{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 4.195880295375049, "eval_steps": 500, "global_step": 5400, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00777302759424796, "grad_norm": 19.018803349985753, "learning_rate": 8.737864077669904e-07, "loss": 8.2473, "step": 10 }, { "epoch": 0.01554605518849592, "grad_norm": 17.967208179671328, "learning_rate": 1.8446601941747572e-06, "loss": 8.1304, "step": 20 }, { "epoch": 0.023319082782743878, "grad_norm": 9.21576906708124, "learning_rate": 2.8155339805825245e-06, "loss": 7.4913, "step": 30 }, { "epoch": 0.03109211037699184, "grad_norm": 4.8422984662740465, "learning_rate": 3.7864077669902915e-06, "loss": 6.7578, "step": 40 }, { "epoch": 0.0388651379712398, "grad_norm": 3.0883237528757603, "learning_rate": 4.7572815533980585e-06, "loss": 6.2789, "step": 50 }, { "epoch": 0.046638165565487756, "grad_norm": 3.0641013238554837, "learning_rate": 5.728155339805825e-06, "loss": 5.9381, "step": 60 }, { "epoch": 0.054411193159735714, "grad_norm": 3.6989178160715803, "learning_rate": 6.699029126213592e-06, "loss": 5.547, "step": 70 }, { "epoch": 0.06218422075398368, "grad_norm": 3.8926133061231023, "learning_rate": 7.66990291262136e-06, "loss": 4.9449, "step": 80 }, { "epoch": 0.06995724834823164, "grad_norm": 6.005297193380389, "learning_rate": 8.640776699029127e-06, "loss": 4.2741, "step": 90 }, { "epoch": 0.0777302759424796, "grad_norm": 4.634097942418493, "learning_rate": 9.611650485436892e-06, "loss": 3.692, "step": 100 }, { "epoch": 0.08550330353672755, "grad_norm": 3.9161281136802915, "learning_rate": 1.0582524271844662e-05, "loss": 3.3021, "step": 110 }, { "epoch": 0.09327633113097551, "grad_norm": 2.668188197386523, "learning_rate": 1.1553398058252427e-05, "loss": 3.0699, "step": 120 }, { "epoch": 0.10104935872522347, "grad_norm": 5.67542909747789, "learning_rate": 1.2524271844660197e-05, "loss": 2.9232, "step": 130 }, { "epoch": 0.10882238631947143, "grad_norm": 8.358891491079559, "learning_rate": 1.3495145631067962e-05, "loss": 2.8142, "step": 140 }, { "epoch": 0.11659541391371939, "grad_norm": 7.521330978238392, "learning_rate": 1.446601941747573e-05, "loss": 2.736, "step": 150 }, { "epoch": 0.12436844150796736, "grad_norm": 16.178722459983547, "learning_rate": 1.5436893203883496e-05, "loss": 2.6651, "step": 160 }, { "epoch": 0.1321414691022153, "grad_norm": 8.335965189770683, "learning_rate": 1.6407766990291263e-05, "loss": 2.6021, "step": 170 }, { "epoch": 0.13991449669646328, "grad_norm": 8.022474097021126, "learning_rate": 1.737864077669903e-05, "loss": 2.5458, "step": 180 }, { "epoch": 0.14768752429071122, "grad_norm": 11.647238033711355, "learning_rate": 1.8349514563106798e-05, "loss": 2.4889, "step": 190 }, { "epoch": 0.1554605518849592, "grad_norm": 11.910883080289608, "learning_rate": 1.9320388349514565e-05, "loss": 2.4326, "step": 200 }, { "epoch": 0.16323357947920716, "grad_norm": 11.410643498860912, "learning_rate": 2.0291262135922333e-05, "loss": 2.3697, "step": 210 }, { "epoch": 0.1710066070734551, "grad_norm": 11.108752154756692, "learning_rate": 2.1262135922330097e-05, "loss": 2.309, "step": 220 }, { "epoch": 0.17877963466770308, "grad_norm": 19.998718279627422, "learning_rate": 2.2233009708737864e-05, "loss": 2.241, "step": 230 }, { "epoch": 0.18655266226195102, "grad_norm": 11.758179967806427, "learning_rate": 2.3203883495145632e-05, "loss": 2.1862, "step": 240 }, { "epoch": 0.194325689856199, "grad_norm": 13.686852090688575, "learning_rate": 2.41747572815534e-05, "loss": 2.1354, "step": 250 }, { "epoch": 0.20209871745044694, "grad_norm": 7.097958211758118, "learning_rate": 2.5145631067961167e-05, "loss": 2.0252, "step": 260 }, { "epoch": 0.2098717450446949, "grad_norm": 12.553623894402433, "learning_rate": 2.6116504854368934e-05, "loss": 1.92, "step": 270 }, { "epoch": 0.21764477263894286, "grad_norm": 7.033016298250838, "learning_rate": 2.7087378640776702e-05, "loss": 1.832, "step": 280 }, { "epoch": 0.22541780023319083, "grad_norm": 8.05454776441266, "learning_rate": 2.8058252427184466e-05, "loss": 1.7505, "step": 290 }, { "epoch": 0.23319082782743877, "grad_norm": 6.32342513670527, "learning_rate": 2.9029126213592233e-05, "loss": 1.6596, "step": 300 }, { "epoch": 0.24096385542168675, "grad_norm": 6.0607588085936435, "learning_rate": 3e-05, "loss": 1.5836, "step": 310 }, { "epoch": 0.24873688301593472, "grad_norm": 7.205879956336063, "learning_rate": 3.097087378640777e-05, "loss": 1.5148, "step": 320 }, { "epoch": 0.2565099106101827, "grad_norm": 5.233158820350977, "learning_rate": 3.194174757281553e-05, "loss": 1.4655, "step": 330 }, { "epoch": 0.2642829382044306, "grad_norm": 6.5668167184777495, "learning_rate": 3.29126213592233e-05, "loss": 1.3996, "step": 340 }, { "epoch": 0.2720559657986786, "grad_norm": 5.866172867997477, "learning_rate": 3.3883495145631074e-05, "loss": 1.3546, "step": 350 }, { "epoch": 0.27982899339292655, "grad_norm": 7.078627326366601, "learning_rate": 3.485436893203884e-05, "loss": 1.2957, "step": 360 }, { "epoch": 0.2876020209871745, "grad_norm": 7.013906915714377, "learning_rate": 3.58252427184466e-05, "loss": 1.265, "step": 370 }, { "epoch": 0.29537504858142244, "grad_norm": 5.721220928268079, "learning_rate": 3.679611650485437e-05, "loss": 1.2163, "step": 380 }, { "epoch": 0.3031480761756704, "grad_norm": 5.571852622479908, "learning_rate": 3.776699029126214e-05, "loss": 1.163, "step": 390 }, { "epoch": 0.3109211037699184, "grad_norm": 5.4843565963743295, "learning_rate": 3.873786407766991e-05, "loss": 1.1277, "step": 400 }, { "epoch": 0.31869413136416636, "grad_norm": 7.069970365890535, "learning_rate": 3.970873786407767e-05, "loss": 1.1094, "step": 410 }, { "epoch": 0.3264671589584143, "grad_norm": 5.425993491783754, "learning_rate": 4.0679611650485436e-05, "loss": 1.069, "step": 420 }, { "epoch": 0.33424018655266224, "grad_norm": 5.03054433074538, "learning_rate": 4.165048543689321e-05, "loss": 1.0382, "step": 430 }, { "epoch": 0.3420132141469102, "grad_norm": 7.103802226586121, "learning_rate": 4.262135922330097e-05, "loss": 0.9988, "step": 440 }, { "epoch": 0.3497862417411582, "grad_norm": 5.180871741408765, "learning_rate": 4.3592233009708735e-05, "loss": 0.979, "step": 450 }, { "epoch": 0.35755926933540616, "grad_norm": 5.168730423055745, "learning_rate": 4.4563106796116506e-05, "loss": 0.9442, "step": 460 }, { "epoch": 0.3653322969296541, "grad_norm": 4.509772926215358, "learning_rate": 4.553398058252427e-05, "loss": 0.9304, "step": 470 }, { "epoch": 0.37310532452390205, "grad_norm": 5.497064414551351, "learning_rate": 4.650485436893204e-05, "loss": 0.8971, "step": 480 }, { "epoch": 0.38087835211815, "grad_norm": 4.2878368849547375, "learning_rate": 4.747572815533981e-05, "loss": 0.8754, "step": 490 }, { "epoch": 0.388651379712398, "grad_norm": 5.023778493195039, "learning_rate": 4.8446601941747576e-05, "loss": 0.8535, "step": 500 }, { "epoch": 0.39642440730664597, "grad_norm": 4.85429288760384, "learning_rate": 4.941747572815535e-05, "loss": 0.8176, "step": 510 }, { "epoch": 0.4041974349008939, "grad_norm": 4.78285229843812, "learning_rate": 5.0388349514563104e-05, "loss": 0.8114, "step": 520 }, { "epoch": 0.41197046249514185, "grad_norm": 5.101751542601933, "learning_rate": 5.135922330097087e-05, "loss": 0.7752, "step": 530 }, { "epoch": 0.4197434900893898, "grad_norm": 5.448054773232898, "learning_rate": 5.233009708737864e-05, "loss": 0.755, "step": 540 }, { "epoch": 0.4275165176836378, "grad_norm": 4.141934961389859, "learning_rate": 5.3300970873786417e-05, "loss": 0.7273, "step": 550 }, { "epoch": 0.4352895452778857, "grad_norm": 4.514745713617805, "learning_rate": 5.427184466019418e-05, "loss": 0.7143, "step": 560 }, { "epoch": 0.4430625728721337, "grad_norm": 3.852074915498448, "learning_rate": 5.524271844660195e-05, "loss": 0.6954, "step": 570 }, { "epoch": 0.45083560046638166, "grad_norm": 4.549795432019635, "learning_rate": 5.6213592233009716e-05, "loss": 0.6695, "step": 580 }, { "epoch": 0.45860862806062963, "grad_norm": 3.920314510813715, "learning_rate": 5.718446601941748e-05, "loss": 0.6503, "step": 590 }, { "epoch": 0.46638165565487755, "grad_norm": 5.518859711149864, "learning_rate": 5.815533980582525e-05, "loss": 0.6249, "step": 600 }, { "epoch": 0.4741546832491255, "grad_norm": 4.876638883083892, "learning_rate": 5.9126213592233015e-05, "loss": 0.6064, "step": 610 }, { "epoch": 0.4819277108433735, "grad_norm": 5.2941697252063955, "learning_rate": 6.009708737864078e-05, "loss": 0.5911, "step": 620 }, { "epoch": 0.48970073843762146, "grad_norm": 4.245229081646686, "learning_rate": 6.106796116504854e-05, "loss": 0.5704, "step": 630 }, { "epoch": 0.49747376603186944, "grad_norm": 4.127680025681991, "learning_rate": 6.203883495145631e-05, "loss": 0.5589, "step": 640 }, { "epoch": 0.5052467936261174, "grad_norm": 3.5437231540377616, "learning_rate": 6.300970873786408e-05, "loss": 0.5378, "step": 650 }, { "epoch": 0.5130198212203654, "grad_norm": 4.180991087743002, "learning_rate": 6.398058252427184e-05, "loss": 0.5056, "step": 660 }, { "epoch": 0.5207928488146133, "grad_norm": 3.7905222943864034, "learning_rate": 6.495145631067961e-05, "loss": 0.4944, "step": 670 }, { "epoch": 0.5285658764088612, "grad_norm": 2.829726998778342, "learning_rate": 6.592233009708738e-05, "loss": 0.4706, "step": 680 }, { "epoch": 0.5363389040031092, "grad_norm": 2.9270824536877456, "learning_rate": 6.689320388349515e-05, "loss": 0.4539, "step": 690 }, { "epoch": 0.5441119315973572, "grad_norm": 2.742603316305724, "learning_rate": 6.786407766990291e-05, "loss": 0.4376, "step": 700 }, { "epoch": 0.5518849591916052, "grad_norm": 2.896538805797215, "learning_rate": 6.883495145631068e-05, "loss": 0.4113, "step": 710 }, { "epoch": 0.5596579867858531, "grad_norm": 3.4815145675652013, "learning_rate": 6.980582524271845e-05, "loss": 0.4005, "step": 720 }, { "epoch": 0.567431014380101, "grad_norm": 2.270621987351258, "learning_rate": 7.077669902912621e-05, "loss": 0.3886, "step": 730 }, { "epoch": 0.575204041974349, "grad_norm": 2.7187166457028344, "learning_rate": 7.174757281553398e-05, "loss": 0.3765, "step": 740 }, { "epoch": 0.582977069568597, "grad_norm": 3.184495607766821, "learning_rate": 7.271844660194175e-05, "loss": 0.3514, "step": 750 }, { "epoch": 0.5907500971628449, "grad_norm": 2.379059028542611, "learning_rate": 7.368932038834951e-05, "loss": 0.341, "step": 760 }, { "epoch": 0.5985231247570929, "grad_norm": 2.4310101684060705, "learning_rate": 7.466019417475728e-05, "loss": 0.3263, "step": 770 }, { "epoch": 0.6062961523513408, "grad_norm": 2.5710567898956005, "learning_rate": 7.563106796116505e-05, "loss": 0.3117, "step": 780 }, { "epoch": 0.6140691799455888, "grad_norm": 2.416082850923419, "learning_rate": 7.660194174757281e-05, "loss": 0.2944, "step": 790 }, { "epoch": 0.6218422075398368, "grad_norm": 2.109447352556029, "learning_rate": 7.757281553398059e-05, "loss": 0.2832, "step": 800 }, { "epoch": 0.6296152351340847, "grad_norm": 2.2994104123752988, "learning_rate": 7.854368932038836e-05, "loss": 0.2726, "step": 810 }, { "epoch": 0.6373882627283327, "grad_norm": 2.9267817958414524, "learning_rate": 7.951456310679612e-05, "loss": 0.2606, "step": 820 }, { "epoch": 0.6451612903225806, "grad_norm": 2.1699995560860197, "learning_rate": 8.048543689320389e-05, "loss": 0.2471, "step": 830 }, { "epoch": 0.6529343179168287, "grad_norm": 1.680681697729957, "learning_rate": 8.145631067961166e-05, "loss": 0.2354, "step": 840 }, { "epoch": 0.6607073455110766, "grad_norm": 1.88393966323043, "learning_rate": 8.242718446601942e-05, "loss": 0.2263, "step": 850 }, { "epoch": 0.6684803731053245, "grad_norm": 2.7385999995385957, "learning_rate": 8.339805825242719e-05, "loss": 0.2109, "step": 860 }, { "epoch": 0.6762534006995725, "grad_norm": 1.71125390353767, "learning_rate": 8.436893203883496e-05, "loss": 0.2034, "step": 870 }, { "epoch": 0.6840264282938204, "grad_norm": 1.8856456915119455, "learning_rate": 8.533980582524272e-05, "loss": 0.1928, "step": 880 }, { "epoch": 0.6917994558880683, "grad_norm": 1.54640226468132, "learning_rate": 8.631067961165049e-05, "loss": 0.1797, "step": 890 }, { "epoch": 0.6995724834823164, "grad_norm": 1.3309710354478357, "learning_rate": 8.728155339805826e-05, "loss": 0.1712, "step": 900 }, { "epoch": 0.7073455110765643, "grad_norm": 1.2897601826602498, "learning_rate": 8.825242718446602e-05, "loss": 0.1624, "step": 910 }, { "epoch": 0.7151185386708123, "grad_norm": 1.1022252566548159, "learning_rate": 8.922330097087379e-05, "loss": 0.1509, "step": 920 }, { "epoch": 0.7228915662650602, "grad_norm": 1.4797407171136665, "learning_rate": 9.019417475728156e-05, "loss": 0.1495, "step": 930 }, { "epoch": 0.7306645938593082, "grad_norm": 1.4708443604696282, "learning_rate": 9.116504854368933e-05, "loss": 0.1407, "step": 940 }, { "epoch": 0.7384376214535562, "grad_norm": 1.2062811965627402, "learning_rate": 9.213592233009709e-05, "loss": 0.1409, "step": 950 }, { "epoch": 0.7462106490478041, "grad_norm": 0.991340571431122, "learning_rate": 9.310679611650486e-05, "loss": 0.1267, "step": 960 }, { "epoch": 0.7539836766420521, "grad_norm": 1.0799976482859923, "learning_rate": 9.407766990291263e-05, "loss": 0.1294, "step": 970 }, { "epoch": 0.7617567042363, "grad_norm": 1.0055612260520772, "learning_rate": 9.504854368932039e-05, "loss": 0.1167, "step": 980 }, { "epoch": 0.769529731830548, "grad_norm": 0.99809772380525, "learning_rate": 9.601941747572816e-05, "loss": 0.1104, "step": 990 }, { "epoch": 0.777302759424796, "grad_norm": 0.8341966391057081, "learning_rate": 9.699029126213593e-05, "loss": 0.104, "step": 1000 }, { "epoch": 0.7850757870190439, "grad_norm": 0.7440675821604489, "learning_rate": 9.796116504854369e-05, "loss": 0.1, "step": 1010 }, { "epoch": 0.7928488146132919, "grad_norm": 1.0089217362175902, "learning_rate": 9.893203883495146e-05, "loss": 0.0926, "step": 1020 }, { "epoch": 0.8006218422075398, "grad_norm": 0.669475479205569, "learning_rate": 9.990291262135923e-05, "loss": 0.0855, "step": 1030 }, { "epoch": 0.8083948698017878, "grad_norm": 0.7508700947786369, "learning_rate": 9.999976722311928e-05, "loss": 0.0824, "step": 1040 }, { "epoch": 0.8161678973960358, "grad_norm": 0.5833904781662174, "learning_rate": 9.999896256507963e-05, "loss": 0.0794, "step": 1050 }, { "epoch": 0.8239409249902837, "grad_norm": 0.6285661168460489, "learning_rate": 9.99975831613399e-05, "loss": 0.0737, "step": 1060 }, { "epoch": 0.8317139525845316, "grad_norm": 0.574291945207083, "learning_rate": 9.99956290277565e-05, "loss": 0.0689, "step": 1070 }, { "epoch": 0.8394869801787797, "grad_norm": 0.4876511188851532, "learning_rate": 9.999310018679253e-05, "loss": 0.0659, "step": 1080 }, { "epoch": 0.8472600077730276, "grad_norm": 0.553792085705227, "learning_rate": 9.998999666751738e-05, "loss": 0.064, "step": 1090 }, { "epoch": 0.8550330353672756, "grad_norm": 0.4302541179456994, "learning_rate": 9.998631850560647e-05, "loss": 0.0612, "step": 1100 }, { "epoch": 0.8628060629615235, "grad_norm": 0.47710435973221127, "learning_rate": 9.998206574334089e-05, "loss": 0.0572, "step": 1110 }, { "epoch": 0.8705790905557714, "grad_norm": 0.6437234961571133, "learning_rate": 9.997723842960671e-05, "loss": 0.0556, "step": 1120 }, { "epoch": 0.8783521181500195, "grad_norm": 0.44297654610119586, "learning_rate": 9.997183661989468e-05, "loss": 0.0551, "step": 1130 }, { "epoch": 0.8861251457442674, "grad_norm": 0.40789308058272417, "learning_rate": 9.996586037629944e-05, "loss": 0.052, "step": 1140 }, { "epoch": 0.8938981733385154, "grad_norm": 0.412683747214122, "learning_rate": 9.99593097675188e-05, "loss": 0.0503, "step": 1150 }, { "epoch": 0.9016712009327633, "grad_norm": 0.4042307583726218, "learning_rate": 9.995218486885302e-05, "loss": 0.0491, "step": 1160 }, { "epoch": 0.9094442285270112, "grad_norm": 0.3917357425568075, "learning_rate": 9.994448576220388e-05, "loss": 0.0472, "step": 1170 }, { "epoch": 0.9172172561212593, "grad_norm": 0.42847580686284464, "learning_rate": 9.99362125360738e-05, "loss": 0.0461, "step": 1180 }, { "epoch": 0.9249902837155072, "grad_norm": 0.36275912435050334, "learning_rate": 9.992736528556474e-05, "loss": 0.045, "step": 1190 }, { "epoch": 0.9327633113097551, "grad_norm": 0.29922320469821373, "learning_rate": 9.991794411237725e-05, "loss": 0.0429, "step": 1200 }, { "epoch": 0.9405363389040031, "grad_norm": 0.3914552553052167, "learning_rate": 9.990794912480913e-05, "loss": 0.0426, "step": 1210 }, { "epoch": 0.948309366498251, "grad_norm": 0.38509264588619113, "learning_rate": 9.989738043775428e-05, "loss": 0.0423, "step": 1220 }, { "epoch": 0.9560823940924991, "grad_norm": 0.3259823714473278, "learning_rate": 9.988623817270137e-05, "loss": 0.0406, "step": 1230 }, { "epoch": 0.963855421686747, "grad_norm": 0.31452752346688945, "learning_rate": 9.987452245773243e-05, "loss": 0.0398, "step": 1240 }, { "epoch": 0.9716284492809949, "grad_norm": 0.338353347661472, "learning_rate": 9.986223342752141e-05, "loss": 0.0386, "step": 1250 }, { "epoch": 0.9794014768752429, "grad_norm": 0.3002478510776732, "learning_rate": 9.984937122333256e-05, "loss": 0.0382, "step": 1260 }, { "epoch": 0.9871745044694908, "grad_norm": 0.40670865355319846, "learning_rate": 9.983593599301891e-05, "loss": 0.037, "step": 1270 }, { "epoch": 0.9949475320637389, "grad_norm": 0.6429283417769656, "learning_rate": 9.982192789102047e-05, "loss": 0.0373, "step": 1280 }, { "epoch": 1.0023319082782745, "grad_norm": 0.2801176127856459, "learning_rate": 9.980734707836248e-05, "loss": 0.0354, "step": 1290 }, { "epoch": 1.0101049358725223, "grad_norm": 0.3724656663427553, "learning_rate": 9.979219372265365e-05, "loss": 0.0344, "step": 1300 }, { "epoch": 1.0178779634667703, "grad_norm": 0.2573842211275922, "learning_rate": 9.97764679980841e-05, "loss": 0.0333, "step": 1310 }, { "epoch": 1.0256509910610183, "grad_norm": 0.24713329711260812, "learning_rate": 9.97601700854234e-05, "loss": 0.0336, "step": 1320 }, { "epoch": 1.0334240186552661, "grad_norm": 0.23958650404178872, "learning_rate": 9.974330017201859e-05, "loss": 0.0328, "step": 1330 }, { "epoch": 1.0411970462495141, "grad_norm": 0.22856953483452255, "learning_rate": 9.972585845179188e-05, "loss": 0.0316, "step": 1340 }, { "epoch": 1.0489700738437622, "grad_norm": 0.25194563553211635, "learning_rate": 9.970784512523848e-05, "loss": 0.0311, "step": 1350 }, { "epoch": 1.0567431014380102, "grad_norm": 0.23842502807724422, "learning_rate": 9.968926039942435e-05, "loss": 0.0306, "step": 1360 }, { "epoch": 1.064516129032258, "grad_norm": 0.2701262980707877, "learning_rate": 9.967010448798375e-05, "loss": 0.0303, "step": 1370 }, { "epoch": 1.072289156626506, "grad_norm": 0.25970806872919033, "learning_rate": 9.965037761111681e-05, "loss": 0.0295, "step": 1380 }, { "epoch": 1.080062184220754, "grad_norm": 0.24331306995976767, "learning_rate": 9.963007999558696e-05, "loss": 0.0291, "step": 1390 }, { "epoch": 1.0878352118150019, "grad_norm": 0.24100978412084842, "learning_rate": 9.96092118747184e-05, "loss": 0.0287, "step": 1400 }, { "epoch": 1.09560823940925, "grad_norm": 0.2184207676934967, "learning_rate": 9.958777348839336e-05, "loss": 0.0277, "step": 1410 }, { "epoch": 1.103381267003498, "grad_norm": 0.21996045383271537, "learning_rate": 9.956576508304938e-05, "loss": 0.0272, "step": 1420 }, { "epoch": 1.1111542945977457, "grad_norm": 0.21628224837569832, "learning_rate": 9.954318691167641e-05, "loss": 0.0273, "step": 1430 }, { "epoch": 1.1189273221919938, "grad_norm": 0.22298883167746006, "learning_rate": 9.952003923381399e-05, "loss": 0.0264, "step": 1440 }, { "epoch": 1.1267003497862418, "grad_norm": 0.2246150118171153, "learning_rate": 9.949632231554819e-05, "loss": 0.0265, "step": 1450 }, { "epoch": 1.1344733773804898, "grad_norm": 0.23186180017701422, "learning_rate": 9.947203642950862e-05, "loss": 0.0262, "step": 1460 }, { "epoch": 1.1422464049747376, "grad_norm": 0.24648849817769855, "learning_rate": 9.944718185486523e-05, "loss": 0.0256, "step": 1470 }, { "epoch": 1.1500194325689856, "grad_norm": 0.30413187225809407, "learning_rate": 9.942175887732517e-05, "loss": 0.025, "step": 1480 }, { "epoch": 1.1577924601632337, "grad_norm": 0.23138441255979614, "learning_rate": 9.93957677891294e-05, "loss": 0.0251, "step": 1490 }, { "epoch": 1.1655654877574815, "grad_norm": 0.24336635292704567, "learning_rate": 9.93692088890495e-05, "loss": 0.0244, "step": 1500 }, { "epoch": 1.1733385153517295, "grad_norm": 0.21185931343408212, "learning_rate": 9.934208248238403e-05, "loss": 0.0243, "step": 1510 }, { "epoch": 1.1811115429459775, "grad_norm": 0.19638440276738353, "learning_rate": 9.93143888809552e-05, "loss": 0.0239, "step": 1520 }, { "epoch": 1.1888845705402253, "grad_norm": 0.21756730427462398, "learning_rate": 9.928612840310514e-05, "loss": 0.0232, "step": 1530 }, { "epoch": 1.1966575981344734, "grad_norm": 0.21305245786411112, "learning_rate": 9.925730137369242e-05, "loss": 0.023, "step": 1540 }, { "epoch": 1.2044306257287214, "grad_norm": 0.22828714542453502, "learning_rate": 9.922790812408808e-05, "loss": 0.0226, "step": 1550 }, { "epoch": 1.2122036533229692, "grad_norm": 0.19930203197693303, "learning_rate": 9.919794899217203e-05, "loss": 0.0224, "step": 1560 }, { "epoch": 1.2199766809172172, "grad_norm": 0.20433748074735467, "learning_rate": 9.916742432232909e-05, "loss": 0.0222, "step": 1570 }, { "epoch": 1.2277497085114653, "grad_norm": 0.20184151603700423, "learning_rate": 9.913633446544493e-05, "loss": 0.0215, "step": 1580 }, { "epoch": 1.2355227361057133, "grad_norm": 0.2081529716929725, "learning_rate": 9.910467977890225e-05, "loss": 0.0216, "step": 1590 }, { "epoch": 1.243295763699961, "grad_norm": 0.27882658958977674, "learning_rate": 9.907246062657648e-05, "loss": 0.0234, "step": 1600 }, { "epoch": 1.2510687912942091, "grad_norm": 0.30986570505669037, "learning_rate": 9.903967737883168e-05, "loss": 0.0248, "step": 1610 }, { "epoch": 1.258841818888457, "grad_norm": 0.2205524563203657, "learning_rate": 9.900633041251631e-05, "loss": 0.0222, "step": 1620 }, { "epoch": 1.266614846482705, "grad_norm": 0.19645809273796086, "learning_rate": 9.897242011095883e-05, "loss": 0.0208, "step": 1630 }, { "epoch": 1.274387874076953, "grad_norm": 0.20220041423279006, "learning_rate": 9.893794686396329e-05, "loss": 0.0203, "step": 1640 }, { "epoch": 1.282160901671201, "grad_norm": 0.19701852522226898, "learning_rate": 9.890291106780495e-05, "loss": 0.0199, "step": 1650 }, { "epoch": 1.289933929265449, "grad_norm": 0.19055264078653414, "learning_rate": 9.886731312522563e-05, "loss": 0.0196, "step": 1660 }, { "epoch": 1.2977069568596968, "grad_norm": 0.17498611562411595, "learning_rate": 9.883115344542911e-05, "loss": 0.0189, "step": 1670 }, { "epoch": 1.3054799844539449, "grad_norm": 0.18664040460319856, "learning_rate": 9.879443244407643e-05, "loss": 0.019, "step": 1680 }, { "epoch": 1.3132530120481927, "grad_norm": 0.186899833087349, "learning_rate": 9.875715054328108e-05, "loss": 0.0186, "step": 1690 }, { "epoch": 1.3210260396424407, "grad_norm": 0.18960588899249967, "learning_rate": 9.871930817160422e-05, "loss": 0.018, "step": 1700 }, { "epoch": 1.3287990672366887, "grad_norm": 0.2246998119833756, "learning_rate": 9.868090576404966e-05, "loss": 0.0185, "step": 1710 }, { "epoch": 1.3365720948309368, "grad_norm": 0.18612335330028418, "learning_rate": 9.864194376205895e-05, "loss": 0.0181, "step": 1720 }, { "epoch": 1.3443451224251846, "grad_norm": 0.19504144084562025, "learning_rate": 9.860242261350623e-05, "loss": 0.0174, "step": 1730 }, { "epoch": 1.3521181500194326, "grad_norm": 0.1940460381388096, "learning_rate": 9.856234277269313e-05, "loss": 0.0173, "step": 1740 }, { "epoch": 1.3598911776136804, "grad_norm": 0.1882305169943444, "learning_rate": 9.852170470034356e-05, "loss": 0.0173, "step": 1750 }, { "epoch": 1.3676642052079284, "grad_norm": 0.1844609631309131, "learning_rate": 9.848050886359835e-05, "loss": 0.0171, "step": 1760 }, { "epoch": 1.3754372328021764, "grad_norm": 0.16755276537647784, "learning_rate": 9.843875573600989e-05, "loss": 0.0169, "step": 1770 }, { "epoch": 1.3832102603964245, "grad_norm": 0.16696100318285242, "learning_rate": 9.839644579753677e-05, "loss": 0.0164, "step": 1780 }, { "epoch": 1.3909832879906725, "grad_norm": 0.1818918991872044, "learning_rate": 9.835357953453821e-05, "loss": 0.0163, "step": 1790 }, { "epoch": 1.3987563155849203, "grad_norm": 0.18963889299339048, "learning_rate": 9.831015743976843e-05, "loss": 0.0158, "step": 1800 }, { "epoch": 1.4065293431791683, "grad_norm": 0.1634818998306774, "learning_rate": 9.8266180012371e-05, "loss": 0.0154, "step": 1810 }, { "epoch": 1.4143023707734161, "grad_norm": 0.197090617938791, "learning_rate": 9.82216477578732e-05, "loss": 0.0152, "step": 1820 }, { "epoch": 1.4220753983676642, "grad_norm": 0.15850580732892314, "learning_rate": 9.817656118818006e-05, "loss": 0.0148, "step": 1830 }, { "epoch": 1.4298484259619122, "grad_norm": 0.15186976089409565, "learning_rate": 9.813092082156858e-05, "loss": 0.0146, "step": 1840 }, { "epoch": 1.4376214535561602, "grad_norm": 0.17352561780495993, "learning_rate": 9.808472718268174e-05, "loss": 0.0146, "step": 1850 }, { "epoch": 1.445394481150408, "grad_norm": 0.16575574275890378, "learning_rate": 9.803798080252245e-05, "loss": 0.014, "step": 1860 }, { "epoch": 1.453167508744656, "grad_norm": 0.16700742476995556, "learning_rate": 9.79906822184475e-05, "loss": 0.0139, "step": 1870 }, { "epoch": 1.460940536338904, "grad_norm": 0.15966930327908196, "learning_rate": 9.79428319741613e-05, "loss": 0.0136, "step": 1880 }, { "epoch": 1.4687135639331519, "grad_norm": 0.16653090767039122, "learning_rate": 9.789443061970973e-05, "loss": 0.0134, "step": 1890 }, { "epoch": 1.4764865915274, "grad_norm": 0.190626948029195, "learning_rate": 9.784547871147374e-05, "loss": 0.0129, "step": 1900 }, { "epoch": 1.484259619121648, "grad_norm": 0.1763435524084487, "learning_rate": 9.779597681216297e-05, "loss": 0.0127, "step": 1910 }, { "epoch": 1.492032646715896, "grad_norm": 0.1672345466206139, "learning_rate": 9.774592549080932e-05, "loss": 0.0126, "step": 1920 }, { "epoch": 1.4998056743101438, "grad_norm": 0.15678075113388967, "learning_rate": 9.769532532276034e-05, "loss": 0.0123, "step": 1930 }, { "epoch": 1.5075787019043918, "grad_norm": 0.14761977546971236, "learning_rate": 9.764417688967268e-05, "loss": 0.0118, "step": 1940 }, { "epoch": 1.5153517294986396, "grad_norm": 0.17063805371316892, "learning_rate": 9.75924807795054e-05, "loss": 0.0118, "step": 1950 }, { "epoch": 1.5231247570928876, "grad_norm": 0.14571436924477155, "learning_rate": 9.754023758651314e-05, "loss": 0.0115, "step": 1960 }, { "epoch": 1.5308977846871357, "grad_norm": 0.15118080081237256, "learning_rate": 9.74874479112394e-05, "loss": 0.0112, "step": 1970 }, { "epoch": 1.5386708122813837, "grad_norm": 0.1524883133010242, "learning_rate": 9.743411236050953e-05, "loss": 0.0112, "step": 1980 }, { "epoch": 1.5464438398756317, "grad_norm": 0.15389453717185902, "learning_rate": 9.738023154742383e-05, "loss": 0.0114, "step": 1990 }, { "epoch": 1.5542168674698795, "grad_norm": 0.14981753056593858, "learning_rate": 9.732580609135047e-05, "loss": 0.0108, "step": 2000 }, { "epoch": 1.5619898950641273, "grad_norm": 1.9198802022850896, "learning_rate": 9.727083661791836e-05, "loss": 0.0165, "step": 2010 }, { "epoch": 1.5697629226583754, "grad_norm": 0.26855012872950995, "learning_rate": 9.721532375900997e-05, "loss": 0.0144, "step": 2020 }, { "epoch": 1.5775359502526234, "grad_norm": 0.2071283206940206, "learning_rate": 9.71592681527541e-05, "loss": 0.0117, "step": 2030 }, { "epoch": 1.5853089778468714, "grad_norm": 0.14770534677344455, "learning_rate": 9.710267044351846e-05, "loss": 0.0109, "step": 2040 }, { "epoch": 1.5930820054411194, "grad_norm": 0.14368540945251085, "learning_rate": 9.704553128190239e-05, "loss": 0.0104, "step": 2050 }, { "epoch": 1.6008550330353672, "grad_norm": 0.13894193794675433, "learning_rate": 9.698785132472926e-05, "loss": 0.01, "step": 2060 }, { "epoch": 1.6086280606296153, "grad_norm": 0.13441313900735385, "learning_rate": 9.692963123503894e-05, "loss": 0.0094, "step": 2070 }, { "epoch": 1.616401088223863, "grad_norm": 0.12841760115701012, "learning_rate": 9.687087168208026e-05, "loss": 0.0094, "step": 2080 }, { "epoch": 1.624174115818111, "grad_norm": 0.1378414358921271, "learning_rate": 9.681157334130326e-05, "loss": 0.0092, "step": 2090 }, { "epoch": 1.6319471434123591, "grad_norm": 0.13875742382402598, "learning_rate": 9.67517368943514e-05, "loss": 0.0093, "step": 2100 }, { "epoch": 1.6397201710066072, "grad_norm": 0.12150978897988295, "learning_rate": 9.669136302905374e-05, "loss": 0.0094, "step": 2110 }, { "epoch": 1.6474931986008552, "grad_norm": 0.13386154431399386, "learning_rate": 9.663045243941711e-05, "loss": 0.009, "step": 2120 }, { "epoch": 1.655266226195103, "grad_norm": 0.14353227081750533, "learning_rate": 9.656900582561801e-05, "loss": 0.009, "step": 2130 }, { "epoch": 1.6630392537893508, "grad_norm": 0.13602583881387148, "learning_rate": 9.650702389399461e-05, "loss": 0.0088, "step": 2140 }, { "epoch": 1.6708122813835988, "grad_norm": 0.13201111610838254, "learning_rate": 9.644450735703872e-05, "loss": 0.0087, "step": 2150 }, { "epoch": 1.6785853089778469, "grad_norm": 0.11982302853617144, "learning_rate": 9.638145693338743e-05, "loss": 0.0087, "step": 2160 }, { "epoch": 1.6863583365720949, "grad_norm": 0.11312867242927008, "learning_rate": 9.631787334781497e-05, "loss": 0.0087, "step": 2170 }, { "epoch": 1.694131364166343, "grad_norm": 0.11767848177751597, "learning_rate": 9.625375733122439e-05, "loss": 0.0085, "step": 2180 }, { "epoch": 1.7019043917605907, "grad_norm": 0.11041145208342112, "learning_rate": 9.618910962063903e-05, "loss": 0.0082, "step": 2190 }, { "epoch": 1.7096774193548387, "grad_norm": 0.10799469734884444, "learning_rate": 9.612393095919423e-05, "loss": 0.0078, "step": 2200 }, { "epoch": 1.7174504469490866, "grad_norm": 0.11477500796146126, "learning_rate": 9.605822209612862e-05, "loss": 0.0078, "step": 2210 }, { "epoch": 1.7252234745433346, "grad_norm": 0.17423934102739813, "learning_rate": 9.599198378677559e-05, "loss": 0.0079, "step": 2220 }, { "epoch": 1.7329965021375826, "grad_norm": 0.11632697553641431, "learning_rate": 9.592521679255464e-05, "loss": 0.008, "step": 2230 }, { "epoch": 1.7407695297318306, "grad_norm": 0.12288031599865465, "learning_rate": 9.585792188096252e-05, "loss": 0.008, "step": 2240 }, { "epoch": 1.7485425573260787, "grad_norm": 0.15984027115213267, "learning_rate": 9.579009982556452e-05, "loss": 0.0079, "step": 2250 }, { "epoch": 1.7563155849203265, "grad_norm": 0.11306629622107851, "learning_rate": 9.572175140598553e-05, "loss": 0.0076, "step": 2260 }, { "epoch": 1.7640886125145743, "grad_norm": 0.1278172766126942, "learning_rate": 9.565287740790101e-05, "loss": 0.0077, "step": 2270 }, { "epoch": 1.7718616401088223, "grad_norm": 0.1251067207191811, "learning_rate": 9.55834786230281e-05, "loss": 0.0074, "step": 2280 }, { "epoch": 1.7796346677030703, "grad_norm": 0.12072123910224757, "learning_rate": 9.551355584911641e-05, "loss": 0.0077, "step": 2290 }, { "epoch": 1.7874076952973184, "grad_norm": 0.13420830427564445, "learning_rate": 9.544310988993889e-05, "loss": 0.0076, "step": 2300 }, { "epoch": 1.7951807228915664, "grad_norm": 0.11275927835211168, "learning_rate": 9.53721415552826e-05, "loss": 0.0072, "step": 2310 }, { "epoch": 1.8029537504858142, "grad_norm": 0.11663410063710995, "learning_rate": 9.530065166093936e-05, "loss": 0.007, "step": 2320 }, { "epoch": 1.8107267780800622, "grad_norm": 0.11515297587501505, "learning_rate": 9.52286410286964e-05, "loss": 0.007, "step": 2330 }, { "epoch": 1.81849980567431, "grad_norm": 0.12034539299056037, "learning_rate": 9.515611048632692e-05, "loss": 0.0071, "step": 2340 }, { "epoch": 1.826272833268558, "grad_norm": 0.13525219378529196, "learning_rate": 9.508306086758059e-05, "loss": 0.0069, "step": 2350 }, { "epoch": 1.834045860862806, "grad_norm": 0.11355987672855966, "learning_rate": 9.500949301217388e-05, "loss": 0.0066, "step": 2360 }, { "epoch": 1.841818888457054, "grad_norm": 0.10553177998244642, "learning_rate": 9.493540776578053e-05, "loss": 0.0067, "step": 2370 }, { "epoch": 1.8495919160513021, "grad_norm": 0.10733467006153838, "learning_rate": 9.486080598002176e-05, "loss": 0.0066, "step": 2380 }, { "epoch": 1.85736494364555, "grad_norm": 0.11088682968161348, "learning_rate": 9.478568851245643e-05, "loss": 0.0064, "step": 2390 }, { "epoch": 1.8651379712397977, "grad_norm": 0.11788349609407499, "learning_rate": 9.471005622657134e-05, "loss": 0.0064, "step": 2400 }, { "epoch": 1.8729109988340458, "grad_norm": 0.1382091673100836, "learning_rate": 9.463390999177113e-05, "loss": 0.0066, "step": 2410 }, { "epoch": 1.8806840264282938, "grad_norm": 0.11080598206299531, "learning_rate": 9.455725068336837e-05, "loss": 0.0067, "step": 2420 }, { "epoch": 1.8884570540225418, "grad_norm": 0.11345029521361591, "learning_rate": 9.44800791825735e-05, "loss": 0.0063, "step": 2430 }, { "epoch": 1.8962300816167899, "grad_norm": 0.12000127996735861, "learning_rate": 9.440239637648473e-05, "loss": 0.0064, "step": 2440 }, { "epoch": 1.9040031092110377, "grad_norm": 0.11742977407222017, "learning_rate": 9.432420315807771e-05, "loss": 0.0063, "step": 2450 }, { "epoch": 1.9117761368052857, "grad_norm": 0.10552545531273427, "learning_rate": 9.424550042619544e-05, "loss": 0.0062, "step": 2460 }, { "epoch": 1.9195491643995335, "grad_norm": 0.0996572096889176, "learning_rate": 9.416628908553784e-05, "loss": 0.0059, "step": 2470 }, { "epoch": 1.9273221919937815, "grad_norm": 0.09626416174818198, "learning_rate": 9.408657004665131e-05, "loss": 0.0058, "step": 2480 }, { "epoch": 1.9350952195880295, "grad_norm": 0.09783061431201936, "learning_rate": 9.400634422591838e-05, "loss": 0.0058, "step": 2490 }, { "epoch": 1.9428682471822776, "grad_norm": 0.11102429789832584, "learning_rate": 9.392561254554713e-05, "loss": 0.0059, "step": 2500 }, { "epoch": 1.9506412747765256, "grad_norm": 0.10011364069857738, "learning_rate": 9.384437593356048e-05, "loss": 0.0059, "step": 2510 }, { "epoch": 1.9584143023707734, "grad_norm": 0.10584225350181801, "learning_rate": 9.37626353237857e-05, "loss": 0.0061, "step": 2520 }, { "epoch": 1.9661873299650212, "grad_norm": 0.10444281925647403, "learning_rate": 9.368039165584359e-05, "loss": 0.0061, "step": 2530 }, { "epoch": 1.9739603575592692, "grad_norm": 0.10604191503186843, "learning_rate": 9.359764587513761e-05, "loss": 0.0057, "step": 2540 }, { "epoch": 1.9817333851535173, "grad_norm": 0.09211496249761421, "learning_rate": 9.351439893284317e-05, "loss": 0.0056, "step": 2550 }, { "epoch": 1.9895064127477653, "grad_norm": 0.14501544032188865, "learning_rate": 9.343065178589654e-05, "loss": 0.0056, "step": 2560 }, { "epoch": 1.9972794403420133, "grad_norm": 0.11456289818413888, "learning_rate": 9.334640539698396e-05, "loss": 0.0058, "step": 2570 }, { "epoch": 2.004663816556549, "grad_norm": 0.08068921187905599, "learning_rate": 9.326166073453051e-05, "loss": 0.0052, "step": 2580 }, { "epoch": 2.012436844150797, "grad_norm": 0.10032295518621465, "learning_rate": 9.317641877268901e-05, "loss": 0.0045, "step": 2590 }, { "epoch": 2.0202098717450445, "grad_norm": 0.0906748520799375, "learning_rate": 9.309068049132882e-05, "loss": 0.0044, "step": 2600 }, { "epoch": 2.0279828993392925, "grad_norm": 0.07982904566291607, "learning_rate": 9.300444687602457e-05, "loss": 0.0041, "step": 2610 }, { "epoch": 2.0357559269335406, "grad_norm": 0.1253437061299033, "learning_rate": 9.291771891804478e-05, "loss": 0.004, "step": 2620 }, { "epoch": 2.0435289545277886, "grad_norm": 0.09180533228491213, "learning_rate": 9.283049761434059e-05, "loss": 0.0041, "step": 2630 }, { "epoch": 2.0513019821220366, "grad_norm": 0.09238927797437002, "learning_rate": 9.27427839675342e-05, "loss": 0.004, "step": 2640 }, { "epoch": 2.0590750097162847, "grad_norm": 0.08085544322712232, "learning_rate": 9.26545789859073e-05, "loss": 0.004, "step": 2650 }, { "epoch": 2.0668480373105322, "grad_norm": 0.08278933444675111, "learning_rate": 9.256588368338968e-05, "loss": 0.0039, "step": 2660 }, { "epoch": 2.0746210649047803, "grad_norm": 0.0821491544443607, "learning_rate": 9.24766990795473e-05, "loss": 0.004, "step": 2670 }, { "epoch": 2.0823940924990283, "grad_norm": 0.0820536970017854, "learning_rate": 9.238702619957083e-05, "loss": 0.0039, "step": 2680 }, { "epoch": 2.0901671200932763, "grad_norm": 0.07783393489314461, "learning_rate": 9.229686607426368e-05, "loss": 0.0038, "step": 2690 }, { "epoch": 2.0979401476875243, "grad_norm": 0.08972295811517289, "learning_rate": 9.220621974003025e-05, "loss": 0.0038, "step": 2700 }, { "epoch": 2.1057131752817724, "grad_norm": 0.10850037565865495, "learning_rate": 9.211508823886398e-05, "loss": 0.0038, "step": 2710 }, { "epoch": 2.1134862028760204, "grad_norm": 0.1165050619921317, "learning_rate": 9.202347261833536e-05, "loss": 0.004, "step": 2720 }, { "epoch": 2.121259230470268, "grad_norm": 0.09613835587740172, "learning_rate": 9.193137393157994e-05, "loss": 0.004, "step": 2730 }, { "epoch": 2.129032258064516, "grad_norm": 0.08222637851192974, "learning_rate": 9.183879323728613e-05, "loss": 0.0041, "step": 2740 }, { "epoch": 2.136805285658764, "grad_norm": 0.09364974494864589, "learning_rate": 9.174573159968319e-05, "loss": 0.0041, "step": 2750 }, { "epoch": 2.144578313253012, "grad_norm": 0.09079410215789208, "learning_rate": 9.165219008852879e-05, "loss": 0.0037, "step": 2760 }, { "epoch": 2.15235134084726, "grad_norm": 0.08693641953192356, "learning_rate": 9.155816977909688e-05, "loss": 0.0038, "step": 2770 }, { "epoch": 2.160124368441508, "grad_norm": 0.08407058222727168, "learning_rate": 9.146367175216527e-05, "loss": 0.0038, "step": 2780 }, { "epoch": 2.167897396035756, "grad_norm": 0.08864727152361798, "learning_rate": 9.136869709400318e-05, "loss": 0.0037, "step": 2790 }, { "epoch": 2.1756704236300037, "grad_norm": 0.08585633309380411, "learning_rate": 9.127324689635879e-05, "loss": 0.0038, "step": 2800 }, { "epoch": 2.1834434512242518, "grad_norm": 0.09079038707160886, "learning_rate": 9.117732225644668e-05, "loss": 0.0037, "step": 2810 }, { "epoch": 2.1912164788185, "grad_norm": 0.08945120074693964, "learning_rate": 9.108092427693521e-05, "loss": 0.0039, "step": 2820 }, { "epoch": 2.198989506412748, "grad_norm": 0.09181352080010166, "learning_rate": 9.098405406593387e-05, "loss": 0.0038, "step": 2830 }, { "epoch": 2.206762534006996, "grad_norm": 0.08585652120551285, "learning_rate": 9.088671273698049e-05, "loss": 0.0038, "step": 2840 }, { "epoch": 2.214535561601244, "grad_norm": 0.08716662155761687, "learning_rate": 9.078890140902851e-05, "loss": 0.0037, "step": 2850 }, { "epoch": 2.2223085891954915, "grad_norm": 0.08274857092352111, "learning_rate": 9.069062120643406e-05, "loss": 0.0036, "step": 2860 }, { "epoch": 2.2300816167897395, "grad_norm": 0.08054936545881469, "learning_rate": 9.059187325894305e-05, "loss": 0.0037, "step": 2870 }, { "epoch": 2.2378546443839875, "grad_norm": 0.08928250602229335, "learning_rate": 9.04926587016782e-05, "loss": 0.0037, "step": 2880 }, { "epoch": 2.2456276719782355, "grad_norm": 0.14580475649103322, "learning_rate": 9.039297867512598e-05, "loss": 0.0039, "step": 2890 }, { "epoch": 2.2534006995724836, "grad_norm": 0.09684044113116728, "learning_rate": 9.02928343251235e-05, "loss": 0.0036, "step": 2900 }, { "epoch": 2.2611737271667316, "grad_norm": 4.610227312049106, "learning_rate": 9.019222680284531e-05, "loss": 0.0177, "step": 2910 }, { "epoch": 2.2689467547609796, "grad_norm": 3.9441098766180716, "learning_rate": 9.009115726479028e-05, "loss": 0.0845, "step": 2920 }, { "epoch": 2.276719782355227, "grad_norm": 0.30362597840942473, "learning_rate": 8.998962687276809e-05, "loss": 0.0336, "step": 2930 }, { "epoch": 2.2844928099494752, "grad_norm": 0.17872746957322608, "learning_rate": 8.988763679388614e-05, "loss": 0.0106, "step": 2940 }, { "epoch": 2.2922658375437233, "grad_norm": 0.11891620122269164, "learning_rate": 8.97851882005359e-05, "loss": 0.0069, "step": 2950 }, { "epoch": 2.3000388651379713, "grad_norm": 0.11931811737114671, "learning_rate": 8.968228227037961e-05, "loss": 0.0054, "step": 2960 }, { "epoch": 2.3078118927322193, "grad_norm": 0.11297205800033525, "learning_rate": 8.957892018633662e-05, "loss": 0.005, "step": 2970 }, { "epoch": 2.3155849203264673, "grad_norm": 0.08607374863983304, "learning_rate": 8.947510313656983e-05, "loss": 0.0046, "step": 2980 }, { "epoch": 2.323357947920715, "grad_norm": 0.08646791211129752, "learning_rate": 8.93708323144721e-05, "loss": 0.0043, "step": 2990 }, { "epoch": 2.331130975514963, "grad_norm": 0.09633865197527709, "learning_rate": 8.926610891865239e-05, "loss": 0.0042, "step": 3000 }, { "epoch": 2.338904003109211, "grad_norm": 0.07797950909850374, "learning_rate": 8.916093415292212e-05, "loss": 0.004, "step": 3010 }, { "epoch": 2.346677030703459, "grad_norm": 0.08803265774925108, "learning_rate": 8.905530922628129e-05, "loss": 0.0039, "step": 3020 }, { "epoch": 2.354450058297707, "grad_norm": 0.08578035815680632, "learning_rate": 8.894923535290452e-05, "loss": 0.0038, "step": 3030 }, { "epoch": 2.362223085891955, "grad_norm": 0.0723027097191447, "learning_rate": 8.884271375212713e-05, "loss": 0.0037, "step": 3040 }, { "epoch": 2.369996113486203, "grad_norm": 0.07933890872564231, "learning_rate": 8.873574564843123e-05, "loss": 0.0037, "step": 3050 }, { "epoch": 2.3777691410804507, "grad_norm": 0.08309597358808056, "learning_rate": 8.862833227143143e-05, "loss": 0.0037, "step": 3060 }, { "epoch": 2.3855421686746987, "grad_norm": 0.0796136928178535, "learning_rate": 8.852047485586093e-05, "loss": 0.0034, "step": 3070 }, { "epoch": 2.3933151962689467, "grad_norm": 0.0906501106792225, "learning_rate": 8.841217464155714e-05, "loss": 0.0036, "step": 3080 }, { "epoch": 2.4010882238631948, "grad_norm": 0.09232238343629308, "learning_rate": 8.830343287344753e-05, "loss": 0.0036, "step": 3090 }, { "epoch": 2.408861251457443, "grad_norm": 0.07677160549185906, "learning_rate": 8.819425080153533e-05, "loss": 0.0036, "step": 3100 }, { "epoch": 2.416634279051691, "grad_norm": 0.07965459624459517, "learning_rate": 8.808462968088512e-05, "loss": 0.0036, "step": 3110 }, { "epoch": 2.4244073066459384, "grad_norm": 0.08152518289735053, "learning_rate": 8.797457077160836e-05, "loss": 0.0036, "step": 3120 }, { "epoch": 2.4321803342401864, "grad_norm": 0.07840524642090889, "learning_rate": 8.786407533884902e-05, "loss": 0.0035, "step": 3130 }, { "epoch": 2.4399533618344345, "grad_norm": 0.0753906754915079, "learning_rate": 8.775314465276896e-05, "loss": 0.0034, "step": 3140 }, { "epoch": 2.4477263894286825, "grad_norm": 0.07553857495501508, "learning_rate": 8.764177998853334e-05, "loss": 0.0034, "step": 3150 }, { "epoch": 2.4554994170229305, "grad_norm": 0.07989895676116511, "learning_rate": 8.752998262629593e-05, "loss": 0.0034, "step": 3160 }, { "epoch": 2.4632724446171785, "grad_norm": 0.08604538052038023, "learning_rate": 8.741775385118447e-05, "loss": 0.0035, "step": 3170 }, { "epoch": 2.4710454722114266, "grad_norm": 0.07301243329178161, "learning_rate": 8.730509495328587e-05, "loss": 0.0034, "step": 3180 }, { "epoch": 2.478818499805674, "grad_norm": 0.07831526315789164, "learning_rate": 8.71920072276313e-05, "loss": 0.0034, "step": 3190 }, { "epoch": 2.486591527399922, "grad_norm": 0.10194734979674533, "learning_rate": 8.707849197418147e-05, "loss": 0.0034, "step": 3200 }, { "epoch": 2.49436455499417, "grad_norm": 0.07574798451139898, "learning_rate": 8.696455049781147e-05, "loss": 0.0035, "step": 3210 }, { "epoch": 2.5021375825884182, "grad_norm": 0.07681960051751799, "learning_rate": 8.6850184108296e-05, "loss": 0.0033, "step": 3220 }, { "epoch": 2.5099106101826663, "grad_norm": 0.07836534928409306, "learning_rate": 8.673539412029413e-05, "loss": 0.0033, "step": 3230 }, { "epoch": 2.517683637776914, "grad_norm": 0.08548600777071955, "learning_rate": 8.662018185333425e-05, "loss": 0.0034, "step": 3240 }, { "epoch": 2.525456665371162, "grad_norm": 0.0873567409210325, "learning_rate": 8.650454863179899e-05, "loss": 0.0032, "step": 3250 }, { "epoch": 2.53322969296541, "grad_norm": 0.08119732193506358, "learning_rate": 8.638849578490983e-05, "loss": 0.0032, "step": 3260 }, { "epoch": 2.541002720559658, "grad_norm": 0.07579199273478096, "learning_rate": 8.627202464671196e-05, "loss": 0.0031, "step": 3270 }, { "epoch": 2.548775748153906, "grad_norm": 0.07826696555904925, "learning_rate": 8.615513655605888e-05, "loss": 0.0031, "step": 3280 }, { "epoch": 2.556548775748154, "grad_norm": 0.07982815545083491, "learning_rate": 8.6037832856597e-05, "loss": 0.0031, "step": 3290 }, { "epoch": 2.564321803342402, "grad_norm": 0.08481539873916785, "learning_rate": 8.592011489675025e-05, "loss": 0.0031, "step": 3300 }, { "epoch": 2.57209483093665, "grad_norm": 0.07916097799005735, "learning_rate": 8.580198402970456e-05, "loss": 0.003, "step": 3310 }, { "epoch": 2.579867858530898, "grad_norm": 0.07473474197283404, "learning_rate": 8.56834416133922e-05, "loss": 0.003, "step": 3320 }, { "epoch": 2.5876408861251456, "grad_norm": 0.09130974953799981, "learning_rate": 8.556448901047638e-05, "loss": 0.0031, "step": 3330 }, { "epoch": 2.5954139137193937, "grad_norm": 0.1047401105445018, "learning_rate": 8.544512758833537e-05, "loss": 0.003, "step": 3340 }, { "epoch": 2.6031869413136417, "grad_norm": 0.06673230506522639, "learning_rate": 8.532535871904695e-05, "loss": 0.003, "step": 3350 }, { "epoch": 2.6109599689078897, "grad_norm": 0.07876904924601609, "learning_rate": 8.520518377937253e-05, "loss": 0.0031, "step": 3360 }, { "epoch": 2.6187329965021373, "grad_norm": 0.07009255329786931, "learning_rate": 8.508460415074137e-05, "loss": 0.0029, "step": 3370 }, { "epoch": 2.6265060240963853, "grad_norm": 0.07519024159981848, "learning_rate": 8.49636212192347e-05, "loss": 0.003, "step": 3380 }, { "epoch": 2.6342790516906334, "grad_norm": 0.08094145785537127, "learning_rate": 8.484223637556974e-05, "loss": 0.0031, "step": 3390 }, { "epoch": 2.6420520792848814, "grad_norm": 0.07736222204990759, "learning_rate": 8.472045101508382e-05, "loss": 0.003, "step": 3400 }, { "epoch": 2.6498251068791294, "grad_norm": 0.0776215180930073, "learning_rate": 8.459826653771821e-05, "loss": 0.003, "step": 3410 }, { "epoch": 2.6575981344733774, "grad_norm": 0.06742420975546093, "learning_rate": 8.44756843480021e-05, "loss": 0.0028, "step": 3420 }, { "epoch": 2.6653711620676255, "grad_norm": 0.0698399904847748, "learning_rate": 8.435270585503647e-05, "loss": 0.0029, "step": 3430 }, { "epoch": 2.6731441896618735, "grad_norm": 0.07591621006160705, "learning_rate": 8.422933247247786e-05, "loss": 0.0029, "step": 3440 }, { "epoch": 2.6809172172561215, "grad_norm": 0.06930363699655918, "learning_rate": 8.410556561852212e-05, "loss": 0.0029, "step": 3450 }, { "epoch": 2.688690244850369, "grad_norm": 0.07067953717607145, "learning_rate": 8.39814067158881e-05, "loss": 0.0028, "step": 3460 }, { "epoch": 2.696463272444617, "grad_norm": 0.077677315745107, "learning_rate": 8.385685719180132e-05, "loss": 0.0029, "step": 3470 }, { "epoch": 2.704236300038865, "grad_norm": 0.07570167649828695, "learning_rate": 8.373191847797754e-05, "loss": 0.0028, "step": 3480 }, { "epoch": 2.712009327633113, "grad_norm": 0.06955310603007175, "learning_rate": 8.360659201060639e-05, "loss": 0.0029, "step": 3490 }, { "epoch": 2.719782355227361, "grad_norm": 0.0659051677019647, "learning_rate": 8.348087923033465e-05, "loss": 0.0029, "step": 3500 }, { "epoch": 2.727555382821609, "grad_norm": 0.07181363122453262, "learning_rate": 8.335478158224996e-05, "loss": 0.0027, "step": 3510 }, { "epoch": 2.735328410415857, "grad_norm": 0.06585918912737933, "learning_rate": 8.3228300515864e-05, "loss": 0.0027, "step": 3520 }, { "epoch": 2.743101438010105, "grad_norm": 0.08664632265940041, "learning_rate": 8.310143748509588e-05, "loss": 0.0029, "step": 3530 }, { "epoch": 2.750874465604353, "grad_norm": 0.0773656650662347, "learning_rate": 8.297419394825554e-05, "loss": 0.0028, "step": 3540 }, { "epoch": 2.758647493198601, "grad_norm": 0.07477928292429042, "learning_rate": 8.28465713680268e-05, "loss": 0.0029, "step": 3550 }, { "epoch": 2.766420520792849, "grad_norm": 0.06614018293609181, "learning_rate": 8.271857121145073e-05, "loss": 0.0028, "step": 3560 }, { "epoch": 2.774193548387097, "grad_norm": 0.07953850815353782, "learning_rate": 8.25901949499086e-05, "loss": 0.0028, "step": 3570 }, { "epoch": 2.781966575981345, "grad_norm": 0.06857404401820201, "learning_rate": 8.246144405910517e-05, "loss": 0.0028, "step": 3580 }, { "epoch": 2.7897396035755926, "grad_norm": 0.06706667623803336, "learning_rate": 8.233232001905151e-05, "loss": 0.0029, "step": 3590 }, { "epoch": 2.7975126311698406, "grad_norm": 0.06548223623701806, "learning_rate": 8.220282431404818e-05, "loss": 0.0027, "step": 3600 }, { "epoch": 2.8052856587640886, "grad_norm": 0.06281526839867438, "learning_rate": 8.207295843266807e-05, "loss": 0.0025, "step": 3610 }, { "epoch": 2.8130586863583367, "grad_norm": 0.06453609241898647, "learning_rate": 8.194272386773928e-05, "loss": 0.0027, "step": 3620 }, { "epoch": 2.8208317139525847, "grad_norm": 0.06696000141114256, "learning_rate": 8.181212211632799e-05, "loss": 0.0027, "step": 3630 }, { "epoch": 2.8286047415468323, "grad_norm": 0.07223279206852921, "learning_rate": 8.168115467972127e-05, "loss": 0.0027, "step": 3640 }, { "epoch": 2.8363777691410803, "grad_norm": 0.0591131066140708, "learning_rate": 8.154982306340976e-05, "loss": 0.0025, "step": 3650 }, { "epoch": 2.8441507967353283, "grad_norm": 0.07344251027891184, "learning_rate": 8.141812877707043e-05, "loss": 0.0026, "step": 3660 }, { "epoch": 2.8519238243295764, "grad_norm": 0.061294159799181576, "learning_rate": 8.128607333454916e-05, "loss": 0.0025, "step": 3670 }, { "epoch": 2.8596968519238244, "grad_norm": 0.07538040581676492, "learning_rate": 8.115365825384343e-05, "loss": 0.0027, "step": 3680 }, { "epoch": 2.8674698795180724, "grad_norm": 0.068469569338319, "learning_rate": 8.10208850570848e-05, "loss": 0.0027, "step": 3690 }, { "epoch": 2.8752429071123204, "grad_norm": 0.07861201842013094, "learning_rate": 8.088775527052138e-05, "loss": 0.0026, "step": 3700 }, { "epoch": 2.8830159347065685, "grad_norm": 0.07032168038481322, "learning_rate": 8.075427042450039e-05, "loss": 0.0026, "step": 3710 }, { "epoch": 2.890788962300816, "grad_norm": 0.0727619064752268, "learning_rate": 8.062043205345048e-05, "loss": 0.0026, "step": 3720 }, { "epoch": 2.898561989895064, "grad_norm": 0.06690511970065317, "learning_rate": 8.048624169586416e-05, "loss": 0.0025, "step": 3730 }, { "epoch": 2.906335017489312, "grad_norm": 0.06902204913355058, "learning_rate": 8.035170089428002e-05, "loss": 0.0027, "step": 3740 }, { "epoch": 2.91410804508356, "grad_norm": 0.06444050726503392, "learning_rate": 8.021681119526514e-05, "loss": 0.0025, "step": 3750 }, { "epoch": 2.921881072677808, "grad_norm": 0.0703027939730794, "learning_rate": 8.008157414939716e-05, "loss": 0.0025, "step": 3760 }, { "epoch": 2.9296541002720558, "grad_norm": 0.0918381465147948, "learning_rate": 7.994599131124653e-05, "loss": 0.0024, "step": 3770 }, { "epoch": 2.9374271278663038, "grad_norm": 0.08102559952546114, "learning_rate": 7.981006423935867e-05, "loss": 0.0026, "step": 3780 }, { "epoch": 2.945200155460552, "grad_norm": 0.09770131109668051, "learning_rate": 7.967379449623601e-05, "loss": 0.0027, "step": 3790 }, { "epoch": 2.9529731830548, "grad_norm": 0.08951762311198015, "learning_rate": 7.953718364832002e-05, "loss": 0.0028, "step": 3800 }, { "epoch": 2.960746210649048, "grad_norm": 0.0816846540545239, "learning_rate": 7.940023326597323e-05, "loss": 0.0024, "step": 3810 }, { "epoch": 2.968519238243296, "grad_norm": 0.09871637060621355, "learning_rate": 7.926294492346116e-05, "loss": 0.0025, "step": 3820 }, { "epoch": 2.976292265837544, "grad_norm": 0.08781538442295887, "learning_rate": 7.912532019893429e-05, "loss": 0.0024, "step": 3830 }, { "epoch": 2.984065293431792, "grad_norm": 0.06767178490942136, "learning_rate": 7.898736067440975e-05, "loss": 0.0025, "step": 3840 }, { "epoch": 2.9918383210260395, "grad_norm": 0.0745712201927625, "learning_rate": 7.884906793575337e-05, "loss": 0.0025, "step": 3850 }, { "epoch": 2.9996113486202876, "grad_norm": 0.07397282294720663, "learning_rate": 7.871044357266124e-05, "loss": 0.0026, "step": 3860 }, { "epoch": 3.006995724834823, "grad_norm": 0.06317771768056155, "learning_rate": 7.85714891786416e-05, "loss": 0.002, "step": 3870 }, { "epoch": 3.014768752429071, "grad_norm": 0.05292609157896675, "learning_rate": 7.843220635099633e-05, "loss": 0.0016, "step": 3880 }, { "epoch": 3.022541780023319, "grad_norm": 0.04882267190819284, "learning_rate": 7.829259669080284e-05, "loss": 0.0015, "step": 3890 }, { "epoch": 3.030314807617567, "grad_norm": 0.07045644307155315, "learning_rate": 7.815266180289542e-05, "loss": 0.0015, "step": 3900 }, { "epoch": 3.038087835211815, "grad_norm": 0.055379078896731576, "learning_rate": 7.8012403295847e-05, "loss": 0.0014, "step": 3910 }, { "epoch": 3.045860862806063, "grad_norm": 0.057709864957742905, "learning_rate": 7.787182278195047e-05, "loss": 0.0014, "step": 3920 }, { "epoch": 3.053633890400311, "grad_norm": 0.05040524795529855, "learning_rate": 7.773092187720029e-05, "loss": 0.0014, "step": 3930 }, { "epoch": 3.061406917994559, "grad_norm": 0.05035382666579594, "learning_rate": 7.758970220127383e-05, "loss": 0.0013, "step": 3940 }, { "epoch": 3.069179945588807, "grad_norm": 0.05592780408751526, "learning_rate": 7.744816537751283e-05, "loss": 0.0013, "step": 3950 }, { "epoch": 3.076952973183055, "grad_norm": 0.05049381750502883, "learning_rate": 7.730631303290466e-05, "loss": 0.0012, "step": 3960 }, { "epoch": 3.084726000777303, "grad_norm": 0.04277340066544573, "learning_rate": 7.716414679806364e-05, "loss": 0.0012, "step": 3970 }, { "epoch": 3.0924990283715506, "grad_norm": 0.05126338146130596, "learning_rate": 7.702166830721234e-05, "loss": 0.0012, "step": 3980 }, { "epoch": 3.1002720559657986, "grad_norm": 0.055321540703598515, "learning_rate": 7.687887919816271e-05, "loss": 0.0012, "step": 3990 }, { "epoch": 3.1080450835600466, "grad_norm": 0.05448432149053431, "learning_rate": 7.673578111229738e-05, "loss": 0.0013, "step": 4000 }, { "epoch": 3.1158181111542946, "grad_norm": 0.05849173735885185, "learning_rate": 7.659237569455064e-05, "loss": 0.0013, "step": 4010 }, { "epoch": 3.1235911387485427, "grad_norm": 0.0532028841075432, "learning_rate": 7.644866459338964e-05, "loss": 0.0012, "step": 4020 }, { "epoch": 3.1313641663427907, "grad_norm": 0.04800300277794506, "learning_rate": 7.630464946079543e-05, "loss": 0.0013, "step": 4030 }, { "epoch": 3.1391371939370383, "grad_norm": 0.05653617859760966, "learning_rate": 7.616033195224391e-05, "loss": 0.0013, "step": 4040 }, { "epoch": 3.1469102215312863, "grad_norm": 0.06752313338740537, "learning_rate": 7.601571372668682e-05, "loss": 0.0013, "step": 4050 }, { "epoch": 3.1546832491255343, "grad_norm": 0.05046243795487172, "learning_rate": 7.587079644653277e-05, "loss": 0.0013, "step": 4060 }, { "epoch": 3.1624562767197824, "grad_norm": 0.05678047625277804, "learning_rate": 7.572558177762797e-05, "loss": 0.0013, "step": 4070 }, { "epoch": 3.1702293043140304, "grad_norm": 0.05051804020211108, "learning_rate": 7.558007138923718e-05, "loss": 0.0012, "step": 4080 }, { "epoch": 3.1780023319082784, "grad_norm": 0.05610066773526129, "learning_rate": 7.543426695402452e-05, "loss": 0.0013, "step": 4090 }, { "epoch": 3.1857753595025264, "grad_norm": 0.04650111729446382, "learning_rate": 7.52881701480342e-05, "loss": 0.0012, "step": 4100 }, { "epoch": 3.193548387096774, "grad_norm": 0.05002456571280218, "learning_rate": 7.514178265067129e-05, "loss": 0.0013, "step": 4110 }, { "epoch": 3.201321414691022, "grad_norm": 0.054771821749841916, "learning_rate": 7.49951061446824e-05, "loss": 0.0012, "step": 4120 }, { "epoch": 3.20909444228527, "grad_norm": 0.054851003739267906, "learning_rate": 7.484814231613633e-05, "loss": 0.0012, "step": 4130 }, { "epoch": 3.216867469879518, "grad_norm": 0.05095639836386469, "learning_rate": 7.470089285440471e-05, "loss": 0.0013, "step": 4140 }, { "epoch": 3.224640497473766, "grad_norm": 0.051210658981078835, "learning_rate": 7.455335945214257e-05, "loss": 0.0013, "step": 4150 }, { "epoch": 3.232413525068014, "grad_norm": 0.050630687016918294, "learning_rate": 7.440554380526884e-05, "loss": 0.0012, "step": 4160 }, { "epoch": 3.2401865526622617, "grad_norm": 0.05481015847694094, "learning_rate": 7.425744761294696e-05, "loss": 0.0014, "step": 4170 }, { "epoch": 3.2479595802565098, "grad_norm": 0.04746139811284292, "learning_rate": 7.41090725775652e-05, "loss": 0.0012, "step": 4180 }, { "epoch": 3.255732607850758, "grad_norm": 0.0488852581761488, "learning_rate": 7.396042040471728e-05, "loss": 0.0012, "step": 4190 }, { "epoch": 3.263505635445006, "grad_norm": 0.054029849239582, "learning_rate": 7.381149280318255e-05, "loss": 0.0013, "step": 4200 }, { "epoch": 3.271278663039254, "grad_norm": 0.05953354906133648, "learning_rate": 7.366229148490654e-05, "loss": 0.0013, "step": 4210 }, { "epoch": 3.279051690633502, "grad_norm": 0.06131326556461926, "learning_rate": 7.351281816498113e-05, "loss": 0.0014, "step": 4220 }, { "epoch": 3.2868247182277495, "grad_norm": 0.059091602709714926, "learning_rate": 7.336307456162492e-05, "loss": 0.0014, "step": 4230 }, { "epoch": 3.2945977458219975, "grad_norm": 0.07565280363176315, "learning_rate": 7.32130623961635e-05, "loss": 0.0014, "step": 4240 }, { "epoch": 3.3023707734162455, "grad_norm": 0.056892619126486126, "learning_rate": 7.306278339300959e-05, "loss": 0.0013, "step": 4250 }, { "epoch": 3.3101438010104935, "grad_norm": 0.11209680884929493, "learning_rate": 7.291223927964321e-05, "loss": 0.0015, "step": 4260 }, { "epoch": 3.3179168286047416, "grad_norm": 0.053482607975617505, "learning_rate": 7.276143178659194e-05, "loss": 0.0014, "step": 4270 }, { "epoch": 3.3256898561989896, "grad_norm": 0.04564916808200296, "learning_rate": 7.261036264741092e-05, "loss": 0.0013, "step": 4280 }, { "epoch": 3.3334628837932376, "grad_norm": 0.045353190964480296, "learning_rate": 7.24590335986629e-05, "loss": 0.0013, "step": 4290 }, { "epoch": 3.3412359113874857, "grad_norm": 0.05770878613559124, "learning_rate": 7.230744637989841e-05, "loss": 0.0012, "step": 4300 }, { "epoch": 3.3490089389817332, "grad_norm": 0.04582085382704389, "learning_rate": 7.215560273363564e-05, "loss": 0.0012, "step": 4310 }, { "epoch": 3.3567819665759813, "grad_norm": 0.05126717402300159, "learning_rate": 7.200350440534048e-05, "loss": 0.0013, "step": 4320 }, { "epoch": 3.3645549941702293, "grad_norm": 0.05175638481119324, "learning_rate": 7.185115314340638e-05, "loss": 0.0013, "step": 4330 }, { "epoch": 3.3723280217644773, "grad_norm": 0.05311419733020393, "learning_rate": 7.169855069913434e-05, "loss": 0.0013, "step": 4340 }, { "epoch": 3.3801010493587254, "grad_norm": 0.056853567416186954, "learning_rate": 7.154569882671273e-05, "loss": 0.0013, "step": 4350 }, { "epoch": 3.387874076952973, "grad_norm": 0.04541502908826204, "learning_rate": 7.139259928319715e-05, "loss": 0.0013, "step": 4360 }, { "epoch": 3.395647104547221, "grad_norm": 0.050130248796668546, "learning_rate": 7.12392538284902e-05, "loss": 0.0014, "step": 4370 }, { "epoch": 3.403420132141469, "grad_norm": 0.05299964388790246, "learning_rate": 7.108566422532123e-05, "loss": 0.0013, "step": 4380 }, { "epoch": 3.411193159735717, "grad_norm": 0.0508152329921838, "learning_rate": 7.093183223922621e-05, "loss": 0.0013, "step": 4390 }, { "epoch": 3.418966187329965, "grad_norm": 0.057542259788822554, "learning_rate": 7.077775963852724e-05, "loss": 0.0014, "step": 4400 }, { "epoch": 3.426739214924213, "grad_norm": 0.050631581931810374, "learning_rate": 7.06234481943124e-05, "loss": 0.0014, "step": 4410 }, { "epoch": 3.434512242518461, "grad_norm": 0.06953796070789972, "learning_rate": 7.046889968041524e-05, "loss": 0.0014, "step": 4420 }, { "epoch": 3.442285270112709, "grad_norm": 0.05342125151124089, "learning_rate": 7.03141158733945e-05, "loss": 0.0013, "step": 4430 }, { "epoch": 3.4500582977069567, "grad_norm": 0.052119437229514516, "learning_rate": 7.015909855251367e-05, "loss": 0.0014, "step": 4440 }, { "epoch": 3.4578313253012047, "grad_norm": 0.06486726674849891, "learning_rate": 7.000384949972047e-05, "loss": 0.0014, "step": 4450 }, { "epoch": 3.4656043528954528, "grad_norm": 0.06859610570190047, "learning_rate": 6.984837049962646e-05, "loss": 0.0014, "step": 4460 }, { "epoch": 3.473377380489701, "grad_norm": 0.05617796165249675, "learning_rate": 6.969266333948646e-05, "loss": 0.0014, "step": 4470 }, { "epoch": 3.481150408083949, "grad_norm": 0.06717819564707593, "learning_rate": 6.953672980917801e-05, "loss": 0.0015, "step": 4480 }, { "epoch": 3.488923435678197, "grad_norm": 0.0685334676438363, "learning_rate": 6.938057170118082e-05, "loss": 0.0014, "step": 4490 }, { "epoch": 3.4966964632724444, "grad_norm": 0.053206585518083986, "learning_rate": 6.922419081055617e-05, "loss": 0.0013, "step": 4500 }, { "epoch": 3.5044694908666925, "grad_norm": 0.057804877493537, "learning_rate": 6.906758893492624e-05, "loss": 0.0013, "step": 4510 }, { "epoch": 3.5122425184609405, "grad_norm": 0.0752984087415248, "learning_rate": 6.891076787445348e-05, "loss": 0.0014, "step": 4520 }, { "epoch": 3.5200155460551885, "grad_norm": 0.07684456686374479, "learning_rate": 6.875372943181989e-05, "loss": 0.0014, "step": 4530 }, { "epoch": 3.5277885736494365, "grad_norm": 0.05151187127939253, "learning_rate": 6.859647541220633e-05, "loss": 0.0015, "step": 4540 }, { "epoch": 3.5355616012436846, "grad_norm": 0.06120977928590361, "learning_rate": 6.843900762327171e-05, "loss": 0.0015, "step": 4550 }, { "epoch": 3.5433346288379326, "grad_norm": 0.052241865212588494, "learning_rate": 6.828132787513232e-05, "loss": 0.0015, "step": 4560 }, { "epoch": 3.55110765643218, "grad_norm": 0.062291869625660766, "learning_rate": 6.812343798034088e-05, "loss": 0.0015, "step": 4570 }, { "epoch": 3.558880684026428, "grad_norm": 0.06940645079889347, "learning_rate": 6.796533975386582e-05, "loss": 0.0014, "step": 4580 }, { "epoch": 3.5666537116206762, "grad_norm": 0.05299761798149833, "learning_rate": 6.780703501307037e-05, "loss": 0.0015, "step": 4590 }, { "epoch": 3.5744267392149243, "grad_norm": 0.0553631663183678, "learning_rate": 6.764852557769168e-05, "loss": 0.0014, "step": 4600 }, { "epoch": 3.5821997668091723, "grad_norm": 0.05928665736489485, "learning_rate": 6.748981326981987e-05, "loss": 0.0014, "step": 4610 }, { "epoch": 3.58997279440342, "grad_norm": 0.06100690574773009, "learning_rate": 6.733089991387711e-05, "loss": 0.0013, "step": 4620 }, { "epoch": 3.597745821997668, "grad_norm": 0.06554679880311645, "learning_rate": 6.717178733659669e-05, "loss": 0.0015, "step": 4630 }, { "epoch": 3.605518849591916, "grad_norm": 0.04648835107205993, "learning_rate": 6.701247736700193e-05, "loss": 0.0014, "step": 4640 }, { "epoch": 3.613291877186164, "grad_norm": 0.0485433533499338, "learning_rate": 6.685297183638524e-05, "loss": 0.0013, "step": 4650 }, { "epoch": 3.621064904780412, "grad_norm": 0.05273132935003627, "learning_rate": 6.669327257828702e-05, "loss": 0.0013, "step": 4660 }, { "epoch": 3.62883793237466, "grad_norm": 0.050580958804008154, "learning_rate": 6.653338142847459e-05, "loss": 0.0013, "step": 4670 }, { "epoch": 3.636610959968908, "grad_norm": 0.0522871787450838, "learning_rate": 6.637330022492112e-05, "loss": 0.0013, "step": 4680 }, { "epoch": 3.644383987563156, "grad_norm": 0.054308887619061295, "learning_rate": 6.621303080778445e-05, "loss": 0.0014, "step": 4690 }, { "epoch": 3.6521570151574037, "grad_norm": 0.05378027866810176, "learning_rate": 6.605257501938596e-05, "loss": 0.0014, "step": 4700 }, { "epoch": 3.6599300427516517, "grad_norm": 0.05266369589319868, "learning_rate": 6.589193470418941e-05, "loss": 0.0014, "step": 4710 }, { "epoch": 3.6677030703458997, "grad_norm": 0.05465334294471026, "learning_rate": 6.573111170877976e-05, "loss": 0.0013, "step": 4720 }, { "epoch": 3.6754760979401477, "grad_norm": 0.05753126693229123, "learning_rate": 6.557010788184182e-05, "loss": 0.0015, "step": 4730 }, { "epoch": 3.6832491255343958, "grad_norm": 0.0867356792695403, "learning_rate": 6.540892507413917e-05, "loss": 0.0016, "step": 4740 }, { "epoch": 3.6910221531286433, "grad_norm": 0.06764490662130833, "learning_rate": 6.524756513849273e-05, "loss": 0.0014, "step": 4750 }, { "epoch": 3.6987951807228914, "grad_norm": 0.0704576802572128, "learning_rate": 6.508602992975963e-05, "loss": 0.0016, "step": 4760 }, { "epoch": 3.7065682083171394, "grad_norm": 0.0802767664255637, "learning_rate": 6.492432130481166e-05, "loss": 0.0015, "step": 4770 }, { "epoch": 3.7143412359113874, "grad_norm": 0.06395636400017118, "learning_rate": 6.476244112251418e-05, "loss": 0.0014, "step": 4780 }, { "epoch": 3.7221142635056355, "grad_norm": 0.0811016126799815, "learning_rate": 6.460039124370455e-05, "loss": 0.0015, "step": 4790 }, { "epoch": 3.7298872910998835, "grad_norm": 0.07545299601321427, "learning_rate": 6.443817353117085e-05, "loss": 0.0014, "step": 4800 }, { "epoch": 3.7376603186941315, "grad_norm": 0.0573497980247029, "learning_rate": 6.42757898496304e-05, "loss": 0.0013, "step": 4810 }, { "epoch": 3.7454333462883795, "grad_norm": 0.05669253189317607, "learning_rate": 6.411324206570843e-05, "loss": 0.0014, "step": 4820 }, { "epoch": 3.753206373882627, "grad_norm": 0.060651625048542414, "learning_rate": 6.395053204791648e-05, "loss": 0.0013, "step": 4830 }, { "epoch": 3.760979401476875, "grad_norm": 0.06271483916694727, "learning_rate": 6.378766166663102e-05, "loss": 0.0014, "step": 4840 }, { "epoch": 3.768752429071123, "grad_norm": 0.058985216905366365, "learning_rate": 6.362463279407192e-05, "loss": 0.0013, "step": 4850 }, { "epoch": 3.776525456665371, "grad_norm": 0.08016429533408413, "learning_rate": 6.346144730428094e-05, "loss": 0.0014, "step": 4860 }, { "epoch": 3.7842984842596192, "grad_norm": 0.05464432483179166, "learning_rate": 6.329810707310017e-05, "loss": 0.0014, "step": 4870 }, { "epoch": 3.792071511853867, "grad_norm": 0.05302175690868426, "learning_rate": 6.313461397815049e-05, "loss": 0.0014, "step": 4880 }, { "epoch": 3.799844539448115, "grad_norm": 0.051860409972017484, "learning_rate": 6.297096989880994e-05, "loss": 0.0014, "step": 4890 }, { "epoch": 3.807617567042363, "grad_norm": 0.06121655864510598, "learning_rate": 6.280717671619219e-05, "loss": 0.0013, "step": 4900 }, { "epoch": 3.815390594636611, "grad_norm": 0.04964639600777849, "learning_rate": 6.264323631312483e-05, "loss": 0.0013, "step": 4910 }, { "epoch": 3.823163622230859, "grad_norm": 0.05610965209960934, "learning_rate": 6.247915057412781e-05, "loss": 0.0013, "step": 4920 }, { "epoch": 3.830936649825107, "grad_norm": 0.06260573144334115, "learning_rate": 6.231492138539174e-05, "loss": 0.0013, "step": 4930 }, { "epoch": 3.838709677419355, "grad_norm": 0.05298276249108928, "learning_rate": 6.21505506347562e-05, "loss": 0.0014, "step": 4940 }, { "epoch": 3.846482705013603, "grad_norm": 0.058326570847754826, "learning_rate": 6.198604021168798e-05, "loss": 0.0013, "step": 4950 }, { "epoch": 3.8542557326078506, "grad_norm": 0.05260934675853932, "learning_rate": 6.182139200725953e-05, "loss": 0.0013, "step": 4960 }, { "epoch": 3.8620287602020986, "grad_norm": 0.05423996230834983, "learning_rate": 6.165660791412704e-05, "loss": 0.0013, "step": 4970 }, { "epoch": 3.8698017877963466, "grad_norm": 0.051638650500176166, "learning_rate": 6.149168982650882e-05, "loss": 0.0013, "step": 4980 }, { "epoch": 3.8775748153905947, "grad_norm": 0.05511171077247131, "learning_rate": 6.132663964016343e-05, "loss": 0.0013, "step": 4990 }, { "epoch": 3.8853478429848427, "grad_norm": 0.04961157230866775, "learning_rate": 6.116145925236795e-05, "loss": 0.0013, "step": 5000 }, { "epoch": 3.8931208705790903, "grad_norm": 0.05265851472161743, "learning_rate": 6.099615056189609e-05, "loss": 0.0013, "step": 5010 }, { "epoch": 3.9008938981733383, "grad_norm": 0.05197040384153092, "learning_rate": 6.083071546899649e-05, "loss": 0.0012, "step": 5020 }, { "epoch": 3.9086669257675863, "grad_norm": 0.058677791758000766, "learning_rate": 6.066515587537077e-05, "loss": 0.0014, "step": 5030 }, { "epoch": 3.9164399533618344, "grad_norm": 0.05080762076034653, "learning_rate": 6.0499473684151695e-05, "loss": 0.0013, "step": 5040 }, { "epoch": 3.9242129809560824, "grad_norm": 0.0505243429638093, "learning_rate": 6.0333670799881346e-05, "loss": 0.0012, "step": 5050 }, { "epoch": 3.9319860085503304, "grad_norm": 0.04592349968189807, "learning_rate": 6.0167749128489136e-05, "loss": 0.0012, "step": 5060 }, { "epoch": 3.9397590361445785, "grad_norm": 0.05707189919349449, "learning_rate": 6.000171057726999e-05, "loss": 0.0013, "step": 5070 }, { "epoch": 3.9475320637388265, "grad_norm": 0.0526931495556647, "learning_rate": 5.983555705486239e-05, "loss": 0.0012, "step": 5080 }, { "epoch": 3.9553050913330745, "grad_norm": 0.051013582659466365, "learning_rate": 5.9669290471226405e-05, "loss": 0.0013, "step": 5090 }, { "epoch": 3.963078118927322, "grad_norm": 0.052603820387661857, "learning_rate": 5.9502912737621764e-05, "loss": 0.0012, "step": 5100 }, { "epoch": 3.97085114652157, "grad_norm": 0.051720172092351926, "learning_rate": 5.9336425766585924e-05, "loss": 0.0012, "step": 5110 }, { "epoch": 3.978624174115818, "grad_norm": 0.10597495725038626, "learning_rate": 5.9169831471911974e-05, "loss": 0.0013, "step": 5120 }, { "epoch": 3.986397201710066, "grad_norm": 0.04999517365959679, "learning_rate": 5.900313176862675e-05, "loss": 0.0013, "step": 5130 }, { "epoch": 3.9941702293043138, "grad_norm": 0.05994926145731603, "learning_rate": 5.883632857296876e-05, "loss": 0.0013, "step": 5140 }, { "epoch": 4.00155460551885, "grad_norm": 0.06828827893546477, "learning_rate": 5.8669423802366177e-05, "loss": 0.0012, "step": 5150 }, { "epoch": 4.009327633113098, "grad_norm": 0.04581917688238487, "learning_rate": 5.850241937541482e-05, "loss": 0.0008, "step": 5160 }, { "epoch": 4.017100660707346, "grad_norm": 0.04767494608662352, "learning_rate": 5.833531721185601e-05, "loss": 0.0008, "step": 5170 }, { "epoch": 4.024873688301594, "grad_norm": 0.03415064425236542, "learning_rate": 5.8168119232554605e-05, "loss": 0.0007, "step": 5180 }, { "epoch": 4.032646715895841, "grad_norm": 0.03156168690639689, "learning_rate": 5.80008273594769e-05, "loss": 0.0006, "step": 5190 }, { "epoch": 4.040419743490089, "grad_norm": 0.02775459034078891, "learning_rate": 5.783344351566849e-05, "loss": 0.0006, "step": 5200 }, { "epoch": 4.048192771084337, "grad_norm": 0.03752890797711968, "learning_rate": 5.7665969625232174e-05, "loss": 0.0006, "step": 5210 }, { "epoch": 4.055965798678585, "grad_norm": 0.039795978106431484, "learning_rate": 5.749840761330587e-05, "loss": 0.0006, "step": 5220 }, { "epoch": 4.063738826272833, "grad_norm": 0.04591425788703762, "learning_rate": 5.733075940604045e-05, "loss": 0.0006, "step": 5230 }, { "epoch": 4.071511853867081, "grad_norm": 0.03678302094567926, "learning_rate": 5.7163026930577636e-05, "loss": 0.0006, "step": 5240 }, { "epoch": 4.079284881461329, "grad_norm": 0.042733165935266, "learning_rate": 5.69952121150278e-05, "loss": 0.0006, "step": 5250 }, { "epoch": 4.087057909055577, "grad_norm": 0.034514951085523264, "learning_rate": 5.682731688844786e-05, "loss": 0.0005, "step": 5260 }, { "epoch": 4.094830936649825, "grad_norm": 0.03331717312064519, "learning_rate": 5.6659343180819036e-05, "loss": 0.0005, "step": 5270 }, { "epoch": 4.102603964244073, "grad_norm": 0.04058083373382621, "learning_rate": 5.649129292302473e-05, "loss": 0.0005, "step": 5280 }, { "epoch": 4.110376991838321, "grad_norm": 0.034283836253464796, "learning_rate": 5.632316804682828e-05, "loss": 0.0005, "step": 5290 }, { "epoch": 4.118150019432569, "grad_norm": 0.037857136276281164, "learning_rate": 5.615497048485078e-05, "loss": 0.0005, "step": 5300 }, { "epoch": 4.125923047026817, "grad_norm": 0.038838286688120054, "learning_rate": 5.598670217054883e-05, "loss": 0.0005, "step": 5310 }, { "epoch": 4.1336960746210645, "grad_norm": 0.02729201236801898, "learning_rate": 5.58183650381924e-05, "loss": 0.0005, "step": 5320 }, { "epoch": 4.1414691022153125, "grad_norm": 0.04084905595927271, "learning_rate": 5.56499610228425e-05, "loss": 0.0005, "step": 5330 }, { "epoch": 4.1492421298095605, "grad_norm": 0.032422360783001807, "learning_rate": 5.5481492060328945e-05, "loss": 0.0005, "step": 5340 }, { "epoch": 4.157015157403809, "grad_norm": 0.037801558928930515, "learning_rate": 5.531296008722816e-05, "loss": 0.0004, "step": 5350 }, { "epoch": 4.164788184998057, "grad_norm": 0.03619523638310936, "learning_rate": 5.5144367040840896e-05, "loss": 0.0006, "step": 5360 }, { "epoch": 4.172561212592305, "grad_norm": 0.04120623681054301, "learning_rate": 5.4975714859169914e-05, "loss": 0.0005, "step": 5370 }, { "epoch": 4.180334240186553, "grad_norm": 0.029566587403069115, "learning_rate": 5.480700548089779e-05, "loss": 0.0005, "step": 5380 }, { "epoch": 4.188107267780801, "grad_norm": 0.03750169201927612, "learning_rate": 5.463824084536453e-05, "loss": 0.0005, "step": 5390 }, { "epoch": 4.195880295375049, "grad_norm": 0.030745808156288912, "learning_rate": 5.446942289254536e-05, "loss": 0.0006, "step": 5400 } ], "logging_steps": 10, "max_steps": 10296, "num_input_tokens_seen": 0, "num_train_epochs": 8, "save_steps": 1800, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 398221773373440.0, "train_batch_size": 128, "trial_name": null, "trial_params": null }