{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 5115, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005865102639296188, "grad_norm": 31.542375564575195, "learning_rate": 9e-07, "loss": 0.5324, "step": 10 }, { "epoch": 0.011730205278592375, "grad_norm": 27.081035614013672, "learning_rate": 1.9e-06, "loss": 0.4886, "step": 20 }, { "epoch": 0.017595307917888565, "grad_norm": 9.631855010986328, "learning_rate": 2.9e-06, "loss": 0.2291, "step": 30 }, { "epoch": 0.02346041055718475, "grad_norm": 7.441354751586914, "learning_rate": 3.9e-06, "loss": 0.1422, "step": 40 }, { "epoch": 0.02932551319648094, "grad_norm": 5.272273063659668, "learning_rate": 4.9000000000000005e-06, "loss": 0.1189, "step": 50 }, { "epoch": 0.03519061583577713, "grad_norm": 4.908827781677246, "learning_rate": 5.9e-06, "loss": 0.0836, "step": 60 }, { "epoch": 0.04105571847507331, "grad_norm": 6.410752296447754, "learning_rate": 6.900000000000001e-06, "loss": 0.0788, "step": 70 }, { "epoch": 0.0469208211143695, "grad_norm": 4.663637638092041, "learning_rate": 7.9e-06, "loss": 0.0797, "step": 80 }, { "epoch": 0.05278592375366569, "grad_norm": 4.668508052825928, "learning_rate": 8.9e-06, "loss": 0.0432, "step": 90 }, { "epoch": 0.05865102639296188, "grad_norm": 4.451730251312256, "learning_rate": 9.900000000000002e-06, "loss": 0.0447, "step": 100 }, { "epoch": 0.06451612903225806, "grad_norm": 2.972118854522705, "learning_rate": 1.09e-05, "loss": 0.0364, "step": 110 }, { "epoch": 0.07038123167155426, "grad_norm": 4.36667013168335, "learning_rate": 1.19e-05, "loss": 0.0427, "step": 120 }, { "epoch": 0.07624633431085044, "grad_norm": 2.4861721992492676, "learning_rate": 1.29e-05, "loss": 0.0434, "step": 130 }, { "epoch": 0.08211143695014662, "grad_norm": 1.6505670547485352, "learning_rate": 1.3900000000000002e-05, "loss": 0.0497, "step": 140 }, { "epoch": 0.08797653958944282, "grad_norm": 4.313763618469238, "learning_rate": 1.49e-05, "loss": 0.0346, "step": 150 }, { "epoch": 0.093841642228739, "grad_norm": 2.6852822303771973, "learning_rate": 1.59e-05, "loss": 0.0425, "step": 160 }, { "epoch": 0.09970674486803519, "grad_norm": 4.099714756011963, "learning_rate": 1.69e-05, "loss": 0.0356, "step": 170 }, { "epoch": 0.10557184750733138, "grad_norm": 5.82313346862793, "learning_rate": 1.79e-05, "loss": 0.0406, "step": 180 }, { "epoch": 0.11143695014662756, "grad_norm": 4.862349510192871, "learning_rate": 1.8900000000000002e-05, "loss": 0.0442, "step": 190 }, { "epoch": 0.11730205278592376, "grad_norm": 4.571470737457275, "learning_rate": 1.9900000000000003e-05, "loss": 0.0505, "step": 200 }, { "epoch": 0.12316715542521994, "grad_norm": 3.140578031539917, "learning_rate": 2.09e-05, "loss": 0.0352, "step": 210 }, { "epoch": 0.12903225806451613, "grad_norm": 1.6524794101715088, "learning_rate": 2.19e-05, "loss": 0.028, "step": 220 }, { "epoch": 0.1348973607038123, "grad_norm": 8.246803283691406, "learning_rate": 2.29e-05, "loss": 0.0497, "step": 230 }, { "epoch": 0.14076246334310852, "grad_norm": 3.31701922416687, "learning_rate": 2.39e-05, "loss": 0.0415, "step": 240 }, { "epoch": 0.1466275659824047, "grad_norm": 6.1794939041137695, "learning_rate": 2.4900000000000002e-05, "loss": 0.0345, "step": 250 }, { "epoch": 0.15249266862170088, "grad_norm": 4.081472396850586, "learning_rate": 2.5900000000000003e-05, "loss": 0.0347, "step": 260 }, { "epoch": 0.15835777126099707, "grad_norm": 2.7104103565216064, "learning_rate": 2.6900000000000003e-05, "loss": 0.0409, "step": 270 }, { "epoch": 0.16422287390029325, "grad_norm": 6.425929546356201, "learning_rate": 2.7900000000000004e-05, "loss": 0.0402, "step": 280 }, { "epoch": 0.17008797653958943, "grad_norm": 1.5873750448226929, "learning_rate": 2.8899999999999998e-05, "loss": 0.0306, "step": 290 }, { "epoch": 0.17595307917888564, "grad_norm": 4.29845666885376, "learning_rate": 2.9900000000000002e-05, "loss": 0.0329, "step": 300 }, { "epoch": 0.18181818181818182, "grad_norm": 1.728096604347229, "learning_rate": 3.09e-05, "loss": 0.0363, "step": 310 }, { "epoch": 0.187683284457478, "grad_norm": 2.5301356315612793, "learning_rate": 3.19e-05, "loss": 0.0293, "step": 320 }, { "epoch": 0.1935483870967742, "grad_norm": 5.745728015899658, "learning_rate": 3.29e-05, "loss": 0.0352, "step": 330 }, { "epoch": 0.19941348973607037, "grad_norm": 3.1042871475219727, "learning_rate": 3.3900000000000004e-05, "loss": 0.0268, "step": 340 }, { "epoch": 0.20527859237536658, "grad_norm": 2.0150339603424072, "learning_rate": 3.49e-05, "loss": 0.0284, "step": 350 }, { "epoch": 0.21114369501466276, "grad_norm": 1.6547868251800537, "learning_rate": 3.59e-05, "loss": 0.0362, "step": 360 }, { "epoch": 0.21700879765395895, "grad_norm": 4.4225754737854, "learning_rate": 3.69e-05, "loss": 0.0284, "step": 370 }, { "epoch": 0.22287390029325513, "grad_norm": 4.417116641998291, "learning_rate": 3.79e-05, "loss": 0.0317, "step": 380 }, { "epoch": 0.2287390029325513, "grad_norm": 3.4028005599975586, "learning_rate": 3.8900000000000004e-05, "loss": 0.0336, "step": 390 }, { "epoch": 0.23460410557184752, "grad_norm": 1.276804804801941, "learning_rate": 3.99e-05, "loss": 0.0291, "step": 400 }, { "epoch": 0.2404692082111437, "grad_norm": 3.228950023651123, "learning_rate": 4.09e-05, "loss": 0.0404, "step": 410 }, { "epoch": 0.24633431085043989, "grad_norm": 2.382463216781616, "learning_rate": 4.19e-05, "loss": 0.0399, "step": 420 }, { "epoch": 0.25219941348973607, "grad_norm": 3.2565174102783203, "learning_rate": 4.29e-05, "loss": 0.0327, "step": 430 }, { "epoch": 0.25806451612903225, "grad_norm": 2.632328510284424, "learning_rate": 4.39e-05, "loss": 0.0301, "step": 440 }, { "epoch": 0.26392961876832843, "grad_norm": 7.466786861419678, "learning_rate": 4.49e-05, "loss": 0.0361, "step": 450 }, { "epoch": 0.2697947214076246, "grad_norm": 1.4194852113723755, "learning_rate": 4.5900000000000004e-05, "loss": 0.0332, "step": 460 }, { "epoch": 0.2756598240469208, "grad_norm": 2.4137372970581055, "learning_rate": 4.69e-05, "loss": 0.0396, "step": 470 }, { "epoch": 0.28152492668621704, "grad_norm": 1.9690659046173096, "learning_rate": 4.79e-05, "loss": 0.0254, "step": 480 }, { "epoch": 0.2873900293255132, "grad_norm": 3.2981226444244385, "learning_rate": 4.89e-05, "loss": 0.0228, "step": 490 }, { "epoch": 0.2932551319648094, "grad_norm": 5.314478397369385, "learning_rate": 4.99e-05, "loss": 0.0291, "step": 500 }, { "epoch": 0.2991202346041056, "grad_norm": 2.0909876823425293, "learning_rate": 4.9902491874322866e-05, "loss": 0.0205, "step": 510 }, { "epoch": 0.30498533724340177, "grad_norm": 5.199825286865234, "learning_rate": 4.979414951245938e-05, "loss": 0.049, "step": 520 }, { "epoch": 0.31085043988269795, "grad_norm": 2.305478096008301, "learning_rate": 4.968580715059589e-05, "loss": 0.0274, "step": 530 }, { "epoch": 0.31671554252199413, "grad_norm": 8.331841468811035, "learning_rate": 4.95774647887324e-05, "loss": 0.0356, "step": 540 }, { "epoch": 0.3225806451612903, "grad_norm": 5.1305437088012695, "learning_rate": 4.9469122426868905e-05, "loss": 0.0385, "step": 550 }, { "epoch": 0.3284457478005865, "grad_norm": 2.931698799133301, "learning_rate": 4.936078006500542e-05, "loss": 0.0255, "step": 560 }, { "epoch": 0.3343108504398827, "grad_norm": 1.6110111474990845, "learning_rate": 4.925243770314193e-05, "loss": 0.0264, "step": 570 }, { "epoch": 0.34017595307917886, "grad_norm": 2.3846256732940674, "learning_rate": 4.914409534127844e-05, "loss": 0.0252, "step": 580 }, { "epoch": 0.3460410557184751, "grad_norm": 2.34324049949646, "learning_rate": 4.903575297941496e-05, "loss": 0.0336, "step": 590 }, { "epoch": 0.3519061583577713, "grad_norm": 2.084900140762329, "learning_rate": 4.892741061755147e-05, "loss": 0.0475, "step": 600 }, { "epoch": 0.35777126099706746, "grad_norm": 0.9921281337738037, "learning_rate": 4.8819068255687975e-05, "loss": 0.0359, "step": 610 }, { "epoch": 0.36363636363636365, "grad_norm": 2.2851696014404297, "learning_rate": 4.871072589382449e-05, "loss": 0.0212, "step": 620 }, { "epoch": 0.36950146627565983, "grad_norm": 2.9308276176452637, "learning_rate": 4.8602383531961e-05, "loss": 0.0328, "step": 630 }, { "epoch": 0.375366568914956, "grad_norm": 6.85349178314209, "learning_rate": 4.849404117009751e-05, "loss": 0.0396, "step": 640 }, { "epoch": 0.3812316715542522, "grad_norm": 2.044726610183716, "learning_rate": 4.838569880823402e-05, "loss": 0.0292, "step": 650 }, { "epoch": 0.3870967741935484, "grad_norm": 1.818989634513855, "learning_rate": 4.827735644637053e-05, "loss": 0.0251, "step": 660 }, { "epoch": 0.39296187683284456, "grad_norm": 3.9918439388275146, "learning_rate": 4.8169014084507045e-05, "loss": 0.0221, "step": 670 }, { "epoch": 0.39882697947214074, "grad_norm": 3.0383472442626953, "learning_rate": 4.8060671722643556e-05, "loss": 0.0239, "step": 680 }, { "epoch": 0.4046920821114369, "grad_norm": 0.7501923441886902, "learning_rate": 4.795232936078007e-05, "loss": 0.0255, "step": 690 }, { "epoch": 0.41055718475073316, "grad_norm": 0.8744826316833496, "learning_rate": 4.784398699891658e-05, "loss": 0.022, "step": 700 }, { "epoch": 0.41642228739002934, "grad_norm": 4.488051891326904, "learning_rate": 4.773564463705309e-05, "loss": 0.0217, "step": 710 }, { "epoch": 0.4222873900293255, "grad_norm": 3.3455092906951904, "learning_rate": 4.76273022751896e-05, "loss": 0.019, "step": 720 }, { "epoch": 0.4281524926686217, "grad_norm": 3.4381587505340576, "learning_rate": 4.751895991332611e-05, "loss": 0.0231, "step": 730 }, { "epoch": 0.4340175953079179, "grad_norm": 2.643965482711792, "learning_rate": 4.741061755146262e-05, "loss": 0.0249, "step": 740 }, { "epoch": 0.4398826979472141, "grad_norm": 3.4764389991760254, "learning_rate": 4.730227518959914e-05, "loss": 0.0228, "step": 750 }, { "epoch": 0.44574780058651026, "grad_norm": 3.8638241291046143, "learning_rate": 4.719393282773565e-05, "loss": 0.038, "step": 760 }, { "epoch": 0.45161290322580644, "grad_norm": 1.6857688426971436, "learning_rate": 4.708559046587216e-05, "loss": 0.0297, "step": 770 }, { "epoch": 0.4574780058651026, "grad_norm": 1.9079605340957642, "learning_rate": 4.697724810400867e-05, "loss": 0.0346, "step": 780 }, { "epoch": 0.4633431085043988, "grad_norm": 2.4099855422973633, "learning_rate": 4.686890574214518e-05, "loss": 0.0192, "step": 790 }, { "epoch": 0.46920821114369504, "grad_norm": 2.6280362606048584, "learning_rate": 4.676056338028169e-05, "loss": 0.0251, "step": 800 }, { "epoch": 0.4750733137829912, "grad_norm": 1.9467144012451172, "learning_rate": 4.66522210184182e-05, "loss": 0.027, "step": 810 }, { "epoch": 0.4809384164222874, "grad_norm": 6.638300895690918, "learning_rate": 4.654387865655471e-05, "loss": 0.0253, "step": 820 }, { "epoch": 0.4868035190615836, "grad_norm": 2.0866501331329346, "learning_rate": 4.643553629469123e-05, "loss": 0.0205, "step": 830 }, { "epoch": 0.49266862170087977, "grad_norm": 0.8170230388641357, "learning_rate": 4.632719393282774e-05, "loss": 0.018, "step": 840 }, { "epoch": 0.49853372434017595, "grad_norm": 2.902468204498291, "learning_rate": 4.621885157096425e-05, "loss": 0.0306, "step": 850 }, { "epoch": 0.5043988269794721, "grad_norm": 1.3711732625961304, "learning_rate": 4.611050920910076e-05, "loss": 0.0169, "step": 860 }, { "epoch": 0.5102639296187683, "grad_norm": 2.804041862487793, "learning_rate": 4.600216684723727e-05, "loss": 0.0185, "step": 870 }, { "epoch": 0.5161290322580645, "grad_norm": 4.9906792640686035, "learning_rate": 4.589382448537378e-05, "loss": 0.023, "step": 880 }, { "epoch": 0.5219941348973607, "grad_norm": 4.329658031463623, "learning_rate": 4.5785482123510294e-05, "loss": 0.0271, "step": 890 }, { "epoch": 0.5278592375366569, "grad_norm": 1.0276806354522705, "learning_rate": 4.567713976164681e-05, "loss": 0.0174, "step": 900 }, { "epoch": 0.533724340175953, "grad_norm": 0.8810903429985046, "learning_rate": 4.556879739978332e-05, "loss": 0.0235, "step": 910 }, { "epoch": 0.5395894428152492, "grad_norm": 4.086939811706543, "learning_rate": 4.546045503791983e-05, "loss": 0.0272, "step": 920 }, { "epoch": 0.5454545454545454, "grad_norm": 0.9442876577377319, "learning_rate": 4.535211267605634e-05, "loss": 0.0231, "step": 930 }, { "epoch": 0.5513196480938416, "grad_norm": 2.153064727783203, "learning_rate": 4.524377031419285e-05, "loss": 0.0228, "step": 940 }, { "epoch": 0.5571847507331378, "grad_norm": 1.1959385871887207, "learning_rate": 4.513542795232936e-05, "loss": 0.0313, "step": 950 }, { "epoch": 0.5630498533724341, "grad_norm": 2.5583062171936035, "learning_rate": 4.5027085590465875e-05, "loss": 0.0303, "step": 960 }, { "epoch": 0.5689149560117303, "grad_norm": 2.264181137084961, "learning_rate": 4.4918743228602387e-05, "loss": 0.0338, "step": 970 }, { "epoch": 0.5747800586510264, "grad_norm": 1.718117594718933, "learning_rate": 4.48104008667389e-05, "loss": 0.0252, "step": 980 }, { "epoch": 0.5806451612903226, "grad_norm": 0.4819270670413971, "learning_rate": 4.470205850487541e-05, "loss": 0.0227, "step": 990 }, { "epoch": 0.5865102639296188, "grad_norm": 5.476009368896484, "learning_rate": 4.459371614301192e-05, "loss": 0.0245, "step": 1000 }, { "epoch": 0.592375366568915, "grad_norm": 1.2682011127471924, "learning_rate": 4.448537378114843e-05, "loss": 0.0127, "step": 1010 }, { "epoch": 0.5982404692082112, "grad_norm": 6.694324493408203, "learning_rate": 4.4377031419284945e-05, "loss": 0.0226, "step": 1020 }, { "epoch": 0.6041055718475073, "grad_norm": 1.3645150661468506, "learning_rate": 4.4268689057421456e-05, "loss": 0.0144, "step": 1030 }, { "epoch": 0.6099706744868035, "grad_norm": 5.142198085784912, "learning_rate": 4.416034669555796e-05, "loss": 0.0176, "step": 1040 }, { "epoch": 0.6158357771260997, "grad_norm": 1.976951241493225, "learning_rate": 4.405200433369447e-05, "loss": 0.0266, "step": 1050 }, { "epoch": 0.6217008797653959, "grad_norm": 1.9132397174835205, "learning_rate": 4.394366197183099e-05, "loss": 0.0328, "step": 1060 }, { "epoch": 0.6275659824046921, "grad_norm": 0.9554237127304077, "learning_rate": 4.38353196099675e-05, "loss": 0.0311, "step": 1070 }, { "epoch": 0.6334310850439883, "grad_norm": 1.418505072593689, "learning_rate": 4.3726977248104014e-05, "loss": 0.0205, "step": 1080 }, { "epoch": 0.6392961876832844, "grad_norm": 1.686772346496582, "learning_rate": 4.361863488624052e-05, "loss": 0.0231, "step": 1090 }, { "epoch": 0.6451612903225806, "grad_norm": 0.7826172113418579, "learning_rate": 4.351029252437703e-05, "loss": 0.024, "step": 1100 }, { "epoch": 0.6510263929618768, "grad_norm": 2.0760345458984375, "learning_rate": 4.340195016251354e-05, "loss": 0.0204, "step": 1110 }, { "epoch": 0.656891495601173, "grad_norm": 1.7399033308029175, "learning_rate": 4.3293607800650054e-05, "loss": 0.0165, "step": 1120 }, { "epoch": 0.6627565982404692, "grad_norm": 1.938363790512085, "learning_rate": 4.3185265438786566e-05, "loss": 0.017, "step": 1130 }, { "epoch": 0.6686217008797654, "grad_norm": 4.907315254211426, "learning_rate": 4.3076923076923084e-05, "loss": 0.0244, "step": 1140 }, { "epoch": 0.6744868035190615, "grad_norm": 0.951277494430542, "learning_rate": 4.296858071505959e-05, "loss": 0.0177, "step": 1150 }, { "epoch": 0.6803519061583577, "grad_norm": 2.8571536540985107, "learning_rate": 4.28602383531961e-05, "loss": 0.0107, "step": 1160 }, { "epoch": 0.6862170087976539, "grad_norm": 4.217930316925049, "learning_rate": 4.275189599133261e-05, "loss": 0.019, "step": 1170 }, { "epoch": 0.6920821114369502, "grad_norm": 5.358763694763184, "learning_rate": 4.2643553629469124e-05, "loss": 0.0142, "step": 1180 }, { "epoch": 0.6979472140762464, "grad_norm": 1.1704353094100952, "learning_rate": 4.2535211267605635e-05, "loss": 0.021, "step": 1190 }, { "epoch": 0.7038123167155426, "grad_norm": 0.6873300075531006, "learning_rate": 4.242686890574215e-05, "loss": 0.0131, "step": 1200 }, { "epoch": 0.7096774193548387, "grad_norm": 0.8728815317153931, "learning_rate": 4.231852654387866e-05, "loss": 0.0155, "step": 1210 }, { "epoch": 0.7155425219941349, "grad_norm": 0.5841957926750183, "learning_rate": 4.221018418201517e-05, "loss": 0.0138, "step": 1220 }, { "epoch": 0.7214076246334311, "grad_norm": 2.72292423248291, "learning_rate": 4.210184182015168e-05, "loss": 0.0154, "step": 1230 }, { "epoch": 0.7272727272727273, "grad_norm": 3.6884212493896484, "learning_rate": 4.1993499458288194e-05, "loss": 0.0146, "step": 1240 }, { "epoch": 0.7331378299120235, "grad_norm": 0.3702751696109772, "learning_rate": 4.1885157096424705e-05, "loss": 0.0094, "step": 1250 }, { "epoch": 0.7390029325513197, "grad_norm": 2.5344738960266113, "learning_rate": 4.177681473456122e-05, "loss": 0.0265, "step": 1260 }, { "epoch": 0.7448680351906158, "grad_norm": 0.8168351650238037, "learning_rate": 4.166847237269773e-05, "loss": 0.0173, "step": 1270 }, { "epoch": 0.750733137829912, "grad_norm": 3.0414071083068848, "learning_rate": 4.156013001083423e-05, "loss": 0.0185, "step": 1280 }, { "epoch": 0.7565982404692082, "grad_norm": 3.424670696258545, "learning_rate": 4.1451787648970745e-05, "loss": 0.0216, "step": 1290 }, { "epoch": 0.7624633431085044, "grad_norm": 0.7243099808692932, "learning_rate": 4.134344528710726e-05, "loss": 0.0117, "step": 1300 }, { "epoch": 0.7683284457478006, "grad_norm": 2.333580493927002, "learning_rate": 4.1235102925243775e-05, "loss": 0.0136, "step": 1310 }, { "epoch": 0.7741935483870968, "grad_norm": 1.190661907196045, "learning_rate": 4.1126760563380286e-05, "loss": 0.0138, "step": 1320 }, { "epoch": 0.7800586510263929, "grad_norm": 2.198655128479004, "learning_rate": 4.10184182015168e-05, "loss": 0.0288, "step": 1330 }, { "epoch": 0.7859237536656891, "grad_norm": 3.7605550289154053, "learning_rate": 4.09100758396533e-05, "loss": 0.0165, "step": 1340 }, { "epoch": 0.7917888563049853, "grad_norm": 2.7459802627563477, "learning_rate": 4.0801733477789815e-05, "loss": 0.0167, "step": 1350 }, { "epoch": 0.7976539589442815, "grad_norm": 1.2568968534469604, "learning_rate": 4.0693391115926326e-05, "loss": 0.018, "step": 1360 }, { "epoch": 0.8035190615835777, "grad_norm": 4.848509788513184, "learning_rate": 4.0585048754062845e-05, "loss": 0.0199, "step": 1370 }, { "epoch": 0.8093841642228738, "grad_norm": 3.814544439315796, "learning_rate": 4.0476706392199356e-05, "loss": 0.0197, "step": 1380 }, { "epoch": 0.8152492668621701, "grad_norm": 3.7389025688171387, "learning_rate": 4.036836403033587e-05, "loss": 0.0164, "step": 1390 }, { "epoch": 0.8211143695014663, "grad_norm": 3.4222829341888428, "learning_rate": 4.026002166847237e-05, "loss": 0.0211, "step": 1400 }, { "epoch": 0.8269794721407625, "grad_norm": 0.8773980140686035, "learning_rate": 4.0151679306608884e-05, "loss": 0.0135, "step": 1410 }, { "epoch": 0.8328445747800587, "grad_norm": 0.4585646688938141, "learning_rate": 4.0043336944745396e-05, "loss": 0.0128, "step": 1420 }, { "epoch": 0.8387096774193549, "grad_norm": 4.22011137008667, "learning_rate": 3.993499458288191e-05, "loss": 0.011, "step": 1430 }, { "epoch": 0.844574780058651, "grad_norm": 0.6671493053436279, "learning_rate": 3.982665222101842e-05, "loss": 0.0166, "step": 1440 }, { "epoch": 0.8504398826979472, "grad_norm": 1.6846585273742676, "learning_rate": 3.971830985915493e-05, "loss": 0.0178, "step": 1450 }, { "epoch": 0.8563049853372434, "grad_norm": 1.7884533405303955, "learning_rate": 3.960996749729144e-05, "loss": 0.0129, "step": 1460 }, { "epoch": 0.8621700879765396, "grad_norm": 1.448573350906372, "learning_rate": 3.9501625135427954e-05, "loss": 0.016, "step": 1470 }, { "epoch": 0.8680351906158358, "grad_norm": 0.4691716730594635, "learning_rate": 3.9393282773564466e-05, "loss": 0.0177, "step": 1480 }, { "epoch": 0.873900293255132, "grad_norm": 2.448608875274658, "learning_rate": 3.928494041170098e-05, "loss": 0.0134, "step": 1490 }, { "epoch": 0.8797653958944281, "grad_norm": 3.9812233448028564, "learning_rate": 3.917659804983749e-05, "loss": 0.0209, "step": 1500 }, { "epoch": 0.8856304985337243, "grad_norm": 2.5593063831329346, "learning_rate": 3.9068255687974e-05, "loss": 0.0241, "step": 1510 }, { "epoch": 0.8914956011730205, "grad_norm": 0.5445829629898071, "learning_rate": 3.8959913326110505e-05, "loss": 0.012, "step": 1520 }, { "epoch": 0.8973607038123167, "grad_norm": 2.9569761753082275, "learning_rate": 3.8851570964247024e-05, "loss": 0.0172, "step": 1530 }, { "epoch": 0.9032258064516129, "grad_norm": 1.6807665824890137, "learning_rate": 3.8743228602383535e-05, "loss": 0.0122, "step": 1540 }, { "epoch": 0.9090909090909091, "grad_norm": 0.29172345995903015, "learning_rate": 3.863488624052005e-05, "loss": 0.0225, "step": 1550 }, { "epoch": 0.9149560117302052, "grad_norm": 2.6526272296905518, "learning_rate": 3.852654387865656e-05, "loss": 0.0148, "step": 1560 }, { "epoch": 0.9208211143695014, "grad_norm": 3.159996271133423, "learning_rate": 3.841820151679307e-05, "loss": 0.0134, "step": 1570 }, { "epoch": 0.9266862170087976, "grad_norm": 3.0480852127075195, "learning_rate": 3.8309859154929575e-05, "loss": 0.0157, "step": 1580 }, { "epoch": 0.9325513196480938, "grad_norm": 0.8675422072410583, "learning_rate": 3.820151679306609e-05, "loss": 0.0178, "step": 1590 }, { "epoch": 0.9384164222873901, "grad_norm": 2.1896984577178955, "learning_rate": 3.80931744312026e-05, "loss": 0.0117, "step": 1600 }, { "epoch": 0.9442815249266863, "grad_norm": 1.3476594686508179, "learning_rate": 3.798483206933912e-05, "loss": 0.0108, "step": 1610 }, { "epoch": 0.9501466275659824, "grad_norm": 0.6463199853897095, "learning_rate": 3.787648970747563e-05, "loss": 0.0191, "step": 1620 }, { "epoch": 0.9560117302052786, "grad_norm": 1.6571842432022095, "learning_rate": 3.776814734561214e-05, "loss": 0.0089, "step": 1630 }, { "epoch": 0.9618768328445748, "grad_norm": 3.092883586883545, "learning_rate": 3.7659804983748645e-05, "loss": 0.0115, "step": 1640 }, { "epoch": 0.967741935483871, "grad_norm": 0.9108274579048157, "learning_rate": 3.7551462621885156e-05, "loss": 0.0094, "step": 1650 }, { "epoch": 0.9736070381231672, "grad_norm": 2.865462064743042, "learning_rate": 3.744312026002167e-05, "loss": 0.0113, "step": 1660 }, { "epoch": 0.9794721407624634, "grad_norm": 3.5765507221221924, "learning_rate": 3.733477789815818e-05, "loss": 0.0146, "step": 1670 }, { "epoch": 0.9853372434017595, "grad_norm": 2.7337465286254883, "learning_rate": 3.722643553629469e-05, "loss": 0.0243, "step": 1680 }, { "epoch": 0.9912023460410557, "grad_norm": 4.337994575500488, "learning_rate": 3.711809317443121e-05, "loss": 0.0197, "step": 1690 }, { "epoch": 0.9970674486803519, "grad_norm": 0.5181761384010315, "learning_rate": 3.7009750812567715e-05, "loss": 0.0104, "step": 1700 }, { "epoch": 1.002932551319648, "grad_norm": 1.3983606100082397, "learning_rate": 3.6901408450704226e-05, "loss": 0.0127, "step": 1710 }, { "epoch": 1.0087976539589443, "grad_norm": 0.8616273999214172, "learning_rate": 3.679306608884074e-05, "loss": 0.0093, "step": 1720 }, { "epoch": 1.0146627565982405, "grad_norm": 4.700988292694092, "learning_rate": 3.668472372697725e-05, "loss": 0.0199, "step": 1730 }, { "epoch": 1.0205278592375366, "grad_norm": 1.5445499420166016, "learning_rate": 3.657638136511376e-05, "loss": 0.0081, "step": 1740 }, { "epoch": 1.0263929618768328, "grad_norm": 1.7290083169937134, "learning_rate": 3.646803900325027e-05, "loss": 0.0187, "step": 1750 }, { "epoch": 1.032258064516129, "grad_norm": 1.9020334482192993, "learning_rate": 3.6359696641386784e-05, "loss": 0.0144, "step": 1760 }, { "epoch": 1.0381231671554252, "grad_norm": 0.6471778750419617, "learning_rate": 3.6251354279523296e-05, "loss": 0.0115, "step": 1770 }, { "epoch": 1.0439882697947214, "grad_norm": 2.929093599319458, "learning_rate": 3.614301191765981e-05, "loss": 0.0167, "step": 1780 }, { "epoch": 1.0498533724340176, "grad_norm": 1.2861549854278564, "learning_rate": 3.603466955579632e-05, "loss": 0.0136, "step": 1790 }, { "epoch": 1.0557184750733137, "grad_norm": 2.8851354122161865, "learning_rate": 3.592632719393283e-05, "loss": 0.0136, "step": 1800 }, { "epoch": 1.06158357771261, "grad_norm": 1.2886507511138916, "learning_rate": 3.581798483206934e-05, "loss": 0.0115, "step": 1810 }, { "epoch": 1.067448680351906, "grad_norm": 1.7136684656143188, "learning_rate": 3.5709642470205854e-05, "loss": 0.0109, "step": 1820 }, { "epoch": 1.0733137829912023, "grad_norm": 2.2909739017486572, "learning_rate": 3.560130010834236e-05, "loss": 0.0119, "step": 1830 }, { "epoch": 1.0791788856304985, "grad_norm": 2.4519524574279785, "learning_rate": 3.549295774647888e-05, "loss": 0.0154, "step": 1840 }, { "epoch": 1.0850439882697946, "grad_norm": 2.0411393642425537, "learning_rate": 3.538461538461539e-05, "loss": 0.0167, "step": 1850 }, { "epoch": 1.0909090909090908, "grad_norm": 4.16176700592041, "learning_rate": 3.52762730227519e-05, "loss": 0.0126, "step": 1860 }, { "epoch": 1.096774193548387, "grad_norm": 0.6198504567146301, "learning_rate": 3.516793066088841e-05, "loss": 0.0133, "step": 1870 }, { "epoch": 1.1026392961876832, "grad_norm": 1.6029118299484253, "learning_rate": 3.505958829902492e-05, "loss": 0.0108, "step": 1880 }, { "epoch": 1.1085043988269794, "grad_norm": 2.381258487701416, "learning_rate": 3.495124593716143e-05, "loss": 0.0091, "step": 1890 }, { "epoch": 1.1143695014662756, "grad_norm": 2.277298927307129, "learning_rate": 3.484290357529794e-05, "loss": 0.0173, "step": 1900 }, { "epoch": 1.1202346041055717, "grad_norm": 0.6369751691818237, "learning_rate": 3.473456121343445e-05, "loss": 0.0097, "step": 1910 }, { "epoch": 1.126099706744868, "grad_norm": 2.223329782485962, "learning_rate": 3.462621885157097e-05, "loss": 0.0136, "step": 1920 }, { "epoch": 1.131964809384164, "grad_norm": 0.8173966407775879, "learning_rate": 3.451787648970748e-05, "loss": 0.0105, "step": 1930 }, { "epoch": 1.1378299120234603, "grad_norm": 1.2677998542785645, "learning_rate": 3.440953412784399e-05, "loss": 0.0107, "step": 1940 }, { "epoch": 1.1436950146627567, "grad_norm": 0.6888647079467773, "learning_rate": 3.43011917659805e-05, "loss": 0.0122, "step": 1950 }, { "epoch": 1.1495601173020529, "grad_norm": 1.7134896516799927, "learning_rate": 3.419284940411701e-05, "loss": 0.0117, "step": 1960 }, { "epoch": 1.155425219941349, "grad_norm": 1.2958227396011353, "learning_rate": 3.408450704225352e-05, "loss": 0.0142, "step": 1970 }, { "epoch": 1.1612903225806452, "grad_norm": 1.2160145044326782, "learning_rate": 3.397616468039003e-05, "loss": 0.0161, "step": 1980 }, { "epoch": 1.1671554252199414, "grad_norm": 0.735089898109436, "learning_rate": 3.3867822318526545e-05, "loss": 0.0125, "step": 1990 }, { "epoch": 1.1730205278592376, "grad_norm": 2.7560253143310547, "learning_rate": 3.3759479956663056e-05, "loss": 0.0088, "step": 2000 }, { "epoch": 1.1788856304985338, "grad_norm": 0.9203332662582397, "learning_rate": 3.365113759479957e-05, "loss": 0.0123, "step": 2010 }, { "epoch": 1.18475073313783, "grad_norm": 1.0320255756378174, "learning_rate": 3.354279523293608e-05, "loss": 0.0125, "step": 2020 }, { "epoch": 1.1906158357771262, "grad_norm": 1.9456615447998047, "learning_rate": 3.343445287107259e-05, "loss": 0.016, "step": 2030 }, { "epoch": 1.1964809384164223, "grad_norm": 0.907472550868988, "learning_rate": 3.33261105092091e-05, "loss": 0.0106, "step": 2040 }, { "epoch": 1.2023460410557185, "grad_norm": 0.8324399590492249, "learning_rate": 3.3217768147345614e-05, "loss": 0.0094, "step": 2050 }, { "epoch": 1.2082111436950147, "grad_norm": 0.7013159394264221, "learning_rate": 3.3109425785482126e-05, "loss": 0.0113, "step": 2060 }, { "epoch": 1.2140762463343109, "grad_norm": 0.7463244795799255, "learning_rate": 3.300108342361863e-05, "loss": 0.0111, "step": 2070 }, { "epoch": 1.219941348973607, "grad_norm": 0.5735973119735718, "learning_rate": 3.289274106175515e-05, "loss": 0.0101, "step": 2080 }, { "epoch": 1.2258064516129032, "grad_norm": 0.7958659529685974, "learning_rate": 3.278439869989166e-05, "loss": 0.0111, "step": 2090 }, { "epoch": 1.2316715542521994, "grad_norm": 2.5547595024108887, "learning_rate": 3.267605633802817e-05, "loss": 0.0093, "step": 2100 }, { "epoch": 1.2375366568914956, "grad_norm": 1.760979175567627, "learning_rate": 3.2567713976164684e-05, "loss": 0.0112, "step": 2110 }, { "epoch": 1.2434017595307918, "grad_norm": 3.6341629028320312, "learning_rate": 3.2459371614301196e-05, "loss": 0.0124, "step": 2120 }, { "epoch": 1.249266862170088, "grad_norm": 3.12435245513916, "learning_rate": 3.23510292524377e-05, "loss": 0.013, "step": 2130 }, { "epoch": 1.2551319648093842, "grad_norm": 2.499950885772705, "learning_rate": 3.224268689057421e-05, "loss": 0.0085, "step": 2140 }, { "epoch": 1.2609970674486803, "grad_norm": 3.02447247505188, "learning_rate": 3.2134344528710724e-05, "loss": 0.0103, "step": 2150 }, { "epoch": 1.2668621700879765, "grad_norm": 1.0911037921905518, "learning_rate": 3.202600216684724e-05, "loss": 0.0131, "step": 2160 }, { "epoch": 1.2727272727272727, "grad_norm": 1.6208757162094116, "learning_rate": 3.1917659804983754e-05, "loss": 0.0103, "step": 2170 }, { "epoch": 1.278592375366569, "grad_norm": 1.3921608924865723, "learning_rate": 3.1809317443120266e-05, "loss": 0.009, "step": 2180 }, { "epoch": 1.284457478005865, "grad_norm": 3.066075325012207, "learning_rate": 3.170097508125677e-05, "loss": 0.0092, "step": 2190 }, { "epoch": 1.2903225806451613, "grad_norm": 0.49130627512931824, "learning_rate": 3.159263271939328e-05, "loss": 0.0126, "step": 2200 }, { "epoch": 1.2961876832844574, "grad_norm": 1.3364100456237793, "learning_rate": 3.1484290357529794e-05, "loss": 0.0129, "step": 2210 }, { "epoch": 1.3020527859237536, "grad_norm": 2.61354660987854, "learning_rate": 3.1375947995666305e-05, "loss": 0.0119, "step": 2220 }, { "epoch": 1.3079178885630498, "grad_norm": 0.6985631585121155, "learning_rate": 3.1267605633802824e-05, "loss": 0.0106, "step": 2230 }, { "epoch": 1.313782991202346, "grad_norm": 3.9875142574310303, "learning_rate": 3.115926327193933e-05, "loss": 0.011, "step": 2240 }, { "epoch": 1.3196480938416422, "grad_norm": 1.963915467262268, "learning_rate": 3.105092091007584e-05, "loss": 0.0108, "step": 2250 }, { "epoch": 1.3255131964809383, "grad_norm": 0.29517853260040283, "learning_rate": 3.094257854821235e-05, "loss": 0.0092, "step": 2260 }, { "epoch": 1.3313782991202345, "grad_norm": 2.272747278213501, "learning_rate": 3.083423618634886e-05, "loss": 0.0112, "step": 2270 }, { "epoch": 1.3372434017595307, "grad_norm": 2.0269525051116943, "learning_rate": 3.0725893824485375e-05, "loss": 0.0107, "step": 2280 }, { "epoch": 1.343108504398827, "grad_norm": 1.2506771087646484, "learning_rate": 3.0617551462621887e-05, "loss": 0.0082, "step": 2290 }, { "epoch": 1.3489736070381233, "grad_norm": 1.7308708429336548, "learning_rate": 3.0509209100758395e-05, "loss": 0.0102, "step": 2300 }, { "epoch": 1.3548387096774195, "grad_norm": 2.230759859085083, "learning_rate": 3.0400866738894913e-05, "loss": 0.0079, "step": 2310 }, { "epoch": 1.3607038123167157, "grad_norm": 1.599900245666504, "learning_rate": 3.029252437703142e-05, "loss": 0.0095, "step": 2320 }, { "epoch": 1.3665689149560118, "grad_norm": 1.4094127416610718, "learning_rate": 3.0184182015167933e-05, "loss": 0.0061, "step": 2330 }, { "epoch": 1.372434017595308, "grad_norm": 1.2801002264022827, "learning_rate": 3.0075839653304445e-05, "loss": 0.0099, "step": 2340 }, { "epoch": 1.3782991202346042, "grad_norm": 2.3603005409240723, "learning_rate": 2.9967497291440956e-05, "loss": 0.0094, "step": 2350 }, { "epoch": 1.3841642228739004, "grad_norm": 2.6935067176818848, "learning_rate": 2.9859154929577465e-05, "loss": 0.0146, "step": 2360 }, { "epoch": 1.3900293255131966, "grad_norm": 1.099675178527832, "learning_rate": 2.9750812567713976e-05, "loss": 0.0073, "step": 2370 }, { "epoch": 1.3958944281524928, "grad_norm": 1.6118828058242798, "learning_rate": 2.9642470205850488e-05, "loss": 0.0079, "step": 2380 }, { "epoch": 1.401759530791789, "grad_norm": 0.4347597062587738, "learning_rate": 2.9534127843987003e-05, "loss": 0.0083, "step": 2390 }, { "epoch": 1.4076246334310851, "grad_norm": 0.7919577956199646, "learning_rate": 2.9425785482123514e-05, "loss": 0.0069, "step": 2400 }, { "epoch": 1.4134897360703813, "grad_norm": 0.8516518473625183, "learning_rate": 2.9317443120260023e-05, "loss": 0.0095, "step": 2410 }, { "epoch": 1.4193548387096775, "grad_norm": 2.754093885421753, "learning_rate": 2.9209100758396534e-05, "loss": 0.0155, "step": 2420 }, { "epoch": 1.4252199413489737, "grad_norm": 3.3311378955841064, "learning_rate": 2.9100758396533046e-05, "loss": 0.0147, "step": 2430 }, { "epoch": 1.4310850439882699, "grad_norm": 1.4020462036132812, "learning_rate": 2.8992416034669557e-05, "loss": 0.0083, "step": 2440 }, { "epoch": 1.436950146627566, "grad_norm": 1.8778059482574463, "learning_rate": 2.8884073672806066e-05, "loss": 0.0125, "step": 2450 }, { "epoch": 1.4428152492668622, "grad_norm": 0.8313784003257751, "learning_rate": 2.8775731310942577e-05, "loss": 0.0089, "step": 2460 }, { "epoch": 1.4486803519061584, "grad_norm": 1.4605448246002197, "learning_rate": 2.8667388949079092e-05, "loss": 0.0186, "step": 2470 }, { "epoch": 1.4545454545454546, "grad_norm": 5.201650619506836, "learning_rate": 2.8559046587215604e-05, "loss": 0.0149, "step": 2480 }, { "epoch": 1.4604105571847508, "grad_norm": 1.246205449104309, "learning_rate": 2.8450704225352116e-05, "loss": 0.013, "step": 2490 }, { "epoch": 1.466275659824047, "grad_norm": 1.1601160764694214, "learning_rate": 2.8342361863488627e-05, "loss": 0.0114, "step": 2500 }, { "epoch": 1.4721407624633431, "grad_norm": 3.673280954360962, "learning_rate": 2.8234019501625135e-05, "loss": 0.0099, "step": 2510 }, { "epoch": 1.4780058651026393, "grad_norm": 1.7461609840393066, "learning_rate": 2.8125677139761647e-05, "loss": 0.0108, "step": 2520 }, { "epoch": 1.4838709677419355, "grad_norm": 2.374141216278076, "learning_rate": 2.801733477789816e-05, "loss": 0.0099, "step": 2530 }, { "epoch": 1.4897360703812317, "grad_norm": 0.3864287734031677, "learning_rate": 2.7908992416034667e-05, "loss": 0.0081, "step": 2540 }, { "epoch": 1.4956011730205279, "grad_norm": 2.1756975650787354, "learning_rate": 2.7800650054171185e-05, "loss": 0.0082, "step": 2550 }, { "epoch": 1.501466275659824, "grad_norm": 1.4991483688354492, "learning_rate": 2.7692307692307694e-05, "loss": 0.0086, "step": 2560 }, { "epoch": 1.5073313782991202, "grad_norm": 1.5785051584243774, "learning_rate": 2.7583965330444205e-05, "loss": 0.0078, "step": 2570 }, { "epoch": 1.5131964809384164, "grad_norm": 0.8412874341011047, "learning_rate": 2.7475622968580717e-05, "loss": 0.0102, "step": 2580 }, { "epoch": 1.5190615835777126, "grad_norm": 1.034793734550476, "learning_rate": 2.736728060671723e-05, "loss": 0.0114, "step": 2590 }, { "epoch": 1.5249266862170088, "grad_norm": 0.5589306950569153, "learning_rate": 2.7258938244853737e-05, "loss": 0.0108, "step": 2600 }, { "epoch": 1.530791788856305, "grad_norm": 0.5028925538063049, "learning_rate": 2.7150595882990248e-05, "loss": 0.0107, "step": 2610 }, { "epoch": 1.5366568914956011, "grad_norm": 0.5622811913490295, "learning_rate": 2.704225352112676e-05, "loss": 0.0108, "step": 2620 }, { "epoch": 1.5425219941348973, "grad_norm": 1.4025564193725586, "learning_rate": 2.6933911159263275e-05, "loss": 0.0102, "step": 2630 }, { "epoch": 1.5483870967741935, "grad_norm": 2.0565545558929443, "learning_rate": 2.6825568797399786e-05, "loss": 0.0068, "step": 2640 }, { "epoch": 1.5542521994134897, "grad_norm": 0.45606544613838196, "learning_rate": 2.6717226435536298e-05, "loss": 0.0156, "step": 2650 }, { "epoch": 1.5601173020527859, "grad_norm": 0.5702988505363464, "learning_rate": 2.6608884073672806e-05, "loss": 0.0065, "step": 2660 }, { "epoch": 1.565982404692082, "grad_norm": 0.6669889092445374, "learning_rate": 2.6500541711809318e-05, "loss": 0.0157, "step": 2670 }, { "epoch": 1.5718475073313782, "grad_norm": 3.8566477298736572, "learning_rate": 2.639219934994583e-05, "loss": 0.0119, "step": 2680 }, { "epoch": 1.5777126099706744, "grad_norm": 1.1893422603607178, "learning_rate": 2.6283856988082338e-05, "loss": 0.0053, "step": 2690 }, { "epoch": 1.5835777126099706, "grad_norm": 0.36327511072158813, "learning_rate": 2.6175514626218856e-05, "loss": 0.005, "step": 2700 }, { "epoch": 1.5894428152492668, "grad_norm": 0.6985073685646057, "learning_rate": 2.6067172264355368e-05, "loss": 0.0093, "step": 2710 }, { "epoch": 1.595307917888563, "grad_norm": 1.7380647659301758, "learning_rate": 2.5958829902491876e-05, "loss": 0.0062, "step": 2720 }, { "epoch": 1.6011730205278591, "grad_norm": 0.3573593199253082, "learning_rate": 2.5850487540628388e-05, "loss": 0.0077, "step": 2730 }, { "epoch": 1.6070381231671553, "grad_norm": 3.5947067737579346, "learning_rate": 2.57421451787649e-05, "loss": 0.0103, "step": 2740 }, { "epoch": 1.6129032258064515, "grad_norm": 1.3845021724700928, "learning_rate": 2.5633802816901408e-05, "loss": 0.0078, "step": 2750 }, { "epoch": 1.6187683284457477, "grad_norm": 0.6750550270080566, "learning_rate": 2.552546045503792e-05, "loss": 0.0069, "step": 2760 }, { "epoch": 1.6246334310850439, "grad_norm": 0.5807213187217712, "learning_rate": 2.541711809317443e-05, "loss": 0.0062, "step": 2770 }, { "epoch": 1.63049853372434, "grad_norm": 0.4663524925708771, "learning_rate": 2.5308775731310946e-05, "loss": 0.01, "step": 2780 }, { "epoch": 1.6363636363636362, "grad_norm": 0.9029988050460815, "learning_rate": 2.5200433369447457e-05, "loss": 0.0066, "step": 2790 }, { "epoch": 1.6422287390029324, "grad_norm": 0.5071028470993042, "learning_rate": 2.509209100758397e-05, "loss": 0.0091, "step": 2800 }, { "epoch": 1.6480938416422286, "grad_norm": 1.9077457189559937, "learning_rate": 2.4983748645720477e-05, "loss": 0.0121, "step": 2810 }, { "epoch": 1.6539589442815248, "grad_norm": 0.7507709860801697, "learning_rate": 2.487540628385699e-05, "loss": 0.0122, "step": 2820 }, { "epoch": 1.659824046920821, "grad_norm": 0.7139337062835693, "learning_rate": 2.47670639219935e-05, "loss": 0.0058, "step": 2830 }, { "epoch": 1.6656891495601172, "grad_norm": 2.0261781215667725, "learning_rate": 2.4658721560130012e-05, "loss": 0.0078, "step": 2840 }, { "epoch": 1.6715542521994133, "grad_norm": 0.9489262700080872, "learning_rate": 2.4550379198266524e-05, "loss": 0.0119, "step": 2850 }, { "epoch": 1.6774193548387095, "grad_norm": 0.3388541340827942, "learning_rate": 2.4442036836403035e-05, "loss": 0.0053, "step": 2860 }, { "epoch": 1.6832844574780057, "grad_norm": 0.9326663017272949, "learning_rate": 2.4333694474539544e-05, "loss": 0.008, "step": 2870 }, { "epoch": 1.689149560117302, "grad_norm": 1.6251760721206665, "learning_rate": 2.422535211267606e-05, "loss": 0.0088, "step": 2880 }, { "epoch": 1.6950146627565983, "grad_norm": 0.45517489314079285, "learning_rate": 2.411700975081257e-05, "loss": 0.0114, "step": 2890 }, { "epoch": 1.7008797653958945, "grad_norm": 1.6923969984054565, "learning_rate": 2.400866738894908e-05, "loss": 0.0082, "step": 2900 }, { "epoch": 1.7067448680351907, "grad_norm": 1.6740838289260864, "learning_rate": 2.390032502708559e-05, "loss": 0.0067, "step": 2910 }, { "epoch": 1.7126099706744868, "grad_norm": 1.280557632446289, "learning_rate": 2.3791982665222105e-05, "loss": 0.0072, "step": 2920 }, { "epoch": 1.718475073313783, "grad_norm": 3.185971260070801, "learning_rate": 2.3683640303358613e-05, "loss": 0.0102, "step": 2930 }, { "epoch": 1.7243401759530792, "grad_norm": 0.6263673901557922, "learning_rate": 2.3575297941495125e-05, "loss": 0.0057, "step": 2940 }, { "epoch": 1.7302052785923754, "grad_norm": 0.5889501571655273, "learning_rate": 2.3466955579631637e-05, "loss": 0.0064, "step": 2950 }, { "epoch": 1.7360703812316716, "grad_norm": 1.5832338333129883, "learning_rate": 2.3358613217768148e-05, "loss": 0.0124, "step": 2960 }, { "epoch": 1.7419354838709677, "grad_norm": 1.794831395149231, "learning_rate": 2.325027085590466e-05, "loss": 0.0085, "step": 2970 }, { "epoch": 1.747800586510264, "grad_norm": 0.6386451125144958, "learning_rate": 2.314192849404117e-05, "loss": 0.0069, "step": 2980 }, { "epoch": 1.7536656891495601, "grad_norm": 1.312626600265503, "learning_rate": 2.3033586132177683e-05, "loss": 0.0064, "step": 2990 }, { "epoch": 1.7595307917888563, "grad_norm": 1.8232412338256836, "learning_rate": 2.2925243770314195e-05, "loss": 0.0066, "step": 3000 }, { "epoch": 1.7653958944281525, "grad_norm": 0.3552861213684082, "learning_rate": 2.2816901408450706e-05, "loss": 0.0058, "step": 3010 }, { "epoch": 1.7712609970674487, "grad_norm": 1.736221194267273, "learning_rate": 2.2708559046587215e-05, "loss": 0.0077, "step": 3020 }, { "epoch": 1.7771260997067448, "grad_norm": 0.21436937153339386, "learning_rate": 2.2600216684723726e-05, "loss": 0.0059, "step": 3030 }, { "epoch": 1.782991202346041, "grad_norm": 0.6992660164833069, "learning_rate": 2.249187432286024e-05, "loss": 0.009, "step": 3040 }, { "epoch": 1.7888563049853372, "grad_norm": 0.7840091586112976, "learning_rate": 2.238353196099675e-05, "loss": 0.0067, "step": 3050 }, { "epoch": 1.7947214076246334, "grad_norm": 2.9690425395965576, "learning_rate": 2.227518959913326e-05, "loss": 0.0072, "step": 3060 }, { "epoch": 1.8005865102639296, "grad_norm": 1.8144841194152832, "learning_rate": 2.2166847237269773e-05, "loss": 0.007, "step": 3070 }, { "epoch": 1.8064516129032258, "grad_norm": 0.38126352429389954, "learning_rate": 2.2058504875406284e-05, "loss": 0.0072, "step": 3080 }, { "epoch": 1.812316715542522, "grad_norm": 0.4111306369304657, "learning_rate": 2.1950162513542796e-05, "loss": 0.008, "step": 3090 }, { "epoch": 1.8181818181818183, "grad_norm": 0.7458495497703552, "learning_rate": 2.1841820151679307e-05, "loss": 0.0063, "step": 3100 }, { "epoch": 1.8240469208211145, "grad_norm": 0.7662573456764221, "learning_rate": 2.173347778981582e-05, "loss": 0.0063, "step": 3110 }, { "epoch": 1.8299120234604107, "grad_norm": 0.8057358860969543, "learning_rate": 2.162513542795233e-05, "loss": 0.0083, "step": 3120 }, { "epoch": 1.835777126099707, "grad_norm": 2.0041463375091553, "learning_rate": 2.1516793066088842e-05, "loss": 0.0074, "step": 3130 }, { "epoch": 1.841642228739003, "grad_norm": 0.4772699475288391, "learning_rate": 2.1408450704225354e-05, "loss": 0.0102, "step": 3140 }, { "epoch": 1.8475073313782993, "grad_norm": 1.6266963481903076, "learning_rate": 2.1300108342361866e-05, "loss": 0.0099, "step": 3150 }, { "epoch": 1.8533724340175954, "grad_norm": 0.8952119946479797, "learning_rate": 2.1191765980498377e-05, "loss": 0.0051, "step": 3160 }, { "epoch": 1.8592375366568916, "grad_norm": 2.7058868408203125, "learning_rate": 2.108342361863489e-05, "loss": 0.0085, "step": 3170 }, { "epoch": 1.8651026392961878, "grad_norm": 1.5164512395858765, "learning_rate": 2.0975081256771397e-05, "loss": 0.0072, "step": 3180 }, { "epoch": 1.870967741935484, "grad_norm": 0.37659189105033875, "learning_rate": 2.0866738894907912e-05, "loss": 0.007, "step": 3190 }, { "epoch": 1.8768328445747802, "grad_norm": 0.7300402522087097, "learning_rate": 2.075839653304442e-05, "loss": 0.0083, "step": 3200 }, { "epoch": 1.8826979472140764, "grad_norm": 0.4265812933444977, "learning_rate": 2.0650054171180932e-05, "loss": 0.0094, "step": 3210 }, { "epoch": 1.8885630498533725, "grad_norm": 0.6551434993743896, "learning_rate": 2.0541711809317444e-05, "loss": 0.0043, "step": 3220 }, { "epoch": 1.8944281524926687, "grad_norm": 0.5182037353515625, "learning_rate": 2.0433369447453955e-05, "loss": 0.0046, "step": 3230 }, { "epoch": 1.900293255131965, "grad_norm": 0.5181695818901062, "learning_rate": 2.0325027085590467e-05, "loss": 0.0054, "step": 3240 }, { "epoch": 1.906158357771261, "grad_norm": 0.30220693349838257, "learning_rate": 2.021668472372698e-05, "loss": 0.0031, "step": 3250 }, { "epoch": 1.9120234604105573, "grad_norm": 0.4141380190849304, "learning_rate": 2.010834236186349e-05, "loss": 0.0041, "step": 3260 }, { "epoch": 1.9178885630498534, "grad_norm": 1.5024000406265259, "learning_rate": 2e-05, "loss": 0.0036, "step": 3270 }, { "epoch": 1.9237536656891496, "grad_norm": 0.37273481488227844, "learning_rate": 1.9891657638136513e-05, "loss": 0.0041, "step": 3280 }, { "epoch": 1.9296187683284458, "grad_norm": 0.7267457246780396, "learning_rate": 1.9783315276273025e-05, "loss": 0.0086, "step": 3290 }, { "epoch": 1.935483870967742, "grad_norm": 1.0580945014953613, "learning_rate": 1.9674972914409533e-05, "loss": 0.0049, "step": 3300 }, { "epoch": 1.9413489736070382, "grad_norm": 0.5923478603363037, "learning_rate": 1.9566630552546048e-05, "loss": 0.0074, "step": 3310 }, { "epoch": 1.9472140762463344, "grad_norm": 2.4155588150024414, "learning_rate": 1.945828819068256e-05, "loss": 0.0104, "step": 3320 }, { "epoch": 1.9530791788856305, "grad_norm": 2.4885783195495605, "learning_rate": 1.9349945828819068e-05, "loss": 0.0059, "step": 3330 }, { "epoch": 1.9589442815249267, "grad_norm": 1.2375839948654175, "learning_rate": 1.924160346695558e-05, "loss": 0.0108, "step": 3340 }, { "epoch": 1.964809384164223, "grad_norm": 2.7441036701202393, "learning_rate": 1.9133261105092095e-05, "loss": 0.0055, "step": 3350 }, { "epoch": 1.970674486803519, "grad_norm": 1.8821948766708374, "learning_rate": 1.9024918743228603e-05, "loss": 0.0043, "step": 3360 }, { "epoch": 1.9765395894428153, "grad_norm": 1.3677663803100586, "learning_rate": 1.8916576381365114e-05, "loss": 0.0047, "step": 3370 }, { "epoch": 1.9824046920821115, "grad_norm": 0.37202900648117065, "learning_rate": 1.8808234019501626e-05, "loss": 0.0043, "step": 3380 }, { "epoch": 1.9882697947214076, "grad_norm": 1.2205904722213745, "learning_rate": 1.8699891657638138e-05, "loss": 0.0044, "step": 3390 }, { "epoch": 1.9941348973607038, "grad_norm": 1.4114491939544678, "learning_rate": 1.859154929577465e-05, "loss": 0.0043, "step": 3400 }, { "epoch": 2.0, "grad_norm": 0.8728663325309753, "learning_rate": 1.848320693391116e-05, "loss": 0.0041, "step": 3410 }, { "epoch": 2.005865102639296, "grad_norm": 1.2277451753616333, "learning_rate": 1.837486457204767e-05, "loss": 0.0047, "step": 3420 }, { "epoch": 2.0117302052785924, "grad_norm": 0.4225451946258545, "learning_rate": 1.8266522210184184e-05, "loss": 0.0025, "step": 3430 }, { "epoch": 2.0175953079178885, "grad_norm": 0.6460304856300354, "learning_rate": 1.8158179848320696e-05, "loss": 0.0035, "step": 3440 }, { "epoch": 2.0234604105571847, "grad_norm": 0.5473723411560059, "learning_rate": 1.8049837486457204e-05, "loss": 0.0037, "step": 3450 }, { "epoch": 2.029325513196481, "grad_norm": 2.4837288856506348, "learning_rate": 1.7941495124593716e-05, "loss": 0.0062, "step": 3460 }, { "epoch": 2.035190615835777, "grad_norm": 0.5354294180870056, "learning_rate": 1.783315276273023e-05, "loss": 0.0051, "step": 3470 }, { "epoch": 2.0410557184750733, "grad_norm": 0.6833767294883728, "learning_rate": 1.772481040086674e-05, "loss": 0.0026, "step": 3480 }, { "epoch": 2.0469208211143695, "grad_norm": 1.8108445405960083, "learning_rate": 1.761646803900325e-05, "loss": 0.0046, "step": 3490 }, { "epoch": 2.0527859237536656, "grad_norm": 0.46405455470085144, "learning_rate": 1.7508125677139762e-05, "loss": 0.0036, "step": 3500 }, { "epoch": 2.058651026392962, "grad_norm": 1.3793003559112549, "learning_rate": 1.7399783315276274e-05, "loss": 0.0049, "step": 3510 }, { "epoch": 2.064516129032258, "grad_norm": 1.083612084388733, "learning_rate": 1.7291440953412785e-05, "loss": 0.0035, "step": 3520 }, { "epoch": 2.070381231671554, "grad_norm": 1.7469717264175415, "learning_rate": 1.7183098591549297e-05, "loss": 0.0035, "step": 3530 }, { "epoch": 2.0762463343108504, "grad_norm": 1.8320294618606567, "learning_rate": 1.707475622968581e-05, "loss": 0.0046, "step": 3540 }, { "epoch": 2.0821114369501466, "grad_norm": 0.7071532011032104, "learning_rate": 1.696641386782232e-05, "loss": 0.0041, "step": 3550 }, { "epoch": 2.0879765395894427, "grad_norm": 0.39700040221214294, "learning_rate": 1.6858071505958832e-05, "loss": 0.0029, "step": 3560 }, { "epoch": 2.093841642228739, "grad_norm": 1.1924680471420288, "learning_rate": 1.674972914409534e-05, "loss": 0.0071, "step": 3570 }, { "epoch": 2.099706744868035, "grad_norm": 1.3607029914855957, "learning_rate": 1.6641386782231855e-05, "loss": 0.0126, "step": 3580 }, { "epoch": 2.1055718475073313, "grad_norm": 0.5861091017723083, "learning_rate": 1.6533044420368367e-05, "loss": 0.0037, "step": 3590 }, { "epoch": 2.1114369501466275, "grad_norm": 0.22819814085960388, "learning_rate": 1.6424702058504875e-05, "loss": 0.0026, "step": 3600 }, { "epoch": 2.1173020527859236, "grad_norm": 0.15041030943393707, "learning_rate": 1.6316359696641387e-05, "loss": 0.0034, "step": 3610 }, { "epoch": 2.12316715542522, "grad_norm": 0.5198802947998047, "learning_rate": 1.62080173347779e-05, "loss": 0.0032, "step": 3620 }, { "epoch": 2.129032258064516, "grad_norm": 0.1846199780702591, "learning_rate": 1.609967497291441e-05, "loss": 0.0029, "step": 3630 }, { "epoch": 2.134897360703812, "grad_norm": 0.6416236758232117, "learning_rate": 1.599133261105092e-05, "loss": 0.0033, "step": 3640 }, { "epoch": 2.1407624633431084, "grad_norm": 0.46757569909095764, "learning_rate": 1.5882990249187433e-05, "loss": 0.0033, "step": 3650 }, { "epoch": 2.1466275659824046, "grad_norm": 2.260544538497925, "learning_rate": 1.5774647887323945e-05, "loss": 0.004, "step": 3660 }, { "epoch": 2.1524926686217007, "grad_norm": 0.4333725869655609, "learning_rate": 1.5666305525460456e-05, "loss": 0.0026, "step": 3670 }, { "epoch": 2.158357771260997, "grad_norm": 0.7353067398071289, "learning_rate": 1.5557963163596968e-05, "loss": 0.003, "step": 3680 }, { "epoch": 2.164222873900293, "grad_norm": 0.9456650614738464, "learning_rate": 1.5449620801733476e-05, "loss": 0.0038, "step": 3690 }, { "epoch": 2.1700879765395893, "grad_norm": 0.4781268239021301, "learning_rate": 1.534127843986999e-05, "loss": 0.0043, "step": 3700 }, { "epoch": 2.1759530791788855, "grad_norm": 0.488057404756546, "learning_rate": 1.5232936078006501e-05, "loss": 0.0025, "step": 3710 }, { "epoch": 2.1818181818181817, "grad_norm": 0.2408045530319214, "learning_rate": 1.5124593716143013e-05, "loss": 0.0022, "step": 3720 }, { "epoch": 2.187683284457478, "grad_norm": 0.3382255434989929, "learning_rate": 1.5016251354279523e-05, "loss": 0.0024, "step": 3730 }, { "epoch": 2.193548387096774, "grad_norm": 0.3861747682094574, "learning_rate": 1.4907908992416036e-05, "loss": 0.0028, "step": 3740 }, { "epoch": 2.19941348973607, "grad_norm": 0.45839062333106995, "learning_rate": 1.4799566630552548e-05, "loss": 0.0033, "step": 3750 }, { "epoch": 2.2052785923753664, "grad_norm": 0.7637222409248352, "learning_rate": 1.4691224268689057e-05, "loss": 0.0023, "step": 3760 }, { "epoch": 2.2111436950146626, "grad_norm": 0.710662841796875, "learning_rate": 1.4582881906825569e-05, "loss": 0.0045, "step": 3770 }, { "epoch": 2.2170087976539588, "grad_norm": 1.2684130668640137, "learning_rate": 1.4474539544962082e-05, "loss": 0.0039, "step": 3780 }, { "epoch": 2.222873900293255, "grad_norm": 0.8279300928115845, "learning_rate": 1.4366197183098592e-05, "loss": 0.0032, "step": 3790 }, { "epoch": 2.228739002932551, "grad_norm": 1.0345526933670044, "learning_rate": 1.4257854821235104e-05, "loss": 0.003, "step": 3800 }, { "epoch": 2.2346041055718473, "grad_norm": 0.5127742290496826, "learning_rate": 1.4149512459371614e-05, "loss": 0.0032, "step": 3810 }, { "epoch": 2.2404692082111435, "grad_norm": 0.7230274677276611, "learning_rate": 1.4041170097508127e-05, "loss": 0.006, "step": 3820 }, { "epoch": 2.2463343108504397, "grad_norm": 0.7685052156448364, "learning_rate": 1.3932827735644637e-05, "loss": 0.0027, "step": 3830 }, { "epoch": 2.252199413489736, "grad_norm": 1.4992603063583374, "learning_rate": 1.3824485373781149e-05, "loss": 0.0041, "step": 3840 }, { "epoch": 2.258064516129032, "grad_norm": 0.30322280526161194, "learning_rate": 1.3716143011917659e-05, "loss": 0.0024, "step": 3850 }, { "epoch": 2.263929618768328, "grad_norm": 0.2453003227710724, "learning_rate": 1.3607800650054172e-05, "loss": 0.0022, "step": 3860 }, { "epoch": 2.2697947214076244, "grad_norm": 1.1497894525527954, "learning_rate": 1.3499458288190684e-05, "loss": 0.0024, "step": 3870 }, { "epoch": 2.2756598240469206, "grad_norm": 1.0339840650558472, "learning_rate": 1.3391115926327194e-05, "loss": 0.0027, "step": 3880 }, { "epoch": 2.281524926686217, "grad_norm": 1.244283676147461, "learning_rate": 1.3282773564463705e-05, "loss": 0.0033, "step": 3890 }, { "epoch": 2.2873900293255134, "grad_norm": 0.17964577674865723, "learning_rate": 1.3174431202600218e-05, "loss": 0.003, "step": 3900 }, { "epoch": 2.2932551319648096, "grad_norm": 0.437898188829422, "learning_rate": 1.3066088840736728e-05, "loss": 0.0025, "step": 3910 }, { "epoch": 2.2991202346041058, "grad_norm": 0.6417920589447021, "learning_rate": 1.295774647887324e-05, "loss": 0.0022, "step": 3920 }, { "epoch": 2.304985337243402, "grad_norm": 0.9770957827568054, "learning_rate": 1.284940411700975e-05, "loss": 0.0042, "step": 3930 }, { "epoch": 2.310850439882698, "grad_norm": 0.2995135486125946, "learning_rate": 1.2741061755146263e-05, "loss": 0.0031, "step": 3940 }, { "epoch": 2.3167155425219943, "grad_norm": 0.23019449412822723, "learning_rate": 1.2632719393282775e-05, "loss": 0.0038, "step": 3950 }, { "epoch": 2.3225806451612905, "grad_norm": 1.9633790254592896, "learning_rate": 1.2524377031419285e-05, "loss": 0.0052, "step": 3960 }, { "epoch": 2.3284457478005867, "grad_norm": 0.5719003081321716, "learning_rate": 1.2416034669555796e-05, "loss": 0.0033, "step": 3970 }, { "epoch": 2.334310850439883, "grad_norm": 0.4849315881729126, "learning_rate": 1.230769230769231e-05, "loss": 0.0029, "step": 3980 }, { "epoch": 2.340175953079179, "grad_norm": 0.5165572166442871, "learning_rate": 1.219934994582882e-05, "loss": 0.0032, "step": 3990 }, { "epoch": 2.346041055718475, "grad_norm": 6.257429599761963, "learning_rate": 1.2091007583965331e-05, "loss": 0.0051, "step": 4000 }, { "epoch": 2.3519061583577714, "grad_norm": 0.1021239385008812, "learning_rate": 1.1982665222101843e-05, "loss": 0.0029, "step": 4010 }, { "epoch": 2.3577712609970676, "grad_norm": 0.5569911599159241, "learning_rate": 1.1874322860238355e-05, "loss": 0.0028, "step": 4020 }, { "epoch": 2.3636363636363638, "grad_norm": 0.21338407695293427, "learning_rate": 1.1765980498374864e-05, "loss": 0.0023, "step": 4030 }, { "epoch": 2.36950146627566, "grad_norm": 0.9345069527626038, "learning_rate": 1.1657638136511378e-05, "loss": 0.0038, "step": 4040 }, { "epoch": 2.375366568914956, "grad_norm": 1.0866254568099976, "learning_rate": 1.1549295774647888e-05, "loss": 0.0036, "step": 4050 }, { "epoch": 2.3812316715542523, "grad_norm": 0.9882946014404297, "learning_rate": 1.14409534127844e-05, "loss": 0.0036, "step": 4060 }, { "epoch": 2.3870967741935485, "grad_norm": 0.50217604637146, "learning_rate": 1.1332611050920911e-05, "loss": 0.0025, "step": 4070 }, { "epoch": 2.3929618768328447, "grad_norm": 1.3795546293258667, "learning_rate": 1.1224268689057423e-05, "loss": 0.0042, "step": 4080 }, { "epoch": 2.398826979472141, "grad_norm": 0.7706465125083923, "learning_rate": 1.1115926327193932e-05, "loss": 0.0027, "step": 4090 }, { "epoch": 2.404692082111437, "grad_norm": 0.30888229608535767, "learning_rate": 1.1007583965330446e-05, "loss": 0.0027, "step": 4100 }, { "epoch": 2.410557184750733, "grad_norm": 0.16666728258132935, "learning_rate": 1.0899241603466956e-05, "loss": 0.0025, "step": 4110 }, { "epoch": 2.4164222873900294, "grad_norm": 0.40352991223335266, "learning_rate": 1.0790899241603467e-05, "loss": 0.0023, "step": 4120 }, { "epoch": 2.4222873900293256, "grad_norm": 0.7607168555259705, "learning_rate": 1.0682556879739979e-05, "loss": 0.0037, "step": 4130 }, { "epoch": 2.4281524926686218, "grad_norm": 0.6904723644256592, "learning_rate": 1.057421451787649e-05, "loss": 0.0033, "step": 4140 }, { "epoch": 2.434017595307918, "grad_norm": 0.4458531141281128, "learning_rate": 1.0465872156013e-05, "loss": 0.0027, "step": 4150 }, { "epoch": 2.439882697947214, "grad_norm": 0.9180742502212524, "learning_rate": 1.0357529794149514e-05, "loss": 0.0023, "step": 4160 }, { "epoch": 2.4457478005865103, "grad_norm": 0.2105313539505005, "learning_rate": 1.0249187432286024e-05, "loss": 0.0033, "step": 4170 }, { "epoch": 2.4516129032258065, "grad_norm": 0.45809683203697205, "learning_rate": 1.0140845070422535e-05, "loss": 0.0025, "step": 4180 }, { "epoch": 2.4574780058651027, "grad_norm": 0.8669016361236572, "learning_rate": 1.0032502708559047e-05, "loss": 0.0043, "step": 4190 }, { "epoch": 2.463343108504399, "grad_norm": 0.4931950569152832, "learning_rate": 9.924160346695559e-06, "loss": 0.0021, "step": 4200 }, { "epoch": 2.469208211143695, "grad_norm": 0.13325130939483643, "learning_rate": 9.81581798483207e-06, "loss": 0.0028, "step": 4210 }, { "epoch": 2.4750733137829912, "grad_norm": 0.5872472524642944, "learning_rate": 9.707475622968582e-06, "loss": 0.0024, "step": 4220 }, { "epoch": 2.4809384164222874, "grad_norm": 1.469139814376831, "learning_rate": 9.599133261105092e-06, "loss": 0.0046, "step": 4230 }, { "epoch": 2.4868035190615836, "grad_norm": 1.5533734560012817, "learning_rate": 9.490790899241603e-06, "loss": 0.0051, "step": 4240 }, { "epoch": 2.4926686217008798, "grad_norm": 0.7671976089477539, "learning_rate": 9.382448537378115e-06, "loss": 0.0027, "step": 4250 }, { "epoch": 2.498533724340176, "grad_norm": 0.3293214440345764, "learning_rate": 9.274106175514627e-06, "loss": 0.0037, "step": 4260 }, { "epoch": 2.504398826979472, "grad_norm": 0.6871675848960876, "learning_rate": 9.165763813651138e-06, "loss": 0.002, "step": 4270 }, { "epoch": 2.5102639296187683, "grad_norm": 0.7354288101196289, "learning_rate": 9.05742145178765e-06, "loss": 0.0028, "step": 4280 }, { "epoch": 2.5161290322580645, "grad_norm": 0.7671726942062378, "learning_rate": 8.94907908992416e-06, "loss": 0.0022, "step": 4290 }, { "epoch": 2.5219941348973607, "grad_norm": 1.1531054973602295, "learning_rate": 8.840736728060673e-06, "loss": 0.0032, "step": 4300 }, { "epoch": 2.527859237536657, "grad_norm": 0.648115873336792, "learning_rate": 8.732394366197183e-06, "loss": 0.0026, "step": 4310 }, { "epoch": 2.533724340175953, "grad_norm": 0.579592764377594, "learning_rate": 8.624052004333695e-06, "loss": 0.0017, "step": 4320 }, { "epoch": 2.5395894428152492, "grad_norm": 1.3247286081314087, "learning_rate": 8.515709642470206e-06, "loss": 0.0039, "step": 4330 }, { "epoch": 2.5454545454545454, "grad_norm": 0.200743168592453, "learning_rate": 8.407367280606718e-06, "loss": 0.0037, "step": 4340 }, { "epoch": 2.5513196480938416, "grad_norm": 0.6144959926605225, "learning_rate": 8.299024918743228e-06, "loss": 0.0026, "step": 4350 }, { "epoch": 2.557184750733138, "grad_norm": 0.6242021918296814, "learning_rate": 8.190682556879741e-06, "loss": 0.0028, "step": 4360 }, { "epoch": 2.563049853372434, "grad_norm": 0.5484371185302734, "learning_rate": 8.082340195016251e-06, "loss": 0.0048, "step": 4370 }, { "epoch": 2.56891495601173, "grad_norm": 0.181168332695961, "learning_rate": 7.973997833152763e-06, "loss": 0.0026, "step": 4380 }, { "epoch": 2.5747800586510263, "grad_norm": 0.9735661745071411, "learning_rate": 7.865655471289274e-06, "loss": 0.0035, "step": 4390 }, { "epoch": 2.5806451612903225, "grad_norm": 0.4242919683456421, "learning_rate": 7.757313109425786e-06, "loss": 0.0025, "step": 4400 }, { "epoch": 2.5865102639296187, "grad_norm": 0.313275009393692, "learning_rate": 7.648970747562296e-06, "loss": 0.0024, "step": 4410 }, { "epoch": 2.592375366568915, "grad_norm": 0.3656627833843231, "learning_rate": 7.540628385698808e-06, "loss": 0.0029, "step": 4420 }, { "epoch": 2.598240469208211, "grad_norm": 0.2241465449333191, "learning_rate": 7.432286023835321e-06, "loss": 0.002, "step": 4430 }, { "epoch": 2.6041055718475072, "grad_norm": 0.3788506090641022, "learning_rate": 7.3239436619718316e-06, "loss": 0.002, "step": 4440 }, { "epoch": 2.6099706744868034, "grad_norm": 0.2104683667421341, "learning_rate": 7.215601300108343e-06, "loss": 0.0021, "step": 4450 }, { "epoch": 2.6158357771260996, "grad_norm": 0.6747612953186035, "learning_rate": 7.107258938244854e-06, "loss": 0.0023, "step": 4460 }, { "epoch": 2.621700879765396, "grad_norm": 0.5167836546897888, "learning_rate": 6.9989165763813664e-06, "loss": 0.002, "step": 4470 }, { "epoch": 2.627565982404692, "grad_norm": 0.4595435857772827, "learning_rate": 6.890574214517876e-06, "loss": 0.0018, "step": 4480 }, { "epoch": 2.633431085043988, "grad_norm": 0.38868948817253113, "learning_rate": 6.782231852654389e-06, "loss": 0.0074, "step": 4490 }, { "epoch": 2.6392961876832843, "grad_norm": 1.027677059173584, "learning_rate": 6.6738894907909e-06, "loss": 0.0018, "step": 4500 }, { "epoch": 2.6451612903225805, "grad_norm": 0.3188434839248657, "learning_rate": 6.565547128927411e-06, "loss": 0.0017, "step": 4510 }, { "epoch": 2.6510263929618767, "grad_norm": 0.3385601043701172, "learning_rate": 6.457204767063922e-06, "loss": 0.0025, "step": 4520 }, { "epoch": 2.656891495601173, "grad_norm": 0.8369510173797607, "learning_rate": 6.3488624052004345e-06, "loss": 0.0021, "step": 4530 }, { "epoch": 2.662756598240469, "grad_norm": 0.32399484515190125, "learning_rate": 6.240520043336945e-06, "loss": 0.002, "step": 4540 }, { "epoch": 2.6686217008797652, "grad_norm": 0.48848479986190796, "learning_rate": 6.132177681473456e-06, "loss": 0.002, "step": 4550 }, { "epoch": 2.6744868035190614, "grad_norm": 0.4203287661075592, "learning_rate": 6.023835319609968e-06, "loss": 0.0024, "step": 4560 }, { "epoch": 2.6803519061583576, "grad_norm": 0.17682945728302002, "learning_rate": 5.915492957746479e-06, "loss": 0.0023, "step": 4570 }, { "epoch": 2.686217008797654, "grad_norm": 0.27645328640937805, "learning_rate": 5.80715059588299e-06, "loss": 0.0016, "step": 4580 }, { "epoch": 2.6920821114369504, "grad_norm": 0.341978520154953, "learning_rate": 5.698808234019502e-06, "loss": 0.0024, "step": 4590 }, { "epoch": 2.6979472140762466, "grad_norm": 0.6040353178977966, "learning_rate": 5.590465872156013e-06, "loss": 0.0029, "step": 4600 }, { "epoch": 2.703812316715543, "grad_norm": 0.4571681320667267, "learning_rate": 5.482123510292524e-06, "loss": 0.0038, "step": 4610 }, { "epoch": 2.709677419354839, "grad_norm": 0.6993141174316406, "learning_rate": 5.373781148429036e-06, "loss": 0.0029, "step": 4620 }, { "epoch": 2.715542521994135, "grad_norm": 0.45035046339035034, "learning_rate": 5.265438786565547e-06, "loss": 0.0018, "step": 4630 }, { "epoch": 2.7214076246334313, "grad_norm": 0.23612183332443237, "learning_rate": 5.157096424702059e-06, "loss": 0.0021, "step": 4640 }, { "epoch": 2.7272727272727275, "grad_norm": 0.5207453370094299, "learning_rate": 5.0487540628385705e-06, "loss": 0.0024, "step": 4650 }, { "epoch": 2.7331378299120237, "grad_norm": 0.7961679100990295, "learning_rate": 4.940411700975082e-06, "loss": 0.0024, "step": 4660 }, { "epoch": 2.73900293255132, "grad_norm": 0.42311325669288635, "learning_rate": 4.832069339111593e-06, "loss": 0.0016, "step": 4670 }, { "epoch": 2.744868035190616, "grad_norm": 0.26033857464790344, "learning_rate": 4.7237269772481045e-06, "loss": 0.0027, "step": 4680 }, { "epoch": 2.7507331378299122, "grad_norm": 0.2687263488769531, "learning_rate": 4.615384615384616e-06, "loss": 0.0024, "step": 4690 }, { "epoch": 2.7565982404692084, "grad_norm": 0.1565217226743698, "learning_rate": 4.507042253521127e-06, "loss": 0.002, "step": 4700 }, { "epoch": 2.7624633431085046, "grad_norm": 0.3572985827922821, "learning_rate": 4.3986998916576385e-06, "loss": 0.0024, "step": 4710 }, { "epoch": 2.768328445747801, "grad_norm": 0.7106755971908569, "learning_rate": 4.29035752979415e-06, "loss": 0.0015, "step": 4720 }, { "epoch": 2.774193548387097, "grad_norm": 0.38818755745887756, "learning_rate": 4.182015167930661e-06, "loss": 0.0017, "step": 4730 }, { "epoch": 2.780058651026393, "grad_norm": 0.19889351725578308, "learning_rate": 4.0736728060671726e-06, "loss": 0.0031, "step": 4740 }, { "epoch": 2.7859237536656893, "grad_norm": 0.7225050330162048, "learning_rate": 3.965330444203684e-06, "loss": 0.0021, "step": 4750 }, { "epoch": 2.7917888563049855, "grad_norm": 0.5237097144126892, "learning_rate": 3.856988082340195e-06, "loss": 0.0016, "step": 4760 }, { "epoch": 2.7976539589442817, "grad_norm": 0.3217989504337311, "learning_rate": 3.7486457204767066e-06, "loss": 0.0037, "step": 4770 }, { "epoch": 2.803519061583578, "grad_norm": 0.3693365454673767, "learning_rate": 3.640303358613218e-06, "loss": 0.0019, "step": 4780 }, { "epoch": 2.809384164222874, "grad_norm": 0.7291551232337952, "learning_rate": 3.5319609967497294e-06, "loss": 0.0037, "step": 4790 }, { "epoch": 2.8152492668621703, "grad_norm": 0.5343610644340515, "learning_rate": 3.4236186348862406e-06, "loss": 0.0056, "step": 4800 }, { "epoch": 2.8211143695014664, "grad_norm": 0.4685341417789459, "learning_rate": 3.315276273022752e-06, "loss": 0.0037, "step": 4810 }, { "epoch": 2.8269794721407626, "grad_norm": 0.4689994752407074, "learning_rate": 3.2069339111592634e-06, "loss": 0.0016, "step": 4820 }, { "epoch": 2.832844574780059, "grad_norm": 0.27341169118881226, "learning_rate": 3.098591549295775e-06, "loss": 0.0018, "step": 4830 }, { "epoch": 2.838709677419355, "grad_norm": 0.4681690037250519, "learning_rate": 2.9902491874322862e-06, "loss": 0.0027, "step": 4840 }, { "epoch": 2.844574780058651, "grad_norm": 0.15625539422035217, "learning_rate": 2.8819068255687974e-06, "loss": 0.0014, "step": 4850 }, { "epoch": 2.8504398826979473, "grad_norm": 0.14638853073120117, "learning_rate": 2.773564463705309e-06, "loss": 0.0024, "step": 4860 }, { "epoch": 2.8563049853372435, "grad_norm": 0.3259941041469574, "learning_rate": 2.6652221018418202e-06, "loss": 0.0024, "step": 4870 }, { "epoch": 2.8621700879765397, "grad_norm": 0.2885695993900299, "learning_rate": 2.5568797399783314e-06, "loss": 0.0018, "step": 4880 }, { "epoch": 2.868035190615836, "grad_norm": 0.13875146210193634, "learning_rate": 2.448537378114843e-06, "loss": 0.0032, "step": 4890 }, { "epoch": 2.873900293255132, "grad_norm": 0.42090490460395813, "learning_rate": 2.3401950162513543e-06, "loss": 0.0022, "step": 4900 }, { "epoch": 2.8797653958944283, "grad_norm": 0.587674617767334, "learning_rate": 2.231852654387866e-06, "loss": 0.0022, "step": 4910 }, { "epoch": 2.8856304985337244, "grad_norm": 0.2683647572994232, "learning_rate": 2.123510292524377e-06, "loss": 0.0028, "step": 4920 }, { "epoch": 2.8914956011730206, "grad_norm": 0.14802850782871246, "learning_rate": 2.0151679306608883e-06, "loss": 0.0027, "step": 4930 }, { "epoch": 2.897360703812317, "grad_norm": 0.8457247018814087, "learning_rate": 1.9068255687973997e-06, "loss": 0.0016, "step": 4940 }, { "epoch": 2.903225806451613, "grad_norm": 0.6568015217781067, "learning_rate": 1.798483206933911e-06, "loss": 0.0019, "step": 4950 }, { "epoch": 2.909090909090909, "grad_norm": 0.8183419108390808, "learning_rate": 1.6901408450704225e-06, "loss": 0.0033, "step": 4960 }, { "epoch": 2.9149560117302054, "grad_norm": 0.717965841293335, "learning_rate": 1.5817984832069341e-06, "loss": 0.0019, "step": 4970 }, { "epoch": 2.9208211143695015, "grad_norm": 0.3152722120285034, "learning_rate": 1.4734561213434453e-06, "loss": 0.0012, "step": 4980 }, { "epoch": 2.9266862170087977, "grad_norm": 0.26775985956192017, "learning_rate": 1.3651137594799567e-06, "loss": 0.0021, "step": 4990 }, { "epoch": 2.932551319648094, "grad_norm": 0.44031721353530884, "learning_rate": 1.2567713976164681e-06, "loss": 0.0019, "step": 5000 }, { "epoch": 2.93841642228739, "grad_norm": 0.4502199590206146, "learning_rate": 1.1484290357529793e-06, "loss": 0.0017, "step": 5010 }, { "epoch": 2.9442815249266863, "grad_norm": 0.18106575310230255, "learning_rate": 1.040086673889491e-06, "loss": 0.0018, "step": 5020 }, { "epoch": 2.9501466275659824, "grad_norm": 1.1088088750839233, "learning_rate": 9.317443120260022e-07, "loss": 0.0024, "step": 5030 }, { "epoch": 2.9560117302052786, "grad_norm": 0.2301834672689438, "learning_rate": 8.234019501625137e-07, "loss": 0.0016, "step": 5040 }, { "epoch": 2.961876832844575, "grad_norm": 0.23097343742847443, "learning_rate": 7.15059588299025e-07, "loss": 0.0016, "step": 5050 }, { "epoch": 2.967741935483871, "grad_norm": 0.47115635871887207, "learning_rate": 6.067172264355364e-07, "loss": 0.0018, "step": 5060 }, { "epoch": 2.973607038123167, "grad_norm": 0.7237260341644287, "learning_rate": 4.983748645720477e-07, "loss": 0.0031, "step": 5070 }, { "epoch": 2.9794721407624634, "grad_norm": 0.5529869794845581, "learning_rate": 3.900325027085591e-07, "loss": 0.0025, "step": 5080 }, { "epoch": 2.9853372434017595, "grad_norm": 0.2470860332250595, "learning_rate": 2.8169014084507043e-07, "loss": 0.0023, "step": 5090 }, { "epoch": 2.9912023460410557, "grad_norm": 0.6672024726867676, "learning_rate": 1.7334777898158182e-07, "loss": 0.0014, "step": 5100 }, { "epoch": 2.997067448680352, "grad_norm": 0.777362585067749, "learning_rate": 6.500541711809318e-08, "loss": 0.0027, "step": 5110 } ], "logging_steps": 10, "max_steps": 5115, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.0761671760758784e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }