Jevlet / progress.jsonl
NAME0x0's picture
Jevlet v6: weights, calibration, results, model card
c59f205 verified
Raw History Blame Contribute Delete
50.9 kB
{"step": 8550, "loss": 0.0991, "lr_factor": 0.7687, "steps_per_second": 1.335, "tokens_per_second": 25229, "eta_hours": 3.42, "time": 1790352708.826475}
{"step": 8600, "loss": 0.1317, "lr_factor": 0.7661, "steps_per_second": 1.38, "tokens_per_second": 25769, "eta_hours": 3.3, "time": 1790352743.8178291}
{"step": 8650, "loss": 0.0671, "lr_factor": 0.7634, "steps_per_second": 1.382, "tokens_per_second": 25962, "eta_hours": 3.29, "time": 1790352779.8933947}
{"step": 8700, "loss": 0.0467, "lr_factor": 0.7608, "steps_per_second": 1.369, "tokens_per_second": 25883, "eta_hours": 3.31, "time": 1790352817.4701867}
{"step": 8750, "loss": 0.0707, "lr_factor": 0.7581, "steps_per_second": 1.371, "tokens_per_second": 25991, "eta_hours": 3.29, "time": 1790352853.7810183}
{"step": 8800, "loss": 0.1018, "lr_factor": 0.7555, "steps_per_second": 1.373, "tokens_per_second": 26028, "eta_hours": 3.28, "time": 1790352889.9086173}
{"step": 8850, "loss": 0.0858, "lr_factor": 0.7528, "steps_per_second": 1.377, "tokens_per_second": 26076, "eta_hours": 3.26, "time": 1790352925.5861843}
{"step": 8900, "loss": 0.0897, "lr_factor": 0.7501, "steps_per_second": 1.377, "tokens_per_second": 26098, "eta_hours": 3.25, "time": 1790352961.9302604}
{"step": 8950, "loss": 0.0839, "lr_factor": 0.7475, "steps_per_second": 1.376, "tokens_per_second": 26086, "eta_hours": 3.24, "time": 1790352998.3651476}
{"step": 9000, "loss": 0.1011, "lr_factor": 0.7448, "steps_per_second": 1.381, "tokens_per_second": 26136, "eta_hours": 3.22, "time": 1790353033.419074}
{"step": 9050, "loss": 0.2009, "lr_factor": 0.7421, "steps_per_second": 1.377, "tokens_per_second": 26033, "eta_hours": 3.22, "time": 1790353070.662574}
{"step": 9100, "loss": 0.1058, "lr_factor": 0.7393, "steps_per_second": 1.379, "tokens_per_second": 26055, "eta_hours": 3.2, "time": 1790353106.5833836}
{"step": 9150, "loss": 0.1069, "lr_factor": 0.7366, "steps_per_second": 1.381, "tokens_per_second": 26087, "eta_hours": 3.19, "time": 1790353142.0617192}
{"step": 9200, "loss": 0.0817, "lr_factor": 0.7339, "steps_per_second": 1.381, "tokens_per_second": 26080, "eta_hours": 3.18, "time": 1790353178.2539692}
{"step": 9250, "loss": 0.0838, "lr_factor": 0.7311, "steps_per_second": 1.381, "tokens_per_second": 26101, "eta_hours": 3.17, "time": 1790353214.4188626}
{"step": 9300, "loss": 0.0998, "lr_factor": 0.7284, "steps_per_second": 1.382, "tokens_per_second": 26103, "eta_hours": 3.16, "time": 1790353250.30128}
{"step": 9350, "loss": 0.0718, "lr_factor": 0.7256, "steps_per_second": 1.383, "tokens_per_second": 26116, "eta_hours": 3.14, "time": 1790353286.1385643}
{"step": 9400, "loss": 0.0636, "lr_factor": 0.7229, "steps_per_second": 1.383, "tokens_per_second": 26126, "eta_hours": 3.13, "time": 1790353321.9322164}
{"step": 9450, "loss": 0.2181, "lr_factor": 0.7201, "steps_per_second": 1.382, "tokens_per_second": 26120, "eta_hours": 3.13, "time": 1790353358.7262015}
{"step": 9500, "loss": 0.1543, "lr_factor": 0.7173, "steps_per_second": 1.383, "tokens_per_second": 26131, "eta_hours": 3.11, "time": 1790353394.6220694}
{"step": 9550, "loss": 0.0857, "lr_factor": 0.7145, "steps_per_second": 1.378, "tokens_per_second": 26037, "eta_hours": 3.11, "time": 1790353433.1132288}
{"step": 9600, "loss": 0.0914, "lr_factor": 0.7117, "steps_per_second": 1.379, "tokens_per_second": 26049, "eta_hours": 3.1, "time": 1790353469.2935545}
{"step": 9650, "loss": 0.0574, "lr_factor": 0.7089, "steps_per_second": 1.38, "tokens_per_second": 26058, "eta_hours": 3.09, "time": 1790353504.990679}
{"step": 9700, "loss": 0.101, "lr_factor": 0.7061, "steps_per_second": 1.379, "tokens_per_second": 26049, "eta_hours": 3.08, "time": 1790353541.2999835}
{"step": 9750, "loss": 0.0741, "lr_factor": 0.7033, "steps_per_second": 1.38, "tokens_per_second": 26057, "eta_hours": 3.07, "time": 1790353577.2167177}
{"step": 9800, "loss": 0.1041, "lr_factor": 0.7005, "steps_per_second": 1.379, "tokens_per_second": 26055, "eta_hours": 3.06, "time": 1790353613.8629315}
{"step": 9850, "loss": 0.1374, "lr_factor": 0.6976, "steps_per_second": 1.38, "tokens_per_second": 26064, "eta_hours": 3.05, "time": 1790353649.796325}
{"step": 9900, "loss": 0.0704, "lr_factor": 0.6948, "steps_per_second": 1.381, "tokens_per_second": 26067, "eta_hours": 3.04, "time": 1790353685.2283869}
{"step": 9950, "loss": 0.1027, "lr_factor": 0.692, "steps_per_second": 1.381, "tokens_per_second": 26065, "eta_hours": 3.03, "time": 1790353721.455884}
{"step": 10000, "loss": 0.1267, "lr_factor": 0.6891, "steps_per_second": 1.382, "tokens_per_second": 26079, "eta_hours": 3.02, "time": 1790353757.093576}
{"step": 10050, "loss": 0.0889, "lr_factor": 0.6862, "steps_per_second": 1.378, "tokens_per_second": 26013, "eta_hours": 3.01, "time": 1790353795.790212}
{"step": 10100, "loss": 0.1225, "lr_factor": 0.6834, "steps_per_second": 1.378, "tokens_per_second": 26017, "eta_hours": 3.0, "time": 1790353832.5368912}
{"step": 10150, "loss": 0.0928, "lr_factor": 0.6805, "steps_per_second": 1.378, "tokens_per_second": 26025, "eta_hours": 2.99, "time": 1790353868.5391111}
{"step": 10200, "loss": 0.0958, "lr_factor": 0.6776, "steps_per_second": 1.379, "tokens_per_second": 26020, "eta_hours": 2.98, "time": 1790353904.590837}
{"step": 10250, "loss": 0.0848, "lr_factor": 0.6747, "steps_per_second": 1.378, "tokens_per_second": 26029, "eta_hours": 2.97, "time": 1790353940.958501}
{"step": 10300, "loss": 0.1097, "lr_factor": 0.6718, "steps_per_second": 1.379, "tokens_per_second": 26033, "eta_hours": 2.96, "time": 1790353976.7090642}
{"step": 10350, "loss": 0.0877, "lr_factor": 0.6689, "steps_per_second": 1.38, "tokens_per_second": 26046, "eta_hours": 2.95, "time": 1790354011.879104}
{"step": 10400, "loss": 0.0674, "lr_factor": 0.666, "steps_per_second": 1.379, "tokens_per_second": 26047, "eta_hours": 2.94, "time": 1790354048.7453048}
{"step": 10450, "loss": 0.0993, "lr_factor": 0.6631, "steps_per_second": 1.38, "tokens_per_second": 26051, "eta_hours": 2.93, "time": 1790354084.816886}
{"step": 10500, "loss": 0.1092, "lr_factor": 0.6602, "steps_per_second": 1.38, "tokens_per_second": 26063, "eta_hours": 2.92, "time": 1790354120.2495856}
{"step": 10550, "loss": 0.0812, "lr_factor": 0.6573, "steps_per_second": 1.378, "tokens_per_second": 26024, "eta_hours": 2.91, "time": 1790354158.7158437}
{"step": 10600, "loss": 0.0812, "lr_factor": 0.6544, "steps_per_second": 1.379, "tokens_per_second": 26032, "eta_hours": 2.9, "time": 1790354194.2146516}
{"step": 10650, "loss": 0.1168, "lr_factor": 0.6514, "steps_per_second": 1.379, "tokens_per_second": 26032, "eta_hours": 2.89, "time": 1790354230.0641377}
{"step": 10700, "loss": 0.0774, "lr_factor": 0.6485, "steps_per_second": 1.38, "tokens_per_second": 26037, "eta_hours": 2.88, "time": 1790354265.8529913}
{"step": 10750, "loss": 0.1935, "lr_factor": 0.6455, "steps_per_second": 1.38, "tokens_per_second": 26043, "eta_hours": 2.87, "time": 1790354301.6356368}
{"step": 10800, "loss": 0.0528, "lr_factor": 0.6426, "steps_per_second": 1.381, "tokens_per_second": 26051, "eta_hours": 2.86, "time": 1790354337.009171}
{"step": 10850, "loss": 0.0647, "lr_factor": 0.6396, "steps_per_second": 1.38, "tokens_per_second": 26053, "eta_hours": 2.85, "time": 1790354373.6884592}
{"step": 10900, "loss": 0.3504, "lr_factor": 0.6367, "steps_per_second": 1.381, "tokens_per_second": 26058, "eta_hours": 2.84, "time": 1790354409.6050127}
{"step": 10950, "loss": 0.1341, "lr_factor": 0.6337, "steps_per_second": 1.381, "tokens_per_second": 26060, "eta_hours": 2.83, "time": 1790354445.7641041}
{"step": 11000, "loss": 0.0769, "lr_factor": 0.6308, "steps_per_second": 1.381, "tokens_per_second": 26060, "eta_hours": 2.82, "time": 1790354481.7830155}
{"step": 11050, "loss": 0.1025, "lr_factor": 0.6278, "steps_per_second": 1.379, "tokens_per_second": 26019, "eta_hours": 2.81, "time": 1790354520.7121909}
{"step": 11100, "loss": 0.1012, "lr_factor": 0.6248, "steps_per_second": 1.379, "tokens_per_second": 26015, "eta_hours": 2.8, "time": 1790354557.1459143}
{"step": 11150, "loss": 0.0756, "lr_factor": 0.6218, "steps_per_second": 1.379, "tokens_per_second": 26015, "eta_hours": 2.79, "time": 1790354593.5726886}
{"step": 11200, "loss": 0.0994, "lr_factor": 0.6188, "steps_per_second": 1.379, "tokens_per_second": 26015, "eta_hours": 2.78, "time": 1790354629.9408784}
{"step": 11250, "loss": 0.0693, "lr_factor": 0.6159, "steps_per_second": 1.379, "tokens_per_second": 26020, "eta_hours": 2.77, "time": 1790354666.1213346}
{"step": 11300, "loss": 0.0641, "lr_factor": 0.6129, "steps_per_second": 1.379, "tokens_per_second": 26021, "eta_hours": 2.76, "time": 1790354702.183648}
{"step": 11350, "loss": 0.1085, "lr_factor": 0.6099, "steps_per_second": 1.379, "tokens_per_second": 26024, "eta_hours": 2.75, "time": 1790354738.0970244}
{"step": 11400, "loss": 0.0823, "lr_factor": 0.6069, "steps_per_second": 1.379, "tokens_per_second": 26024, "eta_hours": 2.74, "time": 1790354774.0744092}
{"step": 11450, "loss": 0.0825, "lr_factor": 0.6039, "steps_per_second": 1.379, "tokens_per_second": 26029, "eta_hours": 2.73, "time": 1790354810.169926}
{"step": 11500, "loss": 0.068, "lr_factor": 0.6009, "steps_per_second": 1.38, "tokens_per_second": 26029, "eta_hours": 2.72, "time": 1790354845.8435612}
{"step": 11550, "loss": 0.1938, "lr_factor": 0.5979, "steps_per_second": 1.378, "tokens_per_second": 25997, "eta_hours": 2.71, "time": 1790354885.3334632}
{"step": 11600, "loss": 0.0512, "lr_factor": 0.5949, "steps_per_second": 1.378, "tokens_per_second": 25999, "eta_hours": 2.7, "time": 1790354921.8181844}
{"step": 11650, "loss": 0.0647, "lr_factor": 0.5918, "steps_per_second": 1.377, "tokens_per_second": 25994, "eta_hours": 2.69, "time": 1790354958.5066822}
{"step": 11700, "loss": 0.1068, "lr_factor": 0.5888, "steps_per_second": 1.377, "tokens_per_second": 25997, "eta_hours": 2.68, "time": 1790354994.54688}
{"step": 11750, "loss": 0.0803, "lr_factor": 0.5858, "steps_per_second": 1.377, "tokens_per_second": 26003, "eta_hours": 2.67, "time": 1790355030.8754482}
{"step": 11800, "loss": 0.0972, "lr_factor": 0.5828, "steps_per_second": 1.378, "tokens_per_second": 26004, "eta_hours": 2.66, "time": 1790355066.6560566}
{"step": 11850, "loss": 0.0709, "lr_factor": 0.5798, "steps_per_second": 1.378, "tokens_per_second": 26008, "eta_hours": 2.65, "time": 1790355101.8401399}
{"step": 11900, "loss": 0.077, "lr_factor": 0.5767, "steps_per_second": 1.378, "tokens_per_second": 26006, "eta_hours": 2.64, "time": 1790355139.066832}
{"step": 11950, "loss": 0.087, "lr_factor": 0.5737, "steps_per_second": 1.378, "tokens_per_second": 26012, "eta_hours": 2.63, "time": 1790355175.4944158}
{"step": 12000, "loss": 0.1056, "lr_factor": 0.5707, "steps_per_second": 1.377, "tokens_per_second": 26014, "eta_hours": 2.62, "time": 1790355212.215404}
{"step": 12050, "loss": 0.1063, "lr_factor": 0.5676, "steps_per_second": 1.376, "tokens_per_second": 25989, "eta_hours": 2.61, "time": 1790355251.043001}
{"step": 12100, "loss": 0.0919, "lr_factor": 0.5646, "steps_per_second": 1.376, "tokens_per_second": 25992, "eta_hours": 2.6, "time": 1790355286.9453056}
{"step": 12150, "loss": 0.1127, "lr_factor": 0.5616, "steps_per_second": 1.376, "tokens_per_second": 25990, "eta_hours": 2.59, "time": 1790355323.593656}
{"step": 12200, "loss": 0.1176, "lr_factor": 0.5585, "steps_per_second": 1.377, "tokens_per_second": 25996, "eta_hours": 2.58, "time": 1790355358.85198}
{"step": 12250, "loss": 0.0893, "lr_factor": 0.5555, "steps_per_second": 1.377, "tokens_per_second": 25999, "eta_hours": 2.57, "time": 1790355394.0864422}
{"step": 12300, "loss": 0.0834, "lr_factor": 0.5525, "steps_per_second": 1.378, "tokens_per_second": 26007, "eta_hours": 2.56, "time": 1790355429.8490975}
{"step": 12350, "loss": 0.0936, "lr_factor": 0.5494, "steps_per_second": 1.378, "tokens_per_second": 26013, "eta_hours": 2.55, "time": 1790355466.1885002}
{"step": 12400, "loss": 0.0697, "lr_factor": 0.5464, "steps_per_second": 1.377, "tokens_per_second": 26014, "eta_hours": 2.54, "time": 1790355502.9390879}
{"step": 12450, "loss": 0.13, "lr_factor": 0.5433, "steps_per_second": 1.377, "tokens_per_second": 26016, "eta_hours": 2.53, "time": 1790355539.0062845}
{"step": 12500, "loss": 0.0964, "lr_factor": 0.5403, "steps_per_second": 1.377, "tokens_per_second": 26020, "eta_hours": 2.52, "time": 1790355575.5739343}
{"step": 12550, "loss": 0.0733, "lr_factor": 0.5372, "steps_per_second": 1.376, "tokens_per_second": 25993, "eta_hours": 2.51, "time": 1790355615.2902853}
{"step": 12600, "loss": 0.0939, "lr_factor": 0.5342, "steps_per_second": 1.376, "tokens_per_second": 25993, "eta_hours": 2.5, "time": 1790355650.6994529}
{"step": 12650, "loss": 0.0721, "lr_factor": 0.5312, "steps_per_second": 1.376, "tokens_per_second": 25995, "eta_hours": 2.49, "time": 1790355686.7814848}
{"step": 12700, "loss": 0.0827, "lr_factor": 0.5281, "steps_per_second": 1.376, "tokens_per_second": 25999, "eta_hours": 2.48, "time": 1790355722.9737227}
{"step": 12750, "loss": 0.0895, "lr_factor": 0.5251, "steps_per_second": 1.377, "tokens_per_second": 26005, "eta_hours": 2.47, "time": 1790355758.7187166}
{"step": 12800, "loss": 0.0629, "lr_factor": 0.522, "steps_per_second": 1.377, "tokens_per_second": 26008, "eta_hours": 2.46, "time": 1790355793.9664774}
{"step": 12850, "loss": 0.0798, "lr_factor": 0.519, "steps_per_second": 1.377, "tokens_per_second": 26013, "eta_hours": 2.45, "time": 1790355829.7349632}
{"step": 12900, "loss": 0.1718, "lr_factor": 0.5159, "steps_per_second": 1.377, "tokens_per_second": 26014, "eta_hours": 2.44, "time": 1790355866.831912}
{"step": 12950, "loss": 0.1083, "lr_factor": 0.5129, "steps_per_second": 1.377, "tokens_per_second": 26017, "eta_hours": 2.43, "time": 1790355902.804829}
{"step": 13000, "loss": 0.0822, "lr_factor": 0.5098, "steps_per_second": 1.377, "tokens_per_second": 26019, "eta_hours": 2.42, "time": 1790355938.8569949}
{"step": 13050, "loss": 0.1258, "lr_factor": 0.5068, "steps_per_second": 1.376, "tokens_per_second": 25999, "eta_hours": 2.41, "time": 1790355977.824168}
{"step": 13100, "loss": 0.1176, "lr_factor": 0.5038, "steps_per_second": 1.376, "tokens_per_second": 26001, "eta_hours": 2.4, "time": 1790356013.5338998}
{"step": 13150, "loss": 0.0648, "lr_factor": 0.5007, "steps_per_second": 1.377, "tokens_per_second": 26003, "eta_hours": 2.39, "time": 1790356049.1436288}
{"step": 13200, "loss": 0.0824, "lr_factor": 0.4977, "steps_per_second": 1.377, "tokens_per_second": 26006, "eta_hours": 2.38, "time": 1790356085.3710275}
{"step": 13250, "loss": 0.1054, "lr_factor": 0.4946, "steps_per_second": 1.377, "tokens_per_second": 26006, "eta_hours": 2.37, "time": 1790356120.949615}
{"step": 13300, "loss": 0.0577, "lr_factor": 0.4916, "steps_per_second": 1.377, "tokens_per_second": 26009, "eta_hours": 2.36, "time": 1790356156.9304554}
{"step": 13350, "loss": 0.1674, "lr_factor": 0.4886, "steps_per_second": 1.377, "tokens_per_second": 26010, "eta_hours": 2.35, "time": 1790356193.3751192}
{"step": 13400, "loss": 0.0445, "lr_factor": 0.4855, "steps_per_second": 1.377, "tokens_per_second": 26012, "eta_hours": 2.34, "time": 1790356229.5996175}
{"step": 13450, "loss": 0.109, "lr_factor": 0.4825, "steps_per_second": 1.377, "tokens_per_second": 26016, "eta_hours": 2.33, "time": 1790356265.906521}
{"step": 13500, "loss": 0.0625, "lr_factor": 0.4794, "steps_per_second": 1.377, "tokens_per_second": 26017, "eta_hours": 2.32, "time": 1790356301.8203588}
{"step": 13550, "loss": 0.0771, "lr_factor": 0.4764, "steps_per_second": 1.376, "tokens_per_second": 26003, "eta_hours": 2.31, "time": 1790356340.217182}
{"step": 13600, "loss": 0.0556, "lr_factor": 0.4734, "steps_per_second": 1.376, "tokens_per_second": 26002, "eta_hours": 2.3, "time": 1790356376.7148252}
{"step": 13650, "loss": 0.0839, "lr_factor": 0.4704, "steps_per_second": 1.376, "tokens_per_second": 26004, "eta_hours": 2.29, "time": 1790356413.0101132}
{"step": 13700, "loss": 0.2098, "lr_factor": 0.4673, "steps_per_second": 1.377, "tokens_per_second": 26009, "eta_hours": 2.28, "time": 1790356448.8839376}
{"step": 13750, "loss": 0.0514, "lr_factor": 0.4643, "steps_per_second": 1.377, "tokens_per_second": 26013, "eta_hours": 2.27, "time": 1790356484.4035902}
{"step": 13800, "loss": 0.0887, "lr_factor": 0.4613, "steps_per_second": 1.377, "tokens_per_second": 26016, "eta_hours": 2.26, "time": 1790356520.1521597}
{"step": 13850, "loss": 0.0918, "lr_factor": 0.4583, "steps_per_second": 1.377, "tokens_per_second": 26016, "eta_hours": 2.25, "time": 1790356556.3043268}
{"step": 13900, "loss": 0.1274, "lr_factor": 0.4553, "steps_per_second": 1.377, "tokens_per_second": 26022, "eta_hours": 2.24, "time": 1790356591.7466636}
{"step": 13950, "loss": 0.1599, "lr_factor": 0.4523, "steps_per_second": 1.378, "tokens_per_second": 26025, "eta_hours": 2.23, "time": 1790356627.2769341}
{"step": 14000, "loss": 0.0776, "lr_factor": 0.4493, "steps_per_second": 1.378, "tokens_per_second": 26032, "eta_hours": 2.22, "time": 1790356663.0730813}
{"step": 14050, "loss": 0.0961, "lr_factor": 0.4462, "steps_per_second": 1.377, "tokens_per_second": 26018, "eta_hours": 2.21, "time": 1790356701.5645893}
{"step": 14100, "loss": 0.1381, "lr_factor": 0.4432, "steps_per_second": 1.377, "tokens_per_second": 26015, "eta_hours": 2.2, "time": 1790356738.4007127}
{"step": 14150, "loss": 0.1128, "lr_factor": 0.4402, "steps_per_second": 1.377, "tokens_per_second": 26019, "eta_hours": 2.19, "time": 1790356774.5759695}
{"step": 14200, "loss": 0.0778, "lr_factor": 0.4373, "steps_per_second": 1.377, "tokens_per_second": 26022, "eta_hours": 2.18, "time": 1790356810.6318576}
{"step": 14250, "loss": 0.0698, "lr_factor": 0.4343, "steps_per_second": 1.377, "tokens_per_second": 26026, "eta_hours": 2.17, "time": 1790356847.0838869}
{"step": 14300, "loss": 0.14, "lr_factor": 0.4313, "steps_per_second": 1.377, "tokens_per_second": 26028, "eta_hours": 2.16, "time": 1790356882.9106677}
{"step": 14350, "loss": 0.0686, "lr_factor": 0.4283, "steps_per_second": 1.377, "tokens_per_second": 26027, "eta_hours": 2.15, "time": 1790356919.274097}
{"step": 14400, "loss": 0.0915, "lr_factor": 0.4253, "steps_per_second": 1.377, "tokens_per_second": 26026, "eta_hours": 2.14, "time": 1790356955.8541205}
{"step": 14450, "loss": 0.0876, "lr_factor": 0.4223, "steps_per_second": 1.377, "tokens_per_second": 26027, "eta_hours": 2.13, "time": 1790356992.0459118}
{"step": 14500, "loss": 0.0462, "lr_factor": 0.4194, "steps_per_second": 1.377, "tokens_per_second": 26030, "eta_hours": 2.12, "time": 1790357027.4768026}
{"step": 14550, "loss": 0.0882, "lr_factor": 0.4164, "steps_per_second": 1.377, "tokens_per_second": 26017, "eta_hours": 2.11, "time": 1790357065.9113326}
{"step": 14600, "loss": 0.0904, "lr_factor": 0.4134, "steps_per_second": 1.377, "tokens_per_second": 26019, "eta_hours": 2.1, "time": 1790357102.6147573}
{"step": 14650, "loss": 0.0908, "lr_factor": 0.4105, "steps_per_second": 1.377, "tokens_per_second": 26021, "eta_hours": 2.09, "time": 1790357138.9379063}
{"step": 14700, "loss": 0.0693, "lr_factor": 0.4075, "steps_per_second": 1.377, "tokens_per_second": 26025, "eta_hours": 2.08, "time": 1790357174.5358071}
{"step": 14750, "loss": 0.125, "lr_factor": 0.4046, "steps_per_second": 1.377, "tokens_per_second": 26028, "eta_hours": 2.07, "time": 1790357210.476818}
{"step": 14800, "loss": 0.0849, "lr_factor": 0.4016, "steps_per_second": 1.377, "tokens_per_second": 26030, "eta_hours": 2.06, "time": 1790357246.4076366}
{"step": 14850, "loss": 0.16, "lr_factor": 0.3987, "steps_per_second": 1.377, "tokens_per_second": 26031, "eta_hours": 2.05, "time": 1790357282.5719993}
{"step": 14900, "loss": 0.0831, "lr_factor": 0.3958, "steps_per_second": 1.377, "tokens_per_second": 26033, "eta_hours": 2.04, "time": 1790357319.0367591}
{"step": 14950, "loss": 0.0624, "lr_factor": 0.3928, "steps_per_second": 1.377, "tokens_per_second": 26035, "eta_hours": 2.03, "time": 1790357355.0465484}
{"step": 15000, "loss": 0.0812, "lr_factor": 0.3899, "steps_per_second": 1.377, "tokens_per_second": 26037, "eta_hours": 2.02, "time": 1790357392.206836}
{"step": 15050, "loss": 0.1017, "lr_factor": 0.387, "steps_per_second": 1.376, "tokens_per_second": 26022, "eta_hours": 2.01, "time": 1790357431.145247}
{"step": 15100, "loss": 0.101, "lr_factor": 0.3841, "steps_per_second": 1.376, "tokens_per_second": 26025, "eta_hours": 2.0, "time": 1790357467.422023}
{"step": 15150, "loss": 0.0981, "lr_factor": 0.3812, "steps_per_second": 1.376, "tokens_per_second": 26028, "eta_hours": 1.99, "time": 1790357503.0998785}
{"step": 15200, "loss": 0.1002, "lr_factor": 0.3783, "steps_per_second": 1.376, "tokens_per_second": 26030, "eta_hours": 1.98, "time": 1790357539.2400293}
{"step": 15250, "loss": 0.0935, "lr_factor": 0.3754, "steps_per_second": 1.377, "tokens_per_second": 26033, "eta_hours": 1.97, "time": 1790357574.6404016}
{"step": 15300, "loss": 0.073, "lr_factor": 0.3725, "steps_per_second": 1.377, "tokens_per_second": 26036, "eta_hours": 1.96, "time": 1790357610.5660443}
{"step": 15350, "loss": 0.0726, "lr_factor": 0.3696, "steps_per_second": 1.377, "tokens_per_second": 26036, "eta_hours": 1.95, "time": 1790357647.0707479}
{"step": 15400, "loss": 0.1192, "lr_factor": 0.3667, "steps_per_second": 1.377, "tokens_per_second": 26039, "eta_hours": 1.94, "time": 1790357682.8697503}
{"step": 15450, "loss": 0.0752, "lr_factor": 0.3639, "steps_per_second": 1.377, "tokens_per_second": 26041, "eta_hours": 1.93, "time": 1790357719.214488}
{"step": 15500, "loss": 0.0746, "lr_factor": 0.361, "steps_per_second": 1.377, "tokens_per_second": 26042, "eta_hours": 1.92, "time": 1790357755.0163794}
{"step": 15550, "loss": 0.1303, "lr_factor": 0.3582, "steps_per_second": 1.376, "tokens_per_second": 26029, "eta_hours": 1.91, "time": 1790357794.2576253}
{"step": 15600, "loss": 0.0652, "lr_factor": 0.3553, "steps_per_second": 1.376, "tokens_per_second": 26027, "eta_hours": 1.9, "time": 1790357830.7314842}
{"step": 15650, "loss": 0.0748, "lr_factor": 0.3525, "steps_per_second": 1.376, "tokens_per_second": 26030, "eta_hours": 1.89, "time": 1790357866.2076914}
{"step": 15700, "loss": 0.1982, "lr_factor": 0.3496, "steps_per_second": 1.376, "tokens_per_second": 26031, "eta_hours": 1.88, "time": 1790357902.8128972}
{"step": 15750, "loss": 0.1073, "lr_factor": 0.3468, "steps_per_second": 1.376, "tokens_per_second": 26034, "eta_hours": 1.87, "time": 1790357938.5319774}
{"step": 15800, "loss": 0.0599, "lr_factor": 0.344, "steps_per_second": 1.376, "tokens_per_second": 26035, "eta_hours": 1.86, "time": 1790357974.790803}
{"step": 15850, "loss": 0.0631, "lr_factor": 0.3412, "steps_per_second": 1.377, "tokens_per_second": 26036, "eta_hours": 1.85, "time": 1790358010.1593542}
{"step": 15900, "loss": 0.0763, "lr_factor": 0.3384, "steps_per_second": 1.377, "tokens_per_second": 26038, "eta_hours": 1.84, "time": 1790358046.26416}
{"step": 15950, "loss": 0.1064, "lr_factor": 0.3356, "steps_per_second": 1.377, "tokens_per_second": 26039, "eta_hours": 1.83, "time": 1790358082.4689412}
{"step": 16000, "loss": 0.0941, "lr_factor": 0.3328, "steps_per_second": 1.377, "tokens_per_second": 26041, "eta_hours": 1.82, "time": 1790358118.0720263}
{"step": 16050, "loss": 0.07, "lr_factor": 0.33, "steps_per_second": 1.376, "tokens_per_second": 26026, "eta_hours": 1.81, "time": 1790358157.7685213}
{"step": 16100, "loss": 0.1, "lr_factor": 0.3272, "steps_per_second": 1.376, "tokens_per_second": 26027, "eta_hours": 1.8, "time": 1790358193.2815816}
{"step": 16150, "loss": 0.0993, "lr_factor": 0.3245, "steps_per_second": 1.376, "tokens_per_second": 26030, "eta_hours": 1.79, "time": 1790358228.9453185}
{"step": 16200, "loss": 0.0694, "lr_factor": 0.3217, "steps_per_second": 1.376, "tokens_per_second": 26032, "eta_hours": 1.78, "time": 1790358265.2931669}
{"step": 16250, "loss": 0.0497, "lr_factor": 0.319, "steps_per_second": 1.377, "tokens_per_second": 26035, "eta_hours": 1.77, "time": 1790358300.7220218}
{"step": 16300, "loss": 0.0583, "lr_factor": 0.3162, "steps_per_second": 1.377, "tokens_per_second": 26035, "eta_hours": 1.76, "time": 1790358336.8863585}
{"step": 16350, "loss": 0.0524, "lr_factor": 0.3135, "steps_per_second": 1.377, "tokens_per_second": 26038, "eta_hours": 1.74, "time": 1790358372.2944288}
{"step": 16400, "loss": 0.0685, "lr_factor": 0.3108, "steps_per_second": 1.377, "tokens_per_second": 26039, "eta_hours": 1.73, "time": 1790358408.0507495}
{"step": 16450, "loss": 0.0487, "lr_factor": 0.3081, "steps_per_second": 1.377, "tokens_per_second": 26041, "eta_hours": 1.72, "time": 1790358444.1824112}
{"step": 16500, "loss": 0.0494, "lr_factor": 0.3053, "steps_per_second": 1.377, "tokens_per_second": 26044, "eta_hours": 1.71, "time": 1790358479.8340104}
{"step": 16550, "loss": 0.0823, "lr_factor": 0.3027, "steps_per_second": 1.376, "tokens_per_second": 26029, "eta_hours": 1.71, "time": 1790358519.7339365}
{"step": 16600, "loss": 0.0707, "lr_factor": 0.3, "steps_per_second": 1.377, "tokens_per_second": 26031, "eta_hours": 1.7, "time": 1790358555.6325462}
{"step": 16650, "loss": 0.1404, "lr_factor": 0.2973, "steps_per_second": 1.377, "tokens_per_second": 26033, "eta_hours": 1.68, "time": 1790358590.8278325}
{"step": 16700, "loss": 0.0623, "lr_factor": 0.2946, "steps_per_second": 1.377, "tokens_per_second": 26034, "eta_hours": 1.67, "time": 1790358627.185009}
{"step": 16750, "loss": 0.0663, "lr_factor": 0.292, "steps_per_second": 1.377, "tokens_per_second": 26036, "eta_hours": 1.66, "time": 1790358663.0606852}
{"step": 16800, "loss": 0.1039, "lr_factor": 0.2893, "steps_per_second": 1.377, "tokens_per_second": 26035, "eta_hours": 1.65, "time": 1790358699.8069153}
{"step": 16850, "loss": 0.0856, "lr_factor": 0.2867, "steps_per_second": 1.377, "tokens_per_second": 26037, "eta_hours": 1.64, "time": 1790358735.7757888}
{"step": 16900, "loss": 0.0937, "lr_factor": 0.284, "steps_per_second": 1.377, "tokens_per_second": 26040, "eta_hours": 1.63, "time": 1790358771.7256684}
{"step": 16950, "loss": 0.1246, "lr_factor": 0.2814, "steps_per_second": 1.377, "tokens_per_second": 26042, "eta_hours": 1.62, "time": 1790358807.200881}
{"step": 17000, "loss": 0.0577, "lr_factor": 0.2788, "steps_per_second": 1.377, "tokens_per_second": 26044, "eta_hours": 1.61, "time": 1790358843.0246375}
{"step": 17050, "loss": 0.0901, "lr_factor": 0.2762, "steps_per_second": 1.377, "tokens_per_second": 26032, "eta_hours": 1.6, "time": 1790358882.3763595}
{"step": 17100, "loss": 0.0849, "lr_factor": 0.2736, "steps_per_second": 1.377, "tokens_per_second": 26034, "eta_hours": 1.59, "time": 1790358918.007631}
{"step": 17150, "loss": 0.1181, "lr_factor": 0.271, "steps_per_second": 1.377, "tokens_per_second": 26035, "eta_hours": 1.58, "time": 1790358954.087293}
{"step": 17200, "loss": 0.0636, "lr_factor": 0.2685, "steps_per_second": 1.377, "tokens_per_second": 26038, "eta_hours": 1.57, "time": 1790358989.3116539}
{"step": 17250, "loss": 0.0519, "lr_factor": 0.2659, "steps_per_second": 1.377, "tokens_per_second": 26040, "eta_hours": 1.56, "time": 1790359025.445062}
{"step": 17300, "loss": 0.0494, "lr_factor": 0.2634, "steps_per_second": 1.377, "tokens_per_second": 26039, "eta_hours": 1.55, "time": 1790359062.0393038}
{"step": 17350, "loss": 0.051, "lr_factor": 0.2608, "steps_per_second": 1.377, "tokens_per_second": 26040, "eta_hours": 1.54, "time": 1790359097.0855901}
{"step": 17400, "loss": 0.0706, "lr_factor": 0.2583, "steps_per_second": 1.377, "tokens_per_second": 26044, "eta_hours": 1.53, "time": 1790359132.7785854}
{"step": 17450, "loss": 0.0912, "lr_factor": 0.2558, "steps_per_second": 1.378, "tokens_per_second": 26046, "eta_hours": 1.52, "time": 1790359168.4985967}
{"step": 17500, "loss": 0.0833, "lr_factor": 0.2533, "steps_per_second": 1.377, "tokens_per_second": 26047, "eta_hours": 1.51, "time": 1790359205.1381629}
{"step": 17550, "loss": 0.1001, "lr_factor": 0.2508, "steps_per_second": 1.377, "tokens_per_second": 26037, "eta_hours": 1.5, "time": 1790359244.9598231}
{"step": 17600, "loss": 0.0555, "lr_factor": 0.2483, "steps_per_second": 1.377, "tokens_per_second": 26038, "eta_hours": 1.49, "time": 1790359280.9969356}
{"step": 17650, "loss": 0.0656, "lr_factor": 0.2459, "steps_per_second": 1.377, "tokens_per_second": 26041, "eta_hours": 1.48, "time": 1790359315.9222383}
{"step": 17700, "loss": 0.0712, "lr_factor": 0.2434, "steps_per_second": 1.377, "tokens_per_second": 26041, "eta_hours": 1.47, "time": 1790359352.2163963}
{"step": 17750, "loss": 0.0856, "lr_factor": 0.2409, "steps_per_second": 1.377, "tokens_per_second": 26042, "eta_hours": 1.46, "time": 1790359387.9277964}
{"step": 17800, "loss": 0.069, "lr_factor": 0.2385, "steps_per_second": 1.377, "tokens_per_second": 26043, "eta_hours": 1.45, "time": 1790359423.565699}
{"step": 17850, "loss": 0.0466, "lr_factor": 0.2361, "steps_per_second": 1.377, "tokens_per_second": 26044, "eta_hours": 1.44, "time": 1790359459.8124547}
{"step": 17900, "loss": 0.113, "lr_factor": 0.2337, "steps_per_second": 1.377, "tokens_per_second": 26046, "eta_hours": 1.43, "time": 1790359495.6685646}
{"step": 17950, "loss": 0.053, "lr_factor": 0.2313, "steps_per_second": 1.377, "tokens_per_second": 26047, "eta_hours": 1.42, "time": 1790359531.7091415}
{"step": 18000, "loss": 0.0727, "lr_factor": 0.2289, "steps_per_second": 1.377, "tokens_per_second": 26049, "eta_hours": 1.41, "time": 1790359567.927576}
{"step": 18050, "loss": 0.0871, "lr_factor": 0.2265, "steps_per_second": 1.377, "tokens_per_second": 26038, "eta_hours": 1.4, "time": 1790359607.1206784}
{"step": 18100, "loss": 0.0559, "lr_factor": 0.2242, "steps_per_second": 1.377, "tokens_per_second": 26039, "eta_hours": 1.39, "time": 1790359643.2203047}
{"step": 18150, "loss": 0.0571, "lr_factor": 0.2218, "steps_per_second": 1.377, "tokens_per_second": 26041, "eta_hours": 1.38, "time": 1790359678.9685543}
{"step": 18200, "loss": 0.1378, "lr_factor": 0.2195, "steps_per_second": 1.377, "tokens_per_second": 26042, "eta_hours": 1.37, "time": 1790359714.7249663}
{"step": 18250, "loss": 0.0543, "lr_factor": 0.2171, "steps_per_second": 1.377, "tokens_per_second": 26043, "eta_hours": 1.36, "time": 1790359750.5357544}
{"step": 18300, "loss": 0.0954, "lr_factor": 0.2148, "steps_per_second": 1.378, "tokens_per_second": 26046, "eta_hours": 1.35, "time": 1790359785.689961}
{"step": 18350, "loss": 0.1139, "lr_factor": 0.2125, "steps_per_second": 1.378, "tokens_per_second": 26048, "eta_hours": 1.34, "time": 1790359821.5125258}
{"step": 18400, "loss": 0.0916, "lr_factor": 0.2102, "steps_per_second": 1.378, "tokens_per_second": 26049, "eta_hours": 1.33, "time": 1790359857.0951138}
{"step": 18450, "loss": 0.0467, "lr_factor": 0.208, "steps_per_second": 1.378, "tokens_per_second": 26051, "eta_hours": 1.32, "time": 1790359893.0415123}
{"step": 18500, "loss": 0.0847, "lr_factor": 0.2057, "steps_per_second": 1.378, "tokens_per_second": 26052, "eta_hours": 1.31, "time": 1790359929.1695893}
{"step": 18550, "loss": 0.0765, "lr_factor": 0.2035, "steps_per_second": 1.377, "tokens_per_second": 26042, "eta_hours": 1.3, "time": 1790359968.4360085}
{"step": 18600, "loss": 0.0654, "lr_factor": 0.2012, "steps_per_second": 1.377, "tokens_per_second": 26044, "eta_hours": 1.29, "time": 1790360004.2517514}
{"step": 18650, "loss": 0.0732, "lr_factor": 0.199, "steps_per_second": 1.377, "tokens_per_second": 26046, "eta_hours": 1.28, "time": 1790360039.804735}
{"step": 18700, "loss": 0.0559, "lr_factor": 0.1968, "steps_per_second": 1.378, "tokens_per_second": 26048, "eta_hours": 1.27, "time": 1790360075.3677948}
{"step": 18750, "loss": 0.0688, "lr_factor": 0.1946, "steps_per_second": 1.378, "tokens_per_second": 26049, "eta_hours": 1.26, "time": 1790360111.3004923}
{"step": 18800, "loss": 0.0797, "lr_factor": 0.1924, "steps_per_second": 1.378, "tokens_per_second": 26051, "eta_hours": 1.25, "time": 1790360147.0819423}
{"step": 18850, "loss": 0.0792, "lr_factor": 0.1902, "steps_per_second": 1.378, "tokens_per_second": 26053, "eta_hours": 1.24, "time": 1790360183.0007753}
{"step": 18900, "loss": 0.0844, "lr_factor": 0.1881, "steps_per_second": 1.378, "tokens_per_second": 26053, "eta_hours": 1.23, "time": 1790360219.6549528}
{"step": 18950, "loss": 0.0433, "lr_factor": 0.186, "steps_per_second": 1.378, "tokens_per_second": 26055, "eta_hours": 1.22, "time": 1790360255.6766915}
{"step": 19000, "loss": 0.1254, "lr_factor": 0.1838, "steps_per_second": 1.378, "tokens_per_second": 26054, "eta_hours": 1.21, "time": 1790360291.0161633}
{"step": 19050, "loss": 0.1026, "lr_factor": 0.1817, "steps_per_second": 1.378, "tokens_per_second": 26046, "eta_hours": 1.2, "time": 1790360329.5958493}
{"step": 19100, "loss": 0.0714, "lr_factor": 0.1796, "steps_per_second": 1.378, "tokens_per_second": 26046, "eta_hours": 1.19, "time": 1790360365.4057753}
{"step": 19150, "loss": 0.075, "lr_factor": 0.1775, "steps_per_second": 1.378, "tokens_per_second": 26047, "eta_hours": 1.18, "time": 1790360401.717723}
{"step": 19200, "loss": 0.126, "lr_factor": 0.1755, "steps_per_second": 1.378, "tokens_per_second": 26048, "eta_hours": 1.17, "time": 1790360437.684595}
{"step": 19250, "loss": 0.1253, "lr_factor": 0.1734, "steps_per_second": 1.378, "tokens_per_second": 26049, "eta_hours": 1.16, "time": 1790360474.0088816}
{"step": 19300, "loss": 0.0619, "lr_factor": 0.1714, "steps_per_second": 1.378, "tokens_per_second": 26053, "eta_hours": 1.15, "time": 1790360509.4471722}
{"step": 19350, "loss": 0.0765, "lr_factor": 0.1693, "steps_per_second": 1.378, "tokens_per_second": 26054, "eta_hours": 1.14, "time": 1790360545.8796985}
{"step": 19400, "loss": 0.0433, "lr_factor": 0.1673, "steps_per_second": 1.378, "tokens_per_second": 26055, "eta_hours": 1.13, "time": 1790360581.8818579}
{"step": 19450, "loss": 0.1062, "lr_factor": 0.1653, "steps_per_second": 1.378, "tokens_per_second": 26056, "eta_hours": 1.12, "time": 1790360618.3914886}
{"step": 19500, "loss": 0.0645, "lr_factor": 0.1634, "steps_per_second": 1.378, "tokens_per_second": 26056, "eta_hours": 1.11, "time": 1790360654.8149006}
{"step": 19550, "loss": 0.0999, "lr_factor": 0.1614, "steps_per_second": 1.378, "tokens_per_second": 26049, "eta_hours": 1.1, "time": 1790360693.1364048}
{"step": 19600, "loss": 0.0562, "lr_factor": 0.1594, "steps_per_second": 1.378, "tokens_per_second": 26050, "eta_hours": 1.09, "time": 1790360729.3231854}
{"step": 19650, "loss": 0.1466, "lr_factor": 0.1575, "steps_per_second": 1.378, "tokens_per_second": 26053, "eta_hours": 1.08, "time": 1790360764.8755758}
{"step": 19700, "loss": 0.0535, "lr_factor": 0.1556, "steps_per_second": 1.378, "tokens_per_second": 26055, "eta_hours": 1.07, "time": 1790360800.8742464}
{"step": 19750, "loss": 0.1025, "lr_factor": 0.1537, "steps_per_second": 1.378, "tokens_per_second": 26055, "eta_hours": 1.06, "time": 1790360837.2883663}
{"step": 19800, "loss": 0.0582, "lr_factor": 0.1518, "steps_per_second": 1.378, "tokens_per_second": 26056, "eta_hours": 1.05, "time": 1790360872.4150934}
{"step": 19850, "loss": 0.0572, "lr_factor": 0.1499, "steps_per_second": 1.378, "tokens_per_second": 26056, "eta_hours": 1.04, "time": 1790360908.7948172}
{"step": 19900, "loss": 0.0676, "lr_factor": 0.148, "steps_per_second": 1.378, "tokens_per_second": 26057, "eta_hours": 1.03, "time": 1790360945.1450064}
{"step": 19950, "loss": 0.0749, "lr_factor": 0.1462, "steps_per_second": 1.378, "tokens_per_second": 26058, "eta_hours": 1.02, "time": 1790360980.8396041}
{"step": 20000, "loss": 0.0842, "lr_factor": 0.1444, "steps_per_second": 1.378, "tokens_per_second": 26057, "eta_hours": 1.01, "time": 1790361017.929973}
{"step": 20050, "loss": 0.0832, "lr_factor": 0.1426, "steps_per_second": 1.377, "tokens_per_second": 26050, "eta_hours": 1.0, "time": 1790361056.62579}
{"step": 20100, "loss": 0.0529, "lr_factor": 0.1408, "steps_per_second": 1.378, "tokens_per_second": 26053, "eta_hours": 0.99, "time": 1790361091.8921676}
{"step": 20150, "loss": 0.1112, "lr_factor": 0.139, "steps_per_second": 1.378, "tokens_per_second": 26054, "eta_hours": 0.98, "time": 1790361127.6191907}
{"step": 20200, "loss": 0.0686, "lr_factor": 0.1372, "steps_per_second": 1.378, "tokens_per_second": 26055, "eta_hours": 0.97, "time": 1790361164.2685142}
{"step": 20250, "loss": 0.1072, "lr_factor": 0.1355, "steps_per_second": 1.378, "tokens_per_second": 26055, "eta_hours": 0.96, "time": 1790361200.6588829}
{"step": 20300, "loss": 0.0689, "lr_factor": 0.1337, "steps_per_second": 1.378, "tokens_per_second": 26056, "eta_hours": 0.95, "time": 1790361236.529403}
{"step": 20350, "loss": 0.0879, "lr_factor": 0.132, "steps_per_second": 1.378, "tokens_per_second": 26057, "eta_hours": 0.94, "time": 1790361272.5495267}
{"step": 20400, "loss": 0.1063, "lr_factor": 0.1303, "steps_per_second": 1.378, "tokens_per_second": 26058, "eta_hours": 0.93, "time": 1790361308.4308362}
{"step": 20450, "loss": 0.0721, "lr_factor": 0.1286, "steps_per_second": 1.378, "tokens_per_second": 26058, "eta_hours": 0.92, "time": 1790361344.4174623}
{"step": 20500, "loss": 0.0935, "lr_factor": 0.1269, "steps_per_second": 1.378, "tokens_per_second": 26060, "eta_hours": 0.91, "time": 1790361380.0353096}
{"step": 20550, "loss": 0.074, "lr_factor": 0.1253, "steps_per_second": 1.377, "tokens_per_second": 26051, "eta_hours": 0.9, "time": 1790361419.2978814}
{"step": 20600, "loss": 0.0784, "lr_factor": 0.1237, "steps_per_second": 1.377, "tokens_per_second": 26052, "eta_hours": 0.89, "time": 1790361455.7827687}
{"step": 20650, "loss": 0.0474, "lr_factor": 0.122, "steps_per_second": 1.378, "tokens_per_second": 26052, "eta_hours": 0.88, "time": 1790361491.113181}
{"step": 20700, "loss": 0.0805, "lr_factor": 0.1204, "steps_per_second": 1.378, "tokens_per_second": 26051, "eta_hours": 0.87, "time": 1790361526.5643394}
{"step": 20750, "loss": 0.077, "lr_factor": 0.1188, "steps_per_second": 1.378, "tokens_per_second": 26052, "eta_hours": 0.86, "time": 1790361562.2215903}
{"step": 20800, "loss": 0.0812, "lr_factor": 0.1173, "steps_per_second": 1.378, "tokens_per_second": 26052, "eta_hours": 0.85, "time": 1790361598.3463547}
{"step": 20850, "loss": 0.0496, "lr_factor": 0.1157, "steps_per_second": 1.378, "tokens_per_second": 26053, "eta_hours": 0.84, "time": 1790361634.2216063}
{"step": 20900, "loss": 0.0898, "lr_factor": 0.1142, "steps_per_second": 1.378, "tokens_per_second": 26055, "eta_hours": 0.83, "time": 1790361670.1678305}
{"step": 20950, "loss": 0.119, "lr_factor": 0.1127, "steps_per_second": 1.378, "tokens_per_second": 26053, "eta_hours": 0.82, "time": 1790361707.1217592}
{"step": 21000, "loss": 0.0676, "lr_factor": 0.1112, "steps_per_second": 1.378, "tokens_per_second": 26053, "eta_hours": 0.81, "time": 1790361743.4637375}
{"step": 21050, "loss": 0.0779, "lr_factor": 0.1097, "steps_per_second": 1.377, "tokens_per_second": 26045, "eta_hours": 0.8, "time": 1790361782.3896015}
{"step": 21100, "loss": 0.0632, "lr_factor": 0.1082, "steps_per_second": 1.377, "tokens_per_second": 26045, "eta_hours": 0.79, "time": 1790361818.8907874}
{"step": 21150, "loss": 0.0566, "lr_factor": 0.1067, "steps_per_second": 1.377, "tokens_per_second": 26042, "eta_hours": 0.78, "time": 1790361855.7334638}
{"step": 21200, "loss": 0.0788, "lr_factor": 0.1053, "steps_per_second": 1.377, "tokens_per_second": 26040, "eta_hours": 0.77, "time": 1790361892.3226647}
{"step": 21250, "loss": 0.0721, "lr_factor": 0.1039, "steps_per_second": 1.377, "tokens_per_second": 26040, "eta_hours": 0.76, "time": 1790361928.7731442}
{"step": 21300, "loss": 0.0733, "lr_factor": 0.1025, "steps_per_second": 1.377, "tokens_per_second": 26039, "eta_hours": 0.75, "time": 1790361964.914121}
{"step": 21350, "loss": 0.0761, "lr_factor": 0.1011, "steps_per_second": 1.377, "tokens_per_second": 26039, "eta_hours": 0.74, "time": 1790362001.0486796}
{"step": 21400, "loss": 0.044, "lr_factor": 0.0997, "steps_per_second": 1.377, "tokens_per_second": 26039, "eta_hours": 0.73, "time": 1790362037.423049}
{"step": 21450, "loss": 0.0482, "lr_factor": 0.0984, "steps_per_second": 1.377, "tokens_per_second": 26036, "eta_hours": 0.72, "time": 1790362074.7028809}
{"step": 21500, "loss": 0.0739, "lr_factor": 0.0971, "steps_per_second": 1.377, "tokens_per_second": 26036, "eta_hours": 0.71, "time": 1790362111.660852}
{"step": 21550, "loss": 0.0576, "lr_factor": 0.0958, "steps_per_second": 1.377, "tokens_per_second": 26026, "eta_hours": 0.7, "time": 1790362151.5311484}
{"step": 21600, "loss": 0.0869, "lr_factor": 0.0945, "steps_per_second": 1.377, "tokens_per_second": 26026, "eta_hours": 0.69, "time": 1790362188.2030578}
{"step": 21650, "loss": 0.0785, "lr_factor": 0.0932, "steps_per_second": 1.377, "tokens_per_second": 26026, "eta_hours": 0.68, "time": 1790362224.2518697}
{"step": 21700, "loss": 0.0454, "lr_factor": 0.0919, "steps_per_second": 1.376, "tokens_per_second": 26025, "eta_hours": 0.67, "time": 1790362261.0318668}
{"step": 21750, "loss": 0.0604, "lr_factor": 0.0907, "steps_per_second": 1.376, "tokens_per_second": 26024, "eta_hours": 0.66, "time": 1790362297.5078878}
{"step": 21800, "loss": 0.0642, "lr_factor": 0.0895, "steps_per_second": 1.376, "tokens_per_second": 26024, "eta_hours": 0.65, "time": 1790362333.8714485}
{"step": 21850, "loss": 0.069, "lr_factor": 0.0882, "steps_per_second": 1.376, "tokens_per_second": 26023, "eta_hours": 0.64, "time": 1790362370.000825}
{"step": 21900, "loss": 0.1025, "lr_factor": 0.0871, "steps_per_second": 1.376, "tokens_per_second": 26023, "eta_hours": 0.63, "time": 1790362406.4367347}
{"step": 21950, "loss": 0.0804, "lr_factor": 0.0859, "steps_per_second": 1.376, "tokens_per_second": 26021, "eta_hours": 0.62, "time": 1790362443.512592}
{"step": 22000, "loss": 0.0745, "lr_factor": 0.0847, "steps_per_second": 1.376, "tokens_per_second": 26021, "eta_hours": 0.61, "time": 1790362479.7590082}
{"step": 22050, "loss": 0.0553, "lr_factor": 0.0836, "steps_per_second": 1.376, "tokens_per_second": 26014, "eta_hours": 0.6, "time": 1790362518.8919196}
{"step": 22100, "loss": 0.0705, "lr_factor": 0.0825, "steps_per_second": 1.376, "tokens_per_second": 26013, "eta_hours": 0.59, "time": 1790362555.8408813}
{"step": 22150, "loss": 0.0744, "lr_factor": 0.0814, "steps_per_second": 1.376, "tokens_per_second": 26014, "eta_hours": 0.58, "time": 1790362592.4643714}
{"step": 22200, "loss": 0.0858, "lr_factor": 0.0803, "steps_per_second": 1.376, "tokens_per_second": 26012, "eta_hours": 0.57, "time": 1790362629.563581}
{"step": 22250, "loss": 0.0673, "lr_factor": 0.0792, "steps_per_second": 1.376, "tokens_per_second": 26010, "eta_hours": 0.56, "time": 1790362666.6749337}
{"step": 22300, "loss": 0.057, "lr_factor": 0.0782, "steps_per_second": 1.376, "tokens_per_second": 26010, "eta_hours": 0.55, "time": 1790362702.9830034}
{"step": 22350, "loss": 0.0755, "lr_factor": 0.0772, "steps_per_second": 1.376, "tokens_per_second": 26010, "eta_hours": 0.54, "time": 1790362739.8632853}
{"step": 22400, "loss": 0.0753, "lr_factor": 0.0762, "steps_per_second": 1.376, "tokens_per_second": 26010, "eta_hours": 0.53, "time": 1790362776.690162}
{"step": 22450, "loss": 0.0904, "lr_factor": 0.0752, "steps_per_second": 1.375, "tokens_per_second": 26008, "eta_hours": 0.52, "time": 1790362814.1015608}
{"step": 22500, "loss": 0.0614, "lr_factor": 0.0742, "steps_per_second": 1.375, "tokens_per_second": 26008, "eta_hours": 0.5, "time": 1790362849.9650576}
{"step": 22550, "loss": 0.065, "lr_factor": 0.0733, "steps_per_second": 1.375, "tokens_per_second": 26001, "eta_hours": 0.49, "time": 1790362889.13605}
{"step": 22600, "loss": 0.0746, "lr_factor": 0.0723, "steps_per_second": 1.375, "tokens_per_second": 26000, "eta_hours": 0.48, "time": 1790362924.5911744}
{"step": 22650, "loss": 0.0699, "lr_factor": 0.0714, "steps_per_second": 1.375, "tokens_per_second": 26001, "eta_hours": 0.47, "time": 1790362960.841097}
{"step": 22700, "loss": 0.0747, "lr_factor": 0.0705, "steps_per_second": 1.375, "tokens_per_second": 26000, "eta_hours": 0.46, "time": 1790362997.9782946}
{"step": 22750, "loss": 0.0823, "lr_factor": 0.0697, "steps_per_second": 1.375, "tokens_per_second": 26001, "eta_hours": 0.45, "time": 1790363034.5096972}
{"step": 22800, "loss": 0.0893, "lr_factor": 0.0688, "steps_per_second": 1.375, "tokens_per_second": 26000, "eta_hours": 0.44, "time": 1790363070.998902}
{"step": 22850, "loss": 0.0804, "lr_factor": 0.068, "steps_per_second": 1.375, "tokens_per_second": 26000, "eta_hours": 0.43, "time": 1790363107.92292}
{"step": 22900, "loss": 0.0633, "lr_factor": 0.0671, "steps_per_second": 1.375, "tokens_per_second": 25999, "eta_hours": 0.42, "time": 1790363144.8340626}
{"step": 22950, "loss": 0.0719, "lr_factor": 0.0663, "steps_per_second": 1.375, "tokens_per_second": 25999, "eta_hours": 0.41, "time": 1790363181.5248532}
{"step": 23000, "loss": 0.0511, "lr_factor": 0.0656, "steps_per_second": 1.375, "tokens_per_second": 25999, "eta_hours": 0.4, "time": 1790363216.6715717}
{"step": 23050, "loss": 0.0459, "lr_factor": 0.0648, "steps_per_second": 1.375, "tokens_per_second": 25992, "eta_hours": 0.39, "time": 1790363255.4991956}
{"step": 23100, "loss": 0.0976, "lr_factor": 0.064, "steps_per_second": 1.375, "tokens_per_second": 25993, "eta_hours": 0.38, "time": 1790363292.0613587}
{"step": 23150, "loss": 0.1347, "lr_factor": 0.0633, "steps_per_second": 1.375, "tokens_per_second": 25991, "eta_hours": 0.37, "time": 1790363329.3014078}
{"step": 23200, "loss": 0.1633, "lr_factor": 0.0626, "steps_per_second": 1.375, "tokens_per_second": 25992, "eta_hours": 0.36, "time": 1790363365.3048346}
{"step": 23250, "loss": 0.0522, "lr_factor": 0.0619, "steps_per_second": 1.375, "tokens_per_second": 25992, "eta_hours": 0.35, "time": 1790363401.465069}
{"step": 23300, "loss": 0.0997, "lr_factor": 0.0613, "steps_per_second": 1.375, "tokens_per_second": 25992, "eta_hours": 0.34, "time": 1790363437.5017488}
{"step": 23350, "loss": 0.0667, "lr_factor": 0.0606, "steps_per_second": 1.375, "tokens_per_second": 25993, "eta_hours": 0.33, "time": 1790363473.0948305}
{"step": 23400, "loss": 0.0673, "lr_factor": 0.06, "steps_per_second": 1.375, "tokens_per_second": 25993, "eta_hours": 0.32, "time": 1790363509.5854023}
{"step": 23450, "loss": 0.1012, "lr_factor": 0.0594, "steps_per_second": 1.375, "tokens_per_second": 25993, "eta_hours": 0.31, "time": 1790363546.1665049}
{"step": 23500, "loss": 0.0757, "lr_factor": 0.0588, "steps_per_second": 1.375, "tokens_per_second": 25993, "eta_hours": 0.3, "time": 1790363582.412394}
{"step": 23550, "loss": 0.0643, "lr_factor": 0.0582, "steps_per_second": 1.374, "tokens_per_second": 25987, "eta_hours": 0.29, "time": 1790363621.4975178}
{"step": 23600, "loss": 0.0483, "lr_factor": 0.0576, "steps_per_second": 1.374, "tokens_per_second": 25987, "eta_hours": 0.28, "time": 1790363657.818135}
{"step": 23650, "loss": 0.0629, "lr_factor": 0.0571, "steps_per_second": 1.374, "tokens_per_second": 25986, "eta_hours": 0.27, "time": 1790363694.1579716}
{"step": 23700, "loss": 0.0755, "lr_factor": 0.0566, "steps_per_second": 1.374, "tokens_per_second": 25986, "eta_hours": 0.26, "time": 1790363730.9194317}
{"step": 23750, "loss": 0.0665, "lr_factor": 0.0561, "steps_per_second": 1.374, "tokens_per_second": 25987, "eta_hours": 0.25, "time": 1790363767.207319}
{"step": 23800, "loss": 0.0639, "lr_factor": 0.0556, "steps_per_second": 1.374, "tokens_per_second": 25987, "eta_hours": 0.24, "time": 1790363803.273214}
{"step": 23850, "loss": 0.0718, "lr_factor": 0.0552, "steps_per_second": 1.374, "tokens_per_second": 25987, "eta_hours": 0.23, "time": 1790363839.7882826}
{"step": 23900, "loss": 0.0498, "lr_factor": 0.0547, "steps_per_second": 1.374, "tokens_per_second": 25987, "eta_hours": 0.22, "time": 1790363875.8785164}
{"step": 23950, "loss": 0.0608, "lr_factor": 0.0543, "steps_per_second": 1.374, "tokens_per_second": 25987, "eta_hours": 0.21, "time": 1790363912.32346}
{"step": 24000, "loss": 0.0922, "lr_factor": 0.0539, "steps_per_second": 1.374, "tokens_per_second": 25986, "eta_hours": 0.2, "time": 1790363949.0123184}
{"step": 24050, "loss": 0.0499, "lr_factor": 0.0535, "steps_per_second": 1.374, "tokens_per_second": 25979, "eta_hours": 0.19, "time": 1790363988.6001613}
{"step": 24100, "loss": 0.0739, "lr_factor": 0.0532, "steps_per_second": 1.374, "tokens_per_second": 25979, "eta_hours": 0.18, "time": 1790364024.9052186}
{"step": 24150, "loss": 0.0663, "lr_factor": 0.0528, "steps_per_second": 1.374, "tokens_per_second": 25979, "eta_hours": 0.17, "time": 1790364061.3694232}
{"step": 24200, "loss": 0.0596, "lr_factor": 0.0525, "steps_per_second": 1.374, "tokens_per_second": 25979, "eta_hours": 0.16, "time": 1790364097.514306}
{"step": 24250, "loss": 0.0457, "lr_factor": 0.0522, "steps_per_second": 1.374, "tokens_per_second": 25978, "eta_hours": 0.15, "time": 1790364134.549944}
{"step": 24300, "loss": 0.0682, "lr_factor": 0.0519, "steps_per_second": 1.374, "tokens_per_second": 25979, "eta_hours": 0.14, "time": 1790364170.2408764}
{"step": 24350, "loss": 0.076, "lr_factor": 0.0517, "steps_per_second": 1.374, "tokens_per_second": 25979, "eta_hours": 0.13, "time": 1790364205.87173}
{"step": 24400, "loss": 0.0698, "lr_factor": 0.0514, "steps_per_second": 1.374, "tokens_per_second": 25978, "eta_hours": 0.12, "time": 1790364242.6718836}
{"step": 24450, "loss": 0.0621, "lr_factor": 0.0512, "steps_per_second": 1.374, "tokens_per_second": 25979, "eta_hours": 0.11, "time": 1790364279.1709}
{"step": 24500, "loss": 0.0682, "lr_factor": 0.051, "steps_per_second": 1.374, "tokens_per_second": 25979, "eta_hours": 0.1, "time": 1790364315.2337623}
{"step": 24550, "loss": 0.0628, "lr_factor": 0.0508, "steps_per_second": 1.374, "tokens_per_second": 25974, "eta_hours": 0.09, "time": 1790364353.9254382}
{"step": 24600, "loss": 0.039, "lr_factor": 0.0506, "steps_per_second": 1.374, "tokens_per_second": 25974, "eta_hours": 0.08, "time": 1790364391.2148545}
{"step": 24650, "loss": 0.062, "lr_factor": 0.0505, "steps_per_second": 1.374, "tokens_per_second": 25973, "eta_hours": 0.07, "time": 1790364428.0352294}
{"step": 24700, "loss": 0.0763, "lr_factor": 0.0504, "steps_per_second": 1.374, "tokens_per_second": 25973, "eta_hours": 0.06, "time": 1790364464.370826}
{"step": 24750, "loss": 0.0588, "lr_factor": 0.0502, "steps_per_second": 1.374, "tokens_per_second": 25973, "eta_hours": 0.05, "time": 1790364500.8662481}
{"step": 24800, "loss": 0.0774, "lr_factor": 0.0502, "steps_per_second": 1.374, "tokens_per_second": 25974, "eta_hours": 0.04, "time": 1790364537.7468266}
{"step": 24850, "loss": 0.0362, "lr_factor": 0.0501, "steps_per_second": 1.374, "tokens_per_second": 25974, "eta_hours": 0.03, "time": 1790364574.3550994}
{"step": 24900, "loss": 0.0803, "lr_factor": 0.05, "steps_per_second": 1.374, "tokens_per_second": 25973, "eta_hours": 0.02, "time": 1790364610.6941576}
{"step": 24950, "loss": 0.0464, "lr_factor": 0.05, "steps_per_second": 1.374, "tokens_per_second": 25972, "eta_hours": 0.01, "time": 1790364647.769705}
{"step": 25000, "loss": 0.092, "lr_factor": 0.05, "steps_per_second": 1.374, "tokens_per_second": 25972, "eta_hours": 0.0, "time": 1790364683.1608877}