diff --git "a/trainer_state.json" "b/trainer_state.json" --- "a/trainer_state.json" +++ "b/trainer_state.json" @@ -1,9616 +1,1336 @@ { "best_metric": null, "best_model_checkpoint": null, - "epoch": 5.274435470578539, - "global_step": 800000, + "epoch": 9.177373602536292, + "global_step": 110000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { - "epoch": 0.0, - "learning_rate": 4.999732157684128e-05, - "loss": 8.0441, + "epoch": 0.04, + "learning_rate": 4.9791423327215084e-05, + "loss": 8.0732, "step": 500 }, { - "epoch": 0.01, - "learning_rate": 4.999464315368257e-05, - "loss": 7.4643, + "epoch": 0.08, + "learning_rate": 4.958284665443017e-05, + "loss": 7.3801, "step": 1000 }, { - "epoch": 0.01, - "learning_rate": 4.999196473052385e-05, - "loss": 7.2385, + "epoch": 0.13, + "learning_rate": 4.9374269981645254e-05, + "loss": 7.0667, "step": 1500 }, { - "epoch": 0.01, - "learning_rate": 4.998928630736513e-05, - "loss": 7.0295, + "epoch": 0.17, + "learning_rate": 4.9165693308860336e-05, + "loss": 6.906, "step": 2000 }, { - "epoch": 0.01, - "learning_rate": 4.998660788420641e-05, - "loss": 6.7795, + "epoch": 0.21, + "learning_rate": 4.8957116636075424e-05, + "loss": 6.7114, "step": 2500 }, { - "epoch": 0.02, - "learning_rate": 4.99839294610477e-05, - "loss": 6.4582, + "epoch": 0.25, + "learning_rate": 4.8748539963290505e-05, + "loss": 6.6333, "step": 3000 }, { - "epoch": 0.02, - "learning_rate": 4.998125103788898e-05, - "loss": 6.1945, + "epoch": 0.29, + "learning_rate": 4.8539963290505594e-05, + "loss": 6.4948, "step": 3500 }, { - "epoch": 0.02, - "learning_rate": 4.997857261473026e-05, - "loss": 5.9526, + "epoch": 0.33, + "learning_rate": 4.8331386617720675e-05, + "loss": 6.3157, "step": 4000 }, { - "epoch": 0.02, - "learning_rate": 4.9975894191571545e-05, - "loss": 5.7498, + "epoch": 0.38, + "learning_rate": 4.812280994493576e-05, + "loss": 6.1185, "step": 4500 }, { - "epoch": 0.03, - "learning_rate": 4.9973215768412825e-05, - "loss": 5.5682, + "epoch": 0.42, + "learning_rate": 4.7914233272150845e-05, + "loss": 5.9335, "step": 5000 }, { - "epoch": 0.03, - "learning_rate": 4.9970537345254105e-05, - "loss": 5.4361, + "epoch": 0.46, + "learning_rate": 4.770565659936593e-05, + "loss": 5.7535, "step": 5500 }, { - "epoch": 0.03, - "learning_rate": 4.9967858922095386e-05, - "loss": 5.2997, + "epoch": 0.5, + "learning_rate": 4.749707992658101e-05, + "loss": 5.5631, "step": 6000 }, { - "epoch": 0.03, - "learning_rate": 4.996518049893667e-05, - "loss": 5.1931, + "epoch": 0.54, + "learning_rate": 4.72885032537961e-05, + "loss": 5.3707, "step": 6500 }, { - "epoch": 0.04, - "learning_rate": 4.996250207577795e-05, - "loss": 5.0977, + "epoch": 0.58, + "learning_rate": 4.707992658101118e-05, + "loss": 5.2234, "step": 7000 }, { - "epoch": 0.04, - "learning_rate": 4.995982365261923e-05, - "loss": 4.9985, + "epoch": 0.63, + "learning_rate": 4.687134990822627e-05, + "loss": 5.1324, "step": 7500 }, { - "epoch": 0.04, - "learning_rate": 4.995714522946052e-05, - "loss": 4.9181, + "epoch": 0.67, + "learning_rate": 4.666277323544135e-05, + "loss": 5.023, "step": 8000 }, { - "epoch": 0.05, - "learning_rate": 4.99544668063018e-05, - "loss": 4.8393, + "epoch": 0.71, + "learning_rate": 4.645419656265643e-05, + "loss": 4.9164, "step": 8500 }, { - "epoch": 0.05, - "learning_rate": 4.995178838314308e-05, - "loss": 4.7635, + "epoch": 0.75, + "learning_rate": 4.624561988987152e-05, + "loss": 4.8293, "step": 9000 }, { - "epoch": 0.05, - "learning_rate": 4.994910995998436e-05, - "loss": 4.691, + "epoch": 0.79, + "learning_rate": 4.60370432170866e-05, + "loss": 4.7737, "step": 9500 }, { - "epoch": 0.05, - "learning_rate": 4.994643153682564e-05, - "loss": 4.6334, + "epoch": 0.83, + "learning_rate": 4.582846654430168e-05, + "loss": 4.6915, "step": 10000 }, { - "epoch": 0.06, - "learning_rate": 4.994375311366692e-05, - "loss": 4.5618, + "epoch": 0.88, + "learning_rate": 4.561988987151678e-05, + "loss": 4.6345, "step": 10500 }, { - "epoch": 0.06, - "learning_rate": 4.99410746905082e-05, - "loss": 4.5111, + "epoch": 0.92, + "learning_rate": 4.541131319873186e-05, + "loss": 4.6052, "step": 11000 }, { - "epoch": 0.06, - "learning_rate": 4.993839626734949e-05, - "loss": 4.4506, + "epoch": 0.96, + "learning_rate": 4.520273652594694e-05, + "loss": 4.5157, "step": 11500 }, { - "epoch": 0.06, - "learning_rate": 4.993571784419077e-05, - "loss": 4.3953, + "epoch": 1.0, + "learning_rate": 4.499415985316203e-05, + "loss": 4.4535, "step": 12000 }, { - "epoch": 0.07, - "learning_rate": 4.993303942103205e-05, - "loss": 4.3535, + "epoch": 1.04, + "learning_rate": 4.478558318037711e-05, + "loss": 4.4238, "step": 12500 }, { - "epoch": 0.07, - "learning_rate": 4.993036099787333e-05, - "loss": 4.298, + "epoch": 1.08, + "learning_rate": 4.45770065075922e-05, + "loss": 4.3574, "step": 13000 }, { - "epoch": 0.07, - "learning_rate": 4.9927682574714617e-05, - "loss": 4.2497, + "epoch": 1.13, + "learning_rate": 4.436842983480728e-05, + "loss": 4.3355, "step": 13500 }, { - "epoch": 0.07, - "learning_rate": 4.99250041515559e-05, - "loss": 4.2168, + "epoch": 1.17, + "learning_rate": 4.415985316202236e-05, + "loss": 4.3007, "step": 14000 }, { - "epoch": 0.08, - "learning_rate": 4.992232572839718e-05, - "loss": 4.1752, + "epoch": 1.21, + "learning_rate": 4.395127648923745e-05, + "loss": 4.2482, "step": 14500 }, { - "epoch": 0.08, - "learning_rate": 4.9919647305238464e-05, - "loss": 4.1256, + "epoch": 1.25, + "learning_rate": 4.374269981645253e-05, + "loss": 4.1904, "step": 15000 }, { - "epoch": 0.08, - "learning_rate": 4.9916968882079744e-05, - "loss": 4.0846, + "epoch": 1.29, + "learning_rate": 4.353412314366761e-05, + "loss": 4.1877, "step": 15500 }, { - "epoch": 0.09, - "learning_rate": 4.9914290458921025e-05, - "loss": 4.0592, + "epoch": 1.33, + "learning_rate": 4.33255464708827e-05, + "loss": 4.1422, "step": 16000 }, { - "epoch": 0.09, - "learning_rate": 4.9911612035762305e-05, - "loss": 4.0098, + "epoch": 1.38, + "learning_rate": 4.311696979809778e-05, + "loss": 4.0952, "step": 16500 }, { - "epoch": 0.09, - "learning_rate": 4.990893361260359e-05, - "loss": 3.9768, + "epoch": 1.42, + "learning_rate": 4.2908393125312865e-05, + "loss": 4.0837, "step": 17000 }, { - "epoch": 0.09, - "learning_rate": 4.990625518944487e-05, - "loss": 3.9523, + "epoch": 1.46, + "learning_rate": 4.269981645252795e-05, + "loss": 4.0552, "step": 17500 }, { - "epoch": 0.1, - "learning_rate": 4.990357676628615e-05, - "loss": 3.9248, + "epoch": 1.5, + "learning_rate": 4.2491239779743035e-05, + "loss": 4.0141, "step": 18000 }, { - "epoch": 0.1, - "learning_rate": 4.990089834312744e-05, - "loss": 3.8991, + "epoch": 1.54, + "learning_rate": 4.228266310695812e-05, + "loss": 3.9979, "step": 18500 }, { - "epoch": 0.1, - "learning_rate": 4.989821991996872e-05, - "loss": 3.8507, + "epoch": 1.59, + "learning_rate": 4.2074086434173204e-05, + "loss": 3.9504, "step": 19000 }, { - "epoch": 0.1, - "learning_rate": 4.989554149681e-05, - "loss": 3.8259, + "epoch": 1.63, + "learning_rate": 4.1865509761388286e-05, + "loss": 3.9522, "step": 19500 }, { - "epoch": 0.11, - "learning_rate": 4.989286307365128e-05, - "loss": 3.803, + "epoch": 1.67, + "learning_rate": 4.1656933088603374e-05, + "loss": 3.9057, "step": 20000 }, { - "epoch": 0.14, - "learning_rate": 4.986484259106643e-05, - "loss": 3.7553, + "epoch": 1.71, + "learning_rate": 4.1448356415818456e-05, + "loss": 3.8997, "step": 20500 }, { - "epoch": 0.14, - "learning_rate": 4.986154606889731e-05, - "loss": 3.7416, + "epoch": 1.75, + "learning_rate": 4.123977974303354e-05, + "loss": 3.8594, "step": 21000 }, { - "epoch": 0.14, - "learning_rate": 4.98582495467282e-05, - "loss": 3.6909, + "epoch": 1.79, + "learning_rate": 4.1031203070248626e-05, + "loss": 3.823, "step": 21500 }, { - "epoch": 0.15, - "learning_rate": 4.985495302455909e-05, - "loss": 3.6867, + "epoch": 1.84, + "learning_rate": 4.082262639746371e-05, + "loss": 3.8168, "step": 22000 }, { - "epoch": 0.15, - "learning_rate": 4.985165650238998e-05, - "loss": 3.6577, + "epoch": 1.88, + "learning_rate": 4.0614049724678796e-05, + "loss": 3.7902, "step": 22500 }, { - "epoch": 0.15, - "learning_rate": 4.984835998022087e-05, - "loss": 3.6213, + "epoch": 1.92, + "learning_rate": 4.040547305189388e-05, + "loss": 3.7825, "step": 23000 }, { - "epoch": 0.15, - "learning_rate": 4.9845063458051755e-05, - "loss": 3.5919, + "epoch": 1.96, + "learning_rate": 4.019689637910896e-05, + "loss": 3.7529, "step": 23500 }, { - "epoch": 0.16, - "learning_rate": 4.9841766935882646e-05, - "loss": 3.5865, + "epoch": 2.0, + "learning_rate": 3.998831970632405e-05, + "loss": 3.7309, "step": 24000 }, { - "epoch": 0.16, - "learning_rate": 4.9838470413713536e-05, - "loss": 3.5505, + "epoch": 2.04, + "learning_rate": 3.977974303353913e-05, + "loss": 3.6979, "step": 24500 }, { - "epoch": 0.16, - "learning_rate": 4.983517389154443e-05, - "loss": 3.5237, + "epoch": 2.09, + "learning_rate": 3.957116636075421e-05, + "loss": 3.6644, "step": 25000 }, { - "epoch": 0.17, - "learning_rate": 4.983187736937531e-05, - "loss": 3.5161, + "epoch": 2.13, + "learning_rate": 3.93625896879693e-05, + "loss": 3.6569, "step": 25500 }, { - "epoch": 0.17, - "learning_rate": 4.98285808472062e-05, - "loss": 3.4829, + "epoch": 2.17, + "learning_rate": 3.915401301518438e-05, + "loss": 3.6378, "step": 26000 }, { - "epoch": 0.17, - "learning_rate": 4.9825284325037084e-05, - "loss": 3.472, + "epoch": 2.21, + "learning_rate": 3.894543634239947e-05, + "loss": 3.6143, "step": 26500 }, { - "epoch": 0.18, - "learning_rate": 4.9821987802867975e-05, - "loss": 3.4559, + "epoch": 2.25, + "learning_rate": 3.873685966961455e-05, + "loss": 3.5909, "step": 27000 }, { - "epoch": 0.18, - "learning_rate": 4.9818691280698865e-05, - "loss": 3.4372, + "epoch": 2.29, + "learning_rate": 3.852828299682963e-05, + "loss": 3.6046, "step": 27500 }, { - "epoch": 0.18, - "learning_rate": 4.9815394758529755e-05, - "loss": 3.4142, + "epoch": 2.34, + "learning_rate": 3.831970632404472e-05, + "loss": 3.577, "step": 28000 }, { - "epoch": 0.19, - "learning_rate": 4.9812098236360646e-05, - "loss": 3.3985, + "epoch": 2.38, + "learning_rate": 3.81111296512598e-05, + "loss": 3.5381, "step": 28500 }, { - "epoch": 0.19, - "learning_rate": 4.9808801714191536e-05, - "loss": 3.3688, + "epoch": 2.42, + "learning_rate": 3.7902552978474884e-05, + "loss": 3.5436, "step": 29000 }, { - "epoch": 0.19, - "learning_rate": 4.980550519202242e-05, - "loss": 3.3551, + "epoch": 2.46, + "learning_rate": 3.769397630568997e-05, + "loss": 3.5292, "step": 29500 }, { - "epoch": 0.2, - "learning_rate": 4.98022086698533e-05, - "loss": 3.3385, + "epoch": 2.5, + "learning_rate": 3.7485399632905054e-05, + "loss": 3.5224, "step": 30000 }, { - "epoch": 0.2, - "learning_rate": 4.9798912147684194e-05, - "loss": 3.3144, + "epoch": 2.54, + "learning_rate": 3.727682296012014e-05, + "loss": 3.5099, "step": 30500 }, { - "epoch": 0.2, - "learning_rate": 4.9795615625515084e-05, - "loss": 3.3038, + "epoch": 2.59, + "learning_rate": 3.706824628733523e-05, + "loss": 3.4796, "step": 31000 }, { - "epoch": 0.21, - "learning_rate": 4.9792319103345974e-05, - "loss": 3.2812, + "epoch": 2.63, + "learning_rate": 3.685966961455031e-05, + "loss": 3.475, "step": 31500 }, { - "epoch": 0.21, - "learning_rate": 4.978902258117686e-05, - "loss": 3.2711, + "epoch": 2.67, + "learning_rate": 3.66510929417654e-05, + "loss": 3.4557, "step": 32000 }, { - "epoch": 0.21, - "learning_rate": 4.978572605900775e-05, - "loss": 3.2544, + "epoch": 2.71, + "learning_rate": 3.644251626898048e-05, + "loss": 3.4315, "step": 32500 }, { - "epoch": 0.22, - "learning_rate": 4.978242953683864e-05, - "loss": 3.2355, + "epoch": 2.75, + "learning_rate": 3.6233939596195564e-05, + "loss": 3.4356, "step": 33000 }, { - "epoch": 0.22, - "learning_rate": 4.977913301466953e-05, - "loss": 3.219, + "epoch": 2.79, + "learning_rate": 3.602536292341065e-05, + "loss": 3.4244, "step": 33500 }, { - "epoch": 0.22, - "learning_rate": 4.977583649250041e-05, - "loss": 3.2102, + "epoch": 2.84, + "learning_rate": 3.5816786250625733e-05, + "loss": 3.4026, "step": 34000 }, { - "epoch": 0.23, - "learning_rate": 4.97725399703313e-05, - "loss": 3.2046, + "epoch": 2.88, + "learning_rate": 3.5608209577840815e-05, + "loss": 3.42, "step": 34500 }, { - "epoch": 0.23, - "learning_rate": 4.976924344816219e-05, - "loss": 3.1857, + "epoch": 2.92, + "learning_rate": 3.5399632905055903e-05, + "loss": 3.3832, "step": 35000 }, { - "epoch": 0.23, - "learning_rate": 4.976594692599308e-05, - "loss": 3.1825, + "epoch": 2.96, + "learning_rate": 3.5191056232270985e-05, + "loss": 3.3545, "step": 35500 }, { - "epoch": 0.24, - "learning_rate": 4.976265040382397e-05, - "loss": 3.1562, + "epoch": 3.0, + "learning_rate": 3.4982479559486067e-05, + "loss": 3.3327, "step": 36000 }, { - "epoch": 0.24, - "learning_rate": 4.975935388165486e-05, - "loss": 3.1416, + "epoch": 3.05, + "learning_rate": 3.4773902886701155e-05, + "loss": 3.3129, "step": 36500 }, { - "epoch": 0.24, - "learning_rate": 4.975605735948575e-05, - "loss": 3.1348, + "epoch": 3.09, + "learning_rate": 3.4565326213916237e-05, + "loss": 3.3115, "step": 37000 }, { - "epoch": 0.25, - "learning_rate": 4.975276083731663e-05, - "loss": 3.1253, + "epoch": 3.13, + "learning_rate": 3.4356749541131325e-05, + "loss": 3.2831, "step": 37500 }, { - "epoch": 0.25, - "learning_rate": 4.974946431514752e-05, - "loss": 3.1049, + "epoch": 3.17, + "learning_rate": 3.4148172868346407e-05, + "loss": 3.2743, "step": 38000 }, { - "epoch": 0.25, - "learning_rate": 4.974616779297841e-05, - "loss": 3.0918, + "epoch": 3.21, + "learning_rate": 3.393959619556149e-05, + "loss": 3.2856, "step": 38500 }, { - "epoch": 0.26, - "learning_rate": 4.9742871270809296e-05, - "loss": 3.0909, + "epoch": 3.25, + "learning_rate": 3.3731019522776576e-05, + "loss": 3.267, "step": 39000 }, { - "epoch": 0.26, - "learning_rate": 4.973957474864019e-05, - "loss": 3.0675, + "epoch": 3.3, + "learning_rate": 3.352244284999166e-05, + "loss": 3.264, "step": 39500 }, { - "epoch": 0.26, - "learning_rate": 4.973627822647108e-05, - "loss": 3.0627, + "epoch": 3.34, + "learning_rate": 3.331386617720674e-05, + "loss": 3.2614, "step": 40000 }, { - "epoch": 0.27, - "learning_rate": 4.973298170430196e-05, - "loss": 3.0625, + "epoch": 3.38, + "learning_rate": 3.310528950442183e-05, + "loss": 3.2554, "step": 40500 }, { - "epoch": 0.27, - "learning_rate": 4.972968518213285e-05, - "loss": 3.0419, + "epoch": 3.42, + "learning_rate": 3.289671283163691e-05, + "loss": 3.2308, "step": 41000 }, { - "epoch": 0.27, - "learning_rate": 4.972638865996374e-05, - "loss": 3.036, + "epoch": 3.46, + "learning_rate": 3.2688136158852e-05, + "loss": 3.2329, "step": 41500 }, { - "epoch": 0.28, - "learning_rate": 4.972309213779463e-05, - "loss": 3.0209, + "epoch": 3.5, + "learning_rate": 3.247955948606708e-05, + "loss": 3.2174, "step": 42000 }, { - "epoch": 0.28, - "learning_rate": 4.971979561562552e-05, - "loss": 3.0085, + "epoch": 3.55, + "learning_rate": 3.227098281328216e-05, + "loss": 3.1932, "step": 42500 }, { - "epoch": 0.28, - "learning_rate": 4.9716499093456406e-05, - "loss": 2.9991, + "epoch": 3.59, + "learning_rate": 3.206240614049725e-05, + "loss": 3.1748, "step": 43000 }, { - "epoch": 0.29, - "learning_rate": 4.9713202571287296e-05, - "loss": 2.9887, + "epoch": 3.63, + "learning_rate": 3.185382946771233e-05, + "loss": 3.1664, "step": 43500 }, { - "epoch": 0.29, - "learning_rate": 4.970990604911818e-05, - "loss": 2.9756, + "epoch": 3.67, + "learning_rate": 3.164525279492741e-05, + "loss": 3.1862, "step": 44000 }, { - "epoch": 0.29, - "learning_rate": 4.970660952694907e-05, - "loss": 2.9713, + "epoch": 3.71, + "learning_rate": 3.14366761221425e-05, + "loss": 3.1649, "step": 44500 }, { - "epoch": 0.3, - "learning_rate": 4.970331300477996e-05, - "loss": 2.969, + "epoch": 3.75, + "learning_rate": 3.122809944935758e-05, + "loss": 3.1528, "step": 45000 }, { - "epoch": 0.3, - "learning_rate": 4.970001648261085e-05, - "loss": 2.9515, + "epoch": 3.8, + "learning_rate": 3.101952277657267e-05, + "loss": 3.1512, "step": 45500 }, { - "epoch": 0.3, - "learning_rate": 4.9696719960441735e-05, - "loss": 2.9405, + "epoch": 3.84, + "learning_rate": 3.081094610378775e-05, + "loss": 3.1362, "step": 46000 }, { - "epoch": 0.31, - "learning_rate": 4.9693423438272625e-05, - "loss": 2.9343, + "epoch": 3.88, + "learning_rate": 3.0602369431002834e-05, + "loss": 3.1517, "step": 46500 }, { - "epoch": 0.31, - "learning_rate": 4.9690126916103515e-05, - "loss": 2.9378, + "epoch": 3.92, + "learning_rate": 3.039379275821792e-05, + "loss": 3.1104, "step": 47000 }, { - "epoch": 0.31, - "learning_rate": 4.9686830393934406e-05, - "loss": 2.9235, + "epoch": 3.96, + "learning_rate": 3.0185216085433004e-05, + "loss": 3.1216, "step": 47500 }, { - "epoch": 0.32, - "learning_rate": 4.968353387176529e-05, - "loss": 2.9166, + "epoch": 4.0, + "learning_rate": 2.997663941264809e-05, + "loss": 3.1177, "step": 48000 }, { - "epoch": 0.32, - "learning_rate": 4.968023734959617e-05, - "loss": 2.9011, + "epoch": 4.05, + "learning_rate": 2.9768062739863174e-05, + "loss": 3.0815, "step": 48500 }, { - "epoch": 0.32, - "learning_rate": 4.967694082742706e-05, - "loss": 2.9034, + "epoch": 4.09, + "learning_rate": 2.9559486067078256e-05, + "loss": 3.0839, "step": 49000 }, { - "epoch": 0.33, - "learning_rate": 4.9673644305257954e-05, - "loss": 2.891, + "epoch": 4.13, + "learning_rate": 2.935090939429334e-05, + "loss": 3.0499, "step": 49500 }, { - "epoch": 0.33, - "learning_rate": 4.9670347783088844e-05, - "loss": 2.8763, + "epoch": 4.17, + "learning_rate": 2.9142332721508426e-05, + "loss": 3.0597, "step": 50000 }, { - "epoch": 0.33, - "learning_rate": 4.9667051260919734e-05, - "loss": 2.8794, + "epoch": 4.21, + "learning_rate": 2.8933756048723514e-05, + "loss": 3.0588, "step": 50500 }, { - "epoch": 0.34, - "learning_rate": 4.9663754738750625e-05, - "loss": 2.8709, + "epoch": 4.25, + "learning_rate": 2.87251793759386e-05, + "loss": 3.0393, "step": 51000 }, { - "epoch": 0.34, - "learning_rate": 4.966045821658151e-05, - "loss": 2.8652, + "epoch": 4.3, + "learning_rate": 2.8516602703153684e-05, + "loss": 3.041, "step": 51500 }, { - "epoch": 0.34, - "learning_rate": 4.96571616944124e-05, - "loss": 2.8576, + "epoch": 4.34, + "learning_rate": 2.8308026030368766e-05, + "loss": 3.0235, "step": 52000 }, { - "epoch": 0.35, - "learning_rate": 4.965386517224328e-05, - "loss": 2.8556, + "epoch": 4.38, + "learning_rate": 2.809944935758385e-05, + "loss": 3.0257, "step": 52500 }, { - "epoch": 0.35, - "learning_rate": 4.965056865007417e-05, - "loss": 2.8413, + "epoch": 4.42, + "learning_rate": 2.7890872684798936e-05, + "loss": 3.0206, "step": 53000 }, { - "epoch": 0.35, - "learning_rate": 4.964727212790506e-05, - "loss": 2.8377, + "epoch": 4.46, + "learning_rate": 2.768229601201402e-05, + "loss": 3.0039, "step": 53500 }, { - "epoch": 0.36, - "learning_rate": 4.964397560573595e-05, - "loss": 2.8303, + "epoch": 4.51, + "learning_rate": 2.7473719339229102e-05, + "loss": 2.9904, "step": 54000 }, { - "epoch": 0.36, - "learning_rate": 4.964067908356684e-05, - "loss": 2.8156, + "epoch": 4.55, + "learning_rate": 2.7265142666444187e-05, + "loss": 2.9984, "step": 54500 }, { - "epoch": 0.36, - "learning_rate": 4.963738256139773e-05, - "loss": 2.8099, + "epoch": 4.59, + "learning_rate": 2.7056565993659272e-05, + "loss": 2.9806, "step": 55000 }, { - "epoch": 0.37, - "learning_rate": 4.963408603922862e-05, - "loss": 2.797, + "epoch": 4.63, + "learning_rate": 2.6847989320874357e-05, + "loss": 2.9864, "step": 55500 }, { - "epoch": 0.37, - "learning_rate": 4.963078951705951e-05, - "loss": 2.8075, + "epoch": 4.67, + "learning_rate": 2.663941264808944e-05, + "loss": 2.9916, "step": 56000 }, { - "epoch": 0.37, - "learning_rate": 4.96274929948904e-05, - "loss": 2.8034, + "epoch": 4.71, + "learning_rate": 2.6430835975304524e-05, + "loss": 2.9799, "step": 56500 }, { - "epoch": 0.38, - "learning_rate": 4.962419647272128e-05, - "loss": 2.7894, + "epoch": 4.76, + "learning_rate": 2.622225930251961e-05, + "loss": 2.9744, "step": 57000 }, { - "epoch": 0.38, - "learning_rate": 4.9620899950552166e-05, - "loss": 2.7845, + "epoch": 4.8, + "learning_rate": 2.6013682629734694e-05, + "loss": 2.9689, "step": 57500 }, { - "epoch": 0.38, - "learning_rate": 4.9617603428383056e-05, - "loss": 2.773, + "epoch": 4.84, + "learning_rate": 2.5805105956949775e-05, + "loss": 2.9755, "step": 58000 }, { - "epoch": 0.39, - "learning_rate": 4.961430690621395e-05, - "loss": 2.7775, + "epoch": 4.88, + "learning_rate": 2.559652928416486e-05, + "loss": 2.9355, "step": 58500 }, { - "epoch": 0.39, - "learning_rate": 4.961101038404484e-05, - "loss": 2.7645, + "epoch": 4.92, + "learning_rate": 2.5387952611379945e-05, + "loss": 2.9549, "step": 59000 }, { - "epoch": 0.39, - "learning_rate": 4.960771386187572e-05, - "loss": 2.7694, + "epoch": 4.96, + "learning_rate": 2.517937593859503e-05, + "loss": 2.9552, "step": 59500 }, { - "epoch": 0.4, - "learning_rate": 4.960441733970661e-05, - "loss": 2.7499, + "epoch": 5.01, + "learning_rate": 2.497079926581011e-05, + "loss": 2.9608, "step": 60000 }, { - "epoch": 0.4, - "learning_rate": 4.96011208175375e-05, - "loss": 2.7481, + "epoch": 5.05, + "learning_rate": 2.4762222593025197e-05, + "loss": 2.9073, "step": 60500 }, { - "epoch": 0.4, - "learning_rate": 4.959782429536839e-05, - "loss": 2.7469, + "epoch": 5.09, + "learning_rate": 2.455364592024028e-05, + "loss": 2.9192, "step": 61000 }, { - "epoch": 0.41, - "learning_rate": 4.9594527773199275e-05, - "loss": 2.7383, + "epoch": 5.13, + "learning_rate": 2.4345069247455367e-05, + "loss": 2.922, "step": 61500 }, { - "epoch": 0.41, - "learning_rate": 4.9591231251030166e-05, - "loss": 2.7422, + "epoch": 5.17, + "learning_rate": 2.4136492574670448e-05, + "loss": 2.8877, "step": 62000 }, { - "epoch": 0.41, - "learning_rate": 4.958793472886105e-05, - "loss": 2.7238, + "epoch": 5.21, + "learning_rate": 2.3927915901885533e-05, + "loss": 2.9045, "step": 62500 }, { - "epoch": 0.42, - "learning_rate": 4.958463820669194e-05, - "loss": 2.7278, + "epoch": 5.26, + "learning_rate": 2.3719339229100618e-05, + "loss": 2.8876, "step": 63000 }, { - "epoch": 0.42, - "learning_rate": 4.958134168452283e-05, - "loss": 2.7129, + "epoch": 5.3, + "learning_rate": 2.3510762556315703e-05, + "loss": 2.8986, "step": 63500 }, { - "epoch": 0.42, - "learning_rate": 4.957804516235372e-05, - "loss": 2.7029, + "epoch": 5.34, + "learning_rate": 2.3302185883530785e-05, + "loss": 2.8924, "step": 64000 }, { - "epoch": 0.43, - "learning_rate": 4.957474864018461e-05, - "loss": 2.7112, + "epoch": 5.38, + "learning_rate": 2.309360921074587e-05, + "loss": 2.8761, "step": 64500 }, { - "epoch": 0.43, - "learning_rate": 4.9571452118015495e-05, - "loss": 2.7075, + "epoch": 5.42, + "learning_rate": 2.2885032537960955e-05, + "loss": 2.8782, "step": 65000 }, { - "epoch": 0.43, - "learning_rate": 4.9568155595846385e-05, - "loss": 2.7002, + "epoch": 5.46, + "learning_rate": 2.267645586517604e-05, + "loss": 2.878, "step": 65500 }, { - "epoch": 0.44, - "learning_rate": 4.9564859073677275e-05, - "loss": 2.6964, + "epoch": 5.51, + "learning_rate": 2.2467879192391125e-05, + "loss": 2.8706, "step": 66000 }, { - "epoch": 0.44, - "learning_rate": 4.956156255150816e-05, - "loss": 2.6903, + "epoch": 5.55, + "learning_rate": 2.225930251960621e-05, + "loss": 2.8647, "step": 66500 }, { - "epoch": 0.44, - "learning_rate": 4.955826602933905e-05, - "loss": 2.6826, + "epoch": 5.59, + "learning_rate": 2.2050725846821295e-05, + "loss": 2.8407, "step": 67000 }, { - "epoch": 0.45, - "learning_rate": 4.955496950716994e-05, - "loss": 2.6792, + "epoch": 5.63, + "learning_rate": 2.1842149174036376e-05, + "loss": 2.86, "step": 67500 }, { - "epoch": 0.45, - "learning_rate": 4.955167298500082e-05, - "loss": 2.6813, + "epoch": 5.67, + "learning_rate": 2.163357250125146e-05, + "loss": 2.8585, "step": 68000 }, { - "epoch": 0.45, - "learning_rate": 4.9548376462831714e-05, - "loss": 2.6754, + "epoch": 5.72, + "learning_rate": 2.1424995828466546e-05, + "loss": 2.8472, "step": 68500 }, { - "epoch": 0.45, - "learning_rate": 4.9545079940662604e-05, - "loss": 2.6738, + "epoch": 5.76, + "learning_rate": 2.121641915568163e-05, + "loss": 2.8495, "step": 69000 }, { - "epoch": 0.46, - "learning_rate": 4.9541783418493494e-05, - "loss": 2.6611, + "epoch": 5.8, + "learning_rate": 2.1007842482896713e-05, + "loss": 2.8375, "step": 69500 }, { - "epoch": 0.46, - "learning_rate": 4.9538486896324385e-05, - "loss": 2.6583, + "epoch": 5.84, + "learning_rate": 2.0799265810111798e-05, + "loss": 2.8456, "step": 70000 }, { - "epoch": 0.46, - "learning_rate": 4.953519037415527e-05, - "loss": 2.6517, + "epoch": 5.88, + "learning_rate": 2.0590689137326883e-05, + "loss": 2.8388, "step": 70500 }, { - "epoch": 0.47, - "learning_rate": 4.953189385198615e-05, - "loss": 2.6484, + "epoch": 5.92, + "learning_rate": 2.0382112464541968e-05, + "loss": 2.8346, "step": 71000 }, { - "epoch": 0.47, - "learning_rate": 4.952859732981704e-05, - "loss": 2.6524, + "epoch": 5.97, + "learning_rate": 2.017353579175705e-05, + "loss": 2.8259, "step": 71500 }, { - "epoch": 0.47, - "learning_rate": 4.952530080764793e-05, - "loss": 2.6388, + "epoch": 6.01, + "learning_rate": 1.9964959118972134e-05, + "loss": 2.8211, "step": 72000 }, { - "epoch": 0.48, - "learning_rate": 4.952200428547882e-05, - "loss": 2.6442, + "epoch": 6.05, + "learning_rate": 1.975638244618722e-05, + "loss": 2.7936, "step": 72500 }, { - "epoch": 0.48, - "learning_rate": 4.9518707763309714e-05, - "loss": 2.6387, + "epoch": 6.09, + "learning_rate": 1.9547805773402304e-05, + "loss": 2.7904, "step": 73000 }, { - "epoch": 0.48, - "learning_rate": 4.95154112411406e-05, - "loss": 2.6312, + "epoch": 6.13, + "learning_rate": 1.9339229100617386e-05, + "loss": 2.7982, "step": 73500 }, { - "epoch": 0.49, - "learning_rate": 4.951211471897149e-05, - "loss": 2.6244, + "epoch": 6.17, + "learning_rate": 1.913065242783247e-05, + "loss": 2.7948, "step": 74000 }, { - "epoch": 0.49, - "learning_rate": 4.950881819680238e-05, - "loss": 2.6254, + "epoch": 6.22, + "learning_rate": 1.8922075755047556e-05, + "loss": 2.8152, "step": 74500 }, { - "epoch": 0.49, - "learning_rate": 4.950552167463327e-05, - "loss": 2.6278, + "epoch": 6.26, + "learning_rate": 1.871349908226264e-05, + "loss": 2.7862, "step": 75000 }, { - "epoch": 0.5, - "learning_rate": 4.950222515246415e-05, - "loss": 2.6234, + "epoch": 6.3, + "learning_rate": 1.8504922409477726e-05, + "loss": 2.7915, "step": 75500 }, { - "epoch": 0.5, - "learning_rate": 4.9498928630295036e-05, - "loss": 2.6137, + "epoch": 6.34, + "learning_rate": 1.829634573669281e-05, + "loss": 2.7796, "step": 76000 }, { - "epoch": 0.5, - "learning_rate": 4.9495632108125926e-05, - "loss": 2.6111, + "epoch": 6.38, + "learning_rate": 1.8087769063907896e-05, + "loss": 2.7892, "step": 76500 }, { - "epoch": 0.51, - "learning_rate": 4.9492335585956816e-05, - "loss": 2.596, + "epoch": 6.42, + "learning_rate": 1.7879192391122977e-05, + "loss": 2.7827, "step": 77000 }, { - "epoch": 0.51, - "learning_rate": 4.948903906378771e-05, - "loss": 2.5971, + "epoch": 6.47, + "learning_rate": 1.7670615718338062e-05, + "loss": 2.7857, "step": 77500 }, { - "epoch": 0.51, - "learning_rate": 4.94857425416186e-05, - "loss": 2.5906, + "epoch": 6.51, + "learning_rate": 1.7462039045553147e-05, + "loss": 2.7889, "step": 78000 }, { - "epoch": 0.52, - "learning_rate": 4.948244601944949e-05, - "loss": 2.5988, + "epoch": 6.55, + "learning_rate": 1.7253462372768232e-05, + "loss": 2.748, "step": 78500 }, { - "epoch": 0.52, - "learning_rate": 4.947914949728037e-05, - "loss": 2.5873, + "epoch": 6.59, + "learning_rate": 1.7044885699983314e-05, + "loss": 2.7607, "step": 79000 }, { - "epoch": 0.52, - "learning_rate": 4.947585297511126e-05, - "loss": 2.5862, + "epoch": 6.63, + "learning_rate": 1.68363090271984e-05, + "loss": 2.7597, "step": 79500 }, { - "epoch": 0.53, - "learning_rate": 4.9472556452942145e-05, - "loss": 2.5773, + "epoch": 6.67, + "learning_rate": 1.6627732354413484e-05, + "loss": 2.7591, "step": 80000 }, { - "epoch": 0.53, - "learning_rate": 4.9469259930773035e-05, - "loss": 2.588, + "epoch": 6.72, + "learning_rate": 1.641915568162857e-05, + "loss": 2.759, "step": 80500 }, { - "epoch": 0.53, - "learning_rate": 4.9465963408603926e-05, - "loss": 2.5739, + "epoch": 6.76, + "learning_rate": 1.621057900884365e-05, + "loss": 2.7519, "step": 81000 }, { - "epoch": 0.54, - "learning_rate": 4.9462666886434816e-05, - "loss": 2.5789, + "epoch": 6.8, + "learning_rate": 1.6002002336058735e-05, + "loss": 2.745, "step": 81500 }, { - "epoch": 0.54, - "learning_rate": 4.94593703642657e-05, - "loss": 2.5712, + "epoch": 6.84, + "learning_rate": 1.579342566327382e-05, + "loss": 2.7569, "step": 82000 }, { - "epoch": 0.54, - "learning_rate": 4.945607384209659e-05, - "loss": 2.5632, + "epoch": 6.88, + "learning_rate": 1.5584848990488905e-05, + "loss": 2.7549, "step": 82500 }, { - "epoch": 0.55, - "learning_rate": 4.945277731992748e-05, - "loss": 2.5599, + "epoch": 6.92, + "learning_rate": 1.5376272317703987e-05, + "loss": 2.748, "step": 83000 }, { - "epoch": 0.55, - "learning_rate": 4.944948079775837e-05, - "loss": 2.5642, + "epoch": 6.97, + "learning_rate": 1.5167695644919072e-05, + "loss": 2.7653, "step": 83500 }, { - "epoch": 0.55, - "learning_rate": 4.9446184275589255e-05, - "loss": 2.5583, + "epoch": 7.01, + "learning_rate": 1.4959118972134157e-05, + "loss": 2.7258, "step": 84000 }, { - "epoch": 0.56, - "learning_rate": 4.9442887753420145e-05, - "loss": 2.5562, + "epoch": 7.05, + "learning_rate": 1.475054229934924e-05, + "loss": 2.729, "step": 84500 }, { - "epoch": 0.56, - "learning_rate": 4.943959123125103e-05, - "loss": 2.5575, + "epoch": 7.09, + "learning_rate": 1.4541965626564325e-05, + "loss": 2.7198, "step": 85000 }, { - "epoch": 0.56, - "learning_rate": 4.943629470908192e-05, - "loss": 2.5476, + "epoch": 7.13, + "learning_rate": 1.4333388953779412e-05, + "loss": 2.7184, "step": 85500 }, { - "epoch": 0.57, - "learning_rate": 4.943299818691281e-05, - "loss": 2.5461, + "epoch": 7.18, + "learning_rate": 1.4124812280994495e-05, + "loss": 2.7079, "step": 86000 }, { - "epoch": 0.57, - "learning_rate": 4.94297016647437e-05, - "loss": 2.5409, + "epoch": 7.22, + "learning_rate": 1.391623560820958e-05, + "loss": 2.7243, "step": 86500 }, { - "epoch": 0.57, - "learning_rate": 4.942640514257459e-05, - "loss": 2.5314, + "epoch": 7.26, + "learning_rate": 1.3707658935424663e-05, + "loss": 2.6942, "step": 87000 }, { - "epoch": 0.58, - "learning_rate": 4.9423108620405474e-05, - "loss": 2.537, + "epoch": 7.3, + "learning_rate": 1.3499082262639748e-05, + "loss": 2.7002, "step": 87500 }, { - "epoch": 0.58, - "learning_rate": 4.9419812098236364e-05, - "loss": 2.5294, + "epoch": 7.34, + "learning_rate": 1.3290505589854831e-05, + "loss": 2.7085, "step": 88000 }, { - "epoch": 0.58, - "learning_rate": 4.9416515576067254e-05, - "loss": 2.527, + "epoch": 7.38, + "learning_rate": 1.3081928917069916e-05, + "loss": 2.6986, "step": 88500 }, { - "epoch": 0.59, - "learning_rate": 4.941321905389814e-05, - "loss": 2.5351, + "epoch": 7.43, + "learning_rate": 1.2873352244285e-05, + "loss": 2.7054, "step": 89000 }, { - "epoch": 0.59, - "learning_rate": 4.940992253172903e-05, - "loss": 2.5248, + "epoch": 7.47, + "learning_rate": 1.2664775571500085e-05, + "loss": 2.7214, "step": 89500 }, { - "epoch": 0.59, - "learning_rate": 4.940662600955991e-05, - "loss": 2.5288, + "epoch": 7.51, + "learning_rate": 1.2456198898715168e-05, + "loss": 2.7054, "step": 90000 }, { - "epoch": 0.6, - "learning_rate": 4.94033294873908e-05, - "loss": 2.5154, + "epoch": 7.55, + "learning_rate": 1.2247622225930253e-05, + "loss": 2.7054, "step": 90500 }, { - "epoch": 0.6, - "learning_rate": 4.940003296522169e-05, - "loss": 2.5147, + "epoch": 7.59, + "learning_rate": 1.2039045553145336e-05, + "loss": 2.7097, "step": 91000 }, { - "epoch": 0.6, - "learning_rate": 4.939673644305258e-05, - "loss": 2.5169, + "epoch": 7.63, + "learning_rate": 1.1830468880360421e-05, + "loss": 2.6911, "step": 91500 }, { - "epoch": 0.61, - "learning_rate": 4.9393439920883474e-05, - "loss": 2.512, + "epoch": 7.68, + "learning_rate": 1.1621892207575505e-05, + "loss": 2.6768, "step": 92000 }, { - "epoch": 0.61, - "learning_rate": 4.9390143398714364e-05, - "loss": 2.4993, + "epoch": 7.72, + "learning_rate": 1.141331553479059e-05, + "loss": 2.6735, "step": 92500 }, { - "epoch": 0.61, - "learning_rate": 4.938684687654525e-05, - "loss": 2.5128, + "epoch": 7.76, + "learning_rate": 1.1204738862005673e-05, + "loss": 2.703, "step": 93000 }, { - "epoch": 0.62, - "learning_rate": 4.938355035437614e-05, - "loss": 2.5024, + "epoch": 7.8, + "learning_rate": 1.099616218922076e-05, + "loss": 2.6704, "step": 93500 }, { - "epoch": 0.62, - "learning_rate": 4.938025383220702e-05, - "loss": 2.4978, + "epoch": 7.84, + "learning_rate": 1.0787585516435843e-05, + "loss": 2.6833, "step": 94000 }, { - "epoch": 0.62, - "learning_rate": 4.937695731003791e-05, - "loss": 2.496, + "epoch": 7.88, + "learning_rate": 1.0579008843650926e-05, + "loss": 2.6809, "step": 94500 }, { - "epoch": 0.63, - "learning_rate": 4.93736607878688e-05, - "loss": 2.4999, + "epoch": 7.93, + "learning_rate": 1.0370432170866011e-05, + "loss": 2.6766, "step": 95000 }, { - "epoch": 0.63, - "learning_rate": 4.9370364265699686e-05, - "loss": 2.4981, + "epoch": 7.97, + "learning_rate": 1.0161855498081094e-05, + "loss": 2.6719, "step": 95500 }, { - "epoch": 0.63, - "learning_rate": 4.9367067743530576e-05, - "loss": 2.4843, + "epoch": 8.01, + "learning_rate": 9.95327882529618e-06, + "loss": 2.6801, "step": 96000 }, { - "epoch": 0.64, - "learning_rate": 4.936377122136147e-05, - "loss": 2.48, + "epoch": 8.05, + "learning_rate": 9.744702152511263e-06, + "loss": 2.6555, "step": 96500 }, { - "epoch": 0.64, - "learning_rate": 4.936047469919236e-05, - "loss": 2.4805, + "epoch": 8.09, + "learning_rate": 9.536125479726348e-06, + "loss": 2.656, "step": 97000 }, { - "epoch": 0.64, - "learning_rate": 4.935717817702325e-05, - "loss": 2.4857, + "epoch": 8.13, + "learning_rate": 9.32754880694143e-06, + "loss": 2.6629, "step": 97500 }, { - "epoch": 0.65, - "learning_rate": 4.935388165485413e-05, - "loss": 2.4745, + "epoch": 8.18, + "learning_rate": 9.118972134156516e-06, + "loss": 2.6591, "step": 98000 }, { - "epoch": 0.65, - "learning_rate": 4.9350585132685015e-05, - "loss": 2.4742, + "epoch": 8.22, + "learning_rate": 8.9103954613716e-06, + "loss": 2.6521, "step": 98500 }, { - "epoch": 0.65, - "learning_rate": 4.9347288610515905e-05, - "loss": 2.4656, + "epoch": 8.26, + "learning_rate": 8.701818788586686e-06, + "loss": 2.6594, "step": 99000 }, { - "epoch": 0.66, - "learning_rate": 4.9343992088346795e-05, - "loss": 2.4717, + "epoch": 8.3, + "learning_rate": 8.493242115801769e-06, + "loss": 2.65, "step": 99500 }, { - "epoch": 0.66, - "learning_rate": 4.9340695566177686e-05, - "loss": 2.4641, + "epoch": 8.34, + "learning_rate": 8.284665443016854e-06, + "loss": 2.6492, "step": 100000 }, { - "epoch": 0.66, - "learning_rate": 4.9337399044008576e-05, - "loss": 2.4643, + "epoch": 8.38, + "learning_rate": 8.076088770231937e-06, + "loss": 2.6443, "step": 100500 }, { - "epoch": 0.67, - "learning_rate": 4.933410252183946e-05, - "loss": 2.4587, + "epoch": 8.43, + "learning_rate": 7.867512097447022e-06, + "loss": 2.6567, "step": 101000 }, { - "epoch": 0.67, - "learning_rate": 4.933080599967035e-05, - "loss": 2.4562, + "epoch": 8.47, + "learning_rate": 7.658935424662106e-06, + "loss": 2.6213, "step": 101500 }, { - "epoch": 0.67, - "learning_rate": 4.932750947750124e-05, - "loss": 2.4559, + "epoch": 8.51, + "learning_rate": 7.45035875187719e-06, + "loss": 2.6659, "step": 102000 }, { - "epoch": 0.68, - "learning_rate": 4.9324212955332124e-05, - "loss": 2.4508, + "epoch": 8.55, + "learning_rate": 7.241782079092274e-06, + "loss": 2.6456, "step": 102500 }, { - "epoch": 0.68, - "learning_rate": 4.9320916433163015e-05, - "loss": 2.4525, + "epoch": 8.59, + "learning_rate": 7.033205406307358e-06, + "loss": 2.6431, "step": 103000 }, { - "epoch": 0.68, - "learning_rate": 4.9317619910993905e-05, - "loss": 2.4404, + "epoch": 8.64, + "learning_rate": 6.824628733522444e-06, + "loss": 2.6418, "step": 103500 }, { - "epoch": 0.69, - "learning_rate": 4.931432338882479e-05, - "loss": 2.4506, + "epoch": 8.68, + "learning_rate": 6.616052060737528e-06, + "loss": 2.6437, "step": 104000 }, { - "epoch": 0.69, - "learning_rate": 4.931102686665568e-05, - "loss": 2.4411, + "epoch": 8.72, + "learning_rate": 6.407475387952612e-06, + "loss": 2.6398, "step": 104500 }, { - "epoch": 0.69, - "learning_rate": 4.930773034448657e-05, - "loss": 2.4535, + "epoch": 8.76, + "learning_rate": 6.198898715167696e-06, + "loss": 2.6565, "step": 105000 }, { - "epoch": 0.7, - "learning_rate": 4.930443382231746e-05, - "loss": 2.4456, + "epoch": 8.8, + "learning_rate": 5.99032204238278e-06, + "loss": 2.6403, "step": 105500 }, { - "epoch": 0.7, - "learning_rate": 4.930113730014835e-05, - "loss": 2.4436, + "epoch": 8.84, + "learning_rate": 5.7817453695978644e-06, + "loss": 2.6243, "step": 106000 }, { - "epoch": 0.7, - "learning_rate": 4.9297840777979234e-05, - "loss": 2.4325, + "epoch": 8.89, + "learning_rate": 5.5731686968129486e-06, + "loss": 2.6253, "step": 106500 }, { - "epoch": 0.71, - "learning_rate": 4.9294544255810124e-05, - "loss": 2.4292, + "epoch": 8.93, + "learning_rate": 5.3645920240280335e-06, + "loss": 2.6358, "step": 107000 }, { - "epoch": 0.71, - "learning_rate": 4.929124773364101e-05, - "loss": 2.4327, + "epoch": 8.97, + "learning_rate": 5.156015351243118e-06, + "loss": 2.6267, "step": 107500 }, { - "epoch": 0.71, - "learning_rate": 4.92879512114719e-05, - "loss": 2.4341, + "epoch": 9.01, + "learning_rate": 4.947438678458202e-06, + "loss": 2.6483, "step": 108000 }, { - "epoch": 0.72, - "learning_rate": 4.928465468930279e-05, - "loss": 2.427, + "epoch": 9.05, + "learning_rate": 4.738862005673286e-06, + "loss": 2.6325, "step": 108500 }, { - "epoch": 0.72, - "learning_rate": 4.928135816713368e-05, - "loss": 2.4191, + "epoch": 9.09, + "learning_rate": 4.53028533288837e-06, + "loss": 2.6104, "step": 109000 }, { - "epoch": 0.72, - "learning_rate": 4.927806164496456e-05, - "loss": 2.425, + "epoch": 9.14, + "learning_rate": 4.321708660103454e-06, + "loss": 2.6263, "step": 109500 }, { - "epoch": 0.73, - "learning_rate": 4.927476512279545e-05, - "loss": 2.4173, + "epoch": 9.18, + "learning_rate": 4.113131987318538e-06, + "loss": 2.6118, "step": 110000 - }, - { - "epoch": 0.73, - "learning_rate": 4.927146860062634e-05, - "loss": 2.4139, - "step": 110500 - }, - { - "epoch": 0.73, - "learning_rate": 4.9268172078457234e-05, - "loss": 2.425, - "step": 111000 - }, - { - "epoch": 0.74, - "learning_rate": 4.926487555628812e-05, - "loss": 2.4102, - "step": 111500 - }, - { - "epoch": 0.74, - "learning_rate": 4.926157903411901e-05, - "loss": 2.414, - "step": 112000 - }, - { - "epoch": 0.74, - "learning_rate": 4.925828251194989e-05, - "loss": 2.4037, - "step": 112500 - }, - { - "epoch": 0.75, - "learning_rate": 4.925498598978078e-05, - "loss": 2.409, - "step": 113000 - }, - { - "epoch": 0.75, - "learning_rate": 4.925168946761167e-05, - "loss": 2.4062, - "step": 113500 - }, - { - "epoch": 0.75, - "learning_rate": 4.924839294544256e-05, - "loss": 2.4074, - "step": 114000 - }, - { - "epoch": 0.75, - "learning_rate": 4.924509642327345e-05, - "loss": 2.4025, - "step": 114500 - }, - { - "epoch": 0.76, - "learning_rate": 4.9241799901104336e-05, - "loss": 2.3962, - "step": 115000 - }, - { - "epoch": 0.76, - "learning_rate": 4.923850337893523e-05, - "loss": 2.4029, - "step": 115500 - }, - { - "epoch": 0.76, - "learning_rate": 4.923520685676612e-05, - "loss": 2.4025, - "step": 116000 - }, - { - "epoch": 0.77, - "learning_rate": 4.9231910334597e-05, - "loss": 2.396, - "step": 116500 - }, - { - "epoch": 0.77, - "learning_rate": 4.922861381242789e-05, - "loss": 2.3894, - "step": 117000 - }, - { - "epoch": 0.77, - "learning_rate": 4.9225317290258775e-05, - "loss": 2.3878, - "step": 117500 - }, - { - "epoch": 0.78, - "learning_rate": 4.9222020768089665e-05, - "loss": 2.3897, - "step": 118000 - }, - { - "epoch": 0.78, - "learning_rate": 4.9218724245920555e-05, - "loss": 2.3832, - "step": 118500 - }, - { - "epoch": 0.78, - "learning_rate": 4.9215427723751446e-05, - "loss": 2.3834, - "step": 119000 - }, - { - "epoch": 0.79, - "learning_rate": 4.9212131201582336e-05, - "loss": 2.3887, - "step": 119500 - }, - { - "epoch": 0.79, - "learning_rate": 4.9208834679413227e-05, - "loss": 2.3763, - "step": 120000 - }, - { - "epoch": 0.79, - "learning_rate": 4.920553815724411e-05, - "loss": 2.3772, - "step": 120500 - }, - { - "epoch": 0.8, - "learning_rate": 4.9202241635074994e-05, - "loss": 2.3761, - "step": 121000 - }, - { - "epoch": 0.8, - "learning_rate": 4.9198945112905884e-05, - "loss": 2.3784, - "step": 121500 - }, - { - "epoch": 0.8, - "learning_rate": 4.9195648590736775e-05, - "loss": 2.3782, - "step": 122000 - }, - { - "epoch": 0.81, - "learning_rate": 4.9192352068567665e-05, - "loss": 2.3648, - "step": 122500 - }, - { - "epoch": 0.81, - "learning_rate": 4.918905554639855e-05, - "loss": 2.3759, - "step": 123000 - }, - { - "epoch": 0.81, - "learning_rate": 4.918575902422944e-05, - "loss": 2.3724, - "step": 123500 - }, - { - "epoch": 0.82, - "learning_rate": 4.918246250206033e-05, - "loss": 2.3702, - "step": 124000 - }, - { - "epoch": 0.82, - "learning_rate": 4.917916597989122e-05, - "loss": 2.3668, - "step": 124500 - }, - { - "epoch": 0.82, - "learning_rate": 4.917586945772211e-05, - "loss": 2.361, - "step": 125000 - }, - { - "epoch": 0.83, - "learning_rate": 4.9172572935552994e-05, - "loss": 2.3561, - "step": 125500 - }, - { - "epoch": 0.83, - "learning_rate": 4.916927641338388e-05, - "loss": 2.3553, - "step": 126000 - }, - { - "epoch": 0.83, - "learning_rate": 4.916597989121477e-05, - "loss": 2.3541, - "step": 126500 - }, - { - "epoch": 0.84, - "learning_rate": 4.916268336904566e-05, - "loss": 2.3622, - "step": 127000 - }, - { - "epoch": 0.84, - "learning_rate": 4.915938684687655e-05, - "loss": 2.3488, - "step": 127500 - }, - { - "epoch": 0.84, - "learning_rate": 4.915609032470744e-05, - "loss": 2.3482, - "step": 128000 - }, - { - "epoch": 0.85, - "learning_rate": 4.915279380253832e-05, - "loss": 2.3494, - "step": 128500 - }, - { - "epoch": 0.85, - "learning_rate": 4.914949728036921e-05, - "loss": 2.3457, - "step": 129000 - }, - { - "epoch": 0.85, - "learning_rate": 4.91462007582001e-05, - "loss": 2.3482, - "step": 129500 - }, - { - "epoch": 0.86, - "learning_rate": 4.914290423603099e-05, - "loss": 2.342, - "step": 130000 - }, - { - "epoch": 0.86, - "learning_rate": 4.913960771386188e-05, - "loss": 2.351, - "step": 130500 - }, - { - "epoch": 0.86, - "learning_rate": 4.913631119169277e-05, - "loss": 2.3423, - "step": 131000 - }, - { - "epoch": 0.87, - "learning_rate": 4.913301466952365e-05, - "loss": 2.3414, - "step": 131500 - }, - { - "epoch": 0.87, - "learning_rate": 4.912971814735454e-05, - "loss": 2.3421, - "step": 132000 - }, - { - "epoch": 0.87, - "learning_rate": 4.912642162518543e-05, - "loss": 2.3376, - "step": 132500 - }, - { - "epoch": 0.88, - "learning_rate": 4.912312510301632e-05, - "loss": 2.339, - "step": 133000 - }, - { - "epoch": 0.88, - "learning_rate": 4.911982858084721e-05, - "loss": 2.3396, - "step": 133500 - }, - { - "epoch": 0.88, - "learning_rate": 4.91165320586781e-05, - "loss": 2.3297, - "step": 134000 - }, - { - "epoch": 0.89, - "learning_rate": 4.911323553650899e-05, - "loss": 2.3282, - "step": 134500 - }, - { - "epoch": 0.89, - "learning_rate": 4.910993901433987e-05, - "loss": 2.3207, - "step": 135000 - }, - { - "epoch": 0.89, - "learning_rate": 4.910664249217076e-05, - "loss": 2.3188, - "step": 135500 - }, - { - "epoch": 0.9, - "learning_rate": 4.910334597000165e-05, - "loss": 2.3294, - "step": 136000 - }, - { - "epoch": 0.9, - "learning_rate": 4.910004944783254e-05, - "loss": 2.3308, - "step": 136500 - }, - { - "epoch": 0.9, - "learning_rate": 4.9096752925663425e-05, - "loss": 2.321, - "step": 137000 - }, - { - "epoch": 0.91, - "learning_rate": 4.9093456403494315e-05, - "loss": 2.3293, - "step": 137500 - }, - { - "epoch": 0.91, - "learning_rate": 4.9090159881325206e-05, - "loss": 2.315, - "step": 138000 - }, - { - "epoch": 0.91, - "learning_rate": 4.9086863359156096e-05, - "loss": 2.3236, - "step": 138500 - }, - { - "epoch": 0.92, - "learning_rate": 4.908356683698698e-05, - "loss": 2.311, - "step": 139000 - }, - { - "epoch": 0.92, - "learning_rate": 4.908027031481787e-05, - "loss": 2.3089, - "step": 139500 - }, - { - "epoch": 0.92, - "learning_rate": 4.9076973792648754e-05, - "loss": 2.3214, - "step": 140000 - }, - { - "epoch": 0.93, - "learning_rate": 4.9073677270479644e-05, - "loss": 2.3138, - "step": 140500 - }, - { - "epoch": 0.93, - "learning_rate": 4.9070380748310534e-05, - "loss": 2.3114, - "step": 141000 - }, - { - "epoch": 0.93, - "learning_rate": 4.9067084226141425e-05, - "loss": 2.3112, - "step": 141500 - }, - { - "epoch": 0.94, - "learning_rate": 4.9063787703972315e-05, - "loss": 2.3058, - "step": 142000 - }, - { - "epoch": 0.94, - "learning_rate": 4.90604911818032e-05, - "loss": 2.3086, - "step": 142500 - }, - { - "epoch": 0.94, - "learning_rate": 4.905719465963409e-05, - "loss": 2.3092, - "step": 143000 - }, - { - "epoch": 0.95, - "learning_rate": 4.905389813746498e-05, - "loss": 2.2986, - "step": 143500 - }, - { - "epoch": 0.95, - "learning_rate": 4.905060161529586e-05, - "loss": 2.3005, - "step": 144000 - }, - { - "epoch": 0.95, - "learning_rate": 4.9047305093126754e-05, - "loss": 2.2965, - "step": 144500 - }, - { - "epoch": 0.96, - "learning_rate": 4.9044008570957644e-05, - "loss": 2.2928, - "step": 145000 - }, - { - "epoch": 0.96, - "learning_rate": 4.904071204878853e-05, - "loss": 2.3072, - "step": 145500 - }, - { - "epoch": 0.96, - "learning_rate": 4.903741552661942e-05, - "loss": 2.2947, - "step": 146000 - }, - { - "epoch": 0.97, - "learning_rate": 4.903411900445031e-05, - "loss": 2.2962, - "step": 146500 - }, - { - "epoch": 0.97, - "learning_rate": 4.90308224822812e-05, - "loss": 2.291, - "step": 147000 - }, - { - "epoch": 0.97, - "learning_rate": 4.902752596011209e-05, - "loss": 2.2897, - "step": 147500 - }, - { - "epoch": 0.98, - "learning_rate": 4.902422943794297e-05, - "loss": 2.2941, - "step": 148000 - }, - { - "epoch": 0.98, - "learning_rate": 4.9020932915773856e-05, - "loss": 2.2921, - "step": 148500 - }, - { - "epoch": 0.98, - "learning_rate": 4.901763639360475e-05, - "loss": 2.3028, - "step": 149000 - }, - { - "epoch": 0.99, - "learning_rate": 4.901433987143564e-05, - "loss": 2.2885, - "step": 149500 - }, - { - "epoch": 0.99, - "learning_rate": 4.901104334926653e-05, - "loss": 2.283, - "step": 150000 - }, - { - "epoch": 0.99, - "learning_rate": 4.900774682709742e-05, - "loss": 2.2873, - "step": 150500 - }, - { - "epoch": 1.0, - "learning_rate": 4.90044503049283e-05, - "loss": 2.2927, - "step": 151000 - }, - { - "epoch": 1.0, - "learning_rate": 4.900115378275919e-05, - "loss": 2.2814, - "step": 151500 - }, - { - "epoch": 1.0, - "learning_rate": 4.899785726059008e-05, - "loss": 2.2809, - "step": 152000 - }, - { - "epoch": 1.01, - "learning_rate": 4.899456073842097e-05, - "loss": 2.2708, - "step": 152500 - }, - { - "epoch": 1.01, - "learning_rate": 4.8991264216251856e-05, - "loss": 2.2785, - "step": 153000 - }, - { - "epoch": 1.01, - "learning_rate": 4.898796769408274e-05, - "loss": 2.2759, - "step": 153500 - }, - { - "epoch": 1.02, - "learning_rate": 4.898467117191363e-05, - "loss": 2.28, - "step": 154000 - }, - { - "epoch": 1.02, - "learning_rate": 4.898137464974452e-05, - "loss": 2.273, - "step": 154500 - }, - { - "epoch": 1.02, - "learning_rate": 4.897807812757541e-05, - "loss": 2.2672, - "step": 155000 - }, - { - "epoch": 1.03, - "learning_rate": 4.89747816054063e-05, - "loss": 2.2658, - "step": 155500 - }, - { - "epoch": 1.03, - "learning_rate": 4.897148508323719e-05, - "loss": 2.2705, - "step": 156000 - }, - { - "epoch": 1.03, - "learning_rate": 4.8968188561068075e-05, - "loss": 2.27, - "step": 156500 - }, - { - "epoch": 1.04, - "learning_rate": 4.8964892038898966e-05, - "loss": 2.2557, - "step": 157000 - }, - { - "epoch": 1.04, - "learning_rate": 4.896159551672985e-05, - "loss": 2.2687, - "step": 157500 - }, - { - "epoch": 1.04, - "learning_rate": 4.895829899456074e-05, - "loss": 2.2613, - "step": 158000 - }, - { - "epoch": 1.04, - "learning_rate": 4.895500247239163e-05, - "loss": 2.2628, - "step": 158500 - }, - { - "epoch": 1.05, - "learning_rate": 4.8951705950222514e-05, - "loss": 2.2638, - "step": 159000 - }, - { - "epoch": 1.05, - "learning_rate": 4.8948409428053404e-05, - "loss": 2.2582, - "step": 159500 - }, - { - "epoch": 1.05, - "learning_rate": 4.8945112905884294e-05, - "loss": 2.2617, - "step": 160000 - }, - { - "epoch": 1.06, - "learning_rate": 4.8941816383715185e-05, - "loss": 2.2536, - "step": 160500 - }, - { - "epoch": 1.06, - "learning_rate": 4.8938519861546075e-05, - "loss": 2.2454, - "step": 161000 - }, - { - "epoch": 1.06, - "learning_rate": 4.893522333937696e-05, - "loss": 2.2522, - "step": 161500 - }, - { - "epoch": 1.07, - "learning_rate": 4.893192681720785e-05, - "loss": 2.2413, - "step": 162000 - }, - { - "epoch": 1.07, - "learning_rate": 4.892863029503873e-05, - "loss": 2.2557, - "step": 162500 - }, - { - "epoch": 1.07, - "learning_rate": 4.892533377286962e-05, - "loss": 2.2511, - "step": 163000 - }, - { - "epoch": 1.08, - "learning_rate": 4.8922037250700514e-05, - "loss": 2.2491, - "step": 163500 - }, - { - "epoch": 1.08, - "learning_rate": 4.8918740728531404e-05, - "loss": 2.2508, - "step": 164000 - }, - { - "epoch": 1.08, - "learning_rate": 4.891544420636229e-05, - "loss": 2.2456, - "step": 164500 - }, - { - "epoch": 1.09, - "learning_rate": 4.891214768419318e-05, - "loss": 2.2382, - "step": 165000 - }, - { - "epoch": 1.09, - "learning_rate": 4.890885116202407e-05, - "loss": 2.2546, - "step": 165500 - }, - { - "epoch": 1.09, - "learning_rate": 4.890555463985496e-05, - "loss": 2.2466, - "step": 166000 - }, - { - "epoch": 1.1, - "learning_rate": 4.890225811768584e-05, - "loss": 2.2372, - "step": 166500 - }, - { - "epoch": 1.1, - "learning_rate": 4.889896159551673e-05, - "loss": 2.2306, - "step": 167000 - }, - { - "epoch": 1.1, - "learning_rate": 4.8895665073347616e-05, - "loss": 2.2382, - "step": 167500 - }, - { - "epoch": 1.11, - "learning_rate": 4.889236855117851e-05, - "loss": 2.2369, - "step": 168000 - }, - { - "epoch": 1.11, - "learning_rate": 4.88890720290094e-05, - "loss": 2.2322, - "step": 168500 - }, - { - "epoch": 1.11, - "learning_rate": 4.888577550684029e-05, - "loss": 2.2389, - "step": 169000 - }, - { - "epoch": 1.12, - "learning_rate": 4.888247898467118e-05, - "loss": 2.2352, - "step": 169500 - }, - { - "epoch": 1.12, - "learning_rate": 4.887918246250206e-05, - "loss": 2.2352, - "step": 170000 - }, - { - "epoch": 1.12, - "learning_rate": 4.887588594033295e-05, - "loss": 2.2265, - "step": 170500 - }, - { - "epoch": 1.13, - "learning_rate": 4.887258941816384e-05, - "loss": 2.2443, - "step": 171000 - }, - { - "epoch": 1.13, - "learning_rate": 4.8869292895994726e-05, - "loss": 2.2292, - "step": 171500 - }, - { - "epoch": 1.13, - "learning_rate": 4.8865996373825616e-05, - "loss": 2.2271, - "step": 172000 - }, - { - "epoch": 1.14, - "learning_rate": 4.8862699851656507e-05, - "loss": 2.2312, - "step": 172500 - }, - { - "epoch": 1.14, - "learning_rate": 4.885940332948739e-05, - "loss": 2.2254, - "step": 173000 - }, - { - "epoch": 1.14, - "learning_rate": 4.885610680731828e-05, - "loss": 2.2291, - "step": 173500 - }, - { - "epoch": 1.15, - "learning_rate": 4.885281028514917e-05, - "loss": 2.2221, - "step": 174000 - }, - { - "epoch": 1.15, - "learning_rate": 4.884951376298006e-05, - "loss": 2.2202, - "step": 174500 - }, - { - "epoch": 1.15, - "learning_rate": 4.884621724081095e-05, - "loss": 2.2285, - "step": 175000 - }, - { - "epoch": 1.16, - "learning_rate": 4.8842920718641835e-05, - "loss": 2.2199, - "step": 175500 - }, - { - "epoch": 1.16, - "learning_rate": 4.883962419647272e-05, - "loss": 2.2296, - "step": 176000 - }, - { - "epoch": 1.16, - "learning_rate": 4.883632767430361e-05, - "loss": 2.2232, - "step": 176500 - }, - { - "epoch": 1.17, - "learning_rate": 4.88330311521345e-05, - "loss": 2.2235, - "step": 177000 - }, - { - "epoch": 1.17, - "learning_rate": 4.882973462996539e-05, - "loss": 2.2274, - "step": 177500 - }, - { - "epoch": 1.17, - "learning_rate": 4.882643810779628e-05, - "loss": 2.2128, - "step": 178000 - }, - { - "epoch": 1.18, - "learning_rate": 4.8823141585627164e-05, - "loss": 2.216, - "step": 178500 - }, - { - "epoch": 1.18, - "learning_rate": 4.8819845063458054e-05, - "loss": 2.2124, - "step": 179000 - }, - { - "epoch": 1.18, - "learning_rate": 4.8816548541288945e-05, - "loss": 2.2192, - "step": 179500 - }, - { - "epoch": 1.19, - "learning_rate": 4.881325201911983e-05, - "loss": 2.2223, - "step": 180000 - }, - { - "epoch": 1.19, - "learning_rate": 4.880995549695072e-05, - "loss": 2.2157, - "step": 180500 - }, - { - "epoch": 1.19, - "learning_rate": 4.88066589747816e-05, - "loss": 2.2135, - "step": 181000 - }, - { - "epoch": 1.2, - "learning_rate": 4.880336245261249e-05, - "loss": 2.2124, - "step": 181500 - }, - { - "epoch": 1.2, - "learning_rate": 4.880006593044338e-05, - "loss": 2.2074, - "step": 182000 - }, - { - "epoch": 1.2, - "learning_rate": 4.8796769408274274e-05, - "loss": 2.2099, - "step": 182500 - }, - { - "epoch": 1.21, - "learning_rate": 4.8793472886105164e-05, - "loss": 2.2012, - "step": 183000 - }, - { - "epoch": 1.21, - "learning_rate": 4.8790176363936054e-05, - "loss": 2.2081, - "step": 183500 - }, - { - "epoch": 1.21, - "learning_rate": 4.878687984176694e-05, - "loss": 2.2036, - "step": 184000 - }, - { - "epoch": 1.22, - "learning_rate": 4.878358331959783e-05, - "loss": 2.2096, - "step": 184500 - }, - { - "epoch": 1.22, - "learning_rate": 4.878028679742871e-05, - "loss": 2.2046, - "step": 185000 - }, - { - "epoch": 1.22, - "learning_rate": 4.87769902752596e-05, - "loss": 2.2039, - "step": 185500 - }, - { - "epoch": 1.23, - "learning_rate": 4.877369375309049e-05, - "loss": 2.1952, - "step": 186000 - }, - { - "epoch": 1.23, - "learning_rate": 4.877039723092138e-05, - "loss": 2.1968, - "step": 186500 - }, - { - "epoch": 1.23, - "learning_rate": 4.876710070875227e-05, - "loss": 2.1935, - "step": 187000 - }, - { - "epoch": 1.24, - "learning_rate": 4.876380418658316e-05, - "loss": 2.2039, - "step": 187500 - }, - { - "epoch": 1.24, - "learning_rate": 4.876050766441405e-05, - "loss": 2.199, - "step": 188000 - }, - { - "epoch": 1.24, - "learning_rate": 4.875721114224494e-05, - "loss": 2.1947, - "step": 188500 - }, - { - "epoch": 1.25, - "learning_rate": 4.875391462007582e-05, - "loss": 2.1951, - "step": 189000 - }, - { - "epoch": 1.25, - "learning_rate": 4.8750618097906705e-05, - "loss": 2.1983, - "step": 189500 - }, - { - "epoch": 1.25, - "learning_rate": 4.8747321575737595e-05, - "loss": 2.1919, - "step": 190000 - }, - { - "epoch": 1.26, - "learning_rate": 4.8744025053568486e-05, - "loss": 2.1905, - "step": 190500 - }, - { - "epoch": 1.26, - "learning_rate": 4.8740728531399376e-05, - "loss": 2.1971, - "step": 191000 - }, - { - "epoch": 1.26, - "learning_rate": 4.8737432009230267e-05, - "loss": 2.1937, - "step": 191500 - }, - { - "epoch": 1.27, - "learning_rate": 4.873413548706116e-05, - "loss": 2.1852, - "step": 192000 - }, - { - "epoch": 1.27, - "learning_rate": 4.873083896489204e-05, - "loss": 2.1947, - "step": 192500 - }, - { - "epoch": 1.27, - "learning_rate": 4.872754244272293e-05, - "loss": 2.1902, - "step": 193000 - }, - { - "epoch": 1.28, - "learning_rate": 4.872424592055382e-05, - "loss": 2.185, - "step": 193500 - }, - { - "epoch": 1.28, - "learning_rate": 4.8720949398384705e-05, - "loss": 2.1823, - "step": 194000 - }, - { - "epoch": 1.28, - "learning_rate": 4.8717652876215595e-05, - "loss": 2.1899, - "step": 194500 - }, - { - "epoch": 1.29, - "learning_rate": 4.871435635404648e-05, - "loss": 2.1901, - "step": 195000 - }, - { - "epoch": 1.29, - "learning_rate": 4.871105983187737e-05, - "loss": 2.1755, - "step": 195500 - }, - { - "epoch": 1.29, - "learning_rate": 4.870776330970826e-05, - "loss": 2.1837, - "step": 196000 - }, - { - "epoch": 1.3, - "learning_rate": 4.870446678753915e-05, - "loss": 2.1848, - "step": 196500 - }, - { - "epoch": 1.3, - "learning_rate": 4.870117026537004e-05, - "loss": 2.1837, - "step": 197000 - }, - { - "epoch": 1.3, - "learning_rate": 4.869787374320093e-05, - "loss": 2.1828, - "step": 197500 - }, - { - "epoch": 1.31, - "learning_rate": 4.8694577221031814e-05, - "loss": 2.1798, - "step": 198000 - }, - { - "epoch": 1.31, - "learning_rate": 4.86912806988627e-05, - "loss": 2.1821, - "step": 198500 - }, - { - "epoch": 1.31, - "learning_rate": 4.868798417669359e-05, - "loss": 2.1795, - "step": 199000 - }, - { - "epoch": 1.32, - "learning_rate": 4.868468765452448e-05, - "loss": 2.1763, - "step": 199500 - }, - { - "epoch": 1.32, - "learning_rate": 4.868139113235537e-05, - "loss": 2.1665, - "step": 200000 - }, - { - "epoch": 1.32, - "learning_rate": 4.867809461018625e-05, - "loss": 2.1782, - "step": 200500 - }, - { - "epoch": 1.33, - "learning_rate": 4.867479808801714e-05, - "loss": 2.1749, - "step": 201000 - }, - { - "epoch": 1.33, - "learning_rate": 4.8671501565848034e-05, - "loss": 2.1766, - "step": 201500 - }, - { - "epoch": 1.33, - "learning_rate": 4.8668205043678924e-05, - "loss": 2.1677, - "step": 202000 - }, - { - "epoch": 1.34, - "learning_rate": 4.8664908521509814e-05, - "loss": 2.1755, - "step": 202500 - }, - { - "epoch": 1.34, - "learning_rate": 4.86616119993407e-05, - "loss": 2.1645, - "step": 203000 - }, - { - "epoch": 1.34, - "learning_rate": 4.865831547717158e-05, - "loss": 2.1726, - "step": 203500 - }, - { - "epoch": 1.34, - "learning_rate": 4.865501895500247e-05, - "loss": 2.1726, - "step": 204000 - }, - { - "epoch": 1.35, - "learning_rate": 4.865172243283336e-05, - "loss": 2.17, - "step": 204500 - }, - { - "epoch": 1.35, - "learning_rate": 4.864842591066425e-05, - "loss": 2.1664, - "step": 205000 - }, - { - "epoch": 1.35, - "learning_rate": 4.864512938849514e-05, - "loss": 2.1743, - "step": 205500 - }, - { - "epoch": 1.36, - "learning_rate": 4.864183286632603e-05, - "loss": 2.1568, - "step": 206000 - }, - { - "epoch": 1.36, - "learning_rate": 4.863853634415692e-05, - "loss": 2.1534, - "step": 206500 - }, - { - "epoch": 1.36, - "learning_rate": 4.863523982198781e-05, - "loss": 2.1611, - "step": 207000 - }, - { - "epoch": 1.37, - "learning_rate": 4.863194329981869e-05, - "loss": 2.1631, - "step": 207500 - }, - { - "epoch": 1.37, - "learning_rate": 4.862864677764958e-05, - "loss": 2.1598, - "step": 208000 - }, - { - "epoch": 1.37, - "learning_rate": 4.862535025548047e-05, - "loss": 2.1554, - "step": 208500 - }, - { - "epoch": 1.38, - "learning_rate": 4.8622053733311355e-05, - "loss": 2.1624, - "step": 209000 - }, - { - "epoch": 1.38, - "learning_rate": 4.8618757211142246e-05, - "loss": 2.163, - "step": 209500 - }, - { - "epoch": 1.38, - "learning_rate": 4.8615460688973136e-05, - "loss": 2.1616, - "step": 210000 - }, - { - "epoch": 1.39, - "learning_rate": 4.8612164166804027e-05, - "loss": 2.1594, - "step": 210500 - }, - { - "epoch": 1.39, - "learning_rate": 4.860886764463492e-05, - "loss": 2.1654, - "step": 211000 - }, - { - "epoch": 1.39, - "learning_rate": 4.86055711224658e-05, - "loss": 2.1508, - "step": 211500 - }, - { - "epoch": 1.4, - "learning_rate": 4.860227460029669e-05, - "loss": 2.1602, - "step": 212000 - }, - { - "epoch": 1.4, - "learning_rate": 4.8598978078127575e-05, - "loss": 2.1597, - "step": 212500 - }, - { - "epoch": 1.4, - "learning_rate": 4.8595681555958465e-05, - "loss": 2.1576, - "step": 213000 - }, - { - "epoch": 1.41, - "learning_rate": 4.8592385033789355e-05, - "loss": 2.1595, - "step": 213500 - }, - { - "epoch": 1.41, - "learning_rate": 4.8589088511620246e-05, - "loss": 2.1565, - "step": 214000 - }, - { - "epoch": 1.41, - "learning_rate": 4.858579198945113e-05, - "loss": 2.1561, - "step": 214500 - }, - { - "epoch": 1.42, - "learning_rate": 4.858249546728202e-05, - "loss": 2.1503, - "step": 215000 - }, - { - "epoch": 1.42, - "learning_rate": 4.857919894511291e-05, - "loss": 2.1505, - "step": 215500 - }, - { - "epoch": 1.42, - "learning_rate": 4.85759024229438e-05, - "loss": 2.151, - "step": 216000 - }, - { - "epoch": 1.43, - "learning_rate": 4.8572605900774684e-05, - "loss": 2.1466, - "step": 216500 - }, - { - "epoch": 1.43, - "learning_rate": 4.856930937860557e-05, - "loss": 2.1477, - "step": 217000 - }, - { - "epoch": 1.43, - "learning_rate": 4.856601285643646e-05, - "loss": 2.1546, - "step": 217500 - }, - { - "epoch": 1.44, - "learning_rate": 4.856271633426735e-05, - "loss": 2.1417, - "step": 218000 - }, - { - "epoch": 1.44, - "learning_rate": 4.855941981209824e-05, - "loss": 2.1502, - "step": 218500 - }, - { - "epoch": 1.44, - "learning_rate": 4.855612328992913e-05, - "loss": 2.1368, - "step": 219000 - }, - { - "epoch": 1.45, - "learning_rate": 4.855282676776002e-05, - "loss": 2.1428, - "step": 219500 - }, - { - "epoch": 1.45, - "learning_rate": 4.85495302455909e-05, - "loss": 2.1386, - "step": 220000 - }, - { - "epoch": 1.45, - "learning_rate": 4.8546233723421794e-05, - "loss": 2.1416, - "step": 220500 - }, - { - "epoch": 1.46, - "learning_rate": 4.8542937201252684e-05, - "loss": 2.1419, - "step": 221000 - }, - { - "epoch": 1.46, - "learning_rate": 4.853964067908357e-05, - "loss": 2.1339, - "step": 221500 - }, - { - "epoch": 1.46, - "learning_rate": 4.853634415691446e-05, - "loss": 2.1408, - "step": 222000 - }, - { - "epoch": 1.47, - "learning_rate": 4.853304763474534e-05, - "loss": 2.1423, - "step": 222500 - }, - { - "epoch": 1.47, - "learning_rate": 4.852975111257623e-05, - "loss": 2.1327, - "step": 223000 - }, - { - "epoch": 1.47, - "learning_rate": 4.852645459040712e-05, - "loss": 2.1349, - "step": 223500 - }, - { - "epoch": 1.48, - "learning_rate": 4.852315806823801e-05, - "loss": 2.1455, - "step": 224000 - }, - { - "epoch": 1.48, - "learning_rate": 4.85198615460689e-05, - "loss": 2.1344, - "step": 224500 - }, - { - "epoch": 1.48, - "learning_rate": 4.8516565023899793e-05, - "loss": 2.1361, - "step": 225000 - }, - { - "epoch": 1.49, - "learning_rate": 4.851326850173068e-05, - "loss": 2.1365, - "step": 225500 - }, - { - "epoch": 1.49, - "learning_rate": 4.850997197956156e-05, - "loss": 2.132, - "step": 226000 - }, - { - "epoch": 1.49, - "learning_rate": 4.850667545739245e-05, - "loss": 2.1345, - "step": 226500 - }, - { - "epoch": 1.5, - "learning_rate": 4.850337893522334e-05, - "loss": 2.1354, - "step": 227000 - }, - { - "epoch": 1.5, - "learning_rate": 4.850008241305423e-05, - "loss": 2.1319, - "step": 227500 - }, - { - "epoch": 1.5, - "learning_rate": 4.8496785890885115e-05, - "loss": 2.1264, - "step": 228000 - }, - { - "epoch": 1.51, - "learning_rate": 4.8493489368716006e-05, - "loss": 2.1346, - "step": 228500 - }, - { - "epoch": 1.51, - "learning_rate": 4.8490192846546896e-05, - "loss": 2.1288, - "step": 229000 - }, - { - "epoch": 1.51, - "learning_rate": 4.8486896324377787e-05, - "loss": 2.1392, - "step": 229500 - }, - { - "epoch": 1.52, - "learning_rate": 4.848359980220867e-05, - "loss": 2.1327, - "step": 230000 - }, - { - "epoch": 1.52, - "learning_rate": 4.848030328003956e-05, - "loss": 2.1256, - "step": 230500 - }, - { - "epoch": 1.52, - "learning_rate": 4.8477006757870444e-05, - "loss": 2.1241, - "step": 231000 - }, - { - "epoch": 1.53, - "learning_rate": 4.8473710235701335e-05, - "loss": 2.1348, - "step": 231500 - }, - { - "epoch": 1.53, - "learning_rate": 4.8470413713532225e-05, - "loss": 2.1226, - "step": 232000 - }, - { - "epoch": 1.53, - "learning_rate": 4.8467117191363115e-05, - "loss": 2.1268, - "step": 232500 - }, - { - "epoch": 1.54, - "learning_rate": 4.8463820669194006e-05, - "loss": 2.1212, - "step": 233000 - }, - { - "epoch": 1.54, - "learning_rate": 4.846052414702489e-05, - "loss": 2.1277, - "step": 233500 - }, - { - "epoch": 1.54, - "learning_rate": 4.845722762485578e-05, - "loss": 2.1231, - "step": 234000 - }, - { - "epoch": 1.55, - "learning_rate": 4.845393110268667e-05, - "loss": 2.1279, - "step": 234500 - }, - { - "epoch": 1.55, - "learning_rate": 4.8450634580517554e-05, - "loss": 2.125, - "step": 235000 - }, - { - "epoch": 1.55, - "learning_rate": 4.8447338058348444e-05, - "loss": 2.1184, - "step": 235500 - }, - { - "epoch": 1.56, - "learning_rate": 4.8444041536179334e-05, - "loss": 2.1238, - "step": 236000 - }, - { - "epoch": 1.56, - "learning_rate": 4.844074501401022e-05, - "loss": 2.1191, - "step": 236500 - }, - { - "epoch": 1.56, - "learning_rate": 4.843744849184111e-05, - "loss": 2.1236, - "step": 237000 - }, - { - "epoch": 1.57, - "learning_rate": 4.8434151969672e-05, - "loss": 2.1108, - "step": 237500 - }, - { - "epoch": 1.57, - "learning_rate": 4.843085544750289e-05, - "loss": 2.1192, - "step": 238000 - }, - { - "epoch": 1.57, - "learning_rate": 4.842755892533378e-05, - "loss": 2.11, - "step": 238500 - }, - { - "epoch": 1.58, - "learning_rate": 4.842426240316466e-05, - "loss": 2.1226, - "step": 239000 - }, - { - "epoch": 1.58, - "learning_rate": 4.8420965880995554e-05, - "loss": 2.1102, - "step": 239500 - }, - { - "epoch": 1.58, - "learning_rate": 4.841766935882644e-05, - "loss": 2.1169, - "step": 240000 - }, - { - "epoch": 1.59, - "learning_rate": 4.841437283665733e-05, - "loss": 2.1097, - "step": 240500 - }, - { - "epoch": 1.59, - "learning_rate": 4.841107631448822e-05, - "loss": 2.1053, - "step": 241000 - }, - { - "epoch": 1.59, - "learning_rate": 4.840777979231911e-05, - "loss": 2.11, - "step": 241500 - }, - { - "epoch": 1.6, - "learning_rate": 4.840448327014999e-05, - "loss": 2.1099, - "step": 242000 - }, - { - "epoch": 1.6, - "learning_rate": 4.840118674798088e-05, - "loss": 2.1131, - "step": 242500 - }, - { - "epoch": 1.6, - "learning_rate": 4.839789022581177e-05, - "loss": 2.105, - "step": 243000 - }, - { - "epoch": 1.61, - "learning_rate": 4.839459370364266e-05, - "loss": 2.1107, - "step": 243500 - }, - { - "epoch": 1.61, - "learning_rate": 4.839129718147355e-05, - "loss": 2.1128, - "step": 244000 - }, - { - "epoch": 1.61, - "learning_rate": 4.838800065930444e-05, - "loss": 2.1058, - "step": 244500 - }, - { - "epoch": 1.62, - "learning_rate": 4.838470413713532e-05, - "loss": 2.1024, - "step": 245000 - }, - { - "epoch": 1.62, - "learning_rate": 4.838140761496621e-05, - "loss": 2.1152, - "step": 245500 - }, - { - "epoch": 1.62, - "learning_rate": 4.83781110927971e-05, - "loss": 2.0994, - "step": 246000 - }, - { - "epoch": 1.63, - "learning_rate": 4.837481457062799e-05, - "loss": 2.1084, - "step": 246500 - }, - { - "epoch": 1.63, - "learning_rate": 4.837151804845888e-05, - "loss": 2.101, - "step": 247000 - }, - { - "epoch": 1.63, - "learning_rate": 4.8368221526289766e-05, - "loss": 2.1038, - "step": 247500 - }, - { - "epoch": 1.64, - "learning_rate": 4.8364925004120656e-05, - "loss": 2.1045, - "step": 248000 - }, - { - "epoch": 1.64, - "learning_rate": 4.836162848195154e-05, - "loss": 2.0964, - "step": 248500 - }, - { - "epoch": 1.64, - "learning_rate": 4.835833195978243e-05, - "loss": 2.0991, - "step": 249000 - }, - { - "epoch": 1.64, - "learning_rate": 4.835503543761332e-05, - "loss": 2.1044, - "step": 249500 - }, - { - "epoch": 1.65, - "learning_rate": 4.835173891544421e-05, - "loss": 2.1011, - "step": 250000 - }, - { - "epoch": 1.65, - "learning_rate": 4.8348442393275095e-05, - "loss": 2.1058, - "step": 250500 - }, - { - "epoch": 1.65, - "learning_rate": 4.8345145871105985e-05, - "loss": 2.0921, - "step": 251000 - }, - { - "epoch": 1.66, - "learning_rate": 4.8341849348936875e-05, - "loss": 2.0987, - "step": 251500 - }, - { - "epoch": 1.66, - "learning_rate": 4.8338552826767766e-05, - "loss": 2.0972, - "step": 252000 - }, - { - "epoch": 1.66, - "learning_rate": 4.8335256304598656e-05, - "loss": 2.1022, - "step": 252500 - }, - { - "epoch": 1.67, - "learning_rate": 4.833195978242954e-05, - "loss": 2.0963, - "step": 253000 - }, - { - "epoch": 1.67, - "learning_rate": 4.832866326026042e-05, - "loss": 2.0946, - "step": 253500 - }, - { - "epoch": 1.67, - "learning_rate": 4.8325366738091314e-05, - "loss": 2.0863, - "step": 254000 - }, - { - "epoch": 1.68, - "learning_rate": 4.8322070215922204e-05, - "loss": 2.1016, - "step": 254500 - }, - { - "epoch": 1.68, - "learning_rate": 4.8318773693753094e-05, - "loss": 2.0928, - "step": 255000 - }, - { - "epoch": 1.68, - "learning_rate": 4.8315477171583985e-05, - "loss": 2.0888, - "step": 255500 - }, - { - "epoch": 1.69, - "learning_rate": 4.831218064941487e-05, - "loss": 2.0976, - "step": 256000 - }, - { - "epoch": 1.69, - "learning_rate": 4.830888412724576e-05, - "loss": 2.0889, - "step": 256500 - }, - { - "epoch": 1.69, - "learning_rate": 4.830558760507665e-05, - "loss": 2.0857, - "step": 257000 - }, - { - "epoch": 1.7, - "learning_rate": 4.830229108290753e-05, - "loss": 2.0873, - "step": 257500 - }, - { - "epoch": 1.7, - "learning_rate": 4.829899456073842e-05, - "loss": 2.0959, - "step": 258000 - }, - { - "epoch": 1.7, - "learning_rate": 4.829569803856931e-05, - "loss": 2.0909, - "step": 258500 - }, - { - "epoch": 1.71, - "learning_rate": 4.82924015164002e-05, - "loss": 2.0895, - "step": 259000 - }, - { - "epoch": 1.71, - "learning_rate": 4.828910499423109e-05, - "loss": 2.0868, - "step": 259500 - }, - { - "epoch": 1.71, - "learning_rate": 4.828580847206198e-05, - "loss": 2.0872, - "step": 260000 - }, - { - "epoch": 1.72, - "learning_rate": 4.828251194989287e-05, - "loss": 2.0862, - "step": 260500 - }, - { - "epoch": 1.72, - "learning_rate": 4.827921542772376e-05, - "loss": 2.0844, - "step": 261000 - }, - { - "epoch": 1.72, - "learning_rate": 4.827591890555464e-05, - "loss": 2.0864, - "step": 261500 - }, - { - "epoch": 1.73, - "learning_rate": 4.827262238338553e-05, - "loss": 2.0903, - "step": 262000 - }, - { - "epoch": 1.73, - "learning_rate": 4.8269325861216416e-05, - "loss": 2.0882, - "step": 262500 - }, - { - "epoch": 1.73, - "learning_rate": 4.826602933904731e-05, - "loss": 2.0828, - "step": 263000 - }, - { - "epoch": 1.74, - "learning_rate": 4.82627328168782e-05, - "loss": 2.0855, - "step": 263500 - }, - { - "epoch": 1.74, - "learning_rate": 4.825943629470908e-05, - "loss": 2.089, - "step": 264000 - }, - { - "epoch": 1.74, - "learning_rate": 4.825613977253997e-05, - "loss": 2.088, - "step": 264500 - }, - { - "epoch": 1.75, - "learning_rate": 4.825284325037086e-05, - "loss": 2.0847, - "step": 265000 - }, - { - "epoch": 1.75, - "learning_rate": 4.824954672820175e-05, - "loss": 2.0893, - "step": 265500 - }, - { - "epoch": 1.75, - "learning_rate": 4.824625020603264e-05, - "loss": 2.0823, - "step": 266000 - }, - { - "epoch": 1.76, - "learning_rate": 4.8242953683863526e-05, - "loss": 2.0836, - "step": 266500 - }, - { - "epoch": 1.76, - "learning_rate": 4.823965716169441e-05, - "loss": 2.0826, - "step": 267000 - }, - { - "epoch": 1.76, - "learning_rate": 4.82363606395253e-05, - "loss": 2.0841, - "step": 267500 - }, - { - "epoch": 1.77, - "learning_rate": 4.823306411735619e-05, - "loss": 2.084, - "step": 268000 - }, - { - "epoch": 1.77, - "learning_rate": 4.822976759518708e-05, - "loss": 2.0776, - "step": 268500 - }, - { - "epoch": 1.77, - "learning_rate": 4.822647107301797e-05, - "loss": 2.0705, - "step": 269000 - }, - { - "epoch": 1.78, - "learning_rate": 4.8223174550848854e-05, - "loss": 2.0731, - "step": 269500 - }, - { - "epoch": 1.78, - "learning_rate": 4.8219878028679745e-05, - "loss": 2.0759, - "step": 270000 - }, - { - "epoch": 1.78, - "learning_rate": 4.8216581506510635e-05, - "loss": 2.0749, - "step": 270500 - }, - { - "epoch": 1.79, - "learning_rate": 4.8213284984341526e-05, - "loss": 2.0823, - "step": 271000 - }, - { - "epoch": 1.79, - "learning_rate": 4.820998846217241e-05, - "loss": 2.0737, - "step": 271500 - }, - { - "epoch": 1.79, - "learning_rate": 4.82066919400033e-05, - "loss": 2.0754, - "step": 272000 - }, - { - "epoch": 1.8, - "learning_rate": 4.820339541783418e-05, - "loss": 2.0703, - "step": 272500 - }, - { - "epoch": 1.8, - "learning_rate": 4.8200098895665074e-05, - "loss": 2.0751, - "step": 273000 - }, - { - "epoch": 1.8, - "learning_rate": 4.8196802373495964e-05, - "loss": 2.0704, - "step": 273500 - }, - { - "epoch": 1.81, - "learning_rate": 4.8193505851326854e-05, - "loss": 2.0795, - "step": 274000 - }, - { - "epoch": 1.81, - "learning_rate": 4.8190209329157745e-05, - "loss": 2.0777, - "step": 274500 - }, - { - "epoch": 1.81, - "learning_rate": 4.818691280698863e-05, - "loss": 2.0621, - "step": 275000 - }, - { - "epoch": 1.82, - "learning_rate": 4.818361628481952e-05, - "loss": 2.0709, - "step": 275500 - }, - { - "epoch": 1.82, - "learning_rate": 4.81803197626504e-05, - "loss": 2.0791, - "step": 276000 - }, - { - "epoch": 1.82, - "learning_rate": 4.817702324048129e-05, - "loss": 2.0757, - "step": 276500 - }, - { - "epoch": 1.83, - "learning_rate": 4.817372671831218e-05, - "loss": 2.0619, - "step": 277000 - }, - { - "epoch": 1.83, - "learning_rate": 4.8170430196143073e-05, - "loss": 2.072, - "step": 277500 - }, - { - "epoch": 1.83, - "learning_rate": 4.816713367397396e-05, - "loss": 2.0614, - "step": 278000 - }, - { - "epoch": 1.84, - "learning_rate": 4.816383715180485e-05, - "loss": 2.0811, - "step": 278500 - }, - { - "epoch": 1.84, - "learning_rate": 4.816054062963574e-05, - "loss": 2.069, - "step": 279000 - }, - { - "epoch": 1.84, - "learning_rate": 4.815724410746663e-05, - "loss": 2.0635, - "step": 279500 - }, - { - "epoch": 1.85, - "learning_rate": 4.815394758529752e-05, - "loss": 2.0698, - "step": 280000 - }, - { - "epoch": 1.85, - "learning_rate": 4.81506510631284e-05, - "loss": 2.0643, - "step": 280500 - }, - { - "epoch": 1.85, - "learning_rate": 4.8147354540959286e-05, - "loss": 2.0667, - "step": 281000 - }, - { - "epoch": 1.86, - "learning_rate": 4.8144058018790176e-05, - "loss": 2.072, - "step": 281500 - }, - { - "epoch": 1.86, - "learning_rate": 4.8140761496621067e-05, - "loss": 2.0675, - "step": 282000 - }, - { - "epoch": 1.86, - "learning_rate": 4.813746497445196e-05, - "loss": 2.0582, - "step": 282500 - }, - { - "epoch": 1.87, - "learning_rate": 4.813416845228285e-05, - "loss": 2.0688, - "step": 283000 - }, - { - "epoch": 1.87, - "learning_rate": 4.813087193011373e-05, - "loss": 2.0558, - "step": 283500 - }, - { - "epoch": 1.87, - "learning_rate": 4.812757540794462e-05, - "loss": 2.0658, - "step": 284000 - }, - { - "epoch": 1.88, - "learning_rate": 4.812427888577551e-05, - "loss": 2.0616, - "step": 284500 - }, - { - "epoch": 1.88, - "learning_rate": 4.8120982363606395e-05, - "loss": 2.0566, - "step": 285000 - }, - { - "epoch": 1.88, - "learning_rate": 4.8117685841437286e-05, - "loss": 2.0596, - "step": 285500 - }, - { - "epoch": 1.89, - "learning_rate": 4.811438931926817e-05, - "loss": 2.0577, - "step": 286000 - }, - { - "epoch": 1.89, - "learning_rate": 4.811109279709906e-05, - "loss": 2.0622, - "step": 286500 - }, - { - "epoch": 1.89, - "learning_rate": 4.810779627492995e-05, - "loss": 2.0498, - "step": 287000 - }, - { - "epoch": 1.9, - "learning_rate": 4.810449975276084e-05, - "loss": 2.0636, - "step": 287500 - }, - { - "epoch": 1.9, - "learning_rate": 4.810120323059173e-05, - "loss": 2.062, - "step": 288000 - }, - { - "epoch": 1.9, - "learning_rate": 4.809790670842262e-05, - "loss": 2.0591, - "step": 288500 - }, - { - "epoch": 1.91, - "learning_rate": 4.8094610186253505e-05, - "loss": 2.0618, - "step": 289000 - }, - { - "epoch": 1.91, - "learning_rate": 4.8091313664084395e-05, - "loss": 2.0556, - "step": 289500 - }, - { - "epoch": 1.91, - "learning_rate": 4.808801714191528e-05, - "loss": 2.0557, - "step": 290000 - }, - { - "epoch": 1.92, - "learning_rate": 4.808472061974617e-05, - "loss": 2.0565, - "step": 290500 - }, - { - "epoch": 1.92, - "learning_rate": 4.808142409757706e-05, - "loss": 2.0543, - "step": 291000 - }, - { - "epoch": 1.92, - "learning_rate": 4.807812757540795e-05, - "loss": 2.0672, - "step": 291500 - }, - { - "epoch": 1.93, - "learning_rate": 4.8074831053238834e-05, - "loss": 2.0575, - "step": 292000 - }, - { - "epoch": 1.93, - "learning_rate": 4.8071534531069724e-05, - "loss": 2.0482, - "step": 292500 - }, - { - "epoch": 1.93, - "learning_rate": 4.8068238008900614e-05, - "loss": 2.0529, - "step": 293000 - }, - { - "epoch": 1.94, - "learning_rate": 4.8064941486731505e-05, - "loss": 2.0479, - "step": 293500 - }, - { - "epoch": 1.94, - "learning_rate": 4.806164496456239e-05, - "loss": 2.0533, - "step": 294000 - }, - { - "epoch": 1.94, - "learning_rate": 4.805834844239327e-05, - "loss": 2.0459, - "step": 294500 - }, - { - "epoch": 1.94, - "learning_rate": 4.805505192022416e-05, - "loss": 2.0473, - "step": 295000 - }, - { - "epoch": 1.95, - "learning_rate": 4.805175539805505e-05, - "loss": 2.0509, - "step": 295500 - }, - { - "epoch": 1.95, - "learning_rate": 4.804845887588594e-05, - "loss": 2.0521, - "step": 296000 - }, - { - "epoch": 1.95, - "learning_rate": 4.8045162353716833e-05, - "loss": 2.0475, - "step": 296500 - }, - { - "epoch": 1.96, - "learning_rate": 4.8041865831547724e-05, - "loss": 2.0503, - "step": 297000 - }, - { - "epoch": 1.96, - "learning_rate": 4.803856930937861e-05, - "loss": 2.037, - "step": 297500 - }, - { - "epoch": 1.96, - "learning_rate": 4.80352727872095e-05, - "loss": 2.0526, - "step": 298000 - }, - { - "epoch": 1.97, - "learning_rate": 4.803197626504038e-05, - "loss": 2.0473, - "step": 298500 - }, - { - "epoch": 1.97, - "learning_rate": 4.802867974287127e-05, - "loss": 2.0475, - "step": 299000 - }, - { - "epoch": 1.97, - "learning_rate": 4.802538322070216e-05, - "loss": 2.0461, - "step": 299500 - }, - { - "epoch": 1.98, - "learning_rate": 4.8022086698533046e-05, - "loss": 2.054, - "step": 300000 - }, - { - "epoch": 1.98, - "learning_rate": 4.8018790176363936e-05, - "loss": 2.0484, - "step": 300500 - }, - { - "epoch": 1.98, - "learning_rate": 4.8015493654194827e-05, - "loss": 2.0468, - "step": 301000 - }, - { - "epoch": 1.99, - "learning_rate": 4.801219713202572e-05, - "loss": 2.0497, - "step": 301500 - }, - { - "epoch": 1.99, - "learning_rate": 4.800890060985661e-05, - "loss": 2.0463, - "step": 302000 - }, - { - "epoch": 1.99, - "learning_rate": 4.80056040876875e-05, - "loss": 2.0453, - "step": 302500 - }, - { - "epoch": 2.0, - "learning_rate": 4.800230756551838e-05, - "loss": 2.0459, - "step": 303000 - }, - { - "epoch": 2.0, - "learning_rate": 4.7999011043349265e-05, - "loss": 2.0398, - "step": 303500 - }, - { - "epoch": 2.0, - "learning_rate": 4.7995714521180155e-05, - "loss": 2.0366, - "step": 304000 - }, - { - "epoch": 2.01, - "learning_rate": 4.7992417999011046e-05, - "loss": 2.0345, - "step": 304500 - }, - { - "epoch": 2.01, - "learning_rate": 4.7989121476841936e-05, - "loss": 2.0319, - "step": 305000 - }, - { - "epoch": 2.01, - "learning_rate": 4.798582495467282e-05, - "loss": 2.0342, - "step": 305500 - }, - { - "epoch": 2.02, - "learning_rate": 4.798252843250371e-05, - "loss": 2.037, - "step": 306000 - }, - { - "epoch": 2.02, - "learning_rate": 4.79792319103346e-05, - "loss": 2.028, - "step": 306500 - }, - { - "epoch": 2.02, - "learning_rate": 4.797593538816549e-05, - "loss": 2.0301, - "step": 307000 - }, - { - "epoch": 2.03, - "learning_rate": 4.7972638865996374e-05, - "loss": 2.0348, - "step": 307500 - }, - { - "epoch": 2.03, - "learning_rate": 4.7969342343827265e-05, - "loss": 2.0265, - "step": 308000 - }, - { - "epoch": 2.03, - "learning_rate": 4.796604582165815e-05, - "loss": 2.0399, - "step": 308500 - }, - { - "epoch": 2.04, - "learning_rate": 4.796274929948904e-05, - "loss": 2.0382, - "step": 309000 - }, - { - "epoch": 2.04, - "learning_rate": 4.795945277731993e-05, - "loss": 2.0314, - "step": 309500 - }, - { - "epoch": 2.04, - "learning_rate": 4.795615625515082e-05, - "loss": 2.0345, - "step": 310000 - }, - { - "epoch": 2.05, - "learning_rate": 4.795285973298171e-05, - "loss": 2.0239, - "step": 310500 - }, - { - "epoch": 2.05, - "learning_rate": 4.7949563210812594e-05, - "loss": 2.0299, - "step": 311000 - }, - { - "epoch": 2.05, - "learning_rate": 4.7946266688643484e-05, - "loss": 2.0255, - "step": 311500 - }, - { - "epoch": 2.06, - "learning_rate": 4.7942970166474374e-05, - "loss": 2.0303, - "step": 312000 - }, - { - "epoch": 2.06, - "learning_rate": 4.793967364430526e-05, - "loss": 2.0196, - "step": 312500 - }, - { - "epoch": 2.06, - "learning_rate": 4.793637712213615e-05, - "loss": 2.0255, - "step": 313000 - }, - { - "epoch": 2.07, - "learning_rate": 4.793308059996704e-05, - "loss": 2.0247, - "step": 313500 - }, - { - "epoch": 2.07, - "learning_rate": 4.792978407779792e-05, - "loss": 2.0255, - "step": 314000 - }, - { - "epoch": 2.07, - "learning_rate": 4.792648755562881e-05, - "loss": 2.0231, - "step": 314500 - }, - { - "epoch": 2.08, - "learning_rate": 4.79231910334597e-05, - "loss": 2.0329, - "step": 315000 - }, - { - "epoch": 2.08, - "learning_rate": 4.7919894511290593e-05, - "loss": 2.0253, - "step": 315500 - }, - { - "epoch": 2.08, - "learning_rate": 4.7916597989121484e-05, - "loss": 2.0218, - "step": 316000 - }, - { - "epoch": 2.09, - "learning_rate": 4.791330146695237e-05, - "loss": 2.0269, - "step": 316500 - }, - { - "epoch": 2.09, - "learning_rate": 4.791000494478325e-05, - "loss": 2.0294, - "step": 317000 - }, - { - "epoch": 2.09, - "learning_rate": 4.790670842261414e-05, - "loss": 2.0223, - "step": 317500 - }, - { - "epoch": 2.1, - "learning_rate": 4.790341190044503e-05, - "loss": 2.0177, - "step": 318000 - }, - { - "epoch": 2.1, - "learning_rate": 4.790011537827592e-05, - "loss": 2.0223, - "step": 318500 - }, - { - "epoch": 2.1, - "learning_rate": 4.789681885610681e-05, - "loss": 2.0276, - "step": 319000 - }, - { - "epoch": 2.11, - "learning_rate": 4.7893522333937696e-05, - "loss": 2.0244, - "step": 319500 - }, - { - "epoch": 2.11, - "learning_rate": 4.7890225811768587e-05, - "loss": 2.0176, - "step": 320000 - }, - { - "epoch": 2.11, - "learning_rate": 4.788692928959948e-05, - "loss": 2.0182, - "step": 320500 - }, - { - "epoch": 2.12, - "learning_rate": 4.788363276743037e-05, - "loss": 2.017, - "step": 321000 - }, - { - "epoch": 2.12, - "learning_rate": 4.788033624526125e-05, - "loss": 2.0247, - "step": 321500 - }, - { - "epoch": 2.12, - "learning_rate": 4.7877039723092135e-05, - "loss": 2.0193, - "step": 322000 - }, - { - "epoch": 2.13, - "learning_rate": 4.7873743200923025e-05, - "loss": 2.0247, - "step": 322500 - }, - { - "epoch": 2.13, - "learning_rate": 4.7870446678753915e-05, - "loss": 2.0177, - "step": 323000 - }, - { - "epoch": 2.13, - "learning_rate": 4.7867150156584806e-05, - "loss": 2.0159, - "step": 323500 - }, - { - "epoch": 2.14, - "learning_rate": 4.7863853634415696e-05, - "loss": 2.0252, - "step": 324000 - }, - { - "epoch": 2.14, - "learning_rate": 4.7860557112246586e-05, - "loss": 2.0194, - "step": 324500 - }, - { - "epoch": 2.14, - "learning_rate": 4.785726059007747e-05, - "loss": 2.0153, - "step": 325000 - }, - { - "epoch": 2.15, - "learning_rate": 4.785396406790836e-05, - "loss": 2.0146, - "step": 325500 - }, - { - "epoch": 2.15, - "learning_rate": 4.7850667545739244e-05, - "loss": 2.0176, - "step": 326000 - }, - { - "epoch": 2.15, - "learning_rate": 4.7847371023570134e-05, - "loss": 2.0137, - "step": 326500 - }, - { - "epoch": 2.16, - "learning_rate": 4.7844074501401025e-05, - "loss": 2.0203, - "step": 327000 - }, - { - "epoch": 2.16, - "learning_rate": 4.784077797923191e-05, - "loss": 2.0092, - "step": 327500 - }, - { - "epoch": 2.16, - "learning_rate": 4.78374814570628e-05, - "loss": 2.0148, - "step": 328000 - }, - { - "epoch": 2.17, - "learning_rate": 4.783418493489369e-05, - "loss": 2.0177, - "step": 328500 - }, - { - "epoch": 2.17, - "learning_rate": 4.783088841272458e-05, - "loss": 2.0177, - "step": 329000 - }, - { - "epoch": 2.17, - "learning_rate": 4.782759189055547e-05, - "loss": 2.0151, - "step": 329500 - }, - { - "epoch": 2.18, - "learning_rate": 4.782429536838636e-05, - "loss": 2.0159, - "step": 330000 - }, - { - "epoch": 2.18, - "learning_rate": 4.7820998846217244e-05, - "loss": 2.0156, - "step": 330500 - }, - { - "epoch": 2.18, - "learning_rate": 4.781770232404813e-05, - "loss": 2.015, - "step": 331000 - }, - { - "epoch": 2.19, - "learning_rate": 4.781440580187902e-05, - "loss": 2.0068, - "step": 331500 - }, - { - "epoch": 2.19, - "learning_rate": 4.781110927970991e-05, - "loss": 2.002, - "step": 332000 - }, - { - "epoch": 2.19, - "learning_rate": 4.78078127575408e-05, - "loss": 2.0046, - "step": 332500 - }, - { - "epoch": 2.2, - "learning_rate": 4.780451623537168e-05, - "loss": 2.0183, - "step": 333000 - }, - { - "epoch": 2.2, - "learning_rate": 4.780121971320257e-05, - "loss": 2.0091, - "step": 333500 - }, - { - "epoch": 2.2, - "learning_rate": 4.779792319103346e-05, - "loss": 2.0098, - "step": 334000 - }, - { - "epoch": 2.21, - "learning_rate": 4.7794626668864353e-05, - "loss": 2.0088, - "step": 334500 - }, - { - "epoch": 2.21, - "learning_rate": 4.779133014669524e-05, - "loss": 2.0047, - "step": 335000 - }, - { - "epoch": 2.21, - "learning_rate": 4.778803362452613e-05, - "loss": 2.0057, - "step": 335500 - }, - { - "epoch": 2.22, - "learning_rate": 4.778473710235701e-05, - "loss": 2.0036, - "step": 336000 - }, - { - "epoch": 2.22, - "learning_rate": 4.77814405801879e-05, - "loss": 2.0054, - "step": 336500 - }, - { - "epoch": 2.22, - "learning_rate": 4.777814405801879e-05, - "loss": 2.0158, - "step": 337000 - }, - { - "epoch": 2.23, - "learning_rate": 4.777484753584968e-05, - "loss": 2.0196, - "step": 337500 - }, - { - "epoch": 2.23, - "learning_rate": 4.777155101368057e-05, - "loss": 2.0045, - "step": 338000 - }, - { - "epoch": 2.23, - "learning_rate": 4.7768254491511456e-05, - "loss": 2.0045, - "step": 338500 - }, - { - "epoch": 2.24, - "learning_rate": 4.7764957969342347e-05, - "loss": 2.0054, - "step": 339000 - }, - { - "epoch": 2.24, - "learning_rate": 4.776166144717324e-05, - "loss": 2.0048, - "step": 339500 - }, - { - "epoch": 2.24, - "learning_rate": 4.775836492500412e-05, - "loss": 2.005, - "step": 340000 - }, - { - "epoch": 2.24, - "learning_rate": 4.775506840283501e-05, - "loss": 2.0032, - "step": 340500 - }, - { - "epoch": 2.25, - "learning_rate": 4.77517718806659e-05, - "loss": 1.9931, - "step": 341000 - }, - { - "epoch": 2.25, - "learning_rate": 4.7748475358496785e-05, - "loss": 2.0063, - "step": 341500 - }, - { - "epoch": 2.25, - "learning_rate": 4.7745178836327675e-05, - "loss": 2.0071, - "step": 342000 - }, - { - "epoch": 2.26, - "learning_rate": 4.7741882314158566e-05, - "loss": 2.0006, - "step": 342500 - }, - { - "epoch": 2.26, - "learning_rate": 4.7738585791989456e-05, - "loss": 2.0062, - "step": 343000 - }, - { - "epoch": 2.26, - "learning_rate": 4.7735289269820346e-05, - "loss": 2.0062, - "step": 343500 - }, - { - "epoch": 2.27, - "learning_rate": 4.773199274765123e-05, - "loss": 2.0091, - "step": 344000 - }, - { - "epoch": 2.27, - "learning_rate": 4.7728696225482114e-05, - "loss": 1.9992, - "step": 344500 - }, - { - "epoch": 2.27, - "learning_rate": 4.7725399703313004e-05, - "loss": 2.0015, - "step": 345000 - }, - { - "epoch": 2.28, - "learning_rate": 4.7722103181143894e-05, - "loss": 2.01, - "step": 345500 - }, - { - "epoch": 2.28, - "learning_rate": 4.7718806658974785e-05, - "loss": 1.9914, - "step": 346000 - }, - { - "epoch": 2.28, - "learning_rate": 4.7715510136805675e-05, - "loss": 2.0039, - "step": 346500 - }, - { - "epoch": 2.29, - "learning_rate": 4.771221361463656e-05, - "loss": 2.0001, - "step": 347000 - }, - { - "epoch": 2.29, - "learning_rate": 4.770891709246745e-05, - "loss": 2.0027, - "step": 347500 - }, - { - "epoch": 2.29, - "learning_rate": 4.770562057029834e-05, - "loss": 1.9988, - "step": 348000 - }, - { - "epoch": 2.3, - "learning_rate": 4.770232404812923e-05, - "loss": 2.0, - "step": 348500 - }, - { - "epoch": 2.3, - "learning_rate": 4.7699027525960114e-05, - "loss": 1.9909, - "step": 349000 - }, - { - "epoch": 2.3, - "learning_rate": 4.7695731003791004e-05, - "loss": 2.001, - "step": 349500 - }, - { - "epoch": 2.31, - "learning_rate": 4.769243448162189e-05, - "loss": 1.997, - "step": 350000 - }, - { - "epoch": 2.31, - "learning_rate": 4.768913795945278e-05, - "loss": 2.0026, - "step": 350500 - }, - { - "epoch": 2.31, - "learning_rate": 4.768584143728367e-05, - "loss": 2.004, - "step": 351000 - }, - { - "epoch": 2.32, - "learning_rate": 4.768254491511456e-05, - "loss": 1.9978, - "step": 351500 - }, - { - "epoch": 2.32, - "learning_rate": 4.767924839294545e-05, - "loss": 1.9952, - "step": 352000 - }, - { - "epoch": 2.32, - "learning_rate": 4.767595187077633e-05, - "loss": 1.9902, - "step": 352500 - }, - { - "epoch": 2.33, - "learning_rate": 4.767265534860722e-05, - "loss": 1.9957, - "step": 353000 - }, - { - "epoch": 2.33, - "learning_rate": 4.766935882643811e-05, - "loss": 2.0053, - "step": 353500 - }, - { - "epoch": 2.33, - "learning_rate": 4.7666062304269e-05, - "loss": 1.9963, - "step": 354000 - }, - { - "epoch": 2.34, - "learning_rate": 4.766276578209989e-05, - "loss": 1.9905, - "step": 354500 - }, - { - "epoch": 2.34, - "learning_rate": 4.765946925993078e-05, - "loss": 1.9893, - "step": 355000 - }, - { - "epoch": 2.34, - "learning_rate": 4.765617273776166e-05, - "loss": 1.9998, - "step": 355500 - }, - { - "epoch": 2.35, - "learning_rate": 4.765287621559255e-05, - "loss": 1.9844, - "step": 356000 - }, - { - "epoch": 2.35, - "learning_rate": 4.764957969342344e-05, - "loss": 1.9882, - "step": 356500 - }, - { - "epoch": 2.35, - "learning_rate": 4.764628317125433e-05, - "loss": 1.9944, - "step": 357000 - }, - { - "epoch": 2.36, - "learning_rate": 4.7642986649085216e-05, - "loss": 1.9905, - "step": 357500 - }, - { - "epoch": 2.36, - "learning_rate": 4.7639690126916107e-05, - "loss": 1.9897, - "step": 358000 - }, - { - "epoch": 2.36, - "learning_rate": 4.763639360474699e-05, - "loss": 1.9895, - "step": 358500 - }, - { - "epoch": 2.37, - "learning_rate": 4.763309708257788e-05, - "loss": 1.9878, - "step": 359000 - }, - { - "epoch": 2.37, - "learning_rate": 4.762980056040877e-05, - "loss": 1.9992, - "step": 359500 - }, - { - "epoch": 2.37, - "learning_rate": 4.762650403823966e-05, - "loss": 1.9938, - "step": 360000 - }, - { - "epoch": 2.38, - "learning_rate": 4.762320751607055e-05, - "loss": 1.9855, - "step": 360500 - }, - { - "epoch": 2.38, - "learning_rate": 4.7619910993901435e-05, - "loss": 1.9906, - "step": 361000 - }, - { - "epoch": 2.38, - "learning_rate": 4.7616614471732326e-05, - "loss": 1.9893, - "step": 361500 - }, - { - "epoch": 2.39, - "learning_rate": 4.7613317949563216e-05, - "loss": 1.9878, - "step": 362000 - }, - { - "epoch": 2.39, - "learning_rate": 4.76100214273941e-05, - "loss": 1.9812, - "step": 362500 - }, - { - "epoch": 2.39, - "learning_rate": 4.760672490522499e-05, - "loss": 1.9923, - "step": 363000 - }, - { - "epoch": 2.4, - "learning_rate": 4.7603428383055874e-05, - "loss": 1.9963, - "step": 363500 - }, - { - "epoch": 2.4, - "learning_rate": 4.7600131860886764e-05, - "loss": 1.9902, - "step": 364000 - }, - { - "epoch": 2.4, - "learning_rate": 4.7596835338717654e-05, - "loss": 1.9864, - "step": 364500 - }, - { - "epoch": 2.41, - "learning_rate": 4.7593538816548545e-05, - "loss": 1.9904, - "step": 365000 - }, - { - "epoch": 2.41, - "learning_rate": 4.7590242294379435e-05, - "loss": 1.9957, - "step": 365500 - }, - { - "epoch": 2.41, - "learning_rate": 4.7586945772210326e-05, - "loss": 1.9898, - "step": 366000 - }, - { - "epoch": 2.42, - "learning_rate": 4.758364925004121e-05, - "loss": 1.9824, - "step": 366500 - }, - { - "epoch": 2.42, - "learning_rate": 4.75803527278721e-05, - "loss": 1.985, - "step": 367000 - }, - { - "epoch": 2.42, - "learning_rate": 4.757705620570298e-05, - "loss": 1.9824, - "step": 367500 - }, - { - "epoch": 2.43, - "learning_rate": 4.7573759683533874e-05, - "loss": 1.9907, - "step": 368000 - }, - { - "epoch": 2.43, - "learning_rate": 4.7570463161364764e-05, - "loss": 1.9853, - "step": 368500 - }, - { - "epoch": 2.43, - "learning_rate": 4.756716663919565e-05, - "loss": 1.9876, - "step": 369000 - }, - { - "epoch": 2.44, - "learning_rate": 4.756387011702654e-05, - "loss": 1.9796, - "step": 369500 - }, - { - "epoch": 2.44, - "learning_rate": 4.756057359485743e-05, - "loss": 1.9924, - "step": 370000 - }, - { - "epoch": 2.44, - "learning_rate": 4.755727707268832e-05, - "loss": 1.9744, - "step": 370500 - }, - { - "epoch": 2.45, - "learning_rate": 4.755398055051921e-05, - "loss": 1.9794, - "step": 371000 - }, - { - "epoch": 2.45, - "learning_rate": 4.755068402835009e-05, - "loss": 1.9855, - "step": 371500 - }, - { - "epoch": 2.45, - "learning_rate": 4.7547387506180976e-05, - "loss": 1.9773, - "step": 372000 - }, - { - "epoch": 2.46, - "learning_rate": 4.754409098401187e-05, - "loss": 1.9847, - "step": 372500 - }, - { - "epoch": 2.46, - "learning_rate": 4.754079446184276e-05, - "loss": 1.9694, - "step": 373000 - }, - { - "epoch": 2.46, - "learning_rate": 4.753749793967365e-05, - "loss": 1.9854, - "step": 373500 - }, - { - "epoch": 2.47, - "learning_rate": 4.753420141750454e-05, - "loss": 1.9853, - "step": 374000 - }, - { - "epoch": 2.47, - "learning_rate": 4.753090489533542e-05, - "loss": 1.9788, - "step": 374500 - }, - { - "epoch": 2.47, - "learning_rate": 4.752760837316631e-05, - "loss": 1.9858, - "step": 375000 - }, - { - "epoch": 2.48, - "learning_rate": 4.75243118509972e-05, - "loss": 1.9791, - "step": 375500 - }, - { - "epoch": 2.48, - "learning_rate": 4.7521015328828086e-05, - "loss": 1.9745, - "step": 376000 - }, - { - "epoch": 2.48, - "learning_rate": 4.7517718806658976e-05, - "loss": 1.9848, - "step": 376500 - }, - { - "epoch": 2.49, - "learning_rate": 4.7514422284489867e-05, - "loss": 1.9762, - "step": 377000 - }, - { - "epoch": 2.49, - "learning_rate": 4.751112576232075e-05, - "loss": 1.978, - "step": 377500 - }, - { - "epoch": 2.49, - "learning_rate": 4.750782924015164e-05, - "loss": 1.9726, - "step": 378000 - }, - { - "epoch": 2.5, - "learning_rate": 4.750453271798253e-05, - "loss": 1.98, - "step": 378500 - }, - { - "epoch": 2.5, - "learning_rate": 4.750123619581342e-05, - "loss": 1.982, - "step": 379000 - }, - { - "epoch": 2.5, - "learning_rate": 4.749793967364431e-05, - "loss": 1.9801, - "step": 379500 - }, - { - "epoch": 2.51, - "learning_rate": 4.7494643151475195e-05, - "loss": 1.9775, - "step": 380000 - }, - { - "epoch": 2.51, - "learning_rate": 4.7491346629306086e-05, - "loss": 1.9764, - "step": 380500 - }, - { - "epoch": 2.51, - "learning_rate": 4.748805010713697e-05, - "loss": 1.9821, - "step": 381000 - }, - { - "epoch": 2.52, - "learning_rate": 4.748475358496786e-05, - "loss": 1.9733, - "step": 381500 - }, - { - "epoch": 2.52, - "learning_rate": 4.748145706279875e-05, - "loss": 1.9703, - "step": 382000 - }, - { - "epoch": 2.52, - "learning_rate": 4.747816054062964e-05, - "loss": 1.9771, - "step": 382500 - }, - { - "epoch": 2.53, - "learning_rate": 4.7474864018460524e-05, - "loss": 1.9721, - "step": 383000 - }, - { - "epoch": 2.53, - "learning_rate": 4.7471567496291414e-05, - "loss": 1.9811, - "step": 383500 - }, - { - "epoch": 2.53, - "learning_rate": 4.7468270974122305e-05, - "loss": 1.9759, - "step": 384000 - }, - { - "epoch": 2.54, - "learning_rate": 4.7464974451953195e-05, - "loss": 1.9708, - "step": 384500 - }, - { - "epoch": 2.54, - "learning_rate": 4.746167792978408e-05, - "loss": 1.9718, - "step": 385000 - }, - { - "epoch": 2.54, - "learning_rate": 4.745838140761497e-05, - "loss": 1.9675, - "step": 385500 - }, - { - "epoch": 2.54, - "learning_rate": 4.745508488544585e-05, - "loss": 1.9655, - "step": 386000 - }, - { - "epoch": 2.55, - "learning_rate": 4.745178836327674e-05, - "loss": 1.97, - "step": 386500 - }, - { - "epoch": 2.55, - "learning_rate": 4.7448491841107633e-05, - "loss": 1.9584, - "step": 387000 - }, - { - "epoch": 2.55, - "learning_rate": 4.7445195318938524e-05, - "loss": 1.9667, - "step": 387500 - }, - { - "epoch": 2.56, - "learning_rate": 4.7441898796769414e-05, - "loss": 1.961, - "step": 388000 - }, - { - "epoch": 2.56, - "learning_rate": 4.74386022746003e-05, - "loss": 1.9696, - "step": 388500 - }, - { - "epoch": 2.56, - "learning_rate": 4.743530575243119e-05, - "loss": 1.9621, - "step": 389000 - }, - { - "epoch": 2.57, - "learning_rate": 4.743200923026208e-05, - "loss": 1.9661, - "step": 389500 - }, - { - "epoch": 2.57, - "learning_rate": 4.742871270809296e-05, - "loss": 1.967, - "step": 390000 - }, - { - "epoch": 2.57, - "learning_rate": 4.742541618592385e-05, - "loss": 1.964, - "step": 390500 - }, - { - "epoch": 2.58, - "learning_rate": 4.742211966375474e-05, - "loss": 1.9727, - "step": 391000 - }, - { - "epoch": 2.58, - "learning_rate": 4.7418823141585627e-05, - "loss": 1.9583, - "step": 391500 - }, - { - "epoch": 2.58, - "learning_rate": 4.741552661941652e-05, - "loss": 1.9669, - "step": 392000 - }, - { - "epoch": 2.59, - "learning_rate": 4.741223009724741e-05, - "loss": 1.9679, - "step": 392500 - }, - { - "epoch": 2.59, - "learning_rate": 4.74089335750783e-05, - "loss": 1.9583, - "step": 393000 - }, - { - "epoch": 2.59, - "learning_rate": 4.740563705290919e-05, - "loss": 1.9706, - "step": 393500 - }, - { - "epoch": 2.6, - "learning_rate": 4.740234053074007e-05, - "loss": 1.9673, - "step": 394000 - }, - { - "epoch": 2.6, - "learning_rate": 4.7399044008570955e-05, - "loss": 1.971, - "step": 394500 - }, - { - "epoch": 2.6, - "learning_rate": 4.7395747486401846e-05, - "loss": 1.9604, - "step": 395000 - }, - { - "epoch": 2.61, - "learning_rate": 4.7392450964232736e-05, - "loss": 1.9639, - "step": 395500 - }, - { - "epoch": 2.61, - "learning_rate": 4.7389154442063626e-05, - "loss": 1.9628, - "step": 396000 - }, - { - "epoch": 2.61, - "learning_rate": 4.738585791989452e-05, - "loss": 1.9705, - "step": 396500 - }, - { - "epoch": 2.62, - "learning_rate": 4.73825613977254e-05, - "loss": 1.9594, - "step": 397000 - }, - { - "epoch": 2.62, - "learning_rate": 4.737926487555629e-05, - "loss": 1.9612, - "step": 397500 - }, - { - "epoch": 2.62, - "learning_rate": 4.737596835338718e-05, - "loss": 1.9618, - "step": 398000 - }, - { - "epoch": 2.63, - "learning_rate": 4.737267183121807e-05, - "loss": 1.9694, - "step": 398500 - }, - { - "epoch": 2.63, - "learning_rate": 4.7369375309048955e-05, - "loss": 1.9529, - "step": 399000 - }, - { - "epoch": 2.63, - "learning_rate": 4.736607878687984e-05, - "loss": 1.9589, - "step": 399500 - }, - { - "epoch": 2.64, - "learning_rate": 4.736278226471073e-05, - "loss": 1.97, - "step": 400000 - }, - { - "epoch": 2.64, - "learning_rate": 4.735948574254162e-05, - "loss": 1.9609, - "step": 400500 - }, - { - "epoch": 2.64, - "learning_rate": 4.735618922037251e-05, - "loss": 1.9638, - "step": 401000 - }, - { - "epoch": 2.65, - "learning_rate": 4.73528926982034e-05, - "loss": 1.9615, - "step": 401500 - }, - { - "epoch": 2.65, - "learning_rate": 4.734959617603429e-05, - "loss": 1.9617, - "step": 402000 - }, - { - "epoch": 2.65, - "learning_rate": 4.7346299653865174e-05, - "loss": 1.9696, - "step": 402500 - }, - { - "epoch": 2.66, - "learning_rate": 4.7343003131696065e-05, - "loss": 1.9613, - "step": 403000 - }, - { - "epoch": 2.66, - "learning_rate": 4.733970660952695e-05, - "loss": 1.9588, - "step": 403500 - }, - { - "epoch": 2.66, - "learning_rate": 4.733641008735784e-05, - "loss": 1.9603, - "step": 404000 - }, - { - "epoch": 2.67, - "learning_rate": 4.733311356518873e-05, - "loss": 1.9608, - "step": 404500 - }, - { - "epoch": 2.67, - "learning_rate": 4.732981704301961e-05, - "loss": 1.9636, - "step": 405000 - }, - { - "epoch": 2.67, - "learning_rate": 4.73265205208505e-05, - "loss": 1.9651, - "step": 405500 - }, - { - "epoch": 2.68, - "learning_rate": 4.7323223998681393e-05, - "loss": 1.9656, - "step": 406000 - }, - { - "epoch": 2.68, - "learning_rate": 4.7319927476512284e-05, - "loss": 1.9554, - "step": 406500 - }, - { - "epoch": 2.68, - "learning_rate": 4.7316630954343174e-05, - "loss": 1.9631, - "step": 407000 - }, - { - "epoch": 2.69, - "learning_rate": 4.7313334432174065e-05, - "loss": 1.9568, - "step": 407500 - }, - { - "epoch": 2.69, - "learning_rate": 4.731003791000495e-05, - "loss": 1.9642, - "step": 408000 - }, - { - "epoch": 2.69, - "learning_rate": 4.730674138783583e-05, - "loss": 1.9524, - "step": 408500 - }, - { - "epoch": 2.7, - "learning_rate": 4.730344486566672e-05, - "loss": 1.9578, - "step": 409000 - }, - { - "epoch": 2.7, - "learning_rate": 4.730014834349761e-05, - "loss": 1.9653, - "step": 409500 - }, - { - "epoch": 2.7, - "learning_rate": 4.72968518213285e-05, - "loss": 1.9632, - "step": 410000 - }, - { - "epoch": 2.71, - "learning_rate": 4.7293555299159387e-05, - "loss": 1.9589, - "step": 410500 - }, - { - "epoch": 2.71, - "learning_rate": 4.729025877699028e-05, - "loss": 1.9612, - "step": 411000 - }, - { - "epoch": 2.71, - "learning_rate": 4.728696225482117e-05, - "loss": 1.9475, - "step": 411500 - }, - { - "epoch": 2.72, - "learning_rate": 4.728366573265206e-05, - "loss": 1.9505, - "step": 412000 - }, - { - "epoch": 2.72, - "learning_rate": 4.728036921048294e-05, - "loss": 1.949, - "step": 412500 - }, - { - "epoch": 2.72, - "learning_rate": 4.727707268831383e-05, - "loss": 1.9578, - "step": 413000 - }, - { - "epoch": 2.73, - "learning_rate": 4.7273776166144715e-05, - "loss": 1.9562, - "step": 413500 - }, - { - "epoch": 2.73, - "learning_rate": 4.7270479643975606e-05, - "loss": 1.9513, - "step": 414000 - }, - { - "epoch": 2.73, - "learning_rate": 4.7267183121806496e-05, - "loss": 1.9551, - "step": 414500 - }, - { - "epoch": 2.74, - "learning_rate": 4.7263886599637386e-05, - "loss": 1.9545, - "step": 415000 - }, - { - "epoch": 2.74, - "learning_rate": 4.726059007746828e-05, - "loss": 1.9585, - "step": 415500 - }, - { - "epoch": 2.74, - "learning_rate": 4.725729355529916e-05, - "loss": 1.9503, - "step": 416000 - }, - { - "epoch": 2.75, - "learning_rate": 4.725399703313005e-05, - "loss": 1.9584, - "step": 416500 - }, - { - "epoch": 2.75, - "learning_rate": 4.725070051096094e-05, - "loss": 1.9516, - "step": 417000 - }, - { - "epoch": 2.75, - "learning_rate": 4.7247403988791825e-05, - "loss": 1.9586, - "step": 417500 - }, - { - "epoch": 2.76, - "learning_rate": 4.7244107466622715e-05, - "loss": 1.9529, - "step": 418000 - }, - { - "epoch": 2.76, - "learning_rate": 4.7240810944453606e-05, - "loss": 1.9506, - "step": 418500 - }, - { - "epoch": 2.76, - "learning_rate": 4.723751442228449e-05, - "loss": 1.9535, - "step": 419000 - }, - { - "epoch": 2.77, - "learning_rate": 4.723421790011538e-05, - "loss": 1.9484, - "step": 419500 - }, - { - "epoch": 2.77, - "learning_rate": 4.723092137794627e-05, - "loss": 1.946, - "step": 420000 - }, - { - "epoch": 2.77, - "learning_rate": 4.722762485577716e-05, - "loss": 1.945, - "step": 420500 - }, - { - "epoch": 2.78, - "learning_rate": 4.722432833360805e-05, - "loss": 1.9436, - "step": 421000 - }, - { - "epoch": 2.78, - "learning_rate": 4.7221031811438934e-05, - "loss": 1.9461, - "step": 421500 - }, - { - "epoch": 2.78, - "learning_rate": 4.721773528926982e-05, - "loss": 1.9459, - "step": 422000 - }, - { - "epoch": 2.79, - "learning_rate": 4.721443876710071e-05, - "loss": 1.9469, - "step": 422500 - }, - { - "epoch": 2.79, - "learning_rate": 4.72111422449316e-05, - "loss": 1.9427, - "step": 423000 - }, - { - "epoch": 2.79, - "learning_rate": 4.720784572276249e-05, - "loss": 1.9419, - "step": 423500 - }, - { - "epoch": 2.8, - "learning_rate": 4.720454920059338e-05, - "loss": 1.9419, - "step": 424000 - }, - { - "epoch": 2.8, - "learning_rate": 4.720125267842426e-05, - "loss": 1.9578, - "step": 424500 - }, - { - "epoch": 2.8, - "learning_rate": 4.7197956156255153e-05, - "loss": 1.9465, - "step": 425000 - }, - { - "epoch": 2.81, - "learning_rate": 4.7194659634086044e-05, - "loss": 1.9541, - "step": 425500 - }, - { - "epoch": 2.81, - "learning_rate": 4.719136311191693e-05, - "loss": 1.9432, - "step": 426000 - }, - { - "epoch": 2.81, - "learning_rate": 4.718806658974782e-05, - "loss": 1.9535, - "step": 426500 - }, - { - "epoch": 2.82, - "learning_rate": 4.71847700675787e-05, - "loss": 1.9431, - "step": 427000 - }, - { - "epoch": 2.82, - "learning_rate": 4.718147354540959e-05, - "loss": 1.9551, - "step": 427500 - }, - { - "epoch": 2.82, - "learning_rate": 4.717817702324048e-05, - "loss": 1.9456, - "step": 428000 - }, - { - "epoch": 2.83, - "learning_rate": 4.717488050107137e-05, - "loss": 1.9401, - "step": 428500 - }, - { - "epoch": 2.83, - "learning_rate": 4.717158397890226e-05, - "loss": 1.9408, - "step": 429000 - }, - { - "epoch": 2.83, - "learning_rate": 4.716828745673315e-05, - "loss": 1.9461, - "step": 429500 - }, - { - "epoch": 2.84, - "learning_rate": 4.716499093456404e-05, - "loss": 1.9427, - "step": 430000 - }, - { - "epoch": 2.84, - "learning_rate": 4.716169441239493e-05, - "loss": 1.9426, - "step": 430500 - }, - { - "epoch": 2.84, - "learning_rate": 4.715839789022581e-05, - "loss": 1.9321, - "step": 431000 - }, - { - "epoch": 2.84, - "learning_rate": 4.71551013680567e-05, - "loss": 1.9436, - "step": 431500 - }, - { - "epoch": 2.85, - "learning_rate": 4.715180484588759e-05, - "loss": 1.9437, - "step": 432000 - }, - { - "epoch": 2.85, - "learning_rate": 4.7148508323718475e-05, - "loss": 1.9382, - "step": 432500 - }, - { - "epoch": 2.85, - "learning_rate": 4.7145211801549366e-05, - "loss": 1.9379, - "step": 433000 - }, - { - "epoch": 2.86, - "learning_rate": 4.7141915279380256e-05, - "loss": 1.9426, - "step": 433500 - }, - { - "epoch": 2.86, - "learning_rate": 4.7138618757211146e-05, - "loss": 1.9456, - "step": 434000 - }, - { - "epoch": 2.86, - "learning_rate": 4.713532223504204e-05, - "loss": 1.9334, - "step": 434500 - }, - { - "epoch": 2.87, - "learning_rate": 4.713202571287292e-05, - "loss": 1.9458, - "step": 435000 - }, - { - "epoch": 2.87, - "learning_rate": 4.712872919070381e-05, - "loss": 1.952, - "step": 435500 - }, - { - "epoch": 2.87, - "learning_rate": 4.7125432668534694e-05, - "loss": 1.9453, - "step": 436000 - }, - { - "epoch": 2.88, - "learning_rate": 4.7122136146365585e-05, - "loss": 1.9366, - "step": 436500 - }, - { - "epoch": 2.88, - "learning_rate": 4.7118839624196475e-05, - "loss": 1.939, - "step": 437000 - }, - { - "epoch": 2.88, - "learning_rate": 4.7115543102027366e-05, - "loss": 1.9457, - "step": 437500 - }, - { - "epoch": 2.89, - "learning_rate": 4.711224657985825e-05, - "loss": 1.9384, - "step": 438000 - }, - { - "epoch": 2.89, - "learning_rate": 4.710895005768914e-05, - "loss": 1.9262, - "step": 438500 - }, - { - "epoch": 2.89, - "learning_rate": 4.710565353552003e-05, - "loss": 1.9312, - "step": 439000 - }, - { - "epoch": 2.9, - "learning_rate": 4.710235701335092e-05, - "loss": 1.9386, - "step": 439500 - }, - { - "epoch": 2.9, - "learning_rate": 4.7099060491181804e-05, - "loss": 1.9426, - "step": 440000 - }, - { - "epoch": 2.9, - "learning_rate": 4.7095763969012694e-05, - "loss": 1.9395, - "step": 440500 - }, - { - "epoch": 2.91, - "learning_rate": 4.709246744684358e-05, - "loss": 1.9355, - "step": 441000 - }, - { - "epoch": 2.91, - "learning_rate": 4.708917092467447e-05, - "loss": 1.9402, - "step": 441500 - }, - { - "epoch": 2.91, - "learning_rate": 4.708587440250536e-05, - "loss": 1.9395, - "step": 442000 - }, - { - "epoch": 2.92, - "learning_rate": 4.708257788033625e-05, - "loss": 1.9358, - "step": 442500 - }, - { - "epoch": 2.92, - "learning_rate": 4.707928135816714e-05, - "loss": 1.9333, - "step": 443000 - }, - { - "epoch": 2.92, - "learning_rate": 4.707598483599803e-05, - "loss": 1.9361, - "step": 443500 - }, - { - "epoch": 2.93, - "learning_rate": 4.7072688313828913e-05, - "loss": 1.9377, - "step": 444000 - }, - { - "epoch": 2.93, - "learning_rate": 4.70693917916598e-05, - "loss": 1.9352, - "step": 444500 - }, - { - "epoch": 2.93, - "learning_rate": 4.706609526949069e-05, - "loss": 1.933, - "step": 445000 - }, - { - "epoch": 2.94, - "learning_rate": 4.706279874732158e-05, - "loss": 1.9359, - "step": 445500 - }, - { - "epoch": 2.94, - "learning_rate": 4.705950222515247e-05, - "loss": 1.937, - "step": 446000 - }, - { - "epoch": 2.94, - "learning_rate": 4.705620570298335e-05, - "loss": 1.9315, - "step": 446500 - }, - { - "epoch": 2.95, - "learning_rate": 4.705290918081424e-05, - "loss": 1.9307, - "step": 447000 - }, - { - "epoch": 2.95, - "learning_rate": 4.704961265864513e-05, - "loss": 1.9342, - "step": 447500 - }, - { - "epoch": 2.95, - "learning_rate": 4.704631613647602e-05, - "loss": 1.9369, - "step": 448000 - }, - { - "epoch": 2.96, - "learning_rate": 4.704301961430691e-05, - "loss": 1.9326, - "step": 448500 - }, - { - "epoch": 2.96, - "learning_rate": 4.70397230921378e-05, - "loss": 1.9299, - "step": 449000 - }, - { - "epoch": 2.96, - "learning_rate": 4.703642656996868e-05, - "loss": 1.9327, - "step": 449500 - }, - { - "epoch": 2.97, - "learning_rate": 4.703313004779957e-05, - "loss": 1.9339, - "step": 450000 - }, - { - "epoch": 2.97, - "learning_rate": 4.702983352563046e-05, - "loss": 1.9345, - "step": 450500 - }, - { - "epoch": 2.97, - "learning_rate": 4.702653700346135e-05, - "loss": 1.9369, - "step": 451000 - }, - { - "epoch": 2.98, - "learning_rate": 4.702324048129224e-05, - "loss": 1.9207, - "step": 451500 - }, - { - "epoch": 2.98, - "learning_rate": 4.7019943959123126e-05, - "loss": 1.9219, - "step": 452000 - }, - { - "epoch": 2.98, - "learning_rate": 4.7016647436954016e-05, - "loss": 1.928, - "step": 452500 - }, - { - "epoch": 2.99, - "learning_rate": 4.7013350914784906e-05, - "loss": 1.9305, - "step": 453000 - }, - { - "epoch": 2.99, - "learning_rate": 4.701005439261579e-05, - "loss": 1.936, - "step": 453500 - }, - { - "epoch": 2.99, - "learning_rate": 4.700675787044668e-05, - "loss": 1.9346, - "step": 454000 - }, - { - "epoch": 3.0, - "learning_rate": 4.700346134827757e-05, - "loss": 1.9369, - "step": 454500 - }, - { - "epoch": 3.0, - "learning_rate": 4.7000164826108454e-05, - "loss": 1.9352, - "step": 455000 - }, - { - "epoch": 3.0, - "learning_rate": 4.6996868303939345e-05, - "loss": 1.9301, - "step": 455500 - }, - { - "epoch": 3.01, - "learning_rate": 4.6993571781770235e-05, - "loss": 1.9218, - "step": 456000 - }, - { - "epoch": 3.01, - "learning_rate": 4.6990275259601126e-05, - "loss": 1.9205, - "step": 456500 - }, - { - "epoch": 3.01, - "learning_rate": 4.6986978737432016e-05, - "loss": 1.9264, - "step": 457000 - }, - { - "epoch": 3.02, - "learning_rate": 4.69836822152629e-05, - "loss": 1.9197, - "step": 457500 - }, - { - "epoch": 3.02, - "learning_rate": 4.698038569309379e-05, - "loss": 1.9277, - "step": 458000 - }, - { - "epoch": 3.02, - "learning_rate": 4.6977089170924674e-05, - "loss": 1.9248, - "step": 458500 - }, - { - "epoch": 3.03, - "learning_rate": 4.6973792648755564e-05, - "loss": 1.9217, - "step": 459000 - }, - { - "epoch": 3.03, - "learning_rate": 4.6970496126586454e-05, - "loss": 1.9296, - "step": 459500 - }, - { - "epoch": 3.03, - "learning_rate": 4.6967199604417345e-05, - "loss": 1.9226, - "step": 460000 - }, - { - "epoch": 3.04, - "learning_rate": 4.696390308224823e-05, - "loss": 1.9261, - "step": 460500 - }, - { - "epoch": 3.04, - "learning_rate": 4.696060656007912e-05, - "loss": 1.9155, - "step": 461000 - }, - { - "epoch": 3.04, - "learning_rate": 4.695731003791001e-05, - "loss": 1.9128, - "step": 461500 - }, - { - "epoch": 3.05, - "learning_rate": 4.69540135157409e-05, - "loss": 1.9199, - "step": 462000 - }, - { - "epoch": 3.05, - "learning_rate": 4.695071699357178e-05, - "loss": 1.9253, - "step": 462500 - }, - { - "epoch": 3.05, - "learning_rate": 4.694742047140267e-05, - "loss": 1.9244, - "step": 463000 - }, - { - "epoch": 3.06, - "learning_rate": 4.694412394923356e-05, - "loss": 1.9236, - "step": 463500 - }, - { - "epoch": 3.06, - "learning_rate": 4.694082742706445e-05, - "loss": 1.9285, - "step": 464000 - }, - { - "epoch": 3.06, - "learning_rate": 4.693753090489534e-05, - "loss": 1.9181, - "step": 464500 - }, - { - "epoch": 3.07, - "learning_rate": 4.693423438272623e-05, - "loss": 1.9255, - "step": 465000 - }, - { - "epoch": 3.07, - "learning_rate": 4.693093786055712e-05, - "loss": 1.9204, - "step": 465500 - }, - { - "epoch": 3.07, - "learning_rate": 4.6927641338388e-05, - "loss": 1.9271, - "step": 466000 - }, - { - "epoch": 3.08, - "learning_rate": 4.692434481621889e-05, - "loss": 1.9185, - "step": 466500 - }, - { - "epoch": 3.08, - "learning_rate": 4.692104829404978e-05, - "loss": 1.9219, - "step": 467000 - }, - { - "epoch": 3.08, - "learning_rate": 4.6917751771880667e-05, - "loss": 1.9205, - "step": 467500 - }, - { - "epoch": 3.09, - "learning_rate": 4.691445524971156e-05, - "loss": 1.9241, - "step": 468000 - }, - { - "epoch": 3.09, - "learning_rate": 4.691115872754244e-05, - "loss": 1.9302, - "step": 468500 - }, - { - "epoch": 3.09, - "learning_rate": 4.690786220537333e-05, - "loss": 1.9248, - "step": 469000 - }, - { - "epoch": 3.1, - "learning_rate": 4.690456568320422e-05, - "loss": 1.9138, - "step": 469500 - }, - { - "epoch": 3.1, - "learning_rate": 4.690126916103511e-05, - "loss": 1.9183, - "step": 470000 - }, - { - "epoch": 3.1, - "learning_rate": 4.6897972638866e-05, - "loss": 1.9242, - "step": 470500 - }, - { - "epoch": 3.11, - "learning_rate": 4.689467611669689e-05, - "loss": 1.9193, - "step": 471000 - }, - { - "epoch": 3.11, - "learning_rate": 4.6891379594527776e-05, - "loss": 1.9199, - "step": 471500 - }, - { - "epoch": 3.11, - "learning_rate": 4.688808307235866e-05, - "loss": 1.9107, - "step": 472000 - }, - { - "epoch": 3.12, - "learning_rate": 4.688478655018955e-05, - "loss": 1.9166, - "step": 472500 - }, - { - "epoch": 3.12, - "learning_rate": 4.688149002802044e-05, - "loss": 1.9127, - "step": 473000 - }, - { - "epoch": 3.12, - "learning_rate": 4.687819350585133e-05, - "loss": 1.9165, - "step": 473500 - }, - { - "epoch": 3.13, - "learning_rate": 4.6874896983682214e-05, - "loss": 1.9109, - "step": 474000 - }, - { - "epoch": 3.13, - "learning_rate": 4.6871600461513105e-05, - "loss": 1.9178, - "step": 474500 - }, - { - "epoch": 3.13, - "learning_rate": 4.6868303939343995e-05, - "loss": 1.9185, - "step": 475000 - }, - { - "epoch": 3.13, - "learning_rate": 4.6865007417174886e-05, - "loss": 1.9139, - "step": 475500 - }, - { - "epoch": 3.14, - "learning_rate": 4.6861710895005776e-05, - "loss": 1.9131, - "step": 476000 - }, - { - "epoch": 3.14, - "learning_rate": 4.685841437283666e-05, - "loss": 1.926, - "step": 476500 - }, - { - "epoch": 3.14, - "learning_rate": 4.685511785066754e-05, - "loss": 1.9176, - "step": 477000 - }, - { - "epoch": 3.15, - "learning_rate": 4.6851821328498434e-05, - "loss": 1.9203, - "step": 477500 - }, - { - "epoch": 3.15, - "learning_rate": 4.6848524806329324e-05, - "loss": 1.9235, - "step": 478000 - }, - { - "epoch": 3.15, - "learning_rate": 4.6845228284160214e-05, - "loss": 1.9192, - "step": 478500 - }, - { - "epoch": 3.16, - "learning_rate": 4.6841931761991105e-05, - "loss": 1.9122, - "step": 479000 - }, - { - "epoch": 3.16, - "learning_rate": 4.683863523982199e-05, - "loss": 1.9083, - "step": 479500 - }, - { - "epoch": 3.16, - "learning_rate": 4.683533871765288e-05, - "loss": 1.9175, - "step": 480000 - }, - { - "epoch": 3.17, - "learning_rate": 4.683204219548377e-05, - "loss": 1.9125, - "step": 480500 - }, - { - "epoch": 3.17, - "learning_rate": 4.682874567331465e-05, - "loss": 1.9101, - "step": 481000 - }, - { - "epoch": 3.17, - "learning_rate": 4.682544915114554e-05, - "loss": 1.9059, - "step": 481500 - }, - { - "epoch": 3.18, - "learning_rate": 4.6822152628976433e-05, - "loss": 1.9135, - "step": 482000 - }, - { - "epoch": 3.18, - "learning_rate": 4.681885610680732e-05, - "loss": 1.9199, - "step": 482500 - }, - { - "epoch": 3.18, - "learning_rate": 4.681555958463821e-05, - "loss": 1.9142, - "step": 483000 - }, - { - "epoch": 3.19, - "learning_rate": 4.68122630624691e-05, - "loss": 1.9156, - "step": 483500 - }, - { - "epoch": 3.19, - "learning_rate": 4.680896654029999e-05, - "loss": 1.9119, - "step": 484000 - }, - { - "epoch": 3.19, - "learning_rate": 4.680567001813088e-05, - "loss": 1.9141, - "step": 484500 - }, - { - "epoch": 3.2, - "learning_rate": 4.680237349596176e-05, - "loss": 1.9059, - "step": 485000 - }, - { - "epoch": 3.2, - "learning_rate": 4.679907697379265e-05, - "loss": 1.9163, - "step": 485500 - }, - { - "epoch": 3.2, - "learning_rate": 4.6795780451623536e-05, - "loss": 1.9135, - "step": 486000 - }, - { - "epoch": 3.21, - "learning_rate": 4.6792483929454427e-05, - "loss": 1.9118, - "step": 486500 - }, - { - "epoch": 3.21, - "learning_rate": 4.678918740728532e-05, - "loss": 1.9149, - "step": 487000 - }, - { - "epoch": 3.21, - "learning_rate": 4.678589088511621e-05, - "loss": 1.9072, - "step": 487500 - }, - { - "epoch": 3.22, - "learning_rate": 4.678259436294709e-05, - "loss": 1.9088, - "step": 488000 - }, - { - "epoch": 3.22, - "learning_rate": 4.677929784077798e-05, - "loss": 1.9113, - "step": 488500 - }, - { - "epoch": 3.22, - "learning_rate": 4.677600131860887e-05, - "loss": 1.9102, - "step": 489000 - }, - { - "epoch": 3.23, - "learning_rate": 4.677270479643976e-05, - "loss": 1.912, - "step": 489500 - }, - { - "epoch": 3.23, - "learning_rate": 4.6769408274270646e-05, - "loss": 1.9081, - "step": 490000 - }, - { - "epoch": 3.23, - "learning_rate": 4.676611175210153e-05, - "loss": 1.9195, - "step": 490500 - }, - { - "epoch": 3.24, - "learning_rate": 4.676281522993242e-05, - "loss": 1.9068, - "step": 491000 - }, - { - "epoch": 3.24, - "learning_rate": 4.675951870776331e-05, - "loss": 1.9067, - "step": 491500 - }, - { - "epoch": 3.24, - "learning_rate": 4.67562221855942e-05, - "loss": 1.9134, - "step": 492000 - }, - { - "epoch": 3.25, - "learning_rate": 4.675292566342509e-05, - "loss": 1.9089, - "step": 492500 - }, - { - "epoch": 3.25, - "learning_rate": 4.674962914125598e-05, - "loss": 1.9053, - "step": 493000 - }, - { - "epoch": 3.25, - "learning_rate": 4.6746332619086865e-05, - "loss": 1.9086, - "step": 493500 - }, - { - "epoch": 3.26, - "learning_rate": 4.6743036096917755e-05, - "loss": 1.9098, - "step": 494000 - }, - { - "epoch": 3.26, - "learning_rate": 4.6739739574748646e-05, - "loss": 1.9022, - "step": 494500 - }, - { - "epoch": 3.26, - "learning_rate": 4.673644305257953e-05, - "loss": 1.9151, - "step": 495000 - }, - { - "epoch": 3.27, - "learning_rate": 4.673314653041042e-05, - "loss": 1.903, - "step": 495500 - }, - { - "epoch": 3.27, - "learning_rate": 4.672985000824131e-05, - "loss": 1.9071, - "step": 496000 - }, - { - "epoch": 3.27, - "learning_rate": 4.6726553486072193e-05, - "loss": 1.9135, - "step": 496500 - }, - { - "epoch": 3.28, - "learning_rate": 4.6723256963903084e-05, - "loss": 1.9125, - "step": 497000 - }, - { - "epoch": 3.28, - "learning_rate": 4.6719960441733974e-05, - "loss": 1.9123, - "step": 497500 - }, - { - "epoch": 3.28, - "learning_rate": 4.6716663919564865e-05, - "loss": 1.9124, - "step": 498000 - }, - { - "epoch": 3.29, - "learning_rate": 4.6713367397395755e-05, - "loss": 1.91, - "step": 498500 - }, - { - "epoch": 3.29, - "learning_rate": 4.671007087522664e-05, - "loss": 1.8994, - "step": 499000 - }, - { - "epoch": 3.29, - "learning_rate": 4.670677435305752e-05, - "loss": 1.9103, - "step": 499500 - }, - { - "epoch": 3.3, - "learning_rate": 4.670347783088841e-05, - "loss": 1.9014, - "step": 500000 - }, - { - "epoch": 3.3, - "learning_rate": 4.67001813087193e-05, - "loss": 1.896, - "step": 500500 - }, - { - "epoch": 3.3, - "learning_rate": 4.669688478655019e-05, - "loss": 1.9022, - "step": 501000 - }, - { - "epoch": 3.31, - "learning_rate": 4.6693588264381084e-05, - "loss": 1.9079, - "step": 501500 - }, - { - "epoch": 3.31, - "learning_rate": 4.669029174221197e-05, - "loss": 1.9048, - "step": 502000 - }, - { - "epoch": 3.31, - "learning_rate": 4.668699522004286e-05, - "loss": 1.909, - "step": 502500 - }, - { - "epoch": 3.32, - "learning_rate": 4.668369869787375e-05, - "loss": 1.8979, - "step": 503000 - }, - { - "epoch": 3.32, - "learning_rate": 4.668040217570463e-05, - "loss": 1.9037, - "step": 503500 - }, - { - "epoch": 3.32, - "learning_rate": 4.667710565353552e-05, - "loss": 1.905, - "step": 504000 - }, - { - "epoch": 3.33, - "learning_rate": 4.6673809131366406e-05, - "loss": 1.8994, - "step": 504500 - }, - { - "epoch": 3.33, - "learning_rate": 4.6670512609197296e-05, - "loss": 1.9023, - "step": 505000 - }, - { - "epoch": 3.33, - "learning_rate": 4.6667216087028186e-05, - "loss": 1.8999, - "step": 505500 - }, - { - "epoch": 3.34, - "learning_rate": 4.666391956485908e-05, - "loss": 1.8994, - "step": 506000 - }, - { - "epoch": 3.34, - "learning_rate": 4.666062304268997e-05, - "loss": 1.8995, - "step": 506500 - }, - { - "epoch": 3.34, - "learning_rate": 4.665732652052086e-05, - "loss": 1.904, - "step": 507000 - }, - { - "epoch": 3.35, - "learning_rate": 4.665402999835174e-05, - "loss": 1.9115, - "step": 507500 - }, - { - "epoch": 3.35, - "learning_rate": 4.665073347618263e-05, - "loss": 1.8994, - "step": 508000 - }, - { - "epoch": 3.35, - "learning_rate": 4.6647436954013515e-05, - "loss": 1.9074, - "step": 508500 - }, - { - "epoch": 3.36, - "learning_rate": 4.6644140431844406e-05, - "loss": 1.9015, - "step": 509000 - }, - { - "epoch": 3.36, - "learning_rate": 4.6640843909675296e-05, - "loss": 1.8988, - "step": 509500 - }, - { - "epoch": 3.36, - "learning_rate": 4.663754738750618e-05, - "loss": 1.903, - "step": 510000 - }, - { - "epoch": 3.37, - "learning_rate": 4.663425086533707e-05, - "loss": 1.8927, - "step": 510500 - }, - { - "epoch": 3.37, - "learning_rate": 4.663095434316796e-05, - "loss": 1.9047, - "step": 511000 - }, - { - "epoch": 3.37, - "learning_rate": 4.662765782099885e-05, - "loss": 1.8966, - "step": 511500 - }, - { - "epoch": 3.38, - "learning_rate": 4.662436129882974e-05, - "loss": 1.8995, - "step": 512000 - }, - { - "epoch": 3.38, - "learning_rate": 4.6621064776660625e-05, - "loss": 1.9043, - "step": 512500 - }, - { - "epoch": 3.38, - "learning_rate": 4.6617768254491515e-05, - "loss": 1.8966, - "step": 513000 - }, - { - "epoch": 3.39, - "learning_rate": 4.66144717323224e-05, - "loss": 1.8985, - "step": 513500 - }, - { - "epoch": 3.39, - "learning_rate": 4.661117521015329e-05, - "loss": 1.9023, - "step": 514000 - }, - { - "epoch": 3.39, - "learning_rate": 4.660787868798418e-05, - "loss": 1.8947, - "step": 514500 - }, - { - "epoch": 3.4, - "learning_rate": 4.660458216581507e-05, - "loss": 1.8942, - "step": 515000 - }, - { - "epoch": 3.4, - "learning_rate": 4.6601285643645953e-05, - "loss": 1.8973, - "step": 515500 - }, - { - "epoch": 3.4, - "learning_rate": 4.6597989121476844e-05, - "loss": 1.8941, - "step": 516000 - }, - { - "epoch": 3.41, - "learning_rate": 4.6594692599307734e-05, - "loss": 1.8964, - "step": 516500 - }, - { - "epoch": 3.41, - "learning_rate": 4.6591396077138625e-05, - "loss": 1.8977, - "step": 517000 - }, - { - "epoch": 3.41, - "learning_rate": 4.658809955496951e-05, - "loss": 1.9008, - "step": 517500 - }, - { - "epoch": 3.42, - "learning_rate": 4.65848030328004e-05, - "loss": 1.8875, - "step": 518000 - }, - { - "epoch": 3.42, - "learning_rate": 4.658150651063128e-05, - "loss": 1.8974, - "step": 518500 - }, - { - "epoch": 3.42, - "learning_rate": 4.657820998846217e-05, - "loss": 1.8918, - "step": 519000 - }, - { - "epoch": 3.43, - "learning_rate": 4.657491346629306e-05, - "loss": 1.8954, - "step": 519500 - }, - { - "epoch": 3.43, - "learning_rate": 4.657161694412395e-05, - "loss": 1.8996, - "step": 520000 - }, - { - "epoch": 3.43, - "learning_rate": 4.6568320421954844e-05, - "loss": 1.9034, - "step": 520500 - }, - { - "epoch": 3.43, - "learning_rate": 4.656502389978573e-05, - "loss": 1.9001, - "step": 521000 - }, - { - "epoch": 3.44, - "learning_rate": 4.656172737761662e-05, - "loss": 1.8925, - "step": 521500 - }, - { - "epoch": 3.44, - "learning_rate": 4.65584308554475e-05, - "loss": 1.9045, - "step": 522000 - }, - { - "epoch": 3.44, - "learning_rate": 4.655513433327839e-05, - "loss": 1.8957, - "step": 522500 - }, - { - "epoch": 3.45, - "learning_rate": 4.655183781110928e-05, - "loss": 1.8952, - "step": 523000 - }, - { - "epoch": 3.45, - "learning_rate": 4.654854128894017e-05, - "loss": 1.8918, - "step": 523500 - }, - { - "epoch": 3.45, - "learning_rate": 4.6545244766771056e-05, - "loss": 1.8959, - "step": 524000 - }, - { - "epoch": 3.46, - "learning_rate": 4.6541948244601946e-05, - "loss": 1.8896, - "step": 524500 - }, - { - "epoch": 3.46, - "learning_rate": 4.653865172243284e-05, - "loss": 1.8982, - "step": 525000 - }, - { - "epoch": 3.46, - "learning_rate": 4.653535520026373e-05, - "loss": 1.8969, - "step": 525500 - }, - { - "epoch": 3.47, - "learning_rate": 4.653205867809462e-05, - "loss": 1.9, - "step": 526000 - }, - { - "epoch": 3.47, - "learning_rate": 4.65287621559255e-05, - "loss": 1.8978, - "step": 526500 - }, - { - "epoch": 3.47, - "learning_rate": 4.6525465633756385e-05, - "loss": 1.8966, - "step": 527000 - }, - { - "epoch": 3.48, - "learning_rate": 4.6522169111587275e-05, - "loss": 1.8937, - "step": 527500 - }, - { - "epoch": 3.48, - "learning_rate": 4.6518872589418166e-05, - "loss": 1.8949, - "step": 528000 - }, - { - "epoch": 3.48, - "learning_rate": 4.6515576067249056e-05, - "loss": 1.9006, - "step": 528500 - }, - { - "epoch": 3.49, - "learning_rate": 4.6512279545079946e-05, - "loss": 1.8972, - "step": 529000 - }, - { - "epoch": 3.49, - "learning_rate": 4.650898302291083e-05, - "loss": 1.8907, - "step": 529500 - }, - { - "epoch": 3.49, - "learning_rate": 4.650568650074172e-05, - "loss": 1.8988, - "step": 530000 - }, - { - "epoch": 3.5, - "learning_rate": 4.650238997857261e-05, - "loss": 1.8935, - "step": 530500 - }, - { - "epoch": 3.5, - "learning_rate": 4.6499093456403494e-05, - "loss": 1.8883, - "step": 531000 - }, - { - "epoch": 3.5, - "learning_rate": 4.6495796934234385e-05, - "loss": 1.8852, - "step": 531500 - }, - { - "epoch": 3.51, - "learning_rate": 4.649250041206527e-05, - "loss": 1.888, - "step": 532000 - }, - { - "epoch": 3.51, - "learning_rate": 4.648920388989616e-05, - "loss": 1.8932, - "step": 532500 - }, - { - "epoch": 3.51, - "learning_rate": 4.648590736772705e-05, - "loss": 1.8971, - "step": 533000 - }, - { - "epoch": 3.52, - "learning_rate": 4.648261084555794e-05, - "loss": 1.8858, - "step": 533500 - }, - { - "epoch": 3.52, - "learning_rate": 4.647931432338883e-05, - "loss": 1.883, - "step": 534000 - }, - { - "epoch": 3.52, - "learning_rate": 4.647601780121972e-05, - "loss": 1.888, - "step": 534500 - }, - { - "epoch": 3.53, - "learning_rate": 4.6472721279050604e-05, - "loss": 1.9003, - "step": 535000 - }, - { - "epoch": 3.53, - "learning_rate": 4.6469424756881494e-05, - "loss": 1.8942, - "step": 535500 - }, - { - "epoch": 3.53, - "learning_rate": 4.646612823471238e-05, - "loss": 1.895, - "step": 536000 - }, - { - "epoch": 3.54, - "learning_rate": 4.646283171254327e-05, - "loss": 1.8853, - "step": 536500 - }, - { - "epoch": 3.54, - "learning_rate": 4.645953519037416e-05, - "loss": 1.898, - "step": 537000 - }, - { - "epoch": 3.54, - "learning_rate": 4.645623866820504e-05, - "loss": 1.8861, - "step": 537500 - }, - { - "epoch": 3.55, - "learning_rate": 4.645294214603593e-05, - "loss": 1.8906, - "step": 538000 - }, - { - "epoch": 3.55, - "learning_rate": 4.644964562386682e-05, - "loss": 1.8975, - "step": 538500 - }, - { - "epoch": 3.55, - "learning_rate": 4.644634910169771e-05, - "loss": 1.8892, - "step": 539000 - }, - { - "epoch": 3.56, - "learning_rate": 4.6443052579528604e-05, - "loss": 1.8856, - "step": 539500 - }, - { - "epoch": 3.56, - "learning_rate": 4.643975605735949e-05, - "loss": 1.892, - "step": 540000 - }, - { - "epoch": 3.56, - "learning_rate": 4.643645953519037e-05, - "loss": 1.8925, - "step": 540500 - }, - { - "epoch": 3.57, - "learning_rate": 4.643316301302126e-05, - "loss": 1.8864, - "step": 541000 - }, - { - "epoch": 3.57, - "learning_rate": 4.642986649085215e-05, - "loss": 1.8897, - "step": 541500 - }, - { - "epoch": 3.57, - "learning_rate": 4.642656996868304e-05, - "loss": 1.8874, - "step": 542000 - }, - { - "epoch": 3.58, - "learning_rate": 4.642327344651393e-05, - "loss": 1.8834, - "step": 542500 - }, - { - "epoch": 3.58, - "learning_rate": 4.6419976924344816e-05, - "loss": 1.8786, - "step": 543000 - }, - { - "epoch": 3.58, - "learning_rate": 4.6416680402175706e-05, - "loss": 1.8887, - "step": 543500 - }, - { - "epoch": 3.59, - "learning_rate": 4.64133838800066e-05, - "loss": 1.8886, - "step": 544000 - }, - { - "epoch": 3.59, - "learning_rate": 4.641008735783749e-05, - "loss": 1.8939, - "step": 544500 - }, - { - "epoch": 3.59, - "learning_rate": 4.640679083566837e-05, - "loss": 1.8811, - "step": 545000 - }, - { - "epoch": 3.6, - "learning_rate": 4.640349431349926e-05, - "loss": 1.8827, - "step": 545500 - }, - { - "epoch": 3.6, - "learning_rate": 4.6400197791330145e-05, - "loss": 1.8802, - "step": 546000 - }, - { - "epoch": 3.6, - "learning_rate": 4.6396901269161035e-05, - "loss": 1.8855, - "step": 546500 - }, - { - "epoch": 3.61, - "learning_rate": 4.6393604746991926e-05, - "loss": 1.8915, - "step": 547000 - }, - { - "epoch": 3.61, - "learning_rate": 4.6390308224822816e-05, - "loss": 1.8767, - "step": 547500 - }, - { - "epoch": 3.61, - "learning_rate": 4.6387011702653706e-05, - "loss": 1.8877, - "step": 548000 - }, - { - "epoch": 3.62, - "learning_rate": 4.63837151804846e-05, - "loss": 1.8868, - "step": 548500 - }, - { - "epoch": 3.62, - "learning_rate": 4.638041865831548e-05, - "loss": 1.883, - "step": 549000 - }, - { - "epoch": 3.62, - "learning_rate": 4.6377122136146364e-05, - "loss": 1.8878, - "step": 549500 - }, - { - "epoch": 3.63, - "learning_rate": 4.6373825613977254e-05, - "loss": 1.889, - "step": 550000 - }, - { - "epoch": 3.63, - "learning_rate": 4.6370529091808145e-05, - "loss": 1.8856, - "step": 550500 - }, - { - "epoch": 3.63, - "learning_rate": 4.6367232569639035e-05, - "loss": 1.883, - "step": 551000 - }, - { - "epoch": 3.64, - "learning_rate": 4.636393604746992e-05, - "loss": 1.8859, - "step": 551500 - }, - { - "epoch": 3.64, - "learning_rate": 4.636063952530081e-05, - "loss": 1.8843, - "step": 552000 - }, - { - "epoch": 3.64, - "learning_rate": 4.63573430031317e-05, - "loss": 1.884, - "step": 552500 - }, - { - "epoch": 3.65, - "learning_rate": 4.635404648096259e-05, - "loss": 1.8846, - "step": 553000 - }, - { - "epoch": 3.65, - "learning_rate": 4.6350749958793473e-05, - "loss": 1.8826, - "step": 553500 - }, - { - "epoch": 3.65, - "learning_rate": 4.6347453436624364e-05, - "loss": 1.8839, - "step": 554000 - }, - { - "epoch": 3.66, - "learning_rate": 4.634415691445525e-05, - "loss": 1.8822, - "step": 554500 - }, - { - "epoch": 3.66, - "learning_rate": 4.634086039228614e-05, - "loss": 1.8849, - "step": 555000 - }, - { - "epoch": 3.66, - "learning_rate": 4.633756387011703e-05, - "loss": 1.8821, - "step": 555500 - }, - { - "epoch": 3.67, - "learning_rate": 4.633426734794792e-05, - "loss": 1.8781, - "step": 556000 - }, - { - "epoch": 3.67, - "learning_rate": 4.633097082577881e-05, - "loss": 1.8769, - "step": 556500 - }, - { - "epoch": 3.67, - "learning_rate": 4.632767430360969e-05, - "loss": 1.8853, - "step": 557000 - }, - { - "epoch": 3.68, - "learning_rate": 4.632437778144058e-05, - "loss": 1.8836, - "step": 557500 - }, - { - "epoch": 3.68, - "learning_rate": 4.632108125927147e-05, - "loss": 1.8857, - "step": 558000 - }, - { - "epoch": 3.68, - "learning_rate": 4.631778473710236e-05, - "loss": 1.886, - "step": 558500 - }, - { - "epoch": 3.69, - "learning_rate": 4.631448821493325e-05, - "loss": 1.8805, - "step": 559000 - }, - { - "epoch": 3.69, - "learning_rate": 4.631119169276414e-05, - "loss": 1.8794, - "step": 559500 - }, - { - "epoch": 3.69, - "learning_rate": 4.630789517059502e-05, - "loss": 1.8829, - "step": 560000 - }, - { - "epoch": 3.7, - "learning_rate": 4.630459864842591e-05, - "loss": 1.8786, - "step": 560500 - }, - { - "epoch": 3.7, - "learning_rate": 4.63013021262568e-05, - "loss": 1.8814, - "step": 561000 - }, - { - "epoch": 3.7, - "learning_rate": 4.629800560408769e-05, - "loss": 1.8822, - "step": 561500 - }, - { - "epoch": 3.71, - "learning_rate": 4.629470908191858e-05, - "loss": 1.8737, - "step": 562000 - }, - { - "epoch": 3.71, - "learning_rate": 4.6291412559749466e-05, - "loss": 1.8835, - "step": 562500 - }, - { - "epoch": 3.71, - "learning_rate": 4.628811603758036e-05, - "loss": 1.8775, - "step": 563000 - }, - { - "epoch": 3.72, - "learning_rate": 4.628481951541124e-05, - "loss": 1.8749, - "step": 563500 - }, - { - "epoch": 3.72, - "learning_rate": 4.628152299324213e-05, - "loss": 1.878, - "step": 564000 - }, - { - "epoch": 3.72, - "learning_rate": 4.627822647107302e-05, - "loss": 1.8852, - "step": 564500 - }, - { - "epoch": 3.73, - "learning_rate": 4.627492994890391e-05, - "loss": 1.8834, - "step": 565000 - }, - { - "epoch": 3.73, - "learning_rate": 4.6271633426734795e-05, - "loss": 1.8758, - "step": 565500 - }, - { - "epoch": 3.73, - "learning_rate": 4.6268336904565686e-05, - "loss": 1.8802, - "step": 566000 - }, - { - "epoch": 3.73, - "learning_rate": 4.6265040382396576e-05, - "loss": 1.8775, - "step": 566500 - }, - { - "epoch": 3.74, - "learning_rate": 4.6261743860227466e-05, - "loss": 1.88, - "step": 567000 - }, - { - "epoch": 3.74, - "learning_rate": 4.625844733805835e-05, - "loss": 1.8772, - "step": 567500 - }, - { - "epoch": 3.74, - "learning_rate": 4.6255150815889234e-05, - "loss": 1.8731, - "step": 568000 - }, - { - "epoch": 3.75, - "learning_rate": 4.6251854293720124e-05, - "loss": 1.8835, - "step": 568500 - }, - { - "epoch": 3.75, - "learning_rate": 4.6248557771551014e-05, - "loss": 1.8792, - "step": 569000 - }, - { - "epoch": 3.75, - "learning_rate": 4.6245261249381905e-05, - "loss": 1.8738, - "step": 569500 - }, - { - "epoch": 3.76, - "learning_rate": 4.6241964727212795e-05, - "loss": 1.8835, - "step": 570000 - }, - { - "epoch": 3.76, - "learning_rate": 4.6238668205043685e-05, - "loss": 1.8854, - "step": 570500 - }, - { - "epoch": 3.76, - "learning_rate": 4.623537168287457e-05, - "loss": 1.8669, - "step": 571000 - }, - { - "epoch": 3.77, - "learning_rate": 4.623207516070546e-05, - "loss": 1.8762, - "step": 571500 - }, - { - "epoch": 3.77, - "learning_rate": 4.622877863853634e-05, - "loss": 1.884, - "step": 572000 - }, - { - "epoch": 3.77, - "learning_rate": 4.6225482116367233e-05, - "loss": 1.8776, - "step": 572500 - }, - { - "epoch": 3.78, - "learning_rate": 4.6222185594198124e-05, - "loss": 1.8714, - "step": 573000 - }, - { - "epoch": 3.78, - "learning_rate": 4.621888907202901e-05, - "loss": 1.8789, - "step": 573500 - }, - { - "epoch": 3.78, - "learning_rate": 4.62155925498599e-05, - "loss": 1.8624, - "step": 574000 - }, - { - "epoch": 3.79, - "learning_rate": 4.621229602769079e-05, - "loss": 1.8742, - "step": 574500 - }, - { - "epoch": 3.79, - "learning_rate": 4.620899950552168e-05, - "loss": 1.8724, - "step": 575000 - }, - { - "epoch": 3.79, - "learning_rate": 4.620570298335257e-05, - "loss": 1.8792, - "step": 575500 - }, - { - "epoch": 3.8, - "learning_rate": 4.620240646118346e-05, - "loss": 1.8679, - "step": 576000 - }, - { - "epoch": 3.8, - "learning_rate": 4.619910993901434e-05, - "loss": 1.8659, - "step": 576500 - }, - { - "epoch": 3.8, - "learning_rate": 4.6195813416845227e-05, - "loss": 1.8841, - "step": 577000 - }, - { - "epoch": 3.81, - "learning_rate": 4.619251689467612e-05, - "loss": 1.8727, - "step": 577500 - }, - { - "epoch": 3.81, - "learning_rate": 4.618922037250701e-05, - "loss": 1.8698, - "step": 578000 - }, - { - "epoch": 3.81, - "learning_rate": 4.61859238503379e-05, - "loss": 1.8778, - "step": 578500 - }, - { - "epoch": 3.82, - "learning_rate": 4.618262732816878e-05, - "loss": 1.8741, - "step": 579000 - }, - { - "epoch": 3.82, - "learning_rate": 4.617933080599967e-05, - "loss": 1.8791, - "step": 579500 - }, - { - "epoch": 3.82, - "learning_rate": 4.617603428383056e-05, - "loss": 1.8688, - "step": 580000 - }, - { - "epoch": 3.83, - "learning_rate": 4.617273776166145e-05, - "loss": 1.8689, - "step": 580500 - }, - { - "epoch": 3.83, - "learning_rate": 4.6169441239492336e-05, - "loss": 1.8778, - "step": 581000 - }, - { - "epoch": 3.83, - "learning_rate": 4.6166144717323226e-05, - "loss": 1.8732, - "step": 581500 - }, - { - "epoch": 3.84, - "learning_rate": 4.616284819515411e-05, - "loss": 1.8756, - "step": 582000 - }, - { - "epoch": 3.84, - "learning_rate": 4.6159551672985e-05, - "loss": 1.8683, - "step": 582500 - }, - { - "epoch": 3.84, - "learning_rate": 4.615625515081589e-05, - "loss": 1.8709, - "step": 583000 - }, - { - "epoch": 3.85, - "learning_rate": 4.615295862864678e-05, - "loss": 1.8742, - "step": 583500 - }, - { - "epoch": 3.85, - "learning_rate": 4.614966210647767e-05, - "loss": 1.8686, - "step": 584000 - }, - { - "epoch": 3.85, - "learning_rate": 4.6146365584308555e-05, - "loss": 1.8701, - "step": 584500 - }, - { - "epoch": 3.86, - "learning_rate": 4.6143069062139446e-05, - "loss": 1.8662, - "step": 585000 - }, - { - "epoch": 3.86, - "learning_rate": 4.6139772539970336e-05, - "loss": 1.8715, - "step": 585500 - }, - { - "epoch": 3.86, - "learning_rate": 4.613647601780122e-05, - "loss": 1.8754, - "step": 586000 - }, - { - "epoch": 3.87, - "learning_rate": 4.613317949563211e-05, - "loss": 1.8734, - "step": 586500 - }, - { - "epoch": 3.87, - "learning_rate": 4.6129882973463e-05, - "loss": 1.8744, - "step": 587000 - }, - { - "epoch": 3.87, - "learning_rate": 4.6126586451293884e-05, - "loss": 1.8729, - "step": 587500 - }, - { - "epoch": 3.88, - "learning_rate": 4.6123289929124774e-05, - "loss": 1.8695, - "step": 588000 - }, - { - "epoch": 3.88, - "learning_rate": 4.6119993406955665e-05, - "loss": 1.8607, - "step": 588500 - }, - { - "epoch": 3.88, - "learning_rate": 4.6116696884786555e-05, - "loss": 1.867, - "step": 589000 - }, - { - "epoch": 3.89, - "learning_rate": 4.6113400362617445e-05, - "loss": 1.8749, - "step": 589500 - }, - { - "epoch": 3.89, - "learning_rate": 4.611010384044833e-05, - "loss": 1.8694, - "step": 590000 - }, - { - "epoch": 3.89, - "learning_rate": 4.610680731827921e-05, - "loss": 1.8718, - "step": 590500 - }, - { - "epoch": 3.9, - "learning_rate": 4.61035107961101e-05, - "loss": 1.868, - "step": 591000 - }, - { - "epoch": 3.9, - "learning_rate": 4.6100214273940993e-05, - "loss": 1.8725, - "step": 591500 - }, - { - "epoch": 3.9, - "learning_rate": 4.6096917751771884e-05, - "loss": 1.8636, - "step": 592000 - }, - { - "epoch": 3.91, - "learning_rate": 4.6093621229602774e-05, - "loss": 1.8577, - "step": 592500 - }, - { - "epoch": 3.91, - "learning_rate": 4.609032470743366e-05, - "loss": 1.8726, - "step": 593000 - }, - { - "epoch": 3.91, - "learning_rate": 4.608702818526455e-05, - "loss": 1.862, - "step": 593500 - }, - { - "epoch": 3.92, - "learning_rate": 4.608373166309544e-05, - "loss": 1.8658, - "step": 594000 - }, - { - "epoch": 3.92, - "learning_rate": 4.608043514092633e-05, - "loss": 1.8696, - "step": 594500 - }, - { - "epoch": 3.92, - "learning_rate": 4.607713861875721e-05, - "loss": 1.8584, - "step": 595000 - }, - { - "epoch": 3.93, - "learning_rate": 4.6073842096588096e-05, - "loss": 1.8601, - "step": 595500 - }, - { - "epoch": 3.93, - "learning_rate": 4.6070545574418987e-05, - "loss": 1.8716, - "step": 596000 - }, - { - "epoch": 3.93, - "learning_rate": 4.606724905224988e-05, - "loss": 1.8629, - "step": 596500 - }, - { - "epoch": 3.94, - "learning_rate": 4.606395253008077e-05, - "loss": 1.8575, - "step": 597000 - }, - { - "epoch": 3.94, - "learning_rate": 4.606065600791166e-05, - "loss": 1.8634, - "step": 597500 - }, - { - "epoch": 3.94, - "learning_rate": 4.605735948574255e-05, - "loss": 1.8633, - "step": 598000 - }, - { - "epoch": 3.95, - "learning_rate": 4.605406296357343e-05, - "loss": 1.863, - "step": 598500 - }, - { - "epoch": 3.95, - "learning_rate": 4.605076644140432e-05, - "loss": 1.8583, - "step": 599000 - }, - { - "epoch": 3.95, - "learning_rate": 4.6047469919235206e-05, - "loss": 1.8666, - "step": 599500 - }, - { - "epoch": 3.96, - "learning_rate": 4.6044173397066096e-05, - "loss": 1.8605, - "step": 600000 - }, - { - "epoch": 3.96, - "learning_rate": 4.6040876874896986e-05, - "loss": 1.8701, - "step": 600500 - }, - { - "epoch": 3.96, - "learning_rate": 4.603758035272788e-05, - "loss": 1.8687, - "step": 601000 - }, - { - "epoch": 3.97, - "learning_rate": 4.603428383055876e-05, - "loss": 1.8649, - "step": 601500 - }, - { - "epoch": 3.97, - "learning_rate": 4.603098730838965e-05, - "loss": 1.8666, - "step": 602000 - }, - { - "epoch": 3.97, - "learning_rate": 4.602769078622054e-05, - "loss": 1.8622, - "step": 602500 - }, - { - "epoch": 3.98, - "learning_rate": 4.602439426405143e-05, - "loss": 1.8639, - "step": 603000 - }, - { - "epoch": 3.98, - "learning_rate": 4.602109774188232e-05, - "loss": 1.8633, - "step": 603500 - }, - { - "epoch": 3.98, - "learning_rate": 4.6017801219713206e-05, - "loss": 1.8531, - "step": 604000 - }, - { - "epoch": 3.99, - "learning_rate": 4.601450469754409e-05, - "loss": 1.868, - "step": 604500 - }, - { - "epoch": 3.99, - "learning_rate": 4.601120817537498e-05, - "loss": 1.8561, - "step": 605000 - }, - { - "epoch": 3.99, - "learning_rate": 4.600791165320587e-05, - "loss": 1.8649, - "step": 605500 - }, - { - "epoch": 4.0, - "learning_rate": 4.600461513103676e-05, - "loss": 1.8552, - "step": 606000 - }, - { - "epoch": 4.0, - "learning_rate": 4.600131860886765e-05, - "loss": 1.8661, - "step": 606500 - }, - { - "epoch": 4.0, - "learning_rate": 4.5998022086698534e-05, - "loss": 1.8595, - "step": 607000 - }, - { - "epoch": 4.01, - "learning_rate": 4.5994725564529425e-05, - "loss": 1.857, - "step": 607500 - }, - { - "epoch": 4.01, - "learning_rate": 4.5991429042360315e-05, - "loss": 1.8585, - "step": 608000 - }, - { - "epoch": 4.01, - "learning_rate": 4.59881325201912e-05, - "loss": 1.8523, - "step": 608500 - }, - { - "epoch": 4.02, - "learning_rate": 4.598483599802209e-05, - "loss": 1.8566, - "step": 609000 - }, - { - "epoch": 4.02, - "learning_rate": 4.598153947585297e-05, - "loss": 1.8541, - "step": 609500 - }, - { - "epoch": 4.02, - "learning_rate": 4.597824295368386e-05, - "loss": 1.8532, - "step": 610000 - }, - { - "epoch": 4.03, - "learning_rate": 4.597494643151475e-05, - "loss": 1.8564, - "step": 610500 - }, - { - "epoch": 4.03, - "learning_rate": 4.5971649909345644e-05, - "loss": 1.8642, - "step": 611000 - }, - { - "epoch": 4.03, - "learning_rate": 4.5968353387176534e-05, - "loss": 1.8454, - "step": 611500 - }, - { - "epoch": 4.03, - "learning_rate": 4.5965056865007425e-05, - "loss": 1.8532, - "step": 612000 - }, - { - "epoch": 4.04, - "learning_rate": 4.596176034283831e-05, - "loss": 1.8547, - "step": 612500 - }, - { - "epoch": 4.04, - "learning_rate": 4.59584638206692e-05, - "loss": 1.8549, - "step": 613000 - }, - { - "epoch": 4.04, - "learning_rate": 4.595516729850008e-05, - "loss": 1.8444, - "step": 613500 - }, - { - "epoch": 4.05, - "learning_rate": 4.595187077633097e-05, - "loss": 1.8539, - "step": 614000 - }, - { - "epoch": 4.05, - "learning_rate": 4.594857425416186e-05, - "loss": 1.8495, - "step": 614500 - }, - { - "epoch": 4.05, - "learning_rate": 4.5945277731992746e-05, - "loss": 1.8555, - "step": 615000 - }, - { - "epoch": 4.06, - "learning_rate": 4.594198120982364e-05, - "loss": 1.8524, - "step": 615500 - }, - { - "epoch": 4.06, - "learning_rate": 4.593868468765453e-05, - "loss": 1.8527, - "step": 616000 - }, - { - "epoch": 4.06, - "learning_rate": 4.593538816548542e-05, - "loss": 1.8562, - "step": 616500 - }, - { - "epoch": 4.07, - "learning_rate": 4.593209164331631e-05, - "loss": 1.8629, - "step": 617000 - }, - { - "epoch": 4.07, - "learning_rate": 4.592879512114719e-05, - "loss": 1.8541, - "step": 617500 - }, - { - "epoch": 4.07, - "learning_rate": 4.5925498598978075e-05, - "loss": 1.8554, - "step": 618000 - }, - { - "epoch": 4.08, - "learning_rate": 4.5922202076808966e-05, - "loss": 1.858, - "step": 618500 - }, - { - "epoch": 4.08, - "learning_rate": 4.5918905554639856e-05, - "loss": 1.8547, - "step": 619000 - }, - { - "epoch": 4.08, - "learning_rate": 4.5915609032470746e-05, - "loss": 1.8541, - "step": 619500 - }, - { - "epoch": 4.09, - "learning_rate": 4.591231251030164e-05, - "loss": 1.8488, - "step": 620000 - }, - { - "epoch": 4.09, - "learning_rate": 4.590901598813252e-05, - "loss": 1.8512, - "step": 620500 - }, - { - "epoch": 4.09, - "learning_rate": 4.590571946596341e-05, - "loss": 1.8501, - "step": 621000 - }, - { - "epoch": 4.1, - "learning_rate": 4.59024229437943e-05, - "loss": 1.8497, - "step": 621500 - }, - { - "epoch": 4.1, - "learning_rate": 4.589912642162519e-05, - "loss": 1.8501, - "step": 622000 - }, - { - "epoch": 4.1, - "learning_rate": 4.5895829899456075e-05, - "loss": 1.8515, - "step": 622500 - }, - { - "epoch": 4.11, - "learning_rate": 4.5892533377286966e-05, - "loss": 1.8533, - "step": 623000 - }, - { - "epoch": 4.11, - "learning_rate": 4.588923685511785e-05, - "loss": 1.8549, - "step": 623500 - }, - { - "epoch": 4.11, - "learning_rate": 4.588594033294874e-05, - "loss": 1.8537, - "step": 624000 - }, - { - "epoch": 4.12, - "learning_rate": 4.588264381077963e-05, - "loss": 1.8546, - "step": 624500 - }, - { - "epoch": 4.12, - "learning_rate": 4.587934728861052e-05, - "loss": 1.8573, - "step": 625000 - }, - { - "epoch": 4.12, - "learning_rate": 4.587605076644141e-05, - "loss": 1.8441, - "step": 625500 - }, - { - "epoch": 4.13, - "learning_rate": 4.5872754244272294e-05, - "loss": 1.8587, - "step": 626000 - }, - { - "epoch": 4.13, - "learning_rate": 4.5869457722103185e-05, - "loss": 1.8557, - "step": 626500 - }, - { - "epoch": 4.13, - "learning_rate": 4.586616119993407e-05, - "loss": 1.8526, - "step": 627000 - }, - { - "epoch": 4.14, - "learning_rate": 4.586286467776496e-05, - "loss": 1.8479, - "step": 627500 - }, - { - "epoch": 4.14, - "learning_rate": 4.585956815559585e-05, - "loss": 1.8596, - "step": 628000 - }, - { - "epoch": 4.14, - "learning_rate": 4.585627163342674e-05, - "loss": 1.8486, - "step": 628500 - }, - { - "epoch": 4.15, - "learning_rate": 4.585297511125762e-05, - "loss": 1.853, - "step": 629000 - }, - { - "epoch": 4.15, - "learning_rate": 4.584967858908851e-05, - "loss": 1.8496, - "step": 629500 - }, - { - "epoch": 4.15, - "learning_rate": 4.5846382066919404e-05, - "loss": 1.8597, - "step": 630000 - }, - { - "epoch": 4.16, - "learning_rate": 4.5843085544750294e-05, - "loss": 1.8499, - "step": 630500 - }, - { - "epoch": 4.16, - "learning_rate": 4.583978902258118e-05, - "loss": 1.847, - "step": 631000 - }, - { - "epoch": 4.16, - "learning_rate": 4.583649250041207e-05, - "loss": 1.8454, - "step": 631500 - }, - { - "epoch": 4.17, - "learning_rate": 4.583319597824295e-05, - "loss": 1.8592, - "step": 632000 - }, - { - "epoch": 4.17, - "learning_rate": 4.582989945607384e-05, - "loss": 1.8487, - "step": 632500 - }, - { - "epoch": 4.17, - "learning_rate": 4.582660293390473e-05, - "loss": 1.8562, - "step": 633000 - }, - { - "epoch": 4.18, - "learning_rate": 4.582330641173562e-05, - "loss": 1.8509, - "step": 633500 - }, - { - "epoch": 4.18, - "learning_rate": 4.582000988956651e-05, - "loss": 1.8581, - "step": 634000 - }, - { - "epoch": 4.18, - "learning_rate": 4.58167133673974e-05, - "loss": 1.8455, - "step": 634500 - }, - { - "epoch": 4.19, - "learning_rate": 4.581341684522829e-05, - "loss": 1.8569, - "step": 635000 - }, - { - "epoch": 4.19, - "learning_rate": 4.581012032305918e-05, - "loss": 1.8516, - "step": 635500 - }, - { - "epoch": 4.19, - "learning_rate": 4.580682380089006e-05, - "loss": 1.8416, - "step": 636000 - }, - { - "epoch": 4.2, - "learning_rate": 4.580352727872095e-05, - "loss": 1.849, - "step": 636500 - }, - { - "epoch": 4.2, - "learning_rate": 4.5800230756551835e-05, - "loss": 1.8505, - "step": 637000 - }, - { - "epoch": 4.2, - "learning_rate": 4.5796934234382726e-05, - "loss": 1.8465, - "step": 637500 - }, - { - "epoch": 4.21, - "learning_rate": 4.5793637712213616e-05, - "loss": 1.85, - "step": 638000 - }, - { - "epoch": 4.21, - "learning_rate": 4.5790341190044506e-05, - "loss": 1.8464, - "step": 638500 - }, - { - "epoch": 4.21, - "learning_rate": 4.57870446678754e-05, - "loss": 1.8538, - "step": 639000 - }, - { - "epoch": 4.22, - "learning_rate": 4.578374814570629e-05, - "loss": 1.8543, - "step": 639500 - }, - { - "epoch": 4.22, - "learning_rate": 4.578045162353717e-05, - "loss": 1.8526, - "step": 640000 - }, - { - "epoch": 4.22, - "learning_rate": 4.577715510136806e-05, - "loss": 1.8468, - "step": 640500 - }, - { - "epoch": 4.23, - "learning_rate": 4.5773858579198945e-05, - "loss": 1.8499, - "step": 641000 - }, - { - "epoch": 4.23, - "learning_rate": 4.5770562057029835e-05, - "loss": 1.8415, - "step": 641500 - }, - { - "epoch": 4.23, - "learning_rate": 4.5767265534860725e-05, - "loss": 1.8427, - "step": 642000 - }, - { - "epoch": 4.24, - "learning_rate": 4.576396901269161e-05, - "loss": 1.8492, - "step": 642500 - }, - { - "epoch": 4.24, - "learning_rate": 4.57606724905225e-05, - "loss": 1.8502, - "step": 643000 - }, - { - "epoch": 4.24, - "learning_rate": 4.575737596835339e-05, - "loss": 1.8479, - "step": 643500 - }, - { - "epoch": 4.25, - "learning_rate": 4.575407944618428e-05, - "loss": 1.8479, - "step": 644000 - }, - { - "epoch": 4.25, - "learning_rate": 4.575078292401517e-05, - "loss": 1.8452, - "step": 644500 - }, - { - "epoch": 4.25, - "learning_rate": 4.5747486401846054e-05, - "loss": 1.8516, - "step": 645000 - }, - { - "epoch": 4.26, - "learning_rate": 4.574418987967694e-05, - "loss": 1.8507, - "step": 645500 - }, - { - "epoch": 4.26, - "learning_rate": 4.574089335750783e-05, - "loss": 1.8442, - "step": 646000 - }, - { - "epoch": 4.26, - "learning_rate": 4.573759683533872e-05, - "loss": 1.8466, - "step": 646500 - }, - { - "epoch": 4.27, - "learning_rate": 4.573430031316961e-05, - "loss": 1.843, - "step": 647000 - }, - { - "epoch": 4.27, - "learning_rate": 4.57310037910005e-05, - "loss": 1.8494, - "step": 647500 - }, - { - "epoch": 4.27, - "learning_rate": 4.572770726883138e-05, - "loss": 1.8433, - "step": 648000 - }, - { - "epoch": 4.28, - "learning_rate": 4.572441074666227e-05, - "loss": 1.8482, - "step": 648500 - }, - { - "epoch": 4.28, - "learning_rate": 4.5721114224493164e-05, - "loss": 1.843, - "step": 649000 - }, - { - "epoch": 4.28, - "learning_rate": 4.571781770232405e-05, - "loss": 1.8464, - "step": 649500 - }, - { - "epoch": 4.29, - "learning_rate": 4.571452118015494e-05, - "loss": 1.8378, - "step": 650000 - }, - { - "epoch": 4.29, - "learning_rate": 4.571122465798583e-05, - "loss": 1.8503, - "step": 650500 - }, - { - "epoch": 4.29, - "learning_rate": 4.570792813581671e-05, - "loss": 1.847, - "step": 651000 - }, - { - "epoch": 4.3, - "learning_rate": 4.57046316136476e-05, - "loss": 1.8417, - "step": 651500 - }, - { - "epoch": 4.3, - "learning_rate": 4.570133509147849e-05, - "loss": 1.843, - "step": 652000 - }, - { - "epoch": 4.3, - "learning_rate": 4.569803856930938e-05, - "loss": 1.8405, - "step": 652500 - }, - { - "epoch": 4.31, - "learning_rate": 4.569474204714027e-05, - "loss": 1.8447, - "step": 653000 - }, - { - "epoch": 4.31, - "learning_rate": 4.5691445524971164e-05, - "loss": 1.8348, - "step": 653500 - }, - { - "epoch": 4.31, - "learning_rate": 4.568814900280205e-05, - "loss": 1.8436, - "step": 654000 - }, - { - "epoch": 4.32, - "learning_rate": 4.568485248063293e-05, - "loss": 1.8543, - "step": 654500 - }, - { - "epoch": 4.32, - "learning_rate": 4.568155595846382e-05, - "loss": 1.8402, - "step": 655000 - }, - { - "epoch": 4.32, - "learning_rate": 4.567825943629471e-05, - "loss": 1.8466, - "step": 655500 - }, - { - "epoch": 4.33, - "learning_rate": 4.56749629141256e-05, - "loss": 1.8429, - "step": 656000 - }, - { - "epoch": 4.33, - "learning_rate": 4.5671666391956486e-05, - "loss": 1.8442, - "step": 656500 - }, - { - "epoch": 4.33, - "learning_rate": 4.5668369869787376e-05, - "loss": 1.8486, - "step": 657000 - }, - { - "epoch": 4.33, - "learning_rate": 4.5665073347618266e-05, - "loss": 1.8429, - "step": 657500 - }, - { - "epoch": 4.34, - "learning_rate": 4.566177682544916e-05, - "loss": 1.8446, - "step": 658000 - }, - { - "epoch": 4.34, - "learning_rate": 4.565848030328004e-05, - "loss": 1.8346, - "step": 658500 - }, - { - "epoch": 4.34, - "learning_rate": 4.565518378111093e-05, - "loss": 1.8355, - "step": 659000 - }, - { - "epoch": 4.35, - "learning_rate": 4.5651887258941814e-05, - "loss": 1.8441, - "step": 659500 - }, - { - "epoch": 4.35, - "learning_rate": 4.5648590736772705e-05, - "loss": 1.8421, - "step": 660000 - }, - { - "epoch": 4.35, - "learning_rate": 4.5645294214603595e-05, - "loss": 1.8404, - "step": 660500 - }, - { - "epoch": 4.36, - "learning_rate": 4.5641997692434485e-05, - "loss": 1.8449, - "step": 661000 - }, - { - "epoch": 4.36, - "learning_rate": 4.5638701170265376e-05, - "loss": 1.8428, - "step": 661500 - }, - { - "epoch": 4.36, - "learning_rate": 4.563540464809626e-05, - "loss": 1.8459, - "step": 662000 - }, - { - "epoch": 4.37, - "learning_rate": 4.563210812592715e-05, - "loss": 1.8432, - "step": 662500 - }, - { - "epoch": 4.37, - "learning_rate": 4.562881160375804e-05, - "loss": 1.8486, - "step": 663000 - }, - { - "epoch": 4.37, - "learning_rate": 4.5625515081588924e-05, - "loss": 1.8521, - "step": 663500 - }, - { - "epoch": 4.38, - "learning_rate": 4.5622218559419814e-05, - "loss": 1.8401, - "step": 664000 - }, - { - "epoch": 4.38, - "learning_rate": 4.5618922037250705e-05, - "loss": 1.8395, - "step": 664500 - }, - { - "epoch": 4.38, - "learning_rate": 4.561562551508159e-05, - "loss": 1.8462, - "step": 665000 - }, - { - "epoch": 4.39, - "learning_rate": 4.561232899291248e-05, - "loss": 1.8395, - "step": 665500 - }, - { - "epoch": 4.39, - "learning_rate": 4.560903247074337e-05, - "loss": 1.8431, - "step": 666000 - }, - { - "epoch": 4.39, - "learning_rate": 4.560573594857426e-05, - "loss": 1.8474, - "step": 666500 - }, - { - "epoch": 4.4, - "learning_rate": 4.560243942640515e-05, - "loss": 1.8367, - "step": 667000 - }, - { - "epoch": 4.4, - "learning_rate": 4.559914290423603e-05, - "loss": 1.8409, - "step": 667500 - }, - { - "epoch": 4.4, - "learning_rate": 4.559584638206692e-05, - "loss": 1.8375, - "step": 668000 - }, - { - "epoch": 4.41, - "learning_rate": 4.559254985989781e-05, - "loss": 1.8404, - "step": 668500 - }, - { - "epoch": 4.41, - "learning_rate": 4.55892533377287e-05, - "loss": 1.8334, - "step": 669000 - }, - { - "epoch": 4.41, - "learning_rate": 4.558595681555959e-05, - "loss": 1.8372, - "step": 669500 - }, - { - "epoch": 4.42, - "learning_rate": 4.558266029339048e-05, - "loss": 1.8386, - "step": 670000 - }, - { - "epoch": 4.42, - "learning_rate": 4.557936377122136e-05, - "loss": 1.8362, - "step": 670500 - }, - { - "epoch": 4.42, - "learning_rate": 4.557606724905225e-05, - "loss": 1.8486, - "step": 671000 - }, - { - "epoch": 4.43, - "learning_rate": 4.557277072688314e-05, - "loss": 1.8375, - "step": 671500 - }, - { - "epoch": 4.43, - "learning_rate": 4.556947420471403e-05, - "loss": 1.8408, - "step": 672000 - }, - { - "epoch": 4.43, - "learning_rate": 4.556617768254492e-05, - "loss": 1.8427, - "step": 672500 - }, - { - "epoch": 4.44, - "learning_rate": 4.55628811603758e-05, - "loss": 1.8415, - "step": 673000 - }, - { - "epoch": 4.44, - "learning_rate": 4.555958463820669e-05, - "loss": 1.8276, - "step": 673500 - }, - { - "epoch": 4.44, - "learning_rate": 4.555628811603758e-05, - "loss": 1.8322, - "step": 674000 - }, - { - "epoch": 4.45, - "learning_rate": 4.555299159386847e-05, - "loss": 1.8362, - "step": 674500 - }, - { - "epoch": 4.45, - "learning_rate": 4.554969507169936e-05, - "loss": 1.8384, - "step": 675000 - }, - { - "epoch": 4.45, - "learning_rate": 4.554639854953025e-05, - "loss": 1.8357, - "step": 675500 - }, - { - "epoch": 4.46, - "learning_rate": 4.5543102027361136e-05, - "loss": 1.8455, - "step": 676000 - }, - { - "epoch": 4.46, - "learning_rate": 4.5539805505192026e-05, - "loss": 1.8426, - "step": 676500 - }, - { - "epoch": 4.46, - "learning_rate": 4.553650898302291e-05, - "loss": 1.8242, - "step": 677000 - }, - { - "epoch": 4.47, - "learning_rate": 4.55332124608538e-05, - "loss": 1.8313, - "step": 677500 - }, - { - "epoch": 4.47, - "learning_rate": 4.552991593868469e-05, - "loss": 1.8413, - "step": 678000 - }, - { - "epoch": 4.47, - "learning_rate": 4.5526619416515574e-05, - "loss": 1.8395, - "step": 678500 - }, - { - "epoch": 4.48, - "learning_rate": 4.5523322894346465e-05, - "loss": 1.8334, - "step": 679000 - }, - { - "epoch": 4.48, - "learning_rate": 4.5520026372177355e-05, - "loss": 1.8349, - "step": 679500 - }, - { - "epoch": 4.48, - "learning_rate": 4.5516729850008245e-05, - "loss": 1.8294, - "step": 680000 - }, - { - "epoch": 4.49, - "learning_rate": 4.5513433327839136e-05, - "loss": 1.842, - "step": 680500 - }, - { - "epoch": 4.49, - "learning_rate": 4.551013680567002e-05, - "loss": 1.8352, - "step": 681000 - }, - { - "epoch": 4.49, - "learning_rate": 4.550684028350091e-05, - "loss": 1.8345, - "step": 681500 - }, - { - "epoch": 4.5, - "learning_rate": 4.5503543761331793e-05, - "loss": 1.8331, - "step": 682000 - }, - { - "epoch": 4.5, - "learning_rate": 4.5500247239162684e-05, - "loss": 1.831, - "step": 682500 - }, - { - "epoch": 4.5, - "learning_rate": 4.5496950716993574e-05, - "loss": 1.8317, - "step": 683000 - }, - { - "epoch": 4.51, - "learning_rate": 4.5493654194824465e-05, - "loss": 1.8291, - "step": 683500 - }, - { - "epoch": 4.51, - "learning_rate": 4.549035767265535e-05, - "loss": 1.8354, - "step": 684000 - }, - { - "epoch": 4.51, - "learning_rate": 4.548706115048624e-05, - "loss": 1.832, - "step": 684500 - }, - { - "epoch": 4.52, - "learning_rate": 4.548376462831713e-05, - "loss": 1.8388, - "step": 685000 - }, - { - "epoch": 4.52, - "learning_rate": 4.548046810614802e-05, - "loss": 1.8318, - "step": 685500 - }, - { - "epoch": 4.52, - "learning_rate": 4.54771715839789e-05, - "loss": 1.8329, - "step": 686000 - }, - { - "epoch": 4.53, - "learning_rate": 4.547387506180979e-05, - "loss": 1.8335, - "step": 686500 - }, - { - "epoch": 4.53, - "learning_rate": 4.547057853964068e-05, - "loss": 1.8293, - "step": 687000 - }, - { - "epoch": 4.53, - "learning_rate": 4.546728201747157e-05, - "loss": 1.8394, - "step": 687500 - }, - { - "epoch": 4.54, - "learning_rate": 4.546398549530246e-05, - "loss": 1.8342, - "step": 688000 - }, - { - "epoch": 4.54, - "learning_rate": 4.546068897313335e-05, - "loss": 1.8343, - "step": 688500 - }, - { - "epoch": 4.54, - "learning_rate": 4.545739245096424e-05, - "loss": 1.8351, - "step": 689000 - }, - { - "epoch": 4.55, - "learning_rate": 4.545409592879512e-05, - "loss": 1.8327, - "step": 689500 - }, - { - "epoch": 4.55, - "learning_rate": 4.545079940662601e-05, - "loss": 1.8395, - "step": 690000 - }, - { - "epoch": 4.55, - "learning_rate": 4.54475028844569e-05, - "loss": 1.8343, - "step": 690500 - }, - { - "epoch": 4.56, - "learning_rate": 4.5444206362287786e-05, - "loss": 1.8297, - "step": 691000 - }, - { - "epoch": 4.56, - "learning_rate": 4.544090984011868e-05, - "loss": 1.8412, - "step": 691500 - }, - { - "epoch": 4.56, - "learning_rate": 4.543761331794957e-05, - "loss": 1.8274, - "step": 692000 - }, - { - "epoch": 4.57, - "learning_rate": 4.543431679578045e-05, - "loss": 1.8293, - "step": 692500 - }, - { - "epoch": 4.57, - "learning_rate": 4.543102027361134e-05, - "loss": 1.8354, - "step": 693000 - }, - { - "epoch": 4.57, - "learning_rate": 4.542772375144223e-05, - "loss": 1.8326, - "step": 693500 - }, - { - "epoch": 4.58, - "learning_rate": 4.542442722927312e-05, - "loss": 1.83, - "step": 694000 - }, - { - "epoch": 4.58, - "learning_rate": 4.542113070710401e-05, - "loss": 1.8242, - "step": 694500 - }, - { - "epoch": 4.58, - "learning_rate": 4.5417834184934896e-05, - "loss": 1.8318, - "step": 695000 - }, - { - "epoch": 4.59, - "learning_rate": 4.541453766276578e-05, - "loss": 1.8327, - "step": 695500 - }, - { - "epoch": 4.59, - "learning_rate": 4.541124114059667e-05, - "loss": 1.8333, - "step": 696000 - }, - { - "epoch": 4.59, - "learning_rate": 4.540794461842756e-05, - "loss": 1.8367, - "step": 696500 - }, - { - "epoch": 4.6, - "learning_rate": 4.540464809625845e-05, - "loss": 1.8273, - "step": 697000 - }, - { - "epoch": 4.6, - "learning_rate": 4.540135157408934e-05, - "loss": 1.827, - "step": 697500 - }, - { - "epoch": 4.6, - "learning_rate": 4.5398055051920225e-05, - "loss": 1.8338, - "step": 698000 - }, - { - "epoch": 4.61, - "learning_rate": 4.5394758529751115e-05, - "loss": 1.8276, - "step": 698500 - }, - { - "epoch": 4.61, - "learning_rate": 4.5391462007582005e-05, - "loss": 1.8315, - "step": 699000 - }, - { - "epoch": 4.61, - "learning_rate": 4.538816548541289e-05, - "loss": 1.8311, - "step": 699500 - }, - { - "epoch": 4.62, - "learning_rate": 4.538486896324378e-05, - "loss": 1.8273, - "step": 700000 - }, - { - "epoch": 4.62, - "learning_rate": 4.538157244107466e-05, - "loss": 1.8286, - "step": 700500 - }, - { - "epoch": 4.62, - "learning_rate": 4.5378275918905553e-05, - "loss": 1.8381, - "step": 701000 - }, - { - "epoch": 4.63, - "learning_rate": 4.5374979396736444e-05, - "loss": 1.8241, - "step": 701500 - }, - { - "epoch": 4.63, - "learning_rate": 4.5371682874567334e-05, - "loss": 1.8277, - "step": 702000 - }, - { - "epoch": 4.63, - "learning_rate": 4.5368386352398225e-05, - "loss": 1.8308, - "step": 702500 - }, - { - "epoch": 4.63, - "learning_rate": 4.5365089830229115e-05, - "loss": 1.8279, - "step": 703000 - }, - { - "epoch": 4.64, - "learning_rate": 4.536179330806e-05, - "loss": 1.8298, - "step": 703500 - }, - { - "epoch": 4.64, - "learning_rate": 4.535849678589089e-05, - "loss": 1.8355, - "step": 704000 - }, - { - "epoch": 4.64, - "learning_rate": 4.535520026372177e-05, - "loss": 1.8244, - "step": 704500 - }, - { - "epoch": 4.65, - "learning_rate": 4.535190374155266e-05, - "loss": 1.8303, - "step": 705000 - }, - { - "epoch": 4.65, - "learning_rate": 4.534860721938355e-05, - "loss": 1.8347, - "step": 705500 - }, - { - "epoch": 4.65, - "learning_rate": 4.5345310697214444e-05, - "loss": 1.8202, - "step": 706000 - }, - { - "epoch": 4.66, - "learning_rate": 4.534201417504533e-05, - "loss": 1.831, - "step": 706500 - }, - { - "epoch": 4.66, - "learning_rate": 4.533871765287622e-05, - "loss": 1.8318, - "step": 707000 - }, - { - "epoch": 4.66, - "learning_rate": 4.533542113070711e-05, - "loss": 1.819, - "step": 707500 - }, - { - "epoch": 4.67, - "learning_rate": 4.5332124608538e-05, - "loss": 1.8276, - "step": 708000 - }, - { - "epoch": 4.67, - "learning_rate": 4.532882808636888e-05, - "loss": 1.8265, - "step": 708500 - }, - { - "epoch": 4.67, - "learning_rate": 4.532553156419977e-05, - "loss": 1.8293, - "step": 709000 - }, - { - "epoch": 4.68, - "learning_rate": 4.5322235042030656e-05, - "loss": 1.8295, - "step": 709500 - }, - { - "epoch": 4.68, - "learning_rate": 4.5318938519861546e-05, - "loss": 1.8291, - "step": 710000 - }, - { - "epoch": 4.68, - "learning_rate": 4.531564199769244e-05, - "loss": 1.8233, - "step": 710500 - }, - { - "epoch": 4.69, - "learning_rate": 4.531234547552333e-05, - "loss": 1.8248, - "step": 711000 - }, - { - "epoch": 4.69, - "learning_rate": 4.530904895335422e-05, - "loss": 1.8247, - "step": 711500 - }, - { - "epoch": 4.69, - "learning_rate": 4.53057524311851e-05, - "loss": 1.826, - "step": 712000 - }, - { - "epoch": 4.7, - "learning_rate": 4.530245590901599e-05, - "loss": 1.8246, - "step": 712500 - }, - { - "epoch": 4.7, - "learning_rate": 4.529915938684688e-05, - "loss": 1.8191, - "step": 713000 - }, - { - "epoch": 4.7, - "learning_rate": 4.5295862864677766e-05, - "loss": 1.8246, - "step": 713500 - }, - { - "epoch": 4.71, - "learning_rate": 4.5292566342508656e-05, - "loss": 1.8236, - "step": 714000 - }, - { - "epoch": 4.71, - "learning_rate": 4.528926982033954e-05, - "loss": 1.8298, - "step": 714500 - }, - { - "epoch": 4.71, - "learning_rate": 4.528597329817043e-05, - "loss": 1.8211, - "step": 715000 - }, - { - "epoch": 4.72, - "learning_rate": 4.528267677600132e-05, - "loss": 1.8214, - "step": 715500 - }, - { - "epoch": 4.72, - "learning_rate": 4.527938025383221e-05, - "loss": 1.8277, - "step": 716000 - }, - { - "epoch": 4.72, - "learning_rate": 4.52760837316631e-05, - "loss": 1.8242, - "step": 716500 - }, - { - "epoch": 4.73, - "learning_rate": 4.527278720949399e-05, - "loss": 1.8218, - "step": 717000 - }, - { - "epoch": 4.73, - "learning_rate": 4.5269490687324875e-05, - "loss": 1.8202, - "step": 717500 - }, - { - "epoch": 4.73, - "learning_rate": 4.526619416515576e-05, - "loss": 1.8247, - "step": 718000 - }, - { - "epoch": 4.74, - "learning_rate": 4.526289764298665e-05, - "loss": 1.8271, - "step": 718500 - }, - { - "epoch": 4.74, - "learning_rate": 4.525960112081754e-05, - "loss": 1.8224, - "step": 719000 - }, - { - "epoch": 4.74, - "learning_rate": 4.525630459864843e-05, - "loss": 1.8211, - "step": 719500 - }, - { - "epoch": 4.75, - "learning_rate": 4.5253008076479313e-05, - "loss": 1.825, - "step": 720000 - }, - { - "epoch": 4.75, - "learning_rate": 4.5249711554310204e-05, - "loss": 1.8326, - "step": 720500 - }, - { - "epoch": 4.75, - "learning_rate": 4.5246415032141094e-05, - "loss": 1.8285, - "step": 721000 - }, - { - "epoch": 4.76, - "learning_rate": 4.5243118509971985e-05, - "loss": 1.8219, - "step": 721500 - }, - { - "epoch": 4.76, - "learning_rate": 4.5239821987802875e-05, - "loss": 1.8305, - "step": 722000 - }, - { - "epoch": 4.76, - "learning_rate": 4.523652546563376e-05, - "loss": 1.8183, - "step": 722500 - }, - { - "epoch": 4.77, - "learning_rate": 4.523322894346464e-05, - "loss": 1.822, - "step": 723000 - }, - { - "epoch": 4.77, - "learning_rate": 4.522993242129553e-05, - "loss": 1.8267, - "step": 723500 - }, - { - "epoch": 4.77, - "learning_rate": 4.522663589912642e-05, - "loss": 1.8224, - "step": 724000 - }, - { - "epoch": 4.78, - "learning_rate": 4.522333937695731e-05, - "loss": 1.8232, - "step": 724500 - }, - { - "epoch": 4.78, - "learning_rate": 4.5220042854788204e-05, - "loss": 1.8308, - "step": 725000 - }, - { - "epoch": 4.78, - "learning_rate": 4.521674633261909e-05, - "loss": 1.8236, - "step": 725500 - }, - { - "epoch": 4.79, - "learning_rate": 4.521344981044998e-05, - "loss": 1.8206, - "step": 726000 - }, - { - "epoch": 4.79, - "learning_rate": 4.521015328828087e-05, - "loss": 1.8155, - "step": 726500 - }, - { - "epoch": 4.79, - "learning_rate": 4.520685676611175e-05, - "loss": 1.8223, - "step": 727000 - }, - { - "epoch": 4.8, - "learning_rate": 4.520356024394264e-05, - "loss": 1.8283, - "step": 727500 - }, - { - "epoch": 4.8, - "learning_rate": 4.520026372177353e-05, - "loss": 1.826, - "step": 728000 - }, - { - "epoch": 4.8, - "learning_rate": 4.5196967199604416e-05, - "loss": 1.8234, - "step": 728500 - }, - { - "epoch": 4.81, - "learning_rate": 4.5193670677435306e-05, - "loss": 1.8136, - "step": 729000 - }, - { - "epoch": 4.81, - "learning_rate": 4.51903741552662e-05, - "loss": 1.8234, - "step": 729500 - }, - { - "epoch": 4.81, - "learning_rate": 4.518707763309709e-05, - "loss": 1.8164, - "step": 730000 - }, - { - "epoch": 4.82, - "learning_rate": 4.518378111092798e-05, - "loss": 1.8215, - "step": 730500 - }, - { - "epoch": 4.82, - "learning_rate": 4.518048458875886e-05, - "loss": 1.8242, - "step": 731000 - }, - { - "epoch": 4.82, - "learning_rate": 4.517718806658975e-05, - "loss": 1.8217, - "step": 731500 - }, - { - "epoch": 4.83, - "learning_rate": 4.5173891544420635e-05, - "loss": 1.8257, - "step": 732000 - }, - { - "epoch": 4.83, - "learning_rate": 4.5170595022251526e-05, - "loss": 1.8215, - "step": 732500 - }, - { - "epoch": 4.83, - "learning_rate": 4.5167298500082416e-05, - "loss": 1.8258, - "step": 733000 - }, - { - "epoch": 4.84, - "learning_rate": 4.5164001977913306e-05, - "loss": 1.8244, - "step": 733500 - }, - { - "epoch": 4.84, - "learning_rate": 4.516070545574419e-05, - "loss": 1.8215, - "step": 734000 - }, - { - "epoch": 4.84, - "learning_rate": 4.515740893357508e-05, - "loss": 1.8204, - "step": 734500 - }, - { - "epoch": 4.85, - "learning_rate": 4.515411241140597e-05, - "loss": 1.8114, - "step": 735000 - }, - { - "epoch": 4.85, - "learning_rate": 4.515081588923686e-05, - "loss": 1.822, - "step": 735500 - }, - { - "epoch": 4.85, - "learning_rate": 4.5147519367067745e-05, - "loss": 1.8218, - "step": 736000 - }, - { - "epoch": 4.86, - "learning_rate": 4.514422284489863e-05, - "loss": 1.8147, - "step": 736500 - }, - { - "epoch": 4.86, - "learning_rate": 4.514092632272952e-05, - "loss": 1.8163, - "step": 737000 - }, - { - "epoch": 4.86, - "learning_rate": 4.513762980056041e-05, - "loss": 1.8227, - "step": 737500 - }, - { - "epoch": 4.87, - "learning_rate": 4.51343332783913e-05, - "loss": 1.8209, - "step": 738000 - }, - { - "epoch": 4.87, - "learning_rate": 4.513103675622219e-05, - "loss": 1.8083, - "step": 738500 - }, - { - "epoch": 4.87, - "learning_rate": 4.512774023405308e-05, - "loss": 1.8279, - "step": 739000 - }, - { - "epoch": 4.88, - "learning_rate": 4.5124443711883964e-05, - "loss": 1.8173, - "step": 739500 - }, - { - "epoch": 4.88, - "learning_rate": 4.5121147189714854e-05, - "loss": 1.8207, - "step": 740000 - }, - { - "epoch": 4.88, - "learning_rate": 4.5117850667545745e-05, - "loss": 1.8208, - "step": 740500 - }, - { - "epoch": 4.89, - "learning_rate": 4.511455414537663e-05, - "loss": 1.8147, - "step": 741000 - }, - { - "epoch": 4.89, - "learning_rate": 4.511125762320752e-05, - "loss": 1.822, - "step": 741500 - }, - { - "epoch": 4.89, - "learning_rate": 4.51079611010384e-05, - "loss": 1.8268, - "step": 742000 - }, - { - "epoch": 4.9, - "learning_rate": 4.510466457886929e-05, - "loss": 1.8182, - "step": 742500 - }, - { - "epoch": 4.9, - "learning_rate": 4.510136805670018e-05, - "loss": 1.8272, - "step": 743000 - }, - { - "epoch": 4.9, - "learning_rate": 4.509807153453107e-05, - "loss": 1.8195, - "step": 743500 - }, - { - "epoch": 4.91, - "learning_rate": 4.5094775012361964e-05, - "loss": 1.8101, - "step": 744000 - }, - { - "epoch": 4.91, - "learning_rate": 4.5091478490192854e-05, - "loss": 1.8151, - "step": 744500 - }, - { - "epoch": 4.91, - "learning_rate": 4.508818196802374e-05, - "loss": 1.8185, - "step": 745000 - }, - { - "epoch": 4.92, - "learning_rate": 4.508488544585462e-05, - "loss": 1.8193, - "step": 745500 - }, - { - "epoch": 4.92, - "learning_rate": 4.508158892368551e-05, - "loss": 1.8136, - "step": 746000 - }, - { - "epoch": 4.92, - "learning_rate": 4.50782924015164e-05, - "loss": 1.818, - "step": 746500 - }, - { - "epoch": 4.93, - "learning_rate": 4.507499587934729e-05, - "loss": 1.8092, - "step": 747000 - }, - { - "epoch": 4.93, - "learning_rate": 4.5071699357178176e-05, - "loss": 1.8136, - "step": 747500 - }, - { - "epoch": 4.93, - "learning_rate": 4.5068402835009066e-05, - "loss": 1.817, - "step": 748000 - }, - { - "epoch": 4.93, - "learning_rate": 4.506510631283996e-05, - "loss": 1.8215, - "step": 748500 - }, - { - "epoch": 4.94, - "learning_rate": 4.506180979067085e-05, - "loss": 1.8193, - "step": 749000 - }, - { - "epoch": 4.94, - "learning_rate": 4.505851326850174e-05, - "loss": 1.8273, - "step": 749500 - }, - { - "epoch": 4.94, - "learning_rate": 4.505521674633262e-05, - "loss": 1.8196, - "step": 750000 - }, - { - "epoch": 4.95, - "learning_rate": 4.5051920224163505e-05, - "loss": 1.8067, - "step": 750500 - }, - { - "epoch": 4.95, - "learning_rate": 4.5048623701994395e-05, - "loss": 1.8192, - "step": 751000 - }, - { - "epoch": 4.95, - "learning_rate": 4.5045327179825285e-05, - "loss": 1.81, - "step": 751500 - }, - { - "epoch": 4.96, - "learning_rate": 4.5042030657656176e-05, - "loss": 1.8048, - "step": 752000 - }, - { - "epoch": 4.96, - "learning_rate": 4.5038734135487066e-05, - "loss": 1.8083, - "step": 752500 - }, - { - "epoch": 4.96, - "learning_rate": 4.503543761331795e-05, - "loss": 1.8162, - "step": 753000 - }, - { - "epoch": 4.97, - "learning_rate": 4.503214109114884e-05, - "loss": 1.8133, - "step": 753500 - }, - { - "epoch": 4.97, - "learning_rate": 4.502884456897973e-05, - "loss": 1.8196, - "step": 754000 - }, - { - "epoch": 4.97, - "learning_rate": 4.5025548046810614e-05, - "loss": 1.8136, - "step": 754500 - }, - { - "epoch": 4.98, - "learning_rate": 4.5022251524641505e-05, - "loss": 1.8204, - "step": 755000 - }, - { - "epoch": 4.98, - "learning_rate": 4.5018955002472395e-05, - "loss": 1.8028, - "step": 755500 - }, - { - "epoch": 4.98, - "learning_rate": 4.501565848030328e-05, - "loss": 1.8125, - "step": 756000 - }, - { - "epoch": 4.99, - "learning_rate": 4.501236195813417e-05, - "loss": 1.8125, - "step": 756500 - }, - { - "epoch": 4.99, - "learning_rate": 4.500906543596506e-05, - "loss": 1.8183, - "step": 757000 - }, - { - "epoch": 4.99, - "learning_rate": 4.500576891379595e-05, - "loss": 1.8104, - "step": 757500 - }, - { - "epoch": 5.0, - "learning_rate": 4.500247239162684e-05, - "loss": 1.8176, - "step": 758000 - }, - { - "epoch": 5.0, - "learning_rate": 4.4999175869457724e-05, - "loss": 1.8081, - "step": 758500 - }, - { - "epoch": 5.0, - "learning_rate": 4.4995879347288614e-05, - "loss": 1.8076, - "step": 759000 - }, - { - "epoch": 5.01, - "learning_rate": 4.49925828251195e-05, - "loss": 1.8079, - "step": 759500 - }, - { - "epoch": 5.01, - "learning_rate": 4.498928630295039e-05, - "loss": 1.8054, - "step": 760000 - }, - { - "epoch": 5.01, - "learning_rate": 4.498598978078128e-05, - "loss": 1.805, - "step": 760500 - }, - { - "epoch": 5.02, - "learning_rate": 4.498269325861217e-05, - "loss": 1.8125, - "step": 761000 - }, - { - "epoch": 5.02, - "learning_rate": 4.497939673644305e-05, - "loss": 1.8115, - "step": 761500 - }, - { - "epoch": 5.02, - "learning_rate": 4.497610021427394e-05, - "loss": 1.8087, - "step": 762000 - }, - { - "epoch": 5.03, - "learning_rate": 4.497280369210483e-05, - "loss": 1.8065, - "step": 762500 - }, - { - "epoch": 5.03, - "learning_rate": 4.4969507169935724e-05, - "loss": 1.8113, - "step": 763000 - }, - { - "epoch": 5.03, - "learning_rate": 4.496621064776661e-05, - "loss": 1.8013, - "step": 763500 - }, - { - "epoch": 5.04, - "learning_rate": 4.49629141255975e-05, - "loss": 1.807, - "step": 764000 - }, - { - "epoch": 5.04, - "learning_rate": 4.495961760342838e-05, - "loss": 1.8101, - "step": 764500 - }, - { - "epoch": 5.04, - "learning_rate": 4.495632108125927e-05, - "loss": 1.8087, - "step": 765000 - }, - { - "epoch": 5.05, - "learning_rate": 4.495302455909016e-05, - "loss": 1.7948, - "step": 765500 - }, - { - "epoch": 5.05, - "learning_rate": 4.494972803692105e-05, - "loss": 1.8083, - "step": 766000 - }, - { - "epoch": 5.05, - "learning_rate": 4.494643151475194e-05, - "loss": 1.8023, - "step": 766500 - }, - { - "epoch": 5.06, - "learning_rate": 4.4943134992582826e-05, - "loss": 1.8102, - "step": 767000 - }, - { - "epoch": 5.06, - "learning_rate": 4.493983847041372e-05, - "loss": 1.8085, - "step": 767500 - }, - { - "epoch": 5.06, - "learning_rate": 4.493654194824461e-05, - "loss": 1.8003, - "step": 768000 - }, - { - "epoch": 5.07, - "learning_rate": 4.493324542607549e-05, - "loss": 1.8086, - "step": 768500 - }, - { - "epoch": 5.07, - "learning_rate": 4.492994890390638e-05, - "loss": 1.8069, - "step": 769000 - }, - { - "epoch": 5.07, - "learning_rate": 4.492665238173727e-05, - "loss": 1.8055, - "step": 769500 - }, - { - "epoch": 5.08, - "learning_rate": 4.4923355859568155e-05, - "loss": 1.8015, - "step": 770000 - }, - { - "epoch": 5.08, - "learning_rate": 4.4920059337399045e-05, - "loss": 1.8079, - "step": 770500 - }, - { - "epoch": 5.08, - "learning_rate": 4.4916762815229936e-05, - "loss": 1.8076, - "step": 771000 - }, - { - "epoch": 5.09, - "learning_rate": 4.4913466293060826e-05, - "loss": 1.8072, - "step": 771500 - }, - { - "epoch": 5.09, - "learning_rate": 4.491016977089172e-05, - "loss": 1.8042, - "step": 772000 - }, - { - "epoch": 5.09, - "learning_rate": 4.49068732487226e-05, - "loss": 1.8086, - "step": 772500 - }, - { - "epoch": 5.1, - "learning_rate": 4.4903576726553484e-05, - "loss": 1.8046, - "step": 773000 - }, - { - "epoch": 5.1, - "learning_rate": 4.4900280204384374e-05, - "loss": 1.8001, - "step": 773500 - }, - { - "epoch": 5.1, - "learning_rate": 4.4896983682215265e-05, - "loss": 1.7975, - "step": 774000 - }, - { - "epoch": 5.11, - "learning_rate": 4.4893687160046155e-05, - "loss": 1.8051, - "step": 774500 - }, - { - "epoch": 5.11, - "learning_rate": 4.4890390637877045e-05, - "loss": 1.8014, - "step": 775000 - }, - { - "epoch": 5.11, - "learning_rate": 4.488709411570793e-05, - "loss": 1.8086, - "step": 775500 - }, - { - "epoch": 5.12, - "learning_rate": 4.488379759353882e-05, - "loss": 1.8041, - "step": 776000 - }, - { - "epoch": 5.12, - "learning_rate": 4.488050107136971e-05, - "loss": 1.8053, - "step": 776500 - }, - { - "epoch": 5.12, - "learning_rate": 4.487720454920059e-05, - "loss": 1.8013, - "step": 777000 - }, - { - "epoch": 5.13, - "learning_rate": 4.4873908027031484e-05, - "loss": 1.8055, - "step": 777500 - }, - { - "epoch": 5.13, - "learning_rate": 4.487061150486237e-05, - "loss": 1.806, - "step": 778000 - }, - { - "epoch": 5.13, - "learning_rate": 4.486731498269326e-05, - "loss": 1.8011, - "step": 778500 - }, - { - "epoch": 5.14, - "learning_rate": 4.486401846052415e-05, - "loss": 1.7989, - "step": 779000 - }, - { - "epoch": 5.14, - "learning_rate": 4.486072193835504e-05, - "loss": 1.7991, - "step": 779500 - }, - { - "epoch": 5.14, - "learning_rate": 4.485742541618593e-05, - "loss": 1.8066, - "step": 780000 - }, - { - "epoch": 5.15, - "learning_rate": 4.485412889401682e-05, - "loss": 1.8007, - "step": 780500 - }, - { - "epoch": 5.15, - "learning_rate": 4.48508323718477e-05, - "loss": 1.8042, - "step": 781000 - }, - { - "epoch": 5.15, - "learning_rate": 4.484753584967859e-05, - "loss": 1.7956, - "step": 781500 - }, - { - "epoch": 5.16, - "learning_rate": 4.484423932750948e-05, - "loss": 1.7978, - "step": 782000 - }, - { - "epoch": 5.16, - "learning_rate": 4.484094280534037e-05, - "loss": 1.8074, - "step": 782500 - }, - { - "epoch": 5.16, - "learning_rate": 4.483764628317126e-05, - "loss": 1.8003, - "step": 783000 - }, - { - "epoch": 5.17, - "learning_rate": 4.483434976100214e-05, - "loss": 1.8035, - "step": 783500 - }, - { - "epoch": 5.17, - "learning_rate": 4.483105323883303e-05, - "loss": 1.803, - "step": 784000 - }, - { - "epoch": 5.17, - "learning_rate": 4.482775671666392e-05, - "loss": 1.8021, - "step": 784500 - }, - { - "epoch": 5.18, - "learning_rate": 4.482446019449481e-05, - "loss": 1.8075, - "step": 785000 - }, - { - "epoch": 5.18, - "learning_rate": 4.48211636723257e-05, - "loss": 1.7987, - "step": 785500 - }, - { - "epoch": 5.18, - "learning_rate": 4.4817867150156586e-05, - "loss": 1.7986, - "step": 786000 - }, - { - "epoch": 5.19, - "learning_rate": 4.481457062798747e-05, - "loss": 1.7976, - "step": 786500 - }, - { - "epoch": 5.19, - "learning_rate": 4.481127410581836e-05, - "loss": 1.8058, - "step": 787000 - }, - { - "epoch": 5.19, - "learning_rate": 4.480797758364925e-05, - "loss": 1.8072, - "step": 787500 - }, - { - "epoch": 5.2, - "learning_rate": 4.480468106148014e-05, - "loss": 1.8007, - "step": 788000 - }, - { - "epoch": 5.2, - "learning_rate": 4.480138453931103e-05, - "loss": 1.7952, - "step": 788500 - }, - { - "epoch": 5.2, - "learning_rate": 4.4798088017141915e-05, - "loss": 1.8076, - "step": 789000 - }, - { - "epoch": 5.21, - "learning_rate": 4.4794791494972805e-05, - "loss": 1.8004, - "step": 789500 - }, - { - "epoch": 5.21, - "learning_rate": 4.4791494972803696e-05, - "loss": 1.8028, - "step": 790000 - }, - { - "epoch": 5.21, - "learning_rate": 4.4788198450634586e-05, - "loss": 1.7984, - "step": 790500 - }, - { - "epoch": 5.22, - "learning_rate": 4.478490192846547e-05, - "loss": 1.8088, - "step": 791000 - }, - { - "epoch": 5.22, - "learning_rate": 4.478160540629636e-05, - "loss": 1.8399, - "step": 791500 - }, - { - "epoch": 5.22, - "learning_rate": 4.4778308884127244e-05, - "loss": 1.8086, - "step": 792000 - }, - { - "epoch": 5.22, - "learning_rate": 4.4775012361958134e-05, - "loss": 1.8089, - "step": 792500 - }, - { - "epoch": 5.23, - "learning_rate": 4.4771715839789025e-05, - "loss": 1.8066, - "step": 793000 - }, - { - "epoch": 5.23, - "learning_rate": 4.4768419317619915e-05, - "loss": 1.8116, - "step": 793500 - }, - { - "epoch": 5.23, - "learning_rate": 4.4765122795450805e-05, - "loss": 1.8075, - "step": 794000 - }, - { - "epoch": 5.24, - "learning_rate": 4.476182627328169e-05, - "loss": 1.7971, - "step": 794500 - }, - { - "epoch": 5.24, - "learning_rate": 4.475852975111258e-05, - "loss": 1.8014, - "step": 795000 - }, - { - "epoch": 5.24, - "learning_rate": 4.475523322894346e-05, - "loss": 1.7935, - "step": 795500 - }, - { - "epoch": 5.25, - "learning_rate": 4.475193670677435e-05, - "loss": 1.8007, - "step": 796000 - }, - { - "epoch": 5.25, - "learning_rate": 4.4748640184605244e-05, - "loss": 1.8051, - "step": 796500 - }, - { - "epoch": 5.25, - "learning_rate": 4.4745343662436134e-05, - "loss": 1.8059, - "step": 797000 - }, - { - "epoch": 5.26, - "learning_rate": 4.474204714026702e-05, - "loss": 1.8046, - "step": 797500 - }, - { - "epoch": 5.26, - "learning_rate": 4.473875061809791e-05, - "loss": 1.8018, - "step": 798000 - }, - { - "epoch": 5.26, - "learning_rate": 4.47354540959288e-05, - "loss": 1.8008, - "step": 798500 - }, - { - "epoch": 5.27, - "learning_rate": 4.473215757375969e-05, - "loss": 1.8015, - "step": 799000 - }, - { - "epoch": 5.27, - "learning_rate": 4.472886105159058e-05, - "loss": 1.804, - "step": 799500 - }, - { - "epoch": 5.27, - "learning_rate": 4.472556452942146e-05, - "loss": 1.7949, - "step": 800000 } ], - "max_steps": 7583750, - "num_train_epochs": 50, - "total_flos": 1.4640792519177398e+19, + "max_steps": 119860, + "num_train_epochs": 10, + "total_flos": 4.514572271830057e+17, "trial_name": null, "trial_params": null }