 3.095649480819702, "learning_rate": 2.4583171711824767e-06, "loss": 0.18656273186206818, "step": 1422 }, { "epoch": 3.0042194092827006, "grad_norm": 1.5715686082839966, "learning_rate": 2.4467658935810738e-06, "loss": 0.48583561182022095, "step": 1424 }, { "epoch": 3.0084388185654007, "grad_norm": 7.386166572570801, "learning_rate": 2.43525177737185e-06, "loss": 0.4914981722831726, "step": 1426 }, { "epoch": 3.0126582278481013, "grad_norm": 5.9179887771606445, "learning_rate": 2.423774962694926e-06, "loss": 0.5489182472229004, "step": 1428 }, { "epoch": 3.0168776371308015, "grad_norm": 2.4354171752929688, "learning_rate": 2.4123355892364162e-06, "loss": 0.22447283565998077, "step": 1430 }, { "epoch": 3.021097046413502, "grad_norm": 1.6375222206115723, "learning_rate": 2.4009337962267354e-06, "loss": 0.7427164316177368, "step": 1432 }, { "epoch": 3.0253164556962027, "grad_norm": 2.2184720039367676, "learning_rate": 2.3895697224388944e-06, "loss": 0.8503177165985107, "step": 1434 }, { "epoch": 3.029535864978903, "grad_norm": 2.904543399810791, "learning_rate": 2.3782435061868237e-06, "loss": 0.8317616581916809, "step": 1436 }, { "epoch": 3.0337552742616034, "grad_norm": 3.2878971099853516, "learning_rate": 2.366955285323682e-06, "loss": 0.38762444257736206, "step": 1438 }, { "epoch": 3.037974683544304, "grad_norm": 5.636815071105957, "learning_rate": 2.3557051972401765e-06, "loss": 0.70168137550354, "step": 1440 }, { "epoch": 3.042194092827004, "grad_norm": 0.48707684874534607, "learning_rate": 2.3444933788629005e-06, "loss": 0.5525423884391785, "step": 1442 }, { "epoch": 3.0464135021097047, "grad_norm": 3.361435651779175, "learning_rate": 2.333319966652656e-06, "loss": 0.7323377728462219, "step": 1444 }, { "epoch": 3.050632911392405, "grad_norm": 4.475218296051025, "learning_rate": 2.322185096602801e-06, "loss": 0.7781831622123718, "step": 1446 }, { "epoch": 3.0548523206751055, "grad_norm": 6.384256362915039, "learning_rate": 2.311088904237586e-06, "loss": 0.5085391998291016, "step": 1448 }, { "epoch": 3.059071729957806, "grad_norm": 5.018730163574219, "learning_rate": 2.300031524610514e-06, "loss": 0.6571500301361084, "step": 1450 }, { "epoch": 3.0632911392405062, "grad_norm": 4.029062271118164, "learning_rate": 2.2890130923026903e-06, "loss": 0.7413759231567383, "step": 1452 }, { "epoch": 3.067510548523207, "grad_norm": 2.8714632987976074, "learning_rate": 2.278033741421187e-06, "loss": 0.5917239189147949, "step": 1454 }, { "epoch": 3.071729957805907, "grad_norm": 5.01410436630249, "learning_rate": 2.2670936055974075e-06, "loss": 0.47011274099349976, "step": 1456 }, { "epoch": 3.0759493670886076, "grad_norm": 2.2328875064849854, "learning_rate": 2.256192817985465e-06, "loss": 0.5652891397476196, "step": 1458 }, { "epoch": 3.080168776371308, "grad_norm": 5.5734333992004395, "learning_rate": 2.2453315112605604e-06, "loss": 0.46141350269317627, "step": 1460 }, { "epoch": 3.0843881856540083, "grad_norm": 1.858008623123169, "learning_rate": 2.2345098176173624e-06, "loss": 0.6961233615875244, "step": 1462 }, { "epoch": 3.088607594936709, "grad_norm": 1.5827645063400269, "learning_rate": 2.2237278687684065e-06, "loss": 0.7743927836418152, "step": 1464 }, { "epoch": 3.0928270042194095, "grad_norm": 1.5431591272354126, "learning_rate": 2.212985795942486e-06, "loss": 0.7057615518569946, "step": 1466 }, { "epoch": 3.0970464135021096, "grad_norm": 4.28744649887085, "learning_rate": 2.20228372988306e-06, "loss": 0.4988563060760498, "step": 1468 }, { "epoch": 3.1012658227848102, "grad_norm": 4.302311897277832, "learning_rate": 2.1916218008466524e-06, "loss": 0.12310986965894699, "step": 1470 }, { "epoch": 3.1054852320675104, "grad_norm": 4.386756420135498, "learning_rate": 2.18100013860128e-06, "loss": 1.1690139770507812, "step": 1472 }, { "epoch": 3.109704641350211, "grad_norm": 0.4702922999858856, "learning_rate": 2.170418872424863e-06, "loss": 0.4561275243759155, "step": 1474 }, { "epoch": 3.1139240506329116, "grad_norm": 1.970653772354126, "learning_rate": 2.1598781311036563e-06, "loss": 0.7653858661651611, "step": 1476 }, { "epoch": 3.1181434599156117, "grad_norm": 3.0102148056030273, "learning_rate": 2.149378042930676e-06, "loss": 0.8254115581512451, "step": 1478 }, { "epoch": 3.1223628691983123, "grad_norm": 2.548327922821045, "learning_rate": 2.138918735704148e-06, "loss": 0.7556872367858887, "step": 1480 }, { "epoch": 3.1265822784810124, "grad_norm": 2.627345085144043, "learning_rate": 2.1285003367259445e-06, "loss": 0.8318365812301636, "step": 1482 }, { "epoch": 3.130801687763713, "grad_norm": 4.124703407287598, "learning_rate": 2.1181229728000353e-06, "loss": 0.7645995616912842, "step": 1484 }, { "epoch": 3.1350210970464136, "grad_norm": 2.083620071411133, "learning_rate": 2.1077867702309482e-06, "loss": 0.5717896223068237, "step": 1486 }, { "epoch": 3.1392405063291138, "grad_norm": 2.0459728240966797, "learning_rate": 2.0974918548222294e-06, "loss": 0.48427456617355347, "step": 1488 }, { "epoch": 3.1434599156118144, "grad_norm": 3.07755970954895, "learning_rate": 2.0872383518749147e-06, "loss": 0.754004955291748, "step": 1490 }, { "epoch": 3.147679324894515, "grad_norm": 2.7117910385131836, "learning_rate": 2.077026386185996e-06, "loss": 0.5141333937644958, "step": 1492 }, { "epoch": 3.151898734177215, "grad_norm": 28.907352447509766, "learning_rate": 2.0668560820469152e-06, "loss": 0.5901731252670288, "step": 1494 }, { "epoch": 3.1561181434599157, "grad_norm": 1.6929947137832642, "learning_rate": 2.0567275632420412e-06, "loss": 0.6309336423873901, "step": 1496 }, { "epoch": 3.160337552742616, "grad_norm": 0.4774731993675232, "learning_rate": 2.0466409530471702e-06, "loss": 0.3961719572544098, "step": 1498 }, { "epoch": 3.1645569620253164, "grad_norm": 1.9566251039505005, "learning_rate": 2.0365963742280178e-06, "loss": 0.3575551509857178, "step": 1500 }, { "epoch": 3.168776371308017, "grad_norm": 2.0274641513824463, "learning_rate": 2.0265939490387325e-06, "loss": 0.754025399684906, "step": 1502 }, { "epoch": 3.172995780590717, "grad_norm": 2.6568617820739746, "learning_rate": 2.016633799220403e-06, "loss": 0.6795116066932678, "step": 1504 }, { "epoch": 3.1772151898734178, "grad_norm": 2.5415151119232178, "learning_rate": 2.00671604599958e-06, "loss": 0.6489322185516357, "step": 1506 }, { "epoch": 3.181434599156118, "grad_norm": 6.573331356048584, "learning_rate": 1.9968408100867947e-06, "loss": 0.8414944410324097, "step": 1508 }, { "epoch": 3.1856540084388185, "grad_norm": 2.2244110107421875, "learning_rate": 1.9870082116750954e-06, "loss": 0.7260029315948486, "step": 1510 }, { "epoch": 3.189873417721519, "grad_norm": 1.565050482749939, "learning_rate": 1.9772183704385846e-06, "loss": 0.15671756863594055, "step": 1512 }, { "epoch": 3.1940928270042193, "grad_norm": 2.8658103942871094, "learning_rate": 1.967471405530956e-06, "loss": 0.7213826179504395, "step": 1514 }, { "epoch": 3.19831223628692, "grad_norm": 0.4529423415660858, "learning_rate": 1.957767435584053e-06, "loss": 0.49789148569107056, "step": 1516 }, { "epoch": 3.2025316455696204, "grad_norm": 3.403698682785034, "learning_rate": 1.948106578706419e-06, "loss": 0.7171260118484497, "step": 1518 }, { "epoch": 3.2067510548523206, "grad_norm": 2.606841802597046, "learning_rate": 1.938488952481863e-06, "loss": 0.6881486773490906, "step": 1520 }, { "epoch": 3.210970464135021, "grad_norm": 5.2538743019104, "learning_rate": 1.928914673968021e-06, "loss": 0.2945752441883087, "step": 1522 }, { "epoch": 3.2151898734177213, "grad_norm": 2.842679023742676, "learning_rate": 1.9193838596949454e-06, "loss": 0.5661529302597046, "step": 1524 }, { "epoch": 3.219409282700422, "grad_norm": 2.0859315395355225, "learning_rate": 1.9098966256636724e-06, "loss": 0.6757782697677612, "step": 1526 }, { "epoch": 3.2236286919831225, "grad_norm": 0.6140679717063904, "learning_rate": 1.9004530873448218e-06, "loss": 0.2596287429332733, "step": 1528 }, { "epoch": 3.2278481012658227, "grad_norm": 5.293236255645752, "learning_rate": 1.8910533596771788e-06, "loss": 0.580342173576355, "step": 1530 }, { "epoch": 3.2320675105485233, "grad_norm": 0.5198884606361389, "learning_rate": 1.8816975570663077e-06, "loss": 0.14968807995319366, "step": 1532 }, { "epoch": 3.2362869198312234, "grad_norm": 4.883198261260986, "learning_rate": 1.8723857933831535e-06, "loss": 0.6340221166610718, "step": 1534 }, { "epoch": 3.240506329113924, "grad_norm": 3.047835111618042, "learning_rate": 1.8631181819626542e-06, "loss": 0.7310760021209717, "step": 1536 }, { "epoch": 3.2447257383966246, "grad_norm": 1.4122538566589355, "learning_rate": 1.8538948356023647e-06, "loss": 0.5707433223724365, "step": 1538 }, { "epoch": 3.2489451476793247, "grad_norm": 5.446000099182129, "learning_rate": 1.8447158665610842e-06, "loss": 0.5451850891113281, "step": 1540 }, { "epoch": 3.2531645569620253, "grad_norm": 8.557243347167969, "learning_rate": 1.8355813865574884e-06, "loss": 0.5123834609985352, "step": 1542 }, { "epoch": 3.257383966244726, "grad_norm": 19.8990478515625, "learning_rate": 1.8264915067687666e-06, "loss": 0.4869286119937897, "step": 1544 }, { "epoch": 3.261603375527426, "grad_norm": 4.238598823547363, "learning_rate": 1.8174463378292762e-06, "loss": 0.34045785665512085, "step": 1546 }, { "epoch": 3.2658227848101267, "grad_norm": 3.0350265502929688, "learning_rate": 1.808445989829189e-06, "loss": 0.7386662364006042, "step": 1548 }, { "epoch": 3.270042194092827, "grad_norm": 13.510923385620117, "learning_rate": 1.7994905723131567e-06, "loss": 0.2664933502674103, "step": 1550 }, { "epoch": 3.2742616033755274, "grad_norm": 1.474900484085083, "learning_rate": 1.7905801942789711e-06, "loss": 0.2093355655670166, "step": 1552 }, { "epoch": 3.278481012658228, "grad_norm": 5.170738697052002, "learning_rate": 1.781714964176245e-06, "loss": 0.31058719754219055, "step": 1554 }, { "epoch": 3.282700421940928, "grad_norm": 2.201634407043457, "learning_rate": 1.7728949899050879e-06, "loss": 0.7703303694725037, "step": 1556 }, { "epoch": 3.2869198312236287, "grad_norm": 1.209177851676941, "learning_rate": 1.7641203788147913e-06, "loss": 0.7063621282577515, "step": 1558 }, { "epoch": 3.291139240506329, "grad_norm": 2.3021647930145264, "learning_rate": 1.7553912377025251e-06, "loss": 0.5122189521789551, "step": 1560 }, { "epoch": 3.2953586497890295, "grad_norm": 5.13539981842041, "learning_rate": 1.7467076728120416e-06, "loss": 0.49912789463996887, "step": 1562 }, { "epoch": 3.29957805907173, "grad_norm": 5.139153480529785, "learning_rate": 1.7380697898323707e-06, "loss": 0.6513366103172302, "step": 1564 }, { "epoch": 3.3037974683544302, "grad_norm": 4.167728900909424, "learning_rate": 1.7294776938965443e-06, "loss": 0.5724246501922607, "step": 1566 }, { "epoch": 3.308016877637131, "grad_norm": 0.7744225859642029, "learning_rate": 1.7209314895803132e-06, "loss": 0.5291566848754883, "step": 1568 }, { "epoch": 3.3122362869198314, "grad_norm": 3.2236380577087402, "learning_rate": 1.7124312809008736e-06, "loss": 0.4096415042877197, "step": 1570 }, { "epoch": 3.3164556962025316, "grad_norm": 2.9624433517456055, "learning_rate": 1.703977171315599e-06, "loss": 0.4044237434864044, "step": 1572 }, { "epoch": 3.320675105485232, "grad_norm": 5.803339004516602, "learning_rate": 1.6955692637207883e-06, "loss": 0.7344896793365479, "step": 1574 }, { "epoch": 3.3248945147679323, "grad_norm": 2.9890189170837402, "learning_rate": 1.6872076604504053e-06, "loss": 0.5600881576538086, "step": 1576 }, { "epoch": 3.329113924050633, "grad_norm": 1.7071126699447632, "learning_rate": 1.6788924632748383e-06, "loss": 0.6768798828125, "step": 1578 }, { "epoch": 3.3333333333333335, "grad_norm": 3.00465989112854, "learning_rate": 1.6706237733996578e-06, "loss": 0.4823209047317505, "step": 1580 }, { "epoch": 3.3375527426160336, "grad_norm": 5.131996154785156, "learning_rate": 1.6624016914643882e-06, "loss": 0.4159541130065918, "step": 1582 }, { "epoch": 3.3417721518987342, "grad_norm": 5.680737018585205, "learning_rate": 1.6542263175412827e-06, "loss": 0.5741168260574341, "step": 1584 }, { "epoch": 3.3459915611814344, "grad_norm": 6.699526786804199, "learning_rate": 1.6460977511340993e-06, "loss": 0.4687027931213379, "step": 1586 }, { "epoch": 3.350210970464135, "grad_norm": 2.526592254638672, "learning_rate": 1.638016091176899e-06, "loss": 0.3336607813835144, "step": 1588 }, { "epoch": 3.3544303797468356, "grad_norm": 2.043327808380127, "learning_rate": 1.6299814360328353e-06, "loss": 0.764235258102417, "step": 1590 }, { "epoch": 3.3586497890295357, "grad_norm": 2.18218731880188, "learning_rate": 1.6219938834929594e-06, "loss": 0.7268835306167603, "step": 1592 }, { "epoch": 3.3628691983122363, "grad_norm": 0.5134976506233215, "learning_rate": 1.6140535307750272e-06, "loss": 0.35852643847465515, "step": 1594 }, { "epoch": 3.367088607594937, "grad_norm": 24.86785316467285, "learning_rate": 1.6061604745223194e-06, "loss": 0.3590257465839386, "step": 1596 }, { "epoch": 3.371308016877637, "grad_norm": 1.6766605377197266, "learning_rate": 1.598314810802466e-06, "loss": 0.3237045109272003, "step": 1598 }, { "epoch": 3.3755274261603376, "grad_norm": 3.1390042304992676, "learning_rate": 1.5905166351062723e-06, "loss": 0.45073699951171875, "step": 1600 }, { "epoch": 3.379746835443038, "grad_norm": 2.2565488815307617, "learning_rate": 1.5827660423465601e-06, "loss": 0.4386592209339142, "step": 1602 }, { "epoch": 3.3839662447257384, "grad_norm": 0.4079744219779968, "learning_rate": 1.5750631268570112e-06, "loss": 0.44573116302490234, "step": 1604 }, { "epoch": 3.388185654008439, "grad_norm": 2.657660961151123, "learning_rate": 1.5674079823910226e-06, "loss": 1.0017364025115967, "step": 1606 }, { "epoch": 3.392405063291139, "grad_norm": 2.0531551837921143, "learning_rate": 1.5598007021205608e-06, "loss": 0.3865770101547241, "step": 1608 }, { "epoch": 3.3966244725738397, "grad_norm": 2.5964906215667725, "learning_rate": 1.552241378635027e-06, "loss": 0.39072859287261963, "step": 1610 }, { "epoch": 3.40084388185654, "grad_norm": 1.6634749174118042, "learning_rate": 1.5447301039401378e-06, "loss": 0.703665018081665, "step": 1612 }, { "epoch": 3.4050632911392404, "grad_norm": 1.3998709917068481, "learning_rate": 1.5372669694567975e-06, "loss": 0.14945901930332184, "step": 1614 }, { "epoch": 3.409282700421941, "grad_norm": 3.6185266971588135, "learning_rate": 1.5298520660199884e-06, "loss": 0.6984498500823975, "step": 1616 }, { "epoch": 3.413502109704641, "grad_norm": 1.7182868719100952, "learning_rate": 1.5224854838776655e-06, "loss": 0.8245247602462769, "step": 1618 }, { "epoch": 3.4177215189873418, "grad_norm": 2.6827356815338135, "learning_rate": 1.5151673126896582e-06, "loss": 0.7499665021896362, "step": 1620 }, { "epoch": 3.4219409282700424, "grad_norm": 9.910405158996582, "learning_rate": 1.5078976415265792e-06, "loss": 0.3542504608631134, "step": 1622 }, { "epoch": 3.4261603375527425, "grad_norm": 5.315154552459717, "learning_rate": 1.5006765588687364e-06, "loss": 0.2197137326002121, "step": 1624 }, { "epoch": 3.430379746835443, "grad_norm": 7.568133354187012, "learning_rate": 1.4935041526050642e-06, "loss": 0.18559637665748596, "step": 1626 }, { "epoch": 3.4345991561181437, "grad_norm": 2.164938449859619, "learning_rate": 1.4863805100320446e-06, "loss": 0.8108969926834106, "step": 1628 }, { "epoch": 3.438818565400844, "grad_norm": 3.3237814903259277, "learning_rate": 1.4793057178526535e-06, "loss": 0.2031504213809967, "step": 1630 }, { "epoch": 3.4430379746835444, "grad_norm": 2.4737513065338135, "learning_rate": 1.4722798621752955e-06, "loss": 0.8397033214569092, "step": 1632 }, { "epoch": 3.4472573839662446, "grad_norm": 0.7437028884887695, "learning_rate": 1.4653030285127655e-06, "loss": 0.44248634576797485, "step": 1634 }, { "epoch": 3.451476793248945, "grad_norm": 5.749112606048584, "learning_rate": 1.458375301781204e-06, "loss": 0.7306268215179443, "step": 1636 }, { "epoch": 3.4556962025316453, "grad_norm": 3.8382222652435303, "learning_rate": 1.4514967662990595e-06, "loss": 0.9104118347167969, "step": 1638 }, { "epoch": 3.459915611814346, "grad_norm": 1.779197335243225, "learning_rate": 1.4446675057860693e-06, "loss": 0.7820116281509399, "step": 1640 }, { "epoch": 3.4641350210970465, "grad_norm": 4.873284816741943, "learning_rate": 1.4378876033622362e-06, "loss": 0.7452319860458374, "step": 1642 }, { "epoch": 3.4683544303797467, "grad_norm": 1.5181903839111328, "learning_rate": 1.4311571415468201e-06, "loss": 0.098818838596344, "step": 1644 }, { "epoch": 3.4725738396624473, "grad_norm": 1.8554273843765259, "learning_rate": 1.4244762022573269e-06, "loss": 0.5109513401985168, "step": 1646 }, { "epoch": 3.476793248945148, "grad_norm": 1.810754418373108, "learning_rate": 1.4178448668085198e-06, "loss": 0.5539188385009766, "step": 1648 }, { "epoch": 3.481012658227848, "grad_norm": 2.064720392227173, "learning_rate": 1.4112632159114253e-06, "loss": 0.34748756885528564, "step": 1650 }, { "epoch": 3.4852320675105486, "grad_norm": 2.179349899291992, "learning_rate": 1.4047313296723512e-06, "loss": 0.6908297538757324, "step": 1652 }, { "epoch": 3.489451476793249, "grad_norm": 0.3789224922657013, "learning_rate": 1.3982492875919098e-06, "loss": 0.3522850275039673, "step": 1654 }, { "epoch": 3.4936708860759493, "grad_norm": 0.43968817591667175, "learning_rate": 1.3918171685640555e-06, "loss": 0.5142955780029297, "step": 1656 }, { "epoch": 3.49789029535865, "grad_norm": 23.7955265045166, "learning_rate": 1.3854350508751193e-06, "loss": 0.6224573850631714, "step": 1658 }, { "epoch": 3.50210970464135, "grad_norm": 2.28059720993042, "learning_rate": 1.379103012202859e-06, "loss": 0.7226071357727051, "step": 1660 }, { "epoch": 3.5063291139240507, "grad_norm": 6.710467338562012, "learning_rate": 1.3728211296155116e-06, "loss": 0.732511043548584, "step": 1662 }, { "epoch": 3.510548523206751, "grad_norm": 6.476405143737793, "learning_rate": 1.3665894795708585e-06, "loss": 0.42246943712234497, "step": 1664 }, { "epoch": 3.5147679324894514, "grad_norm": 2.671142816543579, "learning_rate": 1.3604081379152916e-06, "loss": 0.8179053068161011, "step": 1666 }, { "epoch": 3.518987341772152, "grad_norm": 3.9176056385040283, "learning_rate": 1.3542771798828917e-06, "loss": 0.3286226987838745, "step": 1668 }, { "epoch": 3.523206751054852, "grad_norm": 3.883362054824829, "learning_rate": 1.3481966800945118e-06, "loss": 0.7940263748168945, "step": 1670 }, { "epoch": 3.5274261603375527, "grad_norm": 5.184436321258545, "learning_rate": 1.342166712556871e-06, "loss": 0.31407248973846436, "step": 1672 }, { "epoch": 3.5316455696202533, "grad_norm": 2.035196304321289, "learning_rate": 1.3361873506616527e-06, "loss": 0.49526581168174744, "step": 1674 }, { "epoch": 3.5358649789029535, "grad_norm": 5.8331122398376465, "learning_rate": 1.330258667184609e-06, "loss": 0.5292542576789856, "step": 1676 }, { "epoch": 3.540084388185654, "grad_norm": 7.968428134918213, "learning_rate": 1.3243807342846784e-06, "loss": 0.5500727891921997, "step": 1678 }, { "epoch": 3.5443037974683547, "grad_norm": 2.3754916191101074, "learning_rate": 1.3185536235031075e-06, "loss": 0.720923662185669, "step": 1680 }, { "epoch": 3.548523206751055, "grad_norm": 1.8404473066329956, "learning_rate": 1.3127774057625764e-06, "loss": 0.4998755156993866, "step": 1682 }, { "epoch": 3.5527426160337554, "grad_norm": 5.628260612487793, "learning_rate": 1.307052151366339e-06, "loss": 0.6699142456054688, "step": 1684 }, { "epoch": 3.5569620253164556, "grad_norm": 8.187625885009766, "learning_rate": 1.3013779299973665e-06, "loss": 0.19896043837070465, "step": 1686 }, { "epoch": 3.561181434599156, "grad_norm": 1.2670155763626099, "learning_rate": 1.2957548107174997e-06, "loss": 0.3843368589878082, "step": 1688 }, { "epoch": 3.5654008438818563, "grad_norm": 2.2000648975372314, "learning_rate": 1.2901828619666053e-06, "loss": 0.7845232486724854, "step": 1690 }, { "epoch": 3.569620253164557, "grad_norm": 7.603072643280029, "learning_rate": 1.2846621515617488e-06, "loss": 0.1644367277622223, "step": 1692 }, { "epoch": 3.5738396624472575, "grad_norm": 0.34018248319625854, "learning_rate": 1.2791927466963641e-06, "loss": 0.41313183307647705, "step": 1694 }, { "epoch": 3.5780590717299576, "grad_norm": 4.050682067871094, "learning_rate": 1.2737747139394373e-06, "loss": 0.2239256352186203, "step": 1696 }, { "epoch": 3.5822784810126582, "grad_norm": 3.661517381668091, "learning_rate": 1.2684081192346964e-06, "loss": 0.5216777920722961, "step": 1698 }, { "epoch": 3.586497890295359, "grad_norm": 2.3448452949523926, "learning_rate": 1.263093027899809e-06, "loss": 0.41478461027145386, "step": 1700 }, { "epoch": 3.590717299578059, "grad_norm": 2.0525033473968506, "learning_rate": 1.257829504625587e-06, "loss": 0.36936336755752563, "step": 1702 }, { "epoch": 3.5949367088607596, "grad_norm": 3.7388837337493896, "learning_rate": 1.2526176134752009e-06, "loss": 0.8695687055587769, "step": 1704 }, { "epoch": 3.59915611814346, "grad_norm": 1.8299850225448608, "learning_rate": 1.2474574178833945e-06, "loss": 0.4967671036720276, "step": 1706 }, { "epoch": 3.6033755274261603, "grad_norm": 5.3748931884765625, "learning_rate": 1.2423489806557212e-06, "loss": 0.6329807043075562, "step": 1708 }, { "epoch": 3.607594936708861, "grad_norm": 0.5723101496696472, "learning_rate": 1.2372923639677734e-06, "loss": 0.35278546810150146, "step": 1710 }, { "epoch": 3.611814345991561, "grad_norm": 3.411470413208008, "learning_rate": 1.2322876293644264e-06, "loss": 0.6741088032722473, "step": 1712 }, { "epoch": 3.6160337552742616, "grad_norm": 5.75834321975708, "learning_rate": 1.227334837759092e-06, "loss": 0.8515325784683228, "step": 1714 }, { "epoch": 3.620253164556962, "grad_norm": 3.3537862300872803, "learning_rate": 1.2224340494329754e-06, "loss": 0.4649980664253235, "step": 1716 }, { "epoch": 3.6244725738396624, "grad_norm": 2.4751524925231934, "learning_rate": 1.217585324034343e-06, "loss": 0.27417871356010437, "step": 1718 }, { "epoch": 3.628691983122363, "grad_norm": 7.3662614822387695, "learning_rate": 1.212788720577791e-06, "loss": 0.24572905898094177, "step": 1720 }, { "epoch": 3.632911392405063, "grad_norm": 2.8223509788513184, "learning_rate": 1.2080442974435357e-06, "loss": 0.7377593517303467, "step": 1722 }, { "epoch": 3.6371308016877637, "grad_norm": 4.1688032150268555, "learning_rate": 1.2033521123766964e-06, "loss": 0.2896050214767456, "step": 1724 }, { "epoch": 3.6413502109704643, "grad_norm": 6.984439849853516, "learning_rate": 1.1987122224865958e-06, "loss": 0.21551871299743652, "step": 1726 }, { "epoch": 3.6455696202531644, "grad_norm": 2.7583324909210205, "learning_rate": 1.1941246842460608e-06, "loss": 0.69916832447052, "step": 1728 }, { "epoch": 3.649789029535865, "grad_norm": 3.7309629917144775, "learning_rate": 1.1895895534907422e-06, "loss": 0.16017168760299683, "step": 1730 }, { "epoch": 3.6540084388185656, "grad_norm": 5.507340908050537, "learning_rate": 1.1851068854184285e-06, "loss": 0.7010379433631897, "step": 1732 }, { "epoch": 3.6582278481012658, "grad_norm": 7.017323017120361, "learning_rate": 1.1806767345883786e-06, "loss": 0.17451146245002747, "step": 1734 }, { "epoch": 3.6624472573839664, "grad_norm": 3.1779277324676514, "learning_rate": 1.1762991549206526e-06, "loss": 0.2694070041179657, "step": 1736 }, { "epoch": 3.6666666666666665, "grad_norm": 3.097628116607666, "learning_rate": 1.1719741996954616e-06, "loss": 0.6506730318069458, "step": 1738 }, { "epoch": 3.670886075949367, "grad_norm": 3.804108142852783, "learning_rate": 1.1677019215525157e-06, "loss": 0.32571983337402344, "step": 1740 }, { "epoch": 3.6751054852320673, "grad_norm": 1.4632868766784668, "learning_rate": 1.1634823724903831e-06, "loss": 0.7802934646606445, "step": 1742 }, { "epoch": 3.679324894514768, "grad_norm": 2.942312002182007, "learning_rate": 1.1593156038658585e-06, "loss": 0.3937864303588867, "step": 1744 }, { "epoch": 3.6835443037974684, "grad_norm": 3.0023696422576904, "learning_rate": 1.155201666393338e-06, "loss": 0.4511567950248718, "step": 1746 }, { "epoch": 3.6877637130801686, "grad_norm": 2.039228677749634, "learning_rate": 1.1511406101442017e-06, "loss": 0.798840343952179, "step": 1748 }, { "epoch": 3.691983122362869, "grad_norm": 9.033023834228516, "learning_rate": 1.1471324845462025e-06, "loss": 0.5909087657928467, "step": 1750 }, { "epoch": 3.6962025316455698, "grad_norm": 2.3524653911590576, "learning_rate": 1.1431773383828677e-06, "loss": 0.6905038356781006, "step": 1752 }, { "epoch": 3.70042194092827, "grad_norm": 2.6000936031341553, "learning_rate": 1.139275219792902e-06, "loss": 0.8412216901779175, "step": 1754 }, { "epoch": 3.7046413502109705, "grad_norm": 3.3897039890289307, "learning_rate": 1.1354261762696058e-06, "loss": 0.6651852130889893, "step": 1756 }, { "epoch": 3.708860759493671, "grad_norm": 4.865018844604492, "learning_rate": 1.131630254660291e-06, "loss": 0.5381301641464233, "step": 1758 }, { "epoch": 3.7130801687763713, "grad_norm": 4.956268787384033, "learning_rate": 1.1278875011657168e-06, "loss": 0.5200679302215576, "step": 1760 }, { "epoch": 3.717299578059072, "grad_norm": 5.0099687576293945, "learning_rate": 1.1241979613395246e-06, "loss": 0.2321537584066391, "step": 1762 }, { "epoch": 3.721518987341772, "grad_norm": 13.689009666442871, "learning_rate": 1.120561680087682e-06, "loss": 0.400237113237381, "step": 1764 }, { "epoch": 3.7257383966244726, "grad_norm": 2.460145950317383, "learning_rate": 1.1169787016679412e-06, "loss": 0.7217031121253967, "step": 1766 }, { "epoch": 3.7299578059071727, "grad_norm": 7.271668434143066, "learning_rate": 1.1134490696892955e-06, "loss": 0.4372742176055908, "step": 1768 }, { "epoch": 3.7341772151898733, "grad_norm": 2.220688581466675, "learning_rate": 1.1099728271114502e-06, "loss": 0.49784523248672485, "step": 1770 }, { "epoch": 3.738396624472574, "grad_norm": 2.4671876430511475, "learning_rate": 1.1065500162442996e-06, "loss": 0.6265417337417603, "step": 1772 }, { "epoch": 3.742616033755274, "grad_norm": 0.7870125770568848, "learning_rate": 1.1031806787474133e-06, "loss": 0.10117629170417786, "step": 1774 }, { "epoch": 3.7468354430379747, "grad_norm": 1.3312100172042847, "learning_rate": 1.0998648556295273e-06, "loss": 0.3768368363380432, "step": 1776 }, { "epoch": 3.7510548523206753, "grad_norm": 1.4662823677062988, "learning_rate": 1.0966025872480462e-06, "loss": 0.6424307823181152, "step": 1778 }, { "epoch": 3.7552742616033754, "grad_norm": 2.378920555114746, "learning_rate": 1.0933939133085506e-06, "loss": 0.6810441017150879, "step": 1780 }, { "epoch": 3.759493670886076, "grad_norm": 1.6849637031555176, "learning_rate": 1.090238872864316e-06, "loss": 0.7406947612762451, "step": 1782 }, { "epoch": 3.7637130801687766, "grad_norm": 1.9629346132278442, "learning_rate": 1.0871375043158357e-06, "loss": 0.638360857963562, "step": 1784 }, { "epoch": 3.7679324894514767, "grad_norm": 2.466979503631592, "learning_rate": 1.084089845410352e-06, "loss": 0.7534542083740234, "step": 1786 }, { "epoch": 3.7721518987341773, "grad_norm": 5.9140448570251465, "learning_rate": 1.081095933241402e-06, "loss": 0.10254526138305664, "step": 1788 }, { "epoch": 3.7763713080168775, "grad_norm": 2.441310405731201, "learning_rate": 1.078155804248362e-06, "loss": 0.35849353671073914, "step": 1790 }, { "epoch": 3.780590717299578, "grad_norm": 2.6122334003448486, "learning_rate": 1.0752694942160019e-06, "loss": 0.6726478338241577, "step": 1792 }, { "epoch": 3.7848101265822782, "grad_norm": 3.709134340286255, "learning_rate": 1.0724370382740567e-06, "loss": 0.49919867515563965, "step": 1794 }, { "epoch": 3.789029535864979, "grad_norm": 6.428011417388916, "learning_rate": 1.0696584708967913e-06, "loss": 0.6923050284385681, "step": 1796 }, { "epoch": 3.7932489451476794, "grad_norm": 4.874377250671387, "learning_rate": 1.0669338259025872e-06, "loss": 0.6729787588119507, "step": 1798 }, { "epoch": 3.7974683544303796, "grad_norm": 3.9241809844970703, "learning_rate": 1.0642631364535258e-06, "loss": 0.6629925966262817, "step": 1800 }, { "epoch": 3.80168776371308, "grad_norm": 2.5329127311706543, "learning_rate": 1.0616464350549887e-06, "loss": 0.8236969113349915, "step": 1802 }, { "epoch": 3.8059071729957807, "grad_norm": 1.856214165687561, "learning_rate": 1.0590837535552602e-06, "loss": 0.42748022079467773, "step": 1804 }, { "epoch": 3.810126582278481, "grad_norm": 5.678967475891113, "learning_rate": 1.0565751231451391e-06, "loss": 0.07123240828514099, "step": 1806 }, { "epoch": 3.8143459915611815, "grad_norm": 43.45896911621094, "learning_rate": 1.05412057435756e-06, "loss": 0.6246628761291504, "step": 1808 }, { "epoch": 3.818565400843882, "grad_norm": 2.206404447555542, "learning_rate": 1.0517201370672234e-06, "loss": 0.8135085105895996, "step": 1810 }, { "epoch": 3.8227848101265822, "grad_norm": 4.114138603210449, "learning_rate": 1.0493738404902271e-06, "loss": 0.38385212421417236, "step": 1812 }, { "epoch": 3.827004219409283, "grad_norm": 4.388727188110352, "learning_rate": 1.0470817131837167e-06, "loss": 0.8152976036071777, "step": 1814 }, { "epoch": 3.831223628691983, "grad_norm": 2.508357286453247, "learning_rate": 1.0448437830455336e-06, "loss": 0.7808729410171509, "step": 1816 }, { "epoch": 3.8354430379746836, "grad_norm": 3.590165138244629, "learning_rate": 1.042660077313877e-06, "loss": 0.6491972208023071, "step": 1818 }, { "epoch": 3.8396624472573837, "grad_norm": 3.099669933319092, "learning_rate": 1.0405306225669729e-06, "loss": 0.4528687000274658, "step": 1820 }, { "epoch": 3.8438818565400843, "grad_norm": 2.1718971729278564, "learning_rate": 1.0384554447227493e-06, "loss": 0.7329453229904175, "step": 1822 }, { "epoch": 3.848101265822785, "grad_norm": 3.457826614379883, "learning_rate": 1.0364345690385225e-06, "loss": 0.44147783517837524, "step": 1824 }, { "epoch": 3.852320675105485, "grad_norm": 3.973973035812378, "learning_rate": 1.0344680201106878e-06, "loss": 0.7001845836639404, "step": 1826 }, { "epoch": 3.8565400843881856, "grad_norm": 4.499375820159912, "learning_rate": 1.0325558218744205e-06, "loss": 0.7414108514785767, "step": 1828 }, { "epoch": 3.8607594936708862, "grad_norm": 2.5253515243530273, "learning_rate": 1.0306979976033873e-06, "loss": 0.6885861158370972, "step": 1830 }, { "epoch": 3.8649789029535864, "grad_norm": 8.046545028686523, "learning_rate": 1.0288945699094583e-06, "loss": 0.17440387606620789, "step": 1832 }, { "epoch": 3.869198312236287, "grad_norm": 1.8448333740234375, "learning_rate": 1.0271455607424356e-06, "loss": 0.47151702642440796, "step": 1834 }, { "epoch": 3.8734177215189876, "grad_norm": 8.308198928833008, "learning_rate": 1.0254509913897852e-06, "loss": 0.5803446769714355, "step": 1836 }, { "epoch": 3.8776371308016877, "grad_norm": 10.151689529418945, "learning_rate": 1.0238108824763768e-06, "loss": 0.5345290899276733, "step": 1838 }, { "epoch": 3.8818565400843883, "grad_norm": 15.320477485656738, "learning_rate": 1.022225253964233e-06, "loss": 0.7307233810424805, "step": 1840 }, { "epoch": 3.8860759493670884, "grad_norm": 9.880020141601562, "learning_rate": 1.0206941251522885e-06, "loss": 0.49433356523513794, "step": 1842 }, { "epoch": 3.890295358649789, "grad_norm": 1.4328478574752808, "learning_rate": 1.0192175146761524e-06, "loss": 0.4562499523162842, "step": 1844 }, { "epoch": 3.894514767932489, "grad_norm": 11.020108222961426, "learning_rate": 1.0177954405078835e-06, "loss": 0.7045310735702515, "step": 1846 }, { "epoch": 3.8987341772151898, "grad_norm": 6.312666416168213, "learning_rate": 1.0164279199557686e-06, "loss": 0.3025636672973633, "step": 1848 }, { "epoch": 3.9029535864978904, "grad_norm": 2.3025801181793213, "learning_rate": 1.0151149696641168e-06, "loss": 0.8873302936553955, "step": 1850 }, { "epoch": 3.9071729957805905, "grad_norm": 2.792774200439453, "learning_rate": 1.0138566056130515e-06, "loss": 0.8704756498336792, "step": 1852 }, { "epoch": 3.911392405063291, "grad_norm": 2.597687244415283, "learning_rate": 1.0126528431183195e-06, "loss": 0.7584602236747742, "step": 1854 }, { "epoch": 3.9156118143459917, "grad_norm": 2.009371519088745, "learning_rate": 1.0115036968311033e-06, "loss": 0.7262599468231201, "step": 1856 }, { "epoch": 3.919831223628692, "grad_norm": 1.7187460660934448, "learning_rate": 1.0104091807378438e-06, "loss": 0.7679610252380371, "step": 1858 }, { "epoch": 3.9240506329113924, "grad_norm": 2.1841681003570557, "learning_rate": 1.0093693081600666e-06, "loss": 0.7911632657051086, "step": 1860 }, { "epoch": 3.928270042194093, "grad_norm": 8.022225379943848, "learning_rate": 1.008384091754226e-06, "loss": 0.4581802487373352, "step": 1862 }, { "epoch": 3.932489451476793, "grad_norm": 2.212033271789551, "learning_rate": 1.007453543511545e-06, "loss": 0.47628599405288696, "step": 1864 }, { "epoch": 3.9367088607594938, "grad_norm": 4.698168754577637, "learning_rate": 1.006577674757873e-06, "loss": 0.8686692714691162, "step": 1866 }, { "epoch": 3.9409282700421944, "grad_norm": 1.632333755493164, "learning_rate": 1.0057564961535454e-06, "loss": 0.6620824337005615, "step": 1868 }, { "epoch": 3.9451476793248945, "grad_norm": 5.410098075866699, "learning_rate": 1.0049900176932567e-06, "loss": 0.5263056755065918, "step": 1870 }, { "epoch": 3.9493670886075947, "grad_norm": 0.7221059799194336, "learning_rate": 1.0042782487059369e-06, "loss": 0.3421555757522583, "step": 1872 }, { "epoch": 3.9535864978902953, "grad_norm": 8.672829627990723, "learning_rate": 1.0036211978546373e-06, "loss": 0.26512712240219116, "step": 1874 }, { "epoch": 3.957805907172996, "grad_norm": 3.008295774459839, "learning_rate": 1.0030188731364275e-06, "loss": 0.4937257170677185, "step": 1876 }, { "epoch": 3.962025316455696, "grad_norm": 7.027841567993164, "learning_rate": 1.0024712818822967e-06, "loss": 0.5959345698356628, "step": 1878 }, { "epoch": 3.9662447257383966, "grad_norm": 2.455162525177002, "learning_rate": 1.001978430757064e-06, "loss": 0.5293846130371094, "step": 1880 }, { "epoch": 3.970464135021097, "grad_norm": 4.404110431671143, "learning_rate": 1.0015403257592978e-06, "loss": 0.6860568523406982, "step": 1882 }, { "epoch": 3.9746835443037973, "grad_norm": 4.425588607788086, "learning_rate": 1.0011569722212425e-06, "loss": 0.21463988721370697, "step": 1884 }, { "epoch": 3.978902953586498, "grad_norm": 3.268907308578491, "learning_rate": 1.000828374808755e-06, "loss": 0.7305811643600464, "step": 1886 }, { "epoch": 3.9831223628691985, "grad_norm": 2.7041444778442383, "learning_rate": 1.000554537521245e-06, "loss": 0.4178711771965027, "step": 1888 }, { "epoch": 3.9873417721518987, "grad_norm": 10.676273345947266, "learning_rate": 1.0003354636916303e-06, "loss": 0.7595245242118835, "step": 1890 }, { "epoch": 3.9915611814345993, "grad_norm": 3.8041913509368896, "learning_rate": 1.0001711559862924e-06, "loss": 0.41353878378868103, "step": 1892 }, { "epoch": 3.9957805907173, "grad_norm": 2.085923671722412, "learning_rate": 1.0000616164050463e-06, "loss": 0.6929641366004944, "step": 1894 }, { "epoch": 4.0, "grad_norm": 2.360381603240967, "learning_rate": 1.0000068462811152e-06, "loss": 0.5759221315383911, "step": 1896 }, { "epoch": 4.0, "step": 1896, "total_flos": 3.5948540766149673e+18, "train_loss": 0.8339844654994046, "train_runtime": 4886.5014, "train_samples_per_second": 11.64, "train_steps_per_second": 0.388 } ], "logging_steps": 2, "max_steps": 1896, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 99999, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.5948540766149673e+18, "train_batch_size": 3, "trial_name": null, "trial_params": null }