| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7629947544110635, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0019074868860276585, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 1.9987282207808727e-05, | |
| "loss": 1.8153, | |
| "mean_token_accuracy": 0.5708044067025184, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003814973772055317, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.997456441561745e-05, | |
| "loss": 1.5088, | |
| "mean_token_accuracy": 0.6002451926469803, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005722460658082976, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 1.9961846623426175e-05, | |
| "loss": 1.5696, | |
| "mean_token_accuracy": 0.5999565117061139, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007629947544110634, | |
| "grad_norm": 6.0, | |
| "learning_rate": 1.9949128831234897e-05, | |
| "loss": 1.4962, | |
| "mean_token_accuracy": 0.6145946934819222, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009537434430138292, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.9936411039043622e-05, | |
| "loss": 1.4145, | |
| "mean_token_accuracy": 0.6282299846410752, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011444921316165951, | |
| "grad_norm": 5.75, | |
| "learning_rate": 1.9923693246852348e-05, | |
| "loss": 1.4615, | |
| "mean_token_accuracy": 0.6196133770048619, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01335240820219361, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.9910975454661073e-05, | |
| "loss": 1.4118, | |
| "mean_token_accuracy": 0.6272433631122112, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.015259895088221268, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.98982576624698e-05, | |
| "loss": 1.3874, | |
| "mean_token_accuracy": 0.6295698702335357, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017167381974248927, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 1.988553987027852e-05, | |
| "loss": 1.4997, | |
| "mean_token_accuracy": 0.6131108298897743, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.019074868860276584, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.9872822078087246e-05, | |
| "loss": 1.3386, | |
| "mean_token_accuracy": 0.6355413243174552, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020982355746304245, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.986010428589597e-05, | |
| "loss": 1.3453, | |
| "mean_token_accuracy": 0.6322750248014927, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.022889842632331903, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.9847386493704694e-05, | |
| "loss": 1.4213, | |
| "mean_token_accuracy": 0.6266717866063118, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02479732951835956, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 1.983466870151342e-05, | |
| "loss": 1.3913, | |
| "mean_token_accuracy": 0.6290012784302235, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.02670481640438722, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.982195090932214e-05, | |
| "loss": 1.3871, | |
| "mean_token_accuracy": 0.627622963488102, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02861230329041488, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.9809233117130867e-05, | |
| "loss": 1.3232, | |
| "mean_token_accuracy": 0.6432097807526589, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.030519790176442536, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 1.9796515324939593e-05, | |
| "loss": 1.3287, | |
| "mean_token_accuracy": 0.6405125185847282, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03242727706247019, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.9783797532748318e-05, | |
| "loss": 1.4044, | |
| "mean_token_accuracy": 0.6292843967676163, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.034334763948497854, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.977107974055704e-05, | |
| "loss": 1.3368, | |
| "mean_token_accuracy": 0.6363929770886898, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.036242250834525515, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.9758361948365766e-05, | |
| "loss": 1.3156, | |
| "mean_token_accuracy": 0.6389718689024448, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.03814973772055317, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.974564415617449e-05, | |
| "loss": 1.3213, | |
| "mean_token_accuracy": 0.6437985837459564, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04005722460658083, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.9732926363983213e-05, | |
| "loss": 1.3403, | |
| "mean_token_accuracy": 0.6304401338100434, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.04196471149260849, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.972020857179194e-05, | |
| "loss": 1.4318, | |
| "mean_token_accuracy": 0.6314706668257714, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.043872198378636144, | |
| "grad_norm": 5.625, | |
| "learning_rate": 1.970749077960066e-05, | |
| "loss": 1.3123, | |
| "mean_token_accuracy": 0.6482092589139938, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.045779685264663805, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.9694772987409387e-05, | |
| "loss": 1.2722, | |
| "mean_token_accuracy": 0.6475286811590195, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.047687172150691466, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.9682055195218112e-05, | |
| "loss": 1.3184, | |
| "mean_token_accuracy": 0.636443517357111, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.04959465903671912, | |
| "grad_norm": 4.75, | |
| "learning_rate": 1.9669337403026834e-05, | |
| "loss": 1.3604, | |
| "mean_token_accuracy": 0.6383991658687591, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.05150214592274678, | |
| "grad_norm": 6.3125, | |
| "learning_rate": 1.965661961083556e-05, | |
| "loss": 1.3624, | |
| "mean_token_accuracy": 0.6359823271632195, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.05340963280877444, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.9643901818644285e-05, | |
| "loss": 1.3622, | |
| "mean_token_accuracy": 0.6360629022121429, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.055317119694802096, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.963118402645301e-05, | |
| "loss": 1.3007, | |
| "mean_token_accuracy": 0.6486773908138275, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.05722460658082976, | |
| "grad_norm": 4.625, | |
| "learning_rate": 1.9618466234261733e-05, | |
| "loss": 1.259, | |
| "mean_token_accuracy": 0.6483664289116859, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05913209346685742, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 1.9605748442070458e-05, | |
| "loss": 1.2701, | |
| "mean_token_accuracy": 0.6497010916471482, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.06103958035288507, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.9593030649879184e-05, | |
| "loss": 1.2925, | |
| "mean_token_accuracy": 0.645444954931736, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06294706723891273, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.9580312857687906e-05, | |
| "loss": 1.3194, | |
| "mean_token_accuracy": 0.6443428501486779, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.06485455412494039, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.956759506549663e-05, | |
| "loss": 1.2786, | |
| "mean_token_accuracy": 0.6503037214279175, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06676204101096805, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.9554877273305353e-05, | |
| "loss": 1.3482, | |
| "mean_token_accuracy": 0.6470891699194908, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.06866952789699571, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 1.954215948111408e-05, | |
| "loss": 1.3022, | |
| "mean_token_accuracy": 0.6400970220565796, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.07057701478302336, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.9529441688922804e-05, | |
| "loss": 1.2821, | |
| "mean_token_accuracy": 0.6461471430957317, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.07248450166905103, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.951672389673153e-05, | |
| "loss": 1.2824, | |
| "mean_token_accuracy": 0.649085208773613, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07439198855507868, | |
| "grad_norm": 4.5, | |
| "learning_rate": 1.9504006104540255e-05, | |
| "loss": 1.2508, | |
| "mean_token_accuracy": 0.6536262959241868, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.07629947544110634, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.9491288312348978e-05, | |
| "loss": 1.3044, | |
| "mean_token_accuracy": 0.6513546489179134, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.078206962327134, | |
| "grad_norm": 5.125, | |
| "learning_rate": 1.9478570520157703e-05, | |
| "loss": 1.2265, | |
| "mean_token_accuracy": 0.6645126178860664, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.08011444921316166, | |
| "grad_norm": 5.875, | |
| "learning_rate": 1.9465852727966425e-05, | |
| "loss": 1.3156, | |
| "mean_token_accuracy": 0.6494258716702461, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.08202193609918931, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.945313493577515e-05, | |
| "loss": 1.1655, | |
| "mean_token_accuracy": 0.6783517330884934, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.08392942298521698, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 1.9440417143583876e-05, | |
| "loss": 1.2306, | |
| "mean_token_accuracy": 0.6659620314836502, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.08583690987124463, | |
| "grad_norm": 4.40625, | |
| "learning_rate": 1.9427699351392598e-05, | |
| "loss": 1.3798, | |
| "mean_token_accuracy": 0.6320724219083786, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.08774439675727229, | |
| "grad_norm": 4.75, | |
| "learning_rate": 1.9414981559201324e-05, | |
| "loss": 1.2437, | |
| "mean_token_accuracy": 0.6454930439591408, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.08965188364329996, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.940226376701005e-05, | |
| "loss": 1.2523, | |
| "mean_token_accuracy": 0.6506562553346157, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.09155937052932761, | |
| "grad_norm": 4.75, | |
| "learning_rate": 1.938954597481877e-05, | |
| "loss": 1.2268, | |
| "mean_token_accuracy": 0.6620514318346977, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.09346685741535526, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.9376828182627497e-05, | |
| "loss": 1.2215, | |
| "mean_token_accuracy": 0.6610720351338386, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.09537434430138293, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.9364110390436222e-05, | |
| "loss": 1.2494, | |
| "mean_token_accuracy": 0.653127409517765, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.09728183118741059, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 1.9351392598244948e-05, | |
| "loss": 1.3126, | |
| "mean_token_accuracy": 0.6540979892015457, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.09918931807343824, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.933867480605367e-05, | |
| "loss": 1.2498, | |
| "mean_token_accuracy": 0.6507880866527558, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.10109680495946591, | |
| "grad_norm": 5.8125, | |
| "learning_rate": 1.9325957013862396e-05, | |
| "loss": 1.3294, | |
| "mean_token_accuracy": 0.6403125211596489, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.10300429184549356, | |
| "grad_norm": 6.09375, | |
| "learning_rate": 1.9313239221671118e-05, | |
| "loss": 1.3099, | |
| "mean_token_accuracy": 0.6520273745059967, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.10491177873152122, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.9300521429479843e-05, | |
| "loss": 1.2857, | |
| "mean_token_accuracy": 0.6506179749965668, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.10681926561754888, | |
| "grad_norm": 5.71875, | |
| "learning_rate": 1.928780363728857e-05, | |
| "loss": 1.3496, | |
| "mean_token_accuracy": 0.6408744707703591, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.10872675250357654, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.927508584509729e-05, | |
| "loss": 1.2012, | |
| "mean_token_accuracy": 0.6639982044696808, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.11063423938960419, | |
| "grad_norm": 5.5, | |
| "learning_rate": 1.9262368052906016e-05, | |
| "loss": 1.2449, | |
| "mean_token_accuracy": 0.6594835132360458, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.11254172627563186, | |
| "grad_norm": 4.125, | |
| "learning_rate": 1.9249650260714742e-05, | |
| "loss": 1.1314, | |
| "mean_token_accuracy": 0.6807294517755509, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.11444921316165951, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.9236932468523467e-05, | |
| "loss": 1.2528, | |
| "mean_token_accuracy": 0.6543513402342797, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11635670004768717, | |
| "grad_norm": 4.5, | |
| "learning_rate": 1.9224214676332193e-05, | |
| "loss": 1.201, | |
| "mean_token_accuracy": 0.6674724757671356, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.11826418693371483, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 1.9211496884140915e-05, | |
| "loss": 1.2232, | |
| "mean_token_accuracy": 0.6661024749279022, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.12017167381974249, | |
| "grad_norm": 4.65625, | |
| "learning_rate": 1.919877909194964e-05, | |
| "loss": 1.2015, | |
| "mean_token_accuracy": 0.6703806266188621, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.12207916070577014, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 1.9186061299758362e-05, | |
| "loss": 1.265, | |
| "mean_token_accuracy": 0.6571035169064998, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.12398664759179781, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.9173343507567088e-05, | |
| "loss": 1.1817, | |
| "mean_token_accuracy": 0.6720203042030335, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.12589413447782546, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.916062571537581e-05, | |
| "loss": 1.3305, | |
| "mean_token_accuracy": 0.6445886738598346, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.12780162136385312, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.9147907923184536e-05, | |
| "loss": 1.2302, | |
| "mean_token_accuracy": 0.6632393077015877, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.12970910824988077, | |
| "grad_norm": 4.40625, | |
| "learning_rate": 1.913519013099326e-05, | |
| "loss": 1.2463, | |
| "mean_token_accuracy": 0.6618235319852829, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.13161659513590845, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.9122472338801987e-05, | |
| "loss": 1.1995, | |
| "mean_token_accuracy": 0.6734424993395806, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.1335240820219361, | |
| "grad_norm": 6.09375, | |
| "learning_rate": 1.9109754546610712e-05, | |
| "loss": 1.1695, | |
| "mean_token_accuracy": 0.6744470730423927, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.13543156890796376, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 1.9097036754419434e-05, | |
| "loss": 1.235, | |
| "mean_token_accuracy": 0.6613016352057457, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.13733905579399142, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.908431896222816e-05, | |
| "loss": 1.1908, | |
| "mean_token_accuracy": 0.6631178431212902, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.13924654268001907, | |
| "grad_norm": 6.03125, | |
| "learning_rate": 1.9071601170036885e-05, | |
| "loss": 1.2538, | |
| "mean_token_accuracy": 0.6583275809884072, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.14115402956604672, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.9058883377845607e-05, | |
| "loss": 1.1481, | |
| "mean_token_accuracy": 0.6743377096951008, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.1430615164520744, | |
| "grad_norm": 4.65625, | |
| "learning_rate": 1.9046165585654333e-05, | |
| "loss": 1.1758, | |
| "mean_token_accuracy": 0.6755423441529274, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.14496900333810206, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 1.9033447793463055e-05, | |
| "loss": 1.1526, | |
| "mean_token_accuracy": 0.6709615409374237, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.1468764902241297, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.902073000127178e-05, | |
| "loss": 1.1614, | |
| "mean_token_accuracy": 0.6803930580615998, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.14878397711015737, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.9008012209080503e-05, | |
| "loss": 1.1651, | |
| "mean_token_accuracy": 0.6757953256368637, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.15069146399618502, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.8995294416889228e-05, | |
| "loss": 1.2219, | |
| "mean_token_accuracy": 0.6725533396005631, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.15259895088221268, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 1.8982576624697954e-05, | |
| "loss": 1.2598, | |
| "mean_token_accuracy": 0.6562705941498279, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.15450643776824036, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.896985883250668e-05, | |
| "loss": 1.1586, | |
| "mean_token_accuracy": 0.6731373474001885, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.156413924654268, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.8957141040315405e-05, | |
| "loss": 1.2544, | |
| "mean_token_accuracy": 0.6664155155420304, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.15832141154029566, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 1.8944423248124127e-05, | |
| "loss": 1.2045, | |
| "mean_token_accuracy": 0.6721395581960679, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.16022889842632332, | |
| "grad_norm": 4.65625, | |
| "learning_rate": 1.8931705455932852e-05, | |
| "loss": 1.1623, | |
| "mean_token_accuracy": 0.6825975701212883, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.16213638531235097, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.8918987663741578e-05, | |
| "loss": 1.2345, | |
| "mean_token_accuracy": 0.655138723552227, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.16404387219837863, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.89062698715503e-05, | |
| "loss": 1.1583, | |
| "mean_token_accuracy": 0.6771410465240478, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.1659513590844063, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 1.8893552079359025e-05, | |
| "loss": 1.2226, | |
| "mean_token_accuracy": 0.6566869288682937, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.16785884597043396, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.8880834287167747e-05, | |
| "loss": 1.2531, | |
| "mean_token_accuracy": 0.6537335075438022, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.16976633285646162, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 1.8868116494976473e-05, | |
| "loss": 1.1736, | |
| "mean_token_accuracy": 0.6741863384842872, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.17167381974248927, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.88553987027852e-05, | |
| "loss": 1.1912, | |
| "mean_token_accuracy": 0.6718283355236053, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.17358130662851692, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.8842680910593924e-05, | |
| "loss": 1.2016, | |
| "mean_token_accuracy": 0.670920492708683, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.17548879351454458, | |
| "grad_norm": 5.375, | |
| "learning_rate": 1.882996311840265e-05, | |
| "loss": 1.1818, | |
| "mean_token_accuracy": 0.6705762408673763, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.17739628040057226, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 1.881724532621137e-05, | |
| "loss": 1.3159, | |
| "mean_token_accuracy": 0.6546284504234791, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.1793037672865999, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.8804527534020097e-05, | |
| "loss": 1.2004, | |
| "mean_token_accuracy": 0.6597321718931198, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.18121125417262757, | |
| "grad_norm": 6.9375, | |
| "learning_rate": 1.879180974182882e-05, | |
| "loss": 1.1672, | |
| "mean_token_accuracy": 0.6835288152098655, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.18311874105865522, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.8779091949637545e-05, | |
| "loss": 1.2113, | |
| "mean_token_accuracy": 0.6654989182949066, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.18502622794468288, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 1.876637415744627e-05, | |
| "loss": 1.076, | |
| "mean_token_accuracy": 0.6919501051306725, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.18693371483071053, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.8753656365254992e-05, | |
| "loss": 1.1946, | |
| "mean_token_accuracy": 0.671660166978836, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.1888412017167382, | |
| "grad_norm": 5.875, | |
| "learning_rate": 1.8740938573063718e-05, | |
| "loss": 1.2334, | |
| "mean_token_accuracy": 0.6634502306580543, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.19074868860276586, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.872822078087244e-05, | |
| "loss": 1.1412, | |
| "mean_token_accuracy": 0.6843819186091423, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.19265617548879352, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.8715502988681165e-05, | |
| "loss": 1.1017, | |
| "mean_token_accuracy": 0.6859075799584389, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.19456366237482117, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.870278519648989e-05, | |
| "loss": 1.099, | |
| "mean_token_accuracy": 0.6794175133109093, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.19647114926084883, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.8690067404298616e-05, | |
| "loss": 1.162, | |
| "mean_token_accuracy": 0.6769187614321709, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.19837863614687648, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 1.8677349612107342e-05, | |
| "loss": 1.1241, | |
| "mean_token_accuracy": 0.6816845044493676, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.20028612303290416, | |
| "grad_norm": 7.09375, | |
| "learning_rate": 1.8664631819916064e-05, | |
| "loss": 1.1331, | |
| "mean_token_accuracy": 0.6768893599510193, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.20219360991893182, | |
| "grad_norm": 4.25, | |
| "learning_rate": 1.865191402772479e-05, | |
| "loss": 1.2657, | |
| "mean_token_accuracy": 0.6479664385318756, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.20410109680495947, | |
| "grad_norm": 4.5, | |
| "learning_rate": 1.863919623553351e-05, | |
| "loss": 1.2343, | |
| "mean_token_accuracy": 0.6734806634485722, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.20600858369098712, | |
| "grad_norm": 12.3125, | |
| "learning_rate": 1.8626478443342237e-05, | |
| "loss": 1.1263, | |
| "mean_token_accuracy": 0.6808793410658837, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.20791607057701478, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 1.8613760651150963e-05, | |
| "loss": 1.0617, | |
| "mean_token_accuracy": 0.6977316424250603, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.20982355746304243, | |
| "grad_norm": 5.96875, | |
| "learning_rate": 1.8601042858959685e-05, | |
| "loss": 1.1229, | |
| "mean_token_accuracy": 0.6831489652395248, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.2117310443490701, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.858832506676841e-05, | |
| "loss": 1.1216, | |
| "mean_token_accuracy": 0.6838791735470295, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.21363853123509777, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.8575607274577136e-05, | |
| "loss": 1.2059, | |
| "mean_token_accuracy": 0.6669023260474205, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.21554601812112542, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.856288948238586e-05, | |
| "loss": 1.1515, | |
| "mean_token_accuracy": 0.6748893111944199, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.21745350500715308, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 1.8550171690194583e-05, | |
| "loss": 1.063, | |
| "mean_token_accuracy": 0.7043292924761773, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.21936099189318073, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.853745389800331e-05, | |
| "loss": 1.1071, | |
| "mean_token_accuracy": 0.6816813468933105, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.22126847877920838, | |
| "grad_norm": 7.25, | |
| "learning_rate": 1.8524736105812034e-05, | |
| "loss": 1.1493, | |
| "mean_token_accuracy": 0.6842595711350441, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.22317596566523606, | |
| "grad_norm": 6.3125, | |
| "learning_rate": 1.8512018313620756e-05, | |
| "loss": 1.2036, | |
| "mean_token_accuracy": 0.6606533020734787, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.22508345255126372, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 1.8499300521429482e-05, | |
| "loss": 1.0329, | |
| "mean_token_accuracy": 0.7044132232666016, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.22699093943729137, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 1.8486582729238204e-05, | |
| "loss": 1.183, | |
| "mean_token_accuracy": 0.6742020189762116, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.22889842632331903, | |
| "grad_norm": 5.375, | |
| "learning_rate": 1.847386493704693e-05, | |
| "loss": 1.1212, | |
| "mean_token_accuracy": 0.6900173485279083, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.23080591320934668, | |
| "grad_norm": 5.5, | |
| "learning_rate": 1.8461147144855655e-05, | |
| "loss": 1.1654, | |
| "mean_token_accuracy": 0.6756381630897522, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.23271340009537433, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.8448429352664377e-05, | |
| "loss": 1.1592, | |
| "mean_token_accuracy": 0.6697646602988243, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.23462088698140202, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.8435711560473103e-05, | |
| "loss": 1.0309, | |
| "mean_token_accuracy": 0.6977804109454155, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.23652837386742967, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 1.8422993768281828e-05, | |
| "loss": 1.1705, | |
| "mean_token_accuracy": 0.6789061531424523, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.23843586075345732, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.8410275976090554e-05, | |
| "loss": 1.1715, | |
| "mean_token_accuracy": 0.6736443802714348, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.24034334763948498, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.8397558183899276e-05, | |
| "loss": 1.1535, | |
| "mean_token_accuracy": 0.6837850168347359, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.24225083452551263, | |
| "grad_norm": 5.625, | |
| "learning_rate": 1.8384840391708e-05, | |
| "loss": 1.1403, | |
| "mean_token_accuracy": 0.6860886000096797, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.24415832141154029, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 1.8372122599516727e-05, | |
| "loss": 1.1777, | |
| "mean_token_accuracy": 0.6730990558862686, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.24606580829756797, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.835940480732545e-05, | |
| "loss": 1.2174, | |
| "mean_token_accuracy": 0.6607669338583946, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.24797329518359562, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.8346687015134174e-05, | |
| "loss": 1.1306, | |
| "mean_token_accuracy": 0.6789732642471791, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.24988078206962328, | |
| "grad_norm": 4.5, | |
| "learning_rate": 1.8333969222942896e-05, | |
| "loss": 1.0958, | |
| "mean_token_accuracy": 0.6940956100821495, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.25178826895565093, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.8321251430751622e-05, | |
| "loss": 1.1623, | |
| "mean_token_accuracy": 0.6806924149394036, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.2536957558416786, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 1.8308533638560347e-05, | |
| "loss": 1.1438, | |
| "mean_token_accuracy": 0.6787467435002327, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.25560324272770624, | |
| "grad_norm": 4.65625, | |
| "learning_rate": 1.8295815846369073e-05, | |
| "loss": 1.2902, | |
| "mean_token_accuracy": 0.655436672270298, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.2575107296137339, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.82830980541778e-05, | |
| "loss": 1.1499, | |
| "mean_token_accuracy": 0.6697306737303734, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.25941821649976154, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 1.827038026198652e-05, | |
| "loss": 1.1432, | |
| "mean_token_accuracy": 0.6788436755537987, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.2613257033857892, | |
| "grad_norm": 6.40625, | |
| "learning_rate": 1.8257662469795246e-05, | |
| "loss": 1.1457, | |
| "mean_token_accuracy": 0.6794642567634582, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.2632331902718169, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.8244944677603968e-05, | |
| "loss": 1.1842, | |
| "mean_token_accuracy": 0.6739339649677276, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.26514067715784456, | |
| "grad_norm": 5.375, | |
| "learning_rate": 1.8232226885412694e-05, | |
| "loss": 1.1979, | |
| "mean_token_accuracy": 0.671060286462307, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.2670481640438722, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 1.821950909322142e-05, | |
| "loss": 1.1926, | |
| "mean_token_accuracy": 0.68006531894207, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.26895565092989987, | |
| "grad_norm": 4.5, | |
| "learning_rate": 1.820679130103014e-05, | |
| "loss": 1.1425, | |
| "mean_token_accuracy": 0.686011116206646, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.2708631378159275, | |
| "grad_norm": 4.125, | |
| "learning_rate": 1.8194073508838867e-05, | |
| "loss": 1.1241, | |
| "mean_token_accuracy": 0.6813527546823025, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.2727706247019552, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.8181355716647592e-05, | |
| "loss": 1.0763, | |
| "mean_token_accuracy": 0.6978838533163071, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.27467811158798283, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.8168637924456314e-05, | |
| "loss": 1.1214, | |
| "mean_token_accuracy": 0.6879947543144226, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.2765855984740105, | |
| "grad_norm": 4.65625, | |
| "learning_rate": 1.815592013226504e-05, | |
| "loss": 1.145, | |
| "mean_token_accuracy": 0.6740229934453964, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.27849308536003814, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.8143202340073765e-05, | |
| "loss": 1.0915, | |
| "mean_token_accuracy": 0.6966636836528778, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.2804005722460658, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 1.813048454788249e-05, | |
| "loss": 1.1534, | |
| "mean_token_accuracy": 0.6881409972906113, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.28230805913209345, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.8117766755691213e-05, | |
| "loss": 1.1306, | |
| "mean_token_accuracy": 0.6856201700866222, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.2842155460181211, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 1.810504896349994e-05, | |
| "loss": 1.1514, | |
| "mean_token_accuracy": 0.6833734557032585, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.2861230329041488, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 1.809233117130866e-05, | |
| "loss": 1.1379, | |
| "mean_token_accuracy": 0.6824650421738625, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.28803051979017646, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.8079613379117386e-05, | |
| "loss": 1.1685, | |
| "mean_token_accuracy": 0.6773202955722809, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.2899380066762041, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 1.806689558692611e-05, | |
| "loss": 1.1683, | |
| "mean_token_accuracy": 0.6770651459693908, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.2918454935622318, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.8054177794734834e-05, | |
| "loss": 1.0853, | |
| "mean_token_accuracy": 0.6914259925484657, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.2937529804482594, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.804146000254356e-05, | |
| "loss": 1.1336, | |
| "mean_token_accuracy": 0.6820079162716866, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.2956604673342871, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 1.8028742210352285e-05, | |
| "loss": 1.1233, | |
| "mean_token_accuracy": 0.6821878552436829, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.29756795422031473, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.801602441816101e-05, | |
| "loss": 1.1204, | |
| "mean_token_accuracy": 0.692288200557232, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.2994754411063424, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.8003306625969736e-05, | |
| "loss": 1.2294, | |
| "mean_token_accuracy": 0.673324004560709, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.30138292799237004, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.7990588833778458e-05, | |
| "loss": 1.2059, | |
| "mean_token_accuracy": 0.6697646111249924, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.3032904148783977, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.7977871041587183e-05, | |
| "loss": 1.1745, | |
| "mean_token_accuracy": 0.6823094062507152, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.30519790176442535, | |
| "grad_norm": 4.625, | |
| "learning_rate": 1.7965153249395905e-05, | |
| "loss": 1.1519, | |
| "mean_token_accuracy": 0.6778446674346924, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.307105388650453, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.795243545720463e-05, | |
| "loss": 1.0918, | |
| "mean_token_accuracy": 0.6978467896580696, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.3090128755364807, | |
| "grad_norm": 3.921875, | |
| "learning_rate": 1.7939717665013353e-05, | |
| "loss": 1.1631, | |
| "mean_token_accuracy": 0.6788024313747882, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.31092036242250837, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.792699987282208e-05, | |
| "loss": 1.1259, | |
| "mean_token_accuracy": 0.6834620237350464, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.312827849308536, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.7914282080630804e-05, | |
| "loss": 1.0979, | |
| "mean_token_accuracy": 0.6804828964173794, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.3147353361945637, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.790156428843953e-05, | |
| "loss": 1.204, | |
| "mean_token_accuracy": 0.6713850289583206, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.31664282308059133, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.788884649624825e-05, | |
| "loss": 1.14, | |
| "mean_token_accuracy": 0.6814699381589889, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.318550309966619, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 1.7876128704056977e-05, | |
| "loss": 1.1383, | |
| "mean_token_accuracy": 0.672491405904293, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.32045779685264664, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.7863410911865703e-05, | |
| "loss": 1.1993, | |
| "mean_token_accuracy": 0.662742418050766, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.3223652837386743, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.7850693119674428e-05, | |
| "loss": 1.0142, | |
| "mean_token_accuracy": 0.7142936125397682, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.32427277062470194, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.783797532748315e-05, | |
| "loss": 1.1083, | |
| "mean_token_accuracy": 0.6907312035560608, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.3261802575107296, | |
| "grad_norm": 4.40625, | |
| "learning_rate": 1.7825257535291876e-05, | |
| "loss": 1.0248, | |
| "mean_token_accuracy": 0.7127422258257866, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.32808774439675725, | |
| "grad_norm": 4.375, | |
| "learning_rate": 1.7812539743100598e-05, | |
| "loss": 1.1234, | |
| "mean_token_accuracy": 0.6854491457343102, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.3299952312827849, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.7799821950909323e-05, | |
| "loss": 1.1691, | |
| "mean_token_accuracy": 0.6794403240084648, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.3319027181688126, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 1.7787104158718045e-05, | |
| "loss": 1.1286, | |
| "mean_token_accuracy": 0.6781167238950729, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.33381020505484027, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.777438636652677e-05, | |
| "loss": 1.1314, | |
| "mean_token_accuracy": 0.6972567990422249, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.3357176919408679, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.7761668574335496e-05, | |
| "loss": 1.0309, | |
| "mean_token_accuracy": 0.7109489843249321, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.3376251788268956, | |
| "grad_norm": 5.53125, | |
| "learning_rate": 1.7748950782144222e-05, | |
| "loss": 1.122, | |
| "mean_token_accuracy": 0.6877056941390037, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.33953266571292323, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.7736232989952947e-05, | |
| "loss": 1.0609, | |
| "mean_token_accuracy": 0.7033521652221679, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.3414401525989509, | |
| "grad_norm": 4.125, | |
| "learning_rate": 1.772351519776167e-05, | |
| "loss": 1.0418, | |
| "mean_token_accuracy": 0.7021679773926734, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.34334763948497854, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 1.7710797405570395e-05, | |
| "loss": 1.1233, | |
| "mean_token_accuracy": 0.696443286538124, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3452551263710062, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.7698079613379117e-05, | |
| "loss": 1.043, | |
| "mean_token_accuracy": 0.7000239789485931, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.34716261325703385, | |
| "grad_norm": 4.75, | |
| "learning_rate": 1.7685361821187843e-05, | |
| "loss": 1.0404, | |
| "mean_token_accuracy": 0.7076486960053444, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.3490701001430615, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.7672644028996568e-05, | |
| "loss": 1.2165, | |
| "mean_token_accuracy": 0.6694424465298653, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.35097758702908916, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.765992623680529e-05, | |
| "loss": 1.1061, | |
| "mean_token_accuracy": 0.689212466776371, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.3528850739151168, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.7647208444614016e-05, | |
| "loss": 1.1573, | |
| "mean_token_accuracy": 0.6761819615960121, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.3547925608011445, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.763449065242274e-05, | |
| "loss": 1.0511, | |
| "mean_token_accuracy": 0.7017502933740616, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.3567000476871722, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.7621772860231467e-05, | |
| "loss": 1.176, | |
| "mean_token_accuracy": 0.6732675984501839, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.3586075345731998, | |
| "grad_norm": 4.1875, | |
| "learning_rate": 1.760905506804019e-05, | |
| "loss": 1.0912, | |
| "mean_token_accuracy": 0.6839179575443268, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.3605150214592275, | |
| "grad_norm": 5.53125, | |
| "learning_rate": 1.7596337275848914e-05, | |
| "loss": 1.1048, | |
| "mean_token_accuracy": 0.6849195197224617, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.36242250834525513, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.758361948365764e-05, | |
| "loss": 1.0162, | |
| "mean_token_accuracy": 0.6860754758119583, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.3643299952312828, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.7570901691466362e-05, | |
| "loss": 1.0933, | |
| "mean_token_accuracy": 0.6905333071947097, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.36623748211731044, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.7558183899275088e-05, | |
| "loss": 1.0952, | |
| "mean_token_accuracy": 0.6910875916481019, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.3681449690033381, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.754546610708381e-05, | |
| "loss": 1.2019, | |
| "mean_token_accuracy": 0.6728987120091915, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.37005245588936575, | |
| "grad_norm": 3.890625, | |
| "learning_rate": 1.7532748314892535e-05, | |
| "loss": 1.0999, | |
| "mean_token_accuracy": 0.6894315019249916, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.3719599427753934, | |
| "grad_norm": 4.28125, | |
| "learning_rate": 1.752003052270126e-05, | |
| "loss": 1.0943, | |
| "mean_token_accuracy": 0.6812393218278885, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.37386742966142106, | |
| "grad_norm": 4.5, | |
| "learning_rate": 1.7507312730509983e-05, | |
| "loss": 1.1383, | |
| "mean_token_accuracy": 0.6867758512496949, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.3757749165474487, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.7494594938318708e-05, | |
| "loss": 1.0795, | |
| "mean_token_accuracy": 0.6977563664317131, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.3776824034334764, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 1.7481877146127434e-05, | |
| "loss": 1.0531, | |
| "mean_token_accuracy": 0.7000179141759872, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.3795898903195041, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 1.746915935393616e-05, | |
| "loss": 1.1515, | |
| "mean_token_accuracy": 0.679880291223526, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.38149737720553173, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.7456441561744885e-05, | |
| "loss": 1.139, | |
| "mean_token_accuracy": 0.6736231818795204, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3834048640915594, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.7443723769553607e-05, | |
| "loss": 1.161, | |
| "mean_token_accuracy": 0.6775983899831772, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.38531235097758704, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.7431005977362332e-05, | |
| "loss": 1.1337, | |
| "mean_token_accuracy": 0.6791507929563523, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.3872198378636147, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.7418288185171054e-05, | |
| "loss": 1.0665, | |
| "mean_token_accuracy": 0.6990373253822326, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.38912732474964234, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.740557039297978e-05, | |
| "loss": 0.9875, | |
| "mean_token_accuracy": 0.7201899453997612, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.39103481163567, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.7392852600788502e-05, | |
| "loss": 1.1103, | |
| "mean_token_accuracy": 0.6919103190302849, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.39294229852169765, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 1.7380134808597228e-05, | |
| "loss": 1.1621, | |
| "mean_token_accuracy": 0.6763632833957672, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.3948497854077253, | |
| "grad_norm": 5.375, | |
| "learning_rate": 1.7367417016405953e-05, | |
| "loss": 1.0891, | |
| "mean_token_accuracy": 0.6873229309916496, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.39675727229375296, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.735469922421468e-05, | |
| "loss": 1.0736, | |
| "mean_token_accuracy": 0.6943288549780846, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.3986647591797806, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.7341981432023404e-05, | |
| "loss": 1.1739, | |
| "mean_token_accuracy": 0.6772709146142006, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.4005722460658083, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.7329263639832126e-05, | |
| "loss": 1.132, | |
| "mean_token_accuracy": 0.6861761540174485, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.402479732951836, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.731654584764085e-05, | |
| "loss": 1.0849, | |
| "mean_token_accuracy": 0.6876397714018821, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.40438721983786363, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 1.7303828055449577e-05, | |
| "loss": 1.1119, | |
| "mean_token_accuracy": 0.6828581809997558, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.4062947067238913, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.72911102632583e-05, | |
| "loss": 1.1542, | |
| "mean_token_accuracy": 0.6845688432455063, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.40820219360991894, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.7278392471067025e-05, | |
| "loss": 1.245, | |
| "mean_token_accuracy": 0.6623896270990371, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.4101096804959466, | |
| "grad_norm": 4.40625, | |
| "learning_rate": 1.7265674678875747e-05, | |
| "loss": 0.9855, | |
| "mean_token_accuracy": 0.7169230833649636, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.41201716738197425, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 1.7252956886684472e-05, | |
| "loss": 1.0003, | |
| "mean_token_accuracy": 0.7067764922976494, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.4139246542680019, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.7240239094493198e-05, | |
| "loss": 1.0566, | |
| "mean_token_accuracy": 0.7076253116130828, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.41583214115402956, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.722752130230192e-05, | |
| "loss": 1.0692, | |
| "mean_token_accuracy": 0.6991090714931488, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.4177396280400572, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.7214803510110646e-05, | |
| "loss": 1.1702, | |
| "mean_token_accuracy": 0.6843620404601097, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.41964711492608486, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.720208571791937e-05, | |
| "loss": 1.1131, | |
| "mean_token_accuracy": 0.6780217066407204, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.4215546018121125, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.7189367925728097e-05, | |
| "loss": 1.1733, | |
| "mean_token_accuracy": 0.6738237209618092, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.4234620886981402, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 1.717665013353682e-05, | |
| "loss": 1.0971, | |
| "mean_token_accuracy": 0.6967151150107384, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.4253695755841679, | |
| "grad_norm": 6.125, | |
| "learning_rate": 1.7163932341345544e-05, | |
| "loss": 1.0593, | |
| "mean_token_accuracy": 0.6975896939635277, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.42727706247019553, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.715121454915427e-05, | |
| "loss": 1.045, | |
| "mean_token_accuracy": 0.6995080903172493, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.4291845493562232, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.7138496756962992e-05, | |
| "loss": 1.1514, | |
| "mean_token_accuracy": 0.6870008051395416, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.43109203624225084, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.7125778964771717e-05, | |
| "loss": 1.147, | |
| "mean_token_accuracy": 0.6756279736757278, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.4329995231282785, | |
| "grad_norm": 3.953125, | |
| "learning_rate": 1.711306117258044e-05, | |
| "loss": 1.0626, | |
| "mean_token_accuracy": 0.6975025564432145, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.43490701001430615, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.7100343380389165e-05, | |
| "loss": 1.0843, | |
| "mean_token_accuracy": 0.6906091332435608, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.4368144969003338, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.708762558819789e-05, | |
| "loss": 1.1134, | |
| "mean_token_accuracy": 0.6875185921788216, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.43872198378636146, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 1.7074907796006616e-05, | |
| "loss": 1.1802, | |
| "mean_token_accuracy": 0.6715085253119468, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.4406294706723891, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 1.706219000381534e-05, | |
| "loss": 1.0848, | |
| "mean_token_accuracy": 0.6938497066497803, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.44253695755841677, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 1.7049472211624063e-05, | |
| "loss": 0.99, | |
| "mean_token_accuracy": 0.7224840387701988, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.703675441943279e-05, | |
| "loss": 1.0878, | |
| "mean_token_accuracy": 0.6980762526392936, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.44635193133047213, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.702403662724151e-05, | |
| "loss": 1.0144, | |
| "mean_token_accuracy": 0.7007738411426544, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.4482594182164998, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.7011318835050237e-05, | |
| "loss": 1.0875, | |
| "mean_token_accuracy": 0.6976178154349327, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.45016690510252744, | |
| "grad_norm": 4.25, | |
| "learning_rate": 1.6998601042858962e-05, | |
| "loss": 1.1086, | |
| "mean_token_accuracy": 0.6936508253216743, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.4520743919885551, | |
| "grad_norm": 4.625, | |
| "learning_rate": 1.6985883250667684e-05, | |
| "loss": 1.0357, | |
| "mean_token_accuracy": 0.7059789746999741, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.45398187887458274, | |
| "grad_norm": 5.84375, | |
| "learning_rate": 1.697316545847641e-05, | |
| "loss": 1.1516, | |
| "mean_token_accuracy": 0.6797626093029976, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.4558893657606104, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.6960447666285135e-05, | |
| "loss": 1.0598, | |
| "mean_token_accuracy": 0.6971547856926918, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.45779685264663805, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 1.6947729874093857e-05, | |
| "loss": 0.9843, | |
| "mean_token_accuracy": 0.7089567899703979, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.4597043395326657, | |
| "grad_norm": 5.6875, | |
| "learning_rate": 1.6935012081902583e-05, | |
| "loss": 1.1058, | |
| "mean_token_accuracy": 0.6865063227713109, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.46161182641869336, | |
| "grad_norm": 4.65625, | |
| "learning_rate": 1.6922294289711308e-05, | |
| "loss": 1.1277, | |
| "mean_token_accuracy": 0.6827705770730972, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.463519313304721, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.6909576497520034e-05, | |
| "loss": 1.1664, | |
| "mean_token_accuracy": 0.6819883540272713, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.46542680019074867, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 1.6896858705328756e-05, | |
| "loss": 1.0562, | |
| "mean_token_accuracy": 0.6979849010705947, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.4673342870767763, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.688414091313748e-05, | |
| "loss": 1.1879, | |
| "mean_token_accuracy": 0.6789781466126442, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.46924177396280403, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.6871423120946204e-05, | |
| "loss": 1.1305, | |
| "mean_token_accuracy": 0.6878492012619972, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.4711492608488317, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 1.685870532875493e-05, | |
| "loss": 1.1696, | |
| "mean_token_accuracy": 0.6815823867917061, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.47305674773485934, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 1.6845987536563655e-05, | |
| "loss": 0.9887, | |
| "mean_token_accuracy": 0.7134695425629616, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.474964234620887, | |
| "grad_norm": 4.625, | |
| "learning_rate": 1.6833269744372377e-05, | |
| "loss": 1.0254, | |
| "mean_token_accuracy": 0.7122278586030006, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.47687172150691465, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.6820551952181102e-05, | |
| "loss": 1.123, | |
| "mean_token_accuracy": 0.6886913120746613, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.4787792083929423, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.6807834159989828e-05, | |
| "loss": 1.1054, | |
| "mean_token_accuracy": 0.6899633683264256, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.48068669527896996, | |
| "grad_norm": 4.5, | |
| "learning_rate": 1.6795116367798553e-05, | |
| "loss": 0.9764, | |
| "mean_token_accuracy": 0.7191405698657036, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.4825941821649976, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.6782398575607275e-05, | |
| "loss": 1.0562, | |
| "mean_token_accuracy": 0.7035323694348335, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.48450166905102526, | |
| "grad_norm": 4.25, | |
| "learning_rate": 1.6769680783416e-05, | |
| "loss": 1.0389, | |
| "mean_token_accuracy": 0.708684840798378, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.4864091559370529, | |
| "grad_norm": 4.375, | |
| "learning_rate": 1.6756962991224726e-05, | |
| "loss": 1.0037, | |
| "mean_token_accuracy": 0.7036843597888947, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.48831664282308057, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.674424519903345e-05, | |
| "loss": 0.9991, | |
| "mean_token_accuracy": 0.708541002869606, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.4902241297091082, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.6731527406842174e-05, | |
| "loss": 1.0307, | |
| "mean_token_accuracy": 0.7065932080149651, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.49213161659513593, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.6718809614650896e-05, | |
| "loss": 1.1893, | |
| "mean_token_accuracy": 0.6674706935882568, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.4940391034811636, | |
| "grad_norm": 4.75, | |
| "learning_rate": 1.670609182245962e-05, | |
| "loss": 1.0691, | |
| "mean_token_accuracy": 0.6954927012324333, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.49594659036719124, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.6693374030268347e-05, | |
| "loss": 1.1, | |
| "mean_token_accuracy": 0.687789686024189, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.4978540772532189, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 1.6680656238077072e-05, | |
| "loss": 0.995, | |
| "mean_token_accuracy": 0.7104071035981179, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.49976156413924655, | |
| "grad_norm": 8.9375, | |
| "learning_rate": 1.6667938445885795e-05, | |
| "loss": 1.1605, | |
| "mean_token_accuracy": 0.6653927579522133, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.5016690510252741, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 1.665522065369452e-05, | |
| "loss": 1.0855, | |
| "mean_token_accuracy": 0.6951776430010795, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.5035765379113019, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.6642502861503246e-05, | |
| "loss": 1.0628, | |
| "mean_token_accuracy": 0.6940785989165306, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.5054840247973296, | |
| "grad_norm": 5.34375, | |
| "learning_rate": 1.6629785069311968e-05, | |
| "loss": 0.988, | |
| "mean_token_accuracy": 0.7169103771448135, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.5073915116833572, | |
| "grad_norm": 6.0, | |
| "learning_rate": 1.6617067277120693e-05, | |
| "loss": 1.1389, | |
| "mean_token_accuracy": 0.6772550821304322, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.5092989985693849, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.660434948492942e-05, | |
| "loss": 1.0482, | |
| "mean_token_accuracy": 0.7066885620355606, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.5112064854554125, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.659163169273814e-05, | |
| "loss": 1.0581, | |
| "mean_token_accuracy": 0.6999363213777542, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.5131139723414402, | |
| "grad_norm": 4.625, | |
| "learning_rate": 1.6578913900546866e-05, | |
| "loss": 1.0167, | |
| "mean_token_accuracy": 0.7108445912599564, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.5150214592274678, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 1.656619610835559e-05, | |
| "loss": 1.0204, | |
| "mean_token_accuracy": 0.7141309767961502, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.5169289461134955, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.6553478316164314e-05, | |
| "loss": 1.0762, | |
| "mean_token_accuracy": 0.681866991519928, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.5188364329995231, | |
| "grad_norm": 4.75, | |
| "learning_rate": 1.654076052397304e-05, | |
| "loss": 1.11, | |
| "mean_token_accuracy": 0.6910865843296051, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.5207439198855508, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.6528042731781765e-05, | |
| "loss": 1.1043, | |
| "mean_token_accuracy": 0.6882475554943085, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.5226514067715784, | |
| "grad_norm": 4.25, | |
| "learning_rate": 1.651532493959049e-05, | |
| "loss": 1.0554, | |
| "mean_token_accuracy": 0.7098303481936454, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.5245588936576061, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.6502607147399213e-05, | |
| "loss": 1.0832, | |
| "mean_token_accuracy": 0.7008169665932655, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.5264663805436338, | |
| "grad_norm": 4.75, | |
| "learning_rate": 1.6489889355207938e-05, | |
| "loss": 1.0496, | |
| "mean_token_accuracy": 0.7001980841159821, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.5283738674296614, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.647717156301666e-05, | |
| "loss": 1.058, | |
| "mean_token_accuracy": 0.6955149456858635, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.5302813543156891, | |
| "grad_norm": 4.5, | |
| "learning_rate": 1.6464453770825386e-05, | |
| "loss": 1.0637, | |
| "mean_token_accuracy": 0.6973527297377586, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.5321888412017167, | |
| "grad_norm": 4.65625, | |
| "learning_rate": 1.645173597863411e-05, | |
| "loss": 1.0224, | |
| "mean_token_accuracy": 0.6985811904072762, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.5340963280877444, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.6439018186442833e-05, | |
| "loss": 0.9889, | |
| "mean_token_accuracy": 0.7180039718747139, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.536003814973772, | |
| "grad_norm": 5.65625, | |
| "learning_rate": 1.642630039425156e-05, | |
| "loss": 1.1035, | |
| "mean_token_accuracy": 0.6911762669682503, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.5379113018597997, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.6413582602060284e-05, | |
| "loss": 1.121, | |
| "mean_token_accuracy": 0.6914720147848129, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.5398187887458273, | |
| "grad_norm": 4.6875, | |
| "learning_rate": 1.640086480986901e-05, | |
| "loss": 1.0923, | |
| "mean_token_accuracy": 0.7057502642273903, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.541726275631855, | |
| "grad_norm": 4.03125, | |
| "learning_rate": 1.6388147017677732e-05, | |
| "loss": 1.0645, | |
| "mean_token_accuracy": 0.6903545215725899, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.5436337625178826, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.6375429225486457e-05, | |
| "loss": 1.067, | |
| "mean_token_accuracy": 0.6956262946128845, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.5455412494039104, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.6362711433295183e-05, | |
| "loss": 1.051, | |
| "mean_token_accuracy": 0.7086583986878395, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.547448736289938, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.6349993641103905e-05, | |
| "loss": 1.083, | |
| "mean_token_accuracy": 0.6992680087685585, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.5493562231759657, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.633727584891263e-05, | |
| "loss": 1.048, | |
| "mean_token_accuracy": 0.7062048301100731, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.5512637100619934, | |
| "grad_norm": 4.375, | |
| "learning_rate": 1.6324558056721353e-05, | |
| "loss": 1.0279, | |
| "mean_token_accuracy": 0.6988534897565841, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.553171196948021, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 1.6311840264530078e-05, | |
| "loss": 1.1266, | |
| "mean_token_accuracy": 0.6839306525886059, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.5550786838340487, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.6299122472338804e-05, | |
| "loss": 1.0217, | |
| "mean_token_accuracy": 0.711203609406948, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.5569861707200763, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.6286404680147526e-05, | |
| "loss": 1.0203, | |
| "mean_token_accuracy": 0.7061103895306587, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.558893657606104, | |
| "grad_norm": 4.5, | |
| "learning_rate": 1.627368688795625e-05, | |
| "loss": 1.1219, | |
| "mean_token_accuracy": 0.6869349181652069, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.5608011444921316, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 1.6260969095764977e-05, | |
| "loss": 1.0224, | |
| "mean_token_accuracy": 0.7102344155311584, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.5627086313781593, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.6248251303573702e-05, | |
| "loss": 1.0301, | |
| "mean_token_accuracy": 0.7014199420809746, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.5646161182641869, | |
| "grad_norm": 4.84375, | |
| "learning_rate": 1.6235533511382428e-05, | |
| "loss": 1.0919, | |
| "mean_token_accuracy": 0.6958119504153728, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.5665236051502146, | |
| "grad_norm": 3.796875, | |
| "learning_rate": 1.622281571919115e-05, | |
| "loss": 1.0172, | |
| "mean_token_accuracy": 0.7171666666865348, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.5684310920362422, | |
| "grad_norm": 4.9375, | |
| "learning_rate": 1.6210097926999875e-05, | |
| "loss": 1.0293, | |
| "mean_token_accuracy": 0.7110596433281898, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.5703385789222699, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.6197380134808597e-05, | |
| "loss": 1.0437, | |
| "mean_token_accuracy": 0.7055989898741245, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.5722460658082976, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.6184662342617323e-05, | |
| "loss": 1.1109, | |
| "mean_token_accuracy": 0.6983527675271034, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5741535526943252, | |
| "grad_norm": 5.21875, | |
| "learning_rate": 1.6171944550426045e-05, | |
| "loss": 1.0585, | |
| "mean_token_accuracy": 0.7039476573467255, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.5760610395803529, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.615922675823477e-05, | |
| "loss": 1.0795, | |
| "mean_token_accuracy": 0.6893104076385498, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.5779685264663805, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.6146508966043496e-05, | |
| "loss": 0.9975, | |
| "mean_token_accuracy": 0.7137760400772095, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.5798760133524082, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.613379117385222e-05, | |
| "loss": 1.0283, | |
| "mean_token_accuracy": 0.7071486204862595, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.5817835002384358, | |
| "grad_norm": 4.125, | |
| "learning_rate": 1.6121073381660947e-05, | |
| "loss": 0.9634, | |
| "mean_token_accuracy": 0.7267276033759117, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.5836909871244635, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 1.610835558946967e-05, | |
| "loss": 1.141, | |
| "mean_token_accuracy": 0.6760995179414749, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.5855984740104911, | |
| "grad_norm": 4.3125, | |
| "learning_rate": 1.6095637797278395e-05, | |
| "loss": 1.0584, | |
| "mean_token_accuracy": 0.7001825541257858, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.5875059608965189, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.608292000508712e-05, | |
| "loss": 0.9554, | |
| "mean_token_accuracy": 0.7191137507557869, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.5894134477825465, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.6070202212895842e-05, | |
| "loss": 1.0338, | |
| "mean_token_accuracy": 0.6991492182016372, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.5913209346685742, | |
| "grad_norm": 4.375, | |
| "learning_rate": 1.6057484420704568e-05, | |
| "loss": 1.1116, | |
| "mean_token_accuracy": 0.6837974414229393, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.5932284215546018, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.604476662851329e-05, | |
| "loss": 1.1166, | |
| "mean_token_accuracy": 0.6914651602506637, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.5951359084406295, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.6032048836322015e-05, | |
| "loss": 1.092, | |
| "mean_token_accuracy": 0.6894845418632031, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.5970433953266572, | |
| "grad_norm": 3.96875, | |
| "learning_rate": 1.601933104413074e-05, | |
| "loss": 1.0382, | |
| "mean_token_accuracy": 0.7044162392616272, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.5989508822126848, | |
| "grad_norm": 5.28125, | |
| "learning_rate": 1.6006613251939463e-05, | |
| "loss": 1.1431, | |
| "mean_token_accuracy": 0.6869931921362877, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.6008583690987125, | |
| "grad_norm": 5.03125, | |
| "learning_rate": 1.599389545974819e-05, | |
| "loss": 0.9842, | |
| "mean_token_accuracy": 0.7128385215997696, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.6027658559847401, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 1.5981177667556914e-05, | |
| "loss": 0.9261, | |
| "mean_token_accuracy": 0.7247092142701149, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.6046733428707678, | |
| "grad_norm": 6.1875, | |
| "learning_rate": 1.596845987536564e-05, | |
| "loss": 1.1425, | |
| "mean_token_accuracy": 0.690905112028122, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.6065808297567954, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 1.595574208317436e-05, | |
| "loss": 1.0104, | |
| "mean_token_accuracy": 0.7160186618566513, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.6084883166428231, | |
| "grad_norm": 4.25, | |
| "learning_rate": 1.5943024290983087e-05, | |
| "loss": 1.0177, | |
| "mean_token_accuracy": 0.7115990072488785, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.6103958035288507, | |
| "grad_norm": 4.125, | |
| "learning_rate": 1.5930306498791813e-05, | |
| "loss": 0.9649, | |
| "mean_token_accuracy": 0.7167477622628212, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6123032904148784, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.5917588706600535e-05, | |
| "loss": 1.0788, | |
| "mean_token_accuracy": 0.6938311874866485, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.614210777300906, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.590487091440926e-05, | |
| "loss": 1.0125, | |
| "mean_token_accuracy": 0.7016476511955261, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.6161182641869337, | |
| "grad_norm": 4.875, | |
| "learning_rate": 1.5892153122217982e-05, | |
| "loss": 1.0339, | |
| "mean_token_accuracy": 0.7032722011208534, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.6180257510729614, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.5879435330026708e-05, | |
| "loss": 1.0328, | |
| "mean_token_accuracy": 0.7095901571214199, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.619933237958989, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.5866717537835433e-05, | |
| "loss": 1.0373, | |
| "mean_token_accuracy": 0.7035743817687035, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.6218407248450167, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.585399974564416e-05, | |
| "loss": 0.9541, | |
| "mean_token_accuracy": 0.7259443908929825, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.6237482117310443, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.5841281953452884e-05, | |
| "loss": 1.163, | |
| "mean_token_accuracy": 0.6807891383767128, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.625655698617072, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 1.5828564161261606e-05, | |
| "loss": 0.9723, | |
| "mean_token_accuracy": 0.7241554304957389, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.6275631855030996, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.5815846369070332e-05, | |
| "loss": 1.0736, | |
| "mean_token_accuracy": 0.7066580310463906, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.6294706723891274, | |
| "grad_norm": 5.125, | |
| "learning_rate": 1.5803128576879054e-05, | |
| "loss": 1.0553, | |
| "mean_token_accuracy": 0.7062164053320885, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.631378159275155, | |
| "grad_norm": 4.1875, | |
| "learning_rate": 1.579041078468778e-05, | |
| "loss": 1.0238, | |
| "mean_token_accuracy": 0.7111857526004315, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.6332856461611827, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.5777692992496505e-05, | |
| "loss": 0.9547, | |
| "mean_token_accuracy": 0.7140131160616875, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.6351931330472103, | |
| "grad_norm": 4.75, | |
| "learning_rate": 1.5764975200305227e-05, | |
| "loss": 1.0719, | |
| "mean_token_accuracy": 0.6966261744499207, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.637100619933238, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.5752257408113953e-05, | |
| "loss": 1.0385, | |
| "mean_token_accuracy": 0.7105199143290519, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.6390081068192656, | |
| "grad_norm": 5.40625, | |
| "learning_rate": 1.5739539615922678e-05, | |
| "loss": 1.0362, | |
| "mean_token_accuracy": 0.7015564523637294, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.6409155937052933, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.57268218237314e-05, | |
| "loss": 0.9366, | |
| "mean_token_accuracy": 0.7337832853198052, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.642823080591321, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 1.5714104031540126e-05, | |
| "loss": 1.1166, | |
| "mean_token_accuracy": 0.6753425896167755, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.6447305674773486, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.570138623934885e-05, | |
| "loss": 1.0364, | |
| "mean_token_accuracy": 0.7042675077915191, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.6466380543633763, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 1.5688668447157577e-05, | |
| "loss": 0.9948, | |
| "mean_token_accuracy": 0.7185570999979973, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.6485455412494039, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.56759506549663e-05, | |
| "loss": 1.0878, | |
| "mean_token_accuracy": 0.6928838163614273, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.6504530281354316, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 1.5663232862775024e-05, | |
| "loss": 1.0671, | |
| "mean_token_accuracy": 0.7043869346380234, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.6523605150214592, | |
| "grad_norm": 4.5, | |
| "learning_rate": 1.5650515070583746e-05, | |
| "loss": 1.0721, | |
| "mean_token_accuracy": 0.7013254553079605, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.6542680019074869, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 1.5637797278392472e-05, | |
| "loss": 1.0065, | |
| "mean_token_accuracy": 0.7042224168777466, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.6561754887935145, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 1.5625079486201197e-05, | |
| "loss": 1.0739, | |
| "mean_token_accuracy": 0.6945244207978248, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.6580829756795422, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 1.561236169400992e-05, | |
| "loss": 1.0859, | |
| "mean_token_accuracy": 0.6950926452875137, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.6599904625655698, | |
| "grad_norm": 4.8125, | |
| "learning_rate": 1.5599643901818645e-05, | |
| "loss": 0.9103, | |
| "mean_token_accuracy": 0.7312288954854012, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.6618979494515975, | |
| "grad_norm": 4.375, | |
| "learning_rate": 1.558692610962737e-05, | |
| "loss": 0.9913, | |
| "mean_token_accuracy": 0.7258316233754158, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.6638054363376252, | |
| "grad_norm": 5.84375, | |
| "learning_rate": 1.5574208317436096e-05, | |
| "loss": 1.1365, | |
| "mean_token_accuracy": 0.6847386986017228, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.6657129232236528, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 1.5561490525244818e-05, | |
| "loss": 0.9208, | |
| "mean_token_accuracy": 0.7318013399839401, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.6676204101096805, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.5548772733053544e-05, | |
| "loss": 1.0381, | |
| "mean_token_accuracy": 0.7117675840854645, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.6695278969957081, | |
| "grad_norm": 4.0, | |
| "learning_rate": 1.553605494086227e-05, | |
| "loss": 0.9807, | |
| "mean_token_accuracy": 0.7145498290657997, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.6714353838817358, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 1.552333714867099e-05, | |
| "loss": 0.9746, | |
| "mean_token_accuracy": 0.7150619328022003, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.6733428707677634, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.5510619356479717e-05, | |
| "loss": 1.0595, | |
| "mean_token_accuracy": 0.7089547023177147, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.6752503576537912, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.549790156428844e-05, | |
| "loss": 1.0631, | |
| "mean_token_accuracy": 0.7015356197953224, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.6771578445398188, | |
| "grad_norm": 6.28125, | |
| "learning_rate": 1.5485183772097164e-05, | |
| "loss": 1.0188, | |
| "mean_token_accuracy": 0.7043671816587448, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.6790653314258465, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 1.547246597990589e-05, | |
| "loss": 1.017, | |
| "mean_token_accuracy": 0.707620695233345, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.6809728183118741, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.5459748187714615e-05, | |
| "loss": 1.0261, | |
| "mean_token_accuracy": 0.7107647344470024, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.6828803051979018, | |
| "grad_norm": 5.1875, | |
| "learning_rate": 1.5447030395523338e-05, | |
| "loss": 0.976, | |
| "mean_token_accuracy": 0.7236540615558624, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.6847877920839294, | |
| "grad_norm": 4.40625, | |
| "learning_rate": 1.5434312603332063e-05, | |
| "loss": 1.0489, | |
| "mean_token_accuracy": 0.7052806288003921, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.6866952789699571, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.542159481114079e-05, | |
| "loss": 1.0648, | |
| "mean_token_accuracy": 0.6937704533338547, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.6886027658559848, | |
| "grad_norm": 3.921875, | |
| "learning_rate": 1.540887701894951e-05, | |
| "loss": 1.0472, | |
| "mean_token_accuracy": 0.7000033929944038, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.6905102527420124, | |
| "grad_norm": 4.0625, | |
| "learning_rate": 1.5396159226758236e-05, | |
| "loss": 0.9398, | |
| "mean_token_accuracy": 0.7206048682332039, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.6924177396280401, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.538344143456696e-05, | |
| "loss": 1.078, | |
| "mean_token_accuracy": 0.6949393272399902, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.6943252265140677, | |
| "grad_norm": 4.78125, | |
| "learning_rate": 1.5370723642375684e-05, | |
| "loss": 0.9936, | |
| "mean_token_accuracy": 0.716967236995697, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.6962327134000954, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 1.535800585018441e-05, | |
| "loss": 1.0597, | |
| "mean_token_accuracy": 0.7033153355121613, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.698140200286123, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 1.534528805799313e-05, | |
| "loss": 1.0689, | |
| "mean_token_accuracy": 0.6991181001067162, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.7000476871721507, | |
| "grad_norm": 5.59375, | |
| "learning_rate": 1.5332570265801857e-05, | |
| "loss": 1.0807, | |
| "mean_token_accuracy": 0.6999934658408165, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.7019551740581783, | |
| "grad_norm": 5.0625, | |
| "learning_rate": 1.5319852473610582e-05, | |
| "loss": 0.9682, | |
| "mean_token_accuracy": 0.723272667825222, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.703862660944206, | |
| "grad_norm": 4.15625, | |
| "learning_rate": 1.5307134681419308e-05, | |
| "loss": 1.031, | |
| "mean_token_accuracy": 0.6966592162847519, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.7057701478302336, | |
| "grad_norm": 5.15625, | |
| "learning_rate": 1.5294416889228033e-05, | |
| "loss": 1.0431, | |
| "mean_token_accuracy": 0.714342576265335, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.7076776347162613, | |
| "grad_norm": 5.78125, | |
| "learning_rate": 1.5281699097036755e-05, | |
| "loss": 1.0259, | |
| "mean_token_accuracy": 0.7083830907940865, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.709585121602289, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.526898130484548e-05, | |
| "loss": 0.9847, | |
| "mean_token_accuracy": 0.7163553655147552, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.7114926084883166, | |
| "grad_norm": 6.28125, | |
| "learning_rate": 1.5256263512654203e-05, | |
| "loss": 0.9951, | |
| "mean_token_accuracy": 0.7172233253717423, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.7134000953743443, | |
| "grad_norm": 5.25, | |
| "learning_rate": 1.5243545720462929e-05, | |
| "loss": 1.0708, | |
| "mean_token_accuracy": 0.6974482744932174, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.7153075822603719, | |
| "grad_norm": 4.625, | |
| "learning_rate": 1.5230827928271654e-05, | |
| "loss": 1.0573, | |
| "mean_token_accuracy": 0.7091765016317367, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.7172150691463997, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.5218110136080378e-05, | |
| "loss": 0.969, | |
| "mean_token_accuracy": 0.7144028797745705, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.7191225560324273, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.5205392343889103e-05, | |
| "loss": 1.0841, | |
| "mean_token_accuracy": 0.696842522919178, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.721030042918455, | |
| "grad_norm": 4.21875, | |
| "learning_rate": 1.5192674551697825e-05, | |
| "loss": 0.9193, | |
| "mean_token_accuracy": 0.7247643247246742, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.7229375298044826, | |
| "grad_norm": 5.3125, | |
| "learning_rate": 1.5179956759506551e-05, | |
| "loss": 0.9693, | |
| "mean_token_accuracy": 0.7202573090791702, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.7248450166905103, | |
| "grad_norm": 4.59375, | |
| "learning_rate": 1.5167238967315275e-05, | |
| "loss": 0.9176, | |
| "mean_token_accuracy": 0.7282809093594551, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.7267525035765379, | |
| "grad_norm": 4.53125, | |
| "learning_rate": 1.5154521175124e-05, | |
| "loss": 0.9122, | |
| "mean_token_accuracy": 0.7338912770152092, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.7286599904625656, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.5141803382932724e-05, | |
| "loss": 1.0756, | |
| "mean_token_accuracy": 0.6949716225266457, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.7305674773485932, | |
| "grad_norm": 4.96875, | |
| "learning_rate": 1.5129085590741448e-05, | |
| "loss": 1.0789, | |
| "mean_token_accuracy": 0.6967040143907071, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 0.7324749642346209, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.5116367798550173e-05, | |
| "loss": 0.9752, | |
| "mean_token_accuracy": 0.7204620942473412, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.7343824511206486, | |
| "grad_norm": 3.8125, | |
| "learning_rate": 1.5103650006358897e-05, | |
| "loss": 1.0254, | |
| "mean_token_accuracy": 0.7050608977675438, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.7362899380066762, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 1.5090932214167621e-05, | |
| "loss": 0.9845, | |
| "mean_token_accuracy": 0.718043963611126, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.7381974248927039, | |
| "grad_norm": 4.75, | |
| "learning_rate": 1.5078214421976347e-05, | |
| "loss": 0.9798, | |
| "mean_token_accuracy": 0.7155537083745003, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.7401049117787315, | |
| "grad_norm": 4.125, | |
| "learning_rate": 1.506549662978507e-05, | |
| "loss": 0.9766, | |
| "mean_token_accuracy": 0.7140335828065872, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.7420123986647592, | |
| "grad_norm": 4.125, | |
| "learning_rate": 1.5052778837593796e-05, | |
| "loss": 1.048, | |
| "mean_token_accuracy": 0.6943504139780998, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 0.7439198855507868, | |
| "grad_norm": 4.46875, | |
| "learning_rate": 1.5040061045402518e-05, | |
| "loss": 0.9615, | |
| "mean_token_accuracy": 0.7220544546842576, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.7458273724368145, | |
| "grad_norm": 5.0, | |
| "learning_rate": 1.5027343253211243e-05, | |
| "loss": 0.9978, | |
| "mean_token_accuracy": 0.7115991845726967, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 0.7477348593228421, | |
| "grad_norm": 4.25, | |
| "learning_rate": 1.5014625461019967e-05, | |
| "loss": 0.9384, | |
| "mean_token_accuracy": 0.7263565197587013, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.7496423462088698, | |
| "grad_norm": 4.90625, | |
| "learning_rate": 1.5001907668828693e-05, | |
| "loss": 1.0709, | |
| "mean_token_accuracy": 0.6875549122691155, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 0.7515498330948974, | |
| "grad_norm": 5.4375, | |
| "learning_rate": 1.4989189876637418e-05, | |
| "loss": 1.0374, | |
| "mean_token_accuracy": 0.7037866428494454, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.7534573199809251, | |
| "grad_norm": 4.4375, | |
| "learning_rate": 1.497647208444614e-05, | |
| "loss": 0.9627, | |
| "mean_token_accuracy": 0.7117268234491348, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.7553648068669528, | |
| "grad_norm": 4.34375, | |
| "learning_rate": 1.4963754292254866e-05, | |
| "loss": 0.9921, | |
| "mean_token_accuracy": 0.7058862507343292, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.7572722937529804, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 1.495103650006359e-05, | |
| "loss": 0.961, | |
| "mean_token_accuracy": 0.7215966627001762, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 0.7591797806390082, | |
| "grad_norm": 4.375, | |
| "learning_rate": 1.4938318707872315e-05, | |
| "loss": 0.8637, | |
| "mean_token_accuracy": 0.7477660223841667, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.7610872675250357, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 1.492560091568104e-05, | |
| "loss": 0.9912, | |
| "mean_token_accuracy": 0.7125525683164596, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 0.7629947544110635, | |
| "grad_norm": 4.09375, | |
| "learning_rate": 1.4912883123489763e-05, | |
| "loss": 0.9836, | |
| "mean_token_accuracy": 0.7163909748196602, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 7863, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.321196176694559e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |