1{"step": 0, "loss": 3.8388280868530273, "lr": 1e-05, "grad_norm": 0.16530217230319977, "tokens": 8192, "tok_per_s": 2189.991939034647, "t": 4.68}2{"step": 20, "loss": 3.6808035373687744, "lr": 0.00021, "grad_norm": 0.12511877715587616, "tokens": 172032, "tok_per_s": 5002.09611667842, "t": 35.32}3{"step": 40, "loss": 4.014457702636719, "lr": 0.00041, "grad_norm": 0.0881873220205307, "tokens": 335872, "tok_per_s": 5019.691035329243, "t": 67.84}4{"step": 60, "loss": 3.8157753944396973, "lr": 0.00061, "grad_norm": 0.03329641371965408, "tokens": 499712, "tok_per_s": 4603.33171524539, "t": 109.49}5{"step": 80, "loss": 3.748676300048828, "lr": 0.0008100000000000001, "grad_norm": 0.006027274299412966, "tokens": 663552, "tok_per_s": 4349.375187402932, "t": 153.5}6{"step": 100, "loss": 3.5858542919158936, "lr": 0.001, "grad_norm": 0.0052193086594343185, "tokens": 827392, "tok_per_s": 4246.1046996405585, "t": 195.79}7{"step": 120, "loss": 3.880399703979492, "lr": 0.000999894384108318, "grad_norm": 0.0109785757958889, "tokens": 991232, "tok_per_s": 4354.167269393639, "t": 228.58}8{"step": 140, "loss": 3.7840025424957275, "lr": 0.0009995775860097895, "grad_norm": 0.011240311898291111, "tokens": 1155072, "tok_per_s": 4367.789164033511, "t": 265.39}9{"step": 160, "loss": 3.9886162281036377, "lr": 0.000999049754410698, "grad_norm": 0.004560643341392279, "tokens": 1318912, "tok_per_s": 4373.153491430897, "t": 302.53}10{"step": 180, "loss": 3.9944658279418945, "lr": 0.0009983111370772877, "grad_norm": 0.007128031458705664, "tokens": 1482752, "tok_per_s": 4143.04601602991, "t": 358.82}11{"step": 200, "loss": 3.7739675045013428, "lr": 0.0009973620807194618, "grad_norm": 0.009019775316119194, "tokens": 1646592, "tok_per_s": 4281.481688401505, "t": 385.52}12{"step": 220, "loss": 3.863001823425293, "lr": 0.0009962030308280363, "grad_norm": 0.00519289867952466, "tokens": 1810432, "tok_per_s": 4359.186253399564, "t": 416.25}13{"step": 240, "loss": 3.7191781997680664, "lr": 0.0009948345314656232, "grad_norm": 0.002841966226696968, "tokens": 1974272, "tok_per_s": 4425.933517637247, "t": 447.0}14{"step": 260, "loss": 3.637939691543579, "lr": 0.0009932572250112468, "grad_norm": 0.0029124803841114044, "tokens": 2138112, "tok_per_s": 4490.33257828908, "t": 477.09}15{"step": 280, "loss": 3.698286771774292, "lr": 0.0009914718518588075, "grad_norm": 0.0032131168991327286, "tokens": 2301952, "tok_per_s": 4544.006774049553, "t": 507.52}16{"step": 300, "loss": 3.9921610355377197, "lr": 0.000989479250069539, "grad_norm": 0.0010528202401474118, "tokens": 2465792, "tok_per_s": 4562.92531436956, "t": 541.33}17{"step": 320, "loss": 3.7762327194213867, "lr": 0.0009872803549786176, "grad_norm": 0.0062053934670984745, "tokens": 2629632, "tok_per_s": 4520.799035769652, "t": 582.61}18{"step": 340, "loss": 3.804210662841797, "lr": 0.0009848761987561131, "grad_norm": 0.0005900497199036181, "tokens": 2793472, "tok_per_s": 4561.215643978213, "t": 613.37}19{"step": 360, "loss": 3.604156255722046, "lr": 0.0009822679099224844, "grad_norm": 3.352270505274646e-05, "tokens": 2957312, "tok_per_s": 4587.212764933459, "t": 645.62}20{"step": 380, "loss": 3.8292174339294434, "lr": 0.0009794567128188466, "grad_norm": 4.346859896031674e-06, "tokens": 3121152, "tok_per_s": 4608.571327450373, "t": 678.18}21{"step": 400, "loss": 3.7056641578674316, "lr": 0.0009764439270322612, "grad_norm": 9.81551238510292e-06, "tokens": 3284992, "tok_per_s": 4593.664180642176, "t": 716.05}22{"step": 420, "loss": 3.809422492980957, "lr": 0.0009732309667763159, "grad_norm": 0.0003124283975921571, "tokens": 3448832, "tok_per_s": 4606.842777291537, "t": 749.57}23{"step": 440, "loss": 3.8328089714050293, "lr": 0.0009698193402272879, "grad_norm": 7.377779638773063e-06, "tokens": 3612672, "tok_per_s": 4502.143707626625, "t": 803.37}24{"step": 460, "loss": 3.6838221549987793, "lr": 0.0009662106488162, "grad_norm": 8.204017831303645e-06, "tokens": 3776512, "tok_per_s": 4508.4363438224755, "t": 838.59}25{"step": 480, "loss": 3.674121856689453, "lr": 0.0009624065864771017, "grad_norm": 0.0011083257850259542, "tokens": 3940352, "tok_per_s": 4515.839882247294, "t": 873.5}26{"step": 499, "val_loss_b0": 3.9889174699783325, "val_loss_b1": 3.9889174461364747, "val_loss_b2": 3.9889180421829225, "val_loss_b4": 3.988917875289917, "val_loss_b8": 3.9889188766479493, "t": 952.44}27{"step": 500, "loss": 3.5863096714019775, "lr": 0.0009584089388519307, "grad_norm": 2.0285011487430893e-05, "tokens": 4104192, "tok_per_s": 4295.777773575887, "t": 956.34}28{"step": 520, "loss": 3.732170581817627, "lr": 0.0009542195824523249, "grad_norm": 5.151562731953163e-08, "tokens": 4268032, "tok_per_s": 4297.374844580515, "t": 994.1}29{"step": 540, "loss": 3.6762001514434814, "lr": 0.0009498404837787811, "grad_norm": 2.5482135242782533e-05, "tokens": 4431872, "tok_per_s": 4338.979835204479, "t": 1022.34}30{"step": 560, "loss": 3.8690714836120605, "lr": 0.0009452736983975708, "grad_norm": 0.00144662382081151, "tokens": 4595712, "tok_per_s": 4356.228424811298, "t": 1055.91}31{"step": 580, "loss": 3.806818962097168, "lr": 0.0009405213699758506, "grad_norm": 0.0021665082313120365, "tokens": 4759552, "tok_per_s": 4386.901428827112, "t": 1085.88}32{"step": 600, "loss": 3.8241353034973145, "lr": 0.0009355857292754152, "grad_norm": 6.351193587761372e-05, "tokens": 4923392, "tok_per_s": 4410.270631365612, "t": 1117.28}33{"step": 620, "loss": 3.6988236904144287, "lr": 0.0009304690931055693, "grad_norm": 6.431922088268038e-07, "tokens": 5087232, "tok_per_s": 4429.192935899972, "t": 1149.5}34{"step": 640, "loss": 3.8020288944244385, "lr": 0.0009251738632356086, "grad_norm": 4.0666203858563676e-05, "tokens": 5251072, "tok_per_s": 4413.326106278967, "t": 1190.75}35