[ { "loss": 5.60179638671875, "learning_rate": 4.9189600959512466e-05, "epoch": 0.048623942429252165, "total_flos": 127437846067872, "step": 500 }, { "loss": 4.56484326171875, "learning_rate": 4.837920191902493e-05, "epoch": 0.09724788485850433, "total_flos": 258224201311392, "step": 1000 }, { "loss": 4.172212890625, "learning_rate": 4.756880287853739e-05, "epoch": 0.1458718272877565, "total_flos": 389157743771424, "step": 1500 }, { "loss": 4.0773701171875, "learning_rate": 4.6758403838049856e-05, "epoch": 0.19449576971700866, "total_flos": 515696696481312, "step": 2000 }, { "loss": 3.90251953125, "learning_rate": 4.594800479756232e-05, "epoch": 0.24311971214626082, "total_flos": 643145055921792, "step": 2500 }, { "loss": 3.74609375, "learning_rate": 4.513760575707479e-05, "epoch": 0.291743654575513, "total_flos": 771103313933760, "step": 3000 }, { "loss": 3.63271875, "learning_rate": 4.432720671658725e-05, "epoch": 0.34036759700476515, "total_flos": 899392743182880, "step": 3500 }, { "loss": 3.617484375, "learning_rate": 4.3516807676099715e-05, "epoch": 0.3889915394340173, "total_flos": 1031971628456064, "step": 4000 }, { "loss": 3.59037109375, "learning_rate": 4.270640863561218e-05, "epoch": 0.4376154818632695, "total_flos": 1159745902447392, "step": 4500 }, { "loss": 3.5753984375, "learning_rate": 4.189600959512464e-05, "epoch": 0.48623942429252165, "total_flos": 1288030075010208, "step": 5000 }, { "loss": 3.5130390625, "learning_rate": 4.1085610554637105e-05, "epoch": 0.5348633667217738, "total_flos": 1414432353876192, "step": 5500 }, { "loss": 3.469171875, "learning_rate": 4.027521151414957e-05, "epoch": 0.583487309151026, "total_flos": 1539068386144032, "step": 6000 }, { "loss": 3.4336640625, "learning_rate": 3.946481247366203e-05, "epoch": 0.6321112515802781, "total_flos": 1667946564259200, "step": 6500 }, { "loss": 3.39712109375, "learning_rate": 3.8654413433174495e-05, "epoch": 0.6807351940095303, "total_flos": 1794422436733440, "step": 7000 }, { "loss": 3.3770703125, "learning_rate": 3.784401439268696e-05, "epoch": 0.7293591364387825, "total_flos": 1922738149414080, "step": 7500 }, { "loss": 3.3730703125, "learning_rate": 3.703361535219942e-05, "epoch": 0.7779830788680346, "total_flos": 2052888445614816, "step": 8000 }, { "loss": 3.310546875, "learning_rate": 3.622321631171189e-05, "epoch": 0.8266070212972868, "total_flos": 2186350454187072, "step": 8500 }, { "loss": 3.260265625, "learning_rate": 3.5412817271224355e-05, "epoch": 0.875230963726539, "total_flos": 2314024851138624, "step": 9000 }, { "loss": 3.2306796875, "learning_rate": 3.460241823073682e-05, "epoch": 0.9238549061557911, "total_flos": 2442719045233152, "step": 9500 }, { "loss": 3.2746796875, "learning_rate": 3.379201919024928e-05, "epoch": 0.9724788485850433, "total_flos": 2569378901728032, "step": 10000 }, { "loss": 3.1525703125, "learning_rate": 3.2981620149761745e-05, "epoch": 1.0211027910142954, "total_flos": 2698954904950056, "step": 10500 }, { "loss": 3.2410859375, "learning_rate": 3.217122110927421e-05, "epoch": 1.0697267334435476, "total_flos": 2828821340090376, "step": 11000 }, { "loss": 3.0903984375, "learning_rate": 3.136082206878667e-05, "epoch": 1.1183506758727997, "total_flos": 2958682518544392, "step": 11500 }, { "loss": 3.08865625, "learning_rate": 3.0550423028299135e-05, "epoch": 1.166974618302052, "total_flos": 3088039055113224, "step": 12000 }, { "loss": 3.1113671875, "learning_rate": 2.9740023987811598e-05, "epoch": 1.215598560731304, "total_flos": 3214535954332680, "step": 12500 }, { "loss": 3.088109375, "learning_rate": 2.8929624947324065e-05, "epoch": 1.2642225031605563, "total_flos": 3340123446821544, "step": 13000 }, { "loss": 3.03825, "learning_rate": 2.8119225906836528e-05, "epoch": 1.3128464455898083, "total_flos": 3469900518294696, "step": 13500 }, { "loss": 3.1165703125, "learning_rate": 2.730882686634899e-05, "epoch": 1.3614703880190606, "total_flos": 3597664278913416, "step": 14000 }, { "loss": 3.0786875, "learning_rate": 2.6498427825861454e-05, "epoch": 1.4100943304483127, "total_flos": 3726390013125768, "step": 14500 }, { "loss": 3.0769453125, "learning_rate": 2.5688028785373918e-05, "epoch": 1.458718272877565, "total_flos": 3854211597293832, "step": 15000 }, { "loss": 2.9751015625, "learning_rate": 2.487762974488638e-05, "epoch": 1.5073422153068172, "total_flos": 3979215597602952, "step": 15500 }, { "loss": 3.004953125, "learning_rate": 2.4067230704398848e-05, "epoch": 1.5559661577360693, "total_flos": 4105360298840040, "step": 16000 }, { "loss": 3.0202265625, "learning_rate": 2.325683166391131e-05, "epoch": 1.6045901001653213, "total_flos": 4232114775688392, "step": 16500 }, { "loss": 2.967203125, "learning_rate": 2.2446432623423774e-05, "epoch": 1.6532140425945736, "total_flos": 4357849455393768, "step": 17000 }, { "loss": 2.95409375, "learning_rate": 2.1636033582936237e-05, "epoch": 1.7018379850238259, "total_flos": 4487106114922824, "step": 17500 }, { "loss": 3.068265625, "learning_rate": 2.08256345424487e-05, "epoch": 1.750461927453078, "total_flos": 4614885645600456, "step": 18000 }, { "loss": 2.992953125, "learning_rate": 2.0015235501961167e-05, "epoch": 1.79908586988233, "total_flos": 4744000374599304, "step": 18500 }, { "loss": 2.9246953125, "learning_rate": 1.920483646147363e-05, "epoch": 1.8477098123115823, "total_flos": 4872962659695336, "step": 19000 }, { "loss": 2.980765625, "learning_rate": 1.8394437420986094e-05, "epoch": 1.8963337547408345, "total_flos": 5000447815939944, "step": 19500 }, { "loss": 2.95859375, "learning_rate": 1.7584038380498557e-05, "epoch": 1.9449576971700866, "total_flos": 5130419384806344, "step": 20000 }, { "loss": 2.951875, "learning_rate": 1.677363934001102e-05, "epoch": 1.9935816395993387, "total_flos": 5260301590005576, "step": 20500 }, { "loss": 2.90753125, "learning_rate": 1.5963240299523484e-05, "epoch": 2.0422055820285907, "total_flos": 5386174914812220, "step": 21000 }, { "loss": 2.8725, "learning_rate": 1.5152841259035949e-05, "epoch": 2.090829524457843, "total_flos": 5515216050202812, "step": 21500 }, { "loss": 2.813546875, "learning_rate": 1.4342442218548414e-05, "epoch": 2.1394534668870953, "total_flos": 5644814394341628, "step": 22000 }, { "loss": 2.867796875, "learning_rate": 1.3532043178060877e-05, "epoch": 2.1880774093163473, "total_flos": 5770811908362204, "step": 22500 }, { "loss": 2.797328125, "learning_rate": 1.272164413757334e-05, "epoch": 2.2367013517455994, "total_flos": 5901487873193340, "step": 23000 }, { "loss": 2.8206875, "learning_rate": 1.1911245097085805e-05, "epoch": 2.285325294174852, "total_flos": 6032090244416220, "step": 23500 }, { "loss": 2.835703125, "learning_rate": 1.110084605659827e-05, "epoch": 2.333949236604104, "total_flos": 6158765870970012, "step": 24000 }, { "loss": 2.888296875, "learning_rate": 1.0290447016110734e-05, "epoch": 2.382573179033356, "total_flos": 6289205284917468, "step": 24500 }, { "loss": 2.82090625, "learning_rate": 9.480047975623198e-06, "epoch": 2.431197121462608, "total_flos": 6419592132001884, "step": 25000 }, { "loss": 2.832359375, "learning_rate": 8.669648935135662e-06, "epoch": 2.4798210638918605, "total_flos": 6547245502208220, "step": 25500 }, { "loss": 2.81575, "learning_rate": 7.859249894648125e-06, "epoch": 2.5284450063211126, "total_flos": 6676738712620956, "step": 26000 }, { "loss": 2.750359375, "learning_rate": 7.048850854160589e-06, "epoch": 2.5770689487503646, "total_flos": 6806862725390172, "step": 26500 }, { "loss": 2.80775, "learning_rate": 6.2384518136730525e-06, "epoch": 2.6256928911796167, "total_flos": 6936345422430300, "step": 27000 }, { "loss": 2.7769375, "learning_rate": 5.4280527731855174e-06, "epoch": 2.674316833608869, "total_flos": 7062795011473020, "step": 27500 }, { "loss": 2.812875, "learning_rate": 4.617653732697981e-06, "epoch": 2.7229407760381212, "total_flos": 7193202885302652, "step": 28000 }, { "loss": 2.82128125, "learning_rate": 3.807254692210445e-06, "epoch": 2.7715647184673733, "total_flos": 7325014294375452, "step": 28500 }, { "loss": 2.7645625, "learning_rate": 2.9968556517229085e-06, "epoch": 2.8201886608966253, "total_flos": 7450607043550620, "step": 29000 }, { "loss": 2.867234375, "learning_rate": 2.1864566112353722e-06, "epoch": 2.8688126033258774, "total_flos": 7577203819809852, "step": 29500 }, { "loss": 2.772796875, "learning_rate": 1.3760575707478364e-06, "epoch": 2.91743654575513, "total_flos": 7705477479000060, "step": 30000 }, { "loss": 2.80721875, "learning_rate": 5.656585302603003e-07, "epoch": 2.966060488184382, "total_flos": 7829551045833372, "step": 30500 } ]