SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.3192179799079895, "lr": 1e-05, "grad_norm": 0.004918727558106184, "tokens": 136, "tok_per_s": 25.82743242265494, "t": 5.88}2{"step": 50, "loss": 0.2608621418476105, "lr": 0.00051, "grad_norm": 0.004002388566732407, "tokens": 8301, "tok_per_s": 221.55287613056694, "t": 38.08}3{"step": 100, "loss": 0.2838420867919922, "lr": 0.001, "grad_norm": 0.009674794040620327, "tokens": 16522, "tok_per_s": 276.6811609435001, "t": 60.33}4{"step": 150, "loss": 0.2172185331583023, "lr": 0.0009993400362330058, "grad_norm": 0.009722846560180187, "tokens": 24768, "tok_per_s": 303.6098868097615, "t": 82.19}5{"step": 200, "loss": 0.3022150695323944, "lr": 0.0009973620807194618, "grad_norm": 0.015606597997248173, "tokens": 33364, "tok_per_s": 323.36409735976235, "t": 103.79}6{"step": 250, "loss": 0.2630655765533447, "lr": 0.000994071935143687, "grad_norm": 0.00781400129199028, "tokens": 41548, "tok_per_s": 331.6325393939442, "t": 125.9}7{"step": 300, "loss": 0.3197755813598633, "lr": 0.000989479250069539, "grad_norm": 0.013463854789733887, "tokens": 49940, "tok_per_s": 338.85382127134994, "t": 147.99}8{"step": 350, "loss": 0.2694982886314392, "lr": 0.0009835974966336503, "grad_norm": 0.013273538090288639, "tokens": 58138, "tok_per_s": 344.4789436451191, "t": 169.38}9{"step": 400, "loss": 0.3633333146572113, "lr": 0.0009764439270322612, "grad_norm": 0.011917849071323872, "tokens": 66357, "tok_per_s": 347.6186471231152, "t": 191.5}10{"step": 450, "loss": 0.2707832455635071, "lr": 0.0009680395239175562, "grad_norm": 0.010077452287077904, "tokens": 74677, "tok_per_s": 351.7919457470124, "t": 212.89}11{"step": 499, "val_loss_b0": 0.41442169654245364, "val_loss_b1": 0.4143188910179648, "val_loss_b2": 0.41434928389573344, "val_loss_b4": 0.4145523853500389, "val_loss_b8": 0.4164288238820137, "t": 238.35}12{"step": 500, "loss": 0.3310023844242096, "lr": 0.0009584089388519307, "grad_norm": 0.015196610242128372, "tokens": 83033, "tok_per_s": 348.62164355539795, "t": 238.79}13{"step": 550, "loss": 0.2803497016429901, "lr": 0.0009475804200007103, "grad_norm": 0.012505416758358479, "tokens": 91368, "tok_per_s": 351.2446636859917, "t": 260.74}14{"step": 600, "loss": 0.3320615291595459, "lr": 0.0009355857292754152, "grad_norm": 0.010147147811949253, "tokens": 99517, "tok_per_s": 352.90750633707677, "t": 282.6}15{"step": 650, "loss": 0.24493151903152466, "lr": 0.0009224600491706008, "grad_norm": 0.013797991909086704, "tokens": 107636, "tok_per_s": 353.9739857635011, "t": 304.69}16{"step": 700, "loss": 0.26863163709640503, "lr": 0.0009082418795675396, "grad_norm": 0.01640203222632408, "tokens": 115923, "tok_per_s": 355.93056597314825, "t": 326.3}17{"step": 750, "loss": 0.27431315183639526, "lr": 0.0008929729248074364, "grad_norm": 0.027448339387774467, "tokens": 124250, "tok_per_s": 357.3704845677696, "t": 348.29}18{"step": 800, "loss": 0.40662869811058044, "lr": 0.0008766979713654089, "grad_norm": 0.017294418066740036, "tokens": 132683, "tok_per_s": 358.588086915113, "t": 370.63}19{"step": 850, "loss": 0.2539444863796234, "lr": 0.0008594647564840406, "grad_norm": 0.023262226954102516, "tokens": 140993, "tok_per_s": 359.6254528926168, "t": 392.67}20{"step": 900, "loss": 0.36071065068244934, "lr": 0.0008413238281518224, "grad_norm": 0.017947403714060783, "tokens": 148988, "tok_per_s": 355.0166654655354, "t": 420.28}21
Files · 20e88d79efe28fb13610284e7be1ef0ef40c265d
Menu

Theme