| { | |
| "best_global_step": 66218, | |
| "best_metric": 0.9523090398381104, | |
| "best_model_checkpoint": "ai-vs-hum\\checkpoint-66218", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 66218, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007550816998399227, | |
| "grad_norm": 65.657958984375, | |
| "learning_rate": 7.550816998399228e-08, | |
| "loss": 0.7738, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.015101633996798454, | |
| "grad_norm": 56.08807373046875, | |
| "learning_rate": 1.5101633996798456e-07, | |
| "loss": 0.715, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02265245099519768, | |
| "grad_norm": 80.93883514404297, | |
| "learning_rate": 2.265245099519768e-07, | |
| "loss": 0.6352, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.03020326799359691, | |
| "grad_norm": 99.87760925292969, | |
| "learning_rate": 3.020326799359691e-07, | |
| "loss": 0.5265, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.03775408499199613, | |
| "grad_norm": 61.885841369628906, | |
| "learning_rate": 3.7754084991996136e-07, | |
| "loss": 0.4273, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.04530490199039536, | |
| "grad_norm": 704.5555419921875, | |
| "learning_rate": 4.530490199039536e-07, | |
| "loss": 0.4747, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.05285571898879459, | |
| "grad_norm": 0.1631409078836441, | |
| "learning_rate": 5.285571898879459e-07, | |
| "loss": 0.5541, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.06040653598719382, | |
| "grad_norm": 0.1648247241973877, | |
| "learning_rate": 6.040653598719382e-07, | |
| "loss": 0.7388, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.06795735298559304, | |
| "grad_norm": 2444.441650390625, | |
| "learning_rate": 6.795735298559304e-07, | |
| "loss": 0.6825, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.07550816998399226, | |
| "grad_norm": 0.37286192178726196, | |
| "learning_rate": 7.550816998399227e-07, | |
| "loss": 0.6872, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.08305898698239149, | |
| "grad_norm": 0.28558024764060974, | |
| "learning_rate": 8.305898698239149e-07, | |
| "loss": 0.7039, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.09060980398079072, | |
| "grad_norm": 182.67251586914062, | |
| "learning_rate": 9.060980398079072e-07, | |
| "loss": 0.6045, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.09816062097918994, | |
| "grad_norm": 0.0031864135526120663, | |
| "learning_rate": 9.816062097918996e-07, | |
| "loss": 0.5625, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.10571143797758918, | |
| "grad_norm": 0.03901828080415726, | |
| "learning_rate": 1.0571143797758919e-06, | |
| "loss": 0.5507, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.11326225497598841, | |
| "grad_norm": 0.004638838116079569, | |
| "learning_rate": 1.1326225497598842e-06, | |
| "loss": 0.5191, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.12081307197438763, | |
| "grad_norm": 0.14078642427921295, | |
| "learning_rate": 1.2081307197438765e-06, | |
| "loss": 0.5333, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.12836388897278686, | |
| "grad_norm": 0.07704892754554749, | |
| "learning_rate": 1.2836388897278688e-06, | |
| "loss": 0.5258, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.13591470597118607, | |
| "grad_norm": 0.03960805386304855, | |
| "learning_rate": 1.3591470597118609e-06, | |
| "loss": 0.4775, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.1434655229695853, | |
| "grad_norm": 0.8385183215141296, | |
| "learning_rate": 1.4346552296958531e-06, | |
| "loss": 0.4945, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.15101633996798453, | |
| "grad_norm": 574.739990234375, | |
| "learning_rate": 1.5101633996798454e-06, | |
| "loss": 0.5178, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.15856715696638377, | |
| "grad_norm": 0.06548255681991577, | |
| "learning_rate": 1.5856715696638377e-06, | |
| "loss": 0.4735, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.16611797396478298, | |
| "grad_norm": 1357.1788330078125, | |
| "learning_rate": 1.6611797396478298e-06, | |
| "loss": 0.5533, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.17366879096318222, | |
| "grad_norm": 0.12339621037244797, | |
| "learning_rate": 1.7366879096318223e-06, | |
| "loss": 0.4891, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.18121960796158143, | |
| "grad_norm": 0.3505186438560486, | |
| "learning_rate": 1.8121960796158144e-06, | |
| "loss": 0.4935, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.18877042495998067, | |
| "grad_norm": 1131.322509765625, | |
| "learning_rate": 1.887704249599807e-06, | |
| "loss": 0.4447, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.19632124195837988, | |
| "grad_norm": 0.030383553355932236, | |
| "learning_rate": 1.963212419583799e-06, | |
| "loss": 0.5052, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.20387205895677912, | |
| "grad_norm": 0.06966419517993927, | |
| "learning_rate": 2.0387205895677913e-06, | |
| "loss": 0.4477, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.21142287595517836, | |
| "grad_norm": 0.14627192914485931, | |
| "learning_rate": 2.1142287595517838e-06, | |
| "loss": 0.4535, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.21897369295357758, | |
| "grad_norm": 0.013991514220833778, | |
| "learning_rate": 2.189736929535776e-06, | |
| "loss": 0.414, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.22652450995197682, | |
| "grad_norm": 278.3962707519531, | |
| "learning_rate": 2.2652450995197684e-06, | |
| "loss": 0.3346, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.23407532695037603, | |
| "grad_norm": 0.012267685495316982, | |
| "learning_rate": 2.3407532695037605e-06, | |
| "loss": 0.426, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.24162614394877527, | |
| "grad_norm": 0.0350683256983757, | |
| "learning_rate": 2.416261439487753e-06, | |
| "loss": 0.3849, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.24917696094717448, | |
| "grad_norm": 0.01037506852298975, | |
| "learning_rate": 2.491769609471745e-06, | |
| "loss": 0.3726, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.2567277779455737, | |
| "grad_norm": 139.85562133789062, | |
| "learning_rate": 2.5672777794557375e-06, | |
| "loss": 0.4721, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.26427859494397293, | |
| "grad_norm": 0.11431169509887695, | |
| "learning_rate": 2.6427859494397296e-06, | |
| "loss": 0.4746, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.27182941194237215, | |
| "grad_norm": 0.024222318083047867, | |
| "learning_rate": 2.7182941194237217e-06, | |
| "loss": 0.3612, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.2793802289407714, | |
| "grad_norm": 0.0600462444126606, | |
| "learning_rate": 2.793802289407714e-06, | |
| "loss": 0.3716, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.2869310459391706, | |
| "grad_norm": 0.0730457752943039, | |
| "learning_rate": 2.8693104593917063e-06, | |
| "loss": 0.4519, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.29448186293756984, | |
| "grad_norm": 0.1063174456357956, | |
| "learning_rate": 2.944818629375699e-06, | |
| "loss": 0.3865, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.30203267993596905, | |
| "grad_norm": 0.009060272946953773, | |
| "learning_rate": 3.020326799359691e-06, | |
| "loss": 0.3653, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.3095834969343683, | |
| "grad_norm": 0.0033603431656956673, | |
| "learning_rate": 3.0958349693436834e-06, | |
| "loss": 0.4347, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.31713431393276753, | |
| "grad_norm": 0.011356896720826626, | |
| "learning_rate": 3.1713431393276755e-06, | |
| "loss": 0.3759, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.32468513093116674, | |
| "grad_norm": 0.2442641258239746, | |
| "learning_rate": 3.2468513093116675e-06, | |
| "loss": 0.3776, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.33223594792956596, | |
| "grad_norm": 0.029270794242620468, | |
| "learning_rate": 3.3223594792956596e-06, | |
| "loss": 0.3688, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.3397867649279652, | |
| "grad_norm": 0.28456059098243713, | |
| "learning_rate": 3.3978676492796526e-06, | |
| "loss": 0.3656, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.34733758192636444, | |
| "grad_norm": 0.07442634552717209, | |
| "learning_rate": 3.4733758192636446e-06, | |
| "loss": 0.4154, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.35488839892476365, | |
| "grad_norm": 0.029278529807925224, | |
| "learning_rate": 3.5488839892476367e-06, | |
| "loss": 0.4295, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.36243921592316286, | |
| "grad_norm": 128.08538818359375, | |
| "learning_rate": 3.624392159231629e-06, | |
| "loss": 0.376, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.36999003292156213, | |
| "grad_norm": 0.05300796404480934, | |
| "learning_rate": 3.6999003292156217e-06, | |
| "loss": 0.3514, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.37754084991996134, | |
| "grad_norm": 0.005980394314974546, | |
| "learning_rate": 3.775408499199614e-06, | |
| "loss": 0.4061, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.38509166691836055, | |
| "grad_norm": 121.62598419189453, | |
| "learning_rate": 3.8509166691836055e-06, | |
| "loss": 0.3857, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.39264248391675977, | |
| "grad_norm": 0.09926415979862213, | |
| "learning_rate": 3.926424839167598e-06, | |
| "loss": 0.3912, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.40019330091515903, | |
| "grad_norm": 0.11781750619411469, | |
| "learning_rate": 4.0019330091515905e-06, | |
| "loss": 0.4562, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.40774411791355825, | |
| "grad_norm": 0.034933462738990784, | |
| "learning_rate": 4.0774411791355826e-06, | |
| "loss": 0.3881, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.41529493491195746, | |
| "grad_norm": 0.07762602716684341, | |
| "learning_rate": 4.152949349119575e-06, | |
| "loss": 0.4326, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.4228457519103567, | |
| "grad_norm": 0.03593170642852783, | |
| "learning_rate": 4.2284575191035676e-06, | |
| "loss": 0.4169, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.43039656890875594, | |
| "grad_norm": 6.517802715301514, | |
| "learning_rate": 4.30396568908756e-06, | |
| "loss": 0.3935, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.43794738590715515, | |
| "grad_norm": 0.08031677454710007, | |
| "learning_rate": 4.379473859071552e-06, | |
| "loss": 0.3949, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.44549820290555436, | |
| "grad_norm": 0.00936515349894762, | |
| "learning_rate": 4.454982029055544e-06, | |
| "loss": 0.4852, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.45304901990395363, | |
| "grad_norm": 0.01062073465436697, | |
| "learning_rate": 4.530490199039537e-06, | |
| "loss": 0.3993, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.46059983690235284, | |
| "grad_norm": 0.0008572549559175968, | |
| "learning_rate": 4.605998369023529e-06, | |
| "loss": 0.4309, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.46815065390075206, | |
| "grad_norm": 0.042835455387830734, | |
| "learning_rate": 4.681506539007521e-06, | |
| "loss": 0.5426, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.47570147089915127, | |
| "grad_norm": 0.006536947563290596, | |
| "learning_rate": 4.757014708991513e-06, | |
| "loss": 0.3503, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.48325228789755054, | |
| "grad_norm": 0.16728435456752777, | |
| "learning_rate": 4.832522878975506e-06, | |
| "loss": 0.4025, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.49080310489594975, | |
| "grad_norm": 0.24009940028190613, | |
| "learning_rate": 4.908031048959498e-06, | |
| "loss": 0.373, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.49835392189434896, | |
| "grad_norm": 0.03488277643918991, | |
| "learning_rate": 4.98353921894349e-06, | |
| "loss": 0.4516, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.5059047388927482, | |
| "grad_norm": 0.07614383846521378, | |
| "learning_rate": 4.993439179008058e-06, | |
| "loss": 0.4391, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.5134555558911474, | |
| "grad_norm": 0.2857000231742859, | |
| "learning_rate": 4.98504938234317e-06, | |
| "loss": 0.4202, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.5210063728895467, | |
| "grad_norm": 0.005722880829125643, | |
| "learning_rate": 4.9766595856782815e-06, | |
| "loss": 0.3904, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.5285571898879459, | |
| "grad_norm": 0.08243716508150101, | |
| "learning_rate": 4.968269789013394e-06, | |
| "loss": 0.355, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.5361080068863451, | |
| "grad_norm": 764.4724731445312, | |
| "learning_rate": 4.959879992348506e-06, | |
| "loss": 0.4357, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.5436588238847443, | |
| "grad_norm": 0.0467102974653244, | |
| "learning_rate": 4.9514901956836175e-06, | |
| "loss": 0.4425, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.5512096408831435, | |
| "grad_norm": 0.4159618318080902, | |
| "learning_rate": 4.94310039901873e-06, | |
| "loss": 0.404, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.5587604578815428, | |
| "grad_norm": 0.0004953582538291812, | |
| "learning_rate": 4.934710602353842e-06, | |
| "loss": 0.3587, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.566311274879942, | |
| "grad_norm": 0.03575737774372101, | |
| "learning_rate": 4.926320805688954e-06, | |
| "loss": 0.3726, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.5738620918783413, | |
| "grad_norm": 0.02385396882891655, | |
| "learning_rate": 4.917931009024066e-06, | |
| "loss": 0.3771, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.5814129088767405, | |
| "grad_norm": 0.02760937251150608, | |
| "learning_rate": 4.909541212359178e-06, | |
| "loss": 0.4108, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.5889637258751397, | |
| "grad_norm": 0.7694607377052307, | |
| "learning_rate": 4.901151415694289e-06, | |
| "loss": 0.3603, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.5965145428735389, | |
| "grad_norm": 1522.3602294921875, | |
| "learning_rate": 4.892761619029401e-06, | |
| "loss": 0.3335, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.6040653598719381, | |
| "grad_norm": 0.3060073256492615, | |
| "learning_rate": 4.884371822364514e-06, | |
| "loss": 0.3266, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.6116161768703374, | |
| "grad_norm": 0.07775181531906128, | |
| "learning_rate": 4.875982025699625e-06, | |
| "loss": 0.3596, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.6191669938687366, | |
| "grad_norm": 0.05560746416449547, | |
| "learning_rate": 4.867592229034738e-06, | |
| "loss": 0.4614, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.6267178108671358, | |
| "grad_norm": 0.11702022701501846, | |
| "learning_rate": 4.85920243236985e-06, | |
| "loss": 0.4036, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.6342686278655351, | |
| "grad_norm": 0.20153406262397766, | |
| "learning_rate": 4.850812635704961e-06, | |
| "loss": 0.3323, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.6418194448639343, | |
| "grad_norm": 1046.9708251953125, | |
| "learning_rate": 4.842422839040073e-06, | |
| "loss": 0.423, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.6493702618623335, | |
| "grad_norm": 0.005386498291045427, | |
| "learning_rate": 4.834033042375186e-06, | |
| "loss": 0.3607, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.6569210788607327, | |
| "grad_norm": 0.0019247422460466623, | |
| "learning_rate": 4.825643245710297e-06, | |
| "loss": 0.3117, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.6644718958591319, | |
| "grad_norm": 0.03873920440673828, | |
| "learning_rate": 4.817253449045409e-06, | |
| "loss": 0.4158, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.6720227128575312, | |
| "grad_norm": 0.00777060491964221, | |
| "learning_rate": 4.808863652380522e-06, | |
| "loss": 0.3424, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.6795735298559304, | |
| "grad_norm": 0.0689612627029419, | |
| "learning_rate": 4.800473855715633e-06, | |
| "loss": 0.3596, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.6871243468543297, | |
| "grad_norm": 164.3638916015625, | |
| "learning_rate": 4.792084059050745e-06, | |
| "loss": 0.3271, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.6946751638527289, | |
| "grad_norm": 0.9296920895576477, | |
| "learning_rate": 4.783694262385858e-06, | |
| "loss": 0.4008, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.7022259808511281, | |
| "grad_norm": 0.008974584750831127, | |
| "learning_rate": 4.775304465720969e-06, | |
| "loss": 0.3232, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.7097767978495273, | |
| "grad_norm": 126.27271270751953, | |
| "learning_rate": 4.766914669056081e-06, | |
| "loss": 0.3716, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.7173276148479265, | |
| "grad_norm": 0.003123954404145479, | |
| "learning_rate": 4.758524872391193e-06, | |
| "loss": 0.3153, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.7248784318463257, | |
| "grad_norm": 0.008505255915224552, | |
| "learning_rate": 4.750135075726304e-06, | |
| "loss": 0.3477, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.732429248844725, | |
| "grad_norm": 0.07402774691581726, | |
| "learning_rate": 4.741745279061417e-06, | |
| "loss": 0.3588, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.7399800658431243, | |
| "grad_norm": 0.029175467789173126, | |
| "learning_rate": 4.733355482396529e-06, | |
| "loss": 0.353, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.7475308828415235, | |
| "grad_norm": 229.5810089111328, | |
| "learning_rate": 4.724965685731641e-06, | |
| "loss": 0.361, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.7550816998399227, | |
| "grad_norm": 0.14088426530361176, | |
| "learning_rate": 4.716575889066753e-06, | |
| "loss": 0.3988, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.7626325168383219, | |
| "grad_norm": 0.5763397216796875, | |
| "learning_rate": 4.7081860924018655e-06, | |
| "loss": 0.3646, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 0.7701833338367211, | |
| "grad_norm": 4.555429458618164, | |
| "learning_rate": 4.699796295736977e-06, | |
| "loss": 0.3308, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.7777341508351203, | |
| "grad_norm": 0.031139669939875603, | |
| "learning_rate": 4.691406499072089e-06, | |
| "loss": 0.3487, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 0.7852849678335195, | |
| "grad_norm": 1.3805643320083618, | |
| "learning_rate": 4.683016702407201e-06, | |
| "loss": 0.3193, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.7928357848319189, | |
| "grad_norm": 0.00282275746576488, | |
| "learning_rate": 4.674626905742312e-06, | |
| "loss": 0.4172, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.8003866018303181, | |
| "grad_norm": 0.0008711374830454588, | |
| "learning_rate": 4.666237109077425e-06, | |
| "loss": 0.3291, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.8079374188287173, | |
| "grad_norm": 0.007124012336134911, | |
| "learning_rate": 4.657847312412537e-06, | |
| "loss": 0.3363, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 0.8154882358271165, | |
| "grad_norm": 0.3629874587059021, | |
| "learning_rate": 4.649457515747648e-06, | |
| "loss": 0.3525, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.8230390528255157, | |
| "grad_norm": 89.42652130126953, | |
| "learning_rate": 4.641067719082761e-06, | |
| "loss": 0.3133, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 0.8305898698239149, | |
| "grad_norm": 0.0034131056163460016, | |
| "learning_rate": 4.6326779224178726e-06, | |
| "loss": 0.3381, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.8381406868223141, | |
| "grad_norm": 8.344011306762695, | |
| "learning_rate": 4.624288125752985e-06, | |
| "loss": 0.2783, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 0.8456915038207135, | |
| "grad_norm": 0.015363700687885284, | |
| "learning_rate": 4.615898329088097e-06, | |
| "loss": 0.3976, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.8532423208191127, | |
| "grad_norm": 218.98626708984375, | |
| "learning_rate": 4.6075085324232085e-06, | |
| "loss": 0.3916, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 0.8607931378175119, | |
| "grad_norm": 0.052222587168216705, | |
| "learning_rate": 4.59911873575832e-06, | |
| "loss": 0.3614, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.8683439548159111, | |
| "grad_norm": 0.042011819779872894, | |
| "learning_rate": 4.590728939093432e-06, | |
| "loss": 0.422, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 0.8758947718143103, | |
| "grad_norm": 0.2174474447965622, | |
| "learning_rate": 4.5823391424285445e-06, | |
| "loss": 0.3086, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.8834455888127095, | |
| "grad_norm": 0.11423001438379288, | |
| "learning_rate": 4.573949345763656e-06, | |
| "loss": 0.3596, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 0.8909964058111087, | |
| "grad_norm": 0.1473008543252945, | |
| "learning_rate": 4.565559549098769e-06, | |
| "loss": 0.3845, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.8985472228095079, | |
| "grad_norm": 0.6927057504653931, | |
| "learning_rate": 4.5571697524338805e-06, | |
| "loss": 0.3272, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 0.9060980398079073, | |
| "grad_norm": 0.052435796707868576, | |
| "learning_rate": 4.548779955768992e-06, | |
| "loss": 0.3124, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.9136488568063065, | |
| "grad_norm": 0.0011638773139566183, | |
| "learning_rate": 4.540390159104105e-06, | |
| "loss": 0.3051, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 0.9211996738047057, | |
| "grad_norm": 0.002878799568861723, | |
| "learning_rate": 4.5320003624392165e-06, | |
| "loss": 0.3196, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.9287504908031049, | |
| "grad_norm": 0.022700993344187737, | |
| "learning_rate": 4.523610565774328e-06, | |
| "loss": 0.3307, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 0.9363013078015041, | |
| "grad_norm": 18.183610916137695, | |
| "learning_rate": 4.51522076910944e-06, | |
| "loss": 0.3215, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.9438521247999033, | |
| "grad_norm": 0.006543469615280628, | |
| "learning_rate": 4.5068309724445524e-06, | |
| "loss": 0.3398, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 0.9514029417983025, | |
| "grad_norm": 0.07925090938806534, | |
| "learning_rate": 4.498441175779664e-06, | |
| "loss": 0.2937, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.9589537587967017, | |
| "grad_norm": 0.1537381261587143, | |
| "learning_rate": 4.490051379114776e-06, | |
| "loss": 0.2819, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 0.9665045757951011, | |
| "grad_norm": 0.01872635819017887, | |
| "learning_rate": 4.481661582449888e-06, | |
| "loss": 0.2671, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.9740553927935003, | |
| "grad_norm": 0.024023612961173058, | |
| "learning_rate": 4.473271785785e-06, | |
| "loss": 0.3206, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 0.9816062097918995, | |
| "grad_norm": 0.059889055788517, | |
| "learning_rate": 4.464881989120113e-06, | |
| "loss": 0.2976, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.9891570267902987, | |
| "grad_norm": 0.002819158136844635, | |
| "learning_rate": 4.456492192455224e-06, | |
| "loss": 0.3465, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 0.9967078437886979, | |
| "grad_norm": 0.02669268473982811, | |
| "learning_rate": 4.448102395790336e-06, | |
| "loss": 0.3076, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9523090398381104, | |
| "eval_loss": 0.3044677674770355, | |
| "eval_runtime": 202.6207, | |
| "eval_samples_per_second": 163.404, | |
| "eval_steps_per_second": 40.855, | |
| "step": 66218 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 331090, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1092242844591276e+19, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |