{"current_steps": 5, "total_steps": 33920, "loss": 7.1049, "lr": 1.179245283018868e-08, "epoch": 0.00294811320754717, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "2:19:29", "throughput": 2230.26, "total_tokens": 2752} {"current_steps": 10, "total_steps": 33920, "loss": 6.8578, "lr": 2.6533018867924528e-08, "epoch": 0.00589622641509434, "percentage": 0.03, "elapsed_time": "0:00:01", "remaining_time": "1:39:50", "throughput": 3260.43, "total_tokens": 5760} {"current_steps": 15, "total_steps": 33920, "loss": 6.5348, "lr": 4.127358490566038e-08, "epoch": 0.00884433962264151, "percentage": 0.04, "elapsed_time": "0:00:02", "remaining_time": "1:27:26", "throughput": 4066.62, "total_tokens": 9440} {"current_steps": 20, "total_steps": 33920, "loss": 7.0069, "lr": 5.601415094339623e-08, "epoch": 0.01179245283018868, "percentage": 0.06, "elapsed_time": "0:00:02", "remaining_time": "1:19:27", "throughput": 4425.33, "total_tokens": 12448} {"current_steps": 25, "total_steps": 33920, "loss": 6.7258, "lr": 7.075471698113208e-08, "epoch": 0.01474056603773585, "percentage": 0.07, "elapsed_time": "0:00:03", "remaining_time": "1:14:00", "throughput": 4660.14, "total_tokens": 15264} {"current_steps": 30, "total_steps": 33920, "loss": 7.1352, "lr": 8.549528301886793e-08, "epoch": 0.01768867924528302, "percentage": 0.09, "elapsed_time": "0:00:03", "remaining_time": "1:11:16", "throughput": 4818.4, "total_tokens": 18240} {"current_steps": 35, "total_steps": 33920, "loss": 6.9864, "lr": 1.0023584905660378e-07, "epoch": 0.020636792452830188, "percentage": 0.1, "elapsed_time": "0:00:04", "remaining_time": "1:08:53", "throughput": 4924.24, "total_tokens": 21024} {"current_steps": 40, "total_steps": 33920, "loss": 6.8129, "lr": 1.1497641509433962e-07, "epoch": 0.02358490566037736, "percentage": 0.12, "elapsed_time": "0:00:04", "remaining_time": "1:07:19", "throughput": 5098.86, "total_tokens": 24320} {"current_steps": 45, "total_steps": 33920, "loss": 6.923, "lr": 1.297169811320755e-07, "epoch": 0.02653301886792453, "percentage": 0.13, "elapsed_time": "0:00:05", "remaining_time": "1:06:09", "throughput": 5213.2, "total_tokens": 27488} {"current_steps": 50, "total_steps": 33920, "loss": 6.6817, "lr": 1.4445754716981135e-07, "epoch": 0.0294811320754717, "percentage": 0.15, "elapsed_time": "0:00:05", "remaining_time": "1:05:05", "throughput": 5300.1, "total_tokens": 30560} {"current_steps": 55, "total_steps": 33920, "loss": 6.5194, "lr": 1.591981132075472e-07, "epoch": 0.03242924528301887, "percentage": 0.16, "elapsed_time": "0:00:06", "remaining_time": "1:04:11", "throughput": 5325.76, "total_tokens": 33312} {"current_steps": 60, "total_steps": 33920, "loss": 6.531, "lr": 1.7393867924528304e-07, "epoch": 0.03537735849056604, "percentage": 0.18, "elapsed_time": "0:00:06", "remaining_time": "1:03:25", "throughput": 5385.78, "total_tokens": 36320} {"current_steps": 65, "total_steps": 33920, "loss": 6.4735, "lr": 1.886792452830189e-07, "epoch": 0.038325471698113206, "percentage": 0.19, "elapsed_time": "0:00:07", "remaining_time": "1:02:48", "throughput": 5439.45, "total_tokens": 39360} {"current_steps": 70, "total_steps": 33920, "loss": 6.2651, "lr": 2.0341981132075473e-07, "epoch": 0.041273584905660375, "percentage": 0.21, "elapsed_time": "0:00:07", "remaining_time": "1:03:16", "throughput": 5518.22, "total_tokens": 43328} {"current_steps": 75, "total_steps": 33920, "loss": 6.398, "lr": 2.1816037735849058e-07, "epoch": 0.044221698113207544, "percentage": 0.22, "elapsed_time": "0:00:08", "remaining_time": "1:03:23", "throughput": 5573.54, "total_tokens": 46976} {"current_steps": 80, "total_steps": 33920, "loss": 6.4309, "lr": 2.3290094339622643e-07, "epoch": 0.04716981132075472, "percentage": 0.24, "elapsed_time": "0:00:08", "remaining_time": "1:03:03", "throughput": 5612.78, "total_tokens": 50208} {"current_steps": 85, "total_steps": 33920, "loss": 6.0212, "lr": 2.476415094339623e-07, "epoch": 0.05011792452830189, "percentage": 0.25, "elapsed_time": "0:00:09", "remaining_time": "1:02:27", "throughput": 5615.86, "total_tokens": 52864} {"current_steps": 90, "total_steps": 33920, "loss": 6.2668, "lr": 2.6238207547169815e-07, "epoch": 0.05306603773584906, "percentage": 0.27, "elapsed_time": "0:00:09", "remaining_time": "1:02:32", "throughput": 5673.51, "total_tokens": 56640} {"current_steps": 95, "total_steps": 33920, "loss": 5.7736, "lr": 2.7712264150943397e-07, "epoch": 0.05601415094339623, "percentage": 0.28, "elapsed_time": "0:00:10", "remaining_time": "1:02:06", "throughput": 5690.24, "total_tokens": 59552} {"current_steps": 100, "total_steps": 33920, "loss": 5.9678, "lr": 2.9186320754716984e-07, "epoch": 0.0589622641509434, "percentage": 0.29, "elapsed_time": "0:00:11", "remaining_time": "1:02:17", "throughput": 5735.92, "total_tokens": 63392} {"current_steps": 105, "total_steps": 33920, "loss": 6.0436, "lr": 3.0660377358490567e-07, "epoch": 0.061910377358490566, "percentage": 0.31, "elapsed_time": "0:00:11", "remaining_time": "1:01:59", "throughput": 5759.57, "total_tokens": 66528} {"current_steps": 110, "total_steps": 33920, "loss": 5.8762, "lr": 3.213443396226416e-07, "epoch": 0.06485849056603774, "percentage": 0.32, "elapsed_time": "0:00:12", "remaining_time": "1:01:39", "throughput": 5784.82, "total_tokens": 69632} {"current_steps": 115, "total_steps": 33920, "loss": 5.6497, "lr": 3.3608490566037736e-07, "epoch": 0.06780660377358491, "percentage": 0.34, "elapsed_time": "0:00:12", "remaining_time": "1:01:59", "throughput": 5829.07, "total_tokens": 73760} {"current_steps": 120, "total_steps": 33920, "loss": 5.5807, "lr": 3.508254716981133e-07, "epoch": 0.07075471698113207, "percentage": 0.35, "elapsed_time": "0:00:13", "remaining_time": "1:01:45", "throughput": 5859.19, "total_tokens": 77088} {"current_steps": 125, "total_steps": 33920, "loss": 5.6997, "lr": 3.6556603773584905e-07, "epoch": 0.07370283018867925, "percentage": 0.37, "elapsed_time": "0:00:13", "remaining_time": "1:02:17", "throughput": 5881.68, "total_tokens": 81312} {"current_steps": 130, "total_steps": 33920, "loss": 5.7322, "lr": 3.80306603773585e-07, "epoch": 0.07665094339622641, "percentage": 0.38, "elapsed_time": "0:00:14", "remaining_time": "1:01:55", "throughput": 5889.26, "total_tokens": 84192} {"current_steps": 135, "total_steps": 33920, "loss": 5.0634, "lr": 3.9504716981132075e-07, "epoch": 0.07959905660377359, "percentage": 0.4, "elapsed_time": "0:00:14", "remaining_time": "1:01:55", "throughput": 5919.41, "total_tokens": 87872} {"current_steps": 140, "total_steps": 33920, "loss": 5.002, "lr": 4.097877358490567e-07, "epoch": 0.08254716981132075, "percentage": 0.41, "elapsed_time": "0:00:15", "remaining_time": "1:01:39", "throughput": 5931.9, "total_tokens": 90944} {"current_steps": 145, "total_steps": 33920, "loss": 5.163, "lr": 4.2452830188679244e-07, "epoch": 0.08549528301886793, "percentage": 0.43, "elapsed_time": "0:00:15", "remaining_time": "1:01:27", "throughput": 5927.14, "total_tokens": 93824} {"current_steps": 150, "total_steps": 33920, "loss": 5.1964, "lr": 4.3926886792452837e-07, "epoch": 0.08844339622641509, "percentage": 0.44, "elapsed_time": "0:00:16", "remaining_time": "1:01:22", "throughput": 5947.47, "total_tokens": 97280} {"current_steps": 155, "total_steps": 33920, "loss": 4.592, "lr": 4.5400943396226414e-07, "epoch": 0.09139150943396226, "percentage": 0.46, "elapsed_time": "0:00:16", "remaining_time": "1:01:07", "throughput": 5951.08, "total_tokens": 100192} {"current_steps": 160, "total_steps": 33920, "loss": 4.6367, "lr": 4.6875000000000006e-07, "epoch": 0.09433962264150944, "percentage": 0.47, "elapsed_time": "0:00:17", "remaining_time": "1:00:56", "throughput": 5964.23, "total_tokens": 103360} {"current_steps": 165, "total_steps": 33920, "loss": 4.6398, "lr": 4.834905660377359e-07, "epoch": 0.0972877358490566, "percentage": 0.49, "elapsed_time": "0:00:17", "remaining_time": "1:00:41", "throughput": 5964.2, "total_tokens": 106176} {"current_steps": 170, "total_steps": 33920, "loss": 4.4901, "lr": 4.982311320754717e-07, "epoch": 0.10023584905660378, "percentage": 0.5, "elapsed_time": "0:00:18", "remaining_time": "1:00:34", "throughput": 5966.44, "total_tokens": 109216} {"current_steps": 175, "total_steps": 33920, "loss": 4.6312, "lr": 5.129716981132076e-07, "epoch": 0.10318396226415094, "percentage": 0.52, "elapsed_time": "0:00:18", "remaining_time": "1:00:20", "throughput": 5961.23, "total_tokens": 111936} {"current_steps": 180, "total_steps": 33920, "loss": 4.4435, "lr": 5.277122641509435e-07, "epoch": 0.10613207547169812, "percentage": 0.53, "elapsed_time": "0:00:19", "remaining_time": "1:00:04", "throughput": 5954.79, "total_tokens": 114496} {"current_steps": 185, "total_steps": 33920, "loss": 4.5376, "lr": 5.424528301886793e-07, "epoch": 0.10908018867924528, "percentage": 0.55, "elapsed_time": "0:00:19", "remaining_time": "1:00:25", "throughput": 5986.51, "total_tokens": 119008} {"current_steps": 190, "total_steps": 33920, "loss": 4.3266, "lr": 5.571933962264151e-07, "epoch": 0.11202830188679246, "percentage": 0.56, "elapsed_time": "0:00:20", "remaining_time": "1:00:15", "throughput": 5997.23, "total_tokens": 122144} {"current_steps": 195, "total_steps": 33920, "loss": 4.6784, "lr": 5.71933962264151e-07, "epoch": 0.11497641509433962, "percentage": 0.57, "elapsed_time": "0:00:20", "remaining_time": "1:00:13", "throughput": 6010.17, "total_tokens": 125568} {"current_steps": 200, "total_steps": 33920, "loss": 3.7943, "lr": 5.866745283018868e-07, "epoch": 0.1179245283018868, "percentage": 0.59, "elapsed_time": "0:00:21", "remaining_time": "1:00:04", "throughput": 6009.11, "total_tokens": 128480} {"current_steps": 205, "total_steps": 33920, "loss": 3.8278, "lr": 6.014150943396227e-07, "epoch": 0.12087264150943396, "percentage": 0.6, "elapsed_time": "0:00:21", "remaining_time": "0:59:53", "throughput": 6004.33, "total_tokens": 131200} {"current_steps": 210, "total_steps": 33920, "loss": 4.1919, "lr": 6.161556603773585e-07, "epoch": 0.12382075471698113, "percentage": 0.62, "elapsed_time": "0:00:22", "remaining_time": "0:59:48", "throughput": 6015.82, "total_tokens": 134496} {"current_steps": 215, "total_steps": 33920, "loss": 4.1177, "lr": 6.308962264150945e-07, "epoch": 0.1267688679245283, "percentage": 0.63, "elapsed_time": "0:00:22", "remaining_time": "0:59:36", "throughput": 6012.49, "total_tokens": 137152} {"current_steps": 220, "total_steps": 33920, "loss": 3.89, "lr": 6.456367924528302e-07, "epoch": 0.12971698113207547, "percentage": 0.65, "elapsed_time": "0:00:23", "remaining_time": "0:59:36", "throughput": 6020.49, "total_tokens": 140576} {"current_steps": 225, "total_steps": 33920, "loss": 3.3574, "lr": 6.603773584905661e-07, "epoch": 0.13266509433962265, "percentage": 0.66, "elapsed_time": "0:00:24", "remaining_time": "1:01:02", "throughput": 6033.53, "total_tokens": 147552} {"current_steps": 230, "total_steps": 33920, "loss": 3.8011, "lr": 6.75117924528302e-07, "epoch": 0.13561320754716982, "percentage": 0.68, "elapsed_time": "0:00:24", "remaining_time": "1:01:00", "throughput": 6043.55, "total_tokens": 151040} {"current_steps": 235, "total_steps": 33920, "loss": 4.497, "lr": 6.898584905660379e-07, "epoch": 0.13856132075471697, "percentage": 0.69, "elapsed_time": "0:00:25", "remaining_time": "1:00:49", "throughput": 6043.78, "total_tokens": 153888} {"current_steps": 240, "total_steps": 33920, "loss": 3.7578, "lr": 7.045990566037736e-07, "epoch": 0.14150943396226415, "percentage": 0.71, "elapsed_time": "0:00:26", "remaining_time": "1:00:50", "throughput": 6050.55, "total_tokens": 157376} {"current_steps": 245, "total_steps": 33920, "loss": 3.4508, "lr": 7.193396226415095e-07, "epoch": 0.14445754716981132, "percentage": 0.72, "elapsed_time": "0:00:26", "remaining_time": "1:00:45", "throughput": 6035.96, "total_tokens": 160096} {"current_steps": 250, "total_steps": 33920, "loss": 4.2039, "lr": 7.340801886792454e-07, "epoch": 0.1474056603773585, "percentage": 0.74, "elapsed_time": "0:00:27", "remaining_time": "1:00:48", "throughput": 6051.86, "total_tokens": 163968} {"current_steps": 255, "total_steps": 33920, "loss": 3.9289, "lr": 7.488207547169812e-07, "epoch": 0.15035377358490565, "percentage": 0.75, "elapsed_time": "0:00:27", "remaining_time": "1:00:39", "throughput": 6046.93, "total_tokens": 166720} {"current_steps": 260, "total_steps": 33920, "loss": 3.5308, "lr": 7.63561320754717e-07, "epoch": 0.15330188679245282, "percentage": 0.77, "elapsed_time": "0:00:28", "remaining_time": "1:00:44", "throughput": 6061.47, "total_tokens": 170656} {"current_steps": 265, "total_steps": 33920, "loss": 3.521, "lr": 7.783018867924529e-07, "epoch": 0.15625, "percentage": 0.78, "elapsed_time": "0:00:28", "remaining_time": "1:00:34", "throughput": 6060.12, "total_tokens": 173408} {"current_steps": 270, "total_steps": 33920, "loss": 3.2204, "lr": 7.930424528301888e-07, "epoch": 0.15919811320754718, "percentage": 0.8, "elapsed_time": "0:00:29", "remaining_time": "1:00:34", "throughput": 6062.14, "total_tokens": 176800} {"current_steps": 275, "total_steps": 33920, "loss": 3.3418, "lr": 8.077830188679246e-07, "epoch": 0.16214622641509435, "percentage": 0.81, "elapsed_time": "0:00:29", "remaining_time": "1:00:30", "throughput": 6059.04, "total_tokens": 179776} {"current_steps": 280, "total_steps": 33920, "loss": 3.2372, "lr": 8.225235849056605e-07, "epoch": 0.1650943396226415, "percentage": 0.83, "elapsed_time": "0:00:30", "remaining_time": "1:00:28", "throughput": 6059.92, "total_tokens": 183040} {"current_steps": 285, "total_steps": 33920, "loss": 3.2967, "lr": 8.372641509433963e-07, "epoch": 0.16804245283018868, "percentage": 0.84, "elapsed_time": "0:00:30", "remaining_time": "1:00:31", "throughput": 6072.97, "total_tokens": 186880} {"current_steps": 290, "total_steps": 33920, "loss": 3.3929, "lr": 8.520047169811321e-07, "epoch": 0.17099056603773585, "percentage": 0.85, "elapsed_time": "0:00:31", "remaining_time": "1:00:21", "throughput": 6072.01, "total_tokens": 189600} {"current_steps": 295, "total_steps": 33920, "loss": 3.4219, "lr": 8.66745283018868e-07, "epoch": 0.17393867924528303, "percentage": 0.87, "elapsed_time": "0:00:31", "remaining_time": "1:00:32", "throughput": 6083.41, "total_tokens": 193856} {"current_steps": 300, "total_steps": 33920, "loss": 3.2748, "lr": 8.814858490566039e-07, "epoch": 0.17688679245283018, "percentage": 0.88, "elapsed_time": "0:00:32", "remaining_time": "1:00:23", "throughput": 6077.33, "total_tokens": 196480} {"current_steps": 305, "total_steps": 33920, "loss": 3.3445, "lr": 8.962264150943397e-07, "epoch": 0.17983490566037735, "percentage": 0.9, "elapsed_time": "0:00:32", "remaining_time": "1:00:21", "throughput": 6067.4, "total_tokens": 199360} {"current_steps": 310, "total_steps": 33920, "loss": 3.031, "lr": 9.109669811320755e-07, "epoch": 0.18278301886792453, "percentage": 0.91, "elapsed_time": "0:00:33", "remaining_time": "1:00:17", "throughput": 6059.21, "total_tokens": 202144} {"current_steps": 315, "total_steps": 33920, "loss": 3.2587, "lr": 9.257075471698114e-07, "epoch": 0.1857311320754717, "percentage": 0.93, "elapsed_time": "0:00:33", "remaining_time": "1:00:14", "throughput": 6059.15, "total_tokens": 205280} {"current_steps": 320, "total_steps": 33920, "loss": 3.123, "lr": 9.404481132075473e-07, "epoch": 0.18867924528301888, "percentage": 0.94, "elapsed_time": "0:00:34", "remaining_time": "1:00:11", "throughput": 6051.87, "total_tokens": 208128} {"current_steps": 325, "total_steps": 33920, "loss": 3.1753, "lr": 9.551886792452833e-07, "epoch": 0.19162735849056603, "percentage": 0.96, "elapsed_time": "0:00:34", "remaining_time": "1:00:07", "throughput": 6052.29, "total_tokens": 211232} {"current_steps": 330, "total_steps": 33920, "loss": 3.1799, "lr": 9.699292452830188e-07, "epoch": 0.1945754716981132, "percentage": 0.97, "elapsed_time": "0:00:35", "remaining_time": "1:00:06", "throughput": 6054.92, "total_tokens": 214560} {"current_steps": 335, "total_steps": 33920, "loss": 2.9134, "lr": 9.846698113207548e-07, "epoch": 0.19752358490566038, "percentage": 0.99, "elapsed_time": "0:00:35", "remaining_time": "1:00:07", "throughput": 6061.48, "total_tokens": 218144} {"current_steps": 340, "total_steps": 33920, "loss": 2.8138, "lr": 9.994103773584906e-07, "epoch": 0.20047169811320756, "percentage": 1.0, "elapsed_time": "0:00:36", "remaining_time": "1:00:00", "throughput": 6052.12, "total_tokens": 220608} {"current_steps": 345, "total_steps": 33920, "loss": 2.9892, "lr": 1.0141509433962265e-06, "epoch": 0.2034198113207547, "percentage": 1.02, "elapsed_time": "0:00:36", "remaining_time": "0:59:55", "throughput": 6052.28, "total_tokens": 223616} {"current_steps": 350, "total_steps": 33920, "loss": 3.0692, "lr": 1.0288915094339623e-06, "epoch": 0.20636792452830188, "percentage": 1.03, "elapsed_time": "0:00:37", "remaining_time": "0:59:52", "throughput": 6055.17, "total_tokens": 226816} {"current_steps": 355, "total_steps": 33920, "loss": 3.1159, "lr": 1.043632075471698e-06, "epoch": 0.20931603773584906, "percentage": 1.05, "elapsed_time": "0:00:37", "remaining_time": "0:59:45", "throughput": 6052.28, "total_tokens": 229504} {"current_steps": 360, "total_steps": 33920, "loss": 3.1408, "lr": 1.058372641509434e-06, "epoch": 0.21226415094339623, "percentage": 1.06, "elapsed_time": "0:00:38", "remaining_time": "0:59:42", "throughput": 6058.09, "total_tokens": 232800} {"current_steps": 365, "total_steps": 33920, "loss": 2.7335, "lr": 1.07311320754717e-06, "epoch": 0.21521226415094338, "percentage": 1.08, "elapsed_time": "0:00:38", "remaining_time": "0:59:37", "throughput": 6054.0, "total_tokens": 235584} {"current_steps": 370, "total_steps": 33920, "loss": 2.9652, "lr": 1.0878537735849056e-06, "epoch": 0.21816037735849056, "percentage": 1.09, "elapsed_time": "0:00:39", "remaining_time": "0:59:44", "throughput": 6061.38, "total_tokens": 239616} {"current_steps": 375, "total_steps": 33920, "loss": 2.7553, "lr": 1.1025943396226416e-06, "epoch": 0.22110849056603774, "percentage": 1.11, "elapsed_time": "0:00:39", "remaining_time": "0:59:37", "throughput": 6058.77, "total_tokens": 242304} {"current_steps": 380, "total_steps": 33920, "loss": 2.7732, "lr": 1.1173349056603773e-06, "epoch": 0.2240566037735849, "percentage": 1.12, "elapsed_time": "0:00:40", "remaining_time": "0:59:43", "throughput": 6070.4, "total_tokens": 246432} {"current_steps": 385, "total_steps": 33920, "loss": 3.0968, "lr": 1.1320754716981133e-06, "epoch": 0.2270047169811321, "percentage": 1.14, "elapsed_time": "0:00:41", "remaining_time": "0:59:40", "throughput": 6067.49, "total_tokens": 249440} {"current_steps": 390, "total_steps": 33920, "loss": 2.5457, "lr": 1.1468160377358493e-06, "epoch": 0.22995283018867924, "percentage": 1.15, "elapsed_time": "0:00:41", "remaining_time": "0:59:52", "throughput": 6080.12, "total_tokens": 254048} {"current_steps": 395, "total_steps": 33920, "loss": 2.4144, "lr": 1.1615566037735849e-06, "epoch": 0.2329009433962264, "percentage": 1.16, "elapsed_time": "0:00:42", "remaining_time": "0:59:45", "throughput": 6078.0, "total_tokens": 256800} {"current_steps": 400, "total_steps": 33920, "loss": 2.2977, "lr": 1.1762971698113208e-06, "epoch": 0.2358490566037736, "percentage": 1.18, "elapsed_time": "0:00:42", "remaining_time": "0:59:40", "throughput": 6069.49, "total_tokens": 259296} {"current_steps": 405, "total_steps": 33920, "loss": 2.5573, "lr": 1.1910377358490568e-06, "epoch": 0.23879716981132076, "percentage": 1.19, "elapsed_time": "0:00:43", "remaining_time": "0:59:34", "throughput": 6068.22, "total_tokens": 262112} {"current_steps": 410, "total_steps": 33920, "loss": 2.5675, "lr": 1.2057783018867926e-06, "epoch": 0.2417452830188679, "percentage": 1.21, "elapsed_time": "0:00:43", "remaining_time": "0:59:32", "throughput": 6069.02, "total_tokens": 265280} {"current_steps": 415, "total_steps": 33920, "loss": 2.4753, "lr": 1.2205188679245284e-06, "epoch": 0.2446933962264151, "percentage": 1.22, "elapsed_time": "0:00:44", "remaining_time": "0:59:31", "throughput": 6064.57, "total_tokens": 268288} {"current_steps": 420, "total_steps": 33920, "loss": 2.7582, "lr": 1.2352594339622641e-06, "epoch": 0.24764150943396226, "percentage": 1.24, "elapsed_time": "0:00:45", "remaining_time": "1:00:03", "throughput": 6075.24, "total_tokens": 274432} {"current_steps": 425, "total_steps": 33920, "loss": 2.5861, "lr": 1.25e-06, "epoch": 0.2505896226415094, "percentage": 1.25, "elapsed_time": "0:00:45", "remaining_time": "1:00:14", "throughput": 6086.59, "total_tokens": 279136} {"current_steps": 430, "total_steps": 33920, "loss": 3.0714, "lr": 1.264740566037736e-06, "epoch": 0.2535377358490566, "percentage": 1.27, "elapsed_time": "0:00:46", "remaining_time": "1:00:16", "throughput": 6095.25, "total_tokens": 283008} {"current_steps": 435, "total_steps": 33920, "loss": 2.439, "lr": 1.2794811320754718e-06, "epoch": 0.25648584905660377, "percentage": 1.28, "elapsed_time": "0:00:46", "remaining_time": "1:00:10", "throughput": 6092.09, "total_tokens": 285728} {"current_steps": 440, "total_steps": 33920, "loss": 2.312, "lr": 1.2942216981132078e-06, "epoch": 0.25943396226415094, "percentage": 1.3, "elapsed_time": "0:00:47", "remaining_time": "1:00:04", "throughput": 6087.64, "total_tokens": 288352} {"current_steps": 445, "total_steps": 33920, "loss": 2.4904, "lr": 1.3089622641509436e-06, "epoch": 0.2623820754716981, "percentage": 1.31, "elapsed_time": "0:00:47", "remaining_time": "0:59:59", "throughput": 6086.99, "total_tokens": 291264} {"current_steps": 450, "total_steps": 33920, "loss": 2.6839, "lr": 1.3237028301886792e-06, "epoch": 0.2653301886792453, "percentage": 1.33, "elapsed_time": "0:00:48", "remaining_time": "0:59:57", "throughput": 6088.84, "total_tokens": 294496} {"current_steps": 455, "total_steps": 33920, "loss": 2.1994, "lr": 1.3384433962264151e-06, "epoch": 0.26827830188679247, "percentage": 1.34, "elapsed_time": "0:00:48", "remaining_time": "0:59:54", "throughput": 6088.1, "total_tokens": 297536} {"current_steps": 460, "total_steps": 33920, "loss": 2.6184, "lr": 1.353183962264151e-06, "epoch": 0.27122641509433965, "percentage": 1.36, "elapsed_time": "0:00:49", "remaining_time": "0:59:51", "throughput": 6089.35, "total_tokens": 300672} {"current_steps": 465, "total_steps": 33920, "loss": 2.5791, "lr": 1.3679245283018869e-06, "epoch": 0.27417452830188677, "percentage": 1.37, "elapsed_time": "0:00:49", "remaining_time": "0:59:47", "throughput": 6085.21, "total_tokens": 303424} {"current_steps": 470, "total_steps": 33920, "loss": 2.1846, "lr": 1.3826650943396229e-06, "epoch": 0.27712264150943394, "percentage": 1.39, "elapsed_time": "0:00:50", "remaining_time": "0:59:48", "throughput": 6090.05, "total_tokens": 307040} {"current_steps": 475, "total_steps": 33920, "loss": 2.3982, "lr": 1.3974056603773586e-06, "epoch": 0.2800707547169811, "percentage": 1.4, "elapsed_time": "0:00:50", "remaining_time": "0:59:48", "throughput": 6095.6, "total_tokens": 310688} {"current_steps": 480, "total_steps": 33920, "loss": 2.4223, "lr": 1.4121462264150946e-06, "epoch": 0.2830188679245283, "percentage": 1.42, "elapsed_time": "0:00:51", "remaining_time": "0:59:44", "throughput": 6092.34, "total_tokens": 313440} {"current_steps": 485, "total_steps": 33920, "loss": 2.2033, "lr": 1.4268867924528304e-06, "epoch": 0.28596698113207547, "percentage": 1.43, "elapsed_time": "0:00:52", "remaining_time": "0:59:44", "throughput": 6094.01, "total_tokens": 316896} {"current_steps": 490, "total_steps": 33920, "loss": 2.161, "lr": 1.4416273584905664e-06, "epoch": 0.28891509433962265, "percentage": 1.44, "elapsed_time": "0:00:52", "remaining_time": "0:59:37", "throughput": 6091.33, "total_tokens": 319456} {"current_steps": 495, "total_steps": 33920, "loss": 2.0782, "lr": 1.456367924528302e-06, "epoch": 0.2918632075471698, "percentage": 1.46, "elapsed_time": "0:00:52", "remaining_time": "0:59:33", "throughput": 6089.67, "total_tokens": 322240} {"current_steps": 500, "total_steps": 33920, "loss": 2.2208, "lr": 1.4711084905660377e-06, "epoch": 0.294811320754717, "percentage": 1.47, "elapsed_time": "0:00:53", "remaining_time": "0:59:34", "throughput": 6095.6, "total_tokens": 325984} {"current_steps": 505, "total_steps": 33920, "loss": 2.17, "lr": 1.4858490566037737e-06, "epoch": 0.2977594339622642, "percentage": 1.49, "elapsed_time": "0:00:53", "remaining_time": "0:59:32", "throughput": 6098.63, "total_tokens": 329312} {"current_steps": 510, "total_steps": 33920, "loss": 2.0781, "lr": 1.5005896226415096e-06, "epoch": 0.3007075471698113, "percentage": 1.5, "elapsed_time": "0:00:54", "remaining_time": "0:59:29", "throughput": 6099.19, "total_tokens": 332352} {"current_steps": 515, "total_steps": 33920, "loss": 2.642, "lr": 1.5153301886792454e-06, "epoch": 0.30365566037735847, "percentage": 1.52, "elapsed_time": "0:00:54", "remaining_time": "0:59:25", "throughput": 6095.05, "total_tokens": 335008} {"current_steps": 520, "total_steps": 33920, "loss": 2.1205, "lr": 1.5300707547169814e-06, "epoch": 0.30660377358490565, "percentage": 1.53, "elapsed_time": "0:00:55", "remaining_time": "0:59:19", "throughput": 6088.54, "total_tokens": 337376} {"current_steps": 525, "total_steps": 33920, "loss": 1.9965, "lr": 1.5448113207547172e-06, "epoch": 0.3095518867924528, "percentage": 1.55, "elapsed_time": "0:00:55", "remaining_time": "0:59:14", "throughput": 6081.0, "total_tokens": 339776} {"current_steps": 530, "total_steps": 33920, "loss": 2.1677, "lr": 1.5595518867924531e-06, "epoch": 0.3125, "percentage": 1.56, "elapsed_time": "0:00:56", "remaining_time": "0:59:08", "throughput": 6078.57, "total_tokens": 342336} {"current_steps": 535, "total_steps": 33920, "loss": 2.0589, "lr": 1.574292452830189e-06, "epoch": 0.3154481132075472, "percentage": 1.58, "elapsed_time": "0:00:56", "remaining_time": "0:59:08", "throughput": 6074.39, "total_tokens": 345440} {"current_steps": 540, "total_steps": 33920, "loss": 2.307, "lr": 1.5890330188679245e-06, "epoch": 0.31839622641509435, "percentage": 1.59, "elapsed_time": "0:00:57", "remaining_time": "0:59:06", "throughput": 6076.55, "total_tokens": 348608} {"current_steps": 545, "total_steps": 33920, "loss": 1.9491, "lr": 1.6037735849056604e-06, "epoch": 0.32134433962264153, "percentage": 1.61, "elapsed_time": "0:00:58", "remaining_time": "0:59:14", "throughput": 6081.74, "total_tokens": 352992} {"current_steps": 550, "total_steps": 33920, "loss": 2.2303, "lr": 1.6185141509433964e-06, "epoch": 0.3242924528301887, "percentage": 1.62, "elapsed_time": "0:00:58", "remaining_time": "0:59:17", "throughput": 6084.36, "total_tokens": 356768} {"current_steps": 555, "total_steps": 33920, "loss": 2.062, "lr": 1.6332547169811322e-06, "epoch": 0.3272405660377358, "percentage": 1.64, "elapsed_time": "0:00:59", "remaining_time": "0:59:13", "throughput": 6079.64, "total_tokens": 359360} {"current_steps": 560, "total_steps": 33920, "loss": 2.131, "lr": 1.6479952830188682e-06, "epoch": 0.330188679245283, "percentage": 1.65, "elapsed_time": "0:00:59", "remaining_time": "0:59:19", "throughput": 6083.51, "total_tokens": 363488} {"current_steps": 565, "total_steps": 33920, "loss": 2.2984, "lr": 1.662735849056604e-06, "epoch": 0.3331367924528302, "percentage": 1.67, "elapsed_time": "0:01:00", "remaining_time": "0:59:19", "throughput": 6082.45, "total_tokens": 366688} {"current_steps": 570, "total_steps": 33920, "loss": 1.9614, "lr": 1.67747641509434e-06, "epoch": 0.33608490566037735, "percentage": 1.68, "elapsed_time": "0:01:00", "remaining_time": "0:59:16", "throughput": 6073.39, "total_tokens": 369152} {"current_steps": 575, "total_steps": 33920, "loss": 1.8213, "lr": 1.6922169811320757e-06, "epoch": 0.33903301886792453, "percentage": 1.7, "elapsed_time": "0:01:01", "remaining_time": "0:59:18", "throughput": 6079.08, "total_tokens": 372992} {"current_steps": 580, "total_steps": 33920, "loss": 2.168, "lr": 1.7069575471698112e-06, "epoch": 0.3419811320754717, "percentage": 1.71, "elapsed_time": "0:01:01", "remaining_time": "0:59:13", "throughput": 6077.55, "total_tokens": 375680} {"current_steps": 585, "total_steps": 33920, "loss": 1.8592, "lr": 1.7216981132075472e-06, "epoch": 0.3449292452830189, "percentage": 1.72, "elapsed_time": "0:01:02", "remaining_time": "0:59:17", "throughput": 6083.85, "total_tokens": 379808} {"current_steps": 590, "total_steps": 33920, "loss": 2.003, "lr": 1.736438679245283e-06, "epoch": 0.34787735849056606, "percentage": 1.74, "elapsed_time": "0:01:02", "remaining_time": "0:59:14", "throughput": 6083.73, "total_tokens": 382752} {"current_steps": 595, "total_steps": 33920, "loss": 1.9762, "lr": 1.751179245283019e-06, "epoch": 0.35082547169811323, "percentage": 1.75, "elapsed_time": "0:01:03", "remaining_time": "0:59:13", "throughput": 6088.8, "total_tokens": 386304} {"current_steps": 600, "total_steps": 33920, "loss": 2.0236, "lr": 1.765919811320755e-06, "epoch": 0.35377358490566035, "percentage": 1.77, "elapsed_time": "0:01:04", "remaining_time": "0:59:19", "throughput": 6094.61, "total_tokens": 390592} {"current_steps": 605, "total_steps": 33920, "loss": 2.2317, "lr": 1.7806603773584907e-06, "epoch": 0.35672169811320753, "percentage": 1.78, "elapsed_time": "0:01:04", "remaining_time": "0:59:18", "throughput": 6101.2, "total_tokens": 394304} {"current_steps": 610, "total_steps": 33920, "loss": 1.8942, "lr": 1.7954009433962267e-06, "epoch": 0.3596698113207547, "percentage": 1.8, "elapsed_time": "0:01:05", "remaining_time": "0:59:20", "throughput": 6098.47, "total_tokens": 397664} {"current_steps": 615, "total_steps": 33920, "loss": 1.9195, "lr": 1.8101415094339625e-06, "epoch": 0.3626179245283019, "percentage": 1.81, "elapsed_time": "0:01:05", "remaining_time": "0:59:23", "throughput": 6103.87, "total_tokens": 401632} {"current_steps": 620, "total_steps": 33920, "loss": 1.5036, "lr": 1.8248820754716984e-06, "epoch": 0.36556603773584906, "percentage": 1.83, "elapsed_time": "0:01:06", "remaining_time": "0:59:17", "throughput": 6097.32, "total_tokens": 403904} {"current_steps": 625, "total_steps": 33920, "loss": 1.6058, "lr": 1.839622641509434e-06, "epoch": 0.36851415094339623, "percentage": 1.84, "elapsed_time": "0:01:06", "remaining_time": "0:59:14", "throughput": 6096.99, "total_tokens": 406816} {"current_steps": 630, "total_steps": 33920, "loss": 1.8395, "lr": 1.8543632075471698e-06, "epoch": 0.3714622641509434, "percentage": 1.86, "elapsed_time": "0:01:07", "remaining_time": "0:59:22", "throughput": 6101.54, "total_tokens": 411360} {"current_steps": 635, "total_steps": 33920, "loss": 1.9946, "lr": 1.8691037735849057e-06, "epoch": 0.3744103773584906, "percentage": 1.87, "elapsed_time": "0:01:08", "remaining_time": "0:59:27", "throughput": 6106.43, "total_tokens": 415552} {"current_steps": 640, "total_steps": 33920, "loss": 1.7062, "lr": 1.8838443396226417e-06, "epoch": 0.37735849056603776, "percentage": 1.89, "elapsed_time": "0:01:08", "remaining_time": "0:59:37", "throughput": 6114.97, "total_tokens": 420736} {"current_steps": 645, "total_steps": 33920, "loss": 1.7871, "lr": 1.8985849056603775e-06, "epoch": 0.3803066037735849, "percentage": 1.9, "elapsed_time": "0:01:09", "remaining_time": "0:59:35", "throughput": 6114.59, "total_tokens": 423744} {"current_steps": 650, "total_steps": 33920, "loss": 2.0758, "lr": 1.9133254716981133e-06, "epoch": 0.38325471698113206, "percentage": 1.92, "elapsed_time": "0:01:09", "remaining_time": "0:59:37", "throughput": 6120.88, "total_tokens": 427776} {"current_steps": 655, "total_steps": 33920, "loss": 1.6892, "lr": 1.9280660377358494e-06, "epoch": 0.38620283018867924, "percentage": 1.93, "elapsed_time": "0:01:10", "remaining_time": "0:59:35", "throughput": 6122.01, "total_tokens": 431040} {"current_steps": 660, "total_steps": 33920, "loss": 1.4992, "lr": 1.9428066037735852e-06, "epoch": 0.3891509433962264, "percentage": 1.95, "elapsed_time": "0:01:10", "remaining_time": "0:59:33", "throughput": 6122.55, "total_tokens": 434144} {"current_steps": 665, "total_steps": 33920, "loss": 1.7418, "lr": 1.957547169811321e-06, "epoch": 0.3920990566037736, "percentage": 1.96, "elapsed_time": "0:01:11", "remaining_time": "0:59:32", "throughput": 6124.65, "total_tokens": 437600} {"current_steps": 670, "total_steps": 33920, "loss": 1.965, "lr": 1.9722877358490568e-06, "epoch": 0.39504716981132076, "percentage": 1.98, "elapsed_time": "0:01:12", "remaining_time": "0:59:33", "throughput": 6126.86, "total_tokens": 441184} {"current_steps": 675, "total_steps": 33920, "loss": 1.6411, "lr": 1.9870283018867925e-06, "epoch": 0.39799528301886794, "percentage": 1.99, "elapsed_time": "0:01:12", "remaining_time": "0:59:33", "throughput": 6131.0, "total_tokens": 444896} {"current_steps": 680, "total_steps": 33920, "loss": 1.6181, "lr": 2.0017688679245283e-06, "epoch": 0.4009433962264151, "percentage": 2.0, "elapsed_time": "0:01:13", "remaining_time": "0:59:32", "throughput": 6128.64, "total_tokens": 447936} {"current_steps": 685, "total_steps": 33920, "loss": 1.6427, "lr": 2.0165094339622645e-06, "epoch": 0.40389150943396224, "percentage": 2.02, "elapsed_time": "0:01:13", "remaining_time": "0:59:34", "throughput": 6128.32, "total_tokens": 451488} {"current_steps": 690, "total_steps": 33920, "loss": 1.4471, "lr": 2.0312500000000002e-06, "epoch": 0.4068396226415094, "percentage": 2.03, "elapsed_time": "0:01:14", "remaining_time": "0:59:30", "throughput": 6127.4, "total_tokens": 454240} {"current_steps": 695, "total_steps": 33920, "loss": 1.5753, "lr": 2.045990566037736e-06, "epoch": 0.4097877358490566, "percentage": 2.05, "elapsed_time": "0:01:14", "remaining_time": "0:59:33", "throughput": 6129.43, "total_tokens": 458240} {"current_steps": 700, "total_steps": 33920, "loss": 1.4879, "lr": 2.0607311320754718e-06, "epoch": 0.41273584905660377, "percentage": 2.06, "elapsed_time": "0:01:15", "remaining_time": "0:59:31", "throughput": 6131.03, "total_tokens": 461376} {"current_steps": 705, "total_steps": 33920, "loss": 1.2819, "lr": 2.075471698113208e-06, "epoch": 0.41568396226415094, "percentage": 2.08, "elapsed_time": "0:01:15", "remaining_time": "0:59:29", "throughput": 6131.24, "total_tokens": 464544} {"current_steps": 710, "total_steps": 33920, "loss": 1.5349, "lr": 2.0902122641509437e-06, "epoch": 0.4186320754716981, "percentage": 2.09, "elapsed_time": "0:01:16", "remaining_time": "0:59:25", "throughput": 6128.38, "total_tokens": 467168} {"current_steps": 715, "total_steps": 33920, "loss": 1.4353, "lr": 2.1049528301886795e-06, "epoch": 0.4215801886792453, "percentage": 2.11, "elapsed_time": "0:01:16", "remaining_time": "0:59:24", "throughput": 6123.57, "total_tokens": 470048} {"current_steps": 720, "total_steps": 33920, "loss": 1.4353, "lr": 2.1196933962264153e-06, "epoch": 0.42452830188679247, "percentage": 2.12, "elapsed_time": "0:01:17", "remaining_time": "0:59:22", "throughput": 6122.34, "total_tokens": 473056} {"current_steps": 725, "total_steps": 33920, "loss": 1.6527, "lr": 2.134433962264151e-06, "epoch": 0.42747641509433965, "percentage": 2.14, "elapsed_time": "0:01:17", "remaining_time": "0:59:20", "throughput": 6124.75, "total_tokens": 476288} {"current_steps": 730, "total_steps": 33920, "loss": 1.2416, "lr": 2.149174528301887e-06, "epoch": 0.43042452830188677, "percentage": 2.15, "elapsed_time": "0:01:18", "remaining_time": "0:59:18", "throughput": 6125.72, "total_tokens": 479392} {"current_steps": 735, "total_steps": 33920, "loss": 1.4099, "lr": 2.163915094339623e-06, "epoch": 0.43337264150943394, "percentage": 2.17, "elapsed_time": "0:01:18", "remaining_time": "0:59:16", "throughput": 6126.24, "total_tokens": 482560} {"current_steps": 740, "total_steps": 33920, "loss": 1.0659, "lr": 2.1786556603773588e-06, "epoch": 0.4363207547169811, "percentage": 2.18, "elapsed_time": "0:01:19", "remaining_time": "0:59:14", "throughput": 6124.54, "total_tokens": 485568} {"current_steps": 745, "total_steps": 33920, "loss": 1.4024, "lr": 2.1933962264150945e-06, "epoch": 0.4392688679245283, "percentage": 2.2, "elapsed_time": "0:01:19", "remaining_time": "0:59:11", "throughput": 6119.21, "total_tokens": 488032} {"current_steps": 750, "total_steps": 33920, "loss": 1.2506, "lr": 2.2081367924528303e-06, "epoch": 0.44221698113207547, "percentage": 2.21, "elapsed_time": "0:01:20", "remaining_time": "0:59:07", "throughput": 6117.52, "total_tokens": 490688} {"current_steps": 755, "total_steps": 33920, "loss": 1.3233, "lr": 2.2228773584905665e-06, "epoch": 0.44516509433962265, "percentage": 2.23, "elapsed_time": "0:01:20", "remaining_time": "0:59:04", "throughput": 6117.37, "total_tokens": 493568} {"current_steps": 760, "total_steps": 33920, "loss": 1.5822, "lr": 2.237617924528302e-06, "epoch": 0.4481132075471698, "percentage": 2.24, "elapsed_time": "0:01:21", "remaining_time": "0:58:59", "throughput": 6114.6, "total_tokens": 496096} {"current_steps": 765, "total_steps": 33920, "loss": 1.3496, "lr": 2.252358490566038e-06, "epoch": 0.451061320754717, "percentage": 2.26, "elapsed_time": "0:01:21", "remaining_time": "0:59:00", "throughput": 6110.42, "total_tokens": 499136} {"current_steps": 770, "total_steps": 33920, "loss": 1.1394, "lr": 2.267099056603774e-06, "epoch": 0.4540094339622642, "percentage": 2.27, "elapsed_time": "0:01:22", "remaining_time": "0:58:57", "throughput": 6110.26, "total_tokens": 502048} {"current_steps": 775, "total_steps": 33920, "loss": 1.0007, "lr": 2.2818396226415096e-06, "epoch": 0.4569575471698113, "percentage": 2.28, "elapsed_time": "0:01:22", "remaining_time": "0:58:56", "throughput": 6113.24, "total_tokens": 505504} {"current_steps": 780, "total_steps": 33920, "loss": 1.1778, "lr": 2.2965801886792453e-06, "epoch": 0.45990566037735847, "percentage": 2.3, "elapsed_time": "0:01:23", "remaining_time": "0:58:53", "throughput": 6114.75, "total_tokens": 508512} {"current_steps": 785, "total_steps": 33920, "loss": 0.8564, "lr": 2.3113207547169815e-06, "epoch": 0.46285377358490565, "percentage": 2.31, "elapsed_time": "0:01:23", "remaining_time": "0:58:51", "throughput": 6117.32, "total_tokens": 511808} {"current_steps": 790, "total_steps": 33920, "loss": 1.0445, "lr": 2.3260613207547173e-06, "epoch": 0.4658018867924528, "percentage": 2.33, "elapsed_time": "0:01:24", "remaining_time": "0:58:46", "throughput": 6113.29, "total_tokens": 514144} {"current_steps": 795, "total_steps": 33920, "loss": 0.9787, "lr": 2.340801886792453e-06, "epoch": 0.46875, "percentage": 2.34, "elapsed_time": "0:01:24", "remaining_time": "0:58:44", "throughput": 6113.04, "total_tokens": 517120} {"current_steps": 800, "total_steps": 33920, "loss": 0.9612, "lr": 2.355542452830189e-06, "epoch": 0.4716981132075472, "percentage": 2.36, "elapsed_time": "0:01:25", "remaining_time": "0:58:41", "throughput": 6112.14, "total_tokens": 519904} {"current_steps": 805, "total_steps": 33920, "loss": 0.9598, "lr": 2.3702830188679246e-06, "epoch": 0.47464622641509435, "percentage": 2.37, "elapsed_time": "0:01:25", "remaining_time": "0:58:42", "throughput": 6114.17, "total_tokens": 523520} {"current_steps": 810, "total_steps": 33920, "loss": 0.7343, "lr": 2.3850235849056604e-06, "epoch": 0.47759433962264153, "percentage": 2.39, "elapsed_time": "0:01:26", "remaining_time": "0:58:38", "throughput": 6110.37, "total_tokens": 525952} {"current_steps": 815, "total_steps": 33920, "loss": 0.9348, "lr": 2.3997641509433966e-06, "epoch": 0.4805424528301887, "percentage": 2.4, "elapsed_time": "0:01:26", "remaining_time": "0:58:39", "throughput": 6111.16, "total_tokens": 529504} {"current_steps": 820, "total_steps": 33920, "loss": 0.8783, "lr": 2.4145047169811323e-06, "epoch": 0.4834905660377358, "percentage": 2.42, "elapsed_time": "0:01:27", "remaining_time": "0:58:38", "throughput": 6113.51, "total_tokens": 532960} {"current_steps": 825, "total_steps": 33920, "loss": 0.8925, "lr": 2.429245283018868e-06, "epoch": 0.486438679245283, "percentage": 2.43, "elapsed_time": "0:01:27", "remaining_time": "0:58:36", "throughput": 6111.68, "total_tokens": 535744} {"current_steps": 830, "total_steps": 33920, "loss": 0.8738, "lr": 2.443985849056604e-06, "epoch": 0.4893867924528302, "percentage": 2.45, "elapsed_time": "0:01:28", "remaining_time": "0:58:36", "throughput": 6114.82, "total_tokens": 539392} {"current_steps": 835, "total_steps": 33920, "loss": 0.6848, "lr": 2.45872641509434e-06, "epoch": 0.49233490566037735, "percentage": 2.46, "elapsed_time": "0:01:28", "remaining_time": "0:58:36", "throughput": 6117.44, "total_tokens": 542912} {"current_steps": 840, "total_steps": 33920, "loss": 0.7666, "lr": 2.473466981132076e-06, "epoch": 0.49528301886792453, "percentage": 2.48, "elapsed_time": "0:01:29", "remaining_time": "0:58:39", "throughput": 6121.74, "total_tokens": 547040} {"current_steps": 845, "total_steps": 33920, "loss": 0.7332, "lr": 2.4882075471698116e-06, "epoch": 0.4982311320754717, "percentage": 2.49, "elapsed_time": "0:01:29", "remaining_time": "0:58:36", "throughput": 6121.64, "total_tokens": 550016} {"current_steps": 850, "total_steps": 33920, "loss": 0.7395, "lr": 2.5029481132075474e-06, "epoch": 0.5011792452830188, "percentage": 2.51, "elapsed_time": "0:01:30", "remaining_time": "0:58:34", "throughput": 6119.52, "total_tokens": 552768} {"current_steps": 855, "total_steps": 33920, "loss": 0.9378, "lr": 2.517688679245283e-06, "epoch": 0.504127358490566, "percentage": 2.52, "elapsed_time": "0:01:30", "remaining_time": "0:58:33", "throughput": 6120.36, "total_tokens": 556096} {"current_steps": 860, "total_steps": 33920, "loss": 0.9479, "lr": 2.532429245283019e-06, "epoch": 0.5070754716981132, "percentage": 2.54, "elapsed_time": "0:01:31", "remaining_time": "0:58:33", "throughput": 6123.3, "total_tokens": 559712} {"current_steps": 865, "total_steps": 33920, "loss": 0.8438, "lr": 2.547169811320755e-06, "epoch": 0.5100235849056604, "percentage": 2.55, "elapsed_time": "0:01:31", "remaining_time": "0:58:33", "throughput": 6123.33, "total_tokens": 563008} {"current_steps": 870, "total_steps": 33920, "loss": 0.6522, "lr": 2.561910377358491e-06, "epoch": 0.5129716981132075, "percentage": 2.56, "elapsed_time": "0:01:32", "remaining_time": "0:58:34", "throughput": 6125.03, "total_tokens": 566592} {"current_steps": 875, "total_steps": 33920, "loss": 0.7146, "lr": 2.5766509433962266e-06, "epoch": 0.5159198113207547, "percentage": 2.58, "elapsed_time": "0:01:33", "remaining_time": "0:58:35", "throughput": 6125.69, "total_tokens": 570144} {"current_steps": 880, "total_steps": 33920, "loss": 0.9545, "lr": 2.5913915094339624e-06, "epoch": 0.5188679245283019, "percentage": 2.59, "elapsed_time": "0:01:33", "remaining_time": "0:58:35", "throughput": 6130.0, "total_tokens": 573984} {"current_steps": 885, "total_steps": 33920, "loss": 0.8072, "lr": 2.6061320754716986e-06, "epoch": 0.5218160377358491, "percentage": 2.61, "elapsed_time": "0:01:34", "remaining_time": "0:58:32", "throughput": 6126.82, "total_tokens": 576608} {"current_steps": 890, "total_steps": 33920, "loss": 0.7248, "lr": 2.6208726415094343e-06, "epoch": 0.5247641509433962, "percentage": 2.62, "elapsed_time": "0:01:34", "remaining_time": "0:58:30", "throughput": 6126.56, "total_tokens": 579520} {"current_steps": 895, "total_steps": 33920, "loss": 0.6788, "lr": 2.63561320754717e-06, "epoch": 0.5277122641509434, "percentage": 2.64, "elapsed_time": "0:01:35", "remaining_time": "0:58:30", "throughput": 6128.07, "total_tokens": 582976} {"current_steps": 900, "total_steps": 33920, "loss": 0.7293, "lr": 2.650353773584906e-06, "epoch": 0.5306603773584906, "percentage": 2.65, "elapsed_time": "0:01:35", "remaining_time": "0:58:29", "throughput": 6127.65, "total_tokens": 586176} {"current_steps": 905, "total_steps": 33920, "loss": 0.5789, "lr": 2.665094339622642e-06, "epoch": 0.5336084905660378, "percentage": 2.67, "elapsed_time": "0:01:36", "remaining_time": "0:58:27", "throughput": 6126.9, "total_tokens": 589088} {"current_steps": 910, "total_steps": 33920, "loss": 0.6258, "lr": 2.679834905660378e-06, "epoch": 0.5365566037735849, "percentage": 2.68, "elapsed_time": "0:01:36", "remaining_time": "0:58:26", "throughput": 6127.11, "total_tokens": 592256} {"current_steps": 915, "total_steps": 33920, "loss": 0.6574, "lr": 2.694575471698113e-06, "epoch": 0.5395047169811321, "percentage": 2.7, "elapsed_time": "0:01:37", "remaining_time": "0:58:38", "throughput": 6133.4, "total_tokens": 598336} {"current_steps": 920, "total_steps": 33920, "loss": 0.7137, "lr": 2.709316037735849e-06, "epoch": 0.5424528301886793, "percentage": 2.71, "elapsed_time": "0:01:38", "remaining_time": "0:58:39", "throughput": 6138.13, "total_tokens": 602336} {"current_steps": 925, "total_steps": 33920, "loss": 0.7011, "lr": 2.724056603773585e-06, "epoch": 0.5454009433962265, "percentage": 2.73, "elapsed_time": "0:01:38", "remaining_time": "0:58:37", "throughput": 6136.87, "total_tokens": 605120} {"current_steps": 930, "total_steps": 33920, "loss": 0.8423, "lr": 2.738797169811321e-06, "epoch": 0.5483490566037735, "percentage": 2.74, "elapsed_time": "0:01:39", "remaining_time": "0:58:37", "throughput": 6138.19, "total_tokens": 608640} {"current_steps": 935, "total_steps": 33920, "loss": 0.8639, "lr": 2.7535377358490567e-06, "epoch": 0.5512971698113207, "percentage": 2.76, "elapsed_time": "0:01:39", "remaining_time": "0:58:35", "throughput": 6139.53, "total_tokens": 611840} {"current_steps": 940, "total_steps": 33920, "loss": 0.6704, "lr": 2.7682783018867925e-06, "epoch": 0.5542452830188679, "percentage": 2.77, "elapsed_time": "0:01:40", "remaining_time": "0:58:35", "throughput": 6141.93, "total_tokens": 615488} {"current_steps": 945, "total_steps": 33920, "loss": 0.7935, "lr": 2.7830188679245286e-06, "epoch": 0.5571933962264151, "percentage": 2.79, "elapsed_time": "0:01:40", "remaining_time": "0:58:34", "throughput": 6143.49, "total_tokens": 618848} {"current_steps": 950, "total_steps": 33920, "loss": 0.6561, "lr": 2.7977594339622644e-06, "epoch": 0.5601415094339622, "percentage": 2.8, "elapsed_time": "0:01:41", "remaining_time": "0:58:34", "throughput": 6145.59, "total_tokens": 622272} {"current_steps": 955, "total_steps": 33920, "loss": 0.5682, "lr": 2.8125e-06, "epoch": 0.5630896226415094, "percentage": 2.82, "elapsed_time": "0:01:41", "remaining_time": "0:58:33", "throughput": 6146.2, "total_tokens": 625632} {"current_steps": 960, "total_steps": 33920, "loss": 0.8593, "lr": 2.827240566037736e-06, "epoch": 0.5660377358490566, "percentage": 2.83, "elapsed_time": "0:01:42", "remaining_time": "0:58:30", "throughput": 6145.71, "total_tokens": 628448} {"current_steps": 965, "total_steps": 33920, "loss": 0.727, "lr": 2.841981132075472e-06, "epoch": 0.5689858490566038, "percentage": 2.84, "elapsed_time": "0:01:42", "remaining_time": "0:58:35", "throughput": 6147.02, "total_tokens": 632736} {"current_steps": 970, "total_steps": 33920, "loss": 0.6668, "lr": 2.856721698113208e-06, "epoch": 0.5719339622641509, "percentage": 2.86, "elapsed_time": "0:01:43", "remaining_time": "0:58:35", "throughput": 6150.39, "total_tokens": 636576} {"current_steps": 975, "total_steps": 33920, "loss": 0.5873, "lr": 2.8714622641509437e-06, "epoch": 0.5748820754716981, "percentage": 2.87, "elapsed_time": "0:01:44", "remaining_time": "0:58:36", "throughput": 6148.36, "total_tokens": 639840} {"current_steps": 980, "total_steps": 33920, "loss": 0.8116, "lr": 2.8862028301886794e-06, "epoch": 0.5778301886792453, "percentage": 2.89, "elapsed_time": "0:01:44", "remaining_time": "0:58:38", "throughput": 6150.05, "total_tokens": 643712} {"current_steps": 985, "total_steps": 33920, "loss": 0.7136, "lr": 2.9009433962264156e-06, "epoch": 0.5807783018867925, "percentage": 2.9, "elapsed_time": "0:01:45", "remaining_time": "0:58:40", "throughput": 6154.04, "total_tokens": 648000} {"current_steps": 990, "total_steps": 33920, "loss": 0.7514, "lr": 2.9156839622641514e-06, "epoch": 0.5837264150943396, "percentage": 2.92, "elapsed_time": "0:01:45", "remaining_time": "0:58:41", "throughput": 6153.64, "total_tokens": 651488} {"current_steps": 995, "total_steps": 33920, "loss": 0.6084, "lr": 2.930424528301887e-06, "epoch": 0.5866745283018868, "percentage": 2.93, "elapsed_time": "0:01:46", "remaining_time": "0:58:41", "throughput": 6152.33, "total_tokens": 654688} {"current_steps": 1000, "total_steps": 33920, "loss": 0.6281, "lr": 2.9451650943396225e-06, "epoch": 0.589622641509434, "percentage": 2.95, "elapsed_time": "0:01:46", "remaining_time": "0:58:39", "throughput": 6148.81, "total_tokens": 657440} {"current_steps": 1005, "total_steps": 33920, "loss": 0.7459, "lr": 2.9599056603773587e-06, "epoch": 0.5925707547169812, "percentage": 2.96, "elapsed_time": "0:01:47", "remaining_time": "0:58:39", "throughput": 6149.21, "total_tokens": 660768} {"current_steps": 1010, "total_steps": 33920, "loss": 0.7491, "lr": 2.9746462264150945e-06, "epoch": 0.5955188679245284, "percentage": 2.98, "elapsed_time": "0:01:48", "remaining_time": "0:58:43", "throughput": 6154.11, "total_tokens": 665536} {"current_steps": 1015, "total_steps": 33920, "loss": 0.7072, "lr": 2.9893867924528302e-06, "epoch": 0.5984669811320755, "percentage": 2.99, "elapsed_time": "0:01:48", "remaining_time": "0:58:42", "throughput": 6154.74, "total_tokens": 668736} {"current_steps": 1020, "total_steps": 33920, "loss": 0.5703, "lr": 3.004127358490566e-06, "epoch": 0.6014150943396226, "percentage": 3.01, "elapsed_time": "0:01:49", "remaining_time": "0:58:40", "throughput": 6152.21, "total_tokens": 671584} {"current_steps": 1025, "total_steps": 33920, "loss": 0.5921, "lr": 3.018867924528302e-06, "epoch": 0.6043632075471698, "percentage": 3.02, "elapsed_time": "0:01:49", "remaining_time": "0:58:40", "throughput": 6150.67, "total_tokens": 674688} {"current_steps": 1030, "total_steps": 33920, "loss": 0.7202, "lr": 3.033608490566038e-06, "epoch": 0.6073113207547169, "percentage": 3.04, "elapsed_time": "0:01:50", "remaining_time": "0:58:45", "throughput": 6154.99, "total_tokens": 679616} {"current_steps": 1035, "total_steps": 33920, "loss": 0.6464, "lr": 3.0483490566037737e-06, "epoch": 0.6102594339622641, "percentage": 3.05, "elapsed_time": "0:01:51", "remaining_time": "0:58:49", "throughput": 6159.65, "total_tokens": 684288} {"current_steps": 1040, "total_steps": 33920, "loss": 0.7889, "lr": 3.0630896226415095e-06, "epoch": 0.6132075471698113, "percentage": 3.07, "elapsed_time": "0:01:51", "remaining_time": "0:58:50", "throughput": 6159.13, "total_tokens": 687776} {"current_steps": 1045, "total_steps": 33920, "loss": 0.7147, "lr": 3.0778301886792457e-06, "epoch": 0.6161556603773585, "percentage": 3.08, "elapsed_time": "0:01:52", "remaining_time": "0:58:50", "throughput": 6159.97, "total_tokens": 691264} {"current_steps": 1050, "total_steps": 33920, "loss": 0.5842, "lr": 3.0925707547169815e-06, "epoch": 0.6191037735849056, "percentage": 3.1, "elapsed_time": "0:01:52", "remaining_time": "0:58:51", "throughput": 6160.57, "total_tokens": 694976} {"current_steps": 1055, "total_steps": 33920, "loss": 0.6791, "lr": 3.1073113207547172e-06, "epoch": 0.6220518867924528, "percentage": 3.11, "elapsed_time": "0:01:53", "remaining_time": "0:58:48", "throughput": 6156.91, "total_tokens": 697472} {"current_steps": 1060, "total_steps": 33920, "loss": 0.8094, "lr": 3.122051886792453e-06, "epoch": 0.625, "percentage": 3.12, "elapsed_time": "0:01:53", "remaining_time": "0:58:48", "throughput": 6159.03, "total_tokens": 701088} {"current_steps": 1065, "total_steps": 33920, "loss": 0.7867, "lr": 3.136792452830189e-06, "epoch": 0.6279481132075472, "percentage": 3.14, "elapsed_time": "0:01:54", "remaining_time": "0:58:49", "throughput": 6159.44, "total_tokens": 704640} {"current_steps": 1070, "total_steps": 33920, "loss": 0.5568, "lr": 3.151533018867925e-06, "epoch": 0.6308962264150944, "percentage": 3.15, "elapsed_time": "0:01:54", "remaining_time": "0:58:46", "throughput": 6159.76, "total_tokens": 707584} {"current_steps": 1075, "total_steps": 33920, "loss": 0.7206, "lr": 3.1662735849056607e-06, "epoch": 0.6338443396226415, "percentage": 3.17, "elapsed_time": "0:01:55", "remaining_time": "0:58:44", "throughput": 6159.89, "total_tokens": 710560} {"current_steps": 1080, "total_steps": 33920, "loss": 0.672, "lr": 3.181014150943397e-06, "epoch": 0.6367924528301887, "percentage": 3.18, "elapsed_time": "0:01:56", "remaining_time": "0:58:48", "throughput": 6164.8, "total_tokens": 715424} {"current_steps": 1085, "total_steps": 33920, "loss": 0.5535, "lr": 3.1957547169811327e-06, "epoch": 0.6397405660377359, "percentage": 3.2, "elapsed_time": "0:01:56", "remaining_time": "0:58:46", "throughput": 6160.84, "total_tokens": 717952} {"current_steps": 1090, "total_steps": 33920, "loss": 0.7721, "lr": 3.210495283018868e-06, "epoch": 0.6426886792452831, "percentage": 3.21, "elapsed_time": "0:01:57", "remaining_time": "0:58:44", "throughput": 6158.5, "total_tokens": 720608} {"current_steps": 1095, "total_steps": 33920, "loss": 0.4886, "lr": 3.225235849056604e-06, "epoch": 0.6456367924528302, "percentage": 3.23, "elapsed_time": "0:01:57", "remaining_time": "0:58:42", "throughput": 6155.47, "total_tokens": 723264} {"current_steps": 1100, "total_steps": 33920, "loss": 0.537, "lr": 3.2399764150943396e-06, "epoch": 0.6485849056603774, "percentage": 3.24, "elapsed_time": "0:01:58", "remaining_time": "0:58:47", "throughput": 6157.84, "total_tokens": 727968} {"current_steps": 1105, "total_steps": 33920, "loss": 0.6572, "lr": 3.2547169811320758e-06, "epoch": 0.6515330188679245, "percentage": 3.26, "elapsed_time": "0:01:58", "remaining_time": "0:58:48", "throughput": 6160.22, "total_tokens": 731936} {"current_steps": 1110, "total_steps": 33920, "loss": 0.5512, "lr": 3.2694575471698115e-06, "epoch": 0.6544811320754716, "percentage": 3.27, "elapsed_time": "0:01:59", "remaining_time": "0:58:47", "throughput": 6161.19, "total_tokens": 735200} {"current_steps": 1115, "total_steps": 33920, "loss": 0.6502, "lr": 3.2841981132075473e-06, "epoch": 0.6574292452830188, "percentage": 3.29, "elapsed_time": "0:01:59", "remaining_time": "0:58:44", "throughput": 6160.21, "total_tokens": 738048} {"current_steps": 1120, "total_steps": 33920, "loss": 0.6195, "lr": 3.298938679245283e-06, "epoch": 0.660377358490566, "percentage": 3.3, "elapsed_time": "0:02:00", "remaining_time": "0:58:43", "throughput": 6155.85, "total_tokens": 740672} {"current_steps": 1125, "total_steps": 33920, "loss": 0.7606, "lr": 3.3136792452830192e-06, "epoch": 0.6633254716981132, "percentage": 3.32, "elapsed_time": "0:02:00", "remaining_time": "0:58:45", "throughput": 6153.68, "total_tokens": 744192} {"current_steps": 1130, "total_steps": 33920, "loss": 0.5875, "lr": 3.328419811320755e-06, "epoch": 0.6662735849056604, "percentage": 3.33, "elapsed_time": "0:02:01", "remaining_time": "0:58:52", "throughput": 6154.91, "total_tokens": 749184} {"current_steps": 1135, "total_steps": 33920, "loss": 0.6495, "lr": 3.3431603773584908e-06, "epoch": 0.6692216981132075, "percentage": 3.35, "elapsed_time": "0:02:02", "remaining_time": "0:58:49", "throughput": 6150.07, "total_tokens": 751552} {"current_steps": 1140, "total_steps": 33920, "loss": 0.661, "lr": 3.3579009433962266e-06, "epoch": 0.6721698113207547, "percentage": 3.36, "elapsed_time": "0:02:02", "remaining_time": "0:58:48", "throughput": 6150.35, "total_tokens": 754752} {"current_steps": 1145, "total_steps": 33920, "loss": 0.5478, "lr": 3.3726415094339627e-06, "epoch": 0.6751179245283019, "percentage": 3.38, "elapsed_time": "0:02:03", "remaining_time": "0:58:46", "throughput": 6151.31, "total_tokens": 757824} {"current_steps": 1150, "total_steps": 33920, "loss": 0.6251, "lr": 3.3873820754716985e-06, "epoch": 0.6780660377358491, "percentage": 3.39, "elapsed_time": "0:02:03", "remaining_time": "0:58:45", "throughput": 6152.48, "total_tokens": 761088} {"current_steps": 1155, "total_steps": 33920, "loss": 0.5632, "lr": 3.4021226415094343e-06, "epoch": 0.6810141509433962, "percentage": 3.41, "elapsed_time": "0:02:04", "remaining_time": "0:58:43", "throughput": 6152.08, "total_tokens": 764224} {"current_steps": 1160, "total_steps": 33920, "loss": 0.6473, "lr": 3.4168632075471705e-06, "epoch": 0.6839622641509434, "percentage": 3.42, "elapsed_time": "0:02:04", "remaining_time": "0:58:43", "throughput": 6151.72, "total_tokens": 767488} {"current_steps": 1165, "total_steps": 33920, "loss": 0.452, "lr": 3.4316037735849062e-06, "epoch": 0.6869103773584906, "percentage": 3.43, "elapsed_time": "0:02:05", "remaining_time": "0:58:42", "throughput": 6152.82, "total_tokens": 770784} {"current_steps": 1170, "total_steps": 33920, "loss": 0.6062, "lr": 3.446344339622642e-06, "epoch": 0.6898584905660378, "percentage": 3.45, "elapsed_time": "0:02:05", "remaining_time": "0:58:40", "throughput": 6153.07, "total_tokens": 773792} {"current_steps": 1175, "total_steps": 33920, "loss": 0.6429, "lr": 3.4610849056603778e-06, "epoch": 0.6928066037735849, "percentage": 3.46, "elapsed_time": "0:02:06", "remaining_time": "0:58:39", "throughput": 6153.93, "total_tokens": 777216} {"current_steps": 1180, "total_steps": 33920, "loss": 0.7303, "lr": 3.475825471698113e-06, "epoch": 0.6957547169811321, "percentage": 3.48, "elapsed_time": "0:02:06", "remaining_time": "0:58:38", "throughput": 6154.82, "total_tokens": 780544} {"current_steps": 1185, "total_steps": 33920, "loss": 0.4687, "lr": 3.4905660377358493e-06, "epoch": 0.6987028301886793, "percentage": 3.49, "elapsed_time": "0:02:07", "remaining_time": "0:58:36", "throughput": 6153.78, "total_tokens": 783264} {"current_steps": 1190, "total_steps": 33920, "loss": 0.4716, "lr": 3.505306603773585e-06, "epoch": 0.7016509433962265, "percentage": 3.51, "elapsed_time": "0:02:07", "remaining_time": "0:58:35", "throughput": 6155.45, "total_tokens": 786688} {"current_steps": 1195, "total_steps": 33920, "loss": 0.7469, "lr": 3.520047169811321e-06, "epoch": 0.7045990566037735, "percentage": 3.52, "elapsed_time": "0:02:08", "remaining_time": "0:58:34", "throughput": 6156.19, "total_tokens": 790112} {"current_steps": 1200, "total_steps": 33920, "loss": 0.7238, "lr": 3.5347877358490566e-06, "epoch": 0.7075471698113207, "percentage": 3.54, "elapsed_time": "0:02:08", "remaining_time": "0:58:31", "throughput": 6155.61, "total_tokens": 792832} {"current_steps": 1205, "total_steps": 33920, "loss": 0.5085, "lr": 3.549528301886793e-06, "epoch": 0.7104952830188679, "percentage": 3.55, "elapsed_time": "0:02:09", "remaining_time": "0:58:29", "throughput": 6154.89, "total_tokens": 795584} {"current_steps": 1210, "total_steps": 33920, "loss": 0.7549, "lr": 3.5642688679245286e-06, "epoch": 0.7134433962264151, "percentage": 3.57, "elapsed_time": "0:02:09", "remaining_time": "0:58:28", "throughput": 6154.29, "total_tokens": 798848} {"current_steps": 1215, "total_steps": 33920, "loss": 0.6684, "lr": 3.5790094339622643e-06, "epoch": 0.7163915094339622, "percentage": 3.58, "elapsed_time": "0:02:10", "remaining_time": "0:58:28", "throughput": 6155.52, "total_tokens": 802272} {"current_steps": 1220, "total_steps": 33920, "loss": 0.7879, "lr": 3.59375e-06, "epoch": 0.7193396226415094, "percentage": 3.6, "elapsed_time": "0:02:10", "remaining_time": "0:58:25", "throughput": 6155.4, "total_tokens": 804960} {"current_steps": 1225, "total_steps": 33920, "loss": 0.5593, "lr": 3.6084905660377363e-06, "epoch": 0.7222877358490566, "percentage": 3.61, "elapsed_time": "0:02:11", "remaining_time": "0:58:23", "throughput": 6151.18, "total_tokens": 807424} {"current_steps": 1230, "total_steps": 33920, "loss": 0.6634, "lr": 3.623231132075472e-06, "epoch": 0.7252358490566038, "percentage": 3.63, "elapsed_time": "0:02:11", "remaining_time": "0:58:20", "throughput": 6149.79, "total_tokens": 809920} {"current_steps": 1235, "total_steps": 33920, "loss": 0.5061, "lr": 3.637971698113208e-06, "epoch": 0.7281839622641509, "percentage": 3.64, "elapsed_time": "0:02:12", "remaining_time": "0:58:17", "throughput": 6148.97, "total_tokens": 812640} {"current_steps": 1240, "total_steps": 33920, "loss": 0.7193, "lr": 3.652712264150944e-06, "epoch": 0.7311320754716981, "percentage": 3.66, "elapsed_time": "0:02:12", "remaining_time": "0:58:20", "throughput": 6152.91, "total_tokens": 817248} {"current_steps": 1245, "total_steps": 33920, "loss": 0.7386, "lr": 3.66745283018868e-06, "epoch": 0.7340801886792453, "percentage": 3.67, "elapsed_time": "0:02:13", "remaining_time": "0:58:17", "throughput": 6151.74, "total_tokens": 819872} {"current_steps": 1250, "total_steps": 33920, "loss": 0.6575, "lr": 3.6821933962264156e-06, "epoch": 0.7370283018867925, "percentage": 3.69, "elapsed_time": "0:02:13", "remaining_time": "0:58:19", "throughput": 6155.35, "total_tokens": 824256} {"current_steps": 1255, "total_steps": 33920, "loss": 0.6276, "lr": 3.6969339622641513e-06, "epoch": 0.7399764150943396, "percentage": 3.7, "elapsed_time": "0:02:14", "remaining_time": "0:58:18", "throughput": 6155.97, "total_tokens": 827488} {"current_steps": 1260, "total_steps": 33920, "loss": 0.7224, "lr": 3.7116745283018875e-06, "epoch": 0.7429245283018868, "percentage": 3.71, "elapsed_time": "0:02:15", "remaining_time": "0:58:20", "throughput": 6157.52, "total_tokens": 831488} {"current_steps": 1265, "total_steps": 33920, "loss": 0.6179, "lr": 3.726415094339623e-06, "epoch": 0.745872641509434, "percentage": 3.73, "elapsed_time": "0:02:15", "remaining_time": "0:58:19", "throughput": 6158.08, "total_tokens": 834752} {"current_steps": 1270, "total_steps": 33920, "loss": 0.6258, "lr": 3.7411556603773586e-06, "epoch": 0.7488207547169812, "percentage": 3.74, "elapsed_time": "0:02:15", "remaining_time": "0:58:16", "throughput": 6156.19, "total_tokens": 837216} {"current_steps": 1275, "total_steps": 33920, "loss": 0.7695, "lr": 3.7558962264150944e-06, "epoch": 0.7517688679245284, "percentage": 3.76, "elapsed_time": "0:02:16", "remaining_time": "0:58:16", "throughput": 6158.37, "total_tokens": 841024} {"current_steps": 1280, "total_steps": 33920, "loss": 0.7388, "lr": 3.77063679245283e-06, "epoch": 0.7547169811320755, "percentage": 3.77, "elapsed_time": "0:02:16", "remaining_time": "0:58:13", "throughput": 6156.15, "total_tokens": 843328} {"current_steps": 1285, "total_steps": 33920, "loss": 0.5092, "lr": 3.7853773584905664e-06, "epoch": 0.7576650943396226, "percentage": 3.79, "elapsed_time": "0:02:17", "remaining_time": "0:58:13", "throughput": 6157.18, "total_tokens": 846912} {"current_steps": 1290, "total_steps": 33920, "loss": 0.6036, "lr": 3.800117924528302e-06, "epoch": 0.7606132075471698, "percentage": 3.8, "elapsed_time": "0:02:18", "remaining_time": "0:58:11", "throughput": 6157.6, "total_tokens": 849984} {"current_steps": 1295, "total_steps": 33920, "loss": 0.6442, "lr": 3.814858490566038e-06, "epoch": 0.7635613207547169, "percentage": 3.82, "elapsed_time": "0:02:18", "remaining_time": "0:58:10", "throughput": 6159.02, "total_tokens": 853408} {"current_steps": 1300, "total_steps": 33920, "loss": 0.5688, "lr": 3.829599056603774e-06, "epoch": 0.7665094339622641, "percentage": 3.83, "elapsed_time": "0:02:19", "remaining_time": "0:58:09", "throughput": 6159.36, "total_tokens": 856480} {"current_steps": 1305, "total_steps": 33920, "loss": 0.6107, "lr": 3.8443396226415094e-06, "epoch": 0.7694575471698113, "percentage": 3.85, "elapsed_time": "0:02:19", "remaining_time": "0:58:09", "throughput": 6161.76, "total_tokens": 860320} {"current_steps": 1310, "total_steps": 33920, "loss": 0.5536, "lr": 3.859080188679246e-06, "epoch": 0.7724056603773585, "percentage": 3.86, "elapsed_time": "0:02:20", "remaining_time": "0:58:06", "throughput": 6160.62, "total_tokens": 862912} {"current_steps": 1315, "total_steps": 33920, "loss": 0.6512, "lr": 3.873820754716982e-06, "epoch": 0.7753537735849056, "percentage": 3.88, "elapsed_time": "0:02:20", "remaining_time": "0:58:04", "throughput": 6161.24, "total_tokens": 865952} {"current_steps": 1320, "total_steps": 33920, "loss": 0.6134, "lr": 3.888561320754717e-06, "epoch": 0.7783018867924528, "percentage": 3.89, "elapsed_time": "0:02:21", "remaining_time": "0:58:04", "throughput": 6162.39, "total_tokens": 869376} {"current_steps": 1325, "total_steps": 33920, "loss": 0.5273, "lr": 3.903301886792453e-06, "epoch": 0.78125, "percentage": 3.91, "elapsed_time": "0:02:21", "remaining_time": "0:58:01", "throughput": 6160.71, "total_tokens": 871968} {"current_steps": 1330, "total_steps": 33920, "loss": 0.4988, "lr": 3.9180424528301895e-06, "epoch": 0.7841981132075472, "percentage": 3.92, "elapsed_time": "0:02:22", "remaining_time": "0:58:02", "throughput": 6163.15, "total_tokens": 875872} {"current_steps": 1335, "total_steps": 33920, "loss": 0.5674, "lr": 3.932783018867925e-06, "epoch": 0.7871462264150944, "percentage": 3.94, "elapsed_time": "0:02:22", "remaining_time": "0:57:59", "throughput": 6162.86, "total_tokens": 878496} {"current_steps": 1340, "total_steps": 33920, "loss": 0.5671, "lr": 3.947523584905661e-06, "epoch": 0.7900943396226415, "percentage": 3.95, "elapsed_time": "0:02:22", "remaining_time": "0:57:56", "throughput": 6161.64, "total_tokens": 881088} {"current_steps": 1345, "total_steps": 33920, "loss": 0.606, "lr": 3.962264150943396e-06, "epoch": 0.7930424528301887, "percentage": 3.97, "elapsed_time": "0:02:23", "remaining_time": "0:57:56", "throughput": 6161.43, "total_tokens": 884320} {"current_steps": 1350, "total_steps": 33920, "loss": 0.5859, "lr": 3.977004716981133e-06, "epoch": 0.7959905660377359, "percentage": 3.98, "elapsed_time": "0:02:23", "remaining_time": "0:57:53", "throughput": 6157.35, "total_tokens": 886464} {"current_steps": 1355, "total_steps": 33920, "loss": 0.778, "lr": 3.991745283018868e-06, "epoch": 0.7989386792452831, "percentage": 3.99, "elapsed_time": "0:02:24", "remaining_time": "0:57:52", "throughput": 6158.7, "total_tokens": 889920} {"current_steps": 1360, "total_steps": 33920, "loss": 0.625, "lr": 4.006485849056604e-06, "epoch": 0.8018867924528302, "percentage": 4.01, "elapsed_time": "0:02:24", "remaining_time": "0:57:49", "throughput": 6157.57, "total_tokens": 892448} {"current_steps": 1365, "total_steps": 33920, "loss": 0.5854, "lr": 4.0212264150943395e-06, "epoch": 0.8048349056603774, "percentage": 4.02, "elapsed_time": "0:02:25", "remaining_time": "0:57:49", "throughput": 6159.25, "total_tokens": 895968} {"current_steps": 1370, "total_steps": 33920, "loss": 0.6505, "lr": 4.035966981132076e-06, "epoch": 0.8077830188679245, "percentage": 4.04, "elapsed_time": "0:02:25", "remaining_time": "0:57:48", "throughput": 6160.18, "total_tokens": 899200} {"current_steps": 1375, "total_steps": 33920, "loss": 0.6649, "lr": 4.050707547169812e-06, "epoch": 0.8107311320754716, "percentage": 4.05, "elapsed_time": "0:02:26", "remaining_time": "0:57:46", "throughput": 6157.14, "total_tokens": 901696} {"current_steps": 1380, "total_steps": 33920, "loss": 0.4304, "lr": 4.065448113207547e-06, "epoch": 0.8136792452830188, "percentage": 4.07, "elapsed_time": "0:02:26", "remaining_time": "0:57:44", "throughput": 6156.83, "total_tokens": 904672} {"current_steps": 1385, "total_steps": 33920, "loss": 0.7747, "lr": 4.080188679245283e-06, "epoch": 0.816627358490566, "percentage": 4.08, "elapsed_time": "0:02:27", "remaining_time": "0:57:42", "throughput": 6155.83, "total_tokens": 907328} {"current_steps": 1390, "total_steps": 33920, "loss": 0.5602, "lr": 4.094929245283019e-06, "epoch": 0.8195754716981132, "percentage": 4.1, "elapsed_time": "0:02:27", "remaining_time": "0:57:39", "throughput": 6154.62, "total_tokens": 909920} {"current_steps": 1395, "total_steps": 33920, "loss": 0.7597, "lr": 4.109669811320755e-06, "epoch": 0.8225235849056604, "percentage": 4.11, "elapsed_time": "0:02:28", "remaining_time": "0:57:37", "throughput": 6154.48, "total_tokens": 912608} {"current_steps": 1400, "total_steps": 33920, "loss": 0.509, "lr": 4.124410377358491e-06, "epoch": 0.8254716981132075, "percentage": 4.13, "elapsed_time": "0:02:28", "remaining_time": "0:57:36", "throughput": 6154.88, "total_tokens": 915872} {"current_steps": 1405, "total_steps": 33920, "loss": 0.4469, "lr": 4.1391509433962265e-06, "epoch": 0.8284198113207547, "percentage": 4.14, "elapsed_time": "0:02:29", "remaining_time": "0:57:34", "throughput": 6153.26, "total_tokens": 918400} {"current_steps": 1410, "total_steps": 33920, "loss": 0.4976, "lr": 4.153891509433963e-06, "epoch": 0.8313679245283019, "percentage": 4.16, "elapsed_time": "0:02:29", "remaining_time": "0:57:32", "throughput": 6153.49, "total_tokens": 921312} {"current_steps": 1415, "total_steps": 33920, "loss": 0.5315, "lr": 4.168632075471699e-06, "epoch": 0.8343160377358491, "percentage": 4.17, "elapsed_time": "0:02:30", "remaining_time": "0:57:34", "throughput": 6156.79, "total_tokens": 925888} {"current_steps": 1420, "total_steps": 33920, "loss": 0.5742, "lr": 4.183372641509434e-06, "epoch": 0.8372641509433962, "percentage": 4.19, "elapsed_time": "0:02:30", "remaining_time": "0:57:35", "throughput": 6159.01, "total_tokens": 929792} {"current_steps": 1425, "total_steps": 33920, "loss": 0.4752, "lr": 4.19811320754717e-06, "epoch": 0.8402122641509434, "percentage": 4.2, "elapsed_time": "0:02:31", "remaining_time": "0:57:33", "throughput": 6159.11, "total_tokens": 932672} {"current_steps": 1430, "total_steps": 33920, "loss": 0.6862, "lr": 4.212853773584907e-06, "epoch": 0.8431603773584906, "percentage": 4.22, "elapsed_time": "0:02:31", "remaining_time": "0:57:31", "throughput": 6158.86, "total_tokens": 935552} {"current_steps": 1435, "total_steps": 33920, "loss": 0.3899, "lr": 4.227594339622642e-06, "epoch": 0.8461084905660378, "percentage": 4.23, "elapsed_time": "0:02:32", "remaining_time": "0:57:31", "throughput": 6161.15, "total_tokens": 939456} {"current_steps": 1440, "total_steps": 33920, "loss": 0.6798, "lr": 4.242334905660378e-06, "epoch": 0.8490566037735849, "percentage": 4.25, "elapsed_time": "0:02:33", "remaining_time": "0:57:33", "throughput": 6163.25, "total_tokens": 943552} {"current_steps": 1445, "total_steps": 33920, "loss": 0.5412, "lr": 4.2570754716981135e-06, "epoch": 0.8520047169811321, "percentage": 4.26, "elapsed_time": "0:02:33", "remaining_time": "0:57:31", "throughput": 6163.43, "total_tokens": 946464} {"current_steps": 1450, "total_steps": 33920, "loss": 0.5545, "lr": 4.271816037735849e-06, "epoch": 0.8549528301886793, "percentage": 4.27, "elapsed_time": "0:02:34", "remaining_time": "0:57:32", "throughput": 6166.38, "total_tokens": 950816} {"current_steps": 1455, "total_steps": 33920, "loss": 0.6894, "lr": 4.286556603773585e-06, "epoch": 0.8579009433962265, "percentage": 4.29, "elapsed_time": "0:02:34", "remaining_time": "0:57:30", "throughput": 6164.8, "total_tokens": 953216} {"current_steps": 1460, "total_steps": 33920, "loss": 0.5793, "lr": 4.301297169811321e-06, "epoch": 0.8608490566037735, "percentage": 4.3, "elapsed_time": "0:02:35", "remaining_time": "0:57:27", "throughput": 6164.9, "total_tokens": 956064} {"current_steps": 1465, "total_steps": 33920, "loss": 0.7675, "lr": 4.3160377358490565e-06, "epoch": 0.8637971698113207, "percentage": 4.32, "elapsed_time": "0:02:35", "remaining_time": "0:57:26", "throughput": 6165.84, "total_tokens": 959328} {"current_steps": 1470, "total_steps": 33920, "loss": 0.4885, "lr": 4.330778301886793e-06, "epoch": 0.8667452830188679, "percentage": 4.33, "elapsed_time": "0:02:36", "remaining_time": "0:57:25", "throughput": 6166.35, "total_tokens": 962368} {"current_steps": 1475, "total_steps": 33920, "loss": 0.668, "lr": 4.345518867924529e-06, "epoch": 0.8696933962264151, "percentage": 4.35, "elapsed_time": "0:02:36", "remaining_time": "0:57:25", "throughput": 6167.89, "total_tokens": 966080} {"current_steps": 1480, "total_steps": 33920, "loss": 0.5523, "lr": 4.360259433962264e-06, "epoch": 0.8726415094339622, "percentage": 4.36, "elapsed_time": "0:02:37", "remaining_time": "0:57:24", "throughput": 6168.44, "total_tokens": 969344} {"current_steps": 1485, "total_steps": 33920, "loss": 0.6765, "lr": 4.3750000000000005e-06, "epoch": 0.8755896226415094, "percentage": 4.38, "elapsed_time": "0:02:37", "remaining_time": "0:57:24", "throughput": 6170.42, "total_tokens": 973056} {"current_steps": 1490, "total_steps": 33920, "loss": 0.7078, "lr": 4.389740566037737e-06, "epoch": 0.8785377358490566, "percentage": 4.39, "elapsed_time": "0:02:38", "remaining_time": "0:57:22", "throughput": 6170.78, "total_tokens": 975936} {"current_steps": 1495, "total_steps": 33920, "loss": 0.5228, "lr": 4.404481132075472e-06, "epoch": 0.8814858490566038, "percentage": 4.41, "elapsed_time": "0:02:38", "remaining_time": "0:57:22", "throughput": 6172.25, "total_tokens": 979584} {"current_steps": 1500, "total_steps": 33920, "loss": 0.618, "lr": 4.419221698113208e-06, "epoch": 0.8844339622641509, "percentage": 4.42, "elapsed_time": "0:02:39", "remaining_time": "0:57:20", "throughput": 6171.38, "total_tokens": 982528} {"current_steps": 1505, "total_steps": 33920, "loss": 0.549, "lr": 4.4339622641509435e-06, "epoch": 0.8873820754716981, "percentage": 4.44, "elapsed_time": "0:02:39", "remaining_time": "0:57:19", "throughput": 6171.59, "total_tokens": 985504} {"current_steps": 1510, "total_steps": 33920, "loss": 0.6405, "lr": 4.44870283018868e-06, "epoch": 0.8903301886792453, "percentage": 4.45, "elapsed_time": "0:02:40", "remaining_time": "0:57:17", "throughput": 6170.75, "total_tokens": 988224} {"current_steps": 1515, "total_steps": 33920, "loss": 0.5217, "lr": 4.463443396226416e-06, "epoch": 0.8932783018867925, "percentage": 4.47, "elapsed_time": "0:02:40", "remaining_time": "0:57:16", "throughput": 6170.95, "total_tokens": 991424} {"current_steps": 1520, "total_steps": 33920, "loss": 0.4717, "lr": 4.478183962264151e-06, "epoch": 0.8962264150943396, "percentage": 4.48, "elapsed_time": "0:02:41", "remaining_time": "0:57:16", "throughput": 6170.85, "total_tokens": 994784} {"current_steps": 1525, "total_steps": 33920, "loss": 0.636, "lr": 4.4929245283018875e-06, "epoch": 0.8991745283018868, "percentage": 4.5, "elapsed_time": "0:02:41", "remaining_time": "0:57:14", "throughput": 6170.91, "total_tokens": 997600} {"current_steps": 1530, "total_steps": 33920, "loss": 0.4938, "lr": 4.507665094339623e-06, "epoch": 0.902122641509434, "percentage": 4.51, "elapsed_time": "0:02:42", "remaining_time": "0:57:13", "throughput": 6172.15, "total_tokens": 1001024} {"current_steps": 1535, "total_steps": 33920, "loss": 0.6038, "lr": 4.522405660377359e-06, "epoch": 0.9050707547169812, "percentage": 4.53, "elapsed_time": "0:02:42", "remaining_time": "0:57:11", "throughput": 6172.25, "total_tokens": 1003968} {"current_steps": 1540, "total_steps": 33920, "loss": 0.7326, "lr": 4.537146226415094e-06, "epoch": 0.9080188679245284, "percentage": 4.54, "elapsed_time": "0:02:43", "remaining_time": "0:57:22", "throughput": 6175.8, "total_tokens": 1011200} {"current_steps": 1545, "total_steps": 33920, "loss": 0.4789, "lr": 4.5518867924528305e-06, "epoch": 0.9109669811320755, "percentage": 4.55, "elapsed_time": "0:02:44", "remaining_time": "0:57:32", "throughput": 6179.4, "total_tokens": 1018080} {"current_steps": 1550, "total_steps": 33920, "loss": 0.5367, "lr": 4.566627358490566e-06, "epoch": 0.9139150943396226, "percentage": 4.57, "elapsed_time": "0:02:45", "remaining_time": "0:57:30", "throughput": 6178.34, "total_tokens": 1020832} {"current_steps": 1555, "total_steps": 33920, "loss": 0.6011, "lr": 4.581367924528302e-06, "epoch": 0.9168632075471698, "percentage": 4.58, "elapsed_time": "0:02:45", "remaining_time": "0:57:29", "throughput": 6177.38, "total_tokens": 1023744} {"current_steps": 1560, "total_steps": 33920, "loss": 0.5486, "lr": 4.596108490566038e-06, "epoch": 0.9198113207547169, "percentage": 4.6, "elapsed_time": "0:02:46", "remaining_time": "0:57:30", "throughput": 6180.83, "total_tokens": 1028096} {"current_steps": 1565, "total_steps": 33920, "loss": 0.672, "lr": 4.610849056603774e-06, "epoch": 0.9227594339622641, "percentage": 4.61, "elapsed_time": "0:02:46", "remaining_time": "0:57:30", "throughput": 6181.99, "total_tokens": 1031712} {"current_steps": 1570, "total_steps": 33920, "loss": 0.5141, "lr": 4.62558962264151e-06, "epoch": 0.9257075471698113, "percentage": 4.63, "elapsed_time": "0:02:47", "remaining_time": "0:57:31", "throughput": 6182.89, "total_tokens": 1035744} {"current_steps": 1575, "total_steps": 33920, "loss": 0.5329, "lr": 4.640330188679246e-06, "epoch": 0.9286556603773585, "percentage": 4.64, "elapsed_time": "0:02:48", "remaining_time": "0:57:32", "throughput": 6184.82, "total_tokens": 1039616} {"current_steps": 1580, "total_steps": 33920, "loss": 0.6611, "lr": 4.655070754716981e-06, "epoch": 0.9316037735849056, "percentage": 4.66, "elapsed_time": "0:02:48", "remaining_time": "0:57:30", "throughput": 6184.34, "total_tokens": 1042496} {"current_steps": 1585, "total_steps": 33920, "loss": 0.6145, "lr": 4.6698113207547175e-06, "epoch": 0.9345518867924528, "percentage": 4.67, "elapsed_time": "0:02:49", "remaining_time": "0:57:28", "throughput": 6185.04, "total_tokens": 1045568} {"current_steps": 1590, "total_steps": 33920, "loss": 0.5037, "lr": 4.684551886792454e-06, "epoch": 0.9375, "percentage": 4.69, "elapsed_time": "0:02:49", "remaining_time": "0:57:27", "throughput": 6184.39, "total_tokens": 1048480} {"current_steps": 1595, "total_steps": 33920, "loss": 0.6527, "lr": 4.699292452830189e-06, "epoch": 0.9404481132075472, "percentage": 4.7, "elapsed_time": "0:02:49", "remaining_time": "0:57:24", "throughput": 6181.91, "total_tokens": 1050624} {"current_steps": 1600, "total_steps": 33920, "loss": 0.7619, "lr": 4.714033018867925e-06, "epoch": 0.9433962264150944, "percentage": 4.72, "elapsed_time": "0:02:50", "remaining_time": "0:57:24", "throughput": 6184.6, "total_tokens": 1054624} {"current_steps": 1605, "total_steps": 33920, "loss": 0.5878, "lr": 4.728773584905661e-06, "epoch": 0.9463443396226415, "percentage": 4.73, "elapsed_time": "0:02:51", "remaining_time": "0:57:23", "throughput": 6185.52, "total_tokens": 1057888} {"current_steps": 1610, "total_steps": 33920, "loss": 0.5211, "lr": 4.743514150943397e-06, "epoch": 0.9492924528301887, "percentage": 4.75, "elapsed_time": "0:02:51", "remaining_time": "0:57:21", "throughput": 6185.76, "total_tokens": 1060832} {"current_steps": 1615, "total_steps": 33920, "loss": 0.7955, "lr": 4.758254716981133e-06, "epoch": 0.9522405660377359, "percentage": 4.76, "elapsed_time": "0:02:52", "remaining_time": "0:57:23", "throughput": 6187.73, "total_tokens": 1065088} {"current_steps": 1620, "total_steps": 33920, "loss": 0.68, "lr": 4.772995283018868e-06, "epoch": 0.9551886792452831, "percentage": 4.78, "elapsed_time": "0:02:52", "remaining_time": "0:57:23", "throughput": 6188.73, "total_tokens": 1068864} {"current_steps": 1625, "total_steps": 33920, "loss": 0.6414, "lr": 4.787735849056604e-06, "epoch": 0.9581367924528302, "percentage": 4.79, "elapsed_time": "0:02:53", "remaining_time": "0:57:21", "throughput": 6188.22, "total_tokens": 1071616} {"current_steps": 1630, "total_steps": 33920, "loss": 0.6036, "lr": 4.80247641509434e-06, "epoch": 0.9610849056603774, "percentage": 4.81, "elapsed_time": "0:02:53", "remaining_time": "0:57:20", "throughput": 6187.85, "total_tokens": 1074560} {"current_steps": 1635, "total_steps": 33920, "loss": 0.4249, "lr": 4.817216981132076e-06, "epoch": 0.9640330188679245, "percentage": 4.82, "elapsed_time": "0:02:54", "remaining_time": "0:57:23", "throughput": 6190.68, "total_tokens": 1079648} {"current_steps": 1640, "total_steps": 33920, "loss": 0.5219, "lr": 4.831957547169811e-06, "epoch": 0.9669811320754716, "percentage": 4.83, "elapsed_time": "0:02:54", "remaining_time": "0:57:23", "throughput": 6192.78, "total_tokens": 1083520} {"current_steps": 1645, "total_steps": 33920, "loss": 0.4732, "lr": 4.8466981132075476e-06, "epoch": 0.9699292452830188, "percentage": 4.85, "elapsed_time": "0:02:55", "remaining_time": "0:57:23", "throughput": 6193.99, "total_tokens": 1086944} {"current_steps": 1650, "total_steps": 33920, "loss": 0.4876, "lr": 4.861438679245283e-06, "epoch": 0.972877358490566, "percentage": 4.86, "elapsed_time": "0:02:55", "remaining_time": "0:57:21", "throughput": 6194.58, "total_tokens": 1090112} {"current_steps": 1655, "total_steps": 33920, "loss": 0.6371, "lr": 4.876179245283019e-06, "epoch": 0.9758254716981132, "percentage": 4.88, "elapsed_time": "0:02:56", "remaining_time": "0:57:20", "throughput": 6194.98, "total_tokens": 1093152} {"current_steps": 1660, "total_steps": 33920, "loss": 0.7638, "lr": 4.890919811320755e-06, "epoch": 0.9787735849056604, "percentage": 4.89, "elapsed_time": "0:02:56", "remaining_time": "0:57:18", "throughput": 6193.76, "total_tokens": 1095904} {"current_steps": 1665, "total_steps": 33920, "loss": 0.598, "lr": 4.905660377358491e-06, "epoch": 0.9817216981132075, "percentage": 4.91, "elapsed_time": "0:02:57", "remaining_time": "0:57:18", "throughput": 6194.15, "total_tokens": 1099488} {"current_steps": 1670, "total_steps": 33920, "loss": 0.4763, "lr": 4.920400943396227e-06, "epoch": 0.9846698113207547, "percentage": 4.92, "elapsed_time": "0:02:57", "remaining_time": "0:57:16", "throughput": 6192.88, "total_tokens": 1102112} {"current_steps": 1675, "total_steps": 33920, "loss": 0.6022, "lr": 4.935141509433963e-06, "epoch": 0.9876179245283019, "percentage": 4.94, "elapsed_time": "0:02:58", "remaining_time": "0:57:19", "throughput": 6196.02, "total_tokens": 1107136} {"current_steps": 1680, "total_steps": 33920, "loss": 0.6062, "lr": 4.949882075471698e-06, "epoch": 0.9905660377358491, "percentage": 4.95, "elapsed_time": "0:02:59", "remaining_time": "0:57:17", "throughput": 6195.24, "total_tokens": 1109856} {"current_steps": 1685, "total_steps": 33920, "loss": 0.6143, "lr": 4.9646226415094346e-06, "epoch": 0.9935141509433962, "percentage": 4.97, "elapsed_time": "0:02:59", "remaining_time": "0:57:16", "throughput": 6194.82, "total_tokens": 1112704} {"current_steps": 1690, "total_steps": 33920, "loss": 0.6408, "lr": 4.979363207547171e-06, "epoch": 0.9964622641509434, "percentage": 4.98, "elapsed_time": "0:03:00", "remaining_time": "0:57:14", "throughput": 6195.63, "total_tokens": 1115872} {"current_steps": 1695, "total_steps": 33920, "loss": 0.5649, "lr": 4.994103773584906e-06, "epoch": 0.9994103773584906, "percentage": 5.0, "elapsed_time": "0:03:00", "remaining_time": "0:57:14", "throughput": 6195.67, "total_tokens": 1119136} {"current_steps": 1700, "total_steps": 33920, "loss": 0.5179, "lr": 5.0088443396226414e-06, "epoch": 1.0023584905660377, "percentage": 5.01, "elapsed_time": "0:03:01", "remaining_time": "0:57:19", "throughput": 6185.71, "total_tokens": 1122416} {"current_steps": 1705, "total_steps": 33920, "loss": 0.3608, "lr": 5.023584905660378e-06, "epoch": 1.005306603773585, "percentage": 5.03, "elapsed_time": "0:03:01", "remaining_time": "0:57:18", "throughput": 6186.09, "total_tokens": 1125744} {"current_steps": 1710, "total_steps": 33920, "loss": 0.5221, "lr": 5.038325471698113e-06, "epoch": 1.008254716981132, "percentage": 5.04, "elapsed_time": "0:03:02", "remaining_time": "0:57:16", "throughput": 6186.25, "total_tokens": 1128624} {"current_steps": 1715, "total_steps": 33920, "loss": 0.5201, "lr": 5.05306603773585e-06, "epoch": 1.0112028301886793, "percentage": 5.06, "elapsed_time": "0:03:02", "remaining_time": "0:57:15", "throughput": 6187.26, "total_tokens": 1132048} {"current_steps": 1720, "total_steps": 33920, "loss": 0.4196, "lr": 5.067806603773585e-06, "epoch": 1.0141509433962264, "percentage": 5.07, "elapsed_time": "0:03:03", "remaining_time": "0:57:15", "throughput": 6186.56, "total_tokens": 1135248} {"current_steps": 1725, "total_steps": 33920, "loss": 0.5721, "lr": 5.0825471698113216e-06, "epoch": 1.0170990566037736, "percentage": 5.09, "elapsed_time": "0:03:03", "remaining_time": "0:57:13", "throughput": 6186.04, "total_tokens": 1138000} {"current_steps": 1730, "total_steps": 33920, "loss": 0.6633, "lr": 5.097287735849057e-06, "epoch": 1.0200471698113207, "percentage": 5.1, "elapsed_time": "0:03:04", "remaining_time": "0:57:11", "throughput": 6184.71, "total_tokens": 1140752} {"current_steps": 1735, "total_steps": 33920, "loss": 0.5353, "lr": 5.112028301886793e-06, "epoch": 1.022995283018868, "percentage": 5.11, "elapsed_time": "0:03:04", "remaining_time": "0:57:10", "throughput": 6180.48, "total_tokens": 1142832} {"current_steps": 1740, "total_steps": 33920, "loss": 0.6396, "lr": 5.1267688679245284e-06, "epoch": 1.025943396226415, "percentage": 5.13, "elapsed_time": "0:03:05", "remaining_time": "0:57:10", "throughput": 6181.4, "total_tokens": 1146704} {"current_steps": 1745, "total_steps": 33920, "loss": 0.5119, "lr": 5.1415094339622655e-06, "epoch": 1.0288915094339623, "percentage": 5.14, "elapsed_time": "0:03:06", "remaining_time": "0:57:12", "throughput": 6181.96, "total_tokens": 1150704} {"current_steps": 1750, "total_steps": 33920, "loss": 0.5417, "lr": 5.156250000000001e-06, "epoch": 1.0318396226415094, "percentage": 5.16, "elapsed_time": "0:03:06", "remaining_time": "0:57:10", "throughput": 6180.89, "total_tokens": 1153520} {"current_steps": 1755, "total_steps": 33920, "loss": 0.5309, "lr": 5.170990566037736e-06, "epoch": 1.0347877358490567, "percentage": 5.17, "elapsed_time": "0:03:07", "remaining_time": "0:57:09", "throughput": 6180.41, "total_tokens": 1156656} {"current_steps": 1760, "total_steps": 33920, "loss": 0.6719, "lr": 5.185731132075472e-06, "epoch": 1.0377358490566038, "percentage": 5.19, "elapsed_time": "0:03:07", "remaining_time": "0:57:10", "throughput": 6179.26, "total_tokens": 1160112} {"current_steps": 1765, "total_steps": 33920, "loss": 0.6865, "lr": 5.200471698113208e-06, "epoch": 1.040683962264151, "percentage": 5.2, "elapsed_time": "0:03:08", "remaining_time": "0:57:11", "throughput": 6181.11, "total_tokens": 1164336} {"current_steps": 1770, "total_steps": 33920, "loss": 0.5965, "lr": 5.215212264150944e-06, "epoch": 1.0436320754716981, "percentage": 5.22, "elapsed_time": "0:03:08", "remaining_time": "0:57:11", "throughput": 6182.53, "total_tokens": 1168144} {"current_steps": 1775, "total_steps": 33920, "loss": 0.6306, "lr": 5.229952830188679e-06, "epoch": 1.0465801886792452, "percentage": 5.23, "elapsed_time": "0:03:09", "remaining_time": "0:57:13", "throughput": 6184.3, "total_tokens": 1172496} {"current_steps": 1780, "total_steps": 33920, "loss": 0.6169, "lr": 5.2446933962264154e-06, "epoch": 1.0495283018867925, "percentage": 5.25, "elapsed_time": "0:03:10", "remaining_time": "0:57:13", "throughput": 6185.06, "total_tokens": 1176048} {"current_steps": 1785, "total_steps": 33920, "loss": 0.5546, "lr": 5.259433962264151e-06, "epoch": 1.0524764150943395, "percentage": 5.26, "elapsed_time": "0:03:10", "remaining_time": "0:57:12", "throughput": 6183.78, "total_tokens": 1178896} {"current_steps": 1790, "total_steps": 33920, "loss": 0.438, "lr": 5.274174528301888e-06, "epoch": 1.0554245283018868, "percentage": 5.28, "elapsed_time": "0:03:11", "remaining_time": "0:57:11", "throughput": 6183.22, "total_tokens": 1182192} {"current_steps": 1795, "total_steps": 33920, "loss": 0.5778, "lr": 5.288915094339623e-06, "epoch": 1.0583726415094339, "percentage": 5.29, "elapsed_time": "0:03:11", "remaining_time": "0:57:10", "throughput": 6182.57, "total_tokens": 1185104} {"current_steps": 1800, "total_steps": 33920, "loss": 0.7052, "lr": 5.303655660377359e-06, "epoch": 1.0613207547169812, "percentage": 5.31, "elapsed_time": "0:03:12", "remaining_time": "0:57:09", "throughput": 6184.03, "total_tokens": 1188592} {"current_steps": 1805, "total_steps": 33920, "loss": 0.5746, "lr": 5.318396226415095e-06, "epoch": 1.0642688679245282, "percentage": 5.32, "elapsed_time": "0:03:12", "remaining_time": "0:57:09", "throughput": 6185.08, "total_tokens": 1192048} {"current_steps": 1810, "total_steps": 33920, "loss": 0.5713, "lr": 5.333136792452831e-06, "epoch": 1.0672169811320755, "percentage": 5.34, "elapsed_time": "0:03:13", "remaining_time": "0:57:09", "throughput": 6186.98, "total_tokens": 1195984} {"current_steps": 1815, "total_steps": 33920, "loss": 0.6564, "lr": 5.347877358490566e-06, "epoch": 1.0701650943396226, "percentage": 5.35, "elapsed_time": "0:03:13", "remaining_time": "0:57:07", "throughput": 6186.58, "total_tokens": 1198800} {"current_steps": 1820, "total_steps": 33920, "loss": 0.5165, "lr": 5.362617924528302e-06, "epoch": 1.0731132075471699, "percentage": 5.37, "elapsed_time": "0:03:14", "remaining_time": "0:57:07", "throughput": 6187.91, "total_tokens": 1202480} {"current_steps": 1825, "total_steps": 33920, "loss": 0.5944, "lr": 5.377358490566038e-06, "epoch": 1.076061320754717, "percentage": 5.38, "elapsed_time": "0:03:14", "remaining_time": "0:57:07", "throughput": 6188.46, "total_tokens": 1206000} {"current_steps": 1830, "total_steps": 33920, "loss": 0.6458, "lr": 5.392099056603775e-06, "epoch": 1.0790094339622642, "percentage": 5.4, "elapsed_time": "0:03:15", "remaining_time": "0:57:05", "throughput": 6187.57, "total_tokens": 1208848} {"current_steps": 1835, "total_steps": 33920, "loss": 0.4807, "lr": 5.40683962264151e-06, "epoch": 1.0819575471698113, "percentage": 5.41, "elapsed_time": "0:03:15", "remaining_time": "0:57:04", "throughput": 6187.5, "total_tokens": 1211856} {"current_steps": 1840, "total_steps": 33920, "loss": 0.5681, "lr": 5.4215801886792455e-06, "epoch": 1.0849056603773586, "percentage": 5.42, "elapsed_time": "0:03:16", "remaining_time": "0:57:02", "throughput": 6186.85, "total_tokens": 1214576} {"current_steps": 1845, "total_steps": 33920, "loss": 0.6066, "lr": 5.436320754716982e-06, "epoch": 1.0878537735849056, "percentage": 5.44, "elapsed_time": "0:03:16", "remaining_time": "0:57:02", "throughput": 6187.23, "total_tokens": 1218096} {"current_steps": 1850, "total_steps": 33920, "loss": 0.5001, "lr": 5.451061320754717e-06, "epoch": 1.0908018867924527, "percentage": 5.45, "elapsed_time": "0:03:17", "remaining_time": "0:57:01", "throughput": 6187.06, "total_tokens": 1221232} {"current_steps": 1855, "total_steps": 33920, "loss": 0.577, "lr": 5.465801886792453e-06, "epoch": 1.09375, "percentage": 5.47, "elapsed_time": "0:03:17", "remaining_time": "0:57:01", "throughput": 6185.07, "total_tokens": 1224112} {"current_steps": 1860, "total_steps": 33920, "loss": 0.5246, "lr": 5.4805424528301886e-06, "epoch": 1.0966981132075473, "percentage": 5.48, "elapsed_time": "0:03:18", "remaining_time": "0:56:59", "throughput": 6184.08, "total_tokens": 1226768} {"current_steps": 1865, "total_steps": 33920, "loss": 0.5428, "lr": 5.495283018867925e-06, "epoch": 1.0996462264150944, "percentage": 5.5, "elapsed_time": "0:03:18", "remaining_time": "0:56:57", "throughput": 6183.58, "total_tokens": 1229488} {"current_steps": 1870, "total_steps": 33920, "loss": 0.6491, "lr": 5.51002358490566e-06, "epoch": 1.1025943396226414, "percentage": 5.51, "elapsed_time": "0:03:19", "remaining_time": "0:56:57", "throughput": 6185.07, "total_tokens": 1233296} {"current_steps": 1875, "total_steps": 33920, "loss": 0.4462, "lr": 5.524764150943397e-06, "epoch": 1.1055424528301887, "percentage": 5.53, "elapsed_time": "0:03:19", "remaining_time": "0:56:56", "throughput": 6184.67, "total_tokens": 1236176} {"current_steps": 1880, "total_steps": 33920, "loss": 0.5167, "lr": 5.5395047169811325e-06, "epoch": 1.1084905660377358, "percentage": 5.54, "elapsed_time": "0:03:20", "remaining_time": "0:56:55", "throughput": 6184.43, "total_tokens": 1239472} {"current_steps": 1885, "total_steps": 33920, "loss": 0.711, "lr": 5.554245283018869e-06, "epoch": 1.111438679245283, "percentage": 5.56, "elapsed_time": "0:03:20", "remaining_time": "0:56:54", "throughput": 6182.85, "total_tokens": 1242352} {"current_steps": 1890, "total_steps": 33920, "loss": 0.6871, "lr": 5.568985849056604e-06, "epoch": 1.1143867924528301, "percentage": 5.57, "elapsed_time": "0:03:21", "remaining_time": "0:56:53", "throughput": 6183.01, "total_tokens": 1245456} {"current_steps": 1895, "total_steps": 33920, "loss": 0.6044, "lr": 5.58372641509434e-06, "epoch": 1.1173349056603774, "percentage": 5.59, "elapsed_time": "0:03:21", "remaining_time": "0:56:52", "throughput": 6182.61, "total_tokens": 1248432} {"current_steps": 1900, "total_steps": 33920, "loss": 0.502, "lr": 5.5984669811320755e-06, "epoch": 1.1202830188679245, "percentage": 5.6, "elapsed_time": "0:03:22", "remaining_time": "0:56:52", "throughput": 6183.93, "total_tokens": 1252176} {"current_steps": 1905, "total_steps": 33920, "loss": 0.4568, "lr": 5.613207547169813e-06, "epoch": 1.1232311320754718, "percentage": 5.62, "elapsed_time": "0:03:23", "remaining_time": "0:56:51", "throughput": 6183.58, "total_tokens": 1255312} {"current_steps": 1910, "total_steps": 33920, "loss": 0.5332, "lr": 5.627948113207548e-06, "epoch": 1.1261792452830188, "percentage": 5.63, "elapsed_time": "0:03:23", "remaining_time": "0:56:51", "throughput": 6183.71, "total_tokens": 1258736} {"current_steps": 1915, "total_steps": 33920, "loss": 0.6241, "lr": 5.642688679245284e-06, "epoch": 1.1291273584905661, "percentage": 5.65, "elapsed_time": "0:03:24", "remaining_time": "0:56:51", "throughput": 6184.07, "total_tokens": 1262224} {"current_steps": 1920, "total_steps": 33920, "loss": 0.6054, "lr": 5.6574292452830195e-06, "epoch": 1.1320754716981132, "percentage": 5.66, "elapsed_time": "0:03:24", "remaining_time": "0:56:50", "throughput": 6183.27, "total_tokens": 1265264} {"current_steps": 1925, "total_steps": 33920, "loss": 0.7396, "lr": 5.672169811320756e-06, "epoch": 1.1350235849056605, "percentage": 5.68, "elapsed_time": "0:03:25", "remaining_time": "0:56:49", "throughput": 6179.82, "total_tokens": 1267696} {"current_steps": 1930, "total_steps": 33920, "loss": 0.4089, "lr": 5.686910377358491e-06, "epoch": 1.1379716981132075, "percentage": 5.69, "elapsed_time": "0:03:25", "remaining_time": "0:56:49", "throughput": 6181.17, "total_tokens": 1271536} {"current_steps": 1935, "total_steps": 33920, "loss": 0.5402, "lr": 5.701650943396226e-06, "epoch": 1.1409198113207548, "percentage": 5.7, "elapsed_time": "0:03:26", "remaining_time": "0:56:48", "throughput": 6180.78, "total_tokens": 1274480} {"current_steps": 1940, "total_steps": 33920, "loss": 0.5844, "lr": 5.7163915094339625e-06, "epoch": 1.1438679245283019, "percentage": 5.72, "elapsed_time": "0:03:26", "remaining_time": "0:56:47", "throughput": 6181.0, "total_tokens": 1277552} {"current_steps": 1945, "total_steps": 33920, "loss": 0.6108, "lr": 5.731132075471698e-06, "epoch": 1.146816037735849, "percentage": 5.73, "elapsed_time": "0:03:27", "remaining_time": "0:56:47", "throughput": 6182.33, "total_tokens": 1281328} {"current_steps": 1950, "total_steps": 33920, "loss": 0.4906, "lr": 5.745872641509435e-06, "epoch": 1.1497641509433962, "percentage": 5.75, "elapsed_time": "0:03:27", "remaining_time": "0:56:45", "throughput": 6181.26, "total_tokens": 1284016} {"current_steps": 1955, "total_steps": 33920, "loss": 0.4547, "lr": 5.76061320754717e-06, "epoch": 1.1527122641509433, "percentage": 5.76, "elapsed_time": "0:03:28", "remaining_time": "0:56:45", "throughput": 6180.84, "total_tokens": 1287184} {"current_steps": 1960, "total_steps": 33920, "loss": 0.4502, "lr": 5.7753537735849065e-06, "epoch": 1.1556603773584906, "percentage": 5.78, "elapsed_time": "0:03:28", "remaining_time": "0:56:43", "throughput": 6180.16, "total_tokens": 1290128} {"current_steps": 1965, "total_steps": 33920, "loss": 0.4668, "lr": 5.790094339622642e-06, "epoch": 1.1586084905660377, "percentage": 5.79, "elapsed_time": "0:03:29", "remaining_time": "0:56:42", "throughput": 6179.35, "total_tokens": 1292944} {"current_steps": 1970, "total_steps": 33920, "loss": 0.5097, "lr": 5.804834905660378e-06, "epoch": 1.161556603773585, "percentage": 5.81, "elapsed_time": "0:03:29", "remaining_time": "0:56:40", "throughput": 6177.15, "total_tokens": 1295312} {"current_steps": 1975, "total_steps": 33920, "loss": 0.5953, "lr": 5.819575471698113e-06, "epoch": 1.164504716981132, "percentage": 5.82, "elapsed_time": "0:03:30", "remaining_time": "0:56:40", "throughput": 6178.11, "total_tokens": 1298704} {"current_steps": 1980, "total_steps": 33920, "loss": 0.5009, "lr": 5.8343160377358495e-06, "epoch": 1.1674528301886793, "percentage": 5.84, "elapsed_time": "0:03:30", "remaining_time": "0:56:39", "throughput": 6177.92, "total_tokens": 1301808} {"current_steps": 1985, "total_steps": 33920, "loss": 0.6036, "lr": 5.849056603773585e-06, "epoch": 1.1704009433962264, "percentage": 5.85, "elapsed_time": "0:03:31", "remaining_time": "0:56:37", "throughput": 6177.49, "total_tokens": 1304560} {"current_steps": 1990, "total_steps": 33920, "loss": 0.5975, "lr": 5.863797169811322e-06, "epoch": 1.1733490566037736, "percentage": 5.87, "elapsed_time": "0:03:31", "remaining_time": "0:56:36", "throughput": 6177.43, "total_tokens": 1307632} {"current_steps": 1995, "total_steps": 33920, "loss": 0.5743, "lr": 5.878537735849057e-06, "epoch": 1.1762971698113207, "percentage": 5.88, "elapsed_time": "0:03:32", "remaining_time": "0:56:35", "throughput": 6176.8, "total_tokens": 1310576} {"current_steps": 2000, "total_steps": 33920, "loss": 0.5316, "lr": 5.8932783018867934e-06, "epoch": 1.179245283018868, "percentage": 5.9, "elapsed_time": "0:03:32", "remaining_time": "0:56:35", "throughput": 6178.65, "total_tokens": 1314544} {"current_steps": 2005, "total_steps": 33920, "loss": 0.706, "lr": 5.908018867924529e-06, "epoch": 1.182193396226415, "percentage": 5.91, "elapsed_time": "0:03:33", "remaining_time": "0:56:33", "throughput": 6176.93, "total_tokens": 1316912} {"current_steps": 2010, "total_steps": 33920, "loss": 0.4615, "lr": 5.922759433962265e-06, "epoch": 1.1851415094339623, "percentage": 5.93, "elapsed_time": "0:03:33", "remaining_time": "0:56:32", "throughput": 6176.56, "total_tokens": 1319952} {"current_steps": 2015, "total_steps": 33920, "loss": 0.5915, "lr": 5.9375e-06, "epoch": 1.1880896226415094, "percentage": 5.94, "elapsed_time": "0:03:34", "remaining_time": "0:56:31", "throughput": 6176.73, "total_tokens": 1322992} {"current_steps": 2020, "total_steps": 33920, "loss": 0.5422, "lr": 5.952240566037736e-06, "epoch": 1.1910377358490567, "percentage": 5.96, "elapsed_time": "0:03:34", "remaining_time": "0:56:30", "throughput": 6176.17, "total_tokens": 1325936} {"current_steps": 2025, "total_steps": 33920, "loss": 0.4733, "lr": 5.966981132075472e-06, "epoch": 1.1939858490566038, "percentage": 5.97, "elapsed_time": "0:03:35", "remaining_time": "0:56:30", "throughput": 6177.35, "total_tokens": 1329872} {"current_steps": 2030, "total_steps": 33920, "loss": 0.5504, "lr": 5.981721698113207e-06, "epoch": 1.196933962264151, "percentage": 5.98, "elapsed_time": "0:03:36", "remaining_time": "0:56:33", "throughput": 6180.16, "total_tokens": 1334928} {"current_steps": 2035, "total_steps": 33920, "loss": 0.4764, "lr": 5.996462264150944e-06, "epoch": 1.1998820754716981, "percentage": 6.0, "elapsed_time": "0:03:36", "remaining_time": "0:56:31", "throughput": 6179.44, "total_tokens": 1337648} {"current_steps": 2040, "total_steps": 33920, "loss": 0.7481, "lr": 6.01120283018868e-06, "epoch": 1.2028301886792452, "percentage": 6.01, "elapsed_time": "0:03:36", "remaining_time": "0:56:30", "throughput": 6178.7, "total_tokens": 1340592} {"current_steps": 2045, "total_steps": 33920, "loss": 0.5213, "lr": 6.025943396226416e-06, "epoch": 1.2057783018867925, "percentage": 6.03, "elapsed_time": "0:03:37", "remaining_time": "0:56:31", "throughput": 6180.51, "total_tokens": 1344752} {"current_steps": 2050, "total_steps": 33920, "loss": 0.572, "lr": 6.040683962264151e-06, "epoch": 1.2087264150943395, "percentage": 6.04, "elapsed_time": "0:03:38", "remaining_time": "0:56:30", "throughput": 6180.76, "total_tokens": 1347952} {"current_steps": 2055, "total_steps": 33920, "loss": 0.5808, "lr": 6.055424528301887e-06, "epoch": 1.2116745283018868, "percentage": 6.06, "elapsed_time": "0:03:38", "remaining_time": "0:56:28", "throughput": 6178.93, "total_tokens": 1350416} {"current_steps": 2060, "total_steps": 33920, "loss": 0.6433, "lr": 6.070165094339623e-06, "epoch": 1.2146226415094339, "percentage": 6.07, "elapsed_time": "0:03:39", "remaining_time": "0:56:28", "throughput": 6180.09, "total_tokens": 1354160} {"current_steps": 2065, "total_steps": 33920, "loss": 0.5157, "lr": 6.08490566037736e-06, "epoch": 1.2175707547169812, "percentage": 6.09, "elapsed_time": "0:03:39", "remaining_time": "0:56:27", "throughput": 6179.38, "total_tokens": 1357104} {"current_steps": 2070, "total_steps": 33920, "loss": 0.7669, "lr": 6.099646226415095e-06, "epoch": 1.2205188679245282, "percentage": 6.1, "elapsed_time": "0:03:40", "remaining_time": "0:56:26", "throughput": 6179.35, "total_tokens": 1360048} {"current_steps": 2075, "total_steps": 33920, "loss": 0.4846, "lr": 6.114386792452831e-06, "epoch": 1.2234669811320755, "percentage": 6.12, "elapsed_time": "0:03:40", "remaining_time": "0:56:25", "throughput": 6178.09, "total_tokens": 1362960} {"current_steps": 2080, "total_steps": 33920, "loss": 0.7337, "lr": 6.129127358490567e-06, "epoch": 1.2264150943396226, "percentage": 6.13, "elapsed_time": "0:03:41", "remaining_time": "0:56:25", "throughput": 6178.94, "total_tokens": 1366736} {"current_steps": 2085, "total_steps": 33920, "loss": 0.4757, "lr": 6.143867924528303e-06, "epoch": 1.2293632075471699, "percentage": 6.15, "elapsed_time": "0:03:41", "remaining_time": "0:56:24", "throughput": 6178.59, "total_tokens": 1369552} {"current_steps": 2090, "total_steps": 33920, "loss": 0.5077, "lr": 6.158608490566038e-06, "epoch": 1.232311320754717, "percentage": 6.16, "elapsed_time": "0:03:42", "remaining_time": "0:56:23", "throughput": 6179.29, "total_tokens": 1373008} {"current_steps": 2095, "total_steps": 33920, "loss": 0.5869, "lr": 6.173349056603774e-06, "epoch": 1.2352594339622642, "percentage": 6.18, "elapsed_time": "0:03:42", "remaining_time": "0:56:23", "throughput": 6179.15, "total_tokens": 1376208} {"current_steps": 2100, "total_steps": 33920, "loss": 0.6187, "lr": 6.18808962264151e-06, "epoch": 1.2382075471698113, "percentage": 6.19, "elapsed_time": "0:03:43", "remaining_time": "0:56:22", "throughput": 6178.21, "total_tokens": 1379248} {"current_steps": 2105, "total_steps": 33920, "loss": 0.4919, "lr": 6.202830188679245e-06, "epoch": 1.2411556603773586, "percentage": 6.21, "elapsed_time": "0:03:43", "remaining_time": "0:56:21", "throughput": 6178.21, "total_tokens": 1382192} {"current_steps": 2110, "total_steps": 33920, "loss": 0.4038, "lr": 6.217570754716982e-06, "epoch": 1.2441037735849056, "percentage": 6.22, "elapsed_time": "0:03:44", "remaining_time": "0:56:21", "throughput": 6177.88, "total_tokens": 1385552} {"current_steps": 2115, "total_steps": 33920, "loss": 0.4879, "lr": 6.232311320754717e-06, "epoch": 1.2470518867924527, "percentage": 6.24, "elapsed_time": "0:03:44", "remaining_time": "0:56:20", "throughput": 6178.95, "total_tokens": 1389072} {"current_steps": 2120, "total_steps": 33920, "loss": 0.5443, "lr": 6.2470518867924536e-06, "epoch": 1.25, "percentage": 6.25, "elapsed_time": "0:03:45", "remaining_time": "0:56:20", "throughput": 6179.08, "total_tokens": 1392624} {"current_steps": 2125, "total_steps": 33920, "loss": 0.6732, "lr": 6.261792452830189e-06, "epoch": 1.2529481132075473, "percentage": 6.26, "elapsed_time": "0:03:46", "remaining_time": "0:56:21", "throughput": 6180.88, "total_tokens": 1396880} {"current_steps": 2130, "total_steps": 33920, "loss": 0.5951, "lr": 6.276533018867925e-06, "epoch": 1.2558962264150944, "percentage": 6.28, "elapsed_time": "0:03:46", "remaining_time": "0:56:20", "throughput": 6180.08, "total_tokens": 1399760} {"current_steps": 2135, "total_steps": 33920, "loss": 0.4292, "lr": 6.2912735849056604e-06, "epoch": 1.2588443396226414, "percentage": 6.29, "elapsed_time": "0:03:47", "remaining_time": "0:56:21", "throughput": 6181.4, "total_tokens": 1404112} {"current_steps": 2140, "total_steps": 33920, "loss": 0.6067, "lr": 6.306014150943397e-06, "epoch": 1.2617924528301887, "percentage": 6.31, "elapsed_time": "0:03:47", "remaining_time": "0:56:20", "throughput": 6181.88, "total_tokens": 1407344} {"current_steps": 2145, "total_steps": 33920, "loss": 0.4583, "lr": 6.320754716981132e-06, "epoch": 1.2647405660377358, "percentage": 6.32, "elapsed_time": "0:03:48", "remaining_time": "0:56:19", "throughput": 6180.38, "total_tokens": 1409808} {"current_steps": 2150, "total_steps": 33920, "loss": 0.4801, "lr": 6.335495283018869e-06, "epoch": 1.267688679245283, "percentage": 6.34, "elapsed_time": "0:03:48", "remaining_time": "0:56:19", "throughput": 6181.78, "total_tokens": 1413744} {"current_steps": 2155, "total_steps": 33920, "loss": 0.6338, "lr": 6.350235849056604e-06, "epoch": 1.2706367924528301, "percentage": 6.35, "elapsed_time": "0:03:49", "remaining_time": "0:56:17", "throughput": 6181.23, "total_tokens": 1416464} {"current_steps": 2160, "total_steps": 33920, "loss": 0.5422, "lr": 6.3649764150943406e-06, "epoch": 1.2735849056603774, "percentage": 6.37, "elapsed_time": "0:03:49", "remaining_time": "0:56:16", "throughput": 6181.19, "total_tokens": 1419600} {"current_steps": 2165, "total_steps": 33920, "loss": 0.4637, "lr": 6.379716981132076e-06, "epoch": 1.2765330188679245, "percentage": 6.38, "elapsed_time": "0:03:50", "remaining_time": "0:56:16", "throughput": 6181.0, "total_tokens": 1422704} {"current_steps": 2170, "total_steps": 33920, "loss": 0.6099, "lr": 6.394457547169812e-06, "epoch": 1.2794811320754718, "percentage": 6.4, "elapsed_time": "0:03:50", "remaining_time": "0:56:14", "throughput": 6179.73, "total_tokens": 1425328} {"current_steps": 2175, "total_steps": 33920, "loss": 0.3928, "lr": 6.4091981132075474e-06, "epoch": 1.2824292452830188, "percentage": 6.41, "elapsed_time": "0:03:51", "remaining_time": "0:56:14", "throughput": 6180.25, "total_tokens": 1428752} {"current_steps": 2180, "total_steps": 33920, "loss": 0.5865, "lr": 6.423938679245284e-06, "epoch": 1.2853773584905661, "percentage": 6.43, "elapsed_time": "0:03:51", "remaining_time": "0:56:12", "throughput": 6180.35, "total_tokens": 1431728} {"current_steps": 2185, "total_steps": 33920, "loss": 0.5842, "lr": 6.438679245283019e-06, "epoch": 1.2883254716981132, "percentage": 6.44, "elapsed_time": "0:03:52", "remaining_time": "0:56:11", "throughput": 6180.61, "total_tokens": 1434864} {"current_steps": 2190, "total_steps": 33920, "loss": 0.5603, "lr": 6.453419811320756e-06, "epoch": 1.2912735849056602, "percentage": 6.46, "elapsed_time": "0:03:52", "remaining_time": "0:56:10", "throughput": 6179.46, "total_tokens": 1437456} {"current_steps": 2195, "total_steps": 33920, "loss": 0.5184, "lr": 6.468160377358491e-06, "epoch": 1.2942216981132075, "percentage": 6.47, "elapsed_time": "0:03:53", "remaining_time": "0:56:09", "throughput": 6180.43, "total_tokens": 1440848} {"current_steps": 2200, "total_steps": 33920, "loss": 0.5226, "lr": 6.482900943396227e-06, "epoch": 1.2971698113207548, "percentage": 6.49, "elapsed_time": "0:03:53", "remaining_time": "0:56:08", "throughput": 6179.5, "total_tokens": 1443536} {"current_steps": 2205, "total_steps": 33920, "loss": 0.5002, "lr": 6.497641509433963e-06, "epoch": 1.3001179245283019, "percentage": 6.5, "elapsed_time": "0:03:54", "remaining_time": "0:56:06", "throughput": 6179.29, "total_tokens": 1446480} {"current_steps": 2210, "total_steps": 33920, "loss": 0.4116, "lr": 6.512382075471698e-06, "epoch": 1.303066037735849, "percentage": 6.52, "elapsed_time": "0:03:54", "remaining_time": "0:56:08", "throughput": 6180.91, "total_tokens": 1450896} {"current_steps": 2215, "total_steps": 33920, "loss": 0.5683, "lr": 6.5271226415094344e-06, "epoch": 1.3060141509433962, "percentage": 6.53, "elapsed_time": "0:03:55", "remaining_time": "0:56:06", "throughput": 6180.6, "total_tokens": 1453840} {"current_steps": 2220, "total_steps": 33920, "loss": 0.4712, "lr": 6.54186320754717e-06, "epoch": 1.3089622641509435, "percentage": 6.54, "elapsed_time": "0:03:55", "remaining_time": "0:56:06", "throughput": 6179.76, "total_tokens": 1456816} {"current_steps": 2225, "total_steps": 33920, "loss": 0.4585, "lr": 6.556603773584907e-06, "epoch": 1.3119103773584906, "percentage": 6.56, "elapsed_time": "0:03:56", "remaining_time": "0:56:05", "throughput": 6179.61, "total_tokens": 1459920} {"current_steps": 2230, "total_steps": 33920, "loss": 0.558, "lr": 6.571344339622641e-06, "epoch": 1.3148584905660377, "percentage": 6.57, "elapsed_time": "0:03:56", "remaining_time": "0:56:04", "throughput": 6179.39, "total_tokens": 1462800} {"current_steps": 2235, "total_steps": 33920, "loss": 0.475, "lr": 6.586084905660378e-06, "epoch": 1.317806603773585, "percentage": 6.59, "elapsed_time": "0:03:57", "remaining_time": "0:56:04", "throughput": 6180.18, "total_tokens": 1466608} {"current_steps": 2240, "total_steps": 33920, "loss": 0.4883, "lr": 6.600825471698114e-06, "epoch": 1.320754716981132, "percentage": 6.6, "elapsed_time": "0:03:57", "remaining_time": "0:56:03", "throughput": 6179.78, "total_tokens": 1469648} {"current_steps": 2245, "total_steps": 33920, "loss": 0.4371, "lr": 6.61556603773585e-06, "epoch": 1.3237028301886793, "percentage": 6.62, "elapsed_time": "0:03:58", "remaining_time": "0:56:03", "throughput": 6179.05, "total_tokens": 1472848} {"current_steps": 2250, "total_steps": 33920, "loss": 0.3719, "lr": 6.630306603773585e-06, "epoch": 1.3266509433962264, "percentage": 6.63, "elapsed_time": "0:03:58", "remaining_time": "0:56:01", "throughput": 6178.25, "total_tokens": 1475696} {"current_steps": 2255, "total_steps": 33920, "loss": 0.5327, "lr": 6.645047169811321e-06, "epoch": 1.3295990566037736, "percentage": 6.65, "elapsed_time": "0:03:59", "remaining_time": "0:56:01", "throughput": 6178.05, "total_tokens": 1478736} {"current_steps": 2260, "total_steps": 33920, "loss": 0.4748, "lr": 6.659787735849057e-06, "epoch": 1.3325471698113207, "percentage": 6.66, "elapsed_time": "0:03:59", "remaining_time": "0:55:59", "throughput": 6176.48, "total_tokens": 1481232} {"current_steps": 2265, "total_steps": 33920, "loss": 0.5118, "lr": 6.674528301886794e-06, "epoch": 1.335495283018868, "percentage": 6.68, "elapsed_time": "0:04:00", "remaining_time": "0:55:58", "throughput": 6174.58, "total_tokens": 1483664} {"current_steps": 2270, "total_steps": 33920, "loss": 0.401, "lr": 6.689268867924529e-06, "epoch": 1.338443396226415, "percentage": 6.69, "elapsed_time": "0:04:00", "remaining_time": "0:55:56", "throughput": 6174.09, "total_tokens": 1486480} {"current_steps": 2275, "total_steps": 33920, "loss": 0.528, "lr": 6.704009433962265e-06, "epoch": 1.3413915094339623, "percentage": 6.71, "elapsed_time": "0:04:01", "remaining_time": "0:55:57", "throughput": 6175.4, "total_tokens": 1490448} {"current_steps": 2280, "total_steps": 33920, "loss": 0.4612, "lr": 6.718750000000001e-06, "epoch": 1.3443396226415094, "percentage": 6.72, "elapsed_time": "0:04:01", "remaining_time": "0:55:56", "throughput": 6175.76, "total_tokens": 1493776} {"current_steps": 2285, "total_steps": 33920, "loss": 0.7333, "lr": 6.733490566037736e-06, "epoch": 1.3472877358490565, "percentage": 6.74, "elapsed_time": "0:04:02", "remaining_time": "0:55:55", "throughput": 6174.38, "total_tokens": 1496464} {"current_steps": 2290, "total_steps": 33920, "loss": 0.5952, "lr": 6.748231132075472e-06, "epoch": 1.3502358490566038, "percentage": 6.75, "elapsed_time": "0:04:02", "remaining_time": "0:55:55", "throughput": 6175.8, "total_tokens": 1500496} {"current_steps": 2295, "total_steps": 33920, "loss": 0.532, "lr": 6.7629716981132076e-06, "epoch": 1.353183962264151, "percentage": 6.77, "elapsed_time": "0:04:03", "remaining_time": "0:55:55", "throughput": 6176.39, "total_tokens": 1503888} {"current_steps": 2300, "total_steps": 33920, "loss": 0.5461, "lr": 6.777712264150944e-06, "epoch": 1.3561320754716981, "percentage": 6.78, "elapsed_time": "0:04:04", "remaining_time": "0:55:55", "throughput": 6177.7, "total_tokens": 1507632} {"current_steps": 2305, "total_steps": 33920, "loss": 0.4835, "lr": 6.792452830188679e-06, "epoch": 1.3590801886792452, "percentage": 6.8, "elapsed_time": "0:04:04", "remaining_time": "0:55:54", "throughput": 6178.51, "total_tokens": 1511088} {"current_steps": 2310, "total_steps": 33920, "loss": 0.7306, "lr": 6.807193396226416e-06, "epoch": 1.3620283018867925, "percentage": 6.81, "elapsed_time": "0:04:05", "remaining_time": "0:55:59", "throughput": 6180.31, "total_tokens": 1517392} {"current_steps": 2315, "total_steps": 33920, "loss": 0.6151, "lr": 6.8219339622641515e-06, "epoch": 1.3649764150943398, "percentage": 6.82, "elapsed_time": "0:04:06", "remaining_time": "0:55:58", "throughput": 6179.16, "total_tokens": 1520176} {"current_steps": 2320, "total_steps": 33920, "loss": 0.5326, "lr": 6.836674528301888e-06, "epoch": 1.3679245283018868, "percentage": 6.84, "elapsed_time": "0:04:06", "remaining_time": "0:55:57", "throughput": 6178.74, "total_tokens": 1523088} {"current_steps": 2325, "total_steps": 33920, "loss": 0.4285, "lr": 6.851415094339623e-06, "epoch": 1.3708726415094339, "percentage": 6.85, "elapsed_time": "0:04:07", "remaining_time": "0:55:57", "throughput": 6178.99, "total_tokens": 1526736} {"current_steps": 2330, "total_steps": 33920, "loss": 0.492, "lr": 6.866155660377359e-06, "epoch": 1.3738207547169812, "percentage": 6.87, "elapsed_time": "0:04:07", "remaining_time": "0:55:56", "throughput": 6178.25, "total_tokens": 1529488} {"current_steps": 2335, "total_steps": 33920, "loss": 0.3746, "lr": 6.8808962264150946e-06, "epoch": 1.3767688679245282, "percentage": 6.88, "elapsed_time": "0:04:08", "remaining_time": "0:55:57", "throughput": 6179.52, "total_tokens": 1533616} {"current_steps": 2340, "total_steps": 33920, "loss": 0.536, "lr": 6.895636792452831e-06, "epoch": 1.3797169811320755, "percentage": 6.9, "elapsed_time": "0:04:08", "remaining_time": "0:55:55", "throughput": 6178.98, "total_tokens": 1536432} {"current_steps": 2345, "total_steps": 33920, "loss": 0.3871, "lr": 6.910377358490566e-06, "epoch": 1.3826650943396226, "percentage": 6.91, "elapsed_time": "0:04:09", "remaining_time": "0:55:56", "throughput": 6179.82, "total_tokens": 1540432} {"current_steps": 2350, "total_steps": 33920, "loss": 0.7117, "lr": 6.925117924528303e-06, "epoch": 1.3856132075471699, "percentage": 6.93, "elapsed_time": "0:04:10", "remaining_time": "0:56:02", "throughput": 6181.71, "total_tokens": 1547184} {"current_steps": 2355, "total_steps": 33920, "loss": 0.5208, "lr": 6.9398584905660385e-06, "epoch": 1.388561320754717, "percentage": 6.94, "elapsed_time": "0:04:10", "remaining_time": "0:56:00", "throughput": 6181.1, "total_tokens": 1549872} {"current_steps": 2360, "total_steps": 33920, "loss": 0.4235, "lr": 6.954599056603775e-06, "epoch": 1.3915094339622642, "percentage": 6.96, "elapsed_time": "0:04:11", "remaining_time": "0:56:00", "throughput": 6181.44, "total_tokens": 1553200} {"current_steps": 2365, "total_steps": 33920, "loss": 0.5073, "lr": 6.96933962264151e-06, "epoch": 1.3944575471698113, "percentage": 6.97, "elapsed_time": "0:04:11", "remaining_time": "0:55:58", "throughput": 6180.71, "total_tokens": 1555920} {"current_steps": 2370, "total_steps": 33920, "loss": 0.5834, "lr": 6.984080188679245e-06, "epoch": 1.3974056603773586, "percentage": 6.99, "elapsed_time": "0:04:12", "remaining_time": "0:55:57", "throughput": 6180.3, "total_tokens": 1558736} {"current_steps": 2375, "total_steps": 33920, "loss": 0.4879, "lr": 6.9988207547169815e-06, "epoch": 1.4003537735849056, "percentage": 7.0, "elapsed_time": "0:04:12", "remaining_time": "0:55:56", "throughput": 6180.92, "total_tokens": 1561968} {"current_steps": 2380, "total_steps": 33920, "loss": 0.4974, "lr": 7.013561320754717e-06, "epoch": 1.4033018867924527, "percentage": 7.02, "elapsed_time": "0:04:13", "remaining_time": "0:55:57", "throughput": 6182.09, "total_tokens": 1566096} {"current_steps": 2385, "total_steps": 33920, "loss": 0.5475, "lr": 7.028301886792454e-06, "epoch": 1.40625, "percentage": 7.03, "elapsed_time": "0:04:13", "remaining_time": "0:55:56", "throughput": 6183.07, "total_tokens": 1569744} {"current_steps": 2390, "total_steps": 33920, "loss": 0.5431, "lr": 7.043042452830188e-06, "epoch": 1.4091981132075473, "percentage": 7.05, "elapsed_time": "0:04:14", "remaining_time": "0:55:55", "throughput": 6182.99, "total_tokens": 1572656} {"current_steps": 2395, "total_steps": 33920, "loss": 0.4855, "lr": 7.0577830188679255e-06, "epoch": 1.4121462264150944, "percentage": 7.06, "elapsed_time": "0:04:14", "remaining_time": "0:55:54", "throughput": 6183.36, "total_tokens": 1575664} {"current_steps": 2400, "total_steps": 33920, "loss": 0.4392, "lr": 7.072523584905661e-06, "epoch": 1.4150943396226414, "percentage": 7.08, "elapsed_time": "0:04:15", "remaining_time": "0:55:54", "throughput": 6184.88, "total_tokens": 1579664} {"current_steps": 2405, "total_steps": 33920, "loss": 0.5357, "lr": 7.087264150943397e-06, "epoch": 1.4180424528301887, "percentage": 7.09, "elapsed_time": "0:04:16", "remaining_time": "0:55:54", "throughput": 6185.86, "total_tokens": 1583664} {"current_steps": 2410, "total_steps": 33920, "loss": 0.4366, "lr": 7.102004716981132e-06, "epoch": 1.4209905660377358, "percentage": 7.1, "elapsed_time": "0:04:16", "remaining_time": "0:55:53", "throughput": 6184.86, "total_tokens": 1586320} {"current_steps": 2415, "total_steps": 33920, "loss": 0.3772, "lr": 7.1167452830188685e-06, "epoch": 1.423938679245283, "percentage": 7.12, "elapsed_time": "0:04:17", "remaining_time": "0:55:52", "throughput": 6184.35, "total_tokens": 1589456} {"current_steps": 2420, "total_steps": 33920, "loss": 0.6385, "lr": 7.131485849056604e-06, "epoch": 1.4268867924528301, "percentage": 7.13, "elapsed_time": "0:04:17", "remaining_time": "0:55:51", "throughput": 6183.81, "total_tokens": 1592240} {"current_steps": 2425, "total_steps": 33920, "loss": 0.7068, "lr": 7.146226415094341e-06, "epoch": 1.4298349056603774, "percentage": 7.15, "elapsed_time": "0:04:17", "remaining_time": "0:55:50", "throughput": 6181.55, "total_tokens": 1594512} {"current_steps": 2430, "total_steps": 33920, "loss": 0.5552, "lr": 7.160966981132076e-06, "epoch": 1.4327830188679245, "percentage": 7.16, "elapsed_time": "0:04:18", "remaining_time": "0:55:49", "throughput": 6181.91, "total_tokens": 1598032} {"current_steps": 2435, "total_steps": 33920, "loss": 0.408, "lr": 7.1757075471698125e-06, "epoch": 1.4357311320754718, "percentage": 7.18, "elapsed_time": "0:04:19", "remaining_time": "0:55:49", "throughput": 6182.54, "total_tokens": 1601584} {"current_steps": 2440, "total_steps": 33920, "loss": 0.5061, "lr": 7.190448113207548e-06, "epoch": 1.4386792452830188, "percentage": 7.19, "elapsed_time": "0:04:19", "remaining_time": "0:55:48", "throughput": 6180.13, "total_tokens": 1603888} {"current_steps": 2445, "total_steps": 33920, "loss": 0.4003, "lr": 7.205188679245284e-06, "epoch": 1.4416273584905661, "percentage": 7.21, "elapsed_time": "0:04:20", "remaining_time": "0:55:52", "throughput": 6181.68, "total_tokens": 1610064} {"current_steps": 2450, "total_steps": 33920, "loss": 0.5983, "lr": 7.219929245283019e-06, "epoch": 1.4445754716981132, "percentage": 7.22, "elapsed_time": "0:04:21", "remaining_time": "0:55:52", "throughput": 6182.24, "total_tokens": 1613648} {"current_steps": 2455, "total_steps": 33920, "loss": 0.5458, "lr": 7.2346698113207555e-06, "epoch": 1.4475235849056602, "percentage": 7.24, "elapsed_time": "0:04:21", "remaining_time": "0:55:53", "throughput": 6182.84, "total_tokens": 1617712} {"current_steps": 2460, "total_steps": 33920, "loss": 0.4777, "lr": 7.249410377358491e-06, "epoch": 1.4504716981132075, "percentage": 7.25, "elapsed_time": "0:04:22", "remaining_time": "0:55:53", "throughput": 6183.51, "total_tokens": 1621360} {"current_steps": 2465, "total_steps": 33920, "loss": 0.5654, "lr": 7.264150943396226e-06, "epoch": 1.4534198113207548, "percentage": 7.27, "elapsed_time": "0:04:22", "remaining_time": "0:55:52", "throughput": 6183.22, "total_tokens": 1624592} {"current_steps": 2470, "total_steps": 33920, "loss": 0.3454, "lr": 7.278891509433963e-06, "epoch": 1.4563679245283019, "percentage": 7.28, "elapsed_time": "0:04:23", "remaining_time": "0:55:51", "throughput": 6182.35, "total_tokens": 1627536} {"current_steps": 2475, "total_steps": 33920, "loss": 0.6499, "lr": 7.293632075471699e-06, "epoch": 1.459316037735849, "percentage": 7.3, "elapsed_time": "0:04:23", "remaining_time": "0:55:51", "throughput": 6182.81, "total_tokens": 1630864} {"current_steps": 2480, "total_steps": 33920, "loss": 0.5216, "lr": 7.308372641509435e-06, "epoch": 1.4622641509433962, "percentage": 7.31, "elapsed_time": "0:04:24", "remaining_time": "0:55:57", "throughput": 6183.93, "total_tokens": 1637840} {"current_steps": 2485, "total_steps": 33920, "loss": 0.6997, "lr": 7.32311320754717e-06, "epoch": 1.4652122641509435, "percentage": 7.33, "elapsed_time": "0:04:25", "remaining_time": "0:55:56", "throughput": 6182.2, "total_tokens": 1640240} {"current_steps": 2490, "total_steps": 33920, "loss": 0.6019, "lr": 7.337853773584906e-06, "epoch": 1.4681603773584906, "percentage": 7.34, "elapsed_time": "0:04:25", "remaining_time": "0:55:55", "throughput": 6182.93, "total_tokens": 1643760} {"current_steps": 2495, "total_steps": 33920, "loss": 0.6693, "lr": 7.352594339622642e-06, "epoch": 1.4711084905660377, "percentage": 7.36, "elapsed_time": "0:04:26", "remaining_time": "0:55:55", "throughput": 6183.54, "total_tokens": 1647312} {"current_steps": 2500, "total_steps": 33920, "loss": 0.5773, "lr": 7.367334905660378e-06, "epoch": 1.474056603773585, "percentage": 7.37, "elapsed_time": "0:04:27", "remaining_time": "0:55:57", "throughput": 6185.0, "total_tokens": 1652368} {"current_steps": 2505, "total_steps": 33920, "loss": 0.5642, "lr": 7.382075471698113e-06, "epoch": 1.477004716981132, "percentage": 7.39, "elapsed_time": "0:04:27", "remaining_time": "0:55:58", "throughput": 6186.58, "total_tokens": 1656944} {"current_steps": 2510, "total_steps": 33920, "loss": 0.6037, "lr": 7.39681603773585e-06, "epoch": 1.4799528301886793, "percentage": 7.4, "elapsed_time": "0:04:28", "remaining_time": "0:55:57", "throughput": 6185.8, "total_tokens": 1659696} {"current_steps": 2515, "total_steps": 33920, "loss": 0.4081, "lr": 7.411556603773586e-06, "epoch": 1.4829009433962264, "percentage": 7.41, "elapsed_time": "0:04:28", "remaining_time": "0:55:56", "throughput": 6184.03, "total_tokens": 1662032} {"current_steps": 2520, "total_steps": 33920, "loss": 0.465, "lr": 7.426297169811322e-06, "epoch": 1.4858490566037736, "percentage": 7.43, "elapsed_time": "0:04:29", "remaining_time": "0:56:01", "throughput": 6186.38, "total_tokens": 1668880} {"current_steps": 2525, "total_steps": 33920, "loss": 0.5302, "lr": 7.441037735849057e-06, "epoch": 1.4887971698113207, "percentage": 7.44, "elapsed_time": "0:04:30", "remaining_time": "0:56:00", "throughput": 6185.4, "total_tokens": 1671760} {"current_steps": 2530, "total_steps": 33920, "loss": 0.6271, "lr": 7.455778301886793e-06, "epoch": 1.491745283018868, "percentage": 7.46, "elapsed_time": "0:04:30", "remaining_time": "0:55:59", "throughput": 6184.98, "total_tokens": 1674704} {"current_steps": 2535, "total_steps": 33920, "loss": 0.4941, "lr": 7.470518867924529e-06, "epoch": 1.494693396226415, "percentage": 7.47, "elapsed_time": "0:04:31", "remaining_time": "0:55:59", "throughput": 6186.31, "total_tokens": 1678768} {"current_steps": 2540, "total_steps": 33920, "loss": 0.6335, "lr": 7.485259433962266e-06, "epoch": 1.4976415094339623, "percentage": 7.49, "elapsed_time": "0:04:31", "remaining_time": "0:55:59", "throughput": 6187.61, "total_tokens": 1682672} {"current_steps": 2545, "total_steps": 33920, "loss": 0.5537, "lr": 7.500000000000001e-06, "epoch": 1.5005896226415094, "percentage": 7.5, "elapsed_time": "0:04:32", "remaining_time": "0:55:58", "throughput": 6186.09, "total_tokens": 1685136} {"current_steps": 2550, "total_steps": 33920, "loss": 0.5876, "lr": 7.5147405660377355e-06, "epoch": 1.5035377358490565, "percentage": 7.52, "elapsed_time": "0:04:32", "remaining_time": "0:55:56", "throughput": 6185.76, "total_tokens": 1687952} {"current_steps": 2555, "total_steps": 33920, "loss": 0.6532, "lr": 7.5294811320754726e-06, "epoch": 1.5064858490566038, "percentage": 7.53, "elapsed_time": "0:04:33", "remaining_time": "0:55:56", "throughput": 6186.66, "total_tokens": 1691408} {"current_steps": 2560, "total_steps": 33920, "loss": 0.4903, "lr": 7.544221698113208e-06, "epoch": 1.509433962264151, "percentage": 7.55, "elapsed_time": "0:04:33", "remaining_time": "0:55:55", "throughput": 6186.51, "total_tokens": 1694544} {"current_steps": 2565, "total_steps": 33920, "loss": 0.6899, "lr": 7.558962264150944e-06, "epoch": 1.5123820754716981, "percentage": 7.56, "elapsed_time": "0:04:34", "remaining_time": "0:55:54", "throughput": 6186.51, "total_tokens": 1697872} {"current_steps": 2570, "total_steps": 33920, "loss": 0.4313, "lr": 7.5737028301886795e-06, "epoch": 1.5153301886792452, "percentage": 7.58, "elapsed_time": "0:04:34", "remaining_time": "0:55:54", "throughput": 6186.57, "total_tokens": 1701168} {"current_steps": 2575, "total_steps": 33920, "loss": 0.3597, "lr": 7.588443396226416e-06, "epoch": 1.5182783018867925, "percentage": 7.59, "elapsed_time": "0:04:35", "remaining_time": "0:55:53", "throughput": 6186.67, "total_tokens": 1704624} {"current_steps": 2580, "total_steps": 33920, "loss": 0.7222, "lr": 7.603183962264151e-06, "epoch": 1.5212264150943398, "percentage": 7.61, "elapsed_time": "0:04:35", "remaining_time": "0:55:52", "throughput": 6185.59, "total_tokens": 1707216} {"current_steps": 2585, "total_steps": 33920, "loss": 0.5891, "lr": 7.617924528301888e-06, "epoch": 1.5241745283018868, "percentage": 7.62, "elapsed_time": "0:04:36", "remaining_time": "0:55:52", "throughput": 6184.65, "total_tokens": 1710256} {"current_steps": 2590, "total_steps": 33920, "loss": 0.4943, "lr": 7.632665094339623e-06, "epoch": 1.5271226415094339, "percentage": 7.64, "elapsed_time": "0:04:37", "remaining_time": "0:55:51", "throughput": 6183.67, "total_tokens": 1713168} {"current_steps": 2595, "total_steps": 33920, "loss": 0.5818, "lr": 7.64740566037736e-06, "epoch": 1.5300707547169812, "percentage": 7.65, "elapsed_time": "0:04:37", "remaining_time": "0:55:51", "throughput": 6185.47, "total_tokens": 1717584} {"current_steps": 2600, "total_steps": 33920, "loss": 0.5867, "lr": 7.662146226415095e-06, "epoch": 1.5330188679245285, "percentage": 7.67, "elapsed_time": "0:04:38", "remaining_time": "0:55:51", "throughput": 6186.26, "total_tokens": 1721008} {"current_steps": 2605, "total_steps": 33920, "loss": 0.5149, "lr": 7.676886792452832e-06, "epoch": 1.5359669811320755, "percentage": 7.68, "elapsed_time": "0:04:38", "remaining_time": "0:55:49", "throughput": 6185.81, "total_tokens": 1723824} {"current_steps": 2610, "total_steps": 33920, "loss": 0.5639, "lr": 7.691627358490567e-06, "epoch": 1.5389150943396226, "percentage": 7.69, "elapsed_time": "0:04:39", "remaining_time": "0:55:49", "throughput": 6185.07, "total_tokens": 1726704} {"current_steps": 2615, "total_steps": 33920, "loss": 0.5172, "lr": 7.706367924528303e-06, "epoch": 1.5418632075471699, "percentage": 7.71, "elapsed_time": "0:04:39", "remaining_time": "0:55:47", "throughput": 6183.27, "total_tokens": 1728944} {"current_steps": 2620, "total_steps": 33920, "loss": 0.5789, "lr": 7.721108490566038e-06, "epoch": 1.544811320754717, "percentage": 7.72, "elapsed_time": "0:04:40", "remaining_time": "0:55:47", "throughput": 6184.07, "total_tokens": 1732656} {"current_steps": 2625, "total_steps": 33920, "loss": 0.5201, "lr": 7.735849056603775e-06, "epoch": 1.547759433962264, "percentage": 7.74, "elapsed_time": "0:04:40", "remaining_time": "0:55:47", "throughput": 6184.41, "total_tokens": 1736304} {"current_steps": 2630, "total_steps": 33920, "loss": 0.4645, "lr": 7.75058962264151e-06, "epoch": 1.5507075471698113, "percentage": 7.75, "elapsed_time": "0:04:41", "remaining_time": "0:55:45", "throughput": 6182.72, "total_tokens": 1738800} {"current_steps": 2635, "total_steps": 33920, "loss": 0.6032, "lr": 7.765330188679246e-06, "epoch": 1.5536556603773586, "percentage": 7.77, "elapsed_time": "0:04:41", "remaining_time": "0:55:46", "throughput": 6184.01, "total_tokens": 1742864} {"current_steps": 2640, "total_steps": 33920, "loss": 0.6604, "lr": 7.780070754716981e-06, "epoch": 1.5566037735849056, "percentage": 7.78, "elapsed_time": "0:04:42", "remaining_time": "0:55:45", "throughput": 6183.46, "total_tokens": 1745712} {"current_steps": 2645, "total_steps": 33920, "loss": 0.498, "lr": 7.794811320754716e-06, "epoch": 1.5595518867924527, "percentage": 7.8, "elapsed_time": "0:04:42", "remaining_time": "0:55:44", "throughput": 6183.25, "total_tokens": 1748848} {"current_steps": 2650, "total_steps": 33920, "loss": 0.6063, "lr": 7.809551886792453e-06, "epoch": 1.5625, "percentage": 7.81, "elapsed_time": "0:04:43", "remaining_time": "0:55:43", "throughput": 6182.41, "total_tokens": 1751632} {"current_steps": 2655, "total_steps": 33920, "loss": 0.5786, "lr": 7.824292452830189e-06, "epoch": 1.5654481132075473, "percentage": 7.83, "elapsed_time": "0:04:43", "remaining_time": "0:55:42", "throughput": 6181.1, "total_tokens": 1754256} {"current_steps": 2660, "total_steps": 33920, "loss": 0.4408, "lr": 7.839033018867926e-06, "epoch": 1.5683962264150944, "percentage": 7.84, "elapsed_time": "0:04:44", "remaining_time": "0:55:42", "throughput": 6182.2, "total_tokens": 1758256} {"current_steps": 2665, "total_steps": 33920, "loss": 0.449, "lr": 7.853773584905661e-06, "epoch": 1.5713443396226414, "percentage": 7.86, "elapsed_time": "0:04:44", "remaining_time": "0:55:41", "throughput": 6180.89, "total_tokens": 1761104} {"current_steps": 2670, "total_steps": 33920, "loss": 0.6445, "lr": 7.868514150943397e-06, "epoch": 1.5742924528301887, "percentage": 7.87, "elapsed_time": "0:04:45", "remaining_time": "0:55:40", "throughput": 6181.1, "total_tokens": 1764368} {"current_steps": 2675, "total_steps": 33920, "loss": 0.6282, "lr": 7.883254716981132e-06, "epoch": 1.577240566037736, "percentage": 7.89, "elapsed_time": "0:04:45", "remaining_time": "0:55:40", "throughput": 6181.06, "total_tokens": 1767600} {"current_steps": 2680, "total_steps": 33920, "loss": 0.5946, "lr": 7.897995283018869e-06, "epoch": 1.580188679245283, "percentage": 7.9, "elapsed_time": "0:04:46", "remaining_time": "0:55:39", "throughput": 6181.01, "total_tokens": 1770704} {"current_steps": 2685, "total_steps": 33920, "loss": 0.4877, "lr": 7.912735849056604e-06, "epoch": 1.5831367924528301, "percentage": 7.92, "elapsed_time": "0:04:47", "remaining_time": "0:55:38", "throughput": 6181.4, "total_tokens": 1774192} {"current_steps": 2690, "total_steps": 33920, "loss": 0.5043, "lr": 7.927476415094341e-06, "epoch": 1.5860849056603774, "percentage": 7.93, "elapsed_time": "0:04:47", "remaining_time": "0:55:37", "throughput": 6181.14, "total_tokens": 1777104} {"current_steps": 2695, "total_steps": 33920, "loss": 0.4547, "lr": 7.942216981132077e-06, "epoch": 1.5890330188679245, "percentage": 7.95, "elapsed_time": "0:04:48", "remaining_time": "0:55:38", "throughput": 6181.91, "total_tokens": 1781040} {"current_steps": 2700, "total_steps": 33920, "loss": 0.4374, "lr": 7.956957547169812e-06, "epoch": 1.5919811320754715, "percentage": 7.96, "elapsed_time": "0:04:48", "remaining_time": "0:55:37", "throughput": 6182.26, "total_tokens": 1784240} {"current_steps": 2705, "total_steps": 33920, "loss": 0.5109, "lr": 7.971698113207547e-06, "epoch": 1.5949292452830188, "percentage": 7.97, "elapsed_time": "0:04:49", "remaining_time": "0:55:37", "throughput": 6182.5, "total_tokens": 1788016} {"current_steps": 2710, "total_steps": 33920, "loss": 0.6303, "lr": 7.986438679245284e-06, "epoch": 1.5978773584905661, "percentage": 7.99, "elapsed_time": "0:04:49", "remaining_time": "0:55:36", "throughput": 6182.64, "total_tokens": 1791280} {"current_steps": 2715, "total_steps": 33920, "loss": 0.4833, "lr": 8.00117924528302e-06, "epoch": 1.6008254716981132, "percentage": 8.0, "elapsed_time": "0:04:50", "remaining_time": "0:55:36", "throughput": 6182.13, "total_tokens": 1794384} {"current_steps": 2720, "total_steps": 33920, "loss": 0.7109, "lr": 8.015919811320757e-06, "epoch": 1.6037735849056602, "percentage": 8.02, "elapsed_time": "0:04:50", "remaining_time": "0:55:35", "throughput": 6182.05, "total_tokens": 1797872} {"current_steps": 2725, "total_steps": 33920, "loss": 0.5164, "lr": 8.030660377358492e-06, "epoch": 1.6067216981132075, "percentage": 8.03, "elapsed_time": "0:04:51", "remaining_time": "0:55:35", "throughput": 6181.02, "total_tokens": 1800976} {"current_steps": 2730, "total_steps": 33920, "loss": 0.4662, "lr": 8.045400943396227e-06, "epoch": 1.6096698113207548, "percentage": 8.05, "elapsed_time": "0:04:51", "remaining_time": "0:55:35", "throughput": 6180.75, "total_tokens": 1804368} {"current_steps": 2735, "total_steps": 33920, "loss": 0.4143, "lr": 8.060141509433963e-06, "epoch": 1.6126179245283019, "percentage": 8.06, "elapsed_time": "0:04:52", "remaining_time": "0:55:35", "throughput": 6180.91, "total_tokens": 1807856} {"current_steps": 2740, "total_steps": 33920, "loss": 0.5368, "lr": 8.074882075471698e-06, "epoch": 1.615566037735849, "percentage": 8.08, "elapsed_time": "0:04:52", "remaining_time": "0:55:34", "throughput": 6180.86, "total_tokens": 1810896} {"current_steps": 2745, "total_steps": 33920, "loss": 0.4909, "lr": 8.089622641509435e-06, "epoch": 1.6185141509433962, "percentage": 8.09, "elapsed_time": "0:04:53", "remaining_time": "0:55:34", "throughput": 6181.52, "total_tokens": 1814864} {"current_steps": 2750, "total_steps": 33920, "loss": 0.5272, "lr": 8.10436320754717e-06, "epoch": 1.6214622641509435, "percentage": 8.11, "elapsed_time": "0:04:54", "remaining_time": "0:55:34", "throughput": 6181.85, "total_tokens": 1818544} {"current_steps": 2755, "total_steps": 33920, "loss": 0.6445, "lr": 8.119103773584906e-06, "epoch": 1.6244103773584906, "percentage": 8.12, "elapsed_time": "0:04:54", "remaining_time": "0:55:33", "throughput": 6181.27, "total_tokens": 1821296} {"current_steps": 2760, "total_steps": 33920, "loss": 0.4564, "lr": 8.133844339622641e-06, "epoch": 1.6273584905660377, "percentage": 8.14, "elapsed_time": "0:04:55", "remaining_time": "0:55:32", "throughput": 6180.01, "total_tokens": 1823984} {"current_steps": 2765, "total_steps": 33920, "loss": 0.6902, "lr": 8.148584905660378e-06, "epoch": 1.630306603773585, "percentage": 8.15, "elapsed_time": "0:04:55", "remaining_time": "0:55:30", "throughput": 6178.57, "total_tokens": 1826384} {"current_steps": 2770, "total_steps": 33920, "loss": 0.5771, "lr": 8.163325471698114e-06, "epoch": 1.6332547169811322, "percentage": 8.17, "elapsed_time": "0:04:56", "remaining_time": "0:55:31", "throughput": 6179.06, "total_tokens": 1830768} {"current_steps": 2775, "total_steps": 33920, "loss": 0.5018, "lr": 8.17806603773585e-06, "epoch": 1.6362028301886793, "percentage": 8.18, "elapsed_time": "0:04:56", "remaining_time": "0:55:30", "throughput": 6177.72, "total_tokens": 1833168} {"current_steps": 2780, "total_steps": 33920, "loss": 0.5226, "lr": 8.192806603773586e-06, "epoch": 1.6391509433962264, "percentage": 8.2, "elapsed_time": "0:04:57", "remaining_time": "0:55:29", "throughput": 6176.25, "total_tokens": 1835664} {"current_steps": 2785, "total_steps": 33920, "loss": 0.6979, "lr": 8.207547169811321e-06, "epoch": 1.6420990566037736, "percentage": 8.21, "elapsed_time": "0:04:57", "remaining_time": "0:55:29", "throughput": 6177.0, "total_tokens": 1839440} {"current_steps": 2790, "total_steps": 33920, "loss": 0.7172, "lr": 8.222287735849057e-06, "epoch": 1.6450471698113207, "percentage": 8.23, "elapsed_time": "0:04:58", "remaining_time": "0:55:28", "throughput": 6176.97, "total_tokens": 1842800} {"current_steps": 2795, "total_steps": 33920, "loss": 0.4863, "lr": 8.237028301886794e-06, "epoch": 1.6479952830188678, "percentage": 8.24, "elapsed_time": "0:04:58", "remaining_time": "0:55:28", "throughput": 6176.51, "total_tokens": 1845872} {"current_steps": 2800, "total_steps": 33920, "loss": 0.5963, "lr": 8.251768867924529e-06, "epoch": 1.650943396226415, "percentage": 8.25, "elapsed_time": "0:04:59", "remaining_time": "0:55:26", "throughput": 6176.07, "total_tokens": 1848688} {"current_steps": 2805, "total_steps": 33920, "loss": 0.5444, "lr": 8.266509433962266e-06, "epoch": 1.6538915094339623, "percentage": 8.27, "elapsed_time": "0:04:59", "remaining_time": "0:55:27", "throughput": 6177.18, "total_tokens": 1852784} {"current_steps": 2810, "total_steps": 33920, "loss": 0.4602, "lr": 8.281250000000001e-06, "epoch": 1.6568396226415094, "percentage": 8.28, "elapsed_time": "0:05:00", "remaining_time": "0:55:26", "throughput": 6176.1, "total_tokens": 1855568} {"current_steps": 2815, "total_steps": 33920, "loss": 0.6375, "lr": 8.295990566037737e-06, "epoch": 1.6597877358490565, "percentage": 8.3, "elapsed_time": "0:05:00", "remaining_time": "0:55:25", "throughput": 6177.13, "total_tokens": 1859216} {"current_steps": 2820, "total_steps": 33920, "loss": 0.6615, "lr": 8.310731132075472e-06, "epoch": 1.6627358490566038, "percentage": 8.31, "elapsed_time": "0:05:01", "remaining_time": "0:55:25", "throughput": 6176.86, "total_tokens": 1862832} {"current_steps": 2825, "total_steps": 33920, "loss": 0.5801, "lr": 8.325471698113207e-06, "epoch": 1.665683962264151, "percentage": 8.33, "elapsed_time": "0:05:02", "remaining_time": "0:55:25", "throughput": 6176.34, "total_tokens": 1865840} {"current_steps": 2830, "total_steps": 33920, "loss": 0.4777, "lr": 8.340212264150944e-06, "epoch": 1.6686320754716981, "percentage": 8.34, "elapsed_time": "0:05:02", "remaining_time": "0:55:24", "throughput": 6176.62, "total_tokens": 1869328} {"current_steps": 2835, "total_steps": 33920, "loss": 0.5575, "lr": 8.35495283018868e-06, "epoch": 1.6715801886792452, "percentage": 8.36, "elapsed_time": "0:05:03", "remaining_time": "0:55:26", "throughput": 6177.87, "total_tokens": 1874288} {"current_steps": 2840, "total_steps": 33920, "loss": 0.5495, "lr": 8.369693396226415e-06, "epoch": 1.6745283018867925, "percentage": 8.37, "elapsed_time": "0:05:03", "remaining_time": "0:55:25", "throughput": 6176.66, "total_tokens": 1876784} {"current_steps": 2845, "total_steps": 33920, "loss": 0.5281, "lr": 8.38443396226415e-06, "epoch": 1.6774764150943398, "percentage": 8.39, "elapsed_time": "0:05:04", "remaining_time": "0:55:24", "throughput": 6175.95, "total_tokens": 1879504} {"current_steps": 2850, "total_steps": 33920, "loss": 0.4791, "lr": 8.399174528301888e-06, "epoch": 1.6804245283018868, "percentage": 8.4, "elapsed_time": "0:05:04", "remaining_time": "0:55:24", "throughput": 6177.4, "total_tokens": 1884016} {"current_steps": 2855, "total_steps": 33920, "loss": 0.5521, "lr": 8.413915094339623e-06, "epoch": 1.6833726415094339, "percentage": 8.42, "elapsed_time": "0:05:05", "remaining_time": "0:55:24", "throughput": 6178.14, "total_tokens": 1887568} {"current_steps": 2860, "total_steps": 33920, "loss": 0.6056, "lr": 8.42865566037736e-06, "epoch": 1.6863207547169812, "percentage": 8.43, "elapsed_time": "0:05:06", "remaining_time": "0:55:23", "throughput": 6178.11, "total_tokens": 1890736} {"current_steps": 2865, "total_steps": 33920, "loss": 0.5741, "lr": 8.443396226415095e-06, "epoch": 1.6892688679245285, "percentage": 8.45, "elapsed_time": "0:05:06", "remaining_time": "0:55:23", "throughput": 6178.9, "total_tokens": 1894384} {"current_steps": 2870, "total_steps": 33920, "loss": 0.4658, "lr": 8.45813679245283e-06, "epoch": 1.6922169811320755, "percentage": 8.46, "elapsed_time": "0:05:07", "remaining_time": "0:55:22", "throughput": 6178.94, "total_tokens": 1897456} {"current_steps": 2875, "total_steps": 33920, "loss": 0.5902, "lr": 8.472877358490566e-06, "epoch": 1.6951650943396226, "percentage": 8.48, "elapsed_time": "0:05:07", "remaining_time": "0:55:21", "throughput": 6179.12, "total_tokens": 1900624} {"current_steps": 2880, "total_steps": 33920, "loss": 0.4154, "lr": 8.487617924528303e-06, "epoch": 1.6981132075471699, "percentage": 8.49, "elapsed_time": "0:05:08", "remaining_time": "0:55:20", "throughput": 6178.19, "total_tokens": 1903600} {"current_steps": 2885, "total_steps": 33920, "loss": 0.6079, "lr": 8.502358490566038e-06, "epoch": 1.701061320754717, "percentage": 8.51, "elapsed_time": "0:05:08", "remaining_time": "0:55:19", "throughput": 6177.93, "total_tokens": 1906544} {"current_steps": 2890, "total_steps": 33920, "loss": 0.6543, "lr": 8.517099056603775e-06, "epoch": 1.704009433962264, "percentage": 8.52, "elapsed_time": "0:05:09", "remaining_time": "0:55:18", "throughput": 6178.07, "total_tokens": 1909744} {"current_steps": 2895, "total_steps": 33920, "loss": 0.5449, "lr": 8.53183962264151e-06, "epoch": 1.7069575471698113, "percentage": 8.53, "elapsed_time": "0:05:09", "remaining_time": "0:55:19", "throughput": 6178.74, "total_tokens": 1913616} {"current_steps": 2900, "total_steps": 33920, "loss": 0.4876, "lr": 8.546580188679246e-06, "epoch": 1.7099056603773586, "percentage": 8.55, "elapsed_time": "0:05:10", "remaining_time": "0:55:18", "throughput": 6178.53, "total_tokens": 1916560} {"current_steps": 2905, "total_steps": 33920, "loss": 0.7924, "lr": 8.561320754716981e-06, "epoch": 1.7128537735849056, "percentage": 8.56, "elapsed_time": "0:05:10", "remaining_time": "0:55:16", "throughput": 6177.22, "total_tokens": 1919088} {"current_steps": 2910, "total_steps": 33920, "loss": 0.7876, "lr": 8.576061320754717e-06, "epoch": 1.7158018867924527, "percentage": 8.58, "elapsed_time": "0:05:11", "remaining_time": "0:55:16", "throughput": 6177.61, "total_tokens": 1922640} {"current_steps": 2915, "total_steps": 33920, "loss": 0.4375, "lr": 8.590801886792454e-06, "epoch": 1.71875, "percentage": 8.59, "elapsed_time": "0:05:11", "remaining_time": "0:55:15", "throughput": 6177.09, "total_tokens": 1925392} {"current_steps": 2920, "total_steps": 33920, "loss": 0.7063, "lr": 8.605542452830189e-06, "epoch": 1.7216981132075473, "percentage": 8.61, "elapsed_time": "0:05:12", "remaining_time": "0:55:14", "throughput": 6177.03, "total_tokens": 1928464} {"current_steps": 2925, "total_steps": 33920, "loss": 0.6664, "lr": 8.620283018867926e-06, "epoch": 1.7246462264150944, "percentage": 8.62, "elapsed_time": "0:05:12", "remaining_time": "0:55:13", "throughput": 6177.07, "total_tokens": 1931600} {"current_steps": 2930, "total_steps": 33920, "loss": 0.6571, "lr": 8.635023584905662e-06, "epoch": 1.7275943396226414, "percentage": 8.64, "elapsed_time": "0:05:13", "remaining_time": "0:55:12", "throughput": 6177.36, "total_tokens": 1934864} {"current_steps": 2935, "total_steps": 33920, "loss": 0.5229, "lr": 8.649764150943397e-06, "epoch": 1.7305424528301887, "percentage": 8.65, "elapsed_time": "0:05:13", "remaining_time": "0:55:11", "throughput": 6177.74, "total_tokens": 1938096} {"current_steps": 2940, "total_steps": 33920, "loss": 0.5641, "lr": 8.664504716981132e-06, "epoch": 1.733490566037736, "percentage": 8.67, "elapsed_time": "0:05:14", "remaining_time": "0:55:11", "throughput": 6178.0, "total_tokens": 1941328} {"current_steps": 2945, "total_steps": 33920, "loss": 0.6303, "lr": 8.67924528301887e-06, "epoch": 1.736438679245283, "percentage": 8.68, "elapsed_time": "0:05:14", "remaining_time": "0:55:10", "throughput": 6178.67, "total_tokens": 1944976} {"current_steps": 2950, "total_steps": 33920, "loss": 0.4712, "lr": 8.693985849056605e-06, "epoch": 1.7393867924528301, "percentage": 8.7, "elapsed_time": "0:05:15", "remaining_time": "0:55:09", "throughput": 6177.29, "total_tokens": 1947376} {"current_steps": 2955, "total_steps": 33920, "loss": 0.4929, "lr": 8.70872641509434e-06, "epoch": 1.7423349056603774, "percentage": 8.71, "elapsed_time": "0:05:15", "remaining_time": "0:55:08", "throughput": 6177.56, "total_tokens": 1950576} {"current_steps": 2960, "total_steps": 33920, "loss": 0.5411, "lr": 8.723466981132075e-06, "epoch": 1.7452830188679245, "percentage": 8.73, "elapsed_time": "0:05:16", "remaining_time": "0:55:08", "throughput": 6178.73, "total_tokens": 1954448} {"current_steps": 2965, "total_steps": 33920, "loss": 0.5475, "lr": 8.738207547169812e-06, "epoch": 1.7482311320754715, "percentage": 8.74, "elapsed_time": "0:05:16", "remaining_time": "0:55:08", "throughput": 6179.25, "total_tokens": 1957968} {"current_steps": 2970, "total_steps": 33920, "loss": 0.5321, "lr": 8.752948113207548e-06, "epoch": 1.7511792452830188, "percentage": 8.76, "elapsed_time": "0:05:17", "remaining_time": "0:55:06", "throughput": 6177.28, "total_tokens": 1960176} {"current_steps": 2975, "total_steps": 33920, "loss": 0.5657, "lr": 8.767688679245285e-06, "epoch": 1.7541273584905661, "percentage": 8.77, "elapsed_time": "0:05:17", "remaining_time": "0:55:06", "throughput": 6178.18, "total_tokens": 1964048} {"current_steps": 2980, "total_steps": 33920, "loss": 0.604, "lr": 8.78242924528302e-06, "epoch": 1.7570754716981132, "percentage": 8.79, "elapsed_time": "0:05:18", "remaining_time": "0:55:06", "throughput": 6178.99, "total_tokens": 1967568} {"current_steps": 2985, "total_steps": 33920, "loss": 0.5514, "lr": 8.797169811320755e-06, "epoch": 1.7600235849056602, "percentage": 8.8, "elapsed_time": "0:05:18", "remaining_time": "0:55:05", "throughput": 6178.62, "total_tokens": 1970448} {"current_steps": 2990, "total_steps": 33920, "loss": 0.4758, "lr": 8.81191037735849e-06, "epoch": 1.7629716981132075, "percentage": 8.81, "elapsed_time": "0:05:19", "remaining_time": "0:55:04", "throughput": 6179.24, "total_tokens": 1974160} {"current_steps": 2995, "total_steps": 33920, "loss": 0.7704, "lr": 8.826650943396226e-06, "epoch": 1.7659198113207548, "percentage": 8.83, "elapsed_time": "0:05:19", "remaining_time": "0:55:04", "throughput": 6179.21, "total_tokens": 1977264} {"current_steps": 3000, "total_steps": 33920, "loss": 0.5609, "lr": 8.841391509433963e-06, "epoch": 1.7688679245283019, "percentage": 8.84, "elapsed_time": "0:05:20", "remaining_time": "0:55:03", "throughput": 6179.71, "total_tokens": 1980880} {"current_steps": 3005, "total_steps": 33920, "loss": 0.5336, "lr": 8.856132075471698e-06, "epoch": 1.771816037735849, "percentage": 8.86, "elapsed_time": "0:05:21", "remaining_time": "0:55:02", "throughput": 6178.47, "total_tokens": 1983440} {"current_steps": 3010, "total_steps": 33920, "loss": 0.4548, "lr": 8.870872641509435e-06, "epoch": 1.7747641509433962, "percentage": 8.87, "elapsed_time": "0:05:21", "remaining_time": "0:55:02", "throughput": 6179.02, "total_tokens": 1986960} {"current_steps": 3015, "total_steps": 33920, "loss": 0.5591, "lr": 8.88561320754717e-06, "epoch": 1.7777122641509435, "percentage": 8.89, "elapsed_time": "0:05:22", "remaining_time": "0:55:01", "throughput": 6179.13, "total_tokens": 1989968} {"current_steps": 3020, "total_steps": 33920, "loss": 0.733, "lr": 8.900353773584906e-06, "epoch": 1.7806603773584906, "percentage": 8.9, "elapsed_time": "0:05:22", "remaining_time": "0:55:00", "throughput": 6178.42, "total_tokens": 1992912} {"current_steps": 3025, "total_steps": 33920, "loss": 0.5463, "lr": 8.915094339622642e-06, "epoch": 1.7836084905660377, "percentage": 8.92, "elapsed_time": "0:05:23", "remaining_time": "0:54:59", "throughput": 6178.19, "total_tokens": 1995856} {"current_steps": 3030, "total_steps": 33920, "loss": 0.5287, "lr": 8.929834905660379e-06, "epoch": 1.786556603773585, "percentage": 8.93, "elapsed_time": "0:05:23", "remaining_time": "0:54:58", "throughput": 6178.16, "total_tokens": 1998928} {"current_steps": 3035, "total_steps": 33920, "loss": 0.6037, "lr": 8.944575471698114e-06, "epoch": 1.7895047169811322, "percentage": 8.95, "elapsed_time": "0:05:24", "remaining_time": "0:54:57", "throughput": 6177.9, "total_tokens": 2001776} {"current_steps": 3040, "total_steps": 33920, "loss": 0.6202, "lr": 8.959316037735851e-06, "epoch": 1.7924528301886793, "percentage": 8.96, "elapsed_time": "0:05:24", "remaining_time": "0:54:56", "throughput": 6177.9, "total_tokens": 2005104} {"current_steps": 3045, "total_steps": 33920, "loss": 0.4392, "lr": 8.974056603773586e-06, "epoch": 1.7954009433962264, "percentage": 8.98, "elapsed_time": "0:05:25", "remaining_time": "0:54:57", "throughput": 6179.12, "total_tokens": 2009296} {"current_steps": 3050, "total_steps": 33920, "loss": 0.5464, "lr": 8.988797169811322e-06, "epoch": 1.7983490566037736, "percentage": 8.99, "elapsed_time": "0:05:25", "remaining_time": "0:54:57", "throughput": 6180.36, "total_tokens": 2013840} {"current_steps": 3055, "total_steps": 33920, "loss": 0.4425, "lr": 9.003537735849057e-06, "epoch": 1.8012971698113207, "percentage": 9.01, "elapsed_time": "0:05:26", "remaining_time": "0:54:57", "throughput": 6180.61, "total_tokens": 2017392} {"current_steps": 3060, "total_steps": 33920, "loss": 0.6254, "lr": 9.018278301886794e-06, "epoch": 1.8042452830188678, "percentage": 9.02, "elapsed_time": "0:05:26", "remaining_time": "0:54:56", "throughput": 6180.77, "total_tokens": 2020368} {"current_steps": 3065, "total_steps": 33920, "loss": 0.5859, "lr": 9.03301886792453e-06, "epoch": 1.807193396226415, "percentage": 9.04, "elapsed_time": "0:05:27", "remaining_time": "0:54:56", "throughput": 6180.67, "total_tokens": 2023760} {"current_steps": 3070, "total_steps": 33920, "loss": 0.4831, "lr": 9.047759433962265e-06, "epoch": 1.8101415094339623, "percentage": 9.05, "elapsed_time": "0:05:27", "remaining_time": "0:54:54", "throughput": 6179.79, "total_tokens": 2026288} {"current_steps": 3075, "total_steps": 33920, "loss": 0.5683, "lr": 9.0625e-06, "epoch": 1.8130896226415094, "percentage": 9.07, "elapsed_time": "0:05:28", "remaining_time": "0:54:53", "throughput": 6178.49, "total_tokens": 2028720} {"current_steps": 3080, "total_steps": 33920, "loss": 0.3864, "lr": 9.077240566037735e-06, "epoch": 1.8160377358490565, "percentage": 9.08, "elapsed_time": "0:05:29", "remaining_time": "0:54:55", "throughput": 6179.16, "total_tokens": 2033520} {"current_steps": 3085, "total_steps": 33920, "loss": 0.5524, "lr": 9.091981132075472e-06, "epoch": 1.8189858490566038, "percentage": 9.09, "elapsed_time": "0:05:29", "remaining_time": "0:54:56", "throughput": 6180.75, "total_tokens": 2038320} {"current_steps": 3090, "total_steps": 33920, "loss": 0.5314, "lr": 9.106721698113208e-06, "epoch": 1.821933962264151, "percentage": 9.11, "elapsed_time": "0:05:30", "remaining_time": "0:54:54", "throughput": 6180.24, "total_tokens": 2041008} {"current_steps": 3095, "total_steps": 33920, "loss": 0.5212, "lr": 9.121462264150945e-06, "epoch": 1.8248820754716981, "percentage": 9.12, "elapsed_time": "0:05:30", "remaining_time": "0:54:54", "throughput": 6181.0, "total_tokens": 2044592} {"current_steps": 3100, "total_steps": 33920, "loss": 0.4562, "lr": 9.13620283018868e-06, "epoch": 1.8278301886792452, "percentage": 9.14, "elapsed_time": "0:05:31", "remaining_time": "0:54:53", "throughput": 6181.49, "total_tokens": 2047888} {"current_steps": 3105, "total_steps": 33920, "loss": 0.6087, "lr": 9.150943396226416e-06, "epoch": 1.8307783018867925, "percentage": 9.15, "elapsed_time": "0:05:31", "remaining_time": "0:54:52", "throughput": 6181.21, "total_tokens": 2050928} {"current_steps": 3110, "total_steps": 33920, "loss": 0.4487, "lr": 9.165683962264151e-06, "epoch": 1.8337264150943398, "percentage": 9.17, "elapsed_time": "0:05:32", "remaining_time": "0:54:52", "throughput": 6182.06, "total_tokens": 2054416} {"current_steps": 3115, "total_steps": 33920, "loss": 0.5342, "lr": 9.180424528301888e-06, "epoch": 1.8366745283018868, "percentage": 9.18, "elapsed_time": "0:05:32", "remaining_time": "0:54:51", "throughput": 6182.34, "total_tokens": 2057552} {"current_steps": 3120, "total_steps": 33920, "loss": 0.5337, "lr": 9.195165094339623e-06, "epoch": 1.8396226415094339, "percentage": 9.2, "elapsed_time": "0:05:33", "remaining_time": "0:54:50", "throughput": 6180.86, "total_tokens": 2059920} {"current_steps": 3125, "total_steps": 33920, "loss": 0.4585, "lr": 9.20990566037736e-06, "epoch": 1.8425707547169812, "percentage": 9.21, "elapsed_time": "0:05:33", "remaining_time": "0:54:50", "throughput": 6181.57, "total_tokens": 2063792} {"current_steps": 3130, "total_steps": 33920, "loss": 0.5091, "lr": 9.224646226415096e-06, "epoch": 1.8455188679245285, "percentage": 9.23, "elapsed_time": "0:05:34", "remaining_time": "0:54:48", "throughput": 6181.08, "total_tokens": 2066512} {"current_steps": 3135, "total_steps": 33920, "loss": 0.5233, "lr": 9.239386792452831e-06, "epoch": 1.8484669811320755, "percentage": 9.24, "elapsed_time": "0:05:34", "remaining_time": "0:54:48", "throughput": 6180.93, "total_tokens": 2069904} {"current_steps": 3140, "total_steps": 33920, "loss": 0.5258, "lr": 9.254127358490566e-06, "epoch": 1.8514150943396226, "percentage": 9.26, "elapsed_time": "0:05:35", "remaining_time": "0:54:47", "throughput": 6180.72, "total_tokens": 2073008} {"current_steps": 3145, "total_steps": 33920, "loss": 0.4825, "lr": 9.268867924528303e-06, "epoch": 1.8543632075471699, "percentage": 9.27, "elapsed_time": "0:05:35", "remaining_time": "0:54:46", "throughput": 6179.97, "total_tokens": 2075600} {"current_steps": 3150, "total_steps": 33920, "loss": 0.4515, "lr": 9.283608490566039e-06, "epoch": 1.857311320754717, "percentage": 9.29, "elapsed_time": "0:05:36", "remaining_time": "0:54:45", "throughput": 6179.79, "total_tokens": 2078800} {"current_steps": 3155, "total_steps": 33920, "loss": 0.565, "lr": 9.298349056603774e-06, "epoch": 1.860259433962264, "percentage": 9.3, "elapsed_time": "0:05:36", "remaining_time": "0:54:44", "throughput": 6180.17, "total_tokens": 2081936} {"current_steps": 3160, "total_steps": 33920, "loss": 0.5596, "lr": 9.31308962264151e-06, "epoch": 1.8632075471698113, "percentage": 9.32, "elapsed_time": "0:05:37", "remaining_time": "0:54:43", "throughput": 6179.41, "total_tokens": 2084592} {"current_steps": 3165, "total_steps": 33920, "loss": 0.4971, "lr": 9.327830188679245e-06, "epoch": 1.8661556603773586, "percentage": 9.33, "elapsed_time": "0:05:37", "remaining_time": "0:54:43", "throughput": 6179.89, "total_tokens": 2088496} {"current_steps": 3170, "total_steps": 33920, "loss": 0.5197, "lr": 9.342570754716982e-06, "epoch": 1.8691037735849056, "percentage": 9.35, "elapsed_time": "0:05:38", "remaining_time": "0:54:42", "throughput": 6179.75, "total_tokens": 2091472} {"current_steps": 3175, "total_steps": 33920, "loss": 0.579, "lr": 9.357311320754717e-06, "epoch": 1.8720518867924527, "percentage": 9.36, "elapsed_time": "0:05:38", "remaining_time": "0:54:41", "throughput": 6179.02, "total_tokens": 2094224} {"current_steps": 3180, "total_steps": 33920, "loss": 0.596, "lr": 9.372051886792454e-06, "epoch": 1.875, "percentage": 9.38, "elapsed_time": "0:05:39", "remaining_time": "0:54:42", "throughput": 6179.54, "total_tokens": 2098256} {"current_steps": 3185, "total_steps": 33920, "loss": 0.5862, "lr": 9.38679245283019e-06, "epoch": 1.8779481132075473, "percentage": 9.39, "elapsed_time": "0:05:40", "remaining_time": "0:54:41", "throughput": 6179.94, "total_tokens": 2101584} {"current_steps": 3190, "total_steps": 33920, "loss": 0.5773, "lr": 9.401533018867925e-06, "epoch": 1.8808962264150944, "percentage": 9.4, "elapsed_time": "0:05:40", "remaining_time": "0:54:40", "throughput": 6180.14, "total_tokens": 2104592} {"current_steps": 3195, "total_steps": 33920, "loss": 0.4231, "lr": 9.41627358490566e-06, "epoch": 1.8838443396226414, "percentage": 9.42, "elapsed_time": "0:05:41", "remaining_time": "0:54:40", "throughput": 6180.46, "total_tokens": 2108144} {"current_steps": 3200, "total_steps": 33920, "loss": 0.3617, "lr": 9.431014150943397e-06, "epoch": 1.8867924528301887, "percentage": 9.43, "elapsed_time": "0:05:41", "remaining_time": "0:54:40", "throughput": 6181.37, "total_tokens": 2112304} {"current_steps": 3205, "total_steps": 33920, "loss": 0.5277, "lr": 9.445754716981133e-06, "epoch": 1.889740566037736, "percentage": 9.45, "elapsed_time": "0:05:42", "remaining_time": "0:54:39", "throughput": 6181.24, "total_tokens": 2115312} {"current_steps": 3210, "total_steps": 33920, "loss": 0.4618, "lr": 9.46049528301887e-06, "epoch": 1.892688679245283, "percentage": 9.46, "elapsed_time": "0:05:42", "remaining_time": "0:54:38", "throughput": 6181.3, "total_tokens": 2118576} {"current_steps": 3215, "total_steps": 33920, "loss": 0.7152, "lr": 9.475235849056605e-06, "epoch": 1.8956367924528301, "percentage": 9.48, "elapsed_time": "0:05:43", "remaining_time": "0:54:38", "throughput": 6182.19, "total_tokens": 2122416} {"current_steps": 3220, "total_steps": 33920, "loss": 0.4489, "lr": 9.48997641509434e-06, "epoch": 1.8985849056603774, "percentage": 9.49, "elapsed_time": "0:05:43", "remaining_time": "0:54:37", "throughput": 6181.92, "total_tokens": 2125136} {"current_steps": 3225, "total_steps": 33920, "loss": 0.5092, "lr": 9.504716981132076e-06, "epoch": 1.9015330188679245, "percentage": 9.51, "elapsed_time": "0:05:44", "remaining_time": "0:54:36", "throughput": 6181.87, "total_tokens": 2128112} {"current_steps": 3230, "total_steps": 33920, "loss": 0.6295, "lr": 9.519457547169813e-06, "epoch": 1.9044811320754715, "percentage": 9.52, "elapsed_time": "0:05:44", "remaining_time": "0:54:36", "throughput": 6181.95, "total_tokens": 2131728} {"current_steps": 3235, "total_steps": 33920, "loss": 0.3722, "lr": 9.534198113207548e-06, "epoch": 1.9074292452830188, "percentage": 9.54, "elapsed_time": "0:05:45", "remaining_time": "0:54:35", "throughput": 6182.11, "total_tokens": 2135024} {"current_steps": 3240, "total_steps": 33920, "loss": 0.5673, "lr": 9.548938679245285e-06, "epoch": 1.9103773584905661, "percentage": 9.55, "elapsed_time": "0:05:45", "remaining_time": "0:54:35", "throughput": 6182.08, "total_tokens": 2138448} {"current_steps": 3245, "total_steps": 33920, "loss": 0.5578, "lr": 9.56367924528302e-06, "epoch": 1.9133254716981132, "percentage": 9.57, "elapsed_time": "0:05:46", "remaining_time": "0:54:34", "throughput": 6182.83, "total_tokens": 2142032} {"current_steps": 3250, "total_steps": 33920, "loss": 0.5426, "lr": 9.578419811320756e-06, "epoch": 1.9162735849056602, "percentage": 9.58, "elapsed_time": "0:05:46", "remaining_time": "0:54:34", "throughput": 6181.85, "total_tokens": 2145008} {"current_steps": 3255, "total_steps": 33920, "loss": 0.4345, "lr": 9.593160377358491e-06, "epoch": 1.9192216981132075, "percentage": 9.6, "elapsed_time": "0:05:47", "remaining_time": "0:54:33", "throughput": 6180.29, "total_tokens": 2147568} {"current_steps": 3260, "total_steps": 33920, "loss": 0.6536, "lr": 9.607900943396226e-06, "epoch": 1.9221698113207548, "percentage": 9.61, "elapsed_time": "0:05:47", "remaining_time": "0:54:32", "throughput": 6180.21, "total_tokens": 2150608} {"current_steps": 3265, "total_steps": 33920, "loss": 0.5344, "lr": 9.622641509433963e-06, "epoch": 1.9251179245283019, "percentage": 9.63, "elapsed_time": "0:05:48", "remaining_time": "0:54:32", "throughput": 6180.81, "total_tokens": 2154192} {"current_steps": 3270, "total_steps": 33920, "loss": 0.4811, "lr": 9.637382075471699e-06, "epoch": 1.928066037735849, "percentage": 9.64, "elapsed_time": "0:05:49", "remaining_time": "0:54:31", "throughput": 6179.76, "total_tokens": 2156976} {"current_steps": 3275, "total_steps": 33920, "loss": 0.4355, "lr": 9.652122641509434e-06, "epoch": 1.9310141509433962, "percentage": 9.66, "elapsed_time": "0:05:49", "remaining_time": "0:54:31", "throughput": 6179.85, "total_tokens": 2160432} {"current_steps": 3280, "total_steps": 33920, "loss": 0.4871, "lr": 9.66686320754717e-06, "epoch": 1.9339622641509435, "percentage": 9.67, "elapsed_time": "0:05:50", "remaining_time": "0:54:30", "throughput": 6179.61, "total_tokens": 2163408} {"current_steps": 3285, "total_steps": 33920, "loss": 0.4767, "lr": 9.681603773584907e-06, "epoch": 1.9369103773584906, "percentage": 9.68, "elapsed_time": "0:05:50", "remaining_time": "0:54:29", "throughput": 6179.6, "total_tokens": 2166768} {"current_steps": 3290, "total_steps": 33920, "loss": 0.4676, "lr": 9.696344339622642e-06, "epoch": 1.9398584905660377, "percentage": 9.7, "elapsed_time": "0:05:51", "remaining_time": "0:54:28", "throughput": 6179.4, "total_tokens": 2169456} {"current_steps": 3295, "total_steps": 33920, "loss": 0.4803, "lr": 9.711084905660379e-06, "epoch": 1.942806603773585, "percentage": 9.71, "elapsed_time": "0:05:51", "remaining_time": "0:54:29", "throughput": 6181.03, "total_tokens": 2174352} {"current_steps": 3300, "total_steps": 33920, "loss": 0.5593, "lr": 9.725825471698114e-06, "epoch": 1.9457547169811322, "percentage": 9.73, "elapsed_time": "0:05:52", "remaining_time": "0:54:28", "throughput": 6181.24, "total_tokens": 2177584} {"current_steps": 3305, "total_steps": 33920, "loss": 0.5101, "lr": 9.74056603773585e-06, "epoch": 1.9487028301886793, "percentage": 9.74, "elapsed_time": "0:05:52", "remaining_time": "0:54:27", "throughput": 6180.79, "total_tokens": 2180528} {"current_steps": 3310, "total_steps": 33920, "loss": 0.5028, "lr": 9.755306603773585e-06, "epoch": 1.9516509433962264, "percentage": 9.76, "elapsed_time": "0:05:53", "remaining_time": "0:54:27", "throughput": 6181.0, "total_tokens": 2183888} {"current_steps": 3315, "total_steps": 33920, "loss": 0.5164, "lr": 9.770047169811322e-06, "epoch": 1.9545990566037736, "percentage": 9.77, "elapsed_time": "0:05:53", "remaining_time": "0:54:27", "throughput": 6181.21, "total_tokens": 2187536} {"current_steps": 3320, "total_steps": 33920, "loss": 0.5586, "lr": 9.784787735849057e-06, "epoch": 1.9575471698113207, "percentage": 9.79, "elapsed_time": "0:05:54", "remaining_time": "0:54:26", "throughput": 6181.09, "total_tokens": 2190864} {"current_steps": 3325, "total_steps": 33920, "loss": 0.4895, "lr": 9.799528301886794e-06, "epoch": 1.9604952830188678, "percentage": 9.8, "elapsed_time": "0:05:54", "remaining_time": "0:54:26", "throughput": 6180.82, "total_tokens": 2193872} {"current_steps": 3330, "total_steps": 33920, "loss": 0.4372, "lr": 9.81426886792453e-06, "epoch": 1.963443396226415, "percentage": 9.82, "elapsed_time": "0:05:55", "remaining_time": "0:54:25", "throughput": 6181.65, "total_tokens": 2197744} {"current_steps": 3335, "total_steps": 33920, "loss": 0.4577, "lr": 9.829009433962265e-06, "epoch": 1.9663915094339623, "percentage": 9.83, "elapsed_time": "0:05:56", "remaining_time": "0:54:25", "throughput": 6182.36, "total_tokens": 2201648} {"current_steps": 3340, "total_steps": 33920, "loss": 0.5065, "lr": 9.84375e-06, "epoch": 1.9693396226415094, "percentage": 9.85, "elapsed_time": "0:05:56", "remaining_time": "0:54:26", "throughput": 6183.3, "total_tokens": 2205808} {"current_steps": 3345, "total_steps": 33920, "loss": 0.6834, "lr": 9.858490566037736e-06, "epoch": 1.9722877358490565, "percentage": 9.86, "elapsed_time": "0:05:57", "remaining_time": "0:54:25", "throughput": 6182.97, "total_tokens": 2208656} {"current_steps": 3350, "total_steps": 33920, "loss": 0.563, "lr": 9.873231132075473e-06, "epoch": 1.9752358490566038, "percentage": 9.88, "elapsed_time": "0:05:57", "remaining_time": "0:54:24", "throughput": 6182.69, "total_tokens": 2212048} {"current_steps": 3355, "total_steps": 33920, "loss": 0.5711, "lr": 9.887971698113208e-06, "epoch": 1.978183962264151, "percentage": 9.89, "elapsed_time": "0:05:58", "remaining_time": "0:54:24", "throughput": 6183.29, "total_tokens": 2215344} {"current_steps": 3360, "total_steps": 33920, "loss": 0.3759, "lr": 9.902712264150945e-06, "epoch": 1.9811320754716981, "percentage": 9.91, "elapsed_time": "0:05:58", "remaining_time": "0:54:24", "throughput": 6184.03, "total_tokens": 2219504} {"current_steps": 3365, "total_steps": 33920, "loss": 0.4917, "lr": 9.917452830188679e-06, "epoch": 1.9840801886792452, "percentage": 9.92, "elapsed_time": "0:05:59", "remaining_time": "0:54:23", "throughput": 6183.84, "total_tokens": 2222352} {"current_steps": 3370, "total_steps": 33920, "loss": 0.3843, "lr": 9.932193396226416e-06, "epoch": 1.9870283018867925, "percentage": 9.94, "elapsed_time": "0:05:59", "remaining_time": "0:54:22", "throughput": 6184.02, "total_tokens": 2225520} {"current_steps": 3375, "total_steps": 33920, "loss": 0.6343, "lr": 9.946933962264151e-06, "epoch": 1.9899764150943398, "percentage": 9.95, "elapsed_time": "0:06:00", "remaining_time": "0:54:21", "throughput": 6183.78, "total_tokens": 2228528} {"current_steps": 3380, "total_steps": 33920, "loss": 0.4117, "lr": 9.961674528301888e-06, "epoch": 1.9929245283018868, "percentage": 9.96, "elapsed_time": "0:06:01", "remaining_time": "0:54:22", "throughput": 6184.66, "total_tokens": 2233136} {"current_steps": 3385, "total_steps": 33920, "loss": 0.4315, "lr": 9.976415094339624e-06, "epoch": 1.9958726415094339, "percentage": 9.98, "elapsed_time": "0:06:01", "remaining_time": "0:54:21", "throughput": 6183.98, "total_tokens": 2235952} {"current_steps": 3390, "total_steps": 33920, "loss": 0.39, "lr": 9.991155660377359e-06, "epoch": 1.9988207547169812, "percentage": 9.99, "elapsed_time": "0:06:02", "remaining_time": "0:54:21", "throughput": 6184.2, "total_tokens": 2239280} {"current_steps": 3392, "total_steps": 33920, "eval_loss": 0.5126349329948425, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:06:20", "remaining_time": "0:57:07", "throughput": 5883.78, "total_tokens": 2240840} {"current_steps": 3395, "total_steps": 33920, "loss": 0.5249, "lr": 9.999999894098275e-06, "epoch": 2.0017688679245285, "percentage": 10.01, "elapsed_time": "0:06:25", "remaining_time": "0:57:43", "throughput": 5822.54, "total_tokens": 2242888} {"current_steps": 3400, "total_steps": 33920, "loss": 0.5551, "lr": 9.99999870270391e-06, "epoch": 2.0047169811320753, "percentage": 10.02, "elapsed_time": "0:06:25", "remaining_time": "0:57:42", "throughput": 5822.22, "total_tokens": 2245768} {"current_steps": 3405, "total_steps": 33920, "loss": 0.3755, "lr": 9.999996187538341e-06, "epoch": 2.0076650943396226, "percentage": 10.04, "elapsed_time": "0:06:26", "remaining_time": "0:57:41", "throughput": 5821.23, "total_tokens": 2248360} {"current_steps": 3410, "total_steps": 33920, "loss": 0.5116, "lr": 9.999992348602233e-06, "epoch": 2.01061320754717, "percentage": 10.05, "elapsed_time": "0:06:26", "remaining_time": "0:57:40", "throughput": 5820.93, "total_tokens": 2251432} {"current_steps": 3415, "total_steps": 33920, "loss": 0.5466, "lr": 9.999987185896598e-06, "epoch": 2.013561320754717, "percentage": 10.07, "elapsed_time": "0:06:27", "remaining_time": "0:57:39", "throughput": 5821.19, "total_tokens": 2254792} {"current_steps": 3420, "total_steps": 33920, "loss": 0.6024, "lr": 9.99998069942281e-06, "epoch": 2.016509433962264, "percentage": 10.08, "elapsed_time": "0:06:27", "remaining_time": "0:57:38", "throughput": 5821.8, "total_tokens": 2257928} {"current_steps": 3425, "total_steps": 33920, "loss": 0.5609, "lr": 9.999972889182583e-06, "epoch": 2.0194575471698113, "percentage": 10.1, "elapsed_time": "0:06:28", "remaining_time": "0:57:37", "throughput": 5821.17, "total_tokens": 2260488} {"current_steps": 3430, "total_steps": 33920, "loss": 0.4909, "lr": 9.999963755177984e-06, "epoch": 2.0224056603773586, "percentage": 10.11, "elapsed_time": "0:06:28", "remaining_time": "0:57:37", "throughput": 5820.96, "total_tokens": 2263784} {"current_steps": 3435, "total_steps": 33920, "loss": 0.4853, "lr": 9.999953297411434e-06, "epoch": 2.025353773584906, "percentage": 10.13, "elapsed_time": "0:06:29", "remaining_time": "0:57:35", "throughput": 5821.18, "total_tokens": 2266792} {"current_steps": 3440, "total_steps": 33920, "loss": 0.3852, "lr": 9.999941515885699e-06, "epoch": 2.0283018867924527, "percentage": 10.14, "elapsed_time": "0:06:29", "remaining_time": "0:57:34", "throughput": 5821.56, "total_tokens": 2269832} {"current_steps": 3445, "total_steps": 33920, "loss": 0.4318, "lr": 9.999928410603897e-06, "epoch": 2.03125, "percentage": 10.16, "elapsed_time": "0:06:30", "remaining_time": "0:57:35", "throughput": 5821.84, "total_tokens": 2273928} {"current_steps": 3450, "total_steps": 33920, "loss": 0.5244, "lr": 9.999913981569502e-06, "epoch": 2.0341981132075473, "percentage": 10.17, "elapsed_time": "0:06:31", "remaining_time": "0:57:33", "throughput": 5821.2, "total_tokens": 2276552} {"current_steps": 3455, "total_steps": 33920, "loss": 0.5453, "lr": 9.999898228786332e-06, "epoch": 2.037146226415094, "percentage": 10.19, "elapsed_time": "0:06:31", "remaining_time": "0:57:32", "throughput": 5820.4, "total_tokens": 2279272} {"current_steps": 3460, "total_steps": 33920, "loss": 0.5779, "lr": 9.999881152258557e-06, "epoch": 2.0400943396226414, "percentage": 10.2, "elapsed_time": "0:06:32", "remaining_time": "0:57:31", "throughput": 5820.38, "total_tokens": 2282216} {"current_steps": 3465, "total_steps": 33920, "loss": 0.5276, "lr": 9.999862751990697e-06, "epoch": 2.0430424528301887, "percentage": 10.22, "elapsed_time": "0:06:32", "remaining_time": "0:57:31", "throughput": 5820.1, "total_tokens": 2285480} {"current_steps": 3470, "total_steps": 33920, "loss": 0.5144, "lr": 9.999843027987628e-06, "epoch": 2.045990566037736, "percentage": 10.23, "elapsed_time": "0:06:33", "remaining_time": "0:57:30", "throughput": 5820.94, "total_tokens": 2289160} {"current_steps": 3475, "total_steps": 33920, "loss": 0.5571, "lr": 9.999821980254567e-06, "epoch": 2.048938679245283, "percentage": 10.24, "elapsed_time": "0:06:33", "remaining_time": "0:57:30", "throughput": 5821.22, "total_tokens": 2292520} {"current_steps": 3480, "total_steps": 33920, "loss": 0.3955, "lr": 9.99979960879709e-06, "epoch": 2.05188679245283, "percentage": 10.26, "elapsed_time": "0:06:34", "remaining_time": "0:57:28", "throughput": 5820.91, "total_tokens": 2295144} {"current_steps": 3485, "total_steps": 33920, "loss": 0.6016, "lr": 9.99977591362112e-06, "epoch": 2.0548349056603774, "percentage": 10.27, "elapsed_time": "0:06:34", "remaining_time": "0:57:27", "throughput": 5821.06, "total_tokens": 2297992} {"current_steps": 3490, "total_steps": 33920, "loss": 0.3958, "lr": 9.999750894732927e-06, "epoch": 2.0577830188679247, "percentage": 10.29, "elapsed_time": "0:06:35", "remaining_time": "0:57:26", "throughput": 5822.05, "total_tokens": 2301640} {"current_steps": 3495, "total_steps": 33920, "loss": 0.4512, "lr": 9.999724552139136e-06, "epoch": 2.0607311320754715, "percentage": 10.3, "elapsed_time": "0:06:35", "remaining_time": "0:57:25", "throughput": 5821.92, "total_tokens": 2304456} {"current_steps": 3500, "total_steps": 33920, "loss": 0.5275, "lr": 9.999696885846724e-06, "epoch": 2.063679245283019, "percentage": 10.32, "elapsed_time": "0:06:36", "remaining_time": "0:57:24", "throughput": 5821.32, "total_tokens": 2307304} {"current_steps": 3505, "total_steps": 33920, "loss": 0.5665, "lr": 9.999667895863012e-06, "epoch": 2.066627358490566, "percentage": 10.33, "elapsed_time": "0:06:36", "remaining_time": "0:57:24", "throughput": 5822.03, "total_tokens": 2310920} {"current_steps": 3510, "total_steps": 33920, "loss": 0.4199, "lr": 9.99963758219568e-06, "epoch": 2.0695754716981134, "percentage": 10.35, "elapsed_time": "0:06:37", "remaining_time": "0:57:24", "throughput": 5823.55, "total_tokens": 2315048} {"current_steps": 3515, "total_steps": 33920, "loss": 0.4154, "lr": 9.999605944852749e-06, "epoch": 2.0725235849056602, "percentage": 10.36, "elapsed_time": "0:06:38", "remaining_time": "0:57:23", "throughput": 5823.78, "total_tokens": 2318056} {"current_steps": 3520, "total_steps": 33920, "loss": 0.4955, "lr": 9.999572983842599e-06, "epoch": 2.0754716981132075, "percentage": 10.38, "elapsed_time": "0:06:38", "remaining_time": "0:57:21", "throughput": 5823.59, "total_tokens": 2320936} {"current_steps": 3525, "total_steps": 33920, "loss": 0.5123, "lr": 9.999538699173951e-06, "epoch": 2.078419811320755, "percentage": 10.39, "elapsed_time": "0:06:39", "remaining_time": "0:57:21", "throughput": 5824.09, "total_tokens": 2324424} {"current_steps": 3530, "total_steps": 33920, "loss": 0.592, "lr": 9.99950309085589e-06, "epoch": 2.081367924528302, "percentage": 10.41, "elapsed_time": "0:06:39", "remaining_time": "0:57:21", "throughput": 5824.75, "total_tokens": 2328232} {"current_steps": 3535, "total_steps": 33920, "loss": 0.5512, "lr": 9.999466158897835e-06, "epoch": 2.084316037735849, "percentage": 10.42, "elapsed_time": "0:06:40", "remaining_time": "0:57:20", "throughput": 5825.02, "total_tokens": 2331336} {"current_steps": 3540, "total_steps": 33920, "loss": 0.6292, "lr": 9.999427903309569e-06, "epoch": 2.0872641509433962, "percentage": 10.44, "elapsed_time": "0:06:40", "remaining_time": "0:57:19", "throughput": 5825.37, "total_tokens": 2334632} {"current_steps": 3545, "total_steps": 33920, "loss": 0.6109, "lr": 9.99938832410122e-06, "epoch": 2.0902122641509435, "percentage": 10.45, "elapsed_time": "0:06:41", "remaining_time": "0:57:18", "throughput": 5823.89, "total_tokens": 2337032} {"current_steps": 3550, "total_steps": 33920, "loss": 0.5749, "lr": 9.999347421283267e-06, "epoch": 2.0931603773584904, "percentage": 10.47, "elapsed_time": "0:06:41", "remaining_time": "0:57:17", "throughput": 5823.8, "total_tokens": 2339880} {"current_steps": 3555, "total_steps": 33920, "loss": 0.5289, "lr": 9.999305194866538e-06, "epoch": 2.0961084905660377, "percentage": 10.48, "elapsed_time": "0:06:42", "remaining_time": "0:57:17", "throughput": 5825.43, "total_tokens": 2344168} {"current_steps": 3560, "total_steps": 33920, "loss": 0.6447, "lr": 9.99926164486221e-06, "epoch": 2.099056603773585, "percentage": 10.5, "elapsed_time": "0:06:42", "remaining_time": "0:57:16", "throughput": 5825.78, "total_tokens": 2347336} {"current_steps": 3565, "total_steps": 33920, "loss": 0.5079, "lr": 9.99921677128182e-06, "epoch": 2.1020047169811322, "percentage": 10.51, "elapsed_time": "0:06:43", "remaining_time": "0:57:15", "throughput": 5825.89, "total_tokens": 2350376} {"current_steps": 3570, "total_steps": 33920, "loss": 0.4816, "lr": 9.99917057413724e-06, "epoch": 2.104952830188679, "percentage": 10.52, "elapsed_time": "0:06:43", "remaining_time": "0:57:14", "throughput": 5826.47, "total_tokens": 2353672} {"current_steps": 3575, "total_steps": 33920, "loss": 0.4366, "lr": 9.99912305344071e-06, "epoch": 2.1079009433962264, "percentage": 10.54, "elapsed_time": "0:06:44", "remaining_time": "0:57:13", "throughput": 5826.61, "total_tokens": 2356968} {"current_steps": 3580, "total_steps": 33920, "loss": 0.5367, "lr": 9.999074209204803e-06, "epoch": 2.1108490566037736, "percentage": 10.55, "elapsed_time": "0:06:45", "remaining_time": "0:57:14", "throughput": 5827.69, "total_tokens": 2361640} {"current_steps": 3585, "total_steps": 33920, "loss": 0.4306, "lr": 9.999024041442455e-06, "epoch": 2.113797169811321, "percentage": 10.57, "elapsed_time": "0:06:45", "remaining_time": "0:57:14", "throughput": 5828.74, "total_tokens": 2365736} {"current_steps": 3590, "total_steps": 33920, "loss": 0.5415, "lr": 9.998972550166948e-06, "epoch": 2.1167452830188678, "percentage": 10.58, "elapsed_time": "0:06:46", "remaining_time": "0:57:14", "throughput": 5830.31, "total_tokens": 2369992} {"current_steps": 3595, "total_steps": 33920, "loss": 0.583, "lr": 9.998919735391915e-06, "epoch": 2.119693396226415, "percentage": 10.6, "elapsed_time": "0:06:46", "remaining_time": "0:57:12", "throughput": 5830.08, "total_tokens": 2372712} {"current_steps": 3600, "total_steps": 33920, "loss": 0.5088, "lr": 9.998865597131336e-06, "epoch": 2.1226415094339623, "percentage": 10.61, "elapsed_time": "0:06:47", "remaining_time": "0:57:12", "throughput": 5829.33, "total_tokens": 2375688} {"current_steps": 3605, "total_steps": 33920, "loss": 0.7655, "lr": 9.998810135399545e-06, "epoch": 2.1255896226415096, "percentage": 10.63, "elapsed_time": "0:06:48", "remaining_time": "0:57:12", "throughput": 5829.23, "total_tokens": 2379208} {"current_steps": 3610, "total_steps": 33920, "loss": 0.703, "lr": 9.99875335021123e-06, "epoch": 2.1285377358490565, "percentage": 10.64, "elapsed_time": "0:06:48", "remaining_time": "0:57:11", "throughput": 5829.47, "total_tokens": 2382248} {"current_steps": 3615, "total_steps": 33920, "loss": 0.4949, "lr": 9.998695241581423e-06, "epoch": 2.1314858490566038, "percentage": 10.66, "elapsed_time": "0:06:49", "remaining_time": "0:57:10", "throughput": 5828.22, "total_tokens": 2384680} {"current_steps": 3620, "total_steps": 33920, "loss": 0.5446, "lr": 9.998635809525504e-06, "epoch": 2.134433962264151, "percentage": 10.67, "elapsed_time": "0:06:49", "remaining_time": "0:57:08", "throughput": 5828.44, "total_tokens": 2387720} {"current_steps": 3625, "total_steps": 33920, "loss": 0.419, "lr": 9.998575054059212e-06, "epoch": 2.137382075471698, "percentage": 10.69, "elapsed_time": "0:06:50", "remaining_time": "0:57:08", "throughput": 5828.89, "total_tokens": 2390984} {"current_steps": 3630, "total_steps": 33920, "loss": 0.4044, "lr": 9.998512975198633e-06, "epoch": 2.140330188679245, "percentage": 10.7, "elapsed_time": "0:06:50", "remaining_time": "0:57:07", "throughput": 5828.74, "total_tokens": 2394088} {"current_steps": 3635, "total_steps": 33920, "loss": 0.3272, "lr": 9.998449572960202e-06, "epoch": 2.1432783018867925, "percentage": 10.72, "elapsed_time": "0:06:51", "remaining_time": "0:57:06", "throughput": 5829.3, "total_tokens": 2397448} {"current_steps": 3640, "total_steps": 33920, "loss": 0.4501, "lr": 9.998384847360705e-06, "epoch": 2.1462264150943398, "percentage": 10.73, "elapsed_time": "0:06:51", "remaining_time": "0:57:06", "throughput": 5830.46, "total_tokens": 2401544} {"current_steps": 3645, "total_steps": 33920, "loss": 0.5206, "lr": 9.998318798417276e-06, "epoch": 2.1491745283018866, "percentage": 10.75, "elapsed_time": "0:06:52", "remaining_time": "0:57:06", "throughput": 5831.14, "total_tokens": 2405384} {"current_steps": 3650, "total_steps": 33920, "loss": 0.5323, "lr": 9.998251426147403e-06, "epoch": 2.152122641509434, "percentage": 10.76, "elapsed_time": "0:06:53", "remaining_time": "0:57:06", "throughput": 5832.04, "total_tokens": 2409416} {"current_steps": 3655, "total_steps": 33920, "loss": 0.5034, "lr": 9.998182730568927e-06, "epoch": 2.155070754716981, "percentage": 10.78, "elapsed_time": "0:06:53", "remaining_time": "0:57:05", "throughput": 5830.35, "total_tokens": 2411784} {"current_steps": 3660, "total_steps": 33920, "loss": 0.5168, "lr": 9.998112711700028e-06, "epoch": 2.1580188679245285, "percentage": 10.79, "elapsed_time": "0:06:54", "remaining_time": "0:57:04", "throughput": 5828.42, "total_tokens": 2414056} {"current_steps": 3665, "total_steps": 33920, "loss": 0.5445, "lr": 9.99804136955925e-06, "epoch": 2.1609669811320753, "percentage": 10.8, "elapsed_time": "0:06:54", "remaining_time": "0:57:03", "throughput": 5828.23, "total_tokens": 2417032} {"current_steps": 3670, "total_steps": 33920, "loss": 0.4939, "lr": 9.99796870416548e-06, "epoch": 2.1639150943396226, "percentage": 10.82, "elapsed_time": "0:06:55", "remaining_time": "0:57:03", "throughput": 5828.5, "total_tokens": 2420712} {"current_steps": 3675, "total_steps": 33920, "loss": 0.4394, "lr": 9.997894715537953e-06, "epoch": 2.16686320754717, "percentage": 10.83, "elapsed_time": "0:06:55", "remaining_time": "0:57:02", "throughput": 5828.6, "total_tokens": 2424008} {"current_steps": 3680, "total_steps": 33920, "loss": 0.5627, "lr": 9.997819403696263e-06, "epoch": 2.169811320754717, "percentage": 10.85, "elapsed_time": "0:06:56", "remaining_time": "0:57:01", "throughput": 5827.49, "total_tokens": 2426632} {"current_steps": 3685, "total_steps": 33920, "loss": 0.4672, "lr": 9.997742768660345e-06, "epoch": 2.172759433962264, "percentage": 10.86, "elapsed_time": "0:06:56", "remaining_time": "0:57:01", "throughput": 5827.99, "total_tokens": 2430216} {"current_steps": 3690, "total_steps": 33920, "loss": 0.4919, "lr": 9.99766481045049e-06, "epoch": 2.1757075471698113, "percentage": 10.88, "elapsed_time": "0:06:57", "remaining_time": "0:57:00", "throughput": 5827.78, "total_tokens": 2433064} {"current_steps": 3695, "total_steps": 33920, "loss": 0.4946, "lr": 9.997585529087338e-06, "epoch": 2.1786556603773586, "percentage": 10.89, "elapsed_time": "0:06:58", "remaining_time": "0:56:59", "throughput": 5827.92, "total_tokens": 2436168} {"current_steps": 3700, "total_steps": 33920, "loss": 0.5926, "lr": 9.997504924591878e-06, "epoch": 2.1816037735849054, "percentage": 10.91, "elapsed_time": "0:06:58", "remaining_time": "0:56:58", "throughput": 5827.59, "total_tokens": 2438984} {"current_steps": 3705, "total_steps": 33920, "loss": 0.4573, "lr": 9.99742299698545e-06, "epoch": 2.1845518867924527, "percentage": 10.92, "elapsed_time": "0:06:59", "remaining_time": "0:57:01", "throughput": 5829.62, "total_tokens": 2445704} {"current_steps": 3710, "total_steps": 33920, "loss": 0.6285, "lr": 9.997339746289749e-06, "epoch": 2.1875, "percentage": 10.94, "elapsed_time": "0:07:00", "remaining_time": "0:57:00", "throughput": 5830.42, "total_tokens": 2449416} {"current_steps": 3715, "total_steps": 33920, "loss": 0.9688, "lr": 9.997255172526812e-06, "epoch": 2.1904481132075473, "percentage": 10.95, "elapsed_time": "0:07:00", "remaining_time": "0:56:59", "throughput": 5829.76, "total_tokens": 2451912} {"current_steps": 3720, "total_steps": 33920, "loss": 0.5414, "lr": 9.99716927571903e-06, "epoch": 2.1933962264150946, "percentage": 10.97, "elapsed_time": "0:07:01", "remaining_time": "0:56:58", "throughput": 5828.52, "total_tokens": 2454216} {"current_steps": 3725, "total_steps": 33920, "loss": 0.4932, "lr": 9.997082055889147e-06, "epoch": 2.1963443396226414, "percentage": 10.98, "elapsed_time": "0:07:01", "remaining_time": "0:56:57", "throughput": 5828.82, "total_tokens": 2457192} {"current_steps": 3730, "total_steps": 33920, "loss": 0.5475, "lr": 9.996993513060252e-06, "epoch": 2.1992924528301887, "percentage": 11.0, "elapsed_time": "0:07:02", "remaining_time": "0:56:56", "throughput": 5829.11, "total_tokens": 2460520} {"current_steps": 3735, "total_steps": 33920, "loss": 0.6302, "lr": 9.996903647255789e-06, "epoch": 2.202240566037736, "percentage": 11.01, "elapsed_time": "0:07:02", "remaining_time": "0:56:55", "throughput": 5829.42, "total_tokens": 2463784} {"current_steps": 3740, "total_steps": 33920, "loss": 0.4811, "lr": 9.99681245849955e-06, "epoch": 2.205188679245283, "percentage": 11.03, "elapsed_time": "0:07:03", "remaining_time": "0:56:54", "throughput": 5829.69, "total_tokens": 2466984} {"current_steps": 3745, "total_steps": 33920, "loss": 0.5141, "lr": 9.996719946815679e-06, "epoch": 2.20813679245283, "percentage": 11.04, "elapsed_time": "0:07:03", "remaining_time": "0:56:53", "throughput": 5829.72, "total_tokens": 2469864} {"current_steps": 3750, "total_steps": 33920, "loss": 0.4908, "lr": 9.996626112228665e-06, "epoch": 2.2110849056603774, "percentage": 11.06, "elapsed_time": "0:07:04", "remaining_time": "0:56:52", "throughput": 5829.52, "total_tokens": 2472936} {"current_steps": 3755, "total_steps": 33920, "loss": 0.6395, "lr": 9.996530954763355e-06, "epoch": 2.2140330188679247, "percentage": 11.07, "elapsed_time": "0:07:04", "remaining_time": "0:56:51", "throughput": 5828.84, "total_tokens": 2475688} {"current_steps": 3760, "total_steps": 33920, "loss": 0.5129, "lr": 9.99643447444494e-06, "epoch": 2.2169811320754715, "percentage": 11.08, "elapsed_time": "0:07:05", "remaining_time": "0:56:51", "throughput": 5829.01, "total_tokens": 2479176} {"current_steps": 3765, "total_steps": 33920, "loss": 0.4446, "lr": 9.996336671298965e-06, "epoch": 2.219929245283019, "percentage": 11.1, "elapsed_time": "0:07:05", "remaining_time": "0:56:50", "throughput": 5829.1, "total_tokens": 2482184} {"current_steps": 3770, "total_steps": 33920, "loss": 0.628, "lr": 9.996237545351323e-06, "epoch": 2.222877358490566, "percentage": 11.11, "elapsed_time": "0:07:06", "remaining_time": "0:56:49", "throughput": 5829.12, "total_tokens": 2485320} {"current_steps": 3775, "total_steps": 33920, "loss": 0.4482, "lr": 9.996137096628259e-06, "epoch": 2.2258254716981134, "percentage": 11.13, "elapsed_time": "0:07:07", "remaining_time": "0:56:49", "throughput": 5830.29, "total_tokens": 2489576} {"current_steps": 3780, "total_steps": 33920, "loss": 0.5175, "lr": 9.996035325156366e-06, "epoch": 2.2287735849056602, "percentage": 11.14, "elapsed_time": "0:07:07", "remaining_time": "0:56:48", "throughput": 5830.82, "total_tokens": 2492680} {"current_steps": 3785, "total_steps": 33920, "loss": 0.5551, "lr": 9.995932230962589e-06, "epoch": 2.2317216981132075, "percentage": 11.16, "elapsed_time": "0:07:08", "remaining_time": "0:56:47", "throughput": 5830.5, "total_tokens": 2495656} {"current_steps": 3790, "total_steps": 33920, "loss": 0.5522, "lr": 9.995827814074223e-06, "epoch": 2.234669811320755, "percentage": 11.17, "elapsed_time": "0:07:08", "remaining_time": "0:56:46", "throughput": 5830.47, "total_tokens": 2498536} {"current_steps": 3795, "total_steps": 33920, "loss": 0.4882, "lr": 9.995722074518913e-06, "epoch": 2.237617924528302, "percentage": 11.19, "elapsed_time": "0:07:09", "remaining_time": "0:56:45", "throughput": 5830.35, "total_tokens": 2501320} {"current_steps": 3800, "total_steps": 33920, "loss": 0.4298, "lr": 9.99561501232465e-06, "epoch": 2.240566037735849, "percentage": 11.2, "elapsed_time": "0:07:09", "remaining_time": "0:56:45", "throughput": 5831.5, "total_tokens": 2505352} {"current_steps": 3805, "total_steps": 33920, "loss": 0.5105, "lr": 9.995506627519786e-06, "epoch": 2.2435141509433962, "percentage": 11.22, "elapsed_time": "0:07:10", "remaining_time": "0:56:44", "throughput": 5832.25, "total_tokens": 2509096} {"current_steps": 3810, "total_steps": 33920, "loss": 0.4181, "lr": 9.995396920133012e-06, "epoch": 2.2464622641509435, "percentage": 11.23, "elapsed_time": "0:07:10", "remaining_time": "0:56:44", "throughput": 5832.46, "total_tokens": 2512232} {"current_steps": 3815, "total_steps": 33920, "loss": 0.4455, "lr": 9.995285890193373e-06, "epoch": 2.2494103773584904, "percentage": 11.25, "elapsed_time": "0:07:11", "remaining_time": "0:56:43", "throughput": 5831.81, "total_tokens": 2515208} {"current_steps": 3820, "total_steps": 33920, "loss": 0.6918, "lr": 9.995173537730267e-06, "epoch": 2.2523584905660377, "percentage": 11.26, "elapsed_time": "0:07:11", "remaining_time": "0:56:43", "throughput": 5832.54, "total_tokens": 2519432} {"current_steps": 3825, "total_steps": 33920, "loss": 0.4126, "lr": 9.99505986277344e-06, "epoch": 2.255306603773585, "percentage": 11.28, "elapsed_time": "0:07:12", "remaining_time": "0:56:43", "throughput": 5832.57, "total_tokens": 2522792} {"current_steps": 3830, "total_steps": 33920, "loss": 0.5137, "lr": 9.994944865352986e-06, "epoch": 2.2582547169811322, "percentage": 11.29, "elapsed_time": "0:07:13", "remaining_time": "0:56:42", "throughput": 5832.96, "total_tokens": 2526088} {"current_steps": 3835, "total_steps": 33920, "loss": 0.5356, "lr": 9.994828545499351e-06, "epoch": 2.261202830188679, "percentage": 11.31, "elapsed_time": "0:07:13", "remaining_time": "0:56:41", "throughput": 5832.46, "total_tokens": 2528744} {"current_steps": 3840, "total_steps": 33920, "loss": 0.5342, "lr": 9.994710903243334e-06, "epoch": 2.2641509433962264, "percentage": 11.32, "elapsed_time": "0:07:14", "remaining_time": "0:56:40", "throughput": 5832.31, "total_tokens": 2531720} {"current_steps": 3845, "total_steps": 33920, "loss": 0.4574, "lr": 9.994591938616079e-06, "epoch": 2.2670990566037736, "percentage": 11.34, "elapsed_time": "0:07:14", "remaining_time": "0:56:39", "throughput": 5832.42, "total_tokens": 2534632} {"current_steps": 3850, "total_steps": 33920, "loss": 0.3777, "lr": 9.994471651649082e-06, "epoch": 2.270047169811321, "percentage": 11.35, "elapsed_time": "0:07:15", "remaining_time": "0:56:38", "throughput": 5831.44, "total_tokens": 2537160} {"current_steps": 3855, "total_steps": 33920, "loss": 0.4324, "lr": 9.99435004237419e-06, "epoch": 2.2729952830188678, "percentage": 11.36, "elapsed_time": "0:07:15", "remaining_time": "0:56:37", "throughput": 5832.23, "total_tokens": 2541032} {"current_steps": 3860, "total_steps": 33920, "loss": 0.4278, "lr": 9.9942271108236e-06, "epoch": 2.275943396226415, "percentage": 11.38, "elapsed_time": "0:07:16", "remaining_time": "0:56:37", "throughput": 5832.79, "total_tokens": 2544488} {"current_steps": 3865, "total_steps": 33920, "loss": 0.5759, "lr": 9.994102857029859e-06, "epoch": 2.2788915094339623, "percentage": 11.39, "elapsed_time": "0:07:16", "remaining_time": "0:56:36", "throughput": 5833.71, "total_tokens": 2547944} {"current_steps": 3870, "total_steps": 33920, "loss": 0.572, "lr": 9.993977281025862e-06, "epoch": 2.2818396226415096, "percentage": 11.41, "elapsed_time": "0:07:17", "remaining_time": "0:56:35", "throughput": 5833.7, "total_tokens": 2550824} {"current_steps": 3875, "total_steps": 33920, "loss": 0.5236, "lr": 9.993850382844858e-06, "epoch": 2.2847877358490565, "percentage": 11.42, "elapsed_time": "0:07:17", "remaining_time": "0:56:34", "throughput": 5832.34, "total_tokens": 2553352} {"current_steps": 3880, "total_steps": 33920, "loss": 0.4871, "lr": 9.993722162520443e-06, "epoch": 2.2877358490566038, "percentage": 11.44, "elapsed_time": "0:07:18", "remaining_time": "0:56:33", "throughput": 5832.34, "total_tokens": 2556232} {"current_steps": 3885, "total_steps": 33920, "loss": 0.4901, "lr": 9.993592620086564e-06, "epoch": 2.290683962264151, "percentage": 11.45, "elapsed_time": "0:07:18", "remaining_time": "0:56:32", "throughput": 5830.79, "total_tokens": 2558376} {"current_steps": 3890, "total_steps": 33920, "loss": 0.4081, "lr": 9.993461755577518e-06, "epoch": 2.293632075471698, "percentage": 11.47, "elapsed_time": "0:07:19", "remaining_time": "0:56:32", "throughput": 5832.51, "total_tokens": 2562984} {"current_steps": 3895, "total_steps": 33920, "loss": 0.4689, "lr": 9.99332956902795e-06, "epoch": 2.296580188679245, "percentage": 11.48, "elapsed_time": "0:07:19", "remaining_time": "0:56:31", "throughput": 5830.67, "total_tokens": 2565032} {"current_steps": 3900, "total_steps": 33920, "loss": 0.4981, "lr": 9.993196060472859e-06, "epoch": 2.2995283018867925, "percentage": 11.5, "elapsed_time": "0:07:20", "remaining_time": "0:56:30", "throughput": 5831.88, "total_tokens": 2569064} {"current_steps": 3905, "total_steps": 33920, "loss": 0.3864, "lr": 9.993061229947591e-06, "epoch": 2.3024764150943398, "percentage": 11.51, "elapsed_time": "0:07:21", "remaining_time": "0:56:29", "throughput": 5832.27, "total_tokens": 2572200} {"current_steps": 3910, "total_steps": 33920, "loss": 0.691, "lr": 9.992925077487845e-06, "epoch": 2.3054245283018866, "percentage": 11.53, "elapsed_time": "0:07:21", "remaining_time": "0:56:29", "throughput": 5833.34, "total_tokens": 2576328} {"current_steps": 3915, "total_steps": 33920, "loss": 0.3389, "lr": 9.992787603129666e-06, "epoch": 2.308372641509434, "percentage": 11.54, "elapsed_time": "0:07:22", "remaining_time": "0:56:29", "throughput": 5833.33, "total_tokens": 2579528} {"current_steps": 3920, "total_steps": 33920, "loss": 0.7044, "lr": 9.99264880690945e-06, "epoch": 2.311320754716981, "percentage": 11.56, "elapsed_time": "0:07:22", "remaining_time": "0:56:28", "throughput": 5833.43, "total_tokens": 2582920} {"current_steps": 3925, "total_steps": 33920, "loss": 0.496, "lr": 9.992508688863947e-06, "epoch": 2.3142688679245285, "percentage": 11.57, "elapsed_time": "0:07:23", "remaining_time": "0:56:27", "throughput": 5832.66, "total_tokens": 2585256} {"current_steps": 3930, "total_steps": 33920, "loss": 0.4545, "lr": 9.99236724903025e-06, "epoch": 2.3172169811320753, "percentage": 11.59, "elapsed_time": "0:07:23", "remaining_time": "0:56:26", "throughput": 5832.39, "total_tokens": 2588008} {"current_steps": 3935, "total_steps": 33920, "loss": 0.5569, "lr": 9.992224487445809e-06, "epoch": 2.3201650943396226, "percentage": 11.6, "elapsed_time": "0:07:24", "remaining_time": "0:56:25", "throughput": 5832.11, "total_tokens": 2591304} {"current_steps": 3940, "total_steps": 33920, "loss": 0.5325, "lr": 9.99208040414842e-06, "epoch": 2.32311320754717, "percentage": 11.62, "elapsed_time": "0:07:24", "remaining_time": "0:56:24", "throughput": 5831.92, "total_tokens": 2594312} {"current_steps": 3945, "total_steps": 33920, "loss": 0.5032, "lr": 9.99193499917623e-06, "epoch": 2.326061320754717, "percentage": 11.63, "elapsed_time": "0:07:25", "remaining_time": "0:56:24", "throughput": 5832.82, "total_tokens": 2597832} {"current_steps": 3950, "total_steps": 33920, "loss": 0.4063, "lr": 9.991788272567735e-06, "epoch": 2.329009433962264, "percentage": 11.65, "elapsed_time": "0:07:25", "remaining_time": "0:56:23", "throughput": 5833.76, "total_tokens": 2601704} {"current_steps": 3955, "total_steps": 33920, "loss": 0.388, "lr": 9.991640224361781e-06, "epoch": 2.3319575471698113, "percentage": 11.66, "elapsed_time": "0:07:26", "remaining_time": "0:56:23", "throughput": 5835.22, "total_tokens": 2606184} {"current_steps": 3960, "total_steps": 33920, "loss": 0.4533, "lr": 9.991490854597563e-06, "epoch": 2.3349056603773586, "percentage": 11.67, "elapsed_time": "0:07:27", "remaining_time": "0:56:23", "throughput": 5836.14, "total_tokens": 2609992} {"current_steps": 3965, "total_steps": 33920, "loss": 0.5082, "lr": 9.991340163314632e-06, "epoch": 2.3378537735849054, "percentage": 11.69, "elapsed_time": "0:07:27", "remaining_time": "0:56:22", "throughput": 5835.91, "total_tokens": 2613000} {"current_steps": 3970, "total_steps": 33920, "loss": 0.5198, "lr": 9.991188150552878e-06, "epoch": 2.3408018867924527, "percentage": 11.7, "elapsed_time": "0:07:28", "remaining_time": "0:56:21", "throughput": 5834.51, "total_tokens": 2615400} {"current_steps": 3975, "total_steps": 33920, "loss": 0.7398, "lr": 9.991034816352553e-06, "epoch": 2.34375, "percentage": 11.72, "elapsed_time": "0:07:28", "remaining_time": "0:56:20", "throughput": 5833.86, "total_tokens": 2618056} {"current_steps": 3980, "total_steps": 33920, "loss": 0.5908, "lr": 9.990880160754248e-06, "epoch": 2.3466981132075473, "percentage": 11.73, "elapsed_time": "0:07:29", "remaining_time": "0:56:20", "throughput": 5833.99, "total_tokens": 2621288} {"current_steps": 3985, "total_steps": 33920, "loss": 0.5206, "lr": 9.990724183798914e-06, "epoch": 2.3496462264150946, "percentage": 11.75, "elapsed_time": "0:07:29", "remaining_time": "0:56:19", "throughput": 5834.11, "total_tokens": 2624424} {"current_steps": 3990, "total_steps": 33920, "loss": 0.5438, "lr": 9.990566885527841e-06, "epoch": 2.3525943396226414, "percentage": 11.76, "elapsed_time": "0:07:30", "remaining_time": "0:56:18", "throughput": 5835.32, "total_tokens": 2628360} {"current_steps": 3995, "total_steps": 33920, "loss": 0.45, "lr": 9.99040826598268e-06, "epoch": 2.3555424528301887, "percentage": 11.78, "elapsed_time": "0:07:30", "remaining_time": "0:56:17", "throughput": 5835.62, "total_tokens": 2631432} {"current_steps": 4000, "total_steps": 33920, "loss": 0.4399, "lr": 9.990248325205418e-06, "epoch": 2.358490566037736, "percentage": 11.79, "elapsed_time": "0:07:31", "remaining_time": "0:56:17", "throughput": 5837.01, "total_tokens": 2635528} {"current_steps": 4005, "total_steps": 33920, "loss": 0.5747, "lr": 9.990087063238408e-06, "epoch": 2.361438679245283, "percentage": 11.81, "elapsed_time": "0:07:32", "remaining_time": "0:56:18", "throughput": 5837.26, "total_tokens": 2639880} {"current_steps": 4010, "total_steps": 33920, "loss": 0.4146, "lr": 9.989924480124342e-06, "epoch": 2.36438679245283, "percentage": 11.82, "elapsed_time": "0:07:32", "remaining_time": "0:56:18", "throughput": 5838.74, "total_tokens": 2644360} {"current_steps": 4015, "total_steps": 33920, "loss": 0.5246, "lr": 9.989760575906264e-06, "epoch": 2.3673349056603774, "percentage": 11.84, "elapsed_time": "0:07:33", "remaining_time": "0:56:16", "throughput": 5838.54, "total_tokens": 2647048} {"current_steps": 4020, "total_steps": 33920, "loss": 0.4869, "lr": 9.98959535062757e-06, "epoch": 2.3702830188679247, "percentage": 11.85, "elapsed_time": "0:07:33", "remaining_time": "0:56:16", "throughput": 5839.06, "total_tokens": 2650440} {"current_steps": 4025, "total_steps": 33920, "loss": 0.433, "lr": 9.989428804332002e-06, "epoch": 2.3732311320754715, "percentage": 11.87, "elapsed_time": "0:07:34", "remaining_time": "0:56:15", "throughput": 5839.99, "total_tokens": 2654472} {"current_steps": 4030, "total_steps": 33920, "loss": 0.5308, "lr": 9.989260937063656e-06, "epoch": 2.376179245283019, "percentage": 11.88, "elapsed_time": "0:07:35", "remaining_time": "0:56:19", "throughput": 5840.57, "total_tokens": 2661640} {"current_steps": 4035, "total_steps": 33920, "loss": 0.3831, "lr": 9.989091748866973e-06, "epoch": 2.379127358490566, "percentage": 11.9, "elapsed_time": "0:07:36", "remaining_time": "0:56:18", "throughput": 5840.75, "total_tokens": 2664680} {"current_steps": 4040, "total_steps": 33920, "loss": 0.5771, "lr": 9.988921239786748e-06, "epoch": 2.3820754716981134, "percentage": 11.91, "elapsed_time": "0:07:36", "remaining_time": "0:56:18", "throughput": 5840.26, "total_tokens": 2667624} {"current_steps": 4045, "total_steps": 33920, "loss": 0.387, "lr": 9.988749409868124e-06, "epoch": 2.3850235849056602, "percentage": 11.93, "elapsed_time": "0:07:37", "remaining_time": "0:56:17", "throughput": 5841.17, "total_tokens": 2671464} {"current_steps": 4050, "total_steps": 33920, "loss": 0.677, "lr": 9.988576259156593e-06, "epoch": 2.3879716981132075, "percentage": 11.94, "elapsed_time": "0:07:37", "remaining_time": "0:56:17", "throughput": 5841.45, "total_tokens": 2674760} {"current_steps": 4055, "total_steps": 33920, "loss": 0.4774, "lr": 9.988401787697996e-06, "epoch": 2.390919811320755, "percentage": 11.95, "elapsed_time": "0:07:38", "remaining_time": "0:56:16", "throughput": 5841.35, "total_tokens": 2678088} {"current_steps": 4060, "total_steps": 33920, "loss": 0.3826, "lr": 9.98822599553853e-06, "epoch": 2.393867924528302, "percentage": 11.97, "elapsed_time": "0:07:39", "remaining_time": "0:56:16", "throughput": 5842.13, "total_tokens": 2681864} {"current_steps": 4065, "total_steps": 33920, "loss": 0.4208, "lr": 9.988048882724732e-06, "epoch": 2.396816037735849, "percentage": 11.98, "elapsed_time": "0:07:39", "remaining_time": "0:56:14", "throughput": 5841.98, "total_tokens": 2684488} {"current_steps": 4070, "total_steps": 33920, "loss": 0.4784, "lr": 9.987870449303497e-06, "epoch": 2.3997641509433962, "percentage": 12.0, "elapsed_time": "0:07:40", "remaining_time": "0:56:14", "throughput": 5842.02, "total_tokens": 2687624} {"current_steps": 4075, "total_steps": 33920, "loss": 0.4295, "lr": 9.98769069532206e-06, "epoch": 2.4027122641509435, "percentage": 12.01, "elapsed_time": "0:07:40", "remaining_time": "0:56:13", "throughput": 5842.67, "total_tokens": 2691400} {"current_steps": 4080, "total_steps": 33920, "loss": 0.4634, "lr": 9.98750962082802e-06, "epoch": 2.4056603773584904, "percentage": 12.03, "elapsed_time": "0:07:41", "remaining_time": "0:56:13", "throughput": 5843.72, "total_tokens": 2695464} {"current_steps": 4085, "total_steps": 33920, "loss": 0.5222, "lr": 9.987327225869312e-06, "epoch": 2.4086084905660377, "percentage": 12.04, "elapsed_time": "0:07:41", "remaining_time": "0:56:12", "throughput": 5843.37, "total_tokens": 2698216} {"current_steps": 4090, "total_steps": 33920, "loss": 0.4439, "lr": 9.987143510494225e-06, "epoch": 2.411556603773585, "percentage": 12.06, "elapsed_time": "0:07:42", "remaining_time": "0:56:11", "throughput": 5844.26, "total_tokens": 2701928} {"current_steps": 4095, "total_steps": 33920, "loss": 0.4705, "lr": 9.9869584747514e-06, "epoch": 2.4145047169811322, "percentage": 12.07, "elapsed_time": "0:07:42", "remaining_time": "0:56:10", "throughput": 5843.0, "total_tokens": 2704136} {"current_steps": 4100, "total_steps": 33920, "loss": 0.5592, "lr": 9.986772118689828e-06, "epoch": 2.417452830188679, "percentage": 12.09, "elapsed_time": "0:07:43", "remaining_time": "0:56:10", "throughput": 5843.41, "total_tokens": 2707560} {"current_steps": 4105, "total_steps": 33920, "loss": 0.4479, "lr": 9.986584442358845e-06, "epoch": 2.4204009433962264, "percentage": 12.1, "elapsed_time": "0:07:43", "remaining_time": "0:56:09", "throughput": 5843.59, "total_tokens": 2711208} {"current_steps": 4110, "total_steps": 33920, "loss": 0.4091, "lr": 9.98639544580814e-06, "epoch": 2.4233490566037736, "percentage": 12.12, "elapsed_time": "0:07:44", "remaining_time": "0:56:09", "throughput": 5842.75, "total_tokens": 2714024} {"current_steps": 4115, "total_steps": 33920, "loss": 0.4409, "lr": 9.98620512908775e-06, "epoch": 2.426297169811321, "percentage": 12.13, "elapsed_time": "0:07:45", "remaining_time": "0:56:08", "throughput": 5843.16, "total_tokens": 2717288} {"current_steps": 4120, "total_steps": 33920, "loss": 0.5263, "lr": 9.986013492248064e-06, "epoch": 2.4292452830188678, "percentage": 12.15, "elapsed_time": "0:07:45", "remaining_time": "0:56:07", "throughput": 5842.66, "total_tokens": 2720072} {"current_steps": 4125, "total_steps": 33920, "loss": 0.4058, "lr": 9.985820535339817e-06, "epoch": 2.432193396226415, "percentage": 12.16, "elapsed_time": "0:07:46", "remaining_time": "0:56:06", "throughput": 5842.75, "total_tokens": 2723048} {"current_steps": 4130, "total_steps": 33920, "loss": 0.5037, "lr": 9.985626258414093e-06, "epoch": 2.4351415094339623, "percentage": 12.18, "elapsed_time": "0:07:46", "remaining_time": "0:56:05", "throughput": 5843.17, "total_tokens": 2726184} {"current_steps": 4135, "total_steps": 33920, "loss": 0.4961, "lr": 9.985430661522333e-06, "epoch": 2.4380896226415096, "percentage": 12.19, "elapsed_time": "0:07:47", "remaining_time": "0:56:04", "throughput": 5842.79, "total_tokens": 2728968} {"current_steps": 4140, "total_steps": 33920, "loss": 0.4729, "lr": 9.98523374471632e-06, "epoch": 2.4410377358490565, "percentage": 12.21, "elapsed_time": "0:07:47", "remaining_time": "0:56:03", "throughput": 5843.08, "total_tokens": 2732520} {"current_steps": 4145, "total_steps": 33920, "loss": 0.5134, "lr": 9.985035508048186e-06, "epoch": 2.4439858490566038, "percentage": 12.22, "elapsed_time": "0:07:48", "remaining_time": "0:56:02", "throughput": 5843.43, "total_tokens": 2735624} {"current_steps": 4150, "total_steps": 33920, "loss": 0.4098, "lr": 9.984835951570417e-06, "epoch": 2.446933962264151, "percentage": 12.23, "elapsed_time": "0:07:48", "remaining_time": "0:56:01", "throughput": 5843.4, "total_tokens": 2738536} {"current_steps": 4155, "total_steps": 33920, "loss": 0.4454, "lr": 9.984635075335847e-06, "epoch": 2.449882075471698, "percentage": 12.25, "elapsed_time": "0:07:49", "remaining_time": "0:56:00", "throughput": 5843.3, "total_tokens": 2741480} {"current_steps": 4160, "total_steps": 33920, "loss": 0.5333, "lr": 9.984432879397659e-06, "epoch": 2.452830188679245, "percentage": 12.26, "elapsed_time": "0:07:49", "remaining_time": "0:56:00", "throughput": 5844.25, "total_tokens": 2745480} {"current_steps": 4165, "total_steps": 33920, "loss": 0.4846, "lr": 9.984229363809383e-06, "epoch": 2.4557783018867925, "percentage": 12.28, "elapsed_time": "0:07:50", "remaining_time": "0:56:00", "throughput": 5845.27, "total_tokens": 2749224} {"current_steps": 4170, "total_steps": 33920, "loss": 0.5522, "lr": 9.984024528624904e-06, "epoch": 2.4587264150943398, "percentage": 12.29, "elapsed_time": "0:07:50", "remaining_time": "0:55:59", "throughput": 5845.25, "total_tokens": 2752392} {"current_steps": 4175, "total_steps": 33920, "loss": 0.5109, "lr": 9.98381837389845e-06, "epoch": 2.4616745283018866, "percentage": 12.31, "elapsed_time": "0:07:51", "remaining_time": "0:55:58", "throughput": 5845.47, "total_tokens": 2755624} {"current_steps": 4180, "total_steps": 33920, "loss": 0.4611, "lr": 9.983610899684601e-06, "epoch": 2.464622641509434, "percentage": 12.32, "elapsed_time": "0:07:52", "remaining_time": "0:55:58", "throughput": 5846.02, "total_tokens": 2759560} {"current_steps": 4185, "total_steps": 33920, "loss": 0.6268, "lr": 9.983402106038292e-06, "epoch": 2.467570754716981, "percentage": 12.34, "elapsed_time": "0:07:52", "remaining_time": "0:55:57", "throughput": 5845.82, "total_tokens": 2762664} {"current_steps": 4190, "total_steps": 33920, "loss": 0.5182, "lr": 9.983191993014793e-06, "epoch": 2.4705188679245285, "percentage": 12.35, "elapsed_time": "0:07:53", "remaining_time": "0:55:57", "throughput": 5846.83, "total_tokens": 2766760} {"current_steps": 4195, "total_steps": 33920, "loss": 0.454, "lr": 9.982980560669742e-06, "epoch": 2.4734669811320753, "percentage": 12.37, "elapsed_time": "0:07:53", "remaining_time": "0:55:56", "throughput": 5846.81, "total_tokens": 2769832} {"current_steps": 4200, "total_steps": 33920, "loss": 0.4135, "lr": 9.98276780905911e-06, "epoch": 2.4764150943396226, "percentage": 12.38, "elapsed_time": "0:07:54", "remaining_time": "0:55:55", "throughput": 5846.42, "total_tokens": 2772488} {"current_steps": 4205, "total_steps": 33920, "loss": 0.5507, "lr": 9.982553738239225e-06, "epoch": 2.47936320754717, "percentage": 12.4, "elapsed_time": "0:07:54", "remaining_time": "0:55:55", "throughput": 5847.02, "total_tokens": 2776008} {"current_steps": 4210, "total_steps": 33920, "loss": 0.4561, "lr": 9.982338348266766e-06, "epoch": 2.482311320754717, "percentage": 12.41, "elapsed_time": "0:07:55", "remaining_time": "0:55:54", "throughput": 5847.2, "total_tokens": 2779560} {"current_steps": 4215, "total_steps": 33920, "loss": 0.4362, "lr": 9.982121639198756e-06, "epoch": 2.485259433962264, "percentage": 12.43, "elapsed_time": "0:07:55", "remaining_time": "0:55:53", "throughput": 5846.59, "total_tokens": 2782152} {"current_steps": 4220, "total_steps": 33920, "loss": 0.6411, "lr": 9.98190361109257e-06, "epoch": 2.4882075471698113, "percentage": 12.44, "elapsed_time": "0:07:56", "remaining_time": "0:55:52", "throughput": 5846.79, "total_tokens": 2785352} {"current_steps": 4225, "total_steps": 33920, "loss": 0.5097, "lr": 9.981684264005934e-06, "epoch": 2.4911556603773586, "percentage": 12.46, "elapsed_time": "0:07:56", "remaining_time": "0:55:51", "throughput": 5847.18, "total_tokens": 2788456} {"current_steps": 4230, "total_steps": 33920, "loss": 0.4753, "lr": 9.981463597996917e-06, "epoch": 2.4941037735849054, "percentage": 12.47, "elapsed_time": "0:07:57", "remaining_time": "0:55:51", "throughput": 5848.1, "total_tokens": 2792232} {"current_steps": 4235, "total_steps": 33920, "loss": 0.4779, "lr": 9.981241613123944e-06, "epoch": 2.4970518867924527, "percentage": 12.49, "elapsed_time": "0:07:58", "remaining_time": "0:55:50", "throughput": 5848.65, "total_tokens": 2796008} {"current_steps": 4240, "total_steps": 33920, "loss": 0.5288, "lr": 9.981018309445785e-06, "epoch": 2.5, "percentage": 12.5, "elapsed_time": "0:07:58", "remaining_time": "0:55:49", "throughput": 5848.61, "total_tokens": 2798792} {"current_steps": 4245, "total_steps": 33920, "loss": 0.4292, "lr": 9.980793687021564e-06, "epoch": 2.5029481132075473, "percentage": 12.51, "elapsed_time": "0:07:59", "remaining_time": "0:55:49", "throughput": 5848.91, "total_tokens": 2802344} {"current_steps": 4250, "total_steps": 33920, "loss": 0.502, "lr": 9.980567745910746e-06, "epoch": 2.5058962264150946, "percentage": 12.53, "elapsed_time": "0:07:59", "remaining_time": "0:55:48", "throughput": 5848.41, "total_tokens": 2805288} {"current_steps": 4255, "total_steps": 33920, "loss": 0.3831, "lr": 9.980340486173155e-06, "epoch": 2.5088443396226414, "percentage": 12.54, "elapsed_time": "0:08:00", "remaining_time": "0:55:48", "throughput": 5848.62, "total_tokens": 2808648} {"current_steps": 4260, "total_steps": 33920, "loss": 0.3639, "lr": 9.980111907868954e-06, "epoch": 2.5117924528301887, "percentage": 12.56, "elapsed_time": "0:08:00", "remaining_time": "0:55:47", "throughput": 5848.27, "total_tokens": 2811496} {"current_steps": 4265, "total_steps": 33920, "loss": 0.5316, "lr": 9.979882011058662e-06, "epoch": 2.514740566037736, "percentage": 12.57, "elapsed_time": "0:08:01", "remaining_time": "0:55:46", "throughput": 5847.12, "total_tokens": 2814024} {"current_steps": 4270, "total_steps": 33920, "loss": 0.5004, "lr": 9.979650795803146e-06, "epoch": 2.517688679245283, "percentage": 12.59, "elapsed_time": "0:08:01", "remaining_time": "0:55:45", "throughput": 5847.91, "total_tokens": 2817896} {"current_steps": 4275, "total_steps": 33920, "loss": 0.4178, "lr": 9.979418262163621e-06, "epoch": 2.52063679245283, "percentage": 12.6, "elapsed_time": "0:08:02", "remaining_time": "0:55:45", "throughput": 5847.8, "total_tokens": 2821416} {"current_steps": 4280, "total_steps": 33920, "loss": 0.4974, "lr": 9.979184410201652e-06, "epoch": 2.5235849056603774, "percentage": 12.62, "elapsed_time": "0:08:03", "remaining_time": "0:55:45", "throughput": 5847.27, "total_tokens": 2824456} {"current_steps": 4285, "total_steps": 33920, "loss": 0.3977, "lr": 9.97894923997915e-06, "epoch": 2.5265330188679247, "percentage": 12.63, "elapsed_time": "0:08:03", "remaining_time": "0:55:44", "throughput": 5847.69, "total_tokens": 2827496} {"current_steps": 4290, "total_steps": 33920, "loss": 0.5493, "lr": 9.97871275155838e-06, "epoch": 2.5294811320754715, "percentage": 12.65, "elapsed_time": "0:08:04", "remaining_time": "0:55:43", "throughput": 5846.65, "total_tokens": 2830024} {"current_steps": 4295, "total_steps": 33920, "loss": 0.4841, "lr": 9.978474945001949e-06, "epoch": 2.532429245283019, "percentage": 12.66, "elapsed_time": "0:08:04", "remaining_time": "0:55:42", "throughput": 5846.76, "total_tokens": 2833416} {"current_steps": 4300, "total_steps": 33920, "loss": 0.3385, "lr": 9.978235820372822e-06, "epoch": 2.535377358490566, "percentage": 12.68, "elapsed_time": "0:08:05", "remaining_time": "0:55:41", "throughput": 5847.17, "total_tokens": 2836648} {"current_steps": 4305, "total_steps": 33920, "loss": 0.398, "lr": 9.977995377734307e-06, "epoch": 2.538325471698113, "percentage": 12.69, "elapsed_time": "0:08:05", "remaining_time": "0:55:40", "throughput": 5846.52, "total_tokens": 2839176} {"current_steps": 4310, "total_steps": 33920, "loss": 0.4788, "lr": 9.977753617150061e-06, "epoch": 2.5412735849056602, "percentage": 12.71, "elapsed_time": "0:08:06", "remaining_time": "0:55:39", "throughput": 5846.99, "total_tokens": 2842600} {"current_steps": 4315, "total_steps": 33920, "loss": 0.5259, "lr": 9.977510538684094e-06, "epoch": 2.5442216981132075, "percentage": 12.72, "elapsed_time": "0:08:06", "remaining_time": "0:55:39", "throughput": 5846.73, "total_tokens": 2845576} {"current_steps": 4320, "total_steps": 33920, "loss": 0.3801, "lr": 9.977266142400757e-06, "epoch": 2.547169811320755, "percentage": 12.74, "elapsed_time": "0:08:07", "remaining_time": "0:55:38", "throughput": 5846.05, "total_tokens": 2848360} {"current_steps": 4325, "total_steps": 33920, "loss": 0.5354, "lr": 9.977020428364759e-06, "epoch": 2.550117924528302, "percentage": 12.75, "elapsed_time": "0:08:07", "remaining_time": "0:55:37", "throughput": 5846.26, "total_tokens": 2851624} {"current_steps": 4330, "total_steps": 33920, "loss": 0.4972, "lr": 9.976773396641154e-06, "epoch": 2.553066037735849, "percentage": 12.77, "elapsed_time": "0:08:08", "remaining_time": "0:55:37", "throughput": 5847.27, "total_tokens": 2855720} {"current_steps": 4335, "total_steps": 33920, "loss": 0.5182, "lr": 9.976525047295342e-06, "epoch": 2.5560141509433962, "percentage": 12.78, "elapsed_time": "0:08:08", "remaining_time": "0:55:36", "throughput": 5847.36, "total_tokens": 2858856} {"current_steps": 4340, "total_steps": 33920, "loss": 0.474, "lr": 9.976275380393077e-06, "epoch": 2.5589622641509435, "percentage": 12.79, "elapsed_time": "0:08:09", "remaining_time": "0:55:35", "throughput": 5847.64, "total_tokens": 2861960} {"current_steps": 4345, "total_steps": 33920, "loss": 0.5053, "lr": 9.976024396000459e-06, "epoch": 2.5619103773584904, "percentage": 12.81, "elapsed_time": "0:08:09", "remaining_time": "0:55:34", "throughput": 5847.91, "total_tokens": 2865160} {"current_steps": 4350, "total_steps": 33920, "loss": 0.4972, "lr": 9.975772094183935e-06, "epoch": 2.5648584905660377, "percentage": 12.82, "elapsed_time": "0:08:10", "remaining_time": "0:55:34", "throughput": 5849.08, "total_tokens": 2869352} {"current_steps": 4355, "total_steps": 33920, "loss": 0.3867, "lr": 9.975518475010306e-06, "epoch": 2.567806603773585, "percentage": 12.84, "elapsed_time": "0:08:11", "remaining_time": "0:55:33", "throughput": 5849.3, "total_tokens": 2872360} {"current_steps": 4360, "total_steps": 33920, "loss": 0.4098, "lr": 9.975263538546717e-06, "epoch": 2.5707547169811322, "percentage": 12.85, "elapsed_time": "0:08:11", "remaining_time": "0:55:32", "throughput": 5849.42, "total_tokens": 2875528} {"current_steps": 4365, "total_steps": 33920, "loss": 0.462, "lr": 9.975007284860664e-06, "epoch": 2.5737028301886795, "percentage": 12.87, "elapsed_time": "0:08:12", "remaining_time": "0:55:33", "throughput": 5850.42, "total_tokens": 2879944} {"current_steps": 4370, "total_steps": 33920, "loss": 0.537, "lr": 9.974749714019993e-06, "epoch": 2.5766509433962264, "percentage": 12.88, "elapsed_time": "0:08:12", "remaining_time": "0:55:31", "throughput": 5850.22, "total_tokens": 2882696} {"current_steps": 4375, "total_steps": 33920, "loss": 0.4226, "lr": 9.974490826092894e-06, "epoch": 2.5795990566037736, "percentage": 12.9, "elapsed_time": "0:08:13", "remaining_time": "0:55:31", "throughput": 5851.02, "total_tokens": 2886408} {"current_steps": 4380, "total_steps": 33920, "loss": 0.3779, "lr": 9.974230621147907e-06, "epoch": 2.5825471698113205, "percentage": 12.91, "elapsed_time": "0:08:13", "remaining_time": "0:55:31", "throughput": 5851.95, "total_tokens": 2890408} {"current_steps": 4385, "total_steps": 33920, "loss": 0.4925, "lr": 9.973969099253928e-06, "epoch": 2.5854952830188678, "percentage": 12.93, "elapsed_time": "0:08:14", "remaining_time": "0:55:30", "throughput": 5851.94, "total_tokens": 2893512} {"current_steps": 4390, "total_steps": 33920, "loss": 0.404, "lr": 9.973706260480194e-06, "epoch": 2.588443396226415, "percentage": 12.94, "elapsed_time": "0:08:15", "remaining_time": "0:55:29", "throughput": 5851.67, "total_tokens": 2896712} {"current_steps": 4395, "total_steps": 33920, "loss": 0.4259, "lr": 9.97344210489629e-06, "epoch": 2.5913915094339623, "percentage": 12.96, "elapsed_time": "0:08:15", "remaining_time": "0:55:28", "throughput": 5850.9, "total_tokens": 2899048} {"current_steps": 4400, "total_steps": 33920, "loss": 0.404, "lr": 9.973176632572158e-06, "epoch": 2.5943396226415096, "percentage": 12.97, "elapsed_time": "0:08:16", "remaining_time": "0:55:27", "throughput": 5851.3, "total_tokens": 2902248} {"current_steps": 4405, "total_steps": 33920, "loss": 0.4486, "lr": 9.972909843578076e-06, "epoch": 2.5972877358490565, "percentage": 12.99, "elapsed_time": "0:08:16", "remaining_time": "0:55:27", "throughput": 5852.0, "total_tokens": 2906184} {"current_steps": 4410, "total_steps": 33920, "loss": 0.3976, "lr": 9.972641737984681e-06, "epoch": 2.6002358490566038, "percentage": 13.0, "elapsed_time": "0:08:17", "remaining_time": "0:55:27", "throughput": 5853.02, "total_tokens": 2910152} {"current_steps": 4415, "total_steps": 33920, "loss": 0.483, "lr": 9.972372315862956e-06, "epoch": 2.603183962264151, "percentage": 13.02, "elapsed_time": "0:08:17", "remaining_time": "0:55:26", "throughput": 5853.76, "total_tokens": 2913736} {"current_steps": 4420, "total_steps": 33920, "loss": 0.4722, "lr": 9.97210157728423e-06, "epoch": 2.606132075471698, "percentage": 13.03, "elapsed_time": "0:08:18", "remaining_time": "0:55:25", "throughput": 5854.12, "total_tokens": 2917096} {"current_steps": 4425, "total_steps": 33920, "loss": 0.6214, "lr": 9.971829522320185e-06, "epoch": 2.609080188679245, "percentage": 13.05, "elapsed_time": "0:08:18", "remaining_time": "0:55:25", "throughput": 5854.92, "total_tokens": 2921128} {"current_steps": 4430, "total_steps": 33920, "loss": 0.568, "lr": 9.971556151042843e-06, "epoch": 2.6120283018867925, "percentage": 13.06, "elapsed_time": "0:08:19", "remaining_time": "0:55:25", "throughput": 5855.7, "total_tokens": 2924904} {"current_steps": 4435, "total_steps": 33920, "loss": 0.4269, "lr": 9.971281463524588e-06, "epoch": 2.6149764150943398, "percentage": 13.07, "elapsed_time": "0:08:20", "remaining_time": "0:55:24", "throughput": 5855.84, "total_tokens": 2927976} {"current_steps": 4440, "total_steps": 33920, "loss": 0.5383, "lr": 9.971005459838136e-06, "epoch": 2.617924528301887, "percentage": 13.09, "elapsed_time": "0:08:20", "remaining_time": "0:55:23", "throughput": 5856.12, "total_tokens": 2931176} {"current_steps": 4445, "total_steps": 33920, "loss": 0.5067, "lr": 9.970728140056567e-06, "epoch": 2.620872641509434, "percentage": 13.1, "elapsed_time": "0:08:21", "remaining_time": "0:55:22", "throughput": 5856.89, "total_tokens": 2934952} {"current_steps": 4450, "total_steps": 33920, "loss": 0.599, "lr": 9.9704495042533e-06, "epoch": 2.623820754716981, "percentage": 13.12, "elapsed_time": "0:08:21", "remaining_time": "0:55:22", "throughput": 5857.37, "total_tokens": 2938408} {"current_steps": 4455, "total_steps": 33920, "loss": 0.4809, "lr": 9.970169552502105e-06, "epoch": 2.6267688679245285, "percentage": 13.13, "elapsed_time": "0:08:22", "remaining_time": "0:55:21", "throughput": 5857.93, "total_tokens": 2941768} {"current_steps": 4460, "total_steps": 33920, "loss": 0.4068, "lr": 9.969888284877102e-06, "epoch": 2.6297169811320753, "percentage": 13.15, "elapsed_time": "0:08:22", "remaining_time": "0:55:20", "throughput": 5857.89, "total_tokens": 2944840} {"current_steps": 4465, "total_steps": 33920, "loss": 0.509, "lr": 9.969605701452757e-06, "epoch": 2.6326650943396226, "percentage": 13.16, "elapsed_time": "0:08:23", "remaining_time": "0:55:19", "throughput": 5858.56, "total_tokens": 2948168} {"current_steps": 4470, "total_steps": 33920, "loss": 0.4817, "lr": 9.969321802303882e-06, "epoch": 2.63561320754717, "percentage": 13.18, "elapsed_time": "0:08:23", "remaining_time": "0:55:18", "throughput": 5859.17, "total_tokens": 2951528} {"current_steps": 4475, "total_steps": 33920, "loss": 0.6412, "lr": 9.969036587505644e-06, "epoch": 2.638561320754717, "percentage": 13.19, "elapsed_time": "0:08:24", "remaining_time": "0:55:17", "throughput": 5859.6, "total_tokens": 2954696} {"current_steps": 4480, "total_steps": 33920, "loss": 0.593, "lr": 9.968750057133555e-06, "epoch": 2.641509433962264, "percentage": 13.21, "elapsed_time": "0:08:24", "remaining_time": "0:55:17", "throughput": 5860.17, "total_tokens": 2958248} {"current_steps": 4485, "total_steps": 33920, "loss": 0.588, "lr": 9.968462211263474e-06, "epoch": 2.6444575471698113, "percentage": 13.22, "elapsed_time": "0:08:25", "remaining_time": "0:55:16", "throughput": 5860.66, "total_tokens": 2961256} {"current_steps": 4490, "total_steps": 33920, "loss": 0.4894, "lr": 9.96817304997161e-06, "epoch": 2.6474056603773586, "percentage": 13.24, "elapsed_time": "0:08:25", "remaining_time": "0:55:15", "throughput": 5860.03, "total_tokens": 2963816} {"current_steps": 4495, "total_steps": 33920, "loss": 0.5316, "lr": 9.967882573334519e-06, "epoch": 2.6503537735849054, "percentage": 13.25, "elapsed_time": "0:08:26", "remaining_time": "0:55:14", "throughput": 5860.07, "total_tokens": 2966728} {"current_steps": 4500, "total_steps": 33920, "loss": 0.5928, "lr": 9.967590781429106e-06, "epoch": 2.6533018867924527, "percentage": 13.27, "elapsed_time": "0:08:26", "remaining_time": "0:55:13", "throughput": 5860.59, "total_tokens": 2970376} {"current_steps": 4505, "total_steps": 33920, "loss": 0.6376, "lr": 9.967297674332625e-06, "epoch": 2.65625, "percentage": 13.28, "elapsed_time": "0:08:27", "remaining_time": "0:55:12", "throughput": 5859.88, "total_tokens": 2972840} {"current_steps": 4510, "total_steps": 33920, "loss": 0.4021, "lr": 9.967003252122675e-06, "epoch": 2.6591981132075473, "percentage": 13.3, "elapsed_time": "0:08:27", "remaining_time": "0:55:11", "throughput": 5860.57, "total_tokens": 2976360} {"current_steps": 4515, "total_steps": 33920, "loss": 0.6066, "lr": 9.96670751487721e-06, "epoch": 2.6621462264150946, "percentage": 13.31, "elapsed_time": "0:08:28", "remaining_time": "0:55:10", "throughput": 5860.06, "total_tokens": 2978888} {"current_steps": 4520, "total_steps": 33920, "loss": 0.4737, "lr": 9.966410462674525e-06, "epoch": 2.6650943396226414, "percentage": 13.33, "elapsed_time": "0:08:28", "remaining_time": "0:55:09", "throughput": 5859.88, "total_tokens": 2981608} {"current_steps": 4525, "total_steps": 33920, "loss": 0.4, "lr": 9.966112095593264e-06, "epoch": 2.6680424528301887, "percentage": 13.34, "elapsed_time": "0:08:29", "remaining_time": "0:55:08", "throughput": 5860.08, "total_tokens": 2984648} {"current_steps": 4530, "total_steps": 33920, "loss": 0.4497, "lr": 9.965812413712425e-06, "epoch": 2.670990566037736, "percentage": 13.35, "elapsed_time": "0:08:29", "remaining_time": "0:55:08", "throughput": 5860.53, "total_tokens": 2988168} {"current_steps": 4535, "total_steps": 33920, "loss": 0.504, "lr": 9.965511417111346e-06, "epoch": 2.673938679245283, "percentage": 13.37, "elapsed_time": "0:08:30", "remaining_time": "0:55:07", "throughput": 5860.56, "total_tokens": 2991240} {"current_steps": 4540, "total_steps": 33920, "loss": 0.5166, "lr": 9.96520910586972e-06, "epoch": 2.67688679245283, "percentage": 13.38, "elapsed_time": "0:08:30", "remaining_time": "0:55:06", "throughput": 5859.76, "total_tokens": 2993800} {"current_steps": 4545, "total_steps": 33920, "loss": 0.7833, "lr": 9.964905480067585e-06, "epoch": 2.6798349056603774, "percentage": 13.4, "elapsed_time": "0:08:31", "remaining_time": "0:55:05", "throughput": 5860.11, "total_tokens": 2997032} {"current_steps": 4550, "total_steps": 33920, "loss": 0.535, "lr": 9.964600539785328e-06, "epoch": 2.6827830188679247, "percentage": 13.41, "elapsed_time": "0:08:31", "remaining_time": "0:55:04", "throughput": 5860.57, "total_tokens": 3000552} {"current_steps": 4555, "total_steps": 33920, "loss": 0.4483, "lr": 9.96429428510368e-06, "epoch": 2.6857311320754715, "percentage": 13.43, "elapsed_time": "0:08:32", "remaining_time": "0:55:04", "throughput": 5861.29, "total_tokens": 3004168} {"current_steps": 4560, "total_steps": 33920, "loss": 0.6757, "lr": 9.963986716103724e-06, "epoch": 2.688679245283019, "percentage": 13.44, "elapsed_time": "0:08:32", "remaining_time": "0:55:02", "throughput": 5860.51, "total_tokens": 3006440} {"current_steps": 4565, "total_steps": 33920, "loss": 0.4026, "lr": 9.963677832866893e-06, "epoch": 2.691627358490566, "percentage": 13.46, "elapsed_time": "0:08:33", "remaining_time": "0:55:02", "throughput": 5860.58, "total_tokens": 3009736} {"current_steps": 4570, "total_steps": 33920, "loss": 0.5164, "lr": 9.963367635474962e-06, "epoch": 2.694575471698113, "percentage": 13.47, "elapsed_time": "0:08:34", "remaining_time": "0:55:01", "throughput": 5860.53, "total_tokens": 3012616} {"current_steps": 4575, "total_steps": 33920, "loss": 0.5754, "lr": 9.96305612401006e-06, "epoch": 2.6975235849056602, "percentage": 13.49, "elapsed_time": "0:08:34", "remaining_time": "0:55:00", "throughput": 5860.96, "total_tokens": 3015784} {"current_steps": 4580, "total_steps": 33920, "loss": 0.4224, "lr": 9.96274329855466e-06, "epoch": 2.7004716981132075, "percentage": 13.5, "elapsed_time": "0:08:35", "remaining_time": "0:54:59", "throughput": 5860.98, "total_tokens": 3019048} {"current_steps": 4585, "total_steps": 33920, "loss": 0.4968, "lr": 9.962429159191583e-06, "epoch": 2.703419811320755, "percentage": 13.52, "elapsed_time": "0:08:35", "remaining_time": "0:54:58", "throughput": 5861.01, "total_tokens": 3021896} {"current_steps": 4590, "total_steps": 33920, "loss": 0.4146, "lr": 9.962113706003997e-06, "epoch": 2.706367924528302, "percentage": 13.53, "elapsed_time": "0:08:36", "remaining_time": "0:54:57", "throughput": 5861.03, "total_tokens": 3024904} {"current_steps": 4595, "total_steps": 33920, "loss": 0.5484, "lr": 9.961796939075424e-06, "epoch": 2.709316037735849, "percentage": 13.55, "elapsed_time": "0:08:36", "remaining_time": "0:54:57", "throughput": 5860.65, "total_tokens": 3027720} {"current_steps": 4600, "total_steps": 33920, "loss": 0.5156, "lr": 9.961478858489728e-06, "epoch": 2.7122641509433962, "percentage": 13.56, "elapsed_time": "0:08:37", "remaining_time": "0:54:56", "throughput": 5859.77, "total_tokens": 3030248} {"current_steps": 4605, "total_steps": 33920, "loss": 0.6219, "lr": 9.961159464331119e-06, "epoch": 2.7152122641509435, "percentage": 13.58, "elapsed_time": "0:08:37", "remaining_time": "0:54:55", "throughput": 5860.59, "total_tokens": 3034088} {"current_steps": 4610, "total_steps": 33920, "loss": 0.438, "lr": 9.960838756684161e-06, "epoch": 2.7181603773584904, "percentage": 13.59, "elapsed_time": "0:08:38", "remaining_time": "0:54:54", "throughput": 5860.71, "total_tokens": 3037064} {"current_steps": 4615, "total_steps": 33920, "loss": 0.4455, "lr": 9.960516735633764e-06, "epoch": 2.7211084905660377, "percentage": 13.61, "elapsed_time": "0:08:38", "remaining_time": "0:54:54", "throughput": 5859.96, "total_tokens": 3040200} {"current_steps": 4620, "total_steps": 33920, "loss": 0.6147, "lr": 9.960193401265181e-06, "epoch": 2.724056603773585, "percentage": 13.62, "elapsed_time": "0:08:39", "remaining_time": "0:54:53", "throughput": 5860.65, "total_tokens": 3043912} {"current_steps": 4625, "total_steps": 33920, "loss": 0.566, "lr": 9.959868753664018e-06, "epoch": 2.7270047169811322, "percentage": 13.64, "elapsed_time": "0:08:40", "remaining_time": "0:54:56", "throughput": 5861.74, "total_tokens": 3050568} {"current_steps": 4630, "total_steps": 33920, "loss": 0.437, "lr": 9.959542792916227e-06, "epoch": 2.7299528301886795, "percentage": 13.65, "elapsed_time": "0:08:41", "remaining_time": "0:54:56", "throughput": 5862.62, "total_tokens": 3054856} {"current_steps": 4635, "total_steps": 33920, "loss": 0.4886, "lr": 9.959215519108108e-06, "epoch": 2.7329009433962264, "percentage": 13.66, "elapsed_time": "0:08:41", "remaining_time": "0:54:55", "throughput": 5862.39, "total_tokens": 3057736} {"current_steps": 4640, "total_steps": 33920, "loss": 0.5056, "lr": 9.958886932326306e-06, "epoch": 2.7358490566037736, "percentage": 13.68, "elapsed_time": "0:08:42", "remaining_time": "0:54:55", "throughput": 5862.9, "total_tokens": 3061384} {"current_steps": 4645, "total_steps": 33920, "loss": 0.5473, "lr": 9.958557032657817e-06, "epoch": 2.7387971698113205, "percentage": 13.69, "elapsed_time": "0:08:42", "remaining_time": "0:54:54", "throughput": 5863.89, "total_tokens": 3065288} {"current_steps": 4650, "total_steps": 33920, "loss": 0.5462, "lr": 9.958225820189984e-06, "epoch": 2.7417452830188678, "percentage": 13.71, "elapsed_time": "0:08:43", "remaining_time": "0:54:53", "throughput": 5863.62, "total_tokens": 3068136} {"current_steps": 4655, "total_steps": 33920, "loss": 0.4807, "lr": 9.957893295010495e-06, "epoch": 2.744693396226415, "percentage": 13.72, "elapsed_time": "0:08:43", "remaining_time": "0:54:52", "throughput": 5863.46, "total_tokens": 3070856} {"current_steps": 4660, "total_steps": 33920, "loss": 0.4584, "lr": 9.957559457207391e-06, "epoch": 2.7476415094339623, "percentage": 13.74, "elapsed_time": "0:08:44", "remaining_time": "0:54:51", "throughput": 5863.07, "total_tokens": 3073448} {"current_steps": 4665, "total_steps": 33920, "loss": 0.5709, "lr": 9.957224306869053e-06, "epoch": 2.7505896226415096, "percentage": 13.75, "elapsed_time": "0:08:44", "remaining_time": "0:54:50", "throughput": 5863.93, "total_tokens": 3077256} {"current_steps": 4670, "total_steps": 33920, "loss": 0.4162, "lr": 9.956887844084216e-06, "epoch": 2.7535377358490565, "percentage": 13.77, "elapsed_time": "0:08:45", "remaining_time": "0:54:50", "throughput": 5864.33, "total_tokens": 3080840} {"current_steps": 4675, "total_steps": 33920, "loss": 0.4649, "lr": 9.956550068941958e-06, "epoch": 2.7564858490566038, "percentage": 13.78, "elapsed_time": "0:08:45", "remaining_time": "0:54:49", "throughput": 5864.51, "total_tokens": 3083784} {"current_steps": 4680, "total_steps": 33920, "loss": 0.5056, "lr": 9.95621098153171e-06, "epoch": 2.759433962264151, "percentage": 13.8, "elapsed_time": "0:08:46", "remaining_time": "0:54:48", "throughput": 5864.45, "total_tokens": 3086888} {"current_steps": 4685, "total_steps": 33920, "loss": 0.483, "lr": 9.955870581943243e-06, "epoch": 2.762382075471698, "percentage": 13.81, "elapsed_time": "0:08:46", "remaining_time": "0:54:47", "throughput": 5864.97, "total_tokens": 3090024} {"current_steps": 4690, "total_steps": 33920, "loss": 0.3514, "lr": 9.955528870266681e-06, "epoch": 2.765330188679245, "percentage": 13.83, "elapsed_time": "0:08:47", "remaining_time": "0:54:47", "throughput": 5865.88, "total_tokens": 3094056} {"current_steps": 4695, "total_steps": 33920, "loss": 0.4796, "lr": 9.955185846592495e-06, "epoch": 2.7682783018867925, "percentage": 13.84, "elapsed_time": "0:08:47", "remaining_time": "0:54:46", "throughput": 5866.03, "total_tokens": 3096904} {"current_steps": 4700, "total_steps": 33920, "loss": 0.3768, "lr": 9.9548415110115e-06, "epoch": 2.7712264150943398, "percentage": 13.86, "elapsed_time": "0:08:48", "remaining_time": "0:54:45", "throughput": 5866.24, "total_tokens": 3100232} {"current_steps": 4705, "total_steps": 33920, "loss": 0.4237, "lr": 9.95449586361486e-06, "epoch": 2.774174528301887, "percentage": 13.87, "elapsed_time": "0:08:48", "remaining_time": "0:54:44", "throughput": 5865.92, "total_tokens": 3102888} {"current_steps": 4710, "total_steps": 33920, "loss": 0.4489, "lr": 9.954148904494085e-06, "epoch": 2.777122641509434, "percentage": 13.89, "elapsed_time": "0:08:50", "remaining_time": "0:54:47", "throughput": 5868.64, "total_tokens": 3111336} {"current_steps": 4715, "total_steps": 33920, "loss": 0.4105, "lr": 9.95380063374104e-06, "epoch": 2.780070754716981, "percentage": 13.9, "elapsed_time": "0:08:50", "remaining_time": "0:54:47", "throughput": 5868.75, "total_tokens": 3114440} {"current_steps": 4720, "total_steps": 33920, "loss": 0.6385, "lr": 9.953451051447927e-06, "epoch": 2.7830188679245285, "percentage": 13.92, "elapsed_time": "0:08:51", "remaining_time": "0:54:46", "throughput": 5868.89, "total_tokens": 3117896} {"current_steps": 4725, "total_steps": 33920, "loss": 0.4559, "lr": 9.953100157707299e-06, "epoch": 2.7859669811320753, "percentage": 13.93, "elapsed_time": "0:08:51", "remaining_time": "0:54:45", "throughput": 5868.69, "total_tokens": 3120776} {"current_steps": 4730, "total_steps": 33920, "loss": 0.4768, "lr": 9.952747952612056e-06, "epoch": 2.7889150943396226, "percentage": 13.94, "elapsed_time": "0:08:52", "remaining_time": "0:54:44", "throughput": 5868.65, "total_tokens": 3123880} {"current_steps": 4735, "total_steps": 33920, "loss": 0.4645, "lr": 9.952394436255451e-06, "epoch": 2.79186320754717, "percentage": 13.96, "elapsed_time": "0:08:52", "remaining_time": "0:54:44", "throughput": 5869.47, "total_tokens": 3128040} {"current_steps": 4740, "total_steps": 33920, "loss": 0.4071, "lr": 9.952039608731072e-06, "epoch": 2.794811320754717, "percentage": 13.97, "elapsed_time": "0:08:53", "remaining_time": "0:54:43", "throughput": 5869.78, "total_tokens": 3131176} {"current_steps": 4745, "total_steps": 33920, "loss": 0.5153, "lr": 9.951683470132868e-06, "epoch": 2.797759433962264, "percentage": 13.99, "elapsed_time": "0:08:53", "remaining_time": "0:54:42", "throughput": 5869.71, "total_tokens": 3134024} {"current_steps": 4750, "total_steps": 33920, "loss": 0.7633, "lr": 9.951326020555122e-06, "epoch": 2.8007075471698113, "percentage": 14.0, "elapsed_time": "0:08:54", "remaining_time": "0:54:42", "throughput": 5870.3, "total_tokens": 3137832} {"current_steps": 4755, "total_steps": 33920, "loss": 0.4172, "lr": 9.950967260092473e-06, "epoch": 2.8036556603773586, "percentage": 14.02, "elapsed_time": "0:08:55", "remaining_time": "0:54:41", "throughput": 5870.23, "total_tokens": 3140744} {"current_steps": 4760, "total_steps": 33920, "loss": 0.3426, "lr": 9.950607188839905e-06, "epoch": 2.8066037735849054, "percentage": 14.03, "elapsed_time": "0:08:55", "remaining_time": "0:54:41", "throughput": 5870.53, "total_tokens": 3145000} {"current_steps": 4765, "total_steps": 33920, "loss": 0.4432, "lr": 9.950245806892749e-06, "epoch": 2.8095518867924527, "percentage": 14.05, "elapsed_time": "0:08:56", "remaining_time": "0:54:41", "throughput": 5870.37, "total_tokens": 3148232} {"current_steps": 4770, "total_steps": 33920, "loss": 0.4699, "lr": 9.94988311434668e-06, "epoch": 2.8125, "percentage": 14.06, "elapsed_time": "0:08:56", "remaining_time": "0:54:40", "throughput": 5870.58, "total_tokens": 3151272} {"current_steps": 4775, "total_steps": 33920, "loss": 0.623, "lr": 9.949519111297723e-06, "epoch": 2.8154481132075473, "percentage": 14.08, "elapsed_time": "0:08:57", "remaining_time": "0:54:39", "throughput": 5869.83, "total_tokens": 3153480} {"current_steps": 4780, "total_steps": 33920, "loss": 0.4967, "lr": 9.949153797842252e-06, "epoch": 2.8183962264150946, "percentage": 14.09, "elapsed_time": "0:08:57", "remaining_time": "0:54:38", "throughput": 5870.0, "total_tokens": 3156360} {"current_steps": 4785, "total_steps": 33920, "loss": 0.469, "lr": 9.948787174076982e-06, "epoch": 2.8213443396226414, "percentage": 14.11, "elapsed_time": "0:08:58", "remaining_time": "0:54:38", "throughput": 5870.85, "total_tokens": 3161448} {"current_steps": 4790, "total_steps": 33920, "loss": 0.5256, "lr": 9.948419240098978e-06, "epoch": 2.8242924528301887, "percentage": 14.12, "elapsed_time": "0:08:58", "remaining_time": "0:54:37", "throughput": 5870.41, "total_tokens": 3164040} {"current_steps": 4795, "total_steps": 33920, "loss": 0.4954, "lr": 9.948049996005657e-06, "epoch": 2.827240566037736, "percentage": 14.14, "elapsed_time": "0:08:59", "remaining_time": "0:54:36", "throughput": 5870.4, "total_tokens": 3166920} {"current_steps": 4800, "total_steps": 33920, "loss": 0.4903, "lr": 9.947679441894773e-06, "epoch": 2.830188679245283, "percentage": 14.15, "elapsed_time": "0:08:59", "remaining_time": "0:54:35", "throughput": 5869.72, "total_tokens": 3169352} {"current_steps": 4805, "total_steps": 33920, "loss": 0.5239, "lr": 9.947307577864433e-06, "epoch": 2.83313679245283, "percentage": 14.17, "elapsed_time": "0:09:00", "remaining_time": "0:54:35", "throughput": 5870.93, "total_tokens": 3173608} {"current_steps": 4810, "total_steps": 33920, "loss": 0.5856, "lr": 9.94693440401309e-06, "epoch": 2.8360849056603774, "percentage": 14.18, "elapsed_time": "0:09:01", "remaining_time": "0:54:34", "throughput": 5871.5, "total_tokens": 3177000} {"current_steps": 4815, "total_steps": 33920, "loss": 0.4848, "lr": 9.946559920439545e-06, "epoch": 2.8390330188679247, "percentage": 14.2, "elapsed_time": "0:09:01", "remaining_time": "0:54:34", "throughput": 5872.23, "total_tokens": 3180712} {"current_steps": 4820, "total_steps": 33920, "loss": 0.49, "lr": 9.946184127242942e-06, "epoch": 2.8419811320754715, "percentage": 14.21, "elapsed_time": "0:09:02", "remaining_time": "0:54:32", "throughput": 5872.1, "total_tokens": 3183368} {"current_steps": 4825, "total_steps": 33920, "loss": 0.7982, "lr": 9.945807024522774e-06, "epoch": 2.844929245283019, "percentage": 14.22, "elapsed_time": "0:09:02", "remaining_time": "0:54:32", "throughput": 5873.06, "total_tokens": 3187560} {"current_steps": 4830, "total_steps": 33920, "loss": 0.5629, "lr": 9.945428612378881e-06, "epoch": 2.847877358490566, "percentage": 14.24, "elapsed_time": "0:09:03", "remaining_time": "0:54:32", "throughput": 5873.84, "total_tokens": 3191144} {"current_steps": 4835, "total_steps": 33920, "loss": 0.6127, "lr": 9.94504889091145e-06, "epoch": 2.850825471698113, "percentage": 14.25, "elapsed_time": "0:09:03", "remaining_time": "0:54:30", "throughput": 5874.21, "total_tokens": 3194120} {"current_steps": 4840, "total_steps": 33920, "loss": 0.5936, "lr": 9.944667860221013e-06, "epoch": 2.8537735849056602, "percentage": 14.27, "elapsed_time": "0:09:04", "remaining_time": "0:54:30", "throughput": 5874.9, "total_tokens": 3197800} {"current_steps": 4845, "total_steps": 33920, "loss": 0.4644, "lr": 9.944285520408448e-06, "epoch": 2.8567216981132075, "percentage": 14.28, "elapsed_time": "0:09:04", "remaining_time": "0:54:29", "throughput": 5875.19, "total_tokens": 3200936} {"current_steps": 4850, "total_steps": 33920, "loss": 0.5222, "lr": 9.943901871574984e-06, "epoch": 2.859669811320755, "percentage": 14.3, "elapsed_time": "0:09:05", "remaining_time": "0:54:28", "throughput": 5875.42, "total_tokens": 3204104} {"current_steps": 4855, "total_steps": 33920, "loss": 0.4365, "lr": 9.943516913822192e-06, "epoch": 2.862617924528302, "percentage": 14.31, "elapsed_time": "0:09:05", "remaining_time": "0:54:27", "throughput": 5874.92, "total_tokens": 3206536} {"current_steps": 4860, "total_steps": 33920, "loss": 0.4468, "lr": 9.943130647251994e-06, "epoch": 2.865566037735849, "percentage": 14.33, "elapsed_time": "0:09:06", "remaining_time": "0:54:26", "throughput": 5875.13, "total_tokens": 3209576} {"current_steps": 4865, "total_steps": 33920, "loss": 0.5257, "lr": 9.94274307196665e-06, "epoch": 2.8685141509433962, "percentage": 14.34, "elapsed_time": "0:09:06", "remaining_time": "0:54:25", "throughput": 5874.63, "total_tokens": 3212136} {"current_steps": 4870, "total_steps": 33920, "loss": 0.6088, "lr": 9.942354188068778e-06, "epoch": 2.8714622641509435, "percentage": 14.36, "elapsed_time": "0:09:07", "remaining_time": "0:54:24", "throughput": 5874.9, "total_tokens": 3215240} {"current_steps": 4875, "total_steps": 33920, "loss": 0.595, "lr": 9.941963995661333e-06, "epoch": 2.8744103773584904, "percentage": 14.37, "elapsed_time": "0:09:07", "remaining_time": "0:54:23", "throughput": 5875.06, "total_tokens": 3218184} {"current_steps": 4880, "total_steps": 33920, "loss": 0.6327, "lr": 9.941572494847622e-06, "epoch": 2.8773584905660377, "percentage": 14.39, "elapsed_time": "0:09:08", "remaining_time": "0:54:23", "throughput": 5875.69, "total_tokens": 3221928} {"current_steps": 4885, "total_steps": 33920, "loss": 0.4573, "lr": 9.941179685731297e-06, "epoch": 2.880306603773585, "percentage": 14.4, "elapsed_time": "0:09:08", "remaining_time": "0:54:22", "throughput": 5875.83, "total_tokens": 3224840} {"current_steps": 4890, "total_steps": 33920, "loss": 0.3782, "lr": 9.940785568416354e-06, "epoch": 2.8832547169811322, "percentage": 14.42, "elapsed_time": "0:09:09", "remaining_time": "0:54:21", "throughput": 5876.31, "total_tokens": 3228008} {"current_steps": 4895, "total_steps": 33920, "loss": 0.449, "lr": 9.940390143007137e-06, "epoch": 2.8862028301886795, "percentage": 14.43, "elapsed_time": "0:09:09", "remaining_time": "0:54:20", "throughput": 5875.31, "total_tokens": 3230408} {"current_steps": 4900, "total_steps": 33920, "loss": 0.5554, "lr": 9.939993409608339e-06, "epoch": 2.8891509433962264, "percentage": 14.45, "elapsed_time": "0:09:10", "remaining_time": "0:54:19", "throughput": 5875.62, "total_tokens": 3233640} {"current_steps": 4905, "total_steps": 33920, "loss": 0.4095, "lr": 9.939595368324996e-06, "epoch": 2.8920990566037736, "percentage": 14.46, "elapsed_time": "0:09:10", "remaining_time": "0:54:18", "throughput": 5874.91, "total_tokens": 3236072} {"current_steps": 4910, "total_steps": 33920, "loss": 0.4188, "lr": 9.93919601926249e-06, "epoch": 2.8950471698113205, "percentage": 14.48, "elapsed_time": "0:09:11", "remaining_time": "0:54:17", "throughput": 5874.37, "total_tokens": 3238472} {"current_steps": 4915, "total_steps": 33920, "loss": 0.3847, "lr": 9.938795362526552e-06, "epoch": 2.8979952830188678, "percentage": 14.49, "elapsed_time": "0:09:11", "remaining_time": "0:54:16", "throughput": 5874.68, "total_tokens": 3241544} {"current_steps": 4920, "total_steps": 33920, "loss": 0.5639, "lr": 9.938393398223255e-06, "epoch": 2.900943396226415, "percentage": 14.5, "elapsed_time": "0:09:12", "remaining_time": "0:54:15", "throughput": 5874.63, "total_tokens": 3244456} {"current_steps": 4925, "total_steps": 33920, "loss": 0.4046, "lr": 9.937990126459024e-06, "epoch": 2.9038915094339623, "percentage": 14.52, "elapsed_time": "0:09:12", "remaining_time": "0:54:14", "throughput": 5875.11, "total_tokens": 3247784} {"current_steps": 4930, "total_steps": 33920, "loss": 0.5231, "lr": 9.937585547340624e-06, "epoch": 2.9068396226415096, "percentage": 14.53, "elapsed_time": "0:09:13", "remaining_time": "0:54:14", "throughput": 5876.06, "total_tokens": 3251848} {"current_steps": 4935, "total_steps": 33920, "loss": 0.4796, "lr": 9.937179660975174e-06, "epoch": 2.9097877358490565, "percentage": 14.55, "elapsed_time": "0:09:13", "remaining_time": "0:54:13", "throughput": 5875.9, "total_tokens": 3254600} {"current_steps": 4940, "total_steps": 33920, "loss": 0.4688, "lr": 9.936772467470127e-06, "epoch": 2.9127358490566038, "percentage": 14.56, "elapsed_time": "0:09:14", "remaining_time": "0:54:12", "throughput": 5876.04, "total_tokens": 3258280} {"current_steps": 4945, "total_steps": 33920, "loss": 0.4604, "lr": 9.936363966933294e-06, "epoch": 2.915683962264151, "percentage": 14.58, "elapsed_time": "0:09:15", "remaining_time": "0:54:12", "throughput": 5876.12, "total_tokens": 3261448} {"current_steps": 4950, "total_steps": 33920, "loss": 0.4396, "lr": 9.935954159472828e-06, "epoch": 2.918632075471698, "percentage": 14.59, "elapsed_time": "0:09:15", "remaining_time": "0:54:11", "throughput": 5875.5, "total_tokens": 3263944} {"current_steps": 4955, "total_steps": 33920, "loss": 0.5498, "lr": 9.935543045197222e-06, "epoch": 2.921580188679245, "percentage": 14.61, "elapsed_time": "0:09:16", "remaining_time": "0:54:10", "throughput": 5875.47, "total_tokens": 3266952} {"current_steps": 4960, "total_steps": 33920, "loss": 0.4095, "lr": 9.935130624215326e-06, "epoch": 2.9245283018867925, "percentage": 14.62, "elapsed_time": "0:09:16", "remaining_time": "0:54:09", "throughput": 5875.11, "total_tokens": 3269640} {"current_steps": 4965, "total_steps": 33920, "loss": 0.4913, "lr": 9.934716896636329e-06, "epoch": 2.9274764150943398, "percentage": 14.64, "elapsed_time": "0:09:17", "remaining_time": "0:54:08", "throughput": 5875.3, "total_tokens": 3273032} {"current_steps": 4970, "total_steps": 33920, "loss": 0.3139, "lr": 9.934301862569764e-06, "epoch": 2.930424528301887, "percentage": 14.65, "elapsed_time": "0:09:17", "remaining_time": "0:54:07", "throughput": 5874.77, "total_tokens": 3275560} {"current_steps": 4975, "total_steps": 33920, "loss": 0.5789, "lr": 9.933885522125517e-06, "epoch": 2.933372641509434, "percentage": 14.67, "elapsed_time": "0:09:18", "remaining_time": "0:54:07", "throughput": 5874.86, "total_tokens": 3279272} {"current_steps": 4980, "total_steps": 33920, "loss": 0.4948, "lr": 9.933467875413813e-06, "epoch": 2.936320754716981, "percentage": 14.68, "elapsed_time": "0:09:18", "remaining_time": "0:54:07", "throughput": 5875.67, "total_tokens": 3283176} {"current_steps": 4985, "total_steps": 33920, "loss": 0.6969, "lr": 9.933048922545227e-06, "epoch": 2.9392688679245285, "percentage": 14.7, "elapsed_time": "0:09:19", "remaining_time": "0:54:06", "throughput": 5875.54, "total_tokens": 3285832} {"current_steps": 4990, "total_steps": 33920, "loss": 0.4719, "lr": 9.932628663630679e-06, "epoch": 2.9422169811320753, "percentage": 14.71, "elapsed_time": "0:09:19", "remaining_time": "0:54:05", "throughput": 5876.04, "total_tokens": 3289704} {"current_steps": 4995, "total_steps": 33920, "loss": 0.5436, "lr": 9.932207098781432e-06, "epoch": 2.9451650943396226, "percentage": 14.73, "elapsed_time": "0:09:20", "remaining_time": "0:54:04", "throughput": 5876.47, "total_tokens": 3293000} {"current_steps": 5000, "total_steps": 33920, "loss": 0.442, "lr": 9.931784228109102e-06, "epoch": 2.94811320754717, "percentage": 14.74, "elapsed_time": "0:09:20", "remaining_time": "0:54:03", "throughput": 5876.2, "total_tokens": 3295528} {"current_steps": 5005, "total_steps": 33920, "loss": 0.5258, "lr": 9.93136005172564e-06, "epoch": 2.951061320754717, "percentage": 14.76, "elapsed_time": "0:09:21", "remaining_time": "0:54:02", "throughput": 5876.46, "total_tokens": 3298696} {"current_steps": 5010, "total_steps": 33920, "loss": 0.4759, "lr": 9.930934569743354e-06, "epoch": 2.954009433962264, "percentage": 14.77, "elapsed_time": "0:09:21", "remaining_time": "0:54:02", "throughput": 5876.51, "total_tokens": 3301832} {"current_steps": 5015, "total_steps": 33920, "loss": 0.5014, "lr": 9.930507782274888e-06, "epoch": 2.9569575471698113, "percentage": 14.78, "elapsed_time": "0:09:22", "remaining_time": "0:54:01", "throughput": 5876.41, "total_tokens": 3304456} {"current_steps": 5020, "total_steps": 33920, "loss": 0.5144, "lr": 9.930079689433236e-06, "epoch": 2.9599056603773586, "percentage": 14.8, "elapsed_time": "0:09:22", "remaining_time": "0:54:00", "throughput": 5876.7, "total_tokens": 3307720} {"current_steps": 5025, "total_steps": 33920, "loss": 0.3842, "lr": 9.92965029133174e-06, "epoch": 2.9628537735849054, "percentage": 14.81, "elapsed_time": "0:09:23", "remaining_time": "0:54:01", "throughput": 5877.47, "total_tokens": 3313096} {"current_steps": 5030, "total_steps": 33920, "loss": 0.7789, "lr": 9.929219588084084e-06, "epoch": 2.9658018867924527, "percentage": 14.83, "elapsed_time": "0:09:24", "remaining_time": "0:54:00", "throughput": 5877.66, "total_tokens": 3316552} {"current_steps": 5035, "total_steps": 33920, "loss": 0.4895, "lr": 9.9287875798043e-06, "epoch": 2.96875, "percentage": 14.84, "elapsed_time": "0:09:24", "remaining_time": "0:54:00", "throughput": 5877.9, "total_tokens": 3320200} {"current_steps": 5040, "total_steps": 33920, "loss": 0.4348, "lr": 9.92835426660676e-06, "epoch": 2.9716981132075473, "percentage": 14.86, "elapsed_time": "0:09:25", "remaining_time": "0:53:59", "throughput": 5877.81, "total_tokens": 3322984} {"current_steps": 5045, "total_steps": 33920, "loss": 0.5042, "lr": 9.927919648606188e-06, "epoch": 2.9746462264150946, "percentage": 14.87, "elapsed_time": "0:09:25", "remaining_time": "0:53:59", "throughput": 5878.76, "total_tokens": 3327304} {"current_steps": 5050, "total_steps": 33920, "loss": 0.3553, "lr": 9.927483725917652e-06, "epoch": 2.9775943396226414, "percentage": 14.89, "elapsed_time": "0:09:26", "remaining_time": "0:53:58", "throughput": 5879.32, "total_tokens": 3330856} {"current_steps": 5055, "total_steps": 33920, "loss": 0.5841, "lr": 9.927046498656562e-06, "epoch": 2.9805424528301887, "percentage": 14.9, "elapsed_time": "0:09:27", "remaining_time": "0:53:58", "throughput": 5879.97, "total_tokens": 3334632} {"current_steps": 5060, "total_steps": 33920, "loss": 0.631, "lr": 9.926607966938679e-06, "epoch": 2.983490566037736, "percentage": 14.92, "elapsed_time": "0:09:27", "remaining_time": "0:53:58", "throughput": 5881.0, "total_tokens": 3339048} {"current_steps": 5065, "total_steps": 33920, "loss": 0.3796, "lr": 9.926168130880103e-06, "epoch": 2.986438679245283, "percentage": 14.93, "elapsed_time": "0:09:28", "remaining_time": "0:53:57", "throughput": 5880.8, "total_tokens": 3341960} {"current_steps": 5070, "total_steps": 33920, "loss": 0.4301, "lr": 9.925726990597283e-06, "epoch": 2.98938679245283, "percentage": 14.95, "elapsed_time": "0:09:28", "remaining_time": "0:53:56", "throughput": 5881.3, "total_tokens": 3345448} {"current_steps": 5075, "total_steps": 33920, "loss": 0.5687, "lr": 9.925284546207015e-06, "epoch": 2.9923349056603774, "percentage": 14.96, "elapsed_time": "0:09:29", "remaining_time": "0:53:55", "throughput": 5881.19, "total_tokens": 3348168} {"current_steps": 5080, "total_steps": 33920, "loss": 0.6291, "lr": 9.924840797826436e-06, "epoch": 2.9952830188679247, "percentage": 14.98, "elapsed_time": "0:09:29", "remaining_time": "0:53:55", "throughput": 5882.34, "total_tokens": 3352584} {"current_steps": 5085, "total_steps": 33920, "loss": 0.4345, "lr": 9.924395745573029e-06, "epoch": 2.9982311320754715, "percentage": 14.99, "elapsed_time": "0:09:30", "remaining_time": "0:53:54", "throughput": 5883.17, "total_tokens": 3356264} {"current_steps": 5090, "total_steps": 33920, "loss": 0.6127, "lr": 9.923949389564629e-06, "epoch": 3.001179245283019, "percentage": 15.01, "elapsed_time": "0:09:31", "remaining_time": "0:53:55", "throughput": 5879.08, "total_tokens": 3358648} {"current_steps": 5095, "total_steps": 33920, "loss": 0.4606, "lr": 9.923501729919404e-06, "epoch": 3.004127358490566, "percentage": 15.02, "elapsed_time": "0:09:31", "remaining_time": "0:53:55", "throughput": 5879.6, "total_tokens": 3362520} {"current_steps": 5100, "total_steps": 33920, "loss": 0.4932, "lr": 9.923052766755878e-06, "epoch": 3.0070754716981134, "percentage": 15.04, "elapsed_time": "0:09:32", "remaining_time": "0:53:55", "throughput": 5880.42, "total_tokens": 3366776} {"current_steps": 5105, "total_steps": 33920, "loss": 0.6105, "lr": 9.922602500192914e-06, "epoch": 3.0100235849056602, "percentage": 15.05, "elapsed_time": "0:09:33", "remaining_time": "0:53:55", "throughput": 5880.97, "total_tokens": 3370776} {"current_steps": 5110, "total_steps": 33920, "loss": 0.5598, "lr": 9.922150930349725e-06, "epoch": 3.0129716981132075, "percentage": 15.06, "elapsed_time": "0:09:33", "remaining_time": "0:53:54", "throughput": 5881.34, "total_tokens": 3374040} {"current_steps": 5115, "total_steps": 33920, "loss": 0.5882, "lr": 9.921698057345863e-06, "epoch": 3.015919811320755, "percentage": 15.08, "elapsed_time": "0:09:34", "remaining_time": "0:53:53", "throughput": 5881.0, "total_tokens": 3376696} {"current_steps": 5120, "total_steps": 33920, "loss": 0.57, "lr": 9.921243881301229e-06, "epoch": 3.018867924528302, "percentage": 15.09, "elapsed_time": "0:09:34", "remaining_time": "0:53:52", "throughput": 5881.34, "total_tokens": 3380312} {"current_steps": 5125, "total_steps": 33920, "loss": 0.3741, "lr": 9.920788402336068e-06, "epoch": 3.021816037735849, "percentage": 15.11, "elapsed_time": "0:09:35", "remaining_time": "0:53:52", "throughput": 5881.2, "total_tokens": 3383384} {"current_steps": 5130, "total_steps": 33920, "loss": 0.5019, "lr": 9.92033162057097e-06, "epoch": 3.0247641509433962, "percentage": 15.12, "elapsed_time": "0:09:35", "remaining_time": "0:53:51", "throughput": 5880.36, "total_tokens": 3386008} {"current_steps": 5135, "total_steps": 33920, "loss": 0.4807, "lr": 9.919873536126869e-06, "epoch": 3.0277122641509435, "percentage": 15.14, "elapsed_time": "0:09:36", "remaining_time": "0:53:51", "throughput": 5879.66, "total_tokens": 3389048} {"current_steps": 5140, "total_steps": 33920, "loss": 0.3965, "lr": 9.919414149125046e-06, "epoch": 3.0306603773584904, "percentage": 15.15, "elapsed_time": "0:09:36", "remaining_time": "0:53:50", "throughput": 5879.7, "total_tokens": 3392024} {"current_steps": 5145, "total_steps": 33920, "loss": 0.4001, "lr": 9.918953459687126e-06, "epoch": 3.0336084905660377, "percentage": 15.17, "elapsed_time": "0:09:37", "remaining_time": "0:53:49", "throughput": 5880.39, "total_tokens": 3395864} {"current_steps": 5150, "total_steps": 33920, "loss": 0.4424, "lr": 9.918491467935078e-06, "epoch": 3.036556603773585, "percentage": 15.18, "elapsed_time": "0:09:38", "remaining_time": "0:53:49", "throughput": 5880.97, "total_tokens": 3399288} {"current_steps": 5155, "total_steps": 33920, "loss": 0.4176, "lr": 9.918028173991218e-06, "epoch": 3.0395047169811322, "percentage": 15.2, "elapsed_time": "0:09:38", "remaining_time": "0:53:48", "throughput": 5880.05, "total_tokens": 3401720} {"current_steps": 5160, "total_steps": 33920, "loss": 0.5423, "lr": 9.917563577978202e-06, "epoch": 3.042452830188679, "percentage": 15.21, "elapsed_time": "0:09:39", "remaining_time": "0:53:47", "throughput": 5880.39, "total_tokens": 3405336} {"current_steps": 5165, "total_steps": 33920, "loss": 0.4517, "lr": 9.917097680019035e-06, "epoch": 3.0454009433962264, "percentage": 15.23, "elapsed_time": "0:09:39", "remaining_time": "0:53:46", "throughput": 5880.48, "total_tokens": 3408440} {"current_steps": 5170, "total_steps": 33920, "loss": 0.507, "lr": 9.916630480237066e-06, "epoch": 3.0483490566037736, "percentage": 15.24, "elapsed_time": "0:09:40", "remaining_time": "0:53:46", "throughput": 5880.51, "total_tokens": 3411480} {"current_steps": 5175, "total_steps": 33920, "loss": 0.3844, "lr": 9.916161978755988e-06, "epoch": 3.051297169811321, "percentage": 15.26, "elapsed_time": "0:09:40", "remaining_time": "0:53:45", "throughput": 5880.69, "total_tokens": 3415128} {"current_steps": 5180, "total_steps": 33920, "loss": 0.4293, "lr": 9.915692175699838e-06, "epoch": 3.0542452830188678, "percentage": 15.27, "elapsed_time": "0:09:41", "remaining_time": "0:53:45", "throughput": 5881.37, "total_tokens": 3418936} {"current_steps": 5185, "total_steps": 33920, "loss": 0.6226, "lr": 9.915221071193e-06, "epoch": 3.057193396226415, "percentage": 15.29, "elapsed_time": "0:09:41", "remaining_time": "0:53:44", "throughput": 5881.53, "total_tokens": 3421912} {"current_steps": 5190, "total_steps": 33920, "loss": 0.4832, "lr": 9.914748665360199e-06, "epoch": 3.0601415094339623, "percentage": 15.3, "elapsed_time": "0:09:42", "remaining_time": "0:53:44", "throughput": 5882.3, "total_tokens": 3426008} {"current_steps": 5195, "total_steps": 33920, "loss": 0.5451, "lr": 9.914274958326507e-06, "epoch": 3.0630896226415096, "percentage": 15.32, "elapsed_time": "0:09:43", "remaining_time": "0:53:43", "throughput": 5882.75, "total_tokens": 3429656} {"current_steps": 5200, "total_steps": 33920, "loss": 0.4867, "lr": 9.913799950217341e-06, "epoch": 3.0660377358490565, "percentage": 15.33, "elapsed_time": "0:09:43", "remaining_time": "0:53:42", "throughput": 5882.66, "total_tokens": 3432760} {"current_steps": 5205, "total_steps": 33920, "loss": 0.4476, "lr": 9.91332364115846e-06, "epoch": 3.0689858490566038, "percentage": 15.34, "elapsed_time": "0:09:44", "remaining_time": "0:53:42", "throughput": 5882.75, "total_tokens": 3435800} {"current_steps": 5210, "total_steps": 33920, "loss": 0.4721, "lr": 9.912846031275972e-06, "epoch": 3.071933962264151, "percentage": 15.36, "elapsed_time": "0:09:44", "remaining_time": "0:53:41", "throughput": 5882.55, "total_tokens": 3439064} {"current_steps": 5215, "total_steps": 33920, "loss": 0.5042, "lr": 9.912367120696322e-06, "epoch": 3.074882075471698, "percentage": 15.37, "elapsed_time": "0:09:45", "remaining_time": "0:53:40", "throughput": 5882.35, "total_tokens": 3441976} {"current_steps": 5220, "total_steps": 33920, "loss": 0.4671, "lr": 9.911886909546307e-06, "epoch": 3.077830188679245, "percentage": 15.39, "elapsed_time": "0:09:45", "remaining_time": "0:53:40", "throughput": 5882.2, "total_tokens": 3445048} {"current_steps": 5225, "total_steps": 33920, "loss": 0.4114, "lr": 9.911405397953063e-06, "epoch": 3.0807783018867925, "percentage": 15.4, "elapsed_time": "0:09:46", "remaining_time": "0:53:39", "throughput": 5882.62, "total_tokens": 3448664} {"current_steps": 5230, "total_steps": 33920, "loss": 0.3941, "lr": 9.910922586044073e-06, "epoch": 3.0837264150943398, "percentage": 15.42, "elapsed_time": "0:09:46", "remaining_time": "0:53:38", "throughput": 5883.31, "total_tokens": 3452152} {"current_steps": 5235, "total_steps": 33920, "loss": 0.4591, "lr": 9.910438473947163e-06, "epoch": 3.0866745283018866, "percentage": 15.43, "elapsed_time": "0:09:47", "remaining_time": "0:53:38", "throughput": 5883.76, "total_tokens": 3455640} {"current_steps": 5240, "total_steps": 33920, "loss": 0.4339, "lr": 9.909953061790506e-06, "epoch": 3.089622641509434, "percentage": 15.45, "elapsed_time": "0:09:47", "remaining_time": "0:53:37", "throughput": 5882.95, "total_tokens": 3457976} {"current_steps": 5245, "total_steps": 33920, "loss": 0.5002, "lr": 9.909466349702613e-06, "epoch": 3.092570754716981, "percentage": 15.46, "elapsed_time": "0:09:48", "remaining_time": "0:53:36", "throughput": 5883.27, "total_tokens": 3461240} {"current_steps": 5250, "total_steps": 33920, "loss": 0.615, "lr": 9.908978337812348e-06, "epoch": 3.0955188679245285, "percentage": 15.48, "elapsed_time": "0:09:48", "remaining_time": "0:53:35", "throughput": 5883.11, "total_tokens": 3464216} {"current_steps": 5255, "total_steps": 33920, "loss": 0.5009, "lr": 9.908489026248909e-06, "epoch": 3.0984669811320753, "percentage": 15.49, "elapsed_time": "0:09:49", "remaining_time": "0:53:34", "throughput": 5882.14, "total_tokens": 3466392} {"current_steps": 5260, "total_steps": 33920, "loss": 0.5223, "lr": 9.907998415141846e-06, "epoch": 3.1014150943396226, "percentage": 15.51, "elapsed_time": "0:09:49", "remaining_time": "0:53:33", "throughput": 5882.33, "total_tokens": 3469464} {"current_steps": 5265, "total_steps": 33920, "loss": 0.5, "lr": 9.907506504621052e-06, "epoch": 3.10436320754717, "percentage": 15.52, "elapsed_time": "0:09:50", "remaining_time": "0:53:33", "throughput": 5883.33, "total_tokens": 3473688} {"current_steps": 5270, "total_steps": 33920, "loss": 0.5134, "lr": 9.907013294816759e-06, "epoch": 3.107311320754717, "percentage": 15.54, "elapsed_time": "0:09:50", "remaining_time": "0:53:32", "throughput": 5883.06, "total_tokens": 3476376} {"current_steps": 5275, "total_steps": 33920, "loss": 0.3746, "lr": 9.906518785859548e-06, "epoch": 3.110259433962264, "percentage": 15.55, "elapsed_time": "0:09:51", "remaining_time": "0:53:32", "throughput": 5884.02, "total_tokens": 3480824} {"current_steps": 5280, "total_steps": 33920, "loss": 0.5306, "lr": 9.906022977880344e-06, "epoch": 3.1132075471698113, "percentage": 15.57, "elapsed_time": "0:09:52", "remaining_time": "0:53:31", "throughput": 5884.52, "total_tokens": 3484184} {"current_steps": 5285, "total_steps": 33920, "loss": 0.4324, "lr": 9.905525871010412e-06, "epoch": 3.1161556603773586, "percentage": 15.58, "elapsed_time": "0:09:52", "remaining_time": "0:53:30", "throughput": 5884.1, "total_tokens": 3486744} {"current_steps": 5290, "total_steps": 33920, "loss": 0.4332, "lr": 9.905027465381363e-06, "epoch": 3.119103773584906, "percentage": 15.6, "elapsed_time": "0:09:53", "remaining_time": "0:53:29", "throughput": 5884.24, "total_tokens": 3489816} {"current_steps": 5295, "total_steps": 33920, "loss": 0.516, "lr": 9.904527761125155e-06, "epoch": 3.1220518867924527, "percentage": 15.61, "elapsed_time": "0:09:53", "remaining_time": "0:53:28", "throughput": 5884.0, "total_tokens": 3492568} {"current_steps": 5300, "total_steps": 33920, "loss": 0.4546, "lr": 9.904026758374083e-06, "epoch": 3.125, "percentage": 15.62, "elapsed_time": "0:09:54", "remaining_time": "0:53:28", "throughput": 5883.94, "total_tokens": 3495544} {"current_steps": 5305, "total_steps": 33920, "loss": 0.4462, "lr": 9.903524457260794e-06, "epoch": 3.1279481132075473, "percentage": 15.64, "elapsed_time": "0:09:54", "remaining_time": "0:53:27", "throughput": 5884.08, "total_tokens": 3499032} {"current_steps": 5310, "total_steps": 33920, "loss": 0.4447, "lr": 9.90302085791827e-06, "epoch": 3.1308962264150946, "percentage": 15.65, "elapsed_time": "0:09:55", "remaining_time": "0:53:26", "throughput": 5884.43, "total_tokens": 3502200} {"current_steps": 5315, "total_steps": 33920, "loss": 0.5396, "lr": 9.902515960479844e-06, "epoch": 3.1338443396226414, "percentage": 15.67, "elapsed_time": "0:09:55", "remaining_time": "0:53:26", "throughput": 5884.96, "total_tokens": 3505720} {"current_steps": 5320, "total_steps": 33920, "loss": 0.4462, "lr": 9.902009765079188e-06, "epoch": 3.1367924528301887, "percentage": 15.68, "elapsed_time": "0:09:56", "remaining_time": "0:53:25", "throughput": 5885.05, "total_tokens": 3509240} {"current_steps": 5325, "total_steps": 33920, "loss": 0.4725, "lr": 9.90150227185032e-06, "epoch": 3.139740566037736, "percentage": 15.7, "elapsed_time": "0:09:56", "remaining_time": "0:53:24", "throughput": 5884.04, "total_tokens": 3511640} {"current_steps": 5330, "total_steps": 33920, "loss": 0.4772, "lr": 9.900993480927603e-06, "epoch": 3.142688679245283, "percentage": 15.71, "elapsed_time": "0:09:57", "remaining_time": "0:53:24", "throughput": 5883.91, "total_tokens": 3514904} {"current_steps": 5335, "total_steps": 33920, "loss": 0.2791, "lr": 9.90048339244574e-06, "epoch": 3.14563679245283, "percentage": 15.73, "elapsed_time": "0:09:58", "remaining_time": "0:53:25", "throughput": 5884.83, "total_tokens": 3520536} {"current_steps": 5340, "total_steps": 33920, "loss": 0.5024, "lr": 9.899972006539776e-06, "epoch": 3.1485849056603774, "percentage": 15.74, "elapsed_time": "0:09:58", "remaining_time": "0:53:24", "throughput": 5885.11, "total_tokens": 3524120} {"current_steps": 5345, "total_steps": 33920, "loss": 0.3304, "lr": 9.899459323345106e-06, "epoch": 3.1515330188679247, "percentage": 15.76, "elapsed_time": "0:09:59", "remaining_time": "0:53:24", "throughput": 5885.44, "total_tokens": 3527480} {"current_steps": 5350, "total_steps": 33920, "loss": 0.5043, "lr": 9.898945342997467e-06, "epoch": 3.1544811320754715, "percentage": 15.77, "elapsed_time": "0:10:00", "remaining_time": "0:53:24", "throughput": 5886.51, "total_tokens": 3532216} {"current_steps": 5355, "total_steps": 33920, "loss": 0.4677, "lr": 9.898430065632933e-06, "epoch": 3.157429245283019, "percentage": 15.79, "elapsed_time": "0:10:00", "remaining_time": "0:53:23", "throughput": 5885.81, "total_tokens": 3534680} {"current_steps": 5360, "total_steps": 33920, "loss": 0.4903, "lr": 9.897913491387929e-06, "epoch": 3.160377358490566, "percentage": 15.8, "elapsed_time": "0:10:01", "remaining_time": "0:53:22", "throughput": 5885.59, "total_tokens": 3537592} {"current_steps": 5365, "total_steps": 33920, "loss": 0.3865, "lr": 9.897395620399219e-06, "epoch": 3.1633254716981134, "percentage": 15.82, "elapsed_time": "0:10:01", "remaining_time": "0:53:21", "throughput": 5885.09, "total_tokens": 3540248} {"current_steps": 5370, "total_steps": 33920, "loss": 0.4733, "lr": 9.896876452803913e-06, "epoch": 3.1662735849056602, "percentage": 15.83, "elapsed_time": "0:10:02", "remaining_time": "0:53:21", "throughput": 5885.11, "total_tokens": 3543512} {"current_steps": 5375, "total_steps": 33920, "loss": 0.3976, "lr": 9.896355988739461e-06, "epoch": 3.1692216981132075, "percentage": 15.85, "elapsed_time": "0:10:02", "remaining_time": "0:53:20", "throughput": 5885.03, "total_tokens": 3546488} {"current_steps": 5380, "total_steps": 33920, "loss": 0.4173, "lr": 9.895834228343658e-06, "epoch": 3.172169811320755, "percentage": 15.86, "elapsed_time": "0:10:03", "remaining_time": "0:53:19", "throughput": 5884.11, "total_tokens": 3548888} {"current_steps": 5385, "total_steps": 33920, "loss": 0.552, "lr": 9.895311171754644e-06, "epoch": 3.175117924528302, "percentage": 15.88, "elapsed_time": "0:10:03", "remaining_time": "0:53:18", "throughput": 5883.93, "total_tokens": 3551800} {"current_steps": 5390, "total_steps": 33920, "loss": 0.5465, "lr": 9.8947868191109e-06, "epoch": 3.178066037735849, "percentage": 15.89, "elapsed_time": "0:10:04", "remaining_time": "0:53:18", "throughput": 5883.66, "total_tokens": 3554904} {"current_steps": 5395, "total_steps": 33920, "loss": 0.457, "lr": 9.894261170551249e-06, "epoch": 3.1810141509433962, "percentage": 15.91, "elapsed_time": "0:10:04", "remaining_time": "0:53:17", "throughput": 5884.64, "total_tokens": 3559160} {"current_steps": 5400, "total_steps": 33920, "loss": 0.4234, "lr": 9.893734226214861e-06, "epoch": 3.1839622641509435, "percentage": 15.92, "elapsed_time": "0:10:05", "remaining_time": "0:53:17", "throughput": 5884.83, "total_tokens": 3562712} {"current_steps": 5405, "total_steps": 33920, "loss": 0.5334, "lr": 9.893205986241246e-06, "epoch": 3.1869103773584904, "percentage": 15.93, "elapsed_time": "0:10:05", "remaining_time": "0:53:16", "throughput": 5885.07, "total_tokens": 3566040} {"current_steps": 5410, "total_steps": 33920, "loss": 0.464, "lr": 9.892676450770257e-06, "epoch": 3.1898584905660377, "percentage": 15.95, "elapsed_time": "0:10:06", "remaining_time": "0:53:16", "throughput": 5885.76, "total_tokens": 3569976} {"current_steps": 5415, "total_steps": 33920, "loss": 0.5705, "lr": 9.892145619942092e-06, "epoch": 3.192806603773585, "percentage": 15.96, "elapsed_time": "0:10:07", "remaining_time": "0:53:15", "throughput": 5885.91, "total_tokens": 3572984} {"current_steps": 5420, "total_steps": 33920, "loss": 0.4542, "lr": 9.891613493897289e-06, "epoch": 3.1957547169811322, "percentage": 15.98, "elapsed_time": "0:10:07", "remaining_time": "0:53:14", "throughput": 5886.44, "total_tokens": 3576408} {"current_steps": 5425, "total_steps": 33920, "loss": 0.4925, "lr": 9.891080072776733e-06, "epoch": 3.198702830188679, "percentage": 15.99, "elapsed_time": "0:10:08", "remaining_time": "0:53:14", "throughput": 5885.99, "total_tokens": 3579608} {"current_steps": 5430, "total_steps": 33920, "loss": 0.4849, "lr": 9.890545356721649e-06, "epoch": 3.2016509433962264, "percentage": 16.01, "elapsed_time": "0:10:08", "remaining_time": "0:53:13", "throughput": 5886.13, "total_tokens": 3582552} {"current_steps": 5435, "total_steps": 33920, "loss": 0.4255, "lr": 9.890009345873603e-06, "epoch": 3.2045990566037736, "percentage": 16.02, "elapsed_time": "0:10:09", "remaining_time": "0:53:12", "throughput": 5886.08, "total_tokens": 3585528} {"current_steps": 5440, "total_steps": 33920, "loss": 0.4862, "lr": 9.889472040374509e-06, "epoch": 3.207547169811321, "percentage": 16.04, "elapsed_time": "0:10:09", "remaining_time": "0:53:12", "throughput": 5886.53, "total_tokens": 3589624} {"current_steps": 5445, "total_steps": 33920, "loss": 0.4965, "lr": 9.88893344036662e-06, "epoch": 3.2104952830188678, "percentage": 16.05, "elapsed_time": "0:10:10", "remaining_time": "0:53:12", "throughput": 5886.87, "total_tokens": 3593496} {"current_steps": 5450, "total_steps": 33920, "loss": 0.4272, "lr": 9.888393545992531e-06, "epoch": 3.213443396226415, "percentage": 16.07, "elapsed_time": "0:10:10", "remaining_time": "0:53:11", "throughput": 5887.08, "total_tokens": 3596760} {"current_steps": 5455, "total_steps": 33920, "loss": 0.7132, "lr": 9.887852357395184e-06, "epoch": 3.2163915094339623, "percentage": 16.08, "elapsed_time": "0:10:11", "remaining_time": "0:53:11", "throughput": 5887.75, "total_tokens": 3600664} {"current_steps": 5460, "total_steps": 33920, "loss": 0.4846, "lr": 9.88730987471786e-06, "epoch": 3.2193396226415096, "percentage": 16.1, "elapsed_time": "0:10:12", "remaining_time": "0:53:10", "throughput": 5887.94, "total_tokens": 3604312} {"current_steps": 5465, "total_steps": 33920, "loss": 0.3827, "lr": 9.886766098104183e-06, "epoch": 3.2222877358490565, "percentage": 16.11, "elapsed_time": "0:10:12", "remaining_time": "0:53:10", "throughput": 5888.53, "total_tokens": 3608088} {"current_steps": 5470, "total_steps": 33920, "loss": 0.6941, "lr": 9.886221027698122e-06, "epoch": 3.2252358490566038, "percentage": 16.13, "elapsed_time": "0:10:13", "remaining_time": "0:53:09", "throughput": 5888.34, "total_tokens": 3610808} {"current_steps": 5475, "total_steps": 33920, "loss": 0.4603, "lr": 9.885674663643983e-06, "epoch": 3.228183962264151, "percentage": 16.14, "elapsed_time": "0:10:13", "remaining_time": "0:53:08", "throughput": 5888.95, "total_tokens": 3614680} {"current_steps": 5480, "total_steps": 33920, "loss": 0.6486, "lr": 9.885127006086423e-06, "epoch": 3.231132075471698, "percentage": 16.16, "elapsed_time": "0:10:14", "remaining_time": "0:53:08", "throughput": 5889.34, "total_tokens": 3617912} {"current_steps": 5485, "total_steps": 33920, "loss": 0.4348, "lr": 9.884578055170434e-06, "epoch": 3.234080188679245, "percentage": 16.17, "elapsed_time": "0:10:15", "remaining_time": "0:53:09", "throughput": 5890.02, "total_tokens": 3623800} {"current_steps": 5490, "total_steps": 33920, "loss": 0.4832, "lr": 9.884027811041353e-06, "epoch": 3.2370283018867925, "percentage": 16.19, "elapsed_time": "0:10:15", "remaining_time": "0:53:09", "throughput": 5889.2, "total_tokens": 3626744} {"current_steps": 5495, "total_steps": 33920, "loss": 0.3492, "lr": 9.883476273844861e-06, "epoch": 3.2399764150943398, "percentage": 16.2, "elapsed_time": "0:10:16", "remaining_time": "0:53:08", "throughput": 5889.34, "total_tokens": 3629880} {"current_steps": 5500, "total_steps": 33920, "loss": 0.4926, "lr": 9.882923443726977e-06, "epoch": 3.2429245283018866, "percentage": 16.21, "elapsed_time": "0:10:16", "remaining_time": "0:53:07", "throughput": 5889.29, "total_tokens": 3632792} {"current_steps": 5505, "total_steps": 33920, "loss": 0.5218, "lr": 9.882369320834068e-06, "epoch": 3.245872641509434, "percentage": 16.23, "elapsed_time": "0:10:17", "remaining_time": "0:53:08", "throughput": 5890.61, "total_tokens": 3638232} {"current_steps": 5510, "total_steps": 33920, "loss": 0.6092, "lr": 9.88181390531284e-06, "epoch": 3.248820754716981, "percentage": 16.24, "elapsed_time": "0:10:18", "remaining_time": "0:53:07", "throughput": 5890.16, "total_tokens": 3640920} {"current_steps": 5515, "total_steps": 33920, "loss": 0.3874, "lr": 9.88125719731034e-06, "epoch": 3.2517688679245285, "percentage": 16.26, "elapsed_time": "0:10:18", "remaining_time": "0:53:06", "throughput": 5890.62, "total_tokens": 3644344} {"current_steps": 5520, "total_steps": 33920, "loss": 0.4581, "lr": 9.880699196973962e-06, "epoch": 3.2547169811320753, "percentage": 16.27, "elapsed_time": "0:10:19", "remaining_time": "0:53:05", "throughput": 5890.16, "total_tokens": 3647160} {"current_steps": 5525, "total_steps": 33920, "loss": 0.6643, "lr": 9.880139904451436e-06, "epoch": 3.2576650943396226, "percentage": 16.29, "elapsed_time": "0:10:19", "remaining_time": "0:53:04", "throughput": 5890.15, "total_tokens": 3650040} {"current_steps": 5530, "total_steps": 33920, "loss": 0.4169, "lr": 9.879579319890838e-06, "epoch": 3.26061320754717, "percentage": 16.3, "elapsed_time": "0:10:20", "remaining_time": "0:53:04", "throughput": 5889.72, "total_tokens": 3652824} {"current_steps": 5535, "total_steps": 33920, "loss": 0.5452, "lr": 9.879017443440584e-06, "epoch": 3.263561320754717, "percentage": 16.32, "elapsed_time": "0:10:20", "remaining_time": "0:53:03", "throughput": 5890.58, "total_tokens": 3657080} {"current_steps": 5540, "total_steps": 33920, "loss": 0.348, "lr": 9.878454275249436e-06, "epoch": 3.266509433962264, "percentage": 16.33, "elapsed_time": "0:10:21", "remaining_time": "0:53:03", "throughput": 5890.62, "total_tokens": 3660248} {"current_steps": 5545, "total_steps": 33920, "loss": 0.6093, "lr": 9.877889815466493e-06, "epoch": 3.2694575471698113, "percentage": 16.35, "elapsed_time": "0:10:21", "remaining_time": "0:53:02", "throughput": 5890.48, "total_tokens": 3663352} {"current_steps": 5550, "total_steps": 33920, "loss": 0.4911, "lr": 9.877324064241198e-06, "epoch": 3.2724056603773586, "percentage": 16.36, "elapsed_time": "0:10:22", "remaining_time": "0:53:01", "throughput": 5890.95, "total_tokens": 3666616} {"current_steps": 5555, "total_steps": 33920, "loss": 0.5634, "lr": 9.876757021723338e-06, "epoch": 3.2753537735849054, "percentage": 16.38, "elapsed_time": "0:10:22", "remaining_time": "0:53:00", "throughput": 5890.98, "total_tokens": 3669560} {"current_steps": 5560, "total_steps": 33920, "loss": 0.4424, "lr": 9.876188688063038e-06, "epoch": 3.2783018867924527, "percentage": 16.39, "elapsed_time": "0:10:23", "remaining_time": "0:53:00", "throughput": 5890.61, "total_tokens": 3672536} {"current_steps": 5565, "total_steps": 33920, "loss": 0.5248, "lr": 9.875619063410768e-06, "epoch": 3.28125, "percentage": 16.41, "elapsed_time": "0:10:23", "remaining_time": "0:52:59", "throughput": 5891.07, "total_tokens": 3675960} {"current_steps": 5570, "total_steps": 33920, "loss": 0.3852, "lr": 9.875048147917339e-06, "epoch": 3.2841981132075473, "percentage": 16.42, "elapsed_time": "0:10:24", "remaining_time": "0:52:58", "throughput": 5891.05, "total_tokens": 3679384} {"current_steps": 5575, "total_steps": 33920, "loss": 0.4924, "lr": 9.874475941733902e-06, "epoch": 3.2871462264150946, "percentage": 16.44, "elapsed_time": "0:10:25", "remaining_time": "0:52:57", "throughput": 5890.77, "total_tokens": 3681976} {"current_steps": 5580, "total_steps": 33920, "loss": 0.4218, "lr": 9.873902445011952e-06, "epoch": 3.2900943396226414, "percentage": 16.45, "elapsed_time": "0:10:25", "remaining_time": "0:52:57", "throughput": 5891.93, "total_tokens": 3686488} {"current_steps": 5585, "total_steps": 33920, "loss": 0.4233, "lr": 9.873327657903324e-06, "epoch": 3.2930424528301887, "percentage": 16.47, "elapsed_time": "0:10:26", "remaining_time": "0:52:57", "throughput": 5892.2, "total_tokens": 3689848} {"current_steps": 5590, "total_steps": 33920, "loss": 0.4953, "lr": 9.872751580560194e-06, "epoch": 3.295990566037736, "percentage": 16.48, "elapsed_time": "0:10:26", "remaining_time": "0:52:56", "throughput": 5892.53, "total_tokens": 3693368} {"current_steps": 5595, "total_steps": 33920, "loss": 0.4239, "lr": 9.872174213135084e-06, "epoch": 3.298938679245283, "percentage": 16.49, "elapsed_time": "0:10:27", "remaining_time": "0:52:55", "throughput": 5892.59, "total_tokens": 3696664} {"current_steps": 5600, "total_steps": 33920, "loss": 0.4299, "lr": 9.871595555780855e-06, "epoch": 3.30188679245283, "percentage": 16.51, "elapsed_time": "0:10:27", "remaining_time": "0:52:55", "throughput": 5892.06, "total_tokens": 3699480} {"current_steps": 5605, "total_steps": 33920, "loss": 0.375, "lr": 9.871015608650705e-06, "epoch": 3.3048349056603774, "percentage": 16.52, "elapsed_time": "0:10:28", "remaining_time": "0:52:54", "throughput": 5891.74, "total_tokens": 3702328} {"current_steps": 5610, "total_steps": 33920, "loss": 0.4242, "lr": 9.870434371898182e-06, "epoch": 3.3077830188679247, "percentage": 16.54, "elapsed_time": "0:10:29", "remaining_time": "0:52:54", "throughput": 5892.85, "total_tokens": 3706712} {"current_steps": 5615, "total_steps": 33920, "loss": 0.4119, "lr": 9.869851845677165e-06, "epoch": 3.3107311320754715, "percentage": 16.55, "elapsed_time": "0:10:29", "remaining_time": "0:52:53", "throughput": 5892.73, "total_tokens": 3709464} {"current_steps": 5620, "total_steps": 33920, "loss": 0.5093, "lr": 9.869268030141886e-06, "epoch": 3.313679245283019, "percentage": 16.57, "elapsed_time": "0:10:29", "remaining_time": "0:52:52", "throughput": 5892.26, "total_tokens": 3712088} {"current_steps": 5625, "total_steps": 33920, "loss": 0.5983, "lr": 9.86868292544691e-06, "epoch": 3.316627358490566, "percentage": 16.58, "elapsed_time": "0:10:30", "remaining_time": "0:52:51", "throughput": 5891.61, "total_tokens": 3714744} {"current_steps": 5630, "total_steps": 33920, "loss": 0.3779, "lr": 9.868096531747149e-06, "epoch": 3.3195754716981134, "percentage": 16.6, "elapsed_time": "0:10:31", "remaining_time": "0:52:50", "throughput": 5891.04, "total_tokens": 3717432} {"current_steps": 5635, "total_steps": 33920, "loss": 0.6017, "lr": 9.867508849197848e-06, "epoch": 3.3225235849056602, "percentage": 16.61, "elapsed_time": "0:10:31", "remaining_time": "0:52:50", "throughput": 5891.59, "total_tokens": 3721336} {"current_steps": 5640, "total_steps": 33920, "loss": 0.3692, "lr": 9.866919877954602e-06, "epoch": 3.3254716981132075, "percentage": 16.63, "elapsed_time": "0:10:32", "remaining_time": "0:52:49", "throughput": 5891.4, "total_tokens": 3723960} {"current_steps": 5645, "total_steps": 33920, "loss": 0.5357, "lr": 9.866329618173344e-06, "epoch": 3.328419811320755, "percentage": 16.64, "elapsed_time": "0:10:32", "remaining_time": "0:52:49", "throughput": 5891.98, "total_tokens": 3727736} {"current_steps": 5650, "total_steps": 33920, "loss": 0.4942, "lr": 9.865738070010346e-06, "epoch": 3.331367924528302, "percentage": 16.66, "elapsed_time": "0:10:33", "remaining_time": "0:52:48", "throughput": 5891.86, "total_tokens": 3731256} {"current_steps": 5655, "total_steps": 33920, "loss": 0.4271, "lr": 9.865145233622223e-06, "epoch": 3.334316037735849, "percentage": 16.67, "elapsed_time": "0:10:33", "remaining_time": "0:52:48", "throughput": 5892.02, "total_tokens": 3734616} {"current_steps": 5660, "total_steps": 33920, "loss": 0.5426, "lr": 9.864551109165935e-06, "epoch": 3.3372641509433962, "percentage": 16.69, "elapsed_time": "0:10:34", "remaining_time": "0:52:47", "throughput": 5892.14, "total_tokens": 3738072} {"current_steps": 5665, "total_steps": 33920, "loss": 0.416, "lr": 9.863955696798773e-06, "epoch": 3.3402122641509435, "percentage": 16.7, "elapsed_time": "0:10:34", "remaining_time": "0:52:46", "throughput": 5891.52, "total_tokens": 3740536} {"current_steps": 5670, "total_steps": 33920, "loss": 0.487, "lr": 9.863358996678378e-06, "epoch": 3.3431603773584904, "percentage": 16.72, "elapsed_time": "0:10:35", "remaining_time": "0:52:45", "throughput": 5890.34, "total_tokens": 3742712} {"current_steps": 5675, "total_steps": 33920, "loss": 0.5276, "lr": 9.86276100896273e-06, "epoch": 3.3461084905660377, "percentage": 16.73, "elapsed_time": "0:10:35", "remaining_time": "0:52:45", "throughput": 5889.86, "total_tokens": 3745560} {"current_steps": 5680, "total_steps": 33920, "loss": 0.415, "lr": 9.862161733810147e-06, "epoch": 3.349056603773585, "percentage": 16.75, "elapsed_time": "0:10:36", "remaining_time": "0:52:44", "throughput": 5890.63, "total_tokens": 3749880} {"current_steps": 5685, "total_steps": 33920, "loss": 0.4606, "lr": 9.86156117137929e-06, "epoch": 3.3520047169811322, "percentage": 16.76, "elapsed_time": "0:10:37", "remaining_time": "0:52:44", "throughput": 5890.64, "total_tokens": 3753400} {"current_steps": 5690, "total_steps": 33920, "loss": 0.3834, "lr": 9.860959321829159e-06, "epoch": 3.354952830188679, "percentage": 16.77, "elapsed_time": "0:10:37", "remaining_time": "0:52:44", "throughput": 5891.29, "total_tokens": 3757272} {"current_steps": 5695, "total_steps": 33920, "loss": 0.3978, "lr": 9.860356185319102e-06, "epoch": 3.3579009433962264, "percentage": 16.79, "elapsed_time": "0:10:38", "remaining_time": "0:52:44", "throughput": 5892.21, "total_tokens": 3761848} {"current_steps": 5700, "total_steps": 33920, "loss": 0.3167, "lr": 9.859751762008796e-06, "epoch": 3.3608490566037736, "percentage": 16.8, "elapsed_time": "0:10:38", "remaining_time": "0:52:43", "throughput": 5892.65, "total_tokens": 3765208} {"current_steps": 5705, "total_steps": 33920, "loss": 0.2923, "lr": 9.859146052058266e-06, "epoch": 3.363797169811321, "percentage": 16.82, "elapsed_time": "0:10:39", "remaining_time": "0:52:42", "throughput": 5892.55, "total_tokens": 3768056} {"current_steps": 5710, "total_steps": 33920, "loss": 0.5204, "lr": 9.858539055627876e-06, "epoch": 3.3667452830188678, "percentage": 16.83, "elapsed_time": "0:10:40", "remaining_time": "0:52:42", "throughput": 5893.09, "total_tokens": 3771736} {"current_steps": 5715, "total_steps": 33920, "loss": 0.455, "lr": 9.857930772878333e-06, "epoch": 3.369693396226415, "percentage": 16.85, "elapsed_time": "0:10:40", "remaining_time": "0:52:41", "throughput": 5892.68, "total_tokens": 3774680} {"current_steps": 5720, "total_steps": 33920, "loss": 0.4225, "lr": 9.857321203970682e-06, "epoch": 3.3726415094339623, "percentage": 16.86, "elapsed_time": "0:10:41", "remaining_time": "0:52:40", "throughput": 5892.98, "total_tokens": 3778168} {"current_steps": 5725, "total_steps": 33920, "loss": 0.392, "lr": 9.856710349066307e-06, "epoch": 3.3755896226415096, "percentage": 16.88, "elapsed_time": "0:10:41", "remaining_time": "0:52:39", "throughput": 5892.69, "total_tokens": 3780856} {"current_steps": 5730, "total_steps": 33920, "loss": 0.4486, "lr": 9.856098208326937e-06, "epoch": 3.3785377358490565, "percentage": 16.89, "elapsed_time": "0:10:42", "remaining_time": "0:52:39", "throughput": 5892.95, "total_tokens": 3783960} {"current_steps": 5735, "total_steps": 33920, "loss": 0.4567, "lr": 9.855484781914639e-06, "epoch": 3.3814858490566038, "percentage": 16.91, "elapsed_time": "0:10:42", "remaining_time": "0:52:38", "throughput": 5893.02, "total_tokens": 3786936} {"current_steps": 5740, "total_steps": 33920, "loss": 0.509, "lr": 9.854870069991817e-06, "epoch": 3.384433962264151, "percentage": 16.92, "elapsed_time": "0:10:43", "remaining_time": "0:52:37", "throughput": 5893.46, "total_tokens": 3790712} {"current_steps": 5745, "total_steps": 33920, "loss": 0.475, "lr": 9.854254072721222e-06, "epoch": 3.387382075471698, "percentage": 16.94, "elapsed_time": "0:10:43", "remaining_time": "0:52:38", "throughput": 5894.63, "total_tokens": 3795864} {"current_steps": 5750, "total_steps": 33920, "loss": 0.4216, "lr": 9.853636790265938e-06, "epoch": 3.390330188679245, "percentage": 16.95, "elapsed_time": "0:10:44", "remaining_time": "0:52:37", "throughput": 5894.89, "total_tokens": 3799448} {"current_steps": 5755, "total_steps": 33920, "loss": 0.4959, "lr": 9.853018222789397e-06, "epoch": 3.3932783018867925, "percentage": 16.97, "elapsed_time": "0:10:45", "remaining_time": "0:52:37", "throughput": 5894.46, "total_tokens": 3802552} {"current_steps": 5760, "total_steps": 33920, "loss": 0.4481, "lr": 9.852398370455367e-06, "epoch": 3.3962264150943398, "percentage": 16.98, "elapsed_time": "0:10:45", "remaining_time": "0:52:37", "throughput": 5895.54, "total_tokens": 3807544} {"current_steps": 5765, "total_steps": 33920, "loss": 0.448, "lr": 9.851777233427955e-06, "epoch": 3.3991745283018866, "percentage": 17.0, "elapsed_time": "0:10:46", "remaining_time": "0:52:36", "throughput": 5895.82, "total_tokens": 3810840} {"current_steps": 5770, "total_steps": 33920, "loss": 0.4949, "lr": 9.85115481187161e-06, "epoch": 3.402122641509434, "percentage": 17.01, "elapsed_time": "0:10:46", "remaining_time": "0:52:35", "throughput": 5895.79, "total_tokens": 3813656} {"current_steps": 5775, "total_steps": 33920, "loss": 0.5965, "lr": 9.850531105951123e-06, "epoch": 3.405070754716981, "percentage": 17.03, "elapsed_time": "0:10:47", "remaining_time": "0:52:35", "throughput": 5895.29, "total_tokens": 3816632} {"current_steps": 5780, "total_steps": 33920, "loss": 0.4988, "lr": 9.84990611583162e-06, "epoch": 3.4080188679245285, "percentage": 17.04, "elapsed_time": "0:10:47", "remaining_time": "0:52:34", "throughput": 5895.47, "total_tokens": 3820024} {"current_steps": 5785, "total_steps": 33920, "loss": 0.4874, "lr": 9.849279841678572e-06, "epoch": 3.4109669811320753, "percentage": 17.05, "elapsed_time": "0:10:48", "remaining_time": "0:52:33", "throughput": 5895.65, "total_tokens": 3823160} {"current_steps": 5790, "total_steps": 33920, "loss": 0.5397, "lr": 9.848652283657785e-06, "epoch": 3.4139150943396226, "percentage": 17.07, "elapsed_time": "0:10:49", "remaining_time": "0:52:33", "throughput": 5896.21, "total_tokens": 3826904} {"current_steps": 5795, "total_steps": 33920, "loss": 0.5086, "lr": 9.848023441935411e-06, "epoch": 3.41686320754717, "percentage": 17.08, "elapsed_time": "0:10:49", "remaining_time": "0:52:32", "throughput": 5896.59, "total_tokens": 3830552} {"current_steps": 5800, "total_steps": 33920, "loss": 0.5073, "lr": 9.847393316677935e-06, "epoch": 3.419811320754717, "percentage": 17.1, "elapsed_time": "0:10:50", "remaining_time": "0:52:32", "throughput": 5896.7, "total_tokens": 3833944} {"current_steps": 5805, "total_steps": 33920, "loss": 0.6502, "lr": 9.846761908052188e-06, "epoch": 3.422759433962264, "percentage": 17.11, "elapsed_time": "0:10:50", "remaining_time": "0:52:31", "throughput": 5896.87, "total_tokens": 3837176} {"current_steps": 5810, "total_steps": 33920, "loss": 0.3878, "lr": 9.846129216225338e-06, "epoch": 3.4257075471698113, "percentage": 17.13, "elapsed_time": "0:10:51", "remaining_time": "0:52:31", "throughput": 5897.55, "total_tokens": 3841528} {"current_steps": 5815, "total_steps": 33920, "loss": 0.4118, "lr": 9.845495241364892e-06, "epoch": 3.4286556603773586, "percentage": 17.14, "elapsed_time": "0:10:51", "remaining_time": "0:52:30", "throughput": 5898.17, "total_tokens": 3845304} {"current_steps": 5820, "total_steps": 33920, "loss": 0.6545, "lr": 9.844859983638696e-06, "epoch": 3.4316037735849054, "percentage": 17.16, "elapsed_time": "0:10:52", "remaining_time": "0:52:30", "throughput": 5897.65, "total_tokens": 3847992} {"current_steps": 5825, "total_steps": 33920, "loss": 0.5724, "lr": 9.844223443214942e-06, "epoch": 3.4345518867924527, "percentage": 17.17, "elapsed_time": "0:10:53", "remaining_time": "0:52:29", "throughput": 5898.34, "total_tokens": 3851896} {"current_steps": 5830, "total_steps": 33920, "loss": 0.531, "lr": 9.843585620262153e-06, "epoch": 3.4375, "percentage": 17.19, "elapsed_time": "0:10:53", "remaining_time": "0:52:29", "throughput": 5898.73, "total_tokens": 3855448} {"current_steps": 5835, "total_steps": 33920, "loss": 0.4917, "lr": 9.842946514949197e-06, "epoch": 3.4404481132075473, "percentage": 17.2, "elapsed_time": "0:10:54", "remaining_time": "0:52:28", "throughput": 5898.29, "total_tokens": 3858040} {"current_steps": 5840, "total_steps": 33920, "loss": 0.3642, "lr": 9.842306127445279e-06, "epoch": 3.4433962264150946, "percentage": 17.22, "elapsed_time": "0:10:54", "remaining_time": "0:52:27", "throughput": 5897.93, "total_tokens": 3860536} {"current_steps": 5845, "total_steps": 33920, "loss": 0.4526, "lr": 9.841664457919944e-06, "epoch": 3.4463443396226414, "percentage": 17.23, "elapsed_time": "0:10:55", "remaining_time": "0:52:26", "throughput": 5897.88, "total_tokens": 3863416} {"current_steps": 5850, "total_steps": 33920, "loss": 0.468, "lr": 9.841021506543079e-06, "epoch": 3.4492924528301887, "percentage": 17.25, "elapsed_time": "0:10:55", "remaining_time": "0:52:25", "throughput": 5897.78, "total_tokens": 3866296} {"current_steps": 5855, "total_steps": 33920, "loss": 0.5662, "lr": 9.840377273484904e-06, "epoch": 3.452240566037736, "percentage": 17.26, "elapsed_time": "0:10:56", "remaining_time": "0:52:24", "throughput": 5897.87, "total_tokens": 3869400} {"current_steps": 5860, "total_steps": 33920, "loss": 0.5525, "lr": 9.839731758915986e-06, "epoch": 3.455188679245283, "percentage": 17.28, "elapsed_time": "0:10:56", "remaining_time": "0:52:23", "throughput": 5898.27, "total_tokens": 3872632} {"current_steps": 5865, "total_steps": 33920, "loss": 0.3634, "lr": 9.839084963007226e-06, "epoch": 3.45813679245283, "percentage": 17.29, "elapsed_time": "0:10:57", "remaining_time": "0:52:23", "throughput": 5898.46, "total_tokens": 3875800} {"current_steps": 5870, "total_steps": 33920, "loss": 0.4765, "lr": 9.838436885929868e-06, "epoch": 3.4610849056603774, "percentage": 17.31, "elapsed_time": "0:10:57", "remaining_time": "0:52:22", "throughput": 5898.08, "total_tokens": 3878520} {"current_steps": 5875, "total_steps": 33920, "loss": 0.5723, "lr": 9.837787527855492e-06, "epoch": 3.4640330188679247, "percentage": 17.32, "elapsed_time": "0:10:58", "remaining_time": "0:52:22", "throughput": 5898.47, "total_tokens": 3882424} {"current_steps": 5880, "total_steps": 33920, "loss": 0.4035, "lr": 9.837136888956017e-06, "epoch": 3.4669811320754715, "percentage": 17.33, "elapsed_time": "0:10:58", "remaining_time": "0:52:21", "throughput": 5898.58, "total_tokens": 3885464} {"current_steps": 5885, "total_steps": 33920, "loss": 0.5837, "lr": 9.836484969403705e-06, "epoch": 3.469929245283019, "percentage": 17.35, "elapsed_time": "0:10:59", "remaining_time": "0:52:20", "throughput": 5898.44, "total_tokens": 3888408} {"current_steps": 5890, "total_steps": 33920, "loss": 0.4073, "lr": 9.835831769371152e-06, "epoch": 3.472877358490566, "percentage": 17.36, "elapsed_time": "0:10:59", "remaining_time": "0:52:19", "throughput": 5899.0, "total_tokens": 3891960} {"current_steps": 5895, "total_steps": 33920, "loss": 0.5154, "lr": 9.835177289031298e-06, "epoch": 3.4758254716981134, "percentage": 17.38, "elapsed_time": "0:11:00", "remaining_time": "0:52:19", "throughput": 5899.48, "total_tokens": 3896344} {"current_steps": 5900, "total_steps": 33920, "loss": 0.5181, "lr": 9.834521528557419e-06, "epoch": 3.4787735849056602, "percentage": 17.39, "elapsed_time": "0:11:00", "remaining_time": "0:52:18", "throughput": 5899.15, "total_tokens": 3899096} {"current_steps": 5905, "total_steps": 33920, "loss": 0.4399, "lr": 9.833864488123128e-06, "epoch": 3.4817216981132075, "percentage": 17.41, "elapsed_time": "0:11:01", "remaining_time": "0:52:18", "throughput": 5898.77, "total_tokens": 3901976} {"current_steps": 5910, "total_steps": 33920, "loss": 0.4321, "lr": 9.83320616790238e-06, "epoch": 3.484669811320755, "percentage": 17.42, "elapsed_time": "0:11:02", "remaining_time": "0:52:18", "throughput": 5899.07, "total_tokens": 3905848} {"current_steps": 5915, "total_steps": 33920, "loss": 0.4312, "lr": 9.832546568069472e-06, "epoch": 3.487617924528302, "percentage": 17.44, "elapsed_time": "0:11:02", "remaining_time": "0:52:17", "throughput": 5899.39, "total_tokens": 3909720} {"current_steps": 5920, "total_steps": 33920, "loss": 0.5204, "lr": 9.831885688799031e-06, "epoch": 3.490566037735849, "percentage": 17.45, "elapsed_time": "0:11:03", "remaining_time": "0:52:17", "throughput": 5899.16, "total_tokens": 3912664} {"current_steps": 5925, "total_steps": 33920, "loss": 0.4592, "lr": 9.83122353026603e-06, "epoch": 3.4935141509433962, "percentage": 17.47, "elapsed_time": "0:11:04", "remaining_time": "0:52:19", "throughput": 5899.82, "total_tokens": 3919608} {"current_steps": 5930, "total_steps": 33920, "loss": 0.3905, "lr": 9.830560092645778e-06, "epoch": 3.4964622641509435, "percentage": 17.48, "elapsed_time": "0:11:04", "remaining_time": "0:52:18", "throughput": 5899.3, "total_tokens": 3922136} {"current_steps": 5935, "total_steps": 33920, "loss": 0.4778, "lr": 9.829895376113923e-06, "epoch": 3.4994103773584904, "percentage": 17.5, "elapsed_time": "0:11:05", "remaining_time": "0:52:17", "throughput": 5898.66, "total_tokens": 3924536} {"current_steps": 5940, "total_steps": 33920, "loss": 0.5404, "lr": 9.829229380846452e-06, "epoch": 3.5023584905660377, "percentage": 17.51, "elapsed_time": "0:11:05", "remaining_time": "0:52:16", "throughput": 5897.77, "total_tokens": 3927224} {"current_steps": 5945, "total_steps": 33920, "loss": 0.577, "lr": 9.82856210701969e-06, "epoch": 3.505306603773585, "percentage": 17.53, "elapsed_time": "0:11:06", "remaining_time": "0:52:15", "throughput": 5898.24, "total_tokens": 3930776} {"current_steps": 5950, "total_steps": 33920, "loss": 0.5908, "lr": 9.827893554810298e-06, "epoch": 3.5082547169811322, "percentage": 17.54, "elapsed_time": "0:11:06", "remaining_time": "0:52:15", "throughput": 5897.23, "total_tokens": 3932952} {"current_steps": 5955, "total_steps": 33920, "loss": 0.4346, "lr": 9.827223724395281e-06, "epoch": 3.5112028301886795, "percentage": 17.56, "elapsed_time": "0:11:07", "remaining_time": "0:52:14", "throughput": 5897.37, "total_tokens": 3936504} {"current_steps": 5960, "total_steps": 33920, "loss": 0.5501, "lr": 9.82655261595198e-06, "epoch": 3.5141509433962264, "percentage": 17.57, "elapsed_time": "0:11:07", "remaining_time": "0:52:13", "throughput": 5897.42, "total_tokens": 3939384} {"current_steps": 5965, "total_steps": 33920, "loss": 0.5385, "lr": 9.825880229658073e-06, "epoch": 3.5170990566037736, "percentage": 17.59, "elapsed_time": "0:11:08", "remaining_time": "0:52:12", "throughput": 5896.99, "total_tokens": 3942136} {"current_steps": 5970, "total_steps": 33920, "loss": 0.515, "lr": 9.825206565691576e-06, "epoch": 3.5200471698113205, "percentage": 17.6, "elapsed_time": "0:11:09", "remaining_time": "0:52:12", "throughput": 5896.97, "total_tokens": 3945464} {"current_steps": 5975, "total_steps": 33920, "loss": 0.5044, "lr": 9.824531624230844e-06, "epoch": 3.5229952830188678, "percentage": 17.61, "elapsed_time": "0:11:09", "remaining_time": "0:52:11", "throughput": 5896.97, "total_tokens": 3948248} {"current_steps": 5980, "total_steps": 33920, "loss": 0.502, "lr": 9.823855405454573e-06, "epoch": 3.525943396226415, "percentage": 17.63, "elapsed_time": "0:11:10", "remaining_time": "0:52:10", "throughput": 5896.73, "total_tokens": 3951096} {"current_steps": 5985, "total_steps": 33920, "loss": 0.6346, "lr": 9.823177909541795e-06, "epoch": 3.5288915094339623, "percentage": 17.64, "elapsed_time": "0:11:10", "remaining_time": "0:52:10", "throughput": 5896.84, "total_tokens": 3954456} {"current_steps": 5990, "total_steps": 33920, "loss": 0.5115, "lr": 9.822499136671877e-06, "epoch": 3.5318396226415096, "percentage": 17.66, "elapsed_time": "0:11:11", "remaining_time": "0:52:09", "throughput": 5897.55, "total_tokens": 3958424} {"current_steps": 5995, "total_steps": 33920, "loss": 0.4226, "lr": 9.82181908702453e-06, "epoch": 3.5347877358490565, "percentage": 17.67, "elapsed_time": "0:11:11", "remaining_time": "0:52:09", "throughput": 5897.58, "total_tokens": 3961720} {"current_steps": 6000, "total_steps": 33920, "loss": 0.4087, "lr": 9.821137760779797e-06, "epoch": 3.5377358490566038, "percentage": 17.69, "elapsed_time": "0:11:12", "remaining_time": "0:52:08", "throughput": 5898.2, "total_tokens": 3965304} {"current_steps": 6005, "total_steps": 33920, "loss": 0.4586, "lr": 9.820455158118065e-06, "epoch": 3.540683962264151, "percentage": 17.7, "elapsed_time": "0:11:12", "remaining_time": "0:52:07", "throughput": 5898.52, "total_tokens": 3968632} {"current_steps": 6010, "total_steps": 33920, "loss": 0.4888, "lr": 9.819771279220053e-06, "epoch": 3.543632075471698, "percentage": 17.72, "elapsed_time": "0:11:13", "remaining_time": "0:52:07", "throughput": 5899.18, "total_tokens": 3972600} {"current_steps": 6015, "total_steps": 33920, "loss": 0.4844, "lr": 9.819086124266825e-06, "epoch": 3.546580188679245, "percentage": 17.73, "elapsed_time": "0:11:13", "remaining_time": "0:52:06", "throughput": 5899.02, "total_tokens": 3975704} {"current_steps": 6020, "total_steps": 33920, "loss": 0.4486, "lr": 9.818399693439778e-06, "epoch": 3.5495283018867925, "percentage": 17.75, "elapsed_time": "0:11:14", "remaining_time": "0:52:05", "throughput": 5898.42, "total_tokens": 3978232} {"current_steps": 6025, "total_steps": 33920, "loss": 0.495, "lr": 9.817711986920644e-06, "epoch": 3.5524764150943398, "percentage": 17.76, "elapsed_time": "0:11:15", "remaining_time": "0:52:05", "throughput": 5898.83, "total_tokens": 3981848} {"current_steps": 6030, "total_steps": 33920, "loss": 0.6072, "lr": 9.817023004891497e-06, "epoch": 3.555424528301887, "percentage": 17.78, "elapsed_time": "0:11:15", "remaining_time": "0:52:04", "throughput": 5899.44, "total_tokens": 3985784} {"current_steps": 6035, "total_steps": 33920, "loss": 0.4338, "lr": 9.816332747534752e-06, "epoch": 3.558372641509434, "percentage": 17.79, "elapsed_time": "0:11:16", "remaining_time": "0:52:04", "throughput": 5899.53, "total_tokens": 3989016} {"current_steps": 6040, "total_steps": 33920, "loss": 0.6269, "lr": 9.815641215033153e-06, "epoch": 3.561320754716981, "percentage": 17.81, "elapsed_time": "0:11:16", "remaining_time": "0:52:03", "throughput": 5900.17, "total_tokens": 3992920} {"current_steps": 6045, "total_steps": 33920, "loss": 0.4931, "lr": 9.814948407569789e-06, "epoch": 3.5642688679245285, "percentage": 17.82, "elapsed_time": "0:11:17", "remaining_time": "0:52:03", "throughput": 5900.34, "total_tokens": 3996216} {"current_steps": 6050, "total_steps": 33920, "loss": 0.4217, "lr": 9.814254325328082e-06, "epoch": 3.5672169811320753, "percentage": 17.84, "elapsed_time": "0:11:17", "remaining_time": "0:52:02", "throughput": 5900.94, "total_tokens": 4000472} {"current_steps": 6055, "total_steps": 33920, "loss": 0.4347, "lr": 9.813558968491794e-06, "epoch": 3.5701650943396226, "percentage": 17.85, "elapsed_time": "0:11:18", "remaining_time": "0:52:02", "throughput": 5900.98, "total_tokens": 4003384} {"current_steps": 6060, "total_steps": 33920, "loss": 0.4712, "lr": 9.812862337245024e-06, "epoch": 3.57311320754717, "percentage": 17.87, "elapsed_time": "0:11:18", "remaining_time": "0:52:01", "throughput": 5900.94, "total_tokens": 4006488} {"current_steps": 6065, "total_steps": 33920, "loss": 0.5346, "lr": 9.812164431772208e-06, "epoch": 3.576061320754717, "percentage": 17.88, "elapsed_time": "0:11:19", "remaining_time": "0:52:00", "throughput": 5901.19, "total_tokens": 4009784} {"current_steps": 6070, "total_steps": 33920, "loss": 0.5006, "lr": 9.81146525225812e-06, "epoch": 3.579009433962264, "percentage": 17.9, "elapsed_time": "0:11:20", "remaining_time": "0:52:00", "throughput": 5902.09, "total_tokens": 4014008} {"current_steps": 6075, "total_steps": 33920, "loss": 0.6148, "lr": 9.810764798887868e-06, "epoch": 3.5819575471698113, "percentage": 17.91, "elapsed_time": "0:11:20", "remaining_time": "0:51:59", "throughput": 5902.08, "total_tokens": 4016920} {"current_steps": 6080, "total_steps": 33920, "loss": 0.5133, "lr": 9.810063071846905e-06, "epoch": 3.5849056603773586, "percentage": 17.92, "elapsed_time": "0:11:21", "remaining_time": "0:51:59", "throughput": 5902.07, "total_tokens": 4020312} {"current_steps": 6085, "total_steps": 33920, "loss": 0.4152, "lr": 9.809360071321013e-06, "epoch": 3.5878537735849054, "percentage": 17.94, "elapsed_time": "0:11:21", "remaining_time": "0:51:58", "throughput": 5902.46, "total_tokens": 4024024} {"current_steps": 6090, "total_steps": 33920, "loss": 0.4438, "lr": 9.808655797496314e-06, "epoch": 3.5908018867924527, "percentage": 17.95, "elapsed_time": "0:11:22", "remaining_time": "0:51:57", "throughput": 5902.64, "total_tokens": 4027064} {"current_steps": 6095, "total_steps": 33920, "loss": 0.4349, "lr": 9.807950250559268e-06, "epoch": 3.59375, "percentage": 17.97, "elapsed_time": "0:11:22", "remaining_time": "0:51:56", "throughput": 5902.85, "total_tokens": 4030168} {"current_steps": 6100, "total_steps": 33920, "loss": 0.4176, "lr": 9.807243430696673e-06, "epoch": 3.5966981132075473, "percentage": 17.98, "elapsed_time": "0:11:23", "remaining_time": "0:51:56", "throughput": 5903.16, "total_tokens": 4033400} {"current_steps": 6105, "total_steps": 33920, "loss": 0.5057, "lr": 9.806535338095661e-06, "epoch": 3.5996462264150946, "percentage": 18.0, "elapsed_time": "0:11:23", "remaining_time": "0:51:55", "throughput": 5903.95, "total_tokens": 4037368} {"current_steps": 6110, "total_steps": 33920, "loss": 0.4706, "lr": 9.805825972943706e-06, "epoch": 3.6025943396226414, "percentage": 18.01, "elapsed_time": "0:11:24", "remaining_time": "0:51:54", "throughput": 5903.74, "total_tokens": 4040248} {"current_steps": 6115, "total_steps": 33920, "loss": 0.3238, "lr": 9.80511533542861e-06, "epoch": 3.6055424528301887, "percentage": 18.03, "elapsed_time": "0:11:24", "remaining_time": "0:51:54", "throughput": 5903.77, "total_tokens": 4043224} {"current_steps": 6120, "total_steps": 33920, "loss": 0.5076, "lr": 9.80440342573852e-06, "epoch": 3.608490566037736, "percentage": 18.04, "elapsed_time": "0:11:25", "remaining_time": "0:51:54", "throughput": 5904.59, "total_tokens": 4048440} {"current_steps": 6125, "total_steps": 33920, "loss": 0.5652, "lr": 9.803690244061919e-06, "epoch": 3.611438679245283, "percentage": 18.06, "elapsed_time": "0:11:26", "remaining_time": "0:51:54", "throughput": 5905.26, "total_tokens": 4052312} {"current_steps": 6130, "total_steps": 33920, "loss": 0.4541, "lr": 9.802975790587621e-06, "epoch": 3.61438679245283, "percentage": 18.07, "elapsed_time": "0:11:26", "remaining_time": "0:51:53", "throughput": 5905.0, "total_tokens": 4055128} {"current_steps": 6135, "total_steps": 33920, "loss": 0.4612, "lr": 9.802260065504783e-06, "epoch": 3.6173349056603774, "percentage": 18.09, "elapsed_time": "0:11:27", "remaining_time": "0:51:52", "throughput": 5904.48, "total_tokens": 4057560} {"current_steps": 6140, "total_steps": 33920, "loss": 0.504, "lr": 9.801543069002897e-06, "epoch": 3.6202830188679247, "percentage": 18.1, "elapsed_time": "0:11:27", "remaining_time": "0:51:51", "throughput": 5904.3, "total_tokens": 4060408} {"current_steps": 6145, "total_steps": 33920, "loss": 0.4168, "lr": 9.80082480127179e-06, "epoch": 3.6232311320754715, "percentage": 18.12, "elapsed_time": "0:11:28", "remaining_time": "0:51:50", "throughput": 5904.17, "total_tokens": 4063064} {"current_steps": 6150, "total_steps": 33920, "loss": 0.566, "lr": 9.800105262501628e-06, "epoch": 3.626179245283019, "percentage": 18.13, "elapsed_time": "0:11:28", "remaining_time": "0:51:49", "throughput": 5904.12, "total_tokens": 4066040} {"current_steps": 6155, "total_steps": 33920, "loss": 0.4525, "lr": 9.799384452882907e-06, "epoch": 3.629127358490566, "percentage": 18.15, "elapsed_time": "0:11:29", "remaining_time": "0:51:48", "throughput": 5903.03, "total_tokens": 4068344} {"current_steps": 6160, "total_steps": 33920, "loss": 0.6746, "lr": 9.798662372606469e-06, "epoch": 3.632075471698113, "percentage": 18.16, "elapsed_time": "0:11:29", "remaining_time": "0:51:48", "throughput": 5903.72, "total_tokens": 4072152} {"current_steps": 6165, "total_steps": 33920, "loss": 0.4128, "lr": 9.797939021863487e-06, "epoch": 3.6350235849056602, "percentage": 18.18, "elapsed_time": "0:11:30", "remaining_time": "0:51:47", "throughput": 5903.46, "total_tokens": 4074904} {"current_steps": 6170, "total_steps": 33920, "loss": 0.5732, "lr": 9.797214400845472e-06, "epoch": 3.6379716981132075, "percentage": 18.19, "elapsed_time": "0:11:30", "remaining_time": "0:51:46", "throughput": 5903.43, "total_tokens": 4077912} {"current_steps": 6175, "total_steps": 33920, "loss": 0.4852, "lr": 9.796488509744269e-06, "epoch": 3.640919811320755, "percentage": 18.2, "elapsed_time": "0:11:31", "remaining_time": "0:51:46", "throughput": 5903.66, "total_tokens": 4081624} {"current_steps": 6180, "total_steps": 33920, "loss": 0.5188, "lr": 9.79576134875206e-06, "epoch": 3.643867924528302, "percentage": 18.22, "elapsed_time": "0:11:31", "remaining_time": "0:51:45", "throughput": 5903.77, "total_tokens": 4084600} {"current_steps": 6185, "total_steps": 33920, "loss": 0.4701, "lr": 9.795032918061367e-06, "epoch": 3.646816037735849, "percentage": 18.23, "elapsed_time": "0:11:32", "remaining_time": "0:51:44", "throughput": 5903.6, "total_tokens": 4087384} {"current_steps": 6190, "total_steps": 33920, "loss": 0.3887, "lr": 9.794303217865041e-06, "epoch": 3.6497641509433962, "percentage": 18.25, "elapsed_time": "0:11:32", "remaining_time": "0:51:44", "throughput": 5903.67, "total_tokens": 4090584} {"current_steps": 6195, "total_steps": 33920, "loss": 0.4249, "lr": 9.79357224835628e-06, "epoch": 3.6527122641509435, "percentage": 18.26, "elapsed_time": "0:11:33", "remaining_time": "0:51:43", "throughput": 5903.36, "total_tokens": 4093304} {"current_steps": 6200, "total_steps": 33920, "loss": 0.391, "lr": 9.792840009728605e-06, "epoch": 3.6556603773584904, "percentage": 18.28, "elapsed_time": "0:11:33", "remaining_time": "0:51:42", "throughput": 5903.43, "total_tokens": 4096376} {"current_steps": 6205, "total_steps": 33920, "loss": 0.3752, "lr": 9.79210650217588e-06, "epoch": 3.6586084905660377, "percentage": 18.29, "elapsed_time": "0:11:34", "remaining_time": "0:51:43", "throughput": 5903.95, "total_tokens": 4102168} {"current_steps": 6210, "total_steps": 33920, "loss": 0.4356, "lr": 9.791371725892307e-06, "epoch": 3.661556603773585, "percentage": 18.31, "elapsed_time": "0:11:35", "remaining_time": "0:51:43", "throughput": 5904.38, "total_tokens": 4105944} {"current_steps": 6215, "total_steps": 33920, "loss": 0.5673, "lr": 9.79063568107242e-06, "epoch": 3.6645047169811322, "percentage": 18.32, "elapsed_time": "0:11:36", "remaining_time": "0:51:42", "throughput": 5904.16, "total_tokens": 4109368} {"current_steps": 6220, "total_steps": 33920, "loss": 0.4157, "lr": 9.78989836791109e-06, "epoch": 3.6674528301886795, "percentage": 18.34, "elapsed_time": "0:11:36", "remaining_time": "0:51:41", "throughput": 5904.63, "total_tokens": 4112856} {"current_steps": 6225, "total_steps": 33920, "loss": 0.4811, "lr": 9.789159786603524e-06, "epoch": 3.6704009433962264, "percentage": 18.35, "elapsed_time": "0:11:37", "remaining_time": "0:51:41", "throughput": 5904.23, "total_tokens": 4115384} {"current_steps": 6230, "total_steps": 33920, "loss": 0.4105, "lr": 9.788419937345263e-06, "epoch": 3.6733490566037736, "percentage": 18.37, "elapsed_time": "0:11:37", "remaining_time": "0:51:40", "throughput": 5904.72, "total_tokens": 4119128} {"current_steps": 6235, "total_steps": 33920, "loss": 0.4343, "lr": 9.787678820332188e-06, "epoch": 3.6762971698113205, "percentage": 18.38, "elapsed_time": "0:11:38", "remaining_time": "0:51:39", "throughput": 5904.54, "total_tokens": 4121816} {"current_steps": 6240, "total_steps": 33920, "loss": 0.3914, "lr": 9.78693643576051e-06, "epoch": 3.6792452830188678, "percentage": 18.4, "elapsed_time": "0:11:38", "remaining_time": "0:51:38", "throughput": 5905.01, "total_tokens": 4125272} {"current_steps": 6245, "total_steps": 33920, "loss": 0.5531, "lr": 9.786192783826782e-06, "epoch": 3.682193396226415, "percentage": 18.41, "elapsed_time": "0:11:39", "remaining_time": "0:51:38", "throughput": 5905.16, "total_tokens": 4128312} {"current_steps": 6250, "total_steps": 33920, "loss": 0.5043, "lr": 9.785447864727887e-06, "epoch": 3.6851415094339623, "percentage": 18.43, "elapsed_time": "0:11:39", "remaining_time": "0:51:37", "throughput": 5905.46, "total_tokens": 4131480} {"current_steps": 6255, "total_steps": 33920, "loss": 0.4759, "lr": 9.784701678661045e-06, "epoch": 3.6880896226415096, "percentage": 18.44, "elapsed_time": "0:11:40", "remaining_time": "0:51:36", "throughput": 5905.05, "total_tokens": 4133880} {"current_steps": 6260, "total_steps": 33920, "loss": 0.428, "lr": 9.783954225823813e-06, "epoch": 3.6910377358490565, "percentage": 18.46, "elapsed_time": "0:11:40", "remaining_time": "0:51:35", "throughput": 5905.79, "total_tokens": 4137816} {"current_steps": 6265, "total_steps": 33920, "loss": 0.5055, "lr": 9.783205506414082e-06, "epoch": 3.6939858490566038, "percentage": 18.47, "elapsed_time": "0:11:41", "remaining_time": "0:51:34", "throughput": 5905.58, "total_tokens": 4140632} {"current_steps": 6270, "total_steps": 33920, "loss": 0.5313, "lr": 9.782455520630079e-06, "epoch": 3.696933962264151, "percentage": 18.48, "elapsed_time": "0:11:41", "remaining_time": "0:51:34", "throughput": 5906.04, "total_tokens": 4144184} {"current_steps": 6275, "total_steps": 33920, "loss": 0.411, "lr": 9.781704268670364e-06, "epoch": 3.699882075471698, "percentage": 18.5, "elapsed_time": "0:11:42", "remaining_time": "0:51:33", "throughput": 5905.76, "total_tokens": 4146808} {"current_steps": 6280, "total_steps": 33920, "loss": 0.413, "lr": 9.780951750733837e-06, "epoch": 3.702830188679245, "percentage": 18.51, "elapsed_time": "0:11:42", "remaining_time": "0:51:33", "throughput": 5905.78, "total_tokens": 4150840} {"current_steps": 6285, "total_steps": 33920, "loss": 0.3545, "lr": 9.780197967019728e-06, "epoch": 3.7057783018867925, "percentage": 18.53, "elapsed_time": "0:11:43", "remaining_time": "0:51:32", "throughput": 5904.85, "total_tokens": 4152920} {"current_steps": 6290, "total_steps": 33920, "loss": 0.4635, "lr": 9.779442917727608e-06, "epoch": 3.7087264150943398, "percentage": 18.54, "elapsed_time": "0:11:43", "remaining_time": "0:51:31", "throughput": 5904.3, "total_tokens": 4155704} {"current_steps": 6295, "total_steps": 33920, "loss": 0.4484, "lr": 9.778686603057377e-06, "epoch": 3.711674528301887, "percentage": 18.56, "elapsed_time": "0:11:44", "remaining_time": "0:51:31", "throughput": 5904.33, "total_tokens": 4159416} {"current_steps": 6300, "total_steps": 33920, "loss": 0.6352, "lr": 9.777929023209271e-06, "epoch": 3.714622641509434, "percentage": 18.57, "elapsed_time": "0:11:45", "remaining_time": "0:51:30", "throughput": 5904.77, "total_tokens": 4163096} {"current_steps": 6305, "total_steps": 33920, "loss": 0.5245, "lr": 9.777170178383866e-06, "epoch": 3.717570754716981, "percentage": 18.59, "elapsed_time": "0:11:45", "remaining_time": "0:51:30", "throughput": 5905.71, "total_tokens": 4167576} {"current_steps": 6310, "total_steps": 33920, "loss": 0.5607, "lr": 9.776410068782068e-06, "epoch": 3.7205188679245285, "percentage": 18.6, "elapsed_time": "0:11:46", "remaining_time": "0:51:30", "throughput": 5905.97, "total_tokens": 4171192} {"current_steps": 6315, "total_steps": 33920, "loss": 0.5789, "lr": 9.775648694605118e-06, "epoch": 3.7234669811320753, "percentage": 18.62, "elapsed_time": "0:11:46", "remaining_time": "0:51:29", "throughput": 5906.58, "total_tokens": 4175128} {"current_steps": 6320, "total_steps": 33920, "loss": 0.3881, "lr": 9.774886056054593e-06, "epoch": 3.7264150943396226, "percentage": 18.63, "elapsed_time": "0:11:47", "remaining_time": "0:51:29", "throughput": 5906.81, "total_tokens": 4178584} {"current_steps": 6325, "total_steps": 33920, "loss": 0.5847, "lr": 9.774122153332408e-06, "epoch": 3.72936320754717, "percentage": 18.65, "elapsed_time": "0:11:47", "remaining_time": "0:51:28", "throughput": 5907.0, "total_tokens": 4181688} {"current_steps": 6330, "total_steps": 33920, "loss": 0.5736, "lr": 9.773356986640807e-06, "epoch": 3.732311320754717, "percentage": 18.66, "elapsed_time": "0:11:48", "remaining_time": "0:51:27", "throughput": 5906.61, "total_tokens": 4184152} {"current_steps": 6335, "total_steps": 33920, "loss": 0.5008, "lr": 9.772590556182373e-06, "epoch": 3.735259433962264, "percentage": 18.68, "elapsed_time": "0:11:48", "remaining_time": "0:51:26", "throughput": 5906.42, "total_tokens": 4186808} {"current_steps": 6340, "total_steps": 33920, "loss": 0.4284, "lr": 9.77182286216002e-06, "epoch": 3.7382075471698113, "percentage": 18.69, "elapsed_time": "0:11:49", "remaining_time": "0:51:25", "throughput": 5906.42, "total_tokens": 4189784} {"current_steps": 6345, "total_steps": 33920, "loss": 0.4858, "lr": 9.771053904776998e-06, "epoch": 3.7411556603773586, "percentage": 18.71, "elapsed_time": "0:11:50", "remaining_time": "0:51:26", "throughput": 5907.43, "total_tokens": 4195512} {"current_steps": 6350, "total_steps": 33920, "loss": 0.4829, "lr": 9.770283684236891e-06, "epoch": 3.7441037735849054, "percentage": 18.72, "elapsed_time": "0:11:50", "remaining_time": "0:51:25", "throughput": 5908.01, "total_tokens": 4199096} {"current_steps": 6355, "total_steps": 33920, "loss": 0.5858, "lr": 9.769512200743623e-06, "epoch": 3.7470518867924527, "percentage": 18.74, "elapsed_time": "0:11:51", "remaining_time": "0:51:25", "throughput": 5908.05, "total_tokens": 4202072} {"current_steps": 6360, "total_steps": 33920, "loss": 0.4654, "lr": 9.768739454501444e-06, "epoch": 3.75, "percentage": 18.75, "elapsed_time": "0:11:51", "remaining_time": "0:51:24", "throughput": 5908.25, "total_tokens": 4205208} {"current_steps": 6365, "total_steps": 33920, "loss": 0.4521, "lr": 9.76796544571494e-06, "epoch": 3.7529481132075473, "percentage": 18.76, "elapsed_time": "0:11:52", "remaining_time": "0:51:23", "throughput": 5907.43, "total_tokens": 4208088} {"current_steps": 6370, "total_steps": 33920, "loss": 0.3361, "lr": 9.767190174589036e-06, "epoch": 3.7558962264150946, "percentage": 18.78, "elapsed_time": "0:11:52", "remaining_time": "0:51:23", "throughput": 5906.79, "total_tokens": 4210616} {"current_steps": 6375, "total_steps": 33920, "loss": 0.5059, "lr": 9.76641364132899e-06, "epoch": 3.7588443396226414, "percentage": 18.79, "elapsed_time": "0:11:53", "remaining_time": "0:51:22", "throughput": 5906.37, "total_tokens": 4213176} {"current_steps": 6380, "total_steps": 33920, "loss": 0.62, "lr": 9.765635846140389e-06, "epoch": 3.7617924528301887, "percentage": 18.81, "elapsed_time": "0:11:54", "remaining_time": "0:51:23", "throughput": 5907.17, "total_tokens": 4219960} {"current_steps": 6385, "total_steps": 33920, "loss": 0.4568, "lr": 9.764856789229157e-06, "epoch": 3.764740566037736, "percentage": 18.82, "elapsed_time": "0:11:54", "remaining_time": "0:51:23", "throughput": 5907.5, "total_tokens": 4223352} {"current_steps": 6390, "total_steps": 33920, "loss": 0.5276, "lr": 9.764076470801557e-06, "epoch": 3.767688679245283, "percentage": 18.84, "elapsed_time": "0:11:55", "remaining_time": "0:51:22", "throughput": 5908.06, "total_tokens": 4227160} {"current_steps": 6395, "total_steps": 33920, "loss": 0.5215, "lr": 9.763294891064182e-06, "epoch": 3.77063679245283, "percentage": 18.85, "elapsed_time": "0:11:55", "remaining_time": "0:51:21", "throughput": 5907.92, "total_tokens": 4230008} {"current_steps": 6400, "total_steps": 33920, "loss": 0.3512, "lr": 9.762512050223951e-06, "epoch": 3.7735849056603774, "percentage": 18.87, "elapsed_time": "0:11:56", "remaining_time": "0:51:21", "throughput": 5907.45, "total_tokens": 4232760} {"current_steps": 6405, "total_steps": 33920, "loss": 0.4612, "lr": 9.761727948488132e-06, "epoch": 3.7765330188679247, "percentage": 18.88, "elapsed_time": "0:11:57", "remaining_time": "0:51:20", "throughput": 5907.61, "total_tokens": 4236056} {"current_steps": 6410, "total_steps": 33920, "loss": 0.3381, "lr": 9.760942586064315e-06, "epoch": 3.7794811320754715, "percentage": 18.9, "elapsed_time": "0:11:57", "remaining_time": "0:51:19", "throughput": 5908.18, "total_tokens": 4239768} {"current_steps": 6415, "total_steps": 33920, "loss": 0.4596, "lr": 9.760155963160431e-06, "epoch": 3.782429245283019, "percentage": 18.91, "elapsed_time": "0:11:58", "remaining_time": "0:51:18", "throughput": 5908.24, "total_tokens": 4242552} {"current_steps": 6420, "total_steps": 33920, "loss": 0.8526, "lr": 9.759368079984741e-06, "epoch": 3.785377358490566, "percentage": 18.93, "elapsed_time": "0:11:58", "remaining_time": "0:51:18", "throughput": 5908.64, "total_tokens": 4245912} {"current_steps": 6425, "total_steps": 33920, "loss": 0.4198, "lr": 9.758578936745839e-06, "epoch": 3.788325471698113, "percentage": 18.94, "elapsed_time": "0:11:59", "remaining_time": "0:51:17", "throughput": 5908.3, "total_tokens": 4248376} {"current_steps": 6430, "total_steps": 33920, "loss": 0.4698, "lr": 9.757788533652656e-06, "epoch": 3.7912735849056602, "percentage": 18.96, "elapsed_time": "0:11:59", "remaining_time": "0:51:16", "throughput": 5908.29, "total_tokens": 4251224} {"current_steps": 6435, "total_steps": 33920, "loss": 0.4677, "lr": 9.756996870914454e-06, "epoch": 3.7942216981132075, "percentage": 18.97, "elapsed_time": "0:12:00", "remaining_time": "0:51:15", "throughput": 5908.5, "total_tokens": 4254648} {"current_steps": 6440, "total_steps": 33920, "loss": 0.6443, "lr": 9.756203948740828e-06, "epoch": 3.797169811320755, "percentage": 18.99, "elapsed_time": "0:12:00", "remaining_time": "0:51:14", "throughput": 5908.21, "total_tokens": 4257304} {"current_steps": 6445, "total_steps": 33920, "loss": 0.4746, "lr": 9.755409767341709e-06, "epoch": 3.800117924528302, "percentage": 19.0, "elapsed_time": "0:12:01", "remaining_time": "0:51:13", "throughput": 5908.12, "total_tokens": 4260216} {"current_steps": 6450, "total_steps": 33920, "loss": 0.3998, "lr": 9.75461432692736e-06, "epoch": 3.803066037735849, "percentage": 19.02, "elapsed_time": "0:12:01", "remaining_time": "0:51:13", "throughput": 5908.75, "total_tokens": 4264568} {"current_steps": 6455, "total_steps": 33920, "loss": 0.4958, "lr": 9.753817627708375e-06, "epoch": 3.8060141509433962, "percentage": 19.03, "elapsed_time": "0:12:02", "remaining_time": "0:51:13", "throughput": 5909.44, "total_tokens": 4268696} {"current_steps": 6460, "total_steps": 33920, "loss": 0.417, "lr": 9.753019669895686e-06, "epoch": 3.8089622641509435, "percentage": 19.04, "elapsed_time": "0:12:02", "remaining_time": "0:51:12", "throughput": 5909.7, "total_tokens": 4271800} {"current_steps": 6465, "total_steps": 33920, "loss": 0.4465, "lr": 9.752220453700556e-06, "epoch": 3.8119103773584904, "percentage": 19.06, "elapsed_time": "0:12:03", "remaining_time": "0:51:12", "throughput": 5909.98, "total_tokens": 4275256} {"current_steps": 6470, "total_steps": 33920, "loss": 0.4025, "lr": 9.75141997933458e-06, "epoch": 3.8148584905660377, "percentage": 19.07, "elapsed_time": "0:12:03", "remaining_time": "0:51:11", "throughput": 5909.66, "total_tokens": 4278040} {"current_steps": 6475, "total_steps": 33920, "loss": 0.4501, "lr": 9.750618247009685e-06, "epoch": 3.817806603773585, "percentage": 19.09, "elapsed_time": "0:12:04", "remaining_time": "0:51:10", "throughput": 5910.12, "total_tokens": 4281592} {"current_steps": 6480, "total_steps": 33920, "loss": 0.362, "lr": 9.749815256938138e-06, "epoch": 3.8207547169811322, "percentage": 19.1, "elapsed_time": "0:12:04", "remaining_time": "0:51:10", "throughput": 5910.34, "total_tokens": 4284920} {"current_steps": 6485, "total_steps": 33920, "loss": 0.542, "lr": 9.749011009332529e-06, "epoch": 3.8237028301886795, "percentage": 19.12, "elapsed_time": "0:12:05", "remaining_time": "0:51:09", "throughput": 5910.57, "total_tokens": 4287960} {"current_steps": 6490, "total_steps": 33920, "loss": 0.3796, "lr": 9.748205504405787e-06, "epoch": 3.8266509433962264, "percentage": 19.13, "elapsed_time": "0:12:05", "remaining_time": "0:51:08", "throughput": 5910.64, "total_tokens": 4290872} {"current_steps": 6495, "total_steps": 33920, "loss": 0.5179, "lr": 9.747398742371177e-06, "epoch": 3.8295990566037736, "percentage": 19.15, "elapsed_time": "0:12:06", "remaining_time": "0:51:07", "throughput": 5910.89, "total_tokens": 4294008} {"current_steps": 6500, "total_steps": 33920, "loss": 0.517, "lr": 9.746590723442289e-06, "epoch": 3.8325471698113205, "percentage": 19.16, "elapsed_time": "0:12:07", "remaining_time": "0:51:07", "throughput": 5911.1, "total_tokens": 4297688} {"current_steps": 6505, "total_steps": 33920, "loss": 0.5107, "lr": 9.745781447833049e-06, "epoch": 3.8354952830188678, "percentage": 19.18, "elapsed_time": "0:12:07", "remaining_time": "0:51:06", "throughput": 5911.6, "total_tokens": 4301176} {"current_steps": 6510, "total_steps": 33920, "loss": 0.3731, "lr": 9.74497091575772e-06, "epoch": 3.838443396226415, "percentage": 19.19, "elapsed_time": "0:12:08", "remaining_time": "0:51:05", "throughput": 5911.45, "total_tokens": 4304152} {"current_steps": 6515, "total_steps": 33920, "loss": 0.6074, "lr": 9.744159127430888e-06, "epoch": 3.8413915094339623, "percentage": 19.21, "elapsed_time": "0:12:08", "remaining_time": "0:51:05", "throughput": 5911.11, "total_tokens": 4307320} {"current_steps": 6520, "total_steps": 33920, "loss": 0.407, "lr": 9.743346083067482e-06, "epoch": 3.8443396226415096, "percentage": 19.22, "elapsed_time": "0:12:09", "remaining_time": "0:51:04", "throughput": 5911.06, "total_tokens": 4310232} {"current_steps": 6525, "total_steps": 33920, "loss": 0.586, "lr": 9.742531782882758e-06, "epoch": 3.8472877358490565, "percentage": 19.24, "elapsed_time": "0:12:09", "remaining_time": "0:51:03", "throughput": 5911.39, "total_tokens": 4313560} {"current_steps": 6530, "total_steps": 33920, "loss": 0.4633, "lr": 9.741716227092305e-06, "epoch": 3.8502358490566038, "percentage": 19.25, "elapsed_time": "0:12:10", "remaining_time": "0:51:02", "throughput": 5911.59, "total_tokens": 4316568} {"current_steps": 6535, "total_steps": 33920, "loss": 0.3569, "lr": 9.740899415912048e-06, "epoch": 3.853183962264151, "percentage": 19.27, "elapsed_time": "0:12:10", "remaining_time": "0:51:02", "throughput": 5911.2, "total_tokens": 4319480} {"current_steps": 6540, "total_steps": 33920, "loss": 0.5087, "lr": 9.740081349558236e-06, "epoch": 3.856132075471698, "percentage": 19.28, "elapsed_time": "0:12:11", "remaining_time": "0:51:01", "throughput": 5911.43, "total_tokens": 4322744} {"current_steps": 6545, "total_steps": 33920, "loss": 0.3377, "lr": 9.739262028247459e-06, "epoch": 3.859080188679245, "percentage": 19.3, "elapsed_time": "0:12:11", "remaining_time": "0:51:00", "throughput": 5911.24, "total_tokens": 4325592} {"current_steps": 6550, "total_steps": 33920, "loss": 0.5049, "lr": 9.738441452196633e-06, "epoch": 3.8620283018867925, "percentage": 19.31, "elapsed_time": "0:12:12", "remaining_time": "0:51:00", "throughput": 5911.5, "total_tokens": 4328984} {"current_steps": 6555, "total_steps": 33920, "loss": 0.4847, "lr": 9.737619621623013e-06, "epoch": 3.8649764150943398, "percentage": 19.32, "elapsed_time": "0:12:12", "remaining_time": "0:50:59", "throughput": 5911.88, "total_tokens": 4332376} {"current_steps": 6560, "total_steps": 33920, "loss": 0.4775, "lr": 9.73679653674418e-06, "epoch": 3.867924528301887, "percentage": 19.34, "elapsed_time": "0:12:13", "remaining_time": "0:50:59", "throughput": 5912.7, "total_tokens": 4337112} {"current_steps": 6565, "total_steps": 33920, "loss": 0.4618, "lr": 9.735972197778047e-06, "epoch": 3.870872641509434, "percentage": 19.35, "elapsed_time": "0:12:14", "remaining_time": "0:50:58", "throughput": 5912.34, "total_tokens": 4339768} {"current_steps": 6570, "total_steps": 33920, "loss": 0.475, "lr": 9.735146604942867e-06, "epoch": 3.873820754716981, "percentage": 19.37, "elapsed_time": "0:12:14", "remaining_time": "0:50:57", "throughput": 5912.76, "total_tokens": 4343224} {"current_steps": 6575, "total_steps": 33920, "loss": 0.4637, "lr": 9.734319758457214e-06, "epoch": 3.8767688679245285, "percentage": 19.38, "elapsed_time": "0:12:15", "remaining_time": "0:50:57", "throughput": 5913.41, "total_tokens": 4347224} {"current_steps": 6580, "total_steps": 33920, "loss": 0.5076, "lr": 9.733491658540001e-06, "epoch": 3.8797169811320753, "percentage": 19.4, "elapsed_time": "0:12:15", "remaining_time": "0:50:56", "throughput": 5913.77, "total_tokens": 4350456} {"current_steps": 6585, "total_steps": 33920, "loss": 0.5303, "lr": 9.732662305410474e-06, "epoch": 3.8826650943396226, "percentage": 19.41, "elapsed_time": "0:12:16", "remaining_time": "0:50:55", "throughput": 5913.78, "total_tokens": 4353368} {"current_steps": 6590, "total_steps": 33920, "loss": 0.5727, "lr": 9.731831699288203e-06, "epoch": 3.88561320754717, "percentage": 19.43, "elapsed_time": "0:12:16", "remaining_time": "0:50:54", "throughput": 5913.6, "total_tokens": 4356120} {"current_steps": 6595, "total_steps": 33920, "loss": 0.5971, "lr": 9.730999840393096e-06, "epoch": 3.888561320754717, "percentage": 19.44, "elapsed_time": "0:12:17", "remaining_time": "0:50:54", "throughput": 5913.9, "total_tokens": 4359288} {"current_steps": 6600, "total_steps": 33920, "loss": 0.5912, "lr": 9.730166728945391e-06, "epoch": 3.891509433962264, "percentage": 19.46, "elapsed_time": "0:12:17", "remaining_time": "0:50:53", "throughput": 5914.03, "total_tokens": 4362648} {"current_steps": 6605, "total_steps": 33920, "loss": 0.4529, "lr": 9.72933236516566e-06, "epoch": 3.8944575471698113, "percentage": 19.47, "elapsed_time": "0:12:18", "remaining_time": "0:50:52", "throughput": 5913.61, "total_tokens": 4365176} {"current_steps": 6610, "total_steps": 33920, "loss": 0.5033, "lr": 9.728496749274806e-06, "epoch": 3.8974056603773586, "percentage": 19.49, "elapsed_time": "0:12:18", "remaining_time": "0:50:52", "throughput": 5913.62, "total_tokens": 4368408} {"current_steps": 6615, "total_steps": 33920, "loss": 0.5807, "lr": 9.727659881494054e-06, "epoch": 3.9003537735849054, "percentage": 19.5, "elapsed_time": "0:12:19", "remaining_time": "0:50:51", "throughput": 5912.45, "total_tokens": 4370520} {"current_steps": 6620, "total_steps": 33920, "loss": 0.4864, "lr": 9.726821762044975e-06, "epoch": 3.9033018867924527, "percentage": 19.52, "elapsed_time": "0:12:19", "remaining_time": "0:50:50", "throughput": 5912.39, "total_tokens": 4373400} {"current_steps": 6625, "total_steps": 33920, "loss": 0.6862, "lr": 9.725982391149465e-06, "epoch": 3.90625, "percentage": 19.53, "elapsed_time": "0:12:20", "remaining_time": "0:50:49", "throughput": 5912.49, "total_tokens": 4376600} {"current_steps": 6630, "total_steps": 33920, "loss": 0.3106, "lr": 9.725141769029747e-06, "epoch": 3.9091981132075473, "percentage": 19.55, "elapsed_time": "0:12:20", "remaining_time": "0:50:49", "throughput": 5913.4, "total_tokens": 4381592} {"current_steps": 6635, "total_steps": 33920, "loss": 0.5517, "lr": 9.72429989590838e-06, "epoch": 3.9121462264150946, "percentage": 19.56, "elapsed_time": "0:12:21", "remaining_time": "0:50:49", "throughput": 5913.43, "total_tokens": 4384600} {"current_steps": 6640, "total_steps": 33920, "loss": 0.5346, "lr": 9.723456772008257e-06, "epoch": 3.9150943396226414, "percentage": 19.58, "elapsed_time": "0:12:21", "remaining_time": "0:50:48", "throughput": 5913.66, "total_tokens": 4387864} {"current_steps": 6645, "total_steps": 33920, "loss": 0.5225, "lr": 9.722612397552598e-06, "epoch": 3.9180424528301887, "percentage": 19.59, "elapsed_time": "0:12:22", "remaining_time": "0:50:47", "throughput": 5913.6, "total_tokens": 4390808} {"current_steps": 6650, "total_steps": 33920, "loss": 0.6735, "lr": 9.72176677276495e-06, "epoch": 3.920990566037736, "percentage": 19.6, "elapsed_time": "0:12:23", "remaining_time": "0:50:46", "throughput": 5914.08, "total_tokens": 4394296} {"current_steps": 6655, "total_steps": 33920, "loss": 0.634, "lr": 9.7209198978692e-06, "epoch": 3.923938679245283, "percentage": 19.62, "elapsed_time": "0:12:23", "remaining_time": "0:50:45", "throughput": 5913.73, "total_tokens": 4396760} {"current_steps": 6660, "total_steps": 33920, "loss": 0.7765, "lr": 9.720071773089564e-06, "epoch": 3.92688679245283, "percentage": 19.63, "elapsed_time": "0:12:23", "remaining_time": "0:50:45", "throughput": 5913.17, "total_tokens": 4399128} {"current_steps": 6665, "total_steps": 33920, "loss": 0.4751, "lr": 9.71922239865058e-06, "epoch": 3.9298349056603774, "percentage": 19.65, "elapsed_time": "0:12:24", "remaining_time": "0:50:44", "throughput": 5913.35, "total_tokens": 4402456} {"current_steps": 6670, "total_steps": 33920, "loss": 0.4265, "lr": 9.718371774777131e-06, "epoch": 3.9327830188679247, "percentage": 19.66, "elapsed_time": "0:12:25", "remaining_time": "0:50:43", "throughput": 5913.12, "total_tokens": 4405400} {"current_steps": 6675, "total_steps": 33920, "loss": 0.5091, "lr": 9.717519901694416e-06, "epoch": 3.9357311320754715, "percentage": 19.68, "elapsed_time": "0:12:25", "remaining_time": "0:50:42", "throughput": 5912.63, "total_tokens": 4407992} {"current_steps": 6680, "total_steps": 33920, "loss": 0.4487, "lr": 9.716666779627978e-06, "epoch": 3.938679245283019, "percentage": 19.69, "elapsed_time": "0:12:26", "remaining_time": "0:50:42", "throughput": 5912.88, "total_tokens": 4411512} {"current_steps": 6685, "total_steps": 33920, "loss": 0.5084, "lr": 9.715812408803681e-06, "epoch": 3.941627358490566, "percentage": 19.71, "elapsed_time": "0:12:26", "remaining_time": "0:50:41", "throughput": 5912.73, "total_tokens": 4414296} {"current_steps": 6690, "total_steps": 33920, "loss": 0.3872, "lr": 9.714956789447726e-06, "epoch": 3.944575471698113, "percentage": 19.72, "elapsed_time": "0:12:27", "remaining_time": "0:50:40", "throughput": 5912.47, "total_tokens": 4416856} {"current_steps": 6695, "total_steps": 33920, "loss": 0.5722, "lr": 9.71409992178664e-06, "epoch": 3.9475235849056602, "percentage": 19.74, "elapsed_time": "0:12:27", "remaining_time": "0:50:39", "throughput": 5912.58, "total_tokens": 4419928} {"current_steps": 6700, "total_steps": 33920, "loss": 0.5143, "lr": 9.713241806047282e-06, "epoch": 3.9504716981132075, "percentage": 19.75, "elapsed_time": "0:12:28", "remaining_time": "0:50:38", "throughput": 5912.07, "total_tokens": 4422328} {"current_steps": 6705, "total_steps": 33920, "loss": 0.4196, "lr": 9.712382442456845e-06, "epoch": 3.953419811320755, "percentage": 19.77, "elapsed_time": "0:12:28", "remaining_time": "0:50:38", "throughput": 5912.25, "total_tokens": 4426168} {"current_steps": 6710, "total_steps": 33920, "loss": 0.5061, "lr": 9.711521831242846e-06, "epoch": 3.956367924528302, "percentage": 19.78, "elapsed_time": "0:12:29", "remaining_time": "0:50:37", "throughput": 5912.24, "total_tokens": 4429112} {"current_steps": 6715, "total_steps": 33920, "loss": 0.5524, "lr": 9.710659972633137e-06, "epoch": 3.959316037735849, "percentage": 19.8, "elapsed_time": "0:12:29", "remaining_time": "0:50:37", "throughput": 5912.08, "total_tokens": 4431896} {"current_steps": 6720, "total_steps": 33920, "loss": 0.5136, "lr": 9.709796866855899e-06, "epoch": 3.9622641509433962, "percentage": 19.81, "elapsed_time": "0:12:30", "remaining_time": "0:50:36", "throughput": 5912.03, "total_tokens": 4434808} {"current_steps": 6725, "total_steps": 33920, "loss": 0.4646, "lr": 9.70893251413964e-06, "epoch": 3.9652122641509435, "percentage": 19.83, "elapsed_time": "0:12:30", "remaining_time": "0:50:35", "throughput": 5911.75, "total_tokens": 4437400} {"current_steps": 6730, "total_steps": 33920, "loss": 0.4121, "lr": 9.708066914713205e-06, "epoch": 3.9681603773584904, "percentage": 19.84, "elapsed_time": "0:12:31", "remaining_time": "0:50:34", "throughput": 5912.19, "total_tokens": 4440824} {"current_steps": 6735, "total_steps": 33920, "loss": 0.4789, "lr": 9.707200068805764e-06, "epoch": 3.9711084905660377, "percentage": 19.86, "elapsed_time": "0:12:31", "remaining_time": "0:50:34", "throughput": 5913.14, "total_tokens": 4445304} {"current_steps": 6740, "total_steps": 33920, "loss": 0.2685, "lr": 9.706331976646817e-06, "epoch": 3.974056603773585, "percentage": 19.87, "elapsed_time": "0:12:32", "remaining_time": "0:50:33", "throughput": 5913.0, "total_tokens": 4448056} {"current_steps": 6745, "total_steps": 33920, "loss": 0.4223, "lr": 9.705462638466197e-06, "epoch": 3.9770047169811322, "percentage": 19.89, "elapsed_time": "0:12:32", "remaining_time": "0:50:32", "throughput": 5912.91, "total_tokens": 4450872} {"current_steps": 6750, "total_steps": 33920, "loss": 0.4387, "lr": 9.704592054494065e-06, "epoch": 3.9799528301886795, "percentage": 19.9, "elapsed_time": "0:12:33", "remaining_time": "0:50:31", "throughput": 5913.12, "total_tokens": 4454072} {"current_steps": 6755, "total_steps": 33920, "loss": 0.5674, "lr": 9.703720224960909e-06, "epoch": 3.9829009433962264, "percentage": 19.91, "elapsed_time": "0:12:33", "remaining_time": "0:50:31", "throughput": 5912.96, "total_tokens": 4456952} {"current_steps": 6760, "total_steps": 33920, "loss": 0.3907, "lr": 9.702847150097552e-06, "epoch": 3.9858490566037736, "percentage": 19.93, "elapsed_time": "0:12:34", "remaining_time": "0:50:30", "throughput": 5913.66, "total_tokens": 4460888} {"current_steps": 6765, "total_steps": 33920, "loss": 0.4623, "lr": 9.701972830135143e-06, "epoch": 3.9887971698113205, "percentage": 19.94, "elapsed_time": "0:12:34", "remaining_time": "0:50:30", "throughput": 5913.95, "total_tokens": 4464152} {"current_steps": 6770, "total_steps": 33920, "loss": 0.4955, "lr": 9.701097265305164e-06, "epoch": 3.9917452830188678, "percentage": 19.96, "elapsed_time": "0:12:35", "remaining_time": "0:50:29", "throughput": 5914.22, "total_tokens": 4467704} {"current_steps": 6775, "total_steps": 33920, "loss": 0.3201, "lr": 9.700220455839422e-06, "epoch": 3.994693396226415, "percentage": 19.97, "elapsed_time": "0:12:36", "remaining_time": "0:50:29", "throughput": 5914.73, "total_tokens": 4471736} {"current_steps": 6780, "total_steps": 33920, "loss": 0.4011, "lr": 9.69934240197006e-06, "epoch": 3.9976415094339623, "percentage": 19.99, "elapsed_time": "0:12:36", "remaining_time": "0:50:28", "throughput": 5915.03, "total_tokens": 4475128} {"current_steps": 6784, "total_steps": 33920, "eval_loss": 0.4945891797542572, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:12:55", "remaining_time": "0:51:41", "throughput": 5773.56, "total_tokens": 4476776} {"current_steps": 6785, "total_steps": 33920, "loss": 0.3097, "lr": 9.698463103929542e-06, "epoch": 4.00058962264151, "percentage": 20.0, "elapsed_time": "0:12:58", "remaining_time": "0:51:55", "throughput": 5748.03, "total_tokens": 4477256} {"current_steps": 6790, "total_steps": 33920, "loss": 0.3667, "lr": 9.697582561950669e-06, "epoch": 4.003537735849057, "percentage": 20.02, "elapsed_time": "0:12:59", "remaining_time": "0:51:54", "throughput": 5748.55, "total_tokens": 4481000} {"current_steps": 6795, "total_steps": 33920, "loss": 0.4009, "lr": 9.696700776266568e-06, "epoch": 4.006485849056604, "percentage": 20.03, "elapsed_time": "0:13:00", "remaining_time": "0:51:54", "throughput": 5749.14, "total_tokens": 4485000} {"current_steps": 6800, "total_steps": 33920, "loss": 0.3624, "lr": 9.695817747110694e-06, "epoch": 4.009433962264151, "percentage": 20.05, "elapsed_time": "0:13:00", "remaining_time": "0:51:53", "throughput": 5749.94, "total_tokens": 4489352} {"current_steps": 6805, "total_steps": 33920, "loss": 0.3813, "lr": 9.694933474716831e-06, "epoch": 4.012382075471698, "percentage": 20.06, "elapsed_time": "0:13:01", "remaining_time": "0:51:53", "throughput": 5750.25, "total_tokens": 4492776} {"current_steps": 6810, "total_steps": 33920, "loss": 0.5304, "lr": 9.6940479593191e-06, "epoch": 4.015330188679245, "percentage": 20.08, "elapsed_time": "0:13:01", "remaining_time": "0:51:52", "throughput": 5750.19, "total_tokens": 4495432} {"current_steps": 6815, "total_steps": 33920, "loss": 0.4689, "lr": 9.693161201151942e-06, "epoch": 4.0182783018867925, "percentage": 20.09, "elapsed_time": "0:13:02", "remaining_time": "0:51:51", "throughput": 5750.61, "total_tokens": 4499304} {"current_steps": 6820, "total_steps": 33920, "loss": 0.43, "lr": 9.692273200450128e-06, "epoch": 4.02122641509434, "percentage": 20.11, "elapsed_time": "0:13:02", "remaining_time": "0:51:50", "throughput": 5750.63, "total_tokens": 4502120} {"current_steps": 6825, "total_steps": 33920, "loss": 0.4379, "lr": 9.69138395744876e-06, "epoch": 4.024174528301887, "percentage": 20.12, "elapsed_time": "0:13:03", "remaining_time": "0:51:50", "throughput": 5751.07, "total_tokens": 4505800} {"current_steps": 6830, "total_steps": 33920, "loss": 0.5893, "lr": 9.690493472383274e-06, "epoch": 4.027122641509434, "percentage": 20.14, "elapsed_time": "0:13:03", "remaining_time": "0:51:49", "throughput": 5751.17, "total_tokens": 4508776} {"current_steps": 6835, "total_steps": 33920, "loss": 0.4979, "lr": 9.689601745489423e-06, "epoch": 4.030070754716981, "percentage": 20.15, "elapsed_time": "0:13:04", "remaining_time": "0:51:48", "throughput": 5751.38, "total_tokens": 4511976} {"current_steps": 6840, "total_steps": 33920, "loss": 0.3465, "lr": 9.6887087770033e-06, "epoch": 4.033018867924528, "percentage": 20.17, "elapsed_time": "0:13:05", "remaining_time": "0:51:48", "throughput": 5751.92, "total_tokens": 4515496} {"current_steps": 6845, "total_steps": 33920, "loss": 0.4798, "lr": 9.687814567161322e-06, "epoch": 4.035966981132075, "percentage": 20.18, "elapsed_time": "0:13:05", "remaining_time": "0:51:47", "throughput": 5752.74, "total_tokens": 4519752} {"current_steps": 6850, "total_steps": 33920, "loss": 0.5665, "lr": 9.686919116200232e-06, "epoch": 4.038915094339623, "percentage": 20.19, "elapsed_time": "0:13:06", "remaining_time": "0:51:46", "throughput": 5752.78, "total_tokens": 4522824} {"current_steps": 6855, "total_steps": 33920, "loss": 0.4818, "lr": 9.686022424357108e-06, "epoch": 4.04186320754717, "percentage": 20.21, "elapsed_time": "0:13:06", "remaining_time": "0:51:46", "throughput": 5752.78, "total_tokens": 4525704} {"current_steps": 6860, "total_steps": 33920, "loss": 0.4249, "lr": 9.685124491869353e-06, "epoch": 4.044811320754717, "percentage": 20.22, "elapsed_time": "0:13:07", "remaining_time": "0:51:45", "throughput": 5752.92, "total_tokens": 4528616} {"current_steps": 6865, "total_steps": 33920, "loss": 0.6815, "lr": 9.684225318974696e-06, "epoch": 4.0477594339622645, "percentage": 20.24, "elapsed_time": "0:13:07", "remaining_time": "0:51:44", "throughput": 5753.28, "total_tokens": 4532136} {"current_steps": 6870, "total_steps": 33920, "loss": 0.4211, "lr": 9.683324905911197e-06, "epoch": 4.050707547169812, "percentage": 20.25, "elapsed_time": "0:13:08", "remaining_time": "0:51:43", "throughput": 5753.39, "total_tokens": 4535048} {"current_steps": 6875, "total_steps": 33920, "loss": 0.5969, "lr": 9.682423252917245e-06, "epoch": 4.053655660377358, "percentage": 20.27, "elapsed_time": "0:13:08", "remaining_time": "0:51:43", "throughput": 5753.9, "total_tokens": 4539272} {"current_steps": 6880, "total_steps": 33920, "loss": 0.404, "lr": 9.681520360231557e-06, "epoch": 4.056603773584905, "percentage": 20.28, "elapsed_time": "0:13:09", "remaining_time": "0:51:43", "throughput": 5754.67, "total_tokens": 4543432} {"current_steps": 6885, "total_steps": 33920, "loss": 0.4648, "lr": 9.680616228093178e-06, "epoch": 4.059551886792453, "percentage": 20.3, "elapsed_time": "0:13:10", "remaining_time": "0:51:42", "throughput": 5754.72, "total_tokens": 4546408} {"current_steps": 6890, "total_steps": 33920, "loss": 0.429, "lr": 9.67971085674148e-06, "epoch": 4.0625, "percentage": 20.31, "elapsed_time": "0:13:10", "remaining_time": "0:51:41", "throughput": 5754.64, "total_tokens": 4549512} {"current_steps": 6895, "total_steps": 33920, "loss": 0.3032, "lr": 9.678804246416164e-06, "epoch": 4.065448113207547, "percentage": 20.33, "elapsed_time": "0:13:11", "remaining_time": "0:51:40", "throughput": 5754.78, "total_tokens": 4552648} {"current_steps": 6900, "total_steps": 33920, "loss": 0.4, "lr": 9.677896397357259e-06, "epoch": 4.068396226415095, "percentage": 20.34, "elapsed_time": "0:13:11", "remaining_time": "0:51:40", "throughput": 5755.47, "total_tokens": 4556744} {"current_steps": 6905, "total_steps": 33920, "loss": 0.5477, "lr": 9.676987309805121e-06, "epoch": 4.071344339622642, "percentage": 20.36, "elapsed_time": "0:13:12", "remaining_time": "0:51:39", "throughput": 5755.47, "total_tokens": 4559688} {"current_steps": 6910, "total_steps": 33920, "loss": 0.3645, "lr": 9.67607698400044e-06, "epoch": 4.074292452830188, "percentage": 20.37, "elapsed_time": "0:13:12", "remaining_time": "0:51:38", "throughput": 5755.49, "total_tokens": 4562376} {"current_steps": 6915, "total_steps": 33920, "loss": 0.5246, "lr": 9.67516542018422e-06, "epoch": 4.0772405660377355, "percentage": 20.39, "elapsed_time": "0:13:13", "remaining_time": "0:51:37", "throughput": 5755.31, "total_tokens": 4565032} {"current_steps": 6920, "total_steps": 33920, "loss": 0.5031, "lr": 9.67425261859781e-06, "epoch": 4.080188679245283, "percentage": 20.4, "elapsed_time": "0:13:13", "remaining_time": "0:51:36", "throughput": 5755.38, "total_tokens": 4567880} {"current_steps": 6925, "total_steps": 33920, "loss": 0.439, "lr": 9.673338579482871e-06, "epoch": 4.08313679245283, "percentage": 20.42, "elapsed_time": "0:13:14", "remaining_time": "0:51:36", "throughput": 5755.86, "total_tokens": 4571976} {"current_steps": 6930, "total_steps": 33920, "loss": 0.2951, "lr": 9.672423303081404e-06, "epoch": 4.086084905660377, "percentage": 20.43, "elapsed_time": "0:13:14", "remaining_time": "0:51:35", "throughput": 5756.14, "total_tokens": 4575720} {"current_steps": 6935, "total_steps": 33920, "loss": 0.3466, "lr": 9.67150678963573e-06, "epoch": 4.089033018867925, "percentage": 20.45, "elapsed_time": "0:13:15", "remaining_time": "0:51:35", "throughput": 5756.19, "total_tokens": 4578664} {"current_steps": 6940, "total_steps": 33920, "loss": 0.4631, "lr": 9.670589039388501e-06, "epoch": 4.091981132075472, "percentage": 20.46, "elapsed_time": "0:13:15", "remaining_time": "0:51:34", "throughput": 5755.93, "total_tokens": 4581544} {"current_steps": 6945, "total_steps": 33920, "loss": 0.3037, "lr": 9.669670052582695e-06, "epoch": 4.094929245283019, "percentage": 20.47, "elapsed_time": "0:13:16", "remaining_time": "0:51:33", "throughput": 5755.65, "total_tokens": 4584072} {"current_steps": 6950, "total_steps": 33920, "loss": 0.4392, "lr": 9.668749829461617e-06, "epoch": 4.097877358490566, "percentage": 20.49, "elapsed_time": "0:13:16", "remaining_time": "0:51:32", "throughput": 5756.18, "total_tokens": 4587432} {"current_steps": 6955, "total_steps": 33920, "loss": 0.4542, "lr": 9.667828370268898e-06, "epoch": 4.100825471698113, "percentage": 20.5, "elapsed_time": "0:13:17", "remaining_time": "0:51:31", "throughput": 5756.12, "total_tokens": 4590088} {"current_steps": 6960, "total_steps": 33920, "loss": 0.4443, "lr": 9.666905675248505e-06, "epoch": 4.10377358490566, "percentage": 20.52, "elapsed_time": "0:13:17", "remaining_time": "0:51:30", "throughput": 5755.98, "total_tokens": 4592872} {"current_steps": 6965, "total_steps": 33920, "loss": 0.469, "lr": 9.66598174464472e-06, "epoch": 4.1067216981132075, "percentage": 20.53, "elapsed_time": "0:13:18", "remaining_time": "0:51:30", "throughput": 5756.05, "total_tokens": 4595848} {"current_steps": 6970, "total_steps": 33920, "loss": 0.507, "lr": 9.665056578702157e-06, "epoch": 4.109669811320755, "percentage": 20.55, "elapsed_time": "0:13:18", "remaining_time": "0:51:29", "throughput": 5755.97, "total_tokens": 4598632} {"current_steps": 6975, "total_steps": 33920, "loss": 0.4464, "lr": 9.66413017766576e-06, "epoch": 4.112617924528302, "percentage": 20.56, "elapsed_time": "0:13:19", "remaining_time": "0:51:28", "throughput": 5756.13, "total_tokens": 4602056} {"current_steps": 6980, "total_steps": 33920, "loss": 0.3441, "lr": 9.663202541780799e-06, "epoch": 4.115566037735849, "percentage": 20.58, "elapsed_time": "0:13:20", "remaining_time": "0:51:27", "throughput": 5756.16, "total_tokens": 4605160} {"current_steps": 6985, "total_steps": 33920, "loss": 0.3655, "lr": 9.662273671292866e-06, "epoch": 4.118514150943396, "percentage": 20.59, "elapsed_time": "0:13:20", "remaining_time": "0:51:27", "throughput": 5756.55, "total_tokens": 4608840} {"current_steps": 6990, "total_steps": 33920, "loss": 0.4636, "lr": 9.661343566447886e-06, "epoch": 4.121462264150943, "percentage": 20.61, "elapsed_time": "0:13:21", "remaining_time": "0:51:26", "throughput": 5757.26, "total_tokens": 4612904} {"current_steps": 6995, "total_steps": 33920, "loss": 0.4826, "lr": 9.660412227492107e-06, "epoch": 4.12441037735849, "percentage": 20.62, "elapsed_time": "0:13:21", "remaining_time": "0:51:26", "throughput": 5757.49, "total_tokens": 4616072} {"current_steps": 7000, "total_steps": 33920, "loss": 0.5116, "lr": 9.659479654672106e-06, "epoch": 4.127358490566038, "percentage": 20.64, "elapsed_time": "0:13:22", "remaining_time": "0:51:25", "throughput": 5757.53, "total_tokens": 4619144} {"current_steps": 7005, "total_steps": 33920, "loss": 0.3966, "lr": 9.658545848234784e-06, "epoch": 4.130306603773585, "percentage": 20.65, "elapsed_time": "0:13:22", "remaining_time": "0:51:24", "throughput": 5757.65, "total_tokens": 4621928} {"current_steps": 7010, "total_steps": 33920, "loss": 0.6536, "lr": 9.657610808427372e-06, "epoch": 4.133254716981132, "percentage": 20.67, "elapsed_time": "0:13:23", "remaining_time": "0:51:23", "throughput": 5758.06, "total_tokens": 4625192} {"current_steps": 7015, "total_steps": 33920, "loss": 0.392, "lr": 9.656674535497425e-06, "epoch": 4.1362028301886795, "percentage": 20.68, "elapsed_time": "0:13:23", "remaining_time": "0:51:22", "throughput": 5758.39, "total_tokens": 4628488} {"current_steps": 7020, "total_steps": 33920, "loss": 0.6573, "lr": 9.655737029692827e-06, "epoch": 4.139150943396227, "percentage": 20.7, "elapsed_time": "0:13:24", "remaining_time": "0:51:21", "throughput": 5758.12, "total_tokens": 4631176} {"current_steps": 7025, "total_steps": 33920, "loss": 0.5352, "lr": 9.654798291261785e-06, "epoch": 4.142099056603773, "percentage": 20.71, "elapsed_time": "0:13:24", "remaining_time": "0:51:21", "throughput": 5758.31, "total_tokens": 4634184} {"current_steps": 7030, "total_steps": 33920, "loss": 0.4486, "lr": 9.653858320452833e-06, "epoch": 4.1450471698113205, "percentage": 20.73, "elapsed_time": "0:13:25", "remaining_time": "0:51:21", "throughput": 5758.94, "total_tokens": 4639944} {"current_steps": 7035, "total_steps": 33920, "loss": 0.4741, "lr": 9.652917117514836e-06, "epoch": 4.147995283018868, "percentage": 20.74, "elapsed_time": "0:13:26", "remaining_time": "0:51:20", "throughput": 5759.06, "total_tokens": 4642920} {"current_steps": 7040, "total_steps": 33920, "loss": 0.3218, "lr": 9.651974682696975e-06, "epoch": 4.150943396226415, "percentage": 20.75, "elapsed_time": "0:13:26", "remaining_time": "0:51:20", "throughput": 5759.15, "total_tokens": 4646152} {"current_steps": 7045, "total_steps": 33920, "loss": 0.3787, "lr": 9.651031016248773e-06, "epoch": 4.153891509433962, "percentage": 20.77, "elapsed_time": "0:13:27", "remaining_time": "0:51:19", "throughput": 5759.34, "total_tokens": 4649288} {"current_steps": 7050, "total_steps": 33920, "loss": 0.3528, "lr": 9.65008611842006e-06, "epoch": 4.15683962264151, "percentage": 20.78, "elapsed_time": "0:13:27", "remaining_time": "0:51:18", "throughput": 5759.81, "total_tokens": 4652744} {"current_steps": 7055, "total_steps": 33920, "loss": 0.4679, "lr": 9.64913998946101e-06, "epoch": 4.159787735849057, "percentage": 20.8, "elapsed_time": "0:13:28", "remaining_time": "0:51:18", "throughput": 5760.13, "total_tokens": 4656200} {"current_steps": 7060, "total_steps": 33920, "loss": 0.3994, "lr": 9.648192629622109e-06, "epoch": 4.162735849056604, "percentage": 20.81, "elapsed_time": "0:13:28", "remaining_time": "0:51:17", "throughput": 5759.77, "total_tokens": 4658600} {"current_steps": 7065, "total_steps": 33920, "loss": 0.6261, "lr": 9.647244039154178e-06, "epoch": 4.165683962264151, "percentage": 20.83, "elapsed_time": "0:13:29", "remaining_time": "0:51:16", "throughput": 5759.74, "total_tokens": 4661352} {"current_steps": 7070, "total_steps": 33920, "loss": 0.4016, "lr": 9.64629421830836e-06, "epoch": 4.168632075471698, "percentage": 20.84, "elapsed_time": "0:13:29", "remaining_time": "0:51:15", "throughput": 5760.26, "total_tokens": 4664872} {"current_steps": 7075, "total_steps": 33920, "loss": 0.3856, "lr": 9.64534316733612e-06, "epoch": 4.171580188679245, "percentage": 20.86, "elapsed_time": "0:13:30", "remaining_time": "0:51:14", "throughput": 5760.67, "total_tokens": 4668008} {"current_steps": 7080, "total_steps": 33920, "loss": 0.4582, "lr": 9.644390886489258e-06, "epoch": 4.1745283018867925, "percentage": 20.87, "elapsed_time": "0:13:30", "remaining_time": "0:51:13", "throughput": 5760.41, "total_tokens": 4670504} {"current_steps": 7085, "total_steps": 33920, "loss": 0.5076, "lr": 9.643437376019893e-06, "epoch": 4.17747641509434, "percentage": 20.89, "elapsed_time": "0:13:31", "remaining_time": "0:51:13", "throughput": 5760.94, "total_tokens": 4674344} {"current_steps": 7090, "total_steps": 33920, "loss": 0.5465, "lr": 9.64248263618047e-06, "epoch": 4.180424528301887, "percentage": 20.9, "elapsed_time": "0:13:31", "remaining_time": "0:51:12", "throughput": 5760.94, "total_tokens": 4676968} {"current_steps": 7095, "total_steps": 33920, "loss": 0.355, "lr": 9.64152666722376e-06, "epoch": 4.183372641509434, "percentage": 20.92, "elapsed_time": "0:13:32", "remaining_time": "0:51:11", "throughput": 5761.04, "total_tokens": 4679912} {"current_steps": 7100, "total_steps": 33920, "loss": 0.4788, "lr": 9.640569469402863e-06, "epoch": 4.186320754716981, "percentage": 20.93, "elapsed_time": "0:13:32", "remaining_time": "0:51:10", "throughput": 5761.15, "total_tokens": 4682856} {"current_steps": 7105, "total_steps": 33920, "loss": 0.3387, "lr": 9.639611042971198e-06, "epoch": 4.189268867924528, "percentage": 20.95, "elapsed_time": "0:13:33", "remaining_time": "0:51:09", "throughput": 5761.54, "total_tokens": 4686216} {"current_steps": 7110, "total_steps": 33920, "loss": 0.461, "lr": 9.638651388182514e-06, "epoch": 4.192216981132075, "percentage": 20.96, "elapsed_time": "0:13:33", "remaining_time": "0:51:08", "throughput": 5761.75, "total_tokens": 4689192} {"current_steps": 7115, "total_steps": 33920, "loss": 0.316, "lr": 9.637690505290884e-06, "epoch": 4.195165094339623, "percentage": 20.98, "elapsed_time": "0:13:34", "remaining_time": "0:51:08", "throughput": 5762.06, "total_tokens": 4692552} {"current_steps": 7120, "total_steps": 33920, "loss": 0.4007, "lr": 9.636728394550705e-06, "epoch": 4.19811320754717, "percentage": 20.99, "elapsed_time": "0:13:34", "remaining_time": "0:51:07", "throughput": 5761.98, "total_tokens": 4695272} {"current_steps": 7125, "total_steps": 33920, "loss": 0.498, "lr": 9.6357650562167e-06, "epoch": 4.201061320754717, "percentage": 21.01, "elapsed_time": "0:13:35", "remaining_time": "0:51:06", "throughput": 5761.82, "total_tokens": 4698152} {"current_steps": 7130, "total_steps": 33920, "loss": 0.6924, "lr": 9.634800490543918e-06, "epoch": 4.2040094339622645, "percentage": 21.02, "elapsed_time": "0:13:36", "remaining_time": "0:51:06", "throughput": 5762.2, "total_tokens": 4702280} {"current_steps": 7135, "total_steps": 33920, "loss": 0.3773, "lr": 9.633834697787731e-06, "epoch": 4.206957547169812, "percentage": 21.03, "elapsed_time": "0:13:36", "remaining_time": "0:51:05", "throughput": 5762.05, "total_tokens": 4705064} {"current_steps": 7140, "total_steps": 33920, "loss": 0.4358, "lr": 9.632867678203836e-06, "epoch": 4.209905660377358, "percentage": 21.05, "elapsed_time": "0:13:37", "remaining_time": "0:51:04", "throughput": 5761.53, "total_tokens": 4707336} {"current_steps": 7145, "total_steps": 33920, "loss": 0.4577, "lr": 9.631899432048258e-06, "epoch": 4.212853773584905, "percentage": 21.06, "elapsed_time": "0:13:37", "remaining_time": "0:51:03", "throughput": 5761.95, "total_tokens": 4711176} {"current_steps": 7150, "total_steps": 33920, "loss": 0.3796, "lr": 9.630929959577343e-06, "epoch": 4.215801886792453, "percentage": 21.08, "elapsed_time": "0:13:38", "remaining_time": "0:51:03", "throughput": 5762.09, "total_tokens": 4714280} {"current_steps": 7155, "total_steps": 33920, "loss": 0.5988, "lr": 9.629959261047764e-06, "epoch": 4.21875, "percentage": 21.09, "elapsed_time": "0:13:38", "remaining_time": "0:51:02", "throughput": 5762.33, "total_tokens": 4717256} {"current_steps": 7160, "total_steps": 33920, "loss": 0.5037, "lr": 9.628987336716513e-06, "epoch": 4.221698113207547, "percentage": 21.11, "elapsed_time": "0:13:39", "remaining_time": "0:51:01", "throughput": 5762.69, "total_tokens": 4720520} {"current_steps": 7165, "total_steps": 33920, "loss": 0.3138, "lr": 9.628014186840918e-06, "epoch": 4.224646226415095, "percentage": 21.12, "elapsed_time": "0:13:40", "remaining_time": "0:51:02", "throughput": 5763.57, "total_tokens": 4726760} {"current_steps": 7170, "total_steps": 33920, "loss": 0.4806, "lr": 9.62703981167862e-06, "epoch": 4.227594339622642, "percentage": 21.14, "elapsed_time": "0:13:40", "remaining_time": "0:51:02", "throughput": 5763.91, "total_tokens": 4730632} {"current_steps": 7175, "total_steps": 33920, "loss": 0.5059, "lr": 9.626064211487592e-06, "epoch": 4.230542452830188, "percentage": 21.15, "elapsed_time": "0:13:41", "remaining_time": "0:51:01", "throughput": 5763.6, "total_tokens": 4733224} {"current_steps": 7180, "total_steps": 33920, "loss": 0.4392, "lr": 9.625087386526125e-06, "epoch": 4.2334905660377355, "percentage": 21.17, "elapsed_time": "0:13:41", "remaining_time": "0:51:00", "throughput": 5764.24, "total_tokens": 4736904} {"current_steps": 7185, "total_steps": 33920, "loss": 0.4395, "lr": 9.624109337052839e-06, "epoch": 4.236438679245283, "percentage": 21.18, "elapsed_time": "0:13:42", "remaining_time": "0:50:59", "throughput": 5763.85, "total_tokens": 4739336} {"current_steps": 7190, "total_steps": 33920, "loss": 0.5551, "lr": 9.623130063326678e-06, "epoch": 4.23938679245283, "percentage": 21.2, "elapsed_time": "0:13:42", "remaining_time": "0:50:58", "throughput": 5763.97, "total_tokens": 4742376} {"current_steps": 7195, "total_steps": 33920, "loss": 0.3712, "lr": 9.622149565606909e-06, "epoch": 4.242334905660377, "percentage": 21.21, "elapsed_time": "0:13:43", "remaining_time": "0:50:58", "throughput": 5764.11, "total_tokens": 4745800} {"current_steps": 7200, "total_steps": 33920, "loss": 0.4374, "lr": 9.621167844153122e-06, "epoch": 4.245283018867925, "percentage": 21.23, "elapsed_time": "0:13:43", "remaining_time": "0:50:57", "throughput": 5764.57, "total_tokens": 4749224} {"current_steps": 7205, "total_steps": 33920, "loss": 0.4197, "lr": 9.620184899225231e-06, "epoch": 4.248231132075472, "percentage": 21.24, "elapsed_time": "0:13:44", "remaining_time": "0:50:56", "throughput": 5764.21, "total_tokens": 4751688} {"current_steps": 7210, "total_steps": 33920, "loss": 0.4389, "lr": 9.619200731083477e-06, "epoch": 4.251179245283019, "percentage": 21.26, "elapsed_time": "0:13:44", "remaining_time": "0:50:55", "throughput": 5764.43, "total_tokens": 4755176} {"current_steps": 7215, "total_steps": 33920, "loss": 0.4302, "lr": 9.618215339988422e-06, "epoch": 4.254127358490566, "percentage": 21.27, "elapsed_time": "0:13:45", "remaining_time": "0:50:55", "throughput": 5764.72, "total_tokens": 4759528} {"current_steps": 7220, "total_steps": 33920, "loss": 0.3862, "lr": 9.617228726200951e-06, "epoch": 4.257075471698113, "percentage": 21.29, "elapsed_time": "0:13:46", "remaining_time": "0:50:55", "throughput": 5764.39, "total_tokens": 4762312} {"current_steps": 7225, "total_steps": 33920, "loss": 0.3715, "lr": 9.616240889982277e-06, "epoch": 4.26002358490566, "percentage": 21.3, "elapsed_time": "0:13:46", "remaining_time": "0:50:54", "throughput": 5764.5, "total_tokens": 4765512} {"current_steps": 7230, "total_steps": 33920, "loss": 0.428, "lr": 9.61525183159393e-06, "epoch": 4.2629716981132075, "percentage": 21.31, "elapsed_time": "0:13:47", "remaining_time": "0:50:53", "throughput": 5764.01, "total_tokens": 4767880} {"current_steps": 7235, "total_steps": 33920, "loss": 0.5832, "lr": 9.614261551297774e-06, "epoch": 4.265919811320755, "percentage": 21.33, "elapsed_time": "0:13:47", "remaining_time": "0:50:52", "throughput": 5764.76, "total_tokens": 4771752} {"current_steps": 7240, "total_steps": 33920, "loss": 0.5245, "lr": 9.613270049355983e-06, "epoch": 4.268867924528302, "percentage": 21.34, "elapsed_time": "0:13:48", "remaining_time": "0:50:52", "throughput": 5765.28, "total_tokens": 4775464} {"current_steps": 7245, "total_steps": 33920, "loss": 0.4159, "lr": 9.612277326031065e-06, "epoch": 4.271816037735849, "percentage": 21.36, "elapsed_time": "0:13:48", "remaining_time": "0:50:51", "throughput": 5765.45, "total_tokens": 4778568} {"current_steps": 7250, "total_steps": 33920, "loss": 0.5231, "lr": 9.611283381585848e-06, "epoch": 4.274764150943396, "percentage": 21.37, "elapsed_time": "0:13:49", "remaining_time": "0:50:50", "throughput": 5765.66, "total_tokens": 4781544} {"current_steps": 7255, "total_steps": 33920, "loss": 0.432, "lr": 9.61028821628348e-06, "epoch": 4.277712264150943, "percentage": 21.39, "elapsed_time": "0:13:49", "remaining_time": "0:50:49", "throughput": 5765.59, "total_tokens": 4784456} {"current_steps": 7260, "total_steps": 33920, "loss": 0.4013, "lr": 9.609291830387439e-06, "epoch": 4.28066037735849, "percentage": 21.4, "elapsed_time": "0:13:50", "remaining_time": "0:50:48", "throughput": 5765.41, "total_tokens": 4786984} {"current_steps": 7265, "total_steps": 33920, "loss": 0.3934, "lr": 9.608294224161523e-06, "epoch": 4.283608490566038, "percentage": 21.42, "elapsed_time": "0:13:50", "remaining_time": "0:50:48", "throughput": 5765.53, "total_tokens": 4790312} {"current_steps": 7270, "total_steps": 33920, "loss": 0.4572, "lr": 9.607295397869847e-06, "epoch": 4.286556603773585, "percentage": 21.43, "elapsed_time": "0:13:51", "remaining_time": "0:50:47", "throughput": 5765.63, "total_tokens": 4793224} {"current_steps": 7275, "total_steps": 33920, "loss": 0.3633, "lr": 9.60629535177686e-06, "epoch": 4.289504716981132, "percentage": 21.45, "elapsed_time": "0:13:51", "remaining_time": "0:50:46", "throughput": 5765.23, "total_tokens": 4795752} {"current_steps": 7280, "total_steps": 33920, "loss": 0.5116, "lr": 9.605294086147325e-06, "epoch": 4.2924528301886795, "percentage": 21.46, "elapsed_time": "0:13:52", "remaining_time": "0:50:45", "throughput": 5765.43, "total_tokens": 4798696} {"current_steps": 7285, "total_steps": 33920, "loss": 0.4853, "lr": 9.604291601246333e-06, "epoch": 4.295400943396227, "percentage": 21.48, "elapsed_time": "0:13:52", "remaining_time": "0:50:44", "throughput": 5765.66, "total_tokens": 4801768} {"current_steps": 7290, "total_steps": 33920, "loss": 0.46, "lr": 9.603287897339299e-06, "epoch": 4.298349056603773, "percentage": 21.49, "elapsed_time": "0:13:53", "remaining_time": "0:50:44", "throughput": 5766.3, "total_tokens": 4805768} {"current_steps": 7295, "total_steps": 33920, "loss": 0.5398, "lr": 9.602282974691953e-06, "epoch": 4.3012971698113205, "percentage": 21.51, "elapsed_time": "0:13:53", "remaining_time": "0:50:43", "throughput": 5766.25, "total_tokens": 4808552} {"current_steps": 7300, "total_steps": 33920, "loss": 0.6175, "lr": 9.601276833570355e-06, "epoch": 4.304245283018868, "percentage": 21.52, "elapsed_time": "0:13:54", "remaining_time": "0:50:42", "throughput": 5766.23, "total_tokens": 4811432} {"current_steps": 7305, "total_steps": 33920, "loss": 0.4417, "lr": 9.600269474240885e-06, "epoch": 4.307193396226415, "percentage": 21.54, "elapsed_time": "0:13:55", "remaining_time": "0:50:42", "throughput": 5766.8, "total_tokens": 4815464} {"current_steps": 7310, "total_steps": 33920, "loss": 0.5406, "lr": 9.599260896970246e-06, "epoch": 4.310141509433962, "percentage": 21.55, "elapsed_time": "0:13:55", "remaining_time": "0:50:41", "throughput": 5766.72, "total_tokens": 4818344} {"current_steps": 7315, "total_steps": 33920, "loss": 0.5049, "lr": 9.598251102025463e-06, "epoch": 4.31308962264151, "percentage": 21.57, "elapsed_time": "0:13:56", "remaining_time": "0:50:41", "throughput": 5767.26, "total_tokens": 4822280} {"current_steps": 7320, "total_steps": 33920, "loss": 0.4784, "lr": 9.597240089673882e-06, "epoch": 4.316037735849057, "percentage": 21.58, "elapsed_time": "0:13:56", "remaining_time": "0:50:40", "throughput": 5767.34, "total_tokens": 4825192} {"current_steps": 7325, "total_steps": 33920, "loss": 0.4279, "lr": 9.596227860183175e-06, "epoch": 4.318985849056604, "percentage": 21.59, "elapsed_time": "0:13:57", "remaining_time": "0:50:39", "throughput": 5767.96, "total_tokens": 4829128} {"current_steps": 7330, "total_steps": 33920, "loss": 0.3524, "lr": 9.595214413821334e-06, "epoch": 4.321933962264151, "percentage": 21.61, "elapsed_time": "0:13:57", "remaining_time": "0:50:38", "throughput": 5767.94, "total_tokens": 4832104} {"current_steps": 7335, "total_steps": 33920, "loss": 0.442, "lr": 9.59419975085667e-06, "epoch": 4.324882075471698, "percentage": 21.62, "elapsed_time": "0:13:58", "remaining_time": "0:50:38", "throughput": 5767.71, "total_tokens": 4835016} {"current_steps": 7340, "total_steps": 33920, "loss": 0.3936, "lr": 9.593183871557826e-06, "epoch": 4.327830188679245, "percentage": 21.64, "elapsed_time": "0:13:58", "remaining_time": "0:50:37", "throughput": 5767.91, "total_tokens": 4838216} {"current_steps": 7345, "total_steps": 33920, "loss": 0.4035, "lr": 9.592166776193754e-06, "epoch": 4.3307783018867925, "percentage": 21.65, "elapsed_time": "0:13:59", "remaining_time": "0:50:36", "throughput": 5767.94, "total_tokens": 4841096} {"current_steps": 7350, "total_steps": 33920, "loss": 0.5548, "lr": 9.591148465033738e-06, "epoch": 4.33372641509434, "percentage": 21.67, "elapsed_time": "0:13:59", "remaining_time": "0:50:36", "throughput": 5768.54, "total_tokens": 4845032} {"current_steps": 7355, "total_steps": 33920, "loss": 0.4652, "lr": 9.590128938347378e-06, "epoch": 4.336674528301887, "percentage": 21.68, "elapsed_time": "0:14:00", "remaining_time": "0:50:35", "throughput": 5768.24, "total_tokens": 4847784} {"current_steps": 7360, "total_steps": 33920, "loss": 0.4244, "lr": 9.589108196404599e-06, "epoch": 4.339622641509434, "percentage": 21.7, "elapsed_time": "0:14:00", "remaining_time": "0:50:34", "throughput": 5768.26, "total_tokens": 4850952} {"current_steps": 7365, "total_steps": 33920, "loss": 0.4343, "lr": 9.588086239475649e-06, "epoch": 4.342570754716981, "percentage": 21.71, "elapsed_time": "0:14:01", "remaining_time": "0:50:33", "throughput": 5768.21, "total_tokens": 4853800} {"current_steps": 7370, "total_steps": 33920, "loss": 0.6125, "lr": 9.587063067831092e-06, "epoch": 4.345518867924528, "percentage": 21.73, "elapsed_time": "0:14:02", "remaining_time": "0:50:33", "throughput": 5768.31, "total_tokens": 4857000} {"current_steps": 7375, "total_steps": 33920, "loss": 0.4878, "lr": 9.586038681741818e-06, "epoch": 4.348466981132075, "percentage": 21.74, "elapsed_time": "0:14:02", "remaining_time": "0:50:32", "throughput": 5768.77, "total_tokens": 4860520} {"current_steps": 7380, "total_steps": 33920, "loss": 0.2957, "lr": 9.58501308147904e-06, "epoch": 4.351415094339623, "percentage": 21.76, "elapsed_time": "0:14:03", "remaining_time": "0:50:31", "throughput": 5768.82, "total_tokens": 4863432} {"current_steps": 7385, "total_steps": 33920, "loss": 0.489, "lr": 9.583986267314288e-06, "epoch": 4.35436320754717, "percentage": 21.77, "elapsed_time": "0:14:03", "remaining_time": "0:50:31", "throughput": 5769.23, "total_tokens": 4867112} {"current_steps": 7390, "total_steps": 33920, "loss": 0.4858, "lr": 9.582958239519416e-06, "epoch": 4.357311320754717, "percentage": 21.79, "elapsed_time": "0:14:04", "remaining_time": "0:50:30", "throughput": 5769.6, "total_tokens": 4870536} {"current_steps": 7395, "total_steps": 33920, "loss": 0.4414, "lr": 9.581928998366597e-06, "epoch": 4.3602594339622645, "percentage": 21.8, "elapsed_time": "0:14:04", "remaining_time": "0:50:29", "throughput": 5768.92, "total_tokens": 4872840} {"current_steps": 7400, "total_steps": 33920, "loss": 0.625, "lr": 9.58089854412833e-06, "epoch": 4.363207547169811, "percentage": 21.82, "elapsed_time": "0:14:05", "remaining_time": "0:50:29", "throughput": 5768.94, "total_tokens": 4875912} {"current_steps": 7405, "total_steps": 33920, "loss": 0.4767, "lr": 9.579866877077431e-06, "epoch": 4.366155660377358, "percentage": 21.83, "elapsed_time": "0:14:05", "remaining_time": "0:50:28", "throughput": 5769.51, "total_tokens": 4879816} {"current_steps": 7410, "total_steps": 33920, "loss": 0.6627, "lr": 9.578833997487038e-06, "epoch": 4.369103773584905, "percentage": 21.85, "elapsed_time": "0:14:06", "remaining_time": "0:50:27", "throughput": 5769.76, "total_tokens": 4883240} {"current_steps": 7415, "total_steps": 33920, "loss": 0.595, "lr": 9.57779990563061e-06, "epoch": 4.372051886792453, "percentage": 21.86, "elapsed_time": "0:14:07", "remaining_time": "0:50:27", "throughput": 5770.29, "total_tokens": 4887560} {"current_steps": 7420, "total_steps": 33920, "loss": 0.5417, "lr": 9.576764601781928e-06, "epoch": 4.375, "percentage": 21.88, "elapsed_time": "0:14:07", "remaining_time": "0:50:27", "throughput": 5770.94, "total_tokens": 4891560} {"current_steps": 7425, "total_steps": 33920, "loss": 0.5166, "lr": 9.575728086215093e-06, "epoch": 4.377948113207547, "percentage": 21.89, "elapsed_time": "0:14:08", "remaining_time": "0:50:26", "throughput": 5771.28, "total_tokens": 4895016} {"current_steps": 7430, "total_steps": 33920, "loss": 0.5226, "lr": 9.574690359204527e-06, "epoch": 4.380896226415095, "percentage": 21.9, "elapsed_time": "0:14:08", "remaining_time": "0:50:25", "throughput": 5771.55, "total_tokens": 4898376} {"current_steps": 7435, "total_steps": 33920, "loss": 0.4887, "lr": 9.573651421024972e-06, "epoch": 4.383844339622642, "percentage": 21.92, "elapsed_time": "0:14:09", "remaining_time": "0:50:25", "throughput": 5771.63, "total_tokens": 4901352} {"current_steps": 7440, "total_steps": 33920, "loss": 0.4941, "lr": 9.572611271951494e-06, "epoch": 4.386792452830189, "percentage": 21.93, "elapsed_time": "0:14:09", "remaining_time": "0:50:24", "throughput": 5771.75, "total_tokens": 4904616} {"current_steps": 7445, "total_steps": 33920, "loss": 0.3854, "lr": 9.571569912259473e-06, "epoch": 4.3897405660377355, "percentage": 21.95, "elapsed_time": "0:14:10", "remaining_time": "0:50:23", "throughput": 5771.15, "total_tokens": 4907208} {"current_steps": 7450, "total_steps": 33920, "loss": 0.5374, "lr": 9.570527342224614e-06, "epoch": 4.392688679245283, "percentage": 21.96, "elapsed_time": "0:14:10", "remaining_time": "0:50:23", "throughput": 5771.47, "total_tokens": 4910536} {"current_steps": 7455, "total_steps": 33920, "loss": 0.7987, "lr": 9.569483562122945e-06, "epoch": 4.39563679245283, "percentage": 21.98, "elapsed_time": "0:14:11", "remaining_time": "0:50:22", "throughput": 5772.0, "total_tokens": 4914536} {"current_steps": 7460, "total_steps": 33920, "loss": 0.4393, "lr": 9.568438572230811e-06, "epoch": 4.398584905660377, "percentage": 21.99, "elapsed_time": "0:14:12", "remaining_time": "0:50:22", "throughput": 5772.42, "total_tokens": 4918280} {"current_steps": 7465, "total_steps": 33920, "loss": 0.5315, "lr": 9.567392372824873e-06, "epoch": 4.401533018867925, "percentage": 22.01, "elapsed_time": "0:14:12", "remaining_time": "0:50:21", "throughput": 5772.47, "total_tokens": 4921384} {"current_steps": 7470, "total_steps": 33920, "loss": 0.492, "lr": 9.566344964182123e-06, "epoch": 4.404481132075472, "percentage": 22.02, "elapsed_time": "0:14:13", "remaining_time": "0:50:20", "throughput": 5772.39, "total_tokens": 4924040} {"current_steps": 7475, "total_steps": 33920, "loss": 0.5681, "lr": 9.565296346579862e-06, "epoch": 4.407429245283019, "percentage": 22.04, "elapsed_time": "0:14:13", "remaining_time": "0:50:19", "throughput": 5772.36, "total_tokens": 4926856} {"current_steps": 7480, "total_steps": 33920, "loss": 0.4125, "lr": 9.564246520295719e-06, "epoch": 4.410377358490566, "percentage": 22.05, "elapsed_time": "0:14:14", "remaining_time": "0:50:18", "throughput": 5772.57, "total_tokens": 4929928} {"current_steps": 7485, "total_steps": 33920, "loss": 0.4978, "lr": 9.563195485607638e-06, "epoch": 4.413325471698113, "percentage": 22.07, "elapsed_time": "0:14:14", "remaining_time": "0:50:17", "throughput": 5772.53, "total_tokens": 4932776} {"current_steps": 7490, "total_steps": 33920, "loss": 0.4401, "lr": 9.562143242793885e-06, "epoch": 4.41627358490566, "percentage": 22.08, "elapsed_time": "0:14:15", "remaining_time": "0:50:17", "throughput": 5772.3, "total_tokens": 4935432} {"current_steps": 7495, "total_steps": 33920, "loss": 0.3923, "lr": 9.561089792133048e-06, "epoch": 4.4192216981132075, "percentage": 22.1, "elapsed_time": "0:14:15", "remaining_time": "0:50:16", "throughput": 5772.69, "total_tokens": 4939240} {"current_steps": 7500, "total_steps": 33920, "loss": 0.4536, "lr": 9.560035133904031e-06, "epoch": 4.422169811320755, "percentage": 22.11, "elapsed_time": "0:14:16", "remaining_time": "0:50:15", "throughput": 5772.58, "total_tokens": 4941960} {"current_steps": 7505, "total_steps": 33920, "loss": 0.5492, "lr": 9.55897926838606e-06, "epoch": 4.425117924528302, "percentage": 22.13, "elapsed_time": "0:14:16", "remaining_time": "0:50:15", "throughput": 5772.75, "total_tokens": 4945192} {"current_steps": 7510, "total_steps": 33920, "loss": 0.3717, "lr": 9.55792219585868e-06, "epoch": 4.428066037735849, "percentage": 22.14, "elapsed_time": "0:14:17", "remaining_time": "0:50:14", "throughput": 5773.1, "total_tokens": 4949192} {"current_steps": 7515, "total_steps": 33920, "loss": 0.3789, "lr": 9.556863916601754e-06, "epoch": 4.431014150943396, "percentage": 22.16, "elapsed_time": "0:14:17", "remaining_time": "0:50:14", "throughput": 5773.85, "total_tokens": 4953288} {"current_steps": 7520, "total_steps": 33920, "loss": 0.6161, "lr": 9.555804430895467e-06, "epoch": 4.433962264150943, "percentage": 22.17, "elapsed_time": "0:14:18", "remaining_time": "0:50:13", "throughput": 5773.83, "total_tokens": 4956136} {"current_steps": 7525, "total_steps": 33920, "loss": 0.4528, "lr": 9.554743739020325e-06, "epoch": 4.43691037735849, "percentage": 22.18, "elapsed_time": "0:14:19", "remaining_time": "0:50:13", "throughput": 5774.12, "total_tokens": 4960008} {"current_steps": 7530, "total_steps": 33920, "loss": 0.3395, "lr": 9.553681841257146e-06, "epoch": 4.439858490566038, "percentage": 22.2, "elapsed_time": "0:14:19", "remaining_time": "0:50:12", "throughput": 5774.31, "total_tokens": 4962984} {"current_steps": 7535, "total_steps": 33920, "loss": 0.5006, "lr": 9.552618737887073e-06, "epoch": 4.442806603773585, "percentage": 22.21, "elapsed_time": "0:14:20", "remaining_time": "0:50:11", "throughput": 5774.53, "total_tokens": 4966216} {"current_steps": 7540, "total_steps": 33920, "loss": 0.5901, "lr": 9.55155442919157e-06, "epoch": 4.445754716981132, "percentage": 22.23, "elapsed_time": "0:14:20", "remaining_time": "0:50:10", "throughput": 5773.97, "total_tokens": 4968712} {"current_steps": 7545, "total_steps": 33920, "loss": 0.349, "lr": 9.550488915452416e-06, "epoch": 4.4487028301886795, "percentage": 22.24, "elapsed_time": "0:14:21", "remaining_time": "0:50:10", "throughput": 5773.65, "total_tokens": 4971560} {"current_steps": 7550, "total_steps": 33920, "loss": 0.5026, "lr": 9.54942219695171e-06, "epoch": 4.451650943396227, "percentage": 22.26, "elapsed_time": "0:14:21", "remaining_time": "0:50:09", "throughput": 5773.76, "total_tokens": 4974568} {"current_steps": 7555, "total_steps": 33920, "loss": 0.4905, "lr": 9.54835427397187e-06, "epoch": 4.454599056603773, "percentage": 22.27, "elapsed_time": "0:14:22", "remaining_time": "0:50:08", "throughput": 5773.64, "total_tokens": 4977320} {"current_steps": 7560, "total_steps": 33920, "loss": 0.453, "lr": 9.547285146795634e-06, "epoch": 4.4575471698113205, "percentage": 22.29, "elapsed_time": "0:14:22", "remaining_time": "0:50:07", "throughput": 5773.3, "total_tokens": 4979720} {"current_steps": 7565, "total_steps": 33920, "loss": 0.4132, "lr": 9.546214815706059e-06, "epoch": 4.460495283018868, "percentage": 22.3, "elapsed_time": "0:14:23", "remaining_time": "0:50:06", "throughput": 5773.27, "total_tokens": 4982824} {"current_steps": 7570, "total_steps": 33920, "loss": 0.5406, "lr": 9.545143280986518e-06, "epoch": 4.463443396226415, "percentage": 22.32, "elapsed_time": "0:14:23", "remaining_time": "0:50:06", "throughput": 5773.23, "total_tokens": 4985928} {"current_steps": 7575, "total_steps": 33920, "loss": 0.4692, "lr": 9.544070542920703e-06, "epoch": 4.466391509433962, "percentage": 22.33, "elapsed_time": "0:14:24", "remaining_time": "0:50:05", "throughput": 5773.52, "total_tokens": 4989160} {"current_steps": 7580, "total_steps": 33920, "loss": 0.3725, "lr": 9.542996601792629e-06, "epoch": 4.46933962264151, "percentage": 22.35, "elapsed_time": "0:14:24", "remaining_time": "0:50:04", "throughput": 5772.82, "total_tokens": 4991496} {"current_steps": 7585, "total_steps": 33920, "loss": 0.441, "lr": 9.541921457886624e-06, "epoch": 4.472287735849057, "percentage": 22.36, "elapsed_time": "0:14:25", "remaining_time": "0:50:03", "throughput": 5772.89, "total_tokens": 4994280} {"current_steps": 7590, "total_steps": 33920, "loss": 0.4247, "lr": 9.54084511148734e-06, "epoch": 4.475235849056604, "percentage": 22.38, "elapsed_time": "0:14:25", "remaining_time": "0:50:03", "throughput": 5773.22, "total_tokens": 4997832} {"current_steps": 7595, "total_steps": 33920, "loss": 0.5385, "lr": 9.539767562879742e-06, "epoch": 4.478183962264151, "percentage": 22.39, "elapsed_time": "0:14:26", "remaining_time": "0:50:02", "throughput": 5772.73, "total_tokens": 5000424} {"current_steps": 7600, "total_steps": 33920, "loss": 0.3145, "lr": 9.538688812349118e-06, "epoch": 4.481132075471698, "percentage": 22.41, "elapsed_time": "0:14:26", "remaining_time": "0:50:01", "throughput": 5772.15, "total_tokens": 5003048} {"current_steps": 7605, "total_steps": 33920, "loss": 0.4413, "lr": 9.537608860181069e-06, "epoch": 4.484080188679245, "percentage": 22.42, "elapsed_time": "0:14:27", "remaining_time": "0:50:00", "throughput": 5772.05, "total_tokens": 5005832} {"current_steps": 7610, "total_steps": 33920, "loss": 0.5411, "lr": 9.536527706661519e-06, "epoch": 4.4870283018867925, "percentage": 22.44, "elapsed_time": "0:14:27", "remaining_time": "0:50:00", "throughput": 5771.78, "total_tokens": 5008552} {"current_steps": 7615, "total_steps": 33920, "loss": 0.5087, "lr": 9.535445352076707e-06, "epoch": 4.48997641509434, "percentage": 22.45, "elapsed_time": "0:14:28", "remaining_time": "0:49:59", "throughput": 5771.36, "total_tokens": 5011016} {"current_steps": 7620, "total_steps": 33920, "loss": 0.3792, "lr": 9.534361796713191e-06, "epoch": 4.492924528301887, "percentage": 22.46, "elapsed_time": "0:14:28", "remaining_time": "0:49:58", "throughput": 5771.23, "total_tokens": 5013736} {"current_steps": 7625, "total_steps": 33920, "loss": 0.5086, "lr": 9.533277040857847e-06, "epoch": 4.495872641509434, "percentage": 22.48, "elapsed_time": "0:14:29", "remaining_time": "0:49:57", "throughput": 5771.3, "total_tokens": 5016968} {"current_steps": 7630, "total_steps": 33920, "loss": 0.6187, "lr": 9.53219108479787e-06, "epoch": 4.498820754716981, "percentage": 22.49, "elapsed_time": "0:14:29", "remaining_time": "0:49:56", "throughput": 5770.86, "total_tokens": 5019464} {"current_steps": 7635, "total_steps": 33920, "loss": 0.4901, "lr": 9.53110392882077e-06, "epoch": 4.501768867924528, "percentage": 22.51, "elapsed_time": "0:14:30", "remaining_time": "0:49:56", "throughput": 5770.82, "total_tokens": 5022376} {"current_steps": 7640, "total_steps": 33920, "loss": 0.6376, "lr": 9.530015573214378e-06, "epoch": 4.504716981132075, "percentage": 22.52, "elapsed_time": "0:14:30", "remaining_time": "0:49:55", "throughput": 5771.48, "total_tokens": 5026440} {"current_steps": 7645, "total_steps": 33920, "loss": 0.5844, "lr": 9.528926018266837e-06, "epoch": 4.507665094339623, "percentage": 22.54, "elapsed_time": "0:14:31", "remaining_time": "0:49:55", "throughput": 5771.9, "total_tokens": 5029896} {"current_steps": 7650, "total_steps": 33920, "loss": 0.4099, "lr": 9.527835264266617e-06, "epoch": 4.51061320754717, "percentage": 22.55, "elapsed_time": "0:14:31", "remaining_time": "0:49:54", "throughput": 5771.87, "total_tokens": 5032808} {"current_steps": 7655, "total_steps": 33920, "loss": 0.4673, "lr": 9.526743311502496e-06, "epoch": 4.513561320754717, "percentage": 22.57, "elapsed_time": "0:14:32", "remaining_time": "0:49:53", "throughput": 5771.99, "total_tokens": 5035784} {"current_steps": 7660, "total_steps": 33920, "loss": 0.523, "lr": 9.525650160263573e-06, "epoch": 4.5165094339622645, "percentage": 22.58, "elapsed_time": "0:14:33", "remaining_time": "0:49:52", "throughput": 5772.22, "total_tokens": 5039240} {"current_steps": 7665, "total_steps": 33920, "loss": 0.4746, "lr": 9.524555810839267e-06, "epoch": 4.519457547169811, "percentage": 22.6, "elapsed_time": "0:14:33", "remaining_time": "0:49:52", "throughput": 5772.4, "total_tokens": 5042664} {"current_steps": 7670, "total_steps": 33920, "loss": 0.4488, "lr": 9.523460263519309e-06, "epoch": 4.522405660377358, "percentage": 22.61, "elapsed_time": "0:14:34", "remaining_time": "0:49:51", "throughput": 5772.36, "total_tokens": 5045672} {"current_steps": 7675, "total_steps": 33920, "loss": 0.5539, "lr": 9.522363518593753e-06, "epoch": 4.525353773584905, "percentage": 22.63, "elapsed_time": "0:14:34", "remaining_time": "0:49:51", "throughput": 5772.43, "total_tokens": 5049160} {"current_steps": 7680, "total_steps": 33920, "loss": 0.4399, "lr": 9.521265576352963e-06, "epoch": 4.528301886792453, "percentage": 22.64, "elapsed_time": "0:14:35", "remaining_time": "0:49:50", "throughput": 5772.57, "total_tokens": 5052040} {"current_steps": 7685, "total_steps": 33920, "loss": 0.4534, "lr": 9.520166437087628e-06, "epoch": 4.53125, "percentage": 22.66, "elapsed_time": "0:14:35", "remaining_time": "0:49:49", "throughput": 5772.74, "total_tokens": 5055272} {"current_steps": 7690, "total_steps": 33920, "loss": 0.3648, "lr": 9.519066101088748e-06, "epoch": 4.534198113207547, "percentage": 22.67, "elapsed_time": "0:14:36", "remaining_time": "0:49:48", "throughput": 5772.82, "total_tokens": 5058248} {"current_steps": 7695, "total_steps": 33920, "loss": 0.35, "lr": 9.51796456864764e-06, "epoch": 4.537146226415095, "percentage": 22.69, "elapsed_time": "0:14:36", "remaining_time": "0:49:47", "throughput": 5772.82, "total_tokens": 5061192} {"current_steps": 7700, "total_steps": 33920, "loss": 0.3693, "lr": 9.516861840055942e-06, "epoch": 4.540094339622642, "percentage": 22.7, "elapsed_time": "0:14:37", "remaining_time": "0:49:47", "throughput": 5773.11, "total_tokens": 5064392} {"current_steps": 7705, "total_steps": 33920, "loss": 0.4428, "lr": 9.515757915605604e-06, "epoch": 4.543042452830189, "percentage": 22.72, "elapsed_time": "0:14:37", "remaining_time": "0:49:46", "throughput": 5773.44, "total_tokens": 5067720} {"current_steps": 7710, "total_steps": 33920, "loss": 0.4683, "lr": 9.514652795588899e-06, "epoch": 4.5459905660377355, "percentage": 22.73, "elapsed_time": "0:14:38", "remaining_time": "0:49:45", "throughput": 5773.56, "total_tokens": 5070696} {"current_steps": 7715, "total_steps": 33920, "loss": 0.3422, "lr": 9.513546480298405e-06, "epoch": 4.548938679245283, "percentage": 22.74, "elapsed_time": "0:14:38", "remaining_time": "0:49:45", "throughput": 5774.24, "total_tokens": 5074888} {"current_steps": 7720, "total_steps": 33920, "loss": 0.5659, "lr": 9.512438970027032e-06, "epoch": 4.55188679245283, "percentage": 22.76, "elapsed_time": "0:14:39", "remaining_time": "0:49:44", "throughput": 5774.02, "total_tokens": 5077800} {"current_steps": 7725, "total_steps": 33920, "loss": 0.4758, "lr": 9.511330265067992e-06, "epoch": 4.554834905660377, "percentage": 22.77, "elapsed_time": "0:14:39", "remaining_time": "0:49:43", "throughput": 5774.63, "total_tokens": 5081608} {"current_steps": 7730, "total_steps": 33920, "loss": 0.617, "lr": 9.510220365714822e-06, "epoch": 4.557783018867925, "percentage": 22.79, "elapsed_time": "0:14:40", "remaining_time": "0:49:44", "throughput": 5774.98, "total_tokens": 5086312} {"current_steps": 7735, "total_steps": 33920, "loss": 0.5285, "lr": 9.509109272261373e-06, "epoch": 4.560731132075472, "percentage": 22.8, "elapsed_time": "0:14:41", "remaining_time": "0:49:43", "throughput": 5775.32, "total_tokens": 5090024} {"current_steps": 7740, "total_steps": 33920, "loss": 0.4554, "lr": 9.50799698500181e-06, "epoch": 4.563679245283019, "percentage": 22.82, "elapsed_time": "0:14:41", "remaining_time": "0:49:42", "throughput": 5775.31, "total_tokens": 5093288} {"current_steps": 7745, "total_steps": 33920, "loss": 0.5056, "lr": 9.506883504230618e-06, "epoch": 4.566627358490566, "percentage": 22.83, "elapsed_time": "0:14:42", "remaining_time": "0:49:42", "throughput": 5775.57, "total_tokens": 5096744} {"current_steps": 7750, "total_steps": 33920, "loss": 0.4201, "lr": 9.505768830242593e-06, "epoch": 4.569575471698113, "percentage": 22.85, "elapsed_time": "0:14:42", "remaining_time": "0:49:41", "throughput": 5775.79, "total_tokens": 5100008} {"current_steps": 7755, "total_steps": 33920, "loss": 0.5464, "lr": 9.504652963332852e-06, "epoch": 4.57252358490566, "percentage": 22.86, "elapsed_time": "0:14:43", "remaining_time": "0:49:41", "throughput": 5776.09, "total_tokens": 5103592} {"current_steps": 7760, "total_steps": 33920, "loss": 0.4714, "lr": 9.503535903796825e-06, "epoch": 4.5754716981132075, "percentage": 22.88, "elapsed_time": "0:14:44", "remaining_time": "0:49:40", "throughput": 5775.58, "total_tokens": 5105832} {"current_steps": 7765, "total_steps": 33920, "loss": 0.3874, "lr": 9.50241765193026e-06, "epoch": 4.578419811320755, "percentage": 22.89, "elapsed_time": "0:14:44", "remaining_time": "0:49:40", "throughput": 5776.15, "total_tokens": 5110280} {"current_steps": 7770, "total_steps": 33920, "loss": 0.6047, "lr": 9.501298208029214e-06, "epoch": 4.581367924528302, "percentage": 22.91, "elapsed_time": "0:14:45", "remaining_time": "0:49:39", "throughput": 5776.33, "total_tokens": 5113224} {"current_steps": 7775, "total_steps": 33920, "loss": 0.585, "lr": 9.500177572390071e-06, "epoch": 4.584316037735849, "percentage": 22.92, "elapsed_time": "0:14:45", "remaining_time": "0:49:38", "throughput": 5776.54, "total_tokens": 5116456} {"current_steps": 7780, "total_steps": 33920, "loss": 0.5695, "lr": 9.49905574530952e-06, "epoch": 4.587264150943396, "percentage": 22.94, "elapsed_time": "0:14:46", "remaining_time": "0:49:38", "throughput": 5777.16, "total_tokens": 5120776} {"current_steps": 7785, "total_steps": 33920, "loss": 0.5144, "lr": 9.497932727084571e-06, "epoch": 4.590212264150943, "percentage": 22.95, "elapsed_time": "0:14:46", "remaining_time": "0:49:37", "throughput": 5777.7, "total_tokens": 5124360} {"current_steps": 7790, "total_steps": 33920, "loss": 0.4494, "lr": 9.496808518012545e-06, "epoch": 4.59316037735849, "percentage": 22.97, "elapsed_time": "0:14:47", "remaining_time": "0:49:36", "throughput": 5778.13, "total_tokens": 5127816} {"current_steps": 7795, "total_steps": 33920, "loss": 0.538, "lr": 9.495683118391087e-06, "epoch": 4.596108490566038, "percentage": 22.98, "elapsed_time": "0:14:47", "remaining_time": "0:49:35", "throughput": 5778.3, "total_tokens": 5130856} {"current_steps": 7800, "total_steps": 33920, "loss": 0.4488, "lr": 9.494556528518146e-06, "epoch": 4.599056603773585, "percentage": 23.0, "elapsed_time": "0:14:48", "remaining_time": "0:49:35", "throughput": 5778.4, "total_tokens": 5133768} {"current_steps": 7805, "total_steps": 33920, "loss": 0.5698, "lr": 9.493428748691995e-06, "epoch": 4.602004716981132, "percentage": 23.01, "elapsed_time": "0:14:49", "remaining_time": "0:49:36", "throughput": 5779.4, "total_tokens": 5140584} {"current_steps": 7810, "total_steps": 33920, "loss": 0.307, "lr": 9.492299779211215e-06, "epoch": 4.6049528301886795, "percentage": 23.02, "elapsed_time": "0:14:50", "remaining_time": "0:49:35", "throughput": 5780.02, "total_tokens": 5144616} {"current_steps": 7815, "total_steps": 33920, "loss": 0.45, "lr": 9.49116962037471e-06, "epoch": 4.607900943396227, "percentage": 23.04, "elapsed_time": "0:14:50", "remaining_time": "0:49:35", "throughput": 5780.42, "total_tokens": 5148392} {"current_steps": 7820, "total_steps": 33920, "loss": 0.4428, "lr": 9.490038272481691e-06, "epoch": 4.610849056603773, "percentage": 23.05, "elapsed_time": "0:14:51", "remaining_time": "0:49:34", "throughput": 5780.18, "total_tokens": 5150952} {"current_steps": 7825, "total_steps": 33920, "loss": 0.4114, "lr": 9.488905735831689e-06, "epoch": 4.6137971698113205, "percentage": 23.07, "elapsed_time": "0:14:51", "remaining_time": "0:49:33", "throughput": 5780.38, "total_tokens": 5153928} {"current_steps": 7830, "total_steps": 33920, "loss": 0.4272, "lr": 9.487772010724548e-06, "epoch": 4.616745283018868, "percentage": 23.08, "elapsed_time": "0:14:52", "remaining_time": "0:49:32", "throughput": 5780.62, "total_tokens": 5157192} {"current_steps": 7835, "total_steps": 33920, "loss": 0.428, "lr": 9.486637097460425e-06, "epoch": 4.619693396226415, "percentage": 23.1, "elapsed_time": "0:14:52", "remaining_time": "0:49:31", "throughput": 5780.47, "total_tokens": 5159720} {"current_steps": 7840, "total_steps": 33920, "loss": 0.4263, "lr": 9.485500996339793e-06, "epoch": 4.622641509433962, "percentage": 23.11, "elapsed_time": "0:14:53", "remaining_time": "0:49:31", "throughput": 5780.75, "total_tokens": 5163272} {"current_steps": 7845, "total_steps": 33920, "loss": 0.4253, "lr": 9.484363707663443e-06, "epoch": 4.62558962264151, "percentage": 23.13, "elapsed_time": "0:14:53", "remaining_time": "0:49:30", "throughput": 5781.17, "total_tokens": 5166568} {"current_steps": 7850, "total_steps": 33920, "loss": 0.3894, "lr": 9.483225231732474e-06, "epoch": 4.628537735849057, "percentage": 23.14, "elapsed_time": "0:14:54", "remaining_time": "0:49:30", "throughput": 5781.98, "total_tokens": 5172104} {"current_steps": 7855, "total_steps": 33920, "loss": 0.4598, "lr": 9.482085568848302e-06, "epoch": 4.631485849056604, "percentage": 23.16, "elapsed_time": "0:14:54", "remaining_time": "0:49:29", "throughput": 5781.63, "total_tokens": 5174376} {"current_steps": 7860, "total_steps": 33920, "loss": 0.6963, "lr": 9.480944719312659e-06, "epoch": 4.634433962264151, "percentage": 23.17, "elapsed_time": "0:14:55", "remaining_time": "0:49:28", "throughput": 5781.9, "total_tokens": 5177544} {"current_steps": 7865, "total_steps": 33920, "loss": 0.4846, "lr": 9.47980268342759e-06, "epoch": 4.637382075471698, "percentage": 23.19, "elapsed_time": "0:14:56", "remaining_time": "0:49:28", "throughput": 5781.99, "total_tokens": 5180680} {"current_steps": 7870, "total_steps": 33920, "loss": 0.3767, "lr": 9.478659461495456e-06, "epoch": 4.640330188679245, "percentage": 23.2, "elapsed_time": "0:14:56", "remaining_time": "0:49:27", "throughput": 5781.91, "total_tokens": 5183336} {"current_steps": 7875, "total_steps": 33920, "loss": 0.464, "lr": 9.477515053818926e-06, "epoch": 4.6432783018867925, "percentage": 23.22, "elapsed_time": "0:14:56", "remaining_time": "0:49:26", "throughput": 5782.16, "total_tokens": 5186568} {"current_steps": 7880, "total_steps": 33920, "loss": 0.5222, "lr": 9.476369460700988e-06, "epoch": 4.64622641509434, "percentage": 23.23, "elapsed_time": "0:14:57", "remaining_time": "0:49:25", "throughput": 5782.46, "total_tokens": 5189576} {"current_steps": 7885, "total_steps": 33920, "loss": 0.5426, "lr": 9.475222682444944e-06, "epoch": 4.649174528301887, "percentage": 23.25, "elapsed_time": "0:14:57", "remaining_time": "0:49:24", "throughput": 5782.34, "total_tokens": 5192360} {"current_steps": 7890, "total_steps": 33920, "loss": 0.4254, "lr": 9.474074719354406e-06, "epoch": 4.652122641509434, "percentage": 23.26, "elapsed_time": "0:14:58", "remaining_time": "0:49:24", "throughput": 5782.28, "total_tokens": 5195048} {"current_steps": 7895, "total_steps": 33920, "loss": 0.4954, "lr": 9.472925571733306e-06, "epoch": 4.655070754716981, "percentage": 23.28, "elapsed_time": "0:14:59", "remaining_time": "0:49:23", "throughput": 5782.51, "total_tokens": 5198568} {"current_steps": 7900, "total_steps": 33920, "loss": 0.492, "lr": 9.471775239885883e-06, "epoch": 4.658018867924528, "percentage": 23.29, "elapsed_time": "0:14:59", "remaining_time": "0:49:23", "throughput": 5783.25, "total_tokens": 5203112} {"current_steps": 7905, "total_steps": 33920, "loss": 0.4329, "lr": 9.470623724116693e-06, "epoch": 4.660966981132075, "percentage": 23.3, "elapsed_time": "0:15:00", "remaining_time": "0:49:22", "throughput": 5783.67, "total_tokens": 5206920} {"current_steps": 7910, "total_steps": 33920, "loss": 0.437, "lr": 9.469471024730606e-06, "epoch": 4.663915094339623, "percentage": 23.32, "elapsed_time": "0:15:00", "remaining_time": "0:49:22", "throughput": 5783.71, "total_tokens": 5210056} {"current_steps": 7915, "total_steps": 33920, "loss": 0.5536, "lr": 9.4683171420328e-06, "epoch": 4.66686320754717, "percentage": 23.33, "elapsed_time": "0:15:01", "remaining_time": "0:49:21", "throughput": 5783.99, "total_tokens": 5213256} {"current_steps": 7920, "total_steps": 33920, "loss": 0.393, "lr": 9.467162076328776e-06, "epoch": 4.669811320754717, "percentage": 23.35, "elapsed_time": "0:15:01", "remaining_time": "0:49:20", "throughput": 5784.08, "total_tokens": 5216168} {"current_steps": 7925, "total_steps": 33920, "loss": 0.4699, "lr": 9.466005827924337e-06, "epoch": 4.6727594339622645, "percentage": 23.36, "elapsed_time": "0:15:02", "remaining_time": "0:49:19", "throughput": 5784.25, "total_tokens": 5219368} {"current_steps": 7930, "total_steps": 33920, "loss": 0.3703, "lr": 9.46484839712561e-06, "epoch": 4.675707547169811, "percentage": 23.38, "elapsed_time": "0:15:02", "remaining_time": "0:49:18", "throughput": 5784.41, "total_tokens": 5222344} {"current_steps": 7935, "total_steps": 33920, "loss": 0.5319, "lr": 9.463689784239026e-06, "epoch": 4.678655660377358, "percentage": 23.39, "elapsed_time": "0:15:03", "remaining_time": "0:49:18", "throughput": 5784.7, "total_tokens": 5225576} {"current_steps": 7940, "total_steps": 33920, "loss": 0.3136, "lr": 9.462529989571334e-06, "epoch": 4.681603773584905, "percentage": 23.41, "elapsed_time": "0:15:03", "remaining_time": "0:49:17", "throughput": 5784.26, "total_tokens": 5227816} {"current_steps": 7945, "total_steps": 33920, "loss": 0.4923, "lr": 9.461369013429595e-06, "epoch": 4.684551886792453, "percentage": 23.42, "elapsed_time": "0:15:04", "remaining_time": "0:49:16", "throughput": 5784.3, "total_tokens": 5230888} {"current_steps": 7950, "total_steps": 33920, "loss": 0.4404, "lr": 9.460206856121183e-06, "epoch": 4.6875, "percentage": 23.44, "elapsed_time": "0:15:04", "remaining_time": "0:49:15", "throughput": 5784.72, "total_tokens": 5234280} {"current_steps": 7955, "total_steps": 33920, "loss": 0.4538, "lr": 9.459043517953786e-06, "epoch": 4.690448113207547, "percentage": 23.45, "elapsed_time": "0:15:05", "remaining_time": "0:49:15", "throughput": 5784.86, "total_tokens": 5237768} {"current_steps": 7960, "total_steps": 33920, "loss": 0.5962, "lr": 9.457878999235396e-06, "epoch": 4.693396226415095, "percentage": 23.47, "elapsed_time": "0:15:05", "remaining_time": "0:49:14", "throughput": 5785.01, "total_tokens": 5240648} {"current_steps": 7965, "total_steps": 33920, "loss": 0.417, "lr": 9.45671330027433e-06, "epoch": 4.696344339622642, "percentage": 23.48, "elapsed_time": "0:15:06", "remaining_time": "0:49:13", "throughput": 5785.1, "total_tokens": 5243496} {"current_steps": 7970, "total_steps": 33920, "loss": 0.5585, "lr": 9.45554642137921e-06, "epoch": 4.699292452830189, "percentage": 23.5, "elapsed_time": "0:15:06", "remaining_time": "0:49:12", "throughput": 5784.66, "total_tokens": 5245832} {"current_steps": 7975, "total_steps": 33920, "loss": 0.4596, "lr": 9.454378362858974e-06, "epoch": 4.7022405660377355, "percentage": 23.51, "elapsed_time": "0:15:07", "remaining_time": "0:49:12", "throughput": 5785.16, "total_tokens": 5249608} {"current_steps": 7980, "total_steps": 33920, "loss": 0.4544, "lr": 9.453209125022867e-06, "epoch": 4.705188679245283, "percentage": 23.53, "elapsed_time": "0:15:07", "remaining_time": "0:49:11", "throughput": 5785.41, "total_tokens": 5252840} {"current_steps": 7985, "total_steps": 33920, "loss": 0.5127, "lr": 9.452038708180453e-06, "epoch": 4.70813679245283, "percentage": 23.54, "elapsed_time": "0:15:08", "remaining_time": "0:49:10", "throughput": 5785.65, "total_tokens": 5256584} {"current_steps": 7990, "total_steps": 33920, "loss": 0.5534, "lr": 9.450867112641603e-06, "epoch": 4.711084905660377, "percentage": 23.56, "elapsed_time": "0:15:09", "remaining_time": "0:49:10", "throughput": 5785.83, "total_tokens": 5259816} {"current_steps": 7995, "total_steps": 33920, "loss": 0.4088, "lr": 9.449694338716506e-06, "epoch": 4.714033018867925, "percentage": 23.57, "elapsed_time": "0:15:09", "remaining_time": "0:49:09", "throughput": 5786.28, "total_tokens": 5263496} {"current_steps": 8000, "total_steps": 33920, "loss": 0.4728, "lr": 9.448520386715653e-06, "epoch": 4.716981132075472, "percentage": 23.58, "elapsed_time": "0:15:10", "remaining_time": "0:49:08", "throughput": 5786.24, "total_tokens": 5266184} {"current_steps": 8005, "total_steps": 33920, "loss": 0.4128, "lr": 9.447345256949855e-06, "epoch": 4.719929245283019, "percentage": 23.6, "elapsed_time": "0:15:10", "remaining_time": "0:49:07", "throughput": 5785.94, "total_tokens": 5268584} {"current_steps": 8010, "total_steps": 33920, "loss": 0.4171, "lr": 9.446168949730234e-06, "epoch": 4.722877358490566, "percentage": 23.61, "elapsed_time": "0:15:11", "remaining_time": "0:49:07", "throughput": 5786.32, "total_tokens": 5271912} {"current_steps": 8015, "total_steps": 33920, "loss": 0.6409, "lr": 9.444991465368223e-06, "epoch": 4.725825471698113, "percentage": 23.63, "elapsed_time": "0:15:11", "remaining_time": "0:49:06", "throughput": 5786.37, "total_tokens": 5274760} {"current_steps": 8020, "total_steps": 33920, "loss": 0.3694, "lr": 9.443812804175562e-06, "epoch": 4.72877358490566, "percentage": 23.64, "elapsed_time": "0:15:12", "remaining_time": "0:49:05", "throughput": 5786.7, "total_tokens": 5278376} {"current_steps": 8025, "total_steps": 33920, "loss": 0.3494, "lr": 9.44263296646431e-06, "epoch": 4.7317216981132075, "percentage": 23.66, "elapsed_time": "0:15:12", "remaining_time": "0:49:05", "throughput": 5786.63, "total_tokens": 5281320} {"current_steps": 8030, "total_steps": 33920, "loss": 0.563, "lr": 9.441451952546835e-06, "epoch": 4.734669811320755, "percentage": 23.67, "elapsed_time": "0:15:13", "remaining_time": "0:49:04", "throughput": 5786.89, "total_tokens": 5284808} {"current_steps": 8035, "total_steps": 33920, "loss": 0.5945, "lr": 9.440269762735814e-06, "epoch": 4.737617924528302, "percentage": 23.69, "elapsed_time": "0:15:13", "remaining_time": "0:49:03", "throughput": 5786.43, "total_tokens": 5287496} {"current_steps": 8040, "total_steps": 33920, "loss": 0.5003, "lr": 9.439086397344236e-06, "epoch": 4.740566037735849, "percentage": 23.7, "elapsed_time": "0:15:14", "remaining_time": "0:49:02", "throughput": 5786.55, "total_tokens": 5290472} {"current_steps": 8045, "total_steps": 33920, "loss": 0.5254, "lr": 9.437901856685404e-06, "epoch": 4.743514150943396, "percentage": 23.72, "elapsed_time": "0:15:14", "remaining_time": "0:49:02", "throughput": 5786.9, "total_tokens": 5293800} {"current_steps": 8050, "total_steps": 33920, "loss": 0.544, "lr": 9.436716141072925e-06, "epoch": 4.746462264150943, "percentage": 23.73, "elapsed_time": "0:15:15", "remaining_time": "0:49:01", "throughput": 5786.87, "total_tokens": 5296520} {"current_steps": 8055, "total_steps": 33920, "loss": 0.4185, "lr": 9.435529250820732e-06, "epoch": 4.74941037735849, "percentage": 23.75, "elapsed_time": "0:15:15", "remaining_time": "0:49:00", "throughput": 5786.94, "total_tokens": 5299496} {"current_steps": 8060, "total_steps": 33920, "loss": 0.5485, "lr": 9.43434118624305e-06, "epoch": 4.752358490566038, "percentage": 23.76, "elapsed_time": "0:15:16", "remaining_time": "0:49:00", "throughput": 5787.44, "total_tokens": 5303432} {"current_steps": 8065, "total_steps": 33920, "loss": 0.5121, "lr": 9.433151947654428e-06, "epoch": 4.755306603773585, "percentage": 23.78, "elapsed_time": "0:15:16", "remaining_time": "0:48:59", "throughput": 5788.2, "total_tokens": 5307720} {"current_steps": 8070, "total_steps": 33920, "loss": 0.4827, "lr": 9.431961535369724e-06, "epoch": 4.758254716981132, "percentage": 23.79, "elapsed_time": "0:15:17", "remaining_time": "0:48:59", "throughput": 5788.48, "total_tokens": 5311272} {"current_steps": 8075, "total_steps": 33920, "loss": 0.377, "lr": 9.430769949704103e-06, "epoch": 4.7612028301886795, "percentage": 23.81, "elapsed_time": "0:15:18", "remaining_time": "0:48:58", "throughput": 5788.78, "total_tokens": 5314568} {"current_steps": 8080, "total_steps": 33920, "loss": 0.5035, "lr": 9.42957719097304e-06, "epoch": 4.764150943396227, "percentage": 23.82, "elapsed_time": "0:15:18", "remaining_time": "0:48:57", "throughput": 5788.84, "total_tokens": 5317864} {"current_steps": 8085, "total_steps": 33920, "loss": 0.3304, "lr": 9.42838325949233e-06, "epoch": 4.767099056603773, "percentage": 23.84, "elapsed_time": "0:15:19", "remaining_time": "0:48:57", "throughput": 5788.85, "total_tokens": 5321096} {"current_steps": 8090, "total_steps": 33920, "loss": 0.4516, "lr": 9.427188155578062e-06, "epoch": 4.7700471698113205, "percentage": 23.85, "elapsed_time": "0:15:19", "remaining_time": "0:48:56", "throughput": 5789.17, "total_tokens": 5325000} {"current_steps": 8095, "total_steps": 33920, "loss": 0.4767, "lr": 9.42599187954665e-06, "epoch": 4.772995283018868, "percentage": 23.86, "elapsed_time": "0:15:20", "remaining_time": "0:48:56", "throughput": 5789.1, "total_tokens": 5327752} {"current_steps": 8100, "total_steps": 33920, "loss": 0.6225, "lr": 9.424794431714814e-06, "epoch": 4.775943396226415, "percentage": 23.88, "elapsed_time": "0:15:20", "remaining_time": "0:48:55", "throughput": 5789.35, "total_tokens": 5331112} {"current_steps": 8105, "total_steps": 33920, "loss": 0.4328, "lr": 9.423595812399581e-06, "epoch": 4.778891509433962, "percentage": 23.89, "elapsed_time": "0:15:21", "remaining_time": "0:48:54", "throughput": 5790.01, "total_tokens": 5335336} {"current_steps": 8110, "total_steps": 33920, "loss": 0.575, "lr": 9.422396021918296e-06, "epoch": 4.78183962264151, "percentage": 23.91, "elapsed_time": "0:15:22", "remaining_time": "0:48:54", "throughput": 5790.56, "total_tokens": 5339240} {"current_steps": 8115, "total_steps": 33920, "loss": 0.3858, "lr": 9.421195060588602e-06, "epoch": 4.784787735849057, "percentage": 23.92, "elapsed_time": "0:15:22", "remaining_time": "0:48:54", "throughput": 5790.99, "total_tokens": 5343560} {"current_steps": 8120, "total_steps": 33920, "loss": 0.5195, "lr": 9.419992928728461e-06, "epoch": 4.787735849056604, "percentage": 23.94, "elapsed_time": "0:15:23", "remaining_time": "0:48:53", "throughput": 5790.92, "total_tokens": 5346920} {"current_steps": 8125, "total_steps": 33920, "loss": 0.4021, "lr": 9.418789626656144e-06, "epoch": 4.790683962264151, "percentage": 23.95, "elapsed_time": "0:15:23", "remaining_time": "0:48:53", "throughput": 5791.32, "total_tokens": 5350600} {"current_steps": 8130, "total_steps": 33920, "loss": 0.4669, "lr": 9.417585154690229e-06, "epoch": 4.793632075471698, "percentage": 23.97, "elapsed_time": "0:15:24", "remaining_time": "0:48:52", "throughput": 5791.34, "total_tokens": 5353576} {"current_steps": 8135, "total_steps": 33920, "loss": 0.4523, "lr": 9.416379513149605e-06, "epoch": 4.796580188679245, "percentage": 23.98, "elapsed_time": "0:15:25", "remaining_time": "0:48:51", "throughput": 5791.29, "total_tokens": 5356968} {"current_steps": 8140, "total_steps": 33920, "loss": 0.5766, "lr": 9.415172702353471e-06, "epoch": 4.7995283018867925, "percentage": 24.0, "elapsed_time": "0:15:25", "remaining_time": "0:48:51", "throughput": 5791.7, "total_tokens": 5360744} {"current_steps": 8145, "total_steps": 33920, "loss": 0.4836, "lr": 9.413964722621339e-06, "epoch": 4.80247641509434, "percentage": 24.01, "elapsed_time": "0:15:26", "remaining_time": "0:48:50", "throughput": 5792.46, "total_tokens": 5364968} {"current_steps": 8150, "total_steps": 33920, "loss": 0.4551, "lr": 9.41275557427302e-06, "epoch": 4.805424528301887, "percentage": 24.03, "elapsed_time": "0:15:26", "remaining_time": "0:48:50", "throughput": 5792.33, "total_tokens": 5367688} {"current_steps": 8155, "total_steps": 33920, "loss": 0.3686, "lr": 9.411545257628646e-06, "epoch": 4.808372641509434, "percentage": 24.04, "elapsed_time": "0:15:27", "remaining_time": "0:48:49", "throughput": 5792.02, "total_tokens": 5370152} {"current_steps": 8160, "total_steps": 33920, "loss": 0.5504, "lr": 9.410333773008653e-06, "epoch": 4.811320754716981, "percentage": 24.06, "elapsed_time": "0:15:27", "remaining_time": "0:48:48", "throughput": 5792.57, "total_tokens": 5374056} {"current_steps": 8165, "total_steps": 33920, "loss": 0.4036, "lr": 9.409121120733784e-06, "epoch": 4.814268867924528, "percentage": 24.07, "elapsed_time": "0:15:28", "remaining_time": "0:48:49", "throughput": 5793.9, "total_tokens": 5380904} {"current_steps": 8170, "total_steps": 33920, "loss": 0.3967, "lr": 9.4079073011251e-06, "epoch": 4.817216981132075, "percentage": 24.09, "elapsed_time": "0:15:29", "remaining_time": "0:48:48", "throughput": 5793.14, "total_tokens": 5383144} {"current_steps": 8175, "total_steps": 33920, "loss": 0.486, "lr": 9.406692314503956e-06, "epoch": 4.820165094339623, "percentage": 24.1, "elapsed_time": "0:15:29", "remaining_time": "0:48:48", "throughput": 5793.89, "total_tokens": 5388008} {"current_steps": 8180, "total_steps": 33920, "loss": 0.4633, "lr": 9.405476161192033e-06, "epoch": 4.82311320754717, "percentage": 24.12, "elapsed_time": "0:15:30", "remaining_time": "0:48:47", "throughput": 5793.59, "total_tokens": 5390408} {"current_steps": 8185, "total_steps": 33920, "loss": 0.4813, "lr": 9.40425884151131e-06, "epoch": 4.826061320754717, "percentage": 24.13, "elapsed_time": "0:15:30", "remaining_time": "0:48:46", "throughput": 5793.93, "total_tokens": 5393736} {"current_steps": 8190, "total_steps": 33920, "loss": 0.5507, "lr": 9.403040355784076e-06, "epoch": 4.8290094339622645, "percentage": 24.15, "elapsed_time": "0:15:31", "remaining_time": "0:48:46", "throughput": 5794.23, "total_tokens": 5397128} {"current_steps": 8195, "total_steps": 33920, "loss": 0.4842, "lr": 9.401820704332932e-06, "epoch": 4.831957547169811, "percentage": 24.16, "elapsed_time": "0:15:31", "remaining_time": "0:48:45", "throughput": 5794.55, "total_tokens": 5400456} {"current_steps": 8200, "total_steps": 33920, "loss": 0.4822, "lr": 9.400599887480786e-06, "epoch": 4.834905660377358, "percentage": 24.17, "elapsed_time": "0:15:32", "remaining_time": "0:48:44", "throughput": 5794.59, "total_tokens": 5403272} {"current_steps": 8205, "total_steps": 33920, "loss": 0.5228, "lr": 9.399377905550854e-06, "epoch": 4.837853773584905, "percentage": 24.19, "elapsed_time": "0:15:33", "remaining_time": "0:48:44", "throughput": 5795.04, "total_tokens": 5406952} {"current_steps": 8210, "total_steps": 33920, "loss": 0.4535, "lr": 9.398154758866662e-06, "epoch": 4.840801886792453, "percentage": 24.2, "elapsed_time": "0:15:33", "remaining_time": "0:48:43", "throughput": 5795.6, "total_tokens": 5411272} {"current_steps": 8215, "total_steps": 33920, "loss": 0.3678, "lr": 9.396930447752041e-06, "epoch": 4.84375, "percentage": 24.22, "elapsed_time": "0:15:34", "remaining_time": "0:48:43", "throughput": 5796.05, "total_tokens": 5414760} {"current_steps": 8220, "total_steps": 33920, "loss": 0.4502, "lr": 9.395704972531137e-06, "epoch": 4.846698113207547, "percentage": 24.23, "elapsed_time": "0:15:34", "remaining_time": "0:48:42", "throughput": 5796.38, "total_tokens": 5418248} {"current_steps": 8225, "total_steps": 33920, "loss": 0.4865, "lr": 9.394478333528396e-06, "epoch": 4.849646226415095, "percentage": 24.25, "elapsed_time": "0:15:35", "remaining_time": "0:48:41", "throughput": 5796.34, "total_tokens": 5421096} {"current_steps": 8230, "total_steps": 33920, "loss": 0.5134, "lr": 9.393250531068576e-06, "epoch": 4.852594339622642, "percentage": 24.26, "elapsed_time": "0:15:35", "remaining_time": "0:48:41", "throughput": 5796.65, "total_tokens": 5424648} {"current_steps": 8235, "total_steps": 33920, "loss": 0.3596, "lr": 9.392021565476744e-06, "epoch": 4.855542452830189, "percentage": 24.28, "elapsed_time": "0:15:36", "remaining_time": "0:48:40", "throughput": 5797.23, "total_tokens": 5428904} {"current_steps": 8240, "total_steps": 33920, "loss": 0.4312, "lr": 9.390791437078274e-06, "epoch": 4.8584905660377355, "percentage": 24.29, "elapsed_time": "0:15:36", "remaining_time": "0:48:40", "throughput": 5797.24, "total_tokens": 5431720} {"current_steps": 8245, "total_steps": 33920, "loss": 0.4761, "lr": 9.38956014619885e-06, "epoch": 4.861438679245283, "percentage": 24.31, "elapsed_time": "0:15:37", "remaining_time": "0:48:39", "throughput": 5797.27, "total_tokens": 5434728} {"current_steps": 8250, "total_steps": 33920, "loss": 0.4107, "lr": 9.388327693164456e-06, "epoch": 4.86438679245283, "percentage": 24.32, "elapsed_time": "0:15:37", "remaining_time": "0:48:38", "throughput": 5797.03, "total_tokens": 5437288} {"current_steps": 8255, "total_steps": 33920, "loss": 0.5555, "lr": 9.387094078301395e-06, "epoch": 4.867334905660377, "percentage": 24.34, "elapsed_time": "0:15:38", "remaining_time": "0:48:37", "throughput": 5797.11, "total_tokens": 5440392} {"current_steps": 8260, "total_steps": 33920, "loss": 0.5199, "lr": 9.385859301936269e-06, "epoch": 4.870283018867925, "percentage": 24.35, "elapsed_time": "0:15:39", "remaining_time": "0:48:37", "throughput": 5797.74, "total_tokens": 5444392} {"current_steps": 8265, "total_steps": 33920, "loss": 0.3905, "lr": 9.38462336439599e-06, "epoch": 4.873231132075472, "percentage": 24.37, "elapsed_time": "0:15:39", "remaining_time": "0:48:36", "throughput": 5798.41, "total_tokens": 5448840} {"current_steps": 8270, "total_steps": 33920, "loss": 0.402, "lr": 9.383386266007779e-06, "epoch": 4.876179245283019, "percentage": 24.38, "elapsed_time": "0:15:40", "remaining_time": "0:48:36", "throughput": 5798.39, "total_tokens": 5452168} {"current_steps": 8275, "total_steps": 33920, "loss": 0.5605, "lr": 9.382148007099164e-06, "epoch": 4.879127358490566, "percentage": 24.4, "elapsed_time": "0:15:40", "remaining_time": "0:48:35", "throughput": 5798.9, "total_tokens": 5455784} {"current_steps": 8280, "total_steps": 33920, "loss": 0.5192, "lr": 9.380908587997977e-06, "epoch": 4.882075471698113, "percentage": 24.41, "elapsed_time": "0:15:41", "remaining_time": "0:48:35", "throughput": 5799.06, "total_tokens": 5459080} {"current_steps": 8285, "total_steps": 33920, "loss": 0.3765, "lr": 9.37966800903236e-06, "epoch": 4.88502358490566, "percentage": 24.43, "elapsed_time": "0:15:41", "remaining_time": "0:48:34", "throughput": 5799.6, "total_tokens": 5462920} {"current_steps": 8290, "total_steps": 33920, "loss": 0.5797, "lr": 9.378426270530762e-06, "epoch": 4.8879716981132075, "percentage": 24.44, "elapsed_time": "0:15:42", "remaining_time": "0:48:33", "throughput": 5799.15, "total_tokens": 5465064} {"current_steps": 8295, "total_steps": 33920, "loss": 0.3695, "lr": 9.37718337282194e-06, "epoch": 4.890919811320755, "percentage": 24.45, "elapsed_time": "0:15:42", "remaining_time": "0:48:32", "throughput": 5798.73, "total_tokens": 5467432} {"current_steps": 8300, "total_steps": 33920, "loss": 0.4766, "lr": 9.375939316234956e-06, "epoch": 4.893867924528302, "percentage": 24.47, "elapsed_time": "0:15:43", "remaining_time": "0:48:32", "throughput": 5799.3, "total_tokens": 5471624} {"current_steps": 8305, "total_steps": 33920, "loss": 0.4213, "lr": 9.374694101099178e-06, "epoch": 4.896816037735849, "percentage": 24.48, "elapsed_time": "0:15:44", "remaining_time": "0:48:31", "throughput": 5799.76, "total_tokens": 5475144} {"current_steps": 8310, "total_steps": 33920, "loss": 0.5072, "lr": 9.373447727744282e-06, "epoch": 4.899764150943396, "percentage": 24.5, "elapsed_time": "0:15:44", "remaining_time": "0:48:31", "throughput": 5799.95, "total_tokens": 5478600} {"current_steps": 8315, "total_steps": 33920, "loss": 0.5028, "lr": 9.372200196500253e-06, "epoch": 4.902712264150943, "percentage": 24.51, "elapsed_time": "0:15:45", "remaining_time": "0:48:30", "throughput": 5800.52, "total_tokens": 5483112} {"current_steps": 8320, "total_steps": 33920, "loss": 0.4719, "lr": 9.37095150769738e-06, "epoch": 4.90566037735849, "percentage": 24.53, "elapsed_time": "0:15:45", "remaining_time": "0:48:30", "throughput": 5800.75, "total_tokens": 5486344} {"current_steps": 8325, "total_steps": 33920, "loss": 0.4273, "lr": 9.369701661666255e-06, "epoch": 4.908608490566038, "percentage": 24.54, "elapsed_time": "0:15:46", "remaining_time": "0:48:29", "throughput": 5800.82, "total_tokens": 5489288} {"current_steps": 8330, "total_steps": 33920, "loss": 0.4641, "lr": 9.368450658737782e-06, "epoch": 4.911556603773585, "percentage": 24.56, "elapsed_time": "0:15:46", "remaining_time": "0:48:28", "throughput": 5800.74, "total_tokens": 5492360} {"current_steps": 8335, "total_steps": 33920, "loss": 0.5682, "lr": 9.367198499243173e-06, "epoch": 4.914504716981132, "percentage": 24.57, "elapsed_time": "0:15:47", "remaining_time": "0:48:27", "throughput": 5800.65, "total_tokens": 5494952} {"current_steps": 8340, "total_steps": 33920, "loss": 0.4373, "lr": 9.365945183513938e-06, "epoch": 4.9174528301886795, "percentage": 24.59, "elapsed_time": "0:15:47", "remaining_time": "0:48:26", "throughput": 5800.67, "total_tokens": 5497736} {"current_steps": 8345, "total_steps": 33920, "loss": 0.3846, "lr": 9.3646907118819e-06, "epoch": 4.920400943396227, "percentage": 24.6, "elapsed_time": "0:15:48", "remaining_time": "0:48:26", "throughput": 5801.01, "total_tokens": 5501352} {"current_steps": 8350, "total_steps": 33920, "loss": 0.345, "lr": 9.363435084679185e-06, "epoch": 4.923349056603773, "percentage": 24.62, "elapsed_time": "0:15:48", "remaining_time": "0:48:25", "throughput": 5801.0, "total_tokens": 5504040} {"current_steps": 8355, "total_steps": 33920, "loss": 0.4816, "lr": 9.362178302238227e-06, "epoch": 4.9262971698113205, "percentage": 24.63, "elapsed_time": "0:15:49", "remaining_time": "0:48:24", "throughput": 5801.39, "total_tokens": 5507304} {"current_steps": 8360, "total_steps": 33920, "loss": 0.4617, "lr": 9.360920364891762e-06, "epoch": 4.929245283018868, "percentage": 24.65, "elapsed_time": "0:15:50", "remaining_time": "0:48:25", "throughput": 5802.15, "total_tokens": 5514216} {"current_steps": 8365, "total_steps": 33920, "loss": 0.4421, "lr": 9.359661272972836e-06, "epoch": 4.932193396226415, "percentage": 24.66, "elapsed_time": "0:15:50", "remaining_time": "0:48:25", "throughput": 5802.33, "total_tokens": 5517544} {"current_steps": 8370, "total_steps": 33920, "loss": 0.4665, "lr": 9.3584010268148e-06, "epoch": 4.935141509433962, "percentage": 24.68, "elapsed_time": "0:15:51", "remaining_time": "0:48:24", "throughput": 5802.42, "total_tokens": 5520584} {"current_steps": 8375, "total_steps": 33920, "loss": 0.4224, "lr": 9.357139626751308e-06, "epoch": 4.93808962264151, "percentage": 24.69, "elapsed_time": "0:15:51", "remaining_time": "0:48:23", "throughput": 5802.3, "total_tokens": 5523240} {"current_steps": 8380, "total_steps": 33920, "loss": 0.494, "lr": 9.355877073116321e-06, "epoch": 4.941037735849057, "percentage": 24.71, "elapsed_time": "0:15:52", "remaining_time": "0:48:22", "throughput": 5802.76, "total_tokens": 5526696} {"current_steps": 8385, "total_steps": 33920, "loss": 0.5885, "lr": 9.354613366244108e-06, "epoch": 4.943985849056604, "percentage": 24.72, "elapsed_time": "0:15:52", "remaining_time": "0:48:21", "throughput": 5802.61, "total_tokens": 5529320} {"current_steps": 8390, "total_steps": 33920, "loss": 0.3566, "lr": 9.353348506469236e-06, "epoch": 4.946933962264151, "percentage": 24.73, "elapsed_time": "0:15:53", "remaining_time": "0:48:21", "throughput": 5802.61, "total_tokens": 5532360} {"current_steps": 8395, "total_steps": 33920, "loss": 0.4047, "lr": 9.352082494126586e-06, "epoch": 4.949882075471698, "percentage": 24.75, "elapsed_time": "0:15:53", "remaining_time": "0:48:20", "throughput": 5802.85, "total_tokens": 5535752} {"current_steps": 8400, "total_steps": 33920, "loss": 0.4214, "lr": 9.350815329551341e-06, "epoch": 4.952830188679245, "percentage": 24.76, "elapsed_time": "0:15:54", "remaining_time": "0:48:19", "throughput": 5803.08, "total_tokens": 5539208} {"current_steps": 8405, "total_steps": 33920, "loss": 0.5202, "lr": 9.349547013078986e-06, "epoch": 4.9557783018867925, "percentage": 24.78, "elapsed_time": "0:15:55", "remaining_time": "0:48:19", "throughput": 5803.51, "total_tokens": 5543240} {"current_steps": 8410, "total_steps": 33920, "loss": 0.6079, "lr": 9.348277545045312e-06, "epoch": 4.95872641509434, "percentage": 24.79, "elapsed_time": "0:15:55", "remaining_time": "0:48:18", "throughput": 5803.35, "total_tokens": 5546120} {"current_steps": 8415, "total_steps": 33920, "loss": 0.5532, "lr": 9.347006925786418e-06, "epoch": 4.961674528301887, "percentage": 24.81, "elapsed_time": "0:15:56", "remaining_time": "0:48:18", "throughput": 5803.88, "total_tokens": 5549736} {"current_steps": 8420, "total_steps": 33920, "loss": 0.4977, "lr": 9.34573515563871e-06, "epoch": 4.964622641509434, "percentage": 24.82, "elapsed_time": "0:15:56", "remaining_time": "0:48:17", "throughput": 5804.16, "total_tokens": 5553224} {"current_steps": 8425, "total_steps": 33920, "loss": 0.3935, "lr": 9.344462234938885e-06, "epoch": 4.967570754716981, "percentage": 24.84, "elapsed_time": "0:15:57", "remaining_time": "0:48:16", "throughput": 5804.39, "total_tokens": 5556168} {"current_steps": 8430, "total_steps": 33920, "loss": 0.8096, "lr": 9.343188164023962e-06, "epoch": 4.970518867924528, "percentage": 24.85, "elapsed_time": "0:15:57", "remaining_time": "0:48:16", "throughput": 5804.82, "total_tokens": 5560072} {"current_steps": 8435, "total_steps": 33920, "loss": 0.5861, "lr": 9.341912943231256e-06, "epoch": 4.973466981132075, "percentage": 24.87, "elapsed_time": "0:15:58", "remaining_time": "0:48:15", "throughput": 5804.65, "total_tokens": 5562696} {"current_steps": 8440, "total_steps": 33920, "loss": 0.5444, "lr": 9.340636572898383e-06, "epoch": 4.976415094339623, "percentage": 24.88, "elapsed_time": "0:15:58", "remaining_time": "0:48:15", "throughput": 5805.28, "total_tokens": 5566984} {"current_steps": 8445, "total_steps": 33920, "loss": 0.4823, "lr": 9.339359053363272e-06, "epoch": 4.97936320754717, "percentage": 24.9, "elapsed_time": "0:15:59", "remaining_time": "0:48:14", "throughput": 5805.94, "total_tokens": 5571112} {"current_steps": 8450, "total_steps": 33920, "loss": 0.4066, "lr": 9.338080384964148e-06, "epoch": 4.982311320754717, "percentage": 24.91, "elapsed_time": "0:16:00", "remaining_time": "0:48:13", "throughput": 5806.08, "total_tokens": 5574024} {"current_steps": 8455, "total_steps": 33920, "loss": 0.4422, "lr": 9.336800568039548e-06, "epoch": 4.9852594339622645, "percentage": 24.93, "elapsed_time": "0:16:00", "remaining_time": "0:48:13", "throughput": 5806.79, "total_tokens": 5578600} {"current_steps": 8460, "total_steps": 33920, "loss": 0.4496, "lr": 9.335519602928307e-06, "epoch": 4.988207547169811, "percentage": 24.94, "elapsed_time": "0:16:01", "remaining_time": "0:48:12", "throughput": 5807.12, "total_tokens": 5581928} {"current_steps": 8465, "total_steps": 33920, "loss": 0.3551, "lr": 9.334237489969565e-06, "epoch": 4.991155660377358, "percentage": 24.96, "elapsed_time": "0:16:01", "remaining_time": "0:48:11", "throughput": 5807.19, "total_tokens": 5584776} {"current_steps": 8470, "total_steps": 33920, "loss": 0.5198, "lr": 9.332954229502768e-06, "epoch": 4.994103773584905, "percentage": 24.97, "elapsed_time": "0:16:02", "remaining_time": "0:48:11", "throughput": 5807.55, "total_tokens": 5588040} {"current_steps": 8475, "total_steps": 33920, "loss": 0.3815, "lr": 9.331669821867665e-06, "epoch": 4.997051886792453, "percentage": 24.99, "elapsed_time": "0:16:02", "remaining_time": "0:48:10", "throughput": 5807.64, "total_tokens": 5591208} {"current_steps": 8480, "total_steps": 33920, "loss": 0.458, "lr": 9.33038426740431e-06, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:16:03", "remaining_time": "0:48:10", "throughput": 5806.24, "total_tokens": 5593864} {"current_steps": 8485, "total_steps": 33920, "loss": 0.3867, "lr": 9.329097566453055e-06, "epoch": 5.002948113207547, "percentage": 25.01, "elapsed_time": "0:16:04", "remaining_time": "0:48:10", "throughput": 5805.3, "total_tokens": 5596936} {"current_steps": 8490, "total_steps": 33920, "loss": 0.476, "lr": 9.327809719354564e-06, "epoch": 5.005896226415095, "percentage": 25.03, "elapsed_time": "0:16:04", "remaining_time": "0:48:09", "throughput": 5805.34, "total_tokens": 5599752} {"current_steps": 8495, "total_steps": 33920, "loss": 0.4096, "lr": 9.326520726449795e-06, "epoch": 5.008844339622642, "percentage": 25.04, "elapsed_time": "0:16:05", "remaining_time": "0:48:08", "throughput": 5805.46, "total_tokens": 5602888} {"current_steps": 8500, "total_steps": 33920, "loss": 0.6877, "lr": 9.32523058808002e-06, "epoch": 5.011792452830188, "percentage": 25.06, "elapsed_time": "0:16:05", "remaining_time": "0:48:07", "throughput": 5805.85, "total_tokens": 5606408} {"current_steps": 8505, "total_steps": 33920, "loss": 0.4303, "lr": 9.323939304586806e-06, "epoch": 5.0147405660377355, "percentage": 25.07, "elapsed_time": "0:16:06", "remaining_time": "0:48:07", "throughput": 5806.02, "total_tokens": 5609416} {"current_steps": 8510, "total_steps": 33920, "loss": 0.3231, "lr": 9.322646876312025e-06, "epoch": 5.017688679245283, "percentage": 25.09, "elapsed_time": "0:16:06", "remaining_time": "0:48:06", "throughput": 5805.94, "total_tokens": 5612200} {"current_steps": 8515, "total_steps": 33920, "loss": 0.5221, "lr": 9.321353303597854e-06, "epoch": 5.02063679245283, "percentage": 25.1, "elapsed_time": "0:16:07", "remaining_time": "0:48:06", "throughput": 5806.95, "total_tokens": 5618024} {"current_steps": 8520, "total_steps": 33920, "loss": 0.4345, "lr": 9.320058586786771e-06, "epoch": 5.023584905660377, "percentage": 25.12, "elapsed_time": "0:16:07", "remaining_time": "0:48:05", "throughput": 5806.65, "total_tokens": 5620648} {"current_steps": 8525, "total_steps": 33920, "loss": 0.3552, "lr": 9.31876272622156e-06, "epoch": 5.026533018867925, "percentage": 25.13, "elapsed_time": "0:16:08", "remaining_time": "0:48:05", "throughput": 5806.69, "total_tokens": 5623784} {"current_steps": 8530, "total_steps": 33920, "loss": 0.5272, "lr": 9.317465722245305e-06, "epoch": 5.029481132075472, "percentage": 25.15, "elapsed_time": "0:16:08", "remaining_time": "0:48:04", "throughput": 5806.79, "total_tokens": 5626600} {"current_steps": 8535, "total_steps": 33920, "loss": 0.4404, "lr": 9.316167575201391e-06, "epoch": 5.032429245283019, "percentage": 25.16, "elapsed_time": "0:16:09", "remaining_time": "0:48:03", "throughput": 5807.2, "total_tokens": 5630312} {"current_steps": 8540, "total_steps": 33920, "loss": 0.4199, "lr": 9.31486828543351e-06, "epoch": 5.035377358490566, "percentage": 25.18, "elapsed_time": "0:16:10", "remaining_time": "0:48:02", "throughput": 5807.27, "total_tokens": 5633288} {"current_steps": 8545, "total_steps": 33920, "loss": 0.3826, "lr": 9.313567853285656e-06, "epoch": 5.038325471698113, "percentage": 25.19, "elapsed_time": "0:16:10", "remaining_time": "0:48:02", "throughput": 5807.65, "total_tokens": 5636616} {"current_steps": 8550, "total_steps": 33920, "loss": 0.3861, "lr": 9.31226627910212e-06, "epoch": 5.04127358490566, "percentage": 25.21, "elapsed_time": "0:16:11", "remaining_time": "0:48:01", "throughput": 5808.37, "total_tokens": 5641032} {"current_steps": 8555, "total_steps": 33920, "loss": 0.4716, "lr": 9.310963563227504e-06, "epoch": 5.0442216981132075, "percentage": 25.22, "elapsed_time": "0:16:11", "remaining_time": "0:48:00", "throughput": 5808.42, "total_tokens": 5643912} {"current_steps": 8560, "total_steps": 33920, "loss": 0.4181, "lr": 9.309659706006704e-06, "epoch": 5.047169811320755, "percentage": 25.24, "elapsed_time": "0:16:12", "remaining_time": "0:48:00", "throughput": 5809.01, "total_tokens": 5648008} {"current_steps": 8565, "total_steps": 33920, "loss": 0.3722, "lr": 9.308354707784925e-06, "epoch": 5.050117924528302, "percentage": 25.25, "elapsed_time": "0:16:12", "remaining_time": "0:48:00", "throughput": 5809.67, "total_tokens": 5652136} {"current_steps": 8570, "total_steps": 33920, "loss": 0.3766, "lr": 9.307048568907669e-06, "epoch": 5.053066037735849, "percentage": 25.27, "elapsed_time": "0:16:13", "remaining_time": "0:47:59", "throughput": 5810.29, "total_tokens": 5656264} {"current_steps": 8575, "total_steps": 33920, "loss": 0.4087, "lr": 9.30574128972074e-06, "epoch": 5.056014150943396, "percentage": 25.28, "elapsed_time": "0:16:13", "remaining_time": "0:47:58", "throughput": 5809.84, "total_tokens": 5658408} {"current_steps": 8580, "total_steps": 33920, "loss": 0.3831, "lr": 9.304432870570247e-06, "epoch": 5.058962264150943, "percentage": 25.29, "elapsed_time": "0:16:14", "remaining_time": "0:47:57", "throughput": 5810.13, "total_tokens": 5661672} {"current_steps": 8585, "total_steps": 33920, "loss": 0.4019, "lr": 9.303123311802605e-06, "epoch": 5.06191037735849, "percentage": 25.31, "elapsed_time": "0:16:14", "remaining_time": "0:47:57", "throughput": 5810.02, "total_tokens": 5664328} {"current_steps": 8590, "total_steps": 33920, "loss": 0.3171, "lr": 9.301812613764516e-06, "epoch": 5.064858490566038, "percentage": 25.32, "elapsed_time": "0:16:15", "remaining_time": "0:47:56", "throughput": 5810.42, "total_tokens": 5667816} {"current_steps": 8595, "total_steps": 33920, "loss": 0.4603, "lr": 9.300500776803001e-06, "epoch": 5.067806603773585, "percentage": 25.34, "elapsed_time": "0:16:16", "remaining_time": "0:47:55", "throughput": 5810.84, "total_tokens": 5671528} {"current_steps": 8600, "total_steps": 33920, "loss": 0.3857, "lr": 9.29918780126537e-06, "epoch": 5.070754716981132, "percentage": 25.35, "elapsed_time": "0:16:16", "remaining_time": "0:47:54", "throughput": 5810.83, "total_tokens": 5674248} {"current_steps": 8605, "total_steps": 33920, "loss": 0.4444, "lr": 9.297873687499239e-06, "epoch": 5.0737028301886795, "percentage": 25.37, "elapsed_time": "0:16:17", "remaining_time": "0:47:54", "throughput": 5811.52, "total_tokens": 5678760} {"current_steps": 8610, "total_steps": 33920, "loss": 0.5118, "lr": 9.296558435852528e-06, "epoch": 5.076650943396227, "percentage": 25.38, "elapsed_time": "0:16:17", "remaining_time": "0:47:53", "throughput": 5811.09, "total_tokens": 5681128} {"current_steps": 8615, "total_steps": 33920, "loss": 0.3769, "lr": 9.295242046673454e-06, "epoch": 5.079599056603773, "percentage": 25.4, "elapsed_time": "0:16:18", "remaining_time": "0:47:53", "throughput": 5811.21, "total_tokens": 5684008} {"current_steps": 8620, "total_steps": 33920, "loss": 0.6049, "lr": 9.293924520310535e-06, "epoch": 5.0825471698113205, "percentage": 25.41, "elapsed_time": "0:16:18", "remaining_time": "0:47:52", "throughput": 5810.87, "total_tokens": 5686344} {"current_steps": 8625, "total_steps": 33920, "loss": 0.4212, "lr": 9.292605857112595e-06, "epoch": 5.085495283018868, "percentage": 25.43, "elapsed_time": "0:16:19", "remaining_time": "0:47:51", "throughput": 5811.01, "total_tokens": 5689384} {"current_steps": 8630, "total_steps": 33920, "loss": 0.4699, "lr": 9.291286057428755e-06, "epoch": 5.088443396226415, "percentage": 25.44, "elapsed_time": "0:16:19", "remaining_time": "0:47:50", "throughput": 5810.81, "total_tokens": 5692168} {"current_steps": 8635, "total_steps": 33920, "loss": 0.4806, "lr": 9.289965121608436e-06, "epoch": 5.091391509433962, "percentage": 25.46, "elapsed_time": "0:16:20", "remaining_time": "0:47:49", "throughput": 5810.67, "total_tokens": 5694952} {"current_steps": 8640, "total_steps": 33920, "loss": 0.5384, "lr": 9.288643050001362e-06, "epoch": 5.09433962264151, "percentage": 25.47, "elapsed_time": "0:16:20", "remaining_time": "0:47:49", "throughput": 5810.58, "total_tokens": 5697832} {"current_steps": 8645, "total_steps": 33920, "loss": 0.4735, "lr": 9.287319842957557e-06, "epoch": 5.097287735849057, "percentage": 25.49, "elapsed_time": "0:16:21", "remaining_time": "0:47:48", "throughput": 5810.53, "total_tokens": 5700808} {"current_steps": 8650, "total_steps": 33920, "loss": 0.4567, "lr": 9.285995500827348e-06, "epoch": 5.100235849056604, "percentage": 25.5, "elapsed_time": "0:16:21", "remaining_time": "0:47:47", "throughput": 5810.6, "total_tokens": 5703624} {"current_steps": 8655, "total_steps": 33920, "loss": 0.4706, "lr": 9.284670023961355e-06, "epoch": 5.103183962264151, "percentage": 25.52, "elapsed_time": "0:16:22", "remaining_time": "0:47:46", "throughput": 5810.3, "total_tokens": 5706056} {"current_steps": 8660, "total_steps": 33920, "loss": 0.8608, "lr": 9.28334341271051e-06, "epoch": 5.106132075471698, "percentage": 25.53, "elapsed_time": "0:16:22", "remaining_time": "0:47:46", "throughput": 5810.64, "total_tokens": 5709512} {"current_steps": 8665, "total_steps": 33920, "loss": 0.3945, "lr": 9.282015667426036e-06, "epoch": 5.109080188679245, "percentage": 25.55, "elapsed_time": "0:16:23", "remaining_time": "0:47:45", "throughput": 5810.83, "total_tokens": 5712872} {"current_steps": 8670, "total_steps": 33920, "loss": 0.3572, "lr": 9.280686788459461e-06, "epoch": 5.1120283018867925, "percentage": 25.56, "elapsed_time": "0:16:23", "remaining_time": "0:47:44", "throughput": 5810.78, "total_tokens": 5715528} {"current_steps": 8675, "total_steps": 33920, "loss": 0.3282, "lr": 9.279356776162606e-06, "epoch": 5.11497641509434, "percentage": 25.57, "elapsed_time": "0:16:24", "remaining_time": "0:47:43", "throughput": 5811.05, "total_tokens": 5718824} {"current_steps": 8680, "total_steps": 33920, "loss": 0.4042, "lr": 9.278025630887607e-06, "epoch": 5.117924528301887, "percentage": 25.59, "elapsed_time": "0:16:24", "remaining_time": "0:47:43", "throughput": 5810.96, "total_tokens": 5721576} {"current_steps": 8685, "total_steps": 33920, "loss": 0.4263, "lr": 9.27669335298688e-06, "epoch": 5.120872641509434, "percentage": 25.6, "elapsed_time": "0:16:25", "remaining_time": "0:47:42", "throughput": 5811.04, "total_tokens": 5724520} {"current_steps": 8690, "total_steps": 33920, "loss": 0.4582, "lr": 9.275359942813158e-06, "epoch": 5.123820754716981, "percentage": 25.62, "elapsed_time": "0:16:25", "remaining_time": "0:47:41", "throughput": 5811.01, "total_tokens": 5727272} {"current_steps": 8695, "total_steps": 33920, "loss": 0.5175, "lr": 9.274025400719466e-06, "epoch": 5.126768867924528, "percentage": 25.63, "elapsed_time": "0:16:26", "remaining_time": "0:47:40", "throughput": 5810.88, "total_tokens": 5730088} {"current_steps": 8700, "total_steps": 33920, "loss": 0.4695, "lr": 9.27268972705913e-06, "epoch": 5.129716981132075, "percentage": 25.65, "elapsed_time": "0:16:26", "remaining_time": "0:47:40", "throughput": 5811.18, "total_tokens": 5733544} {"current_steps": 8705, "total_steps": 33920, "loss": 0.4732, "lr": 9.271352922185772e-06, "epoch": 5.132665094339623, "percentage": 25.66, "elapsed_time": "0:16:27", "remaining_time": "0:47:39", "throughput": 5811.32, "total_tokens": 5736552} {"current_steps": 8710, "total_steps": 33920, "loss": 0.4506, "lr": 9.270014986453321e-06, "epoch": 5.13561320754717, "percentage": 25.68, "elapsed_time": "0:16:27", "remaining_time": "0:47:38", "throughput": 5811.52, "total_tokens": 5739848} {"current_steps": 8715, "total_steps": 33920, "loss": 0.4228, "lr": 9.268675920215999e-06, "epoch": 5.138561320754717, "percentage": 25.69, "elapsed_time": "0:16:28", "remaining_time": "0:47:37", "throughput": 5811.62, "total_tokens": 5742888} {"current_steps": 8720, "total_steps": 33920, "loss": 0.4177, "lr": 9.26733572382833e-06, "epoch": 5.1415094339622645, "percentage": 25.71, "elapsed_time": "0:16:28", "remaining_time": "0:47:37", "throughput": 5811.76, "total_tokens": 5746088} {"current_steps": 8725, "total_steps": 33920, "loss": 0.4201, "lr": 9.265994397645137e-06, "epoch": 5.144457547169812, "percentage": 25.72, "elapsed_time": "0:16:29", "remaining_time": "0:47:36", "throughput": 5811.74, "total_tokens": 5749000} {"current_steps": 8730, "total_steps": 33920, "loss": 0.3347, "lr": 9.264651942021543e-06, "epoch": 5.147405660377358, "percentage": 25.74, "elapsed_time": "0:16:29", "remaining_time": "0:47:35", "throughput": 5811.9, "total_tokens": 5752168} {"current_steps": 8735, "total_steps": 33920, "loss": 0.6201, "lr": 9.263308357312966e-06, "epoch": 5.150353773584905, "percentage": 25.75, "elapsed_time": "0:16:30", "remaining_time": "0:47:35", "throughput": 5811.86, "total_tokens": 5755208} {"current_steps": 8740, "total_steps": 33920, "loss": 0.5187, "lr": 9.26196364387513e-06, "epoch": 5.153301886792453, "percentage": 25.77, "elapsed_time": "0:16:30", "remaining_time": "0:47:34", "throughput": 5812.34, "total_tokens": 5758952} {"current_steps": 8745, "total_steps": 33920, "loss": 0.4334, "lr": 9.26061780206405e-06, "epoch": 5.15625, "percentage": 25.78, "elapsed_time": "0:16:31", "remaining_time": "0:47:33", "throughput": 5812.32, "total_tokens": 5761928} {"current_steps": 8750, "total_steps": 33920, "loss": 0.3834, "lr": 9.259270832236043e-06, "epoch": 5.159198113207547, "percentage": 25.8, "elapsed_time": "0:16:31", "remaining_time": "0:47:33", "throughput": 5812.73, "total_tokens": 5765672} {"current_steps": 8755, "total_steps": 33920, "loss": 0.3384, "lr": 9.257922734747729e-06, "epoch": 5.162146226415095, "percentage": 25.81, "elapsed_time": "0:16:32", "remaining_time": "0:47:32", "throughput": 5812.17, "total_tokens": 5768104} {"current_steps": 8760, "total_steps": 33920, "loss": 0.5079, "lr": 9.256573509956018e-06, "epoch": 5.165094339622642, "percentage": 25.83, "elapsed_time": "0:16:32", "remaining_time": "0:47:31", "throughput": 5812.51, "total_tokens": 5771624} {"current_steps": 8765, "total_steps": 33920, "loss": 0.4394, "lr": 9.255223158218127e-06, "epoch": 5.168042452830188, "percentage": 25.84, "elapsed_time": "0:16:33", "remaining_time": "0:47:31", "throughput": 5812.65, "total_tokens": 5774632} {"current_steps": 8770, "total_steps": 33920, "loss": 0.5058, "lr": 9.253871679891566e-06, "epoch": 5.1709905660377355, "percentage": 25.85, "elapsed_time": "0:16:33", "remaining_time": "0:47:30", "throughput": 5812.69, "total_tokens": 5777608} {"current_steps": 8775, "total_steps": 33920, "loss": 0.382, "lr": 9.252519075334143e-06, "epoch": 5.173938679245283, "percentage": 25.87, "elapsed_time": "0:16:34", "remaining_time": "0:47:30", "throughput": 5813.28, "total_tokens": 5782056} {"current_steps": 8780, "total_steps": 33920, "loss": 0.6249, "lr": 9.251165344903969e-06, "epoch": 5.17688679245283, "percentage": 25.88, "elapsed_time": "0:16:35", "remaining_time": "0:47:29", "throughput": 5813.56, "total_tokens": 5785608} {"current_steps": 8785, "total_steps": 33920, "loss": 0.4679, "lr": 9.249810488959448e-06, "epoch": 5.179834905660377, "percentage": 25.9, "elapsed_time": "0:16:35", "remaining_time": "0:47:28", "throughput": 5813.61, "total_tokens": 5788456} {"current_steps": 8790, "total_steps": 33920, "loss": 0.4688, "lr": 9.248454507859285e-06, "epoch": 5.182783018867925, "percentage": 25.91, "elapsed_time": "0:16:36", "remaining_time": "0:47:28", "throughput": 5813.64, "total_tokens": 5791560} {"current_steps": 8795, "total_steps": 33920, "loss": 0.3496, "lr": 9.247097401962482e-06, "epoch": 5.185731132075472, "percentage": 25.93, "elapsed_time": "0:16:36", "remaining_time": "0:47:27", "throughput": 5813.88, "total_tokens": 5794952} {"current_steps": 8800, "total_steps": 33920, "loss": 0.3448, "lr": 9.245739171628335e-06, "epoch": 5.188679245283019, "percentage": 25.94, "elapsed_time": "0:16:37", "remaining_time": "0:47:27", "throughput": 5814.12, "total_tokens": 5798920} {"current_steps": 8805, "total_steps": 33920, "loss": 0.5942, "lr": 9.244379817216447e-06, "epoch": 5.191627358490566, "percentage": 25.96, "elapsed_time": "0:16:37", "remaining_time": "0:47:26", "throughput": 5813.69, "total_tokens": 5801192} {"current_steps": 8810, "total_steps": 33920, "loss": 0.487, "lr": 9.243019339086708e-06, "epoch": 5.194575471698113, "percentage": 25.97, "elapsed_time": "0:16:38", "remaining_time": "0:47:25", "throughput": 5813.48, "total_tokens": 5803752} {"current_steps": 8815, "total_steps": 33920, "loss": 0.4448, "lr": 9.241657737599313e-06, "epoch": 5.19752358490566, "percentage": 25.99, "elapsed_time": "0:16:38", "remaining_time": "0:47:24", "throughput": 5814.07, "total_tokens": 5807720} {"current_steps": 8820, "total_steps": 33920, "loss": 0.4242, "lr": 9.240295013114752e-06, "epoch": 5.2004716981132075, "percentage": 26.0, "elapsed_time": "0:16:39", "remaining_time": "0:47:24", "throughput": 5813.96, "total_tokens": 5811016} {"current_steps": 8825, "total_steps": 33920, "loss": 0.3739, "lr": 9.238931165993811e-06, "epoch": 5.203419811320755, "percentage": 26.02, "elapsed_time": "0:16:39", "remaining_time": "0:47:23", "throughput": 5813.68, "total_tokens": 5813608} {"current_steps": 8830, "total_steps": 33920, "loss": 0.3522, "lr": 9.237566196597577e-06, "epoch": 5.206367924528302, "percentage": 26.03, "elapsed_time": "0:16:40", "remaining_time": "0:47:22", "throughput": 5813.68, "total_tokens": 5816648} {"current_steps": 8835, "total_steps": 33920, "loss": 0.5021, "lr": 9.236200105287427e-06, "epoch": 5.209316037735849, "percentage": 26.05, "elapsed_time": "0:16:41", "remaining_time": "0:47:22", "throughput": 5813.6, "total_tokens": 5819944} {"current_steps": 8840, "total_steps": 33920, "loss": 0.4048, "lr": 9.234832892425042e-06, "epoch": 5.212264150943396, "percentage": 26.06, "elapsed_time": "0:16:41", "remaining_time": "0:47:21", "throughput": 5813.56, "total_tokens": 5823272} {"current_steps": 8845, "total_steps": 33920, "loss": 0.3904, "lr": 9.2334645583724e-06, "epoch": 5.215212264150943, "percentage": 26.08, "elapsed_time": "0:16:42", "remaining_time": "0:47:21", "throughput": 5814.03, "total_tokens": 5827208} {"current_steps": 8850, "total_steps": 33920, "loss": 0.3229, "lr": 9.23209510349177e-06, "epoch": 5.21816037735849, "percentage": 26.09, "elapsed_time": "0:16:42", "remaining_time": "0:47:20", "throughput": 5813.95, "total_tokens": 5829832} {"current_steps": 8855, "total_steps": 33920, "loss": 0.5481, "lr": 9.230724528145722e-06, "epoch": 5.221108490566038, "percentage": 26.11, "elapsed_time": "0:16:43", "remaining_time": "0:47:20", "throughput": 5814.64, "total_tokens": 5834376} {"current_steps": 8860, "total_steps": 33920, "loss": 0.496, "lr": 9.229352832697122e-06, "epoch": 5.224056603773585, "percentage": 26.12, "elapsed_time": "0:16:43", "remaining_time": "0:47:19", "throughput": 5814.87, "total_tokens": 5837960} {"current_steps": 8865, "total_steps": 33920, "loss": 0.4828, "lr": 9.22798001750913e-06, "epoch": 5.227004716981132, "percentage": 26.14, "elapsed_time": "0:16:44", "remaining_time": "0:47:19", "throughput": 5815.3, "total_tokens": 5841512} {"current_steps": 8870, "total_steps": 33920, "loss": 0.4136, "lr": 9.226606082945209e-06, "epoch": 5.2299528301886795, "percentage": 26.15, "elapsed_time": "0:16:45", "remaining_time": "0:47:18", "throughput": 5815.74, "total_tokens": 5845224} {"current_steps": 8875, "total_steps": 33920, "loss": 0.5369, "lr": 9.225231029369112e-06, "epoch": 5.232900943396227, "percentage": 26.16, "elapsed_time": "0:16:45", "remaining_time": "0:47:17", "throughput": 5815.43, "total_tokens": 5847656} {"current_steps": 8880, "total_steps": 33920, "loss": 0.4265, "lr": 9.22385485714489e-06, "epoch": 5.235849056603773, "percentage": 26.18, "elapsed_time": "0:16:46", "remaining_time": "0:47:16", "throughput": 5815.74, "total_tokens": 5850952} {"current_steps": 8885, "total_steps": 33920, "loss": 0.4105, "lr": 9.222477566636889e-06, "epoch": 5.2387971698113205, "percentage": 26.19, "elapsed_time": "0:16:46", "remaining_time": "0:47:16", "throughput": 5815.54, "total_tokens": 5853480} {"current_steps": 8890, "total_steps": 33920, "loss": 0.3943, "lr": 9.221099158209757e-06, "epoch": 5.241745283018868, "percentage": 26.21, "elapsed_time": "0:16:47", "remaining_time": "0:47:15", "throughput": 5815.7, "total_tokens": 5856872} {"current_steps": 8895, "total_steps": 33920, "loss": 0.4919, "lr": 9.219719632228429e-06, "epoch": 5.244693396226415, "percentage": 26.22, "elapsed_time": "0:16:47", "remaining_time": "0:47:14", "throughput": 5815.97, "total_tokens": 5860040} {"current_steps": 8900, "total_steps": 33920, "loss": 0.402, "lr": 9.218338989058141e-06, "epoch": 5.247641509433962, "percentage": 26.24, "elapsed_time": "0:16:48", "remaining_time": "0:47:13", "throughput": 5815.94, "total_tokens": 5862792} {"current_steps": 8905, "total_steps": 33920, "loss": 0.4578, "lr": 9.21695722906443e-06, "epoch": 5.25058962264151, "percentage": 26.25, "elapsed_time": "0:16:48", "remaining_time": "0:47:13", "throughput": 5815.97, "total_tokens": 5865640} {"current_steps": 8910, "total_steps": 33920, "loss": 0.3933, "lr": 9.215574352613115e-06, "epoch": 5.253537735849057, "percentage": 26.27, "elapsed_time": "0:16:49", "remaining_time": "0:47:12", "throughput": 5816.16, "total_tokens": 5868968} {"current_steps": 8915, "total_steps": 33920, "loss": 0.6287, "lr": 9.214190360070323e-06, "epoch": 5.256485849056604, "percentage": 26.28, "elapsed_time": "0:16:49", "remaining_time": "0:47:11", "throughput": 5816.27, "total_tokens": 5872136} {"current_steps": 8920, "total_steps": 33920, "loss": 0.4596, "lr": 9.212805251802471e-06, "epoch": 5.259433962264151, "percentage": 26.3, "elapsed_time": "0:16:50", "remaining_time": "0:47:11", "throughput": 5816.51, "total_tokens": 5875752} {"current_steps": 8925, "total_steps": 33920, "loss": 0.4006, "lr": 9.211419028176273e-06, "epoch": 5.262382075471698, "percentage": 26.31, "elapsed_time": "0:16:50", "remaining_time": "0:47:10", "throughput": 5816.96, "total_tokens": 5879784} {"current_steps": 8930, "total_steps": 33920, "loss": 0.4267, "lr": 9.210031689558738e-06, "epoch": 5.265330188679245, "percentage": 26.33, "elapsed_time": "0:16:51", "remaining_time": "0:47:10", "throughput": 5817.38, "total_tokens": 5883560} {"current_steps": 8935, "total_steps": 33920, "loss": 0.38, "lr": 9.208643236317166e-06, "epoch": 5.2682783018867925, "percentage": 26.34, "elapsed_time": "0:16:51", "remaining_time": "0:47:09", "throughput": 5817.02, "total_tokens": 5886216} {"current_steps": 8940, "total_steps": 33920, "loss": 0.3661, "lr": 9.20725366881916e-06, "epoch": 5.27122641509434, "percentage": 26.36, "elapsed_time": "0:16:52", "remaining_time": "0:47:08", "throughput": 5816.98, "total_tokens": 5888968} {"current_steps": 8945, "total_steps": 33920, "loss": 0.4707, "lr": 9.205862987432614e-06, "epoch": 5.274174528301887, "percentage": 26.37, "elapsed_time": "0:16:52", "remaining_time": "0:47:07", "throughput": 5817.22, "total_tokens": 5892072} {"current_steps": 8950, "total_steps": 33920, "loss": 0.3819, "lr": 9.204471192525715e-06, "epoch": 5.277122641509434, "percentage": 26.39, "elapsed_time": "0:16:53", "remaining_time": "0:47:07", "throughput": 5816.74, "total_tokens": 5894632} {"current_steps": 8955, "total_steps": 33920, "loss": 0.4135, "lr": 9.203078284466949e-06, "epoch": 5.280070754716981, "percentage": 26.4, "elapsed_time": "0:16:53", "remaining_time": "0:47:06", "throughput": 5816.78, "total_tokens": 5897544} {"current_steps": 8960, "total_steps": 33920, "loss": 0.5121, "lr": 9.201684263625091e-06, "epoch": 5.283018867924528, "percentage": 26.42, "elapsed_time": "0:16:54", "remaining_time": "0:47:05", "throughput": 5816.95, "total_tokens": 5900712} {"current_steps": 8965, "total_steps": 33920, "loss": 0.4135, "lr": 9.200289130369218e-06, "epoch": 5.285966981132075, "percentage": 26.43, "elapsed_time": "0:16:54", "remaining_time": "0:47:05", "throughput": 5817.06, "total_tokens": 5903848} {"current_steps": 8970, "total_steps": 33920, "loss": 0.5105, "lr": 9.198892885068693e-06, "epoch": 5.288915094339623, "percentage": 26.44, "elapsed_time": "0:16:55", "remaining_time": "0:47:04", "throughput": 5817.17, "total_tokens": 5907240} {"current_steps": 8975, "total_steps": 33920, "loss": 0.3932, "lr": 9.197495528093182e-06, "epoch": 5.29186320754717, "percentage": 26.46, "elapsed_time": "0:16:56", "remaining_time": "0:47:04", "throughput": 5817.25, "total_tokens": 5910664} {"current_steps": 8980, "total_steps": 33920, "loss": 0.3516, "lr": 9.196097059812639e-06, "epoch": 5.294811320754717, "percentage": 26.47, "elapsed_time": "0:16:56", "remaining_time": "0:47:03", "throughput": 5817.57, "total_tokens": 5914440} {"current_steps": 8985, "total_steps": 33920, "loss": 0.3633, "lr": 9.194697480597316e-06, "epoch": 5.2977594339622645, "percentage": 26.49, "elapsed_time": "0:16:57", "remaining_time": "0:47:03", "throughput": 5817.94, "total_tokens": 5918376} {"current_steps": 8990, "total_steps": 33920, "loss": 0.4814, "lr": 9.193296790817755e-06, "epoch": 5.300707547169811, "percentage": 26.5, "elapsed_time": "0:16:57", "remaining_time": "0:47:02", "throughput": 5818.53, "total_tokens": 5922408} {"current_steps": 8995, "total_steps": 33920, "loss": 0.5305, "lr": 9.1918949908448e-06, "epoch": 5.303655660377358, "percentage": 26.52, "elapsed_time": "0:16:58", "remaining_time": "0:47:02", "throughput": 5819.14, "total_tokens": 5926824} {"current_steps": 9000, "total_steps": 33920, "loss": 0.4199, "lr": 9.190492081049578e-06, "epoch": 5.306603773584905, "percentage": 26.53, "elapsed_time": "0:16:58", "remaining_time": "0:47:01", "throughput": 5818.86, "total_tokens": 5929352} {"current_steps": 9005, "total_steps": 33920, "loss": 0.5947, "lr": 9.189088061803517e-06, "epoch": 5.309551886792453, "percentage": 26.55, "elapsed_time": "0:16:59", "remaining_time": "0:47:00", "throughput": 5819.1, "total_tokens": 5932616} {"current_steps": 9010, "total_steps": 33920, "loss": 0.5621, "lr": 9.187682933478337e-06, "epoch": 5.3125, "percentage": 26.56, "elapsed_time": "0:16:59", "remaining_time": "0:46:59", "throughput": 5819.28, "total_tokens": 5935496} {"current_steps": 9015, "total_steps": 33920, "loss": 0.4553, "lr": 9.186276696446054e-06, "epoch": 5.315448113207547, "percentage": 26.58, "elapsed_time": "0:17:00", "remaining_time": "0:46:59", "throughput": 5819.37, "total_tokens": 5938600} {"current_steps": 9020, "total_steps": 33920, "loss": 0.4703, "lr": 9.184869351078974e-06, "epoch": 5.318396226415095, "percentage": 26.59, "elapsed_time": "0:17:01", "remaining_time": "0:46:58", "throughput": 5819.79, "total_tokens": 5942408} {"current_steps": 9025, "total_steps": 33920, "loss": 0.4289, "lr": 9.183460897749697e-06, "epoch": 5.321344339622642, "percentage": 26.61, "elapsed_time": "0:17:01", "remaining_time": "0:46:57", "throughput": 5819.67, "total_tokens": 5944968} {"current_steps": 9030, "total_steps": 33920, "loss": 0.4282, "lr": 9.182051336831117e-06, "epoch": 5.324292452830189, "percentage": 26.62, "elapsed_time": "0:17:02", "remaining_time": "0:46:57", "throughput": 5819.84, "total_tokens": 5948104} {"current_steps": 9035, "total_steps": 33920, "loss": 0.5665, "lr": 9.180640668696424e-06, "epoch": 5.3272405660377355, "percentage": 26.64, "elapsed_time": "0:17:02", "remaining_time": "0:46:56", "throughput": 5819.94, "total_tokens": 5951432} {"current_steps": 9040, "total_steps": 33920, "loss": 0.532, "lr": 9.179228893719094e-06, "epoch": 5.330188679245283, "percentage": 26.65, "elapsed_time": "0:17:03", "remaining_time": "0:46:55", "throughput": 5820.02, "total_tokens": 5954696} {"current_steps": 9045, "total_steps": 33920, "loss": 0.5023, "lr": 9.177816012272904e-06, "epoch": 5.33313679245283, "percentage": 26.67, "elapsed_time": "0:17:03", "remaining_time": "0:46:55", "throughput": 5819.85, "total_tokens": 5957512} {"current_steps": 9050, "total_steps": 33920, "loss": 0.4039, "lr": 9.17640202473192e-06, "epoch": 5.336084905660377, "percentage": 26.68, "elapsed_time": "0:17:04", "remaining_time": "0:46:54", "throughput": 5819.95, "total_tokens": 5960616} {"current_steps": 9055, "total_steps": 33920, "loss": 0.3783, "lr": 9.1749869314705e-06, "epoch": 5.339033018867925, "percentage": 26.7, "elapsed_time": "0:17:04", "remaining_time": "0:46:53", "throughput": 5820.12, "total_tokens": 5963752} {"current_steps": 9060, "total_steps": 33920, "loss": 0.4014, "lr": 9.173570732863295e-06, "epoch": 5.341981132075472, "percentage": 26.71, "elapsed_time": "0:17:05", "remaining_time": "0:46:53", "throughput": 5820.02, "total_tokens": 5966792} {"current_steps": 9065, "total_steps": 33920, "loss": 0.516, "lr": 9.172153429285254e-06, "epoch": 5.344929245283019, "percentage": 26.72, "elapsed_time": "0:17:05", "remaining_time": "0:46:52", "throughput": 5820.22, "total_tokens": 5970088} {"current_steps": 9070, "total_steps": 33920, "loss": 0.3529, "lr": 9.17073502111161e-06, "epoch": 5.347877358490566, "percentage": 26.74, "elapsed_time": "0:17:06", "remaining_time": "0:46:52", "throughput": 5820.52, "total_tokens": 5973960} {"current_steps": 9075, "total_steps": 33920, "loss": 0.4071, "lr": 9.169315508717895e-06, "epoch": 5.350825471698113, "percentage": 26.75, "elapsed_time": "0:17:07", "remaining_time": "0:46:51", "throughput": 5820.85, "total_tokens": 5978440} {"current_steps": 9080, "total_steps": 33920, "loss": 0.5922, "lr": 9.167894892479932e-06, "epoch": 5.35377358490566, "percentage": 26.77, "elapsed_time": "0:17:07", "remaining_time": "0:46:51", "throughput": 5820.41, "total_tokens": 5980744} {"current_steps": 9085, "total_steps": 33920, "loss": 0.5414, "lr": 9.16647317277383e-06, "epoch": 5.3567216981132075, "percentage": 26.78, "elapsed_time": "0:17:08", "remaining_time": "0:46:50", "throughput": 5820.48, "total_tokens": 5983624} {"current_steps": 9090, "total_steps": 33920, "loss": 0.341, "lr": 9.165050349976002e-06, "epoch": 5.359669811320755, "percentage": 26.8, "elapsed_time": "0:17:08", "remaining_time": "0:46:49", "throughput": 5820.72, "total_tokens": 5986824} {"current_steps": 9095, "total_steps": 33920, "loss": 0.4061, "lr": 9.16362642446314e-06, "epoch": 5.362617924528302, "percentage": 26.81, "elapsed_time": "0:17:09", "remaining_time": "0:46:48", "throughput": 5821.08, "total_tokens": 5990440} {"current_steps": 9100, "total_steps": 33920, "loss": 0.6646, "lr": 9.162201396612242e-06, "epoch": 5.365566037735849, "percentage": 26.83, "elapsed_time": "0:17:09", "remaining_time": "0:46:48", "throughput": 5821.05, "total_tokens": 5993448} {"current_steps": 9105, "total_steps": 33920, "loss": 0.4242, "lr": 9.160775266800583e-06, "epoch": 5.368514150943396, "percentage": 26.84, "elapsed_time": "0:17:10", "remaining_time": "0:46:47", "throughput": 5821.35, "total_tokens": 5997096} {"current_steps": 9110, "total_steps": 33920, "loss": 0.4271, "lr": 9.159348035405742e-06, "epoch": 5.371462264150943, "percentage": 26.86, "elapsed_time": "0:17:10", "remaining_time": "0:46:46", "throughput": 5821.57, "total_tokens": 6000232} {"current_steps": 9115, "total_steps": 33920, "loss": 0.4448, "lr": 9.157919702805582e-06, "epoch": 5.37441037735849, "percentage": 26.87, "elapsed_time": "0:17:11", "remaining_time": "0:46:46", "throughput": 5821.8, "total_tokens": 6003720} {"current_steps": 9120, "total_steps": 33920, "loss": 0.4384, "lr": 9.156490269378262e-06, "epoch": 5.377358490566038, "percentage": 26.89, "elapsed_time": "0:17:11", "remaining_time": "0:46:45", "throughput": 5822.22, "total_tokens": 6007304} {"current_steps": 9125, "total_steps": 33920, "loss": 0.3863, "lr": 9.15505973550223e-06, "epoch": 5.380306603773585, "percentage": 26.9, "elapsed_time": "0:17:12", "remaining_time": "0:46:44", "throughput": 5822.46, "total_tokens": 6010440} {"current_steps": 9130, "total_steps": 33920, "loss": 0.3743, "lr": 9.153628101556223e-06, "epoch": 5.383254716981132, "percentage": 26.92, "elapsed_time": "0:17:12", "remaining_time": "0:46:44", "throughput": 5822.63, "total_tokens": 6013928} {"current_steps": 9135, "total_steps": 33920, "loss": 0.4262, "lr": 9.152195367919277e-06, "epoch": 5.3862028301886795, "percentage": 26.93, "elapsed_time": "0:17:13", "remaining_time": "0:46:43", "throughput": 5822.75, "total_tokens": 6017384} {"current_steps": 9140, "total_steps": 33920, "loss": 0.453, "lr": 9.150761534970713e-06, "epoch": 5.389150943396227, "percentage": 26.95, "elapsed_time": "0:17:14", "remaining_time": "0:46:43", "throughput": 5823.28, "total_tokens": 6021544} {"current_steps": 9145, "total_steps": 33920, "loss": 0.3703, "lr": 9.149326603090144e-06, "epoch": 5.392099056603773, "percentage": 26.96, "elapsed_time": "0:17:14", "remaining_time": "0:46:42", "throughput": 5823.69, "total_tokens": 6025064} {"current_steps": 9150, "total_steps": 33920, "loss": 0.587, "lr": 9.147890572657471e-06, "epoch": 5.3950471698113205, "percentage": 26.98, "elapsed_time": "0:17:15", "remaining_time": "0:46:42", "throughput": 5823.7, "total_tokens": 6028040} {"current_steps": 9155, "total_steps": 33920, "loss": 0.3036, "lr": 9.146453444052895e-06, "epoch": 5.397995283018868, "percentage": 26.99, "elapsed_time": "0:17:15", "remaining_time": "0:46:41", "throughput": 5823.79, "total_tokens": 6031048} {"current_steps": 9160, "total_steps": 33920, "loss": 0.471, "lr": 9.145015217656899e-06, "epoch": 5.400943396226415, "percentage": 27.0, "elapsed_time": "0:17:16", "remaining_time": "0:46:40", "throughput": 5824.2, "total_tokens": 6034760} {"current_steps": 9165, "total_steps": 33920, "loss": 0.5143, "lr": 9.14357589385026e-06, "epoch": 5.403891509433962, "percentage": 27.02, "elapsed_time": "0:17:16", "remaining_time": "0:46:40", "throughput": 5824.06, "total_tokens": 6037896} {"current_steps": 9170, "total_steps": 33920, "loss": 0.7033, "lr": 9.142135473014046e-06, "epoch": 5.40683962264151, "percentage": 27.03, "elapsed_time": "0:17:17", "remaining_time": "0:46:39", "throughput": 5823.68, "total_tokens": 6040552} {"current_steps": 9175, "total_steps": 33920, "loss": 0.4087, "lr": 9.140693955529614e-06, "epoch": 5.409787735849057, "percentage": 27.05, "elapsed_time": "0:17:17", "remaining_time": "0:46:39", "throughput": 5824.25, "total_tokens": 6045032} {"current_steps": 9180, "total_steps": 33920, "loss": 0.4681, "lr": 9.13925134177861e-06, "epoch": 5.412735849056604, "percentage": 27.06, "elapsed_time": "0:17:18", "remaining_time": "0:46:38", "throughput": 5823.83, "total_tokens": 6047400} {"current_steps": 9185, "total_steps": 33920, "loss": 0.4281, "lr": 9.137807632142977e-06, "epoch": 5.415683962264151, "percentage": 27.08, "elapsed_time": "0:17:18", "remaining_time": "0:46:37", "throughput": 5823.92, "total_tokens": 6050344} {"current_steps": 9190, "total_steps": 33920, "loss": 0.436, "lr": 9.136362827004937e-06, "epoch": 5.418632075471698, "percentage": 27.09, "elapsed_time": "0:17:19", "remaining_time": "0:46:36", "throughput": 5823.77, "total_tokens": 6053032} {"current_steps": 9195, "total_steps": 33920, "loss": 0.5363, "lr": 9.134916926747015e-06, "epoch": 5.421580188679245, "percentage": 27.11, "elapsed_time": "0:17:19", "remaining_time": "0:46:36", "throughput": 5823.35, "total_tokens": 6055272} {"current_steps": 9200, "total_steps": 33920, "loss": 0.4272, "lr": 9.133469931752016e-06, "epoch": 5.4245283018867925, "percentage": 27.12, "elapsed_time": "0:17:20", "remaining_time": "0:46:35", "throughput": 5822.92, "total_tokens": 6057800} {"current_steps": 9205, "total_steps": 33920, "loss": 0.5956, "lr": 9.132021842403035e-06, "epoch": 5.42747641509434, "percentage": 27.14, "elapsed_time": "0:17:20", "remaining_time": "0:46:34", "throughput": 5823.05, "total_tokens": 6060904} {"current_steps": 9210, "total_steps": 33920, "loss": 0.3809, "lr": 9.130572659083465e-06, "epoch": 5.430424528301887, "percentage": 27.15, "elapsed_time": "0:17:21", "remaining_time": "0:46:34", "throughput": 5823.2, "total_tokens": 6064296} {"current_steps": 9215, "total_steps": 33920, "loss": 0.5282, "lr": 9.129122382176982e-06, "epoch": 5.433372641509434, "percentage": 27.17, "elapsed_time": "0:17:21", "remaining_time": "0:46:33", "throughput": 5823.56, "total_tokens": 6067944} {"current_steps": 9220, "total_steps": 33920, "loss": 0.403, "lr": 9.127671012067554e-06, "epoch": 5.436320754716981, "percentage": 27.18, "elapsed_time": "0:17:22", "remaining_time": "0:46:32", "throughput": 5823.64, "total_tokens": 6071080} {"current_steps": 9225, "total_steps": 33920, "loss": 0.3707, "lr": 9.126218549139434e-06, "epoch": 5.439268867924528, "percentage": 27.2, "elapsed_time": "0:17:23", "remaining_time": "0:46:32", "throughput": 5823.88, "total_tokens": 6074408} {"current_steps": 9230, "total_steps": 33920, "loss": 0.3522, "lr": 9.124764993777171e-06, "epoch": 5.442216981132075, "percentage": 27.21, "elapsed_time": "0:17:23", "remaining_time": "0:46:31", "throughput": 5824.15, "total_tokens": 6077960} {"current_steps": 9235, "total_steps": 33920, "loss": 0.412, "lr": 9.1233103463656e-06, "epoch": 5.445165094339623, "percentage": 27.23, "elapsed_time": "0:17:24", "remaining_time": "0:46:31", "throughput": 5824.29, "total_tokens": 6081448} {"current_steps": 9240, "total_steps": 33920, "loss": 0.5152, "lr": 9.121854607289842e-06, "epoch": 5.44811320754717, "percentage": 27.24, "elapsed_time": "0:17:24", "remaining_time": "0:46:30", "throughput": 5824.36, "total_tokens": 6084520} {"current_steps": 9245, "total_steps": 33920, "loss": 0.3838, "lr": 9.120397776935314e-06, "epoch": 5.451061320754717, "percentage": 27.26, "elapsed_time": "0:17:25", "remaining_time": "0:46:29", "throughput": 5824.22, "total_tokens": 6087336} {"current_steps": 9250, "total_steps": 33920, "loss": 0.3839, "lr": 9.118939855687717e-06, "epoch": 5.4540094339622645, "percentage": 27.27, "elapsed_time": "0:17:25", "remaining_time": "0:46:28", "throughput": 5823.8, "total_tokens": 6089576} {"current_steps": 9255, "total_steps": 33920, "loss": 0.3567, "lr": 9.117480843933043e-06, "epoch": 5.456957547169811, "percentage": 27.28, "elapsed_time": "0:17:26", "remaining_time": "0:46:28", "throughput": 5823.66, "total_tokens": 6092392} {"current_steps": 9260, "total_steps": 33920, "loss": 0.401, "lr": 9.116020742057567e-06, "epoch": 5.459905660377358, "percentage": 27.3, "elapsed_time": "0:17:26", "remaining_time": "0:46:27", "throughput": 5823.7, "total_tokens": 6095336} {"current_steps": 9265, "total_steps": 33920, "loss": 0.6118, "lr": 9.114559550447863e-06, "epoch": 5.462853773584905, "percentage": 27.31, "elapsed_time": "0:17:27", "remaining_time": "0:46:26", "throughput": 5823.48, "total_tokens": 6098056} {"current_steps": 9270, "total_steps": 33920, "loss": 0.4635, "lr": 9.113097269490784e-06, "epoch": 5.465801886792453, "percentage": 27.33, "elapsed_time": "0:17:27", "remaining_time": "0:46:25", "throughput": 5823.37, "total_tokens": 6101160} {"current_steps": 9275, "total_steps": 33920, "loss": 0.5018, "lr": 9.111633899573476e-06, "epoch": 5.46875, "percentage": 27.34, "elapsed_time": "0:17:28", "remaining_time": "0:46:25", "throughput": 5823.8, "total_tokens": 6104744} {"current_steps": 9280, "total_steps": 33920, "loss": 0.5002, "lr": 9.110169441083374e-06, "epoch": 5.471698113207547, "percentage": 27.36, "elapsed_time": "0:17:28", "remaining_time": "0:46:24", "throughput": 5824.08, "total_tokens": 6108520} {"current_steps": 9285, "total_steps": 33920, "loss": 0.421, "lr": 9.108703894408198e-06, "epoch": 5.474646226415095, "percentage": 27.37, "elapsed_time": "0:17:29", "remaining_time": "0:46:24", "throughput": 5824.2, "total_tokens": 6111592} {"current_steps": 9290, "total_steps": 33920, "loss": 0.6988, "lr": 9.107237259935959e-06, "epoch": 5.477594339622642, "percentage": 27.39, "elapsed_time": "0:17:29", "remaining_time": "0:46:23", "throughput": 5824.65, "total_tokens": 6115432} {"current_steps": 9295, "total_steps": 33920, "loss": 0.5272, "lr": 9.105769538054954e-06, "epoch": 5.480542452830189, "percentage": 27.4, "elapsed_time": "0:17:30", "remaining_time": "0:46:23", "throughput": 5825.0, "total_tokens": 6119176} {"current_steps": 9300, "total_steps": 33920, "loss": 0.4106, "lr": 9.104300729153768e-06, "epoch": 5.4834905660377355, "percentage": 27.42, "elapsed_time": "0:17:31", "remaining_time": "0:46:22", "throughput": 5825.3, "total_tokens": 6122504} {"current_steps": 9305, "total_steps": 33920, "loss": 0.5403, "lr": 9.102830833621277e-06, "epoch": 5.486438679245283, "percentage": 27.43, "elapsed_time": "0:17:31", "remaining_time": "0:46:21", "throughput": 5825.67, "total_tokens": 6126088} {"current_steps": 9310, "total_steps": 33920, "loss": 0.4298, "lr": 9.101359851846639e-06, "epoch": 5.48938679245283, "percentage": 27.45, "elapsed_time": "0:17:32", "remaining_time": "0:46:21", "throughput": 5825.58, "total_tokens": 6128872} {"current_steps": 9315, "total_steps": 33920, "loss": 0.4689, "lr": 9.099887784219305e-06, "epoch": 5.492334905660377, "percentage": 27.46, "elapsed_time": "0:17:32", "remaining_time": "0:46:20", "throughput": 5825.65, "total_tokens": 6132296} {"current_steps": 9320, "total_steps": 33920, "loss": 0.6609, "lr": 9.098414631129012e-06, "epoch": 5.495283018867925, "percentage": 27.48, "elapsed_time": "0:17:33", "remaining_time": "0:46:19", "throughput": 5825.22, "total_tokens": 6134632} {"current_steps": 9325, "total_steps": 33920, "loss": 0.5998, "lr": 9.09694039296578e-06, "epoch": 5.498231132075472, "percentage": 27.49, "elapsed_time": "0:17:33", "remaining_time": "0:46:18", "throughput": 5825.47, "total_tokens": 6137800} {"current_steps": 9330, "total_steps": 33920, "loss": 0.4197, "lr": 9.095465070119924e-06, "epoch": 5.501179245283019, "percentage": 27.51, "elapsed_time": "0:17:34", "remaining_time": "0:46:18", "throughput": 5825.5, "total_tokens": 6140680} {"current_steps": 9335, "total_steps": 33920, "loss": 0.5472, "lr": 9.09398866298204e-06, "epoch": 5.504127358490566, "percentage": 27.52, "elapsed_time": "0:17:34", "remaining_time": "0:46:17", "throughput": 5826.11, "total_tokens": 6145096} {"current_steps": 9340, "total_steps": 33920, "loss": 0.3219, "lr": 9.09251117194301e-06, "epoch": 5.507075471698113, "percentage": 27.54, "elapsed_time": "0:17:35", "remaining_time": "0:46:17", "throughput": 5826.53, "total_tokens": 6148776} {"current_steps": 9345, "total_steps": 33920, "loss": 0.4294, "lr": 9.091032597394012e-06, "epoch": 5.51002358490566, "percentage": 27.55, "elapsed_time": "0:17:35", "remaining_time": "0:46:16", "throughput": 5826.61, "total_tokens": 6152040} {"current_steps": 9350, "total_steps": 33920, "loss": 0.4892, "lr": 9.089552939726503e-06, "epoch": 5.5129716981132075, "percentage": 27.56, "elapsed_time": "0:17:36", "remaining_time": "0:46:15", "throughput": 5826.37, "total_tokens": 6154856} {"current_steps": 9355, "total_steps": 33920, "loss": 0.4272, "lr": 9.088072199332227e-06, "epoch": 5.515919811320755, "percentage": 27.58, "elapsed_time": "0:17:36", "remaining_time": "0:46:15", "throughput": 5826.48, "total_tokens": 6157736} {"current_steps": 9360, "total_steps": 33920, "loss": 0.479, "lr": 9.08659037660322e-06, "epoch": 5.518867924528302, "percentage": 27.59, "elapsed_time": "0:17:37", "remaining_time": "0:46:14", "throughput": 5826.39, "total_tokens": 6160392} {"current_steps": 9365, "total_steps": 33920, "loss": 0.3525, "lr": 9.085107471931797e-06, "epoch": 5.521816037735849, "percentage": 27.61, "elapsed_time": "0:17:37", "remaining_time": "0:46:13", "throughput": 5826.59, "total_tokens": 6163624} {"current_steps": 9370, "total_steps": 33920, "loss": 0.4945, "lr": 9.083623485710564e-06, "epoch": 5.524764150943396, "percentage": 27.62, "elapsed_time": "0:17:38", "remaining_time": "0:46:13", "throughput": 5827.0, "total_tokens": 6167400} {"current_steps": 9375, "total_steps": 33920, "loss": 0.5094, "lr": 9.082138418332416e-06, "epoch": 5.527712264150943, "percentage": 27.64, "elapsed_time": "0:17:38", "remaining_time": "0:46:12", "throughput": 5827.29, "total_tokens": 6171080} {"current_steps": 9380, "total_steps": 33920, "loss": 0.5392, "lr": 9.080652270190527e-06, "epoch": 5.53066037735849, "percentage": 27.65, "elapsed_time": "0:17:39", "remaining_time": "0:46:11", "throughput": 5827.19, "total_tokens": 6173768} {"current_steps": 9385, "total_steps": 33920, "loss": 0.5266, "lr": 9.079165041678363e-06, "epoch": 5.533608490566038, "percentage": 27.67, "elapsed_time": "0:17:40", "remaining_time": "0:46:11", "throughput": 5827.23, "total_tokens": 6177000} {"current_steps": 9390, "total_steps": 33920, "loss": 0.5089, "lr": 9.077676733189675e-06, "epoch": 5.536556603773585, "percentage": 27.68, "elapsed_time": "0:17:40", "remaining_time": "0:46:10", "throughput": 5827.41, "total_tokens": 6180008} {"current_steps": 9395, "total_steps": 33920, "loss": 0.3749, "lr": 9.076187345118496e-06, "epoch": 5.539504716981132, "percentage": 27.7, "elapsed_time": "0:17:40", "remaining_time": "0:46:09", "throughput": 5827.16, "total_tokens": 6182536} {"current_steps": 9400, "total_steps": 33920, "loss": 0.5415, "lr": 9.074696877859152e-06, "epoch": 5.5424528301886795, "percentage": 27.71, "elapsed_time": "0:17:41", "remaining_time": "0:46:08", "throughput": 5827.05, "total_tokens": 6185192} {"current_steps": 9405, "total_steps": 33920, "loss": 0.4007, "lr": 9.073205331806248e-06, "epoch": 5.545400943396227, "percentage": 27.73, "elapsed_time": "0:17:41", "remaining_time": "0:46:08", "throughput": 5827.41, "total_tokens": 6188616} {"current_steps": 9410, "total_steps": 33920, "loss": 0.5834, "lr": 9.071712707354676e-06, "epoch": 5.548349056603773, "percentage": 27.74, "elapsed_time": "0:17:42", "remaining_time": "0:46:07", "throughput": 5827.52, "total_tokens": 6191656} {"current_steps": 9415, "total_steps": 33920, "loss": 0.3858, "lr": 9.070219004899618e-06, "epoch": 5.5512971698113205, "percentage": 27.76, "elapsed_time": "0:17:43", "remaining_time": "0:46:06", "throughput": 5827.61, "total_tokens": 6194792} {"current_steps": 9420, "total_steps": 33920, "loss": 0.4335, "lr": 9.068724224836538e-06, "epoch": 5.554245283018868, "percentage": 27.77, "elapsed_time": "0:17:43", "remaining_time": "0:46:06", "throughput": 5827.88, "total_tokens": 6199976} {"current_steps": 9425, "total_steps": 33920, "loss": 0.5576, "lr": 9.067228367561182e-06, "epoch": 5.557193396226415, "percentage": 27.79, "elapsed_time": "0:17:44", "remaining_time": "0:46:06", "throughput": 5827.77, "total_tokens": 6202600} {"current_steps": 9430, "total_steps": 33920, "loss": 0.3729, "lr": 9.06573143346959e-06, "epoch": 5.560141509433962, "percentage": 27.8, "elapsed_time": "0:17:44", "remaining_time": "0:46:05", "throughput": 5827.57, "total_tokens": 6205192} {"current_steps": 9435, "total_steps": 33920, "loss": 0.4612, "lr": 9.064233422958078e-06, "epoch": 5.56308962264151, "percentage": 27.82, "elapsed_time": "0:17:45", "remaining_time": "0:46:04", "throughput": 5827.55, "total_tokens": 6208008} {"current_steps": 9440, "total_steps": 33920, "loss": 0.4939, "lr": 9.062734336423248e-06, "epoch": 5.566037735849057, "percentage": 27.83, "elapsed_time": "0:17:45", "remaining_time": "0:46:03", "throughput": 5827.99, "total_tokens": 6211688} {"current_steps": 9445, "total_steps": 33920, "loss": 0.4234, "lr": 9.061234174261998e-06, "epoch": 5.568985849056604, "percentage": 27.84, "elapsed_time": "0:17:46", "remaining_time": "0:46:03", "throughput": 5828.1, "total_tokens": 6214920} {"current_steps": 9450, "total_steps": 33920, "loss": 0.4944, "lr": 9.059732936871493e-06, "epoch": 5.571933962264151, "percentage": 27.86, "elapsed_time": "0:17:46", "remaining_time": "0:46:02", "throughput": 5828.3, "total_tokens": 6218088} {"current_steps": 9455, "total_steps": 33920, "loss": 0.4318, "lr": 9.058230624649198e-06, "epoch": 5.574882075471698, "percentage": 27.87, "elapsed_time": "0:17:47", "remaining_time": "0:46:01", "throughput": 5828.25, "total_tokens": 6220808} {"current_steps": 9460, "total_steps": 33920, "loss": 0.4201, "lr": 9.056727237992856e-06, "epoch": 5.577830188679245, "percentage": 27.89, "elapsed_time": "0:17:48", "remaining_time": "0:46:01", "throughput": 5828.64, "total_tokens": 6225160} {"current_steps": 9465, "total_steps": 33920, "loss": 0.437, "lr": 9.055222777300493e-06, "epoch": 5.5807783018867925, "percentage": 27.9, "elapsed_time": "0:17:48", "remaining_time": "0:46:00", "throughput": 5828.97, "total_tokens": 6228488} {"current_steps": 9470, "total_steps": 33920, "loss": 0.3671, "lr": 9.053717242970423e-06, "epoch": 5.58372641509434, "percentage": 27.92, "elapsed_time": "0:17:49", "remaining_time": "0:46:00", "throughput": 5829.09, "total_tokens": 6231848} {"current_steps": 9475, "total_steps": 33920, "loss": 0.3815, "lr": 9.052210635401244e-06, "epoch": 5.586674528301887, "percentage": 27.93, "elapsed_time": "0:17:49", "remaining_time": "0:45:59", "throughput": 5829.2, "total_tokens": 6235336} {"current_steps": 9480, "total_steps": 33920, "loss": 0.4658, "lr": 9.050702954991833e-06, "epoch": 5.589622641509434, "percentage": 27.95, "elapsed_time": "0:17:50", "remaining_time": "0:45:59", "throughput": 5829.35, "total_tokens": 6238696} {"current_steps": 9485, "total_steps": 33920, "loss": 0.5575, "lr": 9.049194202141358e-06, "epoch": 5.592570754716981, "percentage": 27.96, "elapsed_time": "0:17:50", "remaining_time": "0:45:58", "throughput": 5829.27, "total_tokens": 6241544} {"current_steps": 9490, "total_steps": 33920, "loss": 0.5996, "lr": 9.047684377249267e-06, "epoch": 5.595518867924528, "percentage": 27.98, "elapsed_time": "0:17:51", "remaining_time": "0:45:57", "throughput": 5829.29, "total_tokens": 6244520} {"current_steps": 9495, "total_steps": 33920, "loss": 0.4497, "lr": 9.046173480715292e-06, "epoch": 5.598466981132075, "percentage": 27.99, "elapsed_time": "0:17:51", "remaining_time": "0:45:57", "throughput": 5829.6, "total_tokens": 6248328} {"current_steps": 9500, "total_steps": 33920, "loss": 0.5418, "lr": 9.044661512939451e-06, "epoch": 5.601415094339623, "percentage": 28.01, "elapsed_time": "0:17:52", "remaining_time": "0:45:56", "throughput": 5830.07, "total_tokens": 6252392} {"current_steps": 9505, "total_steps": 33920, "loss": 0.397, "lr": 9.043148474322043e-06, "epoch": 5.60436320754717, "percentage": 28.02, "elapsed_time": "0:17:52", "remaining_time": "0:45:55", "throughput": 5830.18, "total_tokens": 6255336} {"current_steps": 9510, "total_steps": 33920, "loss": 0.374, "lr": 9.04163436526365e-06, "epoch": 5.607311320754717, "percentage": 28.04, "elapsed_time": "0:17:53", "remaining_time": "0:45:55", "throughput": 5830.02, "total_tokens": 6258088} {"current_steps": 9515, "total_steps": 33920, "loss": 0.4171, "lr": 9.040119186165142e-06, "epoch": 5.6102594339622645, "percentage": 28.05, "elapsed_time": "0:17:53", "remaining_time": "0:45:54", "throughput": 5830.22, "total_tokens": 6261288} {"current_steps": 9520, "total_steps": 33920, "loss": 0.5387, "lr": 9.038602937427665e-06, "epoch": 5.613207547169811, "percentage": 28.07, "elapsed_time": "0:17:54", "remaining_time": "0:45:53", "throughput": 5830.46, "total_tokens": 6264520} {"current_steps": 9525, "total_steps": 33920, "loss": 0.5055, "lr": 9.037085619452658e-06, "epoch": 5.616155660377358, "percentage": 28.08, "elapsed_time": "0:17:54", "remaining_time": "0:45:53", "throughput": 5830.51, "total_tokens": 6267272} {"current_steps": 9530, "total_steps": 33920, "loss": 0.4539, "lr": 9.035567232641833e-06, "epoch": 5.619103773584905, "percentage": 28.1, "elapsed_time": "0:17:55", "remaining_time": "0:45:52", "throughput": 5830.11, "total_tokens": 6269832} {"current_steps": 9535, "total_steps": 33920, "loss": 0.4009, "lr": 9.03404777739719e-06, "epoch": 5.622051886792453, "percentage": 28.11, "elapsed_time": "0:17:55", "remaining_time": "0:45:51", "throughput": 5829.9, "total_tokens": 6272808} {"current_steps": 9540, "total_steps": 33920, "loss": 0.343, "lr": 9.032527254121013e-06, "epoch": 5.625, "percentage": 28.12, "elapsed_time": "0:17:56", "remaining_time": "0:45:51", "throughput": 5830.1, "total_tokens": 6276104} {"current_steps": 9545, "total_steps": 33920, "loss": 0.437, "lr": 9.031005663215867e-06, "epoch": 5.627948113207547, "percentage": 28.14, "elapsed_time": "0:17:57", "remaining_time": "0:45:50", "throughput": 5830.2, "total_tokens": 6279368} {"current_steps": 9550, "total_steps": 33920, "loss": 0.4777, "lr": 9.029483005084595e-06, "epoch": 5.630896226415095, "percentage": 28.15, "elapsed_time": "0:17:57", "remaining_time": "0:45:49", "throughput": 5830.74, "total_tokens": 6283304} {"current_steps": 9555, "total_steps": 33920, "loss": 0.5354, "lr": 9.027959280130337e-06, "epoch": 5.633844339622642, "percentage": 28.17, "elapsed_time": "0:17:58", "remaining_time": "0:45:49", "throughput": 5831.3, "total_tokens": 6288328} {"current_steps": 9560, "total_steps": 33920, "loss": 0.4689, "lr": 9.026434488756496e-06, "epoch": 5.636792452830189, "percentage": 28.18, "elapsed_time": "0:17:58", "remaining_time": "0:45:49", "throughput": 5831.08, "total_tokens": 6291112} {"current_steps": 9565, "total_steps": 33920, "loss": 0.5872, "lr": 9.024908631366774e-06, "epoch": 5.6397405660377355, "percentage": 28.2, "elapsed_time": "0:17:59", "remaining_time": "0:45:48", "throughput": 5830.86, "total_tokens": 6293864} {"current_steps": 9570, "total_steps": 33920, "loss": 0.4576, "lr": 9.023381708365143e-06, "epoch": 5.642688679245283, "percentage": 28.21, "elapsed_time": "0:17:59", "remaining_time": "0:45:47", "throughput": 5830.91, "total_tokens": 6297160} {"current_steps": 9575, "total_steps": 33920, "loss": 0.3747, "lr": 9.021853720155866e-06, "epoch": 5.64563679245283, "percentage": 28.23, "elapsed_time": "0:18:00", "remaining_time": "0:45:47", "throughput": 5830.67, "total_tokens": 6299848} {"current_steps": 9580, "total_steps": 33920, "loss": 0.5638, "lr": 9.020324667143483e-06, "epoch": 5.648584905660377, "percentage": 28.24, "elapsed_time": "0:18:00", "remaining_time": "0:45:46", "throughput": 5830.85, "total_tokens": 6302888} {"current_steps": 9585, "total_steps": 33920, "loss": 0.4595, "lr": 9.018794549732819e-06, "epoch": 5.651533018867925, "percentage": 28.26, "elapsed_time": "0:18:01", "remaining_time": "0:45:45", "throughput": 5830.89, "total_tokens": 6305960} {"current_steps": 9590, "total_steps": 33920, "loss": 0.5312, "lr": 9.017263368328977e-06, "epoch": 5.654481132075472, "percentage": 28.27, "elapsed_time": "0:18:01", "remaining_time": "0:45:45", "throughput": 5830.98, "total_tokens": 6309064} {"current_steps": 9595, "total_steps": 33920, "loss": 0.3853, "lr": 9.015731123337344e-06, "epoch": 5.657429245283019, "percentage": 28.29, "elapsed_time": "0:18:02", "remaining_time": "0:45:44", "throughput": 5830.83, "total_tokens": 6311752} {"current_steps": 9600, "total_steps": 33920, "loss": 0.4249, "lr": 9.01419781516359e-06, "epoch": 5.660377358490566, "percentage": 28.3, "elapsed_time": "0:18:02", "remaining_time": "0:45:43", "throughput": 5830.98, "total_tokens": 6314792} {"current_steps": 9605, "total_steps": 33920, "loss": 0.5654, "lr": 9.012663444213664e-06, "epoch": 5.663325471698113, "percentage": 28.32, "elapsed_time": "0:18:03", "remaining_time": "0:45:42", "throughput": 5830.79, "total_tokens": 6317640} {"current_steps": 9610, "total_steps": 33920, "loss": 0.6115, "lr": 9.011128010893797e-06, "epoch": 5.66627358490566, "percentage": 28.33, "elapsed_time": "0:18:04", "remaining_time": "0:45:43", "throughput": 5831.67, "total_tokens": 6324680} {"current_steps": 9615, "total_steps": 33920, "loss": 0.4357, "lr": 9.009591515610503e-06, "epoch": 5.6692216981132075, "percentage": 28.35, "elapsed_time": "0:18:05", "remaining_time": "0:45:43", "throughput": 5832.18, "total_tokens": 6330152} {"current_steps": 9620, "total_steps": 33920, "loss": 0.3721, "lr": 9.008053958770575e-06, "epoch": 5.672169811320755, "percentage": 28.36, "elapsed_time": "0:18:05", "remaining_time": "0:45:42", "throughput": 5832.39, "total_tokens": 6333192} {"current_steps": 9625, "total_steps": 33920, "loss": 0.4385, "lr": 9.006515340781087e-06, "epoch": 5.675117924528302, "percentage": 28.38, "elapsed_time": "0:18:06", "remaining_time": "0:45:42", "throughput": 5832.37, "total_tokens": 6336520} {"current_steps": 9630, "total_steps": 33920, "loss": 0.5003, "lr": 9.004975662049396e-06, "epoch": 5.678066037735849, "percentage": 28.39, "elapsed_time": "0:18:07", "remaining_time": "0:45:41", "throughput": 5832.63, "total_tokens": 6340584} {"current_steps": 9635, "total_steps": 33920, "loss": 0.477, "lr": 9.003434922983138e-06, "epoch": 5.681014150943396, "percentage": 28.41, "elapsed_time": "0:18:07", "remaining_time": "0:45:41", "throughput": 5833.14, "total_tokens": 6344936} {"current_steps": 9640, "total_steps": 33920, "loss": 0.5499, "lr": 9.00189312399023e-06, "epoch": 5.683962264150943, "percentage": 28.42, "elapsed_time": "0:18:08", "remaining_time": "0:45:41", "throughput": 5833.39, "total_tokens": 6348520} {"current_steps": 9645, "total_steps": 33920, "loss": 0.5078, "lr": 9.00035026547887e-06, "epoch": 5.68691037735849, "percentage": 28.43, "elapsed_time": "0:18:08", "remaining_time": "0:45:40", "throughput": 5833.63, "total_tokens": 6352296} {"current_steps": 9650, "total_steps": 33920, "loss": 0.5538, "lr": 8.998806347857537e-06, "epoch": 5.689858490566038, "percentage": 28.45, "elapsed_time": "0:18:09", "remaining_time": "0:45:39", "throughput": 5833.77, "total_tokens": 6355464} {"current_steps": 9655, "total_steps": 33920, "loss": 0.4835, "lr": 8.99726137153499e-06, "epoch": 5.692806603773585, "percentage": 28.46, "elapsed_time": "0:18:09", "remaining_time": "0:45:39", "throughput": 5833.8, "total_tokens": 6358472} {"current_steps": 9660, "total_steps": 33920, "loss": 0.5481, "lr": 8.995715336920266e-06, "epoch": 5.695754716981132, "percentage": 28.48, "elapsed_time": "0:18:10", "remaining_time": "0:45:39", "throughput": 5834.57, "total_tokens": 6364680} {"current_steps": 9665, "total_steps": 33920, "loss": 0.4963, "lr": 8.994168244422687e-06, "epoch": 5.6987028301886795, "percentage": 28.49, "elapsed_time": "0:18:11", "remaining_time": "0:45:39", "throughput": 5835.25, "total_tokens": 6369256} {"current_steps": 9670, "total_steps": 33920, "loss": 0.3547, "lr": 8.992620094451852e-06, "epoch": 5.701650943396227, "percentage": 28.51, "elapsed_time": "0:18:12", "remaining_time": "0:45:38", "throughput": 5835.33, "total_tokens": 6372712} {"current_steps": 9675, "total_steps": 33920, "loss": 0.3929, "lr": 8.991070887417639e-06, "epoch": 5.704599056603773, "percentage": 28.52, "elapsed_time": "0:18:12", "remaining_time": "0:45:38", "throughput": 5835.56, "total_tokens": 6376616} {"current_steps": 9680, "total_steps": 33920, "loss": 0.4064, "lr": 8.989520623730208e-06, "epoch": 5.7075471698113205, "percentage": 28.54, "elapsed_time": "0:18:13", "remaining_time": "0:45:37", "throughput": 5835.79, "total_tokens": 6379752} {"current_steps": 9685, "total_steps": 33920, "loss": 0.4259, "lr": 8.987969303799998e-06, "epoch": 5.710495283018868, "percentage": 28.55, "elapsed_time": "0:18:13", "remaining_time": "0:45:36", "throughput": 5836.09, "total_tokens": 6383304} {"current_steps": 9690, "total_steps": 33920, "loss": 0.4262, "lr": 8.986416928037728e-06, "epoch": 5.713443396226415, "percentage": 28.57, "elapsed_time": "0:18:14", "remaining_time": "0:45:36", "throughput": 5836.58, "total_tokens": 6387336} {"current_steps": 9695, "total_steps": 33920, "loss": 0.4522, "lr": 8.984863496854395e-06, "epoch": 5.716391509433962, "percentage": 28.58, "elapsed_time": "0:18:14", "remaining_time": "0:45:35", "throughput": 5836.72, "total_tokens": 6390696} {"current_steps": 9700, "total_steps": 33920, "loss": 0.4524, "lr": 8.983309010661279e-06, "epoch": 5.71933962264151, "percentage": 28.6, "elapsed_time": "0:18:15", "remaining_time": "0:45:35", "throughput": 5837.19, "total_tokens": 6394504} {"current_steps": 9705, "total_steps": 33920, "loss": 0.4784, "lr": 8.981753469869934e-06, "epoch": 5.722287735849057, "percentage": 28.61, "elapsed_time": "0:18:16", "remaining_time": "0:45:34", "throughput": 5837.12, "total_tokens": 6397512} {"current_steps": 9710, "total_steps": 33920, "loss": 0.3025, "lr": 8.980196874892198e-06, "epoch": 5.725235849056604, "percentage": 28.63, "elapsed_time": "0:18:16", "remaining_time": "0:45:34", "throughput": 5837.55, "total_tokens": 6401384} {"current_steps": 9715, "total_steps": 33920, "loss": 0.4736, "lr": 8.978639226140184e-06, "epoch": 5.728183962264151, "percentage": 28.64, "elapsed_time": "0:18:17", "remaining_time": "0:45:33", "throughput": 5838.08, "total_tokens": 6405384} {"current_steps": 9720, "total_steps": 33920, "loss": 0.425, "lr": 8.977080524026289e-06, "epoch": 5.731132075471698, "percentage": 28.66, "elapsed_time": "0:18:17", "remaining_time": "0:45:32", "throughput": 5838.1, "total_tokens": 6408488} {"current_steps": 9725, "total_steps": 33920, "loss": 0.5438, "lr": 8.975520768963186e-06, "epoch": 5.734080188679245, "percentage": 28.67, "elapsed_time": "0:18:18", "remaining_time": "0:45:32", "throughput": 5838.43, "total_tokens": 6411944} {"current_steps": 9730, "total_steps": 33920, "loss": 0.4074, "lr": 8.973959961363825e-06, "epoch": 5.7370283018867925, "percentage": 28.69, "elapsed_time": "0:18:18", "remaining_time": "0:45:31", "throughput": 5838.55, "total_tokens": 6415048} {"current_steps": 9735, "total_steps": 33920, "loss": 0.3532, "lr": 8.972398101641438e-06, "epoch": 5.73997641509434, "percentage": 28.7, "elapsed_time": "0:18:19", "remaining_time": "0:45:30", "throughput": 5838.21, "total_tokens": 6417704} {"current_steps": 9740, "total_steps": 33920, "loss": 0.367, "lr": 8.970835190209532e-06, "epoch": 5.742924528301887, "percentage": 28.71, "elapsed_time": "0:18:19", "remaining_time": "0:45:30", "throughput": 5838.88, "total_tokens": 6422344} {"current_steps": 9745, "total_steps": 33920, "loss": 0.5322, "lr": 8.969271227481899e-06, "epoch": 5.745872641509434, "percentage": 28.73, "elapsed_time": "0:18:20", "remaining_time": "0:45:30", "throughput": 5839.06, "total_tokens": 6425736} {"current_steps": 9750, "total_steps": 33920, "loss": 0.472, "lr": 8.967706213872599e-06, "epoch": 5.748820754716981, "percentage": 28.74, "elapsed_time": "0:18:20", "remaining_time": "0:45:29", "throughput": 5839.01, "total_tokens": 6428552} {"current_steps": 9755, "total_steps": 33920, "loss": 0.4041, "lr": 8.966140149795981e-06, "epoch": 5.751768867924528, "percentage": 28.76, "elapsed_time": "0:18:21", "remaining_time": "0:45:28", "throughput": 5839.43, "total_tokens": 6432392} {"current_steps": 9760, "total_steps": 33920, "loss": 0.386, "lr": 8.964573035666663e-06, "epoch": 5.754716981132075, "percentage": 28.77, "elapsed_time": "0:18:22", "remaining_time": "0:45:29", "throughput": 5839.87, "total_tokens": 6438248} {"current_steps": 9765, "total_steps": 33920, "loss": 0.3704, "lr": 8.96300487189955e-06, "epoch": 5.757665094339623, "percentage": 28.79, "elapsed_time": "0:18:22", "remaining_time": "0:45:28", "throughput": 5839.74, "total_tokens": 6441000} {"current_steps": 9770, "total_steps": 33920, "loss": 0.4554, "lr": 8.961435658909816e-06, "epoch": 5.76061320754717, "percentage": 28.8, "elapsed_time": "0:18:23", "remaining_time": "0:45:27", "throughput": 5839.46, "total_tokens": 6443656} {"current_steps": 9775, "total_steps": 33920, "loss": 0.4212, "lr": 8.959865397112918e-06, "epoch": 5.763561320754717, "percentage": 28.82, "elapsed_time": "0:18:23", "remaining_time": "0:45:26", "throughput": 5839.18, "total_tokens": 6446056} {"current_steps": 9780, "total_steps": 33920, "loss": 0.4737, "lr": 8.95829408692459e-06, "epoch": 5.7665094339622645, "percentage": 28.83, "elapsed_time": "0:18:24", "remaining_time": "0:45:26", "throughput": 5839.42, "total_tokens": 6449224} {"current_steps": 9785, "total_steps": 33920, "loss": 0.4873, "lr": 8.956721728760845e-06, "epoch": 5.769457547169811, "percentage": 28.85, "elapsed_time": "0:18:24", "remaining_time": "0:45:25", "throughput": 5839.67, "total_tokens": 6452552} {"current_steps": 9790, "total_steps": 33920, "loss": 0.3992, "lr": 8.95514832303797e-06, "epoch": 5.772405660377358, "percentage": 28.86, "elapsed_time": "0:18:25", "remaining_time": "0:45:24", "throughput": 5839.57, "total_tokens": 6455176} {"current_steps": 9795, "total_steps": 33920, "loss": 0.5534, "lr": 8.953573870172528e-06, "epoch": 5.775353773584905, "percentage": 28.88, "elapsed_time": "0:18:25", "remaining_time": "0:45:23", "throughput": 5839.76, "total_tokens": 6458504} {"current_steps": 9800, "total_steps": 33920, "loss": 0.4223, "lr": 8.951998370581368e-06, "epoch": 5.778301886792453, "percentage": 28.89, "elapsed_time": "0:18:26", "remaining_time": "0:45:23", "throughput": 5839.83, "total_tokens": 6461512} {"current_steps": 9805, "total_steps": 33920, "loss": 0.3319, "lr": 8.950421824681605e-06, "epoch": 5.78125, "percentage": 28.91, "elapsed_time": "0:18:27", "remaining_time": "0:45:23", "throughput": 5840.44, "total_tokens": 6468552} {"current_steps": 9810, "total_steps": 33920, "loss": 0.4411, "lr": 8.948844232890638e-06, "epoch": 5.784198113207547, "percentage": 28.92, "elapsed_time": "0:18:28", "remaining_time": "0:45:23", "throughput": 5840.52, "total_tokens": 6471688} {"current_steps": 9815, "total_steps": 33920, "loss": 0.361, "lr": 8.947265595626144e-06, "epoch": 5.787146226415095, "percentage": 28.94, "elapsed_time": "0:18:28", "remaining_time": "0:45:22", "throughput": 5840.62, "total_tokens": 6474856} {"current_steps": 9820, "total_steps": 33920, "loss": 0.3831, "lr": 8.945685913306071e-06, "epoch": 5.790094339622642, "percentage": 28.95, "elapsed_time": "0:18:29", "remaining_time": "0:45:21", "throughput": 5840.58, "total_tokens": 6477864} {"current_steps": 9825, "total_steps": 33920, "loss": 0.4454, "lr": 8.944105186348646e-06, "epoch": 5.793042452830189, "percentage": 28.97, "elapsed_time": "0:18:29", "remaining_time": "0:45:21", "throughput": 5840.41, "total_tokens": 6480488} {"current_steps": 9830, "total_steps": 33920, "loss": 0.5029, "lr": 8.942523415172377e-06, "epoch": 5.7959905660377355, "percentage": 28.98, "elapsed_time": "0:18:30", "remaining_time": "0:45:20", "throughput": 5840.38, "total_tokens": 6483432} {"current_steps": 9835, "total_steps": 33920, "loss": 0.3422, "lr": 8.94094060019604e-06, "epoch": 5.798938679245283, "percentage": 28.99, "elapsed_time": "0:18:30", "remaining_time": "0:45:19", "throughput": 5840.48, "total_tokens": 6486696} {"current_steps": 9840, "total_steps": 33920, "loss": 0.6325, "lr": 8.939356741838696e-06, "epoch": 5.80188679245283, "percentage": 29.01, "elapsed_time": "0:18:31", "remaining_time": "0:45:19", "throughput": 5840.44, "total_tokens": 6489352} {"current_steps": 9845, "total_steps": 33920, "loss": 0.2936, "lr": 8.937771840519677e-06, "epoch": 5.804834905660377, "percentage": 29.02, "elapsed_time": "0:18:31", "remaining_time": "0:45:18", "throughput": 5840.91, "total_tokens": 6493192} {"current_steps": 9850, "total_steps": 33920, "loss": 0.5337, "lr": 8.936185896658593e-06, "epoch": 5.807783018867925, "percentage": 29.04, "elapsed_time": "0:18:32", "remaining_time": "0:45:17", "throughput": 5841.14, "total_tokens": 6496680} {"current_steps": 9855, "total_steps": 33920, "loss": 0.366, "lr": 8.934598910675329e-06, "epoch": 5.810731132075472, "percentage": 29.05, "elapsed_time": "0:18:32", "remaining_time": "0:45:17", "throughput": 5841.45, "total_tokens": 6500200} {"current_steps": 9860, "total_steps": 33920, "loss": 0.3677, "lr": 8.933010882990044e-06, "epoch": 5.813679245283019, "percentage": 29.07, "elapsed_time": "0:18:33", "remaining_time": "0:45:16", "throughput": 5841.65, "total_tokens": 6503464} {"current_steps": 9865, "total_steps": 33920, "loss": 0.4401, "lr": 8.93142181402318e-06, "epoch": 5.816627358490566, "percentage": 29.08, "elapsed_time": "0:18:33", "remaining_time": "0:45:16", "throughput": 5842.14, "total_tokens": 6507944} {"current_steps": 9870, "total_steps": 33920, "loss": 0.4738, "lr": 8.929831704195445e-06, "epoch": 5.819575471698113, "percentage": 29.1, "elapsed_time": "0:18:34", "remaining_time": "0:45:15", "throughput": 5841.79, "total_tokens": 6510536} {"current_steps": 9875, "total_steps": 33920, "loss": 0.4499, "lr": 8.928240553927831e-06, "epoch": 5.82252358490566, "percentage": 29.11, "elapsed_time": "0:18:35", "remaining_time": "0:45:14", "throughput": 5842.03, "total_tokens": 6513928} {"current_steps": 9880, "total_steps": 33920, "loss": 0.4003, "lr": 8.926648363641602e-06, "epoch": 5.8254716981132075, "percentage": 29.13, "elapsed_time": "0:18:35", "remaining_time": "0:45:14", "throughput": 5841.86, "total_tokens": 6516648} {"current_steps": 9885, "total_steps": 33920, "loss": 0.4671, "lr": 8.925055133758294e-06, "epoch": 5.828419811320755, "percentage": 29.14, "elapsed_time": "0:18:36", "remaining_time": "0:45:13", "throughput": 5842.19, "total_tokens": 6520488} {"current_steps": 9890, "total_steps": 33920, "loss": 0.448, "lr": 8.923460864699723e-06, "epoch": 5.831367924528302, "percentage": 29.16, "elapsed_time": "0:18:36", "remaining_time": "0:45:13", "throughput": 5842.39, "total_tokens": 6524008} {"current_steps": 9895, "total_steps": 33920, "loss": 0.3078, "lr": 8.921865556887979e-06, "epoch": 5.834316037735849, "percentage": 29.17, "elapsed_time": "0:18:37", "remaining_time": "0:45:12", "throughput": 5842.56, "total_tokens": 6527496} {"current_steps": 9900, "total_steps": 33920, "loss": 0.5449, "lr": 8.920269210745426e-06, "epoch": 5.837264150943396, "percentage": 29.19, "elapsed_time": "0:18:37", "remaining_time": "0:45:12", "throughput": 5842.88, "total_tokens": 6531176} {"current_steps": 9905, "total_steps": 33920, "loss": 0.3596, "lr": 8.918671826694704e-06, "epoch": 5.840212264150943, "percentage": 29.2, "elapsed_time": "0:18:38", "remaining_time": "0:45:11", "throughput": 5843.04, "total_tokens": 6534504} {"current_steps": 9910, "total_steps": 33920, "loss": 0.5187, "lr": 8.91707340515873e-06, "epoch": 5.84316037735849, "percentage": 29.22, "elapsed_time": "0:18:38", "remaining_time": "0:45:10", "throughput": 5843.36, "total_tokens": 6538216} {"current_steps": 9915, "total_steps": 33920, "loss": 0.4976, "lr": 8.915473946560688e-06, "epoch": 5.846108490566038, "percentage": 29.23, "elapsed_time": "0:18:39", "remaining_time": "0:45:10", "throughput": 5843.57, "total_tokens": 6541288} {"current_steps": 9920, "total_steps": 33920, "loss": 0.501, "lr": 8.913873451324044e-06, "epoch": 5.849056603773585, "percentage": 29.25, "elapsed_time": "0:18:39", "remaining_time": "0:45:09", "throughput": 5844.01, "total_tokens": 6545224} {"current_steps": 9925, "total_steps": 33920, "loss": 0.4198, "lr": 8.912271919872538e-06, "epoch": 5.852004716981132, "percentage": 29.26, "elapsed_time": "0:18:40", "remaining_time": "0:45:09", "throughput": 5844.49, "total_tokens": 6549896} {"current_steps": 9930, "total_steps": 33920, "loss": 0.4207, "lr": 8.910669352630176e-06, "epoch": 5.8549528301886795, "percentage": 29.27, "elapsed_time": "0:18:41", "remaining_time": "0:45:08", "throughput": 5844.56, "total_tokens": 6552872} {"current_steps": 9935, "total_steps": 33920, "loss": 0.3752, "lr": 8.909065750021253e-06, "epoch": 5.857900943396227, "percentage": 29.29, "elapsed_time": "0:18:41", "remaining_time": "0:45:07", "throughput": 5844.69, "total_tokens": 6555752} {"current_steps": 9940, "total_steps": 33920, "loss": 0.4117, "lr": 8.907461112470323e-06, "epoch": 5.860849056603773, "percentage": 29.3, "elapsed_time": "0:18:42", "remaining_time": "0:45:07", "throughput": 5844.96, "total_tokens": 6559496} {"current_steps": 9945, "total_steps": 33920, "loss": 0.3881, "lr": 8.905855440402225e-06, "epoch": 5.8637971698113205, "percentage": 29.32, "elapsed_time": "0:18:42", "remaining_time": "0:45:06", "throughput": 5844.52, "total_tokens": 6561768} {"current_steps": 9950, "total_steps": 33920, "loss": 0.3801, "lr": 8.904248734242065e-06, "epoch": 5.866745283018868, "percentage": 29.33, "elapsed_time": "0:18:43", "remaining_time": "0:45:06", "throughput": 5844.75, "total_tokens": 6565416} {"current_steps": 9955, "total_steps": 33920, "loss": 0.4401, "lr": 8.902640994415226e-06, "epoch": 5.869693396226415, "percentage": 29.35, "elapsed_time": "0:18:43", "remaining_time": "0:45:05", "throughput": 5844.81, "total_tokens": 6568584} {"current_steps": 9960, "total_steps": 33920, "loss": 0.3571, "lr": 8.901032221347364e-06, "epoch": 5.872641509433962, "percentage": 29.36, "elapsed_time": "0:18:44", "remaining_time": "0:45:05", "throughput": 5845.14, "total_tokens": 6572776} {"current_steps": 9965, "total_steps": 33920, "loss": 0.5938, "lr": 8.899422415464409e-06, "epoch": 5.87558962264151, "percentage": 29.38, "elapsed_time": "0:18:44", "remaining_time": "0:45:04", "throughput": 5844.97, "total_tokens": 6575368} {"current_steps": 9970, "total_steps": 33920, "loss": 0.3076, "lr": 8.897811577192565e-06, "epoch": 5.878537735849057, "percentage": 29.39, "elapsed_time": "0:18:45", "remaining_time": "0:45:03", "throughput": 5845.46, "total_tokens": 6579688} {"current_steps": 9975, "total_steps": 33920, "loss": 0.4899, "lr": 8.896199706958306e-06, "epoch": 5.881485849056604, "percentage": 29.41, "elapsed_time": "0:18:46", "remaining_time": "0:45:03", "throughput": 5845.83, "total_tokens": 6583368} {"current_steps": 9980, "total_steps": 33920, "loss": 0.4177, "lr": 8.894586805188384e-06, "epoch": 5.884433962264151, "percentage": 29.42, "elapsed_time": "0:18:46", "remaining_time": "0:45:02", "throughput": 5846.28, "total_tokens": 6587336} {"current_steps": 9985, "total_steps": 33920, "loss": 0.4969, "lr": 8.892972872309821e-06, "epoch": 5.887382075471698, "percentage": 29.44, "elapsed_time": "0:18:47", "remaining_time": "0:45:02", "throughput": 5846.65, "total_tokens": 6591112} {"current_steps": 9990, "total_steps": 33920, "loss": 0.5387, "lr": 8.89135790874991e-06, "epoch": 5.890330188679245, "percentage": 29.45, "elapsed_time": "0:18:47", "remaining_time": "0:45:01", "throughput": 5847.05, "total_tokens": 6594760} {"current_steps": 9995, "total_steps": 33920, "loss": 0.462, "lr": 8.889741914936224e-06, "epoch": 5.8932783018867925, "percentage": 29.47, "elapsed_time": "0:18:48", "remaining_time": "0:45:01", "throughput": 5846.91, "total_tokens": 6597576} {"current_steps": 10000, "total_steps": 33920, "loss": 0.3631, "lr": 8.888124891296602e-06, "epoch": 5.89622641509434, "percentage": 29.48, "elapsed_time": "0:18:48", "remaining_time": "0:45:00", "throughput": 5847.01, "total_tokens": 6600776} {"current_steps": 10005, "total_steps": 33920, "loss": 0.4111, "lr": 8.886506838259156e-06, "epoch": 5.899174528301887, "percentage": 29.5, "elapsed_time": "0:18:49", "remaining_time": "0:44:59", "throughput": 5847.12, "total_tokens": 6603816} {"current_steps": 10010, "total_steps": 33920, "loss": 0.3319, "lr": 8.884887756252279e-06, "epoch": 5.902122641509434, "percentage": 29.51, "elapsed_time": "0:18:50", "remaining_time": "0:44:59", "throughput": 5847.58, "total_tokens": 6608040} {"current_steps": 10015, "total_steps": 33920, "loss": 0.4116, "lr": 8.88326764570462e-06, "epoch": 5.905070754716981, "percentage": 29.53, "elapsed_time": "0:18:50", "remaining_time": "0:44:58", "throughput": 5847.77, "total_tokens": 6611144} {"current_steps": 10020, "total_steps": 33920, "loss": 0.5005, "lr": 8.88164650704512e-06, "epoch": 5.908018867924528, "percentage": 29.54, "elapsed_time": "0:18:51", "remaining_time": "0:44:57", "throughput": 5847.91, "total_tokens": 6614408} {"current_steps": 10025, "total_steps": 33920, "loss": 0.4707, "lr": 8.880024340702978e-06, "epoch": 5.910966981132075, "percentage": 29.55, "elapsed_time": "0:18:51", "remaining_time": "0:44:57", "throughput": 5848.13, "total_tokens": 6617864} {"current_steps": 10030, "total_steps": 33920, "loss": 0.3569, "lr": 8.878401147107667e-06, "epoch": 5.913915094339623, "percentage": 29.57, "elapsed_time": "0:18:52", "remaining_time": "0:44:56", "throughput": 5847.89, "total_tokens": 6620200} {"current_steps": 10035, "total_steps": 33920, "loss": 0.2809, "lr": 8.87677692668894e-06, "epoch": 5.91686320754717, "percentage": 29.58, "elapsed_time": "0:18:52", "remaining_time": "0:44:55", "throughput": 5848.01, "total_tokens": 6623240} {"current_steps": 10040, "total_steps": 33920, "loss": 0.445, "lr": 8.875151679876813e-06, "epoch": 5.919811320754717, "percentage": 29.6, "elapsed_time": "0:18:53", "remaining_time": "0:44:55", "throughput": 5848.22, "total_tokens": 6626760} {"current_steps": 10045, "total_steps": 33920, "loss": 0.4078, "lr": 8.873525407101577e-06, "epoch": 5.9227594339622645, "percentage": 29.61, "elapsed_time": "0:18:53", "remaining_time": "0:44:54", "throughput": 5848.05, "total_tokens": 6629288} {"current_steps": 10050, "total_steps": 33920, "loss": 0.3865, "lr": 8.871898108793796e-06, "epoch": 5.925707547169811, "percentage": 29.63, "elapsed_time": "0:18:54", "remaining_time": "0:44:53", "throughput": 5848.53, "total_tokens": 6633672} {"current_steps": 10055, "total_steps": 33920, "loss": 0.6145, "lr": 8.870269785384304e-06, "epoch": 5.928655660377358, "percentage": 29.64, "elapsed_time": "0:18:54", "remaining_time": "0:44:53", "throughput": 5848.53, "total_tokens": 6636360} {"current_steps": 10060, "total_steps": 33920, "loss": 0.4413, "lr": 8.868640437304206e-06, "epoch": 5.931603773584905, "percentage": 29.66, "elapsed_time": "0:18:55", "remaining_time": "0:44:52", "throughput": 5848.22, "total_tokens": 6638920} {"current_steps": 10065, "total_steps": 33920, "loss": 0.2583, "lr": 8.86701006498488e-06, "epoch": 5.934551886792453, "percentage": 29.67, "elapsed_time": "0:18:55", "remaining_time": "0:44:51", "throughput": 5848.47, "total_tokens": 6642376} {"current_steps": 10070, "total_steps": 33920, "loss": 0.4842, "lr": 8.865378668857972e-06, "epoch": 5.9375, "percentage": 29.69, "elapsed_time": "0:18:56", "remaining_time": "0:44:51", "throughput": 5847.74, "total_tokens": 6644424} {"current_steps": 10075, "total_steps": 33920, "loss": 0.515, "lr": 8.863746249355404e-06, "epoch": 5.940448113207547, "percentage": 29.7, "elapsed_time": "0:18:56", "remaining_time": "0:44:50", "throughput": 5847.6, "total_tokens": 6647048} {"current_steps": 10080, "total_steps": 33920, "loss": 0.5031, "lr": 8.862112806909365e-06, "epoch": 5.943396226415095, "percentage": 29.72, "elapsed_time": "0:18:57", "remaining_time": "0:44:49", "throughput": 5847.48, "total_tokens": 6649736} {"current_steps": 10085, "total_steps": 33920, "loss": 0.4718, "lr": 8.860478341952314e-06, "epoch": 5.946344339622642, "percentage": 29.73, "elapsed_time": "0:18:57", "remaining_time": "0:44:48", "throughput": 5847.45, "total_tokens": 6652424} {"current_steps": 10090, "total_steps": 33920, "loss": 0.3692, "lr": 8.858842854916985e-06, "epoch": 5.949292452830189, "percentage": 29.75, "elapsed_time": "0:18:58", "remaining_time": "0:44:48", "throughput": 5847.55, "total_tokens": 6655496} {"current_steps": 10095, "total_steps": 33920, "loss": 0.5314, "lr": 8.85720634623638e-06, "epoch": 5.9522405660377355, "percentage": 29.76, "elapsed_time": "0:18:58", "remaining_time": "0:44:47", "throughput": 5847.72, "total_tokens": 6658856} {"current_steps": 10100, "total_steps": 33920, "loss": 0.2991, "lr": 8.855568816343769e-06, "epoch": 5.955188679245283, "percentage": 29.78, "elapsed_time": "0:18:59", "remaining_time": "0:44:46", "throughput": 5848.1, "total_tokens": 6662376} {"current_steps": 10105, "total_steps": 33920, "loss": 0.4345, "lr": 8.8539302656727e-06, "epoch": 5.95813679245283, "percentage": 29.79, "elapsed_time": "0:18:59", "remaining_time": "0:44:46", "throughput": 5848.39, "total_tokens": 6665768} {"current_steps": 10110, "total_steps": 33920, "loss": 0.4517, "lr": 8.852290694656983e-06, "epoch": 5.961084905660377, "percentage": 29.81, "elapsed_time": "0:19:00", "remaining_time": "0:44:45", "throughput": 5848.98, "total_tokens": 6669832} {"current_steps": 10115, "total_steps": 33920, "loss": 0.4761, "lr": 8.8506501037307e-06, "epoch": 5.964033018867925, "percentage": 29.82, "elapsed_time": "0:19:00", "remaining_time": "0:44:45", "throughput": 5849.37, "total_tokens": 6673608} {"current_steps": 10120, "total_steps": 33920, "loss": 0.6811, "lr": 8.849008493328209e-06, "epoch": 5.966981132075472, "percentage": 29.83, "elapsed_time": "0:19:01", "remaining_time": "0:44:44", "throughput": 5849.82, "total_tokens": 6677544} {"current_steps": 10125, "total_steps": 33920, "loss": 0.4753, "lr": 8.847365863884131e-06, "epoch": 5.969929245283019, "percentage": 29.85, "elapsed_time": "0:19:01", "remaining_time": "0:44:43", "throughput": 5850.03, "total_tokens": 6680680} {"current_steps": 10130, "total_steps": 33920, "loss": 0.405, "lr": 8.845722215833359e-06, "epoch": 5.972877358490566, "percentage": 29.86, "elapsed_time": "0:19:02", "remaining_time": "0:44:43", "throughput": 5850.2, "total_tokens": 6683752} {"current_steps": 10135, "total_steps": 33920, "loss": 0.4319, "lr": 8.844077549611056e-06, "epoch": 5.975825471698113, "percentage": 29.88, "elapsed_time": "0:19:02", "remaining_time": "0:44:42", "throughput": 5849.82, "total_tokens": 6686184} {"current_steps": 10140, "total_steps": 33920, "loss": 0.4206, "lr": 8.842431865652654e-06, "epoch": 5.97877358490566, "percentage": 29.89, "elapsed_time": "0:19:03", "remaining_time": "0:44:41", "throughput": 5850.05, "total_tokens": 6689928} {"current_steps": 10145, "total_steps": 33920, "loss": 0.5223, "lr": 8.840785164393858e-06, "epoch": 5.9817216981132075, "percentage": 29.91, "elapsed_time": "0:19:04", "remaining_time": "0:44:41", "throughput": 5850.17, "total_tokens": 6693032} {"current_steps": 10150, "total_steps": 33920, "loss": 0.6188, "lr": 8.839137446270634e-06, "epoch": 5.984669811320755, "percentage": 29.92, "elapsed_time": "0:19:04", "remaining_time": "0:44:40", "throughput": 5849.77, "total_tokens": 6695304} {"current_steps": 10155, "total_steps": 33920, "loss": 0.5571, "lr": 8.837488711719226e-06, "epoch": 5.987617924528302, "percentage": 29.94, "elapsed_time": "0:19:05", "remaining_time": "0:44:39", "throughput": 5849.86, "total_tokens": 6698280} {"current_steps": 10160, "total_steps": 33920, "loss": 0.3638, "lr": 8.835838961176143e-06, "epoch": 5.990566037735849, "percentage": 29.95, "elapsed_time": "0:19:05", "remaining_time": "0:44:39", "throughput": 5850.21, "total_tokens": 6701928} {"current_steps": 10165, "total_steps": 33920, "loss": 0.4256, "lr": 8.834188195078164e-06, "epoch": 5.993514150943396, "percentage": 29.97, "elapsed_time": "0:19:06", "remaining_time": "0:44:38", "throughput": 5850.72, "total_tokens": 6706088} {"current_steps": 10170, "total_steps": 33920, "loss": 0.3445, "lr": 8.832536413862337e-06, "epoch": 5.996462264150943, "percentage": 29.98, "elapsed_time": "0:19:06", "remaining_time": "0:44:37", "throughput": 5850.68, "total_tokens": 6709128} {"current_steps": 10175, "total_steps": 33920, "loss": 0.6057, "lr": 8.830883617965976e-06, "epoch": 5.99941037735849, "percentage": 30.0, "elapsed_time": "0:19:07", "remaining_time": "0:44:37", "throughput": 5850.88, "total_tokens": 6712264} {"current_steps": 10176, "total_steps": 33920, "eval_loss": 0.4917214512825012, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:19:25", "remaining_time": "0:45:20", "throughput": 5757.72, "total_tokens": 6712376} {"current_steps": 10180, "total_steps": 33920, "loss": 0.3546, "lr": 8.829229807826665e-06, "epoch": 6.002358490566038, "percentage": 30.01, "elapsed_time": "0:19:29", "remaining_time": "0:45:27", "throughput": 5741.33, "total_tokens": 6714904} {"current_steps": 10185, "total_steps": 33920, "loss": 0.3122, "lr": 8.82757498388226e-06, "epoch": 6.005306603773585, "percentage": 30.03, "elapsed_time": "0:19:30", "remaining_time": "0:45:26", "throughput": 5741.8, "total_tokens": 6718680} {"current_steps": 10190, "total_steps": 33920, "loss": 0.2737, "lr": 8.825919146570884e-06, "epoch": 6.008254716981132, "percentage": 30.04, "elapsed_time": "0:19:30", "remaining_time": "0:45:26", "throughput": 5741.86, "total_tokens": 6721688} {"current_steps": 10195, "total_steps": 33920, "loss": 0.4707, "lr": 8.824262296330925e-06, "epoch": 6.0112028301886795, "percentage": 30.06, "elapsed_time": "0:19:31", "remaining_time": "0:45:25", "throughput": 5741.9, "total_tokens": 6724888} {"current_steps": 10200, "total_steps": 33920, "loss": 0.4338, "lr": 8.822604433601041e-06, "epoch": 6.014150943396227, "percentage": 30.07, "elapsed_time": "0:19:31", "remaining_time": "0:45:24", "throughput": 5741.87, "total_tokens": 6727736} {"current_steps": 10205, "total_steps": 33920, "loss": 0.2976, "lr": 8.820945558820158e-06, "epoch": 6.017099056603773, "percentage": 30.09, "elapsed_time": "0:19:32", "remaining_time": "0:45:24", "throughput": 5742.27, "total_tokens": 6731352} {"current_steps": 10210, "total_steps": 33920, "loss": 0.5263, "lr": 8.81928567242747e-06, "epoch": 6.0200471698113205, "percentage": 30.1, "elapsed_time": "0:19:32", "remaining_time": "0:45:23", "throughput": 5742.2, "total_tokens": 6734136} {"current_steps": 10215, "total_steps": 33920, "loss": 0.3116, "lr": 8.817624774862443e-06, "epoch": 6.022995283018868, "percentage": 30.11, "elapsed_time": "0:19:33", "remaining_time": "0:45:22", "throughput": 5742.27, "total_tokens": 6736952} {"current_steps": 10220, "total_steps": 33920, "loss": 0.4562, "lr": 8.815962866564803e-06, "epoch": 6.025943396226415, "percentage": 30.13, "elapsed_time": "0:19:33", "remaining_time": "0:45:21", "throughput": 5742.22, "total_tokens": 6740024} {"current_steps": 10225, "total_steps": 33920, "loss": 0.5364, "lr": 8.814299947974547e-06, "epoch": 6.028891509433962, "percentage": 30.14, "elapsed_time": "0:19:34", "remaining_time": "0:45:21", "throughput": 5742.23, "total_tokens": 6742616} {"current_steps": 10230, "total_steps": 33920, "loss": 0.4198, "lr": 8.812636019531942e-06, "epoch": 6.03183962264151, "percentage": 30.16, "elapsed_time": "0:19:34", "remaining_time": "0:45:20", "throughput": 5742.26, "total_tokens": 6745336} {"current_steps": 10235, "total_steps": 33920, "loss": 0.4909, "lr": 8.810971081677517e-06, "epoch": 6.034787735849057, "percentage": 30.17, "elapsed_time": "0:19:35", "remaining_time": "0:45:19", "throughput": 5742.64, "total_tokens": 6748856} {"current_steps": 10240, "total_steps": 33920, "loss": 0.4479, "lr": 8.809305134852076e-06, "epoch": 6.037735849056604, "percentage": 30.19, "elapsed_time": "0:19:35", "remaining_time": "0:45:18", "throughput": 5742.62, "total_tokens": 6751768} {"current_steps": 10245, "total_steps": 33920, "loss": 0.3877, "lr": 8.807638179496684e-06, "epoch": 6.040683962264151, "percentage": 30.2, "elapsed_time": "0:19:36", "remaining_time": "0:45:18", "throughput": 5742.96, "total_tokens": 6755160} {"current_steps": 10250, "total_steps": 33920, "loss": 0.3035, "lr": 8.805970216052673e-06, "epoch": 6.043632075471698, "percentage": 30.22, "elapsed_time": "0:19:36", "remaining_time": "0:45:17", "throughput": 5743.07, "total_tokens": 6758040} {"current_steps": 10255, "total_steps": 33920, "loss": 0.422, "lr": 8.804301244961645e-06, "epoch": 6.046580188679245, "percentage": 30.23, "elapsed_time": "0:19:37", "remaining_time": "0:45:16", "throughput": 5742.91, "total_tokens": 6760440} {"current_steps": 10260, "total_steps": 33920, "loss": 0.4337, "lr": 8.802631266665465e-06, "epoch": 6.0495283018867925, "percentage": 30.25, "elapsed_time": "0:19:38", "remaining_time": "0:45:16", "throughput": 5743.41, "total_tokens": 6766232} {"current_steps": 10265, "total_steps": 33920, "loss": 0.4287, "lr": 8.80096028160627e-06, "epoch": 6.05247641509434, "percentage": 30.26, "elapsed_time": "0:19:38", "remaining_time": "0:45:16", "throughput": 5743.83, "total_tokens": 6770232} {"current_steps": 10270, "total_steps": 33920, "loss": 0.3458, "lr": 8.799288290226457e-06, "epoch": 6.055424528301887, "percentage": 30.28, "elapsed_time": "0:19:39", "remaining_time": "0:45:15", "throughput": 5743.99, "total_tokens": 6773240} {"current_steps": 10275, "total_steps": 33920, "loss": 0.5066, "lr": 8.797615292968698e-06, "epoch": 6.058372641509434, "percentage": 30.29, "elapsed_time": "0:19:39", "remaining_time": "0:45:14", "throughput": 5744.3, "total_tokens": 6776600} {"current_steps": 10280, "total_steps": 33920, "loss": 0.5154, "lr": 8.795941290275923e-06, "epoch": 6.061320754716981, "percentage": 30.31, "elapsed_time": "0:19:40", "remaining_time": "0:45:14", "throughput": 5744.59, "total_tokens": 6779896} {"current_steps": 10285, "total_steps": 33920, "loss": 0.5529, "lr": 8.79426628259133e-06, "epoch": 6.064268867924528, "percentage": 30.32, "elapsed_time": "0:19:40", "remaining_time": "0:45:13", "throughput": 5744.6, "total_tokens": 6782552} {"current_steps": 10290, "total_steps": 33920, "loss": 0.527, "lr": 8.792590270358389e-06, "epoch": 6.067216981132075, "percentage": 30.34, "elapsed_time": "0:19:41", "remaining_time": "0:45:12", "throughput": 5744.77, "total_tokens": 6785624} {"current_steps": 10295, "total_steps": 33920, "loss": 0.4358, "lr": 8.790913254020827e-06, "epoch": 6.070165094339623, "percentage": 30.35, "elapsed_time": "0:19:41", "remaining_time": "0:45:11", "throughput": 5744.99, "total_tokens": 6789112} {"current_steps": 10300, "total_steps": 33920, "loss": 0.3886, "lr": 8.789235234022643e-06, "epoch": 6.07311320754717, "percentage": 30.37, "elapsed_time": "0:19:42", "remaining_time": "0:45:11", "throughput": 5745.54, "total_tokens": 6793688} {"current_steps": 10305, "total_steps": 33920, "loss": 0.4007, "lr": 8.787556210808101e-06, "epoch": 6.076061320754717, "percentage": 30.38, "elapsed_time": "0:19:43", "remaining_time": "0:45:11", "throughput": 5746.0, "total_tokens": 6797624} {"current_steps": 10310, "total_steps": 33920, "loss": 0.3217, "lr": 8.78587618482173e-06, "epoch": 6.0790094339622645, "percentage": 30.4, "elapsed_time": "0:19:43", "remaining_time": "0:45:10", "throughput": 5745.51, "total_tokens": 6799896} {"current_steps": 10315, "total_steps": 33920, "loss": 0.4801, "lr": 8.78419515650832e-06, "epoch": 6.081957547169812, "percentage": 30.41, "elapsed_time": "0:19:44", "remaining_time": "0:45:09", "throughput": 5745.89, "total_tokens": 6803416} {"current_steps": 10320, "total_steps": 33920, "loss": 0.4218, "lr": 8.782513126312934e-06, "epoch": 6.084905660377358, "percentage": 30.42, "elapsed_time": "0:19:44", "remaining_time": "0:45:08", "throughput": 5746.39, "total_tokens": 6807192} {"current_steps": 10325, "total_steps": 33920, "loss": 0.467, "lr": 8.780830094680897e-06, "epoch": 6.087853773584905, "percentage": 30.44, "elapsed_time": "0:19:45", "remaining_time": "0:45:08", "throughput": 5746.71, "total_tokens": 6810744} {"current_steps": 10330, "total_steps": 33920, "loss": 0.4842, "lr": 8.779146062057797e-06, "epoch": 6.090801886792453, "percentage": 30.45, "elapsed_time": "0:19:45", "remaining_time": "0:45:07", "throughput": 5747.08, "total_tokens": 6814200} {"current_steps": 10335, "total_steps": 33920, "loss": 0.4476, "lr": 8.777461028889492e-06, "epoch": 6.09375, "percentage": 30.47, "elapsed_time": "0:19:46", "remaining_time": "0:45:06", "throughput": 5747.07, "total_tokens": 6816824} {"current_steps": 10340, "total_steps": 33920, "loss": 0.5366, "lr": 8.775774995622097e-06, "epoch": 6.096698113207547, "percentage": 30.48, "elapsed_time": "0:19:46", "remaining_time": "0:45:06", "throughput": 5747.13, "total_tokens": 6819864} {"current_steps": 10345, "total_steps": 33920, "loss": 0.4101, "lr": 8.774087962702e-06, "epoch": 6.099646226415095, "percentage": 30.5, "elapsed_time": "0:19:47", "remaining_time": "0:45:06", "throughput": 5747.81, "total_tokens": 6825688} {"current_steps": 10350, "total_steps": 33920, "loss": 0.4961, "lr": 8.772399930575849e-06, "epoch": 6.102594339622642, "percentage": 30.51, "elapsed_time": "0:19:48", "remaining_time": "0:45:05", "throughput": 5747.77, "total_tokens": 6828440} {"current_steps": 10355, "total_steps": 33920, "loss": 0.3896, "lr": 8.77071089969056e-06, "epoch": 6.105542452830188, "percentage": 30.53, "elapsed_time": "0:19:48", "remaining_time": "0:45:04", "throughput": 5748.15, "total_tokens": 6831736} {"current_steps": 10360, "total_steps": 33920, "loss": 0.4842, "lr": 8.769020870493309e-06, "epoch": 6.1084905660377355, "percentage": 30.54, "elapsed_time": "0:19:49", "remaining_time": "0:45:04", "throughput": 5748.37, "total_tokens": 6835128} {"current_steps": 10365, "total_steps": 33920, "loss": 0.3925, "lr": 8.767329843431537e-06, "epoch": 6.111438679245283, "percentage": 30.56, "elapsed_time": "0:19:49", "remaining_time": "0:45:03", "throughput": 5748.76, "total_tokens": 6838936} {"current_steps": 10370, "total_steps": 33920, "loss": 0.4446, "lr": 8.765637818952954e-06, "epoch": 6.11438679245283, "percentage": 30.57, "elapsed_time": "0:19:50", "remaining_time": "0:45:03", "throughput": 5749.25, "total_tokens": 6843288} {"current_steps": 10375, "total_steps": 33920, "loss": 0.3959, "lr": 8.76394479750553e-06, "epoch": 6.117334905660377, "percentage": 30.59, "elapsed_time": "0:19:50", "remaining_time": "0:45:02", "throughput": 5749.36, "total_tokens": 6846392} {"current_steps": 10380, "total_steps": 33920, "loss": 0.5094, "lr": 8.762250779537499e-06, "epoch": 6.120283018867925, "percentage": 30.6, "elapsed_time": "0:19:51", "remaining_time": "0:45:01", "throughput": 5749.45, "total_tokens": 6849784} {"current_steps": 10385, "total_steps": 33920, "loss": 0.422, "lr": 8.760555765497358e-06, "epoch": 6.123231132075472, "percentage": 30.62, "elapsed_time": "0:19:51", "remaining_time": "0:45:01", "throughput": 5749.68, "total_tokens": 6853048} {"current_steps": 10390, "total_steps": 33920, "loss": 0.5775, "lr": 8.758859755833873e-06, "epoch": 6.126179245283019, "percentage": 30.63, "elapsed_time": "0:19:52", "remaining_time": "0:45:00", "throughput": 5749.56, "total_tokens": 6855832} {"current_steps": 10395, "total_steps": 33920, "loss": 0.377, "lr": 8.757162750996066e-06, "epoch": 6.129127358490566, "percentage": 30.65, "elapsed_time": "0:19:52", "remaining_time": "0:44:59", "throughput": 5749.69, "total_tokens": 6859320} {"current_steps": 10400, "total_steps": 33920, "loss": 0.4393, "lr": 8.755464751433229e-06, "epoch": 6.132075471698113, "percentage": 30.66, "elapsed_time": "0:19:53", "remaining_time": "0:44:59", "throughput": 5749.7, "total_tokens": 6862264} {"current_steps": 10405, "total_steps": 33920, "loss": 0.4472, "lr": 8.753765757594915e-06, "epoch": 6.13502358490566, "percentage": 30.68, "elapsed_time": "0:19:54", "remaining_time": "0:44:58", "throughput": 5749.53, "total_tokens": 6865112} {"current_steps": 10410, "total_steps": 33920, "loss": 0.472, "lr": 8.752065769930938e-06, "epoch": 6.1379716981132075, "percentage": 30.69, "elapsed_time": "0:19:54", "remaining_time": "0:44:57", "throughput": 5749.55, "total_tokens": 6867992} {"current_steps": 10415, "total_steps": 33920, "loss": 0.3743, "lr": 8.75036478889138e-06, "epoch": 6.140919811320755, "percentage": 30.7, "elapsed_time": "0:19:55", "remaining_time": "0:44:57", "throughput": 5750.32, "total_tokens": 6872856} {"current_steps": 10420, "total_steps": 33920, "loss": 0.5279, "lr": 8.748662814926576e-06, "epoch": 6.143867924528302, "percentage": 30.72, "elapsed_time": "0:19:55", "remaining_time": "0:44:56", "throughput": 5750.45, "total_tokens": 6875832} {"current_steps": 10425, "total_steps": 33920, "loss": 0.3651, "lr": 8.746959848487139e-06, "epoch": 6.146816037735849, "percentage": 30.73, "elapsed_time": "0:19:56", "remaining_time": "0:44:55", "throughput": 5750.52, "total_tokens": 6878968} {"current_steps": 10430, "total_steps": 33920, "loss": 0.4598, "lr": 8.745255890023934e-06, "epoch": 6.149764150943396, "percentage": 30.75, "elapsed_time": "0:19:56", "remaining_time": "0:44:55", "throughput": 5750.19, "total_tokens": 6881272} {"current_steps": 10435, "total_steps": 33920, "loss": 0.3769, "lr": 8.74355093998809e-06, "epoch": 6.152712264150943, "percentage": 30.76, "elapsed_time": "0:19:57", "remaining_time": "0:44:54", "throughput": 5750.47, "total_tokens": 6884568} {"current_steps": 10440, "total_steps": 33920, "loss": 0.4119, "lr": 8.741844998831001e-06, "epoch": 6.15566037735849, "percentage": 30.78, "elapsed_time": "0:19:57", "remaining_time": "0:44:53", "throughput": 5750.42, "total_tokens": 6887384} {"current_steps": 10445, "total_steps": 33920, "loss": 0.6006, "lr": 8.740138067004323e-06, "epoch": 6.158608490566038, "percentage": 30.79, "elapsed_time": "0:19:58", "remaining_time": "0:44:52", "throughput": 5750.41, "total_tokens": 6890040} {"current_steps": 10450, "total_steps": 33920, "loss": 0.4364, "lr": 8.738430144959973e-06, "epoch": 6.161556603773585, "percentage": 30.81, "elapsed_time": "0:19:58", "remaining_time": "0:44:52", "throughput": 5750.29, "total_tokens": 6892504} {"current_steps": 10455, "total_steps": 33920, "loss": 0.4951, "lr": 8.73672123315013e-06, "epoch": 6.164504716981132, "percentage": 30.82, "elapsed_time": "0:19:59", "remaining_time": "0:44:51", "throughput": 5750.67, "total_tokens": 6896312} {"current_steps": 10460, "total_steps": 33920, "loss": 0.4711, "lr": 8.735011332027234e-06, "epoch": 6.1674528301886795, "percentage": 30.84, "elapsed_time": "0:19:59", "remaining_time": "0:44:50", "throughput": 5750.43, "total_tokens": 6898968} {"current_steps": 10465, "total_steps": 33920, "loss": 0.3913, "lr": 8.733300442043993e-06, "epoch": 6.170400943396227, "percentage": 30.85, "elapsed_time": "0:20:00", "remaining_time": "0:44:50", "throughput": 5751.0, "total_tokens": 6903512} {"current_steps": 10470, "total_steps": 33920, "loss": 0.4078, "lr": 8.73158856365337e-06, "epoch": 6.173349056603773, "percentage": 30.87, "elapsed_time": "0:20:00", "remaining_time": "0:44:49", "throughput": 5751.16, "total_tokens": 6906552} {"current_steps": 10475, "total_steps": 33920, "loss": 0.3746, "lr": 8.729875697308592e-06, "epoch": 6.1762971698113205, "percentage": 30.88, "elapsed_time": "0:20:01", "remaining_time": "0:44:48", "throughput": 5750.96, "total_tokens": 6908888} {"current_steps": 10480, "total_steps": 33920, "loss": 0.3597, "lr": 8.728161843463148e-06, "epoch": 6.179245283018868, "percentage": 30.9, "elapsed_time": "0:20:01", "remaining_time": "0:44:48", "throughput": 5751.08, "total_tokens": 6912056} {"current_steps": 10485, "total_steps": 33920, "loss": 0.4361, "lr": 8.726447002570791e-06, "epoch": 6.182193396226415, "percentage": 30.91, "elapsed_time": "0:20:02", "remaining_time": "0:44:47", "throughput": 5751.26, "total_tokens": 6915480} {"current_steps": 10490, "total_steps": 33920, "loss": 0.3809, "lr": 8.724731175085526e-06, "epoch": 6.185141509433962, "percentage": 30.93, "elapsed_time": "0:20:02", "remaining_time": "0:44:46", "throughput": 5751.34, "total_tokens": 6918200} {"current_steps": 10495, "total_steps": 33920, "loss": 0.4802, "lr": 8.723014361461633e-06, "epoch": 6.18808962264151, "percentage": 30.94, "elapsed_time": "0:20:03", "remaining_time": "0:44:46", "throughput": 5751.85, "total_tokens": 6922360} {"current_steps": 10500, "total_steps": 33920, "loss": 0.5085, "lr": 8.72129656215364e-06, "epoch": 6.191037735849057, "percentage": 30.96, "elapsed_time": "0:20:04", "remaining_time": "0:44:45", "throughput": 5752.14, "total_tokens": 6925976} {"current_steps": 10505, "total_steps": 33920, "loss": 0.4434, "lr": 8.719577777616347e-06, "epoch": 6.193985849056604, "percentage": 30.97, "elapsed_time": "0:20:04", "remaining_time": "0:44:44", "throughput": 5752.14, "total_tokens": 6928856} {"current_steps": 10510, "total_steps": 33920, "loss": 0.3371, "lr": 8.717858008304804e-06, "epoch": 6.196933962264151, "percentage": 30.98, "elapsed_time": "0:20:05", "remaining_time": "0:44:44", "throughput": 5752.63, "total_tokens": 6932728} {"current_steps": 10515, "total_steps": 33920, "loss": 0.4266, "lr": 8.71613725467433e-06, "epoch": 6.199882075471698, "percentage": 31.0, "elapsed_time": "0:20:05", "remaining_time": "0:44:43", "throughput": 5752.78, "total_tokens": 6935832} {"current_steps": 10520, "total_steps": 33920, "loss": 0.3919, "lr": 8.714415517180506e-06, "epoch": 6.202830188679245, "percentage": 31.01, "elapsed_time": "0:20:06", "remaining_time": "0:44:42", "throughput": 5752.99, "total_tokens": 6939128} {"current_steps": 10525, "total_steps": 33920, "loss": 0.6216, "lr": 8.712692796279164e-06, "epoch": 6.2057783018867925, "percentage": 31.03, "elapsed_time": "0:20:07", "remaining_time": "0:44:43", "throughput": 5753.68, "total_tokens": 6947096} {"current_steps": 10530, "total_steps": 33920, "loss": 0.3592, "lr": 8.710969092426401e-06, "epoch": 6.20872641509434, "percentage": 31.04, "elapsed_time": "0:20:07", "remaining_time": "0:44:43", "throughput": 5754.02, "total_tokens": 6950456} {"current_steps": 10535, "total_steps": 33920, "loss": 0.5177, "lr": 8.70924440607858e-06, "epoch": 6.211674528301887, "percentage": 31.06, "elapsed_time": "0:20:08", "remaining_time": "0:44:42", "throughput": 5754.29, "total_tokens": 6953752} {"current_steps": 10540, "total_steps": 33920, "loss": 0.3401, "lr": 8.707518737692315e-06, "epoch": 6.214622641509434, "percentage": 31.07, "elapsed_time": "0:20:08", "remaining_time": "0:44:41", "throughput": 5754.12, "total_tokens": 6956248} {"current_steps": 10545, "total_steps": 33920, "loss": 0.4212, "lr": 8.705792087724485e-06, "epoch": 6.217570754716981, "percentage": 31.09, "elapsed_time": "0:20:09", "remaining_time": "0:44:40", "throughput": 5754.15, "total_tokens": 6959224} {"current_steps": 10550, "total_steps": 33920, "loss": 0.4576, "lr": 8.704064456632231e-06, "epoch": 6.220518867924528, "percentage": 31.1, "elapsed_time": "0:20:09", "remaining_time": "0:44:40", "throughput": 5753.93, "total_tokens": 6961944} {"current_steps": 10555, "total_steps": 33920, "loss": 0.3196, "lr": 8.702335844872946e-06, "epoch": 6.223466981132075, "percentage": 31.12, "elapsed_time": "0:20:10", "remaining_time": "0:44:39", "throughput": 5754.21, "total_tokens": 6965464} {"current_steps": 10560, "total_steps": 33920, "loss": 0.2915, "lr": 8.700606252904293e-06, "epoch": 6.226415094339623, "percentage": 31.13, "elapsed_time": "0:20:11", "remaining_time": "0:44:38", "throughput": 5754.49, "total_tokens": 6968952} {"current_steps": 10565, "total_steps": 33920, "loss": 0.4269, "lr": 8.698875681184183e-06, "epoch": 6.22936320754717, "percentage": 31.15, "elapsed_time": "0:20:11", "remaining_time": "0:44:38", "throughput": 5754.63, "total_tokens": 6971960} {"current_steps": 10570, "total_steps": 33920, "loss": 0.3847, "lr": 8.697144130170797e-06, "epoch": 6.232311320754717, "percentage": 31.16, "elapsed_time": "0:20:12", "remaining_time": "0:44:37", "throughput": 5754.83, "total_tokens": 6975992} {"current_steps": 10575, "total_steps": 33920, "loss": 0.3748, "lr": 8.695411600322568e-06, "epoch": 6.2352594339622645, "percentage": 31.18, "elapsed_time": "0:20:12", "remaining_time": "0:44:37", "throughput": 5754.53, "total_tokens": 6978488} {"current_steps": 10580, "total_steps": 33920, "loss": 0.4509, "lr": 8.693678092098191e-06, "epoch": 6.238207547169812, "percentage": 31.19, "elapsed_time": "0:20:13", "remaining_time": "0:44:36", "throughput": 5755.01, "total_tokens": 6982264} {"current_steps": 10585, "total_steps": 33920, "loss": 0.4246, "lr": 8.691943605956621e-06, "epoch": 6.241155660377358, "percentage": 31.21, "elapsed_time": "0:20:13", "remaining_time": "0:44:35", "throughput": 5755.34, "total_tokens": 6986008} {"current_steps": 10590, "total_steps": 33920, "loss": 0.4234, "lr": 8.690208142357069e-06, "epoch": 6.244103773584905, "percentage": 31.22, "elapsed_time": "0:20:14", "remaining_time": "0:44:35", "throughput": 5755.22, "total_tokens": 6989080} {"current_steps": 10595, "total_steps": 33920, "loss": 0.4418, "lr": 8.68847170175901e-06, "epoch": 6.247051886792453, "percentage": 31.24, "elapsed_time": "0:20:14", "remaining_time": "0:44:34", "throughput": 5755.35, "total_tokens": 6992248} {"current_steps": 10600, "total_steps": 33920, "loss": 0.5605, "lr": 8.686734284622168e-06, "epoch": 6.25, "percentage": 31.25, "elapsed_time": "0:20:15", "remaining_time": "0:44:33", "throughput": 5755.46, "total_tokens": 6995256} {"current_steps": 10605, "total_steps": 33920, "loss": 0.4648, "lr": 8.684995891406537e-06, "epoch": 6.252948113207547, "percentage": 31.26, "elapsed_time": "0:20:16", "remaining_time": "0:44:33", "throughput": 5755.8, "total_tokens": 6999096} {"current_steps": 10610, "total_steps": 33920, "loss": 0.3969, "lr": 8.683256522572362e-06, "epoch": 6.255896226415095, "percentage": 31.28, "elapsed_time": "0:20:16", "remaining_time": "0:44:32", "throughput": 5755.47, "total_tokens": 7001496} {"current_steps": 10615, "total_steps": 33920, "loss": 0.5116, "lr": 8.68151617858015e-06, "epoch": 6.258844339622642, "percentage": 31.29, "elapsed_time": "0:20:17", "remaining_time": "0:44:31", "throughput": 5755.83, "total_tokens": 7004984} {"current_steps": 10620, "total_steps": 33920, "loss": 0.3112, "lr": 8.67977485989066e-06, "epoch": 6.261792452830189, "percentage": 31.31, "elapsed_time": "0:20:17", "remaining_time": "0:44:31", "throughput": 5756.37, "total_tokens": 7009368} {"current_steps": 10625, "total_steps": 33920, "loss": 0.5368, "lr": 8.67803256696492e-06, "epoch": 6.2647405660377355, "percentage": 31.32, "elapsed_time": "0:20:18", "remaining_time": "0:44:30", "throughput": 5756.67, "total_tokens": 7012952} {"current_steps": 10630, "total_steps": 33920, "loss": 0.4526, "lr": 8.676289300264205e-06, "epoch": 6.267688679245283, "percentage": 31.34, "elapsed_time": "0:20:18", "remaining_time": "0:44:30", "throughput": 5757.12, "total_tokens": 7016792} {"current_steps": 10635, "total_steps": 33920, "loss": 0.377, "lr": 8.674545060250054e-06, "epoch": 6.27063679245283, "percentage": 31.35, "elapsed_time": "0:20:19", "remaining_time": "0:44:29", "throughput": 5757.59, "total_tokens": 7020536} {"current_steps": 10640, "total_steps": 33920, "loss": 0.4219, "lr": 8.672799847384263e-06, "epoch": 6.273584905660377, "percentage": 31.37, "elapsed_time": "0:20:19", "remaining_time": "0:44:29", "throughput": 5758.07, "total_tokens": 7024344} {"current_steps": 10645, "total_steps": 33920, "loss": 0.4081, "lr": 8.671053662128883e-06, "epoch": 6.276533018867925, "percentage": 31.38, "elapsed_time": "0:20:20", "remaining_time": "0:44:28", "throughput": 5758.61, "total_tokens": 7028856} {"current_steps": 10650, "total_steps": 33920, "loss": 0.423, "lr": 8.669306504946223e-06, "epoch": 6.279481132075472, "percentage": 31.4, "elapsed_time": "0:20:21", "remaining_time": "0:44:28", "throughput": 5758.79, "total_tokens": 7032312} {"current_steps": 10655, "total_steps": 33920, "loss": 0.4791, "lr": 8.667558376298854e-06, "epoch": 6.282429245283019, "percentage": 31.41, "elapsed_time": "0:20:21", "remaining_time": "0:44:27", "throughput": 5758.8, "total_tokens": 7035096} {"current_steps": 10660, "total_steps": 33920, "loss": 0.4338, "lr": 8.665809276649597e-06, "epoch": 6.285377358490566, "percentage": 31.43, "elapsed_time": "0:20:22", "remaining_time": "0:44:26", "throughput": 5758.91, "total_tokens": 7038200} {"current_steps": 10665, "total_steps": 33920, "loss": 0.3428, "lr": 8.664059206461537e-06, "epoch": 6.288325471698113, "percentage": 31.44, "elapsed_time": "0:20:22", "remaining_time": "0:44:25", "throughput": 5758.81, "total_tokens": 7040888} {"current_steps": 10670, "total_steps": 33920, "loss": 0.5691, "lr": 8.662308166198009e-06, "epoch": 6.29127358490566, "percentage": 31.46, "elapsed_time": "0:20:23", "remaining_time": "0:44:25", "throughput": 5759.01, "total_tokens": 7044088} {"current_steps": 10675, "total_steps": 33920, "loss": 0.4697, "lr": 8.660556156322611e-06, "epoch": 6.2942216981132075, "percentage": 31.47, "elapsed_time": "0:20:23", "remaining_time": "0:44:24", "throughput": 5758.81, "total_tokens": 7046584} {"current_steps": 10680, "total_steps": 33920, "loss": 0.3717, "lr": 8.658803177299196e-06, "epoch": 6.297169811320755, "percentage": 31.49, "elapsed_time": "0:20:24", "remaining_time": "0:44:24", "throughput": 5759.68, "total_tokens": 7053720} {"current_steps": 10685, "total_steps": 33920, "loss": 0.3932, "lr": 8.65704922959187e-06, "epoch": 6.300117924528302, "percentage": 31.5, "elapsed_time": "0:20:25", "remaining_time": "0:44:24", "throughput": 5759.43, "total_tokens": 7056088} {"current_steps": 10690, "total_steps": 33920, "loss": 0.4927, "lr": 8.655294313664998e-06, "epoch": 6.303066037735849, "percentage": 31.52, "elapsed_time": "0:20:25", "remaining_time": "0:44:23", "throughput": 5759.88, "total_tokens": 7059992} {"current_steps": 10695, "total_steps": 33920, "loss": 0.5177, "lr": 8.653538429983204e-06, "epoch": 6.306014150943396, "percentage": 31.53, "elapsed_time": "0:20:26", "remaining_time": "0:44:22", "throughput": 5759.61, "total_tokens": 7062392} {"current_steps": 10700, "total_steps": 33920, "loss": 0.3208, "lr": 8.651781579011366e-06, "epoch": 6.308962264150943, "percentage": 31.54, "elapsed_time": "0:20:26", "remaining_time": "0:44:22", "throughput": 5759.65, "total_tokens": 7065240} {"current_steps": 10705, "total_steps": 33920, "loss": 0.4158, "lr": 8.650023761214615e-06, "epoch": 6.31191037735849, "percentage": 31.56, "elapsed_time": "0:20:27", "remaining_time": "0:44:21", "throughput": 5759.92, "total_tokens": 7068472} {"current_steps": 10710, "total_steps": 33920, "loss": 0.4388, "lr": 8.648264977058344e-06, "epoch": 6.314858490566038, "percentage": 31.57, "elapsed_time": "0:20:27", "remaining_time": "0:44:20", "throughput": 5760.49, "total_tokens": 7073112} {"current_steps": 10715, "total_steps": 33920, "loss": 0.489, "lr": 8.646505227008197e-06, "epoch": 6.317806603773585, "percentage": 31.59, "elapsed_time": "0:20:28", "remaining_time": "0:44:20", "throughput": 5760.15, "total_tokens": 7075544} {"current_steps": 10720, "total_steps": 33920, "loss": 0.489, "lr": 8.644744511530074e-06, "epoch": 6.320754716981132, "percentage": 31.6, "elapsed_time": "0:20:28", "remaining_time": "0:44:19", "throughput": 5760.21, "total_tokens": 7078456} {"current_steps": 10725, "total_steps": 33920, "loss": 0.3252, "lr": 8.642982831090135e-06, "epoch": 6.3237028301886795, "percentage": 31.62, "elapsed_time": "0:20:29", "remaining_time": "0:44:19", "throughput": 5760.83, "total_tokens": 7082904} {"current_steps": 10730, "total_steps": 33920, "loss": 0.4343, "lr": 8.64122018615479e-06, "epoch": 6.326650943396227, "percentage": 31.63, "elapsed_time": "0:20:30", "remaining_time": "0:44:18", "throughput": 5760.95, "total_tokens": 7085976} {"current_steps": 10735, "total_steps": 33920, "loss": 0.4189, "lr": 8.63945657719071e-06, "epoch": 6.329599056603773, "percentage": 31.65, "elapsed_time": "0:20:30", "remaining_time": "0:44:17", "throughput": 5760.71, "total_tokens": 7088888} {"current_steps": 10740, "total_steps": 33920, "loss": 0.4566, "lr": 8.637692004664816e-06, "epoch": 6.3325471698113205, "percentage": 31.66, "elapsed_time": "0:20:31", "remaining_time": "0:44:17", "throughput": 5760.82, "total_tokens": 7092120} {"current_steps": 10745, "total_steps": 33920, "loss": 0.4778, "lr": 8.635926469044284e-06, "epoch": 6.335495283018868, "percentage": 31.68, "elapsed_time": "0:20:31", "remaining_time": "0:44:16", "throughput": 5761.15, "total_tokens": 7095672} {"current_steps": 10750, "total_steps": 33920, "loss": 0.3156, "lr": 8.63415997079655e-06, "epoch": 6.338443396226415, "percentage": 31.69, "elapsed_time": "0:20:32", "remaining_time": "0:44:15", "throughput": 5761.28, "total_tokens": 7099032} {"current_steps": 10755, "total_steps": 33920, "loss": 0.4353, "lr": 8.6323925103893e-06, "epoch": 6.341391509433962, "percentage": 31.71, "elapsed_time": "0:20:32", "remaining_time": "0:44:15", "throughput": 5761.55, "total_tokens": 7102680} {"current_steps": 10760, "total_steps": 33920, "loss": 0.4208, "lr": 8.63062408829048e-06, "epoch": 6.34433962264151, "percentage": 31.72, "elapsed_time": "0:20:33", "remaining_time": "0:44:14", "throughput": 5762.1, "total_tokens": 7107192} {"current_steps": 10765, "total_steps": 33920, "loss": 0.3723, "lr": 8.628854704968285e-06, "epoch": 6.347287735849057, "percentage": 31.74, "elapsed_time": "0:20:33", "remaining_time": "0:44:14", "throughput": 5762.1, "total_tokens": 7109912} {"current_steps": 10770, "total_steps": 33920, "loss": 0.4302, "lr": 8.62708436089117e-06, "epoch": 6.350235849056604, "percentage": 31.75, "elapsed_time": "0:20:34", "remaining_time": "0:44:13", "throughput": 5762.36, "total_tokens": 7113176} {"current_steps": 10775, "total_steps": 33920, "loss": 0.5979, "lr": 8.625313056527836e-06, "epoch": 6.353183962264151, "percentage": 31.77, "elapsed_time": "0:20:34", "remaining_time": "0:44:12", "throughput": 5762.42, "total_tokens": 7116120} {"current_steps": 10780, "total_steps": 33920, "loss": 0.4104, "lr": 8.623540792347244e-06, "epoch": 6.356132075471698, "percentage": 31.78, "elapsed_time": "0:20:35", "remaining_time": "0:44:11", "throughput": 5762.62, "total_tokens": 7119160} {"current_steps": 10785, "total_steps": 33920, "loss": 0.4433, "lr": 8.621767568818614e-06, "epoch": 6.359080188679245, "percentage": 31.8, "elapsed_time": "0:20:35", "remaining_time": "0:44:11", "throughput": 5762.72, "total_tokens": 7122136} {"current_steps": 10790, "total_steps": 33920, "loss": 0.3679, "lr": 8.619993386411409e-06, "epoch": 6.3620283018867925, "percentage": 31.81, "elapsed_time": "0:20:36", "remaining_time": "0:44:10", "throughput": 5762.84, "total_tokens": 7125080} {"current_steps": 10795, "total_steps": 33920, "loss": 0.5295, "lr": 8.618218245595356e-06, "epoch": 6.36497641509434, "percentage": 31.82, "elapsed_time": "0:20:37", "remaining_time": "0:44:10", "throughput": 5763.2, "total_tokens": 7129400} {"current_steps": 10800, "total_steps": 33920, "loss": 0.4853, "lr": 8.616442146840427e-06, "epoch": 6.367924528301887, "percentage": 31.84, "elapsed_time": "0:20:37", "remaining_time": "0:44:09", "throughput": 5763.33, "total_tokens": 7132408} {"current_steps": 10805, "total_steps": 33920, "loss": 0.5536, "lr": 8.614665090616854e-06, "epoch": 6.370872641509434, "percentage": 31.85, "elapsed_time": "0:20:38", "remaining_time": "0:44:08", "throughput": 5763.31, "total_tokens": 7135160} {"current_steps": 10810, "total_steps": 33920, "loss": 0.5215, "lr": 8.61288707739512e-06, "epoch": 6.373820754716981, "percentage": 31.87, "elapsed_time": "0:20:38", "remaining_time": "0:44:07", "throughput": 5763.23, "total_tokens": 7137752} {"current_steps": 10815, "total_steps": 33920, "loss": 0.4412, "lr": 8.611108107645963e-06, "epoch": 6.376768867924528, "percentage": 31.88, "elapsed_time": "0:20:39", "remaining_time": "0:44:07", "throughput": 5763.44, "total_tokens": 7141048} {"current_steps": 10820, "total_steps": 33920, "loss": 0.5216, "lr": 8.609328181840368e-06, "epoch": 6.379716981132075, "percentage": 31.9, "elapsed_time": "0:20:39", "remaining_time": "0:44:06", "throughput": 5763.46, "total_tokens": 7143864} {"current_steps": 10825, "total_steps": 33920, "loss": 0.3668, "lr": 8.607547300449585e-06, "epoch": 6.382665094339623, "percentage": 31.91, "elapsed_time": "0:20:39", "remaining_time": "0:44:05", "throughput": 5763.46, "total_tokens": 7146584} {"current_steps": 10830, "total_steps": 33920, "loss": 0.3445, "lr": 8.605765463945105e-06, "epoch": 6.38561320754717, "percentage": 31.93, "elapsed_time": "0:20:40", "remaining_time": "0:44:04", "throughput": 5763.5, "total_tokens": 7149272} {"current_steps": 10835, "total_steps": 33920, "loss": 0.4165, "lr": 8.603982672798678e-06, "epoch": 6.388561320754717, "percentage": 31.94, "elapsed_time": "0:20:40", "remaining_time": "0:44:03", "throughput": 5763.61, "total_tokens": 7152216} {"current_steps": 10840, "total_steps": 33920, "loss": 0.4128, "lr": 8.602198927482309e-06, "epoch": 6.3915094339622645, "percentage": 31.96, "elapsed_time": "0:20:41", "remaining_time": "0:44:03", "throughput": 5763.87, "total_tokens": 7155800} {"current_steps": 10845, "total_steps": 33920, "loss": 0.3889, "lr": 8.600414228468245e-06, "epoch": 6.394457547169811, "percentage": 31.97, "elapsed_time": "0:20:41", "remaining_time": "0:44:02", "throughput": 5763.87, "total_tokens": 7158456} {"current_steps": 10850, "total_steps": 33920, "loss": 0.6064, "lr": 8.598628576229e-06, "epoch": 6.397405660377358, "percentage": 31.99, "elapsed_time": "0:20:42", "remaining_time": "0:44:01", "throughput": 5763.67, "total_tokens": 7160984} {"current_steps": 10855, "total_steps": 33920, "loss": 0.3546, "lr": 8.596841971237328e-06, "epoch": 6.400353773584905, "percentage": 32.0, "elapsed_time": "0:20:42", "remaining_time": "0:44:01", "throughput": 5763.94, "total_tokens": 7164568} {"current_steps": 10860, "total_steps": 33920, "loss": 0.4047, "lr": 8.595054413966246e-06, "epoch": 6.403301886792453, "percentage": 32.02, "elapsed_time": "0:20:43", "remaining_time": "0:44:00", "throughput": 5764.17, "total_tokens": 7167800} {"current_steps": 10865, "total_steps": 33920, "loss": 0.348, "lr": 8.593265904889011e-06, "epoch": 6.40625, "percentage": 32.03, "elapsed_time": "0:20:44", "remaining_time": "0:43:59", "throughput": 5764.28, "total_tokens": 7170776} {"current_steps": 10870, "total_steps": 33920, "loss": 0.4048, "lr": 8.591476444479141e-06, "epoch": 6.409198113207547, "percentage": 32.05, "elapsed_time": "0:20:44", "remaining_time": "0:43:58", "throughput": 5764.35, "total_tokens": 7173496} {"current_steps": 10875, "total_steps": 33920, "loss": 0.5386, "lr": 8.589686033210407e-06, "epoch": 6.412146226415095, "percentage": 32.06, "elapsed_time": "0:20:45", "remaining_time": "0:43:58", "throughput": 5764.96, "total_tokens": 7178200} {"current_steps": 10880, "total_steps": 33920, "loss": 0.3884, "lr": 8.587894671556823e-06, "epoch": 6.415094339622642, "percentage": 32.08, "elapsed_time": "0:20:45", "remaining_time": "0:43:57", "throughput": 5765.08, "total_tokens": 7181240} {"current_steps": 10885, "total_steps": 33920, "loss": 0.4836, "lr": 8.586102359992663e-06, "epoch": 6.418042452830189, "percentage": 32.09, "elapsed_time": "0:20:46", "remaining_time": "0:43:57", "throughput": 5765.29, "total_tokens": 7184472} {"current_steps": 10890, "total_steps": 33920, "loss": 0.4532, "lr": 8.584309098992447e-06, "epoch": 6.4209905660377355, "percentage": 32.1, "elapsed_time": "0:20:46", "remaining_time": "0:43:56", "throughput": 5765.4, "total_tokens": 7187320} {"current_steps": 10895, "total_steps": 33920, "loss": 0.3383, "lr": 8.58251488903095e-06, "epoch": 6.423938679245283, "percentage": 32.12, "elapsed_time": "0:20:47", "remaining_time": "0:43:55", "throughput": 5765.39, "total_tokens": 7190424} {"current_steps": 10900, "total_steps": 33920, "loss": 0.4092, "lr": 8.580719730583196e-06, "epoch": 6.42688679245283, "percentage": 32.13, "elapsed_time": "0:20:47", "remaining_time": "0:43:55", "throughput": 5765.66, "total_tokens": 7193816} {"current_steps": 10905, "total_steps": 33920, "loss": 0.3982, "lr": 8.578923624124462e-06, "epoch": 6.429834905660377, "percentage": 32.15, "elapsed_time": "0:20:48", "remaining_time": "0:43:54", "throughput": 5765.93, "total_tokens": 7197176} {"current_steps": 10910, "total_steps": 33920, "loss": 0.3963, "lr": 8.577126570130273e-06, "epoch": 6.432783018867925, "percentage": 32.16, "elapsed_time": "0:20:48", "remaining_time": "0:43:53", "throughput": 5765.99, "total_tokens": 7200120} {"current_steps": 10915, "total_steps": 33920, "loss": 0.3412, "lr": 8.575328569076408e-06, "epoch": 6.435731132075472, "percentage": 32.18, "elapsed_time": "0:20:49", "remaining_time": "0:43:52", "throughput": 5766.05, "total_tokens": 7203160} {"current_steps": 10920, "total_steps": 33920, "loss": 0.522, "lr": 8.573529621438896e-06, "epoch": 6.438679245283019, "percentage": 32.19, "elapsed_time": "0:20:49", "remaining_time": "0:43:52", "throughput": 5766.24, "total_tokens": 7206296} {"current_steps": 10925, "total_steps": 33920, "loss": 0.4112, "lr": 8.571729727694015e-06, "epoch": 6.441627358490566, "percentage": 32.21, "elapsed_time": "0:20:50", "remaining_time": "0:43:51", "throughput": 5766.43, "total_tokens": 7209560} {"current_steps": 10930, "total_steps": 33920, "loss": 0.3771, "lr": 8.569928888318298e-06, "epoch": 6.444575471698113, "percentage": 32.22, "elapsed_time": "0:20:50", "remaining_time": "0:43:50", "throughput": 5766.51, "total_tokens": 7212408} {"current_steps": 10935, "total_steps": 33920, "loss": 0.6758, "lr": 8.56812710378852e-06, "epoch": 6.44752358490566, "percentage": 32.24, "elapsed_time": "0:20:51", "remaining_time": "0:43:50", "throughput": 5766.74, "total_tokens": 7215992} {"current_steps": 10940, "total_steps": 33920, "loss": 0.5332, "lr": 8.566324374581714e-06, "epoch": 6.4504716981132075, "percentage": 32.25, "elapsed_time": "0:20:52", "remaining_time": "0:43:50", "throughput": 5767.51, "total_tokens": 7221784} {"current_steps": 10945, "total_steps": 33920, "loss": 0.4538, "lr": 8.564520701175158e-06, "epoch": 6.453419811320755, "percentage": 32.27, "elapsed_time": "0:20:52", "remaining_time": "0:43:49", "throughput": 5767.55, "total_tokens": 7224664} {"current_steps": 10950, "total_steps": 33920, "loss": 0.4694, "lr": 8.562716084046387e-06, "epoch": 6.456367924528302, "percentage": 32.28, "elapsed_time": "0:20:53", "remaining_time": "0:43:48", "throughput": 5767.98, "total_tokens": 7228536} {"current_steps": 10955, "total_steps": 33920, "loss": 0.558, "lr": 8.560910523673177e-06, "epoch": 6.459316037735849, "percentage": 32.3, "elapsed_time": "0:20:53", "remaining_time": "0:43:48", "throughput": 5768.32, "total_tokens": 7232248} {"current_steps": 10960, "total_steps": 33920, "loss": 0.3462, "lr": 8.55910402053356e-06, "epoch": 6.462264150943396, "percentage": 32.31, "elapsed_time": "0:20:54", "remaining_time": "0:43:48", "throughput": 5768.52, "total_tokens": 7237208} {"current_steps": 10965, "total_steps": 33920, "loss": 0.3625, "lr": 8.557296575105814e-06, "epoch": 6.465212264150943, "percentage": 32.33, "elapsed_time": "0:20:55", "remaining_time": "0:43:47", "throughput": 5768.63, "total_tokens": 7240216} {"current_steps": 10970, "total_steps": 33920, "loss": 0.3941, "lr": 8.555488187868469e-06, "epoch": 6.46816037735849, "percentage": 32.34, "elapsed_time": "0:20:55", "remaining_time": "0:43:47", "throughput": 5768.79, "total_tokens": 7244120} {"current_steps": 10975, "total_steps": 33920, "loss": 0.334, "lr": 8.5536788593003e-06, "epoch": 6.471108490566038, "percentage": 32.36, "elapsed_time": "0:20:56", "remaining_time": "0:43:46", "throughput": 5768.97, "total_tokens": 7247288} {"current_steps": 10980, "total_steps": 33920, "loss": 0.4408, "lr": 8.55186858988034e-06, "epoch": 6.474056603773585, "percentage": 32.37, "elapsed_time": "0:20:56", "remaining_time": "0:43:45", "throughput": 5769.11, "total_tokens": 7250904} {"current_steps": 10985, "total_steps": 33920, "loss": 0.3348, "lr": 8.550057380087863e-06, "epoch": 6.477004716981132, "percentage": 32.39, "elapsed_time": "0:20:57", "remaining_time": "0:43:45", "throughput": 5769.17, "total_tokens": 7253912} {"current_steps": 10990, "total_steps": 33920, "loss": 0.5838, "lr": 8.548245230402396e-06, "epoch": 6.4799528301886795, "percentage": 32.4, "elapsed_time": "0:20:57", "remaining_time": "0:43:44", "throughput": 5768.93, "total_tokens": 7256440} {"current_steps": 10995, "total_steps": 33920, "loss": 0.5001, "lr": 8.546432141303711e-06, "epoch": 6.482900943396227, "percentage": 32.41, "elapsed_time": "0:20:58", "remaining_time": "0:43:43", "throughput": 5769.06, "total_tokens": 7259736} {"current_steps": 11000, "total_steps": 33920, "loss": 0.5421, "lr": 8.544618113271833e-06, "epoch": 6.485849056603773, "percentage": 32.43, "elapsed_time": "0:20:58", "remaining_time": "0:43:42", "throughput": 5768.83, "total_tokens": 7262104} {"current_steps": 11005, "total_steps": 33920, "loss": 0.407, "lr": 8.542803146787032e-06, "epoch": 6.4887971698113205, "percentage": 32.44, "elapsed_time": "0:20:59", "remaining_time": "0:43:42", "throughput": 5768.95, "total_tokens": 7265144} {"current_steps": 11010, "total_steps": 33920, "loss": 0.3753, "lr": 8.54098724232983e-06, "epoch": 6.491745283018868, "percentage": 32.46, "elapsed_time": "0:20:59", "remaining_time": "0:43:41", "throughput": 5768.91, "total_tokens": 7268088} {"current_steps": 11015, "total_steps": 33920, "loss": 0.494, "lr": 8.539170400380994e-06, "epoch": 6.494693396226415, "percentage": 32.47, "elapsed_time": "0:21:00", "remaining_time": "0:43:40", "throughput": 5768.82, "total_tokens": 7270808} {"current_steps": 11020, "total_steps": 33920, "loss": 0.4612, "lr": 8.537352621421542e-06, "epoch": 6.497641509433962, "percentage": 32.49, "elapsed_time": "0:21:00", "remaining_time": "0:43:40", "throughput": 5769.27, "total_tokens": 7274616} {"current_steps": 11025, "total_steps": 33920, "loss": 0.3647, "lr": 8.535533905932739e-06, "epoch": 6.50058962264151, "percentage": 32.5, "elapsed_time": "0:21:01", "remaining_time": "0:43:39", "throughput": 5769.24, "total_tokens": 7277752} {"current_steps": 11030, "total_steps": 33920, "loss": 0.4609, "lr": 8.533714254396096e-06, "epoch": 6.503537735849057, "percentage": 32.52, "elapsed_time": "0:21:01", "remaining_time": "0:43:38", "throughput": 5769.4, "total_tokens": 7280920} {"current_steps": 11035, "total_steps": 33920, "loss": 0.3676, "lr": 8.531893667293375e-06, "epoch": 6.506485849056604, "percentage": 32.53, "elapsed_time": "0:21:02", "remaining_time": "0:43:38", "throughput": 5769.77, "total_tokens": 7284952} {"current_steps": 11040, "total_steps": 33920, "loss": 0.3634, "lr": 8.530072145106585e-06, "epoch": 6.509433962264151, "percentage": 32.55, "elapsed_time": "0:21:03", "remaining_time": "0:43:37", "throughput": 5769.7, "total_tokens": 7287544} {"current_steps": 11045, "total_steps": 33920, "loss": 0.4465, "lr": 8.528249688317978e-06, "epoch": 6.512382075471698, "percentage": 32.56, "elapsed_time": "0:21:03", "remaining_time": "0:43:36", "throughput": 5769.56, "total_tokens": 7290232} {"current_steps": 11050, "total_steps": 33920, "loss": 0.578, "lr": 8.526426297410062e-06, "epoch": 6.515330188679245, "percentage": 32.58, "elapsed_time": "0:21:04", "remaining_time": "0:43:36", "throughput": 5769.63, "total_tokens": 7293176} {"current_steps": 11055, "total_steps": 33920, "loss": 0.3039, "lr": 8.524601972865586e-06, "epoch": 6.5182783018867925, "percentage": 32.59, "elapsed_time": "0:21:04", "remaining_time": "0:43:35", "throughput": 5769.87, "total_tokens": 7296536} {"current_steps": 11060, "total_steps": 33920, "loss": 0.5273, "lr": 8.522776715167548e-06, "epoch": 6.52122641509434, "percentage": 32.61, "elapsed_time": "0:21:05", "remaining_time": "0:43:34", "throughput": 5769.99, "total_tokens": 7299608} {"current_steps": 11065, "total_steps": 33920, "loss": 0.4288, "lr": 8.520950524799192e-06, "epoch": 6.524174528301887, "percentage": 32.62, "elapsed_time": "0:21:05", "remaining_time": "0:43:34", "throughput": 5770.29, "total_tokens": 7303160} {"current_steps": 11070, "total_steps": 33920, "loss": 0.4529, "lr": 8.51912340224401e-06, "epoch": 6.527122641509434, "percentage": 32.64, "elapsed_time": "0:21:06", "remaining_time": "0:43:33", "throughput": 5770.23, "total_tokens": 7305784} {"current_steps": 11075, "total_steps": 33920, "loss": 0.387, "lr": 8.51729534798574e-06, "epoch": 6.530070754716981, "percentage": 32.65, "elapsed_time": "0:21:06", "remaining_time": "0:43:32", "throughput": 5770.71, "total_tokens": 7309912} {"current_steps": 11080, "total_steps": 33920, "loss": 0.3805, "lr": 8.515466362508369e-06, "epoch": 6.533018867924528, "percentage": 32.67, "elapsed_time": "0:21:07", "remaining_time": "0:43:32", "throughput": 5771.01, "total_tokens": 7313496} {"current_steps": 11085, "total_steps": 33920, "loss": 0.5176, "lr": 8.513636446296125e-06, "epoch": 6.535966981132075, "percentage": 32.68, "elapsed_time": "0:21:07", "remaining_time": "0:43:31", "throughput": 5770.99, "total_tokens": 7316920} {"current_steps": 11090, "total_steps": 33920, "loss": 0.3954, "lr": 8.51180559983349e-06, "epoch": 6.538915094339623, "percentage": 32.69, "elapsed_time": "0:21:08", "remaining_time": "0:43:31", "throughput": 5770.83, "total_tokens": 7319864} {"current_steps": 11095, "total_steps": 33920, "loss": 0.5401, "lr": 8.50997382360519e-06, "epoch": 6.54186320754717, "percentage": 32.71, "elapsed_time": "0:21:09", "remaining_time": "0:43:30", "throughput": 5771.5, "total_tokens": 7324536} {"current_steps": 11100, "total_steps": 33920, "loss": 0.3527, "lr": 8.508141118096191e-06, "epoch": 6.544811320754717, "percentage": 32.72, "elapsed_time": "0:21:09", "remaining_time": "0:43:30", "throughput": 5771.45, "total_tokens": 7327768} {"current_steps": 11105, "total_steps": 33920, "loss": 0.4778, "lr": 8.506307483791712e-06, "epoch": 6.5477594339622645, "percentage": 32.74, "elapsed_time": "0:21:10", "remaining_time": "0:43:29", "throughput": 5771.53, "total_tokens": 7330872} {"current_steps": 11110, "total_steps": 33920, "loss": 0.434, "lr": 8.504472921177215e-06, "epoch": 6.550707547169811, "percentage": 32.75, "elapsed_time": "0:21:10", "remaining_time": "0:43:28", "throughput": 5771.26, "total_tokens": 7333368} {"current_steps": 11115, "total_steps": 33920, "loss": 0.4674, "lr": 8.502637430738409e-06, "epoch": 6.553655660377358, "percentage": 32.77, "elapsed_time": "0:21:11", "remaining_time": "0:43:28", "throughput": 5771.4, "total_tokens": 7336952} {"current_steps": 11120, "total_steps": 33920, "loss": 0.3752, "lr": 8.500801012961248e-06, "epoch": 6.556603773584905, "percentage": 32.78, "elapsed_time": "0:21:11", "remaining_time": "0:43:27", "throughput": 5771.66, "total_tokens": 7340440} {"current_steps": 11125, "total_steps": 33920, "loss": 0.4025, "lr": 8.49896366833193e-06, "epoch": 6.559551886792453, "percentage": 32.8, "elapsed_time": "0:21:12", "remaining_time": "0:43:26", "throughput": 5771.21, "total_tokens": 7342648} {"current_steps": 11130, "total_steps": 33920, "loss": 0.3832, "lr": 8.497125397336903e-06, "epoch": 6.5625, "percentage": 32.81, "elapsed_time": "0:21:12", "remaining_time": "0:43:26", "throughput": 5771.41, "total_tokens": 7346200} {"current_steps": 11135, "total_steps": 33920, "loss": 0.4314, "lr": 8.495286200462854e-06, "epoch": 6.565448113207547, "percentage": 32.83, "elapsed_time": "0:21:13", "remaining_time": "0:43:25", "throughput": 5772.03, "total_tokens": 7350840} {"current_steps": 11140, "total_steps": 33920, "loss": 0.4958, "lr": 8.49344607819672e-06, "epoch": 6.568396226415095, "percentage": 32.84, "elapsed_time": "0:21:13", "remaining_time": "0:43:25", "throughput": 5771.94, "total_tokens": 7353432} {"current_steps": 11145, "total_steps": 33920, "loss": 0.4229, "lr": 8.49160503102568e-06, "epoch": 6.571344339622642, "percentage": 32.86, "elapsed_time": "0:21:14", "remaining_time": "0:43:24", "throughput": 5771.84, "total_tokens": 7356216} {"current_steps": 11150, "total_steps": 33920, "loss": 0.4368, "lr": 8.489763059437161e-06, "epoch": 6.574292452830189, "percentage": 32.87, "elapsed_time": "0:21:14", "remaining_time": "0:43:23", "throughput": 5771.76, "total_tokens": 7358904} {"current_steps": 11155, "total_steps": 33920, "loss": 0.3649, "lr": 8.487920163918833e-06, "epoch": 6.5772405660377355, "percentage": 32.89, "elapsed_time": "0:21:15", "remaining_time": "0:43:23", "throughput": 5771.78, "total_tokens": 7361944} {"current_steps": 11160, "total_steps": 33920, "loss": 0.6176, "lr": 8.486076344958607e-06, "epoch": 6.580188679245283, "percentage": 32.9, "elapsed_time": "0:21:16", "remaining_time": "0:43:22", "throughput": 5772.26, "total_tokens": 7366136} {"current_steps": 11165, "total_steps": 33920, "loss": 0.3394, "lr": 8.484231603044647e-06, "epoch": 6.58313679245283, "percentage": 32.92, "elapsed_time": "0:21:16", "remaining_time": "0:43:22", "throughput": 5772.81, "total_tokens": 7370424} {"current_steps": 11170, "total_steps": 33920, "loss": 0.4776, "lr": 8.482385938665352e-06, "epoch": 6.586084905660377, "percentage": 32.93, "elapsed_time": "0:21:17", "remaining_time": "0:43:21", "throughput": 5773.05, "total_tokens": 7373912} {"current_steps": 11175, "total_steps": 33920, "loss": 0.4372, "lr": 8.480539352309373e-06, "epoch": 6.589033018867925, "percentage": 32.95, "elapsed_time": "0:21:17", "remaining_time": "0:43:20", "throughput": 5773.29, "total_tokens": 7377368} {"current_steps": 11180, "total_steps": 33920, "loss": 0.5315, "lr": 8.478691844465598e-06, "epoch": 6.591981132075472, "percentage": 32.96, "elapsed_time": "0:21:18", "remaining_time": "0:43:20", "throughput": 5773.35, "total_tokens": 7380280} {"current_steps": 11185, "total_steps": 33920, "loss": 0.469, "lr": 8.476843415623168e-06, "epoch": 6.594929245283019, "percentage": 32.97, "elapsed_time": "0:21:19", "remaining_time": "0:43:19", "throughput": 5773.96, "total_tokens": 7385016} {"current_steps": 11190, "total_steps": 33920, "loss": 0.4901, "lr": 8.474994066271458e-06, "epoch": 6.597877358490566, "percentage": 32.99, "elapsed_time": "0:21:19", "remaining_time": "0:43:19", "throughput": 5774.17, "total_tokens": 7388312} {"current_steps": 11195, "total_steps": 33920, "loss": 0.2955, "lr": 8.473143796900089e-06, "epoch": 6.600825471698113, "percentage": 33.0, "elapsed_time": "0:21:20", "remaining_time": "0:43:18", "throughput": 5774.25, "total_tokens": 7391288} {"current_steps": 11200, "total_steps": 33920, "loss": 0.4492, "lr": 8.471292607998936e-06, "epoch": 6.60377358490566, "percentage": 33.02, "elapsed_time": "0:21:20", "remaining_time": "0:43:18", "throughput": 5775.12, "total_tokens": 7397304} {"current_steps": 11205, "total_steps": 33920, "loss": 0.4804, "lr": 8.469440500058104e-06, "epoch": 6.6067216981132075, "percentage": 33.03, "elapsed_time": "0:21:21", "remaining_time": "0:43:17", "throughput": 5774.92, "total_tokens": 7400056} {"current_steps": 11210, "total_steps": 33920, "loss": 0.4484, "lr": 8.467587473567945e-06, "epoch": 6.609669811320755, "percentage": 33.05, "elapsed_time": "0:21:21", "remaining_time": "0:43:16", "throughput": 5774.95, "total_tokens": 7402872} {"current_steps": 11215, "total_steps": 33920, "loss": 0.4644, "lr": 8.46573352901906e-06, "epoch": 6.612617924528302, "percentage": 33.06, "elapsed_time": "0:21:22", "remaining_time": "0:43:16", "throughput": 5775.29, "total_tokens": 7406552} {"current_steps": 11220, "total_steps": 33920, "loss": 0.4456, "lr": 8.463878666902286e-06, "epoch": 6.615566037735849, "percentage": 33.08, "elapsed_time": "0:21:22", "remaining_time": "0:43:15", "throughput": 5775.23, "total_tokens": 7409400} {"current_steps": 11225, "total_steps": 33920, "loss": 0.4297, "lr": 8.462022887708706e-06, "epoch": 6.618514150943396, "percentage": 33.09, "elapsed_time": "0:21:23", "remaining_time": "0:43:14", "throughput": 5775.28, "total_tokens": 7412344} {"current_steps": 11230, "total_steps": 33920, "loss": 0.393, "lr": 8.460166191929646e-06, "epoch": 6.621462264150943, "percentage": 33.11, "elapsed_time": "0:21:23", "remaining_time": "0:43:14", "throughput": 5775.01, "total_tokens": 7415032} {"current_steps": 11235, "total_steps": 33920, "loss": 0.4511, "lr": 8.458308580056675e-06, "epoch": 6.62441037735849, "percentage": 33.12, "elapsed_time": "0:21:24", "remaining_time": "0:43:13", "throughput": 5775.24, "total_tokens": 7418904} {"current_steps": 11240, "total_steps": 33920, "loss": 0.336, "lr": 8.456450052581602e-06, "epoch": 6.627358490566038, "percentage": 33.14, "elapsed_time": "0:21:25", "remaining_time": "0:43:13", "throughput": 5775.13, "total_tokens": 7421528} {"current_steps": 11245, "total_steps": 33920, "loss": 0.3695, "lr": 8.45459060999648e-06, "epoch": 6.630306603773585, "percentage": 33.15, "elapsed_time": "0:21:25", "remaining_time": "0:43:12", "throughput": 5775.03, "total_tokens": 7424248} {"current_steps": 11250, "total_steps": 33920, "loss": 0.3543, "lr": 8.452730252793608e-06, "epoch": 6.633254716981132, "percentage": 33.17, "elapsed_time": "0:21:26", "remaining_time": "0:43:11", "throughput": 5775.08, "total_tokens": 7427384} {"current_steps": 11255, "total_steps": 33920, "loss": 0.4579, "lr": 8.450868981465519e-06, "epoch": 6.6362028301886795, "percentage": 33.18, "elapsed_time": "0:21:26", "remaining_time": "0:43:10", "throughput": 5774.77, "total_tokens": 7429688} {"current_steps": 11260, "total_steps": 33920, "loss": 0.4476, "lr": 8.449006796504997e-06, "epoch": 6.639150943396227, "percentage": 33.2, "elapsed_time": "0:21:27", "remaining_time": "0:43:10", "throughput": 5774.82, "total_tokens": 7432888} {"current_steps": 11265, "total_steps": 33920, "loss": 0.4953, "lr": 8.44714369840506e-06, "epoch": 6.642099056603773, "percentage": 33.21, "elapsed_time": "0:21:27", "remaining_time": "0:43:09", "throughput": 5774.9, "total_tokens": 7436184} {"current_steps": 11270, "total_steps": 33920, "loss": 0.4082, "lr": 8.445279687658973e-06, "epoch": 6.6450471698113205, "percentage": 33.23, "elapsed_time": "0:21:28", "remaining_time": "0:43:08", "throughput": 5774.68, "total_tokens": 7438712} {"current_steps": 11275, "total_steps": 33920, "loss": 0.398, "lr": 8.44341476476024e-06, "epoch": 6.647995283018868, "percentage": 33.24, "elapsed_time": "0:21:28", "remaining_time": "0:43:08", "throughput": 5774.48, "total_tokens": 7441496} {"current_steps": 11280, "total_steps": 33920, "loss": 0.5777, "lr": 8.441548930202608e-06, "epoch": 6.650943396226415, "percentage": 33.25, "elapsed_time": "0:21:29", "remaining_time": "0:43:07", "throughput": 5774.46, "total_tokens": 7444440} {"current_steps": 11285, "total_steps": 33920, "loss": 0.3995, "lr": 8.439682184480065e-06, "epoch": 6.653891509433962, "percentage": 33.27, "elapsed_time": "0:21:29", "remaining_time": "0:43:06", "throughput": 5774.87, "total_tokens": 7448344} {"current_steps": 11290, "total_steps": 33920, "loss": 0.4502, "lr": 8.437814528086837e-06, "epoch": 6.65683962264151, "percentage": 33.28, "elapsed_time": "0:21:30", "remaining_time": "0:43:06", "throughput": 5774.91, "total_tokens": 7451576} {"current_steps": 11295, "total_steps": 33920, "loss": 0.6278, "lr": 8.435945961517398e-06, "epoch": 6.659787735849057, "percentage": 33.3, "elapsed_time": "0:21:30", "remaining_time": "0:43:05", "throughput": 5775.1, "total_tokens": 7454840} {"current_steps": 11300, "total_steps": 33920, "loss": 0.379, "lr": 8.434076485266458e-06, "epoch": 6.662735849056604, "percentage": 33.31, "elapsed_time": "0:21:31", "remaining_time": "0:43:05", "throughput": 5775.4, "total_tokens": 7458392} {"current_steps": 11305, "total_steps": 33920, "loss": 0.387, "lr": 8.432206099828969e-06, "epoch": 6.665683962264151, "percentage": 33.33, "elapsed_time": "0:21:31", "remaining_time": "0:43:04", "throughput": 5775.79, "total_tokens": 7462264} {"current_steps": 11310, "total_steps": 33920, "loss": 0.5668, "lr": 8.430334805700122e-06, "epoch": 6.668632075471698, "percentage": 33.34, "elapsed_time": "0:21:32", "remaining_time": "0:43:03", "throughput": 5775.71, "total_tokens": 7465048} {"current_steps": 11315, "total_steps": 33920, "loss": 0.469, "lr": 8.428462603375351e-06, "epoch": 6.671580188679245, "percentage": 33.36, "elapsed_time": "0:21:33", "remaining_time": "0:43:03", "throughput": 5775.87, "total_tokens": 7468376} {"current_steps": 11320, "total_steps": 33920, "loss": 0.4044, "lr": 8.426589493350332e-06, "epoch": 6.6745283018867925, "percentage": 33.37, "elapsed_time": "0:21:33", "remaining_time": "0:43:02", "throughput": 5776.1, "total_tokens": 7471608} {"current_steps": 11325, "total_steps": 33920, "loss": 0.4599, "lr": 8.424715476120976e-06, "epoch": 6.67747641509434, "percentage": 33.39, "elapsed_time": "0:21:34", "remaining_time": "0:43:01", "throughput": 5776.51, "total_tokens": 7475576} {"current_steps": 11330, "total_steps": 33920, "loss": 0.4661, "lr": 8.422840552183437e-06, "epoch": 6.680424528301887, "percentage": 33.4, "elapsed_time": "0:21:34", "remaining_time": "0:43:01", "throughput": 5776.57, "total_tokens": 7478616} {"current_steps": 11335, "total_steps": 33920, "loss": 0.42, "lr": 8.420964722034111e-06, "epoch": 6.683372641509434, "percentage": 33.42, "elapsed_time": "0:21:35", "remaining_time": "0:43:00", "throughput": 5776.97, "total_tokens": 7482936} {"current_steps": 11340, "total_steps": 33920, "loss": 0.3029, "lr": 8.41908798616963e-06, "epoch": 6.686320754716981, "percentage": 33.43, "elapsed_time": "0:21:35", "remaining_time": "0:43:00", "throughput": 5776.8, "total_tokens": 7485272} {"current_steps": 11345, "total_steps": 33920, "loss": 0.5398, "lr": 8.41721034508687e-06, "epoch": 6.689268867924528, "percentage": 33.45, "elapsed_time": "0:21:36", "remaining_time": "0:42:59", "throughput": 5776.93, "total_tokens": 7488344} {"current_steps": 11350, "total_steps": 33920, "loss": 0.4474, "lr": 8.415331799282942e-06, "epoch": 6.692216981132075, "percentage": 33.46, "elapsed_time": "0:21:36", "remaining_time": "0:42:58", "throughput": 5777.35, "total_tokens": 7492344} {"current_steps": 11355, "total_steps": 33920, "loss": 0.3848, "lr": 8.413452349255205e-06, "epoch": 6.695165094339623, "percentage": 33.48, "elapsed_time": "0:21:37", "remaining_time": "0:42:58", "throughput": 5777.6, "total_tokens": 7496184} {"current_steps": 11360, "total_steps": 33920, "loss": 0.4236, "lr": 8.411571995501245e-06, "epoch": 6.69811320754717, "percentage": 33.49, "elapsed_time": "0:21:38", "remaining_time": "0:42:57", "throughput": 5777.88, "total_tokens": 7499768} {"current_steps": 11365, "total_steps": 33920, "loss": 0.4957, "lr": 8.409690738518895e-06, "epoch": 6.701061320754717, "percentage": 33.51, "elapsed_time": "0:21:38", "remaining_time": "0:42:57", "throughput": 5778.12, "total_tokens": 7503192} {"current_steps": 11370, "total_steps": 33920, "loss": 0.4984, "lr": 8.407808578806229e-06, "epoch": 6.7040094339622645, "percentage": 33.52, "elapsed_time": "0:21:39", "remaining_time": "0:42:56", "throughput": 5778.37, "total_tokens": 7506712} {"current_steps": 11375, "total_steps": 33920, "loss": 0.5494, "lr": 8.405925516861555e-06, "epoch": 6.706957547169811, "percentage": 33.53, "elapsed_time": "0:21:39", "remaining_time": "0:42:55", "throughput": 5778.76, "total_tokens": 7510680} {"current_steps": 11380, "total_steps": 33920, "loss": 0.3637, "lr": 8.40404155318342e-06, "epoch": 6.709905660377358, "percentage": 33.55, "elapsed_time": "0:21:40", "remaining_time": "0:42:55", "throughput": 5778.61, "total_tokens": 7513016} {"current_steps": 11385, "total_steps": 33920, "loss": 0.3957, "lr": 8.402156688270613e-06, "epoch": 6.712853773584905, "percentage": 33.56, "elapsed_time": "0:21:40", "remaining_time": "0:42:54", "throughput": 5778.93, "total_tokens": 7516696} {"current_steps": 11390, "total_steps": 33920, "loss": 0.4848, "lr": 8.400270922622162e-06, "epoch": 6.715801886792453, "percentage": 33.58, "elapsed_time": "0:21:41", "remaining_time": "0:42:53", "throughput": 5779.27, "total_tokens": 7520344} {"current_steps": 11395, "total_steps": 33920, "loss": 0.3306, "lr": 8.398384256737328e-06, "epoch": 6.71875, "percentage": 33.59, "elapsed_time": "0:21:41", "remaining_time": "0:42:53", "throughput": 5779.64, "total_tokens": 7524024} {"current_steps": 11400, "total_steps": 33920, "loss": 0.4645, "lr": 8.396496691115619e-06, "epoch": 6.721698113207547, "percentage": 33.61, "elapsed_time": "0:21:42", "remaining_time": "0:42:52", "throughput": 5779.57, "total_tokens": 7526616} {"current_steps": 11405, "total_steps": 33920, "loss": 0.4364, "lr": 8.39460822625677e-06, "epoch": 6.724646226415095, "percentage": 33.62, "elapsed_time": "0:21:42", "remaining_time": "0:42:51", "throughput": 5779.61, "total_tokens": 7529400} {"current_steps": 11410, "total_steps": 33920, "loss": 0.573, "lr": 8.392718862660765e-06, "epoch": 6.727594339622642, "percentage": 33.64, "elapsed_time": "0:21:43", "remaining_time": "0:42:51", "throughput": 5779.41, "total_tokens": 7531864} {"current_steps": 11415, "total_steps": 33920, "loss": 0.4473, "lr": 8.390828600827818e-06, "epoch": 6.730542452830189, "percentage": 33.65, "elapsed_time": "0:21:43", "remaining_time": "0:42:50", "throughput": 5779.73, "total_tokens": 7535224} {"current_steps": 11420, "total_steps": 33920, "loss": 0.425, "lr": 8.388937441258385e-06, "epoch": 6.7334905660377355, "percentage": 33.67, "elapsed_time": "0:21:44", "remaining_time": "0:42:49", "throughput": 5780.09, "total_tokens": 7539288} {"current_steps": 11425, "total_steps": 33920, "loss": 0.441, "lr": 8.387045384453162e-06, "epoch": 6.736438679245283, "percentage": 33.68, "elapsed_time": "0:21:44", "remaining_time": "0:42:49", "throughput": 5780.07, "total_tokens": 7542168} {"current_steps": 11430, "total_steps": 33920, "loss": 0.554, "lr": 8.385152430913073e-06, "epoch": 6.73938679245283, "percentage": 33.7, "elapsed_time": "0:21:45", "remaining_time": "0:42:48", "throughput": 5780.19, "total_tokens": 7545304} {"current_steps": 11435, "total_steps": 33920, "loss": 0.4312, "lr": 8.383258581139288e-06, "epoch": 6.742334905660377, "percentage": 33.71, "elapsed_time": "0:21:45", "remaining_time": "0:42:47", "throughput": 5780.1, "total_tokens": 7547928} {"current_steps": 11440, "total_steps": 33920, "loss": 0.7171, "lr": 8.381363835633213e-06, "epoch": 6.745283018867925, "percentage": 33.73, "elapsed_time": "0:21:46", "remaining_time": "0:42:47", "throughput": 5780.32, "total_tokens": 7551096} {"current_steps": 11445, "total_steps": 33920, "loss": 0.3886, "lr": 8.379468194896492e-06, "epoch": 6.748231132075472, "percentage": 33.74, "elapsed_time": "0:21:46", "remaining_time": "0:42:46", "throughput": 5780.65, "total_tokens": 7554712} {"current_steps": 11450, "total_steps": 33920, "loss": 0.392, "lr": 8.377571659431e-06, "epoch": 6.751179245283019, "percentage": 33.76, "elapsed_time": "0:21:47", "remaining_time": "0:42:45", "throughput": 5780.87, "total_tokens": 7558136} {"current_steps": 11455, "total_steps": 33920, "loss": 0.5621, "lr": 8.375674229738855e-06, "epoch": 6.754127358490566, "percentage": 33.77, "elapsed_time": "0:21:48", "remaining_time": "0:42:45", "throughput": 5781.14, "total_tokens": 7561944} {"current_steps": 11460, "total_steps": 33920, "loss": 0.5763, "lr": 8.37377590632241e-06, "epoch": 6.757075471698113, "percentage": 33.79, "elapsed_time": "0:21:48", "remaining_time": "0:42:44", "throughput": 5781.45, "total_tokens": 7565528} {"current_steps": 11465, "total_steps": 33920, "loss": 0.3349, "lr": 8.371876689684253e-06, "epoch": 6.76002358490566, "percentage": 33.8, "elapsed_time": "0:21:49", "remaining_time": "0:42:43", "throughput": 5781.45, "total_tokens": 7568152} {"current_steps": 11470, "total_steps": 33920, "loss": 0.4289, "lr": 8.369976580327211e-06, "epoch": 6.7629716981132075, "percentage": 33.81, "elapsed_time": "0:21:49", "remaining_time": "0:42:43", "throughput": 5781.38, "total_tokens": 7570680} {"current_steps": 11475, "total_steps": 33920, "loss": 0.4548, "lr": 8.368075578754345e-06, "epoch": 6.765919811320755, "percentage": 33.83, "elapsed_time": "0:21:49", "remaining_time": "0:42:42", "throughput": 5781.65, "total_tokens": 7573848} {"current_steps": 11480, "total_steps": 33920, "loss": 0.4193, "lr": 8.366173685468952e-06, "epoch": 6.768867924528302, "percentage": 33.84, "elapsed_time": "0:21:50", "remaining_time": "0:42:41", "throughput": 5781.71, "total_tokens": 7576920} {"current_steps": 11485, "total_steps": 33920, "loss": 0.4847, "lr": 8.364270900974572e-06, "epoch": 6.771816037735849, "percentage": 33.86, "elapsed_time": "0:21:50", "remaining_time": "0:42:40", "throughput": 5781.81, "total_tokens": 7579768} {"current_steps": 11490, "total_steps": 33920, "loss": 0.523, "lr": 8.362367225774968e-06, "epoch": 6.774764150943396, "percentage": 33.87, "elapsed_time": "0:21:51", "remaining_time": "0:42:40", "throughput": 5781.82, "total_tokens": 7582424} {"current_steps": 11495, "total_steps": 33920, "loss": 0.4128, "lr": 8.360462660374153e-06, "epoch": 6.777712264150943, "percentage": 33.89, "elapsed_time": "0:21:51", "remaining_time": "0:42:39", "throughput": 5782.06, "total_tokens": 7585688} {"current_steps": 11500, "total_steps": 33920, "loss": 0.4709, "lr": 8.358557205276365e-06, "epoch": 6.78066037735849, "percentage": 33.9, "elapsed_time": "0:21:52", "remaining_time": "0:42:38", "throughput": 5782.38, "total_tokens": 7589144} {"current_steps": 11505, "total_steps": 33920, "loss": 0.4718, "lr": 8.356650860986083e-06, "epoch": 6.783608490566038, "percentage": 33.92, "elapsed_time": "0:21:52", "remaining_time": "0:42:37", "throughput": 5782.3, "total_tokens": 7591704} {"current_steps": 11510, "total_steps": 33920, "loss": 0.4928, "lr": 8.354743628008017e-06, "epoch": 6.786556603773585, "percentage": 33.93, "elapsed_time": "0:21:53", "remaining_time": "0:42:37", "throughput": 5782.46, "total_tokens": 7594680} {"current_steps": 11515, "total_steps": 33920, "loss": 0.4124, "lr": 8.35283550684712e-06, "epoch": 6.789504716981132, "percentage": 33.95, "elapsed_time": "0:21:53", "remaining_time": "0:42:36", "throughput": 5782.37, "total_tokens": 7597208} {"current_steps": 11520, "total_steps": 33920, "loss": 0.3846, "lr": 8.350926498008572e-06, "epoch": 6.7924528301886795, "percentage": 33.96, "elapsed_time": "0:21:54", "remaining_time": "0:42:36", "throughput": 5782.89, "total_tokens": 7601880} {"current_steps": 11525, "total_steps": 33920, "loss": 0.3437, "lr": 8.34901660199779e-06, "epoch": 6.795400943396227, "percentage": 33.98, "elapsed_time": "0:21:55", "remaining_time": "0:42:35", "throughput": 5782.94, "total_tokens": 7605208} {"current_steps": 11530, "total_steps": 33920, "loss": 0.3991, "lr": 8.347105819320432e-06, "epoch": 6.798349056603773, "percentage": 33.99, "elapsed_time": "0:21:55", "remaining_time": "0:42:34", "throughput": 5783.08, "total_tokens": 7608184} {"current_steps": 11535, "total_steps": 33920, "loss": 0.4036, "lr": 8.34519415048238e-06, "epoch": 6.8012971698113205, "percentage": 34.01, "elapsed_time": "0:21:56", "remaining_time": "0:42:34", "throughput": 5783.18, "total_tokens": 7611640} {"current_steps": 11540, "total_steps": 33920, "loss": 0.4668, "lr": 8.343281595989761e-06, "epoch": 6.804245283018868, "percentage": 34.02, "elapsed_time": "0:21:56", "remaining_time": "0:42:33", "throughput": 5783.28, "total_tokens": 7614808} {"current_steps": 11545, "total_steps": 33920, "loss": 0.436, "lr": 8.341368156348933e-06, "epoch": 6.807193396226415, "percentage": 34.04, "elapsed_time": "0:21:57", "remaining_time": "0:42:32", "throughput": 5783.54, "total_tokens": 7618136} {"current_steps": 11550, "total_steps": 33920, "loss": 0.539, "lr": 8.339453832066482e-06, "epoch": 6.810141509433962, "percentage": 34.05, "elapsed_time": "0:21:57", "remaining_time": "0:42:32", "throughput": 5783.93, "total_tokens": 7622264} {"current_steps": 11555, "total_steps": 33920, "loss": 0.4246, "lr": 8.337538623649237e-06, "epoch": 6.81308962264151, "percentage": 34.07, "elapsed_time": "0:21:58", "remaining_time": "0:42:31", "throughput": 5783.72, "total_tokens": 7624600} {"current_steps": 11560, "total_steps": 33920, "loss": 0.4031, "lr": 8.33562253160426e-06, "epoch": 6.816037735849057, "percentage": 34.08, "elapsed_time": "0:21:58", "remaining_time": "0:42:30", "throughput": 5784.05, "total_tokens": 7628152} {"current_steps": 11565, "total_steps": 33920, "loss": 0.4248, "lr": 8.33370555643884e-06, "epoch": 6.818985849056604, "percentage": 34.09, "elapsed_time": "0:21:59", "remaining_time": "0:42:30", "throughput": 5784.25, "total_tokens": 7631896} {"current_steps": 11570, "total_steps": 33920, "loss": 0.3935, "lr": 8.331787698660507e-06, "epoch": 6.821933962264151, "percentage": 34.11, "elapsed_time": "0:21:59", "remaining_time": "0:42:29", "throughput": 5784.21, "total_tokens": 7634616} {"current_steps": 11575, "total_steps": 33920, "loss": 0.4515, "lr": 8.32986895877702e-06, "epoch": 6.824882075471698, "percentage": 34.12, "elapsed_time": "0:22:00", "remaining_time": "0:42:28", "throughput": 5784.24, "total_tokens": 7637560} {"current_steps": 11580, "total_steps": 33920, "loss": 0.3164, "lr": 8.327949337296378e-06, "epoch": 6.827830188679245, "percentage": 34.14, "elapsed_time": "0:22:00", "remaining_time": "0:42:28", "throughput": 5784.4, "total_tokens": 7640696} {"current_steps": 11585, "total_steps": 33920, "loss": 0.4385, "lr": 8.326028834726803e-06, "epoch": 6.8307783018867925, "percentage": 34.15, "elapsed_time": "0:22:01", "remaining_time": "0:42:27", "throughput": 5784.43, "total_tokens": 7643576} {"current_steps": 11590, "total_steps": 33920, "loss": 0.4273, "lr": 8.324107451576762e-06, "epoch": 6.83372641509434, "percentage": 34.17, "elapsed_time": "0:22:01", "remaining_time": "0:42:26", "throughput": 5784.52, "total_tokens": 7646840} {"current_steps": 11595, "total_steps": 33920, "loss": 0.3965, "lr": 8.322185188354947e-06, "epoch": 6.836674528301887, "percentage": 34.18, "elapsed_time": "0:22:02", "remaining_time": "0:42:26", "throughput": 5784.54, "total_tokens": 7649848} {"current_steps": 11600, "total_steps": 33920, "loss": 0.4758, "lr": 8.320262045570284e-06, "epoch": 6.839622641509434, "percentage": 34.2, "elapsed_time": "0:22:02", "remaining_time": "0:42:25", "throughput": 5784.41, "total_tokens": 7652344} {"current_steps": 11605, "total_steps": 33920, "loss": 0.6088, "lr": 8.318338023731937e-06, "epoch": 6.842570754716981, "percentage": 34.21, "elapsed_time": "0:22:03", "remaining_time": "0:42:24", "throughput": 5784.32, "total_tokens": 7654936} {"current_steps": 11610, "total_steps": 33920, "loss": 0.4064, "lr": 8.316413123349296e-06, "epoch": 6.845518867924528, "percentage": 34.23, "elapsed_time": "0:22:03", "remaining_time": "0:42:23", "throughput": 5784.39, "total_tokens": 7657784} {"current_steps": 11615, "total_steps": 33920, "loss": 0.4841, "lr": 8.314487344931987e-06, "epoch": 6.848466981132075, "percentage": 34.24, "elapsed_time": "0:22:04", "remaining_time": "0:42:23", "throughput": 5784.56, "total_tokens": 7660920} {"current_steps": 11620, "total_steps": 33920, "loss": 0.4097, "lr": 8.31256068898987e-06, "epoch": 6.851415094339623, "percentage": 34.26, "elapsed_time": "0:22:04", "remaining_time": "0:42:22", "throughput": 5784.73, "total_tokens": 7664120} {"current_steps": 11625, "total_steps": 33920, "loss": 0.2865, "lr": 8.310633156033032e-06, "epoch": 6.85436320754717, "percentage": 34.27, "elapsed_time": "0:22:05", "remaining_time": "0:42:21", "throughput": 5784.83, "total_tokens": 7667128} {"current_steps": 11630, "total_steps": 33920, "loss": 0.5364, "lr": 8.3087047465718e-06, "epoch": 6.857311320754717, "percentage": 34.29, "elapsed_time": "0:22:05", "remaining_time": "0:42:21", "throughput": 5784.84, "total_tokens": 7669912} {"current_steps": 11635, "total_steps": 33920, "loss": 0.4674, "lr": 8.306775461116727e-06, "epoch": 6.8602594339622645, "percentage": 34.3, "elapsed_time": "0:22:06", "remaining_time": "0:42:20", "throughput": 5785.05, "total_tokens": 7673112} {"current_steps": 11640, "total_steps": 33920, "loss": 0.4549, "lr": 8.304845300178597e-06, "epoch": 6.863207547169811, "percentage": 34.32, "elapsed_time": "0:22:06", "remaining_time": "0:42:19", "throughput": 5785.16, "total_tokens": 7676088} {"current_steps": 11645, "total_steps": 33920, "loss": 0.4324, "lr": 8.302914264268433e-06, "epoch": 6.866155660377358, "percentage": 34.33, "elapsed_time": "0:22:07", "remaining_time": "0:42:19", "throughput": 5785.16, "total_tokens": 7678936} {"current_steps": 11650, "total_steps": 33920, "loss": 0.6085, "lr": 8.300982353897482e-06, "epoch": 6.869103773584905, "percentage": 34.35, "elapsed_time": "0:22:07", "remaining_time": "0:42:18", "throughput": 5785.35, "total_tokens": 7682360} {"current_steps": 11655, "total_steps": 33920, "loss": 0.3583, "lr": 8.299049569577226e-06, "epoch": 6.872051886792453, "percentage": 34.36, "elapsed_time": "0:22:08", "remaining_time": "0:42:17", "throughput": 5785.68, "total_tokens": 7685944} {"current_steps": 11660, "total_steps": 33920, "loss": 0.4451, "lr": 8.297115911819379e-06, "epoch": 6.875, "percentage": 34.38, "elapsed_time": "0:22:08", "remaining_time": "0:42:17", "throughput": 5785.76, "total_tokens": 7688824} {"current_steps": 11665, "total_steps": 33920, "loss": 0.3842, "lr": 8.295181381135884e-06, "epoch": 6.877948113207547, "percentage": 34.39, "elapsed_time": "0:22:09", "remaining_time": "0:42:16", "throughput": 5785.98, "total_tokens": 7692280} {"current_steps": 11670, "total_steps": 33920, "loss": 0.422, "lr": 8.293245978038917e-06, "epoch": 6.880896226415095, "percentage": 34.4, "elapsed_time": "0:22:10", "remaining_time": "0:42:15", "throughput": 5786.14, "total_tokens": 7695736} {"current_steps": 11675, "total_steps": 33920, "loss": 0.3823, "lr": 8.291309703040884e-06, "epoch": 6.883844339622642, "percentage": 34.42, "elapsed_time": "0:22:10", "remaining_time": "0:42:15", "throughput": 5786.31, "total_tokens": 7699000} {"current_steps": 11680, "total_steps": 33920, "loss": 0.4415, "lr": 8.289372556654422e-06, "epoch": 6.886792452830189, "percentage": 34.43, "elapsed_time": "0:22:11", "remaining_time": "0:42:14", "throughput": 5786.44, "total_tokens": 7701944} {"current_steps": 11685, "total_steps": 33920, "loss": 0.4749, "lr": 8.287434539392401e-06, "epoch": 6.8897405660377355, "percentage": 34.45, "elapsed_time": "0:22:11", "remaining_time": "0:42:14", "throughput": 5786.96, "total_tokens": 7706360} {"current_steps": 11690, "total_steps": 33920, "loss": 0.3878, "lr": 8.285495651767916e-06, "epoch": 6.892688679245283, "percentage": 34.46, "elapsed_time": "0:22:12", "remaining_time": "0:42:13", "throughput": 5787.04, "total_tokens": 7709112} {"current_steps": 11695, "total_steps": 33920, "loss": 0.4794, "lr": 8.283555894294297e-06, "epoch": 6.89563679245283, "percentage": 34.48, "elapsed_time": "0:22:13", "remaining_time": "0:42:13", "throughput": 5787.58, "total_tokens": 7715704} {"current_steps": 11700, "total_steps": 33920, "loss": 0.4183, "lr": 8.281615267485105e-06, "epoch": 6.898584905660377, "percentage": 34.49, "elapsed_time": "0:22:13", "remaining_time": "0:42:12", "throughput": 5787.72, "total_tokens": 7719320} {"current_steps": 11705, "total_steps": 33920, "loss": 0.53, "lr": 8.279673771854127e-06, "epoch": 6.901533018867925, "percentage": 34.51, "elapsed_time": "0:22:14", "remaining_time": "0:42:12", "throughput": 5787.86, "total_tokens": 7722808} {"current_steps": 11710, "total_steps": 33920, "loss": 0.588, "lr": 8.277731407915386e-06, "epoch": 6.904481132075472, "percentage": 34.52, "elapsed_time": "0:22:14", "remaining_time": "0:42:11", "throughput": 5787.89, "total_tokens": 7725848} {"current_steps": 11715, "total_steps": 33920, "loss": 0.5166, "lr": 8.275788176183126e-06, "epoch": 6.907429245283019, "percentage": 34.54, "elapsed_time": "0:22:15", "remaining_time": "0:42:11", "throughput": 5788.24, "total_tokens": 7729848} {"current_steps": 11720, "total_steps": 33920, "loss": 0.441, "lr": 8.273844077171827e-06, "epoch": 6.910377358490566, "percentage": 34.55, "elapsed_time": "0:22:16", "remaining_time": "0:42:10", "throughput": 5788.57, "total_tokens": 7734136} {"current_steps": 11725, "total_steps": 33920, "loss": 0.3997, "lr": 8.271899111396202e-06, "epoch": 6.913325471698113, "percentage": 34.57, "elapsed_time": "0:22:16", "remaining_time": "0:42:10", "throughput": 5788.61, "total_tokens": 7737560} {"current_steps": 11730, "total_steps": 33920, "loss": 0.6019, "lr": 8.269953279371185e-06, "epoch": 6.91627358490566, "percentage": 34.58, "elapsed_time": "0:22:17", "remaining_time": "0:42:09", "throughput": 5788.55, "total_tokens": 7740312} {"current_steps": 11735, "total_steps": 33920, "loss": 0.3484, "lr": 8.268006581611945e-06, "epoch": 6.9192216981132075, "percentage": 34.6, "elapsed_time": "0:22:17", "remaining_time": "0:42:08", "throughput": 5788.47, "total_tokens": 7742808} {"current_steps": 11740, "total_steps": 33920, "loss": 0.4711, "lr": 8.266059018633878e-06, "epoch": 6.922169811320755, "percentage": 34.61, "elapsed_time": "0:22:18", "remaining_time": "0:42:08", "throughput": 5788.69, "total_tokens": 7746168} {"current_steps": 11745, "total_steps": 33920, "loss": 0.3492, "lr": 8.264110590952609e-06, "epoch": 6.925117924528302, "percentage": 34.63, "elapsed_time": "0:22:18", "remaining_time": "0:42:07", "throughput": 5789.02, "total_tokens": 7749880} {"current_steps": 11750, "total_steps": 33920, "loss": 0.3994, "lr": 8.262161299083993e-06, "epoch": 6.928066037735849, "percentage": 34.64, "elapsed_time": "0:22:19", "remaining_time": "0:42:06", "throughput": 5789.11, "total_tokens": 7752984} {"current_steps": 11755, "total_steps": 33920, "loss": 0.5534, "lr": 8.260211143544117e-06, "epoch": 6.931014150943396, "percentage": 34.66, "elapsed_time": "0:22:19", "remaining_time": "0:42:06", "throughput": 5789.26, "total_tokens": 7756312} {"current_steps": 11760, "total_steps": 33920, "loss": 0.4149, "lr": 8.258260124849288e-06, "epoch": 6.933962264150943, "percentage": 34.67, "elapsed_time": "0:22:20", "remaining_time": "0:42:05", "throughput": 5788.91, "total_tokens": 7758584} {"current_steps": 11765, "total_steps": 33920, "loss": 0.4997, "lr": 8.256308243516048e-06, "epoch": 6.93691037735849, "percentage": 34.68, "elapsed_time": "0:22:20", "remaining_time": "0:42:05", "throughput": 5789.33, "total_tokens": 7762680} {"current_steps": 11770, "total_steps": 33920, "loss": 0.4599, "lr": 8.254355500061168e-06, "epoch": 6.939858490566038, "percentage": 34.7, "elapsed_time": "0:22:21", "remaining_time": "0:42:04", "throughput": 5789.71, "total_tokens": 7766552} {"current_steps": 11775, "total_steps": 33920, "loss": 0.3772, "lr": 8.252401895001643e-06, "epoch": 6.942806603773585, "percentage": 34.71, "elapsed_time": "0:22:21", "remaining_time": "0:42:03", "throughput": 5789.91, "total_tokens": 7769752} {"current_steps": 11780, "total_steps": 33920, "loss": 0.393, "lr": 8.2504474288547e-06, "epoch": 6.945754716981132, "percentage": 34.73, "elapsed_time": "0:22:22", "remaining_time": "0:42:03", "throughput": 5790.19, "total_tokens": 7773112} {"current_steps": 11785, "total_steps": 33920, "loss": 0.4728, "lr": 8.248492102137791e-06, "epoch": 6.9487028301886795, "percentage": 34.74, "elapsed_time": "0:22:22", "remaining_time": "0:42:02", "throughput": 5790.22, "total_tokens": 7775896} {"current_steps": 11790, "total_steps": 33920, "loss": 0.2882, "lr": 8.246535915368596e-06, "epoch": 6.951650943396227, "percentage": 34.76, "elapsed_time": "0:22:23", "remaining_time": "0:42:01", "throughput": 5789.98, "total_tokens": 7778264} {"current_steps": 11795, "total_steps": 33920, "loss": 0.3778, "lr": 8.24457886906503e-06, "epoch": 6.954599056603773, "percentage": 34.77, "elapsed_time": "0:22:23", "remaining_time": "0:42:00", "throughput": 5790.03, "total_tokens": 7781048} {"current_steps": 11800, "total_steps": 33920, "loss": 0.5072, "lr": 8.242620963745222e-06, "epoch": 6.9575471698113205, "percentage": 34.79, "elapsed_time": "0:22:24", "remaining_time": "0:42:00", "throughput": 5790.06, "total_tokens": 7784152} {"current_steps": 11805, "total_steps": 33920, "loss": 0.4466, "lr": 8.240662199927538e-06, "epoch": 6.960495283018868, "percentage": 34.8, "elapsed_time": "0:22:24", "remaining_time": "0:41:59", "throughput": 5790.19, "total_tokens": 7787256} {"current_steps": 11810, "total_steps": 33920, "loss": 0.5972, "lr": 8.238702578130573e-06, "epoch": 6.963443396226415, "percentage": 34.82, "elapsed_time": "0:22:25", "remaining_time": "0:41:58", "throughput": 5790.11, "total_tokens": 7789944} {"current_steps": 11815, "total_steps": 33920, "loss": 0.5488, "lr": 8.23674209887314e-06, "epoch": 6.966391509433962, "percentage": 34.83, "elapsed_time": "0:22:25", "remaining_time": "0:41:58", "throughput": 5790.41, "total_tokens": 7793752} {"current_steps": 11820, "total_steps": 33920, "loss": 0.3018, "lr": 8.234780762674288e-06, "epoch": 6.96933962264151, "percentage": 34.85, "elapsed_time": "0:22:26", "remaining_time": "0:41:57", "throughput": 5790.51, "total_tokens": 7796664} {"current_steps": 11825, "total_steps": 33920, "loss": 0.524, "lr": 8.232818570053286e-06, "epoch": 6.972287735849057, "percentage": 34.86, "elapsed_time": "0:22:26", "remaining_time": "0:41:56", "throughput": 5790.41, "total_tokens": 7799352} {"current_steps": 11830, "total_steps": 33920, "loss": 0.5217, "lr": 8.230855521529637e-06, "epoch": 6.975235849056604, "percentage": 34.88, "elapsed_time": "0:22:27", "remaining_time": "0:41:56", "throughput": 5790.57, "total_tokens": 7802360} {"current_steps": 11835, "total_steps": 33920, "loss": 0.4067, "lr": 8.228891617623064e-06, "epoch": 6.978183962264151, "percentage": 34.89, "elapsed_time": "0:22:27", "remaining_time": "0:41:55", "throughput": 5790.37, "total_tokens": 7804952} {"current_steps": 11840, "total_steps": 33920, "loss": 0.4676, "lr": 8.22692685885352e-06, "epoch": 6.981132075471698, "percentage": 34.91, "elapsed_time": "0:22:28", "remaining_time": "0:41:54", "throughput": 5790.6, "total_tokens": 7808312} {"current_steps": 11845, "total_steps": 33920, "loss": 0.4633, "lr": 8.224961245741183e-06, "epoch": 6.984080188679245, "percentage": 34.92, "elapsed_time": "0:22:28", "remaining_time": "0:41:53", "throughput": 5790.68, "total_tokens": 7811352} {"current_steps": 11850, "total_steps": 33920, "loss": 0.3804, "lr": 8.222994778806457e-06, "epoch": 6.9870283018867925, "percentage": 34.94, "elapsed_time": "0:22:29", "remaining_time": "0:41:53", "throughput": 5790.59, "total_tokens": 7813976} {"current_steps": 11855, "total_steps": 33920, "loss": 0.4361, "lr": 8.221027458569972e-06, "epoch": 6.98997641509434, "percentage": 34.95, "elapsed_time": "0:22:29", "remaining_time": "0:41:52", "throughput": 5790.45, "total_tokens": 7816664} {"current_steps": 11860, "total_steps": 33920, "loss": 0.318, "lr": 8.219059285552586e-06, "epoch": 6.992924528301887, "percentage": 34.96, "elapsed_time": "0:22:30", "remaining_time": "0:41:51", "throughput": 5790.4, "total_tokens": 7819576} {"current_steps": 11865, "total_steps": 33920, "loss": 0.3466, "lr": 8.21709026027538e-06, "epoch": 6.995872641509434, "percentage": 34.98, "elapsed_time": "0:22:30", "remaining_time": "0:41:51", "throughput": 5790.33, "total_tokens": 7822616} {"current_steps": 11870, "total_steps": 33920, "loss": 0.4409, "lr": 8.215120383259664e-06, "epoch": 6.998820754716981, "percentage": 34.99, "elapsed_time": "0:22:31", "remaining_time": "0:41:50", "throughput": 5790.34, "total_tokens": 7825944} {"current_steps": 11875, "total_steps": 33920, "loss": 0.3555, "lr": 8.21314965502697e-06, "epoch": 7.001768867924528, "percentage": 35.01, "elapsed_time": "0:22:32", "remaining_time": "0:41:50", "throughput": 5789.02, "total_tokens": 7828312} {"current_steps": 11880, "total_steps": 33920, "loss": 0.2281, "lr": 8.211178076099056e-06, "epoch": 7.004716981132075, "percentage": 35.02, "elapsed_time": "0:22:33", "remaining_time": "0:41:50", "throughput": 5789.46, "total_tokens": 7834872} {"current_steps": 11885, "total_steps": 33920, "loss": 0.2771, "lr": 8.209205646997909e-06, "epoch": 7.007665094339623, "percentage": 35.04, "elapsed_time": "0:22:33", "remaining_time": "0:41:49", "throughput": 5789.31, "total_tokens": 7837528} {"current_steps": 11890, "total_steps": 33920, "loss": 0.541, "lr": 8.207232368245735e-06, "epoch": 7.01061320754717, "percentage": 35.05, "elapsed_time": "0:22:34", "remaining_time": "0:41:49", "throughput": 5789.1, "total_tokens": 7840088} {"current_steps": 11895, "total_steps": 33920, "loss": 0.4539, "lr": 8.205258240364968e-06, "epoch": 7.013561320754717, "percentage": 35.07, "elapsed_time": "0:22:34", "remaining_time": "0:41:48", "throughput": 5789.11, "total_tokens": 7843032} {"current_steps": 11900, "total_steps": 33920, "loss": 0.401, "lr": 8.203283263878268e-06, "epoch": 7.0165094339622645, "percentage": 35.08, "elapsed_time": "0:22:35", "remaining_time": "0:41:47", "throughput": 5789.08, "total_tokens": 7846200} {"current_steps": 11905, "total_steps": 33920, "loss": 0.3884, "lr": 8.201307439308518e-06, "epoch": 7.019457547169812, "percentage": 35.1, "elapsed_time": "0:22:35", "remaining_time": "0:41:47", "throughput": 5789.06, "total_tokens": 7849144} {"current_steps": 11910, "total_steps": 33920, "loss": 0.4108, "lr": 8.199330767178828e-06, "epoch": 7.022405660377358, "percentage": 35.11, "elapsed_time": "0:22:36", "remaining_time": "0:41:46", "throughput": 5789.34, "total_tokens": 7852536} {"current_steps": 11915, "total_steps": 33920, "loss": 0.2859, "lr": 8.19735324801253e-06, "epoch": 7.025353773584905, "percentage": 35.13, "elapsed_time": "0:22:36", "remaining_time": "0:41:45", "throughput": 5789.23, "total_tokens": 7855480} {"current_steps": 11920, "total_steps": 33920, "loss": 0.4175, "lr": 8.195374882333178e-06, "epoch": 7.028301886792453, "percentage": 35.14, "elapsed_time": "0:22:37", "remaining_time": "0:41:45", "throughput": 5789.09, "total_tokens": 7858264} {"current_steps": 11925, "total_steps": 33920, "loss": 0.4256, "lr": 8.193395670664555e-06, "epoch": 7.03125, "percentage": 35.16, "elapsed_time": "0:22:37", "remaining_time": "0:41:44", "throughput": 5789.09, "total_tokens": 7860984} {"current_steps": 11930, "total_steps": 33920, "loss": 0.3041, "lr": 8.191415613530667e-06, "epoch": 7.034198113207547, "percentage": 35.17, "elapsed_time": "0:22:38", "remaining_time": "0:41:44", "throughput": 5789.43, "total_tokens": 7865400} {"current_steps": 11935, "total_steps": 33920, "loss": 0.5428, "lr": 8.189434711455739e-06, "epoch": 7.037146226415095, "percentage": 35.19, "elapsed_time": "0:22:39", "remaining_time": "0:41:43", "throughput": 5789.46, "total_tokens": 7868600} {"current_steps": 11940, "total_steps": 33920, "loss": 0.2429, "lr": 8.187452964964226e-06, "epoch": 7.040094339622642, "percentage": 35.2, "elapsed_time": "0:22:39", "remaining_time": "0:41:42", "throughput": 5789.32, "total_tokens": 7871352} {"current_steps": 11945, "total_steps": 33920, "loss": 0.4978, "lr": 8.185470374580805e-06, "epoch": 7.043042452830188, "percentage": 35.22, "elapsed_time": "0:22:40", "remaining_time": "0:41:42", "throughput": 5789.49, "total_tokens": 7874520} {"current_steps": 11950, "total_steps": 33920, "loss": 0.5216, "lr": 8.183486940830371e-06, "epoch": 7.0459905660377355, "percentage": 35.23, "elapsed_time": "0:22:40", "remaining_time": "0:41:41", "throughput": 5789.65, "total_tokens": 7877944} {"current_steps": 11955, "total_steps": 33920, "loss": 0.3632, "lr": 8.18150266423805e-06, "epoch": 7.048938679245283, "percentage": 35.24, "elapsed_time": "0:22:41", "remaining_time": "0:41:40", "throughput": 5789.8, "total_tokens": 7881112} {"current_steps": 11960, "total_steps": 33920, "loss": 0.3467, "lr": 8.179517545329188e-06, "epoch": 7.05188679245283, "percentage": 35.26, "elapsed_time": "0:22:41", "remaining_time": "0:41:40", "throughput": 5790.04, "total_tokens": 7884920} {"current_steps": 11965, "total_steps": 33920, "loss": 0.4874, "lr": 8.177531584629353e-06, "epoch": 7.054834905660377, "percentage": 35.27, "elapsed_time": "0:22:42", "remaining_time": "0:41:40", "throughput": 5790.65, "total_tokens": 7891160} {"current_steps": 11970, "total_steps": 33920, "loss": 0.3617, "lr": 8.175544782664335e-06, "epoch": 7.057783018867925, "percentage": 35.29, "elapsed_time": "0:22:43", "remaining_time": "0:41:39", "throughput": 5790.98, "total_tokens": 7894776} {"current_steps": 11975, "total_steps": 33920, "loss": 0.3546, "lr": 8.173557139960151e-06, "epoch": 7.060731132075472, "percentage": 35.3, "elapsed_time": "0:22:43", "remaining_time": "0:41:39", "throughput": 5790.86, "total_tokens": 7897464} {"current_steps": 11980, "total_steps": 33920, "loss": 0.3924, "lr": 8.17156865704304e-06, "epoch": 7.063679245283019, "percentage": 35.32, "elapsed_time": "0:22:44", "remaining_time": "0:41:38", "throughput": 5790.54, "total_tokens": 7899768} {"current_steps": 11985, "total_steps": 33920, "loss": 0.5694, "lr": 8.169579334439453e-06, "epoch": 7.066627358490566, "percentage": 35.33, "elapsed_time": "0:22:44", "remaining_time": "0:41:37", "throughput": 5790.55, "total_tokens": 7902968} {"current_steps": 11990, "total_steps": 33920, "loss": 0.3631, "lr": 8.16758917267608e-06, "epoch": 7.069575471698113, "percentage": 35.35, "elapsed_time": "0:22:45", "remaining_time": "0:41:37", "throughput": 5789.94, "total_tokens": 7905304} {"current_steps": 11995, "total_steps": 33920, "loss": 0.3753, "lr": 8.165598172279822e-06, "epoch": 7.07252358490566, "percentage": 35.36, "elapsed_time": "0:22:45", "remaining_time": "0:41:36", "throughput": 5789.47, "total_tokens": 7907704} {"current_steps": 12000, "total_steps": 33920, "loss": 0.4126, "lr": 8.163606333777804e-06, "epoch": 7.0754716981132075, "percentage": 35.38, "elapsed_time": "0:22:46", "remaining_time": "0:41:35", "throughput": 5789.72, "total_tokens": 7911000} {"current_steps": 12005, "total_steps": 33920, "loss": 0.4333, "lr": 8.161613657697374e-06, "epoch": 7.078419811320755, "percentage": 35.39, "elapsed_time": "0:22:46", "remaining_time": "0:41:35", "throughput": 5789.57, "total_tokens": 7913752} {"current_steps": 12010, "total_steps": 33920, "loss": 0.3891, "lr": 8.159620144566103e-06, "epoch": 7.081367924528302, "percentage": 35.41, "elapsed_time": "0:22:47", "remaining_time": "0:41:34", "throughput": 5789.81, "total_tokens": 7917240} {"current_steps": 12015, "total_steps": 33920, "loss": 0.5114, "lr": 8.157625794911782e-06, "epoch": 7.084316037735849, "percentage": 35.42, "elapsed_time": "0:22:47", "remaining_time": "0:41:33", "throughput": 5789.99, "total_tokens": 7920376} {"current_steps": 12020, "total_steps": 33920, "loss": 0.4484, "lr": 8.155630609262424e-06, "epoch": 7.087264150943396, "percentage": 35.44, "elapsed_time": "0:22:48", "remaining_time": "0:41:33", "throughput": 5790.12, "total_tokens": 7923608} {"current_steps": 12025, "total_steps": 33920, "loss": 0.4673, "lr": 8.153634588146262e-06, "epoch": 7.090212264150943, "percentage": 35.45, "elapsed_time": "0:22:48", "remaining_time": "0:41:32", "throughput": 5790.31, "total_tokens": 7926936} {"current_steps": 12030, "total_steps": 33920, "loss": 0.3382, "lr": 8.15163773209175e-06, "epoch": 7.09316037735849, "percentage": 35.47, "elapsed_time": "0:22:49", "remaining_time": "0:41:31", "throughput": 5790.35, "total_tokens": 7929880} {"current_steps": 12035, "total_steps": 33920, "loss": 0.6378, "lr": 8.149640041627566e-06, "epoch": 7.096108490566038, "percentage": 35.48, "elapsed_time": "0:22:50", "remaining_time": "0:41:31", "throughput": 5790.32, "total_tokens": 7932824} {"current_steps": 12040, "total_steps": 33920, "loss": 0.3601, "lr": 8.147641517282608e-06, "epoch": 7.099056603773585, "percentage": 35.5, "elapsed_time": "0:22:50", "remaining_time": "0:41:30", "throughput": 5790.44, "total_tokens": 7936088} {"current_steps": 12045, "total_steps": 33920, "loss": 0.5363, "lr": 8.145642159585992e-06, "epoch": 7.102004716981132, "percentage": 35.51, "elapsed_time": "0:22:51", "remaining_time": "0:41:30", "throughput": 5790.7, "total_tokens": 7939672} {"current_steps": 12050, "total_steps": 33920, "loss": 0.4101, "lr": 8.143641969067057e-06, "epoch": 7.1049528301886795, "percentage": 35.52, "elapsed_time": "0:22:51", "remaining_time": "0:41:29", "throughput": 5790.85, "total_tokens": 7942840} {"current_steps": 12055, "total_steps": 33920, "loss": 0.4651, "lr": 8.141640946255362e-06, "epoch": 7.107900943396227, "percentage": 35.54, "elapsed_time": "0:22:52", "remaining_time": "0:41:28", "throughput": 5790.9, "total_tokens": 7945720} {"current_steps": 12060, "total_steps": 33920, "loss": 0.381, "lr": 8.139639091680687e-06, "epoch": 7.110849056603773, "percentage": 35.55, "elapsed_time": "0:22:52", "remaining_time": "0:41:27", "throughput": 5790.64, "total_tokens": 7948152} {"current_steps": 12065, "total_steps": 33920, "loss": 0.5678, "lr": 8.137636405873031e-06, "epoch": 7.1137971698113205, "percentage": 35.57, "elapsed_time": "0:22:53", "remaining_time": "0:41:27", "throughput": 5790.82, "total_tokens": 7951704} {"current_steps": 12070, "total_steps": 33920, "loss": 0.4609, "lr": 8.135632889362614e-06, "epoch": 7.116745283018868, "percentage": 35.58, "elapsed_time": "0:22:53", "remaining_time": "0:41:27", "throughput": 5791.37, "total_tokens": 7956600} {"current_steps": 12075, "total_steps": 33920, "loss": 0.4442, "lr": 8.133628542679879e-06, "epoch": 7.119693396226415, "percentage": 35.6, "elapsed_time": "0:22:54", "remaining_time": "0:41:27", "throughput": 5792.17, "total_tokens": 7964120} {"current_steps": 12080, "total_steps": 33920, "loss": 0.5668, "lr": 8.131623366355478e-06, "epoch": 7.122641509433962, "percentage": 35.61, "elapsed_time": "0:22:55", "remaining_time": "0:41:26", "throughput": 5792.32, "total_tokens": 7967544} {"current_steps": 12085, "total_steps": 33920, "loss": 0.4981, "lr": 8.129617360920297e-06, "epoch": 7.12558962264151, "percentage": 35.63, "elapsed_time": "0:22:56", "remaining_time": "0:41:26", "throughput": 5792.18, "total_tokens": 7970264} {"current_steps": 12090, "total_steps": 33920, "loss": 0.4953, "lr": 8.12761052690543e-06, "epoch": 7.128537735849057, "percentage": 35.64, "elapsed_time": "0:22:56", "remaining_time": "0:41:25", "throughput": 5792.38, "total_tokens": 7973496} {"current_steps": 12095, "total_steps": 33920, "loss": 0.362, "lr": 8.125602864842197e-06, "epoch": 7.131485849056604, "percentage": 35.66, "elapsed_time": "0:22:57", "remaining_time": "0:41:24", "throughput": 5792.54, "total_tokens": 7976952} {"current_steps": 12100, "total_steps": 33920, "loss": 0.3519, "lr": 8.123594375262135e-06, "epoch": 7.134433962264151, "percentage": 35.67, "elapsed_time": "0:22:57", "remaining_time": "0:41:24", "throughput": 5792.67, "total_tokens": 7980088} {"current_steps": 12105, "total_steps": 33920, "loss": 0.3875, "lr": 8.121585058697e-06, "epoch": 7.137382075471698, "percentage": 35.69, "elapsed_time": "0:22:58", "remaining_time": "0:41:23", "throughput": 5792.49, "total_tokens": 7982648} {"current_steps": 12110, "total_steps": 33920, "loss": 0.5038, "lr": 8.119574915678767e-06, "epoch": 7.140330188679245, "percentage": 35.7, "elapsed_time": "0:22:58", "remaining_time": "0:41:22", "throughput": 5792.48, "total_tokens": 7985400} {"current_steps": 12115, "total_steps": 33920, "loss": 0.5605, "lr": 8.117563946739632e-06, "epoch": 7.1432783018867925, "percentage": 35.72, "elapsed_time": "0:22:59", "remaining_time": "0:41:22", "throughput": 5792.33, "total_tokens": 7987928} {"current_steps": 12120, "total_steps": 33920, "loss": 0.4284, "lr": 8.115552152412006e-06, "epoch": 7.14622641509434, "percentage": 35.73, "elapsed_time": "0:22:59", "remaining_time": "0:41:21", "throughput": 5792.64, "total_tokens": 7991960} {"current_steps": 12125, "total_steps": 33920, "loss": 0.4275, "lr": 8.11353953322852e-06, "epoch": 7.149174528301887, "percentage": 35.75, "elapsed_time": "0:23:00", "remaining_time": "0:41:21", "throughput": 5793.09, "total_tokens": 7996696} {"current_steps": 12130, "total_steps": 33920, "loss": 0.4642, "lr": 8.111526089722024e-06, "epoch": 7.152122641509434, "percentage": 35.76, "elapsed_time": "0:23:00", "remaining_time": "0:41:20", "throughput": 5793.05, "total_tokens": 7999576} {"current_steps": 12135, "total_steps": 33920, "loss": 0.5544, "lr": 8.109511822425586e-06, "epoch": 7.155070754716981, "percentage": 35.78, "elapsed_time": "0:23:01", "remaining_time": "0:41:20", "throughput": 5793.65, "total_tokens": 8004536} {"current_steps": 12140, "total_steps": 33920, "loss": 0.4123, "lr": 8.107496731872491e-06, "epoch": 7.158018867924528, "percentage": 35.79, "elapsed_time": "0:23:02", "remaining_time": "0:41:19", "throughput": 5793.66, "total_tokens": 8007288} {"current_steps": 12145, "total_steps": 33920, "loss": 0.3759, "lr": 8.105480818596243e-06, "epoch": 7.160966981132075, "percentage": 35.8, "elapsed_time": "0:23:02", "remaining_time": "0:41:18", "throughput": 5793.78, "total_tokens": 8010456} {"current_steps": 12150, "total_steps": 33920, "loss": 0.287, "lr": 8.103464083130566e-06, "epoch": 7.163915094339623, "percentage": 35.82, "elapsed_time": "0:23:03", "remaining_time": "0:41:18", "throughput": 5793.63, "total_tokens": 8013080} {"current_steps": 12155, "total_steps": 33920, "loss": 0.5479, "lr": 8.101446526009397e-06, "epoch": 7.16686320754717, "percentage": 35.83, "elapsed_time": "0:23:03", "remaining_time": "0:41:17", "throughput": 5793.65, "total_tokens": 8016056} {"current_steps": 12160, "total_steps": 33920, "loss": 0.3829, "lr": 8.099428147766894e-06, "epoch": 7.169811320754717, "percentage": 35.85, "elapsed_time": "0:23:04", "remaining_time": "0:41:16", "throughput": 5793.47, "total_tokens": 8018520} {"current_steps": 12165, "total_steps": 33920, "loss": 0.3065, "lr": 8.097408948937431e-06, "epoch": 7.1727594339622645, "percentage": 35.86, "elapsed_time": "0:23:04", "remaining_time": "0:41:16", "throughput": 5793.89, "total_tokens": 8022488} {"current_steps": 12170, "total_steps": 33920, "loss": 0.4271, "lr": 8.095388930055599e-06, "epoch": 7.175707547169812, "percentage": 35.88, "elapsed_time": "0:23:05", "remaining_time": "0:41:15", "throughput": 5794.05, "total_tokens": 8025720} {"current_steps": 12175, "total_steps": 33920, "loss": 0.3369, "lr": 8.093368091656209e-06, "epoch": 7.178655660377358, "percentage": 35.89, "elapsed_time": "0:23:05", "remaining_time": "0:41:14", "throughput": 5794.19, "total_tokens": 8028856} {"current_steps": 12180, "total_steps": 33920, "loss": 0.4204, "lr": 8.091346434274284e-06, "epoch": 7.181603773584905, "percentage": 35.91, "elapsed_time": "0:23:06", "remaining_time": "0:41:14", "throughput": 5794.4, "total_tokens": 8032216} {"current_steps": 12185, "total_steps": 33920, "loss": 0.4894, "lr": 8.089323958445068e-06, "epoch": 7.184551886792453, "percentage": 35.92, "elapsed_time": "0:23:06", "remaining_time": "0:41:13", "throughput": 5794.57, "total_tokens": 8035608} {"current_steps": 12190, "total_steps": 33920, "loss": 0.4828, "lr": 8.08730066470402e-06, "epoch": 7.1875, "percentage": 35.94, "elapsed_time": "0:23:07", "remaining_time": "0:41:12", "throughput": 5794.67, "total_tokens": 8038808} {"current_steps": 12195, "total_steps": 33920, "loss": 0.368, "lr": 8.085276553586814e-06, "epoch": 7.190448113207547, "percentage": 35.95, "elapsed_time": "0:23:07", "remaining_time": "0:41:12", "throughput": 5795.02, "total_tokens": 8042488} {"current_steps": 12200, "total_steps": 33920, "loss": 0.3617, "lr": 8.083251625629345e-06, "epoch": 7.193396226415095, "percentage": 35.97, "elapsed_time": "0:23:08", "remaining_time": "0:41:11", "throughput": 5794.91, "total_tokens": 8045144} {"current_steps": 12205, "total_steps": 33920, "loss": 0.4036, "lr": 8.08122588136772e-06, "epoch": 7.196344339622642, "percentage": 35.98, "elapsed_time": "0:23:08", "remaining_time": "0:41:10", "throughput": 5794.82, "total_tokens": 8047864} {"current_steps": 12210, "total_steps": 33920, "loss": 0.4021, "lr": 8.079199321338262e-06, "epoch": 7.199292452830188, "percentage": 36.0, "elapsed_time": "0:23:09", "remaining_time": "0:41:10", "throughput": 5794.97, "total_tokens": 8050872} {"current_steps": 12215, "total_steps": 33920, "loss": 0.4112, "lr": 8.077171946077516e-06, "epoch": 7.2022405660377355, "percentage": 36.01, "elapsed_time": "0:23:09", "remaining_time": "0:41:09", "throughput": 5794.93, "total_tokens": 8053496} {"current_steps": 12220, "total_steps": 33920, "loss": 0.3453, "lr": 8.075143756122232e-06, "epoch": 7.205188679245283, "percentage": 36.03, "elapsed_time": "0:23:10", "remaining_time": "0:41:08", "throughput": 5794.89, "total_tokens": 8056248} {"current_steps": 12225, "total_steps": 33920, "loss": 0.3943, "lr": 8.073114752009388e-06, "epoch": 7.20813679245283, "percentage": 36.04, "elapsed_time": "0:23:10", "remaining_time": "0:41:08", "throughput": 5794.83, "total_tokens": 8059032} {"current_steps": 12230, "total_steps": 33920, "loss": 0.3494, "lr": 8.071084934276168e-06, "epoch": 7.211084905660377, "percentage": 36.06, "elapsed_time": "0:23:11", "remaining_time": "0:41:07", "throughput": 5794.81, "total_tokens": 8061816} {"current_steps": 12235, "total_steps": 33920, "loss": 0.495, "lr": 8.069054303459976e-06, "epoch": 7.214033018867925, "percentage": 36.07, "elapsed_time": "0:23:11", "remaining_time": "0:41:06", "throughput": 5795.08, "total_tokens": 8065176} {"current_steps": 12240, "total_steps": 33920, "loss": 0.4357, "lr": 8.06702286009843e-06, "epoch": 7.216981132075472, "percentage": 36.08, "elapsed_time": "0:23:12", "remaining_time": "0:41:05", "throughput": 5795.05, "total_tokens": 8068120} {"current_steps": 12245, "total_steps": 33920, "loss": 0.424, "lr": 8.064990604729363e-06, "epoch": 7.219929245283019, "percentage": 36.1, "elapsed_time": "0:23:12", "remaining_time": "0:41:05", "throughput": 5795.45, "total_tokens": 8071896} {"current_steps": 12250, "total_steps": 33920, "loss": 0.4937, "lr": 8.062957537890827e-06, "epoch": 7.222877358490566, "percentage": 36.11, "elapsed_time": "0:23:13", "remaining_time": "0:41:05", "throughput": 5795.98, "total_tokens": 8076504} {"current_steps": 12255, "total_steps": 33920, "loss": 0.3749, "lr": 8.060923660121081e-06, "epoch": 7.225825471698113, "percentage": 36.13, "elapsed_time": "0:23:13", "remaining_time": "0:41:04", "throughput": 5795.82, "total_tokens": 8078872} {"current_steps": 12260, "total_steps": 33920, "loss": 0.4491, "lr": 8.058888971958603e-06, "epoch": 7.22877358490566, "percentage": 36.14, "elapsed_time": "0:23:14", "remaining_time": "0:41:03", "throughput": 5795.92, "total_tokens": 8081848} {"current_steps": 12265, "total_steps": 33920, "loss": 0.3189, "lr": 8.056853473942085e-06, "epoch": 7.2317216981132075, "percentage": 36.16, "elapsed_time": "0:23:14", "remaining_time": "0:41:02", "throughput": 5795.77, "total_tokens": 8084344} {"current_steps": 12270, "total_steps": 33920, "loss": 0.2589, "lr": 8.054817166610438e-06, "epoch": 7.234669811320755, "percentage": 36.17, "elapsed_time": "0:23:15", "remaining_time": "0:41:02", "throughput": 5795.55, "total_tokens": 8086712} {"current_steps": 12275, "total_steps": 33920, "loss": 0.3593, "lr": 8.052780050502781e-06, "epoch": 7.237617924528302, "percentage": 36.19, "elapsed_time": "0:23:15", "remaining_time": "0:41:01", "throughput": 5795.75, "total_tokens": 8089848} {"current_steps": 12280, "total_steps": 33920, "loss": 0.4967, "lr": 8.050742126158448e-06, "epoch": 7.240566037735849, "percentage": 36.2, "elapsed_time": "0:23:16", "remaining_time": "0:41:00", "throughput": 5796.0, "total_tokens": 8093176} {"current_steps": 12285, "total_steps": 33920, "loss": 0.2922, "lr": 8.04870339411699e-06, "epoch": 7.243514150943396, "percentage": 36.22, "elapsed_time": "0:23:16", "remaining_time": "0:41:00", "throughput": 5796.25, "total_tokens": 8097080} {"current_steps": 12290, "total_steps": 33920, "loss": 0.6073, "lr": 8.046663854918166e-06, "epoch": 7.246462264150943, "percentage": 36.23, "elapsed_time": "0:23:17", "remaining_time": "0:40:59", "throughput": 5796.15, "total_tokens": 8099832} {"current_steps": 12295, "total_steps": 33920, "loss": 0.3052, "lr": 8.044623509101959e-06, "epoch": 7.24941037735849, "percentage": 36.25, "elapsed_time": "0:23:17", "remaining_time": "0:40:58", "throughput": 5796.28, "total_tokens": 8102680} {"current_steps": 12300, "total_steps": 33920, "loss": 0.557, "lr": 8.042582357208557e-06, "epoch": 7.252358490566038, "percentage": 36.26, "elapsed_time": "0:23:18", "remaining_time": "0:40:58", "throughput": 5796.65, "total_tokens": 8106584} {"current_steps": 12305, "total_steps": 33920, "loss": 0.3727, "lr": 8.04054039977836e-06, "epoch": 7.255306603773585, "percentage": 36.28, "elapsed_time": "0:23:18", "remaining_time": "0:40:57", "throughput": 5796.8, "total_tokens": 8109688} {"current_steps": 12310, "total_steps": 33920, "loss": 0.3327, "lr": 8.038497637351992e-06, "epoch": 7.258254716981132, "percentage": 36.29, "elapsed_time": "0:23:19", "remaining_time": "0:40:56", "throughput": 5796.91, "total_tokens": 8112856} {"current_steps": 12315, "total_steps": 33920, "loss": 0.4205, "lr": 8.036454070470276e-06, "epoch": 7.2612028301886795, "percentage": 36.31, "elapsed_time": "0:23:19", "remaining_time": "0:40:56", "throughput": 5796.77, "total_tokens": 8115384} {"current_steps": 12320, "total_steps": 33920, "loss": 0.3896, "lr": 8.03440969967426e-06, "epoch": 7.264150943396227, "percentage": 36.32, "elapsed_time": "0:23:20", "remaining_time": "0:40:55", "throughput": 5797.0, "total_tokens": 8118840} {"current_steps": 12325, "total_steps": 33920, "loss": 0.3146, "lr": 8.032364525505198e-06, "epoch": 7.267099056603773, "percentage": 36.34, "elapsed_time": "0:23:21", "remaining_time": "0:40:54", "throughput": 5797.44, "total_tokens": 8122808} {"current_steps": 12330, "total_steps": 33920, "loss": 0.3651, "lr": 8.030318548504561e-06, "epoch": 7.2700471698113205, "percentage": 36.35, "elapsed_time": "0:23:21", "remaining_time": "0:40:54", "throughput": 5797.55, "total_tokens": 8125912} {"current_steps": 12335, "total_steps": 33920, "loss": 0.5903, "lr": 8.028271769214026e-06, "epoch": 7.272995283018868, "percentage": 36.36, "elapsed_time": "0:23:22", "remaining_time": "0:40:53", "throughput": 5797.85, "total_tokens": 8130008} {"current_steps": 12340, "total_steps": 33920, "loss": 0.3305, "lr": 8.02622418817549e-06, "epoch": 7.275943396226415, "percentage": 36.38, "elapsed_time": "0:23:22", "remaining_time": "0:40:53", "throughput": 5798.0, "total_tokens": 8133112} {"current_steps": 12345, "total_steps": 33920, "loss": 0.3108, "lr": 8.024175805931056e-06, "epoch": 7.278891509433962, "percentage": 36.39, "elapsed_time": "0:23:23", "remaining_time": "0:40:52", "throughput": 5798.38, "total_tokens": 8137240} {"current_steps": 12350, "total_steps": 33920, "loss": 0.4009, "lr": 8.022126623023045e-06, "epoch": 7.28183962264151, "percentage": 36.41, "elapsed_time": "0:23:23", "remaining_time": "0:40:51", "throughput": 5798.52, "total_tokens": 8140216} {"current_steps": 12355, "total_steps": 33920, "loss": 0.3393, "lr": 8.020076639993987e-06, "epoch": 7.284787735849057, "percentage": 36.42, "elapsed_time": "0:23:24", "remaining_time": "0:40:51", "throughput": 5798.62, "total_tokens": 8143256} {"current_steps": 12360, "total_steps": 33920, "loss": 0.3125, "lr": 8.018025857386622e-06, "epoch": 7.287735849056604, "percentage": 36.44, "elapsed_time": "0:23:24", "remaining_time": "0:40:50", "throughput": 5798.89, "total_tokens": 8146648} {"current_steps": 12365, "total_steps": 33920, "loss": 0.4056, "lr": 8.015974275743905e-06, "epoch": 7.290683962264151, "percentage": 36.45, "elapsed_time": "0:23:25", "remaining_time": "0:40:49", "throughput": 5798.96, "total_tokens": 8149656} {"current_steps": 12370, "total_steps": 33920, "loss": 0.4872, "lr": 8.013921895609e-06, "epoch": 7.293632075471698, "percentage": 36.47, "elapsed_time": "0:23:25", "remaining_time": "0:40:49", "throughput": 5799.07, "total_tokens": 8152856} {"current_steps": 12375, "total_steps": 33920, "loss": 0.4503, "lr": 8.011868717525283e-06, "epoch": 7.296580188679245, "percentage": 36.48, "elapsed_time": "0:23:26", "remaining_time": "0:40:48", "throughput": 5799.03, "total_tokens": 8155512} {"current_steps": 12380, "total_steps": 33920, "loss": 0.4159, "lr": 8.009814742036343e-06, "epoch": 7.2995283018867925, "percentage": 36.5, "elapsed_time": "0:23:26", "remaining_time": "0:40:47", "throughput": 5799.1, "total_tokens": 8158584} {"current_steps": 12385, "total_steps": 33920, "loss": 0.385, "lr": 8.007759969685979e-06, "epoch": 7.30247641509434, "percentage": 36.51, "elapsed_time": "0:23:27", "remaining_time": "0:40:47", "throughput": 5799.13, "total_tokens": 8161912} {"current_steps": 12390, "total_steps": 33920, "loss": 0.4315, "lr": 8.005704401018199e-06, "epoch": 7.305424528301887, "percentage": 36.53, "elapsed_time": "0:23:27", "remaining_time": "0:40:46", "throughput": 5799.2, "total_tokens": 8165080} {"current_steps": 12395, "total_steps": 33920, "loss": 0.3556, "lr": 8.003648036577226e-06, "epoch": 7.308372641509434, "percentage": 36.54, "elapsed_time": "0:23:28", "remaining_time": "0:40:46", "throughput": 5799.48, "total_tokens": 8169240} {"current_steps": 12400, "total_steps": 33920, "loss": 0.3136, "lr": 8.00159087690749e-06, "epoch": 7.311320754716981, "percentage": 36.56, "elapsed_time": "0:23:29", "remaining_time": "0:40:45", "throughput": 5799.29, "total_tokens": 8171544} {"current_steps": 12405, "total_steps": 33920, "loss": 0.3956, "lr": 7.999532922553635e-06, "epoch": 7.314268867924528, "percentage": 36.57, "elapsed_time": "0:23:29", "remaining_time": "0:40:44", "throughput": 5799.42, "total_tokens": 8174712} {"current_steps": 12410, "total_steps": 33920, "loss": 0.3863, "lr": 7.997474174060508e-06, "epoch": 7.317216981132075, "percentage": 36.59, "elapsed_time": "0:23:30", "remaining_time": "0:40:44", "throughput": 5799.9, "total_tokens": 8179192} {"current_steps": 12415, "total_steps": 33920, "loss": 0.4067, "lr": 7.995414631973179e-06, "epoch": 7.320165094339623, "percentage": 36.6, "elapsed_time": "0:23:30", "remaining_time": "0:40:43", "throughput": 5800.22, "total_tokens": 8183416} {"current_steps": 12420, "total_steps": 33920, "loss": 0.3012, "lr": 7.993354296836914e-06, "epoch": 7.32311320754717, "percentage": 36.62, "elapsed_time": "0:23:31", "remaining_time": "0:40:43", "throughput": 5800.35, "total_tokens": 8186648} {"current_steps": 12425, "total_steps": 33920, "loss": 0.4547, "lr": 7.991293169197198e-06, "epoch": 7.326061320754717, "percentage": 36.63, "elapsed_time": "0:23:31", "remaining_time": "0:40:42", "throughput": 5800.58, "total_tokens": 8189912} {"current_steps": 12430, "total_steps": 33920, "loss": 0.4129, "lr": 7.989231249599725e-06, "epoch": 7.3290094339622645, "percentage": 36.65, "elapsed_time": "0:23:32", "remaining_time": "0:40:41", "throughput": 5800.84, "total_tokens": 8193496} {"current_steps": 12435, "total_steps": 33920, "loss": 0.3314, "lr": 7.987168538590395e-06, "epoch": 7.331957547169811, "percentage": 36.66, "elapsed_time": "0:23:32", "remaining_time": "0:40:41", "throughput": 5800.79, "total_tokens": 8196376} {"current_steps": 12440, "total_steps": 33920, "loss": 0.4108, "lr": 7.985105036715322e-06, "epoch": 7.334905660377358, "percentage": 36.67, "elapsed_time": "0:23:33", "remaining_time": "0:40:40", "throughput": 5800.98, "total_tokens": 8200024} {"current_steps": 12445, "total_steps": 33920, "loss": 0.4297, "lr": 7.983040744520823e-06, "epoch": 7.337853773584905, "percentage": 36.69, "elapsed_time": "0:23:34", "remaining_time": "0:40:40", "throughput": 5801.41, "total_tokens": 8205080} {"current_steps": 12450, "total_steps": 33920, "loss": 0.3954, "lr": 7.980975662553432e-06, "epoch": 7.340801886792453, "percentage": 36.7, "elapsed_time": "0:23:34", "remaining_time": "0:40:39", "throughput": 5801.35, "total_tokens": 8208248} {"current_steps": 12455, "total_steps": 33920, "loss": 0.3764, "lr": 7.978909791359888e-06, "epoch": 7.34375, "percentage": 36.72, "elapsed_time": "0:23:35", "remaining_time": "0:40:39", "throughput": 5801.64, "total_tokens": 8211896} {"current_steps": 12460, "total_steps": 33920, "loss": 0.3915, "lr": 7.976843131487136e-06, "epoch": 7.346698113207547, "percentage": 36.73, "elapsed_time": "0:23:35", "remaining_time": "0:40:38", "throughput": 5801.54, "total_tokens": 8214616} {"current_steps": 12465, "total_steps": 33920, "loss": 0.4368, "lr": 7.974775683482337e-06, "epoch": 7.349646226415095, "percentage": 36.75, "elapsed_time": "0:23:36", "remaining_time": "0:40:38", "throughput": 5801.66, "total_tokens": 8217976} {"current_steps": 12470, "total_steps": 33920, "loss": 0.4141, "lr": 7.972707447892855e-06, "epoch": 7.352594339622642, "percentage": 36.76, "elapsed_time": "0:23:37", "remaining_time": "0:40:37", "throughput": 5801.83, "total_tokens": 8221624} {"current_steps": 12475, "total_steps": 33920, "loss": 0.2845, "lr": 7.970638425266264e-06, "epoch": 7.355542452830189, "percentage": 36.78, "elapsed_time": "0:23:37", "remaining_time": "0:40:36", "throughput": 5801.99, "total_tokens": 8224632} {"current_steps": 12480, "total_steps": 33920, "loss": 0.4526, "lr": 7.968568616150349e-06, "epoch": 7.3584905660377355, "percentage": 36.79, "elapsed_time": "0:23:38", "remaining_time": "0:40:36", "throughput": 5802.39, "total_tokens": 8228824} {"current_steps": 12485, "total_steps": 33920, "loss": 0.5487, "lr": 7.966498021093096e-06, "epoch": 7.361438679245283, "percentage": 36.81, "elapsed_time": "0:23:38", "remaining_time": "0:40:35", "throughput": 5802.5, "total_tokens": 8231736} {"current_steps": 12490, "total_steps": 33920, "loss": 0.3745, "lr": 7.96442664064271e-06, "epoch": 7.36438679245283, "percentage": 36.82, "elapsed_time": "0:23:39", "remaining_time": "0:40:34", "throughput": 5802.64, "total_tokens": 8235000} {"current_steps": 12495, "total_steps": 33920, "loss": 0.4795, "lr": 7.962354475347593e-06, "epoch": 7.367334905660377, "percentage": 36.84, "elapsed_time": "0:23:39", "remaining_time": "0:40:34", "throughput": 5802.78, "total_tokens": 8238328} {"current_steps": 12500, "total_steps": 33920, "loss": 0.5202, "lr": 7.960281525756364e-06, "epoch": 7.370283018867925, "percentage": 36.85, "elapsed_time": "0:23:40", "remaining_time": "0:40:33", "throughput": 5802.94, "total_tokens": 8242136} {"current_steps": 12505, "total_steps": 33920, "loss": 0.3696, "lr": 7.95820779241784e-06, "epoch": 7.373231132075472, "percentage": 36.87, "elapsed_time": "0:23:40", "remaining_time": "0:40:33", "throughput": 5803.06, "total_tokens": 8245496} {"current_steps": 12510, "total_steps": 33920, "loss": 0.5257, "lr": 7.956133275881055e-06, "epoch": 7.376179245283019, "percentage": 36.88, "elapsed_time": "0:23:41", "remaining_time": "0:40:32", "throughput": 5803.45, "total_tokens": 8249560} {"current_steps": 12515, "total_steps": 33920, "loss": 0.2659, "lr": 7.954057976695244e-06, "epoch": 7.379127358490566, "percentage": 36.9, "elapsed_time": "0:23:42", "remaining_time": "0:40:32", "throughput": 5803.59, "total_tokens": 8252920} {"current_steps": 12520, "total_steps": 33920, "loss": 0.418, "lr": 7.951981895409854e-06, "epoch": 7.382075471698113, "percentage": 36.91, "elapsed_time": "0:23:42", "remaining_time": "0:40:31", "throughput": 5803.79, "total_tokens": 8256792} {"current_steps": 12525, "total_steps": 33920, "loss": 0.3879, "lr": 7.949905032574534e-06, "epoch": 7.38502358490566, "percentage": 36.93, "elapsed_time": "0:23:43", "remaining_time": "0:40:31", "throughput": 5803.92, "total_tokens": 8260088} {"current_steps": 12530, "total_steps": 33920, "loss": 0.346, "lr": 7.947827388739145e-06, "epoch": 7.3879716981132075, "percentage": 36.94, "elapsed_time": "0:23:43", "remaining_time": "0:40:30", "throughput": 5803.96, "total_tokens": 8263096} {"current_steps": 12535, "total_steps": 33920, "loss": 0.4257, "lr": 7.945748964453747e-06, "epoch": 7.390919811320755, "percentage": 36.95, "elapsed_time": "0:23:44", "remaining_time": "0:40:29", "throughput": 5804.52, "total_tokens": 8267736} {"current_steps": 12540, "total_steps": 33920, "loss": 0.3682, "lr": 7.943669760268618e-06, "epoch": 7.393867924528302, "percentage": 36.97, "elapsed_time": "0:23:44", "remaining_time": "0:40:29", "throughput": 5804.41, "total_tokens": 8270296} {"current_steps": 12545, "total_steps": 33920, "loss": 0.3684, "lr": 7.941589776734232e-06, "epoch": 7.396816037735849, "percentage": 36.98, "elapsed_time": "0:23:45", "remaining_time": "0:40:28", "throughput": 5804.75, "total_tokens": 8274232} {"current_steps": 12550, "total_steps": 33920, "loss": 0.4721, "lr": 7.939509014401277e-06, "epoch": 7.399764150943396, "percentage": 37.0, "elapsed_time": "0:23:45", "remaining_time": "0:40:28", "throughput": 5804.87, "total_tokens": 8277240} {"current_steps": 12555, "total_steps": 33920, "loss": 0.4506, "lr": 7.93742747382064e-06, "epoch": 7.402712264150943, "percentage": 37.01, "elapsed_time": "0:23:46", "remaining_time": "0:40:27", "throughput": 5804.91, "total_tokens": 8280664} {"current_steps": 12560, "total_steps": 33920, "loss": 0.4691, "lr": 7.93534515554342e-06, "epoch": 7.40566037735849, "percentage": 37.03, "elapsed_time": "0:23:46", "remaining_time": "0:40:26", "throughput": 5804.59, "total_tokens": 8282968} {"current_steps": 12565, "total_steps": 33920, "loss": 0.3627, "lr": 7.933262060120918e-06, "epoch": 7.408608490566038, "percentage": 37.04, "elapsed_time": "0:23:47", "remaining_time": "0:40:26", "throughput": 5804.5, "total_tokens": 8285880} {"current_steps": 12570, "total_steps": 33920, "loss": 0.5136, "lr": 7.931178188104646e-06, "epoch": 7.411556603773585, "percentage": 37.06, "elapsed_time": "0:23:48", "remaining_time": "0:40:25", "throughput": 5804.15, "total_tokens": 8288440} {"current_steps": 12575, "total_steps": 33920, "loss": 0.3408, "lr": 7.929093540046317e-06, "epoch": 7.414504716981132, "percentage": 37.07, "elapsed_time": "0:23:48", "remaining_time": "0:40:24", "throughput": 5804.25, "total_tokens": 8291576} {"current_steps": 12580, "total_steps": 33920, "loss": 0.3392, "lr": 7.927008116497848e-06, "epoch": 7.4174528301886795, "percentage": 37.09, "elapsed_time": "0:23:49", "remaining_time": "0:40:24", "throughput": 5804.21, "total_tokens": 8294552} {"current_steps": 12585, "total_steps": 33920, "loss": 0.4557, "lr": 7.924921918011366e-06, "epoch": 7.420400943396227, "percentage": 37.1, "elapsed_time": "0:23:49", "remaining_time": "0:40:23", "throughput": 5804.06, "total_tokens": 8297176} {"current_steps": 12590, "total_steps": 33920, "loss": 0.618, "lr": 7.9228349451392e-06, "epoch": 7.423349056603773, "percentage": 37.12, "elapsed_time": "0:23:50", "remaining_time": "0:40:22", "throughput": 5804.44, "total_tokens": 8301208} {"current_steps": 12595, "total_steps": 33920, "loss": 0.4359, "lr": 7.920747198433884e-06, "epoch": 7.4262971698113205, "percentage": 37.13, "elapsed_time": "0:23:50", "remaining_time": "0:40:22", "throughput": 5804.7, "total_tokens": 8304920} {"current_steps": 12600, "total_steps": 33920, "loss": 0.4272, "lr": 7.91865867844816e-06, "epoch": 7.429245283018868, "percentage": 37.15, "elapsed_time": "0:23:51", "remaining_time": "0:40:21", "throughput": 5804.6, "total_tokens": 8307448} {"current_steps": 12605, "total_steps": 33920, "loss": 0.3848, "lr": 7.916569385734976e-06, "epoch": 7.432193396226415, "percentage": 37.16, "elapsed_time": "0:23:51", "remaining_time": "0:40:21", "throughput": 5804.84, "total_tokens": 8310840} {"current_steps": 12610, "total_steps": 33920, "loss": 0.4, "lr": 7.914479320847474e-06, "epoch": 7.435141509433962, "percentage": 37.18, "elapsed_time": "0:23:52", "remaining_time": "0:40:20", "throughput": 5805.0, "total_tokens": 8314136} {"current_steps": 12615, "total_steps": 33920, "loss": 0.2877, "lr": 7.912388484339012e-06, "epoch": 7.43808962264151, "percentage": 37.19, "elapsed_time": "0:23:52", "remaining_time": "0:40:19", "throughput": 5805.33, "total_tokens": 8318232} {"current_steps": 12620, "total_steps": 33920, "loss": 0.6555, "lr": 7.910296876763147e-06, "epoch": 7.441037735849057, "percentage": 37.21, "elapsed_time": "0:23:53", "remaining_time": "0:40:19", "throughput": 5805.33, "total_tokens": 8321080} {"current_steps": 12625, "total_steps": 33920, "loss": 0.4273, "lr": 7.90820449867364e-06, "epoch": 7.443985849056604, "percentage": 37.22, "elapsed_time": "0:23:53", "remaining_time": "0:40:18", "throughput": 5805.27, "total_tokens": 8323928} {"current_steps": 12630, "total_steps": 33920, "loss": 0.5016, "lr": 7.90611135062446e-06, "epoch": 7.446933962264151, "percentage": 37.23, "elapsed_time": "0:23:54", "remaining_time": "0:40:18", "throughput": 5805.47, "total_tokens": 8327640} {"current_steps": 12635, "total_steps": 33920, "loss": 0.4359, "lr": 7.904017433169775e-06, "epoch": 7.449882075471698, "percentage": 37.25, "elapsed_time": "0:23:55", "remaining_time": "0:40:17", "throughput": 5805.8, "total_tokens": 8332088} {"current_steps": 12640, "total_steps": 33920, "loss": 0.4862, "lr": 7.901922746863957e-06, "epoch": 7.452830188679245, "percentage": 37.26, "elapsed_time": "0:23:55", "remaining_time": "0:40:16", "throughput": 5805.94, "total_tokens": 8335192} {"current_steps": 12645, "total_steps": 33920, "loss": 0.4067, "lr": 7.899827292261589e-06, "epoch": 7.4557783018867925, "percentage": 37.28, "elapsed_time": "0:23:56", "remaining_time": "0:40:16", "throughput": 5805.71, "total_tokens": 8337944} {"current_steps": 12650, "total_steps": 33920, "loss": 0.3311, "lr": 7.897731069917444e-06, "epoch": 7.45872641509434, "percentage": 37.29, "elapsed_time": "0:23:56", "remaining_time": "0:40:15", "throughput": 5805.92, "total_tokens": 8341208} {"current_steps": 12655, "total_steps": 33920, "loss": 0.3819, "lr": 7.895634080386512e-06, "epoch": 7.461674528301887, "percentage": 37.31, "elapsed_time": "0:23:57", "remaining_time": "0:40:14", "throughput": 5806.14, "total_tokens": 8344376} {"current_steps": 12660, "total_steps": 33920, "loss": 0.4465, "lr": 7.893536324223977e-06, "epoch": 7.464622641509434, "percentage": 37.32, "elapsed_time": "0:23:57", "remaining_time": "0:40:14", "throughput": 5806.28, "total_tokens": 8347736} {"current_steps": 12665, "total_steps": 33920, "loss": 0.3517, "lr": 7.89143780198523e-06, "epoch": 7.467570754716981, "percentage": 37.34, "elapsed_time": "0:23:58", "remaining_time": "0:40:13", "throughput": 5806.69, "total_tokens": 8351992} {"current_steps": 12670, "total_steps": 33920, "loss": 0.4466, "lr": 7.889338514225862e-06, "epoch": 7.470518867924528, "percentage": 37.35, "elapsed_time": "0:23:58", "remaining_time": "0:40:13", "throughput": 5806.59, "total_tokens": 8354968} {"current_steps": 12675, "total_steps": 33920, "loss": 0.4257, "lr": 7.887238461501671e-06, "epoch": 7.473466981132075, "percentage": 37.37, "elapsed_time": "0:23:59", "remaining_time": "0:40:12", "throughput": 5806.81, "total_tokens": 8358360} {"current_steps": 12680, "total_steps": 33920, "loss": 0.3245, "lr": 7.885137644368654e-06, "epoch": 7.476415094339623, "percentage": 37.38, "elapsed_time": "0:23:59", "remaining_time": "0:40:12", "throughput": 5806.84, "total_tokens": 8361496} {"current_steps": 12685, "total_steps": 33920, "loss": 0.3441, "lr": 7.883036063383012e-06, "epoch": 7.47936320754717, "percentage": 37.4, "elapsed_time": "0:24:00", "remaining_time": "0:40:11", "throughput": 5806.86, "total_tokens": 8364344} {"current_steps": 12690, "total_steps": 33920, "loss": 0.4532, "lr": 7.880933719101148e-06, "epoch": 7.482311320754717, "percentage": 37.41, "elapsed_time": "0:24:01", "remaining_time": "0:40:10", "throughput": 5807.18, "total_tokens": 8368344} {"current_steps": 12695, "total_steps": 33920, "loss": 0.3592, "lr": 7.878830612079664e-06, "epoch": 7.4852594339622645, "percentage": 37.43, "elapsed_time": "0:24:01", "remaining_time": "0:40:10", "throughput": 5807.11, "total_tokens": 8371224} {"current_steps": 12700, "total_steps": 33920, "loss": 0.4829, "lr": 7.876726742875369e-06, "epoch": 7.488207547169811, "percentage": 37.44, "elapsed_time": "0:24:02", "remaining_time": "0:40:09", "throughput": 5807.46, "total_tokens": 8375064} {"current_steps": 12705, "total_steps": 33920, "loss": 0.3579, "lr": 7.874622112045269e-06, "epoch": 7.491155660377358, "percentage": 37.46, "elapsed_time": "0:24:02", "remaining_time": "0:40:09", "throughput": 5807.82, "total_tokens": 8378840} {"current_steps": 12710, "total_steps": 33920, "loss": 0.4134, "lr": 7.872516720146578e-06, "epoch": 7.494103773584905, "percentage": 37.47, "elapsed_time": "0:24:03", "remaining_time": "0:40:08", "throughput": 5808.19, "total_tokens": 8382872} {"current_steps": 12715, "total_steps": 33920, "loss": 0.3694, "lr": 7.870410567736705e-06, "epoch": 7.497051886792453, "percentage": 37.49, "elapsed_time": "0:24:03", "remaining_time": "0:40:07", "throughput": 5808.11, "total_tokens": 8385464} {"current_steps": 12720, "total_steps": 33920, "loss": 0.4036, "lr": 7.868303655373264e-06, "epoch": 7.5, "percentage": 37.5, "elapsed_time": "0:24:04", "remaining_time": "0:40:07", "throughput": 5808.27, "total_tokens": 8388856} {"current_steps": 12725, "total_steps": 33920, "loss": 0.4558, "lr": 7.866195983614066e-06, "epoch": 7.502948113207547, "percentage": 37.51, "elapsed_time": "0:24:04", "remaining_time": "0:40:06", "throughput": 5808.27, "total_tokens": 8391832} {"current_steps": 12730, "total_steps": 33920, "loss": 0.3876, "lr": 7.864087553017133e-06, "epoch": 7.505896226415095, "percentage": 37.53, "elapsed_time": "0:24:05", "remaining_time": "0:40:05", "throughput": 5808.54, "total_tokens": 8395544} {"current_steps": 12735, "total_steps": 33920, "loss": 0.4424, "lr": 7.861978364140674e-06, "epoch": 7.508844339622642, "percentage": 37.54, "elapsed_time": "0:24:05", "remaining_time": "0:40:05", "throughput": 5808.62, "total_tokens": 8398840} {"current_steps": 12740, "total_steps": 33920, "loss": 0.4938, "lr": 7.859868417543109e-06, "epoch": 7.511792452830189, "percentage": 37.56, "elapsed_time": "0:24:06", "remaining_time": "0:40:04", "throughput": 5808.54, "total_tokens": 8401688} {"current_steps": 12745, "total_steps": 33920, "loss": 0.3881, "lr": 7.857757713783055e-06, "epoch": 7.5147405660377355, "percentage": 37.57, "elapsed_time": "0:24:07", "remaining_time": "0:40:04", "throughput": 5809.17, "total_tokens": 8406520} {"current_steps": 12750, "total_steps": 33920, "loss": 0.4287, "lr": 7.855646253419331e-06, "epoch": 7.517688679245283, "percentage": 37.59, "elapsed_time": "0:24:07", "remaining_time": "0:40:03", "throughput": 5809.36, "total_tokens": 8410360} {"current_steps": 12755, "total_steps": 33920, "loss": 0.4079, "lr": 7.853534037010952e-06, "epoch": 7.52063679245283, "percentage": 37.6, "elapsed_time": "0:24:08", "remaining_time": "0:40:03", "throughput": 5809.59, "total_tokens": 8413848} {"current_steps": 12760, "total_steps": 33920, "loss": 0.478, "lr": 7.851421065117142e-06, "epoch": 7.523584905660377, "percentage": 37.62, "elapsed_time": "0:24:08", "remaining_time": "0:40:02", "throughput": 5809.93, "total_tokens": 8418232} {"current_steps": 12765, "total_steps": 33920, "loss": 0.4866, "lr": 7.849307338297314e-06, "epoch": 7.526533018867925, "percentage": 37.63, "elapsed_time": "0:24:09", "remaining_time": "0:40:02", "throughput": 5810.33, "total_tokens": 8422360} {"current_steps": 12770, "total_steps": 33920, "loss": 0.3786, "lr": 7.847192857111087e-06, "epoch": 7.529481132075472, "percentage": 37.65, "elapsed_time": "0:24:10", "remaining_time": "0:40:01", "throughput": 5810.56, "total_tokens": 8426040} {"current_steps": 12775, "total_steps": 33920, "loss": 0.3595, "lr": 7.845077622118282e-06, "epoch": 7.532429245283019, "percentage": 37.66, "elapsed_time": "0:24:10", "remaining_time": "0:40:01", "throughput": 5810.38, "total_tokens": 8428536} {"current_steps": 12780, "total_steps": 33920, "loss": 0.4823, "lr": 7.842961633878916e-06, "epoch": 7.535377358490566, "percentage": 37.68, "elapsed_time": "0:24:11", "remaining_time": "0:40:00", "throughput": 5810.4, "total_tokens": 8431736} {"current_steps": 12785, "total_steps": 33920, "loss": 0.4486, "lr": 7.840844892953204e-06, "epoch": 7.538325471698113, "percentage": 37.69, "elapsed_time": "0:24:11", "remaining_time": "0:39:59", "throughput": 5810.5, "total_tokens": 8435096} {"current_steps": 12790, "total_steps": 33920, "loss": 0.3923, "lr": 7.838727399901562e-06, "epoch": 7.54127358490566, "percentage": 37.71, "elapsed_time": "0:24:12", "remaining_time": "0:39:59", "throughput": 5810.47, "total_tokens": 8438072} {"current_steps": 12795, "total_steps": 33920, "loss": 0.4602, "lr": 7.836609155284607e-06, "epoch": 7.5442216981132075, "percentage": 37.72, "elapsed_time": "0:24:12", "remaining_time": "0:39:58", "throughput": 5810.66, "total_tokens": 8441432} {"current_steps": 12800, "total_steps": 33920, "loss": 0.3183, "lr": 7.834490159663154e-06, "epoch": 7.547169811320755, "percentage": 37.74, "elapsed_time": "0:24:13", "remaining_time": "0:39:57", "throughput": 5810.75, "total_tokens": 8444472} {"current_steps": 12805, "total_steps": 33920, "loss": 0.4815, "lr": 7.832370413598215e-06, "epoch": 7.550117924528302, "percentage": 37.75, "elapsed_time": "0:24:13", "remaining_time": "0:39:57", "throughput": 5810.89, "total_tokens": 8448152} {"current_steps": 12810, "total_steps": 33920, "loss": 0.3048, "lr": 7.830249917651003e-06, "epoch": 7.553066037735849, "percentage": 37.77, "elapsed_time": "0:24:14", "remaining_time": "0:39:56", "throughput": 5810.99, "total_tokens": 8451288} {"current_steps": 12815, "total_steps": 33920, "loss": 0.4801, "lr": 7.828128672382926e-06, "epoch": 7.556014150943396, "percentage": 37.78, "elapsed_time": "0:24:14", "remaining_time": "0:39:56", "throughput": 5810.62, "total_tokens": 8453848} {"current_steps": 12820, "total_steps": 33920, "loss": 0.4045, "lr": 7.826006678355596e-06, "epoch": 7.558962264150943, "percentage": 37.79, "elapsed_time": "0:24:15", "remaining_time": "0:39:55", "throughput": 5810.5, "total_tokens": 8456536} {"current_steps": 12825, "total_steps": 33920, "loss": 0.4178, "lr": 7.823883936130817e-06, "epoch": 7.56191037735849, "percentage": 37.81, "elapsed_time": "0:24:15", "remaining_time": "0:39:54", "throughput": 5810.28, "total_tokens": 8459032} {"current_steps": 12830, "total_steps": 33920, "loss": 0.4196, "lr": 7.821760446270597e-06, "epoch": 7.564858490566038, "percentage": 37.82, "elapsed_time": "0:24:16", "remaining_time": "0:39:53", "throughput": 5810.34, "total_tokens": 8462008} {"current_steps": 12835, "total_steps": 33920, "loss": 0.4354, "lr": 7.819636209337136e-06, "epoch": 7.567806603773585, "percentage": 37.84, "elapsed_time": "0:24:16", "remaining_time": "0:39:53", "throughput": 5810.54, "total_tokens": 8465464} {"current_steps": 12840, "total_steps": 33920, "loss": 0.3966, "lr": 7.817511225892838e-06, "epoch": 7.570754716981132, "percentage": 37.85, "elapsed_time": "0:24:17", "remaining_time": "0:39:52", "throughput": 5810.76, "total_tokens": 8468856} {"current_steps": 12845, "total_steps": 33920, "loss": 0.3088, "lr": 7.8153854965003e-06, "epoch": 7.5737028301886795, "percentage": 37.87, "elapsed_time": "0:24:17", "remaining_time": "0:39:52", "throughput": 5810.59, "total_tokens": 8471576} {"current_steps": 12850, "total_steps": 33920, "loss": 0.3737, "lr": 7.813259021722319e-06, "epoch": 7.576650943396227, "percentage": 37.88, "elapsed_time": "0:24:18", "remaining_time": "0:39:51", "throughput": 5810.49, "total_tokens": 8474232} {"current_steps": 12855, "total_steps": 33920, "loss": 0.3267, "lr": 7.811131802121885e-06, "epoch": 7.579599056603773, "percentage": 37.9, "elapsed_time": "0:24:19", "remaining_time": "0:39:50", "throughput": 5810.94, "total_tokens": 8478744} {"current_steps": 12860, "total_steps": 33920, "loss": 0.3616, "lr": 7.809003838262193e-06, "epoch": 7.5825471698113205, "percentage": 37.91, "elapsed_time": "0:24:19", "remaining_time": "0:39:50", "throughput": 5810.62, "total_tokens": 8481112} {"current_steps": 12865, "total_steps": 33920, "loss": 0.4685, "lr": 7.806875130706628e-06, "epoch": 7.585495283018868, "percentage": 37.93, "elapsed_time": "0:24:20", "remaining_time": "0:39:49", "throughput": 5810.73, "total_tokens": 8484472} {"current_steps": 12870, "total_steps": 33920, "loss": 0.429, "lr": 7.804745680018775e-06, "epoch": 7.588443396226415, "percentage": 37.94, "elapsed_time": "0:24:20", "remaining_time": "0:39:49", "throughput": 5810.84, "total_tokens": 8487800} {"current_steps": 12875, "total_steps": 33920, "loss": 0.377, "lr": 7.802615486762418e-06, "epoch": 7.591391509433962, "percentage": 37.96, "elapsed_time": "0:24:21", "remaining_time": "0:39:48", "throughput": 5810.79, "total_tokens": 8490680} {"current_steps": 12880, "total_steps": 33920, "loss": 0.5189, "lr": 7.800484551501528e-06, "epoch": 7.59433962264151, "percentage": 37.97, "elapsed_time": "0:24:21", "remaining_time": "0:39:47", "throughput": 5810.77, "total_tokens": 8493656} {"current_steps": 12885, "total_steps": 33920, "loss": 0.431, "lr": 7.798352874800285e-06, "epoch": 7.597287735849057, "percentage": 37.99, "elapsed_time": "0:24:22", "remaining_time": "0:39:47", "throughput": 5810.88, "total_tokens": 8497400} {"current_steps": 12890, "total_steps": 33920, "loss": 0.3768, "lr": 7.79622045722306e-06, "epoch": 7.600235849056604, "percentage": 38.0, "elapsed_time": "0:24:22", "remaining_time": "0:39:46", "throughput": 5810.98, "total_tokens": 8500504} {"current_steps": 12895, "total_steps": 33920, "loss": 0.3749, "lr": 7.794087299334416e-06, "epoch": 7.603183962264151, "percentage": 38.02, "elapsed_time": "0:24:23", "remaining_time": "0:39:45", "throughput": 5810.86, "total_tokens": 8503224} {"current_steps": 12900, "total_steps": 33920, "loss": 0.3836, "lr": 7.79195340169912e-06, "epoch": 7.606132075471698, "percentage": 38.03, "elapsed_time": "0:24:23", "remaining_time": "0:39:45", "throughput": 5810.77, "total_tokens": 8506552} {"current_steps": 12905, "total_steps": 33920, "loss": 0.4344, "lr": 7.789818764882127e-06, "epoch": 7.609080188679245, "percentage": 38.05, "elapsed_time": "0:24:24", "remaining_time": "0:39:44", "throughput": 5810.73, "total_tokens": 8509496} {"current_steps": 12910, "total_steps": 33920, "loss": 0.4151, "lr": 7.78768338944859e-06, "epoch": 7.6120283018867925, "percentage": 38.06, "elapsed_time": "0:24:24", "remaining_time": "0:39:44", "throughput": 5810.69, "total_tokens": 8512504} {"current_steps": 12915, "total_steps": 33920, "loss": 0.4821, "lr": 7.785547275963865e-06, "epoch": 7.61497641509434, "percentage": 38.07, "elapsed_time": "0:24:25", "remaining_time": "0:39:43", "throughput": 5810.64, "total_tokens": 8515224} {"current_steps": 12920, "total_steps": 33920, "loss": 0.3697, "lr": 7.783410424993492e-06, "epoch": 7.617924528301887, "percentage": 38.09, "elapsed_time": "0:24:25", "remaining_time": "0:39:42", "throughput": 5810.54, "total_tokens": 8518040} {"current_steps": 12925, "total_steps": 33920, "loss": 0.4344, "lr": 7.781272837103213e-06, "epoch": 7.620872641509434, "percentage": 38.1, "elapsed_time": "0:24:26", "remaining_time": "0:39:42", "throughput": 5810.55, "total_tokens": 8521176} {"current_steps": 12930, "total_steps": 33920, "loss": 0.427, "lr": 7.779134512858964e-06, "epoch": 7.623820754716981, "percentage": 38.12, "elapsed_time": "0:24:27", "remaining_time": "0:39:41", "throughput": 5810.66, "total_tokens": 8524312} {"current_steps": 12935, "total_steps": 33920, "loss": 0.3135, "lr": 7.776995452826876e-06, "epoch": 7.626768867924528, "percentage": 38.13, "elapsed_time": "0:24:27", "remaining_time": "0:39:40", "throughput": 5810.89, "total_tokens": 8527960} {"current_steps": 12940, "total_steps": 33920, "loss": 0.5258, "lr": 7.774855657573274e-06, "epoch": 7.629716981132075, "percentage": 38.15, "elapsed_time": "0:24:28", "remaining_time": "0:39:40", "throughput": 5810.99, "total_tokens": 8531064} {"current_steps": 12945, "total_steps": 33920, "loss": 0.5103, "lr": 7.772715127664676e-06, "epoch": 7.632665094339623, "percentage": 38.16, "elapsed_time": "0:24:28", "remaining_time": "0:39:39", "throughput": 5811.23, "total_tokens": 8534488} {"current_steps": 12950, "total_steps": 33920, "loss": 0.408, "lr": 7.7705738636678e-06, "epoch": 7.63561320754717, "percentage": 38.18, "elapsed_time": "0:24:29", "remaining_time": "0:39:38", "throughput": 5811.38, "total_tokens": 8537624} {"current_steps": 12955, "total_steps": 33920, "loss": 0.4022, "lr": 7.768431866149552e-06, "epoch": 7.638561320754717, "percentage": 38.19, "elapsed_time": "0:24:29", "remaining_time": "0:39:38", "throughput": 5811.24, "total_tokens": 8540152} {"current_steps": 12960, "total_steps": 33920, "loss": 0.3094, "lr": 7.766289135677035e-06, "epoch": 7.6415094339622645, "percentage": 38.21, "elapsed_time": "0:24:30", "remaining_time": "0:39:37", "throughput": 5811.16, "total_tokens": 8542744} {"current_steps": 12965, "total_steps": 33920, "loss": 0.4244, "lr": 7.764145672817549e-06, "epoch": 7.644457547169811, "percentage": 38.22, "elapsed_time": "0:24:30", "remaining_time": "0:39:36", "throughput": 5811.35, "total_tokens": 8546488} {"current_steps": 12970, "total_steps": 33920, "loss": 0.5385, "lr": 7.762001478138583e-06, "epoch": 7.647405660377358, "percentage": 38.24, "elapsed_time": "0:24:31", "remaining_time": "0:39:36", "throughput": 5811.75, "total_tokens": 8551256} {"current_steps": 12975, "total_steps": 33920, "loss": 0.3986, "lr": 7.759856552207822e-06, "epoch": 7.650353773584905, "percentage": 38.25, "elapsed_time": "0:24:31", "remaining_time": "0:39:36", "throughput": 5812.03, "total_tokens": 8554680} {"current_steps": 12980, "total_steps": 33920, "loss": 0.4563, "lr": 7.757710895593144e-06, "epoch": 7.653301886792453, "percentage": 38.27, "elapsed_time": "0:24:32", "remaining_time": "0:39:35", "throughput": 5812.34, "total_tokens": 8558680} {"current_steps": 12985, "total_steps": 33920, "loss": 0.5012, "lr": 7.755564508862623e-06, "epoch": 7.65625, "percentage": 38.28, "elapsed_time": "0:24:33", "remaining_time": "0:39:34", "throughput": 5812.62, "total_tokens": 8562328} {"current_steps": 12990, "total_steps": 33920, "loss": 0.4466, "lr": 7.753417392584522e-06, "epoch": 7.659198113207547, "percentage": 38.3, "elapsed_time": "0:24:33", "remaining_time": "0:39:34", "throughput": 5812.69, "total_tokens": 8565432} {"current_steps": 12995, "total_steps": 33920, "loss": 0.5145, "lr": 7.751269547327298e-06, "epoch": 7.662146226415095, "percentage": 38.31, "elapsed_time": "0:24:34", "remaining_time": "0:39:33", "throughput": 5812.62, "total_tokens": 8568088} {"current_steps": 13000, "total_steps": 33920, "loss": 0.4619, "lr": 7.749120973659606e-06, "epoch": 7.665094339622642, "percentage": 38.33, "elapsed_time": "0:24:34", "remaining_time": "0:39:32", "throughput": 5812.55, "total_tokens": 8570808} {"current_steps": 13005, "total_steps": 33920, "loss": 0.3417, "lr": 7.746971672150286e-06, "epoch": 7.668042452830189, "percentage": 38.34, "elapsed_time": "0:24:35", "remaining_time": "0:39:32", "throughput": 5812.76, "total_tokens": 8574232} {"current_steps": 13010, "total_steps": 33920, "loss": 0.4455, "lr": 7.74482164336838e-06, "epoch": 7.6709905660377355, "percentage": 38.35, "elapsed_time": "0:24:35", "remaining_time": "0:39:31", "throughput": 5812.95, "total_tokens": 8577464} {"current_steps": 13015, "total_steps": 33920, "loss": 0.4237, "lr": 7.742670887883111e-06, "epoch": 7.673938679245283, "percentage": 38.37, "elapsed_time": "0:24:36", "remaining_time": "0:39:30", "throughput": 5813.04, "total_tokens": 8580600} {"current_steps": 13020, "total_steps": 33920, "loss": 0.3882, "lr": 7.740519406263905e-06, "epoch": 7.67688679245283, "percentage": 38.38, "elapsed_time": "0:24:36", "remaining_time": "0:39:30", "throughput": 5813.21, "total_tokens": 8584312} {"current_steps": 13025, "total_steps": 33920, "loss": 0.355, "lr": 7.738367199080376e-06, "epoch": 7.679834905660377, "percentage": 38.4, "elapsed_time": "0:24:37", "remaining_time": "0:39:29", "throughput": 5813.42, "total_tokens": 8587800} {"current_steps": 13030, "total_steps": 33920, "loss": 0.6053, "lr": 7.73621426690233e-06, "epoch": 7.682783018867925, "percentage": 38.41, "elapsed_time": "0:24:37", "remaining_time": "0:39:29", "throughput": 5813.9, "total_tokens": 8592344} {"current_steps": 13035, "total_steps": 33920, "loss": 0.3858, "lr": 7.734060610299764e-06, "epoch": 7.685731132075472, "percentage": 38.43, "elapsed_time": "0:24:38", "remaining_time": "0:39:28", "throughput": 5813.73, "total_tokens": 8594840} {"current_steps": 13040, "total_steps": 33920, "loss": 0.5705, "lr": 7.731906229842869e-06, "epoch": 7.688679245283019, "percentage": 38.44, "elapsed_time": "0:24:38", "remaining_time": "0:39:28", "throughput": 5813.91, "total_tokens": 8598232} {"current_steps": 13045, "total_steps": 33920, "loss": 0.409, "lr": 7.729751126102023e-06, "epoch": 7.691627358490566, "percentage": 38.46, "elapsed_time": "0:24:39", "remaining_time": "0:39:27", "throughput": 5814.4, "total_tokens": 8602712} {"current_steps": 13050, "total_steps": 33920, "loss": 0.4245, "lr": 7.727595299647805e-06, "epoch": 7.694575471698113, "percentage": 38.47, "elapsed_time": "0:24:40", "remaining_time": "0:39:27", "throughput": 5814.53, "total_tokens": 8606008} {"current_steps": 13055, "total_steps": 33920, "loss": 0.4312, "lr": 7.725438751050973e-06, "epoch": 7.69752358490566, "percentage": 38.49, "elapsed_time": "0:24:40", "remaining_time": "0:39:26", "throughput": 5814.64, "total_tokens": 8609080} {"current_steps": 13060, "total_steps": 33920, "loss": 0.433, "lr": 7.723281480882489e-06, "epoch": 7.7004716981132075, "percentage": 38.5, "elapsed_time": "0:24:41", "remaining_time": "0:39:25", "throughput": 5814.47, "total_tokens": 8611544} {"current_steps": 13065, "total_steps": 33920, "loss": 0.3685, "lr": 7.721123489713494e-06, "epoch": 7.703419811320755, "percentage": 38.52, "elapsed_time": "0:24:41", "remaining_time": "0:39:24", "throughput": 5814.38, "total_tokens": 8614424} {"current_steps": 13070, "total_steps": 33920, "loss": 0.2937, "lr": 7.718964778115328e-06, "epoch": 7.706367924528302, "percentage": 38.53, "elapsed_time": "0:24:42", "remaining_time": "0:39:24", "throughput": 5814.47, "total_tokens": 8617688} {"current_steps": 13075, "total_steps": 33920, "loss": 0.3597, "lr": 7.716805346659519e-06, "epoch": 7.709316037735849, "percentage": 38.55, "elapsed_time": "0:24:42", "remaining_time": "0:39:23", "throughput": 5814.26, "total_tokens": 8620408} {"current_steps": 13080, "total_steps": 33920, "loss": 0.3966, "lr": 7.714645195917788e-06, "epoch": 7.712264150943396, "percentage": 38.56, "elapsed_time": "0:24:43", "remaining_time": "0:39:23", "throughput": 5814.4, "total_tokens": 8623768} {"current_steps": 13085, "total_steps": 33920, "loss": 0.3388, "lr": 7.712484326462038e-06, "epoch": 7.715212264150943, "percentage": 38.58, "elapsed_time": "0:24:43", "remaining_time": "0:39:22", "throughput": 5814.34, "total_tokens": 8626712} {"current_steps": 13090, "total_steps": 33920, "loss": 0.4173, "lr": 7.710322738864375e-06, "epoch": 7.71816037735849, "percentage": 38.59, "elapsed_time": "0:24:44", "remaining_time": "0:39:21", "throughput": 5814.49, "total_tokens": 8629944} {"current_steps": 13095, "total_steps": 33920, "loss": 0.4305, "lr": 7.708160433697085e-06, "epoch": 7.721108490566038, "percentage": 38.61, "elapsed_time": "0:24:44", "remaining_time": "0:39:21", "throughput": 5814.58, "total_tokens": 8633080} {"current_steps": 13100, "total_steps": 33920, "loss": 0.3866, "lr": 7.705997411532649e-06, "epoch": 7.724056603773585, "percentage": 38.62, "elapsed_time": "0:24:45", "remaining_time": "0:39:20", "throughput": 5814.91, "total_tokens": 8637464} {"current_steps": 13105, "total_steps": 33920, "loss": 0.4051, "lr": 7.703833672943735e-06, "epoch": 7.727004716981132, "percentage": 38.64, "elapsed_time": "0:24:46", "remaining_time": "0:39:20", "throughput": 5815.09, "total_tokens": 8641368} {"current_steps": 13110, "total_steps": 33920, "loss": 0.3502, "lr": 7.701669218503206e-06, "epoch": 7.7299528301886795, "percentage": 38.65, "elapsed_time": "0:24:46", "remaining_time": "0:39:19", "throughput": 5814.94, "total_tokens": 8643960} {"current_steps": 13115, "total_steps": 33920, "loss": 0.3713, "lr": 7.699504048784106e-06, "epoch": 7.732900943396227, "percentage": 38.66, "elapsed_time": "0:24:47", "remaining_time": "0:39:18", "throughput": 5814.93, "total_tokens": 8646872} {"current_steps": 13120, "total_steps": 33920, "loss": 0.4108, "lr": 7.697338164359675e-06, "epoch": 7.735849056603773, "percentage": 38.68, "elapsed_time": "0:24:47", "remaining_time": "0:39:18", "throughput": 5815.08, "total_tokens": 8649912} {"current_steps": 13125, "total_steps": 33920, "loss": 0.3408, "lr": 7.69517156580334e-06, "epoch": 7.7387971698113205, "percentage": 38.69, "elapsed_time": "0:24:48", "remaining_time": "0:39:17", "throughput": 5815.33, "total_tokens": 8654008} {"current_steps": 13130, "total_steps": 33920, "loss": 0.5282, "lr": 7.693004253688716e-06, "epoch": 7.741745283018868, "percentage": 38.71, "elapsed_time": "0:24:48", "remaining_time": "0:39:17", "throughput": 5815.33, "total_tokens": 8656888} {"current_steps": 13135, "total_steps": 33920, "loss": 0.3486, "lr": 7.690836228589613e-06, "epoch": 7.744693396226415, "percentage": 38.72, "elapsed_time": "0:24:49", "remaining_time": "0:39:16", "throughput": 5815.11, "total_tokens": 8659544} {"current_steps": 13140, "total_steps": 33920, "loss": 0.3006, "lr": 7.688667491080019e-06, "epoch": 7.747641509433962, "percentage": 38.74, "elapsed_time": "0:24:49", "remaining_time": "0:39:16", "throughput": 5815.67, "total_tokens": 8664472} {"current_steps": 13145, "total_steps": 33920, "loss": 0.4796, "lr": 7.686498041734121e-06, "epoch": 7.75058962264151, "percentage": 38.75, "elapsed_time": "0:24:50", "remaining_time": "0:39:15", "throughput": 5815.79, "total_tokens": 8667576} {"current_steps": 13150, "total_steps": 33920, "loss": 0.6387, "lr": 7.684327881126285e-06, "epoch": 7.753537735849057, "percentage": 38.77, "elapsed_time": "0:24:50", "remaining_time": "0:39:14", "throughput": 5816.03, "total_tokens": 8670936} {"current_steps": 13155, "total_steps": 33920, "loss": 0.4186, "lr": 7.682157009831078e-06, "epoch": 7.756485849056604, "percentage": 38.78, "elapsed_time": "0:24:51", "remaining_time": "0:39:14", "throughput": 5816.04, "total_tokens": 8673752} {"current_steps": 13160, "total_steps": 33920, "loss": 0.3413, "lr": 7.67998542842324e-06, "epoch": 7.759433962264151, "percentage": 38.8, "elapsed_time": "0:24:51", "remaining_time": "0:39:13", "throughput": 5816.24, "total_tokens": 8677016} {"current_steps": 13165, "total_steps": 33920, "loss": 0.4019, "lr": 7.677813137477711e-06, "epoch": 7.762382075471698, "percentage": 38.81, "elapsed_time": "0:24:52", "remaining_time": "0:39:12", "throughput": 5816.36, "total_tokens": 8680536} {"current_steps": 13170, "total_steps": 33920, "loss": 0.49, "lr": 7.675640137569614e-06, "epoch": 7.765330188679245, "percentage": 38.83, "elapsed_time": "0:24:52", "remaining_time": "0:39:12", "throughput": 5816.34, "total_tokens": 8683256} {"current_steps": 13175, "total_steps": 33920, "loss": 0.4392, "lr": 7.673466429274257e-06, "epoch": 7.7682783018867925, "percentage": 38.84, "elapsed_time": "0:24:53", "remaining_time": "0:39:11", "throughput": 5815.92, "total_tokens": 8685560} {"current_steps": 13180, "total_steps": 33920, "loss": 0.5012, "lr": 7.671292013167143e-06, "epoch": 7.77122641509434, "percentage": 38.86, "elapsed_time": "0:24:53", "remaining_time": "0:39:10", "throughput": 5815.9, "total_tokens": 8688312} {"current_steps": 13185, "total_steps": 33920, "loss": 0.5108, "lr": 7.669116889823955e-06, "epoch": 7.774174528301887, "percentage": 38.87, "elapsed_time": "0:24:54", "remaining_time": "0:39:10", "throughput": 5815.91, "total_tokens": 8691032} {"current_steps": 13190, "total_steps": 33920, "loss": 0.4321, "lr": 7.666941059820567e-06, "epoch": 7.777122641509434, "percentage": 38.89, "elapsed_time": "0:24:54", "remaining_time": "0:39:09", "throughput": 5816.2, "total_tokens": 8694648} {"current_steps": 13195, "total_steps": 33920, "loss": 0.5551, "lr": 7.66476452373304e-06, "epoch": 7.780070754716981, "percentage": 38.9, "elapsed_time": "0:24:55", "remaining_time": "0:39:08", "throughput": 5816.41, "total_tokens": 8698552} {"current_steps": 13200, "total_steps": 33920, "loss": 0.4037, "lr": 7.66258728213762e-06, "epoch": 7.783018867924528, "percentage": 38.92, "elapsed_time": "0:24:56", "remaining_time": "0:39:08", "throughput": 5816.43, "total_tokens": 8701976} {"current_steps": 13205, "total_steps": 33920, "loss": 0.4969, "lr": 7.66040933561074e-06, "epoch": 7.785966981132075, "percentage": 38.93, "elapsed_time": "0:24:56", "remaining_time": "0:39:07", "throughput": 5816.32, "total_tokens": 8704664} {"current_steps": 13210, "total_steps": 33920, "loss": 0.5963, "lr": 7.658230684729027e-06, "epoch": 7.788915094339623, "percentage": 38.94, "elapsed_time": "0:24:57", "remaining_time": "0:39:07", "throughput": 5816.48, "total_tokens": 8708312} {"current_steps": 13215, "total_steps": 33920, "loss": 0.5418, "lr": 7.656051330069282e-06, "epoch": 7.79186320754717, "percentage": 38.96, "elapsed_time": "0:24:57", "remaining_time": "0:39:06", "throughput": 5816.72, "total_tokens": 8712056} {"current_steps": 13220, "total_steps": 33920, "loss": 0.4647, "lr": 7.6538712722085e-06, "epoch": 7.794811320754717, "percentage": 38.97, "elapsed_time": "0:24:58", "remaining_time": "0:39:06", "throughput": 5816.95, "total_tokens": 8715352} {"current_steps": 13225, "total_steps": 33920, "loss": 0.4084, "lr": 7.651690511723862e-06, "epoch": 7.7977594339622645, "percentage": 38.99, "elapsed_time": "0:24:58", "remaining_time": "0:39:05", "throughput": 5816.77, "total_tokens": 8718008} {"current_steps": 13230, "total_steps": 33920, "loss": 0.5511, "lr": 7.64950904919273e-06, "epoch": 7.800707547169811, "percentage": 39.0, "elapsed_time": "0:24:59", "remaining_time": "0:39:04", "throughput": 5816.93, "total_tokens": 8721048} {"current_steps": 13235, "total_steps": 33920, "loss": 0.4106, "lr": 7.647326885192662e-06, "epoch": 7.803655660377358, "percentage": 39.02, "elapsed_time": "0:24:59", "remaining_time": "0:39:03", "throughput": 5816.5, "total_tokens": 8723096} {"current_steps": 13240, "total_steps": 33920, "loss": 0.3379, "lr": 7.645144020301392e-06, "epoch": 7.806603773584905, "percentage": 39.03, "elapsed_time": "0:25:00", "remaining_time": "0:39:03", "throughput": 5816.82, "total_tokens": 8727032} {"current_steps": 13245, "total_steps": 33920, "loss": 0.3942, "lr": 7.64296045509684e-06, "epoch": 7.809551886792453, "percentage": 39.05, "elapsed_time": "0:25:01", "remaining_time": "0:39:03", "throughput": 5817.21, "total_tokens": 8732568} {"current_steps": 13250, "total_steps": 33920, "loss": 0.462, "lr": 7.64077619015712e-06, "epoch": 7.8125, "percentage": 39.06, "elapsed_time": "0:25:01", "remaining_time": "0:39:02", "throughput": 5817.37, "total_tokens": 8735832} {"current_steps": 13255, "total_steps": 33920, "loss": 0.4958, "lr": 7.638591226060519e-06, "epoch": 7.815448113207547, "percentage": 39.08, "elapsed_time": "0:25:02", "remaining_time": "0:39:02", "throughput": 5817.42, "total_tokens": 8739192} {"current_steps": 13260, "total_steps": 33920, "loss": 0.3928, "lr": 7.636405563385522e-06, "epoch": 7.818396226415095, "percentage": 39.09, "elapsed_time": "0:25:02", "remaining_time": "0:39:01", "throughput": 5817.6, "total_tokens": 8743352} {"current_steps": 13265, "total_steps": 33920, "loss": 0.4979, "lr": 7.634219202710789e-06, "epoch": 7.821344339622642, "percentage": 39.11, "elapsed_time": "0:25:03", "remaining_time": "0:39:00", "throughput": 5817.42, "total_tokens": 8745816} {"current_steps": 13270, "total_steps": 33920, "loss": 0.4135, "lr": 7.632032144615168e-06, "epoch": 7.824292452830189, "percentage": 39.12, "elapsed_time": "0:25:03", "remaining_time": "0:39:00", "throughput": 5817.53, "total_tokens": 8749016} {"current_steps": 13275, "total_steps": 33920, "loss": 0.4454, "lr": 7.629844389677695e-06, "epoch": 7.8272405660377355, "percentage": 39.14, "elapsed_time": "0:25:04", "remaining_time": "0:38:59", "throughput": 5817.51, "total_tokens": 8752120} {"current_steps": 13280, "total_steps": 33920, "loss": 0.4533, "lr": 7.627655938477586e-06, "epoch": 7.830188679245283, "percentage": 39.15, "elapsed_time": "0:25:05", "remaining_time": "0:38:59", "throughput": 5817.68, "total_tokens": 8755640} {"current_steps": 13285, "total_steps": 33920, "loss": 0.349, "lr": 7.6254667915942415e-06, "epoch": 7.83313679245283, "percentage": 39.17, "elapsed_time": "0:25:05", "remaining_time": "0:38:58", "throughput": 5817.38, "total_tokens": 8757976} {"current_steps": 13290, "total_steps": 33920, "loss": 0.4238, "lr": 7.62327694960725e-06, "epoch": 7.836084905660377, "percentage": 39.18, "elapsed_time": "0:25:06", "remaining_time": "0:38:57", "throughput": 5817.35, "total_tokens": 8761112} {"current_steps": 13295, "total_steps": 33920, "loss": 0.3783, "lr": 7.621086413096379e-06, "epoch": 7.839033018867925, "percentage": 39.2, "elapsed_time": "0:25:06", "remaining_time": "0:38:57", "throughput": 5817.48, "total_tokens": 8764536} {"current_steps": 13300, "total_steps": 33920, "loss": 0.5001, "lr": 7.618895182641584e-06, "epoch": 7.841981132075472, "percentage": 39.21, "elapsed_time": "0:25:07", "remaining_time": "0:38:56", "throughput": 5817.78, "total_tokens": 8768152} {"current_steps": 13305, "total_steps": 33920, "loss": 0.3837, "lr": 7.6167032588230035e-06, "epoch": 7.844929245283019, "percentage": 39.22, "elapsed_time": "0:25:07", "remaining_time": "0:38:55", "throughput": 5817.7, "total_tokens": 8770776} {"current_steps": 13310, "total_steps": 33920, "loss": 0.554, "lr": 7.614510642220958e-06, "epoch": 7.847877358490566, "percentage": 39.24, "elapsed_time": "0:25:08", "remaining_time": "0:38:56", "throughput": 5818.28, "total_tokens": 8778328} {"current_steps": 13315, "total_steps": 33920, "loss": 0.4062, "lr": 7.612317333415951e-06, "epoch": 7.850825471698113, "percentage": 39.25, "elapsed_time": "0:25:09", "remaining_time": "0:38:55", "throughput": 5818.33, "total_tokens": 8781944} {"current_steps": 13320, "total_steps": 33920, "loss": 0.4486, "lr": 7.610123332988673e-06, "epoch": 7.85377358490566, "percentage": 39.27, "elapsed_time": "0:25:09", "remaining_time": "0:38:55", "throughput": 5818.44, "total_tokens": 8785016} {"current_steps": 13325, "total_steps": 33920, "loss": 0.3732, "lr": 7.607928641519992e-06, "epoch": 7.8567216981132075, "percentage": 39.28, "elapsed_time": "0:25:10", "remaining_time": "0:38:54", "throughput": 5818.52, "total_tokens": 8788472} {"current_steps": 13330, "total_steps": 33920, "loss": 0.486, "lr": 7.605733259590964e-06, "epoch": 7.859669811320755, "percentage": 39.3, "elapsed_time": "0:25:10", "remaining_time": "0:38:53", "throughput": 5818.18, "total_tokens": 8791096} {"current_steps": 13335, "total_steps": 33920, "loss": 0.3774, "lr": 7.603537187782826e-06, "epoch": 7.862617924528302, "percentage": 39.31, "elapsed_time": "0:25:11", "remaining_time": "0:38:53", "throughput": 5818.49, "total_tokens": 8795000} {"current_steps": 13340, "total_steps": 33920, "loss": 0.5162, "lr": 7.601340426676996e-06, "epoch": 7.865566037735849, "percentage": 39.33, "elapsed_time": "0:25:12", "remaining_time": "0:38:52", "throughput": 5818.48, "total_tokens": 8797880} {"current_steps": 13345, "total_steps": 33920, "loss": 0.4843, "lr": 7.599142976855077e-06, "epoch": 7.868514150943396, "percentage": 39.34, "elapsed_time": "0:25:12", "remaining_time": "0:38:52", "throughput": 5818.71, "total_tokens": 8801240} {"current_steps": 13350, "total_steps": 33920, "loss": 0.3644, "lr": 7.596944838898854e-06, "epoch": 7.871462264150943, "percentage": 39.36, "elapsed_time": "0:25:13", "remaining_time": "0:38:51", "throughput": 5818.61, "total_tokens": 8804216} {"current_steps": 13355, "total_steps": 33920, "loss": 0.4207, "lr": 7.594746013390293e-06, "epoch": 7.87441037735849, "percentage": 39.37, "elapsed_time": "0:25:13", "remaining_time": "0:38:50", "throughput": 5818.66, "total_tokens": 8807544} {"current_steps": 13360, "total_steps": 33920, "loss": 0.3643, "lr": 7.59254650091154e-06, "epoch": 7.877358490566038, "percentage": 39.39, "elapsed_time": "0:25:14", "remaining_time": "0:38:50", "throughput": 5819.22, "total_tokens": 8813176} {"current_steps": 13365, "total_steps": 33920, "loss": 0.414, "lr": 7.59034630204493e-06, "epoch": 7.880306603773585, "percentage": 39.4, "elapsed_time": "0:25:14", "remaining_time": "0:38:50", "throughput": 5819.12, "total_tokens": 8815928} {"current_steps": 13370, "total_steps": 33920, "loss": 0.4021, "lr": 7.588145417372972e-06, "epoch": 7.883254716981132, "percentage": 39.42, "elapsed_time": "0:25:15", "remaining_time": "0:38:49", "throughput": 5819.02, "total_tokens": 8818776} {"current_steps": 13375, "total_steps": 33920, "loss": 0.4822, "lr": 7.585943847478361e-06, "epoch": 7.8862028301886795, "percentage": 39.43, "elapsed_time": "0:25:16", "remaining_time": "0:38:48", "throughput": 5818.85, "total_tokens": 8821688} {"current_steps": 13380, "total_steps": 33920, "loss": 0.3712, "lr": 7.583741592943971e-06, "epoch": 7.889150943396227, "percentage": 39.45, "elapsed_time": "0:25:16", "remaining_time": "0:38:48", "throughput": 5818.84, "total_tokens": 8824664} {"current_steps": 13385, "total_steps": 33920, "loss": 0.4835, "lr": 7.581538654352859e-06, "epoch": 7.892099056603773, "percentage": 39.46, "elapsed_time": "0:25:17", "remaining_time": "0:38:47", "throughput": 5818.69, "total_tokens": 8827288} {"current_steps": 13390, "total_steps": 33920, "loss": 0.2788, "lr": 7.579335032288262e-06, "epoch": 7.8950471698113205, "percentage": 39.48, "elapsed_time": "0:25:17", "remaining_time": "0:38:46", "throughput": 5818.59, "total_tokens": 8829944} {"current_steps": 13395, "total_steps": 33920, "loss": 0.5815, "lr": 7.577130727333598e-06, "epoch": 7.897995283018868, "percentage": 39.49, "elapsed_time": "0:25:18", "remaining_time": "0:38:46", "throughput": 5818.61, "total_tokens": 8832920} {"current_steps": 13400, "total_steps": 33920, "loss": 0.4463, "lr": 7.5749257400724695e-06, "epoch": 7.900943396226415, "percentage": 39.5, "elapsed_time": "0:25:18", "remaining_time": "0:38:45", "throughput": 5818.63, "total_tokens": 8836120} {"current_steps": 13405, "total_steps": 33920, "loss": 0.5252, "lr": 7.572720071088653e-06, "epoch": 7.903891509433962, "percentage": 39.52, "elapsed_time": "0:25:19", "remaining_time": "0:38:44", "throughput": 5818.52, "total_tokens": 8838648} {"current_steps": 13410, "total_steps": 33920, "loss": 0.3148, "lr": 7.570513720966108e-06, "epoch": 7.90683962264151, "percentage": 39.53, "elapsed_time": "0:25:19", "remaining_time": "0:38:44", "throughput": 5818.79, "total_tokens": 8842136} {"current_steps": 13415, "total_steps": 33920, "loss": 0.4732, "lr": 7.56830669028898e-06, "epoch": 7.909787735849057, "percentage": 39.55, "elapsed_time": "0:25:20", "remaining_time": "0:38:43", "throughput": 5818.96, "total_tokens": 8845624} {"current_steps": 13420, "total_steps": 33920, "loss": 0.5637, "lr": 7.566098979641588e-06, "epoch": 7.912735849056604, "percentage": 39.56, "elapsed_time": "0:25:20", "remaining_time": "0:38:42", "throughput": 5818.8, "total_tokens": 8848216} {"current_steps": 13425, "total_steps": 33920, "loss": 0.3969, "lr": 7.563890589608427e-06, "epoch": 7.915683962264151, "percentage": 39.58, "elapsed_time": "0:25:21", "remaining_time": "0:38:42", "throughput": 5819.06, "total_tokens": 8851928} {"current_steps": 13430, "total_steps": 33920, "loss": 0.2593, "lr": 7.561681520774187e-06, "epoch": 7.918632075471698, "percentage": 39.59, "elapsed_time": "0:25:21", "remaining_time": "0:38:41", "throughput": 5819.08, "total_tokens": 8854680} {"current_steps": 13435, "total_steps": 33920, "loss": 0.547, "lr": 7.559471773723721e-06, "epoch": 7.921580188679245, "percentage": 39.61, "elapsed_time": "0:25:22", "remaining_time": "0:38:40", "throughput": 5819.29, "total_tokens": 8858200} {"current_steps": 13440, "total_steps": 33920, "loss": 0.5313, "lr": 7.557261349042073e-06, "epoch": 7.9245283018867925, "percentage": 39.62, "elapsed_time": "0:25:22", "remaining_time": "0:38:40", "throughput": 5819.59, "total_tokens": 8862680} {"current_steps": 13445, "total_steps": 33920, "loss": 0.3822, "lr": 7.555050247314464e-06, "epoch": 7.92747641509434, "percentage": 39.64, "elapsed_time": "0:25:23", "remaining_time": "0:38:40", "throughput": 5819.84, "total_tokens": 8866712} {"current_steps": 13450, "total_steps": 33920, "loss": 0.478, "lr": 7.552838469126289e-06, "epoch": 7.930424528301887, "percentage": 39.65, "elapsed_time": "0:25:24", "remaining_time": "0:38:39", "throughput": 5820.09, "total_tokens": 8870328} {"current_steps": 13455, "total_steps": 33920, "loss": 0.4273, "lr": 7.550626015063125e-06, "epoch": 7.933372641509434, "percentage": 39.67, "elapsed_time": "0:25:24", "remaining_time": "0:38:38", "throughput": 5820.17, "total_tokens": 8873400} {"current_steps": 13460, "total_steps": 33920, "loss": 0.4008, "lr": 7.548412885710734e-06, "epoch": 7.936320754716981, "percentage": 39.68, "elapsed_time": "0:25:25", "remaining_time": "0:38:38", "throughput": 5820.32, "total_tokens": 8876568} {"current_steps": 13465, "total_steps": 33920, "loss": 0.3885, "lr": 7.546199081655048e-06, "epoch": 7.939268867924528, "percentage": 39.7, "elapsed_time": "0:25:25", "remaining_time": "0:38:37", "throughput": 5820.7, "total_tokens": 8880760} {"current_steps": 13470, "total_steps": 33920, "loss": 0.3752, "lr": 7.54398460348218e-06, "epoch": 7.942216981132075, "percentage": 39.71, "elapsed_time": "0:25:26", "remaining_time": "0:38:37", "throughput": 5820.73, "total_tokens": 8883608} {"current_steps": 13475, "total_steps": 33920, "loss": 0.4531, "lr": 7.541769451778425e-06, "epoch": 7.945165094339623, "percentage": 39.73, "elapsed_time": "0:25:26", "remaining_time": "0:38:36", "throughput": 5820.87, "total_tokens": 8886904} {"current_steps": 13480, "total_steps": 33920, "loss": 0.4012, "lr": 7.5395536271302536e-06, "epoch": 7.94811320754717, "percentage": 39.74, "elapsed_time": "0:25:27", "remaining_time": "0:38:35", "throughput": 5820.89, "total_tokens": 8889752} {"current_steps": 13485, "total_steps": 33920, "loss": 0.587, "lr": 7.5373371301243136e-06, "epoch": 7.951061320754717, "percentage": 39.76, "elapsed_time": "0:25:27", "remaining_time": "0:38:35", "throughput": 5821.08, "total_tokens": 8893048} {"current_steps": 13490, "total_steps": 33920, "loss": 0.3798, "lr": 7.535119961347433e-06, "epoch": 7.9540094339622645, "percentage": 39.77, "elapsed_time": "0:25:28", "remaining_time": "0:38:34", "throughput": 5821.05, "total_tokens": 8896024} {"current_steps": 13495, "total_steps": 33920, "loss": 0.3822, "lr": 7.532902121386618e-06, "epoch": 7.956957547169811, "percentage": 39.78, "elapsed_time": "0:25:28", "remaining_time": "0:38:33", "throughput": 5821.02, "total_tokens": 8898872} {"current_steps": 13500, "total_steps": 33920, "loss": 0.4316, "lr": 7.530683610829051e-06, "epoch": 7.959905660377358, "percentage": 39.8, "elapsed_time": "0:25:29", "remaining_time": "0:38:33", "throughput": 5820.69, "total_tokens": 8901176} {"current_steps": 13505, "total_steps": 33920, "loss": 0.285, "lr": 7.5284644302620906e-06, "epoch": 7.962853773584905, "percentage": 39.81, "elapsed_time": "0:25:29", "remaining_time": "0:38:32", "throughput": 5820.5, "total_tokens": 8903832} {"current_steps": 13510, "total_steps": 33920, "loss": 0.322, "lr": 7.526244580273274e-06, "epoch": 7.965801886792453, "percentage": 39.83, "elapsed_time": "0:25:30", "remaining_time": "0:38:31", "throughput": 5820.39, "total_tokens": 8906648} {"current_steps": 13515, "total_steps": 33920, "loss": 0.5009, "lr": 7.524024061450318e-06, "epoch": 7.96875, "percentage": 39.84, "elapsed_time": "0:25:30", "remaining_time": "0:38:31", "throughput": 5820.62, "total_tokens": 8910168} {"current_steps": 13520, "total_steps": 33920, "loss": 0.5671, "lr": 7.521802874381115e-06, "epoch": 7.971698113207547, "percentage": 39.86, "elapsed_time": "0:25:31", "remaining_time": "0:38:30", "throughput": 5820.85, "total_tokens": 8913720} {"current_steps": 13525, "total_steps": 33920, "loss": 0.3402, "lr": 7.519581019653731e-06, "epoch": 7.974646226415095, "percentage": 39.87, "elapsed_time": "0:25:31", "remaining_time": "0:38:29", "throughput": 5820.76, "total_tokens": 8916344} {"current_steps": 13530, "total_steps": 33920, "loss": 0.4036, "lr": 7.517358497856413e-06, "epoch": 7.977594339622642, "percentage": 39.89, "elapsed_time": "0:25:32", "remaining_time": "0:38:29", "throughput": 5820.74, "total_tokens": 8919096} {"current_steps": 13535, "total_steps": 33920, "loss": 0.378, "lr": 7.515135309577584e-06, "epoch": 7.980542452830189, "percentage": 39.9, "elapsed_time": "0:25:32", "remaining_time": "0:38:28", "throughput": 5820.46, "total_tokens": 8921336} {"current_steps": 13540, "total_steps": 33920, "loss": 0.5267, "lr": 7.5129114554058425e-06, "epoch": 7.9834905660377355, "percentage": 39.92, "elapsed_time": "0:25:33", "remaining_time": "0:38:27", "throughput": 5820.41, "total_tokens": 8924696} {"current_steps": 13545, "total_steps": 33920, "loss": 0.3761, "lr": 7.510686935929963e-06, "epoch": 7.986438679245283, "percentage": 39.93, "elapsed_time": "0:25:33", "remaining_time": "0:38:27", "throughput": 5820.56, "total_tokens": 8928728} {"current_steps": 13550, "total_steps": 33920, "loss": 0.367, "lr": 7.5084617517388965e-06, "epoch": 7.98938679245283, "percentage": 39.95, "elapsed_time": "0:25:34", "remaining_time": "0:38:26", "throughput": 5820.57, "total_tokens": 8931640} {"current_steps": 13555, "total_steps": 33920, "loss": 0.3144, "lr": 7.506235903421771e-06, "epoch": 7.992334905660377, "percentage": 39.96, "elapsed_time": "0:25:35", "remaining_time": "0:38:26", "throughput": 5820.66, "total_tokens": 8934808} {"current_steps": 13560, "total_steps": 33920, "loss": 0.4559, "lr": 7.504009391567889e-06, "epoch": 7.995283018867925, "percentage": 39.98, "elapsed_time": "0:25:35", "remaining_time": "0:38:25", "throughput": 5820.65, "total_tokens": 8937624} {"current_steps": 13565, "total_steps": 33920, "loss": 0.3139, "lr": 7.501782216766729e-06, "epoch": 7.998231132075472, "percentage": 39.99, "elapsed_time": "0:25:36", "remaining_time": "0:38:24", "throughput": 5820.57, "total_tokens": 8940440} {"current_steps": 13568, "total_steps": 33920, "eval_loss": 0.5016111135482788, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:25:54", "remaining_time": "0:38:52", "throughput": 5751.66, "total_tokens": 8942288} {"current_steps": 13570, "total_steps": 33920, "loss": 0.2684, "lr": 7.499554379607944e-06, "epoch": 8.00117924528302, "percentage": 40.01, "elapsed_time": "0:25:58", "remaining_time": "0:38:56", "throughput": 5740.22, "total_tokens": 8943856} {"current_steps": 13575, "total_steps": 33920, "loss": 0.352, "lr": 7.497325880681365e-06, "epoch": 8.004127358490566, "percentage": 40.02, "elapsed_time": "0:25:58", "remaining_time": "0:38:55", "throughput": 5740.14, "total_tokens": 8946736} {"current_steps": 13580, "total_steps": 33920, "loss": 0.3488, "lr": 7.495096720576994e-06, "epoch": 8.007075471698114, "percentage": 40.04, "elapsed_time": "0:25:59", "remaining_time": "0:38:55", "throughput": 5740.39, "total_tokens": 8950256} {"current_steps": 13585, "total_steps": 33920, "loss": 0.3393, "lr": 7.492866899885017e-06, "epoch": 8.01002358490566, "percentage": 40.05, "elapsed_time": "0:25:59", "remaining_time": "0:38:54", "throughput": 5740.17, "total_tokens": 8952880} {"current_steps": 13590, "total_steps": 33920, "loss": 0.5546, "lr": 7.490636419195782e-06, "epoch": 8.012971698113208, "percentage": 40.06, "elapsed_time": "0:26:00", "remaining_time": "0:38:54", "throughput": 5740.37, "total_tokens": 8956432} {"current_steps": 13595, "total_steps": 33920, "loss": 0.4678, "lr": 7.488405279099821e-06, "epoch": 8.015919811320755, "percentage": 40.08, "elapsed_time": "0:26:00", "remaining_time": "0:38:53", "throughput": 5740.32, "total_tokens": 8959056} {"current_steps": 13600, "total_steps": 33920, "loss": 0.4259, "lr": 7.48617348018784e-06, "epoch": 8.018867924528301, "percentage": 40.09, "elapsed_time": "0:26:01", "remaining_time": "0:38:52", "throughput": 5740.55, "total_tokens": 8962256} {"current_steps": 13605, "total_steps": 33920, "loss": 0.4995, "lr": 7.4839410230507134e-06, "epoch": 8.02181603773585, "percentage": 40.11, "elapsed_time": "0:26:01", "remaining_time": "0:38:52", "throughput": 5740.23, "total_tokens": 8965008} {"current_steps": 13610, "total_steps": 33920, "loss": 0.3597, "lr": 7.481707908279496e-06, "epoch": 8.024764150943396, "percentage": 40.12, "elapsed_time": "0:26:02", "remaining_time": "0:38:51", "throughput": 5740.1, "total_tokens": 8968496} {"current_steps": 13615, "total_steps": 33920, "loss": 0.3939, "lr": 7.4794741364654144e-06, "epoch": 8.027712264150944, "percentage": 40.14, "elapsed_time": "0:26:02", "remaining_time": "0:38:50", "throughput": 5740.17, "total_tokens": 8971792} {"current_steps": 13620, "total_steps": 33920, "loss": 0.4118, "lr": 7.477239708199871e-06, "epoch": 8.03066037735849, "percentage": 40.15, "elapsed_time": "0:26:03", "remaining_time": "0:38:50", "throughput": 5740.45, "total_tokens": 8975728} {"current_steps": 13625, "total_steps": 33920, "loss": 0.3325, "lr": 7.475004624074434e-06, "epoch": 8.033608490566039, "percentage": 40.17, "elapsed_time": "0:26:04", "remaining_time": "0:38:49", "throughput": 5740.46, "total_tokens": 8978960} {"current_steps": 13630, "total_steps": 33920, "loss": 0.3482, "lr": 7.4727688846808595e-06, "epoch": 8.036556603773585, "percentage": 40.18, "elapsed_time": "0:26:04", "remaining_time": "0:38:49", "throughput": 5740.7, "total_tokens": 8983408} {"current_steps": 13635, "total_steps": 33920, "loss": 0.3403, "lr": 7.4705324906110654e-06, "epoch": 8.039504716981131, "percentage": 40.2, "elapsed_time": "0:26:05", "remaining_time": "0:38:48", "throughput": 5740.47, "total_tokens": 8986096} {"current_steps": 13640, "total_steps": 33920, "loss": 0.3737, "lr": 7.4682954424571466e-06, "epoch": 8.04245283018868, "percentage": 40.21, "elapsed_time": "0:26:05", "remaining_time": "0:38:48", "throughput": 5740.5, "total_tokens": 8989136} {"current_steps": 13645, "total_steps": 33920, "loss": 0.4144, "lr": 7.466057740811372e-06, "epoch": 8.045400943396226, "percentage": 40.23, "elapsed_time": "0:26:06", "remaining_time": "0:38:47", "throughput": 5740.43, "total_tokens": 8992240} {"current_steps": 13650, "total_steps": 33920, "loss": 0.3699, "lr": 7.463819386266182e-06, "epoch": 8.048349056603774, "percentage": 40.24, "elapsed_time": "0:26:07", "remaining_time": "0:38:46", "throughput": 5740.51, "total_tokens": 8995472} {"current_steps": 13655, "total_steps": 33920, "loss": 0.4968, "lr": 7.461580379414191e-06, "epoch": 8.05129716981132, "percentage": 40.26, "elapsed_time": "0:26:07", "remaining_time": "0:38:46", "throughput": 5740.59, "total_tokens": 8998512} {"current_steps": 13660, "total_steps": 33920, "loss": 0.4761, "lr": 7.459340720848187e-06, "epoch": 8.054245283018869, "percentage": 40.27, "elapsed_time": "0:26:08", "remaining_time": "0:38:45", "throughput": 5740.51, "total_tokens": 9001200} {"current_steps": 13665, "total_steps": 33920, "loss": 0.3293, "lr": 7.457100411161128e-06, "epoch": 8.057193396226415, "percentage": 40.29, "elapsed_time": "0:26:08", "remaining_time": "0:38:45", "throughput": 5740.71, "total_tokens": 9005008} {"current_steps": 13670, "total_steps": 33920, "loss": 0.4912, "lr": 7.454859450946144e-06, "epoch": 8.060141509433961, "percentage": 40.3, "elapsed_time": "0:26:09", "remaining_time": "0:38:44", "throughput": 5740.54, "total_tokens": 9007728} {"current_steps": 13675, "total_steps": 33920, "loss": 0.3022, "lr": 7.4526178407965396e-06, "epoch": 8.06308962264151, "percentage": 40.32, "elapsed_time": "0:26:09", "remaining_time": "0:38:43", "throughput": 5740.67, "total_tokens": 9010864} {"current_steps": 13680, "total_steps": 33920, "loss": 0.365, "lr": 7.450375581305794e-06, "epoch": 8.066037735849056, "percentage": 40.33, "elapsed_time": "0:26:10", "remaining_time": "0:38:43", "throughput": 5740.45, "total_tokens": 9013264} {"current_steps": 13685, "total_steps": 33920, "loss": 0.4364, "lr": 7.448132673067552e-06, "epoch": 8.068985849056604, "percentage": 40.34, "elapsed_time": "0:26:10", "remaining_time": "0:38:42", "throughput": 5740.35, "total_tokens": 9016112} {"current_steps": 13690, "total_steps": 33920, "loss": 0.4565, "lr": 7.445889116675634e-06, "epoch": 8.07193396226415, "percentage": 40.36, "elapsed_time": "0:26:11", "remaining_time": "0:38:41", "throughput": 5740.49, "total_tokens": 9019120} {"current_steps": 13695, "total_steps": 33920, "loss": 0.3414, "lr": 7.443644912724031e-06, "epoch": 8.074882075471699, "percentage": 40.37, "elapsed_time": "0:26:11", "remaining_time": "0:38:41", "throughput": 5740.55, "total_tokens": 9022096} {"current_steps": 13700, "total_steps": 33920, "loss": 0.316, "lr": 7.441400061806907e-06, "epoch": 8.077830188679245, "percentage": 40.39, "elapsed_time": "0:26:12", "remaining_time": "0:38:40", "throughput": 5740.44, "total_tokens": 9024816} {"current_steps": 13705, "total_steps": 33920, "loss": 0.4317, "lr": 7.439154564518592e-06, "epoch": 8.080778301886792, "percentage": 40.4, "elapsed_time": "0:26:12", "remaining_time": "0:38:39", "throughput": 5740.35, "total_tokens": 9027472} {"current_steps": 13710, "total_steps": 33920, "loss": 0.4304, "lr": 7.436908421453597e-06, "epoch": 8.08372641509434, "percentage": 40.42, "elapsed_time": "0:26:13", "remaining_time": "0:38:39", "throughput": 5740.5, "total_tokens": 9031024} {"current_steps": 13715, "total_steps": 33920, "loss": 0.387, "lr": 7.434661633206593e-06, "epoch": 8.086674528301886, "percentage": 40.43, "elapsed_time": "0:26:13", "remaining_time": "0:38:38", "throughput": 5740.66, "total_tokens": 9034704} {"current_steps": 13720, "total_steps": 33920, "loss": 0.6207, "lr": 7.4324142003724286e-06, "epoch": 8.089622641509434, "percentage": 40.45, "elapsed_time": "0:26:14", "remaining_time": "0:38:38", "throughput": 5741.19, "total_tokens": 9039440} {"current_steps": 13725, "total_steps": 33920, "loss": 0.4052, "lr": 7.430166123546122e-06, "epoch": 8.09257075471698, "percentage": 40.46, "elapsed_time": "0:26:15", "remaining_time": "0:38:37", "throughput": 5741.47, "total_tokens": 9043184} {"current_steps": 13730, "total_steps": 33920, "loss": 0.37, "lr": 7.427917403322862e-06, "epoch": 8.095518867924529, "percentage": 40.48, "elapsed_time": "0:26:15", "remaining_time": "0:38:36", "throughput": 5741.55, "total_tokens": 9046544} {"current_steps": 13735, "total_steps": 33920, "loss": 0.3334, "lr": 7.425668040298003e-06, "epoch": 8.098466981132075, "percentage": 40.49, "elapsed_time": "0:26:16", "remaining_time": "0:38:36", "throughput": 5741.85, "total_tokens": 9050448} {"current_steps": 13740, "total_steps": 33920, "loss": 0.4407, "lr": 7.4234180350670785e-06, "epoch": 8.101415094339623, "percentage": 40.51, "elapsed_time": "0:26:16", "remaining_time": "0:38:35", "throughput": 5741.85, "total_tokens": 9053776} {"current_steps": 13745, "total_steps": 33920, "loss": 0.3709, "lr": 7.421167388225785e-06, "epoch": 8.10436320754717, "percentage": 40.52, "elapsed_time": "0:26:17", "remaining_time": "0:38:35", "throughput": 5741.43, "total_tokens": 9056528} {"current_steps": 13750, "total_steps": 33920, "loss": 0.3862, "lr": 7.41891610036999e-06, "epoch": 8.107311320754716, "percentage": 40.54, "elapsed_time": "0:26:17", "remaining_time": "0:38:34", "throughput": 5741.61, "total_tokens": 9060016} {"current_steps": 13755, "total_steps": 33920, "loss": 0.4048, "lr": 7.416664172095732e-06, "epoch": 8.110259433962264, "percentage": 40.55, "elapsed_time": "0:26:18", "remaining_time": "0:38:33", "throughput": 5741.67, "total_tokens": 9062768} {"current_steps": 13760, "total_steps": 33920, "loss": 0.4656, "lr": 7.414411603999221e-06, "epoch": 8.11320754716981, "percentage": 40.57, "elapsed_time": "0:26:19", "remaining_time": "0:38:33", "throughput": 5741.96, "total_tokens": 9066608} {"current_steps": 13765, "total_steps": 33920, "loss": 0.3562, "lr": 7.4121583966768295e-06, "epoch": 8.116155660377359, "percentage": 40.58, "elapsed_time": "0:26:19", "remaining_time": "0:38:32", "throughput": 5742.05, "total_tokens": 9069552} {"current_steps": 13770, "total_steps": 33920, "loss": 0.389, "lr": 7.409904550725109e-06, "epoch": 8.119103773584905, "percentage": 40.6, "elapsed_time": "0:26:19", "remaining_time": "0:38:32", "throughput": 5742.18, "total_tokens": 9072496} {"current_steps": 13775, "total_steps": 33920, "loss": 0.3993, "lr": 7.407650066740771e-06, "epoch": 8.122051886792454, "percentage": 40.61, "elapsed_time": "0:26:20", "remaining_time": "0:38:31", "throughput": 5742.24, "total_tokens": 9075408} {"current_steps": 13780, "total_steps": 33920, "loss": 0.3386, "lr": 7.405394945320702e-06, "epoch": 8.125, "percentage": 40.62, "elapsed_time": "0:26:20", "remaining_time": "0:38:30", "throughput": 5742.11, "total_tokens": 9077968} {"current_steps": 13785, "total_steps": 33920, "loss": 0.3953, "lr": 7.403139187061955e-06, "epoch": 8.127948113207546, "percentage": 40.64, "elapsed_time": "0:26:21", "remaining_time": "0:38:29", "throughput": 5742.27, "total_tokens": 9081040} {"current_steps": 13790, "total_steps": 33920, "loss": 0.4323, "lr": 7.400882792561752e-06, "epoch": 8.130896226415095, "percentage": 40.65, "elapsed_time": "0:26:21", "remaining_time": "0:38:29", "throughput": 5742.36, "total_tokens": 9084016} {"current_steps": 13795, "total_steps": 33920, "loss": 0.41, "lr": 7.39862576241748e-06, "epoch": 8.133844339622641, "percentage": 40.67, "elapsed_time": "0:26:22", "remaining_time": "0:38:28", "throughput": 5742.63, "total_tokens": 9087536} {"current_steps": 13800, "total_steps": 33920, "loss": 0.3829, "lr": 7.396368097226703e-06, "epoch": 8.13679245283019, "percentage": 40.68, "elapsed_time": "0:26:22", "remaining_time": "0:38:27", "throughput": 5742.71, "total_tokens": 9090640} {"current_steps": 13805, "total_steps": 33920, "loss": 0.4993, "lr": 7.394109797587144e-06, "epoch": 8.139740566037736, "percentage": 40.7, "elapsed_time": "0:26:23", "remaining_time": "0:38:27", "throughput": 5742.78, "total_tokens": 9093840} {"current_steps": 13810, "total_steps": 33920, "loss": 0.3093, "lr": 7.3918508640966956e-06, "epoch": 8.142688679245284, "percentage": 40.71, "elapsed_time": "0:26:24", "remaining_time": "0:38:26", "throughput": 5743.03, "total_tokens": 9097808} {"current_steps": 13815, "total_steps": 33920, "loss": 0.4807, "lr": 7.389591297353424e-06, "epoch": 8.14563679245283, "percentage": 40.73, "elapsed_time": "0:26:24", "remaining_time": "0:38:26", "throughput": 5743.17, "total_tokens": 9101040} {"current_steps": 13820, "total_steps": 33920, "loss": 0.3468, "lr": 7.3873310979555565e-06, "epoch": 8.148584905660377, "percentage": 40.74, "elapsed_time": "0:26:25", "remaining_time": "0:38:25", "throughput": 5743.05, "total_tokens": 9103568} {"current_steps": 13825, "total_steps": 33920, "loss": 0.403, "lr": 7.385070266501495e-06, "epoch": 8.151533018867925, "percentage": 40.76, "elapsed_time": "0:26:25", "remaining_time": "0:38:24", "throughput": 5743.23, "total_tokens": 9106928} {"current_steps": 13830, "total_steps": 33920, "loss": 0.4096, "lr": 7.382808803589798e-06, "epoch": 8.154481132075471, "percentage": 40.77, "elapsed_time": "0:26:26", "remaining_time": "0:38:24", "throughput": 5743.22, "total_tokens": 9110000} {"current_steps": 13835, "total_steps": 33920, "loss": 0.3627, "lr": 7.380546709819204e-06, "epoch": 8.15742924528302, "percentage": 40.79, "elapsed_time": "0:26:26", "remaining_time": "0:38:23", "throughput": 5742.85, "total_tokens": 9112080} {"current_steps": 13840, "total_steps": 33920, "loss": 0.3426, "lr": 7.378283985788608e-06, "epoch": 8.160377358490566, "percentage": 40.8, "elapsed_time": "0:26:27", "remaining_time": "0:38:22", "throughput": 5742.81, "total_tokens": 9115088} {"current_steps": 13845, "total_steps": 33920, "loss": 0.3764, "lr": 7.376020632097076e-06, "epoch": 8.163325471698114, "percentage": 40.82, "elapsed_time": "0:26:27", "remaining_time": "0:38:22", "throughput": 5742.81, "total_tokens": 9117968} {"current_steps": 13850, "total_steps": 33920, "loss": 0.3365, "lr": 7.373756649343841e-06, "epoch": 8.16627358490566, "percentage": 40.83, "elapsed_time": "0:26:28", "remaining_time": "0:38:21", "throughput": 5743.0, "total_tokens": 9121264} {"current_steps": 13855, "total_steps": 33920, "loss": 0.3409, "lr": 7.371492038128305e-06, "epoch": 8.169221698113208, "percentage": 40.85, "elapsed_time": "0:26:28", "remaining_time": "0:38:21", "throughput": 5743.31, "total_tokens": 9125424} {"current_steps": 13860, "total_steps": 33920, "loss": 0.4168, "lr": 7.36922679905003e-06, "epoch": 8.172169811320755, "percentage": 40.86, "elapsed_time": "0:26:29", "remaining_time": "0:38:20", "throughput": 5743.41, "total_tokens": 9128976} {"current_steps": 13865, "total_steps": 33920, "loss": 0.3741, "lr": 7.366960932708749e-06, "epoch": 8.175117924528301, "percentage": 40.88, "elapsed_time": "0:26:29", "remaining_time": "0:38:19", "throughput": 5743.48, "total_tokens": 9131984} {"current_steps": 13870, "total_steps": 33920, "loss": 0.5639, "lr": 7.364694439704361e-06, "epoch": 8.17806603773585, "percentage": 40.89, "elapsed_time": "0:26:30", "remaining_time": "0:38:19", "throughput": 5743.47, "total_tokens": 9134928} {"current_steps": 13875, "total_steps": 33920, "loss": 0.4021, "lr": 7.3624273206369264e-06, "epoch": 8.181014150943396, "percentage": 40.91, "elapsed_time": "0:26:31", "remaining_time": "0:38:18", "throughput": 5743.54, "total_tokens": 9138160} {"current_steps": 13880, "total_steps": 33920, "loss": 0.4155, "lr": 7.360159576106681e-06, "epoch": 8.183962264150944, "percentage": 40.92, "elapsed_time": "0:26:31", "remaining_time": "0:38:17", "throughput": 5743.93, "total_tokens": 9142128} {"current_steps": 13885, "total_steps": 33920, "loss": 0.4404, "lr": 7.357891206714014e-06, "epoch": 8.18691037735849, "percentage": 40.93, "elapsed_time": "0:26:32", "remaining_time": "0:38:17", "throughput": 5744.13, "total_tokens": 9145264} {"current_steps": 13890, "total_steps": 33920, "loss": 0.3466, "lr": 7.355622213059487e-06, "epoch": 8.189858490566039, "percentage": 40.95, "elapsed_time": "0:26:32", "remaining_time": "0:38:16", "throughput": 5744.17, "total_tokens": 9148112} {"current_steps": 13895, "total_steps": 33920, "loss": 0.3022, "lr": 7.353352595743829e-06, "epoch": 8.192806603773585, "percentage": 40.96, "elapsed_time": "0:26:33", "remaining_time": "0:38:15", "throughput": 5744.06, "total_tokens": 9150704} {"current_steps": 13900, "total_steps": 33920, "loss": 0.3419, "lr": 7.351082355367928e-06, "epoch": 8.195754716981131, "percentage": 40.98, "elapsed_time": "0:26:33", "remaining_time": "0:38:15", "throughput": 5744.11, "total_tokens": 9153936} {"current_steps": 13905, "total_steps": 33920, "loss": 0.5638, "lr": 7.34881149253284e-06, "epoch": 8.19870283018868, "percentage": 40.99, "elapsed_time": "0:26:34", "remaining_time": "0:38:14", "throughput": 5744.23, "total_tokens": 9157776} {"current_steps": 13910, "total_steps": 33920, "loss": 0.4448, "lr": 7.346540007839787e-06, "epoch": 8.201650943396226, "percentage": 41.01, "elapsed_time": "0:26:34", "remaining_time": "0:38:14", "throughput": 5744.39, "total_tokens": 9161488} {"current_steps": 13915, "total_steps": 33920, "loss": 0.4064, "lr": 7.344267901890154e-06, "epoch": 8.204599056603774, "percentage": 41.02, "elapsed_time": "0:26:35", "remaining_time": "0:38:13", "throughput": 5744.35, "total_tokens": 9164208} {"current_steps": 13920, "total_steps": 33920, "loss": 0.3181, "lr": 7.341995175285491e-06, "epoch": 8.20754716981132, "percentage": 41.04, "elapsed_time": "0:26:35", "remaining_time": "0:38:12", "throughput": 5744.48, "total_tokens": 9167344} {"current_steps": 13925, "total_steps": 33920, "loss": 0.2954, "lr": 7.339721828627512e-06, "epoch": 8.210495283018869, "percentage": 41.05, "elapsed_time": "0:26:36", "remaining_time": "0:38:12", "throughput": 5744.68, "total_tokens": 9171088} {"current_steps": 13930, "total_steps": 33920, "loss": 0.4682, "lr": 7.337447862518096e-06, "epoch": 8.213443396226415, "percentage": 41.07, "elapsed_time": "0:26:36", "remaining_time": "0:38:11", "throughput": 5744.65, "total_tokens": 9174128} {"current_steps": 13935, "total_steps": 33920, "loss": 0.515, "lr": 7.335173277559282e-06, "epoch": 8.216391509433961, "percentage": 41.08, "elapsed_time": "0:26:37", "remaining_time": "0:38:11", "throughput": 5745.07, "total_tokens": 9178576} {"current_steps": 13940, "total_steps": 33920, "loss": 0.4989, "lr": 7.332898074353281e-06, "epoch": 8.21933962264151, "percentage": 41.1, "elapsed_time": "0:26:38", "remaining_time": "0:38:10", "throughput": 5745.29, "total_tokens": 9181968} {"current_steps": 13945, "total_steps": 33920, "loss": 0.5387, "lr": 7.330622253502461e-06, "epoch": 8.222287735849056, "percentage": 41.11, "elapsed_time": "0:26:38", "remaining_time": "0:38:09", "throughput": 5745.28, "total_tokens": 9184912} {"current_steps": 13950, "total_steps": 33920, "loss": 0.5097, "lr": 7.3283458156093534e-06, "epoch": 8.225235849056604, "percentage": 41.13, "elapsed_time": "0:26:39", "remaining_time": "0:38:09", "throughput": 5745.39, "total_tokens": 9188176} {"current_steps": 13955, "total_steps": 33920, "loss": 0.4382, "lr": 7.326068761276657e-06, "epoch": 8.22818396226415, "percentage": 41.14, "elapsed_time": "0:26:39", "remaining_time": "0:38:08", "throughput": 5745.62, "total_tokens": 9191376} {"current_steps": 13960, "total_steps": 33920, "loss": 0.4316, "lr": 7.323791091107231e-06, "epoch": 8.231132075471699, "percentage": 41.16, "elapsed_time": "0:26:40", "remaining_time": "0:38:08", "throughput": 5745.78, "total_tokens": 9194800} {"current_steps": 13965, "total_steps": 33920, "loss": 0.356, "lr": 7.3215128057040986e-06, "epoch": 8.234080188679245, "percentage": 41.17, "elapsed_time": "0:26:40", "remaining_time": "0:38:07", "throughput": 5745.81, "total_tokens": 9197680} {"current_steps": 13970, "total_steps": 33920, "loss": 0.4317, "lr": 7.319233905670447e-06, "epoch": 8.237028301886792, "percentage": 41.19, "elapsed_time": "0:26:41", "remaining_time": "0:38:06", "throughput": 5745.84, "total_tokens": 9200976} {"current_steps": 13975, "total_steps": 33920, "loss": 0.4006, "lr": 7.316954391609622e-06, "epoch": 8.23997641509434, "percentage": 41.2, "elapsed_time": "0:26:41", "remaining_time": "0:38:06", "throughput": 5746.17, "total_tokens": 9204944} {"current_steps": 13980, "total_steps": 33920, "loss": 0.3648, "lr": 7.314674264125137e-06, "epoch": 8.242924528301886, "percentage": 41.21, "elapsed_time": "0:26:42", "remaining_time": "0:38:05", "throughput": 5746.04, "total_tokens": 9207536} {"current_steps": 13985, "total_steps": 33920, "loss": 0.4463, "lr": 7.312393523820665e-06, "epoch": 8.245872641509434, "percentage": 41.23, "elapsed_time": "0:26:43", "remaining_time": "0:38:05", "throughput": 5746.63, "total_tokens": 9213136} {"current_steps": 13990, "total_steps": 33920, "loss": 0.3641, "lr": 7.310112171300041e-06, "epoch": 8.24882075471698, "percentage": 41.24, "elapsed_time": "0:26:43", "remaining_time": "0:38:04", "throughput": 5746.94, "total_tokens": 9216752} {"current_steps": 13995, "total_steps": 33920, "loss": 0.4339, "lr": 7.307830207167263e-06, "epoch": 8.251768867924529, "percentage": 41.26, "elapsed_time": "0:26:44", "remaining_time": "0:38:04", "throughput": 5747.11, "total_tokens": 9220240} {"current_steps": 14000, "total_steps": 33920, "loss": 0.3773, "lr": 7.305547632026493e-06, "epoch": 8.254716981132075, "percentage": 41.27, "elapsed_time": "0:26:44", "remaining_time": "0:38:03", "throughput": 5747.05, "total_tokens": 9222864} {"current_steps": 14005, "total_steps": 33920, "loss": 0.2655, "lr": 7.3032644464820515e-06, "epoch": 8.257665094339623, "percentage": 41.29, "elapsed_time": "0:26:45", "remaining_time": "0:38:02", "throughput": 5746.79, "total_tokens": 9225296} {"current_steps": 14010, "total_steps": 33920, "loss": 0.4156, "lr": 7.30098065113842e-06, "epoch": 8.26061320754717, "percentage": 41.3, "elapsed_time": "0:26:45", "remaining_time": "0:38:02", "throughput": 5746.46, "total_tokens": 9227696} {"current_steps": 14015, "total_steps": 33920, "loss": 0.51, "lr": 7.298696246600244e-06, "epoch": 8.263561320754716, "percentage": 41.32, "elapsed_time": "0:26:46", "remaining_time": "0:38:01", "throughput": 5746.33, "total_tokens": 9230384} {"current_steps": 14020, "total_steps": 33920, "loss": 0.3572, "lr": 7.2964112334723315e-06, "epoch": 8.266509433962264, "percentage": 41.33, "elapsed_time": "0:26:46", "remaining_time": "0:38:00", "throughput": 5746.49, "total_tokens": 9234384} {"current_steps": 14025, "total_steps": 33920, "loss": 0.4624, "lr": 7.294125612359647e-06, "epoch": 8.26945754716981, "percentage": 41.35, "elapsed_time": "0:26:47", "remaining_time": "0:38:00", "throughput": 5746.93, "total_tokens": 9239056} {"current_steps": 14030, "total_steps": 33920, "loss": 0.3987, "lr": 7.291839383867318e-06, "epoch": 8.272405660377359, "percentage": 41.36, "elapsed_time": "0:26:48", "remaining_time": "0:37:59", "throughput": 5746.86, "total_tokens": 9241616} {"current_steps": 14035, "total_steps": 33920, "loss": 0.4439, "lr": 7.289552548600638e-06, "epoch": 8.275353773584905, "percentage": 41.38, "elapsed_time": "0:26:48", "remaining_time": "0:37:59", "throughput": 5746.91, "total_tokens": 9245200} {"current_steps": 14040, "total_steps": 33920, "loss": 0.322, "lr": 7.287265107165052e-06, "epoch": 8.278301886792454, "percentage": 41.39, "elapsed_time": "0:26:49", "remaining_time": "0:37:58", "throughput": 5747.04, "total_tokens": 9248304} {"current_steps": 14045, "total_steps": 33920, "loss": 0.3898, "lr": 7.284977060166171e-06, "epoch": 8.28125, "percentage": 41.41, "elapsed_time": "0:26:49", "remaining_time": "0:37:57", "throughput": 5747.21, "total_tokens": 9251664} {"current_steps": 14050, "total_steps": 33920, "loss": 0.5222, "lr": 7.282688408209766e-06, "epoch": 8.284198113207546, "percentage": 41.42, "elapsed_time": "0:26:50", "remaining_time": "0:37:57", "throughput": 5747.13, "total_tokens": 9254640} {"current_steps": 14055, "total_steps": 33920, "loss": 0.4618, "lr": 7.2803991519017655e-06, "epoch": 8.287146226415095, "percentage": 41.44, "elapsed_time": "0:26:50", "remaining_time": "0:37:56", "throughput": 5747.04, "total_tokens": 9257424} {"current_steps": 14060, "total_steps": 33920, "loss": 0.2689, "lr": 7.2781092918482634e-06, "epoch": 8.290094339622641, "percentage": 41.45, "elapsed_time": "0:26:51", "remaining_time": "0:37:56", "throughput": 5747.33, "total_tokens": 9261040} {"current_steps": 14065, "total_steps": 33920, "loss": 0.2895, "lr": 7.275818828655508e-06, "epoch": 8.29304245283019, "percentage": 41.47, "elapsed_time": "0:26:52", "remaining_time": "0:37:55", "throughput": 5747.58, "total_tokens": 9265744} {"current_steps": 14070, "total_steps": 33920, "loss": 0.4313, "lr": 7.27352776292991e-06, "epoch": 8.295990566037736, "percentage": 41.48, "elapsed_time": "0:26:52", "remaining_time": "0:37:55", "throughput": 5747.91, "total_tokens": 9269904} {"current_steps": 14075, "total_steps": 33920, "loss": 0.3456, "lr": 7.271236095278036e-06, "epoch": 8.298938679245284, "percentage": 41.49, "elapsed_time": "0:26:53", "remaining_time": "0:37:54", "throughput": 5747.92, "total_tokens": 9272976} {"current_steps": 14080, "total_steps": 33920, "loss": 0.5673, "lr": 7.2689438263066195e-06, "epoch": 8.30188679245283, "percentage": 41.51, "elapsed_time": "0:26:53", "remaining_time": "0:37:53", "throughput": 5747.97, "total_tokens": 9276016} {"current_steps": 14085, "total_steps": 33920, "loss": 0.5651, "lr": 7.266650956622546e-06, "epoch": 8.304834905660377, "percentage": 41.52, "elapsed_time": "0:26:54", "remaining_time": "0:37:53", "throughput": 5747.9, "total_tokens": 9278640} {"current_steps": 14090, "total_steps": 33920, "loss": 0.4133, "lr": 7.2643574868328625e-06, "epoch": 8.307783018867925, "percentage": 41.54, "elapsed_time": "0:26:54", "remaining_time": "0:37:52", "throughput": 5747.79, "total_tokens": 9281744} {"current_steps": 14095, "total_steps": 33920, "loss": 0.5088, "lr": 7.262063417544776e-06, "epoch": 8.310731132075471, "percentage": 41.55, "elapsed_time": "0:26:55", "remaining_time": "0:37:52", "throughput": 5747.91, "total_tokens": 9285232} {"current_steps": 14100, "total_steps": 33920, "loss": 0.4382, "lr": 7.25976874936565e-06, "epoch": 8.31367924528302, "percentage": 41.57, "elapsed_time": "0:26:56", "remaining_time": "0:37:51", "throughput": 5748.08, "total_tokens": 9288912} {"current_steps": 14105, "total_steps": 33920, "loss": 0.3888, "lr": 7.257473482903009e-06, "epoch": 8.316627358490566, "percentage": 41.58, "elapsed_time": "0:26:56", "remaining_time": "0:37:50", "throughput": 5748.43, "total_tokens": 9292592} {"current_steps": 14110, "total_steps": 33920, "loss": 0.3185, "lr": 7.255177618764534e-06, "epoch": 8.319575471698114, "percentage": 41.6, "elapsed_time": "0:26:57", "remaining_time": "0:37:50", "throughput": 5748.83, "total_tokens": 9297008} {"current_steps": 14115, "total_steps": 33920, "loss": 0.4918, "lr": 7.252881157558065e-06, "epoch": 8.32252358490566, "percentage": 41.61, "elapsed_time": "0:26:57", "remaining_time": "0:37:49", "throughput": 5749.03, "total_tokens": 9300464} {"current_steps": 14120, "total_steps": 33920, "loss": 0.349, "lr": 7.250584099891602e-06, "epoch": 8.325471698113208, "percentage": 41.63, "elapsed_time": "0:26:58", "remaining_time": "0:37:49", "throughput": 5749.19, "total_tokens": 9303760} {"current_steps": 14125, "total_steps": 33920, "loss": 0.315, "lr": 7.248286446373296e-06, "epoch": 8.328419811320755, "percentage": 41.64, "elapsed_time": "0:26:58", "remaining_time": "0:37:48", "throughput": 5749.44, "total_tokens": 9307440} {"current_steps": 14130, "total_steps": 33920, "loss": 0.3633, "lr": 7.245988197611466e-06, "epoch": 8.331367924528301, "percentage": 41.66, "elapsed_time": "0:26:59", "remaining_time": "0:37:48", "throughput": 5749.66, "total_tokens": 9310704} {"current_steps": 14135, "total_steps": 33920, "loss": 0.4213, "lr": 7.2436893542145805e-06, "epoch": 8.33431603773585, "percentage": 41.67, "elapsed_time": "0:26:59", "remaining_time": "0:37:47", "throughput": 5749.62, "total_tokens": 9313744} {"current_steps": 14140, "total_steps": 33920, "loss": 0.4272, "lr": 7.241389916791269e-06, "epoch": 8.337264150943396, "percentage": 41.69, "elapsed_time": "0:27:00", "remaining_time": "0:37:47", "throughput": 5749.81, "total_tokens": 9318224} {"current_steps": 14145, "total_steps": 33920, "loss": 0.4812, "lr": 7.239089885950317e-06, "epoch": 8.340212264150944, "percentage": 41.7, "elapsed_time": "0:27:01", "remaining_time": "0:37:46", "throughput": 5750.08, "total_tokens": 9322064} {"current_steps": 14150, "total_steps": 33920, "loss": 0.3977, "lr": 7.236789262300667e-06, "epoch": 8.34316037735849, "percentage": 41.72, "elapsed_time": "0:27:01", "remaining_time": "0:37:45", "throughput": 5750.03, "total_tokens": 9324912} {"current_steps": 14155, "total_steps": 33920, "loss": 0.385, "lr": 7.23448804645142e-06, "epoch": 8.346108490566039, "percentage": 41.73, "elapsed_time": "0:27:02", "remaining_time": "0:37:45", "throughput": 5750.12, "total_tokens": 9327984} {"current_steps": 14160, "total_steps": 33920, "loss": 0.2551, "lr": 7.232186239011834e-06, "epoch": 8.349056603773585, "percentage": 41.75, "elapsed_time": "0:27:02", "remaining_time": "0:37:44", "throughput": 5750.17, "total_tokens": 9331376} {"current_steps": 14165, "total_steps": 33920, "loss": 0.4941, "lr": 7.2298838405913195e-06, "epoch": 8.352004716981131, "percentage": 41.76, "elapsed_time": "0:27:03", "remaining_time": "0:37:44", "throughput": 5750.44, "total_tokens": 9335248} {"current_steps": 14170, "total_steps": 33920, "loss": 0.4153, "lr": 7.227580851799448e-06, "epoch": 8.35495283018868, "percentage": 41.77, "elapsed_time": "0:27:03", "remaining_time": "0:37:43", "throughput": 5750.46, "total_tokens": 9338064} {"current_steps": 14175, "total_steps": 33920, "loss": 0.4723, "lr": 7.2252772732459455e-06, "epoch": 8.357900943396226, "percentage": 41.79, "elapsed_time": "0:27:04", "remaining_time": "0:37:42", "throughput": 5750.62, "total_tokens": 9341232} {"current_steps": 14180, "total_steps": 33920, "loss": 0.3703, "lr": 7.222973105540696e-06, "epoch": 8.360849056603774, "percentage": 41.8, "elapsed_time": "0:27:04", "remaining_time": "0:37:42", "throughput": 5750.44, "total_tokens": 9343856} {"current_steps": 14185, "total_steps": 33920, "loss": 0.4622, "lr": 7.2206683492937345e-06, "epoch": 8.36379716981132, "percentage": 41.82, "elapsed_time": "0:27:05", "remaining_time": "0:37:41", "throughput": 5750.45, "total_tokens": 9346768} {"current_steps": 14190, "total_steps": 33920, "loss": 0.4127, "lr": 7.218363005115259e-06, "epoch": 8.366745283018869, "percentage": 41.83, "elapsed_time": "0:27:05", "remaining_time": "0:37:40", "throughput": 5750.28, "total_tokens": 9349264} {"current_steps": 14195, "total_steps": 33920, "loss": 0.4411, "lr": 7.216057073615617e-06, "epoch": 8.369693396226415, "percentage": 41.85, "elapsed_time": "0:27:06", "remaining_time": "0:37:40", "throughput": 5750.14, "total_tokens": 9352304} {"current_steps": 14200, "total_steps": 33920, "loss": 0.4545, "lr": 7.21375055540531e-06, "epoch": 8.372641509433961, "percentage": 41.86, "elapsed_time": "0:27:07", "remaining_time": "0:37:39", "throughput": 5750.41, "total_tokens": 9356112} {"current_steps": 14205, "total_steps": 33920, "loss": 0.3846, "lr": 7.211443451095007e-06, "epoch": 8.37558962264151, "percentage": 41.88, "elapsed_time": "0:27:07", "remaining_time": "0:37:38", "throughput": 5750.34, "total_tokens": 9359216} {"current_steps": 14210, "total_steps": 33920, "loss": 0.4222, "lr": 7.2091357612955185e-06, "epoch": 8.378537735849056, "percentage": 41.89, "elapsed_time": "0:27:08", "remaining_time": "0:37:38", "throughput": 5750.29, "total_tokens": 9362160} {"current_steps": 14215, "total_steps": 33920, "loss": 0.394, "lr": 7.206827486617816e-06, "epoch": 8.381485849056604, "percentage": 41.91, "elapsed_time": "0:27:08", "remaining_time": "0:37:37", "throughput": 5750.47, "total_tokens": 9365616} {"current_steps": 14220, "total_steps": 33920, "loss": 0.4117, "lr": 7.204518627673026e-06, "epoch": 8.38443396226415, "percentage": 41.92, "elapsed_time": "0:27:09", "remaining_time": "0:37:37", "throughput": 5750.46, "total_tokens": 9368880} {"current_steps": 14225, "total_steps": 33920, "loss": 0.3784, "lr": 7.202209185072428e-06, "epoch": 8.387382075471699, "percentage": 41.94, "elapsed_time": "0:27:09", "remaining_time": "0:37:36", "throughput": 5750.2, "total_tokens": 9371600} {"current_steps": 14230, "total_steps": 33920, "loss": 0.4355, "lr": 7.199899159427457e-06, "epoch": 8.390330188679245, "percentage": 41.95, "elapsed_time": "0:27:10", "remaining_time": "0:37:35", "throughput": 5750.4, "total_tokens": 9374992} {"current_steps": 14235, "total_steps": 33920, "loss": 0.4147, "lr": 7.1975885513497035e-06, "epoch": 8.393278301886792, "percentage": 41.97, "elapsed_time": "0:27:10", "remaining_time": "0:37:35", "throughput": 5750.49, "total_tokens": 9378096} {"current_steps": 14240, "total_steps": 33920, "loss": 0.3048, "lr": 7.195277361450909e-06, "epoch": 8.39622641509434, "percentage": 41.98, "elapsed_time": "0:27:11", "remaining_time": "0:37:34", "throughput": 5750.49, "total_tokens": 9381200} {"current_steps": 14245, "total_steps": 33920, "loss": 0.5134, "lr": 7.192965590342973e-06, "epoch": 8.399174528301886, "percentage": 42.0, "elapsed_time": "0:27:11", "remaining_time": "0:37:33", "throughput": 5750.45, "total_tokens": 9383760} {"current_steps": 14250, "total_steps": 33920, "loss": 0.516, "lr": 7.190653238637945e-06, "epoch": 8.402122641509434, "percentage": 42.01, "elapsed_time": "0:27:12", "remaining_time": "0:37:33", "throughput": 5750.48, "total_tokens": 9386672} {"current_steps": 14255, "total_steps": 33920, "loss": 0.4716, "lr": 7.18834030694803e-06, "epoch": 8.40507075471698, "percentage": 42.03, "elapsed_time": "0:27:12", "remaining_time": "0:37:32", "throughput": 5750.58, "total_tokens": 9390128} {"current_steps": 14260, "total_steps": 33920, "loss": 0.532, "lr": 7.186026795885589e-06, "epoch": 8.408018867924529, "percentage": 42.04, "elapsed_time": "0:27:13", "remaining_time": "0:37:31", "throughput": 5750.75, "total_tokens": 9393328} {"current_steps": 14265, "total_steps": 33920, "loss": 0.6031, "lr": 7.183712706063133e-06, "epoch": 8.410966981132075, "percentage": 42.05, "elapsed_time": "0:27:13", "remaining_time": "0:37:31", "throughput": 5750.77, "total_tokens": 9396336} {"current_steps": 14270, "total_steps": 33920, "loss": 0.3649, "lr": 7.1813980380933255e-06, "epoch": 8.413915094339623, "percentage": 42.07, "elapsed_time": "0:27:14", "remaining_time": "0:37:30", "throughput": 5750.81, "total_tokens": 9399600} {"current_steps": 14275, "total_steps": 33920, "loss": 0.3658, "lr": 7.179082792588986e-06, "epoch": 8.41686320754717, "percentage": 42.08, "elapsed_time": "0:27:15", "remaining_time": "0:37:30", "throughput": 5750.97, "total_tokens": 9402864} {"current_steps": 14280, "total_steps": 33920, "loss": 0.3879, "lr": 7.176766970163087e-06, "epoch": 8.419811320754716, "percentage": 42.1, "elapsed_time": "0:27:15", "remaining_time": "0:37:29", "throughput": 5751.14, "total_tokens": 9406256} {"current_steps": 14285, "total_steps": 33920, "loss": 0.4086, "lr": 7.17445057142875e-06, "epoch": 8.422759433962264, "percentage": 42.11, "elapsed_time": "0:27:16", "remaining_time": "0:37:28", "throughput": 5751.41, "total_tokens": 9409872} {"current_steps": 14290, "total_steps": 33920, "loss": 0.3461, "lr": 7.172133596999253e-06, "epoch": 8.42570754716981, "percentage": 42.13, "elapsed_time": "0:27:16", "remaining_time": "0:37:28", "throughput": 5751.49, "total_tokens": 9413072} {"current_steps": 14295, "total_steps": 33920, "loss": 0.448, "lr": 7.1698160474880255e-06, "epoch": 8.428655660377359, "percentage": 42.14, "elapsed_time": "0:27:17", "remaining_time": "0:37:27", "throughput": 5751.31, "total_tokens": 9415536} {"current_steps": 14300, "total_steps": 33920, "loss": 0.3945, "lr": 7.167497923508648e-06, "epoch": 8.431603773584905, "percentage": 42.16, "elapsed_time": "0:27:17", "remaining_time": "0:37:26", "throughput": 5751.27, "total_tokens": 9418384} {"current_steps": 14305, "total_steps": 33920, "loss": 0.4651, "lr": 7.165179225674854e-06, "epoch": 8.434551886792454, "percentage": 42.17, "elapsed_time": "0:27:18", "remaining_time": "0:37:26", "throughput": 5751.2, "total_tokens": 9421360} {"current_steps": 14310, "total_steps": 33920, "loss": 0.3265, "lr": 7.1628599546005276e-06, "epoch": 8.4375, "percentage": 42.19, "elapsed_time": "0:27:18", "remaining_time": "0:37:25", "throughput": 5751.19, "total_tokens": 9424208} {"current_steps": 14315, "total_steps": 33920, "loss": 0.3163, "lr": 7.160540110899708e-06, "epoch": 8.440448113207546, "percentage": 42.2, "elapsed_time": "0:27:19", "remaining_time": "0:37:24", "throughput": 5751.27, "total_tokens": 9427632} {"current_steps": 14320, "total_steps": 33920, "loss": 0.3772, "lr": 7.158219695186582e-06, "epoch": 8.443396226415095, "percentage": 42.22, "elapsed_time": "0:27:19", "remaining_time": "0:37:24", "throughput": 5751.49, "total_tokens": 9431184} {"current_steps": 14325, "total_steps": 33920, "loss": 0.3829, "lr": 7.1558987080754905e-06, "epoch": 8.446344339622641, "percentage": 42.23, "elapsed_time": "0:27:20", "remaining_time": "0:37:23", "throughput": 5751.47, "total_tokens": 9434256} {"current_steps": 14330, "total_steps": 33920, "loss": 0.5402, "lr": 7.1535771501809245e-06, "epoch": 8.44929245283019, "percentage": 42.25, "elapsed_time": "0:27:21", "remaining_time": "0:37:23", "throughput": 5751.97, "total_tokens": 9441680} {"current_steps": 14335, "total_steps": 33920, "loss": 0.4155, "lr": 7.151255022117527e-06, "epoch": 8.452240566037736, "percentage": 42.26, "elapsed_time": "0:27:21", "remaining_time": "0:37:23", "throughput": 5751.95, "total_tokens": 9444432} {"current_steps": 14340, "total_steps": 33920, "loss": 0.509, "lr": 7.148932324500091e-06, "epoch": 8.455188679245284, "percentage": 42.28, "elapsed_time": "0:27:22", "remaining_time": "0:37:22", "throughput": 5752.03, "total_tokens": 9447440} {"current_steps": 14345, "total_steps": 33920, "loss": 0.4263, "lr": 7.146609057943559e-06, "epoch": 8.45813679245283, "percentage": 42.29, "elapsed_time": "0:27:23", "remaining_time": "0:37:22", "throughput": 5752.7, "total_tokens": 9454768} {"current_steps": 14350, "total_steps": 33920, "loss": 0.5042, "lr": 7.14428522306303e-06, "epoch": 8.461084905660377, "percentage": 42.31, "elapsed_time": "0:27:24", "remaining_time": "0:37:22", "throughput": 5752.78, "total_tokens": 9457872} {"current_steps": 14355, "total_steps": 33920, "loss": 0.5227, "lr": 7.141960820473745e-06, "epoch": 8.464033018867925, "percentage": 42.32, "elapsed_time": "0:27:24", "remaining_time": "0:37:21", "throughput": 5752.68, "total_tokens": 9461008} {"current_steps": 14360, "total_steps": 33920, "loss": 0.4048, "lr": 7.139635850791102e-06, "epoch": 8.466981132075471, "percentage": 42.33, "elapsed_time": "0:27:25", "remaining_time": "0:37:20", "throughput": 5752.69, "total_tokens": 9464080} {"current_steps": 14365, "total_steps": 33920, "loss": 0.3527, "lr": 7.137310314630647e-06, "epoch": 8.46992924528302, "percentage": 42.35, "elapsed_time": "0:27:25", "remaining_time": "0:37:20", "throughput": 5752.46, "total_tokens": 9466672} {"current_steps": 14370, "total_steps": 33920, "loss": 0.3123, "lr": 7.134984212608074e-06, "epoch": 8.472877358490566, "percentage": 42.36, "elapsed_time": "0:27:26", "remaining_time": "0:37:20", "throughput": 5752.98, "total_tokens": 9472528} {"current_steps": 14375, "total_steps": 33920, "loss": 0.5056, "lr": 7.13265754533923e-06, "epoch": 8.475825471698114, "percentage": 42.38, "elapsed_time": "0:27:27", "remaining_time": "0:37:19", "throughput": 5753.05, "total_tokens": 9475792} {"current_steps": 14380, "total_steps": 33920, "loss": 0.3099, "lr": 7.130330313440109e-06, "epoch": 8.47877358490566, "percentage": 42.39, "elapsed_time": "0:27:27", "remaining_time": "0:37:18", "throughput": 5753.17, "total_tokens": 9479120} {"current_steps": 14385, "total_steps": 33920, "loss": 0.3164, "lr": 7.128002517526856e-06, "epoch": 8.481721698113208, "percentage": 42.41, "elapsed_time": "0:27:28", "remaining_time": "0:37:18", "throughput": 5753.2, "total_tokens": 9482224} {"current_steps": 14390, "total_steps": 33920, "loss": 0.3905, "lr": 7.1256741582157654e-06, "epoch": 8.484669811320755, "percentage": 42.42, "elapsed_time": "0:27:28", "remaining_time": "0:37:17", "throughput": 5753.14, "total_tokens": 9484816} {"current_steps": 14395, "total_steps": 33920, "loss": 0.3638, "lr": 7.123345236123282e-06, "epoch": 8.487617924528301, "percentage": 42.44, "elapsed_time": "0:27:29", "remaining_time": "0:37:16", "throughput": 5752.95, "total_tokens": 9487248} {"current_steps": 14400, "total_steps": 33920, "loss": 0.3615, "lr": 7.121015751865994e-06, "epoch": 8.49056603773585, "percentage": 42.45, "elapsed_time": "0:27:29", "remaining_time": "0:37:16", "throughput": 5753.16, "total_tokens": 9490672} {"current_steps": 14405, "total_steps": 33920, "loss": 0.473, "lr": 7.118685706060645e-06, "epoch": 8.493514150943396, "percentage": 42.47, "elapsed_time": "0:27:30", "remaining_time": "0:37:15", "throughput": 5753.38, "total_tokens": 9494288} {"current_steps": 14410, "total_steps": 33920, "loss": 0.2988, "lr": 7.116355099324126e-06, "epoch": 8.496462264150944, "percentage": 42.48, "elapsed_time": "0:27:30", "remaining_time": "0:37:14", "throughput": 5753.44, "total_tokens": 9497264} {"current_steps": 14415, "total_steps": 33920, "loss": 0.36, "lr": 7.114023932273471e-06, "epoch": 8.49941037735849, "percentage": 42.5, "elapsed_time": "0:27:31", "remaining_time": "0:37:14", "throughput": 5753.14, "total_tokens": 9499696} {"current_steps": 14420, "total_steps": 33920, "loss": 0.2717, "lr": 7.111692205525871e-06, "epoch": 8.502358490566039, "percentage": 42.51, "elapsed_time": "0:27:31", "remaining_time": "0:37:13", "throughput": 5753.43, "total_tokens": 9503408} {"current_steps": 14425, "total_steps": 33920, "loss": 0.5106, "lr": 7.109359919698658e-06, "epoch": 8.505306603773585, "percentage": 42.53, "elapsed_time": "0:27:32", "remaining_time": "0:37:13", "throughput": 5753.66, "total_tokens": 9507184} {"current_steps": 14430, "total_steps": 33920, "loss": 0.5292, "lr": 7.107027075409316e-06, "epoch": 8.508254716981131, "percentage": 42.54, "elapsed_time": "0:27:32", "remaining_time": "0:37:12", "throughput": 5753.82, "total_tokens": 9510480} {"current_steps": 14435, "total_steps": 33920, "loss": 0.417, "lr": 7.104693673275475e-06, "epoch": 8.51120283018868, "percentage": 42.56, "elapsed_time": "0:27:33", "remaining_time": "0:37:11", "throughput": 5753.58, "total_tokens": 9512912} {"current_steps": 14440, "total_steps": 33920, "loss": 0.393, "lr": 7.1023597139149115e-06, "epoch": 8.514150943396226, "percentage": 42.57, "elapsed_time": "0:27:33", "remaining_time": "0:37:11", "throughput": 5753.74, "total_tokens": 9516400} {"current_steps": 14445, "total_steps": 33920, "loss": 0.2696, "lr": 7.100025197945555e-06, "epoch": 8.517099056603774, "percentage": 42.59, "elapsed_time": "0:27:34", "remaining_time": "0:37:10", "throughput": 5753.74, "total_tokens": 9519536} {"current_steps": 14450, "total_steps": 33920, "loss": 0.3735, "lr": 7.097690125985476e-06, "epoch": 8.52004716981132, "percentage": 42.6, "elapsed_time": "0:27:35", "remaining_time": "0:37:10", "throughput": 5753.97, "total_tokens": 9523344} {"current_steps": 14455, "total_steps": 33920, "loss": 0.5123, "lr": 7.095354498652895e-06, "epoch": 8.522995283018869, "percentage": 42.61, "elapsed_time": "0:27:35", "remaining_time": "0:37:09", "throughput": 5753.88, "total_tokens": 9526032} {"current_steps": 14460, "total_steps": 33920, "loss": 0.3797, "lr": 7.093018316566182e-06, "epoch": 8.525943396226415, "percentage": 42.63, "elapsed_time": "0:27:36", "remaining_time": "0:37:08", "throughput": 5753.97, "total_tokens": 9529424} {"current_steps": 14465, "total_steps": 33920, "loss": 0.3898, "lr": 7.0906815803438465e-06, "epoch": 8.528891509433961, "percentage": 42.64, "elapsed_time": "0:27:36", "remaining_time": "0:37:08", "throughput": 5754.0, "total_tokens": 9532624} {"current_steps": 14470, "total_steps": 33920, "loss": 0.4562, "lr": 7.088344290604554e-06, "epoch": 8.53183962264151, "percentage": 42.66, "elapsed_time": "0:27:37", "remaining_time": "0:37:07", "throughput": 5754.0, "total_tokens": 9535664} {"current_steps": 14475, "total_steps": 33920, "loss": 0.2613, "lr": 7.086006447967111e-06, "epoch": 8.534787735849056, "percentage": 42.67, "elapsed_time": "0:27:37", "remaining_time": "0:37:06", "throughput": 5754.18, "total_tokens": 9539056} {"current_steps": 14480, "total_steps": 33920, "loss": 0.3961, "lr": 7.08366805305047e-06, "epoch": 8.537735849056604, "percentage": 42.69, "elapsed_time": "0:27:38", "remaining_time": "0:37:06", "throughput": 5754.19, "total_tokens": 9541968} {"current_steps": 14485, "total_steps": 33920, "loss": 0.3961, "lr": 7.08132910647373e-06, "epoch": 8.54068396226415, "percentage": 42.7, "elapsed_time": "0:27:38", "remaining_time": "0:37:05", "throughput": 5754.25, "total_tokens": 9545104} {"current_steps": 14490, "total_steps": 33920, "loss": 0.4737, "lr": 7.078989608856142e-06, "epoch": 8.543632075471699, "percentage": 42.72, "elapsed_time": "0:27:39", "remaining_time": "0:37:04", "throughput": 5754.12, "total_tokens": 9547696} {"current_steps": 14495, "total_steps": 33920, "loss": 0.4596, "lr": 7.076649560817092e-06, "epoch": 8.546580188679245, "percentage": 42.73, "elapsed_time": "0:27:39", "remaining_time": "0:37:04", "throughput": 5754.01, "total_tokens": 9550384} {"current_steps": 14500, "total_steps": 33920, "loss": 0.4897, "lr": 7.0743089629761245e-06, "epoch": 8.549528301886792, "percentage": 42.75, "elapsed_time": "0:27:40", "remaining_time": "0:37:03", "throughput": 5753.92, "total_tokens": 9553200} {"current_steps": 14505, "total_steps": 33920, "loss": 0.3657, "lr": 7.071967815952917e-06, "epoch": 8.55247641509434, "percentage": 42.76, "elapsed_time": "0:27:41", "remaining_time": "0:37:03", "throughput": 5754.29, "total_tokens": 9558800} {"current_steps": 14510, "total_steps": 33920, "loss": 0.3844, "lr": 7.0696261203673e-06, "epoch": 8.555424528301886, "percentage": 42.78, "elapsed_time": "0:27:41", "remaining_time": "0:37:02", "throughput": 5754.46, "total_tokens": 9562224} {"current_steps": 14515, "total_steps": 33920, "loss": 0.4624, "lr": 7.067283876839249e-06, "epoch": 8.558372641509434, "percentage": 42.79, "elapsed_time": "0:27:42", "remaining_time": "0:37:02", "throughput": 5754.51, "total_tokens": 9565200} {"current_steps": 14520, "total_steps": 33920, "loss": 0.3077, "lr": 7.064941085988884e-06, "epoch": 8.56132075471698, "percentage": 42.81, "elapsed_time": "0:27:42", "remaining_time": "0:37:01", "throughput": 5754.48, "total_tokens": 9568080} {"current_steps": 14525, "total_steps": 33920, "loss": 0.45, "lr": 7.062597748436464e-06, "epoch": 8.564268867924529, "percentage": 42.82, "elapsed_time": "0:27:43", "remaining_time": "0:37:01", "throughput": 5754.59, "total_tokens": 9571728} {"current_steps": 14530, "total_steps": 33920, "loss": 0.4319, "lr": 7.060253864802402e-06, "epoch": 8.567216981132075, "percentage": 42.84, "elapsed_time": "0:27:43", "remaining_time": "0:37:00", "throughput": 5754.91, "total_tokens": 9575760} {"current_steps": 14535, "total_steps": 33920, "loss": 0.3891, "lr": 7.05790943570725e-06, "epoch": 8.570165094339622, "percentage": 42.85, "elapsed_time": "0:27:44", "remaining_time": "0:36:59", "throughput": 5755.14, "total_tokens": 9579184} {"current_steps": 14540, "total_steps": 33920, "loss": 0.4471, "lr": 7.055564461771704e-06, "epoch": 8.57311320754717, "percentage": 42.87, "elapsed_time": "0:27:45", "remaining_time": "0:36:59", "throughput": 5755.04, "total_tokens": 9582160} {"current_steps": 14545, "total_steps": 33920, "loss": 0.3732, "lr": 7.053218943616611e-06, "epoch": 8.576061320754716, "percentage": 42.88, "elapsed_time": "0:27:45", "remaining_time": "0:36:58", "throughput": 5755.0, "total_tokens": 9584880} {"current_steps": 14550, "total_steps": 33920, "loss": 0.3742, "lr": 7.050872881862952e-06, "epoch": 8.579009433962264, "percentage": 42.9, "elapsed_time": "0:27:46", "remaining_time": "0:36:57", "throughput": 5755.11, "total_tokens": 9588176} {"current_steps": 14555, "total_steps": 33920, "loss": 0.5314, "lr": 7.04852627713186e-06, "epoch": 8.58195754716981, "percentage": 42.91, "elapsed_time": "0:27:46", "remaining_time": "0:36:57", "throughput": 5755.12, "total_tokens": 9591280} {"current_steps": 14560, "total_steps": 33920, "loss": 0.3788, "lr": 7.0461791300446055e-06, "epoch": 8.584905660377359, "percentage": 42.92, "elapsed_time": "0:27:47", "remaining_time": "0:36:56", "throughput": 5755.32, "total_tokens": 9594704} {"current_steps": 14565, "total_steps": 33920, "loss": 0.4005, "lr": 7.043831441222611e-06, "epoch": 8.587853773584905, "percentage": 42.94, "elapsed_time": "0:27:47", "remaining_time": "0:36:56", "throughput": 5754.99, "total_tokens": 9596944} {"current_steps": 14570, "total_steps": 33920, "loss": 0.4399, "lr": 7.04148321128743e-06, "epoch": 8.590801886792454, "percentage": 42.95, "elapsed_time": "0:27:48", "remaining_time": "0:36:55", "throughput": 5754.92, "total_tokens": 9599792} {"current_steps": 14575, "total_steps": 33920, "loss": 0.4287, "lr": 7.039134440860773e-06, "epoch": 8.59375, "percentage": 42.97, "elapsed_time": "0:27:48", "remaining_time": "0:36:54", "throughput": 5755.25, "total_tokens": 9603760} {"current_steps": 14580, "total_steps": 33920, "loss": 0.4367, "lr": 7.036785130564484e-06, "epoch": 8.596698113207546, "percentage": 42.98, "elapsed_time": "0:27:49", "remaining_time": "0:36:54", "throughput": 5755.2, "total_tokens": 9606480} {"current_steps": 14585, "total_steps": 33920, "loss": 0.3861, "lr": 7.0344352810205544e-06, "epoch": 8.599646226415095, "percentage": 43.0, "elapsed_time": "0:27:49", "remaining_time": "0:36:53", "throughput": 5755.17, "total_tokens": 9609264} {"current_steps": 14590, "total_steps": 33920, "loss": 0.2969, "lr": 7.032084892851115e-06, "epoch": 8.602594339622641, "percentage": 43.01, "elapsed_time": "0:27:50", "remaining_time": "0:36:52", "throughput": 5755.39, "total_tokens": 9612528} {"current_steps": 14595, "total_steps": 33920, "loss": 0.3879, "lr": 7.0297339666784425e-06, "epoch": 8.60554245283019, "percentage": 43.03, "elapsed_time": "0:27:50", "remaining_time": "0:36:52", "throughput": 5755.51, "total_tokens": 9615600} {"current_steps": 14600, "total_steps": 33920, "loss": 0.4943, "lr": 7.0273825031249556e-06, "epoch": 8.608490566037736, "percentage": 43.04, "elapsed_time": "0:27:51", "remaining_time": "0:36:51", "throughput": 5755.7, "total_tokens": 9618928} {"current_steps": 14605, "total_steps": 33920, "loss": 0.5256, "lr": 7.025030502813213e-06, "epoch": 8.611438679245284, "percentage": 43.06, "elapsed_time": "0:27:51", "remaining_time": "0:36:50", "throughput": 5755.91, "total_tokens": 9622512} {"current_steps": 14610, "total_steps": 33920, "loss": 0.3294, "lr": 7.022677966365917e-06, "epoch": 8.61438679245283, "percentage": 43.07, "elapsed_time": "0:27:52", "remaining_time": "0:36:50", "throughput": 5755.99, "total_tokens": 9625552} {"current_steps": 14615, "total_steps": 33920, "loss": 0.3854, "lr": 7.020324894405913e-06, "epoch": 8.617334905660378, "percentage": 43.09, "elapsed_time": "0:27:52", "remaining_time": "0:36:49", "throughput": 5755.65, "total_tokens": 9627888} {"current_steps": 14620, "total_steps": 33920, "loss": 0.4034, "lr": 7.017971287556185e-06, "epoch": 8.620283018867925, "percentage": 43.1, "elapsed_time": "0:27:53", "remaining_time": "0:36:48", "throughput": 5755.89, "total_tokens": 9631440} {"current_steps": 14625, "total_steps": 33920, "loss": 0.3278, "lr": 7.015617146439863e-06, "epoch": 8.623231132075471, "percentage": 43.12, "elapsed_time": "0:27:54", "remaining_time": "0:36:48", "throughput": 5756.27, "total_tokens": 9636368} {"current_steps": 14630, "total_steps": 33920, "loss": 0.514, "lr": 7.0132624716802125e-06, "epoch": 8.62617924528302, "percentage": 43.13, "elapsed_time": "0:27:54", "remaining_time": "0:36:47", "throughput": 5756.33, "total_tokens": 9639344} {"current_steps": 14635, "total_steps": 33920, "loss": 0.3615, "lr": 7.0109072639006474e-06, "epoch": 8.629127358490566, "percentage": 43.15, "elapsed_time": "0:27:55", "remaining_time": "0:36:47", "throughput": 5756.18, "total_tokens": 9641808} {"current_steps": 14640, "total_steps": 33920, "loss": 0.3708, "lr": 7.008551523724717e-06, "epoch": 8.632075471698114, "percentage": 43.16, "elapsed_time": "0:27:55", "remaining_time": "0:36:46", "throughput": 5756.4, "total_tokens": 9645104} {"current_steps": 14645, "total_steps": 33920, "loss": 0.4096, "lr": 7.006195251776116e-06, "epoch": 8.63502358490566, "percentage": 43.18, "elapsed_time": "0:27:56", "remaining_time": "0:36:46", "throughput": 5756.64, "total_tokens": 9648848} {"current_steps": 14650, "total_steps": 33920, "loss": 0.31, "lr": 7.003838448678674e-06, "epoch": 8.637971698113208, "percentage": 43.19, "elapsed_time": "0:27:56", "remaining_time": "0:36:45", "throughput": 5756.74, "total_tokens": 9652752} {"current_steps": 14655, "total_steps": 33920, "loss": 0.3395, "lr": 7.0014811150563675e-06, "epoch": 8.640919811320755, "percentage": 43.2, "elapsed_time": "0:27:57", "remaining_time": "0:36:44", "throughput": 5756.85, "total_tokens": 9656048} {"current_steps": 14660, "total_steps": 33920, "loss": 0.3764, "lr": 6.999123251533311e-06, "epoch": 8.643867924528301, "percentage": 43.22, "elapsed_time": "0:27:57", "remaining_time": "0:36:44", "throughput": 5756.96, "total_tokens": 9659472} {"current_steps": 14665, "total_steps": 33920, "loss": 0.4102, "lr": 6.996764858733756e-06, "epoch": 8.64681603773585, "percentage": 43.23, "elapsed_time": "0:27:58", "remaining_time": "0:36:43", "throughput": 5756.96, "total_tokens": 9662544} {"current_steps": 14670, "total_steps": 33920, "loss": 0.3832, "lr": 6.994405937282099e-06, "epoch": 8.649764150943396, "percentage": 43.25, "elapsed_time": "0:27:58", "remaining_time": "0:36:43", "throughput": 5756.86, "total_tokens": 9665168} {"current_steps": 14675, "total_steps": 33920, "loss": 0.5294, "lr": 6.9920464878028745e-06, "epoch": 8.652712264150944, "percentage": 43.26, "elapsed_time": "0:27:59", "remaining_time": "0:36:42", "throughput": 5756.89, "total_tokens": 9668336} {"current_steps": 14680, "total_steps": 33920, "loss": 0.4458, "lr": 6.989686510920758e-06, "epoch": 8.65566037735849, "percentage": 43.28, "elapsed_time": "0:27:59", "remaining_time": "0:36:41", "throughput": 5756.93, "total_tokens": 9671344} {"current_steps": 14685, "total_steps": 33920, "loss": 0.4076, "lr": 6.9873260072605634e-06, "epoch": 8.658608490566039, "percentage": 43.29, "elapsed_time": "0:28:00", "remaining_time": "0:36:41", "throughput": 5757.04, "total_tokens": 9674480} {"current_steps": 14690, "total_steps": 33920, "loss": 0.3586, "lr": 6.984964977447243e-06, "epoch": 8.661556603773585, "percentage": 43.31, "elapsed_time": "0:28:01", "remaining_time": "0:36:40", "throughput": 5757.35, "total_tokens": 9678544} {"current_steps": 14695, "total_steps": 33920, "loss": 0.3537, "lr": 6.982603422105889e-06, "epoch": 8.664504716981131, "percentage": 43.32, "elapsed_time": "0:28:01", "remaining_time": "0:36:40", "throughput": 5756.97, "total_tokens": 9681040} {"current_steps": 14700, "total_steps": 33920, "loss": 0.4171, "lr": 6.980241341861736e-06, "epoch": 8.66745283018868, "percentage": 43.34, "elapsed_time": "0:28:02", "remaining_time": "0:36:39", "throughput": 5757.19, "total_tokens": 9684304} {"current_steps": 14705, "total_steps": 33920, "loss": 0.3896, "lr": 6.977878737340153e-06, "epoch": 8.670400943396226, "percentage": 43.35, "elapsed_time": "0:28:02", "remaining_time": "0:36:38", "throughput": 5757.37, "total_tokens": 9687728} {"current_steps": 14710, "total_steps": 33920, "loss": 0.3111, "lr": 6.97551560916665e-06, "epoch": 8.673349056603774, "percentage": 43.37, "elapsed_time": "0:28:03", "remaining_time": "0:36:38", "throughput": 5757.41, "total_tokens": 9690512} {"current_steps": 14715, "total_steps": 33920, "loss": 0.4103, "lr": 6.973151957966875e-06, "epoch": 8.67629716981132, "percentage": 43.38, "elapsed_time": "0:28:03", "remaining_time": "0:36:37", "throughput": 5757.53, "total_tokens": 9693776} {"current_steps": 14720, "total_steps": 33920, "loss": 0.3441, "lr": 6.970787784366616e-06, "epoch": 8.679245283018869, "percentage": 43.4, "elapsed_time": "0:28:04", "remaining_time": "0:36:36", "throughput": 5757.8, "total_tokens": 9697584} {"current_steps": 14725, "total_steps": 33920, "loss": 0.3822, "lr": 6.968423088991797e-06, "epoch": 8.682193396226415, "percentage": 43.41, "elapsed_time": "0:28:04", "remaining_time": "0:36:36", "throughput": 5758.18, "total_tokens": 9701744} {"current_steps": 14730, "total_steps": 33920, "loss": 0.3305, "lr": 6.966057872468481e-06, "epoch": 8.685141509433961, "percentage": 43.43, "elapsed_time": "0:28:05", "remaining_time": "0:36:35", "throughput": 5758.29, "total_tokens": 9704880} {"current_steps": 14735, "total_steps": 33920, "loss": 0.4792, "lr": 6.963692135422872e-06, "epoch": 8.68808962264151, "percentage": 43.44, "elapsed_time": "0:28:05", "remaining_time": "0:36:35", "throughput": 5758.35, "total_tokens": 9708048} {"current_steps": 14740, "total_steps": 33920, "loss": 0.4285, "lr": 6.961325878481305e-06, "epoch": 8.691037735849056, "percentage": 43.46, "elapsed_time": "0:28:06", "remaining_time": "0:36:34", "throughput": 5758.7, "total_tokens": 9712240} {"current_steps": 14745, "total_steps": 33920, "loss": 0.4784, "lr": 6.958959102270259e-06, "epoch": 8.693985849056604, "percentage": 43.47, "elapsed_time": "0:28:07", "remaining_time": "0:36:33", "throughput": 5758.55, "total_tokens": 9714960} {"current_steps": 14750, "total_steps": 33920, "loss": 0.3839, "lr": 6.95659180741635e-06, "epoch": 8.69693396226415, "percentage": 43.48, "elapsed_time": "0:28:07", "remaining_time": "0:36:33", "throughput": 5758.67, "total_tokens": 9717968} {"current_steps": 14755, "total_steps": 33920, "loss": 0.5077, "lr": 6.954223994546326e-06, "epoch": 8.699882075471699, "percentage": 43.5, "elapsed_time": "0:28:08", "remaining_time": "0:36:32", "throughput": 5758.84, "total_tokens": 9721424} {"current_steps": 14760, "total_steps": 33920, "loss": 0.4426, "lr": 6.951855664287077e-06, "epoch": 8.702830188679245, "percentage": 43.51, "elapsed_time": "0:28:08", "remaining_time": "0:36:31", "throughput": 5758.87, "total_tokens": 9724336} {"current_steps": 14765, "total_steps": 33920, "loss": 0.3786, "lr": 6.9494868172656304e-06, "epoch": 8.705778301886792, "percentage": 43.53, "elapsed_time": "0:28:09", "remaining_time": "0:36:31", "throughput": 5759.12, "total_tokens": 9727888} {"current_steps": 14770, "total_steps": 33920, "loss": 0.4551, "lr": 6.947117454109146e-06, "epoch": 8.70872641509434, "percentage": 43.54, "elapsed_time": "0:28:09", "remaining_time": "0:36:30", "throughput": 5759.09, "total_tokens": 9730576} {"current_steps": 14775, "total_steps": 33920, "loss": 0.3004, "lr": 6.944747575444924e-06, "epoch": 8.711674528301886, "percentage": 43.56, "elapsed_time": "0:28:10", "remaining_time": "0:36:29", "throughput": 5759.1, "total_tokens": 9733520} {"current_steps": 14780, "total_steps": 33920, "loss": 0.3492, "lr": 6.942377181900399e-06, "epoch": 8.714622641509434, "percentage": 43.57, "elapsed_time": "0:28:10", "remaining_time": "0:36:29", "throughput": 5759.05, "total_tokens": 9736368} {"current_steps": 14785, "total_steps": 33920, "loss": 0.436, "lr": 6.940006274103146e-06, "epoch": 8.71757075471698, "percentage": 43.59, "elapsed_time": "0:28:11", "remaining_time": "0:36:28", "throughput": 5759.07, "total_tokens": 9739152} {"current_steps": 14790, "total_steps": 33920, "loss": 0.3965, "lr": 6.93763485268087e-06, "epoch": 8.720518867924529, "percentage": 43.6, "elapsed_time": "0:28:11", "remaining_time": "0:36:27", "throughput": 5758.91, "total_tokens": 9741808} {"current_steps": 14795, "total_steps": 33920, "loss": 0.4341, "lr": 6.935262918261416e-06, "epoch": 8.723466981132075, "percentage": 43.62, "elapsed_time": "0:28:12", "remaining_time": "0:36:27", "throughput": 5758.9, "total_tokens": 9745104} {"current_steps": 14800, "total_steps": 33920, "loss": 0.3238, "lr": 6.932890471472764e-06, "epoch": 8.726415094339622, "percentage": 43.63, "elapsed_time": "0:28:12", "remaining_time": "0:36:26", "throughput": 5759.07, "total_tokens": 9748368} {"current_steps": 14805, "total_steps": 33920, "loss": 0.3357, "lr": 6.930517512943029e-06, "epoch": 8.72936320754717, "percentage": 43.65, "elapsed_time": "0:28:13", "remaining_time": "0:36:26", "throughput": 5759.51, "total_tokens": 9753648} {"current_steps": 14810, "total_steps": 33920, "loss": 0.3539, "lr": 6.928144043300463e-06, "epoch": 8.732311320754716, "percentage": 43.66, "elapsed_time": "0:28:13", "remaining_time": "0:36:25", "throughput": 5759.47, "total_tokens": 9756368} {"current_steps": 14815, "total_steps": 33920, "loss": 0.4372, "lr": 6.925770063173451e-06, "epoch": 8.735259433962264, "percentage": 43.68, "elapsed_time": "0:28:14", "remaining_time": "0:36:25", "throughput": 5759.84, "total_tokens": 9761200} {"current_steps": 14820, "total_steps": 33920, "loss": 0.3592, "lr": 6.923395573190514e-06, "epoch": 8.73820754716981, "percentage": 43.69, "elapsed_time": "0:28:15", "remaining_time": "0:36:24", "throughput": 5759.93, "total_tokens": 9764400} {"current_steps": 14825, "total_steps": 33920, "loss": 0.3501, "lr": 6.921020573980313e-06, "epoch": 8.741155660377359, "percentage": 43.71, "elapsed_time": "0:28:15", "remaining_time": "0:36:24", "throughput": 5759.61, "total_tokens": 9766576} {"current_steps": 14830, "total_steps": 33920, "loss": 0.4067, "lr": 6.918645066171634e-06, "epoch": 8.744103773584905, "percentage": 43.72, "elapsed_time": "0:28:16", "remaining_time": "0:36:23", "throughput": 5759.69, "total_tokens": 9769584} {"current_steps": 14835, "total_steps": 33920, "loss": 0.3625, "lr": 6.916269050393404e-06, "epoch": 8.747051886792454, "percentage": 43.74, "elapsed_time": "0:28:16", "remaining_time": "0:36:22", "throughput": 5759.92, "total_tokens": 9772912} {"current_steps": 14840, "total_steps": 33920, "loss": 0.502, "lr": 6.913892527274686e-06, "epoch": 8.75, "percentage": 43.75, "elapsed_time": "0:28:17", "remaining_time": "0:36:22", "throughput": 5760.37, "total_tokens": 9779248} {"current_steps": 14845, "total_steps": 33920, "loss": 0.4122, "lr": 6.9115154974446716e-06, "epoch": 8.752948113207546, "percentage": 43.76, "elapsed_time": "0:28:18", "remaining_time": "0:36:22", "throughput": 5760.44, "total_tokens": 9782384} {"current_steps": 14850, "total_steps": 33920, "loss": 0.3307, "lr": 6.909137961532692e-06, "epoch": 8.755896226415095, "percentage": 43.78, "elapsed_time": "0:28:18", "remaining_time": "0:36:21", "throughput": 5760.62, "total_tokens": 9786032} {"current_steps": 14855, "total_steps": 33920, "loss": 0.3788, "lr": 6.906759920168209e-06, "epoch": 8.758844339622641, "percentage": 43.79, "elapsed_time": "0:28:19", "remaining_time": "0:36:20", "throughput": 5760.74, "total_tokens": 9789648} {"current_steps": 14860, "total_steps": 33920, "loss": 0.5233, "lr": 6.90438137398082e-06, "epoch": 8.76179245283019, "percentage": 43.81, "elapsed_time": "0:28:19", "remaining_time": "0:36:20", "throughput": 5760.95, "total_tokens": 9793264} {"current_steps": 14865, "total_steps": 33920, "loss": 0.3027, "lr": 6.902002323600252e-06, "epoch": 8.764740566037736, "percentage": 43.82, "elapsed_time": "0:28:20", "remaining_time": "0:36:19", "throughput": 5760.86, "total_tokens": 9795856} {"current_steps": 14870, "total_steps": 33920, "loss": 0.4261, "lr": 6.899622769656373e-06, "epoch": 8.767688679245284, "percentage": 43.84, "elapsed_time": "0:28:20", "remaining_time": "0:36:19", "throughput": 5761.15, "total_tokens": 9799696} {"current_steps": 14875, "total_steps": 33920, "loss": 0.3516, "lr": 6.897242712779179e-06, "epoch": 8.77063679245283, "percentage": 43.85, "elapsed_time": "0:28:21", "remaining_time": "0:36:18", "throughput": 5760.98, "total_tokens": 9802576} {"current_steps": 14880, "total_steps": 33920, "loss": 0.3853, "lr": 6.894862153598802e-06, "epoch": 8.773584905660378, "percentage": 43.87, "elapsed_time": "0:28:22", "remaining_time": "0:36:17", "throughput": 5761.14, "total_tokens": 9806000} {"current_steps": 14885, "total_steps": 33920, "loss": 0.5326, "lr": 6.892481092745502e-06, "epoch": 8.776533018867925, "percentage": 43.88, "elapsed_time": "0:28:22", "remaining_time": "0:36:17", "throughput": 5761.15, "total_tokens": 9808720} {"current_steps": 14890, "total_steps": 33920, "loss": 0.4566, "lr": 6.890099530849677e-06, "epoch": 8.779481132075471, "percentage": 43.9, "elapsed_time": "0:28:23", "remaining_time": "0:36:16", "throughput": 5761.29, "total_tokens": 9812176} {"current_steps": 14895, "total_steps": 33920, "loss": 0.4473, "lr": 6.887717468541855e-06, "epoch": 8.78242924528302, "percentage": 43.91, "elapsed_time": "0:28:23", "remaining_time": "0:36:16", "throughput": 5761.46, "total_tokens": 9815568} {"current_steps": 14900, "total_steps": 33920, "loss": 0.4307, "lr": 6.885334906452696e-06, "epoch": 8.785377358490566, "percentage": 43.93, "elapsed_time": "0:28:24", "remaining_time": "0:36:15", "throughput": 5761.27, "total_tokens": 9817936} {"current_steps": 14905, "total_steps": 33920, "loss": 0.5848, "lr": 6.882951845212997e-06, "epoch": 8.788325471698114, "percentage": 43.94, "elapsed_time": "0:28:25", "remaining_time": "0:36:15", "throughput": 5761.62, "total_tokens": 9823920} {"current_steps": 14910, "total_steps": 33920, "loss": 0.4125, "lr": 6.880568285453682e-06, "epoch": 8.79127358490566, "percentage": 43.96, "elapsed_time": "0:28:25", "remaining_time": "0:36:14", "throughput": 5761.76, "total_tokens": 9827952} {"current_steps": 14915, "total_steps": 33920, "loss": 0.412, "lr": 6.878184227805807e-06, "epoch": 8.794221698113208, "percentage": 43.97, "elapsed_time": "0:28:26", "remaining_time": "0:36:14", "throughput": 5761.88, "total_tokens": 9831760} {"current_steps": 14920, "total_steps": 33920, "loss": 0.3481, "lr": 6.8757996729005645e-06, "epoch": 8.797169811320755, "percentage": 43.99, "elapsed_time": "0:28:26", "remaining_time": "0:36:13", "throughput": 5762.03, "total_tokens": 9835024} {"current_steps": 14925, "total_steps": 33920, "loss": 0.4268, "lr": 6.8734146213692756e-06, "epoch": 8.800117924528301, "percentage": 44.0, "elapsed_time": "0:28:27", "remaining_time": "0:36:13", "throughput": 5762.27, "total_tokens": 9838704} {"current_steps": 14930, "total_steps": 33920, "loss": 0.4463, "lr": 6.87102907384339e-06, "epoch": 8.80306603773585, "percentage": 44.02, "elapsed_time": "0:28:27", "remaining_time": "0:36:12", "throughput": 5762.11, "total_tokens": 9841392} {"current_steps": 14935, "total_steps": 33920, "loss": 0.3902, "lr": 6.868643030954494e-06, "epoch": 8.806014150943396, "percentage": 44.03, "elapsed_time": "0:28:28", "remaining_time": "0:36:11", "throughput": 5762.16, "total_tokens": 9844688} {"current_steps": 14940, "total_steps": 33920, "loss": 0.4415, "lr": 6.866256493334302e-06, "epoch": 8.808962264150944, "percentage": 44.04, "elapsed_time": "0:28:29", "remaining_time": "0:36:11", "throughput": 5762.39, "total_tokens": 9848272} {"current_steps": 14945, "total_steps": 33920, "loss": 0.378, "lr": 6.863869461614659e-06, "epoch": 8.81191037735849, "percentage": 44.06, "elapsed_time": "0:28:29", "remaining_time": "0:36:10", "throughput": 5762.29, "total_tokens": 9851056} {"current_steps": 14950, "total_steps": 33920, "loss": 0.3488, "lr": 6.861481936427545e-06, "epoch": 8.814858490566039, "percentage": 44.07, "elapsed_time": "0:28:30", "remaining_time": "0:36:09", "throughput": 5762.26, "total_tokens": 9853712} {"current_steps": 14955, "total_steps": 33920, "loss": 0.4817, "lr": 6.859093918405067e-06, "epoch": 8.817806603773585, "percentage": 44.09, "elapsed_time": "0:28:30", "remaining_time": "0:36:09", "throughput": 5762.18, "total_tokens": 9856272} {"current_steps": 14960, "total_steps": 33920, "loss": 0.3902, "lr": 6.856705408179458e-06, "epoch": 8.820754716981131, "percentage": 44.1, "elapsed_time": "0:28:30", "remaining_time": "0:36:08", "throughput": 5762.06, "total_tokens": 9858864} {"current_steps": 14965, "total_steps": 33920, "loss": 0.4003, "lr": 6.854316406383093e-06, "epoch": 8.82370283018868, "percentage": 44.12, "elapsed_time": "0:28:31", "remaining_time": "0:36:07", "throughput": 5762.21, "total_tokens": 9862000} {"current_steps": 14970, "total_steps": 33920, "loss": 0.62, "lr": 6.8519269136484665e-06, "epoch": 8.826650943396226, "percentage": 44.13, "elapsed_time": "0:28:32", "remaining_time": "0:36:07", "throughput": 5762.39, "total_tokens": 9865232} {"current_steps": 14975, "total_steps": 33920, "loss": 0.3342, "lr": 6.849536930608208e-06, "epoch": 8.829599056603774, "percentage": 44.15, "elapsed_time": "0:28:32", "remaining_time": "0:36:06", "throughput": 5762.31, "total_tokens": 9867792} {"current_steps": 14980, "total_steps": 33920, "loss": 0.3836, "lr": 6.847146457895078e-06, "epoch": 8.83254716981132, "percentage": 44.16, "elapsed_time": "0:28:33", "remaining_time": "0:36:05", "throughput": 5762.46, "total_tokens": 9871216} {"current_steps": 14985, "total_steps": 33920, "loss": 0.4956, "lr": 6.8447554961419615e-06, "epoch": 8.835495283018869, "percentage": 44.18, "elapsed_time": "0:28:33", "remaining_time": "0:36:05", "throughput": 5762.58, "total_tokens": 9874448} {"current_steps": 14990, "total_steps": 33920, "loss": 0.4028, "lr": 6.842364045981876e-06, "epoch": 8.838443396226415, "percentage": 44.19, "elapsed_time": "0:28:34", "remaining_time": "0:36:04", "throughput": 5762.74, "total_tokens": 9877968} {"current_steps": 14995, "total_steps": 33920, "loss": 0.4299, "lr": 6.83997210804797e-06, "epoch": 8.841391509433961, "percentage": 44.21, "elapsed_time": "0:28:34", "remaining_time": "0:36:04", "throughput": 5762.96, "total_tokens": 9881968} {"current_steps": 15000, "total_steps": 33920, "loss": 0.4149, "lr": 6.837579682973519e-06, "epoch": 8.84433962264151, "percentage": 44.22, "elapsed_time": "0:28:35", "remaining_time": "0:36:03", "throughput": 5763.1, "total_tokens": 9885520} {"current_steps": 15005, "total_steps": 33920, "loss": 0.4172, "lr": 6.835186771391926e-06, "epoch": 8.847287735849056, "percentage": 44.24, "elapsed_time": "0:28:35", "remaining_time": "0:36:03", "throughput": 5763.41, "total_tokens": 9889840} {"current_steps": 15010, "total_steps": 33920, "loss": 0.3497, "lr": 6.8327933739367266e-06, "epoch": 8.850235849056604, "percentage": 44.25, "elapsed_time": "0:28:36", "remaining_time": "0:36:02", "throughput": 5763.53, "total_tokens": 9893168} {"current_steps": 15015, "total_steps": 33920, "loss": 0.3034, "lr": 6.830399491241584e-06, "epoch": 8.85318396226415, "percentage": 44.27, "elapsed_time": "0:28:37", "remaining_time": "0:36:01", "throughput": 5763.78, "total_tokens": 9896752} {"current_steps": 15020, "total_steps": 33920, "loss": 0.4806, "lr": 6.828005123940287e-06, "epoch": 8.856132075471699, "percentage": 44.28, "elapsed_time": "0:28:37", "remaining_time": "0:36:01", "throughput": 5764.1, "total_tokens": 9900496} {"current_steps": 15025, "total_steps": 33920, "loss": 0.3455, "lr": 6.825610272666754e-06, "epoch": 8.859080188679245, "percentage": 44.3, "elapsed_time": "0:28:38", "remaining_time": "0:36:00", "throughput": 5764.23, "total_tokens": 9903472} {"current_steps": 15030, "total_steps": 33920, "loss": 0.3066, "lr": 6.823214938055034e-06, "epoch": 8.862028301886792, "percentage": 44.31, "elapsed_time": "0:28:38", "remaining_time": "0:36:00", "throughput": 5764.51, "total_tokens": 9907280} {"current_steps": 15035, "total_steps": 33920, "loss": 0.4943, "lr": 6.8208191207393e-06, "epoch": 8.86497641509434, "percentage": 44.32, "elapsed_time": "0:28:39", "remaining_time": "0:35:59", "throughput": 5764.53, "total_tokens": 9910128} {"current_steps": 15040, "total_steps": 33920, "loss": 0.4882, "lr": 6.818422821353859e-06, "epoch": 8.867924528301886, "percentage": 44.34, "elapsed_time": "0:28:39", "remaining_time": "0:35:58", "throughput": 5764.76, "total_tokens": 9914224} {"current_steps": 15045, "total_steps": 33920, "loss": 0.3132, "lr": 6.816026040533139e-06, "epoch": 8.870872641509434, "percentage": 44.35, "elapsed_time": "0:28:40", "remaining_time": "0:35:58", "throughput": 5764.64, "total_tokens": 9916912} {"current_steps": 15050, "total_steps": 33920, "loss": 0.3566, "lr": 6.8136287789116966e-06, "epoch": 8.87382075471698, "percentage": 44.37, "elapsed_time": "0:28:40", "remaining_time": "0:35:57", "throughput": 5764.75, "total_tokens": 9920464} {"current_steps": 15055, "total_steps": 33920, "loss": 0.4491, "lr": 6.81123103712422e-06, "epoch": 8.876768867924529, "percentage": 44.38, "elapsed_time": "0:28:41", "remaining_time": "0:35:57", "throughput": 5764.74, "total_tokens": 9923376} {"current_steps": 15060, "total_steps": 33920, "loss": 0.5668, "lr": 6.808832815805518e-06, "epoch": 8.879716981132075, "percentage": 44.4, "elapsed_time": "0:28:41", "remaining_time": "0:35:56", "throughput": 5764.97, "total_tokens": 9927184} {"current_steps": 15065, "total_steps": 33920, "loss": 0.3227, "lr": 6.806434115590534e-06, "epoch": 8.882665094339622, "percentage": 44.41, "elapsed_time": "0:28:42", "remaining_time": "0:35:55", "throughput": 5765.03, "total_tokens": 9930384} {"current_steps": 15070, "total_steps": 33920, "loss": 0.3758, "lr": 6.804034937114332e-06, "epoch": 8.88561320754717, "percentage": 44.43, "elapsed_time": "0:28:43", "remaining_time": "0:35:55", "throughput": 5765.04, "total_tokens": 9933392} {"current_steps": 15075, "total_steps": 33920, "loss": 0.4805, "lr": 6.8016352810121064e-06, "epoch": 8.888561320754716, "percentage": 44.44, "elapsed_time": "0:28:43", "remaining_time": "0:35:54", "throughput": 5765.17, "total_tokens": 9936912} {"current_steps": 15080, "total_steps": 33920, "loss": 0.475, "lr": 6.799235147919176e-06, "epoch": 8.891509433962264, "percentage": 44.46, "elapsed_time": "0:28:44", "remaining_time": "0:35:53", "throughput": 5765.26, "total_tokens": 9939888} {"current_steps": 15085, "total_steps": 33920, "loss": 0.4648, "lr": 6.796834538470985e-06, "epoch": 8.89445754716981, "percentage": 44.47, "elapsed_time": "0:28:44", "remaining_time": "0:35:53", "throughput": 5765.46, "total_tokens": 9943216} {"current_steps": 15090, "total_steps": 33920, "loss": 0.3022, "lr": 6.794433453303106e-06, "epoch": 8.897405660377359, "percentage": 44.49, "elapsed_time": "0:28:45", "remaining_time": "0:35:52", "throughput": 5765.58, "total_tokens": 9946160} {"current_steps": 15095, "total_steps": 33920, "loss": 0.4346, "lr": 6.792031893051238e-06, "epoch": 8.900353773584905, "percentage": 44.5, "elapsed_time": "0:28:45", "remaining_time": "0:35:52", "throughput": 5765.92, "total_tokens": 9950352} {"current_steps": 15100, "total_steps": 33920, "loss": 0.4233, "lr": 6.789629858351201e-06, "epoch": 8.903301886792454, "percentage": 44.52, "elapsed_time": "0:28:46", "remaining_time": "0:35:51", "throughput": 5766.17, "total_tokens": 9954000} {"current_steps": 15105, "total_steps": 33920, "loss": 0.434, "lr": 6.787227349838946e-06, "epoch": 8.90625, "percentage": 44.53, "elapsed_time": "0:28:46", "remaining_time": "0:35:50", "throughput": 5766.23, "total_tokens": 9957040} {"current_steps": 15110, "total_steps": 33920, "loss": 0.428, "lr": 6.784824368150548e-06, "epoch": 8.909198113207546, "percentage": 44.55, "elapsed_time": "0:28:47", "remaining_time": "0:35:50", "throughput": 5766.26, "total_tokens": 9960112} {"current_steps": 15115, "total_steps": 33920, "loss": 0.4508, "lr": 6.7824209139222076e-06, "epoch": 8.912146226415095, "percentage": 44.56, "elapsed_time": "0:28:47", "remaining_time": "0:35:49", "throughput": 5766.39, "total_tokens": 9963600} {"current_steps": 15120, "total_steps": 33920, "loss": 0.3221, "lr": 6.780016987790248e-06, "epoch": 8.915094339622641, "percentage": 44.58, "elapsed_time": "0:28:48", "remaining_time": "0:35:49", "throughput": 5766.57, "total_tokens": 9967120} {"current_steps": 15125, "total_steps": 33920, "loss": 0.4, "lr": 6.7776125903911194e-06, "epoch": 8.91804245283019, "percentage": 44.59, "elapsed_time": "0:28:48", "remaining_time": "0:35:48", "throughput": 5766.41, "total_tokens": 9969648} {"current_steps": 15130, "total_steps": 33920, "loss": 0.3599, "lr": 6.775207722361396e-06, "epoch": 8.920990566037736, "percentage": 44.6, "elapsed_time": "0:28:49", "remaining_time": "0:35:47", "throughput": 5766.44, "total_tokens": 9972624} {"current_steps": 15135, "total_steps": 33920, "loss": 0.4664, "lr": 6.772802384337778e-06, "epoch": 8.923938679245284, "percentage": 44.62, "elapsed_time": "0:28:49", "remaining_time": "0:35:47", "throughput": 5766.44, "total_tokens": 9975856} {"current_steps": 15140, "total_steps": 33920, "loss": 0.3172, "lr": 6.770396576957088e-06, "epoch": 8.92688679245283, "percentage": 44.63, "elapsed_time": "0:28:50", "remaining_time": "0:35:46", "throughput": 5766.81, "total_tokens": 9980336} {"current_steps": 15145, "total_steps": 33920, "loss": 0.4792, "lr": 6.767990300856274e-06, "epoch": 8.929834905660378, "percentage": 44.65, "elapsed_time": "0:28:51", "remaining_time": "0:35:46", "throughput": 5766.65, "total_tokens": 9982896} {"current_steps": 15150, "total_steps": 33920, "loss": 0.4385, "lr": 6.765583556672408e-06, "epoch": 8.932783018867925, "percentage": 44.66, "elapsed_time": "0:28:51", "remaining_time": "0:35:45", "throughput": 5766.71, "total_tokens": 9985808} {"current_steps": 15155, "total_steps": 33920, "loss": 0.3542, "lr": 6.763176345042687e-06, "epoch": 8.935731132075471, "percentage": 44.68, "elapsed_time": "0:28:52", "remaining_time": "0:35:44", "throughput": 5766.51, "total_tokens": 9988400} {"current_steps": 15160, "total_steps": 33920, "loss": 0.4296, "lr": 6.760768666604429e-06, "epoch": 8.93867924528302, "percentage": 44.69, "elapsed_time": "0:28:52", "remaining_time": "0:35:44", "throughput": 5766.49, "total_tokens": 9991536} {"current_steps": 15165, "total_steps": 33920, "loss": 0.3158, "lr": 6.758360521995079e-06, "epoch": 8.941627358490566, "percentage": 44.71, "elapsed_time": "0:28:53", "remaining_time": "0:35:43", "throughput": 5766.48, "total_tokens": 9994448} {"current_steps": 15170, "total_steps": 33920, "loss": 0.43, "lr": 6.755951911852202e-06, "epoch": 8.944575471698114, "percentage": 44.72, "elapsed_time": "0:28:53", "remaining_time": "0:35:42", "throughput": 5766.64, "total_tokens": 9997584} {"current_steps": 15175, "total_steps": 33920, "loss": 0.332, "lr": 6.7535428368134885e-06, "epoch": 8.94752358490566, "percentage": 44.74, "elapsed_time": "0:28:54", "remaining_time": "0:35:42", "throughput": 5766.71, "total_tokens": 10000624} {"current_steps": 15180, "total_steps": 33920, "loss": 0.4222, "lr": 6.751133297516752e-06, "epoch": 8.950471698113208, "percentage": 44.75, "elapsed_time": "0:28:54", "remaining_time": "0:35:41", "throughput": 5766.65, "total_tokens": 10003696} {"current_steps": 15185, "total_steps": 33920, "loss": 0.3971, "lr": 6.748723294599928e-06, "epoch": 8.953419811320755, "percentage": 44.77, "elapsed_time": "0:28:55", "remaining_time": "0:35:41", "throughput": 5766.66, "total_tokens": 10006992} {"current_steps": 15190, "total_steps": 33920, "loss": 0.5256, "lr": 6.746312828701075e-06, "epoch": 8.956367924528301, "percentage": 44.78, "elapsed_time": "0:28:55", "remaining_time": "0:35:40", "throughput": 5766.4, "total_tokens": 10009456} {"current_steps": 15195, "total_steps": 33920, "loss": 0.4394, "lr": 6.743901900458374e-06, "epoch": 8.95931603773585, "percentage": 44.8, "elapsed_time": "0:28:56", "remaining_time": "0:35:39", "throughput": 5766.4, "total_tokens": 10012752} {"current_steps": 15200, "total_steps": 33920, "loss": 0.3747, "lr": 6.741490510510129e-06, "epoch": 8.962264150943396, "percentage": 44.81, "elapsed_time": "0:28:56", "remaining_time": "0:35:39", "throughput": 5766.41, "total_tokens": 10016016} {"current_steps": 15205, "total_steps": 33920, "loss": 0.4653, "lr": 6.7390786594947665e-06, "epoch": 8.965212264150944, "percentage": 44.83, "elapsed_time": "0:28:57", "remaining_time": "0:35:38", "throughput": 5766.77, "total_tokens": 10020176} {"current_steps": 15210, "total_steps": 33920, "loss": 0.574, "lr": 6.7366663480508335e-06, "epoch": 8.96816037735849, "percentage": 44.84, "elapsed_time": "0:28:58", "remaining_time": "0:35:38", "throughput": 5766.67, "total_tokens": 10022864} {"current_steps": 15215, "total_steps": 33920, "loss": 0.2998, "lr": 6.734253576817002e-06, "epoch": 8.971108490566039, "percentage": 44.86, "elapsed_time": "0:28:58", "remaining_time": "0:35:37", "throughput": 5766.62, "total_tokens": 10025776} {"current_steps": 15220, "total_steps": 33920, "loss": 0.3626, "lr": 6.731840346432061e-06, "epoch": 8.974056603773585, "percentage": 44.87, "elapsed_time": "0:28:59", "remaining_time": "0:35:36", "throughput": 5766.65, "total_tokens": 10028560} {"current_steps": 15225, "total_steps": 33920, "loss": 0.3695, "lr": 6.729426657534922e-06, "epoch": 8.977004716981131, "percentage": 44.89, "elapsed_time": "0:28:59", "remaining_time": "0:35:36", "throughput": 5766.63, "total_tokens": 10031408} {"current_steps": 15230, "total_steps": 33920, "loss": 0.3048, "lr": 6.727012510764624e-06, "epoch": 8.97995283018868, "percentage": 44.9, "elapsed_time": "0:29:00", "remaining_time": "0:35:35", "throughput": 5766.72, "total_tokens": 10034960} {"current_steps": 15235, "total_steps": 33920, "loss": 0.5018, "lr": 6.724597906760322e-06, "epoch": 8.982900943396226, "percentage": 44.91, "elapsed_time": "0:29:00", "remaining_time": "0:35:34", "throughput": 5766.91, "total_tokens": 10038544} {"current_steps": 15240, "total_steps": 33920, "loss": 0.376, "lr": 6.722182846161289e-06, "epoch": 8.985849056603774, "percentage": 44.93, "elapsed_time": "0:29:01", "remaining_time": "0:35:34", "throughput": 5766.98, "total_tokens": 10041488} {"current_steps": 15245, "total_steps": 33920, "loss": 0.4869, "lr": 6.719767329606926e-06, "epoch": 8.98879716981132, "percentage": 44.94, "elapsed_time": "0:29:01", "remaining_time": "0:35:33", "throughput": 5767.4, "total_tokens": 10045680} {"current_steps": 15250, "total_steps": 33920, "loss": 0.312, "lr": 6.717351357736751e-06, "epoch": 8.991745283018869, "percentage": 44.96, "elapsed_time": "0:29:02", "remaining_time": "0:35:33", "throughput": 5767.49, "total_tokens": 10048816} {"current_steps": 15255, "total_steps": 33920, "loss": 0.4906, "lr": 6.7149349311904025e-06, "epoch": 8.994693396226415, "percentage": 44.97, "elapsed_time": "0:29:02", "remaining_time": "0:35:32", "throughput": 5767.43, "total_tokens": 10051632} {"current_steps": 15260, "total_steps": 33920, "loss": 0.3336, "lr": 6.712518050607642e-06, "epoch": 8.997641509433961, "percentage": 44.99, "elapsed_time": "0:29:03", "remaining_time": "0:35:31", "throughput": 5767.75, "total_tokens": 10055344} {"current_steps": 15265, "total_steps": 33920, "loss": 0.3089, "lr": 6.710100716628345e-06, "epoch": 9.00058962264151, "percentage": 45.0, "elapsed_time": "0:29:04", "remaining_time": "0:35:31", "throughput": 5766.94, "total_tokens": 10058512} {"current_steps": 15270, "total_steps": 33920, "loss": 0.3634, "lr": 6.707682929892513e-06, "epoch": 9.003537735849056, "percentage": 45.02, "elapsed_time": "0:29:04", "remaining_time": "0:35:30", "throughput": 5767.08, "total_tokens": 10061808} {"current_steps": 15275, "total_steps": 33920, "loss": 0.3887, "lr": 6.705264691040266e-06, "epoch": 9.006485849056604, "percentage": 45.03, "elapsed_time": "0:29:05", "remaining_time": "0:35:30", "throughput": 5767.13, "total_tokens": 10064784} {"current_steps": 15280, "total_steps": 33920, "loss": 0.2358, "lr": 6.7028460007118435e-06, "epoch": 9.00943396226415, "percentage": 45.05, "elapsed_time": "0:29:05", "remaining_time": "0:35:29", "throughput": 5767.32, "total_tokens": 10068464} {"current_steps": 15285, "total_steps": 33920, "loss": 0.3526, "lr": 6.700426859547602e-06, "epoch": 9.012382075471699, "percentage": 45.06, "elapsed_time": "0:29:06", "remaining_time": "0:35:29", "throughput": 5767.67, "total_tokens": 10073520} {"current_steps": 15290, "total_steps": 33920, "loss": 0.3503, "lr": 6.6980072681880224e-06, "epoch": 9.015330188679245, "percentage": 45.08, "elapsed_time": "0:29:07", "remaining_time": "0:35:28", "throughput": 5767.71, "total_tokens": 10076432} {"current_steps": 15295, "total_steps": 33920, "loss": 0.4459, "lr": 6.695587227273699e-06, "epoch": 9.018278301886792, "percentage": 45.09, "elapsed_time": "0:29:07", "remaining_time": "0:35:28", "throughput": 5767.76, "total_tokens": 10079408} {"current_steps": 15300, "total_steps": 33920, "loss": 0.3703, "lr": 6.69316673744535e-06, "epoch": 9.02122641509434, "percentage": 45.11, "elapsed_time": "0:29:08", "remaining_time": "0:35:27", "throughput": 5767.82, "total_tokens": 10082384} {"current_steps": 15305, "total_steps": 33920, "loss": 0.3479, "lr": 6.6907457993438115e-06, "epoch": 9.024174528301886, "percentage": 45.12, "elapsed_time": "0:29:08", "remaining_time": "0:35:26", "throughput": 5767.81, "total_tokens": 10085296} {"current_steps": 15310, "total_steps": 33920, "loss": 0.2981, "lr": 6.688324413610036e-06, "epoch": 9.027122641509434, "percentage": 45.14, "elapsed_time": "0:29:09", "remaining_time": "0:35:26", "throughput": 5767.97, "total_tokens": 10088656} {"current_steps": 15315, "total_steps": 33920, "loss": 0.5301, "lr": 6.685902580885094e-06, "epoch": 9.03007075471698, "percentage": 45.15, "elapsed_time": "0:29:09", "remaining_time": "0:35:25", "throughput": 5768.13, "total_tokens": 10092080} {"current_steps": 15320, "total_steps": 33920, "loss": 0.2865, "lr": 6.6834803018101794e-06, "epoch": 9.033018867924529, "percentage": 45.17, "elapsed_time": "0:29:10", "remaining_time": "0:35:24", "throughput": 5768.49, "total_tokens": 10096400} {"current_steps": 15325, "total_steps": 33920, "loss": 0.2344, "lr": 6.681057577026599e-06, "epoch": 9.035966981132075, "percentage": 45.18, "elapsed_time": "0:29:10", "remaining_time": "0:35:24", "throughput": 5768.74, "total_tokens": 10100688} {"current_steps": 15330, "total_steps": 33920, "loss": 0.3288, "lr": 6.6786344071757795e-06, "epoch": 9.038915094339623, "percentage": 45.19, "elapsed_time": "0:29:11", "remaining_time": "0:35:23", "throughput": 5769.01, "total_tokens": 10104208} {"current_steps": 15335, "total_steps": 33920, "loss": 0.3332, "lr": 6.676210792899267e-06, "epoch": 9.04186320754717, "percentage": 45.21, "elapsed_time": "0:29:12", "remaining_time": "0:35:23", "throughput": 5769.11, "total_tokens": 10107504} {"current_steps": 15340, "total_steps": 33920, "loss": 0.3871, "lr": 6.6737867348387235e-06, "epoch": 9.044811320754716, "percentage": 45.22, "elapsed_time": "0:29:12", "remaining_time": "0:35:22", "throughput": 5769.41, "total_tokens": 10111952} {"current_steps": 15345, "total_steps": 33920, "loss": 0.3008, "lr": 6.671362233635926e-06, "epoch": 9.047759433962264, "percentage": 45.24, "elapsed_time": "0:29:13", "remaining_time": "0:35:22", "throughput": 5769.59, "total_tokens": 10115280} {"current_steps": 15350, "total_steps": 33920, "loss": 0.3436, "lr": 6.668937289932775e-06, "epoch": 9.05070754716981, "percentage": 45.25, "elapsed_time": "0:29:13", "remaining_time": "0:35:21", "throughput": 5769.72, "total_tokens": 10118224} {"current_steps": 15355, "total_steps": 33920, "loss": 0.3723, "lr": 6.666511904371285e-06, "epoch": 9.053655660377359, "percentage": 45.27, "elapsed_time": "0:29:14", "remaining_time": "0:35:20", "throughput": 5769.82, "total_tokens": 10121648} {"current_steps": 15360, "total_steps": 33920, "loss": 0.3351, "lr": 6.664086077593586e-06, "epoch": 9.056603773584905, "percentage": 45.28, "elapsed_time": "0:29:14", "remaining_time": "0:35:20", "throughput": 5769.77, "total_tokens": 10124336} {"current_steps": 15365, "total_steps": 33920, "loss": 0.3092, "lr": 6.661659810241924e-06, "epoch": 9.059551886792454, "percentage": 45.3, "elapsed_time": "0:29:15", "remaining_time": "0:35:19", "throughput": 5769.83, "total_tokens": 10127600} {"current_steps": 15370, "total_steps": 33920, "loss": 0.4212, "lr": 6.659233102958667e-06, "epoch": 9.0625, "percentage": 45.31, "elapsed_time": "0:29:15", "remaining_time": "0:35:18", "throughput": 5769.82, "total_tokens": 10130288} {"current_steps": 15375, "total_steps": 33920, "loss": 0.4061, "lr": 6.6568059563862965e-06, "epoch": 9.065448113207546, "percentage": 45.33, "elapsed_time": "0:29:16", "remaining_time": "0:35:18", "throughput": 5770.02, "total_tokens": 10133808} {"current_steps": 15380, "total_steps": 33920, "loss": 0.5556, "lr": 6.654378371167407e-06, "epoch": 9.068396226415095, "percentage": 45.34, "elapsed_time": "0:29:16", "remaining_time": "0:35:17", "throughput": 5769.83, "total_tokens": 10136208} {"current_steps": 15385, "total_steps": 33920, "loss": 0.3422, "lr": 6.651950347944715e-06, "epoch": 9.071344339622641, "percentage": 45.36, "elapsed_time": "0:29:17", "remaining_time": "0:35:17", "throughput": 5769.89, "total_tokens": 10139216} {"current_steps": 15390, "total_steps": 33920, "loss": 0.4554, "lr": 6.649521887361048e-06, "epoch": 9.07429245283019, "percentage": 45.37, "elapsed_time": "0:29:17", "remaining_time": "0:35:16", "throughput": 5769.94, "total_tokens": 10142256} {"current_steps": 15395, "total_steps": 33920, "loss": 0.3383, "lr": 6.647092990059352e-06, "epoch": 9.077240566037736, "percentage": 45.39, "elapsed_time": "0:29:18", "remaining_time": "0:35:15", "throughput": 5770.07, "total_tokens": 10145648} {"current_steps": 15400, "total_steps": 33920, "loss": 0.3647, "lr": 6.644663656682689e-06, "epoch": 9.080188679245284, "percentage": 45.4, "elapsed_time": "0:29:18", "remaining_time": "0:35:15", "throughput": 5770.04, "total_tokens": 10148272} {"current_steps": 15405, "total_steps": 33920, "loss": 0.2996, "lr": 6.642233887874234e-06, "epoch": 9.08313679245283, "percentage": 45.42, "elapsed_time": "0:29:19", "remaining_time": "0:35:14", "throughput": 5770.01, "total_tokens": 10151088} {"current_steps": 15410, "total_steps": 33920, "loss": 0.5501, "lr": 6.639803684277279e-06, "epoch": 9.086084905660377, "percentage": 45.43, "elapsed_time": "0:29:19", "remaining_time": "0:35:13", "throughput": 5770.24, "total_tokens": 10154384} {"current_steps": 15415, "total_steps": 33920, "loss": 0.4086, "lr": 6.637373046535233e-06, "epoch": 9.089033018867925, "percentage": 45.45, "elapsed_time": "0:29:20", "remaining_time": "0:35:13", "throughput": 5770.49, "total_tokens": 10157904} {"current_steps": 15420, "total_steps": 33920, "loss": 0.5231, "lr": 6.634941975291617e-06, "epoch": 9.091981132075471, "percentage": 45.46, "elapsed_time": "0:29:20", "remaining_time": "0:35:12", "throughput": 5770.45, "total_tokens": 10160784} {"current_steps": 15425, "total_steps": 33920, "loss": 0.3914, "lr": 6.632510471190065e-06, "epoch": 9.09492924528302, "percentage": 45.47, "elapsed_time": "0:29:21", "remaining_time": "0:35:11", "throughput": 5770.74, "total_tokens": 10164400} {"current_steps": 15430, "total_steps": 33920, "loss": 0.3354, "lr": 6.630078534874332e-06, "epoch": 9.097877358490566, "percentage": 45.49, "elapsed_time": "0:29:21", "remaining_time": "0:35:11", "throughput": 5770.94, "total_tokens": 10168080} {"current_steps": 15435, "total_steps": 33920, "loss": 0.4626, "lr": 6.62764616698828e-06, "epoch": 9.100825471698114, "percentage": 45.5, "elapsed_time": "0:29:22", "remaining_time": "0:35:10", "throughput": 5771.09, "total_tokens": 10171440} {"current_steps": 15440, "total_steps": 33920, "loss": 0.3855, "lr": 6.625213368175889e-06, "epoch": 9.10377358490566, "percentage": 45.52, "elapsed_time": "0:29:23", "remaining_time": "0:35:10", "throughput": 5771.23, "total_tokens": 10174736} {"current_steps": 15445, "total_steps": 33920, "loss": 0.3896, "lr": 6.622780139081256e-06, "epoch": 9.106721698113208, "percentage": 45.53, "elapsed_time": "0:29:23", "remaining_time": "0:35:09", "throughput": 5771.37, "total_tokens": 10177968} {"current_steps": 15450, "total_steps": 33920, "loss": 0.308, "lr": 6.620346480348589e-06, "epoch": 9.109669811320755, "percentage": 45.55, "elapsed_time": "0:29:24", "remaining_time": "0:35:08", "throughput": 5771.68, "total_tokens": 10182096} {"current_steps": 15455, "total_steps": 33920, "loss": 0.4058, "lr": 6.617912392622206e-06, "epoch": 9.112617924528301, "percentage": 45.56, "elapsed_time": "0:29:24", "remaining_time": "0:35:08", "throughput": 5771.63, "total_tokens": 10184976} {"current_steps": 15460, "total_steps": 33920, "loss": 0.3297, "lr": 6.615477876546544e-06, "epoch": 9.11556603773585, "percentage": 45.58, "elapsed_time": "0:29:25", "remaining_time": "0:35:07", "throughput": 5771.94, "total_tokens": 10189232} {"current_steps": 15465, "total_steps": 33920, "loss": 0.3577, "lr": 6.6130429327661535e-06, "epoch": 9.118514150943396, "percentage": 45.59, "elapsed_time": "0:29:25", "remaining_time": "0:35:07", "throughput": 5772.38, "total_tokens": 10193872} {"current_steps": 15470, "total_steps": 33920, "loss": 0.5834, "lr": 6.610607561925694e-06, "epoch": 9.121462264150944, "percentage": 45.61, "elapsed_time": "0:29:26", "remaining_time": "0:35:06", "throughput": 5772.6, "total_tokens": 10197360} {"current_steps": 15475, "total_steps": 33920, "loss": 0.3124, "lr": 6.608171764669941e-06, "epoch": 9.12441037735849, "percentage": 45.62, "elapsed_time": "0:29:27", "remaining_time": "0:35:06", "throughput": 5772.66, "total_tokens": 10200496} {"current_steps": 15480, "total_steps": 33920, "loss": 0.4438, "lr": 6.605735541643783e-06, "epoch": 9.127358490566039, "percentage": 45.64, "elapsed_time": "0:29:27", "remaining_time": "0:35:05", "throughput": 5772.92, "total_tokens": 10204784} {"current_steps": 15485, "total_steps": 33920, "loss": 0.2676, "lr": 6.603298893492219e-06, "epoch": 9.130306603773585, "percentage": 45.65, "elapsed_time": "0:29:28", "remaining_time": "0:35:05", "throughput": 5773.0, "total_tokens": 10207920} {"current_steps": 15490, "total_steps": 33920, "loss": 0.542, "lr": 6.6008618208603625e-06, "epoch": 9.133254716981131, "percentage": 45.67, "elapsed_time": "0:29:29", "remaining_time": "0:35:04", "throughput": 5773.48, "total_tokens": 10214032} {"current_steps": 15495, "total_steps": 33920, "loss": 0.4325, "lr": 6.598424324393442e-06, "epoch": 9.13620283018868, "percentage": 45.68, "elapsed_time": "0:29:29", "remaining_time": "0:35:04", "throughput": 5773.57, "total_tokens": 10217136} {"current_steps": 15500, "total_steps": 33920, "loss": 0.4116, "lr": 6.595986404736792e-06, "epoch": 9.139150943396226, "percentage": 45.7, "elapsed_time": "0:29:30", "remaining_time": "0:35:03", "throughput": 5773.49, "total_tokens": 10219728} {"current_steps": 15505, "total_steps": 33920, "loss": 0.3537, "lr": 6.5935480625358615e-06, "epoch": 9.142099056603774, "percentage": 45.71, "elapsed_time": "0:29:30", "remaining_time": "0:35:02", "throughput": 5773.57, "total_tokens": 10222864} {"current_steps": 15510, "total_steps": 33920, "loss": 0.377, "lr": 6.591109298436216e-06, "epoch": 9.14504716981132, "percentage": 45.73, "elapsed_time": "0:29:31", "remaining_time": "0:35:02", "throughput": 5773.72, "total_tokens": 10226160} {"current_steps": 15515, "total_steps": 33920, "loss": 0.3585, "lr": 6.5886701130835255e-06, "epoch": 9.147995283018869, "percentage": 45.74, "elapsed_time": "0:29:31", "remaining_time": "0:35:01", "throughput": 5773.75, "total_tokens": 10229296} {"current_steps": 15520, "total_steps": 33920, "loss": 0.6145, "lr": 6.586230507123574e-06, "epoch": 9.150943396226415, "percentage": 45.75, "elapsed_time": "0:29:32", "remaining_time": "0:35:01", "throughput": 5773.91, "total_tokens": 10232496} {"current_steps": 15525, "total_steps": 33920, "loss": 0.5124, "lr": 6.583790481202261e-06, "epoch": 9.153891509433961, "percentage": 45.77, "elapsed_time": "0:29:32", "remaining_time": "0:35:00", "throughput": 5774.13, "total_tokens": 10236176} {"current_steps": 15530, "total_steps": 33920, "loss": 0.3845, "lr": 6.5813500359655925e-06, "epoch": 9.15683962264151, "percentage": 45.78, "elapsed_time": "0:29:33", "remaining_time": "0:35:00", "throughput": 5774.55, "total_tokens": 10240976} {"current_steps": 15535, "total_steps": 33920, "loss": 0.4629, "lr": 6.578909172059687e-06, "epoch": 9.159787735849056, "percentage": 45.8, "elapsed_time": "0:29:33", "remaining_time": "0:34:59", "throughput": 5774.57, "total_tokens": 10243760} {"current_steps": 15540, "total_steps": 33920, "loss": 0.3208, "lr": 6.576467890130772e-06, "epoch": 9.162735849056604, "percentage": 45.81, "elapsed_time": "0:29:34", "remaining_time": "0:34:59", "throughput": 5775.0, "total_tokens": 10249488} {"current_steps": 15545, "total_steps": 33920, "loss": 0.3414, "lr": 6.574026190825191e-06, "epoch": 9.16568396226415, "percentage": 45.83, "elapsed_time": "0:29:35", "remaining_time": "0:34:58", "throughput": 5775.25, "total_tokens": 10253360} {"current_steps": 15550, "total_steps": 33920, "loss": 0.4506, "lr": 6.57158407478939e-06, "epoch": 9.168632075471699, "percentage": 45.84, "elapsed_time": "0:29:35", "remaining_time": "0:34:57", "throughput": 5775.39, "total_tokens": 10256592} {"current_steps": 15555, "total_steps": 33920, "loss": 0.3927, "lr": 6.569141542669935e-06, "epoch": 9.171580188679245, "percentage": 45.86, "elapsed_time": "0:29:36", "remaining_time": "0:34:57", "throughput": 5775.65, "total_tokens": 10260272} {"current_steps": 15560, "total_steps": 33920, "loss": 0.4328, "lr": 6.566698595113492e-06, "epoch": 9.174528301886792, "percentage": 45.87, "elapsed_time": "0:29:37", "remaining_time": "0:34:56", "throughput": 5776.0, "total_tokens": 10264464} {"current_steps": 15565, "total_steps": 33920, "loss": 0.3105, "lr": 6.564255232766843e-06, "epoch": 9.17747641509434, "percentage": 45.89, "elapsed_time": "0:29:37", "remaining_time": "0:34:56", "throughput": 5776.11, "total_tokens": 10267792} {"current_steps": 15570, "total_steps": 33920, "loss": 0.3905, "lr": 6.561811456276881e-06, "epoch": 9.180424528301886, "percentage": 45.9, "elapsed_time": "0:29:38", "remaining_time": "0:34:55", "throughput": 5775.99, "total_tokens": 10270224} {"current_steps": 15575, "total_steps": 33920, "loss": 0.4422, "lr": 6.559367266290605e-06, "epoch": 9.183372641509434, "percentage": 45.92, "elapsed_time": "0:29:38", "remaining_time": "0:34:54", "throughput": 5775.85, "total_tokens": 10272688} {"current_steps": 15580, "total_steps": 33920, "loss": 0.3231, "lr": 6.556922663455123e-06, "epoch": 9.18632075471698, "percentage": 45.93, "elapsed_time": "0:29:39", "remaining_time": "0:34:54", "throughput": 5775.64, "total_tokens": 10274928} {"current_steps": 15585, "total_steps": 33920, "loss": 0.512, "lr": 6.554477648417657e-06, "epoch": 9.189268867924529, "percentage": 45.95, "elapsed_time": "0:29:39", "remaining_time": "0:34:53", "throughput": 5775.45, "total_tokens": 10278032} {"current_steps": 15590, "total_steps": 33920, "loss": 0.4183, "lr": 6.552032221825535e-06, "epoch": 9.192216981132075, "percentage": 45.96, "elapsed_time": "0:29:40", "remaining_time": "0:34:53", "throughput": 5775.62, "total_tokens": 10281392} {"current_steps": 15595, "total_steps": 33920, "loss": 0.4397, "lr": 6.549586384326192e-06, "epoch": 9.195165094339623, "percentage": 45.98, "elapsed_time": "0:29:40", "remaining_time": "0:34:52", "throughput": 5775.93, "total_tokens": 10285360} {"current_steps": 15600, "total_steps": 33920, "loss": 0.6144, "lr": 6.547140136567176e-06, "epoch": 9.19811320754717, "percentage": 45.99, "elapsed_time": "0:29:41", "remaining_time": "0:34:51", "throughput": 5775.99, "total_tokens": 10288240} {"current_steps": 15605, "total_steps": 33920, "loss": 0.4217, "lr": 6.544693479196142e-06, "epoch": 9.201061320754716, "percentage": 46.01, "elapsed_time": "0:29:41", "remaining_time": "0:34:51", "throughput": 5776.26, "total_tokens": 10291920} {"current_steps": 15610, "total_steps": 33920, "loss": 0.3631, "lr": 6.542246412860851e-06, "epoch": 9.204009433962264, "percentage": 46.02, "elapsed_time": "0:29:42", "remaining_time": "0:34:50", "throughput": 5776.28, "total_tokens": 10295504} {"current_steps": 15615, "total_steps": 33920, "loss": 0.401, "lr": 6.5397989382091754e-06, "epoch": 9.20695754716981, "percentage": 46.03, "elapsed_time": "0:29:42", "remaining_time": "0:34:50", "throughput": 5776.29, "total_tokens": 10298544} {"current_steps": 15620, "total_steps": 33920, "loss": 0.3868, "lr": 6.537351055889096e-06, "epoch": 9.209905660377359, "percentage": 46.05, "elapsed_time": "0:29:43", "remaining_time": "0:34:49", "throughput": 5776.6, "total_tokens": 10302416} {"current_steps": 15625, "total_steps": 33920, "loss": 0.2747, "lr": 6.534902766548698e-06, "epoch": 9.212853773584905, "percentage": 46.06, "elapsed_time": "0:29:44", "remaining_time": "0:34:48", "throughput": 5776.78, "total_tokens": 10305872} {"current_steps": 15630, "total_steps": 33920, "loss": 0.3127, "lr": 6.532454070836176e-06, "epoch": 9.215801886792454, "percentage": 46.08, "elapsed_time": "0:29:44", "remaining_time": "0:34:48", "throughput": 5776.86, "total_tokens": 10308784} {"current_steps": 15635, "total_steps": 33920, "loss": 0.3404, "lr": 6.530004969399836e-06, "epoch": 9.21875, "percentage": 46.09, "elapsed_time": "0:29:44", "remaining_time": "0:34:47", "throughput": 5776.8, "total_tokens": 10311568} {"current_steps": 15640, "total_steps": 33920, "loss": 0.4196, "lr": 6.5275554628880865e-06, "epoch": 9.221698113207546, "percentage": 46.11, "elapsed_time": "0:29:45", "remaining_time": "0:34:46", "throughput": 5776.7, "total_tokens": 10314000} {"current_steps": 15645, "total_steps": 33920, "loss": 0.4763, "lr": 6.525105551949444e-06, "epoch": 9.224646226415095, "percentage": 46.12, "elapsed_time": "0:29:45", "remaining_time": "0:34:46", "throughput": 5776.72, "total_tokens": 10316880} {"current_steps": 15650, "total_steps": 33920, "loss": 0.331, "lr": 6.522655237232535e-06, "epoch": 9.227594339622641, "percentage": 46.14, "elapsed_time": "0:29:46", "remaining_time": "0:34:45", "throughput": 5776.71, "total_tokens": 10319856} {"current_steps": 15655, "total_steps": 33920, "loss": 0.2695, "lr": 6.5202045193860885e-06, "epoch": 9.23054245283019, "percentage": 46.15, "elapsed_time": "0:29:46", "remaining_time": "0:34:44", "throughput": 5776.87, "total_tokens": 10323184} {"current_steps": 15660, "total_steps": 33920, "loss": 0.3704, "lr": 6.517753399058944e-06, "epoch": 9.233490566037736, "percentage": 46.17, "elapsed_time": "0:29:47", "remaining_time": "0:34:44", "throughput": 5776.75, "total_tokens": 10325744} {"current_steps": 15665, "total_steps": 33920, "loss": 0.3358, "lr": 6.515301876900047e-06, "epoch": 9.236438679245284, "percentage": 46.18, "elapsed_time": "0:29:47", "remaining_time": "0:34:43", "throughput": 5776.99, "total_tokens": 10329264} {"current_steps": 15670, "total_steps": 33920, "loss": 0.3235, "lr": 6.512849953558445e-06, "epoch": 9.23938679245283, "percentage": 46.2, "elapsed_time": "0:29:48", "remaining_time": "0:34:43", "throughput": 5777.23, "total_tokens": 10332976} {"current_steps": 15675, "total_steps": 33920, "loss": 0.4397, "lr": 6.510397629683301e-06, "epoch": 9.242334905660377, "percentage": 46.21, "elapsed_time": "0:29:49", "remaining_time": "0:34:42", "throughput": 5777.12, "total_tokens": 10335440} {"current_steps": 15680, "total_steps": 33920, "loss": 0.3979, "lr": 6.507944905923872e-06, "epoch": 9.245283018867925, "percentage": 46.23, "elapsed_time": "0:29:49", "remaining_time": "0:34:41", "throughput": 5776.95, "total_tokens": 10337840} {"current_steps": 15685, "total_steps": 33920, "loss": 0.3284, "lr": 6.505491782929531e-06, "epoch": 9.248231132075471, "percentage": 46.24, "elapsed_time": "0:29:49", "remaining_time": "0:34:40", "throughput": 5776.9, "total_tokens": 10340464} {"current_steps": 15690, "total_steps": 33920, "loss": 0.3522, "lr": 6.5030382613497535e-06, "epoch": 9.25117924528302, "percentage": 46.26, "elapsed_time": "0:29:50", "remaining_time": "0:34:40", "throughput": 5776.99, "total_tokens": 10343568} {"current_steps": 15695, "total_steps": 33920, "loss": 0.3534, "lr": 6.500584341834119e-06, "epoch": 9.254127358490566, "percentage": 46.27, "elapsed_time": "0:29:50", "remaining_time": "0:34:39", "throughput": 5777.08, "total_tokens": 10346480} {"current_steps": 15700, "total_steps": 33920, "loss": 0.3925, "lr": 6.498130025032312e-06, "epoch": 9.257075471698114, "percentage": 46.29, "elapsed_time": "0:29:51", "remaining_time": "0:34:38", "throughput": 5777.15, "total_tokens": 10349264} {"current_steps": 15705, "total_steps": 33920, "loss": 0.3727, "lr": 6.495675311594123e-06, "epoch": 9.26002358490566, "percentage": 46.3, "elapsed_time": "0:29:51", "remaining_time": "0:34:38", "throughput": 5777.35, "total_tokens": 10352688} {"current_steps": 15710, "total_steps": 33920, "loss": 0.3559, "lr": 6.493220202169452e-06, "epoch": 9.262971698113208, "percentage": 46.31, "elapsed_time": "0:29:52", "remaining_time": "0:34:37", "throughput": 5777.51, "total_tokens": 10356048} {"current_steps": 15715, "total_steps": 33920, "loss": 0.3496, "lr": 6.490764697408295e-06, "epoch": 9.265919811320755, "percentage": 46.33, "elapsed_time": "0:29:52", "remaining_time": "0:34:37", "throughput": 5777.54, "total_tokens": 10358800} {"current_steps": 15720, "total_steps": 33920, "loss": 0.4063, "lr": 6.48830879796076e-06, "epoch": 9.268867924528301, "percentage": 46.34, "elapsed_time": "0:29:53", "remaining_time": "0:34:36", "throughput": 5777.67, "total_tokens": 10362096} {"current_steps": 15725, "total_steps": 33920, "loss": 0.3954, "lr": 6.4858525044770546e-06, "epoch": 9.27181603773585, "percentage": 46.36, "elapsed_time": "0:29:53", "remaining_time": "0:34:35", "throughput": 5777.58, "total_tokens": 10364688} {"current_steps": 15730, "total_steps": 33920, "loss": 0.2945, "lr": 6.483395817607497e-06, "epoch": 9.274764150943396, "percentage": 46.37, "elapsed_time": "0:29:54", "remaining_time": "0:34:35", "throughput": 5777.75, "total_tokens": 10368368} {"current_steps": 15735, "total_steps": 33920, "loss": 0.4554, "lr": 6.480938738002504e-06, "epoch": 9.277712264150944, "percentage": 46.39, "elapsed_time": "0:29:55", "remaining_time": "0:34:34", "throughput": 5777.92, "total_tokens": 10371568} {"current_steps": 15740, "total_steps": 33920, "loss": 0.4589, "lr": 6.478481266312597e-06, "epoch": 9.28066037735849, "percentage": 46.4, "elapsed_time": "0:29:55", "remaining_time": "0:34:33", "throughput": 5777.96, "total_tokens": 10374608} {"current_steps": 15745, "total_steps": 33920, "loss": 0.3308, "lr": 6.476023403188403e-06, "epoch": 9.283608490566039, "percentage": 46.42, "elapsed_time": "0:29:56", "remaining_time": "0:34:33", "throughput": 5777.91, "total_tokens": 10377360} {"current_steps": 15750, "total_steps": 33920, "loss": 0.3199, "lr": 6.473565149280651e-06, "epoch": 9.286556603773585, "percentage": 46.43, "elapsed_time": "0:29:56", "remaining_time": "0:34:32", "throughput": 5778.01, "total_tokens": 10380592} {"current_steps": 15755, "total_steps": 33920, "loss": 0.437, "lr": 6.471106505240175e-06, "epoch": 9.289504716981131, "percentage": 46.45, "elapsed_time": "0:29:57", "remaining_time": "0:34:32", "throughput": 5778.11, "total_tokens": 10383920} {"current_steps": 15760, "total_steps": 33920, "loss": 0.4269, "lr": 6.468647471717914e-06, "epoch": 9.29245283018868, "percentage": 46.46, "elapsed_time": "0:29:57", "remaining_time": "0:34:31", "throughput": 5778.07, "total_tokens": 10386544} {"current_steps": 15765, "total_steps": 33920, "loss": 0.4011, "lr": 6.466188049364902e-06, "epoch": 9.295400943396226, "percentage": 46.48, "elapsed_time": "0:29:58", "remaining_time": "0:34:30", "throughput": 5778.11, "total_tokens": 10389808} {"current_steps": 15770, "total_steps": 33920, "loss": 0.3676, "lr": 6.463728238832288e-06, "epoch": 9.298349056603774, "percentage": 46.49, "elapsed_time": "0:29:58", "remaining_time": "0:34:30", "throughput": 5778.25, "total_tokens": 10393456} {"current_steps": 15775, "total_steps": 33920, "loss": 0.3108, "lr": 6.461268040771311e-06, "epoch": 9.30129716981132, "percentage": 46.51, "elapsed_time": "0:29:59", "remaining_time": "0:34:29", "throughput": 5778.37, "total_tokens": 10396528} {"current_steps": 15780, "total_steps": 33920, "loss": 0.4034, "lr": 6.458807455833326e-06, "epoch": 9.304245283018869, "percentage": 46.52, "elapsed_time": "0:29:59", "remaining_time": "0:34:28", "throughput": 5778.52, "total_tokens": 10399760} {"current_steps": 15785, "total_steps": 33920, "loss": 0.3829, "lr": 6.456346484669778e-06, "epoch": 9.307193396226415, "percentage": 46.54, "elapsed_time": "0:30:00", "remaining_time": "0:34:28", "throughput": 5778.56, "total_tokens": 10402768} {"current_steps": 15790, "total_steps": 33920, "loss": 0.5584, "lr": 6.4538851279322225e-06, "epoch": 9.310141509433961, "percentage": 46.55, "elapsed_time": "0:30:01", "remaining_time": "0:34:28", "throughput": 5778.85, "total_tokens": 10409360} {"current_steps": 15795, "total_steps": 33920, "loss": 0.389, "lr": 6.451423386272312e-06, "epoch": 9.31308962264151, "percentage": 46.57, "elapsed_time": "0:30:01", "remaining_time": "0:34:27", "throughput": 5779.18, "total_tokens": 10413680} {"current_steps": 15800, "total_steps": 33920, "loss": 0.3796, "lr": 6.448961260341806e-06, "epoch": 9.316037735849056, "percentage": 46.58, "elapsed_time": "0:30:02", "remaining_time": "0:34:27", "throughput": 5779.09, "total_tokens": 10416208} {"current_steps": 15805, "total_steps": 33920, "loss": 0.4199, "lr": 6.446498750792563e-06, "epoch": 9.318985849056604, "percentage": 46.59, "elapsed_time": "0:30:02", "remaining_time": "0:34:26", "throughput": 5779.35, "total_tokens": 10419888} {"current_steps": 15810, "total_steps": 33920, "loss": 0.4398, "lr": 6.444035858276538e-06, "epoch": 9.32193396226415, "percentage": 46.61, "elapsed_time": "0:30:03", "remaining_time": "0:34:25", "throughput": 5779.53, "total_tokens": 10423248} {"current_steps": 15815, "total_steps": 33920, "loss": 0.3836, "lr": 6.441572583445799e-06, "epoch": 9.324882075471699, "percentage": 46.62, "elapsed_time": "0:30:03", "remaining_time": "0:34:25", "throughput": 5779.6, "total_tokens": 10426224} {"current_steps": 15820, "total_steps": 33920, "loss": 0.3539, "lr": 6.439108926952504e-06, "epoch": 9.327830188679245, "percentage": 46.64, "elapsed_time": "0:30:04", "remaining_time": "0:34:24", "throughput": 5779.82, "total_tokens": 10430032} {"current_steps": 15825, "total_steps": 33920, "loss": 0.5264, "lr": 6.43664488944892e-06, "epoch": 9.330778301886792, "percentage": 46.65, "elapsed_time": "0:30:05", "remaining_time": "0:34:24", "throughput": 5780.1, "total_tokens": 10433968} {"current_steps": 15830, "total_steps": 33920, "loss": 0.3509, "lr": 6.434180471587409e-06, "epoch": 9.33372641509434, "percentage": 46.67, "elapsed_time": "0:30:05", "remaining_time": "0:34:23", "throughput": 5780.07, "total_tokens": 10436720} {"current_steps": 15835, "total_steps": 33920, "loss": 0.462, "lr": 6.431715674020438e-06, "epoch": 9.336674528301886, "percentage": 46.68, "elapsed_time": "0:30:06", "remaining_time": "0:34:22", "throughput": 5780.17, "total_tokens": 10439920} {"current_steps": 15840, "total_steps": 33920, "loss": 0.3398, "lr": 6.429250497400571e-06, "epoch": 9.339622641509434, "percentage": 46.7, "elapsed_time": "0:30:06", "remaining_time": "0:34:22", "throughput": 5780.21, "total_tokens": 10442800} {"current_steps": 15845, "total_steps": 33920, "loss": 0.4117, "lr": 6.426784942380475e-06, "epoch": 9.34257075471698, "percentage": 46.71, "elapsed_time": "0:30:07", "remaining_time": "0:34:21", "throughput": 5780.53, "total_tokens": 10447216} {"current_steps": 15850, "total_steps": 33920, "loss": 0.3732, "lr": 6.424319009612917e-06, "epoch": 9.345518867924529, "percentage": 46.73, "elapsed_time": "0:30:07", "remaining_time": "0:34:20", "throughput": 5780.5, "total_tokens": 10449904} {"current_steps": 15855, "total_steps": 33920, "loss": 0.463, "lr": 6.421852699750763e-06, "epoch": 9.348466981132075, "percentage": 46.74, "elapsed_time": "0:30:08", "remaining_time": "0:34:20", "throughput": 5780.38, "total_tokens": 10452784} {"current_steps": 15860, "total_steps": 33920, "loss": 0.3649, "lr": 6.4193860134469775e-06, "epoch": 9.351415094339623, "percentage": 46.76, "elapsed_time": "0:30:08", "remaining_time": "0:34:19", "throughput": 5780.51, "total_tokens": 10455888} {"current_steps": 15865, "total_steps": 33920, "loss": 0.3342, "lr": 6.416918951354629e-06, "epoch": 9.35436320754717, "percentage": 46.77, "elapsed_time": "0:30:09", "remaining_time": "0:34:19", "throughput": 5780.62, "total_tokens": 10458992} {"current_steps": 15870, "total_steps": 33920, "loss": 0.3881, "lr": 6.4144515141268816e-06, "epoch": 9.357311320754716, "percentage": 46.79, "elapsed_time": "0:30:09", "remaining_time": "0:34:18", "throughput": 5780.58, "total_tokens": 10461712} {"current_steps": 15875, "total_steps": 33920, "loss": 0.3327, "lr": 6.411983702416999e-06, "epoch": 9.360259433962264, "percentage": 46.8, "elapsed_time": "0:30:10", "remaining_time": "0:34:17", "throughput": 5780.6, "total_tokens": 10464496} {"current_steps": 15880, "total_steps": 33920, "loss": 0.3557, "lr": 6.409515516878346e-06, "epoch": 9.36320754716981, "percentage": 46.82, "elapsed_time": "0:30:10", "remaining_time": "0:34:17", "throughput": 5780.59, "total_tokens": 10467152} {"current_steps": 15885, "total_steps": 33920, "loss": 0.3156, "lr": 6.407046958164387e-06, "epoch": 9.366155660377359, "percentage": 46.83, "elapsed_time": "0:30:11", "remaining_time": "0:34:16", "throughput": 5780.5, "total_tokens": 10470032} {"current_steps": 15890, "total_steps": 33920, "loss": 0.4149, "lr": 6.404578026928679e-06, "epoch": 9.369103773584905, "percentage": 46.85, "elapsed_time": "0:30:11", "remaining_time": "0:34:15", "throughput": 5780.47, "total_tokens": 10472720} {"current_steps": 15895, "total_steps": 33920, "loss": 0.3023, "lr": 6.402108723824887e-06, "epoch": 9.372051886792454, "percentage": 46.86, "elapsed_time": "0:30:12", "remaining_time": "0:34:15", "throughput": 5780.56, "total_tokens": 10475952} {"current_steps": 15900, "total_steps": 33920, "loss": 0.3633, "lr": 6.399639049506767e-06, "epoch": 9.375, "percentage": 46.88, "elapsed_time": "0:30:12", "remaining_time": "0:34:14", "throughput": 5780.69, "total_tokens": 10479376} {"current_steps": 15905, "total_steps": 33920, "loss": 0.43, "lr": 6.397169004628177e-06, "epoch": 9.377948113207546, "percentage": 46.89, "elapsed_time": "0:30:13", "remaining_time": "0:34:13", "throughput": 5780.99, "total_tokens": 10483280} {"current_steps": 15910, "total_steps": 33920, "loss": 0.3532, "lr": 6.39469858984307e-06, "epoch": 9.380896226415095, "percentage": 46.9, "elapsed_time": "0:30:13", "remaining_time": "0:34:13", "throughput": 5780.92, "total_tokens": 10486256} {"current_steps": 15915, "total_steps": 33920, "loss": 0.3761, "lr": 6.3922278058055024e-06, "epoch": 9.383844339622641, "percentage": 46.92, "elapsed_time": "0:30:14", "remaining_time": "0:34:12", "throughput": 5780.91, "total_tokens": 10489072} {"current_steps": 15920, "total_steps": 33920, "loss": 0.3796, "lr": 6.389756653169622e-06, "epoch": 9.38679245283019, "percentage": 46.93, "elapsed_time": "0:30:14", "remaining_time": "0:34:12", "throughput": 5780.75, "total_tokens": 10491408} {"current_steps": 15925, "total_steps": 33920, "loss": 0.3763, "lr": 6.387285132589678e-06, "epoch": 9.389740566037736, "percentage": 46.95, "elapsed_time": "0:30:15", "remaining_time": "0:34:11", "throughput": 5780.91, "total_tokens": 10494576} {"current_steps": 15930, "total_steps": 33920, "loss": 0.4519, "lr": 6.3848132447200166e-06, "epoch": 9.392688679245284, "percentage": 46.96, "elapsed_time": "0:30:15", "remaining_time": "0:34:10", "throughput": 5780.91, "total_tokens": 10497392} {"current_steps": 15935, "total_steps": 33920, "loss": 0.3953, "lr": 6.38234099021508e-06, "epoch": 9.39563679245283, "percentage": 46.98, "elapsed_time": "0:30:16", "remaining_time": "0:34:10", "throughput": 5781.07, "total_tokens": 10500720} {"current_steps": 15940, "total_steps": 33920, "loss": 0.5015, "lr": 6.379868369729409e-06, "epoch": 9.398584905660377, "percentage": 46.99, "elapsed_time": "0:30:16", "remaining_time": "0:34:09", "throughput": 5781.16, "total_tokens": 10503856} {"current_steps": 15945, "total_steps": 33920, "loss": 0.4907, "lr": 6.377395383917642e-06, "epoch": 9.401533018867925, "percentage": 47.01, "elapsed_time": "0:30:17", "remaining_time": "0:34:08", "throughput": 5781.4, "total_tokens": 10507728} {"current_steps": 15950, "total_steps": 33920, "loss": 0.4059, "lr": 6.374922033434507e-06, "epoch": 9.404481132075471, "percentage": 47.02, "elapsed_time": "0:30:17", "remaining_time": "0:34:08", "throughput": 5781.41, "total_tokens": 10510480} {"current_steps": 15955, "total_steps": 33920, "loss": 0.4514, "lr": 6.372448318934842e-06, "epoch": 9.40742924528302, "percentage": 47.04, "elapsed_time": "0:30:18", "remaining_time": "0:34:07", "throughput": 5781.61, "total_tokens": 10514128} {"current_steps": 15960, "total_steps": 33920, "loss": 0.4656, "lr": 6.369974241073569e-06, "epoch": 9.410377358490566, "percentage": 47.05, "elapsed_time": "0:30:19", "remaining_time": "0:34:07", "throughput": 5781.88, "total_tokens": 10518000} {"current_steps": 15965, "total_steps": 33920, "loss": 0.3952, "lr": 6.367499800505709e-06, "epoch": 9.413325471698114, "percentage": 47.07, "elapsed_time": "0:30:20", "remaining_time": "0:34:06", "throughput": 5782.19, "total_tokens": 10523728} {"current_steps": 15970, "total_steps": 33920, "loss": 0.447, "lr": 6.365024997886384e-06, "epoch": 9.41627358490566, "percentage": 47.08, "elapsed_time": "0:30:20", "remaining_time": "0:34:06", "throughput": 5782.4, "total_tokens": 10527088} {"current_steps": 15975, "total_steps": 33920, "loss": 0.3378, "lr": 6.362549833870808e-06, "epoch": 9.419221698113208, "percentage": 47.1, "elapsed_time": "0:30:21", "remaining_time": "0:34:05", "throughput": 5782.58, "total_tokens": 10530768} {"current_steps": 15980, "total_steps": 33920, "loss": 0.3106, "lr": 6.360074309114293e-06, "epoch": 9.422169811320755, "percentage": 47.11, "elapsed_time": "0:30:21", "remaining_time": "0:34:05", "throughput": 5782.63, "total_tokens": 10533840} {"current_steps": 15985, "total_steps": 33920, "loss": 0.3863, "lr": 6.357598424272241e-06, "epoch": 9.425117924528301, "percentage": 47.13, "elapsed_time": "0:30:22", "remaining_time": "0:34:04", "throughput": 5782.75, "total_tokens": 10537264} {"current_steps": 15990, "total_steps": 33920, "loss": 0.4871, "lr": 6.355122180000156e-06, "epoch": 9.42806603773585, "percentage": 47.14, "elapsed_time": "0:30:22", "remaining_time": "0:34:03", "throughput": 5782.83, "total_tokens": 10540624} {"current_steps": 15995, "total_steps": 33920, "loss": 0.3189, "lr": 6.352645576953635e-06, "epoch": 9.431014150943396, "percentage": 47.16, "elapsed_time": "0:30:23", "remaining_time": "0:34:03", "throughput": 5782.75, "total_tokens": 10543280} {"current_steps": 16000, "total_steps": 33920, "loss": 0.412, "lr": 6.350168615788366e-06, "epoch": 9.433962264150944, "percentage": 47.17, "elapsed_time": "0:30:23", "remaining_time": "0:34:02", "throughput": 5782.87, "total_tokens": 10546928} {"current_steps": 16005, "total_steps": 33920, "loss": 0.3631, "lr": 6.347691297160137e-06, "epoch": 9.43691037735849, "percentage": 47.18, "elapsed_time": "0:30:24", "remaining_time": "0:34:01", "throughput": 5782.77, "total_tokens": 10549424} {"current_steps": 16010, "total_steps": 33920, "loss": 0.4464, "lr": 6.34521362172483e-06, "epoch": 9.439858490566039, "percentage": 47.2, "elapsed_time": "0:30:24", "remaining_time": "0:34:01", "throughput": 5782.89, "total_tokens": 10553040} {"current_steps": 16015, "total_steps": 33920, "loss": 0.3019, "lr": 6.342735590138417e-06, "epoch": 9.442806603773585, "percentage": 47.21, "elapsed_time": "0:30:25", "remaining_time": "0:34:00", "throughput": 5782.95, "total_tokens": 10556240} {"current_steps": 16020, "total_steps": 33920, "loss": 0.5718, "lr": 6.340257203056972e-06, "epoch": 9.445754716981131, "percentage": 47.23, "elapsed_time": "0:30:25", "remaining_time": "0:34:00", "throughput": 5783.1, "total_tokens": 10559440} {"current_steps": 16025, "total_steps": 33920, "loss": 0.3251, "lr": 6.3377784611366554e-06, "epoch": 9.44870283018868, "percentage": 47.24, "elapsed_time": "0:30:26", "remaining_time": "0:33:59", "throughput": 5783.41, "total_tokens": 10563632} {"current_steps": 16030, "total_steps": 33920, "loss": 0.441, "lr": 6.335299365033726e-06, "epoch": 9.451650943396226, "percentage": 47.26, "elapsed_time": "0:30:27", "remaining_time": "0:33:59", "throughput": 5783.26, "total_tokens": 10566256} {"current_steps": 16035, "total_steps": 33920, "loss": 0.4296, "lr": 6.3328199154045346e-06, "epoch": 9.454599056603774, "percentage": 47.27, "elapsed_time": "0:30:27", "remaining_time": "0:33:58", "throughput": 5783.34, "total_tokens": 10569232} {"current_steps": 16040, "total_steps": 33920, "loss": 0.3256, "lr": 6.3303401129055265e-06, "epoch": 9.45754716981132, "percentage": 47.29, "elapsed_time": "0:30:28", "remaining_time": "0:33:57", "throughput": 5783.38, "total_tokens": 10572368} {"current_steps": 16045, "total_steps": 33920, "loss": 0.39, "lr": 6.32785995819324e-06, "epoch": 9.460495283018869, "percentage": 47.3, "elapsed_time": "0:30:28", "remaining_time": "0:33:57", "throughput": 5783.58, "total_tokens": 10575888} {"current_steps": 16050, "total_steps": 33920, "loss": 0.3999, "lr": 6.3253794519243075e-06, "epoch": 9.463443396226415, "percentage": 47.32, "elapsed_time": "0:30:29", "remaining_time": "0:33:56", "throughput": 5783.99, "total_tokens": 10580592} {"current_steps": 16055, "total_steps": 33920, "loss": 0.3657, "lr": 6.322898594755452e-06, "epoch": 9.466391509433961, "percentage": 47.33, "elapsed_time": "0:30:29", "remaining_time": "0:33:56", "throughput": 5784.08, "total_tokens": 10583696} {"current_steps": 16060, "total_steps": 33920, "loss": 0.5301, "lr": 6.320417387343492e-06, "epoch": 9.46933962264151, "percentage": 47.35, "elapsed_time": "0:30:30", "remaining_time": "0:33:55", "throughput": 5784.29, "total_tokens": 10587216} {"current_steps": 16065, "total_steps": 33920, "loss": 0.3546, "lr": 6.3179358303453386e-06, "epoch": 9.472287735849056, "percentage": 47.36, "elapsed_time": "0:30:30", "remaining_time": "0:33:54", "throughput": 5784.36, "total_tokens": 10590320} {"current_steps": 16070, "total_steps": 33920, "loss": 0.5066, "lr": 6.315453924417995e-06, "epoch": 9.475235849056604, "percentage": 47.38, "elapsed_time": "0:30:31", "remaining_time": "0:33:54", "throughput": 5784.37, "total_tokens": 10593072} {"current_steps": 16075, "total_steps": 33920, "loss": 0.4722, "lr": 6.312971670218554e-06, "epoch": 9.47818396226415, "percentage": 47.39, "elapsed_time": "0:30:31", "remaining_time": "0:33:53", "throughput": 5784.51, "total_tokens": 10596208} {"current_steps": 16080, "total_steps": 33920, "loss": 0.3566, "lr": 6.3104890684042055e-06, "epoch": 9.481132075471699, "percentage": 47.41, "elapsed_time": "0:30:32", "remaining_time": "0:33:53", "throughput": 5784.96, "total_tokens": 10600880} {"current_steps": 16085, "total_steps": 33920, "loss": 0.3187, "lr": 6.308006119632228e-06, "epoch": 9.484080188679245, "percentage": 47.42, "elapsed_time": "0:30:33", "remaining_time": "0:33:52", "throughput": 5785.24, "total_tokens": 10604528} {"current_steps": 16090, "total_steps": 33920, "loss": 0.4103, "lr": 6.305522824559993e-06, "epoch": 9.487028301886792, "percentage": 47.44, "elapsed_time": "0:30:33", "remaining_time": "0:33:51", "throughput": 5785.43, "total_tokens": 10607856} {"current_steps": 16095, "total_steps": 33920, "loss": 0.3644, "lr": 6.303039183844965e-06, "epoch": 9.48997641509434, "percentage": 47.45, "elapsed_time": "0:30:34", "remaining_time": "0:33:51", "throughput": 5785.61, "total_tokens": 10611184} {"current_steps": 16100, "total_steps": 33920, "loss": 0.3904, "lr": 6.300555198144697e-06, "epoch": 9.492924528301886, "percentage": 47.46, "elapsed_time": "0:30:34", "remaining_time": "0:33:50", "throughput": 5785.69, "total_tokens": 10614096} {"current_steps": 16105, "total_steps": 33920, "loss": 0.3193, "lr": 6.2980708681168335e-06, "epoch": 9.495872641509434, "percentage": 47.48, "elapsed_time": "0:30:35", "remaining_time": "0:33:49", "throughput": 5785.84, "total_tokens": 10617392} {"current_steps": 16110, "total_steps": 33920, "loss": 0.421, "lr": 6.2955861944191145e-06, "epoch": 9.49882075471698, "percentage": 47.49, "elapsed_time": "0:30:35", "remaining_time": "0:33:49", "throughput": 5785.88, "total_tokens": 10620304} {"current_steps": 16115, "total_steps": 33920, "loss": 0.4589, "lr": 6.293101177709367e-06, "epoch": 9.501768867924529, "percentage": 47.51, "elapsed_time": "0:30:36", "remaining_time": "0:33:48", "throughput": 5786.2, "total_tokens": 10624432} {"current_steps": 16120, "total_steps": 33920, "loss": 0.5776, "lr": 6.290615818645509e-06, "epoch": 9.504716981132075, "percentage": 47.52, "elapsed_time": "0:30:36", "remaining_time": "0:33:48", "throughput": 5786.31, "total_tokens": 10627440} {"current_steps": 16125, "total_steps": 33920, "loss": 0.3821, "lr": 6.288130117885552e-06, "epoch": 9.507665094339622, "percentage": 47.54, "elapsed_time": "0:30:37", "remaining_time": "0:33:47", "throughput": 5786.47, "total_tokens": 10631024} {"current_steps": 16130, "total_steps": 33920, "loss": 0.3806, "lr": 6.285644076087594e-06, "epoch": 9.51061320754717, "percentage": 47.55, "elapsed_time": "0:30:37", "remaining_time": "0:33:46", "throughput": 5786.72, "total_tokens": 10634896} {"current_steps": 16135, "total_steps": 33920, "loss": 0.351, "lr": 6.283157693909826e-06, "epoch": 9.513561320754716, "percentage": 47.57, "elapsed_time": "0:30:38", "remaining_time": "0:33:46", "throughput": 5786.48, "total_tokens": 10637232} {"current_steps": 16140, "total_steps": 33920, "loss": 0.4315, "lr": 6.280670972010528e-06, "epoch": 9.516509433962264, "percentage": 47.58, "elapsed_time": "0:30:38", "remaining_time": "0:33:45", "throughput": 5786.48, "total_tokens": 10640144} {"current_steps": 16145, "total_steps": 33920, "loss": 0.3745, "lr": 6.278183911048072e-06, "epoch": 9.51945754716981, "percentage": 47.6, "elapsed_time": "0:30:39", "remaining_time": "0:33:45", "throughput": 5786.81, "total_tokens": 10644464} {"current_steps": 16150, "total_steps": 33920, "loss": 0.5696, "lr": 6.275696511680915e-06, "epoch": 9.522405660377359, "percentage": 47.61, "elapsed_time": "0:30:39", "remaining_time": "0:33:44", "throughput": 5786.84, "total_tokens": 10647472} {"current_steps": 16155, "total_steps": 33920, "loss": 0.3241, "lr": 6.27320877456761e-06, "epoch": 9.525353773584905, "percentage": 47.63, "elapsed_time": "0:30:40", "remaining_time": "0:33:43", "throughput": 5787.11, "total_tokens": 10651184} {"current_steps": 16160, "total_steps": 33920, "loss": 0.3144, "lr": 6.270720700366793e-06, "epoch": 9.528301886792454, "percentage": 47.64, "elapsed_time": "0:30:41", "remaining_time": "0:33:43", "throughput": 5787.37, "total_tokens": 10654864} {"current_steps": 16165, "total_steps": 33920, "loss": 0.39, "lr": 6.2682322897371974e-06, "epoch": 9.53125, "percentage": 47.66, "elapsed_time": "0:30:41", "remaining_time": "0:33:42", "throughput": 5787.53, "total_tokens": 10658064} {"current_steps": 16170, "total_steps": 33920, "loss": 0.3637, "lr": 6.265743543337634e-06, "epoch": 9.534198113207546, "percentage": 47.67, "elapsed_time": "0:30:42", "remaining_time": "0:33:42", "throughput": 5787.46, "total_tokens": 10660656} {"current_steps": 16175, "total_steps": 33920, "loss": 0.3809, "lr": 6.2632544618270156e-06, "epoch": 9.537146226415095, "percentage": 47.69, "elapsed_time": "0:30:42", "remaining_time": "0:33:41", "throughput": 5787.46, "total_tokens": 10663696} {"current_steps": 16180, "total_steps": 33920, "loss": 0.3462, "lr": 6.260765045864332e-06, "epoch": 9.540094339622641, "percentage": 47.7, "elapsed_time": "0:30:43", "remaining_time": "0:33:40", "throughput": 5787.62, "total_tokens": 10666992} {"current_steps": 16185, "total_steps": 33920, "loss": 0.3293, "lr": 6.258275296108669e-06, "epoch": 9.54304245283019, "percentage": 47.72, "elapsed_time": "0:30:43", "remaining_time": "0:33:40", "throughput": 5787.74, "total_tokens": 10670160} {"current_steps": 16190, "total_steps": 33920, "loss": 0.468, "lr": 6.2557852132191985e-06, "epoch": 9.545990566037736, "percentage": 47.73, "elapsed_time": "0:30:44", "remaining_time": "0:33:39", "throughput": 5788.03, "total_tokens": 10673776} {"current_steps": 16195, "total_steps": 33920, "loss": 0.392, "lr": 6.253294797855182e-06, "epoch": 9.548938679245284, "percentage": 47.74, "elapsed_time": "0:30:44", "remaining_time": "0:33:38", "throughput": 5788.1, "total_tokens": 10676848} {"current_steps": 16200, "total_steps": 33920, "loss": 0.339, "lr": 6.250804050675964e-06, "epoch": 9.55188679245283, "percentage": 47.76, "elapsed_time": "0:30:45", "remaining_time": "0:33:38", "throughput": 5788.17, "total_tokens": 10680048} {"current_steps": 16205, "total_steps": 33920, "loss": 0.3713, "lr": 6.248312972340984e-06, "epoch": 9.554834905660378, "percentage": 47.77, "elapsed_time": "0:30:45", "remaining_time": "0:33:37", "throughput": 5788.2, "total_tokens": 10683056} {"current_steps": 16210, "total_steps": 33920, "loss": 0.4619, "lr": 6.2458215635097656e-06, "epoch": 9.557783018867925, "percentage": 47.79, "elapsed_time": "0:30:46", "remaining_time": "0:33:37", "throughput": 5788.27, "total_tokens": 10686096} {"current_steps": 16215, "total_steps": 33920, "loss": 0.3797, "lr": 6.2433298248419175e-06, "epoch": 9.560731132075471, "percentage": 47.8, "elapsed_time": "0:30:46", "remaining_time": "0:33:36", "throughput": 5788.19, "total_tokens": 10689104} {"current_steps": 16220, "total_steps": 33920, "loss": 0.4094, "lr": 6.2408377569971405e-06, "epoch": 9.56367924528302, "percentage": 47.82, "elapsed_time": "0:30:47", "remaining_time": "0:33:35", "throughput": 5788.03, "total_tokens": 10691952} {"current_steps": 16225, "total_steps": 33920, "loss": 0.4849, "lr": 6.238345360635221e-06, "epoch": 9.566627358490566, "percentage": 47.83, "elapsed_time": "0:30:47", "remaining_time": "0:33:35", "throughput": 5787.95, "total_tokens": 10695568} {"current_steps": 16230, "total_steps": 33920, "loss": 0.4056, "lr": 6.2358526364160274e-06, "epoch": 9.569575471698114, "percentage": 47.85, "elapsed_time": "0:30:48", "remaining_time": "0:33:34", "throughput": 5787.92, "total_tokens": 10698704} {"current_steps": 16235, "total_steps": 33920, "loss": 0.4211, "lr": 6.2333595849995245e-06, "epoch": 9.57252358490566, "percentage": 47.86, "elapsed_time": "0:30:49", "remaining_time": "0:33:34", "throughput": 5787.87, "total_tokens": 10701840} {"current_steps": 16240, "total_steps": 33920, "loss": 0.3481, "lr": 6.230866207045756e-06, "epoch": 9.575471698113208, "percentage": 47.88, "elapsed_time": "0:30:49", "remaining_time": "0:33:33", "throughput": 5788.22, "total_tokens": 10706256} {"current_steps": 16245, "total_steps": 33920, "loss": 0.4383, "lr": 6.228372503214853e-06, "epoch": 9.578419811320755, "percentage": 47.89, "elapsed_time": "0:30:50", "remaining_time": "0:33:33", "throughput": 5788.13, "total_tokens": 10708912} {"current_steps": 16250, "total_steps": 33920, "loss": 0.2566, "lr": 6.225878474167035e-06, "epoch": 9.581367924528301, "percentage": 47.91, "elapsed_time": "0:30:50", "remaining_time": "0:33:32", "throughput": 5787.77, "total_tokens": 10711504} {"current_steps": 16255, "total_steps": 33920, "loss": 0.4221, "lr": 6.22338412056261e-06, "epoch": 9.58431603773585, "percentage": 47.92, "elapsed_time": "0:30:51", "remaining_time": "0:33:31", "throughput": 5787.67, "total_tokens": 10714192} {"current_steps": 16260, "total_steps": 33920, "loss": 0.4104, "lr": 6.220889443061966e-06, "epoch": 9.587264150943396, "percentage": 47.94, "elapsed_time": "0:30:51", "remaining_time": "0:33:31", "throughput": 5787.83, "total_tokens": 10717520} {"current_steps": 16265, "total_steps": 33920, "loss": 0.3601, "lr": 6.2183944423255796e-06, "epoch": 9.590212264150944, "percentage": 47.95, "elapsed_time": "0:30:52", "remaining_time": "0:33:30", "throughput": 5787.93, "total_tokens": 10720880} {"current_steps": 16270, "total_steps": 33920, "loss": 0.421, "lr": 6.215899119014015e-06, "epoch": 9.59316037735849, "percentage": 47.97, "elapsed_time": "0:30:52", "remaining_time": "0:33:29", "throughput": 5788.03, "total_tokens": 10723920} {"current_steps": 16275, "total_steps": 33920, "loss": 0.5537, "lr": 6.2134034737879175e-06, "epoch": 9.596108490566039, "percentage": 47.98, "elapsed_time": "0:30:53", "remaining_time": "0:33:29", "throughput": 5787.94, "total_tokens": 10726672} {"current_steps": 16280, "total_steps": 33920, "loss": 0.4608, "lr": 6.2109075073080205e-06, "epoch": 9.599056603773585, "percentage": 48.0, "elapsed_time": "0:30:53", "remaining_time": "0:33:28", "throughput": 5788.04, "total_tokens": 10730128} {"current_steps": 16285, "total_steps": 33920, "loss": 0.3784, "lr": 6.2084112202351425e-06, "epoch": 9.602004716981131, "percentage": 48.01, "elapsed_time": "0:30:54", "remaining_time": "0:33:28", "throughput": 5787.83, "total_tokens": 10732528} {"current_steps": 16290, "total_steps": 33920, "loss": 0.322, "lr": 6.205914613230186e-06, "epoch": 9.60495283018868, "percentage": 48.02, "elapsed_time": "0:30:54", "remaining_time": "0:33:27", "throughput": 5787.84, "total_tokens": 10735568} {"current_steps": 16295, "total_steps": 33920, "loss": 0.2567, "lr": 6.203417686954138e-06, "epoch": 9.607900943396226, "percentage": 48.04, "elapsed_time": "0:30:55", "remaining_time": "0:33:26", "throughput": 5787.82, "total_tokens": 10738640} {"current_steps": 16300, "total_steps": 33920, "loss": 0.3694, "lr": 6.2009204420680706e-06, "epoch": 9.610849056603774, "percentage": 48.05, "elapsed_time": "0:30:55", "remaining_time": "0:33:26", "throughput": 5787.97, "total_tokens": 10741968} {"current_steps": 16305, "total_steps": 33920, "loss": 0.4177, "lr": 6.198422879233141e-06, "epoch": 9.61379716981132, "percentage": 48.07, "elapsed_time": "0:30:56", "remaining_time": "0:33:25", "throughput": 5787.85, "total_tokens": 10744784} {"current_steps": 16310, "total_steps": 33920, "loss": 0.3804, "lr": 6.1959249991105895e-06, "epoch": 9.616745283018869, "percentage": 48.08, "elapsed_time": "0:30:57", "remaining_time": "0:33:25", "throughput": 5787.93, "total_tokens": 10748304} {"current_steps": 16315, "total_steps": 33920, "loss": 0.518, "lr": 6.19342680236174e-06, "epoch": 9.619693396226415, "percentage": 48.1, "elapsed_time": "0:30:57", "remaining_time": "0:33:24", "throughput": 5788.2, "total_tokens": 10752400} {"current_steps": 16320, "total_steps": 33920, "loss": 0.4098, "lr": 6.190928289648003e-06, "epoch": 9.622641509433961, "percentage": 48.11, "elapsed_time": "0:30:58", "remaining_time": "0:33:24", "throughput": 5788.5, "total_tokens": 10756848} {"current_steps": 16325, "total_steps": 33920, "loss": 0.3584, "lr": 6.188429461630866e-06, "epoch": 9.62558962264151, "percentage": 48.13, "elapsed_time": "0:30:58", "remaining_time": "0:33:23", "throughput": 5788.87, "total_tokens": 10761200} {"current_steps": 16330, "total_steps": 33920, "loss": 0.3569, "lr": 6.185930318971909e-06, "epoch": 9.628537735849056, "percentage": 48.14, "elapsed_time": "0:30:59", "remaining_time": "0:33:22", "throughput": 5788.73, "total_tokens": 10763632} {"current_steps": 16335, "total_steps": 33920, "loss": 0.3204, "lr": 6.1834308623327885e-06, "epoch": 9.631485849056604, "percentage": 48.16, "elapsed_time": "0:31:00", "remaining_time": "0:33:22", "throughput": 5789.11, "total_tokens": 10768432} {"current_steps": 16340, "total_steps": 33920, "loss": 0.3629, "lr": 6.180931092375247e-06, "epoch": 9.63443396226415, "percentage": 48.17, "elapsed_time": "0:31:00", "remaining_time": "0:33:21", "throughput": 5789.19, "total_tokens": 10771696} {"current_steps": 16345, "total_steps": 33920, "loss": 0.4084, "lr": 6.1784310097611075e-06, "epoch": 9.637382075471699, "percentage": 48.19, "elapsed_time": "0:31:01", "remaining_time": "0:33:21", "throughput": 5789.08, "total_tokens": 10774512} {"current_steps": 16350, "total_steps": 33920, "loss": 0.4797, "lr": 6.1759306151522815e-06, "epoch": 9.640330188679245, "percentage": 48.2, "elapsed_time": "0:31:01", "remaining_time": "0:33:20", "throughput": 5788.97, "total_tokens": 10777200} {"current_steps": 16355, "total_steps": 33920, "loss": 0.3854, "lr": 6.173429909210755e-06, "epoch": 9.643278301886792, "percentage": 48.22, "elapsed_time": "0:31:02", "remaining_time": "0:33:20", "throughput": 5788.97, "total_tokens": 10780464} {"current_steps": 16360, "total_steps": 33920, "loss": 0.3413, "lr": 6.170928892598606e-06, "epoch": 9.64622641509434, "percentage": 48.23, "elapsed_time": "0:31:02", "remaining_time": "0:33:19", "throughput": 5789.08, "total_tokens": 10783920} {"current_steps": 16365, "total_steps": 33920, "loss": 0.3881, "lr": 6.168427565977984e-06, "epoch": 9.649174528301886, "percentage": 48.25, "elapsed_time": "0:31:03", "remaining_time": "0:33:18", "throughput": 5789.25, "total_tokens": 10787600} {"current_steps": 16370, "total_steps": 33920, "loss": 0.4713, "lr": 6.165925930011129e-06, "epoch": 9.652122641509434, "percentage": 48.26, "elapsed_time": "0:31:03", "remaining_time": "0:33:18", "throughput": 5789.32, "total_tokens": 10790896} {"current_steps": 16375, "total_steps": 33920, "loss": 0.361, "lr": 6.163423985360359e-06, "epoch": 9.65507075471698, "percentage": 48.28, "elapsed_time": "0:31:04", "remaining_time": "0:33:17", "throughput": 5789.38, "total_tokens": 10794256} {"current_steps": 16380, "total_steps": 33920, "loss": 0.375, "lr": 6.160921732688076e-06, "epoch": 9.658018867924529, "percentage": 48.29, "elapsed_time": "0:31:05", "remaining_time": "0:33:17", "throughput": 5789.21, "total_tokens": 10797168} {"current_steps": 16385, "total_steps": 33920, "loss": 0.3736, "lr": 6.158419172656759e-06, "epoch": 9.660966981132075, "percentage": 48.3, "elapsed_time": "0:31:05", "remaining_time": "0:33:16", "throughput": 5789.15, "total_tokens": 10799792} {"current_steps": 16390, "total_steps": 33920, "loss": 0.3225, "lr": 6.155916305928974e-06, "epoch": 9.663915094339622, "percentage": 48.32, "elapsed_time": "0:31:06", "remaining_time": "0:33:15", "throughput": 5789.28, "total_tokens": 10803088} {"current_steps": 16395, "total_steps": 33920, "loss": 0.3878, "lr": 6.153413133167366e-06, "epoch": 9.66686320754717, "percentage": 48.33, "elapsed_time": "0:31:06", "remaining_time": "0:33:15", "throughput": 5789.56, "total_tokens": 10807728} {"current_steps": 16400, "total_steps": 33920, "loss": 0.3631, "lr": 6.1509096550346596e-06, "epoch": 9.669811320754716, "percentage": 48.35, "elapsed_time": "0:31:07", "remaining_time": "0:33:14", "throughput": 5789.61, "total_tokens": 10810960} {"current_steps": 16405, "total_steps": 33920, "loss": 0.3592, "lr": 6.148405872193661e-06, "epoch": 9.672759433962264, "percentage": 48.36, "elapsed_time": "0:31:07", "remaining_time": "0:33:14", "throughput": 5789.53, "total_tokens": 10813584} {"current_steps": 16410, "total_steps": 33920, "loss": 0.4353, "lr": 6.14590178530726e-06, "epoch": 9.67570754716981, "percentage": 48.38, "elapsed_time": "0:31:08", "remaining_time": "0:33:13", "throughput": 5789.61, "total_tokens": 10816944} {"current_steps": 16415, "total_steps": 33920, "loss": 0.3223, "lr": 6.143397395038422e-06, "epoch": 9.678655660377359, "percentage": 48.39, "elapsed_time": "0:31:08", "remaining_time": "0:33:12", "throughput": 5789.65, "total_tokens": 10820080} {"current_steps": 16420, "total_steps": 33920, "loss": 0.4101, "lr": 6.140892702050196e-06, "epoch": 9.681603773584905, "percentage": 48.41, "elapsed_time": "0:31:09", "remaining_time": "0:33:12", "throughput": 5789.63, "total_tokens": 10822832} {"current_steps": 16425, "total_steps": 33920, "loss": 0.3621, "lr": 6.138387707005711e-06, "epoch": 9.684551886792454, "percentage": 48.42, "elapsed_time": "0:31:09", "remaining_time": "0:33:11", "throughput": 5789.5, "total_tokens": 10825520} {"current_steps": 16430, "total_steps": 33920, "loss": 0.402, "lr": 6.135882410568172e-06, "epoch": 9.6875, "percentage": 48.44, "elapsed_time": "0:31:10", "remaining_time": "0:33:11", "throughput": 5789.56, "total_tokens": 10828528} {"current_steps": 16435, "total_steps": 33920, "loss": 0.4365, "lr": 6.133376813400872e-06, "epoch": 9.690448113207546, "percentage": 48.45, "elapsed_time": "0:31:10", "remaining_time": "0:33:10", "throughput": 5789.82, "total_tokens": 10832176} {"current_steps": 16440, "total_steps": 33920, "loss": 0.4009, "lr": 6.130870916167175e-06, "epoch": 9.693396226415095, "percentage": 48.47, "elapsed_time": "0:31:11", "remaining_time": "0:33:09", "throughput": 5789.78, "total_tokens": 10835280} {"current_steps": 16445, "total_steps": 33920, "loss": 0.3993, "lr": 6.128364719530528e-06, "epoch": 9.696344339622641, "percentage": 48.48, "elapsed_time": "0:31:11", "remaining_time": "0:33:09", "throughput": 5789.89, "total_tokens": 10838544} {"current_steps": 16450, "total_steps": 33920, "loss": 0.4381, "lr": 6.125858224154459e-06, "epoch": 9.69929245283019, "percentage": 48.5, "elapsed_time": "0:31:12", "remaining_time": "0:33:08", "throughput": 5789.98, "total_tokens": 10841936} {"current_steps": 16455, "total_steps": 33920, "loss": 0.3866, "lr": 6.123351430702576e-06, "epoch": 9.702240566037736, "percentage": 48.51, "elapsed_time": "0:31:13", "remaining_time": "0:33:08", "throughput": 5790.05, "total_tokens": 10845168} {"current_steps": 16460, "total_steps": 33920, "loss": 0.3487, "lr": 6.1208443398385575e-06, "epoch": 9.705188679245284, "percentage": 48.53, "elapsed_time": "0:31:13", "remaining_time": "0:33:07", "throughput": 5790.06, "total_tokens": 10848240} {"current_steps": 16465, "total_steps": 33920, "loss": 0.59, "lr": 6.118336952226169e-06, "epoch": 9.70813679245283, "percentage": 48.54, "elapsed_time": "0:31:14", "remaining_time": "0:33:06", "throughput": 5789.99, "total_tokens": 10850800} {"current_steps": 16470, "total_steps": 33920, "loss": 0.3362, "lr": 6.115829268529254e-06, "epoch": 9.711084905660378, "percentage": 48.56, "elapsed_time": "0:31:14", "remaining_time": "0:33:06", "throughput": 5790.2, "total_tokens": 10854544} {"current_steps": 16475, "total_steps": 33920, "loss": 0.4121, "lr": 6.1133212894117326e-06, "epoch": 9.714033018867925, "percentage": 48.57, "elapsed_time": "0:31:15", "remaining_time": "0:33:05", "throughput": 5790.43, "total_tokens": 10858608} {"current_steps": 16480, "total_steps": 33920, "loss": 0.3382, "lr": 6.1108130155375986e-06, "epoch": 9.716981132075471, "percentage": 48.58, "elapsed_time": "0:31:15", "remaining_time": "0:33:05", "throughput": 5790.43, "total_tokens": 10861712} {"current_steps": 16485, "total_steps": 33920, "loss": 0.2772, "lr": 6.108304447570933e-06, "epoch": 9.71992924528302, "percentage": 48.6, "elapsed_time": "0:31:16", "remaining_time": "0:33:04", "throughput": 5790.52, "total_tokens": 10864912} {"current_steps": 16490, "total_steps": 33920, "loss": 0.2627, "lr": 6.105795586175888e-06, "epoch": 9.722877358490566, "percentage": 48.61, "elapsed_time": "0:31:16", "remaining_time": "0:33:03", "throughput": 5790.33, "total_tokens": 10867344} {"current_steps": 16495, "total_steps": 33920, "loss": 0.3403, "lr": 6.1032864320166954e-06, "epoch": 9.725825471698114, "percentage": 48.63, "elapsed_time": "0:31:17", "remaining_time": "0:33:03", "throughput": 5790.47, "total_tokens": 10871056} {"current_steps": 16500, "total_steps": 33920, "loss": 0.3365, "lr": 6.100776985757666e-06, "epoch": 9.72877358490566, "percentage": 48.64, "elapsed_time": "0:31:18", "remaining_time": "0:33:02", "throughput": 5790.36, "total_tokens": 10874512} {"current_steps": 16505, "total_steps": 33920, "loss": 0.4998, "lr": 6.098267248063186e-06, "epoch": 9.731721698113208, "percentage": 48.66, "elapsed_time": "0:31:18", "remaining_time": "0:33:02", "throughput": 5790.36, "total_tokens": 10877360} {"current_steps": 16510, "total_steps": 33920, "loss": 0.3456, "lr": 6.0957572195977165e-06, "epoch": 9.734669811320755, "percentage": 48.67, "elapsed_time": "0:31:19", "remaining_time": "0:33:01", "throughput": 5790.35, "total_tokens": 10880272} {"current_steps": 16515, "total_steps": 33920, "loss": 0.3386, "lr": 6.0932469010258025e-06, "epoch": 9.737617924528301, "percentage": 48.69, "elapsed_time": "0:31:19", "remaining_time": "0:33:00", "throughput": 5790.46, "total_tokens": 10883568} {"current_steps": 16520, "total_steps": 33920, "loss": 0.4295, "lr": 6.0907362930120594e-06, "epoch": 9.74056603773585, "percentage": 48.7, "elapsed_time": "0:31:20", "remaining_time": "0:33:00", "throughput": 5790.68, "total_tokens": 10887184} {"current_steps": 16525, "total_steps": 33920, "loss": 0.3841, "lr": 6.088225396221181e-06, "epoch": 9.743514150943396, "percentage": 48.72, "elapsed_time": "0:31:20", "remaining_time": "0:32:59", "throughput": 5790.7, "total_tokens": 10890160} {"current_steps": 16530, "total_steps": 33920, "loss": 0.4524, "lr": 6.0857142113179415e-06, "epoch": 9.746462264150944, "percentage": 48.73, "elapsed_time": "0:31:21", "remaining_time": "0:32:59", "throughput": 5790.98, "total_tokens": 10896944} {"current_steps": 16535, "total_steps": 33920, "loss": 0.417, "lr": 6.083202738967182e-06, "epoch": 9.74941037735849, "percentage": 48.75, "elapsed_time": "0:31:22", "remaining_time": "0:32:58", "throughput": 5790.95, "total_tokens": 10899856} {"current_steps": 16540, "total_steps": 33920, "loss": 0.2901, "lr": 6.0806909798338324e-06, "epoch": 9.752358490566039, "percentage": 48.76, "elapsed_time": "0:31:22", "remaining_time": "0:32:58", "throughput": 5790.91, "total_tokens": 10902704} {"current_steps": 16545, "total_steps": 33920, "loss": 0.4776, "lr": 6.0781789345828854e-06, "epoch": 9.755306603773585, "percentage": 48.78, "elapsed_time": "0:31:23", "remaining_time": "0:32:57", "throughput": 5790.91, "total_tokens": 10905648} {"current_steps": 16550, "total_steps": 33920, "loss": 0.462, "lr": 6.0756666038794195e-06, "epoch": 9.758254716981131, "percentage": 48.79, "elapsed_time": "0:31:23", "remaining_time": "0:32:57", "throughput": 5790.94, "total_tokens": 10908752} {"current_steps": 16555, "total_steps": 33920, "loss": 0.3116, "lr": 6.073153988388586e-06, "epoch": 9.76120283018868, "percentage": 48.81, "elapsed_time": "0:31:24", "remaining_time": "0:32:56", "throughput": 5790.91, "total_tokens": 10911728} {"current_steps": 16560, "total_steps": 33920, "loss": 0.462, "lr": 6.070641088775608e-06, "epoch": 9.764150943396226, "percentage": 48.82, "elapsed_time": "0:31:24", "remaining_time": "0:32:55", "throughput": 5790.92, "total_tokens": 10914992} {"current_steps": 16565, "total_steps": 33920, "loss": 0.3768, "lr": 6.068127905705787e-06, "epoch": 9.767099056603774, "percentage": 48.84, "elapsed_time": "0:31:25", "remaining_time": "0:32:55", "throughput": 5790.74, "total_tokens": 10917424} {"current_steps": 16570, "total_steps": 33920, "loss": 0.3254, "lr": 6.065614439844501e-06, "epoch": 9.77004716981132, "percentage": 48.85, "elapsed_time": "0:31:25", "remaining_time": "0:32:54", "throughput": 5790.9, "total_tokens": 10921104} {"current_steps": 16575, "total_steps": 33920, "loss": 0.4148, "lr": 6.063100691857198e-06, "epoch": 9.772995283018869, "percentage": 48.86, "elapsed_time": "0:31:26", "remaining_time": "0:32:54", "throughput": 5791.01, "total_tokens": 10924816} {"current_steps": 16580, "total_steps": 33920, "loss": 0.3912, "lr": 6.060586662409407e-06, "epoch": 9.775943396226415, "percentage": 48.88, "elapsed_time": "0:31:27", "remaining_time": "0:32:53", "throughput": 5791.25, "total_tokens": 10928784} {"current_steps": 16585, "total_steps": 33920, "loss": 0.3441, "lr": 6.058072352166724e-06, "epoch": 9.778891509433961, "percentage": 48.89, "elapsed_time": "0:31:27", "remaining_time": "0:32:53", "throughput": 5791.38, "total_tokens": 10932560} {"current_steps": 16590, "total_steps": 33920, "loss": 0.5294, "lr": 6.055557761794826e-06, "epoch": 9.78183962264151, "percentage": 48.91, "elapsed_time": "0:31:28", "remaining_time": "0:32:52", "throughput": 5791.33, "total_tokens": 10935344} {"current_steps": 16595, "total_steps": 33920, "loss": 0.4417, "lr": 6.053042891959462e-06, "epoch": 9.784787735849056, "percentage": 48.92, "elapsed_time": "0:31:28", "remaining_time": "0:32:51", "throughput": 5791.61, "total_tokens": 10939408} {"current_steps": 16600, "total_steps": 33920, "loss": 0.4129, "lr": 6.050527743326455e-06, "epoch": 9.787735849056604, "percentage": 48.94, "elapsed_time": "0:31:29", "remaining_time": "0:32:51", "throughput": 5791.49, "total_tokens": 10942032} {"current_steps": 16605, "total_steps": 33920, "loss": 0.4349, "lr": 6.048012316561699e-06, "epoch": 9.79068396226415, "percentage": 48.95, "elapsed_time": "0:31:29", "remaining_time": "0:32:50", "throughput": 5791.41, "total_tokens": 10944944} {"current_steps": 16610, "total_steps": 33920, "loss": 0.4045, "lr": 6.045496612331166e-06, "epoch": 9.793632075471699, "percentage": 48.97, "elapsed_time": "0:31:30", "remaining_time": "0:32:50", "throughput": 5791.48, "total_tokens": 10948272} {"current_steps": 16615, "total_steps": 33920, "loss": 0.4418, "lr": 6.0429806313009e-06, "epoch": 9.796580188679245, "percentage": 48.98, "elapsed_time": "0:31:30", "remaining_time": "0:32:49", "throughput": 5791.43, "total_tokens": 10950992} {"current_steps": 16620, "total_steps": 33920, "loss": 0.2871, "lr": 6.040464374137015e-06, "epoch": 9.799528301886792, "percentage": 49.0, "elapsed_time": "0:31:31", "remaining_time": "0:32:48", "throughput": 5791.59, "total_tokens": 10954640} {"current_steps": 16625, "total_steps": 33920, "loss": 0.2637, "lr": 6.0379478415057045e-06, "epoch": 9.80247641509434, "percentage": 49.01, "elapsed_time": "0:31:32", "remaining_time": "0:32:48", "throughput": 5791.73, "total_tokens": 10958032} {"current_steps": 16630, "total_steps": 33920, "loss": 0.3441, "lr": 6.035431034073228e-06, "epoch": 9.805424528301886, "percentage": 49.03, "elapsed_time": "0:31:32", "remaining_time": "0:32:47", "throughput": 5792.02, "total_tokens": 10962224} {"current_steps": 16635, "total_steps": 33920, "loss": 0.3613, "lr": 6.0329139525059235e-06, "epoch": 9.808372641509434, "percentage": 49.04, "elapsed_time": "0:31:33", "remaining_time": "0:32:47", "throughput": 5791.83, "total_tokens": 10964816} {"current_steps": 16640, "total_steps": 33920, "loss": 0.361, "lr": 6.030396597470198e-06, "epoch": 9.81132075471698, "percentage": 49.06, "elapsed_time": "0:31:33", "remaining_time": "0:32:46", "throughput": 5792.05, "total_tokens": 10968624} {"current_steps": 16645, "total_steps": 33920, "loss": 0.3633, "lr": 6.027878969632534e-06, "epoch": 9.814268867924529, "percentage": 49.07, "elapsed_time": "0:31:34", "remaining_time": "0:32:45", "throughput": 5792.17, "total_tokens": 10971792} {"current_steps": 16650, "total_steps": 33920, "loss": 0.2944, "lr": 6.025361069659482e-06, "epoch": 9.817216981132075, "percentage": 49.09, "elapsed_time": "0:31:34", "remaining_time": "0:32:45", "throughput": 5792.13, "total_tokens": 10974768} {"current_steps": 16655, "total_steps": 33920, "loss": 0.4413, "lr": 6.022842898217668e-06, "epoch": 9.820165094339622, "percentage": 49.1, "elapsed_time": "0:31:35", "remaining_time": "0:32:44", "throughput": 5792.03, "total_tokens": 10977456} {"current_steps": 16660, "total_steps": 33920, "loss": 0.3004, "lr": 6.020324455973788e-06, "epoch": 9.82311320754717, "percentage": 49.12, "elapsed_time": "0:31:35", "remaining_time": "0:32:44", "throughput": 5792.18, "total_tokens": 10981232} {"current_steps": 16665, "total_steps": 33920, "loss": 0.4032, "lr": 6.017805743594612e-06, "epoch": 9.826061320754716, "percentage": 49.13, "elapsed_time": "0:31:36", "remaining_time": "0:32:43", "throughput": 5791.9, "total_tokens": 10983376} {"current_steps": 16670, "total_steps": 33920, "loss": 0.3178, "lr": 6.0152867617469776e-06, "epoch": 9.829009433962264, "percentage": 49.15, "elapsed_time": "0:31:37", "remaining_time": "0:32:43", "throughput": 5792.17, "total_tokens": 10987824} {"current_steps": 16675, "total_steps": 33920, "loss": 0.4393, "lr": 6.012767511097799e-06, "epoch": 9.83195754716981, "percentage": 49.16, "elapsed_time": "0:31:37", "remaining_time": "0:32:42", "throughput": 5792.28, "total_tokens": 10991408} {"current_steps": 16680, "total_steps": 33920, "loss": 0.5009, "lr": 6.010247992314055e-06, "epoch": 9.834905660377359, "percentage": 49.17, "elapsed_time": "0:31:38", "remaining_time": "0:32:41", "throughput": 5792.25, "total_tokens": 10994640} {"current_steps": 16685, "total_steps": 33920, "loss": 0.4586, "lr": 6.007728206062802e-06, "epoch": 9.837853773584905, "percentage": 49.19, "elapsed_time": "0:31:38", "remaining_time": "0:32:41", "throughput": 5792.46, "total_tokens": 10998256} {"current_steps": 16690, "total_steps": 33920, "loss": 0.4408, "lr": 6.005208153011163e-06, "epoch": 9.840801886792454, "percentage": 49.2, "elapsed_time": "0:31:39", "remaining_time": "0:32:40", "throughput": 5792.54, "total_tokens": 11001456} {"current_steps": 16695, "total_steps": 33920, "loss": 0.3665, "lr": 6.0026878338263335e-06, "epoch": 9.84375, "percentage": 49.22, "elapsed_time": "0:31:39", "remaining_time": "0:32:40", "throughput": 5792.6, "total_tokens": 11004880} {"current_steps": 16700, "total_steps": 33920, "loss": 0.4263, "lr": 6.000167249175579e-06, "epoch": 9.846698113207546, "percentage": 49.23, "elapsed_time": "0:31:40", "remaining_time": "0:32:39", "throughput": 5792.73, "total_tokens": 11008048} {"current_steps": 16705, "total_steps": 33920, "loss": 0.4164, "lr": 5.997646399726236e-06, "epoch": 9.849646226415095, "percentage": 49.25, "elapsed_time": "0:31:40", "remaining_time": "0:32:38", "throughput": 5792.89, "total_tokens": 11011504} {"current_steps": 16710, "total_steps": 33920, "loss": 0.2716, "lr": 5.995125286145707e-06, "epoch": 9.852594339622641, "percentage": 49.26, "elapsed_time": "0:31:41", "remaining_time": "0:32:38", "throughput": 5792.75, "total_tokens": 11014128} {"current_steps": 16715, "total_steps": 33920, "loss": 0.2733, "lr": 5.99260390910147e-06, "epoch": 9.85554245283019, "percentage": 49.28, "elapsed_time": "0:31:42", "remaining_time": "0:32:37", "throughput": 5793.08, "total_tokens": 11019376} {"current_steps": 16720, "total_steps": 33920, "loss": 0.3036, "lr": 5.990082269261071e-06, "epoch": 9.858490566037736, "percentage": 49.29, "elapsed_time": "0:31:42", "remaining_time": "0:32:37", "throughput": 5793.08, "total_tokens": 11022128} {"current_steps": 16725, "total_steps": 33920, "loss": 0.3551, "lr": 5.987560367292123e-06, "epoch": 9.861438679245284, "percentage": 49.31, "elapsed_time": "0:31:43", "remaining_time": "0:32:36", "throughput": 5792.89, "total_tokens": 11024656} {"current_steps": 16730, "total_steps": 33920, "loss": 0.531, "lr": 5.985038203862313e-06, "epoch": 9.86438679245283, "percentage": 49.32, "elapsed_time": "0:31:43", "remaining_time": "0:32:35", "throughput": 5792.82, "total_tokens": 11027280} {"current_steps": 16735, "total_steps": 33920, "loss": 0.3371, "lr": 5.982515779639393e-06, "epoch": 9.867334905660378, "percentage": 49.34, "elapsed_time": "0:31:44", "remaining_time": "0:32:35", "throughput": 5792.81, "total_tokens": 11030672} {"current_steps": 16740, "total_steps": 33920, "loss": 0.3193, "lr": 5.979993095291186e-06, "epoch": 9.870283018867925, "percentage": 49.35, "elapsed_time": "0:31:44", "remaining_time": "0:32:34", "throughput": 5792.98, "total_tokens": 11034544} {"current_steps": 16745, "total_steps": 33920, "loss": 0.4287, "lr": 5.977470151485582e-06, "epoch": 9.873231132075471, "percentage": 49.37, "elapsed_time": "0:31:45", "remaining_time": "0:32:34", "throughput": 5792.78, "total_tokens": 11037072} {"current_steps": 16750, "total_steps": 33920, "loss": 0.3153, "lr": 5.974946948890544e-06, "epoch": 9.87617924528302, "percentage": 49.38, "elapsed_time": "0:31:45", "remaining_time": "0:32:33", "throughput": 5792.71, "total_tokens": 11040112} {"current_steps": 16755, "total_steps": 33920, "loss": 0.3546, "lr": 5.9724234881740994e-06, "epoch": 9.879127358490566, "percentage": 49.4, "elapsed_time": "0:31:46", "remaining_time": "0:32:33", "throughput": 5793.07, "total_tokens": 11045232} {"current_steps": 16760, "total_steps": 33920, "loss": 0.3767, "lr": 5.9698997700043445e-06, "epoch": 9.882075471698114, "percentage": 49.41, "elapsed_time": "0:31:47", "remaining_time": "0:32:32", "throughput": 5792.79, "total_tokens": 11047440} {"current_steps": 16765, "total_steps": 33920, "loss": 0.3728, "lr": 5.9673757950494475e-06, "epoch": 9.88502358490566, "percentage": 49.43, "elapsed_time": "0:31:47", "remaining_time": "0:32:32", "throughput": 5793.0, "total_tokens": 11051280} {"current_steps": 16770, "total_steps": 33920, "loss": 0.3493, "lr": 5.964851563977639e-06, "epoch": 9.887971698113208, "percentage": 49.44, "elapsed_time": "0:31:48", "remaining_time": "0:32:31", "throughput": 5793.14, "total_tokens": 11054608} {"current_steps": 16775, "total_steps": 33920, "loss": 0.3556, "lr": 5.962327077457219e-06, "epoch": 9.890919811320755, "percentage": 49.45, "elapsed_time": "0:31:48", "remaining_time": "0:32:30", "throughput": 5793.24, "total_tokens": 11057936} {"current_steps": 16780, "total_steps": 33920, "loss": 0.2843, "lr": 5.959802336156558e-06, "epoch": 9.893867924528301, "percentage": 49.47, "elapsed_time": "0:31:49", "remaining_time": "0:32:30", "throughput": 5793.39, "total_tokens": 11061488} {"current_steps": 16785, "total_steps": 33920, "loss": 0.4644, "lr": 5.957277340744094e-06, "epoch": 9.89681603773585, "percentage": 49.48, "elapsed_time": "0:31:49", "remaining_time": "0:32:29", "throughput": 5793.47, "total_tokens": 11064560} {"current_steps": 16790, "total_steps": 33920, "loss": 0.3493, "lr": 5.954752091888326e-06, "epoch": 9.899764150943396, "percentage": 49.5, "elapsed_time": "0:31:50", "remaining_time": "0:32:29", "throughput": 5793.42, "total_tokens": 11067760} {"current_steps": 16795, "total_steps": 33920, "loss": 0.3598, "lr": 5.952226590257829e-06, "epoch": 9.902712264150944, "percentage": 49.51, "elapsed_time": "0:31:50", "remaining_time": "0:32:28", "throughput": 5793.26, "total_tokens": 11070576} {"current_steps": 16800, "total_steps": 33920, "loss": 0.3815, "lr": 5.949700836521239e-06, "epoch": 9.90566037735849, "percentage": 49.53, "elapsed_time": "0:31:51", "remaining_time": "0:32:27", "throughput": 5793.35, "total_tokens": 11074416} {"current_steps": 16805, "total_steps": 33920, "loss": 0.3763, "lr": 5.947174831347257e-06, "epoch": 9.908608490566039, "percentage": 49.54, "elapsed_time": "0:31:52", "remaining_time": "0:32:27", "throughput": 5793.56, "total_tokens": 11078160} {"current_steps": 16810, "total_steps": 33920, "loss": 0.4018, "lr": 5.944648575404657e-06, "epoch": 9.911556603773585, "percentage": 49.56, "elapsed_time": "0:31:52", "remaining_time": "0:32:26", "throughput": 5793.45, "total_tokens": 11080848} {"current_steps": 16815, "total_steps": 33920, "loss": 0.3331, "lr": 5.942122069362276e-06, "epoch": 9.914504716981131, "percentage": 49.57, "elapsed_time": "0:31:53", "remaining_time": "0:32:26", "throughput": 5793.41, "total_tokens": 11083760} {"current_steps": 16820, "total_steps": 33920, "loss": 0.4073, "lr": 5.939595313889016e-06, "epoch": 9.91745283018868, "percentage": 49.59, "elapsed_time": "0:31:53", "remaining_time": "0:32:25", "throughput": 5793.28, "total_tokens": 11086256} {"current_steps": 16825, "total_steps": 33920, "loss": 0.4575, "lr": 5.937068309653848e-06, "epoch": 9.920400943396226, "percentage": 49.6, "elapsed_time": "0:31:54", "remaining_time": "0:32:24", "throughput": 5793.18, "total_tokens": 11088848} {"current_steps": 16830, "total_steps": 33920, "loss": 0.5658, "lr": 5.934541057325807e-06, "epoch": 9.923349056603774, "percentage": 49.62, "elapsed_time": "0:31:54", "remaining_time": "0:32:24", "throughput": 5793.35, "total_tokens": 11092464} {"current_steps": 16835, "total_steps": 33920, "loss": 0.4293, "lr": 5.932013557573992e-06, "epoch": 9.92629716981132, "percentage": 49.63, "elapsed_time": "0:31:55", "remaining_time": "0:32:23", "throughput": 5793.47, "total_tokens": 11095824} {"current_steps": 16840, "total_steps": 33920, "loss": 0.283, "lr": 5.929485811067572e-06, "epoch": 9.929245283018869, "percentage": 49.65, "elapsed_time": "0:31:55", "remaining_time": "0:32:23", "throughput": 5793.55, "total_tokens": 11099376} {"current_steps": 16845, "total_steps": 33920, "loss": 0.3157, "lr": 5.926957818475778e-06, "epoch": 9.932193396226415, "percentage": 49.66, "elapsed_time": "0:31:56", "remaining_time": "0:32:22", "throughput": 5793.89, "total_tokens": 11104144} {"current_steps": 16850, "total_steps": 33920, "loss": 0.4131, "lr": 5.924429580467905e-06, "epoch": 9.935141509433961, "percentage": 49.68, "elapsed_time": "0:31:57", "remaining_time": "0:32:22", "throughput": 5794.04, "total_tokens": 11107856} {"current_steps": 16855, "total_steps": 33920, "loss": 0.5004, "lr": 5.921901097713317e-06, "epoch": 9.93808962264151, "percentage": 49.69, "elapsed_time": "0:31:57", "remaining_time": "0:32:21", "throughput": 5793.82, "total_tokens": 11110416} {"current_steps": 16860, "total_steps": 33920, "loss": 0.3065, "lr": 5.919372370881442e-06, "epoch": 9.941037735849056, "percentage": 49.71, "elapsed_time": "0:31:58", "remaining_time": "0:32:20", "throughput": 5793.61, "total_tokens": 11112848} {"current_steps": 16865, "total_steps": 33920, "loss": 0.4216, "lr": 5.916843400641768e-06, "epoch": 9.943985849056604, "percentage": 49.72, "elapsed_time": "0:31:58", "remaining_time": "0:32:20", "throughput": 5793.33, "total_tokens": 11115216} {"current_steps": 16870, "total_steps": 33920, "loss": 0.3907, "lr": 5.914314187663851e-06, "epoch": 9.94693396226415, "percentage": 49.73, "elapsed_time": "0:31:59", "remaining_time": "0:32:19", "throughput": 5793.45, "total_tokens": 11118576} {"current_steps": 16875, "total_steps": 33920, "loss": 0.3534, "lr": 5.911784732617314e-06, "epoch": 9.949882075471699, "percentage": 49.75, "elapsed_time": "0:31:59", "remaining_time": "0:32:19", "throughput": 5793.4, "total_tokens": 11121456} {"current_steps": 16880, "total_steps": 33920, "loss": 0.324, "lr": 5.90925503617184e-06, "epoch": 9.952830188679245, "percentage": 49.76, "elapsed_time": "0:32:00", "remaining_time": "0:32:18", "throughput": 5793.32, "total_tokens": 11124240} {"current_steps": 16885, "total_steps": 33920, "loss": 0.3944, "lr": 5.9067250989971745e-06, "epoch": 9.955778301886792, "percentage": 49.78, "elapsed_time": "0:32:00", "remaining_time": "0:32:17", "throughput": 5793.47, "total_tokens": 11127888} {"current_steps": 16890, "total_steps": 33920, "loss": 0.3444, "lr": 5.904194921763133e-06, "epoch": 9.95872641509434, "percentage": 49.79, "elapsed_time": "0:32:01", "remaining_time": "0:32:17", "throughput": 5793.52, "total_tokens": 11131088} {"current_steps": 16895, "total_steps": 33920, "loss": 0.5355, "lr": 5.901664505139589e-06, "epoch": 9.961674528301886, "percentage": 49.81, "elapsed_time": "0:32:01", "remaining_time": "0:32:16", "throughput": 5793.81, "total_tokens": 11135248} {"current_steps": 16900, "total_steps": 33920, "loss": 0.2978, "lr": 5.8991338497964814e-06, "epoch": 9.964622641509434, "percentage": 49.82, "elapsed_time": "0:32:02", "remaining_time": "0:32:16", "throughput": 5793.95, "total_tokens": 11138800} {"current_steps": 16905, "total_steps": 33920, "loss": 0.4102, "lr": 5.896602956403812e-06, "epoch": 9.96757075471698, "percentage": 49.84, "elapsed_time": "0:32:03", "remaining_time": "0:32:15", "throughput": 5793.99, "total_tokens": 11142384} {"current_steps": 16910, "total_steps": 33920, "loss": 0.3951, "lr": 5.894071825631645e-06, "epoch": 9.970518867924529, "percentage": 49.85, "elapsed_time": "0:32:03", "remaining_time": "0:32:14", "throughput": 5794.12, "total_tokens": 11145680} {"current_steps": 16915, "total_steps": 33920, "loss": 0.4012, "lr": 5.891540458150109e-06, "epoch": 9.973466981132075, "percentage": 49.87, "elapsed_time": "0:32:04", "remaining_time": "0:32:14", "throughput": 5794.34, "total_tokens": 11149392} {"current_steps": 16920, "total_steps": 33920, "loss": 0.433, "lr": 5.889008854629395e-06, "epoch": 9.976415094339622, "percentage": 49.88, "elapsed_time": "0:32:04", "remaining_time": "0:32:13", "throughput": 5794.31, "total_tokens": 11152240} {"current_steps": 16925, "total_steps": 33920, "loss": 0.3514, "lr": 5.886477015739754e-06, "epoch": 9.97936320754717, "percentage": 49.9, "elapsed_time": "0:32:05", "remaining_time": "0:32:13", "throughput": 5794.41, "total_tokens": 11155376} {"current_steps": 16930, "total_steps": 33920, "loss": 0.5083, "lr": 5.883944942151502e-06, "epoch": 9.982311320754716, "percentage": 49.91, "elapsed_time": "0:32:05", "remaining_time": "0:32:12", "throughput": 5794.43, "total_tokens": 11158512} {"current_steps": 16935, "total_steps": 33920, "loss": 0.4999, "lr": 5.88141263453502e-06, "epoch": 9.985259433962264, "percentage": 49.93, "elapsed_time": "0:32:06", "remaining_time": "0:32:11", "throughput": 5794.32, "total_tokens": 11161264} {"current_steps": 16940, "total_steps": 33920, "loss": 0.4499, "lr": 5.878880093560744e-06, "epoch": 9.98820754716981, "percentage": 49.94, "elapsed_time": "0:32:06", "remaining_time": "0:32:11", "throughput": 5794.46, "total_tokens": 11164464} {"current_steps": 16945, "total_steps": 33920, "loss": 0.3578, "lr": 5.876347319899173e-06, "epoch": 9.991155660377359, "percentage": 49.96, "elapsed_time": "0:32:07", "remaining_time": "0:32:10", "throughput": 5794.54, "total_tokens": 11167728} {"current_steps": 16950, "total_steps": 33920, "loss": 0.3859, "lr": 5.873814314220874e-06, "epoch": 9.994103773584905, "percentage": 49.97, "elapsed_time": "0:32:07", "remaining_time": "0:32:10", "throughput": 5794.38, "total_tokens": 11170256} {"current_steps": 16955, "total_steps": 33920, "loss": 0.4061, "lr": 5.871281077196469e-06, "epoch": 9.997051886792454, "percentage": 49.99, "elapsed_time": "0:32:08", "remaining_time": "0:32:09", "throughput": 5794.38, "total_tokens": 11173200} {"current_steps": 16960, "total_steps": 33920, "loss": 0.4498, "lr": 5.868747609496643e-06, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:32:08", "remaining_time": "0:32:08", "throughput": 5793.88, "total_tokens": 11175920} {"current_steps": 16960, "total_steps": 33920, "eval_loss": 0.517292857170105, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:32:27", "remaining_time": "0:32:27", "throughput": 5738.9, "total_tokens": 11175920} {"current_steps": 16965, "total_steps": 33920, "loss": 0.4673, "lr": 5.8662139117921435e-06, "epoch": 10.002948113207546, "percentage": 50.01, "elapsed_time": "0:32:31", "remaining_time": "0:32:29", "throughput": 5729.77, "total_tokens": 11179632} {"current_steps": 16970, "total_steps": 33920, "loss": 0.3146, "lr": 5.8636799847537785e-06, "epoch": 10.005896226415095, "percentage": 50.03, "elapsed_time": "0:32:31", "remaining_time": "0:32:29", "throughput": 5729.7, "total_tokens": 11182544} {"current_steps": 16975, "total_steps": 33920, "loss": 0.5098, "lr": 5.861145829052415e-06, "epoch": 10.008844339622641, "percentage": 50.04, "elapsed_time": "0:32:32", "remaining_time": "0:32:28", "throughput": 5729.87, "total_tokens": 11186704} {"current_steps": 16980, "total_steps": 33920, "loss": 0.3644, "lr": 5.858611445358982e-06, "epoch": 10.01179245283019, "percentage": 50.06, "elapsed_time": "0:32:32", "remaining_time": "0:32:28", "throughput": 5730.03, "total_tokens": 11190032} {"current_steps": 16985, "total_steps": 33920, "loss": 0.3688, "lr": 5.856076834344468e-06, "epoch": 10.014740566037736, "percentage": 50.07, "elapsed_time": "0:32:33", "remaining_time": "0:32:27", "throughput": 5730.15, "total_tokens": 11193232} {"current_steps": 16990, "total_steps": 33920, "loss": 0.3522, "lr": 5.853541996679924e-06, "epoch": 10.017688679245284, "percentage": 50.09, "elapsed_time": "0:32:33", "remaining_time": "0:32:27", "throughput": 5730.33, "total_tokens": 11196688} {"current_steps": 16995, "total_steps": 33920, "loss": 0.2796, "lr": 5.851006933036456e-06, "epoch": 10.02063679245283, "percentage": 50.1, "elapsed_time": "0:32:34", "remaining_time": "0:32:26", "throughput": 5730.01, "total_tokens": 11199056} {"current_steps": 17000, "total_steps": 33920, "loss": 0.2656, "lr": 5.848471644085236e-06, "epoch": 10.023584905660377, "percentage": 50.12, "elapsed_time": "0:32:34", "remaining_time": "0:32:25", "throughput": 5729.95, "total_tokens": 11201488} {"current_steps": 17005, "total_steps": 33920, "loss": 0.3411, "lr": 5.84593613049749e-06, "epoch": 10.026533018867925, "percentage": 50.13, "elapsed_time": "0:32:35", "remaining_time": "0:32:25", "throughput": 5730.13, "total_tokens": 11205264} {"current_steps": 17010, "total_steps": 33920, "loss": 0.3283, "lr": 5.843400392944509e-06, "epoch": 10.029481132075471, "percentage": 50.15, "elapsed_time": "0:32:36", "remaining_time": "0:32:24", "throughput": 5730.16, "total_tokens": 11208240} {"current_steps": 17015, "total_steps": 33920, "loss": 0.5012, "lr": 5.840864432097639e-06, "epoch": 10.03242924528302, "percentage": 50.16, "elapsed_time": "0:32:36", "remaining_time": "0:32:23", "throughput": 5730.33, "total_tokens": 11211696} {"current_steps": 17020, "total_steps": 33920, "loss": 0.3471, "lr": 5.838328248628286e-06, "epoch": 10.035377358490566, "percentage": 50.18, "elapsed_time": "0:32:37", "remaining_time": "0:32:23", "throughput": 5730.12, "total_tokens": 11213968} {"current_steps": 17025, "total_steps": 33920, "loss": 0.4902, "lr": 5.835791843207916e-06, "epoch": 10.038325471698114, "percentage": 50.19, "elapsed_time": "0:32:37", "remaining_time": "0:32:22", "throughput": 5730.18, "total_tokens": 11217168} {"current_steps": 17030, "total_steps": 33920, "loss": 0.2933, "lr": 5.833255216508056e-06, "epoch": 10.04127358490566, "percentage": 50.21, "elapsed_time": "0:32:38", "remaining_time": "0:32:22", "throughput": 5730.48, "total_tokens": 11221040} {"current_steps": 17035, "total_steps": 33920, "loss": 0.3766, "lr": 5.830718369200284e-06, "epoch": 10.044221698113208, "percentage": 50.22, "elapsed_time": "0:32:38", "remaining_time": "0:32:21", "throughput": 5730.69, "total_tokens": 11224688} {"current_steps": 17040, "total_steps": 33920, "loss": 0.4673, "lr": 5.828181301956244e-06, "epoch": 10.047169811320755, "percentage": 50.24, "elapsed_time": "0:32:39", "remaining_time": "0:32:20", "throughput": 5730.8, "total_tokens": 11227760} {"current_steps": 17045, "total_steps": 33920, "loss": 0.4404, "lr": 5.825644015447636e-06, "epoch": 10.050117924528301, "percentage": 50.25, "elapsed_time": "0:32:39", "remaining_time": "0:32:20", "throughput": 5730.7, "total_tokens": 11230288} {"current_steps": 17050, "total_steps": 33920, "loss": 0.3335, "lr": 5.823106510346216e-06, "epoch": 10.05306603773585, "percentage": 50.27, "elapsed_time": "0:32:40", "remaining_time": "0:32:19", "throughput": 5730.74, "total_tokens": 11233520} {"current_steps": 17055, "total_steps": 33920, "loss": 0.3012, "lr": 5.820568787323798e-06, "epoch": 10.056014150943396, "percentage": 50.28, "elapsed_time": "0:32:40", "remaining_time": "0:32:18", "throughput": 5730.88, "total_tokens": 11236944} {"current_steps": 17060, "total_steps": 33920, "loss": 0.344, "lr": 5.818030847052258e-06, "epoch": 10.058962264150944, "percentage": 50.29, "elapsed_time": "0:32:41", "remaining_time": "0:32:18", "throughput": 5731.11, "total_tokens": 11240848} {"current_steps": 17065, "total_steps": 33920, "loss": 0.322, "lr": 5.815492690203528e-06, "epoch": 10.06191037735849, "percentage": 50.31, "elapsed_time": "0:32:41", "remaining_time": "0:32:17", "throughput": 5731.34, "total_tokens": 11244528} {"current_steps": 17070, "total_steps": 33920, "loss": 0.5287, "lr": 5.812954317449591e-06, "epoch": 10.064858490566039, "percentage": 50.32, "elapsed_time": "0:32:42", "remaining_time": "0:32:17", "throughput": 5731.53, "total_tokens": 11247824} {"current_steps": 17075, "total_steps": 33920, "loss": 0.3295, "lr": 5.810415729462496e-06, "epoch": 10.067806603773585, "percentage": 50.34, "elapsed_time": "0:32:42", "remaining_time": "0:32:16", "throughput": 5731.71, "total_tokens": 11251152} {"current_steps": 17080, "total_steps": 33920, "loss": 0.395, "lr": 5.807876926914344e-06, "epoch": 10.070754716981131, "percentage": 50.35, "elapsed_time": "0:32:43", "remaining_time": "0:32:15", "throughput": 5731.72, "total_tokens": 11254064} {"current_steps": 17085, "total_steps": 33920, "loss": 0.3323, "lr": 5.8053379104772935e-06, "epoch": 10.07370283018868, "percentage": 50.37, "elapsed_time": "0:32:43", "remaining_time": "0:32:15", "throughput": 5731.68, "total_tokens": 11256688} {"current_steps": 17090, "total_steps": 33920, "loss": 0.2621, "lr": 5.802798680823562e-06, "epoch": 10.076650943396226, "percentage": 50.38, "elapsed_time": "0:32:44", "remaining_time": "0:32:14", "throughput": 5731.75, "total_tokens": 11259984} {"current_steps": 17095, "total_steps": 33920, "loss": 0.4442, "lr": 5.8002592386254186e-06, "epoch": 10.079599056603774, "percentage": 50.4, "elapsed_time": "0:32:44", "remaining_time": "0:32:13", "throughput": 5731.61, "total_tokens": 11262384} {"current_steps": 17100, "total_steps": 33920, "loss": 0.4045, "lr": 5.797719584555192e-06, "epoch": 10.08254716981132, "percentage": 50.41, "elapsed_time": "0:32:45", "remaining_time": "0:32:13", "throughput": 5731.85, "total_tokens": 11266160} {"current_steps": 17105, "total_steps": 33920, "loss": 0.3396, "lr": 5.795179719285269e-06, "epoch": 10.085495283018869, "percentage": 50.43, "elapsed_time": "0:32:46", "remaining_time": "0:32:12", "throughput": 5731.93, "total_tokens": 11269008} {"current_steps": 17110, "total_steps": 33920, "loss": 0.377, "lr": 5.792639643488086e-06, "epoch": 10.088443396226415, "percentage": 50.44, "elapsed_time": "0:32:46", "remaining_time": "0:32:12", "throughput": 5731.99, "total_tokens": 11272048} {"current_steps": 17115, "total_steps": 33920, "loss": 0.4302, "lr": 5.7900993578361434e-06, "epoch": 10.091391509433961, "percentage": 50.46, "elapsed_time": "0:32:47", "remaining_time": "0:32:11", "throughput": 5732.22, "total_tokens": 11275568} {"current_steps": 17120, "total_steps": 33920, "loss": 0.3266, "lr": 5.7875588630019895e-06, "epoch": 10.09433962264151, "percentage": 50.47, "elapsed_time": "0:32:47", "remaining_time": "0:32:10", "throughput": 5732.17, "total_tokens": 11278128} {"current_steps": 17125, "total_steps": 33920, "loss": 0.3205, "lr": 5.7850181596582335e-06, "epoch": 10.097287735849056, "percentage": 50.49, "elapsed_time": "0:32:48", "remaining_time": "0:32:10", "throughput": 5732.23, "total_tokens": 11281456} {"current_steps": 17130, "total_steps": 33920, "loss": 0.252, "lr": 5.782477248477535e-06, "epoch": 10.100235849056604, "percentage": 50.5, "elapsed_time": "0:32:48", "remaining_time": "0:32:09", "throughput": 5732.44, "total_tokens": 11284976} {"current_steps": 17135, "total_steps": 33920, "loss": 0.4114, "lr": 5.779936130132614e-06, "epoch": 10.10318396226415, "percentage": 50.52, "elapsed_time": "0:32:49", "remaining_time": "0:32:08", "throughput": 5732.57, "total_tokens": 11288048} {"current_steps": 17140, "total_steps": 33920, "loss": 0.2595, "lr": 5.777394805296242e-06, "epoch": 10.106132075471699, "percentage": 50.53, "elapsed_time": "0:32:49", "remaining_time": "0:32:08", "throughput": 5732.7, "total_tokens": 11291152} {"current_steps": 17145, "total_steps": 33920, "loss": 0.3184, "lr": 5.774853274641243e-06, "epoch": 10.109080188679245, "percentage": 50.55, "elapsed_time": "0:32:50", "remaining_time": "0:32:07", "throughput": 5732.78, "total_tokens": 11293936} {"current_steps": 17150, "total_steps": 33920, "loss": 0.3817, "lr": 5.772311538840501e-06, "epoch": 10.112028301886792, "percentage": 50.56, "elapsed_time": "0:32:50", "remaining_time": "0:32:06", "throughput": 5732.85, "total_tokens": 11296912} {"current_steps": 17155, "total_steps": 33920, "loss": 0.414, "lr": 5.76976959856695e-06, "epoch": 10.11497641509434, "percentage": 50.57, "elapsed_time": "0:32:51", "remaining_time": "0:32:06", "throughput": 5733.15, "total_tokens": 11300752} {"current_steps": 17160, "total_steps": 33920, "loss": 0.3142, "lr": 5.767227454493582e-06, "epoch": 10.117924528301886, "percentage": 50.59, "elapsed_time": "0:32:51", "remaining_time": "0:32:05", "throughput": 5733.06, "total_tokens": 11303152} {"current_steps": 17165, "total_steps": 33920, "loss": 0.3003, "lr": 5.764685107293436e-06, "epoch": 10.120872641509434, "percentage": 50.6, "elapsed_time": "0:32:52", "remaining_time": "0:32:04", "throughput": 5733.13, "total_tokens": 11306064} {"current_steps": 17170, "total_steps": 33920, "loss": 0.3024, "lr": 5.762142557639614e-06, "epoch": 10.12382075471698, "percentage": 50.62, "elapsed_time": "0:32:52", "remaining_time": "0:32:04", "throughput": 5733.37, "total_tokens": 11309904} {"current_steps": 17175, "total_steps": 33920, "loss": 0.3384, "lr": 5.759599806205266e-06, "epoch": 10.126768867924529, "percentage": 50.63, "elapsed_time": "0:32:53", "remaining_time": "0:32:03", "throughput": 5733.5, "total_tokens": 11313136} {"current_steps": 17180, "total_steps": 33920, "loss": 0.2867, "lr": 5.757056853663594e-06, "epoch": 10.129716981132075, "percentage": 50.65, "elapsed_time": "0:32:53", "remaining_time": "0:32:03", "throughput": 5733.33, "total_tokens": 11315568} {"current_steps": 17185, "total_steps": 33920, "loss": 0.4057, "lr": 5.754513700687858e-06, "epoch": 10.132665094339623, "percentage": 50.66, "elapsed_time": "0:32:54", "remaining_time": "0:32:02", "throughput": 5733.51, "total_tokens": 11318960} {"current_steps": 17190, "total_steps": 33920, "loss": 0.4012, "lr": 5.751970347951369e-06, "epoch": 10.13561320754717, "percentage": 50.68, "elapsed_time": "0:32:54", "remaining_time": "0:32:01", "throughput": 5733.59, "total_tokens": 11322128} {"current_steps": 17195, "total_steps": 33920, "loss": 0.3865, "lr": 5.7494267961274875e-06, "epoch": 10.138561320754716, "percentage": 50.69, "elapsed_time": "0:32:55", "remaining_time": "0:32:01", "throughput": 5733.78, "total_tokens": 11325680} {"current_steps": 17200, "total_steps": 33920, "loss": 0.4417, "lr": 5.746883045889633e-06, "epoch": 10.141509433962264, "percentage": 50.71, "elapsed_time": "0:32:55", "remaining_time": "0:32:00", "throughput": 5733.87, "total_tokens": 11329200} {"current_steps": 17205, "total_steps": 33920, "loss": 0.4266, "lr": 5.744339097911272e-06, "epoch": 10.14445754716981, "percentage": 50.72, "elapsed_time": "0:32:56", "remaining_time": "0:32:00", "throughput": 5734.18, "total_tokens": 11333648} {"current_steps": 17210, "total_steps": 33920, "loss": 0.3007, "lr": 5.741794952865928e-06, "epoch": 10.147405660377359, "percentage": 50.74, "elapsed_time": "0:32:57", "remaining_time": "0:31:59", "throughput": 5734.42, "total_tokens": 11337488} {"current_steps": 17215, "total_steps": 33920, "loss": 0.414, "lr": 5.739250611427173e-06, "epoch": 10.150353773584905, "percentage": 50.75, "elapsed_time": "0:32:57", "remaining_time": "0:31:59", "throughput": 5734.65, "total_tokens": 11341136} {"current_steps": 17220, "total_steps": 33920, "loss": 0.3734, "lr": 5.736706074268633e-06, "epoch": 10.153301886792454, "percentage": 50.77, "elapsed_time": "0:32:58", "remaining_time": "0:31:58", "throughput": 5734.71, "total_tokens": 11344400} {"current_steps": 17225, "total_steps": 33920, "loss": 0.3563, "lr": 5.734161342063984e-06, "epoch": 10.15625, "percentage": 50.78, "elapsed_time": "0:32:58", "remaining_time": "0:31:57", "throughput": 5734.96, "total_tokens": 11348272} {"current_steps": 17230, "total_steps": 33920, "loss": 0.3563, "lr": 5.731616415486957e-06, "epoch": 10.159198113207546, "percentage": 50.8, "elapsed_time": "0:32:59", "remaining_time": "0:31:57", "throughput": 5734.98, "total_tokens": 11351056} {"current_steps": 17235, "total_steps": 33920, "loss": 0.4593, "lr": 5.72907129521133e-06, "epoch": 10.162146226415095, "percentage": 50.81, "elapsed_time": "0:32:59", "remaining_time": "0:31:56", "throughput": 5734.94, "total_tokens": 11353776} {"current_steps": 17240, "total_steps": 33920, "loss": 0.3762, "lr": 5.726525981910935e-06, "epoch": 10.165094339622641, "percentage": 50.83, "elapsed_time": "0:33:00", "remaining_time": "0:31:55", "throughput": 5734.98, "total_tokens": 11356944} {"current_steps": 17245, "total_steps": 33920, "loss": 0.32, "lr": 5.723980476259658e-06, "epoch": 10.16804245283019, "percentage": 50.84, "elapsed_time": "0:33:00", "remaining_time": "0:31:55", "throughput": 5735.07, "total_tokens": 11359920} {"current_steps": 17250, "total_steps": 33920, "loss": 0.2306, "lr": 5.721434778931426e-06, "epoch": 10.170990566037736, "percentage": 50.85, "elapsed_time": "0:33:01", "remaining_time": "0:31:54", "throughput": 5735.32, "total_tokens": 11363568} {"current_steps": 17255, "total_steps": 33920, "loss": 0.3836, "lr": 5.7188888906002284e-06, "epoch": 10.173938679245284, "percentage": 50.87, "elapsed_time": "0:33:01", "remaining_time": "0:31:54", "throughput": 5735.64, "total_tokens": 11367728} {"current_steps": 17260, "total_steps": 33920, "loss": 0.3498, "lr": 5.716342811940098e-06, "epoch": 10.17688679245283, "percentage": 50.88, "elapsed_time": "0:33:02", "remaining_time": "0:31:53", "throughput": 5735.91, "total_tokens": 11371504} {"current_steps": 17265, "total_steps": 33920, "loss": 0.3458, "lr": 5.713796543625123e-06, "epoch": 10.179834905660377, "percentage": 50.9, "elapsed_time": "0:33:02", "remaining_time": "0:31:52", "throughput": 5735.73, "total_tokens": 11373744} {"current_steps": 17270, "total_steps": 33920, "loss": 0.3732, "lr": 5.711250086329435e-06, "epoch": 10.182783018867925, "percentage": 50.91, "elapsed_time": "0:33:03", "remaining_time": "0:31:52", "throughput": 5735.74, "total_tokens": 11376624} {"current_steps": 17275, "total_steps": 33920, "loss": 0.3698, "lr": 5.7087034407272225e-06, "epoch": 10.185731132075471, "percentage": 50.93, "elapsed_time": "0:33:03", "remaining_time": "0:31:51", "throughput": 5735.9, "total_tokens": 11379984} {"current_steps": 17280, "total_steps": 33920, "loss": 0.3569, "lr": 5.70615660749272e-06, "epoch": 10.18867924528302, "percentage": 50.94, "elapsed_time": "0:33:04", "remaining_time": "0:31:51", "throughput": 5735.83, "total_tokens": 11382864} {"current_steps": 17285, "total_steps": 33920, "loss": 0.3453, "lr": 5.7036095873002106e-06, "epoch": 10.191627358490566, "percentage": 50.96, "elapsed_time": "0:33:05", "remaining_time": "0:31:50", "throughput": 5736.06, "total_tokens": 11386320} {"current_steps": 17290, "total_steps": 33920, "loss": 0.3316, "lr": 5.701062380824032e-06, "epoch": 10.194575471698114, "percentage": 50.97, "elapsed_time": "0:33:05", "remaining_time": "0:31:49", "throughput": 5736.3, "total_tokens": 11390256} {"current_steps": 17295, "total_steps": 33920, "loss": 0.3709, "lr": 5.698514988738566e-06, "epoch": 10.19752358490566, "percentage": 50.99, "elapsed_time": "0:33:06", "remaining_time": "0:31:49", "throughput": 5736.36, "total_tokens": 11393264} {"current_steps": 17300, "total_steps": 33920, "loss": 0.4348, "lr": 5.6959674117182465e-06, "epoch": 10.200471698113208, "percentage": 51.0, "elapsed_time": "0:33:06", "remaining_time": "0:31:48", "throughput": 5736.65, "total_tokens": 11397584} {"current_steps": 17305, "total_steps": 33920, "loss": 0.602, "lr": 5.693419650437554e-06, "epoch": 10.203419811320755, "percentage": 51.02, "elapsed_time": "0:33:07", "remaining_time": "0:31:48", "throughput": 5736.84, "total_tokens": 11400848} {"current_steps": 17310, "total_steps": 33920, "loss": 0.328, "lr": 5.690871705571022e-06, "epoch": 10.206367924528301, "percentage": 51.03, "elapsed_time": "0:33:07", "remaining_time": "0:31:47", "throughput": 5736.88, "total_tokens": 11403760} {"current_steps": 17315, "total_steps": 33920, "loss": 0.4283, "lr": 5.688323577793229e-06, "epoch": 10.20931603773585, "percentage": 51.05, "elapsed_time": "0:33:08", "remaining_time": "0:31:46", "throughput": 5737.01, "total_tokens": 11407056} {"current_steps": 17320, "total_steps": 33920, "loss": 0.3968, "lr": 5.685775267778801e-06, "epoch": 10.212264150943396, "percentage": 51.06, "elapsed_time": "0:33:08", "remaining_time": "0:31:46", "throughput": 5737.05, "total_tokens": 11409936} {"current_steps": 17325, "total_steps": 33920, "loss": 0.3831, "lr": 5.683226776202416e-06, "epoch": 10.215212264150944, "percentage": 51.08, "elapsed_time": "0:33:09", "remaining_time": "0:31:45", "throughput": 5737.29, "total_tokens": 11413680} {"current_steps": 17330, "total_steps": 33920, "loss": 0.3491, "lr": 5.680678103738798e-06, "epoch": 10.21816037735849, "percentage": 51.09, "elapsed_time": "0:33:09", "remaining_time": "0:31:44", "throughput": 5737.4, "total_tokens": 11416912} {"current_steps": 17335, "total_steps": 33920, "loss": 0.3004, "lr": 5.678129251062717e-06, "epoch": 10.221108490566039, "percentage": 51.11, "elapsed_time": "0:33:10", "remaining_time": "0:31:44", "throughput": 5737.45, "total_tokens": 11419792} {"current_steps": 17340, "total_steps": 33920, "loss": 0.4182, "lr": 5.675580218848995e-06, "epoch": 10.224056603773585, "percentage": 51.12, "elapsed_time": "0:33:10", "remaining_time": "0:31:43", "throughput": 5737.52, "total_tokens": 11422992} {"current_steps": 17345, "total_steps": 33920, "loss": 0.4616, "lr": 5.673031007772498e-06, "epoch": 10.227004716981131, "percentage": 51.14, "elapsed_time": "0:33:11", "remaining_time": "0:31:42", "throughput": 5737.43, "total_tokens": 11425552} {"current_steps": 17350, "total_steps": 33920, "loss": 0.3495, "lr": 5.670481618508141e-06, "epoch": 10.22995283018868, "percentage": 51.15, "elapsed_time": "0:33:11", "remaining_time": "0:31:42", "throughput": 5737.48, "total_tokens": 11428592} {"current_steps": 17355, "total_steps": 33920, "loss": 0.3195, "lr": 5.667932051730887e-06, "epoch": 10.232900943396226, "percentage": 51.16, "elapsed_time": "0:33:12", "remaining_time": "0:31:41", "throughput": 5737.88, "total_tokens": 11433264} {"current_steps": 17360, "total_steps": 33920, "loss": 0.4186, "lr": 5.6653823081157434e-06, "epoch": 10.235849056603774, "percentage": 51.18, "elapsed_time": "0:33:13", "remaining_time": "0:31:41", "throughput": 5737.93, "total_tokens": 11436272} {"current_steps": 17365, "total_steps": 33920, "loss": 0.4221, "lr": 5.662832388337766e-06, "epoch": 10.23879716981132, "percentage": 51.19, "elapsed_time": "0:33:13", "remaining_time": "0:31:40", "throughput": 5738.03, "total_tokens": 11439824} {"current_steps": 17370, "total_steps": 33920, "loss": 0.259, "lr": 5.660282293072057e-06, "epoch": 10.241745283018869, "percentage": 51.21, "elapsed_time": "0:33:14", "remaining_time": "0:31:40", "throughput": 5738.19, "total_tokens": 11443120} {"current_steps": 17375, "total_steps": 33920, "loss": 0.4514, "lr": 5.657732022993765e-06, "epoch": 10.244693396226415, "percentage": 51.22, "elapsed_time": "0:33:14", "remaining_time": "0:31:39", "throughput": 5738.48, "total_tokens": 11447376} {"current_steps": 17380, "total_steps": 33920, "loss": 0.3614, "lr": 5.655181578778085e-06, "epoch": 10.247641509433961, "percentage": 51.24, "elapsed_time": "0:33:15", "remaining_time": "0:31:38", "throughput": 5738.62, "total_tokens": 11450736} {"current_steps": 17385, "total_steps": 33920, "loss": 0.4529, "lr": 5.65263096110026e-06, "epoch": 10.25058962264151, "percentage": 51.25, "elapsed_time": "0:33:15", "remaining_time": "0:31:38", "throughput": 5738.88, "total_tokens": 11454576} {"current_steps": 17390, "total_steps": 33920, "loss": 0.4595, "lr": 5.650080170635573e-06, "epoch": 10.253537735849056, "percentage": 51.27, "elapsed_time": "0:33:16", "remaining_time": "0:31:37", "throughput": 5739.08, "total_tokens": 11458384} {"current_steps": 17395, "total_steps": 33920, "loss": 0.4427, "lr": 5.647529208059359e-06, "epoch": 10.256485849056604, "percentage": 51.28, "elapsed_time": "0:33:17", "remaining_time": "0:31:37", "throughput": 5739.45, "total_tokens": 11462768} {"current_steps": 17400, "total_steps": 33920, "loss": 0.3722, "lr": 5.6449780740469985e-06, "epoch": 10.25943396226415, "percentage": 51.3, "elapsed_time": "0:33:17", "remaining_time": "0:31:36", "throughput": 5739.59, "total_tokens": 11466032} {"current_steps": 17405, "total_steps": 33920, "loss": 0.3084, "lr": 5.642426769273912e-06, "epoch": 10.262382075471699, "percentage": 51.31, "elapsed_time": "0:33:18", "remaining_time": "0:31:36", "throughput": 5739.78, "total_tokens": 11469424} {"current_steps": 17410, "total_steps": 33920, "loss": 0.3305, "lr": 5.63987529441557e-06, "epoch": 10.265330188679245, "percentage": 51.33, "elapsed_time": "0:33:18", "remaining_time": "0:31:35", "throughput": 5739.97, "total_tokens": 11472720} {"current_steps": 17415, "total_steps": 33920, "loss": 0.2741, "lr": 5.637323650147487e-06, "epoch": 10.268278301886792, "percentage": 51.34, "elapsed_time": "0:33:19", "remaining_time": "0:31:34", "throughput": 5739.91, "total_tokens": 11475280} {"current_steps": 17420, "total_steps": 33920, "loss": 0.4447, "lr": 5.63477183714522e-06, "epoch": 10.27122641509434, "percentage": 51.36, "elapsed_time": "0:33:19", "remaining_time": "0:31:34", "throughput": 5740.11, "total_tokens": 11478608} {"current_steps": 17425, "total_steps": 33920, "loss": 0.3441, "lr": 5.632219856084373e-06, "epoch": 10.274174528301886, "percentage": 51.37, "elapsed_time": "0:33:20", "remaining_time": "0:31:33", "throughput": 5740.28, "total_tokens": 11481840} {"current_steps": 17430, "total_steps": 33920, "loss": 0.4164, "lr": 5.6296677076405944e-06, "epoch": 10.277122641509434, "percentage": 51.39, "elapsed_time": "0:33:20", "remaining_time": "0:31:32", "throughput": 5740.3, "total_tokens": 11484944} {"current_steps": 17435, "total_steps": 33920, "loss": 0.365, "lr": 5.627115392489578e-06, "epoch": 10.28007075471698, "percentage": 51.4, "elapsed_time": "0:33:21", "remaining_time": "0:31:32", "throughput": 5740.65, "total_tokens": 11492016} {"current_steps": 17440, "total_steps": 33920, "loss": 0.3669, "lr": 5.624562911307058e-06, "epoch": 10.283018867924529, "percentage": 51.42, "elapsed_time": "0:33:22", "remaining_time": "0:31:32", "throughput": 5740.87, "total_tokens": 11495536} {"current_steps": 17445, "total_steps": 33920, "loss": 0.3799, "lr": 5.622010264768813e-06, "epoch": 10.285966981132075, "percentage": 51.43, "elapsed_time": "0:33:22", "remaining_time": "0:31:31", "throughput": 5741.02, "total_tokens": 11498832} {"current_steps": 17450, "total_steps": 33920, "loss": 0.4193, "lr": 5.619457453550673e-06, "epoch": 10.288915094339623, "percentage": 51.44, "elapsed_time": "0:33:23", "remaining_time": "0:31:30", "throughput": 5741.0, "total_tokens": 11501776} {"current_steps": 17455, "total_steps": 33920, "loss": 0.3483, "lr": 5.616904478328502e-06, "epoch": 10.29186320754717, "percentage": 51.46, "elapsed_time": "0:33:24", "remaining_time": "0:31:30", "throughput": 5741.2, "total_tokens": 11505712} {"current_steps": 17460, "total_steps": 33920, "loss": 0.5449, "lr": 5.6143513397782104e-06, "epoch": 10.294811320754716, "percentage": 51.47, "elapsed_time": "0:33:24", "remaining_time": "0:31:29", "throughput": 5741.33, "total_tokens": 11509232} {"current_steps": 17465, "total_steps": 33920, "loss": 0.363, "lr": 5.611798038575755e-06, "epoch": 10.297759433962264, "percentage": 51.49, "elapsed_time": "0:33:25", "remaining_time": "0:31:29", "throughput": 5741.24, "total_tokens": 11511824} {"current_steps": 17470, "total_steps": 33920, "loss": 0.3302, "lr": 5.609244575397131e-06, "epoch": 10.30070754716981, "percentage": 51.5, "elapsed_time": "0:33:25", "remaining_time": "0:31:28", "throughput": 5741.2, "total_tokens": 11514672} {"current_steps": 17475, "total_steps": 33920, "loss": 0.3756, "lr": 5.606690950918381e-06, "epoch": 10.303655660377359, "percentage": 51.52, "elapsed_time": "0:33:26", "remaining_time": "0:31:27", "throughput": 5741.27, "total_tokens": 11517808} {"current_steps": 17480, "total_steps": 33920, "loss": 0.3818, "lr": 5.604137165815586e-06, "epoch": 10.306603773584905, "percentage": 51.53, "elapsed_time": "0:33:26", "remaining_time": "0:31:27", "throughput": 5741.39, "total_tokens": 11520880} {"current_steps": 17485, "total_steps": 33920, "loss": 0.3999, "lr": 5.601583220764874e-06, "epoch": 10.309551886792454, "percentage": 51.55, "elapsed_time": "0:33:27", "remaining_time": "0:31:26", "throughput": 5741.32, "total_tokens": 11523600} {"current_steps": 17490, "total_steps": 33920, "loss": 0.3503, "lr": 5.599029116442409e-06, "epoch": 10.3125, "percentage": 51.56, "elapsed_time": "0:33:27", "remaining_time": "0:31:25", "throughput": 5741.46, "total_tokens": 11526896} {"current_steps": 17495, "total_steps": 33920, "loss": 0.2845, "lr": 5.596474853524406e-06, "epoch": 10.315448113207546, "percentage": 51.58, "elapsed_time": "0:33:28", "remaining_time": "0:31:25", "throughput": 5741.3, "total_tokens": 11529584} {"current_steps": 17500, "total_steps": 33920, "loss": 0.4112, "lr": 5.593920432687115e-06, "epoch": 10.318396226415095, "percentage": 51.59, "elapsed_time": "0:33:28", "remaining_time": "0:31:24", "throughput": 5741.2, "total_tokens": 11532240} {"current_steps": 17505, "total_steps": 33920, "loss": 0.4267, "lr": 5.591365854606829e-06, "epoch": 10.321344339622641, "percentage": 51.61, "elapsed_time": "0:33:29", "remaining_time": "0:31:24", "throughput": 5741.58, "total_tokens": 11536560} {"current_steps": 17510, "total_steps": 33920, "loss": 0.3476, "lr": 5.588811119959885e-06, "epoch": 10.32429245283019, "percentage": 51.62, "elapsed_time": "0:33:29", "remaining_time": "0:31:23", "throughput": 5741.52, "total_tokens": 11539280} {"current_steps": 17515, "total_steps": 33920, "loss": 0.4788, "lr": 5.58625622942266e-06, "epoch": 10.327240566037736, "percentage": 51.64, "elapsed_time": "0:33:30", "remaining_time": "0:31:22", "throughput": 5741.34, "total_tokens": 11541840} {"current_steps": 17520, "total_steps": 33920, "loss": 0.5361, "lr": 5.58370118367157e-06, "epoch": 10.330188679245284, "percentage": 51.65, "elapsed_time": "0:33:30", "remaining_time": "0:31:22", "throughput": 5741.55, "total_tokens": 11545584} {"current_steps": 17525, "total_steps": 33920, "loss": 0.5079, "lr": 5.581145983383077e-06, "epoch": 10.33313679245283, "percentage": 51.67, "elapsed_time": "0:33:31", "remaining_time": "0:31:21", "throughput": 5741.53, "total_tokens": 11548208} {"current_steps": 17530, "total_steps": 33920, "loss": 0.347, "lr": 5.57859062923368e-06, "epoch": 10.336084905660377, "percentage": 51.68, "elapsed_time": "0:33:31", "remaining_time": "0:31:21", "throughput": 5741.67, "total_tokens": 11551472} {"current_steps": 17535, "total_steps": 33920, "loss": 0.4886, "lr": 5.5760351218999194e-06, "epoch": 10.339033018867925, "percentage": 51.7, "elapsed_time": "0:33:32", "remaining_time": "0:31:20", "throughput": 5741.66, "total_tokens": 11554128} {"current_steps": 17540, "total_steps": 33920, "loss": 0.2445, "lr": 5.573479462058379e-06, "epoch": 10.341981132075471, "percentage": 51.71, "elapsed_time": "0:33:32", "remaining_time": "0:31:19", "throughput": 5741.68, "total_tokens": 11556912} {"current_steps": 17545, "total_steps": 33920, "loss": 0.3514, "lr": 5.570923650385679e-06, "epoch": 10.34492924528302, "percentage": 51.72, "elapsed_time": "0:33:33", "remaining_time": "0:31:19", "throughput": 5741.49, "total_tokens": 11559312} {"current_steps": 17550, "total_steps": 33920, "loss": 0.2918, "lr": 5.568367687558481e-06, "epoch": 10.347877358490566, "percentage": 51.74, "elapsed_time": "0:33:33", "remaining_time": "0:31:18", "throughput": 5741.45, "total_tokens": 11562224} {"current_steps": 17555, "total_steps": 33920, "loss": 0.3667, "lr": 5.56581157425349e-06, "epoch": 10.350825471698114, "percentage": 51.75, "elapsed_time": "0:33:34", "remaining_time": "0:31:17", "throughput": 5741.38, "total_tokens": 11564784} {"current_steps": 17560, "total_steps": 33920, "loss": 0.3993, "lr": 5.563255311147446e-06, "epoch": 10.35377358490566, "percentage": 51.77, "elapsed_time": "0:33:34", "remaining_time": "0:31:17", "throughput": 5741.51, "total_tokens": 11568336} {"current_steps": 17565, "total_steps": 33920, "loss": 0.2758, "lr": 5.560698898917129e-06, "epoch": 10.356721698113208, "percentage": 51.78, "elapsed_time": "0:33:35", "remaining_time": "0:31:16", "throughput": 5741.67, "total_tokens": 11571568} {"current_steps": 17570, "total_steps": 33920, "loss": 0.3208, "lr": 5.558142338239365e-06, "epoch": 10.359669811320755, "percentage": 51.8, "elapsed_time": "0:33:36", "remaining_time": "0:31:16", "throughput": 5742.04, "total_tokens": 11576816} {"current_steps": 17575, "total_steps": 33920, "loss": 0.4641, "lr": 5.55558562979101e-06, "epoch": 10.362617924528301, "percentage": 51.81, "elapsed_time": "0:33:36", "remaining_time": "0:31:15", "throughput": 5741.74, "total_tokens": 11579056} {"current_steps": 17580, "total_steps": 33920, "loss": 0.4172, "lr": 5.553028774248964e-06, "epoch": 10.36556603773585, "percentage": 51.83, "elapsed_time": "0:33:37", "remaining_time": "0:31:14", "throughput": 5741.87, "total_tokens": 11582480} {"current_steps": 17585, "total_steps": 33920, "loss": 0.4336, "lr": 5.5504717722901665e-06, "epoch": 10.368514150943396, "percentage": 51.84, "elapsed_time": "0:33:38", "remaining_time": "0:31:14", "throughput": 5742.17, "total_tokens": 11588304} {"current_steps": 17590, "total_steps": 33920, "loss": 0.4142, "lr": 5.547914624591597e-06, "epoch": 10.371462264150944, "percentage": 51.86, "elapsed_time": "0:33:38", "remaining_time": "0:31:14", "throughput": 5742.43, "total_tokens": 11592624} {"current_steps": 17595, "total_steps": 33920, "loss": 0.3614, "lr": 5.545357331830269e-06, "epoch": 10.37441037735849, "percentage": 51.87, "elapsed_time": "0:33:39", "remaining_time": "0:31:13", "throughput": 5742.55, "total_tokens": 11595856} {"current_steps": 17600, "total_steps": 33920, "loss": 0.3253, "lr": 5.542799894683235e-06, "epoch": 10.377358490566039, "percentage": 51.89, "elapsed_time": "0:33:39", "remaining_time": "0:31:12", "throughput": 5742.15, "total_tokens": 11598000} {"current_steps": 17605, "total_steps": 33920, "loss": 0.3058, "lr": 5.540242313827591e-06, "epoch": 10.380306603773585, "percentage": 51.9, "elapsed_time": "0:33:40", "remaining_time": "0:31:12", "throughput": 5742.44, "total_tokens": 11602192} {"current_steps": 17610, "total_steps": 33920, "loss": 0.2837, "lr": 5.537684589940466e-06, "epoch": 10.383254716981131, "percentage": 51.92, "elapsed_time": "0:33:40", "remaining_time": "0:31:11", "throughput": 5742.67, "total_tokens": 11605712} {"current_steps": 17615, "total_steps": 33920, "loss": 0.4152, "lr": 5.535126723699029e-06, "epoch": 10.38620283018868, "percentage": 51.93, "elapsed_time": "0:33:41", "remaining_time": "0:31:11", "throughput": 5742.9, "total_tokens": 11609328} {"current_steps": 17620, "total_steps": 33920, "loss": 0.3895, "lr": 5.532568715780485e-06, "epoch": 10.389150943396226, "percentage": 51.95, "elapsed_time": "0:33:42", "remaining_time": "0:31:10", "throughput": 5743.05, "total_tokens": 11612880} {"current_steps": 17625, "total_steps": 33920, "loss": 0.4914, "lr": 5.530010566862077e-06, "epoch": 10.392099056603774, "percentage": 51.96, "elapsed_time": "0:33:42", "remaining_time": "0:31:10", "throughput": 5743.33, "total_tokens": 11616976} {"current_steps": 17630, "total_steps": 33920, "loss": 0.3408, "lr": 5.527452277621089e-06, "epoch": 10.39504716981132, "percentage": 51.98, "elapsed_time": "0:33:43", "remaining_time": "0:31:09", "throughput": 5743.29, "total_tokens": 11619696} {"current_steps": 17635, "total_steps": 33920, "loss": 0.2638, "lr": 5.524893848734837e-06, "epoch": 10.397995283018869, "percentage": 51.99, "elapsed_time": "0:33:43", "remaining_time": "0:31:08", "throughput": 5743.25, "total_tokens": 11622384} {"current_steps": 17640, "total_steps": 33920, "loss": 0.3031, "lr": 5.522335280880676e-06, "epoch": 10.400943396226415, "percentage": 52.0, "elapsed_time": "0:33:44", "remaining_time": "0:31:08", "throughput": 5743.6, "total_tokens": 11627024} {"current_steps": 17645, "total_steps": 33920, "loss": 0.3545, "lr": 5.519776574735999e-06, "epoch": 10.403891509433961, "percentage": 52.02, "elapsed_time": "0:33:44", "remaining_time": "0:31:07", "throughput": 5743.42, "total_tokens": 11629616} {"current_steps": 17650, "total_steps": 33920, "loss": 0.3726, "lr": 5.5172177309782325e-06, "epoch": 10.40683962264151, "percentage": 52.03, "elapsed_time": "0:33:45", "remaining_time": "0:31:06", "throughput": 5743.41, "total_tokens": 11632272} {"current_steps": 17655, "total_steps": 33920, "loss": 0.4201, "lr": 5.514658750284844e-06, "epoch": 10.409787735849056, "percentage": 52.05, "elapsed_time": "0:33:45", "remaining_time": "0:31:06", "throughput": 5743.43, "total_tokens": 11635632} {"current_steps": 17660, "total_steps": 33920, "loss": 0.5319, "lr": 5.512099633333332e-06, "epoch": 10.412735849056604, "percentage": 52.06, "elapsed_time": "0:33:46", "remaining_time": "0:31:06", "throughput": 5743.69, "total_tokens": 11642224} {"current_steps": 17665, "total_steps": 33920, "loss": 0.3848, "lr": 5.509540380801236e-06, "epoch": 10.41568396226415, "percentage": 52.08, "elapsed_time": "0:33:47", "remaining_time": "0:31:05", "throughput": 5743.41, "total_tokens": 11644304} {"current_steps": 17670, "total_steps": 33920, "loss": 0.2432, "lr": 5.506980993366129e-06, "epoch": 10.418632075471699, "percentage": 52.09, "elapsed_time": "0:33:47", "remaining_time": "0:31:04", "throughput": 5743.45, "total_tokens": 11647536} {"current_steps": 17675, "total_steps": 33920, "loss": 0.5112, "lr": 5.504421471705616e-06, "epoch": 10.421580188679245, "percentage": 52.11, "elapsed_time": "0:33:48", "remaining_time": "0:31:04", "throughput": 5743.39, "total_tokens": 11650576} {"current_steps": 17680, "total_steps": 33920, "loss": 0.3255, "lr": 5.501861816497346e-06, "epoch": 10.424528301886792, "percentage": 52.12, "elapsed_time": "0:33:49", "remaining_time": "0:31:03", "throughput": 5743.36, "total_tokens": 11653584} {"current_steps": 17685, "total_steps": 33920, "loss": 0.3423, "lr": 5.499302028418998e-06, "epoch": 10.42747641509434, "percentage": 52.14, "elapsed_time": "0:33:49", "remaining_time": "0:31:03", "throughput": 5743.48, "total_tokens": 11657040} {"current_steps": 17690, "total_steps": 33920, "loss": 0.3767, "lr": 5.496742108148285e-06, "epoch": 10.430424528301886, "percentage": 52.15, "elapsed_time": "0:33:50", "remaining_time": "0:31:02", "throughput": 5743.54, "total_tokens": 11660208} {"current_steps": 17695, "total_steps": 33920, "loss": 0.3984, "lr": 5.494182056362959e-06, "epoch": 10.433372641509434, "percentage": 52.17, "elapsed_time": "0:33:50", "remaining_time": "0:31:01", "throughput": 5743.63, "total_tokens": 11663248} {"current_steps": 17700, "total_steps": 33920, "loss": 0.3888, "lr": 5.491621873740804e-06, "epoch": 10.43632075471698, "percentage": 52.18, "elapsed_time": "0:33:51", "remaining_time": "0:31:01", "throughput": 5743.69, "total_tokens": 11666224} {"current_steps": 17705, "total_steps": 33920, "loss": 0.3159, "lr": 5.4890615609596375e-06, "epoch": 10.439268867924529, "percentage": 52.2, "elapsed_time": "0:33:51", "remaining_time": "0:31:00", "throughput": 5743.85, "total_tokens": 11669616} {"current_steps": 17710, "total_steps": 33920, "loss": 0.3419, "lr": 5.486501118697317e-06, "epoch": 10.442216981132075, "percentage": 52.21, "elapsed_time": "0:33:52", "remaining_time": "0:31:00", "throughput": 5744.13, "total_tokens": 11673488} {"current_steps": 17715, "total_steps": 33920, "loss": 0.3849, "lr": 5.483940547631727e-06, "epoch": 10.445165094339623, "percentage": 52.23, "elapsed_time": "0:33:52", "remaining_time": "0:30:59", "throughput": 5744.01, "total_tokens": 11675824} {"current_steps": 17720, "total_steps": 33920, "loss": 0.4163, "lr": 5.481379848440792e-06, "epoch": 10.44811320754717, "percentage": 52.24, "elapsed_time": "0:33:53", "remaining_time": "0:30:58", "throughput": 5744.07, "total_tokens": 11678960} {"current_steps": 17725, "total_steps": 33920, "loss": 0.3369, "lr": 5.478819021802468e-06, "epoch": 10.451061320754716, "percentage": 52.26, "elapsed_time": "0:33:53", "remaining_time": "0:30:58", "throughput": 5744.3, "total_tokens": 11682480} {"current_steps": 17730, "total_steps": 33920, "loss": 0.5086, "lr": 5.476258068394743e-06, "epoch": 10.454009433962264, "percentage": 52.27, "elapsed_time": "0:33:54", "remaining_time": "0:30:57", "throughput": 5744.31, "total_tokens": 11685328} {"current_steps": 17735, "total_steps": 33920, "loss": 0.4602, "lr": 5.473696988895644e-06, "epoch": 10.45695754716981, "percentage": 52.28, "elapsed_time": "0:33:54", "remaining_time": "0:30:56", "throughput": 5744.52, "total_tokens": 11688720} {"current_steps": 17740, "total_steps": 33920, "loss": 0.3031, "lr": 5.471135783983224e-06, "epoch": 10.459905660377359, "percentage": 52.3, "elapsed_time": "0:33:55", "remaining_time": "0:30:56", "throughput": 5744.76, "total_tokens": 11692592} {"current_steps": 17745, "total_steps": 33920, "loss": 0.4848, "lr": 5.4685744543355745e-06, "epoch": 10.462853773584905, "percentage": 52.31, "elapsed_time": "0:33:55", "remaining_time": "0:30:55", "throughput": 5745.01, "total_tokens": 11696400} {"current_steps": 17750, "total_steps": 33920, "loss": 0.4125, "lr": 5.466013000630819e-06, "epoch": 10.465801886792454, "percentage": 52.33, "elapsed_time": "0:33:56", "remaining_time": "0:30:55", "throughput": 5744.94, "total_tokens": 11699088} {"current_steps": 17755, "total_steps": 33920, "loss": 0.4946, "lr": 5.463451423547114e-06, "epoch": 10.46875, "percentage": 52.34, "elapsed_time": "0:33:57", "remaining_time": "0:30:54", "throughput": 5745.28, "total_tokens": 11703472} {"current_steps": 17760, "total_steps": 33920, "loss": 0.3876, "lr": 5.460889723762647e-06, "epoch": 10.471698113207546, "percentage": 52.36, "elapsed_time": "0:33:57", "remaining_time": "0:30:54", "throughput": 5745.42, "total_tokens": 11706832} {"current_steps": 17765, "total_steps": 33920, "loss": 0.4897, "lr": 5.458327901955639e-06, "epoch": 10.474646226415095, "percentage": 52.37, "elapsed_time": "0:33:58", "remaining_time": "0:30:53", "throughput": 5745.62, "total_tokens": 11710416} {"current_steps": 17770, "total_steps": 33920, "loss": 0.3524, "lr": 5.455765958804344e-06, "epoch": 10.477594339622641, "percentage": 52.39, "elapsed_time": "0:33:58", "remaining_time": "0:30:52", "throughput": 5745.45, "total_tokens": 11712816} {"current_steps": 17775, "total_steps": 33920, "loss": 0.438, "lr": 5.4532038949870455e-06, "epoch": 10.48054245283019, "percentage": 52.4, "elapsed_time": "0:33:59", "remaining_time": "0:30:52", "throughput": 5745.43, "total_tokens": 11715440} {"current_steps": 17780, "total_steps": 33920, "loss": 0.4489, "lr": 5.450641711182066e-06, "epoch": 10.483490566037736, "percentage": 52.42, "elapsed_time": "0:33:59", "remaining_time": "0:30:51", "throughput": 5745.48, "total_tokens": 11718512} {"current_steps": 17785, "total_steps": 33920, "loss": 0.381, "lr": 5.448079408067748e-06, "epoch": 10.486438679245284, "percentage": 52.43, "elapsed_time": "0:34:00", "remaining_time": "0:30:50", "throughput": 5745.65, "total_tokens": 11722160} {"current_steps": 17790, "total_steps": 33920, "loss": 0.3153, "lr": 5.4455169863224775e-06, "epoch": 10.48938679245283, "percentage": 52.45, "elapsed_time": "0:34:00", "remaining_time": "0:30:50", "throughput": 5745.7, "total_tokens": 11725712} {"current_steps": 17795, "total_steps": 33920, "loss": 0.3751, "lr": 5.442954446624664e-06, "epoch": 10.492334905660377, "percentage": 52.46, "elapsed_time": "0:34:01", "remaining_time": "0:30:49", "throughput": 5745.9, "total_tokens": 11729264} {"current_steps": 17800, "total_steps": 33920, "loss": 0.4519, "lr": 5.440391789652752e-06, "epoch": 10.495283018867925, "percentage": 52.48, "elapsed_time": "0:34:01", "remaining_time": "0:30:49", "throughput": 5746.29, "total_tokens": 11733520} {"current_steps": 17805, "total_steps": 33920, "loss": 0.2985, "lr": 5.437829016085216e-06, "epoch": 10.498231132075471, "percentage": 52.49, "elapsed_time": "0:34:02", "remaining_time": "0:30:48", "throughput": 5746.59, "total_tokens": 11737904} {"current_steps": 17810, "total_steps": 33920, "loss": 0.3346, "lr": 5.435266126600561e-06, "epoch": 10.50117924528302, "percentage": 52.51, "elapsed_time": "0:34:03", "remaining_time": "0:30:48", "throughput": 5746.81, "total_tokens": 11741968} {"current_steps": 17815, "total_steps": 33920, "loss": 0.3188, "lr": 5.4327031218773215e-06, "epoch": 10.504127358490566, "percentage": 52.52, "elapsed_time": "0:34:03", "remaining_time": "0:30:47", "throughput": 5747.09, "total_tokens": 11745840} {"current_steps": 17820, "total_steps": 33920, "loss": 0.5295, "lr": 5.430140002594067e-06, "epoch": 10.507075471698114, "percentage": 52.54, "elapsed_time": "0:34:04", "remaining_time": "0:30:46", "throughput": 5747.28, "total_tokens": 11749264} {"current_steps": 17825, "total_steps": 33920, "loss": 0.3536, "lr": 5.4275767694293934e-06, "epoch": 10.51002358490566, "percentage": 52.55, "elapsed_time": "0:34:04", "remaining_time": "0:30:46", "throughput": 5747.64, "total_tokens": 11753520} {"current_steps": 17830, "total_steps": 33920, "loss": 0.3533, "lr": 5.425013423061926e-06, "epoch": 10.512971698113208, "percentage": 52.56, "elapsed_time": "0:34:05", "remaining_time": "0:30:45", "throughput": 5747.54, "total_tokens": 11756048} {"current_steps": 17835, "total_steps": 33920, "loss": 0.4816, "lr": 5.422449964170324e-06, "epoch": 10.515919811320755, "percentage": 52.58, "elapsed_time": "0:34:05", "remaining_time": "0:30:45", "throughput": 5747.69, "total_tokens": 11759344} {"current_steps": 17840, "total_steps": 33920, "loss": 0.4331, "lr": 5.419886393433275e-06, "epoch": 10.518867924528301, "percentage": 52.59, "elapsed_time": "0:34:06", "remaining_time": "0:30:44", "throughput": 5747.94, "total_tokens": 11763440} {"current_steps": 17845, "total_steps": 33920, "loss": 0.3704, "lr": 5.417322711529491e-06, "epoch": 10.52181603773585, "percentage": 52.61, "elapsed_time": "0:34:07", "remaining_time": "0:30:43", "throughput": 5747.8, "total_tokens": 11765904} {"current_steps": 17850, "total_steps": 33920, "loss": 0.2673, "lr": 5.4147589191377224e-06, "epoch": 10.524764150943396, "percentage": 52.62, "elapsed_time": "0:34:07", "remaining_time": "0:30:43", "throughput": 5747.84, "total_tokens": 11768816} {"current_steps": 17855, "total_steps": 33920, "loss": 0.2738, "lr": 5.412195016936742e-06, "epoch": 10.527712264150944, "percentage": 52.64, "elapsed_time": "0:34:08", "remaining_time": "0:30:42", "throughput": 5747.78, "total_tokens": 11771536} {"current_steps": 17860, "total_steps": 33920, "loss": 0.3413, "lr": 5.409631005605354e-06, "epoch": 10.53066037735849, "percentage": 52.65, "elapsed_time": "0:34:08", "remaining_time": "0:30:42", "throughput": 5747.92, "total_tokens": 11774832} {"current_steps": 17865, "total_steps": 33920, "loss": 0.2595, "lr": 5.407066885822391e-06, "epoch": 10.533608490566039, "percentage": 52.67, "elapsed_time": "0:34:09", "remaining_time": "0:30:41", "throughput": 5747.97, "total_tokens": 11777776} {"current_steps": 17870, "total_steps": 33920, "loss": 0.4319, "lr": 5.404502658266717e-06, "epoch": 10.536556603773585, "percentage": 52.68, "elapsed_time": "0:34:09", "remaining_time": "0:30:40", "throughput": 5748.12, "total_tokens": 11780944} {"current_steps": 17875, "total_steps": 33920, "loss": 0.316, "lr": 5.4019383236172195e-06, "epoch": 10.539504716981131, "percentage": 52.7, "elapsed_time": "0:34:10", "remaining_time": "0:30:40", "throughput": 5748.44, "total_tokens": 11784976} {"current_steps": 17880, "total_steps": 33920, "loss": 0.4316, "lr": 5.39937388255282e-06, "epoch": 10.54245283018868, "percentage": 52.71, "elapsed_time": "0:34:10", "remaining_time": "0:30:39", "throughput": 5748.47, "total_tokens": 11787760} {"current_steps": 17885, "total_steps": 33920, "loss": 0.2893, "lr": 5.3968093357524645e-06, "epoch": 10.545400943396226, "percentage": 52.73, "elapsed_time": "0:34:11", "remaining_time": "0:30:38", "throughput": 5748.36, "total_tokens": 11790352} {"current_steps": 17890, "total_steps": 33920, "loss": 0.3111, "lr": 5.3942446838951245e-06, "epoch": 10.548349056603774, "percentage": 52.74, "elapsed_time": "0:34:11", "remaining_time": "0:30:38", "throughput": 5748.36, "total_tokens": 11793200} {"current_steps": 17895, "total_steps": 33920, "loss": 0.4033, "lr": 5.3916799276598074e-06, "epoch": 10.55129716981132, "percentage": 52.76, "elapsed_time": "0:34:12", "remaining_time": "0:30:37", "throughput": 5748.52, "total_tokens": 11796848} {"current_steps": 17900, "total_steps": 33920, "loss": 0.3175, "lr": 5.3891150677255425e-06, "epoch": 10.554245283018869, "percentage": 52.77, "elapsed_time": "0:34:12", "remaining_time": "0:30:37", "throughput": 5748.66, "total_tokens": 11800176} {"current_steps": 17905, "total_steps": 33920, "loss": 0.4033, "lr": 5.386550104771384e-06, "epoch": 10.557193396226415, "percentage": 52.79, "elapsed_time": "0:34:13", "remaining_time": "0:30:36", "throughput": 5748.99, "total_tokens": 11804368} {"current_steps": 17910, "total_steps": 33920, "loss": 0.3809, "lr": 5.3839850394764205e-06, "epoch": 10.560141509433961, "percentage": 52.8, "elapsed_time": "0:34:13", "remaining_time": "0:30:35", "throughput": 5749.16, "total_tokens": 11807760} {"current_steps": 17915, "total_steps": 33920, "loss": 0.3815, "lr": 5.381419872519763e-06, "epoch": 10.56308962264151, "percentage": 52.82, "elapsed_time": "0:34:14", "remaining_time": "0:30:35", "throughput": 5749.03, "total_tokens": 11810384} {"current_steps": 17920, "total_steps": 33920, "loss": 0.3471, "lr": 5.378854604580549e-06, "epoch": 10.566037735849056, "percentage": 52.83, "elapsed_time": "0:34:14", "remaining_time": "0:30:34", "throughput": 5748.95, "total_tokens": 11813072} {"current_steps": 17925, "total_steps": 33920, "loss": 0.42, "lr": 5.376289236337946e-06, "epoch": 10.568985849056604, "percentage": 52.84, "elapsed_time": "0:34:15", "remaining_time": "0:30:34", "throughput": 5748.88, "total_tokens": 11815664} {"current_steps": 17930, "total_steps": 33920, "loss": 0.3151, "lr": 5.373723768471147e-06, "epoch": 10.57193396226415, "percentage": 52.86, "elapsed_time": "0:34:15", "remaining_time": "0:30:33", "throughput": 5748.9, "total_tokens": 11818544} {"current_steps": 17935, "total_steps": 33920, "loss": 0.304, "lr": 5.37115820165937e-06, "epoch": 10.574882075471699, "percentage": 52.87, "elapsed_time": "0:34:16", "remaining_time": "0:30:32", "throughput": 5748.93, "total_tokens": 11821264} {"current_steps": 17940, "total_steps": 33920, "loss": 0.3656, "lr": 5.368592536581858e-06, "epoch": 10.577830188679245, "percentage": 52.89, "elapsed_time": "0:34:16", "remaining_time": "0:30:32", "throughput": 5749.05, "total_tokens": 11824656} {"current_steps": 17945, "total_steps": 33920, "loss": 0.3716, "lr": 5.366026773917885e-06, "epoch": 10.580778301886792, "percentage": 52.9, "elapsed_time": "0:34:17", "remaining_time": "0:30:31", "throughput": 5749.13, "total_tokens": 11827760} {"current_steps": 17950, "total_steps": 33920, "loss": 0.3941, "lr": 5.363460914346746e-06, "epoch": 10.58372641509434, "percentage": 52.92, "elapsed_time": "0:34:17", "remaining_time": "0:30:30", "throughput": 5748.97, "total_tokens": 11830000} {"current_steps": 17955, "total_steps": 33920, "loss": 0.4464, "lr": 5.360894958547762e-06, "epoch": 10.586674528301886, "percentage": 52.93, "elapsed_time": "0:34:18", "remaining_time": "0:30:30", "throughput": 5749.14, "total_tokens": 11833680} {"current_steps": 17960, "total_steps": 33920, "loss": 0.352, "lr": 5.358328907200284e-06, "epoch": 10.589622641509434, "percentage": 52.95, "elapsed_time": "0:34:18", "remaining_time": "0:30:29", "throughput": 5749.34, "total_tokens": 11837456} {"current_steps": 17965, "total_steps": 33920, "loss": 0.3683, "lr": 5.355762760983682e-06, "epoch": 10.59257075471698, "percentage": 52.96, "elapsed_time": "0:34:19", "remaining_time": "0:30:29", "throughput": 5749.42, "total_tokens": 11840784} {"current_steps": 17970, "total_steps": 33920, "loss": 0.3316, "lr": 5.353196520577356e-06, "epoch": 10.595518867924529, "percentage": 52.98, "elapsed_time": "0:34:19", "remaining_time": "0:30:28", "throughput": 5749.33, "total_tokens": 11843280} {"current_steps": 17975, "total_steps": 33920, "loss": 0.4579, "lr": 5.35063018666073e-06, "epoch": 10.598466981132075, "percentage": 52.99, "elapsed_time": "0:34:20", "remaining_time": "0:30:27", "throughput": 5749.28, "total_tokens": 11846224} {"current_steps": 17980, "total_steps": 33920, "loss": 0.2483, "lr": 5.3480637599132515e-06, "epoch": 10.601415094339622, "percentage": 53.01, "elapsed_time": "0:34:20", "remaining_time": "0:30:27", "throughput": 5749.19, "total_tokens": 11848880} {"current_steps": 17985, "total_steps": 33920, "loss": 0.419, "lr": 5.34549724101439e-06, "epoch": 10.60436320754717, "percentage": 53.02, "elapsed_time": "0:34:21", "remaining_time": "0:30:26", "throughput": 5749.36, "total_tokens": 11852528} {"current_steps": 17990, "total_steps": 33920, "loss": 0.4213, "lr": 5.342930630643646e-06, "epoch": 10.607311320754716, "percentage": 53.04, "elapsed_time": "0:34:22", "remaining_time": "0:30:26", "throughput": 5749.64, "total_tokens": 11856560} {"current_steps": 17995, "total_steps": 33920, "loss": 0.3263, "lr": 5.340363929480541e-06, "epoch": 10.610259433962264, "percentage": 53.05, "elapsed_time": "0:34:22", "remaining_time": "0:30:25", "throughput": 5749.97, "total_tokens": 11860688} {"current_steps": 18000, "total_steps": 33920, "loss": 0.4248, "lr": 5.3377971382046164e-06, "epoch": 10.61320754716981, "percentage": 53.07, "elapsed_time": "0:34:23", "remaining_time": "0:30:25", "throughput": 5750.39, "total_tokens": 11866224} {"current_steps": 18005, "total_steps": 33920, "loss": 0.3523, "lr": 5.335230257495446e-06, "epoch": 10.616155660377359, "percentage": 53.08, "elapsed_time": "0:34:24", "remaining_time": "0:30:24", "throughput": 5750.4, "total_tokens": 11869008} {"current_steps": 18010, "total_steps": 33920, "loss": 0.3124, "lr": 5.3326632880326205e-06, "epoch": 10.619103773584905, "percentage": 53.1, "elapsed_time": "0:34:24", "remaining_time": "0:30:23", "throughput": 5750.53, "total_tokens": 11873104} {"current_steps": 18015, "total_steps": 33920, "loss": 0.4119, "lr": 5.3300962304957515e-06, "epoch": 10.622051886792454, "percentage": 53.11, "elapsed_time": "0:34:25", "remaining_time": "0:30:23", "throughput": 5750.92, "total_tokens": 11877680} {"current_steps": 18020, "total_steps": 33920, "loss": 0.3613, "lr": 5.327529085564487e-06, "epoch": 10.625, "percentage": 53.12, "elapsed_time": "0:34:25", "remaining_time": "0:30:22", "throughput": 5750.89, "total_tokens": 11880400} {"current_steps": 18025, "total_steps": 33920, "loss": 0.4057, "lr": 5.324961853918485e-06, "epoch": 10.627948113207546, "percentage": 53.14, "elapsed_time": "0:34:26", "remaining_time": "0:30:22", "throughput": 5751.08, "total_tokens": 11884112} {"current_steps": 18030, "total_steps": 33920, "loss": 0.4549, "lr": 5.32239453623743e-06, "epoch": 10.630896226415095, "percentage": 53.15, "elapsed_time": "0:34:26", "remaining_time": "0:30:21", "throughput": 5751.1, "total_tokens": 11886928} {"current_steps": 18035, "total_steps": 33920, "loss": 0.3012, "lr": 5.3198271332010335e-06, "epoch": 10.633844339622641, "percentage": 53.17, "elapsed_time": "0:34:27", "remaining_time": "0:30:21", "throughput": 5751.43, "total_tokens": 11891280} {"current_steps": 18040, "total_steps": 33920, "loss": 0.3163, "lr": 5.317259645489024e-06, "epoch": 10.63679245283019, "percentage": 53.18, "elapsed_time": "0:34:28", "remaining_time": "0:30:20", "throughput": 5751.33, "total_tokens": 11893840} {"current_steps": 18045, "total_steps": 33920, "loss": 0.448, "lr": 5.314692073781157e-06, "epoch": 10.639740566037736, "percentage": 53.2, "elapsed_time": "0:34:28", "remaining_time": "0:30:19", "throughput": 5751.48, "total_tokens": 11897552} {"current_steps": 18050, "total_steps": 33920, "loss": 0.441, "lr": 5.312124418757207e-06, "epoch": 10.642688679245284, "percentage": 53.21, "elapsed_time": "0:34:29", "remaining_time": "0:30:19", "throughput": 5751.48, "total_tokens": 11900688} {"current_steps": 18055, "total_steps": 33920, "loss": 0.5207, "lr": 5.309556681096972e-06, "epoch": 10.64563679245283, "percentage": 53.23, "elapsed_time": "0:34:29", "remaining_time": "0:30:18", "throughput": 5751.71, "total_tokens": 11904592} {"current_steps": 18060, "total_steps": 33920, "loss": 0.4365, "lr": 5.306988861480271e-06, "epoch": 10.648584905660378, "percentage": 53.24, "elapsed_time": "0:34:30", "remaining_time": "0:30:18", "throughput": 5751.68, "total_tokens": 11908080} {"current_steps": 18065, "total_steps": 33920, "loss": 0.4562, "lr": 5.304420960586946e-06, "epoch": 10.651533018867925, "percentage": 53.26, "elapsed_time": "0:34:30", "remaining_time": "0:30:17", "throughput": 5751.55, "total_tokens": 11910800} {"current_steps": 18070, "total_steps": 33920, "loss": 0.4268, "lr": 5.3018529790968606e-06, "epoch": 10.654481132075471, "percentage": 53.27, "elapsed_time": "0:34:31", "remaining_time": "0:30:16", "throughput": 5751.54, "total_tokens": 11913936} {"current_steps": 18075, "total_steps": 33920, "loss": 0.3427, "lr": 5.299284917689898e-06, "epoch": 10.65742924528302, "percentage": 53.29, "elapsed_time": "0:34:32", "remaining_time": "0:30:16", "throughput": 5751.72, "total_tokens": 11917712} {"current_steps": 18080, "total_steps": 33920, "loss": 0.3976, "lr": 5.296716777045962e-06, "epoch": 10.660377358490566, "percentage": 53.3, "elapsed_time": "0:34:32", "remaining_time": "0:30:15", "throughput": 5751.79, "total_tokens": 11920752} {"current_steps": 18085, "total_steps": 33920, "loss": 0.3997, "lr": 5.294148557844983e-06, "epoch": 10.663325471698114, "percentage": 53.32, "elapsed_time": "0:34:32", "remaining_time": "0:30:15", "throughput": 5751.75, "total_tokens": 11923280} {"current_steps": 18090, "total_steps": 33920, "loss": 0.3161, "lr": 5.291580260766904e-06, "epoch": 10.66627358490566, "percentage": 53.33, "elapsed_time": "0:34:33", "remaining_time": "0:30:14", "throughput": 5751.93, "total_tokens": 11926896} {"current_steps": 18095, "total_steps": 33920, "loss": 0.3377, "lr": 5.289011886491694e-06, "epoch": 10.669221698113208, "percentage": 53.35, "elapsed_time": "0:34:34", "remaining_time": "0:30:13", "throughput": 5752.26, "total_tokens": 11930896} {"current_steps": 18100, "total_steps": 33920, "loss": 0.4421, "lr": 5.286443435699342e-06, "epoch": 10.672169811320755, "percentage": 53.36, "elapsed_time": "0:34:34", "remaining_time": "0:30:13", "throughput": 5752.61, "total_tokens": 11935184} {"current_steps": 18105, "total_steps": 33920, "loss": 0.2512, "lr": 5.283874909069855e-06, "epoch": 10.675117924528301, "percentage": 53.38, "elapsed_time": "0:34:35", "remaining_time": "0:30:12", "throughput": 5752.79, "total_tokens": 11938704} {"current_steps": 18110, "total_steps": 33920, "loss": 0.3036, "lr": 5.281306307283263e-06, "epoch": 10.67806603773585, "percentage": 53.39, "elapsed_time": "0:34:35", "remaining_time": "0:30:12", "throughput": 5752.75, "total_tokens": 11941456} {"current_steps": 18115, "total_steps": 33920, "loss": 0.4092, "lr": 5.2787376310196145e-06, "epoch": 10.681014150943396, "percentage": 53.41, "elapsed_time": "0:34:36", "remaining_time": "0:30:11", "throughput": 5752.74, "total_tokens": 11944240} {"current_steps": 18120, "total_steps": 33920, "loss": 0.4398, "lr": 5.276168880958977e-06, "epoch": 10.683962264150944, "percentage": 53.42, "elapsed_time": "0:34:36", "remaining_time": "0:30:10", "throughput": 5752.72, "total_tokens": 11947152} {"current_steps": 18125, "total_steps": 33920, "loss": 0.4022, "lr": 5.273600057781437e-06, "epoch": 10.68691037735849, "percentage": 53.43, "elapsed_time": "0:34:37", "remaining_time": "0:30:10", "throughput": 5752.63, "total_tokens": 11950352} {"current_steps": 18130, "total_steps": 33920, "loss": 0.3938, "lr": 5.271031162167103e-06, "epoch": 10.689858490566039, "percentage": 53.45, "elapsed_time": "0:34:37", "remaining_time": "0:30:09", "throughput": 5752.69, "total_tokens": 11953680} {"current_steps": 18135, "total_steps": 33920, "loss": 0.4203, "lr": 5.268462194796101e-06, "epoch": 10.692806603773585, "percentage": 53.46, "elapsed_time": "0:34:38", "remaining_time": "0:30:09", "throughput": 5752.64, "total_tokens": 11956464} {"current_steps": 18140, "total_steps": 33920, "loss": 0.2427, "lr": 5.265893156348576e-06, "epoch": 10.695754716981131, "percentage": 53.48, "elapsed_time": "0:34:38", "remaining_time": "0:30:08", "throughput": 5752.67, "total_tokens": 11959312} {"current_steps": 18145, "total_steps": 33920, "loss": 0.3927, "lr": 5.2633240475046925e-06, "epoch": 10.69870283018868, "percentage": 53.49, "elapsed_time": "0:34:39", "remaining_time": "0:30:07", "throughput": 5752.63, "total_tokens": 11961776} {"current_steps": 18150, "total_steps": 33920, "loss": 0.3577, "lr": 5.2607548689446305e-06, "epoch": 10.701650943396226, "percentage": 53.51, "elapsed_time": "0:34:39", "remaining_time": "0:30:07", "throughput": 5752.84, "total_tokens": 11965328} {"current_steps": 18155, "total_steps": 33920, "loss": 0.4081, "lr": 5.258185621348595e-06, "epoch": 10.704599056603774, "percentage": 53.52, "elapsed_time": "0:34:40", "remaining_time": "0:30:06", "throughput": 5753.0, "total_tokens": 11968816} {"current_steps": 18160, "total_steps": 33920, "loss": 0.3621, "lr": 5.255616305396801e-06, "epoch": 10.70754716981132, "percentage": 53.54, "elapsed_time": "0:34:40", "remaining_time": "0:30:05", "throughput": 5753.16, "total_tokens": 11972144} {"current_steps": 18165, "total_steps": 33920, "loss": 0.4234, "lr": 5.253046921769491e-06, "epoch": 10.710495283018869, "percentage": 53.55, "elapsed_time": "0:34:41", "remaining_time": "0:30:05", "throughput": 5753.21, "total_tokens": 11974896} {"current_steps": 18170, "total_steps": 33920, "loss": 0.273, "lr": 5.250477471146916e-06, "epoch": 10.713443396226415, "percentage": 53.57, "elapsed_time": "0:34:41", "remaining_time": "0:30:04", "throughput": 5753.26, "total_tokens": 11977904} {"current_steps": 18175, "total_steps": 33920, "loss": 0.2999, "lr": 5.2479079542093535e-06, "epoch": 10.716391509433961, "percentage": 53.58, "elapsed_time": "0:34:42", "remaining_time": "0:30:04", "throughput": 5753.37, "total_tokens": 11981136} {"current_steps": 18180, "total_steps": 33920, "loss": 0.3352, "lr": 5.245338371637091e-06, "epoch": 10.71933962264151, "percentage": 53.6, "elapsed_time": "0:34:43", "remaining_time": "0:30:03", "throughput": 5753.6, "total_tokens": 11984976} {"current_steps": 18185, "total_steps": 33920, "loss": 0.3329, "lr": 5.242768724110437e-06, "epoch": 10.722287735849056, "percentage": 53.61, "elapsed_time": "0:34:43", "remaining_time": "0:30:02", "throughput": 5753.64, "total_tokens": 11987856} {"current_steps": 18190, "total_steps": 33920, "loss": 0.4604, "lr": 5.240199012309717e-06, "epoch": 10.725235849056604, "percentage": 53.63, "elapsed_time": "0:34:43", "remaining_time": "0:30:02", "throughput": 5753.6, "total_tokens": 11990416} {"current_steps": 18195, "total_steps": 33920, "loss": 0.4422, "lr": 5.237629236915273e-06, "epoch": 10.72818396226415, "percentage": 53.64, "elapsed_time": "0:34:44", "remaining_time": "0:30:01", "throughput": 5753.7, "total_tokens": 11993392} {"current_steps": 18200, "total_steps": 33920, "loss": 0.3743, "lr": 5.235059398607464e-06, "epoch": 10.731132075471699, "percentage": 53.66, "elapsed_time": "0:34:44", "remaining_time": "0:30:00", "throughput": 5753.72, "total_tokens": 11996144} {"current_steps": 18205, "total_steps": 33920, "loss": 0.4656, "lr": 5.232489498066665e-06, "epoch": 10.734080188679245, "percentage": 53.67, "elapsed_time": "0:34:45", "remaining_time": "0:30:00", "throughput": 5753.78, "total_tokens": 11999312} {"current_steps": 18210, "total_steps": 33920, "loss": 0.434, "lr": 5.229919535973272e-06, "epoch": 10.737028301886792, "percentage": 53.69, "elapsed_time": "0:34:45", "remaining_time": "0:29:59", "throughput": 5753.8, "total_tokens": 12002128} {"current_steps": 18215, "total_steps": 33920, "loss": 0.2888, "lr": 5.2273495130076905e-06, "epoch": 10.73997641509434, "percentage": 53.7, "elapsed_time": "0:34:46", "remaining_time": "0:29:59", "throughput": 5754.04, "total_tokens": 12006000} {"current_steps": 18220, "total_steps": 33920, "loss": 0.3708, "lr": 5.224779429850344e-06, "epoch": 10.742924528301886, "percentage": 53.71, "elapsed_time": "0:34:47", "remaining_time": "0:29:58", "throughput": 5754.11, "total_tokens": 12009072} {"current_steps": 18225, "total_steps": 33920, "loss": 0.5322, "lr": 5.222209287181677e-06, "epoch": 10.745872641509434, "percentage": 53.73, "elapsed_time": "0:34:47", "remaining_time": "0:29:57", "throughput": 5754.07, "total_tokens": 12011856} {"current_steps": 18230, "total_steps": 33920, "loss": 0.4388, "lr": 5.219639085682142e-06, "epoch": 10.74882075471698, "percentage": 53.74, "elapsed_time": "0:34:47", "remaining_time": "0:29:57", "throughput": 5754.08, "total_tokens": 12014512} {"current_steps": 18235, "total_steps": 33920, "loss": 0.3748, "lr": 5.2170688260322124e-06, "epoch": 10.751768867924529, "percentage": 53.76, "elapsed_time": "0:34:48", "remaining_time": "0:29:56", "throughput": 5754.18, "total_tokens": 12017520} {"current_steps": 18240, "total_steps": 33920, "loss": 0.3056, "lr": 5.214498508912376e-06, "epoch": 10.754716981132075, "percentage": 53.77, "elapsed_time": "0:34:48", "remaining_time": "0:29:55", "throughput": 5754.15, "total_tokens": 12020336} {"current_steps": 18245, "total_steps": 33920, "loss": 0.3678, "lr": 5.211928135003135e-06, "epoch": 10.757665094339622, "percentage": 53.79, "elapsed_time": "0:34:49", "remaining_time": "0:29:55", "throughput": 5754.39, "total_tokens": 12024240} {"current_steps": 18250, "total_steps": 33920, "loss": 0.5466, "lr": 5.209357704985007e-06, "epoch": 10.76061320754717, "percentage": 53.8, "elapsed_time": "0:34:50", "remaining_time": "0:29:54", "throughput": 5754.49, "total_tokens": 12027248} {"current_steps": 18255, "total_steps": 33920, "loss": 0.4075, "lr": 5.206787219538524e-06, "epoch": 10.763561320754716, "percentage": 53.82, "elapsed_time": "0:34:50", "remaining_time": "0:29:53", "throughput": 5754.54, "total_tokens": 12030320} {"current_steps": 18260, "total_steps": 33920, "loss": 0.4164, "lr": 5.204216679344234e-06, "epoch": 10.766509433962264, "percentage": 53.83, "elapsed_time": "0:34:51", "remaining_time": "0:29:53", "throughput": 5754.76, "total_tokens": 12034672} {"current_steps": 18265, "total_steps": 33920, "loss": 0.339, "lr": 5.201646085082696e-06, "epoch": 10.76945754716981, "percentage": 53.85, "elapsed_time": "0:34:51", "remaining_time": "0:29:52", "throughput": 5754.72, "total_tokens": 12038032} {"current_steps": 18270, "total_steps": 33920, "loss": 0.4487, "lr": 5.199075437434491e-06, "epoch": 10.772405660377359, "percentage": 53.86, "elapsed_time": "0:34:52", "remaining_time": "0:29:52", "throughput": 5754.91, "total_tokens": 12041552} {"current_steps": 18275, "total_steps": 33920, "loss": 0.3815, "lr": 5.1965047370802046e-06, "epoch": 10.775353773584905, "percentage": 53.88, "elapsed_time": "0:34:52", "remaining_time": "0:29:51", "throughput": 5754.98, "total_tokens": 12044752} {"current_steps": 18280, "total_steps": 33920, "loss": 0.3775, "lr": 5.193933984700441e-06, "epoch": 10.778301886792454, "percentage": 53.89, "elapsed_time": "0:34:53", "remaining_time": "0:29:51", "throughput": 5755.07, "total_tokens": 12048944} {"current_steps": 18285, "total_steps": 33920, "loss": 0.4895, "lr": 5.1913631809758216e-06, "epoch": 10.78125, "percentage": 53.91, "elapsed_time": "0:34:54", "remaining_time": "0:29:50", "throughput": 5755.11, "total_tokens": 12052240} {"current_steps": 18290, "total_steps": 33920, "loss": 0.4539, "lr": 5.188792326586973e-06, "epoch": 10.784198113207546, "percentage": 53.92, "elapsed_time": "0:34:54", "remaining_time": "0:29:50", "throughput": 5754.97, "total_tokens": 12054736} {"current_steps": 18295, "total_steps": 33920, "loss": 0.5651, "lr": 5.186221422214544e-06, "epoch": 10.787146226415095, "percentage": 53.94, "elapsed_time": "0:34:55", "remaining_time": "0:29:49", "throughput": 5755.23, "total_tokens": 12058480} {"current_steps": 18300, "total_steps": 33920, "loss": 0.3826, "lr": 5.1836504685391885e-06, "epoch": 10.790094339622641, "percentage": 53.95, "elapsed_time": "0:34:55", "remaining_time": "0:29:48", "throughput": 5755.2, "total_tokens": 12061168} {"current_steps": 18305, "total_steps": 33920, "loss": 0.2994, "lr": 5.181079466241582e-06, "epoch": 10.79304245283019, "percentage": 53.97, "elapsed_time": "0:34:56", "remaining_time": "0:29:48", "throughput": 5755.18, "total_tokens": 12064048} {"current_steps": 18310, "total_steps": 33920, "loss": 0.3996, "lr": 5.178508416002406e-06, "epoch": 10.795990566037736, "percentage": 53.98, "elapsed_time": "0:34:56", "remaining_time": "0:29:47", "throughput": 5755.26, "total_tokens": 12067536} {"current_steps": 18315, "total_steps": 33920, "loss": 0.3335, "lr": 5.175937318502357e-06, "epoch": 10.798938679245284, "percentage": 53.99, "elapsed_time": "0:34:57", "remaining_time": "0:29:46", "throughput": 5755.36, "total_tokens": 12070544} {"current_steps": 18320, "total_steps": 33920, "loss": 0.3019, "lr": 5.173366174422147e-06, "epoch": 10.80188679245283, "percentage": 54.01, "elapsed_time": "0:34:57", "remaining_time": "0:29:46", "throughput": 5755.29, "total_tokens": 12073168} {"current_steps": 18325, "total_steps": 33920, "loss": 0.3791, "lr": 5.170794984442492e-06, "epoch": 10.804834905660378, "percentage": 54.02, "elapsed_time": "0:34:58", "remaining_time": "0:29:45", "throughput": 5755.48, "total_tokens": 12077168} {"current_steps": 18330, "total_steps": 33920, "loss": 0.3573, "lr": 5.16822374924413e-06, "epoch": 10.807783018867925, "percentage": 54.04, "elapsed_time": "0:34:58", "remaining_time": "0:29:45", "throughput": 5755.39, "total_tokens": 12080048} {"current_steps": 18335, "total_steps": 33920, "loss": 0.4951, "lr": 5.165652469507806e-06, "epoch": 10.810731132075471, "percentage": 54.05, "elapsed_time": "0:34:59", "remaining_time": "0:29:44", "throughput": 5755.15, "total_tokens": 12082256} {"current_steps": 18340, "total_steps": 33920, "loss": 0.2989, "lr": 5.163081145914276e-06, "epoch": 10.81367924528302, "percentage": 54.07, "elapsed_time": "0:34:59", "remaining_time": "0:29:43", "throughput": 5754.83, "total_tokens": 12084336} {"current_steps": 18345, "total_steps": 33920, "loss": 0.3409, "lr": 5.160509779144311e-06, "epoch": 10.816627358490566, "percentage": 54.08, "elapsed_time": "0:35:00", "remaining_time": "0:29:43", "throughput": 5754.81, "total_tokens": 12087664} {"current_steps": 18350, "total_steps": 33920, "loss": 0.2602, "lr": 5.157938369878688e-06, "epoch": 10.819575471698114, "percentage": 54.1, "elapsed_time": "0:35:00", "remaining_time": "0:29:42", "throughput": 5754.67, "total_tokens": 12090128} {"current_steps": 18355, "total_steps": 33920, "loss": 0.4003, "lr": 5.155366918798203e-06, "epoch": 10.82252358490566, "percentage": 54.11, "elapsed_time": "0:35:01", "remaining_time": "0:29:42", "throughput": 5754.69, "total_tokens": 12093488} {"current_steps": 18360, "total_steps": 33920, "loss": 0.279, "lr": 5.152795426583654e-06, "epoch": 10.825471698113208, "percentage": 54.13, "elapsed_time": "0:35:02", "remaining_time": "0:29:41", "throughput": 5754.89, "total_tokens": 12097520} {"current_steps": 18365, "total_steps": 33920, "loss": 0.4818, "lr": 5.15022389391586e-06, "epoch": 10.828419811320755, "percentage": 54.14, "elapsed_time": "0:35:02", "remaining_time": "0:29:40", "throughput": 5755.06, "total_tokens": 12100944} {"current_steps": 18370, "total_steps": 33920, "loss": 0.2197, "lr": 5.147652321475642e-06, "epoch": 10.831367924528301, "percentage": 54.16, "elapsed_time": "0:35:03", "remaining_time": "0:29:40", "throughput": 5755.07, "total_tokens": 12103792} {"current_steps": 18375, "total_steps": 33920, "loss": 0.4992, "lr": 5.145080709943835e-06, "epoch": 10.83431603773585, "percentage": 54.17, "elapsed_time": "0:35:03", "remaining_time": "0:29:39", "throughput": 5754.99, "total_tokens": 12106832} {"current_steps": 18380, "total_steps": 33920, "loss": 0.3831, "lr": 5.142509060001285e-06, "epoch": 10.837264150943396, "percentage": 54.19, "elapsed_time": "0:35:04", "remaining_time": "0:29:39", "throughput": 5755.05, "total_tokens": 12110064} {"current_steps": 18385, "total_steps": 33920, "loss": 0.4131, "lr": 5.139937372328847e-06, "epoch": 10.840212264150944, "percentage": 54.2, "elapsed_time": "0:35:04", "remaining_time": "0:29:38", "throughput": 5755.31, "total_tokens": 12114032} {"current_steps": 18390, "total_steps": 33920, "loss": 0.3528, "lr": 5.1373656476073876e-06, "epoch": 10.84316037735849, "percentage": 54.22, "elapsed_time": "0:35:05", "remaining_time": "0:29:37", "throughput": 5755.47, "total_tokens": 12117328} {"current_steps": 18395, "total_steps": 33920, "loss": 0.5094, "lr": 5.134793886517779e-06, "epoch": 10.846108490566039, "percentage": 54.23, "elapsed_time": "0:35:05", "remaining_time": "0:29:37", "throughput": 5755.7, "total_tokens": 12121040} {"current_steps": 18400, "total_steps": 33920, "loss": 0.2512, "lr": 5.1322220897409105e-06, "epoch": 10.849056603773585, "percentage": 54.25, "elapsed_time": "0:35:06", "remaining_time": "0:29:36", "throughput": 5755.69, "total_tokens": 12123824} {"current_steps": 18405, "total_steps": 33920, "loss": 0.3785, "lr": 5.129650257957671e-06, "epoch": 10.852004716981131, "percentage": 54.26, "elapsed_time": "0:35:06", "remaining_time": "0:29:36", "throughput": 5755.65, "total_tokens": 12126960} {"current_steps": 18410, "total_steps": 33920, "loss": 0.3194, "lr": 5.12707839184897e-06, "epoch": 10.85495283018868, "percentage": 54.27, "elapsed_time": "0:35:07", "remaining_time": "0:29:35", "throughput": 5755.72, "total_tokens": 12130096} {"current_steps": 18415, "total_steps": 33920, "loss": 0.3717, "lr": 5.124506492095716e-06, "epoch": 10.857900943396226, "percentage": 54.29, "elapsed_time": "0:35:07", "remaining_time": "0:29:34", "throughput": 5755.66, "total_tokens": 12132848} {"current_steps": 18420, "total_steps": 33920, "loss": 0.2901, "lr": 5.121934559378831e-06, "epoch": 10.860849056603774, "percentage": 54.3, "elapsed_time": "0:35:08", "remaining_time": "0:29:34", "throughput": 5755.77, "total_tokens": 12136304} {"current_steps": 18425, "total_steps": 33920, "loss": 0.3664, "lr": 5.1193625943792456e-06, "epoch": 10.86379716981132, "percentage": 54.32, "elapsed_time": "0:35:09", "remaining_time": "0:29:33", "throughput": 5755.63, "total_tokens": 12138960} {"current_steps": 18430, "total_steps": 33920, "loss": 0.3169, "lr": 5.116790597777901e-06, "epoch": 10.866745283018869, "percentage": 54.33, "elapsed_time": "0:35:09", "remaining_time": "0:29:33", "throughput": 5755.57, "total_tokens": 12141808} {"current_steps": 18435, "total_steps": 33920, "loss": 0.375, "lr": 5.11421857025574e-06, "epoch": 10.869693396226415, "percentage": 54.35, "elapsed_time": "0:35:10", "remaining_time": "0:29:32", "throughput": 5755.76, "total_tokens": 12145264} {"current_steps": 18440, "total_steps": 33920, "loss": 0.4567, "lr": 5.111646512493721e-06, "epoch": 10.872641509433961, "percentage": 54.36, "elapsed_time": "0:35:10", "remaining_time": "0:29:31", "throughput": 5755.7, "total_tokens": 12148496} {"current_steps": 18445, "total_steps": 33920, "loss": 0.4905, "lr": 5.109074425172806e-06, "epoch": 10.87558962264151, "percentage": 54.38, "elapsed_time": "0:35:11", "remaining_time": "0:29:31", "throughput": 5755.68, "total_tokens": 12151216} {"current_steps": 18450, "total_steps": 33920, "loss": 0.4005, "lr": 5.106502308973967e-06, "epoch": 10.878537735849056, "percentage": 54.39, "elapsed_time": "0:35:11", "remaining_time": "0:29:30", "throughput": 5755.62, "total_tokens": 12153840} {"current_steps": 18455, "total_steps": 33920, "loss": 0.3567, "lr": 5.103930164578184e-06, "epoch": 10.881485849056604, "percentage": 54.41, "elapsed_time": "0:35:12", "remaining_time": "0:29:30", "throughput": 5755.86, "total_tokens": 12158192} {"current_steps": 18460, "total_steps": 33920, "loss": 0.2688, "lr": 5.101357992666441e-06, "epoch": 10.88443396226415, "percentage": 54.42, "elapsed_time": "0:35:12", "remaining_time": "0:29:29", "throughput": 5755.94, "total_tokens": 12161328} {"current_steps": 18465, "total_steps": 33920, "loss": 0.3491, "lr": 5.098785793919733e-06, "epoch": 10.887382075471699, "percentage": 54.44, "elapsed_time": "0:35:13", "remaining_time": "0:29:28", "throughput": 5755.85, "total_tokens": 12164560} {"current_steps": 18470, "total_steps": 33920, "loss": 0.4664, "lr": 5.096213569019061e-06, "epoch": 10.890330188679245, "percentage": 54.45, "elapsed_time": "0:35:13", "remaining_time": "0:29:28", "throughput": 5755.56, "total_tokens": 12166800} {"current_steps": 18475, "total_steps": 33920, "loss": 0.358, "lr": 5.0936413186454315e-06, "epoch": 10.893278301886792, "percentage": 54.47, "elapsed_time": "0:35:14", "remaining_time": "0:29:27", "throughput": 5755.3, "total_tokens": 12169232} {"current_steps": 18480, "total_steps": 33920, "loss": 0.3205, "lr": 5.0910690434798584e-06, "epoch": 10.89622641509434, "percentage": 54.48, "elapsed_time": "0:35:14", "remaining_time": "0:29:27", "throughput": 5755.33, "total_tokens": 12172496} {"current_steps": 18485, "total_steps": 33920, "loss": 0.4342, "lr": 5.088496744203364e-06, "epoch": 10.899174528301886, "percentage": 54.5, "elapsed_time": "0:35:15", "remaining_time": "0:29:26", "throughput": 5755.17, "total_tokens": 12175216} {"current_steps": 18490, "total_steps": 33920, "loss": 0.354, "lr": 5.085924421496976e-06, "epoch": 10.902122641509434, "percentage": 54.51, "elapsed_time": "0:35:16", "remaining_time": "0:29:26", "throughput": 5755.56, "total_tokens": 12181552} {"current_steps": 18495, "total_steps": 33920, "loss": 0.3358, "lr": 5.083352076041725e-06, "epoch": 10.90507075471698, "percentage": 54.53, "elapsed_time": "0:35:17", "remaining_time": "0:29:25", "throughput": 5755.93, "total_tokens": 12187632} {"current_steps": 18500, "total_steps": 33920, "loss": 0.3678, "lr": 5.080779708518654e-06, "epoch": 10.908018867924529, "percentage": 54.54, "elapsed_time": "0:35:17", "remaining_time": "0:29:25", "throughput": 5755.72, "total_tokens": 12189904} {"current_steps": 18505, "total_steps": 33920, "loss": 0.4194, "lr": 5.078207319608807e-06, "epoch": 10.910966981132075, "percentage": 54.55, "elapsed_time": "0:35:18", "remaining_time": "0:29:24", "throughput": 5755.97, "total_tokens": 12193904} {"current_steps": 18510, "total_steps": 33920, "loss": 0.377, "lr": 5.075634909993235e-06, "epoch": 10.913915094339622, "percentage": 54.57, "elapsed_time": "0:35:19", "remaining_time": "0:29:24", "throughput": 5756.01, "total_tokens": 12197264} {"current_steps": 18515, "total_steps": 33920, "loss": 0.3608, "lr": 5.073062480352995e-06, "epoch": 10.91686320754717, "percentage": 54.58, "elapsed_time": "0:35:19", "remaining_time": "0:29:23", "throughput": 5755.83, "total_tokens": 12199856} {"current_steps": 18520, "total_steps": 33920, "loss": 0.2692, "lr": 5.070490031369149e-06, "epoch": 10.919811320754716, "percentage": 54.6, "elapsed_time": "0:35:20", "remaining_time": "0:29:23", "throughput": 5756.13, "total_tokens": 12204496} {"current_steps": 18525, "total_steps": 33920, "loss": 0.3354, "lr": 5.067917563722762e-06, "epoch": 10.922759433962264, "percentage": 54.61, "elapsed_time": "0:35:20", "remaining_time": "0:29:22", "throughput": 5755.99, "total_tokens": 12207184} {"current_steps": 18530, "total_steps": 33920, "loss": 0.3568, "lr": 5.065345078094907e-06, "epoch": 10.92570754716981, "percentage": 54.63, "elapsed_time": "0:35:21", "remaining_time": "0:29:21", "throughput": 5755.93, "total_tokens": 12210576} {"current_steps": 18535, "total_steps": 33920, "loss": 0.3528, "lr": 5.062772575166663e-06, "epoch": 10.928655660377359, "percentage": 54.64, "elapsed_time": "0:35:21", "remaining_time": "0:29:21", "throughput": 5755.93, "total_tokens": 12213552} {"current_steps": 18540, "total_steps": 33920, "loss": 0.4683, "lr": 5.0602000556191075e-06, "epoch": 10.931603773584905, "percentage": 54.66, "elapsed_time": "0:35:22", "remaining_time": "0:29:20", "throughput": 5755.72, "total_tokens": 12216208} {"current_steps": 18545, "total_steps": 33920, "loss": 0.3367, "lr": 5.0576275201333284e-06, "epoch": 10.934551886792454, "percentage": 54.67, "elapsed_time": "0:35:23", "remaining_time": "0:29:20", "throughput": 5755.7, "total_tokens": 12220016} {"current_steps": 18550, "total_steps": 33920, "loss": 0.3848, "lr": 5.055054969390415e-06, "epoch": 10.9375, "percentage": 54.69, "elapsed_time": "0:35:23", "remaining_time": "0:29:19", "throughput": 5755.84, "total_tokens": 12223408} {"current_steps": 18555, "total_steps": 33920, "loss": 0.3385, "lr": 5.052482404071461e-06, "epoch": 10.940448113207546, "percentage": 54.7, "elapsed_time": "0:35:24", "remaining_time": "0:29:18", "throughput": 5755.52, "total_tokens": 12225712} {"current_steps": 18560, "total_steps": 33920, "loss": 0.3845, "lr": 5.049909824857564e-06, "epoch": 10.943396226415095, "percentage": 54.72, "elapsed_time": "0:35:24", "remaining_time": "0:29:18", "throughput": 5755.79, "total_tokens": 12229744} {"current_steps": 18565, "total_steps": 33920, "loss": 0.3439, "lr": 5.047337232429827e-06, "epoch": 10.946344339622641, "percentage": 54.73, "elapsed_time": "0:35:25", "remaining_time": "0:29:17", "throughput": 5755.79, "total_tokens": 12232432} {"current_steps": 18570, "total_steps": 33920, "loss": 0.4077, "lr": 5.044764627469354e-06, "epoch": 10.94929245283019, "percentage": 54.75, "elapsed_time": "0:35:25", "remaining_time": "0:29:17", "throughput": 5755.81, "total_tokens": 12235248} {"current_steps": 18575, "total_steps": 33920, "loss": 0.3595, "lr": 5.042192010657251e-06, "epoch": 10.952240566037736, "percentage": 54.76, "elapsed_time": "0:35:26", "remaining_time": "0:29:16", "throughput": 5755.82, "total_tokens": 12238160} {"current_steps": 18580, "total_steps": 33920, "loss": 0.2975, "lr": 5.039619382674632e-06, "epoch": 10.955188679245284, "percentage": 54.78, "elapsed_time": "0:35:26", "remaining_time": "0:29:15", "throughput": 5755.88, "total_tokens": 12242000} {"current_steps": 18585, "total_steps": 33920, "loss": 0.4315, "lr": 5.0370467442026115e-06, "epoch": 10.95813679245283, "percentage": 54.79, "elapsed_time": "0:35:27", "remaining_time": "0:29:15", "throughput": 5755.83, "total_tokens": 12244720} {"current_steps": 18590, "total_steps": 33920, "loss": 0.391, "lr": 5.034474095922304e-06, "epoch": 10.961084905660378, "percentage": 54.81, "elapsed_time": "0:35:27", "remaining_time": "0:29:14", "throughput": 5755.72, "total_tokens": 12247344} {"current_steps": 18595, "total_steps": 33920, "loss": 0.3118, "lr": 5.031901438514832e-06, "epoch": 10.964033018867925, "percentage": 54.82, "elapsed_time": "0:35:28", "remaining_time": "0:29:14", "throughput": 5755.88, "total_tokens": 12250928} {"current_steps": 18600, "total_steps": 33920, "loss": 0.3918, "lr": 5.0293287726613185e-06, "epoch": 10.966981132075471, "percentage": 54.83, "elapsed_time": "0:35:28", "remaining_time": "0:29:13", "throughput": 5755.88, "total_tokens": 12253808} {"current_steps": 18605, "total_steps": 33920, "loss": 0.2938, "lr": 5.0267560990428836e-06, "epoch": 10.96992924528302, "percentage": 54.85, "elapsed_time": "0:35:29", "remaining_time": "0:29:12", "throughput": 5755.99, "total_tokens": 12257296} {"current_steps": 18610, "total_steps": 33920, "loss": 0.4132, "lr": 5.024183418340657e-06, "epoch": 10.972877358490566, "percentage": 54.86, "elapsed_time": "0:35:30", "remaining_time": "0:29:12", "throughput": 5756.03, "total_tokens": 12260560} {"current_steps": 18615, "total_steps": 33920, "loss": 0.3085, "lr": 5.021610731235766e-06, "epoch": 10.975825471698114, "percentage": 54.88, "elapsed_time": "0:35:30", "remaining_time": "0:29:11", "throughput": 5755.73, "total_tokens": 12262608} {"current_steps": 18620, "total_steps": 33920, "loss": 0.3083, "lr": 5.01903803840934e-06, "epoch": 10.97877358490566, "percentage": 54.89, "elapsed_time": "0:35:31", "remaining_time": "0:29:11", "throughput": 5755.81, "total_tokens": 12265744} {"current_steps": 18625, "total_steps": 33920, "loss": 0.3335, "lr": 5.016465340542514e-06, "epoch": 10.981721698113208, "percentage": 54.91, "elapsed_time": "0:35:31", "remaining_time": "0:29:10", "throughput": 5755.98, "total_tokens": 12269424} {"current_steps": 18630, "total_steps": 33920, "loss": 0.5115, "lr": 5.013892638316417e-06, "epoch": 10.984669811320755, "percentage": 54.92, "elapsed_time": "0:35:32", "remaining_time": "0:29:09", "throughput": 5755.93, "total_tokens": 12272016} {"current_steps": 18635, "total_steps": 33920, "loss": 0.3576, "lr": 5.011319932412182e-06, "epoch": 10.987617924528301, "percentage": 54.94, "elapsed_time": "0:35:32", "remaining_time": "0:29:09", "throughput": 5755.98, "total_tokens": 12275152} {"current_steps": 18640, "total_steps": 33920, "loss": 0.4238, "lr": 5.008747223510947e-06, "epoch": 10.99056603773585, "percentage": 54.95, "elapsed_time": "0:35:33", "remaining_time": "0:29:08", "throughput": 5756.17, "total_tokens": 12278576} {"current_steps": 18645, "total_steps": 33920, "loss": 0.5779, "lr": 5.006174512293849e-06, "epoch": 10.993514150943396, "percentage": 54.97, "elapsed_time": "0:35:33", "remaining_time": "0:29:08", "throughput": 5756.29, "total_tokens": 12282000} {"current_steps": 18650, "total_steps": 33920, "loss": 0.5393, "lr": 5.003601799442019e-06, "epoch": 10.996462264150944, "percentage": 54.98, "elapsed_time": "0:35:34", "remaining_time": "0:29:07", "throughput": 5756.43, "total_tokens": 12285712} {"current_steps": 18655, "total_steps": 33920, "loss": 0.235, "lr": 5.0010290856366e-06, "epoch": 10.99941037735849, "percentage": 55.0, "elapsed_time": "0:35:34", "remaining_time": "0:29:06", "throughput": 5756.4, "total_tokens": 12288784} {"current_steps": 18660, "total_steps": 33920, "loss": 0.4223, "lr": 4.998456371558726e-06, "epoch": 11.002358490566039, "percentage": 55.01, "elapsed_time": "0:35:35", "remaining_time": "0:29:06", "throughput": 5755.66, "total_tokens": 12292104} {"current_steps": 18665, "total_steps": 33920, "loss": 0.383, "lr": 4.995883657889531e-06, "epoch": 11.005306603773585, "percentage": 55.03, "elapsed_time": "0:35:36", "remaining_time": "0:29:05", "throughput": 5755.75, "total_tokens": 12295528} {"current_steps": 18670, "total_steps": 33920, "loss": 0.325, "lr": 4.993310945310158e-06, "epoch": 11.008254716981131, "percentage": 55.04, "elapsed_time": "0:35:36", "remaining_time": "0:29:05", "throughput": 5755.79, "total_tokens": 12298824} {"current_steps": 18675, "total_steps": 33920, "loss": 0.3799, "lr": 4.9907382345017416e-06, "epoch": 11.01120283018868, "percentage": 55.06, "elapsed_time": "0:35:37", "remaining_time": "0:29:04", "throughput": 5756.06, "total_tokens": 12303240} {"current_steps": 18680, "total_steps": 33920, "loss": 0.362, "lr": 4.988165526145416e-06, "epoch": 11.014150943396226, "percentage": 55.07, "elapsed_time": "0:35:38", "remaining_time": "0:29:04", "throughput": 5756.44, "total_tokens": 12308104} {"current_steps": 18685, "total_steps": 33920, "loss": 0.3713, "lr": 4.985592820922319e-06, "epoch": 11.017099056603774, "percentage": 55.09, "elapsed_time": "0:35:38", "remaining_time": "0:29:03", "throughput": 5756.48, "total_tokens": 12311272} {"current_steps": 18690, "total_steps": 33920, "loss": 0.3629, "lr": 4.983020119513586e-06, "epoch": 11.02004716981132, "percentage": 55.1, "elapsed_time": "0:35:39", "remaining_time": "0:29:03", "throughput": 5756.34, "total_tokens": 12314024} {"current_steps": 18695, "total_steps": 33920, "loss": 0.4353, "lr": 4.9804474226003465e-06, "epoch": 11.022995283018869, "percentage": 55.11, "elapsed_time": "0:35:39", "remaining_time": "0:29:02", "throughput": 5756.44, "total_tokens": 12317128} {"current_steps": 18700, "total_steps": 33920, "loss": 0.295, "lr": 4.977874730863739e-06, "epoch": 11.025943396226415, "percentage": 55.13, "elapsed_time": "0:35:40", "remaining_time": "0:29:02", "throughput": 5756.62, "total_tokens": 12322600} {"current_steps": 18705, "total_steps": 33920, "loss": 0.3279, "lr": 4.975302044984889e-06, "epoch": 11.028891509433961, "percentage": 55.14, "elapsed_time": "0:35:41", "remaining_time": "0:29:01", "throughput": 5756.61, "total_tokens": 12325416} {"current_steps": 18710, "total_steps": 33920, "loss": 0.2791, "lr": 4.972729365644931e-06, "epoch": 11.03183962264151, "percentage": 55.16, "elapsed_time": "0:35:41", "remaining_time": "0:29:00", "throughput": 5756.58, "total_tokens": 12328168} {"current_steps": 18715, "total_steps": 33920, "loss": 0.4902, "lr": 4.97015669352499e-06, "epoch": 11.034787735849056, "percentage": 55.17, "elapsed_time": "0:35:42", "remaining_time": "0:29:00", "throughput": 5756.49, "total_tokens": 12330760} {"current_steps": 18720, "total_steps": 33920, "loss": 0.4364, "lr": 4.967584029306194e-06, "epoch": 11.037735849056604, "percentage": 55.19, "elapsed_time": "0:35:42", "remaining_time": "0:28:59", "throughput": 5756.6, "total_tokens": 12333768} {"current_steps": 18725, "total_steps": 33920, "loss": 0.3335, "lr": 4.965011373669666e-06, "epoch": 11.04068396226415, "percentage": 55.2, "elapsed_time": "0:35:43", "remaining_time": "0:28:59", "throughput": 5756.59, "total_tokens": 12336744} {"current_steps": 18730, "total_steps": 33920, "loss": 0.3831, "lr": 4.962438727296527e-06, "epoch": 11.043632075471699, "percentage": 55.22, "elapsed_time": "0:35:43", "remaining_time": "0:28:58", "throughput": 5756.88, "total_tokens": 12340872} {"current_steps": 18735, "total_steps": 33920, "loss": 0.2469, "lr": 4.959866090867897e-06, "epoch": 11.046580188679245, "percentage": 55.23, "elapsed_time": "0:35:44", "remaining_time": "0:28:58", "throughput": 5757.21, "total_tokens": 12346216} {"current_steps": 18740, "total_steps": 33920, "loss": 0.3019, "lr": 4.957293465064893e-06, "epoch": 11.049528301886792, "percentage": 55.25, "elapsed_time": "0:35:44", "remaining_time": "0:28:57", "throughput": 5757.19, "total_tokens": 12348936} {"current_steps": 18745, "total_steps": 33920, "loss": 0.3157, "lr": 4.954720850568627e-06, "epoch": 11.05247641509434, "percentage": 55.26, "elapsed_time": "0:35:45", "remaining_time": "0:28:56", "throughput": 5757.22, "total_tokens": 12351816} {"current_steps": 18750, "total_steps": 33920, "loss": 0.3397, "lr": 4.952148248060212e-06, "epoch": 11.055424528301886, "percentage": 55.28, "elapsed_time": "0:35:45", "remaining_time": "0:28:56", "throughput": 5757.24, "total_tokens": 12354952} {"current_steps": 18755, "total_steps": 33920, "loss": 0.4522, "lr": 4.949575658220755e-06, "epoch": 11.058372641509434, "percentage": 55.29, "elapsed_time": "0:35:46", "remaining_time": "0:28:55", "throughput": 5757.23, "total_tokens": 12357704} {"current_steps": 18760, "total_steps": 33920, "loss": 0.3697, "lr": 4.947003081731359e-06, "epoch": 11.06132075471698, "percentage": 55.31, "elapsed_time": "0:35:47", "remaining_time": "0:28:55", "throughput": 5757.39, "total_tokens": 12361608} {"current_steps": 18765, "total_steps": 33920, "loss": 0.4852, "lr": 4.944430519273126e-06, "epoch": 11.064268867924529, "percentage": 55.32, "elapsed_time": "0:35:47", "remaining_time": "0:28:54", "throughput": 5757.46, "total_tokens": 12364744} {"current_steps": 18770, "total_steps": 33920, "loss": 0.3393, "lr": 4.941857971527152e-06, "epoch": 11.067216981132075, "percentage": 55.34, "elapsed_time": "0:35:48", "remaining_time": "0:28:53", "throughput": 5757.59, "total_tokens": 12368360} {"current_steps": 18775, "total_steps": 33920, "loss": 0.3092, "lr": 4.93928543917453e-06, "epoch": 11.070165094339623, "percentage": 55.35, "elapsed_time": "0:35:48", "remaining_time": "0:28:53", "throughput": 5757.7, "total_tokens": 12371720} {"current_steps": 18780, "total_steps": 33920, "loss": 0.2634, "lr": 4.93671292289635e-06, "epoch": 11.07311320754717, "percentage": 55.37, "elapsed_time": "0:35:49", "remaining_time": "0:28:52", "throughput": 5757.95, "total_tokens": 12375688} {"current_steps": 18785, "total_steps": 33920, "loss": 0.4472, "lr": 4.934140423373698e-06, "epoch": 11.076061320754716, "percentage": 55.38, "elapsed_time": "0:35:49", "remaining_time": "0:28:52", "throughput": 5757.99, "total_tokens": 12378792} {"current_steps": 18790, "total_steps": 33920, "loss": 0.4514, "lr": 4.931567941287651e-06, "epoch": 11.079009433962264, "percentage": 55.4, "elapsed_time": "0:35:50", "remaining_time": "0:28:51", "throughput": 5757.97, "total_tokens": 12381736} {"current_steps": 18795, "total_steps": 33920, "loss": 0.3914, "lr": 4.9289954773192875e-06, "epoch": 11.08195754716981, "percentage": 55.41, "elapsed_time": "0:35:50", "remaining_time": "0:28:50", "throughput": 5757.97, "total_tokens": 12384616} {"current_steps": 18800, "total_steps": 33920, "loss": 0.2951, "lr": 4.926423032149677e-06, "epoch": 11.084905660377359, "percentage": 55.42, "elapsed_time": "0:35:51", "remaining_time": "0:28:50", "throughput": 5758.21, "total_tokens": 12388488} {"current_steps": 18805, "total_steps": 33920, "loss": 0.3231, "lr": 4.923850606459883e-06, "epoch": 11.087853773584905, "percentage": 55.44, "elapsed_time": "0:35:52", "remaining_time": "0:28:49", "throughput": 5758.45, "total_tokens": 12392520} {"current_steps": 18810, "total_steps": 33920, "loss": 0.3048, "lr": 4.921278200930972e-06, "epoch": 11.090801886792454, "percentage": 55.45, "elapsed_time": "0:35:52", "remaining_time": "0:28:49", "throughput": 5758.66, "total_tokens": 12396360} {"current_steps": 18815, "total_steps": 33920, "loss": 0.4316, "lr": 4.918705816243996e-06, "epoch": 11.09375, "percentage": 55.47, "elapsed_time": "0:35:53", "remaining_time": "0:28:48", "throughput": 5758.63, "total_tokens": 12399336} {"current_steps": 18820, "total_steps": 33920, "loss": 0.306, "lr": 4.916133453080007e-06, "epoch": 11.096698113207546, "percentage": 55.48, "elapsed_time": "0:35:53", "remaining_time": "0:28:48", "throughput": 5758.81, "total_tokens": 12402856} {"current_steps": 18825, "total_steps": 33920, "loss": 0.3136, "lr": 4.913561112120046e-06, "epoch": 11.099646226415095, "percentage": 55.5, "elapsed_time": "0:35:54", "remaining_time": "0:28:47", "throughput": 5759.15, "total_tokens": 12407880} {"current_steps": 18830, "total_steps": 33920, "loss": 0.3111, "lr": 4.910988794045154e-06, "epoch": 11.102594339622641, "percentage": 55.51, "elapsed_time": "0:35:54", "remaining_time": "0:28:46", "throughput": 5758.9, "total_tokens": 12410280} {"current_steps": 18835, "total_steps": 33920, "loss": 0.351, "lr": 4.9084164995363626e-06, "epoch": 11.10554245283019, "percentage": 55.53, "elapsed_time": "0:35:55", "remaining_time": "0:28:46", "throughput": 5758.96, "total_tokens": 12413384} {"current_steps": 18840, "total_steps": 33920, "loss": 0.3218, "lr": 4.905844229274697e-06, "epoch": 11.108490566037736, "percentage": 55.54, "elapsed_time": "0:35:56", "remaining_time": "0:28:45", "throughput": 5759.14, "total_tokens": 12417416} {"current_steps": 18845, "total_steps": 33920, "loss": 0.4754, "lr": 4.903271983941177e-06, "epoch": 11.111438679245284, "percentage": 55.56, "elapsed_time": "0:35:56", "remaining_time": "0:28:45", "throughput": 5758.94, "total_tokens": 12419688} {"current_steps": 18850, "total_steps": 33920, "loss": 0.3705, "lr": 4.900699764216818e-06, "epoch": 11.11438679245283, "percentage": 55.57, "elapsed_time": "0:35:57", "remaining_time": "0:28:44", "throughput": 5758.89, "total_tokens": 12422920} {"current_steps": 18855, "total_steps": 33920, "loss": 0.2807, "lr": 4.898127570782622e-06, "epoch": 11.117334905660377, "percentage": 55.59, "elapsed_time": "0:35:57", "remaining_time": "0:28:43", "throughput": 5759.07, "total_tokens": 12426408} {"current_steps": 18860, "total_steps": 33920, "loss": 0.413, "lr": 4.895555404319592e-06, "epoch": 11.120283018867925, "percentage": 55.6, "elapsed_time": "0:35:58", "remaining_time": "0:28:43", "throughput": 5759.36, "total_tokens": 12430472} {"current_steps": 18865, "total_steps": 33920, "loss": 0.3242, "lr": 4.89298326550872e-06, "epoch": 11.123231132075471, "percentage": 55.62, "elapsed_time": "0:35:58", "remaining_time": "0:28:42", "throughput": 5759.44, "total_tokens": 12433576} {"current_steps": 18870, "total_steps": 33920, "loss": 0.4144, "lr": 4.8904111550309876e-06, "epoch": 11.12617924528302, "percentage": 55.63, "elapsed_time": "0:35:59", "remaining_time": "0:28:42", "throughput": 5759.48, "total_tokens": 12436552} {"current_steps": 18875, "total_steps": 33920, "loss": 0.2364, "lr": 4.8878390735673755e-06, "epoch": 11.129127358490566, "percentage": 55.65, "elapsed_time": "0:35:59", "remaining_time": "0:28:41", "throughput": 5759.56, "total_tokens": 12439752} {"current_steps": 18880, "total_steps": 33920, "loss": 0.3318, "lr": 4.8852670217988505e-06, "epoch": 11.132075471698114, "percentage": 55.66, "elapsed_time": "0:36:00", "remaining_time": "0:28:40", "throughput": 5759.63, "total_tokens": 12443048} {"current_steps": 18885, "total_steps": 33920, "loss": 0.4253, "lr": 4.882695000406377e-06, "epoch": 11.13502358490566, "percentage": 55.68, "elapsed_time": "0:36:00", "remaining_time": "0:28:40", "throughput": 5759.8, "total_tokens": 12446376} {"current_steps": 18890, "total_steps": 33920, "loss": 0.3583, "lr": 4.880123010070909e-06, "epoch": 11.137971698113208, "percentage": 55.69, "elapsed_time": "0:36:01", "remaining_time": "0:28:39", "throughput": 5759.85, "total_tokens": 12449416} {"current_steps": 18895, "total_steps": 33920, "loss": 0.3632, "lr": 4.877551051473388e-06, "epoch": 11.140919811320755, "percentage": 55.7, "elapsed_time": "0:36:01", "remaining_time": "0:28:39", "throughput": 5760.06, "total_tokens": 12453000} {"current_steps": 18900, "total_steps": 33920, "loss": 0.319, "lr": 4.874979125294755e-06, "epoch": 11.143867924528301, "percentage": 55.72, "elapsed_time": "0:36:02", "remaining_time": "0:28:38", "throughput": 5760.24, "total_tokens": 12456808} {"current_steps": 18905, "total_steps": 33920, "loss": 0.3529, "lr": 4.872407232215937e-06, "epoch": 11.14681603773585, "percentage": 55.73, "elapsed_time": "0:36:03", "remaining_time": "0:28:37", "throughput": 5760.26, "total_tokens": 12459720} {"current_steps": 18910, "total_steps": 33920, "loss": 0.4736, "lr": 4.8698353729178546e-06, "epoch": 11.149764150943396, "percentage": 55.75, "elapsed_time": "0:36:03", "remaining_time": "0:28:37", "throughput": 5760.25, "total_tokens": 12462568} {"current_steps": 18915, "total_steps": 33920, "loss": 0.3913, "lr": 4.867263548081418e-06, "epoch": 11.152712264150944, "percentage": 55.76, "elapsed_time": "0:36:04", "remaining_time": "0:28:36", "throughput": 5760.36, "total_tokens": 12465672} {"current_steps": 18920, "total_steps": 33920, "loss": 0.4973, "lr": 4.8646917583875304e-06, "epoch": 11.15566037735849, "percentage": 55.78, "elapsed_time": "0:36:04", "remaining_time": "0:28:36", "throughput": 5760.47, "total_tokens": 12469288} {"current_steps": 18925, "total_steps": 33920, "loss": 0.4051, "lr": 4.862120004517082e-06, "epoch": 11.158608490566039, "percentage": 55.79, "elapsed_time": "0:36:05", "remaining_time": "0:28:35", "throughput": 5760.7, "total_tokens": 12473032} {"current_steps": 18930, "total_steps": 33920, "loss": 0.4199, "lr": 4.859548287150956e-06, "epoch": 11.161556603773585, "percentage": 55.81, "elapsed_time": "0:36:05", "remaining_time": "0:28:34", "throughput": 5760.5, "total_tokens": 12475304} {"current_steps": 18935, "total_steps": 33920, "loss": 0.2452, "lr": 4.8569766069700275e-06, "epoch": 11.164504716981131, "percentage": 55.82, "elapsed_time": "0:36:06", "remaining_time": "0:28:34", "throughput": 5760.32, "total_tokens": 12477992} {"current_steps": 18940, "total_steps": 33920, "loss": 0.2697, "lr": 4.854404964655158e-06, "epoch": 11.16745283018868, "percentage": 55.84, "elapsed_time": "0:36:06", "remaining_time": "0:28:33", "throughput": 5760.33, "total_tokens": 12481384} {"current_steps": 18945, "total_steps": 33920, "loss": 0.4373, "lr": 4.8518333608872015e-06, "epoch": 11.170400943396226, "percentage": 55.85, "elapsed_time": "0:36:07", "remaining_time": "0:28:33", "throughput": 5760.16, "total_tokens": 12483848} {"current_steps": 18950, "total_steps": 33920, "loss": 0.2967, "lr": 4.849261796347002e-06, "epoch": 11.173349056603774, "percentage": 55.87, "elapsed_time": "0:36:07", "remaining_time": "0:28:32", "throughput": 5760.31, "total_tokens": 12487208} {"current_steps": 18955, "total_steps": 33920, "loss": 0.3472, "lr": 4.846690271715391e-06, "epoch": 11.17629716981132, "percentage": 55.88, "elapsed_time": "0:36:08", "remaining_time": "0:28:31", "throughput": 5760.31, "total_tokens": 12489928} {"current_steps": 18960, "total_steps": 33920, "loss": 0.4645, "lr": 4.844118787673191e-06, "epoch": 11.179245283018869, "percentage": 55.9, "elapsed_time": "0:36:08", "remaining_time": "0:28:31", "throughput": 5760.37, "total_tokens": 12493000} {"current_steps": 18965, "total_steps": 33920, "loss": 0.5068, "lr": 4.841547344901214e-06, "epoch": 11.182193396226415, "percentage": 55.91, "elapsed_time": "0:36:09", "remaining_time": "0:28:30", "throughput": 5760.35, "total_tokens": 12495816} {"current_steps": 18970, "total_steps": 33920, "loss": 0.3168, "lr": 4.838975944080261e-06, "epoch": 11.185141509433961, "percentage": 55.93, "elapsed_time": "0:36:09", "remaining_time": "0:28:30", "throughput": 5760.56, "total_tokens": 12499656} {"current_steps": 18975, "total_steps": 33920, "loss": 0.2596, "lr": 4.83640458589112e-06, "epoch": 11.18808962264151, "percentage": 55.94, "elapsed_time": "0:36:10", "remaining_time": "0:28:29", "throughput": 5760.73, "total_tokens": 12503688} {"current_steps": 18980, "total_steps": 33920, "loss": 0.4329, "lr": 4.833833271014571e-06, "epoch": 11.191037735849056, "percentage": 55.96, "elapsed_time": "0:36:10", "remaining_time": "0:28:28", "throughput": 5760.49, "total_tokens": 12505992} {"current_steps": 18985, "total_steps": 33920, "loss": 0.3256, "lr": 4.831262000131379e-06, "epoch": 11.193985849056604, "percentage": 55.97, "elapsed_time": "0:36:11", "remaining_time": "0:28:28", "throughput": 5760.73, "total_tokens": 12509544} {"current_steps": 18990, "total_steps": 33920, "loss": 0.3073, "lr": 4.828690773922299e-06, "epoch": 11.19693396226415, "percentage": 55.98, "elapsed_time": "0:36:12", "remaining_time": "0:28:27", "throughput": 5760.75, "total_tokens": 12512744} {"current_steps": 18995, "total_steps": 33920, "loss": 0.4185, "lr": 4.826119593068074e-06, "epoch": 11.199882075471699, "percentage": 56.0, "elapsed_time": "0:36:13", "remaining_time": "0:28:27", "throughput": 5761.06, "total_tokens": 12518856} {"current_steps": 19000, "total_steps": 33920, "loss": 0.3045, "lr": 4.8235484582494375e-06, "epoch": 11.202830188679245, "percentage": 56.01, "elapsed_time": "0:36:13", "remaining_time": "0:28:26", "throughput": 5761.17, "total_tokens": 12522120} {"current_steps": 19005, "total_steps": 33920, "loss": 0.3038, "lr": 4.8209773701471076e-06, "epoch": 11.205778301886792, "percentage": 56.03, "elapsed_time": "0:36:14", "remaining_time": "0:28:26", "throughput": 5761.45, "total_tokens": 12526056} {"current_steps": 19010, "total_steps": 33920, "loss": 0.4454, "lr": 4.818406329441789e-06, "epoch": 11.20872641509434, "percentage": 56.04, "elapsed_time": "0:36:14", "remaining_time": "0:28:25", "throughput": 5761.45, "total_tokens": 12528872} {"current_steps": 19015, "total_steps": 33920, "loss": 0.3581, "lr": 4.815835336814179e-06, "epoch": 11.211674528301886, "percentage": 56.06, "elapsed_time": "0:36:15", "remaining_time": "0:28:24", "throughput": 5761.5, "total_tokens": 12531816} {"current_steps": 19020, "total_steps": 33920, "loss": 0.3738, "lr": 4.813264392944957e-06, "epoch": 11.214622641509434, "percentage": 56.07, "elapsed_time": "0:36:15", "remaining_time": "0:28:24", "throughput": 5761.34, "total_tokens": 12534280} {"current_steps": 19025, "total_steps": 33920, "loss": 0.3362, "lr": 4.8106934985147905e-06, "epoch": 11.21757075471698, "percentage": 56.09, "elapsed_time": "0:36:16", "remaining_time": "0:28:23", "throughput": 5761.5, "total_tokens": 12537672} {"current_steps": 19030, "total_steps": 33920, "loss": 0.3173, "lr": 4.808122654204338e-06, "epoch": 11.220518867924529, "percentage": 56.1, "elapsed_time": "0:36:16", "remaining_time": "0:28:23", "throughput": 5761.66, "total_tokens": 12540936} {"current_steps": 19035, "total_steps": 33920, "loss": 0.3173, "lr": 4.805551860694239e-06, "epoch": 11.223466981132075, "percentage": 56.12, "elapsed_time": "0:36:17", "remaining_time": "0:28:22", "throughput": 5761.78, "total_tokens": 12544104} {"current_steps": 19040, "total_steps": 33920, "loss": 0.3687, "lr": 4.802981118665122e-06, "epoch": 11.226415094339623, "percentage": 56.13, "elapsed_time": "0:36:17", "remaining_time": "0:28:21", "throughput": 5761.56, "total_tokens": 12546344} {"current_steps": 19045, "total_steps": 33920, "loss": 0.3838, "lr": 4.800410428797604e-06, "epoch": 11.22936320754717, "percentage": 56.15, "elapsed_time": "0:36:18", "remaining_time": "0:28:21", "throughput": 5761.74, "total_tokens": 12549992} {"current_steps": 19050, "total_steps": 33920, "loss": 0.3666, "lr": 4.797839791772286e-06, "epoch": 11.232311320754716, "percentage": 56.16, "elapsed_time": "0:36:18", "remaining_time": "0:28:20", "throughput": 5761.87, "total_tokens": 12553384} {"current_steps": 19055, "total_steps": 33920, "loss": 0.2759, "lr": 4.795269208269752e-06, "epoch": 11.235259433962264, "percentage": 56.18, "elapsed_time": "0:36:19", "remaining_time": "0:28:19", "throughput": 5761.82, "total_tokens": 12555976} {"current_steps": 19060, "total_steps": 33920, "loss": 0.2561, "lr": 4.792698678970579e-06, "epoch": 11.23820754716981, "percentage": 56.19, "elapsed_time": "0:36:19", "remaining_time": "0:28:19", "throughput": 5761.79, "total_tokens": 12558824} {"current_steps": 19065, "total_steps": 33920, "loss": 0.4508, "lr": 4.7901282045553245e-06, "epoch": 11.241155660377359, "percentage": 56.21, "elapsed_time": "0:36:20", "remaining_time": "0:28:18", "throughput": 5761.83, "total_tokens": 12561800} {"current_steps": 19070, "total_steps": 33920, "loss": 0.4146, "lr": 4.787557785704531e-06, "epoch": 11.244103773584905, "percentage": 56.22, "elapsed_time": "0:36:20", "remaining_time": "0:28:18", "throughput": 5761.74, "total_tokens": 12564328} {"current_steps": 19075, "total_steps": 33920, "loss": 0.4684, "lr": 4.784987423098731e-06, "epoch": 11.247051886792454, "percentage": 56.24, "elapsed_time": "0:36:21", "remaining_time": "0:28:17", "throughput": 5761.82, "total_tokens": 12567400} {"current_steps": 19080, "total_steps": 33920, "loss": 0.3197, "lr": 4.7824171174184354e-06, "epoch": 11.25, "percentage": 56.25, "elapsed_time": "0:36:21", "remaining_time": "0:28:16", "throughput": 5761.93, "total_tokens": 12570792} {"current_steps": 19085, "total_steps": 33920, "loss": 0.2138, "lr": 4.779846869344146e-06, "epoch": 11.252948113207546, "percentage": 56.26, "elapsed_time": "0:36:22", "remaining_time": "0:28:16", "throughput": 5761.98, "total_tokens": 12574184} {"current_steps": 19090, "total_steps": 33920, "loss": 0.4442, "lr": 4.777276679556346e-06, "epoch": 11.255896226415095, "percentage": 56.28, "elapsed_time": "0:36:22", "remaining_time": "0:28:15", "throughput": 5762.13, "total_tokens": 12578376} {"current_steps": 19095, "total_steps": 33920, "loss": 0.3126, "lr": 4.774706548735507e-06, "epoch": 11.258844339622641, "percentage": 56.29, "elapsed_time": "0:36:23", "remaining_time": "0:28:15", "throughput": 5762.15, "total_tokens": 12581256} {"current_steps": 19100, "total_steps": 33920, "loss": 0.2921, "lr": 4.77213647756208e-06, "epoch": 11.26179245283019, "percentage": 56.31, "elapsed_time": "0:36:23", "remaining_time": "0:28:14", "throughput": 5762.35, "total_tokens": 12584936} {"current_steps": 19105, "total_steps": 33920, "loss": 0.2399, "lr": 4.769566466716501e-06, "epoch": 11.264740566037736, "percentage": 56.32, "elapsed_time": "0:36:24", "remaining_time": "0:28:14", "throughput": 5762.25, "total_tokens": 12587944} {"current_steps": 19110, "total_steps": 33920, "loss": 0.2623, "lr": 4.766996516879195e-06, "epoch": 11.267688679245284, "percentage": 56.34, "elapsed_time": "0:36:25", "remaining_time": "0:28:13", "throughput": 5762.31, "total_tokens": 12591560} {"current_steps": 19115, "total_steps": 33920, "loss": 0.4082, "lr": 4.764426628730564e-06, "epoch": 11.27063679245283, "percentage": 56.35, "elapsed_time": "0:36:25", "remaining_time": "0:28:13", "throughput": 5762.57, "total_tokens": 12596200} {"current_steps": 19120, "total_steps": 33920, "loss": 0.4268, "lr": 4.761856802950999e-06, "epoch": 11.273584905660377, "percentage": 56.37, "elapsed_time": "0:36:26", "remaining_time": "0:28:12", "throughput": 5762.82, "total_tokens": 12600168} {"current_steps": 19125, "total_steps": 33920, "loss": 0.2966, "lr": 4.759287040220872e-06, "epoch": 11.276533018867925, "percentage": 56.38, "elapsed_time": "0:36:26", "remaining_time": "0:28:11", "throughput": 5762.85, "total_tokens": 12603272} {"current_steps": 19130, "total_steps": 33920, "loss": 0.2558, "lr": 4.756717341220538e-06, "epoch": 11.279481132075471, "percentage": 56.4, "elapsed_time": "0:36:27", "remaining_time": "0:28:11", "throughput": 5762.82, "total_tokens": 12605960} {"current_steps": 19135, "total_steps": 33920, "loss": 0.3553, "lr": 4.7541477066303365e-06, "epoch": 11.28242924528302, "percentage": 56.41, "elapsed_time": "0:36:27", "remaining_time": "0:28:10", "throughput": 5762.77, "total_tokens": 12608808} {"current_steps": 19140, "total_steps": 33920, "loss": 0.3085, "lr": 4.75157813713059e-06, "epoch": 11.285377358490566, "percentage": 56.43, "elapsed_time": "0:36:28", "remaining_time": "0:28:09", "throughput": 5762.99, "total_tokens": 12612392} {"current_steps": 19145, "total_steps": 33920, "loss": 0.3154, "lr": 4.7490086334016e-06, "epoch": 11.288325471698114, "percentage": 56.44, "elapsed_time": "0:36:29", "remaining_time": "0:28:09", "throughput": 5762.94, "total_tokens": 12615304} {"current_steps": 19150, "total_steps": 33920, "loss": 0.4977, "lr": 4.746439196123659e-06, "epoch": 11.29127358490566, "percentage": 56.46, "elapsed_time": "0:36:29", "remaining_time": "0:28:08", "throughput": 5763.01, "total_tokens": 12618536} {"current_steps": 19155, "total_steps": 33920, "loss": 0.3529, "lr": 4.743869825977032e-06, "epoch": 11.294221698113208, "percentage": 56.47, "elapsed_time": "0:36:30", "remaining_time": "0:28:08", "throughput": 5763.21, "total_tokens": 12622504} {"current_steps": 19160, "total_steps": 33920, "loss": 0.4793, "lr": 4.741300523641972e-06, "epoch": 11.297169811320755, "percentage": 56.49, "elapsed_time": "0:36:30", "remaining_time": "0:28:07", "throughput": 5763.43, "total_tokens": 12626216} {"current_steps": 19165, "total_steps": 33920, "loss": 0.3187, "lr": 4.738731289798715e-06, "epoch": 11.300117924528301, "percentage": 56.5, "elapsed_time": "0:36:31", "remaining_time": "0:28:07", "throughput": 5763.64, "total_tokens": 12630440} {"current_steps": 19170, "total_steps": 33920, "loss": 0.399, "lr": 4.7361621251274744e-06, "epoch": 11.30306603773585, "percentage": 56.52, "elapsed_time": "0:36:31", "remaining_time": "0:28:06", "throughput": 5763.64, "total_tokens": 12633384} {"current_steps": 19175, "total_steps": 33920, "loss": 0.2544, "lr": 4.733593030308446e-06, "epoch": 11.306014150943396, "percentage": 56.53, "elapsed_time": "0:36:32", "remaining_time": "0:28:05", "throughput": 5763.72, "total_tokens": 12636584} {"current_steps": 19180, "total_steps": 33920, "loss": 0.3944, "lr": 4.731024006021814e-06, "epoch": 11.308962264150944, "percentage": 56.54, "elapsed_time": "0:36:33", "remaining_time": "0:28:05", "throughput": 5763.85, "total_tokens": 12640168} {"current_steps": 19185, "total_steps": 33920, "loss": 0.2802, "lr": 4.728455052947732e-06, "epoch": 11.31191037735849, "percentage": 56.56, "elapsed_time": "0:36:33", "remaining_time": "0:28:04", "throughput": 5763.96, "total_tokens": 12643592} {"current_steps": 19190, "total_steps": 33920, "loss": 0.3276, "lr": 4.725886171766349e-06, "epoch": 11.314858490566039, "percentage": 56.57, "elapsed_time": "0:36:34", "remaining_time": "0:28:04", "throughput": 5764.06, "total_tokens": 12647080} {"current_steps": 19195, "total_steps": 33920, "loss": 0.5346, "lr": 4.723317363157781e-06, "epoch": 11.317806603773585, "percentage": 56.59, "elapsed_time": "0:36:34", "remaining_time": "0:28:03", "throughput": 5764.06, "total_tokens": 12649800} {"current_steps": 19200, "total_steps": 33920, "loss": 0.4227, "lr": 4.720748627802135e-06, "epoch": 11.320754716981131, "percentage": 56.6, "elapsed_time": "0:36:35", "remaining_time": "0:28:02", "throughput": 5764.03, "total_tokens": 12652648} {"current_steps": 19205, "total_steps": 33920, "loss": 0.3086, "lr": 4.718179966379492e-06, "epoch": 11.32370283018868, "percentage": 56.62, "elapsed_time": "0:36:35", "remaining_time": "0:28:02", "throughput": 5763.8, "total_tokens": 12655176} {"current_steps": 19210, "total_steps": 33920, "loss": 0.4626, "lr": 4.715611379569919e-06, "epoch": 11.326650943396226, "percentage": 56.63, "elapsed_time": "0:36:36", "remaining_time": "0:28:01", "throughput": 5763.91, "total_tokens": 12658824} {"current_steps": 19215, "total_steps": 33920, "loss": 0.3588, "lr": 4.713042868053458e-06, "epoch": 11.329599056603774, "percentage": 56.65, "elapsed_time": "0:36:36", "remaining_time": "0:28:01", "throughput": 5763.86, "total_tokens": 12661544} {"current_steps": 19220, "total_steps": 33920, "loss": 0.3438, "lr": 4.7104744325101345e-06, "epoch": 11.33254716981132, "percentage": 56.66, "elapsed_time": "0:36:37", "remaining_time": "0:28:00", "throughput": 5763.69, "total_tokens": 12663944} {"current_steps": 19225, "total_steps": 33920, "loss": 0.3697, "lr": 4.7079060736199525e-06, "epoch": 11.335495283018869, "percentage": 56.68, "elapsed_time": "0:36:37", "remaining_time": "0:27:59", "throughput": 5763.7, "total_tokens": 12666984} {"current_steps": 19230, "total_steps": 33920, "loss": 0.3259, "lr": 4.705337792062897e-06, "epoch": 11.338443396226415, "percentage": 56.69, "elapsed_time": "0:36:38", "remaining_time": "0:27:59", "throughput": 5763.65, "total_tokens": 12669832} {"current_steps": 19235, "total_steps": 33920, "loss": 0.3753, "lr": 4.702769588518931e-06, "epoch": 11.341391509433961, "percentage": 56.71, "elapsed_time": "0:36:38", "remaining_time": "0:27:58", "throughput": 5763.36, "total_tokens": 12672104} {"current_steps": 19240, "total_steps": 33920, "loss": 0.2529, "lr": 4.700201463667996e-06, "epoch": 11.34433962264151, "percentage": 56.72, "elapsed_time": "0:36:39", "remaining_time": "0:27:57", "throughput": 5763.33, "total_tokens": 12674760} {"current_steps": 19245, "total_steps": 33920, "loss": 0.3019, "lr": 4.697633418190017e-06, "epoch": 11.347287735849056, "percentage": 56.74, "elapsed_time": "0:36:39", "remaining_time": "0:27:57", "throughput": 5763.34, "total_tokens": 12677640} {"current_steps": 19250, "total_steps": 33920, "loss": 0.3517, "lr": 4.695065452764893e-06, "epoch": 11.350235849056604, "percentage": 56.75, "elapsed_time": "0:36:40", "remaining_time": "0:27:56", "throughput": 5763.29, "total_tokens": 12680392} {"current_steps": 19255, "total_steps": 33920, "loss": 0.3473, "lr": 4.692497568072505e-06, "epoch": 11.35318396226415, "percentage": 56.77, "elapsed_time": "0:36:40", "remaining_time": "0:27:56", "throughput": 5763.54, "total_tokens": 12684360} {"current_steps": 19260, "total_steps": 33920, "loss": 0.4447, "lr": 4.689929764792711e-06, "epoch": 11.356132075471699, "percentage": 56.78, "elapsed_time": "0:36:41", "remaining_time": "0:27:55", "throughput": 5763.57, "total_tokens": 12687240} {"current_steps": 19265, "total_steps": 33920, "loss": 0.3787, "lr": 4.687362043605349e-06, "epoch": 11.359080188679245, "percentage": 56.8, "elapsed_time": "0:36:41", "remaining_time": "0:27:54", "throughput": 5763.47, "total_tokens": 12689928} {"current_steps": 19270, "total_steps": 33920, "loss": 0.381, "lr": 4.684794405190231e-06, "epoch": 11.362028301886792, "percentage": 56.81, "elapsed_time": "0:36:42", "remaining_time": "0:27:54", "throughput": 5763.71, "total_tokens": 12693672} {"current_steps": 19275, "total_steps": 33920, "loss": 0.3712, "lr": 4.682226850227155e-06, "epoch": 11.36497641509434, "percentage": 56.82, "elapsed_time": "0:36:42", "remaining_time": "0:27:53", "throughput": 5763.88, "total_tokens": 12697640} {"current_steps": 19280, "total_steps": 33920, "loss": 0.4843, "lr": 4.6796593793958875e-06, "epoch": 11.367924528301886, "percentage": 56.84, "elapsed_time": "0:36:43", "remaining_time": "0:27:53", "throughput": 5764.09, "total_tokens": 12701352} {"current_steps": 19285, "total_steps": 33920, "loss": 0.3446, "lr": 4.6770919933761815e-06, "epoch": 11.370872641509434, "percentage": 56.85, "elapsed_time": "0:36:44", "remaining_time": "0:27:52", "throughput": 5764.18, "total_tokens": 12704360} {"current_steps": 19290, "total_steps": 33920, "loss": 0.3604, "lr": 4.6745246928477615e-06, "epoch": 11.37382075471698, "percentage": 56.87, "elapsed_time": "0:36:44", "remaining_time": "0:27:51", "throughput": 5764.08, "total_tokens": 12706824} {"current_steps": 19295, "total_steps": 33920, "loss": 0.3684, "lr": 4.671957478490332e-06, "epoch": 11.376768867924529, "percentage": 56.88, "elapsed_time": "0:36:44", "remaining_time": "0:27:51", "throughput": 5764.13, "total_tokens": 12709832} {"current_steps": 19300, "total_steps": 33920, "loss": 0.365, "lr": 4.669390350983574e-06, "epoch": 11.379716981132075, "percentage": 56.9, "elapsed_time": "0:36:45", "remaining_time": "0:27:50", "throughput": 5764.31, "total_tokens": 12713896} {"current_steps": 19305, "total_steps": 33920, "loss": 0.3655, "lr": 4.666823311007145e-06, "epoch": 11.382665094339623, "percentage": 56.91, "elapsed_time": "0:36:46", "remaining_time": "0:27:50", "throughput": 5764.53, "total_tokens": 12717640} {"current_steps": 19310, "total_steps": 33920, "loss": 0.438, "lr": 4.664256359240681e-06, "epoch": 11.38561320754717, "percentage": 56.93, "elapsed_time": "0:36:46", "remaining_time": "0:27:49", "throughput": 5764.74, "total_tokens": 12721512} {"current_steps": 19315, "total_steps": 33920, "loss": 0.3949, "lr": 4.661689496363793e-06, "epoch": 11.388561320754716, "percentage": 56.94, "elapsed_time": "0:36:47", "remaining_time": "0:27:49", "throughput": 5764.72, "total_tokens": 12724136} {"current_steps": 19320, "total_steps": 33920, "loss": 0.2777, "lr": 4.659122723056068e-06, "epoch": 11.391509433962264, "percentage": 56.96, "elapsed_time": "0:36:47", "remaining_time": "0:27:48", "throughput": 5764.71, "total_tokens": 12726760} {"current_steps": 19325, "total_steps": 33920, "loss": 0.4087, "lr": 4.656556039997072e-06, "epoch": 11.39445754716981, "percentage": 56.97, "elapsed_time": "0:36:48", "remaining_time": "0:27:47", "throughput": 5764.54, "total_tokens": 12729192} {"current_steps": 19330, "total_steps": 33920, "loss": 0.5215, "lr": 4.653989447866345e-06, "epoch": 11.397405660377359, "percentage": 56.99, "elapsed_time": "0:36:48", "remaining_time": "0:27:47", "throughput": 5764.37, "total_tokens": 12731592} {"current_steps": 19335, "total_steps": 33920, "loss": 0.5295, "lr": 4.651422947343401e-06, "epoch": 11.400353773584905, "percentage": 57.0, "elapsed_time": "0:36:49", "remaining_time": "0:27:46", "throughput": 5764.26, "total_tokens": 12734344} {"current_steps": 19340, "total_steps": 33920, "loss": 0.4214, "lr": 4.6488565391077355e-06, "epoch": 11.403301886792454, "percentage": 57.02, "elapsed_time": "0:36:49", "remaining_time": "0:27:45", "throughput": 5764.47, "total_tokens": 12738856} {"current_steps": 19345, "total_steps": 33920, "loss": 0.307, "lr": 4.646290223838815e-06, "epoch": 11.40625, "percentage": 57.03, "elapsed_time": "0:36:50", "remaining_time": "0:27:45", "throughput": 5764.67, "total_tokens": 12742696} {"current_steps": 19350, "total_steps": 33920, "loss": 0.3803, "lr": 4.64372400221608e-06, "epoch": 11.409198113207546, "percentage": 57.05, "elapsed_time": "0:36:50", "remaining_time": "0:27:44", "throughput": 5764.71, "total_tokens": 12745736} {"current_steps": 19355, "total_steps": 33920, "loss": 0.4261, "lr": 4.641157874918953e-06, "epoch": 11.412146226415095, "percentage": 57.06, "elapsed_time": "0:36:51", "remaining_time": "0:27:44", "throughput": 5764.74, "total_tokens": 12748680} {"current_steps": 19360, "total_steps": 33920, "loss": 0.3316, "lr": 4.6385918426268245e-06, "epoch": 11.415094339622641, "percentage": 57.08, "elapsed_time": "0:36:52", "remaining_time": "0:27:43", "throughput": 5764.98, "total_tokens": 12752680} {"current_steps": 19365, "total_steps": 33920, "loss": 0.3412, "lr": 4.636025906019062e-06, "epoch": 11.41804245283019, "percentage": 57.09, "elapsed_time": "0:36:52", "remaining_time": "0:27:43", "throughput": 5764.98, "total_tokens": 12755560} {"current_steps": 19370, "total_steps": 33920, "loss": 0.2665, "lr": 4.6334600657750115e-06, "epoch": 11.420990566037736, "percentage": 57.1, "elapsed_time": "0:36:53", "remaining_time": "0:27:42", "throughput": 5765.32, "total_tokens": 12760136} {"current_steps": 19375, "total_steps": 33920, "loss": 0.4247, "lr": 4.6308943225739855e-06, "epoch": 11.423938679245284, "percentage": 57.12, "elapsed_time": "0:36:53", "remaining_time": "0:27:41", "throughput": 5765.5, "total_tokens": 12763752} {"current_steps": 19380, "total_steps": 33920, "loss": 0.3022, "lr": 4.628328677095281e-06, "epoch": 11.42688679245283, "percentage": 57.13, "elapsed_time": "0:36:54", "remaining_time": "0:27:41", "throughput": 5765.44, "total_tokens": 12766312} {"current_steps": 19385, "total_steps": 33920, "loss": 0.3922, "lr": 4.625763130018159e-06, "epoch": 11.429834905660377, "percentage": 57.15, "elapsed_time": "0:36:54", "remaining_time": "0:27:40", "throughput": 5765.49, "total_tokens": 12769288} {"current_steps": 19390, "total_steps": 33920, "loss": 0.4593, "lr": 4.6231976820218635e-06, "epoch": 11.432783018867925, "percentage": 57.16, "elapsed_time": "0:36:55", "remaining_time": "0:27:40", "throughput": 5765.92, "total_tokens": 12774696} {"current_steps": 19395, "total_steps": 33920, "loss": 0.3103, "lr": 4.620632333785605e-06, "epoch": 11.435731132075471, "percentage": 57.18, "elapsed_time": "0:36:56", "remaining_time": "0:27:39", "throughput": 5765.81, "total_tokens": 12777192} {"current_steps": 19400, "total_steps": 33920, "loss": 0.3727, "lr": 4.618067085988569e-06, "epoch": 11.43867924528302, "percentage": 57.19, "elapsed_time": "0:36:56", "remaining_time": "0:27:39", "throughput": 5766.19, "total_tokens": 12782408} {"current_steps": 19405, "total_steps": 33920, "loss": 0.4308, "lr": 4.615501939309921e-06, "epoch": 11.441627358490566, "percentage": 57.21, "elapsed_time": "0:36:57", "remaining_time": "0:27:38", "throughput": 5766.44, "total_tokens": 12786184} {"current_steps": 19410, "total_steps": 33920, "loss": 0.3356, "lr": 4.612936894428791e-06, "epoch": 11.444575471698114, "percentage": 57.22, "elapsed_time": "0:36:57", "remaining_time": "0:27:37", "throughput": 5766.44, "total_tokens": 12789224} {"current_steps": 19415, "total_steps": 33920, "loss": 0.4528, "lr": 4.610371952024285e-06, "epoch": 11.44752358490566, "percentage": 57.24, "elapsed_time": "0:36:58", "remaining_time": "0:27:37", "throughput": 5766.61, "total_tokens": 12792776} {"current_steps": 19420, "total_steps": 33920, "loss": 0.4763, "lr": 4.607807112775485e-06, "epoch": 11.450471698113208, "percentage": 57.25, "elapsed_time": "0:36:58", "remaining_time": "0:27:36", "throughput": 5766.7, "total_tokens": 12795816} {"current_steps": 19425, "total_steps": 33920, "loss": 0.2677, "lr": 4.605242377361441e-06, "epoch": 11.453419811320755, "percentage": 57.27, "elapsed_time": "0:36:59", "remaining_time": "0:27:36", "throughput": 5766.87, "total_tokens": 12799464} {"current_steps": 19430, "total_steps": 33920, "loss": 0.3784, "lr": 4.60267774646118e-06, "epoch": 11.456367924528301, "percentage": 57.28, "elapsed_time": "0:36:59", "remaining_time": "0:27:35", "throughput": 5766.69, "total_tokens": 12802024} {"current_steps": 19435, "total_steps": 33920, "loss": 0.5562, "lr": 4.600113220753698e-06, "epoch": 11.45931603773585, "percentage": 57.3, "elapsed_time": "0:37:00", "remaining_time": "0:27:34", "throughput": 5766.64, "total_tokens": 12805000} {"current_steps": 19440, "total_steps": 33920, "loss": 0.3627, "lr": 4.597548800917964e-06, "epoch": 11.462264150943396, "percentage": 57.31, "elapsed_time": "0:37:01", "remaining_time": "0:27:34", "throughput": 5766.56, "total_tokens": 12807816} {"current_steps": 19445, "total_steps": 33920, "loss": 0.3249, "lr": 4.594984487632919e-06, "epoch": 11.465212264150944, "percentage": 57.33, "elapsed_time": "0:37:01", "remaining_time": "0:27:33", "throughput": 5766.4, "total_tokens": 12810632} {"current_steps": 19450, "total_steps": 33920, "loss": 0.3067, "lr": 4.592420281577478e-06, "epoch": 11.46816037735849, "percentage": 57.34, "elapsed_time": "0:37:02", "remaining_time": "0:27:33", "throughput": 5766.3, "total_tokens": 12813608} {"current_steps": 19455, "total_steps": 33920, "loss": 0.4389, "lr": 4.589856183430521e-06, "epoch": 11.471108490566039, "percentage": 57.36, "elapsed_time": "0:37:02", "remaining_time": "0:27:32", "throughput": 5766.53, "total_tokens": 12817864} {"current_steps": 19460, "total_steps": 33920, "loss": 0.322, "lr": 4.58729219387091e-06, "epoch": 11.474056603773585, "percentage": 57.37, "elapsed_time": "0:37:03", "remaining_time": "0:27:32", "throughput": 5766.54, "total_tokens": 12821224} {"current_steps": 19465, "total_steps": 33920, "loss": 0.32, "lr": 4.584728313577468e-06, "epoch": 11.477004716981131, "percentage": 57.39, "elapsed_time": "0:37:03", "remaining_time": "0:27:31", "throughput": 5766.45, "total_tokens": 12824392} {"current_steps": 19470, "total_steps": 33920, "loss": 0.2951, "lr": 4.582164543228993e-06, "epoch": 11.47995283018868, "percentage": 57.4, "elapsed_time": "0:37:04", "remaining_time": "0:27:30", "throughput": 5766.45, "total_tokens": 12827144} {"current_steps": 19475, "total_steps": 33920, "loss": 0.4044, "lr": 4.5796008835042574e-06, "epoch": 11.482900943396226, "percentage": 57.41, "elapsed_time": "0:37:05", "remaining_time": "0:27:30", "throughput": 5766.35, "total_tokens": 12830344} {"current_steps": 19480, "total_steps": 33920, "loss": 0.2758, "lr": 4.577037335082e-06, "epoch": 11.485849056603774, "percentage": 57.43, "elapsed_time": "0:37:05", "remaining_time": "0:27:29", "throughput": 5766.12, "total_tokens": 12833096} {"current_steps": 19485, "total_steps": 33920, "loss": 0.4237, "lr": 4.574473898640933e-06, "epoch": 11.48879716981132, "percentage": 57.44, "elapsed_time": "0:37:06", "remaining_time": "0:27:29", "throughput": 5766.26, "total_tokens": 12836680} {"current_steps": 19490, "total_steps": 33920, "loss": 0.345, "lr": 4.571910574859732e-06, "epoch": 11.491745283018869, "percentage": 57.46, "elapsed_time": "0:37:06", "remaining_time": "0:27:28", "throughput": 5766.17, "total_tokens": 12839240} {"current_steps": 19495, "total_steps": 33920, "loss": 0.3723, "lr": 4.5693473644170535e-06, "epoch": 11.494693396226415, "percentage": 57.47, "elapsed_time": "0:37:07", "remaining_time": "0:27:27", "throughput": 5766.06, "total_tokens": 12841896} {"current_steps": 19500, "total_steps": 33920, "loss": 0.2908, "lr": 4.566784267991516e-06, "epoch": 11.497641509433961, "percentage": 57.49, "elapsed_time": "0:37:07", "remaining_time": "0:27:27", "throughput": 5766.0, "total_tokens": 12844904} {"current_steps": 19505, "total_steps": 33920, "loss": 0.3063, "lr": 4.564221286261709e-06, "epoch": 11.50058962264151, "percentage": 57.5, "elapsed_time": "0:37:08", "remaining_time": "0:27:26", "throughput": 5766.03, "total_tokens": 12847848} {"current_steps": 19510, "total_steps": 33920, "loss": 0.3584, "lr": 4.5616584199061964e-06, "epoch": 11.503537735849056, "percentage": 57.52, "elapsed_time": "0:37:08", "remaining_time": "0:27:26", "throughput": 5766.19, "total_tokens": 12851656} {"current_steps": 19515, "total_steps": 33920, "loss": 0.4252, "lr": 4.559095669603506e-06, "epoch": 11.506485849056604, "percentage": 57.53, "elapsed_time": "0:37:09", "remaining_time": "0:27:25", "throughput": 5766.42, "total_tokens": 12855432} {"current_steps": 19520, "total_steps": 33920, "loss": 0.269, "lr": 4.556533036032136e-06, "epoch": 11.50943396226415, "percentage": 57.55, "elapsed_time": "0:37:09", "remaining_time": "0:27:25", "throughput": 5766.5, "total_tokens": 12858728} {"current_steps": 19525, "total_steps": 33920, "loss": 0.3452, "lr": 4.553970519870557e-06, "epoch": 11.512382075471699, "percentage": 57.56, "elapsed_time": "0:37:10", "remaining_time": "0:27:24", "throughput": 5766.51, "total_tokens": 12862088} {"current_steps": 19530, "total_steps": 33920, "loss": 0.4002, "lr": 4.551408121797205e-06, "epoch": 11.515330188679245, "percentage": 57.58, "elapsed_time": "0:37:10", "remaining_time": "0:27:23", "throughput": 5766.57, "total_tokens": 12865160} {"current_steps": 19535, "total_steps": 33920, "loss": 0.4154, "lr": 4.548845842490486e-06, "epoch": 11.518278301886792, "percentage": 57.59, "elapsed_time": "0:37:11", "remaining_time": "0:27:23", "throughput": 5766.56, "total_tokens": 12867976} {"current_steps": 19540, "total_steps": 33920, "loss": 0.3731, "lr": 4.5462836826287745e-06, "epoch": 11.52122641509434, "percentage": 57.61, "elapsed_time": "0:37:12", "remaining_time": "0:27:22", "throughput": 5766.58, "total_tokens": 12871432} {"current_steps": 19545, "total_steps": 33920, "loss": 0.3937, "lr": 4.543721642890414e-06, "epoch": 11.524174528301886, "percentage": 57.62, "elapsed_time": "0:37:12", "remaining_time": "0:27:22", "throughput": 5766.71, "total_tokens": 12874856} {"current_steps": 19550, "total_steps": 33920, "loss": 0.4041, "lr": 4.541159723953714e-06, "epoch": 11.527122641509434, "percentage": 57.64, "elapsed_time": "0:37:13", "remaining_time": "0:27:21", "throughput": 5766.85, "total_tokens": 12878664} {"current_steps": 19555, "total_steps": 33920, "loss": 0.325, "lr": 4.538597926496955e-06, "epoch": 11.53007075471698, "percentage": 57.65, "elapsed_time": "0:37:13", "remaining_time": "0:27:20", "throughput": 5767.05, "total_tokens": 12882408} {"current_steps": 19560, "total_steps": 33920, "loss": 0.453, "lr": 4.536036251198384e-06, "epoch": 11.533018867924529, "percentage": 57.67, "elapsed_time": "0:37:14", "remaining_time": "0:27:20", "throughput": 5766.8, "total_tokens": 12884648} {"current_steps": 19565, "total_steps": 33920, "loss": 0.354, "lr": 4.5334746987362124e-06, "epoch": 11.535966981132075, "percentage": 57.68, "elapsed_time": "0:37:14", "remaining_time": "0:27:19", "throughput": 5766.86, "total_tokens": 12887752} {"current_steps": 19570, "total_steps": 33920, "loss": 0.4474, "lr": 4.530913269788627e-06, "epoch": 11.538915094339622, "percentage": 57.69, "elapsed_time": "0:37:15", "remaining_time": "0:27:19", "throughput": 5766.71, "total_tokens": 12890184} {"current_steps": 19575, "total_steps": 33920, "loss": 0.2736, "lr": 4.528351965033775e-06, "epoch": 11.54186320754717, "percentage": 57.71, "elapsed_time": "0:37:15", "remaining_time": "0:27:18", "throughput": 5766.75, "total_tokens": 12893576} {"current_steps": 19580, "total_steps": 33920, "loss": 0.3647, "lr": 4.525790785149774e-06, "epoch": 11.544811320754716, "percentage": 57.72, "elapsed_time": "0:37:16", "remaining_time": "0:27:17", "throughput": 5766.67, "total_tokens": 12896264} {"current_steps": 19585, "total_steps": 33920, "loss": 0.4379, "lr": 4.523229730814705e-06, "epoch": 11.547759433962264, "percentage": 57.74, "elapsed_time": "0:37:16", "remaining_time": "0:27:17", "throughput": 5766.6, "total_tokens": 12898888} {"current_steps": 19590, "total_steps": 33920, "loss": 0.2521, "lr": 4.52066880270662e-06, "epoch": 11.55070754716981, "percentage": 57.75, "elapsed_time": "0:37:17", "remaining_time": "0:27:16", "throughput": 5766.44, "total_tokens": 12901544} {"current_steps": 19595, "total_steps": 33920, "loss": 0.3089, "lr": 4.518108001503536e-06, "epoch": 11.553655660377359, "percentage": 57.77, "elapsed_time": "0:37:17", "remaining_time": "0:27:15", "throughput": 5766.32, "total_tokens": 12904200} {"current_steps": 19600, "total_steps": 33920, "loss": 0.5799, "lr": 4.515547327883434e-06, "epoch": 11.556603773584905, "percentage": 57.78, "elapsed_time": "0:37:18", "remaining_time": "0:27:15", "throughput": 5766.38, "total_tokens": 12907752} {"current_steps": 19605, "total_steps": 33920, "loss": 0.2793, "lr": 4.512986782524266e-06, "epoch": 11.559551886792454, "percentage": 57.8, "elapsed_time": "0:37:18", "remaining_time": "0:27:14", "throughput": 5766.43, "total_tokens": 12910760} {"current_steps": 19610, "total_steps": 33920, "loss": 0.2867, "lr": 4.510426366103946e-06, "epoch": 11.5625, "percentage": 57.81, "elapsed_time": "0:37:19", "remaining_time": "0:27:14", "throughput": 5766.52, "total_tokens": 12913928} {"current_steps": 19615, "total_steps": 33920, "loss": 0.337, "lr": 4.5078660793003544e-06, "epoch": 11.565448113207546, "percentage": 57.83, "elapsed_time": "0:37:20", "remaining_time": "0:27:13", "throughput": 5766.5, "total_tokens": 12917032} {"current_steps": 19620, "total_steps": 33920, "loss": 0.47, "lr": 4.505305922791341e-06, "epoch": 11.568396226415095, "percentage": 57.84, "elapsed_time": "0:37:20", "remaining_time": "0:27:13", "throughput": 5766.56, "total_tokens": 12920584} {"current_steps": 19625, "total_steps": 33920, "loss": 0.3423, "lr": 4.502745897254716e-06, "epoch": 11.571344339622641, "percentage": 57.86, "elapsed_time": "0:37:21", "remaining_time": "0:27:12", "throughput": 5766.94, "total_tokens": 12927112} {"current_steps": 19630, "total_steps": 33920, "loss": 0.3532, "lr": 4.500186003368257e-06, "epoch": 11.57429245283019, "percentage": 57.87, "elapsed_time": "0:37:22", "remaining_time": "0:27:12", "throughput": 5766.81, "total_tokens": 12929576} {"current_steps": 19635, "total_steps": 33920, "loss": 0.4085, "lr": 4.497626241809709e-06, "epoch": 11.577240566037736, "percentage": 57.89, "elapsed_time": "0:37:22", "remaining_time": "0:27:11", "throughput": 5766.88, "total_tokens": 12932648} {"current_steps": 19640, "total_steps": 33920, "loss": 0.3159, "lr": 4.4950666132567775e-06, "epoch": 11.580188679245284, "percentage": 57.9, "elapsed_time": "0:37:23", "remaining_time": "0:27:11", "throughput": 5767.18, "total_tokens": 12937064} {"current_steps": 19645, "total_steps": 33920, "loss": 0.2678, "lr": 4.492507118387136e-06, "epoch": 11.58313679245283, "percentage": 57.92, "elapsed_time": "0:37:23", "remaining_time": "0:27:10", "throughput": 5766.99, "total_tokens": 12939400} {"current_steps": 19650, "total_steps": 33920, "loss": 0.2499, "lr": 4.4899477578784235e-06, "epoch": 11.586084905660378, "percentage": 57.93, "elapsed_time": "0:37:24", "remaining_time": "0:27:09", "throughput": 5766.68, "total_tokens": 12941736} {"current_steps": 19655, "total_steps": 33920, "loss": 0.3875, "lr": 4.487388532408239e-06, "epoch": 11.589033018867925, "percentage": 57.95, "elapsed_time": "0:37:24", "remaining_time": "0:27:09", "throughput": 5766.85, "total_tokens": 12945288} {"current_steps": 19660, "total_steps": 33920, "loss": 0.2571, "lr": 4.48482944265415e-06, "epoch": 11.591981132075471, "percentage": 57.96, "elapsed_time": "0:37:25", "remaining_time": "0:27:08", "throughput": 5766.79, "total_tokens": 12948232} {"current_steps": 19665, "total_steps": 33920, "loss": 0.4816, "lr": 4.482270489293685e-06, "epoch": 11.59492924528302, "percentage": 57.97, "elapsed_time": "0:37:25", "remaining_time": "0:27:08", "throughput": 5766.91, "total_tokens": 12951624} {"current_steps": 19670, "total_steps": 33920, "loss": 0.3033, "lr": 4.479711673004341e-06, "epoch": 11.597877358490566, "percentage": 57.99, "elapsed_time": "0:37:26", "remaining_time": "0:27:07", "throughput": 5767.03, "total_tokens": 12955144} {"current_steps": 19675, "total_steps": 33920, "loss": 0.3832, "lr": 4.477152994463575e-06, "epoch": 11.600825471698114, "percentage": 58.0, "elapsed_time": "0:37:27", "remaining_time": "0:27:06", "throughput": 5767.12, "total_tokens": 12958856} {"current_steps": 19680, "total_steps": 33920, "loss": 0.3431, "lr": 4.474594454348805e-06, "epoch": 11.60377358490566, "percentage": 58.02, "elapsed_time": "0:37:27", "remaining_time": "0:27:06", "throughput": 5767.16, "total_tokens": 12962248} {"current_steps": 19685, "total_steps": 33920, "loss": 0.5126, "lr": 4.472036053337419e-06, "epoch": 11.606721698113208, "percentage": 58.03, "elapsed_time": "0:37:28", "remaining_time": "0:27:05", "throughput": 5767.35, "total_tokens": 12966440} {"current_steps": 19690, "total_steps": 33920, "loss": 0.3579, "lr": 4.469477792106761e-06, "epoch": 11.609669811320755, "percentage": 58.05, "elapsed_time": "0:37:28", "remaining_time": "0:27:05", "throughput": 5767.41, "total_tokens": 12969640} {"current_steps": 19695, "total_steps": 33920, "loss": 0.3822, "lr": 4.466919671334146e-06, "epoch": 11.612617924528301, "percentage": 58.06, "elapsed_time": "0:37:29", "remaining_time": "0:27:04", "throughput": 5767.5, "total_tokens": 12973000} {"current_steps": 19700, "total_steps": 33920, "loss": 0.404, "lr": 4.4643616916968456e-06, "epoch": 11.61556603773585, "percentage": 58.08, "elapsed_time": "0:37:29", "remaining_time": "0:27:04", "throughput": 5767.54, "total_tokens": 12976712} {"current_steps": 19705, "total_steps": 33920, "loss": 0.3176, "lr": 4.461803853872095e-06, "epoch": 11.618514150943396, "percentage": 58.09, "elapsed_time": "0:37:30", "remaining_time": "0:27:03", "throughput": 5767.82, "total_tokens": 12980712} {"current_steps": 19710, "total_steps": 33920, "loss": 0.5088, "lr": 4.459246158537094e-06, "epoch": 11.621462264150944, "percentage": 58.11, "elapsed_time": "0:37:31", "remaining_time": "0:27:02", "throughput": 5767.93, "total_tokens": 12983912} {"current_steps": 19715, "total_steps": 33920, "loss": 0.4019, "lr": 4.456688606369003e-06, "epoch": 11.62441037735849, "percentage": 58.12, "elapsed_time": "0:37:31", "remaining_time": "0:27:02", "throughput": 5768.02, "total_tokens": 12987464} {"current_steps": 19720, "total_steps": 33920, "loss": 0.3761, "lr": 4.4541311980449446e-06, "epoch": 11.627358490566039, "percentage": 58.14, "elapsed_time": "0:37:32", "remaining_time": "0:27:01", "throughput": 5768.07, "total_tokens": 12990984} {"current_steps": 19725, "total_steps": 33920, "loss": 0.3577, "lr": 4.4515739342420045e-06, "epoch": 11.630306603773585, "percentage": 58.15, "elapsed_time": "0:37:32", "remaining_time": "0:27:01", "throughput": 5768.17, "total_tokens": 12994504} {"current_steps": 19730, "total_steps": 33920, "loss": 0.4644, "lr": 4.4490168156372294e-06, "epoch": 11.633254716981131, "percentage": 58.17, "elapsed_time": "0:37:33", "remaining_time": "0:27:00", "throughput": 5768.11, "total_tokens": 12997416} {"current_steps": 19735, "total_steps": 33920, "loss": 0.3106, "lr": 4.446459842907626e-06, "epoch": 11.63620283018868, "percentage": 58.18, "elapsed_time": "0:37:33", "remaining_time": "0:26:59", "throughput": 5768.03, "total_tokens": 12999976} {"current_steps": 19740, "total_steps": 33920, "loss": 0.3702, "lr": 4.443903016730165e-06, "epoch": 11.639150943396226, "percentage": 58.2, "elapsed_time": "0:37:34", "remaining_time": "0:26:59", "throughput": 5768.01, "total_tokens": 13003176} {"current_steps": 19745, "total_steps": 33920, "loss": 0.3244, "lr": 4.4413463377817775e-06, "epoch": 11.642099056603774, "percentage": 58.21, "elapsed_time": "0:37:34", "remaining_time": "0:26:58", "throughput": 5768.11, "total_tokens": 13006312} {"current_steps": 19750, "total_steps": 33920, "loss": 0.3751, "lr": 4.438789806739353e-06, "epoch": 11.64504716981132, "percentage": 58.23, "elapsed_time": "0:37:35", "remaining_time": "0:26:58", "throughput": 5767.97, "total_tokens": 13008776} {"current_steps": 19755, "total_steps": 33920, "loss": 0.4347, "lr": 4.436233424279746e-06, "epoch": 11.647995283018869, "percentage": 58.24, "elapsed_time": "0:37:35", "remaining_time": "0:26:57", "throughput": 5768.04, "total_tokens": 13011944} {"current_steps": 19760, "total_steps": 33920, "loss": 0.3377, "lr": 4.433677191079771e-06, "epoch": 11.650943396226415, "percentage": 58.25, "elapsed_time": "0:37:36", "remaining_time": "0:26:56", "throughput": 5768.2, "total_tokens": 13015464} {"current_steps": 19765, "total_steps": 33920, "loss": 0.371, "lr": 4.431121107816201e-06, "epoch": 11.653891509433961, "percentage": 58.27, "elapsed_time": "0:37:36", "remaining_time": "0:26:56", "throughput": 5768.17, "total_tokens": 13018728} {"current_steps": 19770, "total_steps": 33920, "loss": 0.3916, "lr": 4.4285651751657676e-06, "epoch": 11.65683962264151, "percentage": 58.28, "elapsed_time": "0:37:37", "remaining_time": "0:26:55", "throughput": 5768.3, "total_tokens": 13022024} {"current_steps": 19775, "total_steps": 33920, "loss": 0.3605, "lr": 4.4260093938051685e-06, "epoch": 11.659787735849056, "percentage": 58.3, "elapsed_time": "0:37:37", "remaining_time": "0:26:55", "throughput": 5768.23, "total_tokens": 13024584} {"current_steps": 19780, "total_steps": 33920, "loss": 0.3682, "lr": 4.423453764411056e-06, "epoch": 11.662735849056604, "percentage": 58.31, "elapsed_time": "0:37:38", "remaining_time": "0:26:54", "throughput": 5768.62, "total_tokens": 13029896} {"current_steps": 19785, "total_steps": 33920, "loss": 0.3453, "lr": 4.4208982876600425e-06, "epoch": 11.66568396226415, "percentage": 58.33, "elapsed_time": "0:37:39", "remaining_time": "0:26:54", "throughput": 5768.72, "total_tokens": 13033480} {"current_steps": 19790, "total_steps": 33920, "loss": 0.4401, "lr": 4.418342964228705e-06, "epoch": 11.668632075471699, "percentage": 58.34, "elapsed_time": "0:37:39", "remaining_time": "0:26:53", "throughput": 5768.83, "total_tokens": 13036616} {"current_steps": 19795, "total_steps": 33920, "loss": 0.3532, "lr": 4.415787794793574e-06, "epoch": 11.671580188679245, "percentage": 58.36, "elapsed_time": "0:37:40", "remaining_time": "0:26:52", "throughput": 5768.59, "total_tokens": 13038856} {"current_steps": 19800, "total_steps": 33920, "loss": 0.3176, "lr": 4.4132327800311414e-06, "epoch": 11.674528301886792, "percentage": 58.37, "elapsed_time": "0:37:40", "remaining_time": "0:26:52", "throughput": 5768.43, "total_tokens": 13041416} {"current_steps": 19805, "total_steps": 33920, "loss": 0.3688, "lr": 4.41067792061786e-06, "epoch": 11.67747641509434, "percentage": 58.39, "elapsed_time": "0:37:41", "remaining_time": "0:26:51", "throughput": 5768.31, "total_tokens": 13044008} {"current_steps": 19810, "total_steps": 33920, "loss": 0.3838, "lr": 4.408123217230139e-06, "epoch": 11.680424528301886, "percentage": 58.4, "elapsed_time": "0:37:41", "remaining_time": "0:26:51", "throughput": 5768.48, "total_tokens": 13047560} {"current_steps": 19815, "total_steps": 33920, "loss": 0.2903, "lr": 4.4055686705443464e-06, "epoch": 11.683372641509434, "percentage": 58.42, "elapsed_time": "0:37:42", "remaining_time": "0:26:50", "throughput": 5768.56, "total_tokens": 13050632} {"current_steps": 19820, "total_steps": 33920, "loss": 0.3472, "lr": 4.4030142812368106e-06, "epoch": 11.68632075471698, "percentage": 58.43, "elapsed_time": "0:37:42", "remaining_time": "0:26:49", "throughput": 5768.56, "total_tokens": 13053576} {"current_steps": 19825, "total_steps": 33920, "loss": 0.2619, "lr": 4.400460049983817e-06, "epoch": 11.689268867924529, "percentage": 58.45, "elapsed_time": "0:37:43", "remaining_time": "0:26:49", "throughput": 5768.61, "total_tokens": 13056584} {"current_steps": 19830, "total_steps": 33920, "loss": 0.2889, "lr": 4.397905977461608e-06, "epoch": 11.692216981132075, "percentage": 58.46, "elapsed_time": "0:37:44", "remaining_time": "0:26:48", "throughput": 5768.84, "total_tokens": 13061672} {"current_steps": 19835, "total_steps": 33920, "loss": 0.4467, "lr": 4.395352064346387e-06, "epoch": 11.695165094339622, "percentage": 58.48, "elapsed_time": "0:37:44", "remaining_time": "0:26:48", "throughput": 5768.83, "total_tokens": 13064680} {"current_steps": 19840, "total_steps": 33920, "loss": 0.3919, "lr": 4.392798311314314e-06, "epoch": 11.69811320754717, "percentage": 58.49, "elapsed_time": "0:37:45", "remaining_time": "0:26:47", "throughput": 5768.86, "total_tokens": 13068104} {"current_steps": 19845, "total_steps": 33920, "loss": 0.3168, "lr": 4.390244719041502e-06, "epoch": 11.701061320754716, "percentage": 58.51, "elapsed_time": "0:37:45", "remaining_time": "0:26:46", "throughput": 5768.89, "total_tokens": 13071016} {"current_steps": 19850, "total_steps": 33920, "loss": 0.2882, "lr": 4.387691288204029e-06, "epoch": 11.704009433962264, "percentage": 58.52, "elapsed_time": "0:37:46", "remaining_time": "0:26:46", "throughput": 5768.81, "total_tokens": 13073864} {"current_steps": 19855, "total_steps": 33920, "loss": 0.2804, "lr": 4.385138019477928e-06, "epoch": 11.70695754716981, "percentage": 58.53, "elapsed_time": "0:37:46", "remaining_time": "0:26:45", "throughput": 5768.66, "total_tokens": 13076264} {"current_steps": 19860, "total_steps": 33920, "loss": 0.3444, "lr": 4.3825849135391864e-06, "epoch": 11.709905660377359, "percentage": 58.55, "elapsed_time": "0:37:47", "remaining_time": "0:26:45", "throughput": 5768.53, "total_tokens": 13078664} {"current_steps": 19865, "total_steps": 33920, "loss": 0.3658, "lr": 4.380031971063748e-06, "epoch": 11.712853773584905, "percentage": 58.56, "elapsed_time": "0:37:47", "remaining_time": "0:26:44", "throughput": 5768.7, "total_tokens": 13082216} {"current_steps": 19870, "total_steps": 33920, "loss": 0.4238, "lr": 4.37747919272752e-06, "epoch": 11.715801886792454, "percentage": 58.58, "elapsed_time": "0:37:48", "remaining_time": "0:26:43", "throughput": 5768.6, "total_tokens": 13085064} {"current_steps": 19875, "total_steps": 33920, "loss": 0.2985, "lr": 4.374926579206357e-06, "epoch": 11.71875, "percentage": 58.59, "elapsed_time": "0:37:48", "remaining_time": "0:26:43", "throughput": 5768.48, "total_tokens": 13087656} {"current_steps": 19880, "total_steps": 33920, "loss": 0.3818, "lr": 4.372374131176075e-06, "epoch": 11.721698113207546, "percentage": 58.61, "elapsed_time": "0:37:49", "remaining_time": "0:26:42", "throughput": 5768.58, "total_tokens": 13091176} {"current_steps": 19885, "total_steps": 33920, "loss": 0.4284, "lr": 4.369821849312449e-06, "epoch": 11.724646226415095, "percentage": 58.62, "elapsed_time": "0:37:49", "remaining_time": "0:26:42", "throughput": 5768.55, "total_tokens": 13094536} {"current_steps": 19890, "total_steps": 33920, "loss": 0.4888, "lr": 4.367269734291203e-06, "epoch": 11.727594339622641, "percentage": 58.64, "elapsed_time": "0:37:50", "remaining_time": "0:26:41", "throughput": 5768.63, "total_tokens": 13097864} {"current_steps": 19895, "total_steps": 33920, "loss": 0.3046, "lr": 4.364717786788022e-06, "epoch": 11.73054245283019, "percentage": 58.65, "elapsed_time": "0:37:51", "remaining_time": "0:26:40", "throughput": 5768.55, "total_tokens": 13100840} {"current_steps": 19900, "total_steps": 33920, "loss": 0.3934, "lr": 4.362166007478545e-06, "epoch": 11.733490566037736, "percentage": 58.67, "elapsed_time": "0:37:51", "remaining_time": "0:26:40", "throughput": 5768.65, "total_tokens": 13104136} {"current_steps": 19905, "total_steps": 33920, "loss": 0.3322, "lr": 4.3596143970383665e-06, "epoch": 11.736438679245284, "percentage": 58.68, "elapsed_time": "0:37:52", "remaining_time": "0:26:39", "throughput": 5768.65, "total_tokens": 13107272} {"current_steps": 19910, "total_steps": 33920, "loss": 0.3601, "lr": 4.357062956143035e-06, "epoch": 11.73938679245283, "percentage": 58.7, "elapsed_time": "0:37:52", "remaining_time": "0:26:39", "throughput": 5768.65, "total_tokens": 13110088} {"current_steps": 19915, "total_steps": 33920, "loss": 0.3653, "lr": 4.354511685468059e-06, "epoch": 11.742334905660378, "percentage": 58.71, "elapsed_time": "0:37:53", "remaining_time": "0:26:38", "throughput": 5768.73, "total_tokens": 13113512} {"current_steps": 19920, "total_steps": 33920, "loss": 0.3774, "lr": 4.351960585688894e-06, "epoch": 11.745283018867925, "percentage": 58.73, "elapsed_time": "0:37:53", "remaining_time": "0:26:38", "throughput": 5768.85, "total_tokens": 13116840} {"current_steps": 19925, "total_steps": 33920, "loss": 0.3914, "lr": 4.349409657480959e-06, "epoch": 11.748231132075471, "percentage": 58.74, "elapsed_time": "0:37:54", "remaining_time": "0:26:37", "throughput": 5768.93, "total_tokens": 13120072} {"current_steps": 19930, "total_steps": 33920, "loss": 0.3168, "lr": 4.34685890151962e-06, "epoch": 11.75117924528302, "percentage": 58.76, "elapsed_time": "0:37:54", "remaining_time": "0:26:36", "throughput": 5768.86, "total_tokens": 13122728} {"current_steps": 19935, "total_steps": 33920, "loss": 0.3647, "lr": 4.344308318480201e-06, "epoch": 11.754127358490566, "percentage": 58.77, "elapsed_time": "0:37:55", "remaining_time": "0:26:36", "throughput": 5768.91, "total_tokens": 13126472} {"current_steps": 19940, "total_steps": 33920, "loss": 0.3224, "lr": 4.341757909037981e-06, "epoch": 11.757075471698114, "percentage": 58.79, "elapsed_time": "0:37:55", "remaining_time": "0:26:35", "throughput": 5769.01, "total_tokens": 13129800} {"current_steps": 19945, "total_steps": 33920, "loss": 0.383, "lr": 4.33920767386819e-06, "epoch": 11.76002358490566, "percentage": 58.8, "elapsed_time": "0:37:56", "remaining_time": "0:26:35", "throughput": 5769.05, "total_tokens": 13132744} {"current_steps": 19950, "total_steps": 33920, "loss": 0.3286, "lr": 4.336657613646017e-06, "epoch": 11.762971698113208, "percentage": 58.81, "elapsed_time": "0:37:56", "remaining_time": "0:26:34", "throughput": 5769.05, "total_tokens": 13135528} {"current_steps": 19955, "total_steps": 33920, "loss": 0.2921, "lr": 4.3341077290466e-06, "epoch": 11.765919811320755, "percentage": 58.83, "elapsed_time": "0:37:57", "remaining_time": "0:26:33", "throughput": 5768.93, "total_tokens": 13138344} {"current_steps": 19960, "total_steps": 33920, "loss": 0.4286, "lr": 4.331558020745031e-06, "epoch": 11.768867924528301, "percentage": 58.84, "elapsed_time": "0:37:58", "remaining_time": "0:26:33", "throughput": 5769.13, "total_tokens": 13142728} {"current_steps": 19965, "total_steps": 33920, "loss": 0.3877, "lr": 4.329008489416357e-06, "epoch": 11.77181603773585, "percentage": 58.86, "elapsed_time": "0:37:58", "remaining_time": "0:26:32", "throughput": 5769.42, "total_tokens": 13147592} {"current_steps": 19970, "total_steps": 33920, "loss": 0.3075, "lr": 4.326459135735576e-06, "epoch": 11.774764150943396, "percentage": 58.87, "elapsed_time": "0:37:59", "remaining_time": "0:26:32", "throughput": 5769.4, "total_tokens": 13150376} {"current_steps": 19975, "total_steps": 33920, "loss": 0.3745, "lr": 4.323909960377644e-06, "epoch": 11.777712264150944, "percentage": 58.89, "elapsed_time": "0:37:59", "remaining_time": "0:26:31", "throughput": 5769.5, "total_tokens": 13153960} {"current_steps": 19980, "total_steps": 33920, "loss": 0.2774, "lr": 4.3213609640174625e-06, "epoch": 11.78066037735849, "percentage": 58.9, "elapsed_time": "0:38:00", "remaining_time": "0:26:31", "throughput": 5769.57, "total_tokens": 13157128} {"current_steps": 19985, "total_steps": 33920, "loss": 0.345, "lr": 4.318812147329889e-06, "epoch": 11.783608490566039, "percentage": 58.92, "elapsed_time": "0:38:01", "remaining_time": "0:26:30", "throughput": 5769.64, "total_tokens": 13160968} {"current_steps": 19990, "total_steps": 33920, "loss": 0.3668, "lr": 4.316263510989737e-06, "epoch": 11.786556603773585, "percentage": 58.93, "elapsed_time": "0:38:01", "remaining_time": "0:26:29", "throughput": 5769.44, "total_tokens": 13163304} {"current_steps": 19995, "total_steps": 33920, "loss": 0.2958, "lr": 4.313715055671768e-06, "epoch": 11.789504716981131, "percentage": 58.95, "elapsed_time": "0:38:02", "remaining_time": "0:26:29", "throughput": 5769.4, "total_tokens": 13165992} {"current_steps": 20000, "total_steps": 33920, "loss": 0.3165, "lr": 4.311166782050694e-06, "epoch": 11.79245283018868, "percentage": 58.96, "elapsed_time": "0:38:02", "remaining_time": "0:26:28", "throughput": 5769.36, "total_tokens": 13168744} {"current_steps": 20005, "total_steps": 33920, "loss": 0.3271, "lr": 4.308618690801184e-06, "epoch": 11.795400943396226, "percentage": 58.98, "elapsed_time": "0:38:03", "remaining_time": "0:26:28", "throughput": 5769.33, "total_tokens": 13171624} {"current_steps": 20010, "total_steps": 33920, "loss": 0.3232, "lr": 4.3060707825978564e-06, "epoch": 11.798349056603774, "percentage": 58.99, "elapsed_time": "0:38:03", "remaining_time": "0:26:27", "throughput": 5769.29, "total_tokens": 13174408} {"current_steps": 20015, "total_steps": 33920, "loss": 0.3995, "lr": 4.303523058115278e-06, "epoch": 11.80129716981132, "percentage": 59.01, "elapsed_time": "0:38:04", "remaining_time": "0:26:26", "throughput": 5769.28, "total_tokens": 13177160} {"current_steps": 20020, "total_steps": 33920, "loss": 0.3439, "lr": 4.300975518027972e-06, "epoch": 11.804245283018869, "percentage": 59.02, "elapsed_time": "0:38:04", "remaining_time": "0:26:26", "throughput": 5769.26, "total_tokens": 13179976} {"current_steps": 20025, "total_steps": 33920, "loss": 0.4026, "lr": 4.298428163010411e-06, "epoch": 11.807193396226415, "percentage": 59.04, "elapsed_time": "0:38:05", "remaining_time": "0:26:25", "throughput": 5769.36, "total_tokens": 13183272} {"current_steps": 20030, "total_steps": 33920, "loss": 0.3628, "lr": 4.295880993737016e-06, "epoch": 11.810141509433961, "percentage": 59.05, "elapsed_time": "0:38:05", "remaining_time": "0:26:25", "throughput": 5769.57, "total_tokens": 13187528} {"current_steps": 20035, "total_steps": 33920, "loss": 0.3588, "lr": 4.293334010882164e-06, "epoch": 11.81308962264151, "percentage": 59.07, "elapsed_time": "0:38:06", "remaining_time": "0:26:24", "throughput": 5769.56, "total_tokens": 13190344} {"current_steps": 20040, "total_steps": 33920, "loss": 0.3792, "lr": 4.290787215120178e-06, "epoch": 11.816037735849056, "percentage": 59.08, "elapsed_time": "0:38:06", "remaining_time": "0:26:23", "throughput": 5769.56, "total_tokens": 13193096} {"current_steps": 20045, "total_steps": 33920, "loss": 0.5469, "lr": 4.2882406071253315e-06, "epoch": 11.818985849056604, "percentage": 59.09, "elapsed_time": "0:38:07", "remaining_time": "0:26:23", "throughput": 5769.63, "total_tokens": 13196136} {"current_steps": 20050, "total_steps": 33920, "loss": 0.3205, "lr": 4.285694187571852e-06, "epoch": 11.82193396226415, "percentage": 59.11, "elapsed_time": "0:38:07", "remaining_time": "0:26:22", "throughput": 5769.46, "total_tokens": 13198952} {"current_steps": 20055, "total_steps": 33920, "loss": 0.3507, "lr": 4.283147957133917e-06, "epoch": 11.824882075471699, "percentage": 59.12, "elapsed_time": "0:38:08", "remaining_time": "0:26:21", "throughput": 5769.34, "total_tokens": 13201768} {"current_steps": 20060, "total_steps": 33920, "loss": 0.4598, "lr": 4.280601916485648e-06, "epoch": 11.827830188679245, "percentage": 59.14, "elapsed_time": "0:38:09", "remaining_time": "0:26:21", "throughput": 5769.63, "total_tokens": 13208552} {"current_steps": 20065, "total_steps": 33920, "loss": 0.4202, "lr": 4.278056066301123e-06, "epoch": 11.830778301886792, "percentage": 59.15, "elapsed_time": "0:38:09", "remaining_time": "0:26:21", "throughput": 5769.59, "total_tokens": 13211464} {"current_steps": 20070, "total_steps": 33920, "loss": 0.4425, "lr": 4.275510407254366e-06, "epoch": 11.83372641509434, "percentage": 59.17, "elapsed_time": "0:38:10", "remaining_time": "0:26:20", "throughput": 5769.4, "total_tokens": 13213896} {"current_steps": 20075, "total_steps": 33920, "loss": 0.3867, "lr": 4.27296494001935e-06, "epoch": 11.836674528301886, "percentage": 59.18, "elapsed_time": "0:38:10", "remaining_time": "0:26:19", "throughput": 5769.31, "total_tokens": 13216808} {"current_steps": 20080, "total_steps": 33920, "loss": 0.339, "lr": 4.2704196652700005e-06, "epoch": 11.839622641509434, "percentage": 59.2, "elapsed_time": "0:38:11", "remaining_time": "0:26:19", "throughput": 5769.25, "total_tokens": 13219560} {"current_steps": 20085, "total_steps": 33920, "loss": 0.2976, "lr": 4.2678745836801895e-06, "epoch": 11.84257075471698, "percentage": 59.21, "elapsed_time": "0:38:11", "remaining_time": "0:26:18", "throughput": 5769.31, "total_tokens": 13222728} {"current_steps": 20090, "total_steps": 33920, "loss": 0.4494, "lr": 4.265329695923736e-06, "epoch": 11.845518867924529, "percentage": 59.23, "elapsed_time": "0:38:12", "remaining_time": "0:26:18", "throughput": 5769.44, "total_tokens": 13225992} {"current_steps": 20095, "total_steps": 33920, "loss": 0.3042, "lr": 4.262785002674412e-06, "epoch": 11.848466981132075, "percentage": 59.24, "elapsed_time": "0:38:13", "remaining_time": "0:26:17", "throughput": 5769.74, "total_tokens": 13230312} {"current_steps": 20100, "total_steps": 33920, "loss": 0.3685, "lr": 4.260240504605938e-06, "epoch": 11.851415094339622, "percentage": 59.26, "elapsed_time": "0:38:13", "remaining_time": "0:26:16", "throughput": 5769.85, "total_tokens": 13233576} {"current_steps": 20105, "total_steps": 33920, "loss": 0.3861, "lr": 4.2576962023919775e-06, "epoch": 11.85436320754717, "percentage": 59.27, "elapsed_time": "0:38:14", "remaining_time": "0:26:16", "throughput": 5769.96, "total_tokens": 13237000} {"current_steps": 20110, "total_steps": 33920, "loss": 0.3509, "lr": 4.255152096706145e-06, "epoch": 11.857311320754716, "percentage": 59.29, "elapsed_time": "0:38:14", "remaining_time": "0:26:15", "throughput": 5770.02, "total_tokens": 13240360} {"current_steps": 20115, "total_steps": 33920, "loss": 0.4576, "lr": 4.252608188222007e-06, "epoch": 11.860259433962264, "percentage": 59.3, "elapsed_time": "0:38:15", "remaining_time": "0:26:15", "throughput": 5769.87, "total_tokens": 13242952} {"current_steps": 20120, "total_steps": 33920, "loss": 0.311, "lr": 4.250064477613071e-06, "epoch": 11.86320754716981, "percentage": 59.32, "elapsed_time": "0:38:15", "remaining_time": "0:26:14", "throughput": 5769.92, "total_tokens": 13246248} {"current_steps": 20125, "total_steps": 33920, "loss": 0.2458, "lr": 4.247520965552797e-06, "epoch": 11.866155660377359, "percentage": 59.33, "elapsed_time": "0:38:16", "remaining_time": "0:26:14", "throughput": 5770.0, "total_tokens": 13249480} {"current_steps": 20130, "total_steps": 33920, "loss": 0.4301, "lr": 4.24497765271459e-06, "epoch": 11.869103773584905, "percentage": 59.35, "elapsed_time": "0:38:16", "remaining_time": "0:26:13", "throughput": 5770.02, "total_tokens": 13252680} {"current_steps": 20135, "total_steps": 33920, "loss": 0.3963, "lr": 4.242434539771804e-06, "epoch": 11.872051886792454, "percentage": 59.36, "elapsed_time": "0:38:17", "remaining_time": "0:26:12", "throughput": 5770.1, "total_tokens": 13255784} {"current_steps": 20140, "total_steps": 33920, "loss": 0.3086, "lr": 4.239891627397737e-06, "epoch": 11.875, "percentage": 59.38, "elapsed_time": "0:38:17", "remaining_time": "0:26:12", "throughput": 5770.23, "total_tokens": 13259656} {"current_steps": 20145, "total_steps": 33920, "loss": 0.3578, "lr": 4.237348916265638e-06, "epoch": 11.877948113207546, "percentage": 59.39, "elapsed_time": "0:38:18", "remaining_time": "0:26:11", "throughput": 5770.33, "total_tokens": 13263272} {"current_steps": 20150, "total_steps": 33920, "loss": 0.3382, "lr": 4.234806407048702e-06, "epoch": 11.880896226415095, "percentage": 59.4, "elapsed_time": "0:38:19", "remaining_time": "0:26:11", "throughput": 5770.64, "total_tokens": 13267720} {"current_steps": 20155, "total_steps": 33920, "loss": 0.3323, "lr": 4.232264100420066e-06, "epoch": 11.883844339622641, "percentage": 59.42, "elapsed_time": "0:38:19", "remaining_time": "0:26:10", "throughput": 5770.71, "total_tokens": 13270952} {"current_steps": 20160, "total_steps": 33920, "loss": 0.3585, "lr": 4.229721997052819e-06, "epoch": 11.88679245283019, "percentage": 59.43, "elapsed_time": "0:38:20", "remaining_time": "0:26:10", "throughput": 5770.75, "total_tokens": 13274248} {"current_steps": 20165, "total_steps": 33920, "loss": 0.3392, "lr": 4.227180097619993e-06, "epoch": 11.889740566037736, "percentage": 59.45, "elapsed_time": "0:38:20", "remaining_time": "0:26:09", "throughput": 5770.8, "total_tokens": 13277288} {"current_steps": 20170, "total_steps": 33920, "loss": 0.3371, "lr": 4.224638402794566e-06, "epoch": 11.892688679245284, "percentage": 59.46, "elapsed_time": "0:38:21", "remaining_time": "0:26:08", "throughput": 5770.77, "total_tokens": 13279976} {"current_steps": 20175, "total_steps": 33920, "loss": 0.3385, "lr": 4.222096913249464e-06, "epoch": 11.89563679245283, "percentage": 59.48, "elapsed_time": "0:38:21", "remaining_time": "0:26:08", "throughput": 5770.93, "total_tokens": 13283368} {"current_steps": 20180, "total_steps": 33920, "loss": 0.2733, "lr": 4.219555629657558e-06, "epoch": 11.898584905660378, "percentage": 59.49, "elapsed_time": "0:38:22", "remaining_time": "0:26:07", "throughput": 5770.86, "total_tokens": 13285960} {"current_steps": 20185, "total_steps": 33920, "loss": 0.3836, "lr": 4.21701455269166e-06, "epoch": 11.901533018867925, "percentage": 59.51, "elapsed_time": "0:38:22", "remaining_time": "0:26:06", "throughput": 5770.9, "total_tokens": 13289000} {"current_steps": 20190, "total_steps": 33920, "loss": 0.299, "lr": 4.2144736830245356e-06, "epoch": 11.904481132075471, "percentage": 59.52, "elapsed_time": "0:38:23", "remaining_time": "0:26:06", "throughput": 5770.82, "total_tokens": 13291752} {"current_steps": 20195, "total_steps": 33920, "loss": 0.335, "lr": 4.211933021328889e-06, "epoch": 11.90742924528302, "percentage": 59.54, "elapsed_time": "0:38:23", "remaining_time": "0:26:05", "throughput": 5770.73, "total_tokens": 13294696} {"current_steps": 20200, "total_steps": 33920, "loss": 0.3452, "lr": 4.20939256827737e-06, "epoch": 11.910377358490566, "percentage": 59.55, "elapsed_time": "0:38:24", "remaining_time": "0:26:05", "throughput": 5770.92, "total_tokens": 13298440} {"current_steps": 20205, "total_steps": 33920, "loss": 0.3521, "lr": 4.206852324542578e-06, "epoch": 11.913325471698114, "percentage": 59.57, "elapsed_time": "0:38:24", "remaining_time": "0:26:04", "throughput": 5770.76, "total_tokens": 13300808} {"current_steps": 20210, "total_steps": 33920, "loss": 0.3458, "lr": 4.2043122907970496e-06, "epoch": 11.91627358490566, "percentage": 59.58, "elapsed_time": "0:38:25", "remaining_time": "0:26:04", "throughput": 5771.02, "total_tokens": 13305448} {"current_steps": 20215, "total_steps": 33920, "loss": 0.28, "lr": 4.2017724677132715e-06, "epoch": 11.919221698113208, "percentage": 59.6, "elapsed_time": "0:38:26", "remaining_time": "0:26:03", "throughput": 5771.17, "total_tokens": 13308968} {"current_steps": 20220, "total_steps": 33920, "loss": 0.4215, "lr": 4.1992328559636734e-06, "epoch": 11.922169811320755, "percentage": 59.61, "elapsed_time": "0:38:26", "remaining_time": "0:26:02", "throughput": 5771.04, "total_tokens": 13311336} {"current_steps": 20225, "total_steps": 33920, "loss": 0.3134, "lr": 4.196693456220628e-06, "epoch": 11.925117924528301, "percentage": 59.63, "elapsed_time": "0:38:27", "remaining_time": "0:26:02", "throughput": 5770.94, "total_tokens": 13313992} {"current_steps": 20230, "total_steps": 33920, "loss": 0.3342, "lr": 4.194154269156452e-06, "epoch": 11.92806603773585, "percentage": 59.64, "elapsed_time": "0:38:27", "remaining_time": "0:26:01", "throughput": 5771.24, "total_tokens": 13318568} {"current_steps": 20235, "total_steps": 33920, "loss": 0.2755, "lr": 4.191615295443404e-06, "epoch": 11.931014150943396, "percentage": 59.66, "elapsed_time": "0:38:28", "remaining_time": "0:26:01", "throughput": 5771.38, "total_tokens": 13322120} {"current_steps": 20240, "total_steps": 33920, "loss": 0.408, "lr": 4.189076535753692e-06, "epoch": 11.933962264150944, "percentage": 59.67, "elapsed_time": "0:38:28", "remaining_time": "0:26:00", "throughput": 5771.53, "total_tokens": 13326024} {"current_steps": 20245, "total_steps": 33920, "loss": 0.353, "lr": 4.186537990759464e-06, "epoch": 11.93691037735849, "percentage": 59.68, "elapsed_time": "0:38:29", "remaining_time": "0:25:59", "throughput": 5771.55, "total_tokens": 13329256} {"current_steps": 20250, "total_steps": 33920, "loss": 0.3288, "lr": 4.183999661132806e-06, "epoch": 11.939858490566039, "percentage": 59.7, "elapsed_time": "0:38:29", "remaining_time": "0:25:59", "throughput": 5771.65, "total_tokens": 13332392} {"current_steps": 20255, "total_steps": 33920, "loss": 0.3394, "lr": 4.181461547545756e-06, "epoch": 11.942806603773585, "percentage": 59.71, "elapsed_time": "0:38:30", "remaining_time": "0:25:58", "throughput": 5771.54, "total_tokens": 13335048} {"current_steps": 20260, "total_steps": 33920, "loss": 0.3645, "lr": 4.178923650670289e-06, "epoch": 11.945754716981131, "percentage": 59.73, "elapsed_time": "0:38:30", "remaining_time": "0:25:58", "throughput": 5771.37, "total_tokens": 13337448} {"current_steps": 20265, "total_steps": 33920, "loss": 0.399, "lr": 4.176385971178324e-06, "epoch": 11.94870283018868, "percentage": 59.74, "elapsed_time": "0:38:31", "remaining_time": "0:25:57", "throughput": 5771.37, "total_tokens": 13340360} {"current_steps": 20270, "total_steps": 33920, "loss": 0.3512, "lr": 4.1738485097417225e-06, "epoch": 11.951650943396226, "percentage": 59.76, "elapsed_time": "0:38:31", "remaining_time": "0:25:56", "throughput": 5771.49, "total_tokens": 13343624} {"current_steps": 20275, "total_steps": 33920, "loss": 0.3277, "lr": 4.1713112670322886e-06, "epoch": 11.954599056603774, "percentage": 59.77, "elapsed_time": "0:38:32", "remaining_time": "0:25:56", "throughput": 5771.48, "total_tokens": 13346504} {"current_steps": 20280, "total_steps": 33920, "loss": 0.4813, "lr": 4.168774243721768e-06, "epoch": 11.95754716981132, "percentage": 59.79, "elapsed_time": "0:38:32", "remaining_time": "0:25:55", "throughput": 5771.5, "total_tokens": 13349448} {"current_steps": 20285, "total_steps": 33920, "loss": 0.4238, "lr": 4.166237440481849e-06, "epoch": 11.960495283018869, "percentage": 59.8, "elapsed_time": "0:38:33", "remaining_time": "0:25:55", "throughput": 5771.72, "total_tokens": 13353352} {"current_steps": 20290, "total_steps": 33920, "loss": 0.3998, "lr": 4.163700857984162e-06, "epoch": 11.963443396226415, "percentage": 59.82, "elapsed_time": "0:38:34", "remaining_time": "0:25:54", "throughput": 5771.77, "total_tokens": 13356168} {"current_steps": 20295, "total_steps": 33920, "loss": 0.397, "lr": 4.161164496900275e-06, "epoch": 11.966391509433961, "percentage": 59.83, "elapsed_time": "0:38:34", "remaining_time": "0:25:53", "throughput": 5771.82, "total_tokens": 13359240} {"current_steps": 20300, "total_steps": 33920, "loss": 0.3536, "lr": 4.1586283579017036e-06, "epoch": 11.96933962264151, "percentage": 59.85, "elapsed_time": "0:38:35", "remaining_time": "0:25:53", "throughput": 5771.64, "total_tokens": 13361608} {"current_steps": 20305, "total_steps": 33920, "loss": 0.3228, "lr": 4.156092441659901e-06, "epoch": 11.972287735849056, "percentage": 59.86, "elapsed_time": "0:38:35", "remaining_time": "0:25:52", "throughput": 5771.68, "total_tokens": 13364904} {"current_steps": 20310, "total_steps": 33920, "loss": 0.3636, "lr": 4.153556748846261e-06, "epoch": 11.975235849056604, "percentage": 59.88, "elapsed_time": "0:38:36", "remaining_time": "0:25:52", "throughput": 5771.82, "total_tokens": 13368456} {"current_steps": 20315, "total_steps": 33920, "loss": 0.3552, "lr": 4.15102128013212e-06, "epoch": 11.97818396226415, "percentage": 59.89, "elapsed_time": "0:38:36", "remaining_time": "0:25:51", "throughput": 5772.02, "total_tokens": 13372424} {"current_steps": 20320, "total_steps": 33920, "loss": 0.415, "lr": 4.1484860361887544e-06, "epoch": 11.981132075471699, "percentage": 59.91, "elapsed_time": "0:38:37", "remaining_time": "0:25:51", "throughput": 5772.23, "total_tokens": 13376456} {"current_steps": 20325, "total_steps": 33920, "loss": 0.4113, "lr": 4.145951017687379e-06, "epoch": 11.984080188679245, "percentage": 59.92, "elapsed_time": "0:38:37", "remaining_time": "0:25:50", "throughput": 5772.26, "total_tokens": 13379400} {"current_steps": 20330, "total_steps": 33920, "loss": 0.298, "lr": 4.1434162252991524e-06, "epoch": 11.987028301886792, "percentage": 59.94, "elapsed_time": "0:38:38", "remaining_time": "0:25:49", "throughput": 5772.05, "total_tokens": 13381768} {"current_steps": 20335, "total_steps": 33920, "loss": 0.3688, "lr": 4.140881659695173e-06, "epoch": 11.98997641509434, "percentage": 59.95, "elapsed_time": "0:38:39", "remaining_time": "0:25:49", "throughput": 5772.43, "total_tokens": 13389160} {"current_steps": 20340, "total_steps": 33920, "loss": 0.3397, "lr": 4.138347321546477e-06, "epoch": 11.992924528301886, "percentage": 59.96, "elapsed_time": "0:38:40", "remaining_time": "0:25:48", "throughput": 5772.39, "total_tokens": 13392104} {"current_steps": 20345, "total_steps": 33920, "loss": 0.38, "lr": 4.13581321152404e-06, "epoch": 11.995872641509434, "percentage": 59.98, "elapsed_time": "0:38:40", "remaining_time": "0:25:48", "throughput": 5772.27, "total_tokens": 13395240} {"current_steps": 20350, "total_steps": 33920, "loss": 0.4502, "lr": 4.133279330298781e-06, "epoch": 11.99882075471698, "percentage": 59.99, "elapsed_time": "0:38:41", "remaining_time": "0:25:47", "throughput": 5772.51, "total_tokens": 13399304} {"current_steps": 20352, "total_steps": 33920, "eval_loss": 0.5455325245857239, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "0:38:59", "remaining_time": "0:25:59", "throughput": 5726.52, "total_tokens": 13399864} {"current_steps": 20355, "total_steps": 33920, "loss": 0.3918, "lr": 4.130745678541555e-06, "epoch": 12.001768867924529, "percentage": 60.01, "elapsed_time": "0:39:03", "remaining_time": "0:26:01", "throughput": 5718.66, "total_tokens": 13402104} {"current_steps": 20360, "total_steps": 33920, "loss": 0.2881, "lr": 4.128212256923155e-06, "epoch": 12.004716981132075, "percentage": 60.02, "elapsed_time": "0:39:04", "remaining_time": "0:26:01", "throughput": 5718.54, "total_tokens": 13404728} {"current_steps": 20365, "total_steps": 33920, "loss": 0.4624, "lr": 4.125679066114318e-06, "epoch": 12.007665094339623, "percentage": 60.04, "elapsed_time": "0:39:04", "remaining_time": "0:26:00", "throughput": 5718.78, "total_tokens": 13408728} {"current_steps": 20370, "total_steps": 33920, "loss": 0.3383, "lr": 4.123146106785717e-06, "epoch": 12.01061320754717, "percentage": 60.05, "elapsed_time": "0:39:05", "remaining_time": "0:26:00", "throughput": 5718.59, "total_tokens": 13411288} {"current_steps": 20375, "total_steps": 33920, "loss": 0.3917, "lr": 4.1206133796079625e-06, "epoch": 12.013561320754716, "percentage": 60.07, "elapsed_time": "0:39:05", "remaining_time": "0:25:59", "throughput": 5718.86, "total_tokens": 13415544} {"current_steps": 20380, "total_steps": 33920, "loss": 0.2445, "lr": 4.1180808852516065e-06, "epoch": 12.016509433962264, "percentage": 60.08, "elapsed_time": "0:39:06", "remaining_time": "0:25:58", "throughput": 5719.0, "total_tokens": 13418648} {"current_steps": 20385, "total_steps": 33920, "loss": 0.415, "lr": 4.115548624387136e-06, "epoch": 12.01945754716981, "percentage": 60.1, "elapsed_time": "0:39:06", "remaining_time": "0:25:58", "throughput": 5719.11, "total_tokens": 13422072} {"current_steps": 20390, "total_steps": 33920, "loss": 0.4026, "lr": 4.113016597684979e-06, "epoch": 12.022405660377359, "percentage": 60.11, "elapsed_time": "0:39:07", "remaining_time": "0:25:57", "throughput": 5719.09, "total_tokens": 13424984} {"current_steps": 20395, "total_steps": 33920, "loss": 0.3644, "lr": 4.110484805815502e-06, "epoch": 12.025353773584905, "percentage": 60.13, "elapsed_time": "0:39:07", "remaining_time": "0:25:57", "throughput": 5718.91, "total_tokens": 13427480} {"current_steps": 20400, "total_steps": 33920, "loss": 0.3395, "lr": 4.107953249449005e-06, "epoch": 12.028301886792454, "percentage": 60.14, "elapsed_time": "0:39:08", "remaining_time": "0:25:56", "throughput": 5718.99, "total_tokens": 13431192} {"current_steps": 20405, "total_steps": 33920, "loss": 0.308, "lr": 4.105421929255729e-06, "epoch": 12.03125, "percentage": 60.16, "elapsed_time": "0:39:09", "remaining_time": "0:25:55", "throughput": 5719.1, "total_tokens": 13434936} {"current_steps": 20410, "total_steps": 33920, "loss": 0.3309, "lr": 4.102890845905854e-06, "epoch": 12.034198113207546, "percentage": 60.17, "elapsed_time": "0:39:09", "remaining_time": "0:25:55", "throughput": 5719.1, "total_tokens": 13437720} {"current_steps": 20415, "total_steps": 33920, "loss": 0.4175, "lr": 4.1003600000694935e-06, "epoch": 12.037146226415095, "percentage": 60.19, "elapsed_time": "0:39:10", "remaining_time": "0:25:54", "throughput": 5719.09, "total_tokens": 13440440} {"current_steps": 20420, "total_steps": 33920, "loss": 0.2912, "lr": 4.0978293924167e-06, "epoch": 12.040094339622641, "percentage": 60.2, "elapsed_time": "0:39:10", "remaining_time": "0:25:54", "throughput": 5719.43, "total_tokens": 13445496} {"current_steps": 20425, "total_steps": 33920, "loss": 0.2865, "lr": 4.095299023617461e-06, "epoch": 12.04304245283019, "percentage": 60.22, "elapsed_time": "0:39:11", "remaining_time": "0:25:53", "throughput": 5719.52, "total_tokens": 13448888} {"current_steps": 20430, "total_steps": 33920, "loss": 0.3225, "lr": 4.092768894341707e-06, "epoch": 12.045990566037736, "percentage": 60.23, "elapsed_time": "0:39:11", "remaining_time": "0:25:52", "throughput": 5719.46, "total_tokens": 13451544} {"current_steps": 20435, "total_steps": 33920, "loss": 0.4284, "lr": 4.090239005259298e-06, "epoch": 12.048938679245284, "percentage": 60.24, "elapsed_time": "0:39:12", "remaining_time": "0:25:52", "throughput": 5719.56, "total_tokens": 13454648} {"current_steps": 20440, "total_steps": 33920, "loss": 0.3008, "lr": 4.087709357040033e-06, "epoch": 12.05188679245283, "percentage": 60.26, "elapsed_time": "0:39:12", "remaining_time": "0:25:51", "throughput": 5719.57, "total_tokens": 13457464} {"current_steps": 20445, "total_steps": 33920, "loss": 0.3506, "lr": 4.085179950353648e-06, "epoch": 12.054834905660377, "percentage": 60.27, "elapsed_time": "0:39:13", "remaining_time": "0:25:51", "throughput": 5719.52, "total_tokens": 13460120} {"current_steps": 20450, "total_steps": 33920, "loss": 0.2364, "lr": 4.0826507858698135e-06, "epoch": 12.057783018867925, "percentage": 60.29, "elapsed_time": "0:39:13", "remaining_time": "0:25:50", "throughput": 5719.57, "total_tokens": 13463096} {"current_steps": 20455, "total_steps": 33920, "loss": 0.3364, "lr": 4.080121864258136e-06, "epoch": 12.060731132075471, "percentage": 60.3, "elapsed_time": "0:39:14", "remaining_time": "0:25:49", "throughput": 5719.52, "total_tokens": 13466136} {"current_steps": 20460, "total_steps": 33920, "loss": 0.3335, "lr": 4.077593186188161e-06, "epoch": 12.06367924528302, "percentage": 60.32, "elapsed_time": "0:39:15", "remaining_time": "0:25:49", "throughput": 5719.62, "total_tokens": 13469720} {"current_steps": 20465, "total_steps": 33920, "loss": 0.417, "lr": 4.075064752329364e-06, "epoch": 12.066627358490566, "percentage": 60.33, "elapsed_time": "0:39:15", "remaining_time": "0:25:48", "throughput": 5719.63, "total_tokens": 13472728} {"current_steps": 20470, "total_steps": 33920, "loss": 0.3535, "lr": 4.0725365633511605e-06, "epoch": 12.069575471698114, "percentage": 60.35, "elapsed_time": "0:39:16", "remaining_time": "0:25:48", "throughput": 5719.83, "total_tokens": 13476184} {"current_steps": 20475, "total_steps": 33920, "loss": 0.3399, "lr": 4.070008619922899e-06, "epoch": 12.07252358490566, "percentage": 60.36, "elapsed_time": "0:39:16", "remaining_time": "0:25:47", "throughput": 5719.96, "total_tokens": 13479416} {"current_steps": 20480, "total_steps": 33920, "loss": 0.4352, "lr": 4.067480922713864e-06, "epoch": 12.075471698113208, "percentage": 60.38, "elapsed_time": "0:39:17", "remaining_time": "0:25:46", "throughput": 5720.24, "total_tokens": 13483704} {"current_steps": 20485, "total_steps": 33920, "loss": 0.3808, "lr": 4.064953472393273e-06, "epoch": 12.078419811320755, "percentage": 60.39, "elapsed_time": "0:39:17", "remaining_time": "0:25:46", "throughput": 5720.09, "total_tokens": 13486040} {"current_steps": 20490, "total_steps": 33920, "loss": 0.3056, "lr": 4.06242626963028e-06, "epoch": 12.081367924528301, "percentage": 60.41, "elapsed_time": "0:39:18", "remaining_time": "0:25:45", "throughput": 5720.06, "total_tokens": 13488856} {"current_steps": 20495, "total_steps": 33920, "loss": 0.2571, "lr": 4.059899315093972e-06, "epoch": 12.08431603773585, "percentage": 60.42, "elapsed_time": "0:39:18", "remaining_time": "0:25:45", "throughput": 5719.9, "total_tokens": 13491288} {"current_steps": 20500, "total_steps": 33920, "loss": 0.5939, "lr": 4.057372609453374e-06, "epoch": 12.087264150943396, "percentage": 60.44, "elapsed_time": "0:39:19", "remaining_time": "0:25:44", "throughput": 5719.88, "total_tokens": 13494296} {"current_steps": 20505, "total_steps": 33920, "loss": 0.2981, "lr": 4.054846153377439e-06, "epoch": 12.090212264150944, "percentage": 60.45, "elapsed_time": "0:39:19", "remaining_time": "0:25:43", "throughput": 5719.98, "total_tokens": 13497688} {"current_steps": 20510, "total_steps": 33920, "loss": 0.2914, "lr": 4.052319947535058e-06, "epoch": 12.09316037735849, "percentage": 60.47, "elapsed_time": "0:39:20", "remaining_time": "0:25:43", "throughput": 5720.01, "total_tokens": 13500760} {"current_steps": 20515, "total_steps": 33920, "loss": 0.5623, "lr": 4.049793992595056e-06, "epoch": 12.096108490566039, "percentage": 60.48, "elapsed_time": "0:39:21", "remaining_time": "0:25:42", "throughput": 5720.35, "total_tokens": 13506936} {"current_steps": 20520, "total_steps": 33920, "loss": 0.283, "lr": 4.047268289226187e-06, "epoch": 12.099056603773585, "percentage": 60.5, "elapsed_time": "0:39:21", "remaining_time": "0:25:42", "throughput": 5720.55, "total_tokens": 13511096} {"current_steps": 20525, "total_steps": 33920, "loss": 0.355, "lr": 4.044742838097147e-06, "epoch": 12.102004716981131, "percentage": 60.51, "elapsed_time": "0:39:22", "remaining_time": "0:25:41", "throughput": 5720.67, "total_tokens": 13514168} {"current_steps": 20530, "total_steps": 33920, "loss": 0.2906, "lr": 4.0422176398765564e-06, "epoch": 12.10495283018868, "percentage": 60.52, "elapsed_time": "0:39:22", "remaining_time": "0:25:41", "throughput": 5720.82, "total_tokens": 13517656} {"current_steps": 20535, "total_steps": 33920, "loss": 0.3926, "lr": 4.039692695232975e-06, "epoch": 12.107900943396226, "percentage": 60.54, "elapsed_time": "0:39:23", "remaining_time": "0:25:40", "throughput": 5721.05, "total_tokens": 13521400} {"current_steps": 20540, "total_steps": 33920, "loss": 0.2696, "lr": 4.03716800483489e-06, "epoch": 12.110849056603774, "percentage": 60.55, "elapsed_time": "0:39:24", "remaining_time": "0:25:39", "throughput": 5721.28, "total_tokens": 13525240} {"current_steps": 20545, "total_steps": 33920, "loss": 0.3555, "lr": 4.034643569350726e-06, "epoch": 12.11379716981132, "percentage": 60.57, "elapsed_time": "0:39:24", "remaining_time": "0:25:39", "throughput": 5721.36, "total_tokens": 13528184} {"current_steps": 20550, "total_steps": 33920, "loss": 0.3308, "lr": 4.032119389448837e-06, "epoch": 12.116745283018869, "percentage": 60.58, "elapsed_time": "0:39:25", "remaining_time": "0:25:38", "throughput": 5721.49, "total_tokens": 13531384} {"current_steps": 20555, "total_steps": 33920, "loss": 0.3624, "lr": 4.0295954657975115e-06, "epoch": 12.119693396226415, "percentage": 60.6, "elapsed_time": "0:39:25", "remaining_time": "0:25:38", "throughput": 5721.72, "total_tokens": 13535448} {"current_steps": 20560, "total_steps": 33920, "loss": 0.3538, "lr": 4.027071799064968e-06, "epoch": 12.122641509433961, "percentage": 60.61, "elapsed_time": "0:39:26", "remaining_time": "0:25:37", "throughput": 5721.71, "total_tokens": 13538680} {"current_steps": 20565, "total_steps": 33920, "loss": 0.3277, "lr": 4.02454838991936e-06, "epoch": 12.12558962264151, "percentage": 60.63, "elapsed_time": "0:39:26", "remaining_time": "0:25:36", "throughput": 5721.64, "total_tokens": 13541368} {"current_steps": 20570, "total_steps": 33920, "loss": 0.2935, "lr": 4.022025239028768e-06, "epoch": 12.128537735849056, "percentage": 60.64, "elapsed_time": "0:39:27", "remaining_time": "0:25:36", "throughput": 5721.71, "total_tokens": 13544472} {"current_steps": 20575, "total_steps": 33920, "loss": 0.2101, "lr": 4.0195023470612095e-06, "epoch": 12.131485849056604, "percentage": 60.66, "elapsed_time": "0:39:27", "remaining_time": "0:25:35", "throughput": 5721.76, "total_tokens": 13547480} {"current_steps": 20580, "total_steps": 33920, "loss": 0.2765, "lr": 4.016979714684631e-06, "epoch": 12.13443396226415, "percentage": 60.67, "elapsed_time": "0:39:28", "remaining_time": "0:25:35", "throughput": 5721.86, "total_tokens": 13550712} {"current_steps": 20585, "total_steps": 33920, "loss": 0.2556, "lr": 4.014457342566909e-06, "epoch": 12.137382075471699, "percentage": 60.69, "elapsed_time": "0:39:28", "remaining_time": "0:25:34", "throughput": 5722.22, "total_tokens": 13555800} {"current_steps": 20590, "total_steps": 33920, "loss": 0.3744, "lr": 4.011935231375853e-06, "epoch": 12.140330188679245, "percentage": 60.7, "elapsed_time": "0:39:29", "remaining_time": "0:25:33", "throughput": 5722.12, "total_tokens": 13558296} {"current_steps": 20595, "total_steps": 33920, "loss": 0.4272, "lr": 4.009413381779203e-06, "epoch": 12.143278301886792, "percentage": 60.72, "elapsed_time": "0:39:30", "remaining_time": "0:25:33", "throughput": 5722.39, "total_tokens": 13562584} {"current_steps": 20600, "total_steps": 33920, "loss": 0.2288, "lr": 4.00689179444463e-06, "epoch": 12.14622641509434, "percentage": 60.73, "elapsed_time": "0:39:30", "remaining_time": "0:25:32", "throughput": 5722.14, "total_tokens": 13564632} {"current_steps": 20605, "total_steps": 33920, "loss": 0.3947, "lr": 4.004370470039733e-06, "epoch": 12.149174528301886, "percentage": 60.75, "elapsed_time": "0:39:31", "remaining_time": "0:25:32", "throughput": 5721.88, "total_tokens": 13567160} {"current_steps": 20610, "total_steps": 33920, "loss": 0.3753, "lr": 4.001849409232046e-06, "epoch": 12.152122641509434, "percentage": 60.76, "elapsed_time": "0:39:31", "remaining_time": "0:25:31", "throughput": 5722.05, "total_tokens": 13570808} {"current_steps": 20615, "total_steps": 33920, "loss": 0.3488, "lr": 3.9993286126890274e-06, "epoch": 12.15507075471698, "percentage": 60.78, "elapsed_time": "0:39:32", "remaining_time": "0:25:31", "throughput": 5722.04, "total_tokens": 13574072} {"current_steps": 20620, "total_steps": 33920, "loss": 0.2963, "lr": 3.996808081078074e-06, "epoch": 12.158018867924529, "percentage": 60.79, "elapsed_time": "0:39:32", "remaining_time": "0:25:30", "throughput": 5722.33, "total_tokens": 13578200} {"current_steps": 20625, "total_steps": 33920, "loss": 0.3547, "lr": 3.9942878150665035e-06, "epoch": 12.160966981132075, "percentage": 60.8, "elapsed_time": "0:39:33", "remaining_time": "0:25:29", "throughput": 5722.51, "total_tokens": 13581560} {"current_steps": 20630, "total_steps": 33920, "loss": 0.3796, "lr": 3.991767815321569e-06, "epoch": 12.163915094339623, "percentage": 60.82, "elapsed_time": "0:39:33", "remaining_time": "0:25:29", "throughput": 5722.62, "total_tokens": 13584600} {"current_steps": 20635, "total_steps": 33920, "loss": 0.2736, "lr": 3.9892480825104504e-06, "epoch": 12.16686320754717, "percentage": 60.83, "elapsed_time": "0:39:34", "remaining_time": "0:25:28", "throughput": 5722.69, "total_tokens": 13587800} {"current_steps": 20640, "total_steps": 33920, "loss": 0.3343, "lr": 3.986728617300257e-06, "epoch": 12.169811320754716, "percentage": 60.85, "elapsed_time": "0:39:34", "remaining_time": "0:25:27", "throughput": 5722.73, "total_tokens": 13590584} {"current_steps": 20645, "total_steps": 33920, "loss": 0.2212, "lr": 3.984209420358031e-06, "epoch": 12.172759433962264, "percentage": 60.86, "elapsed_time": "0:39:35", "remaining_time": "0:25:27", "throughput": 5722.89, "total_tokens": 13594040} {"current_steps": 20650, "total_steps": 33920, "loss": 0.2849, "lr": 3.981690492350738e-06, "epoch": 12.17570754716981, "percentage": 60.88, "elapsed_time": "0:39:35", "remaining_time": "0:25:26", "throughput": 5722.86, "total_tokens": 13596824} {"current_steps": 20655, "total_steps": 33920, "loss": 0.3278, "lr": 3.979171833945276e-06, "epoch": 12.178655660377359, "percentage": 60.89, "elapsed_time": "0:39:36", "remaining_time": "0:25:26", "throughput": 5723.04, "total_tokens": 13600248} {"current_steps": 20660, "total_steps": 33920, "loss": 0.4343, "lr": 3.97665344580847e-06, "epoch": 12.181603773584905, "percentage": 60.91, "elapsed_time": "0:39:36", "remaining_time": "0:25:25", "throughput": 5723.14, "total_tokens": 13603544} {"current_steps": 20665, "total_steps": 33920, "loss": 0.3486, "lr": 3.974135328607075e-06, "epoch": 12.184551886792454, "percentage": 60.92, "elapsed_time": "0:39:37", "remaining_time": "0:25:25", "throughput": 5723.35, "total_tokens": 13607832} {"current_steps": 20670, "total_steps": 33920, "loss": 0.4472, "lr": 3.971617483007773e-06, "epoch": 12.1875, "percentage": 60.94, "elapsed_time": "0:39:38", "remaining_time": "0:25:24", "throughput": 5723.46, "total_tokens": 13610968} {"current_steps": 20675, "total_steps": 33920, "loss": 0.3344, "lr": 3.969099909677174e-06, "epoch": 12.190448113207546, "percentage": 60.95, "elapsed_time": "0:39:38", "remaining_time": "0:25:23", "throughput": 5723.4, "total_tokens": 13613560} {"current_steps": 20680, "total_steps": 33920, "loss": 0.2873, "lr": 3.9665826092818165e-06, "epoch": 12.193396226415095, "percentage": 60.97, "elapsed_time": "0:39:39", "remaining_time": "0:25:23", "throughput": 5723.59, "total_tokens": 13617176} {"current_steps": 20685, "total_steps": 33920, "loss": 0.4014, "lr": 3.964065582488168e-06, "epoch": 12.196344339622641, "percentage": 60.98, "elapsed_time": "0:39:39", "remaining_time": "0:25:22", "throughput": 5723.66, "total_tokens": 13620408} {"current_steps": 20690, "total_steps": 33920, "loss": 0.2578, "lr": 3.961548829962622e-06, "epoch": 12.19929245283019, "percentage": 61.0, "elapsed_time": "0:39:40", "remaining_time": "0:25:21", "throughput": 5723.77, "total_tokens": 13623512} {"current_steps": 20695, "total_steps": 33920, "loss": 0.3586, "lr": 3.959032352371496e-06, "epoch": 12.202240566037736, "percentage": 61.01, "elapsed_time": "0:39:40", "remaining_time": "0:25:21", "throughput": 5723.86, "total_tokens": 13626456} {"current_steps": 20700, "total_steps": 33920, "loss": 0.379, "lr": 3.956516150381043e-06, "epoch": 12.205188679245284, "percentage": 61.03, "elapsed_time": "0:39:41", "remaining_time": "0:25:20", "throughput": 5723.83, "total_tokens": 13629048} {"current_steps": 20705, "total_steps": 33920, "loss": 0.353, "lr": 3.954000224657436e-06, "epoch": 12.20813679245283, "percentage": 61.04, "elapsed_time": "0:39:41", "remaining_time": "0:25:20", "throughput": 5723.84, "total_tokens": 13631896} {"current_steps": 20710, "total_steps": 33920, "loss": 0.3479, "lr": 3.951484575866776e-06, "epoch": 12.211084905660377, "percentage": 61.06, "elapsed_time": "0:39:42", "remaining_time": "0:25:19", "throughput": 5723.74, "total_tokens": 13634392} {"current_steps": 20715, "total_steps": 33920, "loss": 0.269, "lr": 3.948969204675096e-06, "epoch": 12.214033018867925, "percentage": 61.07, "elapsed_time": "0:39:42", "remaining_time": "0:25:18", "throughput": 5723.79, "total_tokens": 13637240} {"current_steps": 20720, "total_steps": 33920, "loss": 0.3036, "lr": 3.946454111748346e-06, "epoch": 12.216981132075471, "percentage": 61.08, "elapsed_time": "0:39:43", "remaining_time": "0:25:18", "throughput": 5723.77, "total_tokens": 13639896} {"current_steps": 20725, "total_steps": 33920, "loss": 0.4327, "lr": 3.943939297752413e-06, "epoch": 12.21992924528302, "percentage": 61.1, "elapsed_time": "0:39:43", "remaining_time": "0:25:17", "throughput": 5723.84, "total_tokens": 13642904} {"current_steps": 20730, "total_steps": 33920, "loss": 0.2693, "lr": 3.9414247633531e-06, "epoch": 12.222877358490566, "percentage": 61.11, "elapsed_time": "0:39:44", "remaining_time": "0:25:17", "throughput": 5724.31, "total_tokens": 13649240} {"current_steps": 20735, "total_steps": 33920, "loss": 0.3918, "lr": 3.9389105092161454e-06, "epoch": 12.225825471698114, "percentage": 61.13, "elapsed_time": "0:39:44", "remaining_time": "0:25:16", "throughput": 5724.37, "total_tokens": 13652568} {"current_steps": 20740, "total_steps": 33920, "loss": 0.2771, "lr": 3.936396536007205e-06, "epoch": 12.22877358490566, "percentage": 61.14, "elapsed_time": "0:39:45", "remaining_time": "0:25:15", "throughput": 5724.48, "total_tokens": 13655768} {"current_steps": 20745, "total_steps": 33920, "loss": 0.3925, "lr": 3.933882844391866e-06, "epoch": 12.231721698113208, "percentage": 61.16, "elapsed_time": "0:39:46", "remaining_time": "0:25:15", "throughput": 5724.49, "total_tokens": 13658712} {"current_steps": 20750, "total_steps": 33920, "loss": 0.3587, "lr": 3.931369435035639e-06, "epoch": 12.234669811320755, "percentage": 61.17, "elapsed_time": "0:39:46", "remaining_time": "0:25:14", "throughput": 5724.39, "total_tokens": 13661144} {"current_steps": 20755, "total_steps": 33920, "loss": 0.3029, "lr": 3.92885630860396e-06, "epoch": 12.237617924528301, "percentage": 61.19, "elapsed_time": "0:39:46", "remaining_time": "0:25:14", "throughput": 5724.55, "total_tokens": 13664472} {"current_steps": 20760, "total_steps": 33920, "loss": 0.381, "lr": 3.926343465762189e-06, "epoch": 12.24056603773585, "percentage": 61.2, "elapsed_time": "0:39:47", "remaining_time": "0:25:13", "throughput": 5724.56, "total_tokens": 13667640} {"current_steps": 20765, "total_steps": 33920, "loss": 0.4211, "lr": 3.923830907175613e-06, "epoch": 12.243514150943396, "percentage": 61.22, "elapsed_time": "0:39:48", "remaining_time": "0:25:12", "throughput": 5724.59, "total_tokens": 13670488} {"current_steps": 20770, "total_steps": 33920, "loss": 0.474, "lr": 3.921318633509442e-06, "epoch": 12.246462264150944, "percentage": 61.23, "elapsed_time": "0:39:48", "remaining_time": "0:25:12", "throughput": 5724.45, "total_tokens": 13672920} {"current_steps": 20775, "total_steps": 33920, "loss": 0.5038, "lr": 3.918806645428811e-06, "epoch": 12.24941037735849, "percentage": 61.25, "elapsed_time": "0:39:49", "remaining_time": "0:25:11", "throughput": 5724.47, "total_tokens": 13676216} {"current_steps": 20780, "total_steps": 33920, "loss": 0.4584, "lr": 3.916294943598781e-06, "epoch": 12.252358490566039, "percentage": 61.26, "elapsed_time": "0:39:49", "remaining_time": "0:25:11", "throughput": 5724.57, "total_tokens": 13679448} {"current_steps": 20785, "total_steps": 33920, "loss": 0.3417, "lr": 3.913783528684336e-06, "epoch": 12.255306603773585, "percentage": 61.28, "elapsed_time": "0:39:50", "remaining_time": "0:25:10", "throughput": 5724.64, "total_tokens": 13683096} {"current_steps": 20790, "total_steps": 33920, "loss": 0.3367, "lr": 3.911272401350381e-06, "epoch": 12.258254716981131, "percentage": 61.29, "elapsed_time": "0:39:50", "remaining_time": "0:25:09", "throughput": 5724.71, "total_tokens": 13686328} {"current_steps": 20795, "total_steps": 33920, "loss": 0.3083, "lr": 3.9087615622617525e-06, "epoch": 12.26120283018868, "percentage": 61.31, "elapsed_time": "0:39:51", "remaining_time": "0:25:09", "throughput": 5724.78, "total_tokens": 13689496} {"current_steps": 20800, "total_steps": 33920, "loss": 0.3437, "lr": 3.906251012083202e-06, "epoch": 12.264150943396226, "percentage": 61.32, "elapsed_time": "0:39:51", "remaining_time": "0:25:08", "throughput": 5724.9, "total_tokens": 13692792} {"current_steps": 20805, "total_steps": 33920, "loss": 0.5237, "lr": 3.9037407514794085e-06, "epoch": 12.267099056603774, "percentage": 61.34, "elapsed_time": "0:39:52", "remaining_time": "0:25:08", "throughput": 5724.96, "total_tokens": 13696056} {"current_steps": 20810, "total_steps": 33920, "loss": 0.3817, "lr": 3.901230781114976e-06, "epoch": 12.27004716981132, "percentage": 61.35, "elapsed_time": "0:39:52", "remaining_time": "0:25:07", "throughput": 5725.11, "total_tokens": 13699608} {"current_steps": 20815, "total_steps": 33920, "loss": 0.4064, "lr": 3.898721101654431e-06, "epoch": 12.272995283018869, "percentage": 61.36, "elapsed_time": "0:39:53", "remaining_time": "0:25:06", "throughput": 5725.02, "total_tokens": 13702232} {"current_steps": 20820, "total_steps": 33920, "loss": 0.526, "lr": 3.896211713762221e-06, "epoch": 12.275943396226415, "percentage": 61.38, "elapsed_time": "0:39:53", "remaining_time": "0:25:06", "throughput": 5725.08, "total_tokens": 13705368} {"current_steps": 20825, "total_steps": 33920, "loss": 0.2776, "lr": 3.893702618102715e-06, "epoch": 12.278891509433961, "percentage": 61.39, "elapsed_time": "0:39:54", "remaining_time": "0:25:05", "throughput": 5725.19, "total_tokens": 13708696} {"current_steps": 20830, "total_steps": 33920, "loss": 0.2624, "lr": 3.891193815340211e-06, "epoch": 12.28183962264151, "percentage": 61.41, "elapsed_time": "0:39:54", "remaining_time": "0:25:05", "throughput": 5725.39, "total_tokens": 13712248} {"current_steps": 20835, "total_steps": 33920, "loss": 0.3618, "lr": 3.888685306138922e-06, "epoch": 12.284787735849056, "percentage": 61.42, "elapsed_time": "0:39:55", "remaining_time": "0:25:04", "throughput": 5725.4, "total_tokens": 13715000} {"current_steps": 20840, "total_steps": 33920, "loss": 0.4977, "lr": 3.886177091162987e-06, "epoch": 12.287735849056604, "percentage": 61.44, "elapsed_time": "0:39:55", "remaining_time": "0:25:03", "throughput": 5725.62, "total_tokens": 13718520} {"current_steps": 20845, "total_steps": 33920, "loss": 0.2921, "lr": 3.883669171076468e-06, "epoch": 12.29068396226415, "percentage": 61.45, "elapsed_time": "0:39:56", "remaining_time": "0:25:03", "throughput": 5725.75, "total_tokens": 13721688} {"current_steps": 20850, "total_steps": 33920, "loss": 0.2632, "lr": 3.881161546543348e-06, "epoch": 12.293632075471699, "percentage": 61.47, "elapsed_time": "0:39:57", "remaining_time": "0:25:02", "throughput": 5725.76, "total_tokens": 13724728} {"current_steps": 20855, "total_steps": 33920, "loss": 0.3076, "lr": 3.8786542182275295e-06, "epoch": 12.296580188679245, "percentage": 61.48, "elapsed_time": "0:39:57", "remaining_time": "0:25:02", "throughput": 5725.9, "total_tokens": 13728888} {"current_steps": 20860, "total_steps": 33920, "loss": 0.2329, "lr": 3.87614718679284e-06, "epoch": 12.299528301886792, "percentage": 61.5, "elapsed_time": "0:39:58", "remaining_time": "0:25:01", "throughput": 5726.08, "total_tokens": 13732600} {"current_steps": 20865, "total_steps": 33920, "loss": 0.4568, "lr": 3.8736404529030255e-06, "epoch": 12.30247641509434, "percentage": 61.51, "elapsed_time": "0:39:59", "remaining_time": "0:25:01", "throughput": 5726.45, "total_tokens": 13737912} {"current_steps": 20870, "total_steps": 33920, "loss": 0.3721, "lr": 3.871134017221756e-06, "epoch": 12.305424528301886, "percentage": 61.53, "elapsed_time": "0:39:59", "remaining_time": "0:25:00", "throughput": 5726.86, "total_tokens": 13742712} {"current_steps": 20875, "total_steps": 33920, "loss": 0.2756, "lr": 3.868627880412621e-06, "epoch": 12.308372641509434, "percentage": 61.54, "elapsed_time": "0:40:00", "remaining_time": "0:24:59", "throughput": 5726.89, "total_tokens": 13746168} {"current_steps": 20880, "total_steps": 33920, "loss": 0.3901, "lr": 3.86612204313913e-06, "epoch": 12.31132075471698, "percentage": 61.56, "elapsed_time": "0:40:00", "remaining_time": "0:24:59", "throughput": 5727.09, "total_tokens": 13749752} {"current_steps": 20885, "total_steps": 33920, "loss": 0.3804, "lr": 3.863616506064714e-06, "epoch": 12.314268867924529, "percentage": 61.57, "elapsed_time": "0:40:01", "remaining_time": "0:24:58", "throughput": 5727.04, "total_tokens": 13752216} {"current_steps": 20890, "total_steps": 33920, "loss": 0.3229, "lr": 3.861111269852727e-06, "epoch": 12.317216981132075, "percentage": 61.59, "elapsed_time": "0:40:01", "remaining_time": "0:24:58", "throughput": 5727.13, "total_tokens": 13755480} {"current_steps": 20895, "total_steps": 33920, "loss": 0.3774, "lr": 3.858606335166439e-06, "epoch": 12.320165094339623, "percentage": 61.6, "elapsed_time": "0:40:02", "remaining_time": "0:24:57", "throughput": 5727.31, "total_tokens": 13759032} {"current_steps": 20900, "total_steps": 33920, "loss": 0.3099, "lr": 3.8561017026690415e-06, "epoch": 12.32311320754717, "percentage": 61.62, "elapsed_time": "0:40:02", "remaining_time": "0:24:56", "throughput": 5727.27, "total_tokens": 13761560} {"current_steps": 20905, "total_steps": 33920, "loss": 0.342, "lr": 3.8535973730236495e-06, "epoch": 12.326061320754716, "percentage": 61.63, "elapsed_time": "0:40:03", "remaining_time": "0:24:56", "throughput": 5727.25, "total_tokens": 13764248} {"current_steps": 20910, "total_steps": 33920, "loss": 0.4026, "lr": 3.851093346893294e-06, "epoch": 12.329009433962264, "percentage": 61.65, "elapsed_time": "0:40:03", "remaining_time": "0:24:55", "throughput": 5727.38, "total_tokens": 13767608} {"current_steps": 20915, "total_steps": 33920, "loss": 0.3981, "lr": 3.848589624940927e-06, "epoch": 12.33195754716981, "percentage": 61.66, "elapsed_time": "0:40:04", "remaining_time": "0:24:55", "throughput": 5727.56, "total_tokens": 13771256} {"current_steps": 20920, "total_steps": 33920, "loss": 0.3185, "lr": 3.846086207829417e-06, "epoch": 12.334905660377359, "percentage": 61.67, "elapsed_time": "0:40:04", "remaining_time": "0:24:54", "throughput": 5727.71, "total_tokens": 13774648} {"current_steps": 20925, "total_steps": 33920, "loss": 0.3138, "lr": 3.843583096221559e-06, "epoch": 12.337853773584905, "percentage": 61.69, "elapsed_time": "0:40:05", "remaining_time": "0:24:53", "throughput": 5727.96, "total_tokens": 13778488} {"current_steps": 20930, "total_steps": 33920, "loss": 0.3687, "lr": 3.8410802907800596e-06, "epoch": 12.340801886792454, "percentage": 61.7, "elapsed_time": "0:40:06", "remaining_time": "0:24:53", "throughput": 5728.0, "total_tokens": 13781624} {"current_steps": 20935, "total_steps": 33920, "loss": 0.5076, "lr": 3.838577792167546e-06, "epoch": 12.34375, "percentage": 61.72, "elapsed_time": "0:40:06", "remaining_time": "0:24:52", "throughput": 5728.03, "total_tokens": 13784568} {"current_steps": 20940, "total_steps": 33920, "loss": 0.2932, "lr": 3.836075601046569e-06, "epoch": 12.346698113207546, "percentage": 61.73, "elapsed_time": "0:40:07", "remaining_time": "0:24:52", "throughput": 5728.27, "total_tokens": 13788632} {"current_steps": 20945, "total_steps": 33920, "loss": 0.374, "lr": 3.833573718079594e-06, "epoch": 12.349646226415095, "percentage": 61.75, "elapsed_time": "0:40:07", "remaining_time": "0:24:51", "throughput": 5728.32, "total_tokens": 13791896} {"current_steps": 20950, "total_steps": 33920, "loss": 0.2401, "lr": 3.831072143929002e-06, "epoch": 12.352594339622641, "percentage": 61.76, "elapsed_time": "0:40:08", "remaining_time": "0:24:50", "throughput": 5728.46, "total_tokens": 13795416} {"current_steps": 20955, "total_steps": 33920, "loss": 0.3482, "lr": 3.828570879257098e-06, "epoch": 12.35554245283019, "percentage": 61.78, "elapsed_time": "0:40:08", "remaining_time": "0:24:50", "throughput": 5728.39, "total_tokens": 13797912} {"current_steps": 20960, "total_steps": 33920, "loss": 0.3678, "lr": 3.826069924726102e-06, "epoch": 12.358490566037736, "percentage": 61.79, "elapsed_time": "0:40:09", "remaining_time": "0:24:49", "throughput": 5728.59, "total_tokens": 13801752} {"current_steps": 20965, "total_steps": 33920, "loss": 0.2997, "lr": 3.823569280998154e-06, "epoch": 12.361438679245284, "percentage": 61.81, "elapsed_time": "0:40:10", "remaining_time": "0:24:49", "throughput": 5729.03, "total_tokens": 13809304} {"current_steps": 20970, "total_steps": 33920, "loss": 0.3491, "lr": 3.8210689487353095e-06, "epoch": 12.36438679245283, "percentage": 61.82, "elapsed_time": "0:40:10", "remaining_time": "0:24:48", "throughput": 5729.12, "total_tokens": 13812280} {"current_steps": 20975, "total_steps": 33920, "loss": 0.2966, "lr": 3.818568928599539e-06, "epoch": 12.367334905660377, "percentage": 61.84, "elapsed_time": "0:40:11", "remaining_time": "0:24:48", "throughput": 5729.31, "total_tokens": 13817144} {"current_steps": 20980, "total_steps": 33920, "loss": 0.3286, "lr": 3.816069221252739e-06, "epoch": 12.370283018867925, "percentage": 61.85, "elapsed_time": "0:40:12", "remaining_time": "0:24:47", "throughput": 5729.57, "total_tokens": 13821432} {"current_steps": 20985, "total_steps": 33920, "loss": 0.3445, "lr": 3.813569827356715e-06, "epoch": 12.373231132075471, "percentage": 61.87, "elapsed_time": "0:40:12", "remaining_time": "0:24:47", "throughput": 5729.69, "total_tokens": 13825016} {"current_steps": 20990, "total_steps": 33920, "loss": 0.3867, "lr": 3.811070747573191e-06, "epoch": 12.37617924528302, "percentage": 61.88, "elapsed_time": "0:40:13", "remaining_time": "0:24:46", "throughput": 5729.78, "total_tokens": 13828312} {"current_steps": 20995, "total_steps": 33920, "loss": 0.453, "lr": 3.8085719825638098e-06, "epoch": 12.379127358490566, "percentage": 61.9, "elapsed_time": "0:40:14", "remaining_time": "0:24:46", "throughput": 5730.05, "total_tokens": 13832824} {"current_steps": 21000, "total_steps": 33920, "loss": 0.3033, "lr": 3.806073532990132e-06, "epoch": 12.382075471698114, "percentage": 61.91, "elapsed_time": "0:40:14", "remaining_time": "0:24:45", "throughput": 5730.15, "total_tokens": 13836120} {"current_steps": 21005, "total_steps": 33920, "loss": 0.3448, "lr": 3.8035753995136333e-06, "epoch": 12.38502358490566, "percentage": 61.93, "elapsed_time": "0:40:15", "remaining_time": "0:24:45", "throughput": 5730.34, "total_tokens": 13840216} {"current_steps": 21010, "total_steps": 33920, "loss": 0.4171, "lr": 3.801077582795702e-06, "epoch": 12.387971698113208, "percentage": 61.94, "elapsed_time": "0:40:15", "remaining_time": "0:24:44", "throughput": 5730.3, "total_tokens": 13843288} {"current_steps": 21015, "total_steps": 33920, "loss": 0.4607, "lr": 3.7985800834976494e-06, "epoch": 12.390919811320755, "percentage": 61.95, "elapsed_time": "0:40:16", "remaining_time": "0:24:43", "throughput": 5730.56, "total_tokens": 13847256} {"current_steps": 21020, "total_steps": 33920, "loss": 0.3428, "lr": 3.7960829022806965e-06, "epoch": 12.393867924528301, "percentage": 61.97, "elapsed_time": "0:40:16", "remaining_time": "0:24:43", "throughput": 5730.48, "total_tokens": 13850040} {"current_steps": 21025, "total_steps": 33920, "loss": 0.3314, "lr": 3.793586039805984e-06, "epoch": 12.39681603773585, "percentage": 61.98, "elapsed_time": "0:40:17", "remaining_time": "0:24:42", "throughput": 5730.74, "total_tokens": 13854104} {"current_steps": 21030, "total_steps": 33920, "loss": 0.3496, "lr": 3.791089496734567e-06, "epoch": 12.399764150943396, "percentage": 62.0, "elapsed_time": "0:40:17", "remaining_time": "0:24:42", "throughput": 5730.81, "total_tokens": 13856984} {"current_steps": 21035, "total_steps": 33920, "loss": 0.2725, "lr": 3.7885932737274163e-06, "epoch": 12.402712264150944, "percentage": 62.01, "elapsed_time": "0:40:18", "remaining_time": "0:24:41", "throughput": 5731.06, "total_tokens": 13861144} {"current_steps": 21040, "total_steps": 33920, "loss": 0.3929, "lr": 3.7860973714454156e-06, "epoch": 12.40566037735849, "percentage": 62.03, "elapsed_time": "0:40:19", "remaining_time": "0:24:40", "throughput": 5731.06, "total_tokens": 13864024} {"current_steps": 21045, "total_steps": 33920, "loss": 0.3058, "lr": 3.7836017905493695e-06, "epoch": 12.408608490566039, "percentage": 62.04, "elapsed_time": "0:40:19", "remaining_time": "0:24:40", "throughput": 5731.24, "total_tokens": 13867576} {"current_steps": 21050, "total_steps": 33920, "loss": 0.3554, "lr": 3.7811065316999908e-06, "epoch": 12.411556603773585, "percentage": 62.06, "elapsed_time": "0:40:20", "remaining_time": "0:24:39", "throughput": 5731.39, "total_tokens": 13871256} {"current_steps": 21055, "total_steps": 33920, "loss": 0.3315, "lr": 3.7786115955579105e-06, "epoch": 12.414504716981131, "percentage": 62.07, "elapsed_time": "0:40:20", "remaining_time": "0:24:39", "throughput": 5731.51, "total_tokens": 13874904} {"current_steps": 21060, "total_steps": 33920, "loss": 0.371, "lr": 3.7761169827836746e-06, "epoch": 12.41745283018868, "percentage": 62.09, "elapsed_time": "0:40:21", "remaining_time": "0:24:38", "throughput": 5731.44, "total_tokens": 13877624} {"current_steps": 21065, "total_steps": 33920, "loss": 0.3955, "lr": 3.773622694037743e-06, "epoch": 12.420400943396226, "percentage": 62.1, "elapsed_time": "0:40:21", "remaining_time": "0:24:37", "throughput": 5731.71, "total_tokens": 13881560} {"current_steps": 21070, "total_steps": 33920, "loss": 0.3915, "lr": 3.7711287299804865e-06, "epoch": 12.423349056603774, "percentage": 62.12, "elapsed_time": "0:40:22", "remaining_time": "0:24:37", "throughput": 5731.84, "total_tokens": 13884760} {"current_steps": 21075, "total_steps": 33920, "loss": 0.3324, "lr": 3.768635091272197e-06, "epoch": 12.42629716981132, "percentage": 62.13, "elapsed_time": "0:40:22", "remaining_time": "0:24:36", "throughput": 5731.84, "total_tokens": 13887256} {"current_steps": 21080, "total_steps": 33920, "loss": 0.4246, "lr": 3.7661417785730732e-06, "epoch": 12.429245283018869, "percentage": 62.15, "elapsed_time": "0:40:23", "remaining_time": "0:24:36", "throughput": 5731.94, "total_tokens": 13890232} {"current_steps": 21085, "total_steps": 33920, "loss": 0.3136, "lr": 3.7636487925432304e-06, "epoch": 12.432193396226415, "percentage": 62.16, "elapsed_time": "0:40:23", "remaining_time": "0:24:35", "throughput": 5732.02, "total_tokens": 13893400} {"current_steps": 21090, "total_steps": 33920, "loss": 0.2962, "lr": 3.761156133842697e-06, "epoch": 12.435141509433961, "percentage": 62.18, "elapsed_time": "0:40:24", "remaining_time": "0:24:34", "throughput": 5732.16, "total_tokens": 13896856} {"current_steps": 21095, "total_steps": 33920, "loss": 0.3343, "lr": 3.7586638031314182e-06, "epoch": 12.43808962264151, "percentage": 62.19, "elapsed_time": "0:40:24", "remaining_time": "0:24:34", "throughput": 5732.36, "total_tokens": 13900568} {"current_steps": 21100, "total_steps": 33920, "loss": 0.5443, "lr": 3.7561718010692477e-06, "epoch": 12.441037735849056, "percentage": 62.21, "elapsed_time": "0:40:25", "remaining_time": "0:24:33", "throughput": 5732.39, "total_tokens": 13903576} {"current_steps": 21105, "total_steps": 33920, "loss": 0.3495, "lr": 3.7536801283159523e-06, "epoch": 12.443985849056604, "percentage": 62.22, "elapsed_time": "0:40:25", "remaining_time": "0:24:33", "throughput": 5732.37, "total_tokens": 13906296} {"current_steps": 21110, "total_steps": 33920, "loss": 0.4049, "lr": 3.7511887855312155e-06, "epoch": 12.44693396226415, "percentage": 62.23, "elapsed_time": "0:40:26", "remaining_time": "0:24:32", "throughput": 5732.57, "total_tokens": 13909752} {"current_steps": 21115, "total_steps": 33920, "loss": 0.3823, "lr": 3.74869777337463e-06, "epoch": 12.449882075471699, "percentage": 62.25, "elapsed_time": "0:40:26", "remaining_time": "0:24:31", "throughput": 5732.65, "total_tokens": 13912856} {"current_steps": 21120, "total_steps": 33920, "loss": 0.3385, "lr": 3.7462070925057004e-06, "epoch": 12.452830188679245, "percentage": 62.26, "elapsed_time": "0:40:27", "remaining_time": "0:24:31", "throughput": 5732.69, "total_tokens": 13915640} {"current_steps": 21125, "total_steps": 33920, "loss": 0.351, "lr": 3.7437167435838472e-06, "epoch": 12.455778301886792, "percentage": 62.28, "elapsed_time": "0:40:27", "remaining_time": "0:24:30", "throughput": 5732.81, "total_tokens": 13918904} {"current_steps": 21130, "total_steps": 33920, "loss": 0.3605, "lr": 3.741226727268401e-06, "epoch": 12.45872641509434, "percentage": 62.29, "elapsed_time": "0:40:28", "remaining_time": "0:24:29", "throughput": 5732.81, "total_tokens": 13921624} {"current_steps": 21135, "total_steps": 33920, "loss": 0.2984, "lr": 3.7387370442186027e-06, "epoch": 12.461674528301886, "percentage": 62.31, "elapsed_time": "0:40:28", "remaining_time": "0:24:29", "throughput": 5732.77, "total_tokens": 13924504} {"current_steps": 21140, "total_steps": 33920, "loss": 0.7629, "lr": 3.736247695093609e-06, "epoch": 12.464622641509434, "percentage": 62.32, "elapsed_time": "0:40:29", "remaining_time": "0:24:28", "throughput": 5732.88, "total_tokens": 13928088} {"current_steps": 21145, "total_steps": 33920, "loss": 0.3161, "lr": 3.7337586805524838e-06, "epoch": 12.46757075471698, "percentage": 62.34, "elapsed_time": "0:40:29", "remaining_time": "0:24:28", "throughput": 5732.78, "total_tokens": 13930456} {"current_steps": 21150, "total_steps": 33920, "loss": 0.291, "lr": 3.731270001254205e-06, "epoch": 12.470518867924529, "percentage": 62.35, "elapsed_time": "0:40:30", "remaining_time": "0:24:27", "throughput": 5732.85, "total_tokens": 13934360} {"current_steps": 21155, "total_steps": 33920, "loss": 0.256, "lr": 3.728781657857661e-06, "epoch": 12.473466981132075, "percentage": 62.37, "elapsed_time": "0:40:31", "remaining_time": "0:24:26", "throughput": 5732.97, "total_tokens": 13937752} {"current_steps": 21160, "total_steps": 33920, "loss": 0.2928, "lr": 3.726293651021653e-06, "epoch": 12.476415094339623, "percentage": 62.38, "elapsed_time": "0:40:31", "remaining_time": "0:24:26", "throughput": 5733.23, "total_tokens": 13941816} {"current_steps": 21165, "total_steps": 33920, "loss": 0.3602, "lr": 3.7238059814048888e-06, "epoch": 12.47936320754717, "percentage": 62.4, "elapsed_time": "0:40:32", "remaining_time": "0:24:25", "throughput": 5733.41, "total_tokens": 13945400} {"current_steps": 21170, "total_steps": 33920, "loss": 0.3461, "lr": 3.7213186496659916e-06, "epoch": 12.482311320754716, "percentage": 62.41, "elapsed_time": "0:40:32", "remaining_time": "0:24:25", "throughput": 5733.48, "total_tokens": 13948440} {"current_steps": 21175, "total_steps": 33920, "loss": 0.3034, "lr": 3.718831656463493e-06, "epoch": 12.485259433962264, "percentage": 62.43, "elapsed_time": "0:40:33", "remaining_time": "0:24:24", "throughput": 5733.65, "total_tokens": 13952024} {"current_steps": 21180, "total_steps": 33920, "loss": 0.4156, "lr": 3.7163450024558345e-06, "epoch": 12.48820754716981, "percentage": 62.44, "elapsed_time": "0:40:33", "remaining_time": "0:24:24", "throughput": 5733.82, "total_tokens": 13955480} {"current_steps": 21185, "total_steps": 33920, "loss": 0.3686, "lr": 3.7138586883013694e-06, "epoch": 12.491155660377359, "percentage": 62.46, "elapsed_time": "0:40:34", "remaining_time": "0:24:23", "throughput": 5733.88, "total_tokens": 13958456} {"current_steps": 21190, "total_steps": 33920, "loss": 0.3435, "lr": 3.7113727146583573e-06, "epoch": 12.494103773584905, "percentage": 62.47, "elapsed_time": "0:40:34", "remaining_time": "0:24:22", "throughput": 5733.92, "total_tokens": 13961528} {"current_steps": 21195, "total_steps": 33920, "loss": 0.3313, "lr": 3.7088870821849748e-06, "epoch": 12.497051886792454, "percentage": 62.49, "elapsed_time": "0:40:35", "remaining_time": "0:24:22", "throughput": 5734.11, "total_tokens": 13965048} {"current_steps": 21200, "total_steps": 33920, "loss": 0.4069, "lr": 3.706401791539301e-06, "epoch": 12.5, "percentage": 62.5, "elapsed_time": "0:40:36", "remaining_time": "0:24:21", "throughput": 5734.31, "total_tokens": 13968888} {"current_steps": 21205, "total_steps": 33920, "loss": 0.5053, "lr": 3.703916843379328e-06, "epoch": 12.502948113207546, "percentage": 62.51, "elapsed_time": "0:40:36", "remaining_time": "0:24:20", "throughput": 5734.42, "total_tokens": 13972056} {"current_steps": 21210, "total_steps": 33920, "loss": 0.2706, "lr": 3.7014322383629575e-06, "epoch": 12.505896226415095, "percentage": 62.53, "elapsed_time": "0:40:37", "remaining_time": "0:24:20", "throughput": 5734.46, "total_tokens": 13974904} {"current_steps": 21215, "total_steps": 33920, "loss": 0.3153, "lr": 3.6989479771479976e-06, "epoch": 12.508844339622641, "percentage": 62.54, "elapsed_time": "0:40:37", "remaining_time": "0:24:19", "throughput": 5734.45, "total_tokens": 13977752} {"current_steps": 21220, "total_steps": 33920, "loss": 0.4234, "lr": 3.696464060392169e-06, "epoch": 12.51179245283019, "percentage": 62.56, "elapsed_time": "0:40:38", "remaining_time": "0:24:19", "throughput": 5734.49, "total_tokens": 13980696} {"current_steps": 21225, "total_steps": 33920, "loss": 0.3982, "lr": 3.6939804887530962e-06, "epoch": 12.514740566037736, "percentage": 62.57, "elapsed_time": "0:40:38", "remaining_time": "0:24:18", "throughput": 5734.81, "total_tokens": 13985112} {"current_steps": 21230, "total_steps": 33920, "loss": 0.3047, "lr": 3.6914972628883196e-06, "epoch": 12.517688679245284, "percentage": 62.59, "elapsed_time": "0:40:39", "remaining_time": "0:24:17", "throughput": 5734.97, "total_tokens": 13988696} {"current_steps": 21235, "total_steps": 33920, "loss": 0.3805, "lr": 3.6890143834552814e-06, "epoch": 12.52063679245283, "percentage": 62.6, "elapsed_time": "0:40:39", "remaining_time": "0:24:17", "throughput": 5735.21, "total_tokens": 13993048} {"current_steps": 21240, "total_steps": 33920, "loss": 0.4184, "lr": 3.6865318511113347e-06, "epoch": 12.523584905660378, "percentage": 62.62, "elapsed_time": "0:40:40", "remaining_time": "0:24:16", "throughput": 5735.3, "total_tokens": 13996088} {"current_steps": 21245, "total_steps": 33920, "loss": 0.3745, "lr": 3.684049666513742e-06, "epoch": 12.526533018867925, "percentage": 62.63, "elapsed_time": "0:40:40", "remaining_time": "0:24:16", "throughput": 5735.47, "total_tokens": 13999512} {"current_steps": 21250, "total_steps": 33920, "loss": 0.3271, "lr": 3.6815678303196715e-06, "epoch": 12.529481132075471, "percentage": 62.65, "elapsed_time": "0:40:41", "remaining_time": "0:24:15", "throughput": 5735.67, "total_tokens": 14003512} {"current_steps": 21255, "total_steps": 33920, "loss": 0.388, "lr": 3.6790863431861988e-06, "epoch": 12.53242924528302, "percentage": 62.66, "elapsed_time": "0:40:42", "remaining_time": "0:24:15", "throughput": 5735.94, "total_tokens": 14007416} {"current_steps": 21260, "total_steps": 33920, "loss": 0.4144, "lr": 3.676605205770311e-06, "epoch": 12.535377358490566, "percentage": 62.68, "elapsed_time": "0:40:42", "remaining_time": "0:24:14", "throughput": 5736.03, "total_tokens": 14010456} {"current_steps": 21265, "total_steps": 33920, "loss": 0.2471, "lr": 3.674124418728898e-06, "epoch": 12.538325471698114, "percentage": 62.69, "elapsed_time": "0:40:43", "remaining_time": "0:24:14", "throughput": 5736.43, "total_tokens": 14016792} {"current_steps": 21270, "total_steps": 33920, "loss": 0.4034, "lr": 3.671643982718759e-06, "epoch": 12.54127358490566, "percentage": 62.71, "elapsed_time": "0:40:43", "remaining_time": "0:24:13", "throughput": 5736.49, "total_tokens": 14019864} {"current_steps": 21275, "total_steps": 33920, "loss": 0.4853, "lr": 3.6691638983966017e-06, "epoch": 12.544221698113208, "percentage": 62.72, "elapsed_time": "0:40:44", "remaining_time": "0:24:12", "throughput": 5736.57, "total_tokens": 14023320} {"current_steps": 21280, "total_steps": 33920, "loss": 0.3578, "lr": 3.666684166419037e-06, "epoch": 12.547169811320755, "percentage": 62.74, "elapsed_time": "0:40:45", "remaining_time": "0:24:12", "throughput": 5736.7, "total_tokens": 14026424} {"current_steps": 21285, "total_steps": 33920, "loss": 0.2375, "lr": 3.6642047874425833e-06, "epoch": 12.550117924528301, "percentage": 62.75, "elapsed_time": "0:40:45", "remaining_time": "0:24:11", "throughput": 5736.66, "total_tokens": 14029144} {"current_steps": 21290, "total_steps": 33920, "loss": 0.2837, "lr": 3.661725762123671e-06, "epoch": 12.55306603773585, "percentage": 62.77, "elapsed_time": "0:40:46", "remaining_time": "0:24:11", "throughput": 5736.67, "total_tokens": 14031992} {"current_steps": 21295, "total_steps": 33920, "loss": 0.2455, "lr": 3.659247091118631e-06, "epoch": 12.556014150943396, "percentage": 62.78, "elapsed_time": "0:40:46", "remaining_time": "0:24:10", "throughput": 5736.67, "total_tokens": 14034744} {"current_steps": 21300, "total_steps": 33920, "loss": 0.3363, "lr": 3.6567687750837027e-06, "epoch": 12.558962264150944, "percentage": 62.79, "elapsed_time": "0:40:47", "remaining_time": "0:24:09", "throughput": 5736.53, "total_tokens": 14037432} {"current_steps": 21305, "total_steps": 33920, "loss": 0.3465, "lr": 3.6542908146750287e-06, "epoch": 12.56191037735849, "percentage": 62.81, "elapsed_time": "0:40:47", "remaining_time": "0:24:09", "throughput": 5736.7, "total_tokens": 14040952} {"current_steps": 21310, "total_steps": 33920, "loss": 0.367, "lr": 3.6518132105486624e-06, "epoch": 12.564858490566039, "percentage": 62.82, "elapsed_time": "0:40:48", "remaining_time": "0:24:08", "throughput": 5736.67, "total_tokens": 14043736} {"current_steps": 21315, "total_steps": 33920, "loss": 0.2865, "lr": 3.649335963360559e-06, "epoch": 12.567806603773585, "percentage": 62.84, "elapsed_time": "0:40:48", "remaining_time": "0:24:08", "throughput": 5736.79, "total_tokens": 14047256} {"current_steps": 21320, "total_steps": 33920, "loss": 0.5007, "lr": 3.6468590737665795e-06, "epoch": 12.570754716981131, "percentage": 62.85, "elapsed_time": "0:40:49", "remaining_time": "0:24:07", "throughput": 5736.71, "total_tokens": 14049912} {"current_steps": 21325, "total_steps": 33920, "loss": 0.266, "lr": 3.6443825424224926e-06, "epoch": 12.57370283018868, "percentage": 62.87, "elapsed_time": "0:40:49", "remaining_time": "0:24:06", "throughput": 5736.67, "total_tokens": 14052504} {"current_steps": 21330, "total_steps": 33920, "loss": 0.3872, "lr": 3.64190636998397e-06, "epoch": 12.576650943396226, "percentage": 62.88, "elapsed_time": "0:40:50", "remaining_time": "0:24:06", "throughput": 5736.65, "total_tokens": 14055064} {"current_steps": 21335, "total_steps": 33920, "loss": 0.3636, "lr": 3.639430557106588e-06, "epoch": 12.579599056603774, "percentage": 62.9, "elapsed_time": "0:40:50", "remaining_time": "0:24:05", "throughput": 5736.69, "total_tokens": 14058008} {"current_steps": 21340, "total_steps": 33920, "loss": 0.3605, "lr": 3.6369551044458314e-06, "epoch": 12.58254716981132, "percentage": 62.91, "elapsed_time": "0:40:51", "remaining_time": "0:24:04", "throughput": 5736.74, "total_tokens": 14060856} {"current_steps": 21345, "total_steps": 33920, "loss": 0.3589, "lr": 3.6344800126570846e-06, "epoch": 12.585495283018869, "percentage": 62.93, "elapsed_time": "0:40:51", "remaining_time": "0:24:04", "throughput": 5736.87, "total_tokens": 14064344} {"current_steps": 21350, "total_steps": 33920, "loss": 0.2627, "lr": 3.6320052823956385e-06, "epoch": 12.588443396226415, "percentage": 62.94, "elapsed_time": "0:40:52", "remaining_time": "0:24:03", "throughput": 5736.96, "total_tokens": 14067576} {"current_steps": 21355, "total_steps": 33920, "loss": 0.3252, "lr": 3.6295309143166906e-06, "epoch": 12.591391509433961, "percentage": 62.96, "elapsed_time": "0:40:52", "remaining_time": "0:24:03", "throughput": 5737.27, "total_tokens": 14072024} {"current_steps": 21360, "total_steps": 33920, "loss": 0.3495, "lr": 3.62705690907534e-06, "epoch": 12.59433962264151, "percentage": 62.97, "elapsed_time": "0:40:53", "remaining_time": "0:24:02", "throughput": 5737.43, "total_tokens": 14075576} {"current_steps": 21365, "total_steps": 33920, "loss": 0.2777, "lr": 3.624583267326588e-06, "epoch": 12.597287735849056, "percentage": 62.99, "elapsed_time": "0:40:53", "remaining_time": "0:24:02", "throughput": 5737.76, "total_tokens": 14080312} {"current_steps": 21370, "total_steps": 33920, "loss": 0.3433, "lr": 3.6221099897253454e-06, "epoch": 12.600235849056604, "percentage": 63.0, "elapsed_time": "0:40:54", "remaining_time": "0:24:01", "throughput": 5737.92, "total_tokens": 14083896} {"current_steps": 21375, "total_steps": 33920, "loss": 0.2736, "lr": 3.619637076926421e-06, "epoch": 12.60318396226415, "percentage": 63.02, "elapsed_time": "0:40:55", "remaining_time": "0:24:00", "throughput": 5738.18, "total_tokens": 14087960} {"current_steps": 21380, "total_steps": 33920, "loss": 0.2839, "lr": 3.617164529584528e-06, "epoch": 12.606132075471699, "percentage": 63.03, "elapsed_time": "0:40:55", "remaining_time": "0:24:00", "throughput": 5738.07, "total_tokens": 14090264} {"current_steps": 21385, "total_steps": 33920, "loss": 0.4146, "lr": 3.614692348354286e-06, "epoch": 12.609080188679245, "percentage": 63.05, "elapsed_time": "0:40:56", "remaining_time": "0:23:59", "throughput": 5738.22, "total_tokens": 14093560} {"current_steps": 21390, "total_steps": 33920, "loss": 0.3498, "lr": 3.612220533890216e-06, "epoch": 12.612028301886792, "percentage": 63.06, "elapsed_time": "0:40:56", "remaining_time": "0:23:59", "throughput": 5738.26, "total_tokens": 14096472} {"current_steps": 21395, "total_steps": 33920, "loss": 0.3698, "lr": 3.609749086846741e-06, "epoch": 12.61497641509434, "percentage": 63.07, "elapsed_time": "0:40:57", "remaining_time": "0:23:58", "throughput": 5738.37, "total_tokens": 14100312} {"current_steps": 21400, "total_steps": 33920, "loss": 0.2872, "lr": 3.607278007878186e-06, "epoch": 12.617924528301886, "percentage": 63.09, "elapsed_time": "0:40:57", "remaining_time": "0:23:57", "throughput": 5738.1, "total_tokens": 14102616} {"current_steps": 21405, "total_steps": 33920, "loss": 0.314, "lr": 3.6048072976387817e-06, "epoch": 12.620872641509434, "percentage": 63.1, "elapsed_time": "0:40:58", "remaining_time": "0:23:57", "throughput": 5738.11, "total_tokens": 14105400} {"current_steps": 21410, "total_steps": 33920, "loss": 0.405, "lr": 3.6023369567826585e-06, "epoch": 12.62382075471698, "percentage": 63.12, "elapsed_time": "0:40:58", "remaining_time": "0:23:56", "throughput": 5738.14, "total_tokens": 14108504} {"current_steps": 21415, "total_steps": 33920, "loss": 0.2865, "lr": 3.599866985963848e-06, "epoch": 12.626768867924529, "percentage": 63.13, "elapsed_time": "0:40:59", "remaining_time": "0:23:56", "throughput": 5738.18, "total_tokens": 14111384} {"current_steps": 21420, "total_steps": 33920, "loss": 0.283, "lr": 3.5973973858362885e-06, "epoch": 12.629716981132075, "percentage": 63.15, "elapsed_time": "0:40:59", "remaining_time": "0:23:55", "throughput": 5738.2, "total_tokens": 14114232} {"current_steps": 21425, "total_steps": 33920, "loss": 0.2466, "lr": 3.594928157053816e-06, "epoch": 12.632665094339622, "percentage": 63.16, "elapsed_time": "0:41:00", "remaining_time": "0:23:54", "throughput": 5738.18, "total_tokens": 14116888} {"current_steps": 21430, "total_steps": 33920, "loss": 0.2654, "lr": 3.592459300270168e-06, "epoch": 12.63561320754717, "percentage": 63.18, "elapsed_time": "0:41:00", "remaining_time": "0:23:54", "throughput": 5738.18, "total_tokens": 14119736} {"current_steps": 21435, "total_steps": 33920, "loss": 0.2769, "lr": 3.589990816138988e-06, "epoch": 12.638561320754716, "percentage": 63.19, "elapsed_time": "0:41:01", "remaining_time": "0:23:53", "throughput": 5738.16, "total_tokens": 14122392} {"current_steps": 21440, "total_steps": 33920, "loss": 0.3971, "lr": 3.587522705313816e-06, "epoch": 12.641509433962264, "percentage": 63.21, "elapsed_time": "0:41:01", "remaining_time": "0:23:52", "throughput": 5738.18, "total_tokens": 14125176} {"current_steps": 21445, "total_steps": 33920, "loss": 0.3158, "lr": 3.585054968448094e-06, "epoch": 12.64445754716981, "percentage": 63.22, "elapsed_time": "0:41:02", "remaining_time": "0:23:52", "throughput": 5737.99, "total_tokens": 14127384} {"current_steps": 21450, "total_steps": 33920, "loss": 0.3986, "lr": 3.5825876061951686e-06, "epoch": 12.647405660377359, "percentage": 63.24, "elapsed_time": "0:41:02", "remaining_time": "0:23:51", "throughput": 5738.12, "total_tokens": 14130840} {"current_steps": 21455, "total_steps": 33920, "loss": 0.4326, "lr": 3.5801206192082818e-06, "epoch": 12.650353773584905, "percentage": 63.25, "elapsed_time": "0:41:03", "remaining_time": "0:23:51", "throughput": 5738.21, "total_tokens": 14133912} {"current_steps": 21460, "total_steps": 33920, "loss": 0.3284, "lr": 3.577654008140582e-06, "epoch": 12.653301886792454, "percentage": 63.27, "elapsed_time": "0:41:03", "remaining_time": "0:23:50", "throughput": 5738.3, "total_tokens": 14137368} {"current_steps": 21465, "total_steps": 33920, "loss": 0.2731, "lr": 3.5751877736451123e-06, "epoch": 12.65625, "percentage": 63.28, "elapsed_time": "0:41:04", "remaining_time": "0:23:49", "throughput": 5738.26, "total_tokens": 14139896} {"current_steps": 21470, "total_steps": 33920, "loss": 0.3394, "lr": 3.5727219163748205e-06, "epoch": 12.659198113207546, "percentage": 63.3, "elapsed_time": "0:41:04", "remaining_time": "0:23:49", "throughput": 5738.32, "total_tokens": 14142776} {"current_steps": 21475, "total_steps": 33920, "loss": 0.3508, "lr": 3.570256436982552e-06, "epoch": 12.662146226415095, "percentage": 63.31, "elapsed_time": "0:41:05", "remaining_time": "0:23:48", "throughput": 5738.35, "total_tokens": 14145720} {"current_steps": 21480, "total_steps": 33920, "loss": 0.2604, "lr": 3.5677913361210536e-06, "epoch": 12.665094339622641, "percentage": 63.33, "elapsed_time": "0:41:05", "remaining_time": "0:23:47", "throughput": 5738.34, "total_tokens": 14148632} {"current_steps": 21485, "total_steps": 33920, "loss": 0.2747, "lr": 3.565326614442972e-06, "epoch": 12.66804245283019, "percentage": 63.34, "elapsed_time": "0:41:06", "remaining_time": "0:23:47", "throughput": 5738.28, "total_tokens": 14151320} {"current_steps": 21490, "total_steps": 33920, "loss": 0.4355, "lr": 3.5628622726008523e-06, "epoch": 12.670990566037736, "percentage": 63.35, "elapsed_time": "0:41:06", "remaining_time": "0:23:46", "throughput": 5738.1, "total_tokens": 14153976} {"current_steps": 21495, "total_steps": 33920, "loss": 0.3607, "lr": 3.56039831124714e-06, "epoch": 12.673938679245284, "percentage": 63.37, "elapsed_time": "0:41:07", "remaining_time": "0:23:46", "throughput": 5738.05, "total_tokens": 14156728} {"current_steps": 21500, "total_steps": 33920, "loss": 0.3535, "lr": 3.557934731034179e-06, "epoch": 12.67688679245283, "percentage": 63.38, "elapsed_time": "0:41:07", "remaining_time": "0:23:45", "throughput": 5738.07, "total_tokens": 14159640} {"current_steps": 21505, "total_steps": 33920, "loss": 0.2289, "lr": 3.5554715326142126e-06, "epoch": 12.679834905660378, "percentage": 63.4, "elapsed_time": "0:41:08", "remaining_time": "0:23:44", "throughput": 5738.24, "total_tokens": 14162968} {"current_steps": 21510, "total_steps": 33920, "loss": 0.5167, "lr": 3.553008716639384e-06, "epoch": 12.682783018867925, "percentage": 63.41, "elapsed_time": "0:41:08", "remaining_time": "0:23:44", "throughput": 5738.31, "total_tokens": 14165784} {"current_steps": 21515, "total_steps": 33920, "loss": 0.2372, "lr": 3.5505462837617338e-06, "epoch": 12.685731132075471, "percentage": 63.43, "elapsed_time": "0:41:09", "remaining_time": "0:23:43", "throughput": 5738.47, "total_tokens": 14169400} {"current_steps": 21520, "total_steps": 33920, "loss": 0.2287, "lr": 3.5480842346332013e-06, "epoch": 12.68867924528302, "percentage": 63.44, "elapsed_time": "0:41:09", "remaining_time": "0:23:43", "throughput": 5738.53, "total_tokens": 14172792} {"current_steps": 21525, "total_steps": 33920, "loss": 0.3314, "lr": 3.5456225699056256e-06, "epoch": 12.691627358490566, "percentage": 63.46, "elapsed_time": "0:41:10", "remaining_time": "0:23:42", "throughput": 5738.8, "total_tokens": 14176920} {"current_steps": 21530, "total_steps": 33920, "loss": 0.3823, "lr": 3.5431612902307426e-06, "epoch": 12.694575471698114, "percentage": 63.47, "elapsed_time": "0:41:10", "remaining_time": "0:23:41", "throughput": 5738.86, "total_tokens": 14180120} {"current_steps": 21535, "total_steps": 33920, "loss": 0.4488, "lr": 3.540700396260186e-06, "epoch": 12.69752358490566, "percentage": 63.49, "elapsed_time": "0:41:11", "remaining_time": "0:23:41", "throughput": 5738.98, "total_tokens": 14183416} {"current_steps": 21540, "total_steps": 33920, "loss": 0.4419, "lr": 3.538239888645489e-06, "epoch": 12.700471698113208, "percentage": 63.5, "elapsed_time": "0:41:11", "remaining_time": "0:23:40", "throughput": 5739.08, "total_tokens": 14186392} {"current_steps": 21545, "total_steps": 33920, "loss": 0.459, "lr": 3.535779768038082e-06, "epoch": 12.703419811320755, "percentage": 63.52, "elapsed_time": "0:41:12", "remaining_time": "0:23:40", "throughput": 5739.1, "total_tokens": 14189208} {"current_steps": 21550, "total_steps": 33920, "loss": 0.4566, "lr": 3.5333200350892905e-06, "epoch": 12.706367924528301, "percentage": 63.53, "elapsed_time": "0:41:12", "remaining_time": "0:23:39", "throughput": 5739.29, "total_tokens": 14192984} {"current_steps": 21555, "total_steps": 33920, "loss": 0.3629, "lr": 3.530860690450342e-06, "epoch": 12.70931603773585, "percentage": 63.55, "elapsed_time": "0:41:13", "remaining_time": "0:23:38", "throughput": 5739.54, "total_tokens": 14197080} {"current_steps": 21560, "total_steps": 33920, "loss": 0.3295, "lr": 3.528401734772357e-06, "epoch": 12.712264150943396, "percentage": 63.56, "elapsed_time": "0:41:14", "remaining_time": "0:23:38", "throughput": 5739.29, "total_tokens": 14199256} {"current_steps": 21565, "total_steps": 33920, "loss": 0.2552, "lr": 3.5259431687063538e-06, "epoch": 12.715212264150944, "percentage": 63.58, "elapsed_time": "0:41:14", "remaining_time": "0:23:37", "throughput": 5739.29, "total_tokens": 14201976} {"current_steps": 21570, "total_steps": 33920, "loss": 0.2791, "lr": 3.523484992903249e-06, "epoch": 12.71816037735849, "percentage": 63.59, "elapsed_time": "0:41:15", "remaining_time": "0:23:37", "throughput": 5739.47, "total_tokens": 14205592} {"current_steps": 21575, "total_steps": 33920, "loss": 0.384, "lr": 3.5210272080138573e-06, "epoch": 12.721108490566039, "percentage": 63.61, "elapsed_time": "0:41:15", "remaining_time": "0:23:36", "throughput": 5739.7, "total_tokens": 14209464} {"current_steps": 21580, "total_steps": 33920, "loss": 0.4105, "lr": 3.518569814688887e-06, "epoch": 12.724056603773585, "percentage": 63.62, "elapsed_time": "0:41:16", "remaining_time": "0:23:35", "throughput": 5739.81, "total_tokens": 14212728} {"current_steps": 21585, "total_steps": 33920, "loss": 0.3753, "lr": 3.5161128135789414e-06, "epoch": 12.727004716981131, "percentage": 63.64, "elapsed_time": "0:41:16", "remaining_time": "0:23:35", "throughput": 5739.97, "total_tokens": 14216312} {"current_steps": 21590, "total_steps": 33920, "loss": 0.3197, "lr": 3.513656205334525e-06, "epoch": 12.72995283018868, "percentage": 63.65, "elapsed_time": "0:41:17", "remaining_time": "0:23:34", "throughput": 5739.95, "total_tokens": 14218968} {"current_steps": 21595, "total_steps": 33920, "loss": 0.2827, "lr": 3.5111999906060336e-06, "epoch": 12.732900943396226, "percentage": 63.66, "elapsed_time": "0:41:17", "remaining_time": "0:23:34", "throughput": 5740.1, "total_tokens": 14222328} {"current_steps": 21600, "total_steps": 33920, "loss": 0.4675, "lr": 3.50874417004376e-06, "epoch": 12.735849056603774, "percentage": 63.68, "elapsed_time": "0:41:18", "remaining_time": "0:23:33", "throughput": 5740.26, "total_tokens": 14225528} {"current_steps": 21605, "total_steps": 33920, "loss": 0.3047, "lr": 3.5062887442978956e-06, "epoch": 12.73879716981132, "percentage": 63.69, "elapsed_time": "0:41:18", "remaining_time": "0:23:32", "throughput": 5740.27, "total_tokens": 14228408} {"current_steps": 21610, "total_steps": 33920, "loss": 0.297, "lr": 3.503833714018524e-06, "epoch": 12.741745283018869, "percentage": 63.71, "elapsed_time": "0:41:19", "remaining_time": "0:23:32", "throughput": 5740.51, "total_tokens": 14232312} {"current_steps": 21615, "total_steps": 33920, "loss": 0.3918, "lr": 3.5013790798556228e-06, "epoch": 12.744693396226415, "percentage": 63.72, "elapsed_time": "0:41:19", "remaining_time": "0:23:31", "throughput": 5740.6, "total_tokens": 14235928} {"current_steps": 21620, "total_steps": 33920, "loss": 0.3303, "lr": 3.4989248424590705e-06, "epoch": 12.747641509433961, "percentage": 63.74, "elapsed_time": "0:41:20", "remaining_time": "0:23:31", "throughput": 5740.69, "total_tokens": 14238936} {"current_steps": 21625, "total_steps": 33920, "loss": 0.2812, "lr": 3.4964710024786354e-06, "epoch": 12.75058962264151, "percentage": 63.75, "elapsed_time": "0:41:20", "remaining_time": "0:23:30", "throughput": 5740.72, "total_tokens": 14241656} {"current_steps": 21630, "total_steps": 33920, "loss": 0.2856, "lr": 3.4940175605639813e-06, "epoch": 12.753537735849056, "percentage": 63.77, "elapsed_time": "0:41:21", "remaining_time": "0:23:29", "throughput": 5740.63, "total_tokens": 14244248} {"current_steps": 21635, "total_steps": 33920, "loss": 0.3195, "lr": 3.4915645173646694e-06, "epoch": 12.756485849056604, "percentage": 63.78, "elapsed_time": "0:41:21", "remaining_time": "0:23:29", "throughput": 5740.63, "total_tokens": 14247224} {"current_steps": 21640, "total_steps": 33920, "loss": 0.315, "lr": 3.489111873530153e-06, "epoch": 12.75943396226415, "percentage": 63.8, "elapsed_time": "0:41:22", "remaining_time": "0:23:28", "throughput": 5740.75, "total_tokens": 14250712} {"current_steps": 21645, "total_steps": 33920, "loss": 0.3571, "lr": 3.4866596297097776e-06, "epoch": 12.762382075471699, "percentage": 63.81, "elapsed_time": "0:41:22", "remaining_time": "0:23:28", "throughput": 5740.97, "total_tokens": 14254648} {"current_steps": 21650, "total_steps": 33920, "loss": 0.3032, "lr": 3.484207786552789e-06, "epoch": 12.765330188679245, "percentage": 63.83, "elapsed_time": "0:41:23", "remaining_time": "0:23:27", "throughput": 5741.22, "total_tokens": 14258648} {"current_steps": 21655, "total_steps": 33920, "loss": 0.3669, "lr": 3.4817563447083214e-06, "epoch": 12.768278301886792, "percentage": 63.84, "elapsed_time": "0:41:24", "remaining_time": "0:23:26", "throughput": 5741.37, "total_tokens": 14262104} {"current_steps": 21660, "total_steps": 33920, "loss": 0.3216, "lr": 3.4793053048254044e-06, "epoch": 12.77122641509434, "percentage": 63.86, "elapsed_time": "0:41:24", "remaining_time": "0:23:26", "throughput": 5741.47, "total_tokens": 14265336} {"current_steps": 21665, "total_steps": 33920, "loss": 0.3263, "lr": 3.47685466755296e-06, "epoch": 12.774174528301886, "percentage": 63.87, "elapsed_time": "0:41:25", "remaining_time": "0:23:25", "throughput": 5741.54, "total_tokens": 14268120} {"current_steps": 21670, "total_steps": 33920, "loss": 0.5095, "lr": 3.474404433539809e-06, "epoch": 12.777122641509434, "percentage": 63.89, "elapsed_time": "0:41:25", "remaining_time": "0:23:25", "throughput": 5741.56, "total_tokens": 14271032} {"current_steps": 21675, "total_steps": 33920, "loss": 0.3365, "lr": 3.4719546034346598e-06, "epoch": 12.78007075471698, "percentage": 63.9, "elapsed_time": "0:41:26", "remaining_time": "0:23:24", "throughput": 5741.66, "total_tokens": 14274584} {"current_steps": 21680, "total_steps": 33920, "loss": 0.4179, "lr": 3.4695051778861125e-06, "epoch": 12.783018867924529, "percentage": 63.92, "elapsed_time": "0:41:26", "remaining_time": "0:23:23", "throughput": 5741.75, "total_tokens": 14277656} {"current_steps": 21685, "total_steps": 33920, "loss": 0.2655, "lr": 3.4670561575426677e-06, "epoch": 12.785966981132075, "percentage": 63.93, "elapsed_time": "0:41:27", "remaining_time": "0:23:23", "throughput": 5742.02, "total_tokens": 14282296} {"current_steps": 21690, "total_steps": 33920, "loss": 0.3898, "lr": 3.4646075430527115e-06, "epoch": 12.788915094339622, "percentage": 63.94, "elapsed_time": "0:41:27", "remaining_time": "0:23:22", "throughput": 5742.13, "total_tokens": 14285624} {"current_steps": 21695, "total_steps": 33920, "loss": 0.3078, "lr": 3.4621593350645236e-06, "epoch": 12.79186320754717, "percentage": 63.96, "elapsed_time": "0:41:28", "remaining_time": "0:23:22", "throughput": 5742.22, "total_tokens": 14288760} {"current_steps": 21700, "total_steps": 33920, "loss": 0.3469, "lr": 3.4597115342262817e-06, "epoch": 12.794811320754716, "percentage": 63.97, "elapsed_time": "0:41:28", "remaining_time": "0:23:21", "throughput": 5742.41, "total_tokens": 14292760} {"current_steps": 21705, "total_steps": 33920, "loss": 0.3893, "lr": 3.4572641411860484e-06, "epoch": 12.797759433962264, "percentage": 63.99, "elapsed_time": "0:41:29", "remaining_time": "0:23:21", "throughput": 5742.46, "total_tokens": 14295672} {"current_steps": 21710, "total_steps": 33920, "loss": 0.4166, "lr": 3.454817156591782e-06, "epoch": 12.80070754716981, "percentage": 64.0, "elapsed_time": "0:41:29", "remaining_time": "0:23:20", "throughput": 5742.59, "total_tokens": 14298904} {"current_steps": 21715, "total_steps": 33920, "loss": 0.2914, "lr": 3.4523705810913344e-06, "epoch": 12.803655660377359, "percentage": 64.02, "elapsed_time": "0:41:30", "remaining_time": "0:23:19", "throughput": 5742.7, "total_tokens": 14302136} {"current_steps": 21720, "total_steps": 33920, "loss": 0.2723, "lr": 3.449924415332443e-06, "epoch": 12.806603773584905, "percentage": 64.03, "elapsed_time": "0:41:31", "remaining_time": "0:23:19", "throughput": 5742.87, "total_tokens": 14305560} {"current_steps": 21725, "total_steps": 33920, "loss": 0.2802, "lr": 3.447478659962745e-06, "epoch": 12.809551886792454, "percentage": 64.05, "elapsed_time": "0:41:31", "remaining_time": "0:23:18", "throughput": 5743.03, "total_tokens": 14308920} {"current_steps": 21730, "total_steps": 33920, "loss": 0.3263, "lr": 3.4450333156297625e-06, "epoch": 12.8125, "percentage": 64.06, "elapsed_time": "0:41:31", "remaining_time": "0:23:17", "throughput": 5742.94, "total_tokens": 14311384} {"current_steps": 21735, "total_steps": 33920, "loss": 0.5398, "lr": 3.44258838298091e-06, "epoch": 12.815448113207546, "percentage": 64.08, "elapsed_time": "0:41:32", "remaining_time": "0:23:17", "throughput": 5743.12, "total_tokens": 14314840} {"current_steps": 21740, "total_steps": 33920, "loss": 0.288, "lr": 3.440143862663497e-06, "epoch": 12.818396226415095, "percentage": 64.09, "elapsed_time": "0:41:33", "remaining_time": "0:23:16", "throughput": 5743.1, "total_tokens": 14317784} {"current_steps": 21745, "total_steps": 33920, "loss": 0.3975, "lr": 3.4376997553247183e-06, "epoch": 12.821344339622641, "percentage": 64.11, "elapsed_time": "0:41:33", "remaining_time": "0:23:16", "throughput": 5743.17, "total_tokens": 14320792} {"current_steps": 21750, "total_steps": 33920, "loss": 0.3337, "lr": 3.4352560616116617e-06, "epoch": 12.82429245283019, "percentage": 64.12, "elapsed_time": "0:41:34", "remaining_time": "0:23:15", "throughput": 5743.18, "total_tokens": 14324280} {"current_steps": 21755, "total_steps": 33920, "loss": 0.3133, "lr": 3.4328127821713077e-06, "epoch": 12.827240566037736, "percentage": 64.14, "elapsed_time": "0:41:34", "remaining_time": "0:23:14", "throughput": 5743.27, "total_tokens": 14327448} {"current_steps": 21760, "total_steps": 33920, "loss": 0.3709, "lr": 3.430369917650521e-06, "epoch": 12.830188679245284, "percentage": 64.15, "elapsed_time": "0:41:35", "remaining_time": "0:23:14", "throughput": 5743.39, "total_tokens": 14330648} {"current_steps": 21765, "total_steps": 33920, "loss": 0.4263, "lr": 3.427927468696066e-06, "epoch": 12.83313679245283, "percentage": 64.17, "elapsed_time": "0:41:35", "remaining_time": "0:23:13", "throughput": 5743.39, "total_tokens": 14333528} {"current_steps": 21770, "total_steps": 33920, "loss": 0.3723, "lr": 3.425485435954588e-06, "epoch": 12.836084905660378, "percentage": 64.18, "elapsed_time": "0:41:36", "remaining_time": "0:23:13", "throughput": 5743.49, "total_tokens": 14337176} {"current_steps": 21775, "total_steps": 33920, "loss": 0.3806, "lr": 3.4230438200726274e-06, "epoch": 12.839033018867925, "percentage": 64.2, "elapsed_time": "0:41:36", "remaining_time": "0:23:12", "throughput": 5743.62, "total_tokens": 14340408} {"current_steps": 21780, "total_steps": 33920, "loss": 0.3038, "lr": 3.4206026216966113e-06, "epoch": 12.841981132075471, "percentage": 64.21, "elapsed_time": "0:41:37", "remaining_time": "0:23:11", "throughput": 5743.75, "total_tokens": 14343672} {"current_steps": 21785, "total_steps": 33920, "loss": 0.3872, "lr": 3.418161841472858e-06, "epoch": 12.84492924528302, "percentage": 64.22, "elapsed_time": "0:41:37", "remaining_time": "0:23:11", "throughput": 5743.89, "total_tokens": 14347032} {"current_steps": 21790, "total_steps": 33920, "loss": 0.3607, "lr": 3.4157214800475746e-06, "epoch": 12.847877358490566, "percentage": 64.24, "elapsed_time": "0:41:38", "remaining_time": "0:23:10", "throughput": 5743.97, "total_tokens": 14349976} {"current_steps": 21795, "total_steps": 33920, "loss": 0.4601, "lr": 3.4132815380668577e-06, "epoch": 12.850825471698114, "percentage": 64.25, "elapsed_time": "0:41:38", "remaining_time": "0:23:10", "throughput": 5743.94, "total_tokens": 14352920} {"current_steps": 21800, "total_steps": 33920, "loss": 0.2856, "lr": 3.410842016176691e-06, "epoch": 12.85377358490566, "percentage": 64.27, "elapsed_time": "0:41:39", "remaining_time": "0:23:09", "throughput": 5743.79, "total_tokens": 14355064} {"current_steps": 21805, "total_steps": 33920, "loss": 0.2267, "lr": 3.4084029150229503e-06, "epoch": 12.856721698113208, "percentage": 64.28, "elapsed_time": "0:41:39", "remaining_time": "0:23:08", "throughput": 5743.53, "total_tokens": 14356920} {"current_steps": 21810, "total_steps": 33920, "loss": 0.3542, "lr": 3.4059642352513965e-06, "epoch": 12.859669811320755, "percentage": 64.3, "elapsed_time": "0:41:40", "remaining_time": "0:23:08", "throughput": 5743.66, "total_tokens": 14360632} {"current_steps": 21815, "total_steps": 33920, "loss": 0.3205, "lr": 3.4035259775076813e-06, "epoch": 12.862617924528301, "percentage": 64.31, "elapsed_time": "0:41:40", "remaining_time": "0:23:07", "throughput": 5743.79, "total_tokens": 14363736} {"current_steps": 21820, "total_steps": 33920, "loss": 0.3331, "lr": 3.401088142437344e-06, "epoch": 12.86556603773585, "percentage": 64.33, "elapsed_time": "0:41:41", "remaining_time": "0:23:07", "throughput": 5743.83, "total_tokens": 14367768} {"current_steps": 21825, "total_steps": 33920, "loss": 0.475, "lr": 3.398650730685813e-06, "epoch": 12.868514150943396, "percentage": 64.34, "elapsed_time": "0:41:42", "remaining_time": "0:23:06", "throughput": 5743.97, "total_tokens": 14371704} {"current_steps": 21830, "total_steps": 33920, "loss": 0.3183, "lr": 3.396213742898401e-06, "epoch": 12.871462264150944, "percentage": 64.36, "elapsed_time": "0:41:42", "remaining_time": "0:23:06", "throughput": 5744.03, "total_tokens": 14375032} {"current_steps": 21835, "total_steps": 33920, "loss": 0.4404, "lr": 3.3937771797203134e-06, "epoch": 12.87441037735849, "percentage": 64.37, "elapsed_time": "0:41:43", "remaining_time": "0:23:05", "throughput": 5744.03, "total_tokens": 14377880} {"current_steps": 21840, "total_steps": 33920, "loss": 0.4054, "lr": 3.391341041796641e-06, "epoch": 12.877358490566039, "percentage": 64.39, "elapsed_time": "0:41:43", "remaining_time": "0:23:04", "throughput": 5744.06, "total_tokens": 14380568} {"current_steps": 21845, "total_steps": 33920, "loss": 0.378, "lr": 3.3889053297723585e-06, "epoch": 12.880306603773585, "percentage": 64.4, "elapsed_time": "0:41:44", "remaining_time": "0:23:04", "throughput": 5744.19, "total_tokens": 14384248} {"current_steps": 21850, "total_steps": 33920, "loss": 0.361, "lr": 3.3864700442923342e-06, "epoch": 12.883254716981131, "percentage": 64.42, "elapsed_time": "0:41:44", "remaining_time": "0:23:03", "throughput": 5744.2, "total_tokens": 14387192} {"current_steps": 21855, "total_steps": 33920, "loss": 0.3772, "lr": 3.384035186001318e-06, "epoch": 12.88620283018868, "percentage": 64.43, "elapsed_time": "0:41:45", "remaining_time": "0:23:02", "throughput": 5744.22, "total_tokens": 14390296} {"current_steps": 21860, "total_steps": 33920, "loss": 0.3419, "lr": 3.381600755543953e-06, "epoch": 12.889150943396226, "percentage": 64.45, "elapsed_time": "0:41:45", "remaining_time": "0:23:02", "throughput": 5744.17, "total_tokens": 14392920} {"current_steps": 21865, "total_steps": 33920, "loss": 0.3246, "lr": 3.3791667535647615e-06, "epoch": 12.892099056603774, "percentage": 64.46, "elapsed_time": "0:41:46", "remaining_time": "0:23:01", "throughput": 5744.28, "total_tokens": 14396120} {"current_steps": 21870, "total_steps": 33920, "loss": 0.3179, "lr": 3.3767331807081584e-06, "epoch": 12.89504716981132, "percentage": 64.48, "elapsed_time": "0:41:46", "remaining_time": "0:23:01", "throughput": 5744.42, "total_tokens": 14399320} {"current_steps": 21875, "total_steps": 33920, "loss": 0.3085, "lr": 3.374300037618442e-06, "epoch": 12.897995283018869, "percentage": 64.49, "elapsed_time": "0:41:47", "remaining_time": "0:23:00", "throughput": 5744.52, "total_tokens": 14402488} {"current_steps": 21880, "total_steps": 33920, "loss": 0.3202, "lr": 3.371867324939796e-06, "epoch": 12.900943396226415, "percentage": 64.5, "elapsed_time": "0:41:47", "remaining_time": "0:22:59", "throughput": 5744.68, "total_tokens": 14406328} {"current_steps": 21885, "total_steps": 33920, "loss": 0.3929, "lr": 3.369435043316293e-06, "epoch": 12.903891509433961, "percentage": 64.52, "elapsed_time": "0:41:48", "remaining_time": "0:22:59", "throughput": 5744.73, "total_tokens": 14409656} {"current_steps": 21890, "total_steps": 33920, "loss": 0.4727, "lr": 3.36700319339189e-06, "epoch": 12.90683962264151, "percentage": 64.53, "elapsed_time": "0:41:48", "remaining_time": "0:22:58", "throughput": 5744.52, "total_tokens": 14411640} {"current_steps": 21895, "total_steps": 33920, "loss": 0.4173, "lr": 3.3645717758104286e-06, "epoch": 12.909787735849056, "percentage": 64.55, "elapsed_time": "0:41:49", "remaining_time": "0:22:58", "throughput": 5744.51, "total_tokens": 14414200} {"current_steps": 21900, "total_steps": 33920, "loss": 0.3922, "lr": 3.3621407912156383e-06, "epoch": 12.912735849056604, "percentage": 64.56, "elapsed_time": "0:41:49", "remaining_time": "0:22:57", "throughput": 5744.68, "total_tokens": 14418104} {"current_steps": 21905, "total_steps": 33920, "loss": 0.3998, "lr": 3.3597102402511326e-06, "epoch": 12.91568396226415, "percentage": 64.58, "elapsed_time": "0:41:50", "remaining_time": "0:22:56", "throughput": 5744.75, "total_tokens": 14420984} {"current_steps": 21910, "total_steps": 33920, "loss": 0.322, "lr": 3.3572801235604093e-06, "epoch": 12.918632075471699, "percentage": 64.59, "elapsed_time": "0:41:50", "remaining_time": "0:22:56", "throughput": 5744.81, "total_tokens": 14423896} {"current_steps": 21915, "total_steps": 33920, "loss": 0.321, "lr": 3.3548504417868538e-06, "epoch": 12.921580188679245, "percentage": 64.61, "elapsed_time": "0:41:51", "remaining_time": "0:22:55", "throughput": 5745.01, "total_tokens": 14428056} {"current_steps": 21920, "total_steps": 33920, "loss": 0.3853, "lr": 3.352421195573734e-06, "epoch": 12.924528301886792, "percentage": 64.62, "elapsed_time": "0:41:51", "remaining_time": "0:22:55", "throughput": 5745.19, "total_tokens": 14431576} {"current_steps": 21925, "total_steps": 33920, "loss": 0.4072, "lr": 3.3499923855642026e-06, "epoch": 12.92747641509434, "percentage": 64.64, "elapsed_time": "0:41:53", "remaining_time": "0:22:54", "throughput": 5745.63, "total_tokens": 14438936} {"current_steps": 21930, "total_steps": 33920, "loss": 0.3307, "lr": 3.3475640124012986e-06, "epoch": 12.930424528301886, "percentage": 64.65, "elapsed_time": "0:41:53", "remaining_time": "0:22:54", "throughput": 5745.81, "total_tokens": 14442360} {"current_steps": 21935, "total_steps": 33920, "loss": 0.3261, "lr": 3.345136076727945e-06, "epoch": 12.933372641509434, "percentage": 64.67, "elapsed_time": "0:41:54", "remaining_time": "0:22:53", "throughput": 5745.79, "total_tokens": 14444952} {"current_steps": 21940, "total_steps": 33920, "loss": 0.3067, "lr": 3.3427085791869453e-06, "epoch": 12.93632075471698, "percentage": 64.68, "elapsed_time": "0:41:54", "remaining_time": "0:22:53", "throughput": 5746.06, "total_tokens": 14449272} {"current_steps": 21945, "total_steps": 33920, "loss": 0.3564, "lr": 3.3402815204209926e-06, "epoch": 12.939268867924529, "percentage": 64.7, "elapsed_time": "0:41:55", "remaining_time": "0:22:52", "throughput": 5746.01, "total_tokens": 14451992} {"current_steps": 21950, "total_steps": 33920, "loss": 0.3303, "lr": 3.337854901072659e-06, "epoch": 12.942216981132075, "percentage": 64.71, "elapsed_time": "0:41:55", "remaining_time": "0:22:51", "throughput": 5746.43, "total_tokens": 14457336} {"current_steps": 21955, "total_steps": 33920, "loss": 0.3419, "lr": 3.3354287217844056e-06, "epoch": 12.945165094339622, "percentage": 64.73, "elapsed_time": "0:41:56", "remaining_time": "0:22:51", "throughput": 5746.66, "total_tokens": 14461144} {"current_steps": 21960, "total_steps": 33920, "loss": 0.305, "lr": 3.3330029831985712e-06, "epoch": 12.94811320754717, "percentage": 64.74, "elapsed_time": "0:41:56", "remaining_time": "0:22:50", "throughput": 5746.68, "total_tokens": 14464088} {"current_steps": 21965, "total_steps": 33920, "loss": 0.3907, "lr": 3.330577685957382e-06, "epoch": 12.951061320754716, "percentage": 64.76, "elapsed_time": "0:41:57", "remaining_time": "0:22:50", "throughput": 5746.99, "total_tokens": 14468856} {"current_steps": 21970, "total_steps": 33920, "loss": 0.4445, "lr": 3.3281528307029454e-06, "epoch": 12.954009433962264, "percentage": 64.77, "elapsed_time": "0:41:58", "remaining_time": "0:22:49", "throughput": 5747.05, "total_tokens": 14471960} {"current_steps": 21975, "total_steps": 33920, "loss": 0.4279, "lr": 3.325728418077251e-06, "epoch": 12.95695754716981, "percentage": 64.78, "elapsed_time": "0:41:58", "remaining_time": "0:22:49", "throughput": 5747.02, "total_tokens": 14474904} {"current_steps": 21980, "total_steps": 33920, "loss": 0.3593, "lr": 3.3233044487221744e-06, "epoch": 12.959905660377359, "percentage": 64.8, "elapsed_time": "0:41:59", "remaining_time": "0:22:48", "throughput": 5747.1, "total_tokens": 14477944} {"current_steps": 21985, "total_steps": 33920, "loss": 0.3274, "lr": 3.3208809232794715e-06, "epoch": 12.962853773584905, "percentage": 64.81, "elapsed_time": "0:41:59", "remaining_time": "0:22:47", "throughput": 5747.35, "total_tokens": 14482008} {"current_steps": 21990, "total_steps": 33920, "loss": 0.3005, "lr": 3.3184578423907797e-06, "epoch": 12.965801886792454, "percentage": 64.83, "elapsed_time": "0:42:00", "remaining_time": "0:22:47", "throughput": 5747.48, "total_tokens": 14485400} {"current_steps": 21995, "total_steps": 33920, "loss": 0.3466, "lr": 3.3160352066976224e-06, "epoch": 12.96875, "percentage": 64.84, "elapsed_time": "0:42:00", "remaining_time": "0:22:46", "throughput": 5747.54, "total_tokens": 14488408} {"current_steps": 22000, "total_steps": 33920, "loss": 0.3197, "lr": 3.3136130168414003e-06, "epoch": 12.971698113207546, "percentage": 64.86, "elapsed_time": "0:42:01", "remaining_time": "0:22:46", "throughput": 5747.51, "total_tokens": 14491416} {"current_steps": 22005, "total_steps": 33920, "loss": 0.3662, "lr": 3.311191273463401e-06, "epoch": 12.974646226415095, "percentage": 64.87, "elapsed_time": "0:42:01", "remaining_time": "0:22:45", "throughput": 5747.59, "total_tokens": 14494424} {"current_steps": 22010, "total_steps": 33920, "loss": 0.3907, "lr": 3.3087699772047908e-06, "epoch": 12.977594339622641, "percentage": 64.89, "elapsed_time": "0:42:02", "remaining_time": "0:22:44", "throughput": 5747.67, "total_tokens": 14497496} {"current_steps": 22015, "total_steps": 33920, "loss": 0.423, "lr": 3.3063491287066164e-06, "epoch": 12.98054245283019, "percentage": 64.9, "elapsed_time": "0:42:02", "remaining_time": "0:22:44", "throughput": 5747.8, "total_tokens": 14500568} {"current_steps": 22020, "total_steps": 33920, "loss": 0.4309, "lr": 3.303928728609811e-06, "epoch": 12.983490566037736, "percentage": 64.92, "elapsed_time": "0:42:03", "remaining_time": "0:22:43", "throughput": 5747.7, "total_tokens": 14502904} {"current_steps": 22025, "total_steps": 33920, "loss": 0.2976, "lr": 3.3015087775551835e-06, "epoch": 12.986438679245284, "percentage": 64.93, "elapsed_time": "0:42:03", "remaining_time": "0:22:43", "throughput": 5747.84, "total_tokens": 14506328} {"current_steps": 22030, "total_steps": 33920, "loss": 0.2607, "lr": 3.299089276183427e-06, "epoch": 12.98938679245283, "percentage": 64.95, "elapsed_time": "0:42:04", "remaining_time": "0:22:42", "throughput": 5747.94, "total_tokens": 14509304} {"current_steps": 22035, "total_steps": 33920, "loss": 0.3234, "lr": 3.2966702251351157e-06, "epoch": 12.992334905660378, "percentage": 64.96, "elapsed_time": "0:42:04", "remaining_time": "0:22:41", "throughput": 5748.05, "total_tokens": 14512344} {"current_steps": 22040, "total_steps": 33920, "loss": 0.4604, "lr": 3.2942516250507035e-06, "epoch": 12.995283018867925, "percentage": 64.98, "elapsed_time": "0:42:05", "remaining_time": "0:22:41", "throughput": 5748.0, "total_tokens": 14515000} {"current_steps": 22045, "total_steps": 33920, "loss": 0.3141, "lr": 3.2918334765705227e-06, "epoch": 12.998231132075471, "percentage": 64.99, "elapsed_time": "0:42:05", "remaining_time": "0:22:40", "throughput": 5748.08, "total_tokens": 14517976} {"current_steps": 22050, "total_steps": 33920, "loss": 0.3004, "lr": 3.289415780334792e-06, "epoch": 13.00117924528302, "percentage": 65.01, "elapsed_time": "0:42:06", "remaining_time": "0:22:40", "throughput": 5747.71, "total_tokens": 14522088} {"current_steps": 22055, "total_steps": 33920, "loss": 0.2574, "lr": 3.2869985369836067e-06, "epoch": 13.004127358490566, "percentage": 65.02, "elapsed_time": "0:42:07", "remaining_time": "0:22:39", "throughput": 5747.92, "total_tokens": 14525736} {"current_steps": 22060, "total_steps": 33920, "loss": 0.3146, "lr": 3.2845817471569406e-06, "epoch": 13.007075471698114, "percentage": 65.04, "elapsed_time": "0:42:07", "remaining_time": "0:22:38", "throughput": 5747.94, "total_tokens": 14528712} {"current_steps": 22065, "total_steps": 33920, "loss": 0.291, "lr": 3.28216541149465e-06, "epoch": 13.01002358490566, "percentage": 65.05, "elapsed_time": "0:42:08", "remaining_time": "0:22:38", "throughput": 5747.83, "total_tokens": 14531464} {"current_steps": 22070, "total_steps": 33920, "loss": 0.3103, "lr": 3.2797495306364707e-06, "epoch": 13.012971698113208, "percentage": 65.06, "elapsed_time": "0:42:08", "remaining_time": "0:22:37", "throughput": 5747.6, "total_tokens": 14534056} {"current_steps": 22075, "total_steps": 33920, "loss": 0.3898, "lr": 3.2773341052220174e-06, "epoch": 13.015919811320755, "percentage": 65.08, "elapsed_time": "0:42:09", "remaining_time": "0:22:37", "throughput": 5747.63, "total_tokens": 14537480} {"current_steps": 22080, "total_steps": 33920, "loss": 0.2681, "lr": 3.274919135890783e-06, "epoch": 13.018867924528301, "percentage": 65.09, "elapsed_time": "0:42:09", "remaining_time": "0:22:36", "throughput": 5747.89, "total_tokens": 14541864} {"current_steps": 22085, "total_steps": 33920, "loss": 0.3226, "lr": 3.2725046232821424e-06, "epoch": 13.02181603773585, "percentage": 65.11, "elapsed_time": "0:42:10", "remaining_time": "0:22:36", "throughput": 5748.25, "total_tokens": 14547944} {"current_steps": 22090, "total_steps": 33920, "loss": 0.3688, "lr": 3.270090568035348e-06, "epoch": 13.024764150943396, "percentage": 65.12, "elapsed_time": "0:42:11", "remaining_time": "0:22:35", "throughput": 5748.28, "total_tokens": 14550824} {"current_steps": 22095, "total_steps": 33920, "loss": 0.388, "lr": 3.2676769707895306e-06, "epoch": 13.027712264150944, "percentage": 65.14, "elapsed_time": "0:42:11", "remaining_time": "0:22:35", "throughput": 5748.36, "total_tokens": 14554376} {"current_steps": 22100, "total_steps": 33920, "loss": 0.2622, "lr": 3.2652638321837015e-06, "epoch": 13.03066037735849, "percentage": 65.15, "elapsed_time": "0:42:12", "remaining_time": "0:22:34", "throughput": 5748.29, "total_tokens": 14556904} {"current_steps": 22105, "total_steps": 33920, "loss": 0.3999, "lr": 3.2628511528567497e-06, "epoch": 13.033608490566039, "percentage": 65.17, "elapsed_time": "0:42:12", "remaining_time": "0:22:33", "throughput": 5748.44, "total_tokens": 14560488} {"current_steps": 22110, "total_steps": 33920, "loss": 0.3344, "lr": 3.2604389334474407e-06, "epoch": 13.036556603773585, "percentage": 65.18, "elapsed_time": "0:42:13", "remaining_time": "0:22:33", "throughput": 5748.49, "total_tokens": 14563464} {"current_steps": 22115, "total_steps": 33920, "loss": 0.2874, "lr": 3.2580271745944224e-06, "epoch": 13.039504716981131, "percentage": 65.2, "elapsed_time": "0:42:13", "remaining_time": "0:22:32", "throughput": 5748.44, "total_tokens": 14566120} {"current_steps": 22120, "total_steps": 33920, "loss": 0.4695, "lr": 3.255615876936217e-06, "epoch": 13.04245283018868, "percentage": 65.21, "elapsed_time": "0:42:14", "remaining_time": "0:22:31", "throughput": 5748.44, "total_tokens": 14568936} {"current_steps": 22125, "total_steps": 33920, "loss": 0.3362, "lr": 3.2532050411112248e-06, "epoch": 13.045400943396226, "percentage": 65.23, "elapsed_time": "0:42:15", "remaining_time": "0:22:31", "throughput": 5748.7, "total_tokens": 14573736} {"current_steps": 22130, "total_steps": 33920, "loss": 0.4699, "lr": 3.2507946677577274e-06, "epoch": 13.048349056603774, "percentage": 65.24, "elapsed_time": "0:42:15", "remaining_time": "0:22:30", "throughput": 5748.86, "total_tokens": 14577512} {"current_steps": 22135, "total_steps": 33920, "loss": 0.2792, "lr": 3.2483847575138807e-06, "epoch": 13.05129716981132, "percentage": 65.26, "elapsed_time": "0:42:16", "remaining_time": "0:22:30", "throughput": 5748.86, "total_tokens": 14580584} {"current_steps": 22140, "total_steps": 33920, "loss": 0.2794, "lr": 3.245975311017716e-06, "epoch": 13.054245283018869, "percentage": 65.27, "elapsed_time": "0:42:16", "remaining_time": "0:22:29", "throughput": 5748.73, "total_tokens": 14583080} {"current_steps": 22145, "total_steps": 33920, "loss": 0.4468, "lr": 3.2435663289071486e-06, "epoch": 13.057193396226415, "percentage": 65.29, "elapsed_time": "0:42:17", "remaining_time": "0:22:29", "throughput": 5748.8, "total_tokens": 14586056} {"current_steps": 22150, "total_steps": 33920, "loss": 0.2751, "lr": 3.241157811819966e-06, "epoch": 13.060141509433961, "percentage": 65.3, "elapsed_time": "0:42:17", "remaining_time": "0:22:28", "throughput": 5748.82, "total_tokens": 14589160} {"current_steps": 22155, "total_steps": 33920, "loss": 0.4967, "lr": 3.2387497603938327e-06, "epoch": 13.06308962264151, "percentage": 65.32, "elapsed_time": "0:42:18", "remaining_time": "0:22:27", "throughput": 5748.8, "total_tokens": 14592232} {"current_steps": 22160, "total_steps": 33920, "loss": 0.2827, "lr": 3.2363421752662903e-06, "epoch": 13.066037735849056, "percentage": 65.33, "elapsed_time": "0:42:18", "remaining_time": "0:22:27", "throughput": 5748.92, "total_tokens": 14596008} {"current_steps": 22165, "total_steps": 33920, "loss": 0.276, "lr": 3.233935057074759e-06, "epoch": 13.068985849056604, "percentage": 65.34, "elapsed_time": "0:42:19", "remaining_time": "0:22:26", "throughput": 5748.96, "total_tokens": 14599144} {"current_steps": 22170, "total_steps": 33920, "loss": 0.4082, "lr": 3.2315284064565324e-06, "epoch": 13.07193396226415, "percentage": 65.36, "elapsed_time": "0:42:20", "remaining_time": "0:22:26", "throughput": 5749.04, "total_tokens": 14602600} {"current_steps": 22175, "total_steps": 33920, "loss": 0.3568, "lr": 3.2291222240487813e-06, "epoch": 13.074882075471699, "percentage": 65.37, "elapsed_time": "0:42:20", "remaining_time": "0:22:25", "throughput": 5749.23, "total_tokens": 14606184} {"current_steps": 22180, "total_steps": 33920, "loss": 0.2755, "lr": 3.226716510488554e-06, "epoch": 13.077830188679245, "percentage": 65.39, "elapsed_time": "0:42:21", "remaining_time": "0:22:25", "throughput": 5749.28, "total_tokens": 14609384} {"current_steps": 22185, "total_steps": 33920, "loss": 0.2669, "lr": 3.224311266412773e-06, "epoch": 13.080778301886792, "percentage": 65.4, "elapsed_time": "0:42:21", "remaining_time": "0:22:24", "throughput": 5749.39, "total_tokens": 14612872} {"current_steps": 22190, "total_steps": 33920, "loss": 0.2443, "lr": 3.2219064924582366e-06, "epoch": 13.08372641509434, "percentage": 65.42, "elapsed_time": "0:42:22", "remaining_time": "0:22:23", "throughput": 5749.52, "total_tokens": 14616552} {"current_steps": 22195, "total_steps": 33920, "loss": 0.3891, "lr": 3.2195021892616197e-06, "epoch": 13.086674528301886, "percentage": 65.43, "elapsed_time": "0:42:22", "remaining_time": "0:22:23", "throughput": 5749.56, "total_tokens": 14619528} {"current_steps": 22200, "total_steps": 33920, "loss": 0.3605, "lr": 3.217098357459472e-06, "epoch": 13.089622641509434, "percentage": 65.45, "elapsed_time": "0:42:23", "remaining_time": "0:22:22", "throughput": 5749.51, "total_tokens": 14622312} {"current_steps": 22205, "total_steps": 33920, "loss": 0.4457, "lr": 3.214694997688217e-06, "epoch": 13.09257075471698, "percentage": 65.46, "elapsed_time": "0:42:23", "remaining_time": "0:22:22", "throughput": 5749.57, "total_tokens": 14625416} {"current_steps": 22210, "total_steps": 33920, "loss": 0.4045, "lr": 3.2122921105841572e-06, "epoch": 13.095518867924529, "percentage": 65.48, "elapsed_time": "0:42:24", "remaining_time": "0:22:21", "throughput": 5749.54, "total_tokens": 14628200} {"current_steps": 22215, "total_steps": 33920, "loss": 0.3506, "lr": 3.2098896967834647e-06, "epoch": 13.098466981132075, "percentage": 65.49, "elapsed_time": "0:42:24", "remaining_time": "0:22:20", "throughput": 5749.62, "total_tokens": 14631464} {"current_steps": 22220, "total_steps": 33920, "loss": 0.245, "lr": 3.2074877569221896e-06, "epoch": 13.101415094339623, "percentage": 65.51, "elapsed_time": "0:42:25", "remaining_time": "0:22:20", "throughput": 5749.66, "total_tokens": 14634472} {"current_steps": 22225, "total_steps": 33920, "loss": 0.2453, "lr": 3.205086291636257e-06, "epoch": 13.10436320754717, "percentage": 65.52, "elapsed_time": "0:42:25", "remaining_time": "0:22:19", "throughput": 5749.7, "total_tokens": 14637384} {"current_steps": 22230, "total_steps": 33920, "loss": 0.2829, "lr": 3.202685301561463e-06, "epoch": 13.107311320754716, "percentage": 65.54, "elapsed_time": "0:42:26", "remaining_time": "0:22:19", "throughput": 5749.81, "total_tokens": 14640776} {"current_steps": 22235, "total_steps": 33920, "loss": 0.346, "lr": 3.200284787333482e-06, "epoch": 13.110259433962264, "percentage": 65.55, "elapsed_time": "0:42:26", "remaining_time": "0:22:18", "throughput": 5749.76, "total_tokens": 14643464} {"current_steps": 22240, "total_steps": 33920, "loss": 0.3029, "lr": 3.1978847495878595e-06, "epoch": 13.11320754716981, "percentage": 65.57, "elapsed_time": "0:42:27", "remaining_time": "0:22:17", "throughput": 5749.83, "total_tokens": 14646504} {"current_steps": 22245, "total_steps": 33920, "loss": 0.3179, "lr": 3.1954851889600176e-06, "epoch": 13.116155660377359, "percentage": 65.58, "elapsed_time": "0:42:27", "remaining_time": "0:22:17", "throughput": 5749.91, "total_tokens": 14649704} {"current_steps": 22250, "total_steps": 33920, "loss": 0.3348, "lr": 3.1930861060852485e-06, "epoch": 13.119103773584905, "percentage": 65.6, "elapsed_time": "0:42:28", "remaining_time": "0:22:16", "throughput": 5750.21, "total_tokens": 14654216} {"current_steps": 22255, "total_steps": 33920, "loss": 0.3633, "lr": 3.1906875015987194e-06, "epoch": 13.122051886792454, "percentage": 65.61, "elapsed_time": "0:42:28", "remaining_time": "0:22:16", "throughput": 5750.29, "total_tokens": 14657448} {"current_steps": 22260, "total_steps": 33920, "loss": 0.4501, "lr": 3.188289376135473e-06, "epoch": 13.125, "percentage": 65.62, "elapsed_time": "0:42:29", "remaining_time": "0:22:15", "throughput": 5750.41, "total_tokens": 14661032} {"current_steps": 22265, "total_steps": 33920, "loss": 0.2817, "lr": 3.1858917303304213e-06, "epoch": 13.127948113207546, "percentage": 65.64, "elapsed_time": "0:42:30", "remaining_time": "0:22:14", "throughput": 5750.63, "total_tokens": 14665320} {"current_steps": 22270, "total_steps": 33920, "loss": 0.3238, "lr": 3.1834945648183535e-06, "epoch": 13.130896226415095, "percentage": 65.65, "elapsed_time": "0:42:30", "remaining_time": "0:22:14", "throughput": 5750.84, "total_tokens": 14669736} {"current_steps": 22275, "total_steps": 33920, "loss": 0.3776, "lr": 3.1810978802339283e-06, "epoch": 13.133844339622641, "percentage": 65.67, "elapsed_time": "0:42:31", "remaining_time": "0:22:13", "throughput": 5750.83, "total_tokens": 14673064} {"current_steps": 22280, "total_steps": 33920, "loss": 0.3201, "lr": 3.1787016772116767e-06, "epoch": 13.13679245283019, "percentage": 65.68, "elapsed_time": "0:42:32", "remaining_time": "0:22:13", "throughput": 5751.01, "total_tokens": 14676936} {"current_steps": 22285, "total_steps": 33920, "loss": 0.3818, "lr": 3.1763059563860073e-06, "epoch": 13.139740566037736, "percentage": 65.7, "elapsed_time": "0:42:32", "remaining_time": "0:22:12", "throughput": 5751.04, "total_tokens": 14679720} {"current_steps": 22290, "total_steps": 33920, "loss": 0.3889, "lr": 3.1739107183911953e-06, "epoch": 13.142688679245284, "percentage": 65.71, "elapsed_time": "0:42:33", "remaining_time": "0:22:12", "throughput": 5750.94, "total_tokens": 14682472} {"current_steps": 22295, "total_steps": 33920, "loss": 0.3778, "lr": 3.1715159638613898e-06, "epoch": 13.14563679245283, "percentage": 65.73, "elapsed_time": "0:42:33", "remaining_time": "0:22:11", "throughput": 5751.02, "total_tokens": 14685960} {"current_steps": 22300, "total_steps": 33920, "loss": 0.4128, "lr": 3.1691216934306134e-06, "epoch": 13.148584905660377, "percentage": 65.74, "elapsed_time": "0:42:34", "remaining_time": "0:22:10", "throughput": 5751.12, "total_tokens": 14688904} {"current_steps": 22305, "total_steps": 33920, "loss": 0.3374, "lr": 3.16672790773276e-06, "epoch": 13.151533018867925, "percentage": 65.76, "elapsed_time": "0:42:34", "remaining_time": "0:22:10", "throughput": 5751.1, "total_tokens": 14691720} {"current_steps": 22310, "total_steps": 33920, "loss": 0.3709, "lr": 3.164334607401593e-06, "epoch": 13.154481132075471, "percentage": 65.77, "elapsed_time": "0:42:35", "remaining_time": "0:22:09", "throughput": 5751.08, "total_tokens": 14694408} {"current_steps": 22315, "total_steps": 33920, "loss": 0.318, "lr": 3.1619417930707506e-06, "epoch": 13.15742924528302, "percentage": 65.79, "elapsed_time": "0:42:35", "remaining_time": "0:22:09", "throughput": 5751.16, "total_tokens": 14697448} {"current_steps": 22320, "total_steps": 33920, "loss": 0.3549, "lr": 3.1595494653737408e-06, "epoch": 13.160377358490566, "percentage": 65.8, "elapsed_time": "0:42:36", "remaining_time": "0:22:08", "throughput": 5751.22, "total_tokens": 14700584} {"current_steps": 22325, "total_steps": 33920, "loss": 0.3209, "lr": 3.1571576249439408e-06, "epoch": 13.163325471698114, "percentage": 65.82, "elapsed_time": "0:42:36", "remaining_time": "0:22:07", "throughput": 5751.3, "total_tokens": 14703880} {"current_steps": 22330, "total_steps": 33920, "loss": 0.3372, "lr": 3.1547662724146e-06, "epoch": 13.16627358490566, "percentage": 65.83, "elapsed_time": "0:42:37", "remaining_time": "0:22:07", "throughput": 5751.37, "total_tokens": 14706920} {"current_steps": 22335, "total_steps": 33920, "loss": 0.3073, "lr": 3.1523754084188436e-06, "epoch": 13.169221698113208, "percentage": 65.85, "elapsed_time": "0:42:37", "remaining_time": "0:22:06", "throughput": 5751.45, "total_tokens": 14710248} {"current_steps": 22340, "total_steps": 33920, "loss": 0.2152, "lr": 3.149985033589661e-06, "epoch": 13.172169811320755, "percentage": 65.86, "elapsed_time": "0:42:38", "remaining_time": "0:22:06", "throughput": 5751.7, "total_tokens": 14715336} {"current_steps": 22345, "total_steps": 33920, "loss": 0.3285, "lr": 3.147595148559912e-06, "epoch": 13.175117924528301, "percentage": 65.88, "elapsed_time": "0:42:39", "remaining_time": "0:22:05", "throughput": 5751.92, "total_tokens": 14719304} {"current_steps": 22350, "total_steps": 33920, "loss": 0.3234, "lr": 3.1452057539623328e-06, "epoch": 13.17806603773585, "percentage": 65.89, "elapsed_time": "0:42:39", "remaining_time": "0:22:05", "throughput": 5751.91, "total_tokens": 14722408} {"current_steps": 22355, "total_steps": 33920, "loss": 0.274, "lr": 3.142816850429523e-06, "epoch": 13.181014150943396, "percentage": 65.91, "elapsed_time": "0:42:40", "remaining_time": "0:22:04", "throughput": 5751.9, "total_tokens": 14725032} {"current_steps": 22360, "total_steps": 33920, "loss": 0.4382, "lr": 3.1404284385939552e-06, "epoch": 13.183962264150944, "percentage": 65.92, "elapsed_time": "0:42:40", "remaining_time": "0:22:03", "throughput": 5751.97, "total_tokens": 14728328} {"current_steps": 22365, "total_steps": 33920, "loss": 0.3403, "lr": 3.138040519087975e-06, "epoch": 13.18691037735849, "percentage": 65.93, "elapsed_time": "0:42:41", "remaining_time": "0:22:03", "throughput": 5752.06, "total_tokens": 14731464} {"current_steps": 22370, "total_steps": 33920, "loss": 0.2795, "lr": 3.13565309254379e-06, "epoch": 13.189858490566039, "percentage": 65.95, "elapsed_time": "0:42:41", "remaining_time": "0:22:02", "throughput": 5752.11, "total_tokens": 14734344} {"current_steps": 22375, "total_steps": 33920, "loss": 0.3897, "lr": 3.1332661595934845e-06, "epoch": 13.192806603773585, "percentage": 65.96, "elapsed_time": "0:42:42", "remaining_time": "0:22:02", "throughput": 5752.37, "total_tokens": 14738536} {"current_steps": 22380, "total_steps": 33920, "loss": 0.3192, "lr": 3.130879720869008e-06, "epoch": 13.195754716981131, "percentage": 65.98, "elapsed_time": "0:42:42", "remaining_time": "0:22:01", "throughput": 5752.46, "total_tokens": 14741672} {"current_steps": 22385, "total_steps": 33920, "loss": 0.2924, "lr": 3.1284937770021815e-06, "epoch": 13.19870283018868, "percentage": 65.99, "elapsed_time": "0:42:43", "remaining_time": "0:22:00", "throughput": 5752.65, "total_tokens": 14745288} {"current_steps": 22390, "total_steps": 33920, "loss": 0.2757, "lr": 3.1261083286246916e-06, "epoch": 13.201650943396226, "percentage": 66.01, "elapsed_time": "0:42:43", "remaining_time": "0:22:00", "throughput": 5752.72, "total_tokens": 14748360} {"current_steps": 22395, "total_steps": 33920, "loss": 0.317, "lr": 3.1237233763680997e-06, "epoch": 13.204599056603774, "percentage": 66.02, "elapsed_time": "0:42:44", "remaining_time": "0:21:59", "throughput": 5752.8, "total_tokens": 14751432} {"current_steps": 22400, "total_steps": 33920, "loss": 0.2729, "lr": 3.1213389208638303e-06, "epoch": 13.20754716981132, "percentage": 66.04, "elapsed_time": "0:42:44", "remaining_time": "0:21:58", "throughput": 5752.72, "total_tokens": 14753896} {"current_steps": 22405, "total_steps": 33920, "loss": 0.2267, "lr": 3.1189549627431757e-06, "epoch": 13.210495283018869, "percentage": 66.05, "elapsed_time": "0:42:45", "remaining_time": "0:21:58", "throughput": 5752.69, "total_tokens": 14756840} {"current_steps": 22410, "total_steps": 33920, "loss": 0.3488, "lr": 3.116571502637304e-06, "epoch": 13.213443396226415, "percentage": 66.07, "elapsed_time": "0:42:45", "remaining_time": "0:21:57", "throughput": 5752.57, "total_tokens": 14759240} {"current_steps": 22415, "total_steps": 33920, "loss": 0.433, "lr": 3.1141885411772434e-06, "epoch": 13.216391509433961, "percentage": 66.08, "elapsed_time": "0:42:46", "remaining_time": "0:21:57", "throughput": 5752.84, "total_tokens": 14764296} {"current_steps": 22420, "total_steps": 33920, "loss": 0.3271, "lr": 3.111806078993893e-06, "epoch": 13.21933962264151, "percentage": 66.1, "elapsed_time": "0:42:46", "remaining_time": "0:21:56", "throughput": 5752.93, "total_tokens": 14767336} {"current_steps": 22425, "total_steps": 33920, "loss": 0.5165, "lr": 3.1094241167180223e-06, "epoch": 13.222287735849056, "percentage": 66.11, "elapsed_time": "0:42:48", "remaining_time": "0:21:56", "throughput": 5753.24, "total_tokens": 14774344} {"current_steps": 22430, "total_steps": 33920, "loss": 0.2756, "lr": 3.1070426549802623e-06, "epoch": 13.225235849056604, "percentage": 66.13, "elapsed_time": "0:42:48", "remaining_time": "0:21:55", "throughput": 5753.28, "total_tokens": 14777448} {"current_steps": 22435, "total_steps": 33920, "loss": 0.3208, "lr": 3.1046616944111196e-06, "epoch": 13.22818396226415, "percentage": 66.14, "elapsed_time": "0:42:48", "remaining_time": "0:21:55", "throughput": 5753.34, "total_tokens": 14780296} {"current_steps": 22440, "total_steps": 33920, "loss": 0.2922, "lr": 3.1022812356409606e-06, "epoch": 13.231132075471699, "percentage": 66.16, "elapsed_time": "0:42:49", "remaining_time": "0:21:54", "throughput": 5753.5, "total_tokens": 14783976} {"current_steps": 22445, "total_steps": 33920, "loss": 0.2837, "lr": 3.0999012793000244e-06, "epoch": 13.234080188679245, "percentage": 66.17, "elapsed_time": "0:42:50", "remaining_time": "0:21:53", "throughput": 5753.52, "total_tokens": 14787048} {"current_steps": 22450, "total_steps": 33920, "loss": 0.3257, "lr": 3.097521826018414e-06, "epoch": 13.237028301886792, "percentage": 66.19, "elapsed_time": "0:42:50", "remaining_time": "0:21:53", "throughput": 5753.48, "total_tokens": 14790152} {"current_steps": 22455, "total_steps": 33920, "loss": 0.4397, "lr": 3.0951428764260973e-06, "epoch": 13.23997641509434, "percentage": 66.2, "elapsed_time": "0:42:51", "remaining_time": "0:21:52", "throughput": 5753.64, "total_tokens": 14793480} {"current_steps": 22460, "total_steps": 33920, "loss": 0.3633, "lr": 3.092764431152915e-06, "epoch": 13.242924528301886, "percentage": 66.21, "elapsed_time": "0:42:51", "remaining_time": "0:21:52", "throughput": 5753.66, "total_tokens": 14796200} {"current_steps": 22465, "total_steps": 33920, "loss": 0.2893, "lr": 3.0903864908285693e-06, "epoch": 13.245872641509434, "percentage": 66.23, "elapsed_time": "0:42:52", "remaining_time": "0:21:51", "throughput": 5753.91, "total_tokens": 14800808} {"current_steps": 22470, "total_steps": 33920, "loss": 0.2858, "lr": 3.088009056082629e-06, "epoch": 13.24882075471698, "percentage": 66.24, "elapsed_time": "0:42:52", "remaining_time": "0:21:51", "throughput": 5754.05, "total_tokens": 14804264} {"current_steps": 22475, "total_steps": 33920, "loss": 0.2097, "lr": 3.0856321275445324e-06, "epoch": 13.251768867924529, "percentage": 66.26, "elapsed_time": "0:42:53", "remaining_time": "0:21:50", "throughput": 5754.01, "total_tokens": 14806920} {"current_steps": 22480, "total_steps": 33920, "loss": 0.2354, "lr": 3.0832557058435808e-06, "epoch": 13.254716981132075, "percentage": 66.27, "elapsed_time": "0:42:53", "remaining_time": "0:21:49", "throughput": 5754.22, "total_tokens": 14810696} {"current_steps": 22485, "total_steps": 33920, "loss": 0.3885, "lr": 3.0808797916089405e-06, "epoch": 13.257665094339623, "percentage": 66.29, "elapsed_time": "0:42:54", "remaining_time": "0:21:49", "throughput": 5754.08, "total_tokens": 14813064} {"current_steps": 22490, "total_steps": 33920, "loss": 0.381, "lr": 3.078504385469647e-06, "epoch": 13.26061320754717, "percentage": 66.3, "elapsed_time": "0:42:54", "remaining_time": "0:21:48", "throughput": 5754.09, "total_tokens": 14816360} {"current_steps": 22495, "total_steps": 33920, "loss": 0.3041, "lr": 3.076129488054599e-06, "epoch": 13.263561320754716, "percentage": 66.32, "elapsed_time": "0:42:55", "remaining_time": "0:21:48", "throughput": 5754.36, "total_tokens": 14820616} {"current_steps": 22500, "total_steps": 33920, "loss": 0.3681, "lr": 3.0737550999925604e-06, "epoch": 13.266509433962264, "percentage": 66.33, "elapsed_time": "0:42:56", "remaining_time": "0:21:47", "throughput": 5754.33, "total_tokens": 14823496} {"current_steps": 22505, "total_steps": 33920, "loss": 0.2802, "lr": 3.0713812219121604e-06, "epoch": 13.26945754716981, "percentage": 66.35, "elapsed_time": "0:42:56", "remaining_time": "0:21:46", "throughput": 5754.31, "total_tokens": 14826248} {"current_steps": 22510, "total_steps": 33920, "loss": 0.4064, "lr": 3.0690078544418934e-06, "epoch": 13.272405660377359, "percentage": 66.36, "elapsed_time": "0:42:57", "remaining_time": "0:21:46", "throughput": 5754.34, "total_tokens": 14829320} {"current_steps": 22515, "total_steps": 33920, "loss": 0.399, "lr": 3.0666349982101198e-06, "epoch": 13.275353773584905, "percentage": 66.38, "elapsed_time": "0:42:57", "remaining_time": "0:21:45", "throughput": 5754.38, "total_tokens": 14832456} {"current_steps": 22520, "total_steps": 33920, "loss": 0.3385, "lr": 3.0642626538450627e-06, "epoch": 13.278301886792454, "percentage": 66.39, "elapsed_time": "0:42:58", "remaining_time": "0:21:45", "throughput": 5754.54, "total_tokens": 14836232} {"current_steps": 22525, "total_steps": 33920, "loss": 0.357, "lr": 3.061890821974809e-06, "epoch": 13.28125, "percentage": 66.41, "elapsed_time": "0:42:58", "remaining_time": "0:21:44", "throughput": 5754.48, "total_tokens": 14839208} {"current_steps": 22530, "total_steps": 33920, "loss": 0.2742, "lr": 3.059519503227313e-06, "epoch": 13.284198113207546, "percentage": 66.42, "elapsed_time": "0:42:59", "remaining_time": "0:21:43", "throughput": 5754.38, "total_tokens": 14841832} {"current_steps": 22535, "total_steps": 33920, "loss": 0.2822, "lr": 3.057148698230393e-06, "epoch": 13.287146226415095, "percentage": 66.44, "elapsed_time": "0:42:59", "remaining_time": "0:21:43", "throughput": 5754.64, "total_tokens": 14846280} {"current_steps": 22540, "total_steps": 33920, "loss": 0.3982, "lr": 3.0547784076117294e-06, "epoch": 13.290094339622641, "percentage": 66.45, "elapsed_time": "0:43:00", "remaining_time": "0:21:42", "throughput": 5754.3, "total_tokens": 14848584} {"current_steps": 22545, "total_steps": 33920, "loss": 0.3064, "lr": 3.0524086319988635e-06, "epoch": 13.29304245283019, "percentage": 66.47, "elapsed_time": "0:43:00", "remaining_time": "0:21:42", "throughput": 5754.32, "total_tokens": 14851560} {"current_steps": 22550, "total_steps": 33920, "loss": 0.3257, "lr": 3.0500393720192074e-06, "epoch": 13.295990566037736, "percentage": 66.48, "elapsed_time": "0:43:01", "remaining_time": "0:21:41", "throughput": 5754.45, "total_tokens": 14854888} {"current_steps": 22555, "total_steps": 33920, "loss": 0.3345, "lr": 3.047670628300031e-06, "epoch": 13.298938679245284, "percentage": 66.49, "elapsed_time": "0:43:01", "remaining_time": "0:21:41", "throughput": 5754.57, "total_tokens": 14858120} {"current_steps": 22560, "total_steps": 33920, "loss": 0.2805, "lr": 3.0453024014684694e-06, "epoch": 13.30188679245283, "percentage": 66.51, "elapsed_time": "0:43:02", "remaining_time": "0:21:40", "throughput": 5754.49, "total_tokens": 14860616} {"current_steps": 22565, "total_steps": 33920, "loss": 0.3274, "lr": 3.0429346921515225e-06, "epoch": 13.304834905660377, "percentage": 66.52, "elapsed_time": "0:43:02", "remaining_time": "0:21:39", "throughput": 5754.55, "total_tokens": 14863944} {"current_steps": 22570, "total_steps": 33920, "loss": 0.2823, "lr": 3.04056750097605e-06, "epoch": 13.307783018867925, "percentage": 66.54, "elapsed_time": "0:43:03", "remaining_time": "0:21:39", "throughput": 5754.49, "total_tokens": 14866568} {"current_steps": 22575, "total_steps": 33920, "loss": 0.2766, "lr": 3.0382008285687754e-06, "epoch": 13.310731132075471, "percentage": 66.55, "elapsed_time": "0:43:03", "remaining_time": "0:21:38", "throughput": 5754.61, "total_tokens": 14869896} {"current_steps": 22580, "total_steps": 33920, "loss": 0.347, "lr": 3.035834675556287e-06, "epoch": 13.31367924528302, "percentage": 66.57, "elapsed_time": "0:43:04", "remaining_time": "0:21:37", "throughput": 5754.63, "total_tokens": 14873064} {"current_steps": 22585, "total_steps": 33920, "loss": 0.3775, "lr": 3.0334690425650336e-06, "epoch": 13.316627358490566, "percentage": 66.58, "elapsed_time": "0:43:05", "remaining_time": "0:21:37", "throughput": 5754.78, "total_tokens": 14876392} {"current_steps": 22590, "total_steps": 33920, "loss": 0.3082, "lr": 3.031103930221325e-06, "epoch": 13.319575471698114, "percentage": 66.6, "elapsed_time": "0:43:05", "remaining_time": "0:21:36", "throughput": 5754.67, "total_tokens": 14878792} {"current_steps": 22595, "total_steps": 33920, "loss": 0.2647, "lr": 3.028739339151338e-06, "epoch": 13.32252358490566, "percentage": 66.61, "elapsed_time": "0:43:06", "remaining_time": "0:21:36", "throughput": 5754.82, "total_tokens": 14882120} {"current_steps": 22600, "total_steps": 33920, "loss": 0.3383, "lr": 3.0263752699811067e-06, "epoch": 13.325471698113208, "percentage": 66.63, "elapsed_time": "0:43:06", "remaining_time": "0:21:35", "throughput": 5755.03, "total_tokens": 14886120} {"current_steps": 22605, "total_steps": 33920, "loss": 0.3003, "lr": 3.0240117233365267e-06, "epoch": 13.328419811320755, "percentage": 66.64, "elapsed_time": "0:43:07", "remaining_time": "0:21:35", "throughput": 5755.21, "total_tokens": 14889800} {"current_steps": 22610, "total_steps": 33920, "loss": 0.418, "lr": 3.0216486998433604e-06, "epoch": 13.331367924528301, "percentage": 66.66, "elapsed_time": "0:43:07", "remaining_time": "0:21:34", "throughput": 5755.01, "total_tokens": 14892040} {"current_steps": 22615, "total_steps": 33920, "loss": 0.4085, "lr": 3.0192862001272273e-06, "epoch": 13.33431603773585, "percentage": 66.67, "elapsed_time": "0:43:08", "remaining_time": "0:21:33", "throughput": 5755.07, "total_tokens": 14895272} {"current_steps": 22620, "total_steps": 33920, "loss": 0.4102, "lr": 3.0169242248136066e-06, "epoch": 13.337264150943396, "percentage": 66.69, "elapsed_time": "0:43:08", "remaining_time": "0:21:33", "throughput": 5755.09, "total_tokens": 14898216} {"current_steps": 22625, "total_steps": 33920, "loss": 0.4281, "lr": 3.0145627745278457e-06, "epoch": 13.340212264150944, "percentage": 66.7, "elapsed_time": "0:43:09", "remaining_time": "0:21:32", "throughput": 5755.34, "total_tokens": 14902568} {"current_steps": 22630, "total_steps": 33920, "loss": 0.4025, "lr": 3.0122018498951478e-06, "epoch": 13.34316037735849, "percentage": 66.72, "elapsed_time": "0:43:09", "remaining_time": "0:21:32", "throughput": 5755.4, "total_tokens": 14905608} {"current_steps": 22635, "total_steps": 33920, "loss": 0.3131, "lr": 3.0098414515405765e-06, "epoch": 13.346108490566039, "percentage": 66.73, "elapsed_time": "0:43:10", "remaining_time": "0:21:31", "throughput": 5755.42, "total_tokens": 14908616} {"current_steps": 22640, "total_steps": 33920, "loss": 0.3341, "lr": 3.0074815800890576e-06, "epoch": 13.349056603773585, "percentage": 66.75, "elapsed_time": "0:43:10", "remaining_time": "0:21:30", "throughput": 5755.58, "total_tokens": 14912168} {"current_steps": 22645, "total_steps": 33920, "loss": 0.3476, "lr": 3.005122236165378e-06, "epoch": 13.352004716981131, "percentage": 66.76, "elapsed_time": "0:43:11", "remaining_time": "0:21:30", "throughput": 5755.6, "total_tokens": 14915016} {"current_steps": 22650, "total_steps": 33920, "loss": 0.3392, "lr": 3.0027634203941847e-06, "epoch": 13.35495283018868, "percentage": 66.77, "elapsed_time": "0:43:11", "remaining_time": "0:21:29", "throughput": 5755.48, "total_tokens": 14917544} {"current_steps": 22655, "total_steps": 33920, "loss": 0.2329, "lr": 3.0004051333999816e-06, "epoch": 13.357900943396226, "percentage": 66.79, "elapsed_time": "0:43:12", "remaining_time": "0:21:29", "throughput": 5755.74, "total_tokens": 14923592} {"current_steps": 22660, "total_steps": 33920, "loss": 0.2849, "lr": 2.998047375807139e-06, "epoch": 13.360849056603774, "percentage": 66.8, "elapsed_time": "0:43:13", "remaining_time": "0:21:28", "throughput": 5756.07, "total_tokens": 14928744} {"current_steps": 22665, "total_steps": 33920, "loss": 0.3877, "lr": 2.995690148239881e-06, "epoch": 13.36379716981132, "percentage": 66.82, "elapsed_time": "0:43:14", "remaining_time": "0:21:28", "throughput": 5756.25, "total_tokens": 14932456} {"current_steps": 22670, "total_steps": 33920, "loss": 0.332, "lr": 2.993333451322293e-06, "epoch": 13.366745283018869, "percentage": 66.83, "elapsed_time": "0:43:14", "remaining_time": "0:21:27", "throughput": 5756.2, "total_tokens": 14935304} {"current_steps": 22675, "total_steps": 33920, "loss": 0.4419, "lr": 2.9909772856783242e-06, "epoch": 13.369693396226415, "percentage": 66.85, "elapsed_time": "0:43:15", "remaining_time": "0:21:27", "throughput": 5756.3, "total_tokens": 14938600} {"current_steps": 22680, "total_steps": 33920, "loss": 0.3372, "lr": 2.988621651931777e-06, "epoch": 13.372641509433961, "percentage": 66.86, "elapsed_time": "0:43:15", "remaining_time": "0:21:26", "throughput": 5756.37, "total_tokens": 14941736} {"current_steps": 22685, "total_steps": 33920, "loss": 0.3654, "lr": 2.986266550706315e-06, "epoch": 13.37558962264151, "percentage": 66.88, "elapsed_time": "0:43:16", "remaining_time": "0:21:25", "throughput": 5756.39, "total_tokens": 14944520} {"current_steps": 22690, "total_steps": 33920, "loss": 0.2798, "lr": 2.9839119826254627e-06, "epoch": 13.378537735849056, "percentage": 66.89, "elapsed_time": "0:43:16", "remaining_time": "0:21:25", "throughput": 5756.48, "total_tokens": 14947656} {"current_steps": 22695, "total_steps": 33920, "loss": 0.4951, "lr": 2.981557948312602e-06, "epoch": 13.381485849056604, "percentage": 66.91, "elapsed_time": "0:43:17", "remaining_time": "0:21:24", "throughput": 5756.5, "total_tokens": 14950568} {"current_steps": 22700, "total_steps": 33920, "loss": 0.3244, "lr": 2.9792044483909733e-06, "epoch": 13.38443396226415, "percentage": 66.92, "elapsed_time": "0:43:17", "remaining_time": "0:21:23", "throughput": 5756.53, "total_tokens": 14953416} {"current_steps": 22705, "total_steps": 33920, "loss": 0.293, "lr": 2.9768514834836767e-06, "epoch": 13.387382075471699, "percentage": 66.94, "elapsed_time": "0:43:18", "remaining_time": "0:21:23", "throughput": 5756.51, "total_tokens": 14956104} {"current_steps": 22710, "total_steps": 33920, "loss": 0.332, "lr": 2.9744990542136685e-06, "epoch": 13.390330188679245, "percentage": 66.95, "elapsed_time": "0:43:18", "remaining_time": "0:21:22", "throughput": 5756.42, "total_tokens": 14958760} {"current_steps": 22715, "total_steps": 33920, "loss": 0.3326, "lr": 2.9721471612037637e-06, "epoch": 13.393278301886792, "percentage": 66.97, "elapsed_time": "0:43:19", "remaining_time": "0:21:22", "throughput": 5756.61, "total_tokens": 14962568} {"current_steps": 22720, "total_steps": 33920, "loss": 0.35, "lr": 2.9697958050766385e-06, "epoch": 13.39622641509434, "percentage": 66.98, "elapsed_time": "0:43:19", "remaining_time": "0:21:21", "throughput": 5756.81, "total_tokens": 14966440} {"current_steps": 22725, "total_steps": 33920, "loss": 0.3058, "lr": 2.967444986454825e-06, "epoch": 13.399174528301886, "percentage": 67.0, "elapsed_time": "0:43:20", "remaining_time": "0:21:20", "throughput": 5756.92, "total_tokens": 14969704} {"current_steps": 22730, "total_steps": 33920, "loss": 0.352, "lr": 2.9650947059607106e-06, "epoch": 13.402122641509434, "percentage": 67.01, "elapsed_time": "0:43:20", "remaining_time": "0:21:20", "throughput": 5757.14, "total_tokens": 14973608} {"current_steps": 22735, "total_steps": 33920, "loss": 0.3422, "lr": 2.962744964216542e-06, "epoch": 13.40507075471698, "percentage": 67.03, "elapsed_time": "0:43:21", "remaining_time": "0:21:19", "throughput": 5757.03, "total_tokens": 14975976} {"current_steps": 22740, "total_steps": 33920, "loss": 0.3434, "lr": 2.960395761844425e-06, "epoch": 13.408018867924529, "percentage": 67.04, "elapsed_time": "0:43:21", "remaining_time": "0:21:19", "throughput": 5757.06, "total_tokens": 14978792} {"current_steps": 22745, "total_steps": 33920, "loss": 0.2488, "lr": 2.95804709946632e-06, "epoch": 13.410966981132075, "percentage": 67.05, "elapsed_time": "0:43:22", "remaining_time": "0:21:18", "throughput": 5757.01, "total_tokens": 14981512} {"current_steps": 22750, "total_steps": 33920, "loss": 0.2805, "lr": 2.9556989777040457e-06, "epoch": 13.413915094339623, "percentage": 67.07, "elapsed_time": "0:43:22", "remaining_time": "0:21:17", "throughput": 5757.08, "total_tokens": 14984648} {"current_steps": 22755, "total_steps": 33920, "loss": 0.423, "lr": 2.9533513971792776e-06, "epoch": 13.41686320754717, "percentage": 67.08, "elapsed_time": "0:43:23", "remaining_time": "0:21:17", "throughput": 5757.2, "total_tokens": 14988328} {"current_steps": 22760, "total_steps": 33920, "loss": 0.3803, "lr": 2.9510043585135473e-06, "epoch": 13.419811320754716, "percentage": 67.1, "elapsed_time": "0:43:23", "remaining_time": "0:21:16", "throughput": 5757.19, "total_tokens": 14991336} {"current_steps": 22765, "total_steps": 33920, "loss": 0.3293, "lr": 2.948657862328244e-06, "epoch": 13.422759433962264, "percentage": 67.11, "elapsed_time": "0:43:24", "remaining_time": "0:21:16", "throughput": 5757.12, "total_tokens": 14994504} {"current_steps": 22770, "total_steps": 33920, "loss": 0.3032, "lr": 2.946311909244613e-06, "epoch": 13.42570754716981, "percentage": 67.13, "elapsed_time": "0:43:25", "remaining_time": "0:21:15", "throughput": 5757.22, "total_tokens": 14997704} {"current_steps": 22775, "total_steps": 33920, "loss": 0.3291, "lr": 2.9439664998837538e-06, "epoch": 13.428655660377359, "percentage": 67.14, "elapsed_time": "0:43:25", "remaining_time": "0:21:15", "throughput": 5757.15, "total_tokens": 15000360} {"current_steps": 22780, "total_steps": 33920, "loss": 0.343, "lr": 2.941621634866626e-06, "epoch": 13.431603773584905, "percentage": 67.16, "elapsed_time": "0:43:26", "remaining_time": "0:21:14", "throughput": 5757.17, "total_tokens": 15003336} {"current_steps": 22785, "total_steps": 33920, "loss": 0.3667, "lr": 2.9392773148140406e-06, "epoch": 13.434551886792454, "percentage": 67.17, "elapsed_time": "0:43:26", "remaining_time": "0:21:13", "throughput": 5757.21, "total_tokens": 15006248} {"current_steps": 22790, "total_steps": 33920, "loss": 0.3951, "lr": 2.9369335403466676e-06, "epoch": 13.4375, "percentage": 67.19, "elapsed_time": "0:43:27", "remaining_time": "0:21:13", "throughput": 5757.16, "total_tokens": 15008968} {"current_steps": 22795, "total_steps": 33920, "loss": 0.3026, "lr": 2.9345903120850318e-06, "epoch": 13.440448113207546, "percentage": 67.2, "elapsed_time": "0:43:27", "remaining_time": "0:21:12", "throughput": 5757.34, "total_tokens": 15012712} {"current_steps": 22800, "total_steps": 33920, "loss": 0.3053, "lr": 2.932247630649512e-06, "epoch": 13.443396226415095, "percentage": 67.22, "elapsed_time": "0:43:28", "remaining_time": "0:21:12", "throughput": 5757.12, "total_tokens": 15015144} {"current_steps": 22805, "total_steps": 33920, "loss": 0.4331, "lr": 2.9299054966603424e-06, "epoch": 13.446344339622641, "percentage": 67.23, "elapsed_time": "0:43:28", "remaining_time": "0:21:11", "throughput": 5757.31, "total_tokens": 15019368} {"current_steps": 22810, "total_steps": 33920, "loss": 0.3951, "lr": 2.927563910737613e-06, "epoch": 13.44929245283019, "percentage": 67.25, "elapsed_time": "0:43:29", "remaining_time": "0:21:10", "throughput": 5757.47, "total_tokens": 15022888} {"current_steps": 22815, "total_steps": 33920, "loss": 0.3408, "lr": 2.9252228735012722e-06, "epoch": 13.452240566037736, "percentage": 67.26, "elapsed_time": "0:43:29", "remaining_time": "0:21:10", "throughput": 5757.57, "total_tokens": 15026344} {"current_steps": 22820, "total_steps": 33920, "loss": 0.3159, "lr": 2.9228823855711174e-06, "epoch": 13.455188679245284, "percentage": 67.28, "elapsed_time": "0:43:30", "remaining_time": "0:21:09", "throughput": 5757.74, "total_tokens": 15030632} {"current_steps": 22825, "total_steps": 33920, "loss": 0.3924, "lr": 2.920542447566802e-06, "epoch": 13.45813679245283, "percentage": 67.29, "elapsed_time": "0:43:31", "remaining_time": "0:21:09", "throughput": 5757.77, "total_tokens": 15033640} {"current_steps": 22830, "total_steps": 33920, "loss": 0.4323, "lr": 2.918203060107837e-06, "epoch": 13.461084905660377, "percentage": 67.31, "elapsed_time": "0:43:31", "remaining_time": "0:21:08", "throughput": 5757.9, "total_tokens": 15037320} {"current_steps": 22835, "total_steps": 33920, "loss": 0.3799, "lr": 2.9158642238135813e-06, "epoch": 13.464033018867925, "percentage": 67.32, "elapsed_time": "0:43:32", "remaining_time": "0:21:08", "throughput": 5758.05, "total_tokens": 15040904} {"current_steps": 22840, "total_steps": 33920, "loss": 0.3112, "lr": 2.913525939303257e-06, "epoch": 13.466981132075471, "percentage": 67.33, "elapsed_time": "0:43:32", "remaining_time": "0:21:07", "throughput": 5758.12, "total_tokens": 15044200} {"current_steps": 22845, "total_steps": 33920, "loss": 0.3956, "lr": 2.9111882071959317e-06, "epoch": 13.46992924528302, "percentage": 67.35, "elapsed_time": "0:43:33", "remaining_time": "0:21:06", "throughput": 5758.06, "total_tokens": 15047144} {"current_steps": 22850, "total_steps": 33920, "loss": 0.3643, "lr": 2.908851028110532e-06, "epoch": 13.472877358490566, "percentage": 67.36, "elapsed_time": "0:43:33", "remaining_time": "0:21:06", "throughput": 5757.95, "total_tokens": 15050248} {"current_steps": 22855, "total_steps": 33920, "loss": 0.3488, "lr": 2.906514402665834e-06, "epoch": 13.475825471698114, "percentage": 67.38, "elapsed_time": "0:43:34", "remaining_time": "0:21:05", "throughput": 5758.15, "total_tokens": 15054056} {"current_steps": 22860, "total_steps": 33920, "loss": 0.3138, "lr": 2.9041783314804705e-06, "epoch": 13.47877358490566, "percentage": 67.39, "elapsed_time": "0:43:34", "remaining_time": "0:21:05", "throughput": 5758.18, "total_tokens": 15056936} {"current_steps": 22865, "total_steps": 33920, "loss": 0.2663, "lr": 2.9018428151729238e-06, "epoch": 13.481721698113208, "percentage": 67.41, "elapsed_time": "0:43:35", "remaining_time": "0:21:04", "throughput": 5758.33, "total_tokens": 15060488} {"current_steps": 22870, "total_steps": 33920, "loss": 0.2406, "lr": 2.899507854361537e-06, "epoch": 13.484669811320755, "percentage": 67.42, "elapsed_time": "0:43:35", "remaining_time": "0:21:03", "throughput": 5758.28, "total_tokens": 15063144} {"current_steps": 22875, "total_steps": 33920, "loss": 0.3982, "lr": 2.8971734496644975e-06, "epoch": 13.487617924528301, "percentage": 67.44, "elapsed_time": "0:43:36", "remaining_time": "0:21:03", "throughput": 5758.23, "total_tokens": 15065768} {"current_steps": 22880, "total_steps": 33920, "loss": 0.3479, "lr": 2.894839601699851e-06, "epoch": 13.49056603773585, "percentage": 67.45, "elapsed_time": "0:43:36", "remaining_time": "0:21:02", "throughput": 5758.22, "total_tokens": 15068680} {"current_steps": 22885, "total_steps": 33920, "loss": 0.3949, "lr": 2.8925063110854923e-06, "epoch": 13.493514150943396, "percentage": 67.47, "elapsed_time": "0:43:37", "remaining_time": "0:21:02", "throughput": 5757.99, "total_tokens": 15070984} {"current_steps": 22890, "total_steps": 33920, "loss": 0.4982, "lr": 2.8901735784391683e-06, "epoch": 13.496462264150944, "percentage": 67.48, "elapsed_time": "0:43:37", "remaining_time": "0:21:01", "throughput": 5757.91, "total_tokens": 15073640} {"current_steps": 22895, "total_steps": 33920, "loss": 0.356, "lr": 2.8878414043784844e-06, "epoch": 13.49941037735849, "percentage": 67.5, "elapsed_time": "0:43:38", "remaining_time": "0:21:00", "throughput": 5758.12, "total_tokens": 15077448} {"current_steps": 22900, "total_steps": 33920, "loss": 0.2452, "lr": 2.885509789520891e-06, "epoch": 13.502358490566039, "percentage": 67.51, "elapsed_time": "0:43:38", "remaining_time": "0:21:00", "throughput": 5758.24, "total_tokens": 15080744} {"current_steps": 22905, "total_steps": 33920, "loss": 0.38, "lr": 2.8831787344836926e-06, "epoch": 13.505306603773585, "percentage": 67.53, "elapsed_time": "0:43:39", "remaining_time": "0:20:59", "throughput": 5758.16, "total_tokens": 15083208} {"current_steps": 22910, "total_steps": 33920, "loss": 0.3189, "lr": 2.880848239884049e-06, "epoch": 13.508254716981131, "percentage": 67.54, "elapsed_time": "0:43:40", "remaining_time": "0:20:59", "throughput": 5758.29, "total_tokens": 15087048} {"current_steps": 22915, "total_steps": 33920, "loss": 0.2381, "lr": 2.8785183063389667e-06, "epoch": 13.51120283018868, "percentage": 67.56, "elapsed_time": "0:43:40", "remaining_time": "0:20:58", "throughput": 5758.3, "total_tokens": 15090024} {"current_steps": 22920, "total_steps": 33920, "loss": 0.3169, "lr": 2.876188934465306e-06, "epoch": 13.514150943396226, "percentage": 67.57, "elapsed_time": "0:43:41", "remaining_time": "0:20:57", "throughput": 5758.41, "total_tokens": 15093352} {"current_steps": 22925, "total_steps": 33920, "loss": 0.2277, "lr": 2.8738601248797758e-06, "epoch": 13.517099056603774, "percentage": 67.59, "elapsed_time": "0:43:41", "remaining_time": "0:20:57", "throughput": 5758.41, "total_tokens": 15096328} {"current_steps": 22930, "total_steps": 33920, "loss": 0.3446, "lr": 2.8715318781989432e-06, "epoch": 13.52004716981132, "percentage": 67.6, "elapsed_time": "0:43:42", "remaining_time": "0:20:56", "throughput": 5758.4, "total_tokens": 15099144} {"current_steps": 22935, "total_steps": 33920, "loss": 0.3539, "lr": 2.869204195039219e-06, "epoch": 13.522995283018869, "percentage": 67.61, "elapsed_time": "0:43:42", "remaining_time": "0:20:56", "throughput": 5758.39, "total_tokens": 15102056} {"current_steps": 22940, "total_steps": 33920, "loss": 0.3621, "lr": 2.8668770760168673e-06, "epoch": 13.525943396226415, "percentage": 67.63, "elapsed_time": "0:43:43", "remaining_time": "0:20:55", "throughput": 5758.47, "total_tokens": 15105864} {"current_steps": 22945, "total_steps": 33920, "loss": 0.3495, "lr": 2.864550521748003e-06, "epoch": 13.528891509433961, "percentage": 67.64, "elapsed_time": "0:43:43", "remaining_time": "0:20:55", "throughput": 5758.7, "total_tokens": 15109960} {"current_steps": 22950, "total_steps": 33920, "loss": 0.1823, "lr": 2.862224532848591e-06, "epoch": 13.53183962264151, "percentage": 67.66, "elapsed_time": "0:43:44", "remaining_time": "0:20:54", "throughput": 5758.64, "total_tokens": 15112488} {"current_steps": 22955, "total_steps": 33920, "loss": 0.4086, "lr": 2.8598991099344455e-06, "epoch": 13.534787735849056, "percentage": 67.67, "elapsed_time": "0:43:44", "remaining_time": "0:20:53", "throughput": 5758.7, "total_tokens": 15115784} {"current_steps": 22960, "total_steps": 33920, "loss": 0.2942, "lr": 2.857574253621236e-06, "epoch": 13.537735849056604, "percentage": 67.69, "elapsed_time": "0:43:45", "remaining_time": "0:20:53", "throughput": 5758.79, "total_tokens": 15119048} {"current_steps": 22965, "total_steps": 33920, "loss": 0.3918, "lr": 2.855249964524476e-06, "epoch": 13.54068396226415, "percentage": 67.7, "elapsed_time": "0:43:45", "remaining_time": "0:20:52", "throughput": 5759.04, "total_tokens": 15123208} {"current_steps": 22970, "total_steps": 33920, "loss": 0.3239, "lr": 2.852926243259531e-06, "epoch": 13.543632075471699, "percentage": 67.72, "elapsed_time": "0:43:46", "remaining_time": "0:20:52", "throughput": 5759.03, "total_tokens": 15126024} {"current_steps": 22975, "total_steps": 33920, "loss": 0.3887, "lr": 2.850603090441617e-06, "epoch": 13.546580188679245, "percentage": 67.73, "elapsed_time": "0:43:47", "remaining_time": "0:20:51", "throughput": 5759.05, "total_tokens": 15129288} {"current_steps": 22980, "total_steps": 33920, "loss": 0.3817, "lr": 2.848280506685798e-06, "epoch": 13.549528301886792, "percentage": 67.75, "elapsed_time": "0:43:47", "remaining_time": "0:20:50", "throughput": 5759.1, "total_tokens": 15132552} {"current_steps": 22985, "total_steps": 33920, "loss": 0.3326, "lr": 2.845958492606986e-06, "epoch": 13.55247641509434, "percentage": 67.76, "elapsed_time": "0:43:48", "remaining_time": "0:20:50", "throughput": 5759.24, "total_tokens": 15135944} {"current_steps": 22990, "total_steps": 33920, "loss": 0.4647, "lr": 2.843637048819949e-06, "epoch": 13.555424528301886, "percentage": 67.78, "elapsed_time": "0:43:48", "remaining_time": "0:20:49", "throughput": 5759.25, "total_tokens": 15139112} {"current_steps": 22995, "total_steps": 33920, "loss": 0.2403, "lr": 2.8413161759392966e-06, "epoch": 13.558372641509434, "percentage": 67.79, "elapsed_time": "0:43:49", "remaining_time": "0:20:49", "throughput": 5759.08, "total_tokens": 15141512} {"current_steps": 23000, "total_steps": 33920, "loss": 0.3726, "lr": 2.8389958745794878e-06, "epoch": 13.56132075471698, "percentage": 67.81, "elapsed_time": "0:43:49", "remaining_time": "0:20:48", "throughput": 5759.19, "total_tokens": 15144808} {"current_steps": 23005, "total_steps": 33920, "loss": 0.3846, "lr": 2.8366761453548366e-06, "epoch": 13.564268867924529, "percentage": 67.82, "elapsed_time": "0:43:50", "remaining_time": "0:20:47", "throughput": 5759.15, "total_tokens": 15147464} {"current_steps": 23010, "total_steps": 33920, "loss": 0.3504, "lr": 2.8343569888795e-06, "epoch": 13.567216981132075, "percentage": 67.84, "elapsed_time": "0:43:50", "remaining_time": "0:20:47", "throughput": 5759.07, "total_tokens": 15150024} {"current_steps": 23015, "total_steps": 33920, "loss": 0.4037, "lr": 2.832038405767483e-06, "epoch": 13.570165094339622, "percentage": 67.85, "elapsed_time": "0:43:51", "remaining_time": "0:20:46", "throughput": 5759.21, "total_tokens": 15154088} {"current_steps": 23020, "total_steps": 33920, "loss": 0.3224, "lr": 2.8297203966326397e-06, "epoch": 13.57311320754717, "percentage": 67.87, "elapsed_time": "0:43:51", "remaining_time": "0:20:46", "throughput": 5759.08, "total_tokens": 15156552} {"current_steps": 23025, "total_steps": 33920, "loss": 0.4009, "lr": 2.8274029620886773e-06, "epoch": 13.576061320754716, "percentage": 67.88, "elapsed_time": "0:43:52", "remaining_time": "0:20:45", "throughput": 5759.34, "total_tokens": 15160936} {"current_steps": 23030, "total_steps": 33920, "loss": 0.3311, "lr": 2.825086102749144e-06, "epoch": 13.579009433962264, "percentage": 67.9, "elapsed_time": "0:43:52", "remaining_time": "0:20:45", "throughput": 5759.47, "total_tokens": 15164264} {"current_steps": 23035, "total_steps": 33920, "loss": 0.3118, "lr": 2.822769819227438e-06, "epoch": 13.58195754716981, "percentage": 67.91, "elapsed_time": "0:43:53", "remaining_time": "0:20:44", "throughput": 5759.33, "total_tokens": 15166696} {"current_steps": 23040, "total_steps": 33920, "loss": 0.4028, "lr": 2.8204541121368055e-06, "epoch": 13.584905660377359, "percentage": 67.92, "elapsed_time": "0:43:53", "remaining_time": "0:20:43", "throughput": 5759.44, "total_tokens": 15169768} {"current_steps": 23045, "total_steps": 33920, "loss": 0.3091, "lr": 2.8181389820903402e-06, "epoch": 13.587853773584905, "percentage": 67.94, "elapsed_time": "0:43:54", "remaining_time": "0:20:43", "throughput": 5759.49, "total_tokens": 15173352} {"current_steps": 23050, "total_steps": 33920, "loss": 0.3173, "lr": 2.8158244297009814e-06, "epoch": 13.590801886792454, "percentage": 67.95, "elapsed_time": "0:43:55", "remaining_time": "0:20:42", "throughput": 5759.72, "total_tokens": 15177448} {"current_steps": 23055, "total_steps": 33920, "loss": 0.2443, "lr": 2.8135104555815196e-06, "epoch": 13.59375, "percentage": 67.97, "elapsed_time": "0:43:55", "remaining_time": "0:20:42", "throughput": 5759.88, "total_tokens": 15181256} {"current_steps": 23060, "total_steps": 33920, "loss": 0.2822, "lr": 2.811197060344588e-06, "epoch": 13.596698113207546, "percentage": 67.98, "elapsed_time": "0:43:56", "remaining_time": "0:20:41", "throughput": 5759.97, "total_tokens": 15184808} {"current_steps": 23065, "total_steps": 33920, "loss": 0.3712, "lr": 2.8088842446026677e-06, "epoch": 13.599646226415095, "percentage": 68.0, "elapsed_time": "0:43:56", "remaining_time": "0:20:40", "throughput": 5760.09, "total_tokens": 15188328} {"current_steps": 23070, "total_steps": 33920, "loss": 0.2581, "lr": 2.806572008968087e-06, "epoch": 13.602594339622641, "percentage": 68.01, "elapsed_time": "0:43:57", "remaining_time": "0:20:40", "throughput": 5760.1, "total_tokens": 15191272} {"current_steps": 23075, "total_steps": 33920, "loss": 0.312, "lr": 2.80426035405302e-06, "epoch": 13.60554245283019, "percentage": 68.03, "elapsed_time": "0:43:57", "remaining_time": "0:20:39", "throughput": 5760.26, "total_tokens": 15194760} {"current_steps": 23080, "total_steps": 33920, "loss": 0.5028, "lr": 2.8019492804694852e-06, "epoch": 13.608490566037736, "percentage": 68.04, "elapsed_time": "0:43:58", "remaining_time": "0:20:39", "throughput": 5760.46, "total_tokens": 15201224} {"current_steps": 23085, "total_steps": 33920, "loss": 0.2483, "lr": 2.799638788829354e-06, "epoch": 13.611438679245284, "percentage": 68.06, "elapsed_time": "0:43:59", "remaining_time": "0:20:38", "throughput": 5760.42, "total_tokens": 15203944} {"current_steps": 23090, "total_steps": 33920, "loss": 0.4172, "lr": 2.7973288797443367e-06, "epoch": 13.61438679245283, "percentage": 68.07, "elapsed_time": "0:43:59", "remaining_time": "0:20:38", "throughput": 5760.34, "total_tokens": 15206632} {"current_steps": 23095, "total_steps": 33920, "loss": 0.3293, "lr": 2.7950195538259884e-06, "epoch": 13.617334905660378, "percentage": 68.09, "elapsed_time": "0:44:00", "remaining_time": "0:20:37", "throughput": 5760.34, "total_tokens": 15209768} {"current_steps": 23100, "total_steps": 33920, "loss": 0.3742, "lr": 2.792710811685719e-06, "epoch": 13.620283018867925, "percentage": 68.1, "elapsed_time": "0:44:00", "remaining_time": "0:20:37", "throughput": 5760.44, "total_tokens": 15213032} {"current_steps": 23105, "total_steps": 33920, "loss": 0.4736, "lr": 2.7904026539347743e-06, "epoch": 13.623231132075471, "percentage": 68.12, "elapsed_time": "0:44:01", "remaining_time": "0:20:36", "throughput": 5760.59, "total_tokens": 15216552} {"current_steps": 23110, "total_steps": 33920, "loss": 0.3541, "lr": 2.7880950811842507e-06, "epoch": 13.62617924528302, "percentage": 68.13, "elapsed_time": "0:44:02", "remaining_time": "0:20:35", "throughput": 5760.79, "total_tokens": 15220648} {"current_steps": 23115, "total_steps": 33920, "loss": 0.3123, "lr": 2.785788094045085e-06, "epoch": 13.629127358490566, "percentage": 68.15, "elapsed_time": "0:44:02", "remaining_time": "0:20:35", "throughput": 5760.91, "total_tokens": 15223976} {"current_steps": 23120, "total_steps": 33920, "loss": 0.3704, "lr": 2.7834816931280655e-06, "epoch": 13.632075471698114, "percentage": 68.16, "elapsed_time": "0:44:03", "remaining_time": "0:20:34", "throughput": 5760.94, "total_tokens": 15227208} {"current_steps": 23125, "total_steps": 33920, "loss": 0.4536, "lr": 2.781175879043821e-06, "epoch": 13.63502358490566, "percentage": 68.18, "elapsed_time": "0:44:03", "remaining_time": "0:20:34", "throughput": 5761.12, "total_tokens": 15231176} {"current_steps": 23130, "total_steps": 33920, "loss": 0.3897, "lr": 2.778870652402825e-06, "epoch": 13.637971698113208, "percentage": 68.19, "elapsed_time": "0:44:04", "remaining_time": "0:20:33", "throughput": 5761.09, "total_tokens": 15233896} {"current_steps": 23135, "total_steps": 33920, "loss": 0.2719, "lr": 2.776566013815396e-06, "epoch": 13.640919811320755, "percentage": 68.2, "elapsed_time": "0:44:04", "remaining_time": "0:20:32", "throughput": 5761.07, "total_tokens": 15236776} {"current_steps": 23140, "total_steps": 33920, "loss": 0.3658, "lr": 2.774261963891698e-06, "epoch": 13.643867924528301, "percentage": 68.22, "elapsed_time": "0:44:05", "remaining_time": "0:20:32", "throughput": 5761.26, "total_tokens": 15241064} {"current_steps": 23145, "total_steps": 33920, "loss": 0.2484, "lr": 2.771958503241735e-06, "epoch": 13.64681603773585, "percentage": 68.23, "elapsed_time": "0:44:06", "remaining_time": "0:20:31", "throughput": 5761.28, "total_tokens": 15244488} {"current_steps": 23150, "total_steps": 33920, "loss": 0.2104, "lr": 2.769655632475362e-06, "epoch": 13.649764150943396, "percentage": 68.25, "elapsed_time": "0:44:06", "remaining_time": "0:20:31", "throughput": 5761.44, "total_tokens": 15247816} {"current_steps": 23155, "total_steps": 33920, "loss": 0.2938, "lr": 2.7673533522022733e-06, "epoch": 13.652712264150944, "percentage": 68.26, "elapsed_time": "0:44:07", "remaining_time": "0:20:30", "throughput": 5761.6, "total_tokens": 15251848} {"current_steps": 23160, "total_steps": 33920, "loss": 0.4161, "lr": 2.765051663032007e-06, "epoch": 13.65566037735849, "percentage": 68.28, "elapsed_time": "0:44:07", "remaining_time": "0:20:30", "throughput": 5761.61, "total_tokens": 15254952} {"current_steps": 23165, "total_steps": 33920, "loss": 0.3482, "lr": 2.7627505655739446e-06, "epoch": 13.658608490566039, "percentage": 68.29, "elapsed_time": "0:44:08", "remaining_time": "0:20:29", "throughput": 5761.44, "total_tokens": 15257448} {"current_steps": 23170, "total_steps": 33920, "loss": 0.3191, "lr": 2.7604500604373097e-06, "epoch": 13.661556603773585, "percentage": 68.31, "elapsed_time": "0:44:08", "remaining_time": "0:20:28", "throughput": 5761.5, "total_tokens": 15260680} {"current_steps": 23175, "total_steps": 33920, "loss": 0.2575, "lr": 2.7581501482311757e-06, "epoch": 13.664504716981131, "percentage": 68.32, "elapsed_time": "0:44:09", "remaining_time": "0:20:28", "throughput": 5761.53, "total_tokens": 15263592} {"current_steps": 23180, "total_steps": 33920, "loss": 0.3436, "lr": 2.7558508295644513e-06, "epoch": 13.66745283018868, "percentage": 68.34, "elapsed_time": "0:44:09", "remaining_time": "0:20:27", "throughput": 5761.67, "total_tokens": 15267112} {"current_steps": 23185, "total_steps": 33920, "loss": 0.4172, "lr": 2.7535521050458922e-06, "epoch": 13.670400943396226, "percentage": 68.35, "elapsed_time": "0:44:10", "remaining_time": "0:20:27", "throughput": 5761.78, "total_tokens": 15270536} {"current_steps": 23190, "total_steps": 33920, "loss": 0.374, "lr": 2.7512539752840926e-06, "epoch": 13.673349056603774, "percentage": 68.37, "elapsed_time": "0:44:10", "remaining_time": "0:20:26", "throughput": 5761.69, "total_tokens": 15273064} {"current_steps": 23195, "total_steps": 33920, "loss": 0.3433, "lr": 2.748956440887497e-06, "epoch": 13.67629716981132, "percentage": 68.38, "elapsed_time": "0:44:11", "remaining_time": "0:20:25", "throughput": 5761.67, "total_tokens": 15275976} {"current_steps": 23200, "total_steps": 33920, "loss": 0.3399, "lr": 2.7466595024643843e-06, "epoch": 13.679245283018869, "percentage": 68.4, "elapsed_time": "0:44:11", "remaining_time": "0:20:25", "throughput": 5761.77, "total_tokens": 15279592} {"current_steps": 23205, "total_steps": 33920, "loss": 0.312, "lr": 2.744363160622878e-06, "epoch": 13.682193396226415, "percentage": 68.41, "elapsed_time": "0:44:12", "remaining_time": "0:20:24", "throughput": 5761.7, "total_tokens": 15282120} {"current_steps": 23210, "total_steps": 33920, "loss": 0.2724, "lr": 2.742067415970948e-06, "epoch": 13.685141509433961, "percentage": 68.43, "elapsed_time": "0:44:12", "remaining_time": "0:20:24", "throughput": 5761.75, "total_tokens": 15285320} {"current_steps": 23215, "total_steps": 33920, "loss": 0.3669, "lr": 2.739772269116402e-06, "epoch": 13.68808962264151, "percentage": 68.44, "elapsed_time": "0:44:13", "remaining_time": "0:20:23", "throughput": 5761.79, "total_tokens": 15288648} {"current_steps": 23220, "total_steps": 33920, "loss": 0.3003, "lr": 2.7374777206668874e-06, "epoch": 13.691037735849056, "percentage": 68.46, "elapsed_time": "0:44:13", "remaining_time": "0:20:22", "throughput": 5761.79, "total_tokens": 15291688} {"current_steps": 23225, "total_steps": 33920, "loss": 0.2798, "lr": 2.735183771229898e-06, "epoch": 13.693985849056604, "percentage": 68.47, "elapsed_time": "0:44:14", "remaining_time": "0:20:22", "throughput": 5761.9, "total_tokens": 15295496} {"current_steps": 23230, "total_steps": 33920, "loss": 0.2315, "lr": 2.732890421412765e-06, "epoch": 13.69693396226415, "percentage": 68.48, "elapsed_time": "0:44:15", "remaining_time": "0:20:21", "throughput": 5761.92, "total_tokens": 15298440} {"current_steps": 23235, "total_steps": 33920, "loss": 0.5454, "lr": 2.7305976718226624e-06, "epoch": 13.699882075471699, "percentage": 68.5, "elapsed_time": "0:44:15", "remaining_time": "0:20:21", "throughput": 5762.11, "total_tokens": 15302632} {"current_steps": 23240, "total_steps": 33920, "loss": 0.3489, "lr": 2.728305523066609e-06, "epoch": 13.702830188679245, "percentage": 68.51, "elapsed_time": "0:44:16", "remaining_time": "0:20:20", "throughput": 5762.24, "total_tokens": 15306568} {"current_steps": 23245, "total_steps": 33920, "loss": 0.3517, "lr": 2.726013975751458e-06, "epoch": 13.705778301886792, "percentage": 68.53, "elapsed_time": "0:44:16", "remaining_time": "0:20:20", "throughput": 5762.32, "total_tokens": 15309992} {"current_steps": 23250, "total_steps": 33920, "loss": 0.4006, "lr": 2.723723030483908e-06, "epoch": 13.70872641509434, "percentage": 68.54, "elapsed_time": "0:44:17", "remaining_time": "0:20:19", "throughput": 5762.25, "total_tokens": 15312776} {"current_steps": 23255, "total_steps": 33920, "loss": 0.313, "lr": 2.7214326878704953e-06, "epoch": 13.711674528301886, "percentage": 68.56, "elapsed_time": "0:44:17", "remaining_time": "0:20:18", "throughput": 5762.26, "total_tokens": 15315752} {"current_steps": 23260, "total_steps": 33920, "loss": 0.1979, "lr": 2.7191429485175993e-06, "epoch": 13.714622641509434, "percentage": 68.57, "elapsed_time": "0:44:18", "remaining_time": "0:20:18", "throughput": 5762.2, "total_tokens": 15318856} {"current_steps": 23265, "total_steps": 33920, "loss": 0.3393, "lr": 2.716853813031435e-06, "epoch": 13.71757075471698, "percentage": 68.59, "elapsed_time": "0:44:19", "remaining_time": "0:20:17", "throughput": 5762.31, "total_tokens": 15322376} {"current_steps": 23270, "total_steps": 33920, "loss": 0.3262, "lr": 2.714565282018066e-06, "epoch": 13.720518867924529, "percentage": 68.6, "elapsed_time": "0:44:19", "remaining_time": "0:20:17", "throughput": 5762.35, "total_tokens": 15325512} {"current_steps": 23275, "total_steps": 33920, "loss": 0.3941, "lr": 2.7122773560833877e-06, "epoch": 13.723466981132075, "percentage": 68.62, "elapsed_time": "0:44:20", "remaining_time": "0:20:16", "throughput": 5762.55, "total_tokens": 15329224} {"current_steps": 23280, "total_steps": 33920, "loss": 0.263, "lr": 2.709990035833139e-06, "epoch": 13.726415094339622, "percentage": 68.63, "elapsed_time": "0:44:20", "remaining_time": "0:20:16", "throughput": 5762.52, "total_tokens": 15331976} {"current_steps": 23285, "total_steps": 33920, "loss": 0.3499, "lr": 2.707703321872896e-06, "epoch": 13.72936320754717, "percentage": 68.65, "elapsed_time": "0:44:21", "remaining_time": "0:20:15", "throughput": 5762.7, "total_tokens": 15336104} {"current_steps": 23290, "total_steps": 33920, "loss": 0.3499, "lr": 2.705417214808079e-06, "epoch": 13.732311320754716, "percentage": 68.66, "elapsed_time": "0:44:21", "remaining_time": "0:20:14", "throughput": 5762.82, "total_tokens": 15339432} {"current_steps": 23295, "total_steps": 33920, "loss": 0.2893, "lr": 2.703131715243945e-06, "epoch": 13.735259433962264, "percentage": 68.68, "elapsed_time": "0:44:22", "remaining_time": "0:20:14", "throughput": 5762.84, "total_tokens": 15342344} {"current_steps": 23300, "total_steps": 33920, "loss": 0.2748, "lr": 2.7008468237855855e-06, "epoch": 13.73820754716981, "percentage": 68.69, "elapsed_time": "0:44:22", "remaining_time": "0:20:13", "throughput": 5762.87, "total_tokens": 15345224} {"current_steps": 23305, "total_steps": 33920, "loss": 0.2881, "lr": 2.69856254103794e-06, "epoch": 13.741155660377359, "percentage": 68.71, "elapsed_time": "0:44:23", "remaining_time": "0:20:13", "throughput": 5762.91, "total_tokens": 15348296} {"current_steps": 23310, "total_steps": 33920, "loss": 0.4243, "lr": 2.6962788676057806e-06, "epoch": 13.744103773584905, "percentage": 68.72, "elapsed_time": "0:44:23", "remaining_time": "0:20:12", "throughput": 5762.99, "total_tokens": 15351592} {"current_steps": 23315, "total_steps": 33920, "loss": 0.2624, "lr": 2.69399580409372e-06, "epoch": 13.747051886792454, "percentage": 68.74, "elapsed_time": "0:44:24", "remaining_time": "0:20:11", "throughput": 5763.01, "total_tokens": 15354664} {"current_steps": 23320, "total_steps": 33920, "loss": 0.3973, "lr": 2.6917133511062076e-06, "epoch": 13.75, "percentage": 68.75, "elapsed_time": "0:44:24", "remaining_time": "0:20:11", "throughput": 5762.87, "total_tokens": 15357000} {"current_steps": 23325, "total_steps": 33920, "loss": 0.4247, "lr": 2.6894315092475342e-06, "epoch": 13.752948113207546, "percentage": 68.76, "elapsed_time": "0:44:25", "remaining_time": "0:20:10", "throughput": 5762.88, "total_tokens": 15360136} {"current_steps": 23330, "total_steps": 33920, "loss": 0.3191, "lr": 2.6871502791218245e-06, "epoch": 13.755896226415095, "percentage": 68.78, "elapsed_time": "0:44:25", "remaining_time": "0:20:10", "throughput": 5763.07, "total_tokens": 15364136} {"current_steps": 23335, "total_steps": 33920, "loss": 0.4235, "lr": 2.684869661333048e-06, "epoch": 13.758844339622641, "percentage": 68.79, "elapsed_time": "0:44:26", "remaining_time": "0:20:09", "throughput": 5763.07, "total_tokens": 15367240} {"current_steps": 23340, "total_steps": 33920, "loss": 0.2795, "lr": 2.6825896564850074e-06, "epoch": 13.76179245283019, "percentage": 68.81, "elapsed_time": "0:44:26", "remaining_time": "0:20:08", "throughput": 5763.02, "total_tokens": 15369864} {"current_steps": 23345, "total_steps": 33920, "loss": 0.273, "lr": 2.6803102651813416e-06, "epoch": 13.764740566037736, "percentage": 68.82, "elapsed_time": "0:44:27", "remaining_time": "0:20:08", "throughput": 5763.08, "total_tokens": 15373224} {"current_steps": 23350, "total_steps": 33920, "loss": 0.3606, "lr": 2.6780314880255307e-06, "epoch": 13.767688679245284, "percentage": 68.84, "elapsed_time": "0:44:28", "remaining_time": "0:20:07", "throughput": 5763.01, "total_tokens": 15376296} {"current_steps": 23355, "total_steps": 33920, "loss": 0.2954, "lr": 2.675753325620891e-06, "epoch": 13.77063679245283, "percentage": 68.85, "elapsed_time": "0:44:28", "remaining_time": "0:20:07", "throughput": 5762.99, "total_tokens": 15379400} {"current_steps": 23360, "total_steps": 33920, "loss": 0.2765, "lr": 2.6734757785705727e-06, "epoch": 13.773584905660378, "percentage": 68.87, "elapsed_time": "0:44:29", "remaining_time": "0:20:06", "throughput": 5762.98, "total_tokens": 15382184} {"current_steps": 23365, "total_steps": 33920, "loss": 0.3166, "lr": 2.6711988474775712e-06, "epoch": 13.776533018867925, "percentage": 68.88, "elapsed_time": "0:44:29", "remaining_time": "0:20:05", "throughput": 5762.95, "total_tokens": 15385000} {"current_steps": 23370, "total_steps": 33920, "loss": 0.3679, "lr": 2.668922532944711e-06, "epoch": 13.779481132075471, "percentage": 68.9, "elapsed_time": "0:44:30", "remaining_time": "0:20:05", "throughput": 5763.08, "total_tokens": 15388968} {"current_steps": 23375, "total_steps": 33920, "loss": 0.3627, "lr": 2.6666468355746566e-06, "epoch": 13.78242924528302, "percentage": 68.91, "elapsed_time": "0:44:30", "remaining_time": "0:20:04", "throughput": 5763.1, "total_tokens": 15391912} {"current_steps": 23380, "total_steps": 33920, "loss": 0.3694, "lr": 2.6643717559699073e-06, "epoch": 13.785377358490566, "percentage": 68.93, "elapsed_time": "0:44:31", "remaining_time": "0:20:04", "throughput": 5763.34, "total_tokens": 15396168} {"current_steps": 23385, "total_steps": 33920, "loss": 0.481, "lr": 2.662097294732803e-06, "epoch": 13.788325471698114, "percentage": 68.94, "elapsed_time": "0:44:31", "remaining_time": "0:20:03", "throughput": 5763.38, "total_tokens": 15399208} {"current_steps": 23390, "total_steps": 33920, "loss": 0.285, "lr": 2.6598234524655165e-06, "epoch": 13.79127358490566, "percentage": 68.96, "elapsed_time": "0:44:32", "remaining_time": "0:20:03", "throughput": 5763.5, "total_tokens": 15402632} {"current_steps": 23395, "total_steps": 33920, "loss": 0.4652, "lr": 2.657550229770054e-06, "epoch": 13.794221698113208, "percentage": 68.97, "elapsed_time": "0:44:32", "remaining_time": "0:20:02", "throughput": 5763.67, "total_tokens": 15406248} {"current_steps": 23400, "total_steps": 33920, "loss": 0.4795, "lr": 2.655277627248265e-06, "epoch": 13.797169811320755, "percentage": 68.99, "elapsed_time": "0:44:33", "remaining_time": "0:20:02", "throughput": 5763.9, "total_tokens": 15410728} {"current_steps": 23405, "total_steps": 33920, "loss": 0.4031, "lr": 2.65300564550183e-06, "epoch": 13.800117924528301, "percentage": 69.0, "elapsed_time": "0:44:34", "remaining_time": "0:20:01", "throughput": 5764.01, "total_tokens": 15414312} {"current_steps": 23410, "total_steps": 33920, "loss": 0.4696, "lr": 2.6507342851322647e-06, "epoch": 13.80306603773585, "percentage": 69.02, "elapsed_time": "0:44:34", "remaining_time": "0:20:00", "throughput": 5764.04, "total_tokens": 15417576} {"current_steps": 23415, "total_steps": 33920, "loss": 0.3221, "lr": 2.6484635467409233e-06, "epoch": 13.806014150943396, "percentage": 69.03, "elapsed_time": "0:44:35", "remaining_time": "0:20:00", "throughput": 5764.15, "total_tokens": 15420968} {"current_steps": 23420, "total_steps": 33920, "loss": 0.4141, "lr": 2.64619343092899e-06, "epoch": 13.808962264150944, "percentage": 69.04, "elapsed_time": "0:44:35", "remaining_time": "0:19:59", "throughput": 5764.22, "total_tokens": 15424296} {"current_steps": 23425, "total_steps": 33920, "loss": 0.306, "lr": 2.643923938297492e-06, "epoch": 13.81191037735849, "percentage": 69.06, "elapsed_time": "0:44:36", "remaining_time": "0:19:59", "throughput": 5764.2, "total_tokens": 15426984} {"current_steps": 23430, "total_steps": 33920, "loss": 0.4037, "lr": 2.6416550694472855e-06, "epoch": 13.814858490566039, "percentage": 69.07, "elapsed_time": "0:44:36", "remaining_time": "0:19:58", "throughput": 5764.27, "total_tokens": 15430152} {"current_steps": 23435, "total_steps": 33920, "loss": 0.4638, "lr": 2.639386824979063e-06, "epoch": 13.817806603773585, "percentage": 69.09, "elapsed_time": "0:44:37", "remaining_time": "0:19:57", "throughput": 5764.24, "total_tokens": 15433000} {"current_steps": 23440, "total_steps": 33920, "loss": 0.328, "lr": 2.6371192054933525e-06, "epoch": 13.820754716981131, "percentage": 69.1, "elapsed_time": "0:44:37", "remaining_time": "0:19:57", "throughput": 5764.37, "total_tokens": 15436584} {"current_steps": 23445, "total_steps": 33920, "loss": 0.3026, "lr": 2.634852211590516e-06, "epoch": 13.82370283018868, "percentage": 69.12, "elapsed_time": "0:44:38", "remaining_time": "0:19:56", "throughput": 5764.27, "total_tokens": 15439272} {"current_steps": 23450, "total_steps": 33920, "loss": 0.3002, "lr": 2.6325858438707473e-06, "epoch": 13.826650943396226, "percentage": 69.13, "elapsed_time": "0:44:38", "remaining_time": "0:19:56", "throughput": 5764.24, "total_tokens": 15441928} {"current_steps": 23455, "total_steps": 33920, "loss": 0.362, "lr": 2.630320102934082e-06, "epoch": 13.829599056603774, "percentage": 69.15, "elapsed_time": "0:44:39", "remaining_time": "0:19:55", "throughput": 5764.22, "total_tokens": 15444680} {"current_steps": 23460, "total_steps": 33920, "loss": 0.3706, "lr": 2.628054989380382e-06, "epoch": 13.83254716981132, "percentage": 69.16, "elapsed_time": "0:44:39", "remaining_time": "0:19:54", "throughput": 5763.99, "total_tokens": 15447304} {"current_steps": 23465, "total_steps": 33920, "loss": 0.3384, "lr": 2.625790503809346e-06, "epoch": 13.835495283018869, "percentage": 69.18, "elapsed_time": "0:44:40", "remaining_time": "0:19:54", "throughput": 5764.25, "total_tokens": 15451688} {"current_steps": 23470, "total_steps": 33920, "loss": 0.2223, "lr": 2.6235266468205067e-06, "epoch": 13.838443396226415, "percentage": 69.19, "elapsed_time": "0:44:41", "remaining_time": "0:19:53", "throughput": 5764.21, "total_tokens": 15454664} {"current_steps": 23475, "total_steps": 33920, "loss": 0.5469, "lr": 2.621263419013227e-06, "epoch": 13.841391509433961, "percentage": 69.21, "elapsed_time": "0:44:41", "remaining_time": "0:19:53", "throughput": 5764.39, "total_tokens": 15458344} {"current_steps": 23480, "total_steps": 33920, "loss": 0.383, "lr": 2.619000820986711e-06, "epoch": 13.84433962264151, "percentage": 69.22, "elapsed_time": "0:44:42", "remaining_time": "0:19:52", "throughput": 5764.42, "total_tokens": 15461128} {"current_steps": 23485, "total_steps": 33920, "loss": 0.2277, "lr": 2.616738853339988e-06, "epoch": 13.847287735849056, "percentage": 69.24, "elapsed_time": "0:44:42", "remaining_time": "0:19:51", "throughput": 5764.56, "total_tokens": 15464648} {"current_steps": 23490, "total_steps": 33920, "loss": 0.3104, "lr": 2.614477516671926e-06, "epoch": 13.850235849056604, "percentage": 69.25, "elapsed_time": "0:44:43", "remaining_time": "0:19:51", "throughput": 5764.67, "total_tokens": 15468040} {"current_steps": 23495, "total_steps": 33920, "loss": 0.4968, "lr": 2.612216811581223e-06, "epoch": 13.85318396226415, "percentage": 69.27, "elapsed_time": "0:44:43", "remaining_time": "0:19:50", "throughput": 5764.79, "total_tokens": 15471528} {"current_steps": 23500, "total_steps": 33920, "loss": 0.3312, "lr": 2.6099567386664095e-06, "epoch": 13.856132075471699, "percentage": 69.28, "elapsed_time": "0:44:44", "remaining_time": "0:19:50", "throughput": 5764.77, "total_tokens": 15474440} {"current_steps": 23505, "total_steps": 33920, "loss": 0.2659, "lr": 2.60769729852585e-06, "epoch": 13.859080188679245, "percentage": 69.3, "elapsed_time": "0:44:44", "remaining_time": "0:19:49", "throughput": 5764.8, "total_tokens": 15477416} {"current_steps": 23510, "total_steps": 33920, "loss": 0.3575, "lr": 2.6054384917577413e-06, "epoch": 13.862028301886792, "percentage": 69.31, "elapsed_time": "0:44:45", "remaining_time": "0:19:49", "throughput": 5764.87, "total_tokens": 15480392} {"current_steps": 23515, "total_steps": 33920, "loss": 0.3159, "lr": 2.60318031896011e-06, "epoch": 13.86497641509434, "percentage": 69.32, "elapsed_time": "0:44:45", "remaining_time": "0:19:48", "throughput": 5764.95, "total_tokens": 15483592} {"current_steps": 23520, "total_steps": 33920, "loss": 0.3606, "lr": 2.60092278073082e-06, "epoch": 13.867924528301886, "percentage": 69.34, "elapsed_time": "0:44:46", "remaining_time": "0:19:47", "throughput": 5764.9, "total_tokens": 15486504} {"current_steps": 23525, "total_steps": 33920, "loss": 0.5032, "lr": 2.5986658776675644e-06, "epoch": 13.870872641509434, "percentage": 69.35, "elapsed_time": "0:44:46", "remaining_time": "0:19:47", "throughput": 5764.96, "total_tokens": 15489736} {"current_steps": 23530, "total_steps": 33920, "loss": 0.2873, "lr": 2.5964096103678666e-06, "epoch": 13.87382075471698, "percentage": 69.37, "elapsed_time": "0:44:47", "remaining_time": "0:19:46", "throughput": 5765.03, "total_tokens": 15493096} {"current_steps": 23535, "total_steps": 33920, "loss": 0.351, "lr": 2.5941539794290833e-06, "epoch": 13.876768867924529, "percentage": 69.38, "elapsed_time": "0:44:48", "remaining_time": "0:19:46", "throughput": 5765.03, "total_tokens": 15496616} {"current_steps": 23540, "total_steps": 33920, "loss": 0.3289, "lr": 2.5918989854484024e-06, "epoch": 13.879716981132075, "percentage": 69.4, "elapsed_time": "0:44:48", "remaining_time": "0:19:45", "throughput": 5765.06, "total_tokens": 15500168} {"current_steps": 23545, "total_steps": 33920, "loss": 0.2606, "lr": 2.5896446290228417e-06, "epoch": 13.882665094339622, "percentage": 69.41, "elapsed_time": "0:44:49", "remaining_time": "0:19:44", "throughput": 5765.09, "total_tokens": 15503464} {"current_steps": 23550, "total_steps": 33920, "loss": 0.3382, "lr": 2.5873909107492547e-06, "epoch": 13.88561320754717, "percentage": 69.43, "elapsed_time": "0:44:49", "remaining_time": "0:19:44", "throughput": 5765.04, "total_tokens": 15506440} {"current_steps": 23555, "total_steps": 33920, "loss": 0.3282, "lr": 2.5851378312243224e-06, "epoch": 13.888561320754716, "percentage": 69.44, "elapsed_time": "0:44:50", "remaining_time": "0:19:43", "throughput": 5764.89, "total_tokens": 15509032} {"current_steps": 23560, "total_steps": 33920, "loss": 0.2648, "lr": 2.5828853910445572e-06, "epoch": 13.891509433962264, "percentage": 69.46, "elapsed_time": "0:44:50", "remaining_time": "0:19:43", "throughput": 5764.93, "total_tokens": 15512264} {"current_steps": 23565, "total_steps": 33920, "loss": 0.4764, "lr": 2.5806335908063012e-06, "epoch": 13.89445754716981, "percentage": 69.47, "elapsed_time": "0:44:51", "remaining_time": "0:19:42", "throughput": 5764.91, "total_tokens": 15516072} {"current_steps": 23570, "total_steps": 33920, "loss": 0.2827, "lr": 2.5783824311057293e-06, "epoch": 13.897405660377359, "percentage": 69.49, "elapsed_time": "0:44:51", "remaining_time": "0:19:42", "throughput": 5764.91, "total_tokens": 15518952} {"current_steps": 23575, "total_steps": 33920, "loss": 0.2702, "lr": 2.5761319125388433e-06, "epoch": 13.900353773584905, "percentage": 69.5, "elapsed_time": "0:44:52", "remaining_time": "0:19:41", "throughput": 5765.15, "total_tokens": 15523272} {"current_steps": 23580, "total_steps": 33920, "loss": 0.3749, "lr": 2.57388203570148e-06, "epoch": 13.903301886792454, "percentage": 69.52, "elapsed_time": "0:44:53", "remaining_time": "0:19:40", "throughput": 5765.12, "total_tokens": 15526440} {"current_steps": 23585, "total_steps": 33920, "loss": 0.2858, "lr": 2.5716328011893055e-06, "epoch": 13.90625, "percentage": 69.53, "elapsed_time": "0:44:53", "remaining_time": "0:19:40", "throughput": 5765.31, "total_tokens": 15530152} {"current_steps": 23590, "total_steps": 33920, "loss": 0.3613, "lr": 2.5693842095978127e-06, "epoch": 13.909198113207546, "percentage": 69.55, "elapsed_time": "0:44:54", "remaining_time": "0:19:39", "throughput": 5765.44, "total_tokens": 15534568} {"current_steps": 23595, "total_steps": 33920, "loss": 0.3121, "lr": 2.567136261522325e-06, "epoch": 13.912146226415095, "percentage": 69.56, "elapsed_time": "0:44:54", "remaining_time": "0:19:39", "throughput": 5765.42, "total_tokens": 15537416} {"current_steps": 23600, "total_steps": 33920, "loss": 0.292, "lr": 2.5648889575579985e-06, "epoch": 13.915094339622641, "percentage": 69.58, "elapsed_time": "0:44:55", "remaining_time": "0:19:38", "throughput": 5765.64, "total_tokens": 15541832} {"current_steps": 23605, "total_steps": 33920, "loss": 0.3659, "lr": 2.562642298299814e-06, "epoch": 13.91804245283019, "percentage": 69.59, "elapsed_time": "0:44:56", "remaining_time": "0:19:38", "throughput": 5765.66, "total_tokens": 15544648} {"current_steps": 23610, "total_steps": 33920, "loss": 0.3866, "lr": 2.560396284342584e-06, "epoch": 13.920990566037736, "percentage": 69.6, "elapsed_time": "0:44:56", "remaining_time": "0:19:37", "throughput": 5765.61, "total_tokens": 15547400} {"current_steps": 23615, "total_steps": 33920, "loss": 0.3518, "lr": 2.558150916280954e-06, "epoch": 13.923938679245284, "percentage": 69.62, "elapsed_time": "0:44:57", "remaining_time": "0:19:36", "throughput": 5765.28, "total_tokens": 15549512} {"current_steps": 23620, "total_steps": 33920, "loss": 0.329, "lr": 2.555906194709392e-06, "epoch": 13.92688679245283, "percentage": 69.63, "elapsed_time": "0:44:57", "remaining_time": "0:19:36", "throughput": 5765.38, "total_tokens": 15553096} {"current_steps": 23625, "total_steps": 33920, "loss": 0.3133, "lr": 2.553662120222199e-06, "epoch": 13.929834905660378, "percentage": 69.65, "elapsed_time": "0:44:58", "remaining_time": "0:19:35", "throughput": 5765.47, "total_tokens": 15556360} {"current_steps": 23630, "total_steps": 33920, "loss": 0.2819, "lr": 2.5514186934135026e-06, "epoch": 13.932783018867925, "percentage": 69.66, "elapsed_time": "0:44:58", "remaining_time": "0:19:35", "throughput": 5765.46, "total_tokens": 15559272} {"current_steps": 23635, "total_steps": 33920, "loss": 0.414, "lr": 2.54917591487726e-06, "epoch": 13.935731132075471, "percentage": 69.68, "elapsed_time": "0:44:59", "remaining_time": "0:19:34", "throughput": 5765.61, "total_tokens": 15563144} {"current_steps": 23640, "total_steps": 33920, "loss": 0.2534, "lr": 2.5469337852072547e-06, "epoch": 13.93867924528302, "percentage": 69.69, "elapsed_time": "0:44:59", "remaining_time": "0:19:34", "throughput": 5765.5, "total_tokens": 15565768} {"current_steps": 23645, "total_steps": 33920, "loss": 0.3777, "lr": 2.5446923049971035e-06, "epoch": 13.941627358490566, "percentage": 69.71, "elapsed_time": "0:45:00", "remaining_time": "0:19:33", "throughput": 5765.61, "total_tokens": 15569192} {"current_steps": 23650, "total_steps": 33920, "loss": 0.2661, "lr": 2.5424514748402463e-06, "epoch": 13.944575471698114, "percentage": 69.72, "elapsed_time": "0:45:00", "remaining_time": "0:19:32", "throughput": 5765.4, "total_tokens": 15571400} {"current_steps": 23655, "total_steps": 33920, "loss": 0.3404, "lr": 2.540211295329953e-06, "epoch": 13.94752358490566, "percentage": 69.74, "elapsed_time": "0:45:01", "remaining_time": "0:19:32", "throughput": 5765.57, "total_tokens": 15575432} {"current_steps": 23660, "total_steps": 33920, "loss": 0.3464, "lr": 2.5379717670593197e-06, "epoch": 13.950471698113208, "percentage": 69.75, "elapsed_time": "0:45:02", "remaining_time": "0:19:31", "throughput": 5765.72, "total_tokens": 15579240} {"current_steps": 23665, "total_steps": 33920, "loss": 0.5137, "lr": 2.53573289062127e-06, "epoch": 13.953419811320755, "percentage": 69.77, "elapsed_time": "0:45:02", "remaining_time": "0:19:31", "throughput": 5765.68, "total_tokens": 15582120} {"current_steps": 23670, "total_steps": 33920, "loss": 0.4299, "lr": 2.5334946666085605e-06, "epoch": 13.956367924528301, "percentage": 69.78, "elapsed_time": "0:45:03", "remaining_time": "0:19:30", "throughput": 5765.7, "total_tokens": 15585288} {"current_steps": 23675, "total_steps": 33920, "loss": 0.3311, "lr": 2.531257095613766e-06, "epoch": 13.95931603773585, "percentage": 69.8, "elapsed_time": "0:45:03", "remaining_time": "0:19:29", "throughput": 5765.74, "total_tokens": 15588264} {"current_steps": 23680, "total_steps": 33920, "loss": 0.3197, "lr": 2.529020178229297e-06, "epoch": 13.962264150943396, "percentage": 69.81, "elapsed_time": "0:45:04", "remaining_time": "0:19:29", "throughput": 5765.85, "total_tokens": 15591720} {"current_steps": 23685, "total_steps": 33920, "loss": 0.3382, "lr": 2.5267839150473846e-06, "epoch": 13.965212264150944, "percentage": 69.83, "elapsed_time": "0:45:04", "remaining_time": "0:19:28", "throughput": 5765.99, "total_tokens": 15595176} {"current_steps": 23690, "total_steps": 33920, "loss": 0.4437, "lr": 2.5245483066600896e-06, "epoch": 13.96816037735849, "percentage": 69.84, "elapsed_time": "0:45:05", "remaining_time": "0:19:28", "throughput": 5765.9, "total_tokens": 15597736} {"current_steps": 23695, "total_steps": 33920, "loss": 0.3949, "lr": 2.5223133536592996e-06, "epoch": 13.971108490566039, "percentage": 69.86, "elapsed_time": "0:45:05", "remaining_time": "0:19:27", "throughput": 5765.99, "total_tokens": 15601096} {"current_steps": 23700, "total_steps": 33920, "loss": 0.2182, "lr": 2.520079056636725e-06, "epoch": 13.974056603773585, "percentage": 69.87, "elapsed_time": "0:45:06", "remaining_time": "0:19:27", "throughput": 5766.02, "total_tokens": 15604584} {"current_steps": 23705, "total_steps": 33920, "loss": 0.2664, "lr": 2.5178454161839106e-06, "epoch": 13.977004716981131, "percentage": 69.89, "elapsed_time": "0:45:06", "remaining_time": "0:19:26", "throughput": 5766.0, "total_tokens": 15607560} {"current_steps": 23710, "total_steps": 33920, "loss": 0.3147, "lr": 2.5156124328922195e-06, "epoch": 13.97995283018868, "percentage": 69.9, "elapsed_time": "0:45:07", "remaining_time": "0:19:26", "throughput": 5766.23, "total_tokens": 15613512} {"current_steps": 23715, "total_steps": 33920, "loss": 0.3868, "lr": 2.513380107352844e-06, "epoch": 13.982900943396226, "percentage": 69.91, "elapsed_time": "0:45:08", "remaining_time": "0:19:25", "throughput": 5766.48, "total_tokens": 15617800} {"current_steps": 23720, "total_steps": 33920, "loss": 0.3392, "lr": 2.5111484401568014e-06, "epoch": 13.985849056603774, "percentage": 69.93, "elapsed_time": "0:45:08", "remaining_time": "0:19:24", "throughput": 5766.54, "total_tokens": 15621224} {"current_steps": 23725, "total_steps": 33920, "loss": 0.2901, "lr": 2.508917431894936e-06, "epoch": 13.98879716981132, "percentage": 69.94, "elapsed_time": "0:45:09", "remaining_time": "0:19:24", "throughput": 5766.74, "total_tokens": 15625032} {"current_steps": 23730, "total_steps": 33920, "loss": 0.2862, "lr": 2.5066870831579144e-06, "epoch": 13.991745283018869, "percentage": 69.96, "elapsed_time": "0:45:10", "remaining_time": "0:19:23", "throughput": 5766.77, "total_tokens": 15628008} {"current_steps": 23735, "total_steps": 33920, "loss": 0.3552, "lr": 2.504457394536235e-06, "epoch": 13.994693396226415, "percentage": 69.97, "elapsed_time": "0:45:10", "remaining_time": "0:19:23", "throughput": 5767.0, "total_tokens": 15632392} {"current_steps": 23740, "total_steps": 33920, "loss": 0.2905, "lr": 2.502228366620216e-06, "epoch": 13.997641509433961, "percentage": 69.99, "elapsed_time": "0:45:11", "remaining_time": "0:19:22", "throughput": 5766.99, "total_tokens": 15635048} {"current_steps": 23744, "total_steps": 33920, "eval_loss": 0.5701644420623779, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "0:45:30", "remaining_time": "0:19:30", "throughput": 5727.48, "total_tokens": 15636912} {"current_steps": 23745, "total_steps": 33920, "loss": 0.4082, "lr": 2.5000000000000015e-06, "epoch": 14.00058962264151, "percentage": 70.0, "elapsed_time": "0:45:33", "remaining_time": "0:19:31", "throughput": 5720.75, "total_tokens": 15637744} {"current_steps": 23750, "total_steps": 33920, "loss": 0.2555, "lr": 2.497772295265561e-06, "epoch": 14.003537735849056, "percentage": 70.02, "elapsed_time": "0:45:34", "remaining_time": "0:19:30", "throughput": 5720.78, "total_tokens": 15640912} {"current_steps": 23755, "total_steps": 33920, "loss": 0.3281, "lr": 2.4955452530066897e-06, "epoch": 14.006485849056604, "percentage": 70.03, "elapsed_time": "0:45:34", "remaining_time": "0:19:30", "throughput": 5720.6, "total_tokens": 15643664} {"current_steps": 23760, "total_steps": 33920, "loss": 0.3617, "lr": 2.4933188738130043e-06, "epoch": 14.00943396226415, "percentage": 70.05, "elapsed_time": "0:45:35", "remaining_time": "0:19:29", "throughput": 5720.59, "total_tokens": 15646640} {"current_steps": 23765, "total_steps": 33920, "loss": 0.3329, "lr": 2.49109315827395e-06, "epoch": 14.012382075471699, "percentage": 70.06, "elapsed_time": "0:45:35", "remaining_time": "0:19:28", "throughput": 5720.6, "total_tokens": 15649648} {"current_steps": 23770, "total_steps": 33920, "loss": 0.4057, "lr": 2.4888681069787975e-06, "epoch": 14.015330188679245, "percentage": 70.08, "elapsed_time": "0:45:36", "remaining_time": "0:19:28", "throughput": 5720.65, "total_tokens": 15652720} {"current_steps": 23775, "total_steps": 33920, "loss": 0.3807, "lr": 2.4866437205166353e-06, "epoch": 14.018278301886792, "percentage": 70.09, "elapsed_time": "0:45:36", "remaining_time": "0:19:27", "throughput": 5720.61, "total_tokens": 15655536} {"current_steps": 23780, "total_steps": 33920, "loss": 0.2822, "lr": 2.4844199994763803e-06, "epoch": 14.02122641509434, "percentage": 70.11, "elapsed_time": "0:45:37", "remaining_time": "0:19:27", "throughput": 5720.69, "total_tokens": 15658640} {"current_steps": 23785, "total_steps": 33920, "loss": 0.3251, "lr": 2.482196944446772e-06, "epoch": 14.024174528301886, "percentage": 70.12, "elapsed_time": "0:45:37", "remaining_time": "0:19:26", "throughput": 5720.64, "total_tokens": 15661360} {"current_steps": 23790, "total_steps": 33920, "loss": 0.3203, "lr": 2.4799745560163736e-06, "epoch": 14.027122641509434, "percentage": 70.14, "elapsed_time": "0:45:38", "remaining_time": "0:19:25", "throughput": 5720.57, "total_tokens": 15664368} {"current_steps": 23795, "total_steps": 33920, "loss": 0.3027, "lr": 2.4777528347735707e-06, "epoch": 14.03007075471698, "percentage": 70.15, "elapsed_time": "0:45:38", "remaining_time": "0:19:25", "throughput": 5720.41, "total_tokens": 15666704} {"current_steps": 23800, "total_steps": 33920, "loss": 0.3001, "lr": 2.4755317813065766e-06, "epoch": 14.033018867924529, "percentage": 70.17, "elapsed_time": "0:45:39", "remaining_time": "0:19:24", "throughput": 5720.31, "total_tokens": 15669168} {"current_steps": 23805, "total_steps": 33920, "loss": 0.2512, "lr": 2.4733113962034234e-06, "epoch": 14.035966981132075, "percentage": 70.18, "elapsed_time": "0:45:39", "remaining_time": "0:19:24", "throughput": 5720.44, "total_tokens": 15672880} {"current_steps": 23810, "total_steps": 33920, "loss": 0.3952, "lr": 2.4710916800519674e-06, "epoch": 14.038915094339623, "percentage": 70.19, "elapsed_time": "0:45:40", "remaining_time": "0:19:23", "throughput": 5720.15, "total_tokens": 15674896} {"current_steps": 23815, "total_steps": 33920, "loss": 0.3198, "lr": 2.4688726334398883e-06, "epoch": 14.04186320754717, "percentage": 70.21, "elapsed_time": "0:45:40", "remaining_time": "0:19:22", "throughput": 5720.0, "total_tokens": 15677296} {"current_steps": 23820, "total_steps": 33920, "loss": 0.2681, "lr": 2.466654256954688e-06, "epoch": 14.044811320754716, "percentage": 70.22, "elapsed_time": "0:45:41", "remaining_time": "0:19:22", "throughput": 5720.12, "total_tokens": 15680720} {"current_steps": 23825, "total_steps": 33920, "loss": 0.2255, "lr": 2.4644365511836895e-06, "epoch": 14.047759433962264, "percentage": 70.24, "elapsed_time": "0:45:41", "remaining_time": "0:19:21", "throughput": 5720.08, "total_tokens": 15683696} {"current_steps": 23830, "total_steps": 33920, "loss": 0.3898, "lr": 2.4622195167140432e-06, "epoch": 14.05070754716981, "percentage": 70.25, "elapsed_time": "0:45:42", "remaining_time": "0:19:21", "throughput": 5720.07, "total_tokens": 15686608} {"current_steps": 23835, "total_steps": 33920, "loss": 0.3289, "lr": 2.4600031541327173e-06, "epoch": 14.053655660377359, "percentage": 70.27, "elapsed_time": "0:45:42", "remaining_time": "0:19:20", "throughput": 5720.18, "total_tokens": 15690096} {"current_steps": 23840, "total_steps": 33920, "loss": 0.2721, "lr": 2.457787464026503e-06, "epoch": 14.056603773584905, "percentage": 70.28, "elapsed_time": "0:45:43", "remaining_time": "0:19:19", "throughput": 5720.01, "total_tokens": 15692624} {"current_steps": 23845, "total_steps": 33920, "loss": 0.3008, "lr": 2.455572446982014e-06, "epoch": 14.059551886792454, "percentage": 70.3, "elapsed_time": "0:45:44", "remaining_time": "0:19:19", "throughput": 5720.26, "total_tokens": 15697488} {"current_steps": 23850, "total_steps": 33920, "loss": 0.3316, "lr": 2.453358103585686e-06, "epoch": 14.0625, "percentage": 70.31, "elapsed_time": "0:45:44", "remaining_time": "0:19:18", "throughput": 5720.27, "total_tokens": 15700432} {"current_steps": 23855, "total_steps": 33920, "loss": 0.3776, "lr": 2.4511444344237733e-06, "epoch": 14.065448113207546, "percentage": 70.33, "elapsed_time": "0:45:45", "remaining_time": "0:19:18", "throughput": 5720.39, "total_tokens": 15703696} {"current_steps": 23860, "total_steps": 33920, "loss": 0.3077, "lr": 2.4489314400823567e-06, "epoch": 14.068396226415095, "percentage": 70.34, "elapsed_time": "0:45:45", "remaining_time": "0:19:17", "throughput": 5720.45, "total_tokens": 15706768} {"current_steps": 23865, "total_steps": 33920, "loss": 0.2623, "lr": 2.446719121147337e-06, "epoch": 14.071344339622641, "percentage": 70.36, "elapsed_time": "0:45:46", "remaining_time": "0:19:17", "throughput": 5720.39, "total_tokens": 15709552} {"current_steps": 23870, "total_steps": 33920, "loss": 0.3027, "lr": 2.4445074782044347e-06, "epoch": 14.07429245283019, "percentage": 70.37, "elapsed_time": "0:45:46", "remaining_time": "0:19:16", "throughput": 5720.32, "total_tokens": 15712272} {"current_steps": 23875, "total_steps": 33920, "loss": 0.2152, "lr": 2.442296511839191e-06, "epoch": 14.077240566037736, "percentage": 70.39, "elapsed_time": "0:45:47", "remaining_time": "0:19:15", "throughput": 5720.32, "total_tokens": 15715728} {"current_steps": 23880, "total_steps": 33920, "loss": 0.3359, "lr": 2.4400862226369687e-06, "epoch": 14.080188679245284, "percentage": 70.4, "elapsed_time": "0:45:47", "remaining_time": "0:19:15", "throughput": 5720.36, "total_tokens": 15718800} {"current_steps": 23885, "total_steps": 33920, "loss": 0.4045, "lr": 2.4378766111829514e-06, "epoch": 14.08313679245283, "percentage": 70.42, "elapsed_time": "0:45:48", "remaining_time": "0:19:14", "throughput": 5720.45, "total_tokens": 15721968} {"current_steps": 23890, "total_steps": 33920, "loss": 0.2865, "lr": 2.435667678062142e-06, "epoch": 14.086084905660377, "percentage": 70.43, "elapsed_time": "0:45:48", "remaining_time": "0:19:14", "throughput": 5720.51, "total_tokens": 15725328} {"current_steps": 23895, "total_steps": 33920, "loss": 0.3514, "lr": 2.4334594238593682e-06, "epoch": 14.089033018867925, "percentage": 70.45, "elapsed_time": "0:45:49", "remaining_time": "0:19:13", "throughput": 5720.74, "total_tokens": 15729232} {"current_steps": 23900, "total_steps": 33920, "loss": 0.3263, "lr": 2.4312518491592727e-06, "epoch": 14.091981132075471, "percentage": 70.46, "elapsed_time": "0:45:50", "remaining_time": "0:19:12", "throughput": 5720.73, "total_tokens": 15732048} {"current_steps": 23905, "total_steps": 33920, "loss": 0.2597, "lr": 2.429044954546322e-06, "epoch": 14.09492924528302, "percentage": 70.47, "elapsed_time": "0:45:50", "remaining_time": "0:19:12", "throughput": 5720.8, "total_tokens": 15735216} {"current_steps": 23910, "total_steps": 33920, "loss": 0.3482, "lr": 2.426838740604799e-06, "epoch": 14.097877358490566, "percentage": 70.49, "elapsed_time": "0:45:51", "remaining_time": "0:19:11", "throughput": 5720.88, "total_tokens": 15738352} {"current_steps": 23915, "total_steps": 33920, "loss": 0.4198, "lr": 2.4246332079188066e-06, "epoch": 14.100825471698114, "percentage": 70.5, "elapsed_time": "0:45:51", "remaining_time": "0:19:11", "throughput": 5721.06, "total_tokens": 15742160} {"current_steps": 23920, "total_steps": 33920, "loss": 0.3097, "lr": 2.4224283570722745e-06, "epoch": 14.10377358490566, "percentage": 70.52, "elapsed_time": "0:45:52", "remaining_time": "0:19:10", "throughput": 5721.21, "total_tokens": 15746064} {"current_steps": 23925, "total_steps": 33920, "loss": 0.3429, "lr": 2.420224188648943e-06, "epoch": 14.106721698113208, "percentage": 70.53, "elapsed_time": "0:45:52", "remaining_time": "0:19:09", "throughput": 5721.26, "total_tokens": 15749168} {"current_steps": 23930, "total_steps": 33920, "loss": 0.32, "lr": 2.418020703232376e-06, "epoch": 14.109669811320755, "percentage": 70.55, "elapsed_time": "0:45:53", "remaining_time": "0:19:09", "throughput": 5721.23, "total_tokens": 15751920} {"current_steps": 23935, "total_steps": 33920, "loss": 0.2826, "lr": 2.4158179014059556e-06, "epoch": 14.112617924528301, "percentage": 70.56, "elapsed_time": "0:45:53", "remaining_time": "0:19:08", "throughput": 5721.19, "total_tokens": 15754768} {"current_steps": 23940, "total_steps": 33920, "loss": 0.2938, "lr": 2.413615783752883e-06, "epoch": 14.11556603773585, "percentage": 70.58, "elapsed_time": "0:45:54", "remaining_time": "0:19:08", "throughput": 5721.18, "total_tokens": 15757808} {"current_steps": 23945, "total_steps": 33920, "loss": 0.2979, "lr": 2.4114143508561767e-06, "epoch": 14.118514150943396, "percentage": 70.59, "elapsed_time": "0:45:54", "remaining_time": "0:19:07", "throughput": 5721.21, "total_tokens": 15761136} {"current_steps": 23950, "total_steps": 33920, "loss": 0.3306, "lr": 2.4092136032986783e-06, "epoch": 14.121462264150944, "percentage": 70.61, "elapsed_time": "0:45:55", "remaining_time": "0:19:07", "throughput": 5721.48, "total_tokens": 15765968} {"current_steps": 23955, "total_steps": 33920, "loss": 0.3968, "lr": 2.407013541663043e-06, "epoch": 14.12441037735849, "percentage": 70.62, "elapsed_time": "0:45:56", "remaining_time": "0:19:06", "throughput": 5721.45, "total_tokens": 15768784} {"current_steps": 23960, "total_steps": 33920, "loss": 0.3451, "lr": 2.4048141665317493e-06, "epoch": 14.127358490566039, "percentage": 70.64, "elapsed_time": "0:45:56", "remaining_time": "0:19:05", "throughput": 5721.59, "total_tokens": 15772624} {"current_steps": 23965, "total_steps": 33920, "loss": 0.3421, "lr": 2.40261547848709e-06, "epoch": 14.130306603773585, "percentage": 70.65, "elapsed_time": "0:45:57", "remaining_time": "0:19:05", "throughput": 5721.57, "total_tokens": 15775984} {"current_steps": 23970, "total_steps": 33920, "loss": 0.4255, "lr": 2.400417478111176e-06, "epoch": 14.133254716981131, "percentage": 70.67, "elapsed_time": "0:45:57", "remaining_time": "0:19:04", "throughput": 5721.47, "total_tokens": 15778416} {"current_steps": 23975, "total_steps": 33920, "loss": 0.3657, "lr": 2.3982201659859387e-06, "epoch": 14.13620283018868, "percentage": 70.68, "elapsed_time": "0:45:58", "remaining_time": "0:19:04", "throughput": 5721.46, "total_tokens": 15781424} {"current_steps": 23980, "total_steps": 33920, "loss": 0.2987, "lr": 2.3960235426931237e-06, "epoch": 14.139150943396226, "percentage": 70.7, "elapsed_time": "0:45:58", "remaining_time": "0:19:03", "throughput": 5721.44, "total_tokens": 15784240} {"current_steps": 23985, "total_steps": 33920, "loss": 0.3372, "lr": 2.3938276088143003e-06, "epoch": 14.142099056603774, "percentage": 70.71, "elapsed_time": "0:45:59", "remaining_time": "0:19:02", "throughput": 5721.55, "total_tokens": 15787440} {"current_steps": 23990, "total_steps": 33920, "loss": 0.3126, "lr": 2.391632364930849e-06, "epoch": 14.14504716981132, "percentage": 70.73, "elapsed_time": "0:45:59", "remaining_time": "0:19:02", "throughput": 5721.66, "total_tokens": 15790768} {"current_steps": 23995, "total_steps": 33920, "loss": 0.3391, "lr": 2.3894378116239706e-06, "epoch": 14.147995283018869, "percentage": 70.74, "elapsed_time": "0:46:00", "remaining_time": "0:19:01", "throughput": 5721.67, "total_tokens": 15794128} {"current_steps": 24000, "total_steps": 33920, "loss": 0.3373, "lr": 2.387243949474683e-06, "epoch": 14.150943396226415, "percentage": 70.75, "elapsed_time": "0:46:00", "remaining_time": "0:19:01", "throughput": 5721.64, "total_tokens": 15796880} {"current_steps": 24005, "total_steps": 33920, "loss": 0.3723, "lr": 2.38505077906382e-06, "epoch": 14.153891509433961, "percentage": 70.77, "elapsed_time": "0:46:01", "remaining_time": "0:19:00", "throughput": 5721.89, "total_tokens": 15801392} {"current_steps": 24010, "total_steps": 33920, "loss": 0.3915, "lr": 2.382858300972031e-06, "epoch": 14.15683962264151, "percentage": 70.78, "elapsed_time": "0:46:02", "remaining_time": "0:19:00", "throughput": 5721.97, "total_tokens": 15804592} {"current_steps": 24015, "total_steps": 33920, "loss": 0.2903, "lr": 2.380666515779788e-06, "epoch": 14.159787735849056, "percentage": 70.8, "elapsed_time": "0:46:02", "remaining_time": "0:18:59", "throughput": 5721.94, "total_tokens": 15807408} {"current_steps": 24020, "total_steps": 33920, "loss": 0.3589, "lr": 2.3784754240673734e-06, "epoch": 14.162735849056604, "percentage": 70.81, "elapsed_time": "0:46:03", "remaining_time": "0:18:58", "throughput": 5721.97, "total_tokens": 15810384} {"current_steps": 24025, "total_steps": 33920, "loss": 0.3619, "lr": 2.3762850264148883e-06, "epoch": 14.16568396226415, "percentage": 70.83, "elapsed_time": "0:46:03", "remaining_time": "0:18:58", "throughput": 5722.08, "total_tokens": 15813776} {"current_steps": 24030, "total_steps": 33920, "loss": 0.4063, "lr": 2.374095323402251e-06, "epoch": 14.168632075471699, "percentage": 70.84, "elapsed_time": "0:46:04", "remaining_time": "0:18:57", "throughput": 5722.41, "total_tokens": 15820784} {"current_steps": 24035, "total_steps": 33920, "loss": 0.1986, "lr": 2.371906315609193e-06, "epoch": 14.171580188679245, "percentage": 70.86, "elapsed_time": "0:46:05", "remaining_time": "0:18:57", "throughput": 5722.44, "total_tokens": 15823824} {"current_steps": 24040, "total_steps": 33920, "loss": 0.4196, "lr": 2.369718003615263e-06, "epoch": 14.174528301886792, "percentage": 70.87, "elapsed_time": "0:46:05", "remaining_time": "0:18:56", "throughput": 5722.46, "total_tokens": 15826608} {"current_steps": 24045, "total_steps": 33920, "loss": 0.4197, "lr": 2.3675303879998284e-06, "epoch": 14.17747641509434, "percentage": 70.89, "elapsed_time": "0:46:06", "remaining_time": "0:18:56", "throughput": 5722.51, "total_tokens": 15829776} {"current_steps": 24050, "total_steps": 33920, "loss": 0.36, "lr": 2.365343469342068e-06, "epoch": 14.180424528301886, "percentage": 70.9, "elapsed_time": "0:46:06", "remaining_time": "0:18:55", "throughput": 5722.63, "total_tokens": 15833424} {"current_steps": 24055, "total_steps": 33920, "loss": 0.2349, "lr": 2.3631572482209803e-06, "epoch": 14.183372641509434, "percentage": 70.92, "elapsed_time": "0:46:07", "remaining_time": "0:18:54", "throughput": 5722.74, "total_tokens": 15836656} {"current_steps": 24060, "total_steps": 33920, "loss": 0.3839, "lr": 2.3609717252153752e-06, "epoch": 14.18632075471698, "percentage": 70.93, "elapsed_time": "0:46:07", "remaining_time": "0:18:54", "throughput": 5722.72, "total_tokens": 15839696} {"current_steps": 24065, "total_steps": 33920, "loss": 0.4087, "lr": 2.35878690090388e-06, "epoch": 14.189268867924529, "percentage": 70.95, "elapsed_time": "0:46:08", "remaining_time": "0:18:53", "throughput": 5722.91, "total_tokens": 15843504} {"current_steps": 24070, "total_steps": 33920, "loss": 0.402, "lr": 2.356602775864935e-06, "epoch": 14.192216981132075, "percentage": 70.96, "elapsed_time": "0:46:08", "remaining_time": "0:18:53", "throughput": 5723.03, "total_tokens": 15846800} {"current_steps": 24075, "total_steps": 33920, "loss": 0.3219, "lr": 2.354419350676796e-06, "epoch": 14.195165094339623, "percentage": 70.98, "elapsed_time": "0:46:09", "remaining_time": "0:18:52", "throughput": 5723.06, "total_tokens": 15849936} {"current_steps": 24080, "total_steps": 33920, "loss": 0.3113, "lr": 2.3522366259175377e-06, "epoch": 14.19811320754717, "percentage": 70.99, "elapsed_time": "0:46:10", "remaining_time": "0:18:51", "throughput": 5723.01, "total_tokens": 15852976} {"current_steps": 24085, "total_steps": 33920, "loss": 0.2257, "lr": 2.350054602165044e-06, "epoch": 14.201061320754716, "percentage": 71.01, "elapsed_time": "0:46:10", "remaining_time": "0:18:51", "throughput": 5723.13, "total_tokens": 15857008} {"current_steps": 24090, "total_steps": 33920, "loss": 0.3784, "lr": 2.3478732799970143e-06, "epoch": 14.204009433962264, "percentage": 71.02, "elapsed_time": "0:46:11", "remaining_time": "0:18:50", "throughput": 5722.92, "total_tokens": 15859216} {"current_steps": 24095, "total_steps": 33920, "loss": 0.3519, "lr": 2.3456926599909646e-06, "epoch": 14.20695754716981, "percentage": 71.03, "elapsed_time": "0:46:11", "remaining_time": "0:18:50", "throughput": 5723.04, "total_tokens": 15862512} {"current_steps": 24100, "total_steps": 33920, "loss": 0.274, "lr": 2.343512742724222e-06, "epoch": 14.209905660377359, "percentage": 71.05, "elapsed_time": "0:46:12", "remaining_time": "0:18:49", "throughput": 5723.12, "total_tokens": 15865840} {"current_steps": 24105, "total_steps": 33920, "loss": 0.2337, "lr": 2.341333528773928e-06, "epoch": 14.212853773584905, "percentage": 71.06, "elapsed_time": "0:46:12", "remaining_time": "0:18:49", "throughput": 5723.24, "total_tokens": 15869520} {"current_steps": 24110, "total_steps": 33920, "loss": 0.4347, "lr": 2.3391550187170427e-06, "epoch": 14.215801886792454, "percentage": 71.08, "elapsed_time": "0:46:13", "remaining_time": "0:18:48", "throughput": 5723.43, "total_tokens": 15873072} {"current_steps": 24115, "total_steps": 33920, "loss": 0.2922, "lr": 2.336977213130333e-06, "epoch": 14.21875, "percentage": 71.09, "elapsed_time": "0:46:13", "remaining_time": "0:18:47", "throughput": 5723.52, "total_tokens": 15876656} {"current_steps": 24120, "total_steps": 33920, "loss": 0.2435, "lr": 2.3348001125903837e-06, "epoch": 14.221698113207546, "percentage": 71.11, "elapsed_time": "0:46:14", "remaining_time": "0:18:47", "throughput": 5723.68, "total_tokens": 15880368} {"current_steps": 24125, "total_steps": 33920, "loss": 0.2685, "lr": 2.3326237176735905e-06, "epoch": 14.224646226415095, "percentage": 71.12, "elapsed_time": "0:46:15", "remaining_time": "0:18:46", "throughput": 5723.85, "total_tokens": 15884272} {"current_steps": 24130, "total_steps": 33920, "loss": 0.4165, "lr": 2.330448028956164e-06, "epoch": 14.227594339622641, "percentage": 71.14, "elapsed_time": "0:46:15", "remaining_time": "0:18:46", "throughput": 5723.94, "total_tokens": 15887376} {"current_steps": 24135, "total_steps": 33920, "loss": 0.3006, "lr": 2.3282730470141255e-06, "epoch": 14.23054245283019, "percentage": 71.15, "elapsed_time": "0:46:16", "remaining_time": "0:18:45", "throughput": 5724.15, "total_tokens": 15891632} {"current_steps": 24140, "total_steps": 33920, "loss": 0.259, "lr": 2.3260987724233143e-06, "epoch": 14.233490566037736, "percentage": 71.17, "elapsed_time": "0:46:16", "remaining_time": "0:18:44", "throughput": 5724.3, "total_tokens": 15895408} {"current_steps": 24145, "total_steps": 33920, "loss": 0.3564, "lr": 2.323925205759374e-06, "epoch": 14.236438679245284, "percentage": 71.18, "elapsed_time": "0:46:17", "remaining_time": "0:18:44", "throughput": 5724.37, "total_tokens": 15898736} {"current_steps": 24150, "total_steps": 33920, "loss": 0.2949, "lr": 2.3217523475977715e-06, "epoch": 14.23938679245283, "percentage": 71.2, "elapsed_time": "0:46:17", "remaining_time": "0:18:43", "throughput": 5724.14, "total_tokens": 15901232} {"current_steps": 24155, "total_steps": 33920, "loss": 0.3959, "lr": 2.3195801985137773e-06, "epoch": 14.242334905660377, "percentage": 71.21, "elapsed_time": "0:46:18", "remaining_time": "0:18:43", "throughput": 5724.34, "total_tokens": 15904912} {"current_steps": 24160, "total_steps": 33920, "loss": 0.2769, "lr": 2.317408759082478e-06, "epoch": 14.245283018867925, "percentage": 71.23, "elapsed_time": "0:46:18", "remaining_time": "0:18:42", "throughput": 5724.46, "total_tokens": 15908176} {"current_steps": 24165, "total_steps": 33920, "loss": 0.3429, "lr": 2.31523802987877e-06, "epoch": 14.248231132075471, "percentage": 71.24, "elapsed_time": "0:46:19", "remaining_time": "0:18:42", "throughput": 5724.56, "total_tokens": 15911600} {"current_steps": 24170, "total_steps": 33920, "loss": 0.2988, "lr": 2.3130680114773637e-06, "epoch": 14.25117924528302, "percentage": 71.26, "elapsed_time": "0:46:20", "remaining_time": "0:18:41", "throughput": 5724.54, "total_tokens": 15914384} {"current_steps": 24175, "total_steps": 33920, "loss": 0.4612, "lr": 2.310898704452782e-06, "epoch": 14.254127358490566, "percentage": 71.27, "elapsed_time": "0:46:20", "remaining_time": "0:18:40", "throughput": 5724.61, "total_tokens": 15917328} {"current_steps": 24180, "total_steps": 33920, "loss": 0.2781, "lr": 2.3087301093793584e-06, "epoch": 14.257075471698114, "percentage": 71.29, "elapsed_time": "0:46:21", "remaining_time": "0:18:40", "throughput": 5724.7, "total_tokens": 15920528} {"current_steps": 24185, "total_steps": 33920, "loss": 0.268, "lr": 2.306562226831237e-06, "epoch": 14.26002358490566, "percentage": 71.3, "elapsed_time": "0:46:21", "remaining_time": "0:18:39", "throughput": 5724.91, "total_tokens": 15924496} {"current_steps": 24190, "total_steps": 33920, "loss": 0.2596, "lr": 2.304395057382374e-06, "epoch": 14.262971698113208, "percentage": 71.31, "elapsed_time": "0:46:22", "remaining_time": "0:18:39", "throughput": 5725.05, "total_tokens": 15928048} {"current_steps": 24195, "total_steps": 33920, "loss": 0.3348, "lr": 2.3022286016065354e-06, "epoch": 14.265919811320755, "percentage": 71.33, "elapsed_time": "0:46:22", "remaining_time": "0:18:38", "throughput": 5724.9, "total_tokens": 15930320} {"current_steps": 24200, "total_steps": 33920, "loss": 0.2971, "lr": 2.300062860077303e-06, "epoch": 14.268867924528301, "percentage": 71.34, "elapsed_time": "0:46:23", "remaining_time": "0:18:37", "throughput": 5725.0, "total_tokens": 15933488} {"current_steps": 24205, "total_steps": 33920, "loss": 0.3638, "lr": 2.297897833368064e-06, "epoch": 14.27181603773585, "percentage": 71.36, "elapsed_time": "0:46:23", "remaining_time": "0:18:37", "throughput": 5725.14, "total_tokens": 15937456} {"current_steps": 24210, "total_steps": 33920, "loss": 0.2844, "lr": 2.2957335220520194e-06, "epoch": 14.274764150943396, "percentage": 71.37, "elapsed_time": "0:46:24", "remaining_time": "0:18:36", "throughput": 5725.15, "total_tokens": 15940336} {"current_steps": 24215, "total_steps": 33920, "loss": 0.3234, "lr": 2.293569926702179e-06, "epoch": 14.277712264150944, "percentage": 71.39, "elapsed_time": "0:46:24", "remaining_time": "0:18:36", "throughput": 5725.17, "total_tokens": 15943664} {"current_steps": 24220, "total_steps": 33920, "loss": 0.2792, "lr": 2.291407047891366e-06, "epoch": 14.28066037735849, "percentage": 71.4, "elapsed_time": "0:46:25", "remaining_time": "0:18:35", "throughput": 5725.1, "total_tokens": 15946160} {"current_steps": 24225, "total_steps": 33920, "loss": 0.3187, "lr": 2.2892448861922075e-06, "epoch": 14.283608490566039, "percentage": 71.42, "elapsed_time": "0:46:25", "remaining_time": "0:18:34", "throughput": 5725.14, "total_tokens": 15949552} {"current_steps": 24230, "total_steps": 33920, "loss": 0.2214, "lr": 2.2870834421771505e-06, "epoch": 14.286556603773585, "percentage": 71.43, "elapsed_time": "0:46:26", "remaining_time": "0:18:34", "throughput": 5725.27, "total_tokens": 15953360} {"current_steps": 24235, "total_steps": 33920, "loss": 0.3072, "lr": 2.2849227164184433e-06, "epoch": 14.289504716981131, "percentage": 71.45, "elapsed_time": "0:46:26", "remaining_time": "0:18:33", "throughput": 5725.25, "total_tokens": 15955888} {"current_steps": 24240, "total_steps": 33920, "loss": 0.3027, "lr": 2.2827627094881473e-06, "epoch": 14.29245283018868, "percentage": 71.46, "elapsed_time": "0:46:27", "remaining_time": "0:18:33", "throughput": 5725.2, "total_tokens": 15958480} {"current_steps": 24245, "total_steps": 33920, "loss": 0.3307, "lr": 2.2806034219581364e-06, "epoch": 14.295400943396226, "percentage": 71.48, "elapsed_time": "0:46:27", "remaining_time": "0:18:32", "throughput": 5725.14, "total_tokens": 15960944} {"current_steps": 24250, "total_steps": 33920, "loss": 0.2943, "lr": 2.278444854400089e-06, "epoch": 14.298349056603774, "percentage": 71.49, "elapsed_time": "0:46:28", "remaining_time": "0:18:31", "throughput": 5725.22, "total_tokens": 15963952} {"current_steps": 24255, "total_steps": 33920, "loss": 0.3075, "lr": 2.276287007385496e-06, "epoch": 14.30129716981132, "percentage": 71.51, "elapsed_time": "0:46:28", "remaining_time": "0:18:31", "throughput": 5725.33, "total_tokens": 15967184} {"current_steps": 24260, "total_steps": 33920, "loss": 0.2705, "lr": 2.2741298814856542e-06, "epoch": 14.304245283018869, "percentage": 71.52, "elapsed_time": "0:46:29", "remaining_time": "0:18:30", "throughput": 5725.3, "total_tokens": 15969776} {"current_steps": 24265, "total_steps": 33920, "loss": 0.3575, "lr": 2.2719734772716763e-06, "epoch": 14.307193396226415, "percentage": 71.54, "elapsed_time": "0:46:29", "remaining_time": "0:18:30", "throughput": 5725.53, "total_tokens": 15973840} {"current_steps": 24270, "total_steps": 33920, "loss": 0.3722, "lr": 2.269817795314477e-06, "epoch": 14.310141509433961, "percentage": 71.55, "elapsed_time": "0:46:30", "remaining_time": "0:18:29", "throughput": 5725.99, "total_tokens": 15981008} {"current_steps": 24275, "total_steps": 33920, "loss": 0.357, "lr": 2.2676628361847834e-06, "epoch": 14.31308962264151, "percentage": 71.57, "elapsed_time": "0:46:31", "remaining_time": "0:18:29", "throughput": 5725.92, "total_tokens": 15983472} {"current_steps": 24280, "total_steps": 33920, "loss": 0.4436, "lr": 2.2655086004531296e-06, "epoch": 14.316037735849056, "percentage": 71.58, "elapsed_time": "0:46:31", "remaining_time": "0:18:28", "throughput": 5726.09, "total_tokens": 15987216} {"current_steps": 24285, "total_steps": 33920, "loss": 0.2307, "lr": 2.2633550886898583e-06, "epoch": 14.318985849056604, "percentage": 71.59, "elapsed_time": "0:46:32", "remaining_time": "0:18:27", "throughput": 5726.14, "total_tokens": 15990352} {"current_steps": 24290, "total_steps": 33920, "loss": 0.35, "lr": 2.26120230146512e-06, "epoch": 14.32193396226415, "percentage": 71.61, "elapsed_time": "0:46:33", "remaining_time": "0:18:27", "throughput": 5726.24, "total_tokens": 15994064} {"current_steps": 24295, "total_steps": 33920, "loss": 0.387, "lr": 2.2590502393488777e-06, "epoch": 14.324882075471699, "percentage": 71.62, "elapsed_time": "0:46:33", "remaining_time": "0:18:26", "throughput": 5726.19, "total_tokens": 15996912} {"current_steps": 24300, "total_steps": 33920, "loss": 0.2961, "lr": 2.256898902910898e-06, "epoch": 14.327830188679245, "percentage": 71.64, "elapsed_time": "0:46:34", "remaining_time": "0:18:26", "throughput": 5726.06, "total_tokens": 15999472} {"current_steps": 24305, "total_steps": 33920, "loss": 0.2827, "lr": 2.2547482927207548e-06, "epoch": 14.330778301886792, "percentage": 71.65, "elapsed_time": "0:46:34", "remaining_time": "0:18:25", "throughput": 5726.2, "total_tokens": 16003088} {"current_steps": 24310, "total_steps": 33920, "loss": 0.3858, "lr": 2.252598409347833e-06, "epoch": 14.33372641509434, "percentage": 71.67, "elapsed_time": "0:46:35", "remaining_time": "0:18:24", "throughput": 5726.18, "total_tokens": 16005808} {"current_steps": 24315, "total_steps": 33920, "loss": 0.2975, "lr": 2.250449253361323e-06, "epoch": 14.336674528301886, "percentage": 71.68, "elapsed_time": "0:46:36", "remaining_time": "0:18:24", "throughput": 5726.34, "total_tokens": 16012688} {"current_steps": 24320, "total_steps": 33920, "loss": 0.3857, "lr": 2.2483008253302214e-06, "epoch": 14.339622641509434, "percentage": 71.7, "elapsed_time": "0:46:36", "remaining_time": "0:18:24", "throughput": 5726.35, "total_tokens": 16015504} {"current_steps": 24325, "total_steps": 33920, "loss": 0.233, "lr": 2.246153125823337e-06, "epoch": 14.34257075471698, "percentage": 71.71, "elapsed_time": "0:46:37", "remaining_time": "0:18:23", "throughput": 5726.5, "total_tokens": 16019120} {"current_steps": 24330, "total_steps": 33920, "loss": 0.2131, "lr": 2.2440061554092813e-06, "epoch": 14.345518867924529, "percentage": 71.73, "elapsed_time": "0:46:38", "remaining_time": "0:18:22", "throughput": 5726.63, "total_tokens": 16023184} {"current_steps": 24335, "total_steps": 33920, "loss": 0.37, "lr": 2.2418599146564714e-06, "epoch": 14.348466981132075, "percentage": 71.74, "elapsed_time": "0:46:38", "remaining_time": "0:18:22", "throughput": 5726.51, "total_tokens": 16025712} {"current_steps": 24340, "total_steps": 33920, "loss": 0.3985, "lr": 2.239714404133138e-06, "epoch": 14.351415094339623, "percentage": 71.76, "elapsed_time": "0:46:39", "remaining_time": "0:18:21", "throughput": 5726.45, "total_tokens": 16028496} {"current_steps": 24345, "total_steps": 33920, "loss": 0.365, "lr": 2.2375696244073126e-06, "epoch": 14.35436320754717, "percentage": 71.77, "elapsed_time": "0:46:39", "remaining_time": "0:18:21", "throughput": 5726.42, "total_tokens": 16031216} {"current_steps": 24350, "total_steps": 33920, "loss": 0.3398, "lr": 2.235425576046834e-06, "epoch": 14.357311320754716, "percentage": 71.79, "elapsed_time": "0:46:40", "remaining_time": "0:18:20", "throughput": 5726.63, "total_tokens": 16035440} {"current_steps": 24355, "total_steps": 33920, "loss": 0.3048, "lr": 2.233282259619347e-06, "epoch": 14.360259433962264, "percentage": 71.8, "elapsed_time": "0:46:40", "remaining_time": "0:18:19", "throughput": 5726.91, "total_tokens": 16040208} {"current_steps": 24360, "total_steps": 33920, "loss": 0.305, "lr": 2.231139675692308e-06, "epoch": 14.36320754716981, "percentage": 71.82, "elapsed_time": "0:46:41", "remaining_time": "0:18:19", "throughput": 5726.87, "total_tokens": 16043088} {"current_steps": 24365, "total_steps": 33920, "loss": 0.3536, "lr": 2.228997824832973e-06, "epoch": 14.366155660377359, "percentage": 71.83, "elapsed_time": "0:46:41", "remaining_time": "0:18:18", "throughput": 5727.0, "total_tokens": 16046736} {"current_steps": 24370, "total_steps": 33920, "loss": 0.309, "lr": 2.226856707608406e-06, "epoch": 14.369103773584905, "percentage": 71.85, "elapsed_time": "0:46:42", "remaining_time": "0:18:18", "throughput": 5727.09, "total_tokens": 16049968} {"current_steps": 24375, "total_steps": 33920, "loss": 0.3582, "lr": 2.2247163245854768e-06, "epoch": 14.372051886792454, "percentage": 71.86, "elapsed_time": "0:46:43", "remaining_time": "0:18:17", "throughput": 5727.33, "total_tokens": 16054224} {"current_steps": 24380, "total_steps": 33920, "loss": 0.319, "lr": 2.222576676330862e-06, "epoch": 14.375, "percentage": 71.88, "elapsed_time": "0:46:43", "remaining_time": "0:18:17", "throughput": 5727.45, "total_tokens": 16057552} {"current_steps": 24385, "total_steps": 33920, "loss": 0.4006, "lr": 2.2204377634110403e-06, "epoch": 14.377948113207546, "percentage": 71.89, "elapsed_time": "0:46:44", "remaining_time": "0:18:16", "throughput": 5727.55, "total_tokens": 16061072} {"current_steps": 24390, "total_steps": 33920, "loss": 0.3404, "lr": 2.218299586392301e-06, "epoch": 14.380896226415095, "percentage": 71.9, "elapsed_time": "0:46:44", "remaining_time": "0:18:15", "throughput": 5727.59, "total_tokens": 16064272} {"current_steps": 24395, "total_steps": 33920, "loss": 0.2965, "lr": 2.2161621458407355e-06, "epoch": 14.383844339622641, "percentage": 71.92, "elapsed_time": "0:46:45", "remaining_time": "0:18:15", "throughput": 5727.78, "total_tokens": 16068080} {"current_steps": 24400, "total_steps": 33920, "loss": 0.2487, "lr": 2.2140254423222398e-06, "epoch": 14.38679245283019, "percentage": 71.93, "elapsed_time": "0:46:45", "remaining_time": "0:18:14", "throughput": 5727.92, "total_tokens": 16071728} {"current_steps": 24405, "total_steps": 33920, "loss": 0.409, "lr": 2.2118894764025146e-06, "epoch": 14.389740566037736, "percentage": 71.95, "elapsed_time": "0:46:46", "remaining_time": "0:18:14", "throughput": 5727.81, "total_tokens": 16074256} {"current_steps": 24410, "total_steps": 33920, "loss": 0.317, "lr": 2.2097542486470667e-06, "epoch": 14.392688679245284, "percentage": 71.96, "elapsed_time": "0:46:46", "remaining_time": "0:18:13", "throughput": 5727.62, "total_tokens": 16076528} {"current_steps": 24415, "total_steps": 33920, "loss": 0.3905, "lr": 2.207619759621205e-06, "epoch": 14.39563679245283, "percentage": 71.98, "elapsed_time": "0:46:47", "remaining_time": "0:18:12", "throughput": 5727.65, "total_tokens": 16079664} {"current_steps": 24420, "total_steps": 33920, "loss": 0.2988, "lr": 2.205486009890049e-06, "epoch": 14.398584905660377, "percentage": 71.99, "elapsed_time": "0:46:47", "remaining_time": "0:18:12", "throughput": 5727.85, "total_tokens": 16083696} {"current_steps": 24425, "total_steps": 33920, "loss": 0.3919, "lr": 2.2033530000185146e-06, "epoch": 14.401533018867925, "percentage": 72.01, "elapsed_time": "0:46:48", "remaining_time": "0:18:11", "throughput": 5727.96, "total_tokens": 16086864} {"current_steps": 24430, "total_steps": 33920, "loss": 0.2785, "lr": 2.2012207305713244e-06, "epoch": 14.404481132075471, "percentage": 72.02, "elapsed_time": "0:46:48", "remaining_time": "0:18:11", "throughput": 5727.93, "total_tokens": 16089392} {"current_steps": 24435, "total_steps": 33920, "loss": 0.3006, "lr": 2.19908920211301e-06, "epoch": 14.40742924528302, "percentage": 72.04, "elapsed_time": "0:46:49", "remaining_time": "0:18:10", "throughput": 5728.04, "total_tokens": 16092688} {"current_steps": 24440, "total_steps": 33920, "loss": 0.2934, "lr": 2.196958415207901e-06, "epoch": 14.410377358490566, "percentage": 72.05, "elapsed_time": "0:46:50", "remaining_time": "0:18:09", "throughput": 5728.18, "total_tokens": 16096240} {"current_steps": 24445, "total_steps": 33920, "loss": 0.3167, "lr": 2.1948283704201312e-06, "epoch": 14.413325471698114, "percentage": 72.07, "elapsed_time": "0:46:50", "remaining_time": "0:18:09", "throughput": 5728.17, "total_tokens": 16098928} {"current_steps": 24450, "total_steps": 33920, "loss": 0.2274, "lr": 2.1926990683136383e-06, "epoch": 14.41627358490566, "percentage": 72.08, "elapsed_time": "0:46:51", "remaining_time": "0:18:08", "throughput": 5728.33, "total_tokens": 16102480} {"current_steps": 24455, "total_steps": 33920, "loss": 0.2584, "lr": 2.1905705094521685e-06, "epoch": 14.419221698113208, "percentage": 72.1, "elapsed_time": "0:46:51", "remaining_time": "0:18:08", "throughput": 5728.4, "total_tokens": 16105424} {"current_steps": 24460, "total_steps": 33920, "loss": 0.3662, "lr": 2.1884426943992635e-06, "epoch": 14.422169811320755, "percentage": 72.11, "elapsed_time": "0:46:52", "remaining_time": "0:18:07", "throughput": 5728.55, "total_tokens": 16108880} {"current_steps": 24465, "total_steps": 33920, "loss": 0.2988, "lr": 2.1863156237182727e-06, "epoch": 14.425117924528301, "percentage": 72.13, "elapsed_time": "0:46:52", "remaining_time": "0:18:07", "throughput": 5728.71, "total_tokens": 16112880} {"current_steps": 24470, "total_steps": 33920, "loss": 0.1975, "lr": 2.1841892979723466e-06, "epoch": 14.42806603773585, "percentage": 72.14, "elapsed_time": "0:46:53", "remaining_time": "0:18:06", "throughput": 5728.67, "total_tokens": 16115440} {"current_steps": 24475, "total_steps": 33920, "loss": 0.4245, "lr": 2.1820637177244375e-06, "epoch": 14.431014150943396, "percentage": 72.16, "elapsed_time": "0:46:53", "remaining_time": "0:18:05", "throughput": 5728.76, "total_tokens": 16118576} {"current_steps": 24480, "total_steps": 33920, "loss": 0.3043, "lr": 2.179938883537306e-06, "epoch": 14.433962264150944, "percentage": 72.17, "elapsed_time": "0:46:54", "remaining_time": "0:18:05", "throughput": 5728.72, "total_tokens": 16121296} {"current_steps": 24485, "total_steps": 33920, "loss": 0.3252, "lr": 2.177814795973508e-06, "epoch": 14.43691037735849, "percentage": 72.18, "elapsed_time": "0:46:54", "remaining_time": "0:18:04", "throughput": 5728.91, "total_tokens": 16125296} {"current_steps": 24490, "total_steps": 33920, "loss": 0.2778, "lr": 2.1756914555954064e-06, "epoch": 14.439858490566039, "percentage": 72.2, "elapsed_time": "0:46:55", "remaining_time": "0:18:04", "throughput": 5728.97, "total_tokens": 16128720} {"current_steps": 24495, "total_steps": 33920, "loss": 0.3819, "lr": 2.173568862965164e-06, "epoch": 14.442806603773585, "percentage": 72.21, "elapsed_time": "0:46:55", "remaining_time": "0:18:03", "throughput": 5729.06, "total_tokens": 16132016} {"current_steps": 24500, "total_steps": 33920, "loss": 0.295, "lr": 2.171447018644746e-06, "epoch": 14.445754716981131, "percentage": 72.23, "elapsed_time": "0:46:56", "remaining_time": "0:18:02", "throughput": 5728.97, "total_tokens": 16134544} {"current_steps": 24505, "total_steps": 33920, "loss": 0.3824, "lr": 2.1693259231959186e-06, "epoch": 14.44870283018868, "percentage": 72.24, "elapsed_time": "0:46:56", "remaining_time": "0:18:02", "throughput": 5728.94, "total_tokens": 16137168} {"current_steps": 24510, "total_steps": 33920, "loss": 0.3936, "lr": 2.1672055771802545e-06, "epoch": 14.451650943396226, "percentage": 72.26, "elapsed_time": "0:46:57", "remaining_time": "0:18:01", "throughput": 5729.04, "total_tokens": 16140784} {"current_steps": 24515, "total_steps": 33920, "loss": 0.321, "lr": 2.1650859811591224e-06, "epoch": 14.454599056603774, "percentage": 72.27, "elapsed_time": "0:46:57", "remaining_time": "0:18:01", "throughput": 5729.15, "total_tokens": 16144112} {"current_steps": 24520, "total_steps": 33920, "loss": 0.2936, "lr": 2.1629671356936943e-06, "epoch": 14.45754716981132, "percentage": 72.29, "elapsed_time": "0:46:58", "remaining_time": "0:18:00", "throughput": 5729.17, "total_tokens": 16146800} {"current_steps": 24525, "total_steps": 33920, "loss": 0.3489, "lr": 2.1608490413449428e-06, "epoch": 14.460495283018869, "percentage": 72.3, "elapsed_time": "0:46:58", "remaining_time": "0:17:59", "throughput": 5729.32, "total_tokens": 16150448} {"current_steps": 24530, "total_steps": 33920, "loss": 0.3405, "lr": 2.158731698673645e-06, "epoch": 14.463443396226415, "percentage": 72.32, "elapsed_time": "0:46:59", "remaining_time": "0:17:59", "throughput": 5729.46, "total_tokens": 16153968} {"current_steps": 24535, "total_steps": 33920, "loss": 0.3724, "lr": 2.1566151082403752e-06, "epoch": 14.466391509433961, "percentage": 72.33, "elapsed_time": "0:47:00", "remaining_time": "0:17:58", "throughput": 5729.76, "total_tokens": 16158608} {"current_steps": 24540, "total_steps": 33920, "loss": 0.2717, "lr": 2.154499270605508e-06, "epoch": 14.46933962264151, "percentage": 72.35, "elapsed_time": "0:47:00", "remaining_time": "0:17:58", "throughput": 5729.74, "total_tokens": 16161360} {"current_steps": 24545, "total_steps": 33920, "loss": 0.3602, "lr": 2.1523841863292243e-06, "epoch": 14.472287735849056, "percentage": 72.36, "elapsed_time": "0:47:01", "remaining_time": "0:17:57", "throughput": 5729.91, "total_tokens": 16165168} {"current_steps": 24550, "total_steps": 33920, "loss": 0.2977, "lr": 2.1502698559714998e-06, "epoch": 14.475235849056604, "percentage": 72.38, "elapsed_time": "0:47:01", "remaining_time": "0:17:56", "throughput": 5730.04, "total_tokens": 16168400} {"current_steps": 24555, "total_steps": 33920, "loss": 0.3392, "lr": 2.1481562800921125e-06, "epoch": 14.47818396226415, "percentage": 72.39, "elapsed_time": "0:47:02", "remaining_time": "0:17:56", "throughput": 5730.11, "total_tokens": 16171600} {"current_steps": 24560, "total_steps": 33920, "loss": 0.3625, "lr": 2.146043459250641e-06, "epoch": 14.481132075471699, "percentage": 72.41, "elapsed_time": "0:47:02", "remaining_time": "0:17:55", "throughput": 5730.31, "total_tokens": 16175952} {"current_steps": 24565, "total_steps": 33920, "loss": 0.2612, "lr": 2.1439313940064634e-06, "epoch": 14.484080188679245, "percentage": 72.42, "elapsed_time": "0:47:03", "remaining_time": "0:17:55", "throughput": 5730.44, "total_tokens": 16179664} {"current_steps": 24570, "total_steps": 33920, "loss": 0.3384, "lr": 2.141820084918756e-06, "epoch": 14.487028301886792, "percentage": 72.44, "elapsed_time": "0:47:03", "remaining_time": "0:17:54", "throughput": 5730.49, "total_tokens": 16182736} {"current_steps": 24575, "total_steps": 33920, "loss": 0.3746, "lr": 2.1397095325465013e-06, "epoch": 14.48997641509434, "percentage": 72.45, "elapsed_time": "0:47:04", "remaining_time": "0:17:54", "throughput": 5730.72, "total_tokens": 16187216} {"current_steps": 24580, "total_steps": 33920, "loss": 0.2135, "lr": 2.1375997374484754e-06, "epoch": 14.492924528301886, "percentage": 72.46, "elapsed_time": "0:47:05", "remaining_time": "0:17:53", "throughput": 5730.81, "total_tokens": 16190256} {"current_steps": 24585, "total_steps": 33920, "loss": 0.5057, "lr": 2.1354907001832546e-06, "epoch": 14.495872641509434, "percentage": 72.48, "elapsed_time": "0:47:05", "remaining_time": "0:17:52", "throughput": 5730.87, "total_tokens": 16193328} {"current_steps": 24590, "total_steps": 33920, "loss": 0.3863, "lr": 2.133382421309217e-06, "epoch": 14.49882075471698, "percentage": 72.49, "elapsed_time": "0:47:06", "remaining_time": "0:17:52", "throughput": 5730.96, "total_tokens": 16197200} {"current_steps": 24595, "total_steps": 33920, "loss": 0.3252, "lr": 2.131274901384537e-06, "epoch": 14.501768867924529, "percentage": 72.51, "elapsed_time": "0:47:06", "remaining_time": "0:17:51", "throughput": 5730.99, "total_tokens": 16200112} {"current_steps": 24600, "total_steps": 33920, "loss": 0.2839, "lr": 2.1291681409671896e-06, "epoch": 14.504716981132075, "percentage": 72.52, "elapsed_time": "0:47:07", "remaining_time": "0:17:51", "throughput": 5731.02, "total_tokens": 16203536} {"current_steps": 24605, "total_steps": 33920, "loss": 0.3152, "lr": 2.12706214061495e-06, "epoch": 14.507665094339622, "percentage": 72.54, "elapsed_time": "0:47:07", "remaining_time": "0:17:50", "throughput": 5730.84, "total_tokens": 16206096} {"current_steps": 24610, "total_steps": 33920, "loss": 0.2037, "lr": 2.124956900885391e-06, "epoch": 14.51061320754717, "percentage": 72.55, "elapsed_time": "0:47:08", "remaining_time": "0:17:50", "throughput": 5730.79, "total_tokens": 16209520} {"current_steps": 24615, "total_steps": 33920, "loss": 0.3195, "lr": 2.1228524223358833e-06, "epoch": 14.513561320754716, "percentage": 72.57, "elapsed_time": "0:47:09", "remaining_time": "0:17:49", "throughput": 5730.99, "total_tokens": 16213744} {"current_steps": 24620, "total_steps": 33920, "loss": 0.3604, "lr": 2.120748705523595e-06, "epoch": 14.516509433962264, "percentage": 72.58, "elapsed_time": "0:47:09", "remaining_time": "0:17:48", "throughput": 5731.1, "total_tokens": 16217648} {"current_steps": 24625, "total_steps": 33920, "loss": 0.3207, "lr": 2.1186457510054976e-06, "epoch": 14.51945754716981, "percentage": 72.6, "elapsed_time": "0:47:10", "remaining_time": "0:17:48", "throughput": 5731.05, "total_tokens": 16220592} {"current_steps": 24630, "total_steps": 33920, "loss": 0.3908, "lr": 2.116543559338355e-06, "epoch": 14.522405660377359, "percentage": 72.61, "elapsed_time": "0:47:10", "remaining_time": "0:17:47", "throughput": 5730.75, "total_tokens": 16222832} {"current_steps": 24635, "total_steps": 33920, "loss": 0.2537, "lr": 2.1144421310787305e-06, "epoch": 14.525353773584905, "percentage": 72.63, "elapsed_time": "0:47:11", "remaining_time": "0:17:47", "throughput": 5730.96, "total_tokens": 16226800} {"current_steps": 24640, "total_steps": 33920, "loss": 0.3286, "lr": 2.11234146678299e-06, "epoch": 14.528301886792454, "percentage": 72.64, "elapsed_time": "0:47:11", "remaining_time": "0:17:46", "throughput": 5730.79, "total_tokens": 16229424} {"current_steps": 24645, "total_steps": 33920, "loss": 0.3161, "lr": 2.1102415670072907e-06, "epoch": 14.53125, "percentage": 72.66, "elapsed_time": "0:47:12", "remaining_time": "0:17:46", "throughput": 5730.99, "total_tokens": 16233904} {"current_steps": 24650, "total_steps": 33920, "loss": 0.3441, "lr": 2.108142432307591e-06, "epoch": 14.534198113207546, "percentage": 72.67, "elapsed_time": "0:47:13", "remaining_time": "0:17:45", "throughput": 5731.14, "total_tokens": 16237808} {"current_steps": 24655, "total_steps": 33920, "loss": 0.3469, "lr": 2.1060440632396456e-06, "epoch": 14.537146226415095, "percentage": 72.69, "elapsed_time": "0:47:13", "remaining_time": "0:17:44", "throughput": 5731.3, "total_tokens": 16241584} {"current_steps": 24660, "total_steps": 33920, "loss": 0.3933, "lr": 2.103946460359007e-06, "epoch": 14.540094339622641, "percentage": 72.7, "elapsed_time": "0:47:14", "remaining_time": "0:17:44", "throughput": 5731.3, "total_tokens": 16244432} {"current_steps": 24665, "total_steps": 33920, "loss": 0.2669, "lr": 2.101849624221022e-06, "epoch": 14.54304245283019, "percentage": 72.72, "elapsed_time": "0:47:14", "remaining_time": "0:17:43", "throughput": 5731.3, "total_tokens": 16247344} {"current_steps": 24670, "total_steps": 33920, "loss": 0.3155, "lr": 2.0997535553808417e-06, "epoch": 14.545990566037736, "percentage": 72.73, "elapsed_time": "0:47:15", "remaining_time": "0:17:43", "throughput": 5731.37, "total_tokens": 16250704} {"current_steps": 24675, "total_steps": 33920, "loss": 0.3706, "lr": 2.0976582543934064e-06, "epoch": 14.548938679245284, "percentage": 72.74, "elapsed_time": "0:47:15", "remaining_time": "0:17:42", "throughput": 5731.39, "total_tokens": 16253552} {"current_steps": 24680, "total_steps": 33920, "loss": 0.384, "lr": 2.0955637218134573e-06, "epoch": 14.55188679245283, "percentage": 72.76, "elapsed_time": "0:47:16", "remaining_time": "0:17:41", "throughput": 5731.42, "total_tokens": 16256240} {"current_steps": 24685, "total_steps": 33920, "loss": 0.3212, "lr": 2.09346995819553e-06, "epoch": 14.554834905660378, "percentage": 72.77, "elapsed_time": "0:47:16", "remaining_time": "0:17:41", "throughput": 5731.54, "total_tokens": 16259760} {"current_steps": 24690, "total_steps": 33920, "loss": 0.3434, "lr": 2.0913769640939553e-06, "epoch": 14.557783018867925, "percentage": 72.79, "elapsed_time": "0:47:17", "remaining_time": "0:17:40", "throughput": 5731.71, "total_tokens": 16265648} {"current_steps": 24695, "total_steps": 33920, "loss": 0.4528, "lr": 2.0892847400628674e-06, "epoch": 14.560731132075471, "percentage": 72.8, "elapsed_time": "0:47:18", "remaining_time": "0:17:40", "throughput": 5731.59, "total_tokens": 16268144} {"current_steps": 24700, "total_steps": 33920, "loss": 0.2354, "lr": 2.0871932866561885e-06, "epoch": 14.56367924528302, "percentage": 72.82, "elapsed_time": "0:47:18", "remaining_time": "0:17:39", "throughput": 5731.76, "total_tokens": 16271920} {"current_steps": 24705, "total_steps": 33920, "loss": 0.2196, "lr": 2.0851026044276405e-06, "epoch": 14.566627358490566, "percentage": 72.83, "elapsed_time": "0:47:19", "remaining_time": "0:17:39", "throughput": 5731.91, "total_tokens": 16275408} {"current_steps": 24710, "total_steps": 33920, "loss": 0.2518, "lr": 2.083012693930741e-06, "epoch": 14.569575471698114, "percentage": 72.85, "elapsed_time": "0:47:20", "remaining_time": "0:17:38", "throughput": 5732.1, "total_tokens": 16279376} {"current_steps": 24715, "total_steps": 33920, "loss": 0.4315, "lr": 2.0809235557188e-06, "epoch": 14.57252358490566, "percentage": 72.86, "elapsed_time": "0:47:20", "remaining_time": "0:17:37", "throughput": 5731.87, "total_tokens": 16281776} {"current_steps": 24720, "total_steps": 33920, "loss": 0.4253, "lr": 2.0788351903449307e-06, "epoch": 14.575471698113208, "percentage": 72.88, "elapsed_time": "0:47:21", "remaining_time": "0:17:37", "throughput": 5731.98, "total_tokens": 16285264} {"current_steps": 24725, "total_steps": 33920, "loss": 0.3887, "lr": 2.0767475983620317e-06, "epoch": 14.578419811320755, "percentage": 72.89, "elapsed_time": "0:47:21", "remaining_time": "0:17:36", "throughput": 5732.22, "total_tokens": 16289392} {"current_steps": 24730, "total_steps": 33920, "loss": 0.2601, "lr": 2.074660780322806e-06, "epoch": 14.581367924528301, "percentage": 72.91, "elapsed_time": "0:47:22", "remaining_time": "0:17:36", "throughput": 5732.32, "total_tokens": 16292944} {"current_steps": 24735, "total_steps": 33920, "loss": 0.274, "lr": 2.0725747367797473e-06, "epoch": 14.58431603773585, "percentage": 72.92, "elapsed_time": "0:47:22", "remaining_time": "0:17:35", "throughput": 5732.29, "total_tokens": 16295984} {"current_steps": 24740, "total_steps": 33920, "loss": 0.301, "lr": 2.070489468285143e-06, "epoch": 14.587264150943396, "percentage": 72.94, "elapsed_time": "0:47:23", "remaining_time": "0:17:35", "throughput": 5732.26, "total_tokens": 16298608} {"current_steps": 24745, "total_steps": 33920, "loss": 0.2528, "lr": 2.068404975391077e-06, "epoch": 14.590212264150944, "percentage": 72.95, "elapsed_time": "0:47:23", "remaining_time": "0:17:34", "throughput": 5732.28, "total_tokens": 16301712} {"current_steps": 24750, "total_steps": 33920, "loss": 0.4356, "lr": 2.0663212586494293e-06, "epoch": 14.59316037735849, "percentage": 72.97, "elapsed_time": "0:47:24", "remaining_time": "0:17:33", "throughput": 5732.22, "total_tokens": 16304272} {"current_steps": 24755, "total_steps": 33920, "loss": 0.3156, "lr": 2.064238318611869e-06, "epoch": 14.596108490566039, "percentage": 72.98, "elapsed_time": "0:47:24", "remaining_time": "0:17:33", "throughput": 5732.16, "total_tokens": 16306800} {"current_steps": 24760, "total_steps": 33920, "loss": 0.3129, "lr": 2.0621561558298693e-06, "epoch": 14.599056603773585, "percentage": 73.0, "elapsed_time": "0:47:25", "remaining_time": "0:17:32", "throughput": 5732.24, "total_tokens": 16310160} {"current_steps": 24765, "total_steps": 33920, "loss": 0.2342, "lr": 2.0600747708546877e-06, "epoch": 14.602004716981131, "percentage": 73.01, "elapsed_time": "0:47:25", "remaining_time": "0:17:32", "throughput": 5732.24, "total_tokens": 16312976} {"current_steps": 24770, "total_steps": 33920, "loss": 0.305, "lr": 2.0579941642373814e-06, "epoch": 14.60495283018868, "percentage": 73.02, "elapsed_time": "0:47:26", "remaining_time": "0:17:31", "throughput": 5732.27, "total_tokens": 16315984} {"current_steps": 24775, "total_steps": 33920, "loss": 0.2968, "lr": 2.0559143365287993e-06, "epoch": 14.607900943396226, "percentage": 73.04, "elapsed_time": "0:47:26", "remaining_time": "0:17:30", "throughput": 5732.35, "total_tokens": 16319216} {"current_steps": 24780, "total_steps": 33920, "loss": 0.4066, "lr": 2.0538352882795846e-06, "epoch": 14.610849056603774, "percentage": 73.05, "elapsed_time": "0:47:27", "remaining_time": "0:17:30", "throughput": 5732.39, "total_tokens": 16322256} {"current_steps": 24785, "total_steps": 33920, "loss": 0.2404, "lr": 2.051757020040173e-06, "epoch": 14.61379716981132, "percentage": 73.07, "elapsed_time": "0:47:28", "remaining_time": "0:17:29", "throughput": 5732.54, "total_tokens": 16326512} {"current_steps": 24790, "total_steps": 33920, "loss": 0.2921, "lr": 2.0496795323607983e-06, "epoch": 14.616745283018869, "percentage": 73.08, "elapsed_time": "0:47:28", "remaining_time": "0:17:29", "throughput": 5732.68, "total_tokens": 16330320} {"current_steps": 24795, "total_steps": 33920, "loss": 0.3772, "lr": 2.0476028257914825e-06, "epoch": 14.619693396226415, "percentage": 73.1, "elapsed_time": "0:47:29", "remaining_time": "0:17:28", "throughput": 5732.71, "total_tokens": 16333488} {"current_steps": 24800, "total_steps": 33920, "loss": 0.2256, "lr": 2.0455269008820433e-06, "epoch": 14.622641509433961, "percentage": 73.11, "elapsed_time": "0:47:29", "remaining_time": "0:17:27", "throughput": 5732.72, "total_tokens": 16336336} {"current_steps": 24805, "total_steps": 33920, "loss": 0.3578, "lr": 2.0434517581820893e-06, "epoch": 14.62558962264151, "percentage": 73.13, "elapsed_time": "0:47:30", "remaining_time": "0:17:27", "throughput": 5732.83, "total_tokens": 16339760} {"current_steps": 24810, "total_steps": 33920, "loss": 0.2814, "lr": 2.041377398241025e-06, "epoch": 14.628537735849056, "percentage": 73.14, "elapsed_time": "0:47:30", "remaining_time": "0:17:26", "throughput": 5732.68, "total_tokens": 16342032} {"current_steps": 24815, "total_steps": 33920, "loss": 0.3539, "lr": 2.0393038216080433e-06, "epoch": 14.631485849056604, "percentage": 73.16, "elapsed_time": "0:47:31", "remaining_time": "0:17:26", "throughput": 5732.73, "total_tokens": 16345200} {"current_steps": 24820, "total_steps": 33920, "loss": 0.3397, "lr": 2.037231028832135e-06, "epoch": 14.63443396226415, "percentage": 73.17, "elapsed_time": "0:47:31", "remaining_time": "0:17:25", "throughput": 5732.81, "total_tokens": 16348688} {"current_steps": 24825, "total_steps": 33920, "loss": 0.3364, "lr": 2.0351590204620823e-06, "epoch": 14.637382075471699, "percentage": 73.19, "elapsed_time": "0:47:32", "remaining_time": "0:17:24", "throughput": 5732.81, "total_tokens": 16351568} {"current_steps": 24830, "total_steps": 33920, "loss": 0.5132, "lr": 2.033087797046457e-06, "epoch": 14.640330188679245, "percentage": 73.2, "elapsed_time": "0:47:32", "remaining_time": "0:17:24", "throughput": 5732.86, "total_tokens": 16354640} {"current_steps": 24835, "total_steps": 33920, "loss": 0.424, "lr": 2.031017359133624e-06, "epoch": 14.643278301886792, "percentage": 73.22, "elapsed_time": "0:47:33", "remaining_time": "0:17:23", "throughput": 5732.91, "total_tokens": 16357872} {"current_steps": 24840, "total_steps": 33920, "loss": 0.2375, "lr": 2.0289477072717406e-06, "epoch": 14.64622641509434, "percentage": 73.23, "elapsed_time": "0:47:34", "remaining_time": "0:17:23", "throughput": 5733.08, "total_tokens": 16363024} {"current_steps": 24845, "total_steps": 33920, "loss": 0.2398, "lr": 2.026878842008756e-06, "epoch": 14.649174528301886, "percentage": 73.25, "elapsed_time": "0:47:34", "remaining_time": "0:17:22", "throughput": 5732.87, "total_tokens": 16365712} {"current_steps": 24850, "total_steps": 33920, "loss": 0.2127, "lr": 2.0248107638924105e-06, "epoch": 14.652122641509434, "percentage": 73.26, "elapsed_time": "0:47:35", "remaining_time": "0:17:22", "throughput": 5732.84, "total_tokens": 16368528} {"current_steps": 24855, "total_steps": 33920, "loss": 0.3572, "lr": 2.0227434734702386e-06, "epoch": 14.65507075471698, "percentage": 73.28, "elapsed_time": "0:47:35", "remaining_time": "0:17:21", "throughput": 5732.87, "total_tokens": 16371856} {"current_steps": 24860, "total_steps": 33920, "loss": 0.3253, "lr": 2.020676971289563e-06, "epoch": 14.658018867924529, "percentage": 73.29, "elapsed_time": "0:47:36", "remaining_time": "0:17:20", "throughput": 5732.73, "total_tokens": 16374192} {"current_steps": 24865, "total_steps": 33920, "loss": 0.3795, "lr": 2.0186112578975005e-06, "epoch": 14.660966981132075, "percentage": 73.3, "elapsed_time": "0:47:36", "remaining_time": "0:17:20", "throughput": 5732.92, "total_tokens": 16378160} {"current_steps": 24870, "total_steps": 33920, "loss": 0.2658, "lr": 2.016546333840956e-06, "epoch": 14.663915094339622, "percentage": 73.32, "elapsed_time": "0:47:37", "remaining_time": "0:17:19", "throughput": 5733.06, "total_tokens": 16381808} {"current_steps": 24875, "total_steps": 33920, "loss": 0.3011, "lr": 2.014482199666627e-06, "epoch": 14.66686320754717, "percentage": 73.33, "elapsed_time": "0:47:37", "remaining_time": "0:17:19", "throughput": 5733.08, "total_tokens": 16385136} {"current_steps": 24880, "total_steps": 33920, "loss": 0.4582, "lr": 2.0124188559210017e-06, "epoch": 14.669811320754716, "percentage": 73.35, "elapsed_time": "0:47:38", "remaining_time": "0:17:18", "throughput": 5733.12, "total_tokens": 16388176} {"current_steps": 24885, "total_steps": 33920, "loss": 0.3789, "lr": 2.0103563031503613e-06, "epoch": 14.672759433962264, "percentage": 73.36, "elapsed_time": "0:47:39", "remaining_time": "0:17:18", "throughput": 5733.07, "total_tokens": 16390864} {"current_steps": 24890, "total_steps": 33920, "loss": 0.2624, "lr": 2.0082945419007745e-06, "epoch": 14.67570754716981, "percentage": 73.38, "elapsed_time": "0:47:39", "remaining_time": "0:17:17", "throughput": 5733.24, "total_tokens": 16394800} {"current_steps": 24895, "total_steps": 33920, "loss": 0.3858, "lr": 2.0062335727181007e-06, "epoch": 14.678655660377359, "percentage": 73.39, "elapsed_time": "0:47:40", "remaining_time": "0:17:16", "throughput": 5733.45, "total_tokens": 16398672} {"current_steps": 24900, "total_steps": 33920, "loss": 0.2995, "lr": 2.004173396147992e-06, "epoch": 14.681603773584905, "percentage": 73.41, "elapsed_time": "0:47:40", "remaining_time": "0:17:16", "throughput": 5733.5, "total_tokens": 16401776} {"current_steps": 24905, "total_steps": 33920, "loss": 0.4345, "lr": 2.0021140127358873e-06, "epoch": 14.684551886792454, "percentage": 73.42, "elapsed_time": "0:47:41", "remaining_time": "0:17:15", "throughput": 5733.51, "total_tokens": 16404688} {"current_steps": 24910, "total_steps": 33920, "loss": 0.3103, "lr": 2.0000554230270164e-06, "epoch": 14.6875, "percentage": 73.44, "elapsed_time": "0:47:41", "remaining_time": "0:17:15", "throughput": 5733.46, "total_tokens": 16407376} {"current_steps": 24915, "total_steps": 33920, "loss": 0.3559, "lr": 1.997997627566401e-06, "epoch": 14.690448113207546, "percentage": 73.45, "elapsed_time": "0:47:42", "remaining_time": "0:17:14", "throughput": 5733.68, "total_tokens": 16411408} {"current_steps": 24920, "total_steps": 33920, "loss": 0.3286, "lr": 1.9959406268988536e-06, "epoch": 14.693396226415095, "percentage": 73.47, "elapsed_time": "0:47:42", "remaining_time": "0:17:13", "throughput": 5733.7, "total_tokens": 16414288} {"current_steps": 24925, "total_steps": 33920, "loss": 0.4805, "lr": 1.9938844215689717e-06, "epoch": 14.696344339622641, "percentage": 73.48, "elapsed_time": "0:47:43", "remaining_time": "0:17:13", "throughput": 5733.79, "total_tokens": 16417616} {"current_steps": 24930, "total_steps": 33920, "loss": 0.2547, "lr": 1.991829012121145e-06, "epoch": 14.69929245283019, "percentage": 73.5, "elapsed_time": "0:47:44", "remaining_time": "0:17:12", "throughput": 5734.1, "total_tokens": 16422928} {"current_steps": 24935, "total_steps": 33920, "loss": 0.295, "lr": 1.989774399099552e-06, "epoch": 14.702240566037736, "percentage": 73.51, "elapsed_time": "0:47:44", "remaining_time": "0:17:12", "throughput": 5734.17, "total_tokens": 16426160} {"current_steps": 24940, "total_steps": 33920, "loss": 0.2932, "lr": 1.98772058304816e-06, "epoch": 14.705188679245284, "percentage": 73.53, "elapsed_time": "0:47:45", "remaining_time": "0:17:11", "throughput": 5734.11, "total_tokens": 16429104} {"current_steps": 24945, "total_steps": 33920, "loss": 0.2979, "lr": 1.9856675645107244e-06, "epoch": 14.70813679245283, "percentage": 73.54, "elapsed_time": "0:47:45", "remaining_time": "0:17:11", "throughput": 5734.09, "total_tokens": 16432240} {"current_steps": 24950, "total_steps": 33920, "loss": 0.3373, "lr": 1.9836153440307936e-06, "epoch": 14.711084905660378, "percentage": 73.56, "elapsed_time": "0:47:46", "remaining_time": "0:17:10", "throughput": 5734.23, "total_tokens": 16436016} {"current_steps": 24955, "total_steps": 33920, "loss": 0.3179, "lr": 1.9815639221517002e-06, "epoch": 14.714033018867925, "percentage": 73.57, "elapsed_time": "0:47:46", "remaining_time": "0:17:09", "throughput": 5734.35, "total_tokens": 16439440} {"current_steps": 24960, "total_steps": 33920, "loss": 0.2812, "lr": 1.9795132994165673e-06, "epoch": 14.716981132075471, "percentage": 73.58, "elapsed_time": "0:47:47", "remaining_time": "0:17:09", "throughput": 5734.37, "total_tokens": 16442544} {"current_steps": 24965, "total_steps": 33920, "loss": 0.335, "lr": 1.977463476368306e-06, "epoch": 14.71992924528302, "percentage": 73.6, "elapsed_time": "0:47:47", "remaining_time": "0:17:08", "throughput": 5734.33, "total_tokens": 16445296} {"current_steps": 24970, "total_steps": 33920, "loss": 0.2729, "lr": 1.975414453549614e-06, "epoch": 14.722877358490566, "percentage": 73.61, "elapsed_time": "0:47:48", "remaining_time": "0:17:08", "throughput": 5734.4, "total_tokens": 16449136} {"current_steps": 24975, "total_steps": 33920, "loss": 0.3417, "lr": 1.9733662315029826e-06, "epoch": 14.725825471698114, "percentage": 73.63, "elapsed_time": "0:47:49", "remaining_time": "0:17:07", "throughput": 5734.52, "total_tokens": 16452368} {"current_steps": 24980, "total_steps": 33920, "loss": 0.3835, "lr": 1.9713188107706856e-06, "epoch": 14.72877358490566, "percentage": 73.64, "elapsed_time": "0:47:49", "remaining_time": "0:17:06", "throughput": 5734.67, "total_tokens": 16455952} {"current_steps": 24985, "total_steps": 33920, "loss": 0.3134, "lr": 1.969272191894786e-06, "epoch": 14.731721698113208, "percentage": 73.66, "elapsed_time": "0:47:50", "remaining_time": "0:17:06", "throughput": 5734.73, "total_tokens": 16459280} {"current_steps": 24990, "total_steps": 33920, "loss": 0.3375, "lr": 1.967226375417135e-06, "epoch": 14.734669811320755, "percentage": 73.67, "elapsed_time": "0:47:50", "remaining_time": "0:17:05", "throughput": 5734.75, "total_tokens": 16462288} {"current_steps": 24995, "total_steps": 33920, "loss": 0.5495, "lr": 1.965181361879372e-06, "epoch": 14.737617924528301, "percentage": 73.69, "elapsed_time": "0:47:51", "remaining_time": "0:17:05", "throughput": 5734.75, "total_tokens": 16465040} {"current_steps": 25000, "total_steps": 33920, "loss": 0.2847, "lr": 1.9631371518229214e-06, "epoch": 14.74056603773585, "percentage": 73.7, "elapsed_time": "0:47:51", "remaining_time": "0:17:04", "throughput": 5734.86, "total_tokens": 16468784} {"current_steps": 25005, "total_steps": 33920, "loss": 0.4188, "lr": 1.9610937457889975e-06, "epoch": 14.743514150943396, "percentage": 73.72, "elapsed_time": "0:47:52", "remaining_time": "0:17:04", "throughput": 5735.02, "total_tokens": 16472752} {"current_steps": 25010, "total_steps": 33920, "loss": 0.3339, "lr": 1.9590511443186032e-06, "epoch": 14.746462264150944, "percentage": 73.73, "elapsed_time": "0:47:52", "remaining_time": "0:17:03", "throughput": 5735.08, "total_tokens": 16476496} {"current_steps": 25015, "total_steps": 33920, "loss": 0.4223, "lr": 1.9570093479525243e-06, "epoch": 14.74941037735849, "percentage": 73.75, "elapsed_time": "0:47:53", "remaining_time": "0:17:02", "throughput": 5735.23, "total_tokens": 16480560} {"current_steps": 25020, "total_steps": 33920, "loss": 0.3583, "lr": 1.954968357231335e-06, "epoch": 14.752358490566039, "percentage": 73.76, "elapsed_time": "0:47:54", "remaining_time": "0:17:02", "throughput": 5735.48, "total_tokens": 16485136} {"current_steps": 25025, "total_steps": 33920, "loss": 0.3738, "lr": 1.9529281726953964e-06, "epoch": 14.755306603773585, "percentage": 73.78, "elapsed_time": "0:47:54", "remaining_time": "0:17:01", "throughput": 5735.47, "total_tokens": 16487952} {"current_steps": 25030, "total_steps": 33920, "loss": 0.4055, "lr": 1.9508887948848564e-06, "epoch": 14.758254716981131, "percentage": 73.79, "elapsed_time": "0:47:55", "remaining_time": "0:17:01", "throughput": 5735.53, "total_tokens": 16491184} {"current_steps": 25035, "total_steps": 33920, "loss": 0.4201, "lr": 1.9488502243396475e-06, "epoch": 14.76120283018868, "percentage": 73.81, "elapsed_time": "0:47:55", "remaining_time": "0:17:00", "throughput": 5735.58, "total_tokens": 16494672} {"current_steps": 25040, "total_steps": 33920, "loss": 0.2973, "lr": 1.946812461599492e-06, "epoch": 14.764150943396226, "percentage": 73.82, "elapsed_time": "0:47:56", "remaining_time": "0:17:00", "throughput": 5735.74, "total_tokens": 16498928} {"current_steps": 25045, "total_steps": 33920, "loss": 0.31, "lr": 1.944775507203897e-06, "epoch": 14.767099056603774, "percentage": 73.84, "elapsed_time": "0:47:57", "remaining_time": "0:16:59", "throughput": 5735.72, "total_tokens": 16501808} {"current_steps": 25050, "total_steps": 33920, "loss": 0.2633, "lr": 1.942739361692153e-06, "epoch": 14.77004716981132, "percentage": 73.85, "elapsed_time": "0:47:57", "remaining_time": "0:16:58", "throughput": 5735.82, "total_tokens": 16505296} {"current_steps": 25055, "total_steps": 33920, "loss": 0.2471, "lr": 1.94070402560334e-06, "epoch": 14.772995283018869, "percentage": 73.86, "elapsed_time": "0:47:58", "remaining_time": "0:16:58", "throughput": 5735.84, "total_tokens": 16508144} {"current_steps": 25060, "total_steps": 33920, "loss": 0.4129, "lr": 1.93866949947632e-06, "epoch": 14.775943396226415, "percentage": 73.88, "elapsed_time": "0:47:58", "remaining_time": "0:16:57", "throughput": 5735.61, "total_tokens": 16510384} {"current_steps": 25065, "total_steps": 33920, "loss": 0.2313, "lr": 1.9366357838497423e-06, "epoch": 14.778891509433961, "percentage": 73.89, "elapsed_time": "0:47:59", "remaining_time": "0:16:57", "throughput": 5735.76, "total_tokens": 16513968} {"current_steps": 25070, "total_steps": 33920, "loss": 0.3656, "lr": 1.9346028792620454e-06, "epoch": 14.78183962264151, "percentage": 73.91, "elapsed_time": "0:47:59", "remaining_time": "0:16:56", "throughput": 5735.96, "total_tokens": 16518128} {"current_steps": 25075, "total_steps": 33920, "loss": 0.3232, "lr": 1.9325707862514464e-06, "epoch": 14.784787735849056, "percentage": 73.92, "elapsed_time": "0:48:00", "remaining_time": "0:16:56", "throughput": 5736.02, "total_tokens": 16521616} {"current_steps": 25080, "total_steps": 33920, "loss": 0.3344, "lr": 1.930539505355952e-06, "epoch": 14.787735849056604, "percentage": 73.94, "elapsed_time": "0:48:00", "remaining_time": "0:16:55", "throughput": 5736.11, "total_tokens": 16525488} {"current_steps": 25085, "total_steps": 33920, "loss": 0.3564, "lr": 1.9285090371133524e-06, "epoch": 14.79068396226415, "percentage": 73.95, "elapsed_time": "0:48:01", "remaining_time": "0:16:54", "throughput": 5736.2, "total_tokens": 16529072} {"current_steps": 25090, "total_steps": 33920, "loss": 0.3292, "lr": 1.9264793820612228e-06, "epoch": 14.793632075471699, "percentage": 73.97, "elapsed_time": "0:48:02", "remaining_time": "0:16:54", "throughput": 5736.08, "total_tokens": 16531440} {"current_steps": 25095, "total_steps": 33920, "loss": 0.3884, "lr": 1.924450540736921e-06, "epoch": 14.796580188679245, "percentage": 73.98, "elapsed_time": "0:48:02", "remaining_time": "0:16:53", "throughput": 5735.96, "total_tokens": 16533904} {"current_steps": 25100, "total_steps": 33920, "loss": 0.3897, "lr": 1.922422513677593e-06, "epoch": 14.799528301886792, "percentage": 74.0, "elapsed_time": "0:48:03", "remaining_time": "0:16:53", "throughput": 5735.95, "total_tokens": 16536880} {"current_steps": 25105, "total_steps": 33920, "loss": 0.3692, "lr": 1.9203953014201703e-06, "epoch": 14.80247641509434, "percentage": 74.01, "elapsed_time": "0:48:03", "remaining_time": "0:16:52", "throughput": 5736.18, "total_tokens": 16541424} {"current_steps": 25110, "total_steps": 33920, "loss": 0.2784, "lr": 1.918368904501364e-06, "epoch": 14.805424528301886, "percentage": 74.03, "elapsed_time": "0:48:04", "remaining_time": "0:16:51", "throughput": 5736.27, "total_tokens": 16544592} {"current_steps": 25115, "total_steps": 33920, "loss": 0.3215, "lr": 1.9163433234576713e-06, "epoch": 14.808372641509434, "percentage": 74.04, "elapsed_time": "0:48:04", "remaining_time": "0:16:51", "throughput": 5736.37, "total_tokens": 16548208} {"current_steps": 25120, "total_steps": 33920, "loss": 0.2828, "lr": 1.9143185588253733e-06, "epoch": 14.81132075471698, "percentage": 74.06, "elapsed_time": "0:48:05", "remaining_time": "0:16:50", "throughput": 5736.44, "total_tokens": 16551632} {"current_steps": 25125, "total_steps": 33920, "loss": 0.3046, "lr": 1.9122946111405354e-06, "epoch": 14.814268867924529, "percentage": 74.07, "elapsed_time": "0:48:05", "remaining_time": "0:16:50", "throughput": 5736.67, "total_tokens": 16555824} {"current_steps": 25130, "total_steps": 33920, "loss": 0.2306, "lr": 1.910271480939005e-06, "epoch": 14.817216981132075, "percentage": 74.09, "elapsed_time": "0:48:06", "remaining_time": "0:16:49", "throughput": 5736.67, "total_tokens": 16558512} {"current_steps": 25135, "total_steps": 33920, "loss": 0.3766, "lr": 1.9082491687564176e-06, "epoch": 14.820165094339622, "percentage": 74.1, "elapsed_time": "0:48:06", "remaining_time": "0:16:49", "throughput": 5736.49, "total_tokens": 16560784} {"current_steps": 25140, "total_steps": 33920, "loss": 0.3122, "lr": 1.9062276751281872e-06, "epoch": 14.82311320754717, "percentage": 74.12, "elapsed_time": "0:48:07", "remaining_time": "0:16:48", "throughput": 5736.56, "total_tokens": 16564304} {"current_steps": 25145, "total_steps": 33920, "loss": 0.2729, "lr": 1.9042070005895136e-06, "epoch": 14.826061320754716, "percentage": 74.13, "elapsed_time": "0:48:07", "remaining_time": "0:16:47", "throughput": 5736.48, "total_tokens": 16566896} {"current_steps": 25150, "total_steps": 33920, "loss": 0.4611, "lr": 1.9021871456753788e-06, "epoch": 14.829009433962264, "percentage": 74.15, "elapsed_time": "0:48:08", "remaining_time": "0:16:47", "throughput": 5736.64, "total_tokens": 16570960} {"current_steps": 25155, "total_steps": 33920, "loss": 0.4518, "lr": 1.9001681109205478e-06, "epoch": 14.83195754716981, "percentage": 74.16, "elapsed_time": "0:48:09", "remaining_time": "0:16:46", "throughput": 5736.46, "total_tokens": 16573328} {"current_steps": 25160, "total_steps": 33920, "loss": 0.297, "lr": 1.898149896859567e-06, "epoch": 14.834905660377359, "percentage": 74.17, "elapsed_time": "0:48:09", "remaining_time": "0:16:46", "throughput": 5736.4, "total_tokens": 16576208} {"current_steps": 25165, "total_steps": 33920, "loss": 0.2816, "lr": 1.8961325040267714e-06, "epoch": 14.837853773584905, "percentage": 74.19, "elapsed_time": "0:48:10", "remaining_time": "0:16:45", "throughput": 5736.44, "total_tokens": 16579184} {"current_steps": 25170, "total_steps": 33920, "loss": 0.2444, "lr": 1.894115932956272e-06, "epoch": 14.840801886792454, "percentage": 74.2, "elapsed_time": "0:48:11", "remaining_time": "0:16:45", "throughput": 5736.62, "total_tokens": 16585456} {"current_steps": 25175, "total_steps": 33920, "loss": 0.2764, "lr": 1.8921001841819652e-06, "epoch": 14.84375, "percentage": 74.22, "elapsed_time": "0:48:11", "remaining_time": "0:16:44", "throughput": 5736.73, "total_tokens": 16589104} {"current_steps": 25180, "total_steps": 33920, "loss": 0.2748, "lr": 1.8900852582375284e-06, "epoch": 14.846698113207546, "percentage": 74.23, "elapsed_time": "0:48:12", "remaining_time": "0:16:43", "throughput": 5736.7, "total_tokens": 16591824} {"current_steps": 25185, "total_steps": 33920, "loss": 0.2306, "lr": 1.8880711556564214e-06, "epoch": 14.849646226415095, "percentage": 74.25, "elapsed_time": "0:48:12", "remaining_time": "0:16:43", "throughput": 5736.78, "total_tokens": 16594928} {"current_steps": 25190, "total_steps": 33920, "loss": 0.3496, "lr": 1.8860578769718891e-06, "epoch": 14.852594339622641, "percentage": 74.26, "elapsed_time": "0:48:13", "remaining_time": "0:16:42", "throughput": 5736.7, "total_tokens": 16597360} {"current_steps": 25195, "total_steps": 33920, "loss": 0.3245, "lr": 1.8840454227169525e-06, "epoch": 14.85554245283019, "percentage": 74.28, "elapsed_time": "0:48:13", "remaining_time": "0:16:42", "throughput": 5736.72, "total_tokens": 16600304} {"current_steps": 25200, "total_steps": 33920, "loss": 0.3751, "lr": 1.882033793424421e-06, "epoch": 14.858490566037736, "percentage": 74.29, "elapsed_time": "0:48:14", "remaining_time": "0:16:41", "throughput": 5736.82, "total_tokens": 16603600} {"current_steps": 25205, "total_steps": 33920, "loss": 0.2634, "lr": 1.88002298962688e-06, "epoch": 14.861438679245284, "percentage": 74.31, "elapsed_time": "0:48:14", "remaining_time": "0:16:40", "throughput": 5736.84, "total_tokens": 16606608} {"current_steps": 25210, "total_steps": 33920, "loss": 0.2718, "lr": 1.8780130118566996e-06, "epoch": 14.86438679245283, "percentage": 74.32, "elapsed_time": "0:48:15", "remaining_time": "0:16:40", "throughput": 5736.97, "total_tokens": 16610800} {"current_steps": 25215, "total_steps": 33920, "loss": 0.307, "lr": 1.876003860646029e-06, "epoch": 14.867334905660378, "percentage": 74.34, "elapsed_time": "0:48:15", "remaining_time": "0:16:39", "throughput": 5737.11, "total_tokens": 16614256} {"current_steps": 25220, "total_steps": 33920, "loss": 0.3207, "lr": 1.8739955365267997e-06, "epoch": 14.870283018867925, "percentage": 74.35, "elapsed_time": "0:48:16", "remaining_time": "0:16:39", "throughput": 5737.2, "total_tokens": 16617584} {"current_steps": 25225, "total_steps": 33920, "loss": 0.3272, "lr": 1.8719880400307228e-06, "epoch": 14.873231132075471, "percentage": 74.37, "elapsed_time": "0:48:17", "remaining_time": "0:16:38", "throughput": 5737.27, "total_tokens": 16621136} {"current_steps": 25230, "total_steps": 33920, "loss": 0.3853, "lr": 1.869981371689295e-06, "epoch": 14.87617924528302, "percentage": 74.38, "elapsed_time": "0:48:17", "remaining_time": "0:16:38", "throughput": 5737.3, "total_tokens": 16624016} {"current_steps": 25235, "total_steps": 33920, "loss": 0.3363, "lr": 1.867975532033789e-06, "epoch": 14.879127358490566, "percentage": 74.4, "elapsed_time": "0:48:18", "remaining_time": "0:16:37", "throughput": 5737.24, "total_tokens": 16626704} {"current_steps": 25240, "total_steps": 33920, "loss": 0.3152, "lr": 1.8659705215952589e-06, "epoch": 14.882075471698114, "percentage": 74.41, "elapsed_time": "0:48:18", "remaining_time": "0:16:36", "throughput": 5737.3, "total_tokens": 16629808} {"current_steps": 25245, "total_steps": 33920, "loss": 0.2354, "lr": 1.8639663409045405e-06, "epoch": 14.88502358490566, "percentage": 74.43, "elapsed_time": "0:48:19", "remaining_time": "0:16:36", "throughput": 5737.42, "total_tokens": 16633296} {"current_steps": 25250, "total_steps": 33920, "loss": 0.5455, "lr": 1.8619629904922466e-06, "epoch": 14.887971698113208, "percentage": 74.44, "elapsed_time": "0:48:19", "remaining_time": "0:16:35", "throughput": 5737.46, "total_tokens": 16636240} {"current_steps": 25255, "total_steps": 33920, "loss": 0.2923, "lr": 1.859960470888777e-06, "epoch": 14.890919811320755, "percentage": 74.45, "elapsed_time": "0:48:20", "remaining_time": "0:16:35", "throughput": 5737.38, "total_tokens": 16638928} {"current_steps": 25260, "total_steps": 33920, "loss": 0.2771, "lr": 1.857958782624306e-06, "epoch": 14.893867924528301, "percentage": 74.47, "elapsed_time": "0:48:20", "remaining_time": "0:16:34", "throughput": 5737.52, "total_tokens": 16642448} {"current_steps": 25265, "total_steps": 33920, "loss": 0.307, "lr": 1.8559579262287886e-06, "epoch": 14.89681603773585, "percentage": 74.48, "elapsed_time": "0:48:21", "remaining_time": "0:16:33", "throughput": 5737.54, "total_tokens": 16645616} {"current_steps": 25270, "total_steps": 33920, "loss": 0.3921, "lr": 1.8539579022319599e-06, "epoch": 14.899764150943396, "percentage": 74.5, "elapsed_time": "0:48:21", "remaining_time": "0:16:33", "throughput": 5737.6, "total_tokens": 16648880} {"current_steps": 25275, "total_steps": 33920, "loss": 0.3236, "lr": 1.8519587111633357e-06, "epoch": 14.902712264150944, "percentage": 74.51, "elapsed_time": "0:48:22", "remaining_time": "0:16:32", "throughput": 5737.59, "total_tokens": 16651952} {"current_steps": 25280, "total_steps": 33920, "loss": 0.3492, "lr": 1.8499603535522082e-06, "epoch": 14.90566037735849, "percentage": 74.53, "elapsed_time": "0:48:22", "remaining_time": "0:16:32", "throughput": 5737.71, "total_tokens": 16655312} {"current_steps": 25285, "total_steps": 33920, "loss": 0.2495, "lr": 1.8479628299276543e-06, "epoch": 14.908608490566039, "percentage": 74.54, "elapsed_time": "0:48:23", "remaining_time": "0:16:31", "throughput": 5737.52, "total_tokens": 16657552} {"current_steps": 25290, "total_steps": 33920, "loss": 0.3478, "lr": 1.8459661408185241e-06, "epoch": 14.911556603773585, "percentage": 74.56, "elapsed_time": "0:48:23", "remaining_time": "0:16:30", "throughput": 5737.47, "total_tokens": 16660496} {"current_steps": 25295, "total_steps": 33920, "loss": 0.5152, "lr": 1.8439702867534536e-06, "epoch": 14.914504716981131, "percentage": 74.57, "elapsed_time": "0:48:24", "remaining_time": "0:16:30", "throughput": 5737.49, "total_tokens": 16663504} {"current_steps": 25300, "total_steps": 33920, "loss": 0.3106, "lr": 1.841975268260851e-06, "epoch": 14.91745283018868, "percentage": 74.59, "elapsed_time": "0:48:24", "remaining_time": "0:16:29", "throughput": 5737.4, "total_tokens": 16666000} {"current_steps": 25305, "total_steps": 33920, "loss": 0.3901, "lr": 1.8399810858689066e-06, "epoch": 14.920400943396226, "percentage": 74.6, "elapsed_time": "0:48:25", "remaining_time": "0:16:29", "throughput": 5737.48, "total_tokens": 16669584} {"current_steps": 25310, "total_steps": 33920, "loss": 0.3902, "lr": 1.8379877401055884e-06, "epoch": 14.923349056603774, "percentage": 74.62, "elapsed_time": "0:48:25", "remaining_time": "0:16:28", "throughput": 5737.64, "total_tokens": 16673392} {"current_steps": 25315, "total_steps": 33920, "loss": 0.2983, "lr": 1.8359952314986418e-06, "epoch": 14.92629716981132, "percentage": 74.63, "elapsed_time": "0:48:26", "remaining_time": "0:16:27", "throughput": 5737.71, "total_tokens": 16676592} {"current_steps": 25320, "total_steps": 33920, "loss": 0.3539, "lr": 1.8340035605755957e-06, "epoch": 14.929245283018869, "percentage": 74.65, "elapsed_time": "0:48:27", "remaining_time": "0:16:27", "throughput": 5737.74, "total_tokens": 16679728} {"current_steps": 25325, "total_steps": 33920, "loss": 0.3184, "lr": 1.8320127278637518e-06, "epoch": 14.932193396226415, "percentage": 74.66, "elapsed_time": "0:48:27", "remaining_time": "0:16:26", "throughput": 5737.81, "total_tokens": 16682896} {"current_steps": 25330, "total_steps": 33920, "loss": 0.3487, "lr": 1.830022733890191e-06, "epoch": 14.935141509433961, "percentage": 74.68, "elapsed_time": "0:48:28", "remaining_time": "0:16:26", "throughput": 5737.75, "total_tokens": 16685456} {"current_steps": 25335, "total_steps": 33920, "loss": 0.3706, "lr": 1.8280335791817733e-06, "epoch": 14.93808962264151, "percentage": 74.69, "elapsed_time": "0:48:28", "remaining_time": "0:16:25", "throughput": 5737.77, "total_tokens": 16688336} {"current_steps": 25340, "total_steps": 33920, "loss": 0.5873, "lr": 1.826045264265136e-06, "epoch": 14.941037735849056, "percentage": 74.71, "elapsed_time": "0:48:29", "remaining_time": "0:16:24", "throughput": 5737.74, "total_tokens": 16691248} {"current_steps": 25345, "total_steps": 33920, "loss": 0.2915, "lr": 1.8240577896666928e-06, "epoch": 14.943985849056604, "percentage": 74.72, "elapsed_time": "0:48:29", "remaining_time": "0:16:24", "throughput": 5737.76, "total_tokens": 16694160} {"current_steps": 25350, "total_steps": 33920, "loss": 0.3426, "lr": 1.8220711559126382e-06, "epoch": 14.94693396226415, "percentage": 74.73, "elapsed_time": "0:48:30", "remaining_time": "0:16:23", "throughput": 5737.88, "total_tokens": 16697744} {"current_steps": 25355, "total_steps": 33920, "loss": 0.303, "lr": 1.8200853635289417e-06, "epoch": 14.949882075471699, "percentage": 74.75, "elapsed_time": "0:48:30", "remaining_time": "0:16:23", "throughput": 5737.88, "total_tokens": 16700688} {"current_steps": 25360, "total_steps": 33920, "loss": 0.3338, "lr": 1.81810041304135e-06, "epoch": 14.952830188679245, "percentage": 74.76, "elapsed_time": "0:48:31", "remaining_time": "0:16:22", "throughput": 5737.65, "total_tokens": 16702800} {"current_steps": 25365, "total_steps": 33920, "loss": 0.3703, "lr": 1.8161163049753865e-06, "epoch": 14.955778301886792, "percentage": 74.78, "elapsed_time": "0:48:31", "remaining_time": "0:16:22", "throughput": 5737.84, "total_tokens": 16707056} {"current_steps": 25370, "total_steps": 33920, "loss": 0.2892, "lr": 1.8141330398563533e-06, "epoch": 14.95872641509434, "percentage": 74.79, "elapsed_time": "0:48:32", "remaining_time": "0:16:21", "throughput": 5737.93, "total_tokens": 16710416} {"current_steps": 25375, "total_steps": 33920, "loss": 0.2387, "lr": 1.8121506182093268e-06, "epoch": 14.961674528301886, "percentage": 74.81, "elapsed_time": "0:48:32", "remaining_time": "0:16:20", "throughput": 5737.97, "total_tokens": 16713552} {"current_steps": 25380, "total_steps": 33920, "loss": 0.3566, "lr": 1.8101690405591643e-06, "epoch": 14.964622641509434, "percentage": 74.82, "elapsed_time": "0:48:33", "remaining_time": "0:16:20", "throughput": 5737.92, "total_tokens": 16716368} {"current_steps": 25385, "total_steps": 33920, "loss": 0.2707, "lr": 1.8081883074304945e-06, "epoch": 14.96757075471698, "percentage": 74.84, "elapsed_time": "0:48:33", "remaining_time": "0:16:19", "throughput": 5737.96, "total_tokens": 16719536} {"current_steps": 25390, "total_steps": 33920, "loss": 0.4463, "lr": 1.8062084193477275e-06, "epoch": 14.970518867924529, "percentage": 74.85, "elapsed_time": "0:48:34", "remaining_time": "0:16:19", "throughput": 5738.08, "total_tokens": 16722736} {"current_steps": 25395, "total_steps": 33920, "loss": 0.3108, "lr": 1.804229376835046e-06, "epoch": 14.973466981132075, "percentage": 74.87, "elapsed_time": "0:48:34", "remaining_time": "0:16:18", "throughput": 5738.14, "total_tokens": 16725904} {"current_steps": 25400, "total_steps": 33920, "loss": 0.4073, "lr": 1.8022511804164105e-06, "epoch": 14.976415094339622, "percentage": 74.88, "elapsed_time": "0:48:35", "remaining_time": "0:16:17", "throughput": 5738.01, "total_tokens": 16728400} {"current_steps": 25405, "total_steps": 33920, "loss": 0.3787, "lr": 1.8002738306155559e-06, "epoch": 14.97936320754717, "percentage": 74.9, "elapsed_time": "0:48:35", "remaining_time": "0:16:17", "throughput": 5738.08, "total_tokens": 16731568} {"current_steps": 25410, "total_steps": 33920, "loss": 0.3242, "lr": 1.7982973279559935e-06, "epoch": 14.982311320754716, "percentage": 74.91, "elapsed_time": "0:48:36", "remaining_time": "0:16:16", "throughput": 5737.95, "total_tokens": 16733872} {"current_steps": 25415, "total_steps": 33920, "loss": 0.3405, "lr": 1.7963216729610134e-06, "epoch": 14.985259433962264, "percentage": 74.93, "elapsed_time": "0:48:36", "remaining_time": "0:16:16", "throughput": 5738.08, "total_tokens": 16737648} {"current_steps": 25420, "total_steps": 33920, "loss": 0.2376, "lr": 1.7943468661536773e-06, "epoch": 14.98820754716981, "percentage": 74.94, "elapsed_time": "0:48:37", "remaining_time": "0:16:15", "throughput": 5738.12, "total_tokens": 16740656} {"current_steps": 25425, "total_steps": 33920, "loss": 0.4229, "lr": 1.7923729080568242e-06, "epoch": 14.991155660377359, "percentage": 74.96, "elapsed_time": "0:48:37", "remaining_time": "0:16:14", "throughput": 5738.02, "total_tokens": 16743280} {"current_steps": 25430, "total_steps": 33920, "loss": 0.344, "lr": 1.7903997991930683e-06, "epoch": 14.994103773584905, "percentage": 74.97, "elapsed_time": "0:48:38", "remaining_time": "0:16:14", "throughput": 5738.09, "total_tokens": 16746384} {"current_steps": 25435, "total_steps": 33920, "loss": 0.3275, "lr": 1.7884275400847972e-06, "epoch": 14.997051886792454, "percentage": 74.99, "elapsed_time": "0:48:38", "remaining_time": "0:16:13", "throughput": 5738.01, "total_tokens": 16749040} {"current_steps": 25440, "total_steps": 33920, "loss": 0.3927, "lr": 1.786456131254175e-06, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "0:48:39", "remaining_time": "0:16:13", "throughput": 5737.76, "total_tokens": 16751912} {"current_steps": 25445, "total_steps": 33920, "loss": 0.3048, "lr": 1.784485573223143e-06, "epoch": 15.002948113207546, "percentage": 75.01, "elapsed_time": "0:48:40", "remaining_time": "0:16:12", "throughput": 5737.39, "total_tokens": 16754600} {"current_steps": 25450, "total_steps": 33920, "loss": 0.3289, "lr": 1.782515866513414e-06, "epoch": 15.005896226415095, "percentage": 75.03, "elapsed_time": "0:48:40", "remaining_time": "0:16:12", "throughput": 5737.43, "total_tokens": 16758024} {"current_steps": 25455, "total_steps": 33920, "loss": 0.4376, "lr": 1.7805470116464758e-06, "epoch": 15.008844339622641, "percentage": 75.04, "elapsed_time": "0:48:41", "remaining_time": "0:16:11", "throughput": 5737.45, "total_tokens": 16761160} {"current_steps": 25460, "total_steps": 33920, "loss": 0.3256, "lr": 1.7785790091435911e-06, "epoch": 15.01179245283019, "percentage": 75.06, "elapsed_time": "0:48:41", "remaining_time": "0:16:10", "throughput": 5737.36, "total_tokens": 16763784} {"current_steps": 25465, "total_steps": 33920, "loss": 0.249, "lr": 1.776611859525796e-06, "epoch": 15.014740566037736, "percentage": 75.07, "elapsed_time": "0:48:42", "remaining_time": "0:16:10", "throughput": 5737.44, "total_tokens": 16767272} {"current_steps": 25470, "total_steps": 33920, "loss": 0.2414, "lr": 1.7746455633139042e-06, "epoch": 15.017688679245284, "percentage": 75.09, "elapsed_time": "0:48:42", "remaining_time": "0:16:09", "throughput": 5737.53, "total_tokens": 16770728} {"current_steps": 25475, "total_steps": 33920, "loss": 0.3562, "lr": 1.7726801210285005e-06, "epoch": 15.02063679245283, "percentage": 75.1, "elapsed_time": "0:48:43", "remaining_time": "0:16:09", "throughput": 5737.49, "total_tokens": 16773448} {"current_steps": 25480, "total_steps": 33920, "loss": 0.3023, "lr": 1.7707155331899418e-06, "epoch": 15.023584905660377, "percentage": 75.12, "elapsed_time": "0:48:44", "remaining_time": "0:16:08", "throughput": 5737.68, "total_tokens": 16777320} {"current_steps": 25485, "total_steps": 33920, "loss": 0.3423, "lr": 1.7687518003183645e-06, "epoch": 15.026533018867925, "percentage": 75.13, "elapsed_time": "0:48:44", "remaining_time": "0:16:08", "throughput": 5737.87, "total_tokens": 16781608} {"current_steps": 25490, "total_steps": 33920, "loss": 0.2941, "lr": 1.766788922933675e-06, "epoch": 15.029481132075471, "percentage": 75.15, "elapsed_time": "0:48:45", "remaining_time": "0:16:07", "throughput": 5737.97, "total_tokens": 16785000} {"current_steps": 25495, "total_steps": 33920, "loss": 0.5238, "lr": 1.7648269015555514e-06, "epoch": 15.03242924528302, "percentage": 75.16, "elapsed_time": "0:48:45", "remaining_time": "0:16:06", "throughput": 5737.96, "total_tokens": 16787720} {"current_steps": 25500, "total_steps": 33920, "loss": 0.3335, "lr": 1.7628657367034474e-06, "epoch": 15.035377358490566, "percentage": 75.18, "elapsed_time": "0:48:46", "remaining_time": "0:16:06", "throughput": 5738.03, "total_tokens": 16790920} {"current_steps": 25505, "total_steps": 33920, "loss": 0.256, "lr": 1.7609054288965922e-06, "epoch": 15.038325471698114, "percentage": 75.19, "elapsed_time": "0:48:46", "remaining_time": "0:16:05", "throughput": 5738.19, "total_tokens": 16795048} {"current_steps": 25510, "total_steps": 33920, "loss": 0.4023, "lr": 1.7589459786539847e-06, "epoch": 15.04127358490566, "percentage": 75.21, "elapsed_time": "0:48:47", "remaining_time": "0:16:05", "throughput": 5738.29, "total_tokens": 16798344} {"current_steps": 25515, "total_steps": 33920, "loss": 0.2624, "lr": 1.7569873864943975e-06, "epoch": 15.044221698113208, "percentage": 75.22, "elapsed_time": "0:48:47", "remaining_time": "0:16:04", "throughput": 5738.19, "total_tokens": 16800936} {"current_steps": 25520, "total_steps": 33920, "loss": 0.3751, "lr": 1.7550296529363764e-06, "epoch": 15.047169811320755, "percentage": 75.24, "elapsed_time": "0:48:48", "remaining_time": "0:16:03", "throughput": 5738.17, "total_tokens": 16803848} {"current_steps": 25525, "total_steps": 33920, "loss": 0.3708, "lr": 1.7530727784982393e-06, "epoch": 15.050117924528301, "percentage": 75.25, "elapsed_time": "0:48:48", "remaining_time": "0:16:03", "throughput": 5738.33, "total_tokens": 16807464} {"current_steps": 25530, "total_steps": 33920, "loss": 0.3122, "lr": 1.7511167636980765e-06, "epoch": 15.05306603773585, "percentage": 75.27, "elapsed_time": "0:48:49", "remaining_time": "0:16:02", "throughput": 5738.36, "total_tokens": 16810632} {"current_steps": 25535, "total_steps": 33920, "loss": 0.3106, "lr": 1.7491616090537539e-06, "epoch": 15.056014150943396, "percentage": 75.28, "elapsed_time": "0:48:50", "remaining_time": "0:16:02", "throughput": 5738.53, "total_tokens": 16814792} {"current_steps": 25540, "total_steps": 33920, "loss": 0.3038, "lr": 1.7472073150829056e-06, "epoch": 15.058962264150944, "percentage": 75.29, "elapsed_time": "0:48:50", "remaining_time": "0:16:01", "throughput": 5738.42, "total_tokens": 16817448} {"current_steps": 25545, "total_steps": 33920, "loss": 0.3265, "lr": 1.745253882302939e-06, "epoch": 15.06191037735849, "percentage": 75.31, "elapsed_time": "0:48:51", "remaining_time": "0:16:01", "throughput": 5738.28, "total_tokens": 16820040} {"current_steps": 25550, "total_steps": 33920, "loss": 0.3646, "lr": 1.743301311231035e-06, "epoch": 15.064858490566039, "percentage": 75.32, "elapsed_time": "0:48:51", "remaining_time": "0:16:00", "throughput": 5738.09, "total_tokens": 16822312} {"current_steps": 25555, "total_steps": 33920, "loss": 0.4168, "lr": 1.7413496023841437e-06, "epoch": 15.067806603773585, "percentage": 75.34, "elapsed_time": "0:48:52", "remaining_time": "0:15:59", "throughput": 5738.19, "total_tokens": 16825928} {"current_steps": 25560, "total_steps": 33920, "loss": 0.3144, "lr": 1.7393987562789876e-06, "epoch": 15.070754716981131, "percentage": 75.35, "elapsed_time": "0:48:52", "remaining_time": "0:15:59", "throughput": 5738.23, "total_tokens": 16829416} {"current_steps": 25565, "total_steps": 33920, "loss": 0.2958, "lr": 1.7374487734320655e-06, "epoch": 15.07370283018868, "percentage": 75.37, "elapsed_time": "0:48:53", "remaining_time": "0:15:58", "throughput": 5738.43, "total_tokens": 16833256} {"current_steps": 25570, "total_steps": 33920, "loss": 0.3411, "lr": 1.7354996543596408e-06, "epoch": 15.076650943396226, "percentage": 75.38, "elapsed_time": "0:48:53", "remaining_time": "0:15:58", "throughput": 5738.47, "total_tokens": 16836264} {"current_steps": 25575, "total_steps": 33920, "loss": 0.3851, "lr": 1.7335513995777504e-06, "epoch": 15.079599056603774, "percentage": 75.4, "elapsed_time": "0:48:54", "remaining_time": "0:15:57", "throughput": 5738.53, "total_tokens": 16839656} {"current_steps": 25580, "total_steps": 33920, "loss": 0.2808, "lr": 1.7316040096022062e-06, "epoch": 15.08254716981132, "percentage": 75.41, "elapsed_time": "0:48:55", "remaining_time": "0:15:56", "throughput": 5738.6, "total_tokens": 16842824} {"current_steps": 25585, "total_steps": 33920, "loss": 0.3753, "lr": 1.7296574849485863e-06, "epoch": 15.085495283018869, "percentage": 75.43, "elapsed_time": "0:48:55", "remaining_time": "0:15:56", "throughput": 5738.61, "total_tokens": 16846088} {"current_steps": 25590, "total_steps": 33920, "loss": 0.4453, "lr": 1.7277118261322423e-06, "epoch": 15.088443396226415, "percentage": 75.44, "elapsed_time": "0:48:56", "remaining_time": "0:15:55", "throughput": 5738.76, "total_tokens": 16849896} {"current_steps": 25595, "total_steps": 33920, "loss": 0.3374, "lr": 1.7257670336682925e-06, "epoch": 15.091391509433961, "percentage": 75.46, "elapsed_time": "0:48:56", "remaining_time": "0:15:55", "throughput": 5738.67, "total_tokens": 16852488} {"current_steps": 25600, "total_steps": 33920, "loss": 0.2529, "lr": 1.7238231080716339e-06, "epoch": 15.09433962264151, "percentage": 75.47, "elapsed_time": "0:48:57", "remaining_time": "0:15:54", "throughput": 5738.56, "total_tokens": 16855400} {"current_steps": 25605, "total_steps": 33920, "loss": 0.3211, "lr": 1.721880049856927e-06, "epoch": 15.097287735849056, "percentage": 75.49, "elapsed_time": "0:48:57", "remaining_time": "0:15:54", "throughput": 5738.62, "total_tokens": 16858536} {"current_steps": 25610, "total_steps": 33920, "loss": 0.2696, "lr": 1.7199378595386046e-06, "epoch": 15.100235849056604, "percentage": 75.5, "elapsed_time": "0:48:58", "remaining_time": "0:15:53", "throughput": 5738.66, "total_tokens": 16861928} {"current_steps": 25615, "total_steps": 33920, "loss": 0.2418, "lr": 1.7179965376308705e-06, "epoch": 15.10318396226415, "percentage": 75.52, "elapsed_time": "0:48:58", "remaining_time": "0:15:52", "throughput": 5738.75, "total_tokens": 16865288} {"current_steps": 25620, "total_steps": 33920, "loss": 0.3228, "lr": 1.7160560846476976e-06, "epoch": 15.106132075471699, "percentage": 75.53, "elapsed_time": "0:48:59", "remaining_time": "0:15:52", "throughput": 5738.78, "total_tokens": 16868456} {"current_steps": 25625, "total_steps": 33920, "loss": 0.2527, "lr": 1.7141165011028277e-06, "epoch": 15.109080188679245, "percentage": 75.55, "elapsed_time": "0:48:59", "remaining_time": "0:15:51", "throughput": 5738.86, "total_tokens": 16872008} {"current_steps": 25630, "total_steps": 33920, "loss": 0.3295, "lr": 1.7121777875097767e-06, "epoch": 15.112028301886792, "percentage": 75.56, "elapsed_time": "0:49:00", "remaining_time": "0:15:51", "throughput": 5739.09, "total_tokens": 16876136} {"current_steps": 25635, "total_steps": 33920, "loss": 0.269, "lr": 1.7102399443818268e-06, "epoch": 15.11497641509434, "percentage": 75.57, "elapsed_time": "0:49:01", "remaining_time": "0:15:50", "throughput": 5738.99, "total_tokens": 16878632} {"current_steps": 25640, "total_steps": 33920, "loss": 0.3123, "lr": 1.7083029722320294e-06, "epoch": 15.117924528301886, "percentage": 75.59, "elapsed_time": "0:49:01", "remaining_time": "0:15:49", "throughput": 5739.07, "total_tokens": 16882216} {"current_steps": 25645, "total_steps": 33920, "loss": 0.2988, "lr": 1.7063668715732063e-06, "epoch": 15.120872641509434, "percentage": 75.6, "elapsed_time": "0:49:02", "remaining_time": "0:15:49", "throughput": 5739.11, "total_tokens": 16885288} {"current_steps": 25650, "total_steps": 33920, "loss": 0.4179, "lr": 1.7044316429179492e-06, "epoch": 15.12382075471698, "percentage": 75.62, "elapsed_time": "0:49:02", "remaining_time": "0:15:48", "throughput": 5739.04, "total_tokens": 16887752} {"current_steps": 25655, "total_steps": 33920, "loss": 0.2887, "lr": 1.7024972867786155e-06, "epoch": 15.126768867924529, "percentage": 75.63, "elapsed_time": "0:49:03", "remaining_time": "0:15:48", "throughput": 5739.09, "total_tokens": 16890856} {"current_steps": 25660, "total_steps": 33920, "loss": 0.3167, "lr": 1.7005638036673389e-06, "epoch": 15.129716981132075, "percentage": 75.65, "elapsed_time": "0:49:03", "remaining_time": "0:15:47", "throughput": 5739.33, "total_tokens": 16895336} {"current_steps": 25665, "total_steps": 33920, "loss": 0.2267, "lr": 1.6986311940960148e-06, "epoch": 15.132665094339623, "percentage": 75.66, "elapsed_time": "0:49:04", "remaining_time": "0:15:47", "throughput": 5739.35, "total_tokens": 16898312} {"current_steps": 25670, "total_steps": 33920, "loss": 0.3115, "lr": 1.696699458576308e-06, "epoch": 15.13561320754717, "percentage": 75.68, "elapsed_time": "0:49:04", "remaining_time": "0:15:46", "throughput": 5739.36, "total_tokens": 16901128} {"current_steps": 25675, "total_steps": 33920, "loss": 0.4206, "lr": 1.6947685976196581e-06, "epoch": 15.138561320754716, "percentage": 75.69, "elapsed_time": "0:49:05", "remaining_time": "0:15:45", "throughput": 5739.3, "total_tokens": 16903592} {"current_steps": 25680, "total_steps": 33920, "loss": 0.2522, "lr": 1.692838611737267e-06, "epoch": 15.141509433962264, "percentage": 75.71, "elapsed_time": "0:49:05", "remaining_time": "0:15:45", "throughput": 5739.44, "total_tokens": 16907208} {"current_steps": 25685, "total_steps": 33920, "loss": 0.45, "lr": 1.690909501440106e-06, "epoch": 15.14445754716981, "percentage": 75.72, "elapsed_time": "0:49:06", "remaining_time": "0:15:44", "throughput": 5739.4, "total_tokens": 16910024} {"current_steps": 25690, "total_steps": 33920, "loss": 0.3583, "lr": 1.688981267238915e-06, "epoch": 15.147405660377359, "percentage": 75.74, "elapsed_time": "0:49:06", "remaining_time": "0:15:44", "throughput": 5739.28, "total_tokens": 16912360} {"current_steps": 25695, "total_steps": 33920, "loss": 0.4727, "lr": 1.687053909644204e-06, "epoch": 15.150353773584905, "percentage": 75.75, "elapsed_time": "0:49:07", "remaining_time": "0:15:43", "throughput": 5739.5, "total_tokens": 16916648} {"current_steps": 25700, "total_steps": 33920, "loss": 0.2969, "lr": 1.685127429166249e-06, "epoch": 15.153301886792454, "percentage": 75.77, "elapsed_time": "0:49:07", "remaining_time": "0:15:42", "throughput": 5739.42, "total_tokens": 16919272} {"current_steps": 25705, "total_steps": 33920, "loss": 0.251, "lr": 1.683201826315093e-06, "epoch": 15.15625, "percentage": 75.78, "elapsed_time": "0:49:08", "remaining_time": "0:15:42", "throughput": 5739.54, "total_tokens": 16922600} {"current_steps": 25710, "total_steps": 33920, "loss": 0.278, "lr": 1.681277101600548e-06, "epoch": 15.159198113207546, "percentage": 75.8, "elapsed_time": "0:49:08", "remaining_time": "0:15:41", "throughput": 5739.58, "total_tokens": 16925928} {"current_steps": 25715, "total_steps": 33920, "loss": 0.3313, "lr": 1.6793532555321939e-06, "epoch": 15.162146226415095, "percentage": 75.81, "elapsed_time": "0:49:09", "remaining_time": "0:15:41", "throughput": 5739.51, "total_tokens": 16929576} {"current_steps": 25720, "total_steps": 33920, "loss": 0.2601, "lr": 1.6774302886193744e-06, "epoch": 15.165094339622641, "percentage": 75.83, "elapsed_time": "0:49:10", "remaining_time": "0:15:40", "throughput": 5739.49, "total_tokens": 16933064} {"current_steps": 25725, "total_steps": 33920, "loss": 0.2837, "lr": 1.6755082013712076e-06, "epoch": 15.16804245283019, "percentage": 75.84, "elapsed_time": "0:49:10", "remaining_time": "0:15:40", "throughput": 5739.33, "total_tokens": 16935784} {"current_steps": 25730, "total_steps": 33920, "loss": 0.3122, "lr": 1.6735869942965716e-06, "epoch": 15.170990566037736, "percentage": 75.85, "elapsed_time": "0:49:11", "remaining_time": "0:15:39", "throughput": 5739.09, "total_tokens": 16938344} {"current_steps": 25735, "total_steps": 33920, "loss": 0.3814, "lr": 1.6716666679041155e-06, "epoch": 15.173938679245284, "percentage": 75.87, "elapsed_time": "0:49:11", "remaining_time": "0:15:38", "throughput": 5739.13, "total_tokens": 16941704} {"current_steps": 25740, "total_steps": 33920, "loss": 0.299, "lr": 1.6697472227022533e-06, "epoch": 15.17688679245283, "percentage": 75.88, "elapsed_time": "0:49:12", "remaining_time": "0:15:38", "throughput": 5739.13, "total_tokens": 16945320} {"current_steps": 25745, "total_steps": 33920, "loss": 0.3387, "lr": 1.6678286591991644e-06, "epoch": 15.179834905660377, "percentage": 75.9, "elapsed_time": "0:49:13", "remaining_time": "0:15:37", "throughput": 5738.74, "total_tokens": 16947528} {"current_steps": 25750, "total_steps": 33920, "loss": 0.3161, "lr": 1.665910977902801e-06, "epoch": 15.182783018867925, "percentage": 75.91, "elapsed_time": "0:49:13", "remaining_time": "0:15:37", "throughput": 5738.49, "total_tokens": 16950344} {"current_steps": 25755, "total_steps": 33920, "loss": 0.27, "lr": 1.6639941793208747e-06, "epoch": 15.185731132075471, "percentage": 75.93, "elapsed_time": "0:49:14", "remaining_time": "0:15:36", "throughput": 5738.59, "total_tokens": 16954088} {"current_steps": 25760, "total_steps": 33920, "loss": 0.278, "lr": 1.6620782639608674e-06, "epoch": 15.18867924528302, "percentage": 75.94, "elapsed_time": "0:49:15", "remaining_time": "0:15:36", "throughput": 5738.42, "total_tokens": 16957192} {"current_steps": 25765, "total_steps": 33920, "loss": 0.3524, "lr": 1.6601632323300231e-06, "epoch": 15.191627358490566, "percentage": 75.96, "elapsed_time": "0:49:15", "remaining_time": "0:15:35", "throughput": 5738.6, "total_tokens": 16961704} {"current_steps": 25770, "total_steps": 33920, "loss": 0.3723, "lr": 1.6582490849353595e-06, "epoch": 15.194575471698114, "percentage": 75.97, "elapsed_time": "0:49:16", "remaining_time": "0:15:34", "throughput": 5738.42, "total_tokens": 16964648} {"current_steps": 25775, "total_steps": 33920, "loss": 0.3161, "lr": 1.6563358222836523e-06, "epoch": 15.19752358490566, "percentage": 75.99, "elapsed_time": "0:49:16", "remaining_time": "0:15:34", "throughput": 5738.28, "total_tokens": 16967720} {"current_steps": 25780, "total_steps": 33920, "loss": 0.3366, "lr": 1.654423444881445e-06, "epoch": 15.200471698113208, "percentage": 76.0, "elapsed_time": "0:49:17", "remaining_time": "0:15:33", "throughput": 5738.15, "total_tokens": 16970600} {"current_steps": 25785, "total_steps": 33920, "loss": 0.2729, "lr": 1.652511953235051e-06, "epoch": 15.203419811320755, "percentage": 76.02, "elapsed_time": "0:49:18", "remaining_time": "0:15:33", "throughput": 5738.18, "total_tokens": 16974216} {"current_steps": 25790, "total_steps": 33920, "loss": 0.3119, "lr": 1.650601347850544e-06, "epoch": 15.206367924528301, "percentage": 76.03, "elapsed_time": "0:49:18", "remaining_time": "0:15:32", "throughput": 5738.16, "total_tokens": 16978152} {"current_steps": 25795, "total_steps": 33920, "loss": 0.5124, "lr": 1.6486916292337652e-06, "epoch": 15.20931603773585, "percentage": 76.05, "elapsed_time": "0:49:19", "remaining_time": "0:15:32", "throughput": 5737.99, "total_tokens": 16981000} {"current_steps": 25800, "total_steps": 33920, "loss": 0.2796, "lr": 1.6467827978903212e-06, "epoch": 15.212264150943396, "percentage": 76.06, "elapsed_time": "0:49:19", "remaining_time": "0:15:31", "throughput": 5737.94, "total_tokens": 16983880} {"current_steps": 25805, "total_steps": 33920, "loss": 0.2777, "lr": 1.6448748543255827e-06, "epoch": 15.215212264150944, "percentage": 76.08, "elapsed_time": "0:49:20", "remaining_time": "0:15:31", "throughput": 5737.6, "total_tokens": 16986248} {"current_steps": 25810, "total_steps": 33920, "loss": 0.3486, "lr": 1.6429677990446845e-06, "epoch": 15.21816037735849, "percentage": 76.09, "elapsed_time": "0:49:21", "remaining_time": "0:15:30", "throughput": 5737.77, "total_tokens": 16990408} {"current_steps": 25815, "total_steps": 33920, "loss": 0.3122, "lr": 1.6410616325525319e-06, "epoch": 15.221108490566039, "percentage": 76.11, "elapsed_time": "0:49:21", "remaining_time": "0:15:29", "throughput": 5737.51, "total_tokens": 16992872} {"current_steps": 25820, "total_steps": 33920, "loss": 0.2662, "lr": 1.6391563553537875e-06, "epoch": 15.224056603773585, "percentage": 76.12, "elapsed_time": "0:49:22", "remaining_time": "0:15:29", "throughput": 5737.25, "total_tokens": 16995240} {"current_steps": 25825, "total_steps": 33920, "loss": 0.3, "lr": 1.6372519679528832e-06, "epoch": 15.227004716981131, "percentage": 76.14, "elapsed_time": "0:49:22", "remaining_time": "0:15:28", "throughput": 5737.03, "total_tokens": 16997672} {"current_steps": 25830, "total_steps": 33920, "loss": 0.3838, "lr": 1.6353484708540124e-06, "epoch": 15.22995283018868, "percentage": 76.15, "elapsed_time": "0:49:23", "remaining_time": "0:15:28", "throughput": 5737.01, "total_tokens": 17000776} {"current_steps": 25835, "total_steps": 33920, "loss": 0.2832, "lr": 1.633445864561135e-06, "epoch": 15.232900943396226, "percentage": 76.16, "elapsed_time": "0:49:23", "remaining_time": "0:15:27", "throughput": 5737.06, "total_tokens": 17004488} {"current_steps": 25840, "total_steps": 33920, "loss": 0.436, "lr": 1.6315441495779726e-06, "epoch": 15.235849056603774, "percentage": 76.18, "elapsed_time": "0:49:24", "remaining_time": "0:15:26", "throughput": 5737.01, "total_tokens": 17007624} {"current_steps": 25845, "total_steps": 33920, "loss": 0.294, "lr": 1.6296433264080152e-06, "epoch": 15.23879716981132, "percentage": 76.19, "elapsed_time": "0:49:25", "remaining_time": "0:15:26", "throughput": 5736.89, "total_tokens": 17010760} {"current_steps": 25850, "total_steps": 33920, "loss": 0.4026, "lr": 1.627743395554513e-06, "epoch": 15.241745283018869, "percentage": 76.21, "elapsed_time": "0:49:25", "remaining_time": "0:15:25", "throughput": 5736.99, "total_tokens": 17014120} {"current_steps": 25855, "total_steps": 33920, "loss": 0.2662, "lr": 1.6258443575204802e-06, "epoch": 15.244693396226415, "percentage": 76.22, "elapsed_time": "0:49:26", "remaining_time": "0:15:25", "throughput": 5737.09, "total_tokens": 17017736} {"current_steps": 25860, "total_steps": 33920, "loss": 0.3901, "lr": 1.6239462128086936e-06, "epoch": 15.247641509433961, "percentage": 76.24, "elapsed_time": "0:49:26", "remaining_time": "0:15:24", "throughput": 5737.21, "total_tokens": 17021384} {"current_steps": 25865, "total_steps": 33920, "loss": 0.2683, "lr": 1.6220489619216988e-06, "epoch": 15.25058962264151, "percentage": 76.25, "elapsed_time": "0:49:27", "remaining_time": "0:15:24", "throughput": 5737.37, "total_tokens": 17025128} {"current_steps": 25870, "total_steps": 33920, "loss": 0.364, "lr": 1.6201526053618e-06, "epoch": 15.253537735849056, "percentage": 76.27, "elapsed_time": "0:49:27", "remaining_time": "0:15:23", "throughput": 5737.4, "total_tokens": 17028296} {"current_steps": 25875, "total_steps": 33920, "loss": 0.2027, "lr": 1.6182571436310634e-06, "epoch": 15.256485849056604, "percentage": 76.28, "elapsed_time": "0:49:28", "remaining_time": "0:15:22", "throughput": 5737.1, "total_tokens": 17030504} {"current_steps": 25880, "total_steps": 33920, "loss": 0.417, "lr": 1.616362577231324e-06, "epoch": 15.25943396226415, "percentage": 76.3, "elapsed_time": "0:49:29", "remaining_time": "0:15:22", "throughput": 5737.07, "total_tokens": 17033448} {"current_steps": 25885, "total_steps": 33920, "loss": 0.2369, "lr": 1.614468906664175e-06, "epoch": 15.262382075471699, "percentage": 76.31, "elapsed_time": "0:49:29", "remaining_time": "0:15:21", "throughput": 5737.01, "total_tokens": 17036808} {"current_steps": 25890, "total_steps": 33920, "loss": 0.2515, "lr": 1.612576132430974e-06, "epoch": 15.265330188679245, "percentage": 76.33, "elapsed_time": "0:49:30", "remaining_time": "0:15:21", "throughput": 5736.9, "total_tokens": 17039880} {"current_steps": 25895, "total_steps": 33920, "loss": 0.2961, "lr": 1.6106842550328406e-06, "epoch": 15.268278301886792, "percentage": 76.34, "elapsed_time": "0:49:30", "remaining_time": "0:15:20", "throughput": 5736.86, "total_tokens": 17043048} {"current_steps": 25900, "total_steps": 33920, "loss": 0.3847, "lr": 1.6087932749706582e-06, "epoch": 15.27122641509434, "percentage": 76.36, "elapsed_time": "0:49:31", "remaining_time": "0:15:20", "throughput": 5736.65, "total_tokens": 17045800} {"current_steps": 25905, "total_steps": 33920, "loss": 0.2803, "lr": 1.6069031927450696e-06, "epoch": 15.274174528301886, "percentage": 76.37, "elapsed_time": "0:49:32", "remaining_time": "0:15:19", "throughput": 5736.7, "total_tokens": 17049576} {"current_steps": 25910, "total_steps": 33920, "loss": 0.3702, "lr": 1.605014008856486e-06, "epoch": 15.277122641509434, "percentage": 76.39, "elapsed_time": "0:49:32", "remaining_time": "0:15:18", "throughput": 5736.58, "total_tokens": 17052424} {"current_steps": 25915, "total_steps": 33920, "loss": 0.3557, "lr": 1.6031257238050745e-06, "epoch": 15.28007075471698, "percentage": 76.4, "elapsed_time": "0:49:33", "remaining_time": "0:15:18", "throughput": 5736.39, "total_tokens": 17055272} {"current_steps": 25920, "total_steps": 33920, "loss": 0.2642, "lr": 1.601238338090768e-06, "epoch": 15.283018867924529, "percentage": 76.42, "elapsed_time": "0:49:33", "remaining_time": "0:15:17", "throughput": 5736.53, "total_tokens": 17059080} {"current_steps": 25925, "total_steps": 33920, "loss": 0.3431, "lr": 1.5993518522132595e-06, "epoch": 15.285966981132075, "percentage": 76.43, "elapsed_time": "0:49:34", "remaining_time": "0:15:17", "throughput": 5736.38, "total_tokens": 17061672} {"current_steps": 25930, "total_steps": 33920, "loss": 0.2612, "lr": 1.5974662666720037e-06, "epoch": 15.288915094339623, "percentage": 76.44, "elapsed_time": "0:49:34", "remaining_time": "0:15:16", "throughput": 5736.38, "total_tokens": 17065032} {"current_steps": 25935, "total_steps": 33920, "loss": 0.3122, "lr": 1.5955815819662162e-06, "epoch": 15.29186320754717, "percentage": 76.46, "elapsed_time": "0:49:35", "remaining_time": "0:15:16", "throughput": 5736.34, "total_tokens": 17068008} {"current_steps": 25940, "total_steps": 33920, "loss": 0.3056, "lr": 1.5936977985948788e-06, "epoch": 15.294811320754716, "percentage": 76.47, "elapsed_time": "0:49:35", "remaining_time": "0:15:15", "throughput": 5736.26, "total_tokens": 17070984} {"current_steps": 25945, "total_steps": 33920, "loss": 0.2519, "lr": 1.5918149170567298e-06, "epoch": 15.297759433962264, "percentage": 76.49, "elapsed_time": "0:49:36", "remaining_time": "0:15:14", "throughput": 5736.02, "total_tokens": 17073256} {"current_steps": 25950, "total_steps": 33920, "loss": 0.3043, "lr": 1.5899329378502698e-06, "epoch": 15.30070754716981, "percentage": 76.5, "elapsed_time": "0:49:37", "remaining_time": "0:15:14", "throughput": 5736.03, "total_tokens": 17076712} {"current_steps": 25955, "total_steps": 33920, "loss": 0.3923, "lr": 1.588051861473761e-06, "epoch": 15.303655660377359, "percentage": 76.52, "elapsed_time": "0:49:37", "remaining_time": "0:15:13", "throughput": 5735.9, "total_tokens": 17079400} {"current_steps": 25960, "total_steps": 33920, "loss": 0.2076, "lr": 1.5861716884252253e-06, "epoch": 15.306603773584905, "percentage": 76.53, "elapsed_time": "0:49:38", "remaining_time": "0:15:13", "throughput": 5736.14, "total_tokens": 17084936} {"current_steps": 25965, "total_steps": 33920, "loss": 0.3876, "lr": 1.5842924192024489e-06, "epoch": 15.309551886792454, "percentage": 76.55, "elapsed_time": "0:49:39", "remaining_time": "0:15:12", "throughput": 5736.2, "total_tokens": 17088168} {"current_steps": 25970, "total_steps": 33920, "loss": 0.3964, "lr": 1.5824140543029742e-06, "epoch": 15.3125, "percentage": 76.56, "elapsed_time": "0:49:39", "remaining_time": "0:15:12", "throughput": 5736.1, "total_tokens": 17090952} {"current_steps": 25975, "total_steps": 33920, "loss": 0.3467, "lr": 1.5805365942241092e-06, "epoch": 15.315448113207546, "percentage": 76.58, "elapsed_time": "0:49:40", "remaining_time": "0:15:11", "throughput": 5735.88, "total_tokens": 17093288} {"current_steps": 25980, "total_steps": 33920, "loss": 0.2501, "lr": 1.5786600394629181e-06, "epoch": 15.318396226415095, "percentage": 76.59, "elapsed_time": "0:49:40", "remaining_time": "0:15:10", "throughput": 5735.94, "total_tokens": 17096648} {"current_steps": 25985, "total_steps": 33920, "loss": 0.2978, "lr": 1.5767843905162261e-06, "epoch": 15.321344339622641, "percentage": 76.61, "elapsed_time": "0:49:41", "remaining_time": "0:15:10", "throughput": 5735.98, "total_tokens": 17099912} {"current_steps": 25990, "total_steps": 33920, "loss": 0.2724, "lr": 1.5749096478806209e-06, "epoch": 15.32429245283019, "percentage": 76.62, "elapsed_time": "0:49:41", "remaining_time": "0:15:09", "throughput": 5735.88, "total_tokens": 17102664} {"current_steps": 25995, "total_steps": 33920, "loss": 0.31, "lr": 1.5730358120524452e-06, "epoch": 15.327240566037736, "percentage": 76.64, "elapsed_time": "0:49:42", "remaining_time": "0:15:09", "throughput": 5735.95, "total_tokens": 17106184} {"current_steps": 26000, "total_steps": 33920, "loss": 0.4387, "lr": 1.5711628835278098e-06, "epoch": 15.330188679245284, "percentage": 76.65, "elapsed_time": "0:49:42", "remaining_time": "0:15:08", "throughput": 5735.96, "total_tokens": 17109320} {"current_steps": 26005, "total_steps": 33920, "loss": 0.2836, "lr": 1.5692908628025782e-06, "epoch": 15.33313679245283, "percentage": 76.67, "elapsed_time": "0:49:43", "remaining_time": "0:15:08", "throughput": 5735.85, "total_tokens": 17112392} {"current_steps": 26010, "total_steps": 33920, "loss": 0.3777, "lr": 1.5674197503723765e-06, "epoch": 15.336084905660377, "percentage": 76.68, "elapsed_time": "0:49:44", "remaining_time": "0:15:07", "throughput": 5736.07, "total_tokens": 17116840} {"current_steps": 26015, "total_steps": 33920, "loss": 0.3213, "lr": 1.5655495467325893e-06, "epoch": 15.339033018867925, "percentage": 76.7, "elapsed_time": "0:49:44", "remaining_time": "0:15:06", "throughput": 5736.05, "total_tokens": 17119912} {"current_steps": 26020, "total_steps": 33920, "loss": 0.3411, "lr": 1.5636802523783613e-06, "epoch": 15.341981132075471, "percentage": 76.71, "elapsed_time": "0:49:45", "remaining_time": "0:15:06", "throughput": 5736.0, "total_tokens": 17123304} {"current_steps": 26025, "total_steps": 33920, "loss": 0.3106, "lr": 1.5618118678045947e-06, "epoch": 15.34492924528302, "percentage": 76.72, "elapsed_time": "0:49:45", "remaining_time": "0:15:05", "throughput": 5736.06, "total_tokens": 17127272} {"current_steps": 26030, "total_steps": 33920, "loss": 0.2838, "lr": 1.5599443935059549e-06, "epoch": 15.347877358490566, "percentage": 76.74, "elapsed_time": "0:49:46", "remaining_time": "0:15:05", "throughput": 5735.82, "total_tokens": 17129544} {"current_steps": 26035, "total_steps": 33920, "loss": 0.2892, "lr": 1.5580778299768635e-06, "epoch": 15.350825471698114, "percentage": 76.75, "elapsed_time": "0:49:46", "remaining_time": "0:15:04", "throughput": 5735.83, "total_tokens": 17132872} {"current_steps": 26040, "total_steps": 33920, "loss": 0.3581, "lr": 1.5562121777114997e-06, "epoch": 15.35377358490566, "percentage": 76.77, "elapsed_time": "0:49:47", "remaining_time": "0:15:04", "throughput": 5735.72, "total_tokens": 17135624} {"current_steps": 26045, "total_steps": 33920, "loss": 0.2923, "lr": 1.5543474372038043e-06, "epoch": 15.356721698113208, "percentage": 76.78, "elapsed_time": "0:49:48", "remaining_time": "0:15:03", "throughput": 5735.65, "total_tokens": 17138824} {"current_steps": 26050, "total_steps": 33920, "loss": 0.2701, "lr": 1.5524836089474748e-06, "epoch": 15.359669811320755, "percentage": 76.8, "elapsed_time": "0:49:48", "remaining_time": "0:15:02", "throughput": 5735.63, "total_tokens": 17142184} {"current_steps": 26055, "total_steps": 33920, "loss": 0.3542, "lr": 1.5506206934359664e-06, "epoch": 15.362617924528301, "percentage": 76.81, "elapsed_time": "0:49:49", "remaining_time": "0:15:02", "throughput": 5735.48, "total_tokens": 17144744} {"current_steps": 26060, "total_steps": 33920, "loss": 0.4045, "lr": 1.5487586911624947e-06, "epoch": 15.36556603773585, "percentage": 76.83, "elapsed_time": "0:49:49", "remaining_time": "0:15:01", "throughput": 5735.56, "total_tokens": 17148072} {"current_steps": 26065, "total_steps": 33920, "loss": 0.3564, "lr": 1.5468976026200355e-06, "epoch": 15.368514150943396, "percentage": 76.84, "elapsed_time": "0:49:50", "remaining_time": "0:15:01", "throughput": 5735.55, "total_tokens": 17151496} {"current_steps": 26070, "total_steps": 33920, "loss": 0.3105, "lr": 1.5450374283013187e-06, "epoch": 15.371462264150944, "percentage": 76.86, "elapsed_time": "0:49:50", "remaining_time": "0:15:00", "throughput": 5735.43, "total_tokens": 17154344} {"current_steps": 26075, "total_steps": 33920, "loss": 0.2704, "lr": 1.5431781686988317e-06, "epoch": 15.37441037735849, "percentage": 76.87, "elapsed_time": "0:49:51", "remaining_time": "0:15:00", "throughput": 5735.3, "total_tokens": 17156904} {"current_steps": 26080, "total_steps": 33920, "loss": 0.2789, "lr": 1.5413198243048233e-06, "epoch": 15.377358490566039, "percentage": 76.89, "elapsed_time": "0:49:51", "remaining_time": "0:14:59", "throughput": 5735.14, "total_tokens": 17159464} {"current_steps": 26085, "total_steps": 33920, "loss": 0.3597, "lr": 1.5394623956112974e-06, "epoch": 15.380306603773585, "percentage": 76.9, "elapsed_time": "0:49:52", "remaining_time": "0:14:58", "throughput": 5735.06, "total_tokens": 17162504} {"current_steps": 26090, "total_steps": 33920, "loss": 0.2882, "lr": 1.537605883110015e-06, "epoch": 15.383254716981131, "percentage": 76.92, "elapsed_time": "0:49:53", "remaining_time": "0:14:58", "throughput": 5735.2, "total_tokens": 17167112} {"current_steps": 26095, "total_steps": 33920, "loss": 0.3652, "lr": 1.5357502872924984e-06, "epoch": 15.38620283018868, "percentage": 76.93, "elapsed_time": "0:49:53", "remaining_time": "0:14:57", "throughput": 5735.08, "total_tokens": 17169768} {"current_steps": 26100, "total_steps": 33920, "loss": 0.3263, "lr": 1.5338956086500235e-06, "epoch": 15.389150943396226, "percentage": 76.95, "elapsed_time": "0:49:54", "remaining_time": "0:14:57", "throughput": 5734.99, "total_tokens": 17173096} {"current_steps": 26105, "total_steps": 33920, "loss": 0.4045, "lr": 1.5320418476736237e-06, "epoch": 15.392099056603774, "percentage": 76.96, "elapsed_time": "0:49:54", "remaining_time": "0:14:56", "throughput": 5734.89, "total_tokens": 17175848} {"current_steps": 26110, "total_steps": 33920, "loss": 0.2568, "lr": 1.5301890048540912e-06, "epoch": 15.39504716981132, "percentage": 76.98, "elapsed_time": "0:49:55", "remaining_time": "0:14:56", "throughput": 5734.95, "total_tokens": 17179752} {"current_steps": 26115, "total_steps": 33920, "loss": 0.2369, "lr": 1.5283370806819743e-06, "epoch": 15.397995283018869, "percentage": 76.99, "elapsed_time": "0:49:56", "remaining_time": "0:14:55", "throughput": 5735.02, "total_tokens": 17183304} {"current_steps": 26120, "total_steps": 33920, "loss": 0.3078, "lr": 1.5264860756475752e-06, "epoch": 15.400943396226415, "percentage": 77.0, "elapsed_time": "0:49:56", "remaining_time": "0:14:54", "throughput": 5735.0, "total_tokens": 17186504} {"current_steps": 26125, "total_steps": 33920, "loss": 0.2922, "lr": 1.5246359902409592e-06, "epoch": 15.403891509433961, "percentage": 77.02, "elapsed_time": "0:49:57", "remaining_time": "0:14:54", "throughput": 5735.09, "total_tokens": 17190376} {"current_steps": 26130, "total_steps": 33920, "loss": 0.2848, "lr": 1.5227868249519423e-06, "epoch": 15.40683962264151, "percentage": 77.03, "elapsed_time": "0:49:57", "remaining_time": "0:14:53", "throughput": 5734.89, "total_tokens": 17192776} {"current_steps": 26135, "total_steps": 33920, "loss": 0.2947, "lr": 1.5209385802700999e-06, "epoch": 15.409787735849056, "percentage": 77.05, "elapsed_time": "0:49:58", "remaining_time": "0:14:53", "throughput": 5735.05, "total_tokens": 17196872} {"current_steps": 26140, "total_steps": 33920, "loss": 0.3127, "lr": 1.5190912566847626e-06, "epoch": 15.412735849056604, "percentage": 77.06, "elapsed_time": "0:49:59", "remaining_time": "0:14:52", "throughput": 5735.13, "total_tokens": 17200520} {"current_steps": 26145, "total_steps": 33920, "loss": 0.3653, "lr": 1.5172448546850166e-06, "epoch": 15.41568396226415, "percentage": 77.08, "elapsed_time": "0:49:59", "remaining_time": "0:14:52", "throughput": 5735.21, "total_tokens": 17203944} {"current_steps": 26150, "total_steps": 33920, "loss": 0.2561, "lr": 1.515399374759704e-06, "epoch": 15.418632075471699, "percentage": 77.09, "elapsed_time": "0:50:00", "remaining_time": "0:14:51", "throughput": 5735.16, "total_tokens": 17206984} {"current_steps": 26155, "total_steps": 33920, "loss": 0.3816, "lr": 1.513554817397424e-06, "epoch": 15.421580188679245, "percentage": 77.11, "elapsed_time": "0:50:00", "remaining_time": "0:14:50", "throughput": 5735.16, "total_tokens": 17210376} {"current_steps": 26160, "total_steps": 33920, "loss": 0.3376, "lr": 1.5117111830865338e-06, "epoch": 15.424528301886792, "percentage": 77.12, "elapsed_time": "0:50:01", "remaining_time": "0:14:50", "throughput": 5735.06, "total_tokens": 17213160} {"current_steps": 26165, "total_steps": 33920, "loss": 0.3159, "lr": 1.509868472315142e-06, "epoch": 15.42747641509434, "percentage": 77.14, "elapsed_time": "0:50:01", "remaining_time": "0:14:49", "throughput": 5735.11, "total_tokens": 17216776} {"current_steps": 26170, "total_steps": 33920, "loss": 0.2942, "lr": 1.508026685571113e-06, "epoch": 15.430424528301886, "percentage": 77.15, "elapsed_time": "0:50:02", "remaining_time": "0:14:49", "throughput": 5735.13, "total_tokens": 17220168} {"current_steps": 26175, "total_steps": 33920, "loss": 0.4062, "lr": 1.506185823342069e-06, "epoch": 15.433372641509434, "percentage": 77.17, "elapsed_time": "0:50:03", "remaining_time": "0:14:48", "throughput": 5735.28, "total_tokens": 17223720} {"current_steps": 26180, "total_steps": 33920, "loss": 0.2379, "lr": 1.504345886115386e-06, "epoch": 15.43632075471698, "percentage": 77.18, "elapsed_time": "0:50:03", "remaining_time": "0:14:48", "throughput": 5735.31, "total_tokens": 17226984} {"current_steps": 26185, "total_steps": 33920, "loss": 0.3352, "lr": 1.502506874378193e-06, "epoch": 15.439268867924529, "percentage": 77.2, "elapsed_time": "0:50:04", "remaining_time": "0:14:47", "throughput": 5735.47, "total_tokens": 17230984} {"current_steps": 26190, "total_steps": 33920, "loss": 0.3597, "lr": 1.5006687886173805e-06, "epoch": 15.442216981132075, "percentage": 77.21, "elapsed_time": "0:50:04", "remaining_time": "0:14:46", "throughput": 5735.49, "total_tokens": 17234376} {"current_steps": 26195, "total_steps": 33920, "loss": 0.2993, "lr": 1.498831629319587e-06, "epoch": 15.445165094339623, "percentage": 77.23, "elapsed_time": "0:50:05", "remaining_time": "0:14:46", "throughput": 5735.35, "total_tokens": 17237064} {"current_steps": 26200, "total_steps": 33920, "loss": 0.3496, "lr": 1.4969953969712087e-06, "epoch": 15.44811320754717, "percentage": 77.24, "elapsed_time": "0:50:05", "remaining_time": "0:14:45", "throughput": 5735.2, "total_tokens": 17239656} {"current_steps": 26205, "total_steps": 33920, "loss": 0.3404, "lr": 1.4951600920583963e-06, "epoch": 15.451061320754716, "percentage": 77.26, "elapsed_time": "0:50:06", "remaining_time": "0:14:45", "throughput": 5735.04, "total_tokens": 17242184} {"current_steps": 26210, "total_steps": 33920, "loss": 0.3468, "lr": 1.493325715067055e-06, "epoch": 15.454009433962264, "percentage": 77.27, "elapsed_time": "0:50:07", "remaining_time": "0:14:44", "throughput": 5735.16, "total_tokens": 17245768} {"current_steps": 26215, "total_steps": 33920, "loss": 0.296, "lr": 1.4914922664828417e-06, "epoch": 15.45695754716981, "percentage": 77.28, "elapsed_time": "0:50:07", "remaining_time": "0:14:43", "throughput": 5735.23, "total_tokens": 17249384} {"current_steps": 26220, "total_steps": 33920, "loss": 0.2319, "lr": 1.4896597467911732e-06, "epoch": 15.459905660377359, "percentage": 77.3, "elapsed_time": "0:50:08", "remaining_time": "0:14:43", "throughput": 5735.16, "total_tokens": 17252520} {"current_steps": 26225, "total_steps": 33920, "loss": 0.248, "lr": 1.4878281564772156e-06, "epoch": 15.462853773584905, "percentage": 77.31, "elapsed_time": "0:50:08", "remaining_time": "0:14:42", "throughput": 5735.21, "total_tokens": 17256072} {"current_steps": 26230, "total_steps": 33920, "loss": 0.3952, "lr": 1.4859974960258898e-06, "epoch": 15.465801886792454, "percentage": 77.33, "elapsed_time": "0:50:09", "remaining_time": "0:14:42", "throughput": 5735.12, "total_tokens": 17258728} {"current_steps": 26235, "total_steps": 33920, "loss": 0.4726, "lr": 1.4841677659218723e-06, "epoch": 15.46875, "percentage": 77.34, "elapsed_time": "0:50:09", "remaining_time": "0:14:41", "throughput": 5735.37, "total_tokens": 17263304} {"current_steps": 26240, "total_steps": 33920, "loss": 0.2997, "lr": 1.4823389666495886e-06, "epoch": 15.471698113207546, "percentage": 77.36, "elapsed_time": "0:50:10", "remaining_time": "0:14:41", "throughput": 5735.22, "total_tokens": 17265832} {"current_steps": 26245, "total_steps": 33920, "loss": 0.3383, "lr": 1.4805110986932258e-06, "epoch": 15.474646226415095, "percentage": 77.37, "elapsed_time": "0:50:11", "remaining_time": "0:14:40", "throughput": 5735.58, "total_tokens": 17272584} {"current_steps": 26250, "total_steps": 33920, "loss": 0.2323, "lr": 1.4786841625367166e-06, "epoch": 15.477594339622641, "percentage": 77.39, "elapsed_time": "0:50:12", "remaining_time": "0:14:40", "throughput": 5735.64, "total_tokens": 17275944} {"current_steps": 26255, "total_steps": 33920, "loss": 0.2672, "lr": 1.476858158663752e-06, "epoch": 15.48054245283019, "percentage": 77.4, "elapsed_time": "0:50:12", "remaining_time": "0:14:39", "throughput": 5735.74, "total_tokens": 17279528} {"current_steps": 26260, "total_steps": 33920, "loss": 0.2695, "lr": 1.4750330875577745e-06, "epoch": 15.483490566037736, "percentage": 77.42, "elapsed_time": "0:50:13", "remaining_time": "0:14:38", "throughput": 5735.59, "total_tokens": 17282152} {"current_steps": 26265, "total_steps": 33920, "loss": 0.2342, "lr": 1.4732089497019787e-06, "epoch": 15.486438679245284, "percentage": 77.43, "elapsed_time": "0:50:13", "remaining_time": "0:14:38", "throughput": 5735.68, "total_tokens": 17285448} {"current_steps": 26270, "total_steps": 33920, "loss": 0.2585, "lr": 1.471385745579313e-06, "epoch": 15.48938679245283, "percentage": 77.45, "elapsed_time": "0:50:14", "remaining_time": "0:14:37", "throughput": 5735.7, "total_tokens": 17288936} {"current_steps": 26275, "total_steps": 33920, "loss": 0.3861, "lr": 1.4695634756724775e-06, "epoch": 15.492334905660377, "percentage": 77.46, "elapsed_time": "0:50:14", "remaining_time": "0:14:37", "throughput": 5735.81, "total_tokens": 17292488} {"current_steps": 26280, "total_steps": 33920, "loss": 0.2907, "lr": 1.4677421404639281e-06, "epoch": 15.495283018867925, "percentage": 77.48, "elapsed_time": "0:50:15", "remaining_time": "0:14:36", "throughput": 5735.61, "total_tokens": 17295016} {"current_steps": 26285, "total_steps": 33920, "loss": 0.3993, "lr": 1.4659217404358706e-06, "epoch": 15.498231132075471, "percentage": 77.49, "elapsed_time": "0:50:15", "remaining_time": "0:14:36", "throughput": 5735.55, "total_tokens": 17297960} {"current_steps": 26290, "total_steps": 33920, "loss": 0.223, "lr": 1.4641022760702627e-06, "epoch": 15.50117924528302, "percentage": 77.51, "elapsed_time": "0:50:16", "remaining_time": "0:14:35", "throughput": 5735.58, "total_tokens": 17301160} {"current_steps": 26295, "total_steps": 33920, "loss": 0.2293, "lr": 1.4622837478488172e-06, "epoch": 15.504127358490566, "percentage": 77.52, "elapsed_time": "0:50:17", "remaining_time": "0:14:34", "throughput": 5735.93, "total_tokens": 17307720} {"current_steps": 26300, "total_steps": 33920, "loss": 0.2191, "lr": 1.4604661562529953e-06, "epoch": 15.507075471698114, "percentage": 77.54, "elapsed_time": "0:50:18", "remaining_time": "0:14:34", "throughput": 5736.4, "total_tokens": 17315656} {"current_steps": 26305, "total_steps": 33920, "loss": 0.3279, "lr": 1.4586495017640119e-06, "epoch": 15.51002358490566, "percentage": 77.55, "elapsed_time": "0:50:19", "remaining_time": "0:14:33", "throughput": 5736.3, "total_tokens": 17318536} {"current_steps": 26310, "total_steps": 33920, "loss": 0.2405, "lr": 1.4568337848628366e-06, "epoch": 15.512971698113208, "percentage": 77.56, "elapsed_time": "0:50:19", "remaining_time": "0:14:33", "throughput": 5736.12, "total_tokens": 17321256} {"current_steps": 26315, "total_steps": 33920, "loss": 0.2085, "lr": 1.4550190060301872e-06, "epoch": 15.515919811320755, "percentage": 77.58, "elapsed_time": "0:50:20", "remaining_time": "0:14:32", "throughput": 5736.11, "total_tokens": 17324584} {"current_steps": 26320, "total_steps": 33920, "loss": 0.4389, "lr": 1.4532051657465335e-06, "epoch": 15.518867924528301, "percentage": 77.59, "elapsed_time": "0:50:20", "remaining_time": "0:14:32", "throughput": 5736.12, "total_tokens": 17327848} {"current_steps": 26325, "total_steps": 33920, "loss": 0.3576, "lr": 1.4513922644920985e-06, "epoch": 15.52181603773585, "percentage": 77.61, "elapsed_time": "0:50:21", "remaining_time": "0:14:31", "throughput": 5735.95, "total_tokens": 17330600} {"current_steps": 26330, "total_steps": 33920, "loss": 0.337, "lr": 1.4495803027468552e-06, "epoch": 15.524764150943396, "percentage": 77.62, "elapsed_time": "0:50:21", "remaining_time": "0:14:31", "throughput": 5736.06, "total_tokens": 17334088} {"current_steps": 26335, "total_steps": 33920, "loss": 0.3193, "lr": 1.4477692809905263e-06, "epoch": 15.527712264150944, "percentage": 77.64, "elapsed_time": "0:50:22", "remaining_time": "0:14:30", "throughput": 5736.08, "total_tokens": 17337288} {"current_steps": 26340, "total_steps": 33920, "loss": 0.2271, "lr": 1.4459591997025896e-06, "epoch": 15.53066037735849, "percentage": 77.65, "elapsed_time": "0:50:23", "remaining_time": "0:14:29", "throughput": 5736.19, "total_tokens": 17340808} {"current_steps": 26345, "total_steps": 33920, "loss": 0.343, "lr": 1.4441500593622737e-06, "epoch": 15.533608490566039, "percentage": 77.67, "elapsed_time": "0:50:23", "remaining_time": "0:14:29", "throughput": 5736.13, "total_tokens": 17343848} {"current_steps": 26350, "total_steps": 33920, "loss": 0.3277, "lr": 1.4423418604485539e-06, "epoch": 15.536556603773585, "percentage": 77.68, "elapsed_time": "0:50:24", "remaining_time": "0:14:28", "throughput": 5736.24, "total_tokens": 17347592} {"current_steps": 26355, "total_steps": 33920, "loss": 0.4064, "lr": 1.4405346034401597e-06, "epoch": 15.539504716981131, "percentage": 77.7, "elapsed_time": "0:50:24", "remaining_time": "0:14:28", "throughput": 5736.16, "total_tokens": 17350312} {"current_steps": 26360, "total_steps": 33920, "loss": 0.3379, "lr": 1.4387282888155695e-06, "epoch": 15.54245283018868, "percentage": 77.71, "elapsed_time": "0:50:25", "remaining_time": "0:14:27", "throughput": 5736.09, "total_tokens": 17353192} {"current_steps": 26365, "total_steps": 33920, "loss": 0.2627, "lr": 1.436922917053013e-06, "epoch": 15.545400943396226, "percentage": 77.73, "elapsed_time": "0:50:25", "remaining_time": "0:14:27", "throughput": 5735.87, "total_tokens": 17355752} {"current_steps": 26370, "total_steps": 33920, "loss": 0.3735, "lr": 1.4351184886304686e-06, "epoch": 15.548349056603774, "percentage": 77.74, "elapsed_time": "0:50:26", "remaining_time": "0:14:26", "throughput": 5735.98, "total_tokens": 17359496} {"current_steps": 26375, "total_steps": 33920, "loss": 0.3545, "lr": 1.4333150040256699e-06, "epoch": 15.55129716981132, "percentage": 77.76, "elapsed_time": "0:50:26", "remaining_time": "0:14:25", "throughput": 5736.01, "total_tokens": 17362760} {"current_steps": 26380, "total_steps": 33920, "loss": 0.335, "lr": 1.4315124637160954e-06, "epoch": 15.554245283018869, "percentage": 77.77, "elapsed_time": "0:50:27", "remaining_time": "0:14:25", "throughput": 5736.05, "total_tokens": 17365992} {"current_steps": 26385, "total_steps": 33920, "loss": 0.3401, "lr": 1.4297108681789752e-06, "epoch": 15.557193396226415, "percentage": 77.79, "elapsed_time": "0:50:28", "remaining_time": "0:14:24", "throughput": 5735.99, "total_tokens": 17368936} {"current_steps": 26390, "total_steps": 33920, "loss": 0.3757, "lr": 1.4279102178912902e-06, "epoch": 15.560141509433961, "percentage": 77.8, "elapsed_time": "0:50:28", "remaining_time": "0:14:24", "throughput": 5736.11, "total_tokens": 17373000} {"current_steps": 26395, "total_steps": 33920, "loss": 0.5194, "lr": 1.4261105133297693e-06, "epoch": 15.56308962264151, "percentage": 77.82, "elapsed_time": "0:50:29", "remaining_time": "0:14:23", "throughput": 5736.16, "total_tokens": 17376200} {"current_steps": 26400, "total_steps": 33920, "loss": 0.3226, "lr": 1.4243117549708913e-06, "epoch": 15.566037735849056, "percentage": 77.83, "elapsed_time": "0:50:30", "remaining_time": "0:14:23", "throughput": 5736.46, "total_tokens": 17382728} {"current_steps": 26405, "total_steps": 33920, "loss": 0.2979, "lr": 1.422513943290888e-06, "epoch": 15.568985849056604, "percentage": 77.84, "elapsed_time": "0:50:30", "remaining_time": "0:14:22", "throughput": 5736.59, "total_tokens": 17386376} {"current_steps": 26410, "total_steps": 33920, "loss": 0.2804, "lr": 1.4207170787657365e-06, "epoch": 15.57193396226415, "percentage": 77.86, "elapsed_time": "0:50:31", "remaining_time": "0:14:22", "throughput": 5736.66, "total_tokens": 17390216} {"current_steps": 26415, "total_steps": 33920, "loss": 0.3759, "lr": 1.4189211618711646e-06, "epoch": 15.574882075471699, "percentage": 77.87, "elapsed_time": "0:50:31", "remaining_time": "0:14:21", "throughput": 5736.55, "total_tokens": 17393064} {"current_steps": 26420, "total_steps": 33920, "loss": 0.3598, "lr": 1.417126193082648e-06, "epoch": 15.577830188679245, "percentage": 77.89, "elapsed_time": "0:50:32", "remaining_time": "0:14:20", "throughput": 5736.55, "total_tokens": 17396328} {"current_steps": 26425, "total_steps": 33920, "loss": 0.3908, "lr": 1.4153321728754133e-06, "epoch": 15.580778301886792, "percentage": 77.9, "elapsed_time": "0:50:33", "remaining_time": "0:14:20", "throughput": 5736.57, "total_tokens": 17399656} {"current_steps": 26430, "total_steps": 33920, "loss": 0.2471, "lr": 1.4135391017244338e-06, "epoch": 15.58372641509434, "percentage": 77.92, "elapsed_time": "0:50:33", "remaining_time": "0:14:19", "throughput": 5736.49, "total_tokens": 17402664} {"current_steps": 26435, "total_steps": 33920, "loss": 0.337, "lr": 1.4117469801044332e-06, "epoch": 15.586674528301886, "percentage": 77.93, "elapsed_time": "0:50:34", "remaining_time": "0:14:19", "throughput": 5736.46, "total_tokens": 17406504} {"current_steps": 26440, "total_steps": 33920, "loss": 0.3602, "lr": 1.4099558084898862e-06, "epoch": 15.589622641509434, "percentage": 77.95, "elapsed_time": "0:50:34", "remaining_time": "0:14:18", "throughput": 5736.45, "total_tokens": 17409544} {"current_steps": 26445, "total_steps": 33920, "loss": 0.4229, "lr": 1.408165587355011e-06, "epoch": 15.59257075471698, "percentage": 77.96, "elapsed_time": "0:50:35", "remaining_time": "0:14:18", "throughput": 5736.48, "total_tokens": 17412872} {"current_steps": 26450, "total_steps": 33920, "loss": 0.2604, "lr": 1.4063763171737766e-06, "epoch": 15.595518867924529, "percentage": 77.98, "elapsed_time": "0:50:36", "remaining_time": "0:14:17", "throughput": 5736.59, "total_tokens": 17416552} {"current_steps": 26455, "total_steps": 33920, "loss": 0.3157, "lr": 1.4045879984198996e-06, "epoch": 15.598466981132075, "percentage": 77.99, "elapsed_time": "0:50:36", "remaining_time": "0:14:16", "throughput": 5736.7, "total_tokens": 17420360} {"current_steps": 26460, "total_steps": 33920, "loss": 0.3493, "lr": 1.4028006315668457e-06, "epoch": 15.601415094339622, "percentage": 78.01, "elapsed_time": "0:50:37", "remaining_time": "0:14:16", "throughput": 5736.82, "total_tokens": 17424520} {"current_steps": 26465, "total_steps": 33920, "loss": 0.3189, "lr": 1.4010142170878261e-06, "epoch": 15.60436320754717, "percentage": 78.02, "elapsed_time": "0:50:37", "remaining_time": "0:14:15", "throughput": 5736.82, "total_tokens": 17427656} {"current_steps": 26470, "total_steps": 33920, "loss": 0.2774, "lr": 1.3992287554558042e-06, "epoch": 15.607311320754716, "percentage": 78.04, "elapsed_time": "0:50:38", "remaining_time": "0:14:15", "throughput": 5736.94, "total_tokens": 17431304} {"current_steps": 26475, "total_steps": 33920, "loss": 0.2503, "lr": 1.3974442471434885e-06, "epoch": 15.610259433962264, "percentage": 78.05, "elapsed_time": "0:50:39", "remaining_time": "0:14:14", "throughput": 5736.93, "total_tokens": 17434824} {"current_steps": 26480, "total_steps": 33920, "loss": 0.3014, "lr": 1.395660692623334e-06, "epoch": 15.61320754716981, "percentage": 78.07, "elapsed_time": "0:50:39", "remaining_time": "0:14:14", "throughput": 5736.92, "total_tokens": 17437928} {"current_steps": 26485, "total_steps": 33920, "loss": 0.2935, "lr": 1.3938780923675454e-06, "epoch": 15.616155660377359, "percentage": 78.08, "elapsed_time": "0:50:40", "remaining_time": "0:14:13", "throughput": 5736.79, "total_tokens": 17440616} {"current_steps": 26490, "total_steps": 33920, "loss": 0.3573, "lr": 1.3920964468480718e-06, "epoch": 15.619103773584905, "percentage": 78.1, "elapsed_time": "0:50:40", "remaining_time": "0:14:12", "throughput": 5736.75, "total_tokens": 17443624} {"current_steps": 26495, "total_steps": 33920, "loss": 0.3904, "lr": 1.3903157565366143e-06, "epoch": 15.622051886792454, "percentage": 78.11, "elapsed_time": "0:50:41", "remaining_time": "0:14:12", "throughput": 5736.81, "total_tokens": 17447208} {"current_steps": 26500, "total_steps": 33920, "loss": 0.3225, "lr": 1.3885360219046172e-06, "epoch": 15.625, "percentage": 78.12, "elapsed_time": "0:50:41", "remaining_time": "0:14:11", "throughput": 5736.75, "total_tokens": 17450120} {"current_steps": 26505, "total_steps": 33920, "loss": 0.357, "lr": 1.386757243423273e-06, "epoch": 15.627948113207546, "percentage": 78.14, "elapsed_time": "0:50:42", "remaining_time": "0:14:11", "throughput": 5736.68, "total_tokens": 17453128} {"current_steps": 26510, "total_steps": 33920, "loss": 0.3195, "lr": 1.384979421563521e-06, "epoch": 15.630896226415095, "percentage": 78.15, "elapsed_time": "0:50:42", "remaining_time": "0:14:10", "throughput": 5736.74, "total_tokens": 17456488} {"current_steps": 26515, "total_steps": 33920, "loss": 0.2787, "lr": 1.3832025567960465e-06, "epoch": 15.633844339622641, "percentage": 78.17, "elapsed_time": "0:50:43", "remaining_time": "0:14:09", "throughput": 5736.92, "total_tokens": 17460424} {"current_steps": 26520, "total_steps": 33920, "loss": 0.2895, "lr": 1.3814266495912815e-06, "epoch": 15.63679245283019, "percentage": 78.18, "elapsed_time": "0:50:44", "remaining_time": "0:14:09", "throughput": 5736.97, "total_tokens": 17464104} {"current_steps": 26525, "total_steps": 33920, "loss": 0.3036, "lr": 1.3796517004194078e-06, "epoch": 15.639740566037736, "percentage": 78.2, "elapsed_time": "0:50:44", "remaining_time": "0:14:08", "throughput": 5737.0, "total_tokens": 17467464} {"current_steps": 26530, "total_steps": 33920, "loss": 0.2344, "lr": 1.3778777097503476e-06, "epoch": 15.642688679245284, "percentage": 78.21, "elapsed_time": "0:50:45", "remaining_time": "0:14:08", "throughput": 5736.85, "total_tokens": 17470184} {"current_steps": 26535, "total_steps": 33920, "loss": 0.3325, "lr": 1.3761046780537757e-06, "epoch": 15.64563679245283, "percentage": 78.23, "elapsed_time": "0:50:45", "remaining_time": "0:14:07", "throughput": 5736.74, "total_tokens": 17473480} {"current_steps": 26540, "total_steps": 33920, "loss": 0.3329, "lr": 1.3743326057991086e-06, "epoch": 15.648584905660378, "percentage": 78.24, "elapsed_time": "0:50:46", "remaining_time": "0:14:07", "throughput": 5736.68, "total_tokens": 17476520} {"current_steps": 26545, "total_steps": 33920, "loss": 0.4122, "lr": 1.3725614934555093e-06, "epoch": 15.651533018867925, "percentage": 78.26, "elapsed_time": "0:50:47", "remaining_time": "0:14:06", "throughput": 5736.75, "total_tokens": 17480232} {"current_steps": 26550, "total_steps": 33920, "loss": 0.3684, "lr": 1.3707913414918882e-06, "epoch": 15.654481132075471, "percentage": 78.27, "elapsed_time": "0:50:47", "remaining_time": "0:14:05", "throughput": 5736.73, "total_tokens": 17483208} {"current_steps": 26555, "total_steps": 33920, "loss": 0.5072, "lr": 1.3690221503768996e-06, "epoch": 15.65742924528302, "percentage": 78.29, "elapsed_time": "0:50:48", "remaining_time": "0:14:05", "throughput": 5736.78, "total_tokens": 17486888} {"current_steps": 26560, "total_steps": 33920, "loss": 0.2706, "lr": 1.3672539205789465e-06, "epoch": 15.660377358490566, "percentage": 78.3, "elapsed_time": "0:50:48", "remaining_time": "0:14:04", "throughput": 5736.87, "total_tokens": 17491048} {"current_steps": 26565, "total_steps": 33920, "loss": 0.3145, "lr": 1.3654866525661737e-06, "epoch": 15.663325471698114, "percentage": 78.32, "elapsed_time": "0:50:49", "remaining_time": "0:14:04", "throughput": 5736.84, "total_tokens": 17494120} {"current_steps": 26570, "total_steps": 33920, "loss": 0.3022, "lr": 1.3637203468064741e-06, "epoch": 15.66627358490566, "percentage": 78.33, "elapsed_time": "0:50:50", "remaining_time": "0:14:03", "throughput": 5736.68, "total_tokens": 17496936} {"current_steps": 26575, "total_steps": 33920, "loss": 0.2437, "lr": 1.3619550037674838e-06, "epoch": 15.669221698113208, "percentage": 78.35, "elapsed_time": "0:50:50", "remaining_time": "0:14:03", "throughput": 5736.85, "total_tokens": 17501288} {"current_steps": 26580, "total_steps": 33920, "loss": 0.3058, "lr": 1.3601906239165857e-06, "epoch": 15.672169811320755, "percentage": 78.36, "elapsed_time": "0:50:51", "remaining_time": "0:14:02", "throughput": 5736.94, "total_tokens": 17505064} {"current_steps": 26585, "total_steps": 33920, "loss": 0.281, "lr": 1.3584272077209048e-06, "epoch": 15.675117924528301, "percentage": 78.38, "elapsed_time": "0:50:51", "remaining_time": "0:14:02", "throughput": 5736.94, "total_tokens": 17508264} {"current_steps": 26590, "total_steps": 33920, "loss": 0.4189, "lr": 1.3566647556473168e-06, "epoch": 15.67806603773585, "percentage": 78.39, "elapsed_time": "0:50:52", "remaining_time": "0:14:01", "throughput": 5736.94, "total_tokens": 17511240} {"current_steps": 26595, "total_steps": 33920, "loss": 0.2596, "lr": 1.3549032681624363e-06, "epoch": 15.681014150943396, "percentage": 78.41, "elapsed_time": "0:50:52", "remaining_time": "0:14:00", "throughput": 5736.69, "total_tokens": 17513512} {"current_steps": 26600, "total_steps": 33920, "loss": 0.222, "lr": 1.3531427457326252e-06, "epoch": 15.683962264150944, "percentage": 78.42, "elapsed_time": "0:50:53", "remaining_time": "0:14:00", "throughput": 5736.79, "total_tokens": 17517320} {"current_steps": 26605, "total_steps": 33920, "loss": 0.4369, "lr": 1.3513831888239893e-06, "epoch": 15.68691037735849, "percentage": 78.43, "elapsed_time": "0:50:54", "remaining_time": "0:13:59", "throughput": 5736.97, "total_tokens": 17521160} {"current_steps": 26610, "total_steps": 33920, "loss": 0.3864, "lr": 1.3496245979023786e-06, "epoch": 15.689858490566039, "percentage": 78.45, "elapsed_time": "0:50:54", "remaining_time": "0:13:59", "throughput": 5736.87, "total_tokens": 17523880} {"current_steps": 26615, "total_steps": 33920, "loss": 0.3075, "lr": 1.3478669734333865e-06, "epoch": 15.692806603773585, "percentage": 78.46, "elapsed_time": "0:50:55", "remaining_time": "0:13:58", "throughput": 5736.85, "total_tokens": 17526920} {"current_steps": 26620, "total_steps": 33920, "loss": 0.3274, "lr": 1.3461103158823546e-06, "epoch": 15.695754716981131, "percentage": 78.48, "elapsed_time": "0:50:55", "remaining_time": "0:13:57", "throughput": 5736.85, "total_tokens": 17529992} {"current_steps": 26625, "total_steps": 33920, "loss": 0.3276, "lr": 1.3443546257143624e-06, "epoch": 15.69870283018868, "percentage": 78.49, "elapsed_time": "0:50:56", "remaining_time": "0:13:57", "throughput": 5736.67, "total_tokens": 17532648} {"current_steps": 26630, "total_steps": 33920, "loss": 0.4221, "lr": 1.3425999033942395e-06, "epoch": 15.701650943396226, "percentage": 78.51, "elapsed_time": "0:50:56", "remaining_time": "0:13:56", "throughput": 5736.68, "total_tokens": 17535784} {"current_steps": 26635, "total_steps": 33920, "loss": 0.2913, "lr": 1.3408461493865549e-06, "epoch": 15.704599056603774, "percentage": 78.52, "elapsed_time": "0:50:57", "remaining_time": "0:13:56", "throughput": 5736.56, "total_tokens": 17538632} {"current_steps": 26640, "total_steps": 33920, "loss": 0.4294, "lr": 1.339093364155622e-06, "epoch": 15.70754716981132, "percentage": 78.54, "elapsed_time": "0:50:57", "remaining_time": "0:13:55", "throughput": 5736.4, "total_tokens": 17541384} {"current_steps": 26645, "total_steps": 33920, "loss": 0.3212, "lr": 1.3373415481654988e-06, "epoch": 15.710495283018869, "percentage": 78.55, "elapsed_time": "0:50:58", "remaining_time": "0:13:55", "throughput": 5736.19, "total_tokens": 17544200} {"current_steps": 26650, "total_steps": 33920, "loss": 0.3172, "lr": 1.335590701879984e-06, "epoch": 15.713443396226415, "percentage": 78.57, "elapsed_time": "0:50:59", "remaining_time": "0:13:54", "throughput": 5736.18, "total_tokens": 17547240} {"current_steps": 26655, "total_steps": 33920, "loss": 0.2738, "lr": 1.3338408257626257e-06, "epoch": 15.716391509433961, "percentage": 78.58, "elapsed_time": "0:50:59", "remaining_time": "0:13:53", "throughput": 5736.09, "total_tokens": 17549992} {"current_steps": 26660, "total_steps": 33920, "loss": 0.2783, "lr": 1.3320919202767086e-06, "epoch": 15.71933962264151, "percentage": 78.6, "elapsed_time": "0:51:00", "remaining_time": "0:13:53", "throughput": 5736.13, "total_tokens": 17553384} {"current_steps": 26665, "total_steps": 33920, "loss": 0.2985, "lr": 1.3303439858852636e-06, "epoch": 15.722287735849056, "percentage": 78.61, "elapsed_time": "0:51:00", "remaining_time": "0:13:52", "throughput": 5736.04, "total_tokens": 17556168} {"current_steps": 26670, "total_steps": 33920, "loss": 0.3536, "lr": 1.3285970230510636e-06, "epoch": 15.725235849056604, "percentage": 78.63, "elapsed_time": "0:51:01", "remaining_time": "0:13:52", "throughput": 5736.17, "total_tokens": 17560168} {"current_steps": 26675, "total_steps": 33920, "loss": 0.3398, "lr": 1.3268510322366246e-06, "epoch": 15.72818396226415, "percentage": 78.64, "elapsed_time": "0:51:01", "remaining_time": "0:13:51", "throughput": 5736.11, "total_tokens": 17562984} {"current_steps": 26680, "total_steps": 33920, "loss": 0.2983, "lr": 1.3251060139042038e-06, "epoch": 15.731132075471699, "percentage": 78.66, "elapsed_time": "0:51:02", "remaining_time": "0:13:51", "throughput": 5736.07, "total_tokens": 17565928} {"current_steps": 26685, "total_steps": 33920, "loss": 0.2653, "lr": 1.3233619685158056e-06, "epoch": 15.734080188679245, "percentage": 78.67, "elapsed_time": "0:51:02", "remaining_time": "0:13:50", "throughput": 5736.14, "total_tokens": 17569480} {"current_steps": 26690, "total_steps": 33920, "loss": 0.3667, "lr": 1.3216188965331712e-06, "epoch": 15.737028301886792, "percentage": 78.69, "elapsed_time": "0:51:03", "remaining_time": "0:13:49", "throughput": 5736.0, "total_tokens": 17572424} {"current_steps": 26695, "total_steps": 33920, "loss": 0.1821, "lr": 1.3198767984177869e-06, "epoch": 15.73997641509434, "percentage": 78.7, "elapsed_time": "0:51:04", "remaining_time": "0:13:49", "throughput": 5735.9, "total_tokens": 17575176} {"current_steps": 26700, "total_steps": 33920, "loss": 0.2795, "lr": 1.3181356746308805e-06, "epoch": 15.742924528301886, "percentage": 78.71, "elapsed_time": "0:51:04", "remaining_time": "0:13:48", "throughput": 5735.78, "total_tokens": 17578024} {"current_steps": 26705, "total_steps": 33920, "loss": 0.2513, "lr": 1.3163955256334226e-06, "epoch": 15.745872641509434, "percentage": 78.73, "elapsed_time": "0:51:05", "remaining_time": "0:13:48", "throughput": 5735.79, "total_tokens": 17581384} {"current_steps": 26710, "total_steps": 33920, "loss": 0.3124, "lr": 1.3146563518861227e-06, "epoch": 15.74882075471698, "percentage": 78.74, "elapsed_time": "0:51:05", "remaining_time": "0:13:47", "throughput": 5735.92, "total_tokens": 17585128} {"current_steps": 26715, "total_steps": 33920, "loss": 0.3575, "lr": 1.3129181538494384e-06, "epoch": 15.751768867924529, "percentage": 78.76, "elapsed_time": "0:51:06", "remaining_time": "0:13:46", "throughput": 5735.89, "total_tokens": 17588392} {"current_steps": 26720, "total_steps": 33920, "loss": 0.566, "lr": 1.3111809319835622e-06, "epoch": 15.754716981132075, "percentage": 78.77, "elapsed_time": "0:51:06", "remaining_time": "0:13:46", "throughput": 5735.72, "total_tokens": 17591016} {"current_steps": 26725, "total_steps": 33920, "loss": 0.2884, "lr": 1.3094446867484335e-06, "epoch": 15.757665094339622, "percentage": 78.79, "elapsed_time": "0:51:07", "remaining_time": "0:13:45", "throughput": 5735.84, "total_tokens": 17594536} {"current_steps": 26730, "total_steps": 33920, "loss": 0.2849, "lr": 1.3077094186037287e-06, "epoch": 15.76061320754717, "percentage": 78.8, "elapsed_time": "0:51:08", "remaining_time": "0:13:45", "throughput": 5735.61, "total_tokens": 17597096} {"current_steps": 26735, "total_steps": 33920, "loss": 0.2928, "lr": 1.305975128008869e-06, "epoch": 15.763561320754716, "percentage": 78.82, "elapsed_time": "0:51:08", "remaining_time": "0:13:44", "throughput": 5735.3, "total_tokens": 17599400} {"current_steps": 26740, "total_steps": 33920, "loss": 0.2106, "lr": 1.304241815423014e-06, "epoch": 15.766509433962264, "percentage": 78.83, "elapsed_time": "0:51:09", "remaining_time": "0:13:44", "throughput": 5735.19, "total_tokens": 17602472} {"current_steps": 26745, "total_steps": 33920, "loss": 0.3341, "lr": 1.3025094813050655e-06, "epoch": 15.76945754716981, "percentage": 78.85, "elapsed_time": "0:51:09", "remaining_time": "0:13:43", "throughput": 5735.19, "total_tokens": 17605576} {"current_steps": 26750, "total_steps": 33920, "loss": 0.3119, "lr": 1.3007781261136675e-06, "epoch": 15.772405660377359, "percentage": 78.86, "elapsed_time": "0:51:10", "remaining_time": "0:13:43", "throughput": 5735.42, "total_tokens": 17612648} {"current_steps": 26755, "total_steps": 33920, "loss": 0.337, "lr": 1.299047750307204e-06, "epoch": 15.775353773584905, "percentage": 78.88, "elapsed_time": "0:51:11", "remaining_time": "0:13:42", "throughput": 5735.36, "total_tokens": 17615624} {"current_steps": 26760, "total_steps": 33920, "loss": 0.4219, "lr": 1.297318354343799e-06, "epoch": 15.778301886792454, "percentage": 78.89, "elapsed_time": "0:51:11", "remaining_time": "0:13:41", "throughput": 5735.27, "total_tokens": 17618472} {"current_steps": 26765, "total_steps": 33920, "loss": 0.3267, "lr": 1.295589938681317e-06, "epoch": 15.78125, "percentage": 78.91, "elapsed_time": "0:51:12", "remaining_time": "0:13:41", "throughput": 5735.27, "total_tokens": 17622248} {"current_steps": 26770, "total_steps": 33920, "loss": 0.3135, "lr": 1.2938625037773628e-06, "epoch": 15.784198113207546, "percentage": 78.92, "elapsed_time": "0:51:13", "remaining_time": "0:13:40", "throughput": 5735.25, "total_tokens": 17625576} {"current_steps": 26775, "total_steps": 33920, "loss": 0.425, "lr": 1.2921360500892843e-06, "epoch": 15.787146226415095, "percentage": 78.94, "elapsed_time": "0:51:13", "remaining_time": "0:13:40", "throughput": 5735.14, "total_tokens": 17628424} {"current_steps": 26780, "total_steps": 33920, "loss": 0.2519, "lr": 1.290410578074167e-06, "epoch": 15.790094339622641, "percentage": 78.95, "elapsed_time": "0:51:14", "remaining_time": "0:13:39", "throughput": 5735.37, "total_tokens": 17634600} {"current_steps": 26785, "total_steps": 33920, "loss": 0.3263, "lr": 1.2886860881888362e-06, "epoch": 15.79304245283019, "percentage": 78.97, "elapsed_time": "0:51:15", "remaining_time": "0:13:39", "throughput": 5735.25, "total_tokens": 17637384} {"current_steps": 26790, "total_steps": 33920, "loss": 0.3675, "lr": 1.2869625808898584e-06, "epoch": 15.795990566037736, "percentage": 78.98, "elapsed_time": "0:51:16", "remaining_time": "0:13:38", "throughput": 5735.56, "total_tokens": 17644712} {"current_steps": 26795, "total_steps": 33920, "loss": 0.2799, "lr": 1.2852400566335398e-06, "epoch": 15.798938679245284, "percentage": 78.99, "elapsed_time": "0:51:16", "remaining_time": "0:13:38", "throughput": 5735.44, "total_tokens": 17647304} {"current_steps": 26800, "total_steps": 33920, "loss": 0.2208, "lr": 1.2835185158759244e-06, "epoch": 15.80188679245283, "percentage": 79.01, "elapsed_time": "0:51:17", "remaining_time": "0:13:37", "throughput": 5735.38, "total_tokens": 17650536} {"current_steps": 26805, "total_steps": 33920, "loss": 0.3264, "lr": 1.2817979590728009e-06, "epoch": 15.804834905660378, "percentage": 79.02, "elapsed_time": "0:51:18", "remaining_time": "0:13:37", "throughput": 5735.29, "total_tokens": 17653352} {"current_steps": 26810, "total_steps": 33920, "loss": 0.3008, "lr": 1.2800783866796918e-06, "epoch": 15.807783018867925, "percentage": 79.04, "elapsed_time": "0:51:18", "remaining_time": "0:13:36", "throughput": 5735.31, "total_tokens": 17656808} {"current_steps": 26815, "total_steps": 33920, "loss": 0.3224, "lr": 1.2783597991518604e-06, "epoch": 15.810731132075471, "percentage": 79.05, "elapsed_time": "0:51:19", "remaining_time": "0:13:35", "throughput": 5735.29, "total_tokens": 17660008} {"current_steps": 26820, "total_steps": 33920, "loss": 0.3061, "lr": 1.2766421969443131e-06, "epoch": 15.81367924528302, "percentage": 79.07, "elapsed_time": "0:51:19", "remaining_time": "0:13:35", "throughput": 5735.32, "total_tokens": 17663752} {"current_steps": 26825, "total_steps": 33920, "loss": 0.4666, "lr": 1.274925580511791e-06, "epoch": 15.816627358490566, "percentage": 79.08, "elapsed_time": "0:51:20", "remaining_time": "0:13:34", "throughput": 5735.49, "total_tokens": 17667944} {"current_steps": 26830, "total_steps": 33920, "loss": 0.2726, "lr": 1.2732099503087757e-06, "epoch": 15.819575471698114, "percentage": 79.1, "elapsed_time": "0:51:21", "remaining_time": "0:13:34", "throughput": 5735.29, "total_tokens": 17670600} {"current_steps": 26835, "total_steps": 33920, "loss": 0.2364, "lr": 1.2714953067894859e-06, "epoch": 15.82252358490566, "percentage": 79.11, "elapsed_time": "0:51:21", "remaining_time": "0:13:33", "throughput": 5735.19, "total_tokens": 17673384} {"current_steps": 26840, "total_steps": 33920, "loss": 0.3049, "lr": 1.2697816504078847e-06, "epoch": 15.825471698113208, "percentage": 79.13, "elapsed_time": "0:51:22", "remaining_time": "0:13:33", "throughput": 5735.08, "total_tokens": 17676232} {"current_steps": 26845, "total_steps": 33920, "loss": 0.3372, "lr": 1.2680689816176672e-06, "epoch": 15.828419811320755, "percentage": 79.14, "elapsed_time": "0:51:22", "remaining_time": "0:13:32", "throughput": 5735.12, "total_tokens": 17679784} {"current_steps": 26850, "total_steps": 33920, "loss": 0.2205, "lr": 1.2663573008722707e-06, "epoch": 15.831367924528301, "percentage": 79.16, "elapsed_time": "0:51:23", "remaining_time": "0:13:31", "throughput": 5735.28, "total_tokens": 17683944} {"current_steps": 26855, "total_steps": 33920, "loss": 0.4675, "lr": 1.2646466086248698e-06, "epoch": 15.83431603773585, "percentage": 79.17, "elapsed_time": "0:51:23", "remaining_time": "0:13:31", "throughput": 5735.28, "total_tokens": 17687176} {"current_steps": 26860, "total_steps": 33920, "loss": 0.269, "lr": 1.2629369053283779e-06, "epoch": 15.837264150943396, "percentage": 79.19, "elapsed_time": "0:51:24", "remaining_time": "0:13:30", "throughput": 5735.13, "total_tokens": 17689864} {"current_steps": 26865, "total_steps": 33920, "loss": 0.3144, "lr": 1.2612281914354452e-06, "epoch": 15.840212264150944, "percentage": 79.2, "elapsed_time": "0:51:25", "remaining_time": "0:13:30", "throughput": 5735.24, "total_tokens": 17693736} {"current_steps": 26870, "total_steps": 33920, "loss": 0.2838, "lr": 1.259520467398463e-06, "epoch": 15.84316037735849, "percentage": 79.22, "elapsed_time": "0:51:25", "remaining_time": "0:13:29", "throughput": 5735.16, "total_tokens": 17696616} {"current_steps": 26875, "total_steps": 33920, "loss": 0.2717, "lr": 1.2578137336695573e-06, "epoch": 15.846108490566039, "percentage": 79.23, "elapsed_time": "0:51:26", "remaining_time": "0:13:29", "throughput": 5735.01, "total_tokens": 17699272} {"current_steps": 26880, "total_steps": 33920, "loss": 0.354, "lr": 1.256107990700594e-06, "epoch": 15.849056603773585, "percentage": 79.25, "elapsed_time": "0:51:26", "remaining_time": "0:13:28", "throughput": 5735.18, "total_tokens": 17703176} {"current_steps": 26885, "total_steps": 33920, "loss": 0.2978, "lr": 1.2544032389431753e-06, "epoch": 15.852004716981131, "percentage": 79.26, "elapsed_time": "0:51:27", "remaining_time": "0:13:27", "throughput": 5735.1, "total_tokens": 17706024} {"current_steps": 26890, "total_steps": 33920, "loss": 0.3543, "lr": 1.2526994788486418e-06, "epoch": 15.85495283018868, "percentage": 79.27, "elapsed_time": "0:51:27", "remaining_time": "0:13:27", "throughput": 5735.2, "total_tokens": 17709800} {"current_steps": 26895, "total_steps": 33920, "loss": 0.3739, "lr": 1.2509967108680697e-06, "epoch": 15.857900943396226, "percentage": 79.29, "elapsed_time": "0:51:28", "remaining_time": "0:13:26", "throughput": 5735.28, "total_tokens": 17713256} {"current_steps": 26900, "total_steps": 33920, "loss": 0.3074, "lr": 1.249294935452277e-06, "epoch": 15.860849056603774, "percentage": 79.3, "elapsed_time": "0:51:29", "remaining_time": "0:13:26", "throughput": 5735.23, "total_tokens": 17716488} {"current_steps": 26905, "total_steps": 33920, "loss": 0.328, "lr": 1.247594153051815e-06, "epoch": 15.86379716981132, "percentage": 79.32, "elapsed_time": "0:51:29", "remaining_time": "0:13:25", "throughput": 5735.31, "total_tokens": 17720744} {"current_steps": 26910, "total_steps": 33920, "loss": 0.2243, "lr": 1.2458943641169718e-06, "epoch": 15.866745283018869, "percentage": 79.33, "elapsed_time": "0:51:30", "remaining_time": "0:13:25", "throughput": 5735.28, "total_tokens": 17723912} {"current_steps": 26915, "total_steps": 33920, "loss": 0.2874, "lr": 1.2441955690977758e-06, "epoch": 15.869693396226415, "percentage": 79.35, "elapsed_time": "0:51:31", "remaining_time": "0:13:24", "throughput": 5735.45, "total_tokens": 17728392} {"current_steps": 26920, "total_steps": 33920, "loss": 0.2862, "lr": 1.2424977684439898e-06, "epoch": 15.872641509433961, "percentage": 79.36, "elapsed_time": "0:51:31", "remaining_time": "0:13:23", "throughput": 5735.31, "total_tokens": 17730952} {"current_steps": 26925, "total_steps": 33920, "loss": 0.2427, "lr": 1.2408009626051137e-06, "epoch": 15.87558962264151, "percentage": 79.38, "elapsed_time": "0:51:32", "remaining_time": "0:13:23", "throughput": 5735.12, "total_tokens": 17733576} {"current_steps": 26930, "total_steps": 33920, "loss": 0.3543, "lr": 1.2391051520303826e-06, "epoch": 15.878537735849056, "percentage": 79.39, "elapsed_time": "0:51:32", "remaining_time": "0:13:22", "throughput": 5734.9, "total_tokens": 17736008} {"current_steps": 26935, "total_steps": 33920, "loss": 0.3884, "lr": 1.2374103371687723e-06, "epoch": 15.881485849056604, "percentage": 79.41, "elapsed_time": "0:51:33", "remaining_time": "0:13:22", "throughput": 5734.84, "total_tokens": 17739048} {"current_steps": 26940, "total_steps": 33920, "loss": 0.433, "lr": 1.2357165184689906e-06, "epoch": 15.88443396226415, "percentage": 79.42, "elapsed_time": "0:51:33", "remaining_time": "0:13:21", "throughput": 5734.87, "total_tokens": 17742440} {"current_steps": 26945, "total_steps": 33920, "loss": 0.378, "lr": 1.2340236963794845e-06, "epoch": 15.887382075471699, "percentage": 79.44, "elapsed_time": "0:51:34", "remaining_time": "0:13:20", "throughput": 5734.71, "total_tokens": 17744904} {"current_steps": 26950, "total_steps": 33920, "loss": 0.3055, "lr": 1.232331871348435e-06, "epoch": 15.890330188679245, "percentage": 79.45, "elapsed_time": "0:51:34", "remaining_time": "0:13:20", "throughput": 5734.57, "total_tokens": 17747624} {"current_steps": 26955, "total_steps": 33920, "loss": 0.3857, "lr": 1.2306410438237603e-06, "epoch": 15.893278301886792, "percentage": 79.47, "elapsed_time": "0:51:35", "remaining_time": "0:13:19", "throughput": 5734.64, "total_tokens": 17751560} {"current_steps": 26960, "total_steps": 33920, "loss": 0.572, "lr": 1.228951214253113e-06, "epoch": 15.89622641509434, "percentage": 79.48, "elapsed_time": "0:51:36", "remaining_time": "0:13:19", "throughput": 5734.5, "total_tokens": 17754088} {"current_steps": 26965, "total_steps": 33920, "loss": 0.3336, "lr": 1.2272623830838854e-06, "epoch": 15.899174528301886, "percentage": 79.5, "elapsed_time": "0:51:36", "remaining_time": "0:13:18", "throughput": 5734.46, "total_tokens": 17757224} {"current_steps": 26970, "total_steps": 33920, "loss": 0.3798, "lr": 1.2255745507632016e-06, "epoch": 15.902122641509434, "percentage": 79.51, "elapsed_time": "0:51:37", "remaining_time": "0:13:18", "throughput": 5734.44, "total_tokens": 17760520} {"current_steps": 26975, "total_steps": 33920, "loss": 0.3172, "lr": 1.223887717737922e-06, "epoch": 15.90507075471698, "percentage": 79.53, "elapsed_time": "0:51:37", "remaining_time": "0:13:17", "throughput": 5734.35, "total_tokens": 17763368} {"current_steps": 26980, "total_steps": 33920, "loss": 0.2383, "lr": 1.2222018844546434e-06, "epoch": 15.908018867924529, "percentage": 79.54, "elapsed_time": "0:51:38", "remaining_time": "0:13:16", "throughput": 5734.24, "total_tokens": 17766184} {"current_steps": 26985, "total_steps": 33920, "loss": 0.3076, "lr": 1.2205170513596975e-06, "epoch": 15.910966981132075, "percentage": 79.55, "elapsed_time": "0:51:38", "remaining_time": "0:13:16", "throughput": 5734.23, "total_tokens": 17769256} {"current_steps": 26990, "total_steps": 33920, "loss": 0.3074, "lr": 1.2188332188991493e-06, "epoch": 15.913915094339622, "percentage": 79.57, "elapsed_time": "0:51:39", "remaining_time": "0:13:15", "throughput": 5734.19, "total_tokens": 17772744} {"current_steps": 26995, "total_steps": 33920, "loss": 0.3461, "lr": 1.217150387518804e-06, "epoch": 15.91686320754717, "percentage": 79.58, "elapsed_time": "0:51:40", "remaining_time": "0:13:15", "throughput": 5734.22, "total_tokens": 17776264} {"current_steps": 27000, "total_steps": 33920, "loss": 0.2916, "lr": 1.2154685576641967e-06, "epoch": 15.919811320754716, "percentage": 79.6, "elapsed_time": "0:51:40", "remaining_time": "0:13:14", "throughput": 5734.16, "total_tokens": 17779464} {"current_steps": 27005, "total_steps": 33920, "loss": 0.2223, "lr": 1.2137877297805972e-06, "epoch": 15.922759433962264, "percentage": 79.61, "elapsed_time": "0:51:41", "remaining_time": "0:13:14", "throughput": 5734.22, "total_tokens": 17782664} {"current_steps": 27010, "total_steps": 33920, "loss": 0.2116, "lr": 1.2121079043130162e-06, "epoch": 15.92570754716981, "percentage": 79.63, "elapsed_time": "0:51:41", "remaining_time": "0:13:13", "throughput": 5734.07, "total_tokens": 17785320} {"current_steps": 27015, "total_steps": 33920, "loss": 0.3258, "lr": 1.210429081706192e-06, "epoch": 15.928655660377359, "percentage": 79.64, "elapsed_time": "0:51:42", "remaining_time": "0:13:12", "throughput": 5734.06, "total_tokens": 17788648} {"current_steps": 27020, "total_steps": 33920, "loss": 0.3654, "lr": 1.2087512624046005e-06, "epoch": 15.931603773584905, "percentage": 79.66, "elapsed_time": "0:51:42", "remaining_time": "0:13:12", "throughput": 5734.16, "total_tokens": 17792456} {"current_steps": 27025, "total_steps": 33920, "loss": 0.2825, "lr": 1.2070744468524503e-06, "epoch": 15.934551886792454, "percentage": 79.67, "elapsed_time": "0:51:43", "remaining_time": "0:13:11", "throughput": 5734.12, "total_tokens": 17795400} {"current_steps": 27030, "total_steps": 33920, "loss": 0.4297, "lr": 1.2053986354936887e-06, "epoch": 15.9375, "percentage": 79.69, "elapsed_time": "0:51:44", "remaining_time": "0:13:11", "throughput": 5734.23, "total_tokens": 17799176} {"current_steps": 27035, "total_steps": 33920, "loss": 0.3196, "lr": 1.2037238287719916e-06, "epoch": 15.940448113207546, "percentage": 79.7, "elapsed_time": "0:51:44", "remaining_time": "0:13:10", "throughput": 5734.24, "total_tokens": 17802664} {"current_steps": 27040, "total_steps": 33920, "loss": 0.2412, "lr": 1.2020500271307721e-06, "epoch": 15.943396226415095, "percentage": 79.72, "elapsed_time": "0:51:45", "remaining_time": "0:13:10", "throughput": 5734.21, "total_tokens": 17805576} {"current_steps": 27045, "total_steps": 33920, "loss": 0.2979, "lr": 1.200377231013176e-06, "epoch": 15.946344339622641, "percentage": 79.73, "elapsed_time": "0:51:45", "remaining_time": "0:13:09", "throughput": 5734.27, "total_tokens": 17808904} {"current_steps": 27050, "total_steps": 33920, "loss": 0.2812, "lr": 1.1987054408620825e-06, "epoch": 15.94929245283019, "percentage": 79.75, "elapsed_time": "0:51:46", "remaining_time": "0:13:08", "throughput": 5734.24, "total_tokens": 17812008} {"current_steps": 27055, "total_steps": 33920, "loss": 0.2554, "lr": 1.197034657120107e-06, "epoch": 15.952240566037736, "percentage": 79.76, "elapsed_time": "0:51:46", "remaining_time": "0:13:08", "throughput": 5734.35, "total_tokens": 17815688} {"current_steps": 27060, "total_steps": 33920, "loss": 0.2937, "lr": 1.1953648802295964e-06, "epoch": 15.955188679245284, "percentage": 79.78, "elapsed_time": "0:51:47", "remaining_time": "0:13:07", "throughput": 5734.37, "total_tokens": 17819176} {"current_steps": 27065, "total_steps": 33920, "loss": 0.369, "lr": 1.1936961106326307e-06, "epoch": 15.95813679245283, "percentage": 79.79, "elapsed_time": "0:51:47", "remaining_time": "0:13:07", "throughput": 5734.4, "total_tokens": 17822280} {"current_steps": 27070, "total_steps": 33920, "loss": 0.3169, "lr": 1.1920283487710237e-06, "epoch": 15.961084905660378, "percentage": 79.81, "elapsed_time": "0:51:48", "remaining_time": "0:13:06", "throughput": 5734.34, "total_tokens": 17825288} {"current_steps": 27075, "total_steps": 33920, "loss": 0.2662, "lr": 1.1903615950863228e-06, "epoch": 15.964033018867925, "percentage": 79.82, "elapsed_time": "0:51:49", "remaining_time": "0:13:06", "throughput": 5734.24, "total_tokens": 17827976} {"current_steps": 27080, "total_steps": 33920, "loss": 0.3832, "lr": 1.1886958500198076e-06, "epoch": 15.966981132075471, "percentage": 79.83, "elapsed_time": "0:51:49", "remaining_time": "0:13:05", "throughput": 5734.23, "total_tokens": 17831016} {"current_steps": 27085, "total_steps": 33920, "loss": 0.254, "lr": 1.1870311140124923e-06, "epoch": 15.96992924528302, "percentage": 79.85, "elapsed_time": "0:51:50", "remaining_time": "0:13:04", "throughput": 5734.16, "total_tokens": 17833896} {"current_steps": 27090, "total_steps": 33920, "loss": 0.2919, "lr": 1.185367387505123e-06, "epoch": 15.972877358490566, "percentage": 79.86, "elapsed_time": "0:51:50", "remaining_time": "0:13:04", "throughput": 5734.06, "total_tokens": 17836616} {"current_steps": 27095, "total_steps": 33920, "loss": 0.3475, "lr": 1.1837046709381783e-06, "epoch": 15.975825471698114, "percentage": 79.88, "elapsed_time": "0:51:51", "remaining_time": "0:13:03", "throughput": 5733.95, "total_tokens": 17839592} {"current_steps": 27100, "total_steps": 33920, "loss": 0.407, "lr": 1.1820429647518678e-06, "epoch": 15.97877358490566, "percentage": 79.89, "elapsed_time": "0:51:51", "remaining_time": "0:13:03", "throughput": 5733.91, "total_tokens": 17842440} {"current_steps": 27105, "total_steps": 33920, "loss": 0.3028, "lr": 1.1803822693861377e-06, "epoch": 15.981721698113208, "percentage": 79.91, "elapsed_time": "0:51:52", "remaining_time": "0:13:02", "throughput": 5733.97, "total_tokens": 17846344} {"current_steps": 27110, "total_steps": 33920, "loss": 0.4727, "lr": 1.1787225852806639e-06, "epoch": 15.984669811320755, "percentage": 79.92, "elapsed_time": "0:51:52", "remaining_time": "0:13:01", "throughput": 5734.01, "total_tokens": 17849768} {"current_steps": 27115, "total_steps": 33920, "loss": 0.2607, "lr": 1.177063912874853e-06, "epoch": 15.987617924528301, "percentage": 79.94, "elapsed_time": "0:51:53", "remaining_time": "0:13:01", "throughput": 5734.0, "total_tokens": 17852872} {"current_steps": 27120, "total_steps": 33920, "loss": 0.255, "lr": 1.1754062526078487e-06, "epoch": 15.99056603773585, "percentage": 79.95, "elapsed_time": "0:51:54", "remaining_time": "0:13:00", "throughput": 5733.99, "total_tokens": 17856072} {"current_steps": 27125, "total_steps": 33920, "loss": 0.376, "lr": 1.1737496049185215e-06, "epoch": 15.993514150943396, "percentage": 79.97, "elapsed_time": "0:51:54", "remaining_time": "0:13:00", "throughput": 5734.01, "total_tokens": 17859336} {"current_steps": 27130, "total_steps": 33920, "loss": 0.335, "lr": 1.172093970245477e-06, "epoch": 15.996462264150944, "percentage": 79.98, "elapsed_time": "0:51:55", "remaining_time": "0:12:59", "throughput": 5734.16, "total_tokens": 17863720} {"current_steps": 27135, "total_steps": 33920, "loss": 0.2389, "lr": 1.1704393490270516e-06, "epoch": 15.99941037735849, "percentage": 80.0, "elapsed_time": "0:51:55", "remaining_time": "0:12:59", "throughput": 5734.18, "total_tokens": 17866952} {"current_steps": 27136, "total_steps": 33920, "eval_loss": 0.5845065712928772, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "0:52:14", "remaining_time": "0:13:03", "throughput": 5699.54, "total_tokens": 17867032} {"current_steps": 27140, "total_steps": 33920, "loss": 0.3395, "lr": 1.1687857417013126e-06, "epoch": 16.00235849056604, "percentage": 80.01, "elapsed_time": "0:52:18", "remaining_time": "0:13:04", "throughput": 5693.06, "total_tokens": 17868728} {"current_steps": 27145, "total_steps": 33920, "loss": 0.3546, "lr": 1.1671331487060583e-06, "epoch": 16.005306603773583, "percentage": 80.03, "elapsed_time": "0:52:19", "remaining_time": "0:13:03", "throughput": 5693.16, "total_tokens": 17872984} {"current_steps": 27150, "total_steps": 33920, "loss": 0.4194, "lr": 1.1654815704788237e-06, "epoch": 16.00825471698113, "percentage": 80.04, "elapsed_time": "0:52:19", "remaining_time": "0:13:02", "throughput": 5693.21, "total_tokens": 17876408} {"current_steps": 27155, "total_steps": 33920, "loss": 0.2686, "lr": 1.1638310074568687e-06, "epoch": 16.01120283018868, "percentage": 80.06, "elapsed_time": "0:52:20", "remaining_time": "0:13:02", "throughput": 5693.31, "total_tokens": 17880152} {"current_steps": 27160, "total_steps": 33920, "loss": 0.289, "lr": 1.162181460077188e-06, "epoch": 16.014150943396228, "percentage": 80.07, "elapsed_time": "0:52:21", "remaining_time": "0:13:01", "throughput": 5693.31, "total_tokens": 17883384} {"current_steps": 27165, "total_steps": 33920, "loss": 0.3603, "lr": 1.1605329287765056e-06, "epoch": 16.017099056603772, "percentage": 80.09, "elapsed_time": "0:52:21", "remaining_time": "0:13:01", "throughput": 5692.99, "total_tokens": 17886072} {"current_steps": 27170, "total_steps": 33920, "loss": 0.3244, "lr": 1.1588854139912775e-06, "epoch": 16.02004716981132, "percentage": 80.1, "elapsed_time": "0:52:22", "remaining_time": "0:13:00", "throughput": 5692.91, "total_tokens": 17888920} {"current_steps": 27175, "total_steps": 33920, "loss": 0.2864, "lr": 1.1572389161576886e-06, "epoch": 16.02299528301887, "percentage": 80.11, "elapsed_time": "0:52:22", "remaining_time": "0:13:00", "throughput": 5692.82, "total_tokens": 17891768} {"current_steps": 27180, "total_steps": 33920, "loss": 0.2625, "lr": 1.15559343571166e-06, "epoch": 16.025943396226417, "percentage": 80.13, "elapsed_time": "0:52:23", "remaining_time": "0:12:59", "throughput": 5692.63, "total_tokens": 17894264} {"current_steps": 27185, "total_steps": 33920, "loss": 0.2994, "lr": 1.153948973088837e-06, "epoch": 16.02889150943396, "percentage": 80.14, "elapsed_time": "0:52:23", "remaining_time": "0:12:58", "throughput": 5692.68, "total_tokens": 17897752} {"current_steps": 27190, "total_steps": 33920, "loss": 0.2649, "lr": 1.1523055287245993e-06, "epoch": 16.03183962264151, "percentage": 80.16, "elapsed_time": "0:52:24", "remaining_time": "0:12:58", "throughput": 5692.61, "total_tokens": 17900600} {"current_steps": 27195, "total_steps": 33920, "loss": 0.4161, "lr": 1.150663103054056e-06, "epoch": 16.034787735849058, "percentage": 80.17, "elapsed_time": "0:52:25", "remaining_time": "0:12:57", "throughput": 5692.55, "total_tokens": 17903512} {"current_steps": 27200, "total_steps": 33920, "loss": 0.2875, "lr": 1.1490216965120438e-06, "epoch": 16.037735849056602, "percentage": 80.19, "elapsed_time": "0:52:25", "remaining_time": "0:12:57", "throughput": 5692.6, "total_tokens": 17906776} {"current_steps": 27205, "total_steps": 33920, "loss": 0.3543, "lr": 1.147381309533136e-06, "epoch": 16.04068396226415, "percentage": 80.2, "elapsed_time": "0:52:26", "remaining_time": "0:12:56", "throughput": 5692.54, "total_tokens": 17909656} {"current_steps": 27210, "total_steps": 33920, "loss": 0.3684, "lr": 1.1457419425516287e-06, "epoch": 16.0436320754717, "percentage": 80.22, "elapsed_time": "0:52:26", "remaining_time": "0:12:55", "throughput": 5692.4, "total_tokens": 17912344} {"current_steps": 27215, "total_steps": 33920, "loss": 0.4083, "lr": 1.1441035960015544e-06, "epoch": 16.046580188679247, "percentage": 80.23, "elapsed_time": "0:52:27", "remaining_time": "0:12:55", "throughput": 5692.52, "total_tokens": 17916024} {"current_steps": 27220, "total_steps": 33920, "loss": 0.3038, "lr": 1.1424662703166716e-06, "epoch": 16.04952830188679, "percentage": 80.25, "elapsed_time": "0:52:27", "remaining_time": "0:12:54", "throughput": 5692.51, "total_tokens": 17919032} {"current_steps": 27225, "total_steps": 33920, "loss": 0.318, "lr": 1.1408299659304684e-06, "epoch": 16.05247641509434, "percentage": 80.26, "elapsed_time": "0:52:28", "remaining_time": "0:12:54", "throughput": 5692.59, "total_tokens": 17922648} {"current_steps": 27230, "total_steps": 33920, "loss": 0.3252, "lr": 1.1391946832761642e-06, "epoch": 16.055424528301888, "percentage": 80.28, "elapsed_time": "0:52:28", "remaining_time": "0:12:53", "throughput": 5692.58, "total_tokens": 17925720} {"current_steps": 27235, "total_steps": 33920, "loss": 0.2592, "lr": 1.137560422786706e-06, "epoch": 16.058372641509433, "percentage": 80.29, "elapsed_time": "0:52:29", "remaining_time": "0:12:53", "throughput": 5692.5, "total_tokens": 17928440} {"current_steps": 27240, "total_steps": 33920, "loss": 0.3138, "lr": 1.1359271848947712e-06, "epoch": 16.06132075471698, "percentage": 80.31, "elapsed_time": "0:52:30", "remaining_time": "0:12:52", "throughput": 5692.62, "total_tokens": 17932216} {"current_steps": 27245, "total_steps": 33920, "loss": 0.2315, "lr": 1.1342949700327688e-06, "epoch": 16.06426886792453, "percentage": 80.32, "elapsed_time": "0:52:30", "remaining_time": "0:12:51", "throughput": 5692.62, "total_tokens": 17935480} {"current_steps": 27250, "total_steps": 33920, "loss": 0.2512, "lr": 1.1326637786328332e-06, "epoch": 16.067216981132077, "percentage": 80.34, "elapsed_time": "0:52:31", "remaining_time": "0:12:51", "throughput": 5692.64, "total_tokens": 17939096} {"current_steps": 27255, "total_steps": 33920, "loss": 0.3076, "lr": 1.1310336111268293e-06, "epoch": 16.07016509433962, "percentage": 80.35, "elapsed_time": "0:52:31", "remaining_time": "0:12:50", "throughput": 5692.57, "total_tokens": 17941944} {"current_steps": 27260, "total_steps": 33920, "loss": 0.3169, "lr": 1.1294044679463517e-06, "epoch": 16.07311320754717, "percentage": 80.37, "elapsed_time": "0:52:32", "remaining_time": "0:12:50", "throughput": 5692.67, "total_tokens": 17945816} {"current_steps": 27265, "total_steps": 33920, "loss": 0.3028, "lr": 1.1277763495227207e-06, "epoch": 16.076061320754718, "percentage": 80.38, "elapsed_time": "0:52:33", "remaining_time": "0:12:49", "throughput": 5692.63, "total_tokens": 17948984} {"current_steps": 27270, "total_steps": 33920, "loss": 0.2857, "lr": 1.1261492562869913e-06, "epoch": 16.079009433962263, "percentage": 80.4, "elapsed_time": "0:52:33", "remaining_time": "0:12:49", "throughput": 5692.57, "total_tokens": 17951960} {"current_steps": 27275, "total_steps": 33920, "loss": 0.2725, "lr": 1.1245231886699415e-06, "epoch": 16.08195754716981, "percentage": 80.41, "elapsed_time": "0:52:34", "remaining_time": "0:12:48", "throughput": 5692.5, "total_tokens": 17954712} {"current_steps": 27280, "total_steps": 33920, "loss": 0.4063, "lr": 1.12289814710208e-06, "epoch": 16.08490566037736, "percentage": 80.42, "elapsed_time": "0:52:34", "remaining_time": "0:12:47", "throughput": 5692.59, "total_tokens": 17958424} {"current_steps": 27285, "total_steps": 33920, "loss": 0.4015, "lr": 1.1212741320136433e-06, "epoch": 16.087853773584907, "percentage": 80.44, "elapsed_time": "0:52:35", "remaining_time": "0:12:47", "throughput": 5692.67, "total_tokens": 17961880} {"current_steps": 27290, "total_steps": 33920, "loss": 0.4246, "lr": 1.1196511438345963e-06, "epoch": 16.090801886792452, "percentage": 80.45, "elapsed_time": "0:52:35", "remaining_time": "0:12:46", "throughput": 5692.62, "total_tokens": 17964856} {"current_steps": 27295, "total_steps": 33920, "loss": 0.2875, "lr": 1.118029182994631e-06, "epoch": 16.09375, "percentage": 80.47, "elapsed_time": "0:52:36", "remaining_time": "0:12:46", "throughput": 5692.39, "total_tokens": 17967384} {"current_steps": 27300, "total_steps": 33920, "loss": 0.5074, "lr": 1.1164082499231704e-06, "epoch": 16.096698113207548, "percentage": 80.48, "elapsed_time": "0:52:36", "remaining_time": "0:12:45", "throughput": 5692.24, "total_tokens": 17970136} {"current_steps": 27305, "total_steps": 33920, "loss": 0.2891, "lr": 1.114788345049364e-06, "epoch": 16.099646226415093, "percentage": 80.5, "elapsed_time": "0:52:37", "remaining_time": "0:12:44", "throughput": 5692.29, "total_tokens": 17973784} {"current_steps": 27310, "total_steps": 33920, "loss": 0.1839, "lr": 1.1131694688020872e-06, "epoch": 16.10259433962264, "percentage": 80.51, "elapsed_time": "0:52:38", "remaining_time": "0:12:44", "throughput": 5692.15, "total_tokens": 17976568} {"current_steps": 27315, "total_steps": 33920, "loss": 0.1612, "lr": 1.1115516216099453e-06, "epoch": 16.10554245283019, "percentage": 80.53, "elapsed_time": "0:52:38", "remaining_time": "0:12:43", "throughput": 5692.04, "total_tokens": 17979224} {"current_steps": 27320, "total_steps": 33920, "loss": 0.2355, "lr": 1.1099348039012698e-06, "epoch": 16.108490566037737, "percentage": 80.54, "elapsed_time": "0:52:39", "remaining_time": "0:12:43", "throughput": 5692.26, "total_tokens": 17983800} {"current_steps": 27325, "total_steps": 33920, "loss": 0.4102, "lr": 1.1083190161041202e-06, "epoch": 16.111438679245282, "percentage": 80.56, "elapsed_time": "0:52:39", "remaining_time": "0:12:42", "throughput": 5692.28, "total_tokens": 17987128} {"current_steps": 27330, "total_steps": 33920, "loss": 0.2256, "lr": 1.1067042586462822e-06, "epoch": 16.11438679245283, "percentage": 80.57, "elapsed_time": "0:52:40", "remaining_time": "0:12:42", "throughput": 5692.28, "total_tokens": 17990776} {"current_steps": 27335, "total_steps": 33920, "loss": 0.36, "lr": 1.1050905319552718e-06, "epoch": 16.11733490566038, "percentage": 80.59, "elapsed_time": "0:52:41", "remaining_time": "0:12:41", "throughput": 5692.18, "total_tokens": 17993496} {"current_steps": 27340, "total_steps": 33920, "loss": 0.3636, "lr": 1.1034778364583293e-06, "epoch": 16.120283018867923, "percentage": 80.6, "elapsed_time": "0:52:41", "remaining_time": "0:12:40", "throughput": 5692.03, "total_tokens": 17996088} {"current_steps": 27345, "total_steps": 33920, "loss": 0.3209, "lr": 1.1018661725824231e-06, "epoch": 16.12323113207547, "percentage": 80.62, "elapsed_time": "0:52:42", "remaining_time": "0:12:40", "throughput": 5691.94, "total_tokens": 17999096} {"current_steps": 27350, "total_steps": 33920, "loss": 0.4202, "lr": 1.100255540754247e-06, "epoch": 16.12617924528302, "percentage": 80.63, "elapsed_time": "0:52:42", "remaining_time": "0:12:39", "throughput": 5691.96, "total_tokens": 18002296} {"current_steps": 27355, "total_steps": 33920, "loss": 0.3024, "lr": 1.0986459414002244e-06, "epoch": 16.129127358490567, "percentage": 80.65, "elapsed_time": "0:52:43", "remaining_time": "0:12:39", "throughput": 5692.07, "total_tokens": 18006584} {"current_steps": 27360, "total_steps": 33920, "loss": 0.3106, "lr": 1.0970373749465008e-06, "epoch": 16.132075471698112, "percentage": 80.66, "elapsed_time": "0:52:44", "remaining_time": "0:12:38", "throughput": 5691.92, "total_tokens": 18009304} {"current_steps": 27365, "total_steps": 33920, "loss": 0.5085, "lr": 1.095429841818954e-06, "epoch": 16.13502358490566, "percentage": 80.68, "elapsed_time": "0:52:44", "remaining_time": "0:12:38", "throughput": 5691.82, "total_tokens": 18012440} {"current_steps": 27370, "total_steps": 33920, "loss": 0.203, "lr": 1.093823342443185e-06, "epoch": 16.13797169811321, "percentage": 80.69, "elapsed_time": "0:52:45", "remaining_time": "0:12:37", "throughput": 5691.78, "total_tokens": 18015352} {"current_steps": 27375, "total_steps": 33920, "loss": 0.3381, "lr": 1.0922178772445203e-06, "epoch": 16.140919811320753, "percentage": 80.7, "elapsed_time": "0:52:45", "remaining_time": "0:12:36", "throughput": 5691.84, "total_tokens": 18018776} {"current_steps": 27380, "total_steps": 33920, "loss": 0.27, "lr": 1.0906134466480146e-06, "epoch": 16.1438679245283, "percentage": 80.72, "elapsed_time": "0:52:46", "remaining_time": "0:12:36", "throughput": 5691.77, "total_tokens": 18021976} {"current_steps": 27385, "total_steps": 33920, "loss": 0.2429, "lr": 1.0890100510784473e-06, "epoch": 16.14681603773585, "percentage": 80.73, "elapsed_time": "0:52:46", "remaining_time": "0:12:35", "throughput": 5691.76, "total_tokens": 18025432} {"current_steps": 27390, "total_steps": 33920, "loss": 0.3018, "lr": 1.0874076909603227e-06, "epoch": 16.149764150943398, "percentage": 80.75, "elapsed_time": "0:52:47", "remaining_time": "0:12:35", "throughput": 5691.9, "total_tokens": 18029432} {"current_steps": 27395, "total_steps": 33920, "loss": 0.2821, "lr": 1.0858063667178747e-06, "epoch": 16.152712264150942, "percentage": 80.76, "elapsed_time": "0:52:48", "remaining_time": "0:12:34", "throughput": 5691.92, "total_tokens": 18032696} {"current_steps": 27400, "total_steps": 33920, "loss": 0.3381, "lr": 1.0842060787750614e-06, "epoch": 16.15566037735849, "percentage": 80.78, "elapsed_time": "0:52:48", "remaining_time": "0:12:34", "throughput": 5691.9, "total_tokens": 18035800} {"current_steps": 27405, "total_steps": 33920, "loss": 0.2692, "lr": 1.0826068275555652e-06, "epoch": 16.15860849056604, "percentage": 80.79, "elapsed_time": "0:52:49", "remaining_time": "0:12:33", "throughput": 5691.93, "total_tokens": 18038904} {"current_steps": 27410, "total_steps": 33920, "loss": 0.3032, "lr": 1.081008613482794e-06, "epoch": 16.161556603773583, "percentage": 80.81, "elapsed_time": "0:52:49", "remaining_time": "0:12:32", "throughput": 5692.01, "total_tokens": 18042488} {"current_steps": 27415, "total_steps": 33920, "loss": 0.2949, "lr": 1.079411436979883e-06, "epoch": 16.16450471698113, "percentage": 80.82, "elapsed_time": "0:52:50", "remaining_time": "0:12:32", "throughput": 5692.1, "total_tokens": 18046136} {"current_steps": 27420, "total_steps": 33920, "loss": 0.3068, "lr": 1.0778152984696905e-06, "epoch": 16.16745283018868, "percentage": 80.84, "elapsed_time": "0:52:50", "remaining_time": "0:12:31", "throughput": 5692.09, "total_tokens": 18049144} {"current_steps": 27425, "total_steps": 33920, "loss": 0.3206, "lr": 1.0762201983747993e-06, "epoch": 16.170400943396228, "percentage": 80.85, "elapsed_time": "0:52:51", "remaining_time": "0:12:31", "throughput": 5692.14, "total_tokens": 18052760} {"current_steps": 27430, "total_steps": 33920, "loss": 0.2272, "lr": 1.0746261371175238e-06, "epoch": 16.173349056603772, "percentage": 80.87, "elapsed_time": "0:52:52", "remaining_time": "0:12:30", "throughput": 5692.02, "total_tokens": 18055576} {"current_steps": 27435, "total_steps": 33920, "loss": 0.3295, "lr": 1.0730331151198953e-06, "epoch": 16.17629716981132, "percentage": 80.88, "elapsed_time": "0:52:52", "remaining_time": "0:12:29", "throughput": 5692.11, "total_tokens": 18058968} {"current_steps": 27440, "total_steps": 33920, "loss": 0.2993, "lr": 1.0714411328036733e-06, "epoch": 16.17924528301887, "percentage": 80.9, "elapsed_time": "0:52:53", "remaining_time": "0:12:29", "throughput": 5692.06, "total_tokens": 18061944} {"current_steps": 27445, "total_steps": 33920, "loss": 0.2261, "lr": 1.0698501905903435e-06, "epoch": 16.182193396226417, "percentage": 80.91, "elapsed_time": "0:52:53", "remaining_time": "0:12:28", "throughput": 5692.15, "total_tokens": 18065752} {"current_steps": 27450, "total_steps": 33920, "loss": 0.3262, "lr": 1.0682602889011134e-06, "epoch": 16.18514150943396, "percentage": 80.93, "elapsed_time": "0:52:54", "remaining_time": "0:12:28", "throughput": 5692.04, "total_tokens": 18068376} {"current_steps": 27455, "total_steps": 33920, "loss": 0.1967, "lr": 1.0666714281569152e-06, "epoch": 16.18808962264151, "percentage": 80.94, "elapsed_time": "0:52:55", "remaining_time": "0:12:27", "throughput": 5692.28, "total_tokens": 18073624} {"current_steps": 27460, "total_steps": 33920, "loss": 0.332, "lr": 1.0650836087784095e-06, "epoch": 16.191037735849058, "percentage": 80.96, "elapsed_time": "0:52:55", "remaining_time": "0:12:27", "throughput": 5692.43, "total_tokens": 18077560} {"current_steps": 27465, "total_steps": 33920, "loss": 0.3759, "lr": 1.0634968311859768e-06, "epoch": 16.193985849056602, "percentage": 80.97, "elapsed_time": "0:52:56", "remaining_time": "0:12:26", "throughput": 5692.58, "total_tokens": 18081400} {"current_steps": 27470, "total_steps": 33920, "loss": 0.3733, "lr": 1.0619110957997237e-06, "epoch": 16.19693396226415, "percentage": 80.98, "elapsed_time": "0:52:56", "remaining_time": "0:12:25", "throughput": 5692.61, "total_tokens": 18084952} {"current_steps": 27475, "total_steps": 33920, "loss": 0.2352, "lr": 1.06032640303948e-06, "epoch": 16.1998820754717, "percentage": 81.0, "elapsed_time": "0:52:57", "remaining_time": "0:12:25", "throughput": 5692.76, "total_tokens": 18088696} {"current_steps": 27480, "total_steps": 33920, "loss": 0.2857, "lr": 1.0587427533248002e-06, "epoch": 16.202830188679247, "percentage": 81.01, "elapsed_time": "0:52:58", "remaining_time": "0:12:24", "throughput": 5692.83, "total_tokens": 18092376} {"current_steps": 27485, "total_steps": 33920, "loss": 0.2259, "lr": 1.057160147074961e-06, "epoch": 16.20577830188679, "percentage": 81.03, "elapsed_time": "0:52:58", "remaining_time": "0:12:24", "throughput": 5692.83, "total_tokens": 18095416} {"current_steps": 27490, "total_steps": 33920, "loss": 0.2687, "lr": 1.0555785847089657e-06, "epoch": 16.20872641509434, "percentage": 81.04, "elapsed_time": "0:52:59", "remaining_time": "0:12:23", "throughput": 5692.83, "total_tokens": 18099032} {"current_steps": 27495, "total_steps": 33920, "loss": 0.2523, "lr": 1.0539980666455407e-06, "epoch": 16.211674528301888, "percentage": 81.06, "elapsed_time": "0:52:59", "remaining_time": "0:12:23", "throughput": 5692.84, "total_tokens": 18102104} {"current_steps": 27500, "total_steps": 33920, "loss": 0.284, "lr": 1.052418593303134e-06, "epoch": 16.214622641509433, "percentage": 81.07, "elapsed_time": "0:53:00", "remaining_time": "0:12:22", "throughput": 5693.1, "total_tokens": 18106712} {"current_steps": 27505, "total_steps": 33920, "loss": 0.2114, "lr": 1.0508401650999178e-06, "epoch": 16.21757075471698, "percentage": 81.09, "elapsed_time": "0:53:01", "remaining_time": "0:12:21", "throughput": 5693.07, "total_tokens": 18110488} {"current_steps": 27510, "total_steps": 33920, "loss": 0.234, "lr": 1.0492627824537877e-06, "epoch": 16.22051886792453, "percentage": 81.1, "elapsed_time": "0:53:01", "remaining_time": "0:12:21", "throughput": 5693.1, "total_tokens": 18113560} {"current_steps": 27515, "total_steps": 33920, "loss": 0.3532, "lr": 1.0476864457823626e-06, "epoch": 16.223466981132077, "percentage": 81.12, "elapsed_time": "0:53:02", "remaining_time": "0:12:20", "throughput": 5693.21, "total_tokens": 18117240} {"current_steps": 27520, "total_steps": 33920, "loss": 0.2024, "lr": 1.0461111555029836e-06, "epoch": 16.22641509433962, "percentage": 81.13, "elapsed_time": "0:53:02", "remaining_time": "0:12:20", "throughput": 5693.16, "total_tokens": 18120408} {"current_steps": 27525, "total_steps": 33920, "loss": 0.398, "lr": 1.0445369120327175e-06, "epoch": 16.22936320754717, "percentage": 81.15, "elapsed_time": "0:53:03", "remaining_time": "0:12:19", "throughput": 5693.34, "total_tokens": 18124824} {"current_steps": 27530, "total_steps": 33920, "loss": 0.2983, "lr": 1.0429637157883516e-06, "epoch": 16.232311320754718, "percentage": 81.16, "elapsed_time": "0:53:04", "remaining_time": "0:12:19", "throughput": 5693.23, "total_tokens": 18127544} {"current_steps": 27535, "total_steps": 33920, "loss": 0.2387, "lr": 1.041391567186395e-06, "epoch": 16.235259433962263, "percentage": 81.18, "elapsed_time": "0:53:04", "remaining_time": "0:12:18", "throughput": 5693.27, "total_tokens": 18130936} {"current_steps": 27540, "total_steps": 33920, "loss": 0.3117, "lr": 1.0398204666430821e-06, "epoch": 16.23820754716981, "percentage": 81.19, "elapsed_time": "0:53:05", "remaining_time": "0:12:17", "throughput": 5693.32, "total_tokens": 18134104} {"current_steps": 27545, "total_steps": 33920, "loss": 0.3714, "lr": 1.0382504145743667e-06, "epoch": 16.24115566037736, "percentage": 81.21, "elapsed_time": "0:53:05", "remaining_time": "0:12:17", "throughput": 5693.29, "total_tokens": 18137016} {"current_steps": 27550, "total_steps": 33920, "loss": 0.361, "lr": 1.0366814113959294e-06, "epoch": 16.244103773584907, "percentage": 81.22, "elapsed_time": "0:53:06", "remaining_time": "0:12:16", "throughput": 5693.29, "total_tokens": 18140376} {"current_steps": 27555, "total_steps": 33920, "loss": 0.4209, "lr": 1.0351134575231697e-06, "epoch": 16.247051886792452, "percentage": 81.24, "elapsed_time": "0:53:06", "remaining_time": "0:12:16", "throughput": 5693.15, "total_tokens": 18142968} {"current_steps": 27560, "total_steps": 33920, "loss": 0.3326, "lr": 1.0335465533712098e-06, "epoch": 16.25, "percentage": 81.25, "elapsed_time": "0:53:07", "remaining_time": "0:12:15", "throughput": 5693.13, "total_tokens": 18146072} {"current_steps": 27565, "total_steps": 33920, "loss": 0.2529, "lr": 1.031980699354894e-06, "epoch": 16.252948113207548, "percentage": 81.26, "elapsed_time": "0:53:07", "remaining_time": "0:12:14", "throughput": 5693.14, "total_tokens": 18149432} {"current_steps": 27570, "total_steps": 33920, "loss": 0.3099, "lr": 1.03041589588879e-06, "epoch": 16.255896226415093, "percentage": 81.28, "elapsed_time": "0:53:08", "remaining_time": "0:12:14", "throughput": 5693.15, "total_tokens": 18152600} {"current_steps": 27575, "total_steps": 33920, "loss": 0.2692, "lr": 1.0288521433871834e-06, "epoch": 16.25884433962264, "percentage": 81.29, "elapsed_time": "0:53:09", "remaining_time": "0:12:13", "throughput": 5693.17, "total_tokens": 18156024} {"current_steps": 27580, "total_steps": 33920, "loss": 0.2361, "lr": 1.0272894422640866e-06, "epoch": 16.26179245283019, "percentage": 81.31, "elapsed_time": "0:53:09", "remaining_time": "0:12:13", "throughput": 5693.12, "total_tokens": 18158904} {"current_steps": 27585, "total_steps": 33920, "loss": 0.4583, "lr": 1.0257277929332332e-06, "epoch": 16.264740566037737, "percentage": 81.32, "elapsed_time": "0:53:10", "remaining_time": "0:12:12", "throughput": 5693.19, "total_tokens": 18162136} {"current_steps": 27590, "total_steps": 33920, "loss": 0.2312, "lr": 1.0241671958080745e-06, "epoch": 16.267688679245282, "percentage": 81.34, "elapsed_time": "0:53:10", "remaining_time": "0:12:12", "throughput": 5693.13, "total_tokens": 18164888} {"current_steps": 27595, "total_steps": 33920, "loss": 0.3288, "lr": 1.0226076513017858e-06, "epoch": 16.27063679245283, "percentage": 81.35, "elapsed_time": "0:53:11", "remaining_time": "0:12:11", "throughput": 5693.23, "total_tokens": 18168440} {"current_steps": 27600, "total_steps": 33920, "loss": 0.3015, "lr": 1.0210491598272625e-06, "epoch": 16.27358490566038, "percentage": 81.37, "elapsed_time": "0:53:11", "remaining_time": "0:12:10", "throughput": 5693.28, "total_tokens": 18172216} {"current_steps": 27605, "total_steps": 33920, "loss": 0.3318, "lr": 1.0194917217971229e-06, "epoch": 16.276533018867923, "percentage": 81.38, "elapsed_time": "0:53:12", "remaining_time": "0:12:10", "throughput": 5693.48, "total_tokens": 18176344} {"current_steps": 27610, "total_steps": 33920, "loss": 0.2806, "lr": 1.0179353376237038e-06, "epoch": 16.27948113207547, "percentage": 81.4, "elapsed_time": "0:53:13", "remaining_time": "0:12:09", "throughput": 5693.53, "total_tokens": 18179704} {"current_steps": 27615, "total_steps": 33920, "loss": 0.5186, "lr": 1.0163800077190672e-06, "epoch": 16.28242924528302, "percentage": 81.41, "elapsed_time": "0:53:13", "remaining_time": "0:12:09", "throughput": 5693.52, "total_tokens": 18182584} {"current_steps": 27620, "total_steps": 33920, "loss": 0.3226, "lr": 1.0148257324949916e-06, "epoch": 16.285377358490567, "percentage": 81.43, "elapsed_time": "0:53:14", "remaining_time": "0:12:08", "throughput": 5693.64, "total_tokens": 18186712} {"current_steps": 27625, "total_steps": 33920, "loss": 0.3296, "lr": 1.0132725123629783e-06, "epoch": 16.288325471698112, "percentage": 81.44, "elapsed_time": "0:53:14", "remaining_time": "0:12:08", "throughput": 5693.61, "total_tokens": 18189848} {"current_steps": 27630, "total_steps": 33920, "loss": 0.4389, "lr": 1.0117203477342497e-06, "epoch": 16.29127358490566, "percentage": 81.46, "elapsed_time": "0:53:15", "remaining_time": "0:12:07", "throughput": 5693.55, "total_tokens": 18192664} {"current_steps": 27635, "total_steps": 33920, "loss": 0.2543, "lr": 1.0101692390197477e-06, "epoch": 16.29422169811321, "percentage": 81.47, "elapsed_time": "0:53:15", "remaining_time": "0:12:06", "throughput": 5693.55, "total_tokens": 18195832} {"current_steps": 27640, "total_steps": 33920, "loss": 0.3331, "lr": 1.0086191866301331e-06, "epoch": 16.297169811320753, "percentage": 81.49, "elapsed_time": "0:53:16", "remaining_time": "0:12:06", "throughput": 5693.57, "total_tokens": 18199032} {"current_steps": 27645, "total_steps": 33920, "loss": 0.2416, "lr": 1.0070701909757918e-06, "epoch": 16.3001179245283, "percentage": 81.5, "elapsed_time": "0:53:16", "remaining_time": "0:12:05", "throughput": 5693.62, "total_tokens": 18202456} {"current_steps": 27650, "total_steps": 33920, "loss": 0.3351, "lr": 1.0055222524668267e-06, "epoch": 16.30306603773585, "percentage": 81.52, "elapsed_time": "0:53:17", "remaining_time": "0:12:05", "throughput": 5693.81, "total_tokens": 18206296} {"current_steps": 27655, "total_steps": 33920, "loss": 0.3665, "lr": 1.00397537151306e-06, "epoch": 16.306014150943398, "percentage": 81.53, "elapsed_time": "0:53:18", "remaining_time": "0:12:04", "throughput": 5693.86, "total_tokens": 18210168} {"current_steps": 27660, "total_steps": 33920, "loss": 0.3292, "lr": 1.002429548524036e-06, "epoch": 16.308962264150942, "percentage": 81.54, "elapsed_time": "0:53:18", "remaining_time": "0:12:03", "throughput": 5693.78, "total_tokens": 18213016} {"current_steps": 27665, "total_steps": 33920, "loss": 0.4002, "lr": 1.0008847839090175e-06, "epoch": 16.31191037735849, "percentage": 81.56, "elapsed_time": "0:53:19", "remaining_time": "0:12:03", "throughput": 5693.65, "total_tokens": 18215608} {"current_steps": 27670, "total_steps": 33920, "loss": 0.3133, "lr": 9.993410780769862e-07, "epoch": 16.31485849056604, "percentage": 81.57, "elapsed_time": "0:53:19", "remaining_time": "0:12:02", "throughput": 5693.68, "total_tokens": 18218840} {"current_steps": 27675, "total_steps": 33920, "loss": 0.2918, "lr": 9.977984314366463e-07, "epoch": 16.317806603773583, "percentage": 81.59, "elapsed_time": "0:53:20", "remaining_time": "0:12:02", "throughput": 5693.52, "total_tokens": 18221368} {"current_steps": 27680, "total_steps": 33920, "loss": 0.3002, "lr": 9.962568443964216e-07, "epoch": 16.32075471698113, "percentage": 81.6, "elapsed_time": "0:53:20", "remaining_time": "0:12:01", "throughput": 5693.56, "total_tokens": 18224984} {"current_steps": 27685, "total_steps": 33920, "loss": 0.4216, "lr": 9.947163173644524e-07, "epoch": 16.32370283018868, "percentage": 81.62, "elapsed_time": "0:53:21", "remaining_time": "0:12:01", "throughput": 5693.58, "total_tokens": 18228152} {"current_steps": 27690, "total_steps": 33920, "loss": 0.2827, "lr": 9.931768507486007e-07, "epoch": 16.326650943396228, "percentage": 81.63, "elapsed_time": "0:53:22", "remaining_time": "0:12:00", "throughput": 5693.55, "total_tokens": 18231256} {"current_steps": 27695, "total_steps": 33920, "loss": 0.2464, "lr": 9.916384449564453e-07, "epoch": 16.329599056603772, "percentage": 81.65, "elapsed_time": "0:53:22", "remaining_time": "0:11:59", "throughput": 5693.54, "total_tokens": 18234200} {"current_steps": 27700, "total_steps": 33920, "loss": 0.3234, "lr": 9.90101100395287e-07, "epoch": 16.33254716981132, "percentage": 81.66, "elapsed_time": "0:53:23", "remaining_time": "0:11:59", "throughput": 5693.54, "total_tokens": 18237368} {"current_steps": 27705, "total_steps": 33920, "loss": 0.3815, "lr": 9.885648174721428e-07, "epoch": 16.33549528301887, "percentage": 81.68, "elapsed_time": "0:53:23", "remaining_time": "0:11:58", "throughput": 5693.62, "total_tokens": 18241080} {"current_steps": 27710, "total_steps": 33920, "loss": 0.2977, "lr": 9.870295965937532e-07, "epoch": 16.338443396226417, "percentage": 81.69, "elapsed_time": "0:53:24", "remaining_time": "0:11:58", "throughput": 5693.44, "total_tokens": 18243512} {"current_steps": 27715, "total_steps": 33920, "loss": 0.3667, "lr": 9.854954381665727e-07, "epoch": 16.34139150943396, "percentage": 81.71, "elapsed_time": "0:53:24", "remaining_time": "0:11:57", "throughput": 5693.52, "total_tokens": 18247000} {"current_steps": 27720, "total_steps": 33920, "loss": 0.2263, "lr": 9.83962342596776e-07, "epoch": 16.34433962264151, "percentage": 81.72, "elapsed_time": "0:53:25", "remaining_time": "0:11:56", "throughput": 5693.6, "total_tokens": 18250840} {"current_steps": 27725, "total_steps": 33920, "loss": 0.3732, "lr": 9.824303102902576e-07, "epoch": 16.347287735849058, "percentage": 81.74, "elapsed_time": "0:53:26", "remaining_time": "0:11:56", "throughput": 5693.66, "total_tokens": 18255000} {"current_steps": 27730, "total_steps": 33920, "loss": 0.2576, "lr": 9.808993416526292e-07, "epoch": 16.350235849056602, "percentage": 81.75, "elapsed_time": "0:53:26", "remaining_time": "0:11:55", "throughput": 5693.53, "total_tokens": 18257528} {"current_steps": 27735, "total_steps": 33920, "loss": 0.4106, "lr": 9.793694370892204e-07, "epoch": 16.35318396226415, "percentage": 81.77, "elapsed_time": "0:53:27", "remaining_time": "0:11:55", "throughput": 5693.66, "total_tokens": 18261816} {"current_steps": 27740, "total_steps": 33920, "loss": 0.2587, "lr": 9.77840597005082e-07, "epoch": 16.3561320754717, "percentage": 81.78, "elapsed_time": "0:53:28", "remaining_time": "0:11:54", "throughput": 5693.82, "total_tokens": 18265976} {"current_steps": 27745, "total_steps": 33920, "loss": 0.3032, "lr": 9.763128218049806e-07, "epoch": 16.359080188679247, "percentage": 81.8, "elapsed_time": "0:53:28", "remaining_time": "0:11:54", "throughput": 5693.79, "total_tokens": 18268920} {"current_steps": 27750, "total_steps": 33920, "loss": 0.2935, "lr": 9.747861118934005e-07, "epoch": 16.36202830188679, "percentage": 81.81, "elapsed_time": "0:53:29", "remaining_time": "0:11:53", "throughput": 5693.72, "total_tokens": 18271640} {"current_steps": 27755, "total_steps": 33920, "loss": 0.3236, "lr": 9.732604676745443e-07, "epoch": 16.36497641509434, "percentage": 81.82, "elapsed_time": "0:53:29", "remaining_time": "0:11:52", "throughput": 5693.75, "total_tokens": 18274936} {"current_steps": 27760, "total_steps": 33920, "loss": 0.253, "lr": 9.717358895523333e-07, "epoch": 16.367924528301888, "percentage": 81.84, "elapsed_time": "0:53:30", "remaining_time": "0:11:52", "throughput": 5693.8, "total_tokens": 18278232} {"current_steps": 27765, "total_steps": 33920, "loss": 0.3291, "lr": 9.702123779304074e-07, "epoch": 16.370872641509433, "percentage": 81.85, "elapsed_time": "0:53:30", "remaining_time": "0:11:51", "throughput": 5693.74, "total_tokens": 18281016} {"current_steps": 27770, "total_steps": 33920, "loss": 0.3134, "lr": 9.686899332121203e-07, "epoch": 16.37382075471698, "percentage": 81.87, "elapsed_time": "0:53:31", "remaining_time": "0:11:51", "throughput": 5693.65, "total_tokens": 18283736} {"current_steps": 27775, "total_steps": 33920, "loss": 0.3354, "lr": 9.671685558005488e-07, "epoch": 16.37676886792453, "percentage": 81.88, "elapsed_time": "0:53:31", "remaining_time": "0:11:50", "throughput": 5693.64, "total_tokens": 18286712} {"current_steps": 27780, "total_steps": 33920, "loss": 0.2761, "lr": 9.656482460984828e-07, "epoch": 16.379716981132077, "percentage": 81.9, "elapsed_time": "0:53:32", "remaining_time": "0:11:50", "throughput": 5693.81, "total_tokens": 18291544} {"current_steps": 27785, "total_steps": 33920, "loss": 0.2704, "lr": 9.641290045084307e-07, "epoch": 16.38266509433962, "percentage": 81.91, "elapsed_time": "0:53:33", "remaining_time": "0:11:49", "throughput": 5693.97, "total_tokens": 18296376} {"current_steps": 27790, "total_steps": 33920, "loss": 0.3555, "lr": 9.626108314326182e-07, "epoch": 16.38561320754717, "percentage": 81.93, "elapsed_time": "0:53:33", "remaining_time": "0:11:48", "throughput": 5693.98, "total_tokens": 18299320} {"current_steps": 27795, "total_steps": 33920, "loss": 0.2833, "lr": 9.610937272729881e-07, "epoch": 16.388561320754718, "percentage": 81.94, "elapsed_time": "0:53:34", "remaining_time": "0:11:48", "throughput": 5694.01, "total_tokens": 18302616} {"current_steps": 27800, "total_steps": 33920, "loss": 0.3318, "lr": 9.595776924311996e-07, "epoch": 16.391509433962263, "percentage": 81.96, "elapsed_time": "0:53:35", "remaining_time": "0:11:47", "throughput": 5694.1, "total_tokens": 18307448} {"current_steps": 27805, "total_steps": 33920, "loss": 0.3685, "lr": 9.580627273086313e-07, "epoch": 16.39445754716981, "percentage": 81.97, "elapsed_time": "0:53:35", "remaining_time": "0:11:47", "throughput": 5693.89, "total_tokens": 18309944} {"current_steps": 27810, "total_steps": 33920, "loss": 0.2967, "lr": 9.565488323063754e-07, "epoch": 16.39740566037736, "percentage": 81.99, "elapsed_time": "0:53:36", "remaining_time": "0:11:46", "throughput": 5693.94, "total_tokens": 18313240} {"current_steps": 27815, "total_steps": 33920, "loss": 0.3081, "lr": 9.55036007825243e-07, "epoch": 16.400353773584907, "percentage": 82.0, "elapsed_time": "0:53:36", "remaining_time": "0:11:46", "throughput": 5694.05, "total_tokens": 18317176} {"current_steps": 27820, "total_steps": 33920, "loss": 0.2591, "lr": 9.535242542657602e-07, "epoch": 16.403301886792452, "percentage": 82.02, "elapsed_time": "0:53:37", "remaining_time": "0:11:45", "throughput": 5694.07, "total_tokens": 18320280} {"current_steps": 27825, "total_steps": 33920, "loss": 0.293, "lr": 9.520135720281692e-07, "epoch": 16.40625, "percentage": 82.03, "elapsed_time": "0:53:38", "remaining_time": "0:11:44", "throughput": 5694.21, "total_tokens": 18324152} {"current_steps": 27830, "total_steps": 33920, "loss": 0.3441, "lr": 9.505039615124318e-07, "epoch": 16.409198113207548, "percentage": 82.05, "elapsed_time": "0:53:38", "remaining_time": "0:11:44", "throughput": 5693.96, "total_tokens": 18326328} {"current_steps": 27835, "total_steps": 33920, "loss": 0.2869, "lr": 9.489954231182235e-07, "epoch": 16.412146226415093, "percentage": 82.06, "elapsed_time": "0:53:39", "remaining_time": "0:11:43", "throughput": 5693.79, "total_tokens": 18328856} {"current_steps": 27840, "total_steps": 33920, "loss": 0.2635, "lr": 9.474879572449352e-07, "epoch": 16.41509433962264, "percentage": 82.08, "elapsed_time": "0:53:39", "remaining_time": "0:11:43", "throughput": 5693.86, "total_tokens": 18332696} {"current_steps": 27845, "total_steps": 33920, "loss": 0.431, "lr": 9.459815642916759e-07, "epoch": 16.41804245283019, "percentage": 82.09, "elapsed_time": "0:53:40", "remaining_time": "0:11:42", "throughput": 5693.96, "total_tokens": 18336440} {"current_steps": 27850, "total_steps": 33920, "loss": 0.2783, "lr": 9.444762446572692e-07, "epoch": 16.420990566037737, "percentage": 82.1, "elapsed_time": "0:53:40", "remaining_time": "0:11:42", "throughput": 5694.0, "total_tokens": 18339736} {"current_steps": 27855, "total_steps": 33920, "loss": 0.3791, "lr": 9.429719987402541e-07, "epoch": 16.423938679245282, "percentage": 82.12, "elapsed_time": "0:53:41", "remaining_time": "0:11:41", "throughput": 5694.07, "total_tokens": 18343096} {"current_steps": 27860, "total_steps": 33920, "loss": 0.2765, "lr": 9.414688269388883e-07, "epoch": 16.42688679245283, "percentage": 82.13, "elapsed_time": "0:53:41", "remaining_time": "0:11:40", "throughput": 5694.01, "total_tokens": 18346040} {"current_steps": 27865, "total_steps": 33920, "loss": 0.2686, "lr": 9.3996672965114e-07, "epoch": 16.42983490566038, "percentage": 82.15, "elapsed_time": "0:53:42", "remaining_time": "0:11:40", "throughput": 5693.88, "total_tokens": 18348568} {"current_steps": 27870, "total_steps": 33920, "loss": 0.2725, "lr": 9.384657072747e-07, "epoch": 16.432783018867923, "percentage": 82.16, "elapsed_time": "0:53:43", "remaining_time": "0:11:39", "throughput": 5693.67, "total_tokens": 18350872} {"current_steps": 27875, "total_steps": 33920, "loss": 0.2648, "lr": 9.369657602069676e-07, "epoch": 16.43573113207547, "percentage": 82.18, "elapsed_time": "0:53:43", "remaining_time": "0:11:39", "throughput": 5693.58, "total_tokens": 18353560} {"current_steps": 27880, "total_steps": 33920, "loss": 0.2792, "lr": 9.354668888450608e-07, "epoch": 16.43867924528302, "percentage": 82.19, "elapsed_time": "0:53:44", "remaining_time": "0:11:38", "throughput": 5693.66, "total_tokens": 18357016} {"current_steps": 27885, "total_steps": 33920, "loss": 0.343, "lr": 9.339690935858125e-07, "epoch": 16.441627358490567, "percentage": 82.21, "elapsed_time": "0:53:44", "remaining_time": "0:11:37", "throughput": 5693.71, "total_tokens": 18360376} {"current_steps": 27890, "total_steps": 33920, "loss": 0.2888, "lr": 9.324723748257697e-07, "epoch": 16.444575471698112, "percentage": 82.22, "elapsed_time": "0:53:45", "remaining_time": "0:11:37", "throughput": 5693.64, "total_tokens": 18363480} {"current_steps": 27895, "total_steps": 33920, "loss": 0.29, "lr": 9.309767329611963e-07, "epoch": 16.44752358490566, "percentage": 82.24, "elapsed_time": "0:53:45", "remaining_time": "0:11:36", "throughput": 5693.8, "total_tokens": 18367512} {"current_steps": 27900, "total_steps": 33920, "loss": 0.3776, "lr": 9.294821683880695e-07, "epoch": 16.45047169811321, "percentage": 82.25, "elapsed_time": "0:53:46", "remaining_time": "0:11:36", "throughput": 5693.86, "total_tokens": 18371064} {"current_steps": 27905, "total_steps": 33920, "loss": 0.2196, "lr": 9.279886815020816e-07, "epoch": 16.453419811320753, "percentage": 82.27, "elapsed_time": "0:53:47", "remaining_time": "0:11:35", "throughput": 5693.93, "total_tokens": 18375352} {"current_steps": 27910, "total_steps": 33920, "loss": 0.371, "lr": 9.264962726986393e-07, "epoch": 16.4563679245283, "percentage": 82.28, "elapsed_time": "0:53:47", "remaining_time": "0:11:35", "throughput": 5693.97, "total_tokens": 18379672} {"current_steps": 27915, "total_steps": 33920, "loss": 0.3069, "lr": 9.250049423728652e-07, "epoch": 16.45931603773585, "percentage": 82.3, "elapsed_time": "0:53:48", "remaining_time": "0:11:34", "throughput": 5693.94, "total_tokens": 18382552} {"current_steps": 27920, "total_steps": 33920, "loss": 0.2243, "lr": 9.235146909195936e-07, "epoch": 16.462264150943398, "percentage": 82.31, "elapsed_time": "0:53:48", "remaining_time": "0:11:33", "throughput": 5693.91, "total_tokens": 18385624} {"current_steps": 27925, "total_steps": 33920, "loss": 0.296, "lr": 9.220255187333771e-07, "epoch": 16.465212264150942, "percentage": 82.33, "elapsed_time": "0:53:49", "remaining_time": "0:11:33", "throughput": 5693.73, "total_tokens": 18388152} {"current_steps": 27930, "total_steps": 33920, "loss": 0.4211, "lr": 9.205374262084798e-07, "epoch": 16.46816037735849, "percentage": 82.34, "elapsed_time": "0:53:50", "remaining_time": "0:11:32", "throughput": 5693.71, "total_tokens": 18391160} {"current_steps": 27935, "total_steps": 33920, "loss": 0.3012, "lr": 9.190504137388806e-07, "epoch": 16.47110849056604, "percentage": 82.36, "elapsed_time": "0:53:50", "remaining_time": "0:11:32", "throughput": 5693.79, "total_tokens": 18394808} {"current_steps": 27940, "total_steps": 33920, "loss": 0.29, "lr": 9.175644817182722e-07, "epoch": 16.474056603773583, "percentage": 82.37, "elapsed_time": "0:53:51", "remaining_time": "0:11:31", "throughput": 5693.59, "total_tokens": 18397240} {"current_steps": 27945, "total_steps": 33920, "loss": 0.335, "lr": 9.16079630540061e-07, "epoch": 16.47700471698113, "percentage": 82.39, "elapsed_time": "0:53:51", "remaining_time": "0:11:30", "throughput": 5693.51, "total_tokens": 18400184} {"current_steps": 27950, "total_steps": 33920, "loss": 0.2811, "lr": 9.145958605973676e-07, "epoch": 16.47995283018868, "percentage": 82.4, "elapsed_time": "0:53:52", "remaining_time": "0:11:30", "throughput": 5693.36, "total_tokens": 18402808} {"current_steps": 27955, "total_steps": 33920, "loss": 0.3584, "lr": 9.131131722830289e-07, "epoch": 16.482900943396228, "percentage": 82.41, "elapsed_time": "0:53:53", "remaining_time": "0:11:29", "throughput": 5693.47, "total_tokens": 18408632} {"current_steps": 27960, "total_steps": 33920, "loss": 0.271, "lr": 9.116315659895892e-07, "epoch": 16.485849056603772, "percentage": 82.43, "elapsed_time": "0:53:53", "remaining_time": "0:11:29", "throughput": 5693.28, "total_tokens": 18411128} {"current_steps": 27965, "total_steps": 33920, "loss": 0.3459, "lr": 9.10151042109314e-07, "epoch": 16.48879716981132, "percentage": 82.44, "elapsed_time": "0:53:54", "remaining_time": "0:11:28", "throughput": 5693.26, "total_tokens": 18414104} {"current_steps": 27970, "total_steps": 33920, "loss": 0.2784, "lr": 9.086716010341767e-07, "epoch": 16.49174528301887, "percentage": 82.46, "elapsed_time": "0:53:54", "remaining_time": "0:11:28", "throughput": 5693.25, "total_tokens": 18417112} {"current_steps": 27975, "total_steps": 33920, "loss": 0.4917, "lr": 9.071932431558655e-07, "epoch": 16.494693396226417, "percentage": 82.47, "elapsed_time": "0:53:55", "remaining_time": "0:11:27", "throughput": 5693.41, "total_tokens": 18421240} {"current_steps": 27980, "total_steps": 33920, "loss": 0.3356, "lr": 9.057159688657824e-07, "epoch": 16.49764150943396, "percentage": 82.49, "elapsed_time": "0:53:56", "remaining_time": "0:11:27", "throughput": 5693.39, "total_tokens": 18424472} {"current_steps": 27985, "total_steps": 33920, "loss": 0.3031, "lr": 9.042397785550405e-07, "epoch": 16.50058962264151, "percentage": 82.5, "elapsed_time": "0:53:56", "remaining_time": "0:11:26", "throughput": 5693.31, "total_tokens": 18427160} {"current_steps": 27990, "total_steps": 33920, "loss": 0.2985, "lr": 9.027646726144707e-07, "epoch": 16.503537735849058, "percentage": 82.52, "elapsed_time": "0:53:57", "remaining_time": "0:11:25", "throughput": 5693.23, "total_tokens": 18430040} {"current_steps": 27995, "total_steps": 33920, "loss": 0.2886, "lr": 9.012906514346115e-07, "epoch": 16.506485849056602, "percentage": 82.53, "elapsed_time": "0:53:57", "remaining_time": "0:11:25", "throughput": 5693.16, "total_tokens": 18432920} {"current_steps": 28000, "total_steps": 33920, "loss": 0.2862, "lr": 8.99817715405717e-07, "epoch": 16.50943396226415, "percentage": 82.55, "elapsed_time": "0:53:58", "remaining_time": "0:11:24", "throughput": 5693.26, "total_tokens": 18437112} {"current_steps": 28005, "total_steps": 33920, "loss": 0.3602, "lr": 8.983458649177529e-07, "epoch": 16.5123820754717, "percentage": 82.56, "elapsed_time": "0:53:58", "remaining_time": "0:11:24", "throughput": 5693.08, "total_tokens": 18439480} {"current_steps": 28010, "total_steps": 33920, "loss": 0.3461, "lr": 8.968751003603982e-07, "epoch": 16.515330188679247, "percentage": 82.58, "elapsed_time": "0:53:59", "remaining_time": "0:11:23", "throughput": 5692.88, "total_tokens": 18442040} {"current_steps": 28015, "total_steps": 33920, "loss": 0.3541, "lr": 8.95405422123043e-07, "epoch": 16.51827830188679, "percentage": 82.59, "elapsed_time": "0:54:00", "remaining_time": "0:11:22", "throughput": 5692.76, "total_tokens": 18444984} {"current_steps": 28020, "total_steps": 33920, "loss": 0.3928, "lr": 8.939368305947932e-07, "epoch": 16.52122641509434, "percentage": 82.61, "elapsed_time": "0:54:00", "remaining_time": "0:11:22", "throughput": 5692.75, "total_tokens": 18448088} {"current_steps": 28025, "total_steps": 33920, "loss": 0.3648, "lr": 8.92469326164464e-07, "epoch": 16.524174528301888, "percentage": 82.62, "elapsed_time": "0:54:01", "remaining_time": "0:11:21", "throughput": 5692.86, "total_tokens": 18451864} {"current_steps": 28030, "total_steps": 33920, "loss": 0.2061, "lr": 8.910029092205829e-07, "epoch": 16.527122641509433, "percentage": 82.64, "elapsed_time": "0:54:01", "remaining_time": "0:11:21", "throughput": 5692.87, "total_tokens": 18455448} {"current_steps": 28035, "total_steps": 33920, "loss": 0.292, "lr": 8.895375801513906e-07, "epoch": 16.53007075471698, "percentage": 82.65, "elapsed_time": "0:54:02", "remaining_time": "0:11:20", "throughput": 5692.82, "total_tokens": 18458392} {"current_steps": 28040, "total_steps": 33920, "loss": 0.3379, "lr": 8.880733393448377e-07, "epoch": 16.53301886792453, "percentage": 82.67, "elapsed_time": "0:54:03", "remaining_time": "0:11:20", "throughput": 5692.89, "total_tokens": 18462136} {"current_steps": 28045, "total_steps": 33920, "loss": 0.3793, "lr": 8.866101871885907e-07, "epoch": 16.535966981132077, "percentage": 82.68, "elapsed_time": "0:54:03", "remaining_time": "0:11:19", "throughput": 5692.9, "total_tokens": 18465208} {"current_steps": 28050, "total_steps": 33920, "loss": 0.2346, "lr": 8.851481240700249e-07, "epoch": 16.53891509433962, "percentage": 82.69, "elapsed_time": "0:54:04", "remaining_time": "0:11:18", "throughput": 5692.7, "total_tokens": 18467544} {"current_steps": 28055, "total_steps": 33920, "loss": 0.2625, "lr": 8.836871503762257e-07, "epoch": 16.54186320754717, "percentage": 82.71, "elapsed_time": "0:54:04", "remaining_time": "0:11:18", "throughput": 5692.61, "total_tokens": 18470712} {"current_steps": 28060, "total_steps": 33920, "loss": 0.3232, "lr": 8.822272664939946e-07, "epoch": 16.544811320754718, "percentage": 82.72, "elapsed_time": "0:54:05", "remaining_time": "0:11:17", "throughput": 5692.51, "total_tokens": 18474008} {"current_steps": 28065, "total_steps": 33920, "loss": 0.3403, "lr": 8.80768472809842e-07, "epoch": 16.547759433962263, "percentage": 82.74, "elapsed_time": "0:54:05", "remaining_time": "0:11:17", "throughput": 5692.44, "total_tokens": 18476824} {"current_steps": 28070, "total_steps": 33920, "loss": 0.3451, "lr": 8.793107697099884e-07, "epoch": 16.55070754716981, "percentage": 82.75, "elapsed_time": "0:54:06", "remaining_time": "0:11:16", "throughput": 5692.43, "total_tokens": 18479800} {"current_steps": 28075, "total_steps": 33920, "loss": 0.2581, "lr": 8.778541575803673e-07, "epoch": 16.55365566037736, "percentage": 82.77, "elapsed_time": "0:54:06", "remaining_time": "0:11:15", "throughput": 5692.62, "total_tokens": 18483832} {"current_steps": 28080, "total_steps": 33920, "loss": 0.2903, "lr": 8.763986368066241e-07, "epoch": 16.556603773584907, "percentage": 82.78, "elapsed_time": "0:54:07", "remaining_time": "0:11:15", "throughput": 5692.57, "total_tokens": 18486904} {"current_steps": 28085, "total_steps": 33920, "loss": 0.4272, "lr": 8.749442077741138e-07, "epoch": 16.559551886792452, "percentage": 82.8, "elapsed_time": "0:54:08", "remaining_time": "0:11:14", "throughput": 5692.58, "total_tokens": 18490776} {"current_steps": 28090, "total_steps": 33920, "loss": 0.2738, "lr": 8.734908708679024e-07, "epoch": 16.5625, "percentage": 82.81, "elapsed_time": "0:54:08", "remaining_time": "0:11:14", "throughput": 5692.44, "total_tokens": 18493304} {"current_steps": 28095, "total_steps": 33920, "loss": 0.2339, "lr": 8.72038626472767e-07, "epoch": 16.565448113207548, "percentage": 82.83, "elapsed_time": "0:54:09", "remaining_time": "0:11:13", "throughput": 5692.49, "total_tokens": 18496696} {"current_steps": 28100, "total_steps": 33920, "loss": 0.3231, "lr": 8.705874749731962e-07, "epoch": 16.568396226415093, "percentage": 82.84, "elapsed_time": "0:54:10", "remaining_time": "0:11:13", "throughput": 5692.88, "total_tokens": 18505016} {"current_steps": 28105, "total_steps": 33920, "loss": 0.433, "lr": 8.691374167533867e-07, "epoch": 16.57134433962264, "percentage": 82.86, "elapsed_time": "0:54:11", "remaining_time": "0:11:12", "throughput": 5692.86, "total_tokens": 18508120} {"current_steps": 28110, "total_steps": 33920, "loss": 0.315, "lr": 8.6768845219725e-07, "epoch": 16.57429245283019, "percentage": 82.87, "elapsed_time": "0:54:11", "remaining_time": "0:11:12", "throughput": 5692.77, "total_tokens": 18511064} {"current_steps": 28115, "total_steps": 33920, "loss": 0.4038, "lr": 8.662405816884056e-07, "epoch": 16.577240566037737, "percentage": 82.89, "elapsed_time": "0:54:12", "remaining_time": "0:11:11", "throughput": 5692.76, "total_tokens": 18514360} {"current_steps": 28120, "total_steps": 33920, "loss": 0.1735, "lr": 8.647938056101824e-07, "epoch": 16.580188679245282, "percentage": 82.9, "elapsed_time": "0:54:12", "remaining_time": "0:11:10", "throughput": 5692.71, "total_tokens": 18517336} {"current_steps": 28125, "total_steps": 33920, "loss": 0.2839, "lr": 8.63348124345621e-07, "epoch": 16.58313679245283, "percentage": 82.92, "elapsed_time": "0:54:13", "remaining_time": "0:11:10", "throughput": 5692.62, "total_tokens": 18520152} {"current_steps": 28130, "total_steps": 33920, "loss": 0.308, "lr": 8.619035382774716e-07, "epoch": 16.58608490566038, "percentage": 82.93, "elapsed_time": "0:54:13", "remaining_time": "0:11:09", "throughput": 5692.48, "total_tokens": 18522680} {"current_steps": 28135, "total_steps": 33920, "loss": 0.4035, "lr": 8.60460047788193e-07, "epoch": 16.589033018867923, "percentage": 82.95, "elapsed_time": "0:54:14", "remaining_time": "0:11:09", "throughput": 5692.55, "total_tokens": 18526040} {"current_steps": 28140, "total_steps": 33920, "loss": 0.2745, "lr": 8.590176532599587e-07, "epoch": 16.59198113207547, "percentage": 82.96, "elapsed_time": "0:54:15", "remaining_time": "0:11:08", "throughput": 5692.63, "total_tokens": 18529560} {"current_steps": 28145, "total_steps": 33920, "loss": 0.2488, "lr": 8.575763550746475e-07, "epoch": 16.59492924528302, "percentage": 82.97, "elapsed_time": "0:54:15", "remaining_time": "0:11:07", "throughput": 5692.5, "total_tokens": 18532248} {"current_steps": 28150, "total_steps": 33920, "loss": 0.2905, "lr": 8.56136153613848e-07, "epoch": 16.597877358490567, "percentage": 82.99, "elapsed_time": "0:54:16", "remaining_time": "0:11:07", "throughput": 5692.26, "total_tokens": 18534456} {"current_steps": 28155, "total_steps": 33920, "loss": 0.3022, "lr": 8.546970492588619e-07, "epoch": 16.600825471698112, "percentage": 83.0, "elapsed_time": "0:54:16", "remaining_time": "0:11:06", "throughput": 5692.19, "total_tokens": 18537144} {"current_steps": 28160, "total_steps": 33920, "loss": 0.2192, "lr": 8.532590423906973e-07, "epoch": 16.60377358490566, "percentage": 83.02, "elapsed_time": "0:54:17", "remaining_time": "0:11:06", "throughput": 5692.2, "total_tokens": 18540376} {"current_steps": 28165, "total_steps": 33920, "loss": 0.2789, "lr": 8.518221333900728e-07, "epoch": 16.60672169811321, "percentage": 83.03, "elapsed_time": "0:54:17", "remaining_time": "0:11:05", "throughput": 5692.2, "total_tokens": 18543352} {"current_steps": 28170, "total_steps": 33920, "loss": 0.2842, "lr": 8.503863226374148e-07, "epoch": 16.609669811320753, "percentage": 83.05, "elapsed_time": "0:54:18", "remaining_time": "0:11:05", "throughput": 5692.17, "total_tokens": 18546264} {"current_steps": 28175, "total_steps": 33920, "loss": 0.2735, "lr": 8.489516105128632e-07, "epoch": 16.6126179245283, "percentage": 83.06, "elapsed_time": "0:54:18", "remaining_time": "0:11:04", "throughput": 5692.29, "total_tokens": 18549944} {"current_steps": 28180, "total_steps": 33920, "loss": 0.4499, "lr": 8.475179973962621e-07, "epoch": 16.61556603773585, "percentage": 83.08, "elapsed_time": "0:54:19", "remaining_time": "0:11:03", "throughput": 5692.32, "total_tokens": 18553240} {"current_steps": 28185, "total_steps": 33920, "loss": 0.2656, "lr": 8.460854836671678e-07, "epoch": 16.618514150943398, "percentage": 83.09, "elapsed_time": "0:54:19", "remaining_time": "0:11:03", "throughput": 5692.2, "total_tokens": 18555864} {"current_steps": 28190, "total_steps": 33920, "loss": 0.4284, "lr": 8.446540697048445e-07, "epoch": 16.621462264150942, "percentage": 83.11, "elapsed_time": "0:54:20", "remaining_time": "0:11:02", "throughput": 5692.24, "total_tokens": 18559128} {"current_steps": 28195, "total_steps": 33920, "loss": 0.3038, "lr": 8.432237558882639e-07, "epoch": 16.62441037735849, "percentage": 83.12, "elapsed_time": "0:54:20", "remaining_time": "0:11:02", "throughput": 5692.25, "total_tokens": 18562264} {"current_steps": 28200, "total_steps": 33920, "loss": 0.4736, "lr": 8.417945425961083e-07, "epoch": 16.62735849056604, "percentage": 83.14, "elapsed_time": "0:54:21", "remaining_time": "0:11:01", "throughput": 5692.18, "total_tokens": 18565208} {"current_steps": 28205, "total_steps": 33920, "loss": 0.2664, "lr": 8.403664302067688e-07, "epoch": 16.630306603773583, "percentage": 83.15, "elapsed_time": "0:54:22", "remaining_time": "0:11:00", "throughput": 5692.26, "total_tokens": 18568696} {"current_steps": 28210, "total_steps": 33920, "loss": 0.2916, "lr": 8.389394190983446e-07, "epoch": 16.63325471698113, "percentage": 83.17, "elapsed_time": "0:54:23", "remaining_time": "0:11:00", "throughput": 5692.57, "total_tokens": 18575672} {"current_steps": 28215, "total_steps": 33920, "loss": 0.195, "lr": 8.37513509648642e-07, "epoch": 16.63620283018868, "percentage": 83.18, "elapsed_time": "0:54:23", "remaining_time": "0:10:59", "throughput": 5692.53, "total_tokens": 18578776} {"current_steps": 28220, "total_steps": 33920, "loss": 0.2758, "lr": 8.360887022351771e-07, "epoch": 16.639150943396228, "percentage": 83.2, "elapsed_time": "0:54:24", "remaining_time": "0:10:59", "throughput": 5692.54, "total_tokens": 18582296} {"current_steps": 28225, "total_steps": 33920, "loss": 0.2916, "lr": 8.346649972351739e-07, "epoch": 16.642099056603772, "percentage": 83.21, "elapsed_time": "0:54:24", "remaining_time": "0:10:58", "throughput": 5692.47, "total_tokens": 18585336} {"current_steps": 28230, "total_steps": 33920, "loss": 0.3221, "lr": 8.33242395025563e-07, "epoch": 16.64504716981132, "percentage": 83.23, "elapsed_time": "0:54:25", "remaining_time": "0:10:58", "throughput": 5692.38, "total_tokens": 18588440} {"current_steps": 28235, "total_steps": 33920, "loss": 0.3019, "lr": 8.318208959829871e-07, "epoch": 16.64799528301887, "percentage": 83.24, "elapsed_time": "0:54:26", "remaining_time": "0:10:57", "throughput": 5692.37, "total_tokens": 18591864} {"current_steps": 28240, "total_steps": 33920, "loss": 0.2339, "lr": 8.304005004837929e-07, "epoch": 16.650943396226417, "percentage": 83.25, "elapsed_time": "0:54:26", "remaining_time": "0:10:57", "throughput": 5692.21, "total_tokens": 18594360} {"current_steps": 28245, "total_steps": 33920, "loss": 0.4869, "lr": 8.289812089040344e-07, "epoch": 16.65389150943396, "percentage": 83.27, "elapsed_time": "0:54:27", "remaining_time": "0:10:56", "throughput": 5692.19, "total_tokens": 18597560} {"current_steps": 28250, "total_steps": 33920, "loss": 0.349, "lr": 8.275630216194785e-07, "epoch": 16.65683962264151, "percentage": 83.28, "elapsed_time": "0:54:27", "remaining_time": "0:10:55", "throughput": 5692.07, "total_tokens": 18600472} {"current_steps": 28255, "total_steps": 33920, "loss": 0.3496, "lr": 8.261459390055948e-07, "epoch": 16.659787735849058, "percentage": 83.3, "elapsed_time": "0:54:28", "remaining_time": "0:10:55", "throughput": 5691.98, "total_tokens": 18603192} {"current_steps": 28260, "total_steps": 33920, "loss": 0.2788, "lr": 8.24729961437562e-07, "epoch": 16.662735849056602, "percentage": 83.31, "elapsed_time": "0:54:28", "remaining_time": "0:10:54", "throughput": 5691.95, "total_tokens": 18606392} {"current_steps": 28265, "total_steps": 33920, "loss": 0.2656, "lr": 8.233150892902653e-07, "epoch": 16.66568396226415, "percentage": 83.33, "elapsed_time": "0:54:29", "remaining_time": "0:10:54", "throughput": 5691.88, "total_tokens": 18609176} {"current_steps": 28270, "total_steps": 33920, "loss": 0.454, "lr": 8.219013229383005e-07, "epoch": 16.6686320754717, "percentage": 83.34, "elapsed_time": "0:54:30", "remaining_time": "0:10:53", "throughput": 5691.82, "total_tokens": 18612280} {"current_steps": 28275, "total_steps": 33920, "loss": 0.3329, "lr": 8.204886627559666e-07, "epoch": 16.671580188679247, "percentage": 83.36, "elapsed_time": "0:54:30", "remaining_time": "0:10:52", "throughput": 5691.56, "total_tokens": 18614712} {"current_steps": 28280, "total_steps": 33920, "loss": 0.2392, "lr": 8.190771091172722e-07, "epoch": 16.67452830188679, "percentage": 83.37, "elapsed_time": "0:54:31", "remaining_time": "0:10:52", "throughput": 5691.57, "total_tokens": 18618136} {"current_steps": 28285, "total_steps": 33920, "loss": 0.3215, "lr": 8.176666623959323e-07, "epoch": 16.67747641509434, "percentage": 83.39, "elapsed_time": "0:54:31", "remaining_time": "0:10:51", "throughput": 5691.67, "total_tokens": 18621816} {"current_steps": 28290, "total_steps": 33920, "loss": 0.3087, "lr": 8.162573229653681e-07, "epoch": 16.680424528301888, "percentage": 83.4, "elapsed_time": "0:54:32", "remaining_time": "0:10:51", "throughput": 5691.78, "total_tokens": 18625592} {"current_steps": 28295, "total_steps": 33920, "loss": 0.2302, "lr": 8.148490911987073e-07, "epoch": 16.683372641509433, "percentage": 83.42, "elapsed_time": "0:54:33", "remaining_time": "0:10:50", "throughput": 5691.82, "total_tokens": 18629592} {"current_steps": 28300, "total_steps": 33920, "loss": 0.3124, "lr": 8.134419674687876e-07, "epoch": 16.68632075471698, "percentage": 83.43, "elapsed_time": "0:54:33", "remaining_time": "0:10:50", "throughput": 5691.61, "total_tokens": 18631928} {"current_steps": 28305, "total_steps": 33920, "loss": 0.3479, "lr": 8.120359521481502e-07, "epoch": 16.68926886792453, "percentage": 83.45, "elapsed_time": "0:54:34", "remaining_time": "0:10:49", "throughput": 5691.59, "total_tokens": 18635000} {"current_steps": 28310, "total_steps": 33920, "loss": 0.2552, "lr": 8.106310456090438e-07, "epoch": 16.692216981132077, "percentage": 83.46, "elapsed_time": "0:54:34", "remaining_time": "0:10:48", "throughput": 5691.54, "total_tokens": 18637784} {"current_steps": 28315, "total_steps": 33920, "loss": 0.2903, "lr": 8.092272482234231e-07, "epoch": 16.69516509433962, "percentage": 83.48, "elapsed_time": "0:54:35", "remaining_time": "0:10:48", "throughput": 5691.68, "total_tokens": 18641496} {"current_steps": 28320, "total_steps": 33920, "loss": 0.3211, "lr": 8.078245603629486e-07, "epoch": 16.69811320754717, "percentage": 83.49, "elapsed_time": "0:54:35", "remaining_time": "0:10:47", "throughput": 5691.65, "total_tokens": 18644568} {"current_steps": 28325, "total_steps": 33920, "loss": 0.3889, "lr": 8.0642298239899e-07, "epoch": 16.701061320754718, "percentage": 83.51, "elapsed_time": "0:54:36", "remaining_time": "0:10:47", "throughput": 5691.7, "total_tokens": 18647928} {"current_steps": 28330, "total_steps": 33920, "loss": 0.2747, "lr": 8.050225147026202e-07, "epoch": 16.704009433962263, "percentage": 83.52, "elapsed_time": "0:54:36", "remaining_time": "0:10:46", "throughput": 5691.62, "total_tokens": 18651096} {"current_steps": 28335, "total_steps": 33920, "loss": 0.3594, "lr": 8.03623157644619e-07, "epoch": 16.70695754716981, "percentage": 83.53, "elapsed_time": "0:54:37", "remaining_time": "0:10:46", "throughput": 5691.61, "total_tokens": 18654072} {"current_steps": 28340, "total_steps": 33920, "loss": 0.4267, "lr": 8.022249115954728e-07, "epoch": 16.70990566037736, "percentage": 83.55, "elapsed_time": "0:54:38", "remaining_time": "0:10:45", "throughput": 5691.55, "total_tokens": 18656920} {"current_steps": 28345, "total_steps": 33920, "loss": 0.2899, "lr": 8.008277769253709e-07, "epoch": 16.712853773584907, "percentage": 83.56, "elapsed_time": "0:54:38", "remaining_time": "0:10:44", "throughput": 5691.55, "total_tokens": 18659992} {"current_steps": 28350, "total_steps": 33920, "loss": 0.2287, "lr": 7.994317540042135e-07, "epoch": 16.715801886792452, "percentage": 83.58, "elapsed_time": "0:54:39", "remaining_time": "0:10:44", "throughput": 5691.43, "total_tokens": 18662520} {"current_steps": 28355, "total_steps": 33920, "loss": 0.3209, "lr": 7.980368432016017e-07, "epoch": 16.71875, "percentage": 83.59, "elapsed_time": "0:54:39", "remaining_time": "0:10:43", "throughput": 5691.35, "total_tokens": 18665176} {"current_steps": 28360, "total_steps": 33920, "loss": 0.2147, "lr": 7.966430448868461e-07, "epoch": 16.721698113207548, "percentage": 83.61, "elapsed_time": "0:54:40", "remaining_time": "0:10:43", "throughput": 5691.25, "total_tokens": 18667992} {"current_steps": 28365, "total_steps": 33920, "loss": 0.237, "lr": 7.952503594289601e-07, "epoch": 16.724646226415093, "percentage": 83.62, "elapsed_time": "0:54:40", "remaining_time": "0:10:42", "throughput": 5691.28, "total_tokens": 18671320} {"current_steps": 28370, "total_steps": 33920, "loss": 0.3905, "lr": 7.93858787196663e-07, "epoch": 16.72759433962264, "percentage": 83.64, "elapsed_time": "0:54:41", "remaining_time": "0:10:41", "throughput": 5691.3, "total_tokens": 18674456} {"current_steps": 28375, "total_steps": 33920, "loss": 0.3396, "lr": 7.92468328558379e-07, "epoch": 16.73054245283019, "percentage": 83.65, "elapsed_time": "0:54:41", "remaining_time": "0:10:41", "throughput": 5691.31, "total_tokens": 18677784} {"current_steps": 28380, "total_steps": 33920, "loss": 0.3874, "lr": 7.910789838822386e-07, "epoch": 16.733490566037737, "percentage": 83.67, "elapsed_time": "0:54:42", "remaining_time": "0:10:40", "throughput": 5691.39, "total_tokens": 18681464} {"current_steps": 28385, "total_steps": 33920, "loss": 0.3085, "lr": 7.89690753536076e-07, "epoch": 16.736438679245282, "percentage": 83.68, "elapsed_time": "0:54:43", "remaining_time": "0:10:40", "throughput": 5691.5, "total_tokens": 18685784} {"current_steps": 28390, "total_steps": 33920, "loss": 0.3756, "lr": 7.883036378874326e-07, "epoch": 16.73938679245283, "percentage": 83.7, "elapsed_time": "0:54:43", "remaining_time": "0:10:39", "throughput": 5691.31, "total_tokens": 18688056} {"current_steps": 28395, "total_steps": 33920, "loss": 0.3254, "lr": 7.86917637303552e-07, "epoch": 16.74233490566038, "percentage": 83.71, "elapsed_time": "0:54:44", "remaining_time": "0:10:39", "throughput": 5691.1, "total_tokens": 18690616} {"current_steps": 28400, "total_steps": 33920, "loss": 0.2289, "lr": 7.855327521513851e-07, "epoch": 16.745283018867923, "percentage": 83.73, "elapsed_time": "0:54:44", "remaining_time": "0:10:38", "throughput": 5690.94, "total_tokens": 18693080} {"current_steps": 28405, "total_steps": 33920, "loss": 0.2533, "lr": 7.841489827975851e-07, "epoch": 16.74823113207547, "percentage": 83.74, "elapsed_time": "0:54:45", "remaining_time": "0:10:37", "throughput": 5690.92, "total_tokens": 18695928} {"current_steps": 28410, "total_steps": 33920, "loss": 0.331, "lr": 7.827663296085109e-07, "epoch": 16.75117924528302, "percentage": 83.76, "elapsed_time": "0:54:45", "remaining_time": "0:10:37", "throughput": 5690.88, "total_tokens": 18698808} {"current_steps": 28415, "total_steps": 33920, "loss": 0.2758, "lr": 7.813847929502255e-07, "epoch": 16.754127358490567, "percentage": 83.77, "elapsed_time": "0:54:46", "remaining_time": "0:10:36", "throughput": 5690.85, "total_tokens": 18701880} {"current_steps": 28420, "total_steps": 33920, "loss": 0.3215, "lr": 7.800043731884982e-07, "epoch": 16.757075471698112, "percentage": 83.79, "elapsed_time": "0:54:46", "remaining_time": "0:10:36", "throughput": 5690.78, "total_tokens": 18705080} {"current_steps": 28425, "total_steps": 33920, "loss": 0.2227, "lr": 7.786250706888005e-07, "epoch": 16.76002358490566, "percentage": 83.8, "elapsed_time": "0:54:47", "remaining_time": "0:10:35", "throughput": 5690.78, "total_tokens": 18708408} {"current_steps": 28430, "total_steps": 33920, "loss": 0.3437, "lr": 7.772468858163085e-07, "epoch": 16.76297169811321, "percentage": 83.81, "elapsed_time": "0:54:48", "remaining_time": "0:10:34", "throughput": 5690.98, "total_tokens": 18712312} {"current_steps": 28435, "total_steps": 33920, "loss": 0.2489, "lr": 7.758698189359026e-07, "epoch": 16.765919811320753, "percentage": 83.83, "elapsed_time": "0:54:48", "remaining_time": "0:10:34", "throughput": 5690.94, "total_tokens": 18715064} {"current_steps": 28440, "total_steps": 33920, "loss": 0.4029, "lr": 7.744938704121658e-07, "epoch": 16.7688679245283, "percentage": 83.84, "elapsed_time": "0:54:49", "remaining_time": "0:10:33", "throughput": 5691.01, "total_tokens": 18718552} {"current_steps": 28445, "total_steps": 33920, "loss": 0.2401, "lr": 7.731190406093892e-07, "epoch": 16.77181603773585, "percentage": 83.86, "elapsed_time": "0:54:50", "remaining_time": "0:10:33", "throughput": 5691.3, "total_tokens": 18725048} {"current_steps": 28450, "total_steps": 33920, "loss": 0.365, "lr": 7.717453298915617e-07, "epoch": 16.774764150943398, "percentage": 83.87, "elapsed_time": "0:54:50", "remaining_time": "0:10:32", "throughput": 5691.22, "total_tokens": 18727736} {"current_steps": 28455, "total_steps": 33920, "loss": 0.3972, "lr": 7.703727386223825e-07, "epoch": 16.777712264150942, "percentage": 83.89, "elapsed_time": "0:54:51", "remaining_time": "0:10:32", "throughput": 5691.35, "total_tokens": 18732888} {"current_steps": 28460, "total_steps": 33920, "loss": 0.2851, "lr": 7.690012671652491e-07, "epoch": 16.78066037735849, "percentage": 83.9, "elapsed_time": "0:54:52", "remaining_time": "0:10:31", "throughput": 5691.27, "total_tokens": 18735768} {"current_steps": 28465, "total_steps": 33920, "loss": 0.3289, "lr": 7.676309158832651e-07, "epoch": 16.78360849056604, "percentage": 83.92, "elapsed_time": "0:54:52", "remaining_time": "0:10:30", "throughput": 5691.32, "total_tokens": 18739192} {"current_steps": 28470, "total_steps": 33920, "loss": 0.3194, "lr": 7.662616851392362e-07, "epoch": 16.786556603773583, "percentage": 83.93, "elapsed_time": "0:54:53", "remaining_time": "0:10:30", "throughput": 5691.3, "total_tokens": 18742136} {"current_steps": 28475, "total_steps": 33920, "loss": 0.3906, "lr": 7.648935752956732e-07, "epoch": 16.78950471698113, "percentage": 83.95, "elapsed_time": "0:54:53", "remaining_time": "0:10:29", "throughput": 5691.09, "total_tokens": 18744344} {"current_steps": 28480, "total_steps": 33920, "loss": 0.2042, "lr": 7.635265867147867e-07, "epoch": 16.79245283018868, "percentage": 83.96, "elapsed_time": "0:54:54", "remaining_time": "0:10:29", "throughput": 5691.12, "total_tokens": 18747576} {"current_steps": 28485, "total_steps": 33920, "loss": 0.4581, "lr": 7.621607197584963e-07, "epoch": 16.795400943396228, "percentage": 83.98, "elapsed_time": "0:54:54", "remaining_time": "0:10:28", "throughput": 5691.19, "total_tokens": 18751608} {"current_steps": 28490, "total_steps": 33920, "loss": 0.2733, "lr": 7.607959747884186e-07, "epoch": 16.798349056603772, "percentage": 83.99, "elapsed_time": "0:54:55", "remaining_time": "0:10:28", "throughput": 5691.11, "total_tokens": 18754296} {"current_steps": 28495, "total_steps": 33920, "loss": 0.2711, "lr": 7.594323521658769e-07, "epoch": 16.80129716981132, "percentage": 84.01, "elapsed_time": "0:54:55", "remaining_time": "0:10:27", "throughput": 5691.25, "total_tokens": 18758200} {"current_steps": 28500, "total_steps": 33920, "loss": 0.3673, "lr": 7.580698522518958e-07, "epoch": 16.80424528301887, "percentage": 84.02, "elapsed_time": "0:54:56", "remaining_time": "0:10:26", "throughput": 5691.27, "total_tokens": 18761432} {"current_steps": 28505, "total_steps": 33920, "loss": 0.3825, "lr": 7.567084754072035e-07, "epoch": 16.807193396226417, "percentage": 84.04, "elapsed_time": "0:54:57", "remaining_time": "0:10:26", "throughput": 5691.31, "total_tokens": 18764600} {"current_steps": 28510, "total_steps": 33920, "loss": 0.3376, "lr": 7.553482219922282e-07, "epoch": 16.81014150943396, "percentage": 84.05, "elapsed_time": "0:54:58", "remaining_time": "0:10:25", "throughput": 5691.7, "total_tokens": 18772664} {"current_steps": 28515, "total_steps": 33920, "loss": 0.3282, "lr": 7.539890923671061e-07, "epoch": 16.81308962264151, "percentage": 84.07, "elapsed_time": "0:54:58", "remaining_time": "0:10:25", "throughput": 5691.8, "total_tokens": 18776792} {"current_steps": 28520, "total_steps": 33920, "loss": 0.3245, "lr": 7.526310868916708e-07, "epoch": 16.816037735849058, "percentage": 84.08, "elapsed_time": "0:54:59", "remaining_time": "0:10:24", "throughput": 5691.78, "total_tokens": 18779768} {"current_steps": 28525, "total_steps": 33920, "loss": 0.2924, "lr": 7.512742059254602e-07, "epoch": 16.818985849056602, "percentage": 84.09, "elapsed_time": "0:54:59", "remaining_time": "0:10:24", "throughput": 5691.76, "total_tokens": 18782680} {"current_steps": 28530, "total_steps": 33920, "loss": 0.3955, "lr": 7.499184498277151e-07, "epoch": 16.82193396226415, "percentage": 84.11, "elapsed_time": "0:55:00", "remaining_time": "0:10:23", "throughput": 5691.55, "total_tokens": 18785176} {"current_steps": 28535, "total_steps": 33920, "loss": 0.3055, "lr": 7.485638189573758e-07, "epoch": 16.8248820754717, "percentage": 84.12, "elapsed_time": "0:55:01", "remaining_time": "0:10:22", "throughput": 5691.57, "total_tokens": 18788632} {"current_steps": 28540, "total_steps": 33920, "loss": 0.311, "lr": 7.472103136730891e-07, "epoch": 16.827830188679247, "percentage": 84.14, "elapsed_time": "0:55:01", "remaining_time": "0:10:22", "throughput": 5691.65, "total_tokens": 18791928} {"current_steps": 28545, "total_steps": 33920, "loss": 0.3034, "lr": 7.458579343331996e-07, "epoch": 16.83077830188679, "percentage": 84.15, "elapsed_time": "0:55:02", "remaining_time": "0:10:21", "throughput": 5691.63, "total_tokens": 18795640} {"current_steps": 28550, "total_steps": 33920, "loss": 0.261, "lr": 7.445066812957569e-07, "epoch": 16.83372641509434, "percentage": 84.17, "elapsed_time": "0:55:02", "remaining_time": "0:10:21", "throughput": 5691.74, "total_tokens": 18799448} {"current_steps": 28555, "total_steps": 33920, "loss": 0.3331, "lr": 7.43156554918511e-07, "epoch": 16.836674528301888, "percentage": 84.18, "elapsed_time": "0:55:03", "remaining_time": "0:10:20", "throughput": 5691.88, "total_tokens": 18804152} {"current_steps": 28560, "total_steps": 33920, "loss": 0.2929, "lr": 7.418075555589132e-07, "epoch": 16.839622641509433, "percentage": 84.2, "elapsed_time": "0:55:04", "remaining_time": "0:10:20", "throughput": 5691.84, "total_tokens": 18807256} {"current_steps": 28565, "total_steps": 33920, "loss": 0.2974, "lr": 7.404596835741168e-07, "epoch": 16.84257075471698, "percentage": 84.21, "elapsed_time": "0:55:04", "remaining_time": "0:10:19", "throughput": 5691.9, "total_tokens": 18811000} {"current_steps": 28570, "total_steps": 33920, "loss": 0.2669, "lr": 7.391129393209751e-07, "epoch": 16.84551886792453, "percentage": 84.23, "elapsed_time": "0:55:05", "remaining_time": "0:10:18", "throughput": 5691.96, "total_tokens": 18814712} {"current_steps": 28575, "total_steps": 33920, "loss": 0.3345, "lr": 7.377673231560478e-07, "epoch": 16.848466981132077, "percentage": 84.24, "elapsed_time": "0:55:06", "remaining_time": "0:10:18", "throughput": 5692.04, "total_tokens": 18818840} {"current_steps": 28580, "total_steps": 33920, "loss": 0.3647, "lr": 7.364228354355907e-07, "epoch": 16.85141509433962, "percentage": 84.26, "elapsed_time": "0:55:06", "remaining_time": "0:10:17", "throughput": 5692.15, "total_tokens": 18822392} {"current_steps": 28585, "total_steps": 33920, "loss": 0.4024, "lr": 7.350794765155627e-07, "epoch": 16.85436320754717, "percentage": 84.27, "elapsed_time": "0:55:07", "remaining_time": "0:10:17", "throughput": 5692.23, "total_tokens": 18826360} {"current_steps": 28590, "total_steps": 33920, "loss": 0.4051, "lr": 7.337372467516246e-07, "epoch": 16.857311320754718, "percentage": 84.29, "elapsed_time": "0:55:07", "remaining_time": "0:10:16", "throughput": 5692.06, "total_tokens": 18829048} {"current_steps": 28595, "total_steps": 33920, "loss": 0.3251, "lr": 7.323961464991369e-07, "epoch": 16.860259433962263, "percentage": 84.3, "elapsed_time": "0:55:08", "remaining_time": "0:10:16", "throughput": 5692.08, "total_tokens": 18832632} {"current_steps": 28600, "total_steps": 33920, "loss": 0.2517, "lr": 7.310561761131601e-07, "epoch": 16.86320754716981, "percentage": 84.32, "elapsed_time": "0:55:09", "remaining_time": "0:10:15", "throughput": 5692.0, "total_tokens": 18835480} {"current_steps": 28605, "total_steps": 33920, "loss": 0.3167, "lr": 7.297173359484605e-07, "epoch": 16.86615566037736, "percentage": 84.33, "elapsed_time": "0:55:09", "remaining_time": "0:10:14", "throughput": 5692.16, "total_tokens": 18839384} {"current_steps": 28610, "total_steps": 33920, "loss": 0.2828, "lr": 7.283796263595e-07, "epoch": 16.869103773584907, "percentage": 84.35, "elapsed_time": "0:55:10", "remaining_time": "0:10:14", "throughput": 5692.03, "total_tokens": 18842136} {"current_steps": 28615, "total_steps": 33920, "loss": 0.2462, "lr": 7.270430477004431e-07, "epoch": 16.872051886792452, "percentage": 84.36, "elapsed_time": "0:55:10", "remaining_time": "0:10:13", "throughput": 5692.03, "total_tokens": 18845336} {"current_steps": 28620, "total_steps": 33920, "loss": 0.2611, "lr": 7.257076003251545e-07, "epoch": 16.875, "percentage": 84.38, "elapsed_time": "0:55:11", "remaining_time": "0:10:13", "throughput": 5691.95, "total_tokens": 18848280} {"current_steps": 28625, "total_steps": 33920, "loss": 0.2586, "lr": 7.243732845871998e-07, "epoch": 16.877948113207548, "percentage": 84.39, "elapsed_time": "0:55:11", "remaining_time": "0:10:12", "throughput": 5691.88, "total_tokens": 18851160} {"current_steps": 28630, "total_steps": 33920, "loss": 0.3454, "lr": 7.230401008398441e-07, "epoch": 16.880896226415093, "percentage": 84.4, "elapsed_time": "0:55:12", "remaining_time": "0:10:12", "throughput": 5691.9, "total_tokens": 18854552} {"current_steps": 28635, "total_steps": 33920, "loss": 0.3094, "lr": 7.217080494360546e-07, "epoch": 16.88384433962264, "percentage": 84.42, "elapsed_time": "0:55:13", "remaining_time": "0:10:11", "throughput": 5691.96, "total_tokens": 18857816} {"current_steps": 28640, "total_steps": 33920, "loss": 0.2784, "lr": 7.20377130728498e-07, "epoch": 16.88679245283019, "percentage": 84.43, "elapsed_time": "0:55:13", "remaining_time": "0:10:10", "throughput": 5692.04, "total_tokens": 18861592} {"current_steps": 28645, "total_steps": 33920, "loss": 0.2352, "lr": 7.190473450695407e-07, "epoch": 16.889740566037737, "percentage": 84.45, "elapsed_time": "0:55:14", "remaining_time": "0:10:10", "throughput": 5691.84, "total_tokens": 18864056} {"current_steps": 28650, "total_steps": 33920, "loss": 0.2812, "lr": 7.177186928112484e-07, "epoch": 16.892688679245282, "percentage": 84.46, "elapsed_time": "0:55:14", "remaining_time": "0:10:09", "throughput": 5691.61, "total_tokens": 18866808} {"current_steps": 28655, "total_steps": 33920, "loss": 0.3897, "lr": 7.163911743053876e-07, "epoch": 16.89563679245283, "percentage": 84.48, "elapsed_time": "0:55:15", "remaining_time": "0:10:09", "throughput": 5691.68, "total_tokens": 18870488} {"current_steps": 28660, "total_steps": 33920, "loss": 0.2308, "lr": 7.150647899034252e-07, "epoch": 16.89858490566038, "percentage": 84.49, "elapsed_time": "0:55:15", "remaining_time": "0:10:08", "throughput": 5691.69, "total_tokens": 18873624} {"current_steps": 28665, "total_steps": 33920, "loss": 0.4488, "lr": 7.13739539956525e-07, "epoch": 16.901533018867923, "percentage": 84.51, "elapsed_time": "0:55:16", "remaining_time": "0:10:08", "throughput": 5691.63, "total_tokens": 18876696} {"current_steps": 28670, "total_steps": 33920, "loss": 0.2335, "lr": 7.124154248155562e-07, "epoch": 16.90448113207547, "percentage": 84.52, "elapsed_time": "0:55:17", "remaining_time": "0:10:07", "throughput": 5691.58, "total_tokens": 18879608} {"current_steps": 28675, "total_steps": 33920, "loss": 0.339, "lr": 7.110924448310813e-07, "epoch": 16.90742924528302, "percentage": 84.54, "elapsed_time": "0:55:17", "remaining_time": "0:10:06", "throughput": 5691.67, "total_tokens": 18883576} {"current_steps": 28680, "total_steps": 33920, "loss": 0.2949, "lr": 7.097706003533666e-07, "epoch": 16.910377358490567, "percentage": 84.55, "elapsed_time": "0:55:18", "remaining_time": "0:10:06", "throughput": 5691.58, "total_tokens": 18886296} {"current_steps": 28685, "total_steps": 33920, "loss": 0.305, "lr": 7.084498917323751e-07, "epoch": 16.913325471698112, "percentage": 84.57, "elapsed_time": "0:55:18", "remaining_time": "0:10:05", "throughput": 5691.42, "total_tokens": 18888888} {"current_steps": 28690, "total_steps": 33920, "loss": 0.3394, "lr": 7.071303193177698e-07, "epoch": 16.91627358490566, "percentage": 84.58, "elapsed_time": "0:55:19", "remaining_time": "0:10:05", "throughput": 5691.54, "total_tokens": 18892568} {"current_steps": 28695, "total_steps": 33920, "loss": 0.2748, "lr": 7.058118834589133e-07, "epoch": 16.91922169811321, "percentage": 84.6, "elapsed_time": "0:55:19", "remaining_time": "0:10:04", "throughput": 5691.53, "total_tokens": 18895544} {"current_steps": 28700, "total_steps": 33920, "loss": 0.2788, "lr": 7.044945845048684e-07, "epoch": 16.922169811320753, "percentage": 84.61, "elapsed_time": "0:55:20", "remaining_time": "0:10:03", "throughput": 5691.48, "total_tokens": 18898520} {"current_steps": 28705, "total_steps": 33920, "loss": 0.3332, "lr": 7.031784228043948e-07, "epoch": 16.9251179245283, "percentage": 84.63, "elapsed_time": "0:55:21", "remaining_time": "0:10:03", "throughput": 5691.47, "total_tokens": 18902168} {"current_steps": 28710, "total_steps": 33920, "loss": 0.3683, "lr": 7.01863398705952e-07, "epoch": 16.92806603773585, "percentage": 84.64, "elapsed_time": "0:55:21", "remaining_time": "0:10:02", "throughput": 5691.42, "total_tokens": 18905208} {"current_steps": 28715, "total_steps": 33920, "loss": 0.3794, "lr": 7.005495125576983e-07, "epoch": 16.931014150943398, "percentage": 84.66, "elapsed_time": "0:55:22", "remaining_time": "0:10:02", "throughput": 5691.39, "total_tokens": 18908120} {"current_steps": 28720, "total_steps": 33920, "loss": 0.3158, "lr": 6.99236764707491e-07, "epoch": 16.933962264150942, "percentage": 84.67, "elapsed_time": "0:55:22", "remaining_time": "0:10:01", "throughput": 5691.43, "total_tokens": 18911800} {"current_steps": 28725, "total_steps": 33920, "loss": 0.4096, "lr": 6.979251555028843e-07, "epoch": 16.93691037735849, "percentage": 84.68, "elapsed_time": "0:55:23", "remaining_time": "0:10:01", "throughput": 5691.5, "total_tokens": 18915416} {"current_steps": 28730, "total_steps": 33920, "loss": 0.2819, "lr": 6.966146852911332e-07, "epoch": 16.93985849056604, "percentage": 84.7, "elapsed_time": "0:55:23", "remaining_time": "0:10:00", "throughput": 5691.49, "total_tokens": 18918328} {"current_steps": 28735, "total_steps": 33920, "loss": 0.2565, "lr": 6.953053544191923e-07, "epoch": 16.942806603773583, "percentage": 84.71, "elapsed_time": "0:55:24", "remaining_time": "0:09:59", "throughput": 5691.5, "total_tokens": 18921784} {"current_steps": 28740, "total_steps": 33920, "loss": 0.3185, "lr": 6.939971632337111e-07, "epoch": 16.94575471698113, "percentage": 84.73, "elapsed_time": "0:55:25", "remaining_time": "0:09:59", "throughput": 5691.64, "total_tokens": 18925656} {"current_steps": 28745, "total_steps": 33920, "loss": 0.3391, "lr": 6.926901120810387e-07, "epoch": 16.94870283018868, "percentage": 84.74, "elapsed_time": "0:55:25", "remaining_time": "0:09:58", "throughput": 5691.64, "total_tokens": 18928632} {"current_steps": 28750, "total_steps": 33920, "loss": 0.3481, "lr": 6.91384201307222e-07, "epoch": 16.951650943396228, "percentage": 84.76, "elapsed_time": "0:55:26", "remaining_time": "0:09:58", "throughput": 5691.5, "total_tokens": 18931192} {"current_steps": 28755, "total_steps": 33920, "loss": 0.4799, "lr": 6.900794312580078e-07, "epoch": 16.954599056603772, "percentage": 84.77, "elapsed_time": "0:55:26", "remaining_time": "0:09:57", "throughput": 5691.41, "total_tokens": 18933784} {"current_steps": 28760, "total_steps": 33920, "loss": 0.3484, "lr": 6.887758022788377e-07, "epoch": 16.95754716981132, "percentage": 84.79, "elapsed_time": "0:55:27", "remaining_time": "0:09:56", "throughput": 5691.47, "total_tokens": 18937560} {"current_steps": 28765, "total_steps": 33920, "loss": 0.3171, "lr": 6.874733147148549e-07, "epoch": 16.96049528301887, "percentage": 84.8, "elapsed_time": "0:55:27", "remaining_time": "0:09:56", "throughput": 5691.43, "total_tokens": 18940536} {"current_steps": 28770, "total_steps": 33920, "loss": 0.3087, "lr": 6.861719689108987e-07, "epoch": 16.963443396226417, "percentage": 84.82, "elapsed_time": "0:55:28", "remaining_time": "0:09:55", "throughput": 5691.31, "total_tokens": 18943384} {"current_steps": 28775, "total_steps": 33920, "loss": 0.294, "lr": 6.84871765211505e-07, "epoch": 16.96639150943396, "percentage": 84.83, "elapsed_time": "0:55:29", "remaining_time": "0:09:55", "throughput": 5691.43, "total_tokens": 18947032} {"current_steps": 28780, "total_steps": 33920, "loss": 0.3294, "lr": 6.835727039609086e-07, "epoch": 16.96933962264151, "percentage": 84.85, "elapsed_time": "0:55:29", "remaining_time": "0:09:54", "throughput": 5691.33, "total_tokens": 18950008} {"current_steps": 28785, "total_steps": 33920, "loss": 0.2198, "lr": 6.822747855030415e-07, "epoch": 16.972287735849058, "percentage": 84.86, "elapsed_time": "0:55:30", "remaining_time": "0:09:54", "throughput": 5691.08, "total_tokens": 18952120} {"current_steps": 28790, "total_steps": 33920, "loss": 0.2426, "lr": 6.809780101815322e-07, "epoch": 16.975235849056602, "percentage": 84.88, "elapsed_time": "0:55:30", "remaining_time": "0:09:53", "throughput": 5691.1, "total_tokens": 18955384} {"current_steps": 28795, "total_steps": 33920, "loss": 0.4315, "lr": 6.796823783397099e-07, "epoch": 16.97818396226415, "percentage": 84.89, "elapsed_time": "0:55:31", "remaining_time": "0:09:52", "throughput": 5691.08, "total_tokens": 18958328} {"current_steps": 28800, "total_steps": 33920, "loss": 0.5022, "lr": 6.783878903205976e-07, "epoch": 16.9811320754717, "percentage": 84.91, "elapsed_time": "0:55:31", "remaining_time": "0:09:52", "throughput": 5691.17, "total_tokens": 18961976} {"current_steps": 28805, "total_steps": 33920, "loss": 0.3399, "lr": 6.77094546466916e-07, "epoch": 16.984080188679247, "percentage": 84.92, "elapsed_time": "0:55:32", "remaining_time": "0:09:51", "throughput": 5691.23, "total_tokens": 18965752} {"current_steps": 28810, "total_steps": 33920, "loss": 0.3825, "lr": 6.758023471210845e-07, "epoch": 16.98702830188679, "percentage": 84.94, "elapsed_time": "0:55:33", "remaining_time": "0:09:51", "throughput": 5691.21, "total_tokens": 18969016} {"current_steps": 28815, "total_steps": 33920, "loss": 0.224, "lr": 6.745112926252162e-07, "epoch": 16.98997641509434, "percentage": 84.95, "elapsed_time": "0:55:33", "remaining_time": "0:09:50", "throughput": 5691.05, "total_tokens": 18971672} {"current_steps": 28820, "total_steps": 33920, "loss": 0.2555, "lr": 6.732213833211265e-07, "epoch": 16.992924528301888, "percentage": 84.96, "elapsed_time": "0:55:34", "remaining_time": "0:09:50", "throughput": 5691.07, "total_tokens": 18974776} {"current_steps": 28825, "total_steps": 33920, "loss": 0.375, "lr": 6.719326195503218e-07, "epoch": 16.995872641509433, "percentage": 84.98, "elapsed_time": "0:55:34", "remaining_time": "0:09:49", "throughput": 5690.9, "total_tokens": 18977528} {"current_steps": 28830, "total_steps": 33920, "loss": 0.303, "lr": 6.706450016540094e-07, "epoch": 16.99882075471698, "percentage": 84.99, "elapsed_time": "0:55:35", "remaining_time": "0:09:48", "throughput": 5691.03, "total_tokens": 18981432} {"current_steps": 28835, "total_steps": 33920, "loss": 0.2273, "lr": 6.69358529973092e-07, "epoch": 17.00176886792453, "percentage": 85.01, "elapsed_time": "0:55:36", "remaining_time": "0:09:48", "throughput": 5690.29, "total_tokens": 18984456} {"current_steps": 28840, "total_steps": 33920, "loss": 0.2474, "lr": 6.680732048481681e-07, "epoch": 17.004716981132077, "percentage": 85.02, "elapsed_time": "0:55:36", "remaining_time": "0:09:47", "throughput": 5690.18, "total_tokens": 18987144} {"current_steps": 28845, "total_steps": 33920, "loss": 0.311, "lr": 6.667890266195321e-07, "epoch": 17.00766509433962, "percentage": 85.04, "elapsed_time": "0:55:37", "remaining_time": "0:09:47", "throughput": 5690.14, "total_tokens": 18990280} {"current_steps": 28850, "total_steps": 33920, "loss": 0.2849, "lr": 6.655059956271759e-07, "epoch": 17.01061320754717, "percentage": 85.05, "elapsed_time": "0:55:38", "remaining_time": "0:09:46", "throughput": 5690.28, "total_tokens": 18994376} {"current_steps": 28855, "total_steps": 33920, "loss": 0.2264, "lr": 6.642241122107884e-07, "epoch": 17.013561320754718, "percentage": 85.07, "elapsed_time": "0:55:38", "remaining_time": "0:09:46", "throughput": 5690.2, "total_tokens": 18997128} {"current_steps": 28860, "total_steps": 33920, "loss": 0.2657, "lr": 6.629433767097537e-07, "epoch": 17.016509433962263, "percentage": 85.08, "elapsed_time": "0:55:39", "remaining_time": "0:09:45", "throughput": 5690.07, "total_tokens": 18999784} {"current_steps": 28865, "total_steps": 33920, "loss": 0.3488, "lr": 6.616637894631517e-07, "epoch": 17.01945754716981, "percentage": 85.1, "elapsed_time": "0:55:39", "remaining_time": "0:09:44", "throughput": 5690.09, "total_tokens": 19003208} {"current_steps": 28870, "total_steps": 33920, "loss": 0.3017, "lr": 6.603853508097591e-07, "epoch": 17.02240566037736, "percentage": 85.11, "elapsed_time": "0:55:40", "remaining_time": "0:09:44", "throughput": 5690.15, "total_tokens": 19006504} {"current_steps": 28875, "total_steps": 33920, "loss": 0.2404, "lr": 6.591080610880468e-07, "epoch": 17.025353773584907, "percentage": 85.13, "elapsed_time": "0:55:40", "remaining_time": "0:09:43", "throughput": 5690.18, "total_tokens": 19009704} {"current_steps": 28880, "total_steps": 33920, "loss": 0.4329, "lr": 6.578319206361828e-07, "epoch": 17.028301886792452, "percentage": 85.14, "elapsed_time": "0:55:41", "remaining_time": "0:09:43", "throughput": 5690.22, "total_tokens": 19013128} {"current_steps": 28885, "total_steps": 33920, "loss": 0.3351, "lr": 6.565569297920327e-07, "epoch": 17.03125, "percentage": 85.16, "elapsed_time": "0:55:41", "remaining_time": "0:09:42", "throughput": 5690.18, "total_tokens": 19015976} {"current_steps": 28890, "total_steps": 33920, "loss": 0.1988, "lr": 6.552830888931544e-07, "epoch": 17.034198113207548, "percentage": 85.17, "elapsed_time": "0:55:42", "remaining_time": "0:09:41", "throughput": 5690.13, "total_tokens": 19019080} {"current_steps": 28895, "total_steps": 33920, "loss": 0.2964, "lr": 6.540103982768031e-07, "epoch": 17.037146226415093, "percentage": 85.19, "elapsed_time": "0:55:43", "remaining_time": "0:09:41", "throughput": 5690.12, "total_tokens": 19022312} {"current_steps": 28900, "total_steps": 33920, "loss": 0.3153, "lr": 6.527388582799293e-07, "epoch": 17.04009433962264, "percentage": 85.2, "elapsed_time": "0:55:43", "remaining_time": "0:09:40", "throughput": 5690.04, "total_tokens": 19025064} {"current_steps": 28905, "total_steps": 33920, "loss": 0.2507, "lr": 6.514684692391782e-07, "epoch": 17.04304245283019, "percentage": 85.22, "elapsed_time": "0:55:44", "remaining_time": "0:09:40", "throughput": 5690.08, "total_tokens": 19029128} {"current_steps": 28910, "total_steps": 33920, "loss": 0.3196, "lr": 6.501992314908895e-07, "epoch": 17.045990566037737, "percentage": 85.23, "elapsed_time": "0:55:44", "remaining_time": "0:09:39", "throughput": 5690.01, "total_tokens": 19032168} {"current_steps": 28915, "total_steps": 33920, "loss": 0.251, "lr": 6.489311453711017e-07, "epoch": 17.048938679245282, "percentage": 85.24, "elapsed_time": "0:55:45", "remaining_time": "0:09:39", "throughput": 5690.18, "total_tokens": 19036456} {"current_steps": 28920, "total_steps": 33920, "loss": 0.3522, "lr": 6.476642112155457e-07, "epoch": 17.05188679245283, "percentage": 85.26, "elapsed_time": "0:55:46", "remaining_time": "0:09:38", "throughput": 5690.2, "total_tokens": 19039848} {"current_steps": 28925, "total_steps": 33920, "loss": 0.2651, "lr": 6.463984293596476e-07, "epoch": 17.05483490566038, "percentage": 85.27, "elapsed_time": "0:55:46", "remaining_time": "0:09:37", "throughput": 5690.29, "total_tokens": 19043752} {"current_steps": 28930, "total_steps": 33920, "loss": 0.2463, "lr": 6.451338001385282e-07, "epoch": 17.057783018867923, "percentage": 85.29, "elapsed_time": "0:55:47", "remaining_time": "0:09:37", "throughput": 5690.49, "total_tokens": 19049128} {"current_steps": 28935, "total_steps": 33920, "loss": 0.2951, "lr": 6.438703238870037e-07, "epoch": 17.06073113207547, "percentage": 85.3, "elapsed_time": "0:55:48", "remaining_time": "0:09:36", "throughput": 5690.33, "total_tokens": 19051688} {"current_steps": 28940, "total_steps": 33920, "loss": 0.2147, "lr": 6.426080009395846e-07, "epoch": 17.06367924528302, "percentage": 85.32, "elapsed_time": "0:55:48", "remaining_time": "0:09:36", "throughput": 5690.38, "total_tokens": 19055208} {"current_steps": 28945, "total_steps": 33920, "loss": 0.2424, "lr": 6.413468316304755e-07, "epoch": 17.066627358490567, "percentage": 85.33, "elapsed_time": "0:55:49", "remaining_time": "0:09:35", "throughput": 5690.3, "total_tokens": 19058152} {"current_steps": 28950, "total_steps": 33920, "loss": 0.3135, "lr": 6.400868162935786e-07, "epoch": 17.069575471698112, "percentage": 85.35, "elapsed_time": "0:55:49", "remaining_time": "0:09:35", "throughput": 5690.1, "total_tokens": 19060584} {"current_steps": 28955, "total_steps": 33920, "loss": 0.373, "lr": 6.388279552624877e-07, "epoch": 17.07252358490566, "percentage": 85.36, "elapsed_time": "0:55:50", "remaining_time": "0:09:34", "throughput": 5689.9, "total_tokens": 19062888} {"current_steps": 28960, "total_steps": 33920, "loss": 0.296, "lr": 6.37570248870491e-07, "epoch": 17.07547169811321, "percentage": 85.38, "elapsed_time": "0:55:50", "remaining_time": "0:09:33", "throughput": 5689.92, "total_tokens": 19066120} {"current_steps": 28965, "total_steps": 33920, "loss": 0.3195, "lr": 6.363136974505718e-07, "epoch": 17.078419811320753, "percentage": 85.39, "elapsed_time": "0:55:51", "remaining_time": "0:09:33", "throughput": 5689.73, "total_tokens": 19068488} {"current_steps": 28970, "total_steps": 33920, "loss": 0.331, "lr": 6.350583013354078e-07, "epoch": 17.0813679245283, "percentage": 85.41, "elapsed_time": "0:55:51", "remaining_time": "0:09:32", "throughput": 5689.74, "total_tokens": 19071816} {"current_steps": 28975, "total_steps": 33920, "loss": 0.3813, "lr": 6.338040608573693e-07, "epoch": 17.08431603773585, "percentage": 85.42, "elapsed_time": "0:55:52", "remaining_time": "0:09:32", "throughput": 5689.66, "total_tokens": 19074952} {"current_steps": 28980, "total_steps": 33920, "loss": 0.3138, "lr": 6.325509763485238e-07, "epoch": 17.087264150943398, "percentage": 85.44, "elapsed_time": "0:55:53", "remaining_time": "0:09:31", "throughput": 5689.53, "total_tokens": 19077448} {"current_steps": 28985, "total_steps": 33920, "loss": 0.3523, "lr": 6.312990481406301e-07, "epoch": 17.090212264150942, "percentage": 85.45, "elapsed_time": "0:55:53", "remaining_time": "0:09:31", "throughput": 5689.46, "total_tokens": 19080712} {"current_steps": 28990, "total_steps": 33920, "loss": 0.2523, "lr": 6.300482765651411e-07, "epoch": 17.09316037735849, "percentage": 85.47, "elapsed_time": "0:55:54", "remaining_time": "0:09:30", "throughput": 5689.43, "total_tokens": 19083624} {"current_steps": 28995, "total_steps": 33920, "loss": 0.2042, "lr": 6.28798661953205e-07, "epoch": 17.09610849056604, "percentage": 85.48, "elapsed_time": "0:55:54", "remaining_time": "0:09:29", "throughput": 5689.53, "total_tokens": 19088040} {"current_steps": 29000, "total_steps": 33920, "loss": 0.3421, "lr": 6.275502046356618e-07, "epoch": 17.099056603773583, "percentage": 85.5, "elapsed_time": "0:55:55", "remaining_time": "0:09:29", "throughput": 5689.42, "total_tokens": 19090952} {"current_steps": 29005, "total_steps": 33920, "loss": 0.3413, "lr": 6.263029049430447e-07, "epoch": 17.10200471698113, "percentage": 85.51, "elapsed_time": "0:55:56", "remaining_time": "0:09:28", "throughput": 5689.47, "total_tokens": 19094184} {"current_steps": 29010, "total_steps": 33920, "loss": 0.3831, "lr": 6.250567632055832e-07, "epoch": 17.10495283018868, "percentage": 85.52, "elapsed_time": "0:55:56", "remaining_time": "0:09:28", "throughput": 5689.63, "total_tokens": 19098824} {"current_steps": 29015, "total_steps": 33920, "loss": 0.2814, "lr": 6.238117797532e-07, "epoch": 17.107900943396228, "percentage": 85.54, "elapsed_time": "0:55:57", "remaining_time": "0:09:27", "throughput": 5689.79, "total_tokens": 19102920} {"current_steps": 29020, "total_steps": 33920, "loss": 0.3795, "lr": 6.225679549155083e-07, "epoch": 17.110849056603772, "percentage": 85.55, "elapsed_time": "0:55:57", "remaining_time": "0:09:26", "throughput": 5689.65, "total_tokens": 19105416} {"current_steps": 29025, "total_steps": 33920, "loss": 0.3093, "lr": 6.213252890218163e-07, "epoch": 17.11379716981132, "percentage": 85.57, "elapsed_time": "0:55:58", "remaining_time": "0:09:26", "throughput": 5689.72, "total_tokens": 19109384} {"current_steps": 29030, "total_steps": 33920, "loss": 0.3172, "lr": 6.200837824011247e-07, "epoch": 17.11674528301887, "percentage": 85.58, "elapsed_time": "0:55:59", "remaining_time": "0:09:25", "throughput": 5689.64, "total_tokens": 19112104} {"current_steps": 29035, "total_steps": 33920, "loss": 0.2909, "lr": 6.188434353821282e-07, "epoch": 17.119693396226417, "percentage": 85.6, "elapsed_time": "0:55:59", "remaining_time": "0:09:25", "throughput": 5689.64, "total_tokens": 19115528} {"current_steps": 29040, "total_steps": 33920, "loss": 0.2495, "lr": 6.176042482932132e-07, "epoch": 17.12264150943396, "percentage": 85.61, "elapsed_time": "0:56:00", "remaining_time": "0:09:24", "throughput": 5689.66, "total_tokens": 19118984} {"current_steps": 29045, "total_steps": 33920, "loss": 0.3541, "lr": 6.163662214624616e-07, "epoch": 17.12558962264151, "percentage": 85.63, "elapsed_time": "0:56:00", "remaining_time": "0:09:24", "throughput": 5689.82, "total_tokens": 19122856} {"current_steps": 29050, "total_steps": 33920, "loss": 0.3419, "lr": 6.151293552176451e-07, "epoch": 17.128537735849058, "percentage": 85.64, "elapsed_time": "0:56:01", "remaining_time": "0:09:23", "throughput": 5689.81, "total_tokens": 19125768} {"current_steps": 29055, "total_steps": 33920, "loss": 0.2841, "lr": 6.138936498862291e-07, "epoch": 17.131485849056602, "percentage": 85.66, "elapsed_time": "0:56:01", "remaining_time": "0:09:22", "throughput": 5689.74, "total_tokens": 19128712} {"current_steps": 29060, "total_steps": 33920, "loss": 0.3984, "lr": 6.126591057953729e-07, "epoch": 17.13443396226415, "percentage": 85.67, "elapsed_time": "0:56:02", "remaining_time": "0:09:22", "throughput": 5689.58, "total_tokens": 19131208} {"current_steps": 29065, "total_steps": 33920, "loss": 0.3307, "lr": 6.114257232719267e-07, "epoch": 17.1373820754717, "percentage": 85.69, "elapsed_time": "0:56:03", "remaining_time": "0:09:21", "throughput": 5689.62, "total_tokens": 19135112} {"current_steps": 29070, "total_steps": 33920, "loss": 0.3551, "lr": 6.101935026424332e-07, "epoch": 17.140330188679247, "percentage": 85.7, "elapsed_time": "0:56:03", "remaining_time": "0:09:21", "throughput": 5689.43, "total_tokens": 19137576} {"current_steps": 29075, "total_steps": 33920, "loss": 0.2981, "lr": 6.089624442331293e-07, "epoch": 17.14327830188679, "percentage": 85.72, "elapsed_time": "0:56:04", "remaining_time": "0:09:20", "throughput": 5689.43, "total_tokens": 19140584} {"current_steps": 29080, "total_steps": 33920, "loss": 0.2451, "lr": 6.077325483699432e-07, "epoch": 17.14622641509434, "percentage": 85.73, "elapsed_time": "0:56:04", "remaining_time": "0:09:20", "throughput": 5689.43, "total_tokens": 19143816} {"current_steps": 29085, "total_steps": 33920, "loss": 0.3054, "lr": 6.065038153784947e-07, "epoch": 17.149174528301888, "percentage": 85.75, "elapsed_time": "0:56:05", "remaining_time": "0:09:19", "throughput": 5689.52, "total_tokens": 19147240} {"current_steps": 29090, "total_steps": 33920, "loss": 0.351, "lr": 6.052762455840955e-07, "epoch": 17.152122641509433, "percentage": 85.76, "elapsed_time": "0:56:05", "remaining_time": "0:09:18", "throughput": 5689.55, "total_tokens": 19150344} {"current_steps": 29095, "total_steps": 33920, "loss": 0.2785, "lr": 6.040498393117494e-07, "epoch": 17.15507075471698, "percentage": 85.78, "elapsed_time": "0:56:06", "remaining_time": "0:09:18", "throughput": 5689.48, "total_tokens": 19153128} {"current_steps": 29100, "total_steps": 33920, "loss": 0.3897, "lr": 6.028245968861551e-07, "epoch": 17.15801886792453, "percentage": 85.79, "elapsed_time": "0:56:06", "remaining_time": "0:09:17", "throughput": 5689.29, "total_tokens": 19155592} {"current_steps": 29105, "total_steps": 33920, "loss": 0.3127, "lr": 6.016005186316987e-07, "epoch": 17.160966981132077, "percentage": 85.8, "elapsed_time": "0:56:07", "remaining_time": "0:09:17", "throughput": 5689.3, "total_tokens": 19159528} {"current_steps": 29110, "total_steps": 33920, "loss": 0.3388, "lr": 6.003776048724614e-07, "epoch": 17.16391509433962, "percentage": 85.82, "elapsed_time": "0:56:08", "remaining_time": "0:09:16", "throughput": 5689.3, "total_tokens": 19163464} {"current_steps": 29115, "total_steps": 33920, "loss": 0.3593, "lr": 5.991558559322152e-07, "epoch": 17.16686320754717, "percentage": 85.83, "elapsed_time": "0:56:08", "remaining_time": "0:09:15", "throughput": 5689.27, "total_tokens": 19166632} {"current_steps": 29120, "total_steps": 33920, "loss": 0.3632, "lr": 5.979352721344223e-07, "epoch": 17.169811320754718, "percentage": 85.85, "elapsed_time": "0:56:09", "remaining_time": "0:09:15", "throughput": 5689.23, "total_tokens": 19169608} {"current_steps": 29125, "total_steps": 33920, "loss": 0.3053, "lr": 5.967158538022383e-07, "epoch": 17.172759433962263, "percentage": 85.86, "elapsed_time": "0:56:09", "remaining_time": "0:09:14", "throughput": 5689.23, "total_tokens": 19172616} {"current_steps": 29130, "total_steps": 33920, "loss": 0.3277, "lr": 5.954976012585078e-07, "epoch": 17.17570754716981, "percentage": 85.88, "elapsed_time": "0:56:10", "remaining_time": "0:09:14", "throughput": 5689.06, "total_tokens": 19175016} {"current_steps": 29135, "total_steps": 33920, "loss": 0.297, "lr": 5.942805148257713e-07, "epoch": 17.17865566037736, "percentage": 85.89, "elapsed_time": "0:56:11", "remaining_time": "0:09:13", "throughput": 5689.01, "total_tokens": 19177960} {"current_steps": 29140, "total_steps": 33920, "loss": 0.3035, "lr": 5.930645948262553e-07, "epoch": 17.181603773584907, "percentage": 85.91, "elapsed_time": "0:56:11", "remaining_time": "0:09:13", "throughput": 5688.9, "total_tokens": 19180584} {"current_steps": 29145, "total_steps": 33920, "loss": 0.2727, "lr": 5.918498415818813e-07, "epoch": 17.184551886792452, "percentage": 85.92, "elapsed_time": "0:56:12", "remaining_time": "0:09:12", "throughput": 5688.95, "total_tokens": 19183880} {"current_steps": 29150, "total_steps": 33920, "loss": 0.2697, "lr": 5.906362554142592e-07, "epoch": 17.1875, "percentage": 85.94, "elapsed_time": "0:56:12", "remaining_time": "0:09:11", "throughput": 5689.05, "total_tokens": 19187944} {"current_steps": 29155, "total_steps": 33920, "loss": 0.3094, "lr": 5.894238366446925e-07, "epoch": 17.190448113207548, "percentage": 85.95, "elapsed_time": "0:56:13", "remaining_time": "0:09:11", "throughput": 5689.12, "total_tokens": 19191912} {"current_steps": 29160, "total_steps": 33920, "loss": 0.2264, "lr": 5.882125855941723e-07, "epoch": 17.193396226415093, "percentage": 85.97, "elapsed_time": "0:56:13", "remaining_time": "0:09:10", "throughput": 5689.2, "total_tokens": 19195336} {"current_steps": 29165, "total_steps": 33920, "loss": 0.2723, "lr": 5.870025025833842e-07, "epoch": 17.19634433962264, "percentage": 85.98, "elapsed_time": "0:56:14", "remaining_time": "0:09:10", "throughput": 5689.27, "total_tokens": 19198856} {"current_steps": 29170, "total_steps": 33920, "loss": 0.2278, "lr": 5.857935879327031e-07, "epoch": 17.19929245283019, "percentage": 86.0, "elapsed_time": "0:56:15", "remaining_time": "0:09:09", "throughput": 5689.15, "total_tokens": 19201832} {"current_steps": 29175, "total_steps": 33920, "loss": 0.348, "lr": 5.845858419621936e-07, "epoch": 17.202240566037737, "percentage": 86.01, "elapsed_time": "0:56:15", "remaining_time": "0:09:09", "throughput": 5689.11, "total_tokens": 19204872} {"current_steps": 29180, "total_steps": 33920, "loss": 0.3241, "lr": 5.83379264991612e-07, "epoch": 17.205188679245282, "percentage": 86.03, "elapsed_time": "0:56:16", "remaining_time": "0:09:08", "throughput": 5689.05, "total_tokens": 19207688} {"current_steps": 29185, "total_steps": 33920, "loss": 0.2574, "lr": 5.821738573404046e-07, "epoch": 17.20813679245283, "percentage": 86.04, "elapsed_time": "0:56:16", "remaining_time": "0:09:07", "throughput": 5688.96, "total_tokens": 19210344} {"current_steps": 29190, "total_steps": 33920, "loss": 0.2531, "lr": 5.80969619327707e-07, "epoch": 17.21108490566038, "percentage": 86.06, "elapsed_time": "0:56:17", "remaining_time": "0:09:07", "throughput": 5689.04, "total_tokens": 19213768} {"current_steps": 29195, "total_steps": 33920, "loss": 0.2591, "lr": 5.797665512723488e-07, "epoch": 17.214033018867923, "percentage": 86.07, "elapsed_time": "0:56:17", "remaining_time": "0:09:06", "throughput": 5689.03, "total_tokens": 19216840} {"current_steps": 29200, "total_steps": 33920, "loss": 0.2949, "lr": 5.785646534928452e-07, "epoch": 17.21698113207547, "percentage": 86.08, "elapsed_time": "0:56:18", "remaining_time": "0:09:06", "throughput": 5689.06, "total_tokens": 19220488} {"current_steps": 29205, "total_steps": 33920, "loss": 0.2233, "lr": 5.77363926307406e-07, "epoch": 17.21992924528302, "percentage": 86.1, "elapsed_time": "0:56:19", "remaining_time": "0:09:05", "throughput": 5689.24, "total_tokens": 19224744} {"current_steps": 29210, "total_steps": 33920, "loss": 0.2865, "lr": 5.761643700339281e-07, "epoch": 17.222877358490567, "percentage": 86.11, "elapsed_time": "0:56:19", "remaining_time": "0:09:04", "throughput": 5689.16, "total_tokens": 19227912} {"current_steps": 29215, "total_steps": 33920, "loss": 0.3305, "lr": 5.749659849899985e-07, "epoch": 17.225825471698112, "percentage": 86.13, "elapsed_time": "0:56:20", "remaining_time": "0:09:04", "throughput": 5689.11, "total_tokens": 19231080} {"current_steps": 29220, "total_steps": 33920, "loss": 0.3174, "lr": 5.737687714928953e-07, "epoch": 17.22877358490566, "percentage": 86.14, "elapsed_time": "0:56:20", "remaining_time": "0:09:03", "throughput": 5689.21, "total_tokens": 19235176} {"current_steps": 29225, "total_steps": 33920, "loss": 0.3281, "lr": 5.725727298595846e-07, "epoch": 17.23172169811321, "percentage": 86.16, "elapsed_time": "0:56:21", "remaining_time": "0:09:03", "throughput": 5689.1, "total_tokens": 19237928} {"current_steps": 29230, "total_steps": 33920, "loss": 0.2727, "lr": 5.71377860406726e-07, "epoch": 17.234669811320753, "percentage": 86.17, "elapsed_time": "0:56:22", "remaining_time": "0:09:02", "throughput": 5689.08, "total_tokens": 19241352} {"current_steps": 29235, "total_steps": 33920, "loss": 0.3739, "lr": 5.701841634506655e-07, "epoch": 17.2376179245283, "percentage": 86.19, "elapsed_time": "0:56:22", "remaining_time": "0:09:02", "throughput": 5689.17, "total_tokens": 19244840} {"current_steps": 29240, "total_steps": 33920, "loss": 0.3448, "lr": 5.689916393074391e-07, "epoch": 17.24056603773585, "percentage": 86.2, "elapsed_time": "0:56:23", "remaining_time": "0:09:01", "throughput": 5689.17, "total_tokens": 19247880} {"current_steps": 29245, "total_steps": 33920, "loss": 0.2501, "lr": 5.678002882927725e-07, "epoch": 17.243514150943398, "percentage": 86.22, "elapsed_time": "0:56:23", "remaining_time": "0:09:00", "throughput": 5689.07, "total_tokens": 19250664} {"current_steps": 29250, "total_steps": 33920, "loss": 0.2344, "lr": 5.666101107220811e-07, "epoch": 17.246462264150942, "percentage": 86.23, "elapsed_time": "0:56:24", "remaining_time": "0:09:00", "throughput": 5688.93, "total_tokens": 19253448} {"current_steps": 29255, "total_steps": 33920, "loss": 0.3147, "lr": 5.654211069104693e-07, "epoch": 17.24941037735849, "percentage": 86.25, "elapsed_time": "0:56:24", "remaining_time": "0:08:59", "throughput": 5688.83, "total_tokens": 19256520} {"current_steps": 29260, "total_steps": 33920, "loss": 0.2885, "lr": 5.642332771727321e-07, "epoch": 17.25235849056604, "percentage": 86.26, "elapsed_time": "0:56:25", "remaining_time": "0:08:59", "throughput": 5688.65, "total_tokens": 19259112} {"current_steps": 29265, "total_steps": 33920, "loss": 0.2681, "lr": 5.630466218233521e-07, "epoch": 17.255306603773583, "percentage": 86.28, "elapsed_time": "0:56:26", "remaining_time": "0:08:58", "throughput": 5688.45, "total_tokens": 19262024} {"current_steps": 29270, "total_steps": 33920, "loss": 0.2663, "lr": 5.618611411765007e-07, "epoch": 17.25825471698113, "percentage": 86.29, "elapsed_time": "0:56:26", "remaining_time": "0:08:58", "throughput": 5688.69, "total_tokens": 19266568} {"current_steps": 29275, "total_steps": 33920, "loss": 0.3633, "lr": 5.606768355460401e-07, "epoch": 17.26120283018868, "percentage": 86.31, "elapsed_time": "0:56:27", "remaining_time": "0:08:57", "throughput": 5688.5, "total_tokens": 19269192} {"current_steps": 29280, "total_steps": 33920, "loss": 0.2589, "lr": 5.594937052455191e-07, "epoch": 17.264150943396228, "percentage": 86.32, "elapsed_time": "0:56:28", "remaining_time": "0:08:56", "throughput": 5688.57, "total_tokens": 19273096} {"current_steps": 29285, "total_steps": 33920, "loss": 0.208, "lr": 5.583117505881764e-07, "epoch": 17.267099056603772, "percentage": 86.34, "elapsed_time": "0:56:28", "remaining_time": "0:08:56", "throughput": 5688.53, "total_tokens": 19276072} {"current_steps": 29290, "total_steps": 33920, "loss": 0.3923, "lr": 5.571309718869417e-07, "epoch": 17.27004716981132, "percentage": 86.35, "elapsed_time": "0:56:29", "remaining_time": "0:08:55", "throughput": 5688.43, "total_tokens": 19278760} {"current_steps": 29295, "total_steps": 33920, "loss": 0.2616, "lr": 5.559513694544282e-07, "epoch": 17.27299528301887, "percentage": 86.36, "elapsed_time": "0:56:29", "remaining_time": "0:08:55", "throughput": 5688.55, "total_tokens": 19282856} {"current_steps": 29300, "total_steps": 33920, "loss": 0.3586, "lr": 5.547729436029442e-07, "epoch": 17.275943396226417, "percentage": 86.38, "elapsed_time": "0:56:30", "remaining_time": "0:08:54", "throughput": 5688.56, "total_tokens": 19286408} {"current_steps": 29305, "total_steps": 33920, "loss": 0.5444, "lr": 5.535956946444809e-07, "epoch": 17.27889150943396, "percentage": 86.39, "elapsed_time": "0:56:30", "remaining_time": "0:08:54", "throughput": 5688.58, "total_tokens": 19289768} {"current_steps": 29310, "total_steps": 33920, "loss": 0.304, "lr": 5.524196228907203e-07, "epoch": 17.28183962264151, "percentage": 86.41, "elapsed_time": "0:56:31", "remaining_time": "0:08:53", "throughput": 5688.39, "total_tokens": 19292392} {"current_steps": 29315, "total_steps": 33920, "loss": 0.3056, "lr": 5.512447286530326e-07, "epoch": 17.284787735849058, "percentage": 86.42, "elapsed_time": "0:56:32", "remaining_time": "0:08:52", "throughput": 5688.51, "total_tokens": 19296520} {"current_steps": 29320, "total_steps": 33920, "loss": 0.3769, "lr": 5.500710122424746e-07, "epoch": 17.287735849056602, "percentage": 86.44, "elapsed_time": "0:56:32", "remaining_time": "0:08:52", "throughput": 5688.54, "total_tokens": 19299976} {"current_steps": 29325, "total_steps": 33920, "loss": 0.2944, "lr": 5.488984739697961e-07, "epoch": 17.29068396226415, "percentage": 86.45, "elapsed_time": "0:56:33", "remaining_time": "0:08:51", "throughput": 5688.56, "total_tokens": 19303304} {"current_steps": 29330, "total_steps": 33920, "loss": 0.3015, "lr": 5.477271141454294e-07, "epoch": 17.2936320754717, "percentage": 86.47, "elapsed_time": "0:56:33", "remaining_time": "0:08:51", "throughput": 5688.43, "total_tokens": 19306312} {"current_steps": 29335, "total_steps": 33920, "loss": 0.3237, "lr": 5.465569330794974e-07, "epoch": 17.296580188679247, "percentage": 86.48, "elapsed_time": "0:56:34", "remaining_time": "0:08:50", "throughput": 5688.43, "total_tokens": 19309416} {"current_steps": 29340, "total_steps": 33920, "loss": 0.3546, "lr": 5.453879310818105e-07, "epoch": 17.29952830188679, "percentage": 86.5, "elapsed_time": "0:56:35", "remaining_time": "0:08:49", "throughput": 5688.48, "total_tokens": 19312936} {"current_steps": 29345, "total_steps": 33920, "loss": 0.3274, "lr": 5.442201084618664e-07, "epoch": 17.30247641509434, "percentage": 86.51, "elapsed_time": "0:56:35", "remaining_time": "0:08:49", "throughput": 5688.52, "total_tokens": 19316520} {"current_steps": 29350, "total_steps": 33920, "loss": 0.2335, "lr": 5.430534655288528e-07, "epoch": 17.305424528301888, "percentage": 86.53, "elapsed_time": "0:56:36", "remaining_time": "0:08:48", "throughput": 5688.56, "total_tokens": 19319944} {"current_steps": 29355, "total_steps": 33920, "loss": 0.3737, "lr": 5.418880025916428e-07, "epoch": 17.308372641509433, "percentage": 86.54, "elapsed_time": "0:56:37", "remaining_time": "0:08:48", "throughput": 5688.81, "total_tokens": 19326696} {"current_steps": 29360, "total_steps": 33920, "loss": 0.2577, "lr": 5.407237199587973e-07, "epoch": 17.31132075471698, "percentage": 86.56, "elapsed_time": "0:56:37", "remaining_time": "0:08:47", "throughput": 5688.85, "total_tokens": 19330248} {"current_steps": 29365, "total_steps": 33920, "loss": 0.3215, "lr": 5.395606179385654e-07, "epoch": 17.31426886792453, "percentage": 86.57, "elapsed_time": "0:56:39", "remaining_time": "0:08:47", "throughput": 5689.0, "total_tokens": 19337224} {"current_steps": 29370, "total_steps": 33920, "loss": 0.3201, "lr": 5.383986968388833e-07, "epoch": 17.317216981132077, "percentage": 86.59, "elapsed_time": "0:56:39", "remaining_time": "0:08:46", "throughput": 5688.93, "total_tokens": 19339976} {"current_steps": 29375, "total_steps": 33920, "loss": 0.3633, "lr": 5.372379569673736e-07, "epoch": 17.32016509433962, "percentage": 86.6, "elapsed_time": "0:56:40", "remaining_time": "0:08:46", "throughput": 5688.78, "total_tokens": 19342408} {"current_steps": 29380, "total_steps": 33920, "loss": 0.2557, "lr": 5.360783986313495e-07, "epoch": 17.32311320754717, "percentage": 86.62, "elapsed_time": "0:56:40", "remaining_time": "0:08:45", "throughput": 5688.88, "total_tokens": 19346056} {"current_steps": 29385, "total_steps": 33920, "loss": 0.2692, "lr": 5.349200221378076e-07, "epoch": 17.326061320754718, "percentage": 86.63, "elapsed_time": "0:56:41", "remaining_time": "0:08:44", "throughput": 5688.8, "total_tokens": 19348808} {"current_steps": 29390, "total_steps": 33920, "loss": 0.3213, "lr": 5.33762827793432e-07, "epoch": 17.329009433962263, "percentage": 86.65, "elapsed_time": "0:56:41", "remaining_time": "0:08:44", "throughput": 5688.79, "total_tokens": 19352264} {"current_steps": 29395, "total_steps": 33920, "loss": 0.3158, "lr": 5.326068159045978e-07, "epoch": 17.33195754716981, "percentage": 86.66, "elapsed_time": "0:56:42", "remaining_time": "0:08:43", "throughput": 5688.78, "total_tokens": 19355336} {"current_steps": 29400, "total_steps": 33920, "loss": 0.3525, "lr": 5.314519867773621e-07, "epoch": 17.33490566037736, "percentage": 86.67, "elapsed_time": "0:56:43", "remaining_time": "0:08:43", "throughput": 5689.0, "total_tokens": 19359912} {"current_steps": 29405, "total_steps": 33920, "loss": 0.2654, "lr": 5.302983407174711e-07, "epoch": 17.337853773584907, "percentage": 86.69, "elapsed_time": "0:56:43", "remaining_time": "0:08:42", "throughput": 5689.1, "total_tokens": 19363912} {"current_steps": 29410, "total_steps": 33920, "loss": 0.2146, "lr": 5.291458780303572e-07, "epoch": 17.340801886792452, "percentage": 86.7, "elapsed_time": "0:56:44", "remaining_time": "0:08:42", "throughput": 5689.09, "total_tokens": 19366856} {"current_steps": 29415, "total_steps": 33920, "loss": 0.3007, "lr": 5.279945990211411e-07, "epoch": 17.34375, "percentage": 86.72, "elapsed_time": "0:56:44", "remaining_time": "0:08:41", "throughput": 5689.16, "total_tokens": 19370248} {"current_steps": 29420, "total_steps": 33920, "loss": 0.2787, "lr": 5.26844503994628e-07, "epoch": 17.346698113207548, "percentage": 86.73, "elapsed_time": "0:56:45", "remaining_time": "0:08:40", "throughput": 5689.14, "total_tokens": 19373224} {"current_steps": 29425, "total_steps": 33920, "loss": 0.4259, "lr": 5.25695593255311e-07, "epoch": 17.349646226415093, "percentage": 86.75, "elapsed_time": "0:56:45", "remaining_time": "0:08:40", "throughput": 5689.08, "total_tokens": 19376328} {"current_steps": 29430, "total_steps": 33920, "loss": 0.2093, "lr": 5.24547867107369e-07, "epoch": 17.35259433962264, "percentage": 86.76, "elapsed_time": "0:56:46", "remaining_time": "0:08:39", "throughput": 5689.02, "total_tokens": 19379432} {"current_steps": 29435, "total_steps": 33920, "loss": 0.387, "lr": 5.234013258546672e-07, "epoch": 17.35554245283019, "percentage": 86.78, "elapsed_time": "0:56:47", "remaining_time": "0:08:39", "throughput": 5688.98, "total_tokens": 19382504} {"current_steps": 29440, "total_steps": 33920, "loss": 0.2679, "lr": 5.222559698007563e-07, "epoch": 17.358490566037737, "percentage": 86.79, "elapsed_time": "0:56:47", "remaining_time": "0:08:38", "throughput": 5688.95, "total_tokens": 19385480} {"current_steps": 29445, "total_steps": 33920, "loss": 0.309, "lr": 5.211117992488763e-07, "epoch": 17.361438679245282, "percentage": 86.81, "elapsed_time": "0:56:48", "remaining_time": "0:08:37", "throughput": 5689.09, "total_tokens": 19389736} {"current_steps": 29450, "total_steps": 33920, "loss": 0.3257, "lr": 5.199688145019505e-07, "epoch": 17.36438679245283, "percentage": 86.82, "elapsed_time": "0:56:48", "remaining_time": "0:08:37", "throughput": 5689.13, "total_tokens": 19393224} {"current_steps": 29455, "total_steps": 33920, "loss": 0.3853, "lr": 5.188270158625891e-07, "epoch": 17.36733490566038, "percentage": 86.84, "elapsed_time": "0:56:49", "remaining_time": "0:08:36", "throughput": 5689.21, "total_tokens": 19396520} {"current_steps": 29460, "total_steps": 33920, "loss": 0.431, "lr": 5.176864036330875e-07, "epoch": 17.370283018867923, "percentage": 86.85, "elapsed_time": "0:56:49", "remaining_time": "0:08:36", "throughput": 5689.15, "total_tokens": 19399368} {"current_steps": 29465, "total_steps": 33920, "loss": 0.3145, "lr": 5.165469781154287e-07, "epoch": 17.37323113207547, "percentage": 86.87, "elapsed_time": "0:56:50", "remaining_time": "0:08:35", "throughput": 5689.23, "total_tokens": 19402760} {"current_steps": 29470, "total_steps": 33920, "loss": 0.2619, "lr": 5.154087396112789e-07, "epoch": 17.37617924528302, "percentage": 86.88, "elapsed_time": "0:56:50", "remaining_time": "0:08:35", "throughput": 5689.13, "total_tokens": 19405576} {"current_steps": 29475, "total_steps": 33920, "loss": 0.2536, "lr": 5.142716884219939e-07, "epoch": 17.379127358490567, "percentage": 86.9, "elapsed_time": "0:56:51", "remaining_time": "0:08:34", "throughput": 5689.09, "total_tokens": 19408424} {"current_steps": 29480, "total_steps": 33920, "loss": 0.2993, "lr": 5.131358248486118e-07, "epoch": 17.382075471698112, "percentage": 86.91, "elapsed_time": "0:56:52", "remaining_time": "0:08:33", "throughput": 5689.07, "total_tokens": 19411464} {"current_steps": 29485, "total_steps": 33920, "loss": 0.3543, "lr": 5.120011491918564e-07, "epoch": 17.38502358490566, "percentage": 86.93, "elapsed_time": "0:56:52", "remaining_time": "0:08:33", "throughput": 5689.11, "total_tokens": 19414792} {"current_steps": 29490, "total_steps": 33920, "loss": 0.3289, "lr": 5.108676617521402e-07, "epoch": 17.38797169811321, "percentage": 86.94, "elapsed_time": "0:56:53", "remaining_time": "0:08:32", "throughput": 5689.03, "total_tokens": 19417480} {"current_steps": 29495, "total_steps": 33920, "loss": 0.2378, "lr": 5.097353628295571e-07, "epoch": 17.390919811320753, "percentage": 86.95, "elapsed_time": "0:56:53", "remaining_time": "0:08:32", "throughput": 5689.09, "total_tokens": 19421096} {"current_steps": 29500, "total_steps": 33920, "loss": 0.2667, "lr": 5.086042527238893e-07, "epoch": 17.3938679245283, "percentage": 86.97, "elapsed_time": "0:56:54", "remaining_time": "0:08:31", "throughput": 5689.09, "total_tokens": 19424360} {"current_steps": 29505, "total_steps": 33920, "loss": 0.2091, "lr": 5.074743317346009e-07, "epoch": 17.39681603773585, "percentage": 86.98, "elapsed_time": "0:56:54", "remaining_time": "0:08:30", "throughput": 5688.96, "total_tokens": 19427048} {"current_steps": 29510, "total_steps": 33920, "loss": 0.2467, "lr": 5.063456001608458e-07, "epoch": 17.399764150943398, "percentage": 87.0, "elapsed_time": "0:56:55", "remaining_time": "0:08:30", "throughput": 5689.12, "total_tokens": 19431144} {"current_steps": 29515, "total_steps": 33920, "loss": 0.332, "lr": 5.052180583014599e-07, "epoch": 17.402712264150942, "percentage": 87.01, "elapsed_time": "0:56:56", "remaining_time": "0:08:29", "throughput": 5689.14, "total_tokens": 19434664} {"current_steps": 29520, "total_steps": 33920, "loss": 0.3449, "lr": 5.04091706454965e-07, "epoch": 17.40566037735849, "percentage": 87.03, "elapsed_time": "0:56:56", "remaining_time": "0:08:29", "throughput": 5689.19, "total_tokens": 19437992} {"current_steps": 29525, "total_steps": 33920, "loss": 0.4072, "lr": 5.029665449195665e-07, "epoch": 17.40860849056604, "percentage": 87.04, "elapsed_time": "0:56:57", "remaining_time": "0:08:28", "throughput": 5689.05, "total_tokens": 19440552} {"current_steps": 29530, "total_steps": 33920, "loss": 0.3356, "lr": 5.018425739931559e-07, "epoch": 17.411556603773583, "percentage": 87.06, "elapsed_time": "0:56:57", "remaining_time": "0:08:28", "throughput": 5688.97, "total_tokens": 19443464} {"current_steps": 29535, "total_steps": 33920, "loss": 0.2823, "lr": 5.007197939733099e-07, "epoch": 17.41450471698113, "percentage": 87.07, "elapsed_time": "0:56:58", "remaining_time": "0:08:27", "throughput": 5688.91, "total_tokens": 19446280} {"current_steps": 29540, "total_steps": 33920, "loss": 0.3229, "lr": 4.995982051572895e-07, "epoch": 17.41745283018868, "percentage": 87.09, "elapsed_time": "0:56:58", "remaining_time": "0:08:26", "throughput": 5688.98, "total_tokens": 19450344} {"current_steps": 29545, "total_steps": 33920, "loss": 0.3578, "lr": 4.984778078420405e-07, "epoch": 17.420400943396228, "percentage": 87.1, "elapsed_time": "0:56:59", "remaining_time": "0:08:26", "throughput": 5689.0, "total_tokens": 19453384} {"current_steps": 29550, "total_steps": 33920, "loss": 0.3199, "lr": 4.973586023241917e-07, "epoch": 17.423349056603772, "percentage": 87.12, "elapsed_time": "0:57:00", "remaining_time": "0:08:25", "throughput": 5689.11, "total_tokens": 19457512} {"current_steps": 29555, "total_steps": 33920, "loss": 0.2731, "lr": 4.962405889000588e-07, "epoch": 17.42629716981132, "percentage": 87.13, "elapsed_time": "0:57:00", "remaining_time": "0:08:25", "throughput": 5689.15, "total_tokens": 19460776} {"current_steps": 29560, "total_steps": 33920, "loss": 0.3993, "lr": 4.951237678656396e-07, "epoch": 17.42924528301887, "percentage": 87.15, "elapsed_time": "0:57:01", "remaining_time": "0:08:24", "throughput": 5689.2, "total_tokens": 19464040} {"current_steps": 29565, "total_steps": 33920, "loss": 0.3206, "lr": 4.940081395166174e-07, "epoch": 17.432193396226417, "percentage": 87.16, "elapsed_time": "0:57:01", "remaining_time": "0:08:24", "throughput": 5689.25, "total_tokens": 19467592} {"current_steps": 29570, "total_steps": 33920, "loss": 0.2979, "lr": 4.928937041483606e-07, "epoch": 17.43514150943396, "percentage": 87.18, "elapsed_time": "0:57:02", "remaining_time": "0:08:23", "throughput": 5689.14, "total_tokens": 19470312} {"current_steps": 29575, "total_steps": 33920, "loss": 0.3195, "lr": 4.917804620559202e-07, "epoch": 17.43808962264151, "percentage": 87.19, "elapsed_time": "0:57:02", "remaining_time": "0:08:22", "throughput": 5689.24, "total_tokens": 19473992} {"current_steps": 29580, "total_steps": 33920, "loss": 0.2788, "lr": 4.906684135340317e-07, "epoch": 17.441037735849058, "percentage": 87.21, "elapsed_time": "0:57:03", "remaining_time": "0:08:22", "throughput": 5689.49, "total_tokens": 19479656} {"current_steps": 29585, "total_steps": 33920, "loss": 0.2832, "lr": 4.89557558877114e-07, "epoch": 17.443985849056602, "percentage": 87.22, "elapsed_time": "0:57:04", "remaining_time": "0:08:21", "throughput": 5689.37, "total_tokens": 19482184} {"current_steps": 29590, "total_steps": 33920, "loss": 0.3299, "lr": 4.884478983792728e-07, "epoch": 17.44693396226415, "percentage": 87.23, "elapsed_time": "0:57:04", "remaining_time": "0:08:21", "throughput": 5689.28, "total_tokens": 19484968} {"current_steps": 29595, "total_steps": 33920, "loss": 0.2405, "lr": 4.873394323342939e-07, "epoch": 17.4498820754717, "percentage": 87.25, "elapsed_time": "0:57:05", "remaining_time": "0:08:20", "throughput": 5689.15, "total_tokens": 19487816} {"current_steps": 29600, "total_steps": 33920, "loss": 0.2785, "lr": 4.86232161035648e-07, "epoch": 17.452830188679247, "percentage": 87.26, "elapsed_time": "0:57:05", "remaining_time": "0:08:20", "throughput": 5689.05, "total_tokens": 19490600} {"current_steps": 29605, "total_steps": 33920, "loss": 0.3146, "lr": 4.851260847764916e-07, "epoch": 17.45577830188679, "percentage": 87.28, "elapsed_time": "0:57:06", "remaining_time": "0:08:19", "throughput": 5688.84, "total_tokens": 19493064} {"current_steps": 29610, "total_steps": 33920, "loss": 0.2817, "lr": 4.840212038496622e-07, "epoch": 17.45872641509434, "percentage": 87.29, "elapsed_time": "0:57:07", "remaining_time": "0:08:18", "throughput": 5689.0, "total_tokens": 19497768} {"current_steps": 29615, "total_steps": 33920, "loss": 0.4113, "lr": 4.82917518547682e-07, "epoch": 17.461674528301888, "percentage": 87.31, "elapsed_time": "0:57:07", "remaining_time": "0:08:18", "throughput": 5689.1, "total_tokens": 19501512} {"current_steps": 29620, "total_steps": 33920, "loss": 0.3375, "lr": 4.81815029162756e-07, "epoch": 17.464622641509433, "percentage": 87.32, "elapsed_time": "0:57:08", "remaining_time": "0:08:17", "throughput": 5688.97, "total_tokens": 19504520} {"current_steps": 29625, "total_steps": 33920, "loss": 0.3, "lr": 4.807137359867725e-07, "epoch": 17.46757075471698, "percentage": 87.34, "elapsed_time": "0:57:09", "remaining_time": "0:08:17", "throughput": 5688.89, "total_tokens": 19507368} {"current_steps": 29630, "total_steps": 33920, "loss": 0.3118, "lr": 4.79613639311306e-07, "epoch": 17.47051886792453, "percentage": 87.35, "elapsed_time": "0:57:09", "remaining_time": "0:08:16", "throughput": 5688.89, "total_tokens": 19510536} {"current_steps": 29635, "total_steps": 33920, "loss": 0.3678, "lr": 4.785147394276096e-07, "epoch": 17.473466981132077, "percentage": 87.37, "elapsed_time": "0:57:10", "remaining_time": "0:08:15", "throughput": 5688.76, "total_tokens": 19513128} {"current_steps": 29640, "total_steps": 33920, "loss": 0.3211, "lr": 4.774170366266223e-07, "epoch": 17.47641509433962, "percentage": 87.38, "elapsed_time": "0:57:10", "remaining_time": "0:08:15", "throughput": 5688.69, "total_tokens": 19515880} {"current_steps": 29645, "total_steps": 33920, "loss": 0.2835, "lr": 4.763205311989666e-07, "epoch": 17.47936320754717, "percentage": 87.4, "elapsed_time": "0:57:11", "remaining_time": "0:08:14", "throughput": 5688.62, "total_tokens": 19518600} {"current_steps": 29650, "total_steps": 33920, "loss": 0.2592, "lr": 4.752252234349458e-07, "epoch": 17.482311320754718, "percentage": 87.41, "elapsed_time": "0:57:11", "remaining_time": "0:08:14", "throughput": 5688.62, "total_tokens": 19521800} {"current_steps": 29655, "total_steps": 33920, "loss": 0.3703, "lr": 4.7413111362454634e-07, "epoch": 17.485259433962263, "percentage": 87.43, "elapsed_time": "0:57:12", "remaining_time": "0:08:13", "throughput": 5688.75, "total_tokens": 19525960} {"current_steps": 29660, "total_steps": 33920, "loss": 0.341, "lr": 4.7303820205744143e-07, "epoch": 17.48820754716981, "percentage": 87.44, "elapsed_time": "0:57:13", "remaining_time": "0:08:13", "throughput": 5688.97, "total_tokens": 19531336} {"current_steps": 29665, "total_steps": 33920, "loss": 0.2802, "lr": 4.7194648902298303e-07, "epoch": 17.49115566037736, "percentage": 87.46, "elapsed_time": "0:57:13", "remaining_time": "0:08:12", "throughput": 5688.91, "total_tokens": 19534120} {"current_steps": 29670, "total_steps": 33920, "loss": 0.3529, "lr": 4.7085597481020594e-07, "epoch": 17.494103773584907, "percentage": 87.47, "elapsed_time": "0:57:14", "remaining_time": "0:08:11", "throughput": 5688.91, "total_tokens": 19537864} {"current_steps": 29675, "total_steps": 33920, "loss": 0.3253, "lr": 4.697666597078293e-07, "epoch": 17.497051886792452, "percentage": 87.49, "elapsed_time": "0:57:14", "remaining_time": "0:08:11", "throughput": 5688.94, "total_tokens": 19541224} {"current_steps": 29680, "total_steps": 33920, "loss": 0.311, "lr": 4.6867854400425237e-07, "epoch": 17.5, "percentage": 87.5, "elapsed_time": "0:57:15", "remaining_time": "0:08:10", "throughput": 5688.89, "total_tokens": 19544104} {"current_steps": 29685, "total_steps": 33920, "loss": 0.2602, "lr": 4.6759162798756084e-07, "epoch": 17.502948113207548, "percentage": 87.51, "elapsed_time": "0:57:16", "remaining_time": "0:08:10", "throughput": 5689.03, "total_tokens": 19548168} {"current_steps": 29690, "total_steps": 33920, "loss": 0.2601, "lr": 4.6650591194551895e-07, "epoch": 17.505896226415093, "percentage": 87.53, "elapsed_time": "0:57:16", "remaining_time": "0:08:09", "throughput": 5689.15, "total_tokens": 19551976} {"current_steps": 29695, "total_steps": 33920, "loss": 0.3683, "lr": 4.654213961655757e-07, "epoch": 17.50884433962264, "percentage": 87.54, "elapsed_time": "0:57:17", "remaining_time": "0:08:09", "throughput": 5689.04, "total_tokens": 19554824} {"current_steps": 29700, "total_steps": 33920, "loss": 0.4422, "lr": 4.6433808093486075e-07, "epoch": 17.51179245283019, "percentage": 87.56, "elapsed_time": "0:57:17", "remaining_time": "0:08:08", "throughput": 5688.93, "total_tokens": 19557608} {"current_steps": 29705, "total_steps": 33920, "loss": 0.2603, "lr": 4.63255966540187e-07, "epoch": 17.514740566037737, "percentage": 87.57, "elapsed_time": "0:57:18", "remaining_time": "0:08:07", "throughput": 5688.9, "total_tokens": 19561000} {"current_steps": 29710, "total_steps": 33920, "loss": 0.2645, "lr": 4.62175053268048e-07, "epoch": 17.517688679245282, "percentage": 87.59, "elapsed_time": "0:57:19", "remaining_time": "0:08:07", "throughput": 5689.06, "total_tokens": 19565576} {"current_steps": 29715, "total_steps": 33920, "loss": 0.3407, "lr": 4.6109534140462045e-07, "epoch": 17.52063679245283, "percentage": 87.6, "elapsed_time": "0:57:19", "remaining_time": "0:08:06", "throughput": 5689.02, "total_tokens": 19568936} {"current_steps": 29720, "total_steps": 33920, "loss": 0.3318, "lr": 4.6001683123576226e-07, "epoch": 17.52358490566038, "percentage": 87.62, "elapsed_time": "0:57:20", "remaining_time": "0:08:06", "throughput": 5689.07, "total_tokens": 19572904} {"current_steps": 29725, "total_steps": 33920, "loss": 0.2821, "lr": 4.589395230470145e-07, "epoch": 17.526533018867923, "percentage": 87.63, "elapsed_time": "0:57:20", "remaining_time": "0:08:05", "throughput": 5689.01, "total_tokens": 19575816} {"current_steps": 29730, "total_steps": 33920, "loss": 0.2672, "lr": 4.578634171235996e-07, "epoch": 17.52948113207547, "percentage": 87.65, "elapsed_time": "0:57:21", "remaining_time": "0:08:05", "throughput": 5689.01, "total_tokens": 19579016} {"current_steps": 29735, "total_steps": 33920, "loss": 0.3453, "lr": 4.567885137504202e-07, "epoch": 17.53242924528302, "percentage": 87.66, "elapsed_time": "0:57:22", "remaining_time": "0:08:04", "throughput": 5689.13, "total_tokens": 19582984} {"current_steps": 29740, "total_steps": 33920, "loss": 0.3727, "lr": 4.55714813212062e-07, "epoch": 17.535377358490567, "percentage": 87.68, "elapsed_time": "0:57:22", "remaining_time": "0:08:03", "throughput": 5689.05, "total_tokens": 19585832} {"current_steps": 29745, "total_steps": 33920, "loss": 0.4499, "lr": 4.5464231579279206e-07, "epoch": 17.538325471698112, "percentage": 87.69, "elapsed_time": "0:57:23", "remaining_time": "0:08:03", "throughput": 5689.0, "total_tokens": 19588712} {"current_steps": 29750, "total_steps": 33920, "loss": 0.2943, "lr": 4.535710217765571e-07, "epoch": 17.54127358490566, "percentage": 87.71, "elapsed_time": "0:57:23", "remaining_time": "0:08:02", "throughput": 5689.08, "total_tokens": 19592328} {"current_steps": 29755, "total_steps": 33920, "loss": 0.4056, "lr": 4.5250093144698913e-07, "epoch": 17.54422169811321, "percentage": 87.72, "elapsed_time": "0:57:24", "remaining_time": "0:08:02", "throughput": 5689.03, "total_tokens": 19595272} {"current_steps": 29760, "total_steps": 33920, "loss": 0.2969, "lr": 4.514320450873988e-07, "epoch": 17.547169811320753, "percentage": 87.74, "elapsed_time": "0:57:24", "remaining_time": "0:08:01", "throughput": 5689.01, "total_tokens": 19598248} {"current_steps": 29765, "total_steps": 33920, "loss": 0.2589, "lr": 4.503643629807769e-07, "epoch": 17.5501179245283, "percentage": 87.75, "elapsed_time": "0:57:25", "remaining_time": "0:08:00", "throughput": 5689.22, "total_tokens": 19602632} {"current_steps": 29770, "total_steps": 33920, "loss": 0.357, "lr": 4.4929788540979844e-07, "epoch": 17.55306603773585, "percentage": 87.77, "elapsed_time": "0:57:26", "remaining_time": "0:08:00", "throughput": 5689.28, "total_tokens": 19606376} {"current_steps": 29775, "total_steps": 33920, "loss": 0.2627, "lr": 4.4823261265681596e-07, "epoch": 17.556014150943398, "percentage": 87.78, "elapsed_time": "0:57:26", "remaining_time": "0:07:59", "throughput": 5689.29, "total_tokens": 19609736} {"current_steps": 29780, "total_steps": 33920, "loss": 0.3106, "lr": 4.471685450038671e-07, "epoch": 17.558962264150942, "percentage": 87.79, "elapsed_time": "0:57:27", "remaining_time": "0:07:59", "throughput": 5689.42, "total_tokens": 19613704} {"current_steps": 29785, "total_steps": 33920, "loss": 0.3188, "lr": 4.4610568273266706e-07, "epoch": 17.56191037735849, "percentage": 87.81, "elapsed_time": "0:57:27", "remaining_time": "0:07:58", "throughput": 5689.35, "total_tokens": 19616584} {"current_steps": 29790, "total_steps": 33920, "loss": 0.2875, "lr": 4.450440261246142e-07, "epoch": 17.56485849056604, "percentage": 87.82, "elapsed_time": "0:57:28", "remaining_time": "0:07:58", "throughput": 5689.24, "total_tokens": 19619240} {"current_steps": 29795, "total_steps": 33920, "loss": 0.3021, "lr": 4.439835754607863e-07, "epoch": 17.567806603773583, "percentage": 87.84, "elapsed_time": "0:57:29", "remaining_time": "0:07:57", "throughput": 5689.25, "total_tokens": 19622312} {"current_steps": 29800, "total_steps": 33920, "loss": 0.3804, "lr": 4.429243310219422e-07, "epoch": 17.57075471698113, "percentage": 87.85, "elapsed_time": "0:57:30", "remaining_time": "0:07:56", "throughput": 5689.45, "total_tokens": 19629288} {"current_steps": 29805, "total_steps": 33920, "loss": 0.2913, "lr": 4.418662930885215e-07, "epoch": 17.57370283018868, "percentage": 87.87, "elapsed_time": "0:57:30", "remaining_time": "0:07:56", "throughput": 5689.53, "total_tokens": 19632680} {"current_steps": 29810, "total_steps": 33920, "loss": 0.2566, "lr": 4.408094619406439e-07, "epoch": 17.576650943396228, "percentage": 87.88, "elapsed_time": "0:57:31", "remaining_time": "0:07:55", "throughput": 5689.47, "total_tokens": 19635880} {"current_steps": 29815, "total_steps": 33920, "loss": 0.3008, "lr": 4.3975383785810954e-07, "epoch": 17.579599056603772, "percentage": 87.9, "elapsed_time": "0:57:31", "remaining_time": "0:07:55", "throughput": 5689.37, "total_tokens": 19638536} {"current_steps": 29820, "total_steps": 33920, "loss": 0.2424, "lr": 4.3869942112040096e-07, "epoch": 17.58254716981132, "percentage": 87.91, "elapsed_time": "0:57:32", "remaining_time": "0:07:54", "throughput": 5689.46, "total_tokens": 19642472} {"current_steps": 29825, "total_steps": 33920, "loss": 0.2496, "lr": 4.3764621200667936e-07, "epoch": 17.58549528301887, "percentage": 87.93, "elapsed_time": "0:57:33", "remaining_time": "0:07:54", "throughput": 5689.49, "total_tokens": 19645928} {"current_steps": 29830, "total_steps": 33920, "loss": 0.5703, "lr": 4.365942107957849e-07, "epoch": 17.588443396226417, "percentage": 87.94, "elapsed_time": "0:57:33", "remaining_time": "0:07:53", "throughput": 5689.49, "total_tokens": 19649128} {"current_steps": 29835, "total_steps": 33920, "loss": 0.2541, "lr": 4.35543417766241e-07, "epoch": 17.59139150943396, "percentage": 87.96, "elapsed_time": "0:57:34", "remaining_time": "0:07:52", "throughput": 5689.4, "total_tokens": 19651816} {"current_steps": 29840, "total_steps": 33920, "loss": 0.3981, "lr": 4.3449383319624785e-07, "epoch": 17.59433962264151, "percentage": 87.97, "elapsed_time": "0:57:34", "remaining_time": "0:07:52", "throughput": 5689.46, "total_tokens": 19655336} {"current_steps": 29845, "total_steps": 33920, "loss": 0.347, "lr": 4.3344545736368926e-07, "epoch": 17.597287735849058, "percentage": 87.99, "elapsed_time": "0:57:35", "remaining_time": "0:07:51", "throughput": 5689.48, "total_tokens": 19658792} {"current_steps": 29850, "total_steps": 33920, "loss": 0.358, "lr": 4.323982905461266e-07, "epoch": 17.600235849056602, "percentage": 88.0, "elapsed_time": "0:57:35", "remaining_time": "0:07:51", "throughput": 5689.51, "total_tokens": 19662056} {"current_steps": 29855, "total_steps": 33920, "loss": 0.2482, "lr": 4.313523330208019e-07, "epoch": 17.60318396226415, "percentage": 88.02, "elapsed_time": "0:57:36", "remaining_time": "0:07:50", "throughput": 5689.36, "total_tokens": 19664712} {"current_steps": 29860, "total_steps": 33920, "loss": 0.2477, "lr": 4.303075850646371e-07, "epoch": 17.6061320754717, "percentage": 88.03, "elapsed_time": "0:57:37", "remaining_time": "0:07:50", "throughput": 5689.64, "total_tokens": 19671336} {"current_steps": 29865, "total_steps": 33920, "loss": 0.3539, "lr": 4.2926404695423305e-07, "epoch": 17.609080188679247, "percentage": 88.05, "elapsed_time": "0:57:37", "remaining_time": "0:07:49", "throughput": 5689.64, "total_tokens": 19674504} {"current_steps": 29870, "total_steps": 33920, "loss": 0.3731, "lr": 4.282217189658705e-07, "epoch": 17.61202830188679, "percentage": 88.06, "elapsed_time": "0:57:38", "remaining_time": "0:07:48", "throughput": 5689.41, "total_tokens": 19676648} {"current_steps": 29875, "total_steps": 33920, "loss": 0.2962, "lr": 4.27180601375512e-07, "epoch": 17.61497641509434, "percentage": 88.07, "elapsed_time": "0:57:39", "remaining_time": "0:07:48", "throughput": 5689.47, "total_tokens": 19680104} {"current_steps": 29880, "total_steps": 33920, "loss": 0.3189, "lr": 4.2614069445879646e-07, "epoch": 17.617924528301888, "percentage": 88.09, "elapsed_time": "0:57:39", "remaining_time": "0:07:47", "throughput": 5689.45, "total_tokens": 19683240} {"current_steps": 29885, "total_steps": 33920, "loss": 0.3343, "lr": 4.251019984910448e-07, "epoch": 17.620872641509433, "percentage": 88.1, "elapsed_time": "0:57:40", "remaining_time": "0:07:47", "throughput": 5689.57, "total_tokens": 19688040} {"current_steps": 29890, "total_steps": 33920, "loss": 0.2138, "lr": 4.2406451374725597e-07, "epoch": 17.62382075471698, "percentage": 88.12, "elapsed_time": "0:57:40", "remaining_time": "0:07:46", "throughput": 5689.45, "total_tokens": 19690664} {"current_steps": 29895, "total_steps": 33920, "loss": 0.2724, "lr": 4.2302824050210855e-07, "epoch": 17.62676886792453, "percentage": 88.13, "elapsed_time": "0:57:41", "remaining_time": "0:07:46", "throughput": 5689.55, "total_tokens": 19694248} {"current_steps": 29900, "total_steps": 33920, "loss": 0.322, "lr": 4.2199317902995974e-07, "epoch": 17.629716981132077, "percentage": 88.15, "elapsed_time": "0:57:42", "remaining_time": "0:07:45", "throughput": 5689.34, "total_tokens": 19696552} {"current_steps": 29905, "total_steps": 33920, "loss": 0.3478, "lr": 4.209593296048459e-07, "epoch": 17.63266509433962, "percentage": 88.16, "elapsed_time": "0:57:42", "remaining_time": "0:07:44", "throughput": 5689.4, "total_tokens": 19700296} {"current_steps": 29910, "total_steps": 33920, "loss": 0.3821, "lr": 4.1992669250048524e-07, "epoch": 17.63561320754717, "percentage": 88.18, "elapsed_time": "0:57:43", "remaining_time": "0:07:44", "throughput": 5689.27, "total_tokens": 19702856} {"current_steps": 29915, "total_steps": 33920, "loss": 0.2874, "lr": 4.188952679902719e-07, "epoch": 17.638561320754718, "percentage": 88.19, "elapsed_time": "0:57:43", "remaining_time": "0:07:43", "throughput": 5689.16, "total_tokens": 19705544} {"current_steps": 29920, "total_steps": 33920, "loss": 0.4021, "lr": 4.178650563472797e-07, "epoch": 17.641509433962263, "percentage": 88.21, "elapsed_time": "0:57:44", "remaining_time": "0:07:43", "throughput": 5689.1, "total_tokens": 19708520} {"current_steps": 29925, "total_steps": 33920, "loss": 0.4028, "lr": 4.168360578442615e-07, "epoch": 17.64445754716981, "percentage": 88.22, "elapsed_time": "0:57:44", "remaining_time": "0:07:42", "throughput": 5689.06, "total_tokens": 19711720} {"current_steps": 29930, "total_steps": 33920, "loss": 0.4136, "lr": 4.1580827275365e-07, "epoch": 17.64740566037736, "percentage": 88.24, "elapsed_time": "0:57:45", "remaining_time": "0:07:41", "throughput": 5689.23, "total_tokens": 19716200} {"current_steps": 29935, "total_steps": 33920, "loss": 0.302, "lr": 4.147817013475536e-07, "epoch": 17.650353773584907, "percentage": 88.25, "elapsed_time": "0:57:46", "remaining_time": "0:07:41", "throughput": 5689.35, "total_tokens": 19719624} {"current_steps": 29940, "total_steps": 33920, "loss": 0.3181, "lr": 4.1375634389776375e-07, "epoch": 17.653301886792452, "percentage": 88.27, "elapsed_time": "0:57:46", "remaining_time": "0:07:40", "throughput": 5689.64, "total_tokens": 19725896} {"current_steps": 29945, "total_steps": 33920, "loss": 0.2546, "lr": 4.127322006757478e-07, "epoch": 17.65625, "percentage": 88.28, "elapsed_time": "0:57:47", "remaining_time": "0:07:40", "throughput": 5689.62, "total_tokens": 19728968} {"current_steps": 29950, "total_steps": 33920, "loss": 0.1704, "lr": 4.1170927195265163e-07, "epoch": 17.659198113207548, "percentage": 88.3, "elapsed_time": "0:57:48", "remaining_time": "0:07:39", "throughput": 5689.56, "total_tokens": 19732008} {"current_steps": 29955, "total_steps": 33920, "loss": 0.2706, "lr": 4.1068755799930026e-07, "epoch": 17.662146226415093, "percentage": 88.31, "elapsed_time": "0:57:48", "remaining_time": "0:07:39", "throughput": 5689.48, "total_tokens": 19734792} {"current_steps": 29960, "total_steps": 33920, "loss": 0.2953, "lr": 4.096670590861962e-07, "epoch": 17.66509433962264, "percentage": 88.33, "elapsed_time": "0:57:49", "remaining_time": "0:07:38", "throughput": 5689.52, "total_tokens": 19738728} {"current_steps": 29965, "total_steps": 33920, "loss": 0.3379, "lr": 4.086477754835211e-07, "epoch": 17.66804245283019, "percentage": 88.34, "elapsed_time": "0:57:49", "remaining_time": "0:07:37", "throughput": 5689.55, "total_tokens": 19741800} {"current_steps": 29970, "total_steps": 33920, "loss": 0.3077, "lr": 4.0762970746113517e-07, "epoch": 17.670990566037737, "percentage": 88.35, "elapsed_time": "0:57:50", "remaining_time": "0:07:37", "throughput": 5689.47, "total_tokens": 19744520} {"current_steps": 29975, "total_steps": 33920, "loss": 0.3189, "lr": 4.0661285528857676e-07, "epoch": 17.673938679245282, "percentage": 88.37, "elapsed_time": "0:57:50", "remaining_time": "0:07:36", "throughput": 5689.23, "total_tokens": 19746632} {"current_steps": 29980, "total_steps": 33920, "loss": 0.3724, "lr": 4.0559721923506155e-07, "epoch": 17.67688679245283, "percentage": 88.38, "elapsed_time": "0:57:51", "remaining_time": "0:07:36", "throughput": 5689.27, "total_tokens": 19750088} {"current_steps": 29985, "total_steps": 33920, "loss": 0.3247, "lr": 4.045827995694834e-07, "epoch": 17.67983490566038, "percentage": 88.4, "elapsed_time": "0:57:52", "remaining_time": "0:07:35", "throughput": 5689.14, "total_tokens": 19752840} {"current_steps": 29990, "total_steps": 33920, "loss": 0.2222, "lr": 4.035695965604142e-07, "epoch": 17.682783018867923, "percentage": 88.41, "elapsed_time": "0:57:52", "remaining_time": "0:07:35", "throughput": 5689.26, "total_tokens": 19756392} {"current_steps": 29995, "total_steps": 33920, "loss": 0.2544, "lr": 4.0255761047610365e-07, "epoch": 17.68573113207547, "percentage": 88.43, "elapsed_time": "0:57:53", "remaining_time": "0:07:34", "throughput": 5689.26, "total_tokens": 19759368} {"current_steps": 30000, "total_steps": 33920, "loss": 0.3438, "lr": 4.0154684158447864e-07, "epoch": 17.68867924528302, "percentage": 88.44, "elapsed_time": "0:57:53", "remaining_time": "0:07:33", "throughput": 5689.4, "total_tokens": 19763496} {"current_steps": 30005, "total_steps": 33920, "loss": 0.2484, "lr": 4.0053729015314623e-07, "epoch": 17.691627358490567, "percentage": 88.46, "elapsed_time": "0:57:54", "remaining_time": "0:07:33", "throughput": 5689.51, "total_tokens": 19767560} {"current_steps": 30010, "total_steps": 33920, "loss": 0.4186, "lr": 3.9952895644938926e-07, "epoch": 17.694575471698112, "percentage": 88.47, "elapsed_time": "0:57:54", "remaining_time": "0:07:32", "throughput": 5689.52, "total_tokens": 19770664} {"current_steps": 30015, "total_steps": 33920, "loss": 0.2302, "lr": 3.985218407401681e-07, "epoch": 17.69752358490566, "percentage": 88.49, "elapsed_time": "0:57:55", "remaining_time": "0:07:32", "throughput": 5689.33, "total_tokens": 19772936} {"current_steps": 30020, "total_steps": 33920, "loss": 0.2621, "lr": 3.975159432921205e-07, "epoch": 17.70047169811321, "percentage": 88.5, "elapsed_time": "0:57:55", "remaining_time": "0:07:31", "throughput": 5689.25, "total_tokens": 19775784} {"current_steps": 30025, "total_steps": 33920, "loss": 0.2319, "lr": 3.9651126437156294e-07, "epoch": 17.703419811320753, "percentage": 88.52, "elapsed_time": "0:57:56", "remaining_time": "0:07:30", "throughput": 5689.0, "total_tokens": 19778120} {"current_steps": 30030, "total_steps": 33920, "loss": 0.2403, "lr": 3.9550780424448653e-07, "epoch": 17.7063679245283, "percentage": 88.53, "elapsed_time": "0:57:57", "remaining_time": "0:07:30", "throughput": 5688.92, "total_tokens": 19780872} {"current_steps": 30035, "total_steps": 33920, "loss": 0.3197, "lr": 3.9450556317656487e-07, "epoch": 17.70931603773585, "percentage": 88.55, "elapsed_time": "0:57:57", "remaining_time": "0:07:29", "throughput": 5688.72, "total_tokens": 19783624} {"current_steps": 30040, "total_steps": 33920, "loss": 0.2392, "lr": 3.935045414331434e-07, "epoch": 17.712264150943398, "percentage": 88.56, "elapsed_time": "0:57:58", "remaining_time": "0:07:29", "throughput": 5688.68, "total_tokens": 19786856} {"current_steps": 30045, "total_steps": 33920, "loss": 0.2502, "lr": 3.925047392792475e-07, "epoch": 17.715212264150942, "percentage": 88.58, "elapsed_time": "0:57:58", "remaining_time": "0:07:28", "throughput": 5688.65, "total_tokens": 19789736} {"current_steps": 30050, "total_steps": 33920, "loss": 0.359, "lr": 3.9150615697957917e-07, "epoch": 17.71816037735849, "percentage": 88.59, "elapsed_time": "0:57:59", "remaining_time": "0:07:28", "throughput": 5688.6, "total_tokens": 19792680} {"current_steps": 30055, "total_steps": 33920, "loss": 0.3283, "lr": 3.9050879479851753e-07, "epoch": 17.72110849056604, "percentage": 88.61, "elapsed_time": "0:57:59", "remaining_time": "0:07:27", "throughput": 5688.54, "total_tokens": 19795464} {"current_steps": 30060, "total_steps": 33920, "loss": 0.2638, "lr": 3.89512653000117e-07, "epoch": 17.724056603773583, "percentage": 88.62, "elapsed_time": "0:58:00", "remaining_time": "0:07:26", "throughput": 5688.54, "total_tokens": 19798696} {"current_steps": 30065, "total_steps": 33920, "loss": 0.4844, "lr": 3.8851773184811203e-07, "epoch": 17.72700471698113, "percentage": 88.64, "elapsed_time": "0:58:00", "remaining_time": "0:07:26", "throughput": 5688.41, "total_tokens": 19801256} {"current_steps": 30070, "total_steps": 33920, "loss": 0.3087, "lr": 3.8752403160591255e-07, "epoch": 17.72995283018868, "percentage": 88.65, "elapsed_time": "0:58:01", "remaining_time": "0:07:25", "throughput": 5688.46, "total_tokens": 19804616} {"current_steps": 30075, "total_steps": 33920, "loss": 0.377, "lr": 3.8653155253660477e-07, "epoch": 17.732900943396228, "percentage": 88.66, "elapsed_time": "0:58:02", "remaining_time": "0:07:25", "throughput": 5688.54, "total_tokens": 19808072} {"current_steps": 30080, "total_steps": 33920, "loss": 0.3582, "lr": 3.8554029490295073e-07, "epoch": 17.735849056603772, "percentage": 88.68, "elapsed_time": "0:58:02", "remaining_time": "0:07:24", "throughput": 5688.38, "total_tokens": 19810440} {"current_steps": 30085, "total_steps": 33920, "loss": 0.3507, "lr": 3.8455025896739164e-07, "epoch": 17.73879716981132, "percentage": 88.69, "elapsed_time": "0:58:03", "remaining_time": "0:07:24", "throughput": 5688.43, "total_tokens": 19813736} {"current_steps": 30090, "total_steps": 33920, "loss": 0.2504, "lr": 3.8356144499204215e-07, "epoch": 17.74174528301887, "percentage": 88.71, "elapsed_time": "0:58:03", "remaining_time": "0:07:23", "throughput": 5688.39, "total_tokens": 19816552} {"current_steps": 30095, "total_steps": 33920, "loss": 0.3446, "lr": 3.8257385323869576e-07, "epoch": 17.744693396226417, "percentage": 88.72, "elapsed_time": "0:58:04", "remaining_time": "0:07:22", "throughput": 5688.33, "total_tokens": 19819432} {"current_steps": 30100, "total_steps": 33920, "loss": 0.2953, "lr": 3.815874839688222e-07, "epoch": 17.74764150943396, "percentage": 88.74, "elapsed_time": "0:58:04", "remaining_time": "0:07:22", "throughput": 5688.42, "total_tokens": 19823240} {"current_steps": 30105, "total_steps": 33920, "loss": 0.3521, "lr": 3.8060233744356634e-07, "epoch": 17.75058962264151, "percentage": 88.75, "elapsed_time": "0:58:05", "remaining_time": "0:07:21", "throughput": 5688.29, "total_tokens": 19826120} {"current_steps": 30110, "total_steps": 33920, "loss": 0.2488, "lr": 3.796184139237502e-07, "epoch": 17.753537735849058, "percentage": 88.77, "elapsed_time": "0:58:06", "remaining_time": "0:07:21", "throughput": 5688.32, "total_tokens": 19829480} {"current_steps": 30115, "total_steps": 33920, "loss": 0.3368, "lr": 3.7863571366987206e-07, "epoch": 17.756485849056602, "percentage": 88.78, "elapsed_time": "0:58:06", "remaining_time": "0:07:20", "throughput": 5688.37, "total_tokens": 19833160} {"current_steps": 30120, "total_steps": 33920, "loss": 0.2812, "lr": 3.776542369421049e-07, "epoch": 17.75943396226415, "percentage": 88.8, "elapsed_time": "0:58:07", "remaining_time": "0:07:19", "throughput": 5688.4, "total_tokens": 19836744} {"current_steps": 30125, "total_steps": 33920, "loss": 0.3167, "lr": 3.766739840003003e-07, "epoch": 17.7623820754717, "percentage": 88.81, "elapsed_time": "0:58:07", "remaining_time": "0:07:19", "throughput": 5688.13, "total_tokens": 19839016} {"current_steps": 30130, "total_steps": 33920, "loss": 0.3715, "lr": 3.756949551039835e-07, "epoch": 17.765330188679247, "percentage": 88.83, "elapsed_time": "0:58:08", "remaining_time": "0:07:18", "throughput": 5688.13, "total_tokens": 19842344} {"current_steps": 30135, "total_steps": 33920, "loss": 0.2821, "lr": 3.7471715051235757e-07, "epoch": 17.76827830188679, "percentage": 88.84, "elapsed_time": "0:58:09", "remaining_time": "0:07:18", "throughput": 5688.27, "total_tokens": 19846728} {"current_steps": 30140, "total_steps": 33920, "loss": 0.2732, "lr": 3.7374057048429947e-07, "epoch": 17.77122641509434, "percentage": 88.86, "elapsed_time": "0:58:09", "remaining_time": "0:07:17", "throughput": 5688.29, "total_tokens": 19849960} {"current_steps": 30145, "total_steps": 33920, "loss": 0.2152, "lr": 3.7276521527836396e-07, "epoch": 17.774174528301888, "percentage": 88.87, "elapsed_time": "0:58:10", "remaining_time": "0:07:17", "throughput": 5688.38, "total_tokens": 19853480} {"current_steps": 30150, "total_steps": 33920, "loss": 0.3317, "lr": 3.717910851527784e-07, "epoch": 17.777122641509433, "percentage": 88.89, "elapsed_time": "0:58:10", "remaining_time": "0:07:16", "throughput": 5688.31, "total_tokens": 19856168} {"current_steps": 30155, "total_steps": 33920, "loss": 0.3423, "lr": 3.708181803654498e-07, "epoch": 17.78007075471698, "percentage": 88.9, "elapsed_time": "0:58:11", "remaining_time": "0:07:15", "throughput": 5688.36, "total_tokens": 19859880} {"current_steps": 30160, "total_steps": 33920, "loss": 0.2323, "lr": 3.6984650117395993e-07, "epoch": 17.78301886792453, "percentage": 88.92, "elapsed_time": "0:58:11", "remaining_time": "0:07:15", "throughput": 5688.36, "total_tokens": 19863080} {"current_steps": 30165, "total_steps": 33920, "loss": 0.1986, "lr": 3.688760478355635e-07, "epoch": 17.785966981132077, "percentage": 88.93, "elapsed_time": "0:58:12", "remaining_time": "0:07:14", "throughput": 5688.25, "total_tokens": 19866056} {"current_steps": 30170, "total_steps": 33920, "loss": 0.2789, "lr": 3.679068206071923e-07, "epoch": 17.78891509433962, "percentage": 88.94, "elapsed_time": "0:58:12", "remaining_time": "0:07:14", "throughput": 5688.29, "total_tokens": 19869192} {"current_steps": 30175, "total_steps": 33920, "loss": 0.3625, "lr": 3.669388197454532e-07, "epoch": 17.79186320754717, "percentage": 88.96, "elapsed_time": "0:58:13", "remaining_time": "0:07:13", "throughput": 5688.31, "total_tokens": 19872648} {"current_steps": 30180, "total_steps": 33920, "loss": 0.2976, "lr": 3.6597204550662956e-07, "epoch": 17.794811320754718, "percentage": 88.97, "elapsed_time": "0:58:14", "remaining_time": "0:07:13", "throughput": 5688.15, "total_tokens": 19875432} {"current_steps": 30185, "total_steps": 33920, "loss": 0.2565, "lr": 3.650064981466772e-07, "epoch": 17.797759433962263, "percentage": 88.99, "elapsed_time": "0:58:14", "remaining_time": "0:07:12", "throughput": 5688.21, "total_tokens": 19878696} {"current_steps": 30190, "total_steps": 33920, "loss": 0.269, "lr": 3.640421779212311e-07, "epoch": 17.80070754716981, "percentage": 89.0, "elapsed_time": "0:58:15", "remaining_time": "0:07:11", "throughput": 5688.21, "total_tokens": 19881896} {"current_steps": 30195, "total_steps": 33920, "loss": 0.3456, "lr": 3.630790850855986e-07, "epoch": 17.80365566037736, "percentage": 89.02, "elapsed_time": "0:58:15", "remaining_time": "0:07:11", "throughput": 5688.17, "total_tokens": 19884808} {"current_steps": 30200, "total_steps": 33920, "loss": 0.25, "lr": 3.62117219894762e-07, "epoch": 17.806603773584907, "percentage": 89.03, "elapsed_time": "0:58:16", "remaining_time": "0:07:10", "throughput": 5688.09, "total_tokens": 19887528} {"current_steps": 30205, "total_steps": 33920, "loss": 0.2629, "lr": 3.611565826033797e-07, "epoch": 17.809551886792452, "percentage": 89.05, "elapsed_time": "0:58:16", "remaining_time": "0:07:10", "throughput": 5688.02, "total_tokens": 19890440} {"current_steps": 30210, "total_steps": 33920, "loss": 0.2757, "lr": 3.6019717346578445e-07, "epoch": 17.8125, "percentage": 89.06, "elapsed_time": "0:58:17", "remaining_time": "0:07:09", "throughput": 5687.97, "total_tokens": 19893288} {"current_steps": 30215, "total_steps": 33920, "loss": 0.2749, "lr": 3.5923899273598293e-07, "epoch": 17.815448113207548, "percentage": 89.08, "elapsed_time": "0:58:17", "remaining_time": "0:07:08", "throughput": 5687.93, "total_tokens": 19896136} {"current_steps": 30220, "total_steps": 33920, "loss": 0.2919, "lr": 3.582820406676596e-07, "epoch": 17.818396226415093, "percentage": 89.09, "elapsed_time": "0:58:18", "remaining_time": "0:07:08", "throughput": 5688.05, "total_tokens": 19899880} {"current_steps": 30225, "total_steps": 33920, "loss": 0.2423, "lr": 3.5732631751417056e-07, "epoch": 17.82134433962264, "percentage": 89.11, "elapsed_time": "0:58:19", "remaining_time": "0:07:07", "throughput": 5688.22, "total_tokens": 19903944} {"current_steps": 30230, "total_steps": 33920, "loss": 0.3418, "lr": 3.563718235285485e-07, "epoch": 17.82429245283019, "percentage": 89.12, "elapsed_time": "0:58:19", "remaining_time": "0:07:07", "throughput": 5688.19, "total_tokens": 19906952} {"current_steps": 30235, "total_steps": 33920, "loss": 0.3596, "lr": 3.5541855896349844e-07, "epoch": 17.827240566037737, "percentage": 89.14, "elapsed_time": "0:58:20", "remaining_time": "0:07:06", "throughput": 5688.07, "total_tokens": 19909512} {"current_steps": 30240, "total_steps": 33920, "loss": 0.4664, "lr": 3.544665240714018e-07, "epoch": 17.830188679245282, "percentage": 89.15, "elapsed_time": "0:58:20", "remaining_time": "0:07:06", "throughput": 5688.01, "total_tokens": 19912392} {"current_steps": 30245, "total_steps": 33920, "loss": 0.2597, "lr": 3.535157191043137e-07, "epoch": 17.83313679245283, "percentage": 89.17, "elapsed_time": "0:58:21", "remaining_time": "0:07:05", "throughput": 5688.09, "total_tokens": 19916104} {"current_steps": 30250, "total_steps": 33920, "loss": 0.3624, "lr": 3.5256614431396385e-07, "epoch": 17.83608490566038, "percentage": 89.18, "elapsed_time": "0:58:21", "remaining_time": "0:07:04", "throughput": 5688.03, "total_tokens": 19919016} {"current_steps": 30255, "total_steps": 33920, "loss": 0.2706, "lr": 3.516177999517578e-07, "epoch": 17.839033018867923, "percentage": 89.2, "elapsed_time": "0:58:22", "remaining_time": "0:07:04", "throughput": 5688.0, "total_tokens": 19921992} {"current_steps": 30260, "total_steps": 33920, "loss": 0.2668, "lr": 3.50670686268772e-07, "epoch": 17.84198113207547, "percentage": 89.21, "elapsed_time": "0:58:23", "remaining_time": "0:07:03", "throughput": 5688.07, "total_tokens": 19925800} {"current_steps": 30265, "total_steps": 33920, "loss": 0.2921, "lr": 3.497248035157602e-07, "epoch": 17.84492924528302, "percentage": 89.22, "elapsed_time": "0:58:23", "remaining_time": "0:07:03", "throughput": 5687.85, "total_tokens": 19928104} {"current_steps": 30270, "total_steps": 33920, "loss": 0.3811, "lr": 3.4878015194314773e-07, "epoch": 17.847877358490567, "percentage": 89.24, "elapsed_time": "0:58:24", "remaining_time": "0:07:02", "throughput": 5687.72, "total_tokens": 19930600} {"current_steps": 30275, "total_steps": 33920, "loss": 0.3804, "lr": 3.4783673180103617e-07, "epoch": 17.850825471698112, "percentage": 89.25, "elapsed_time": "0:58:24", "remaining_time": "0:07:01", "throughput": 5687.8, "total_tokens": 19934504} {"current_steps": 30280, "total_steps": 33920, "loss": 0.2882, "lr": 3.468945433391985e-07, "epoch": 17.85377358490566, "percentage": 89.27, "elapsed_time": "0:58:25", "remaining_time": "0:07:01", "throughput": 5687.83, "total_tokens": 19938024} {"current_steps": 30285, "total_steps": 33920, "loss": 0.2419, "lr": 3.459535868070851e-07, "epoch": 17.85672169811321, "percentage": 89.28, "elapsed_time": "0:58:26", "remaining_time": "0:07:00", "throughput": 5687.79, "total_tokens": 19941576} {"current_steps": 30290, "total_steps": 33920, "loss": 0.3102, "lr": 3.450138624538174e-07, "epoch": 17.859669811320753, "percentage": 89.3, "elapsed_time": "0:58:26", "remaining_time": "0:07:00", "throughput": 5687.87, "total_tokens": 19945384} {"current_steps": 30295, "total_steps": 33920, "loss": 0.309, "lr": 3.440753705281913e-07, "epoch": 17.8626179245283, "percentage": 89.31, "elapsed_time": "0:58:27", "remaining_time": "0:06:59", "throughput": 5687.87, "total_tokens": 19948904} {"current_steps": 30300, "total_steps": 33920, "loss": 0.3372, "lr": 3.4313811127867693e-07, "epoch": 17.86556603773585, "percentage": 89.33, "elapsed_time": "0:58:27", "remaining_time": "0:06:59", "throughput": 5687.91, "total_tokens": 19952200} {"current_steps": 30305, "total_steps": 33920, "loss": 0.2357, "lr": 3.4220208495341745e-07, "epoch": 17.868514150943398, "percentage": 89.34, "elapsed_time": "0:58:28", "remaining_time": "0:06:58", "throughput": 5688.04, "total_tokens": 19956072} {"current_steps": 30310, "total_steps": 33920, "loss": 0.3974, "lr": 3.412672918002291e-07, "epoch": 17.871462264150942, "percentage": 89.36, "elapsed_time": "0:58:28", "remaining_time": "0:06:57", "throughput": 5688.05, "total_tokens": 19959304} {"current_steps": 30315, "total_steps": 33920, "loss": 0.4897, "lr": 3.403337320666045e-07, "epoch": 17.87441037735849, "percentage": 89.37, "elapsed_time": "0:58:29", "remaining_time": "0:06:57", "throughput": 5687.87, "total_tokens": 19961736} {"current_steps": 30320, "total_steps": 33920, "loss": 0.3162, "lr": 3.394014059997064e-07, "epoch": 17.87735849056604, "percentage": 89.39, "elapsed_time": "0:58:30", "remaining_time": "0:06:56", "throughput": 5687.83, "total_tokens": 19964776} {"current_steps": 30325, "total_steps": 33920, "loss": 0.2975, "lr": 3.3847031384637185e-07, "epoch": 17.880306603773583, "percentage": 89.4, "elapsed_time": "0:58:30", "remaining_time": "0:06:56", "throughput": 5687.8, "total_tokens": 19967688} {"current_steps": 30330, "total_steps": 33920, "loss": 0.2639, "lr": 3.3754045585311147e-07, "epoch": 17.88325471698113, "percentage": 89.42, "elapsed_time": "0:58:31", "remaining_time": "0:06:55", "throughput": 5687.84, "total_tokens": 19971112} {"current_steps": 30335, "total_steps": 33920, "loss": 0.5017, "lr": 3.366118322661094e-07, "epoch": 17.88620283018868, "percentage": 89.43, "elapsed_time": "0:58:31", "remaining_time": "0:06:55", "throughput": 5688.01, "total_tokens": 19975528} {"current_steps": 30340, "total_steps": 33920, "loss": 0.4853, "lr": 3.3568444333122283e-07, "epoch": 17.889150943396228, "percentage": 89.45, "elapsed_time": "0:58:32", "remaining_time": "0:06:54", "throughput": 5688.05, "total_tokens": 19979048} {"current_steps": 30345, "total_steps": 33920, "loss": 0.3321, "lr": 3.347582892939816e-07, "epoch": 17.892099056603772, "percentage": 89.46, "elapsed_time": "0:58:33", "remaining_time": "0:06:53", "throughput": 5688.12, "total_tokens": 19982376} {"current_steps": 30350, "total_steps": 33920, "loss": 0.5144, "lr": 3.338333703995905e-07, "epoch": 17.89504716981132, "percentage": 89.48, "elapsed_time": "0:58:33", "remaining_time": "0:06:53", "throughput": 5688.17, "total_tokens": 19985576} {"current_steps": 30355, "total_steps": 33920, "loss": 0.2666, "lr": 3.329096868929238e-07, "epoch": 17.89799528301887, "percentage": 89.49, "elapsed_time": "0:58:34", "remaining_time": "0:06:52", "throughput": 5688.11, "total_tokens": 19988456} {"current_steps": 30360, "total_steps": 33920, "loss": 0.3393, "lr": 3.319872390185325e-07, "epoch": 17.900943396226417, "percentage": 89.5, "elapsed_time": "0:58:34", "remaining_time": "0:06:52", "throughput": 5688.12, "total_tokens": 19991784} {"current_steps": 30365, "total_steps": 33920, "loss": 0.3493, "lr": 3.3106602702063727e-07, "epoch": 17.90389150943396, "percentage": 89.52, "elapsed_time": "0:58:35", "remaining_time": "0:06:51", "throughput": 5688.15, "total_tokens": 19995080} {"current_steps": 30370, "total_steps": 33920, "loss": 0.2601, "lr": 3.3014605114313316e-07, "epoch": 17.90683962264151, "percentage": 89.53, "elapsed_time": "0:58:35", "remaining_time": "0:06:50", "throughput": 5688.02, "total_tokens": 19997576} {"current_steps": 30375, "total_steps": 33920, "loss": 0.32, "lr": 3.2922731162958744e-07, "epoch": 17.909787735849058, "percentage": 89.55, "elapsed_time": "0:58:36", "remaining_time": "0:06:50", "throughput": 5688.04, "total_tokens": 20000968} {"current_steps": 30380, "total_steps": 33920, "loss": 0.3419, "lr": 3.2830980872324114e-07, "epoch": 17.912735849056602, "percentage": 89.56, "elapsed_time": "0:58:36", "remaining_time": "0:06:49", "throughput": 5688.14, "total_tokens": 20005000} {"current_steps": 30385, "total_steps": 33920, "loss": 0.4541, "lr": 3.2739354266700775e-07, "epoch": 17.91568396226415, "percentage": 89.58, "elapsed_time": "0:58:37", "remaining_time": "0:06:49", "throughput": 5688.34, "total_tokens": 20009288} {"current_steps": 30390, "total_steps": 33920, "loss": 0.3424, "lr": 3.264785137034709e-07, "epoch": 17.9186320754717, "percentage": 89.59, "elapsed_time": "0:58:38", "remaining_time": "0:06:48", "throughput": 5688.37, "total_tokens": 20012584} {"current_steps": 30395, "total_steps": 33920, "loss": 0.2917, "lr": 3.2556472207488977e-07, "epoch": 17.921580188679247, "percentage": 89.61, "elapsed_time": "0:58:38", "remaining_time": "0:06:48", "throughput": 5688.34, "total_tokens": 20015624} {"current_steps": 30400, "total_steps": 33920, "loss": 0.2219, "lr": 3.246521680231934e-07, "epoch": 17.92452830188679, "percentage": 89.62, "elapsed_time": "0:58:39", "remaining_time": "0:06:47", "throughput": 5688.19, "total_tokens": 20018248} {"current_steps": 30405, "total_steps": 33920, "loss": 0.2703, "lr": 3.2374085178998594e-07, "epoch": 17.92747641509434, "percentage": 89.64, "elapsed_time": "0:58:39", "remaining_time": "0:06:46", "throughput": 5688.28, "total_tokens": 20021960} {"current_steps": 30410, "total_steps": 33920, "loss": 0.2776, "lr": 3.2283077361654145e-07, "epoch": 17.930424528301888, "percentage": 89.65, "elapsed_time": "0:58:40", "remaining_time": "0:06:46", "throughput": 5688.25, "total_tokens": 20024904} {"current_steps": 30415, "total_steps": 33920, "loss": 0.4731, "lr": 3.2192193374380677e-07, "epoch": 17.933372641509433, "percentage": 89.67, "elapsed_time": "0:58:40", "remaining_time": "0:06:45", "throughput": 5688.25, "total_tokens": 20028008} {"current_steps": 30420, "total_steps": 33920, "loss": 0.3391, "lr": 3.210143324124021e-07, "epoch": 17.93632075471698, "percentage": 89.68, "elapsed_time": "0:58:41", "remaining_time": "0:06:45", "throughput": 5688.13, "total_tokens": 20030632} {"current_steps": 30425, "total_steps": 33920, "loss": 0.2719, "lr": 3.2010796986261805e-07, "epoch": 17.93926886792453, "percentage": 89.7, "elapsed_time": "0:58:42", "remaining_time": "0:06:44", "throughput": 5688.15, "total_tokens": 20033704} {"current_steps": 30430, "total_steps": 33920, "loss": 0.2505, "lr": 3.1920284633441713e-07, "epoch": 17.942216981132077, "percentage": 89.71, "elapsed_time": "0:58:42", "remaining_time": "0:06:44", "throughput": 5688.2, "total_tokens": 20037160} {"current_steps": 30435, "total_steps": 33920, "loss": 0.4609, "lr": 3.1829896206743704e-07, "epoch": 17.94516509433962, "percentage": 89.73, "elapsed_time": "0:58:43", "remaining_time": "0:06:43", "throughput": 5688.22, "total_tokens": 20040616} {"current_steps": 30440, "total_steps": 33920, "loss": 0.3146, "lr": 3.173963173009825e-07, "epoch": 17.94811320754717, "percentage": 89.74, "elapsed_time": "0:58:43", "remaining_time": "0:06:42", "throughput": 5688.07, "total_tokens": 20043112} {"current_steps": 30445, "total_steps": 33920, "loss": 0.2848, "lr": 3.164949122740352e-07, "epoch": 17.951061320754718, "percentage": 89.76, "elapsed_time": "0:58:44", "remaining_time": "0:06:42", "throughput": 5687.93, "total_tokens": 20045864} {"current_steps": 30450, "total_steps": 33920, "loss": 0.2781, "lr": 3.1559474722524406e-07, "epoch": 17.954009433962263, "percentage": 89.77, "elapsed_time": "0:58:44", "remaining_time": "0:06:41", "throughput": 5687.84, "total_tokens": 20049064} {"current_steps": 30455, "total_steps": 33920, "loss": 0.2871, "lr": 3.146958223929325e-07, "epoch": 17.95695754716981, "percentage": 89.78, "elapsed_time": "0:58:45", "remaining_time": "0:06:41", "throughput": 5687.9, "total_tokens": 20052552} {"current_steps": 30460, "total_steps": 33920, "loss": 0.381, "lr": 3.1379813801509454e-07, "epoch": 17.95990566037736, "percentage": 89.8, "elapsed_time": "0:58:46", "remaining_time": "0:06:40", "throughput": 5687.83, "total_tokens": 20055336} {"current_steps": 30465, "total_steps": 33920, "loss": 0.4078, "lr": 3.1290169432939556e-07, "epoch": 17.962853773584907, "percentage": 89.81, "elapsed_time": "0:58:46", "remaining_time": "0:06:39", "throughput": 5687.83, "total_tokens": 20058824} {"current_steps": 30470, "total_steps": 33920, "loss": 0.2885, "lr": 3.120064915731735e-07, "epoch": 17.965801886792452, "percentage": 89.83, "elapsed_time": "0:58:47", "remaining_time": "0:06:39", "throughput": 5687.71, "total_tokens": 20061512} {"current_steps": 30475, "total_steps": 33920, "loss": 0.3101, "lr": 3.1111252998343723e-07, "epoch": 17.96875, "percentage": 89.84, "elapsed_time": "0:58:47", "remaining_time": "0:06:38", "throughput": 5687.57, "total_tokens": 20064040} {"current_steps": 30480, "total_steps": 33920, "loss": 0.2692, "lr": 3.102198097968662e-07, "epoch": 17.971698113207548, "percentage": 89.86, "elapsed_time": "0:58:48", "remaining_time": "0:06:38", "throughput": 5687.52, "total_tokens": 20066920} {"current_steps": 30485, "total_steps": 33920, "loss": 0.3757, "lr": 3.093283312498124e-07, "epoch": 17.974646226415093, "percentage": 89.87, "elapsed_time": "0:58:48", "remaining_time": "0:06:37", "throughput": 5687.56, "total_tokens": 20070312} {"current_steps": 30490, "total_steps": 33920, "loss": 0.2376, "lr": 3.084380945782989e-07, "epoch": 17.97759433962264, "percentage": 89.89, "elapsed_time": "0:58:49", "remaining_time": "0:06:37", "throughput": 5687.64, "total_tokens": 20073864} {"current_steps": 30495, "total_steps": 33920, "loss": 0.3591, "lr": 3.0754910001801866e-07, "epoch": 17.98054245283019, "percentage": 89.9, "elapsed_time": "0:58:49", "remaining_time": "0:06:36", "throughput": 5687.7, "total_tokens": 20077224} {"current_steps": 30500, "total_steps": 33920, "loss": 0.3332, "lr": 3.0666134780433786e-07, "epoch": 17.983490566037737, "percentage": 89.92, "elapsed_time": "0:58:50", "remaining_time": "0:06:35", "throughput": 5687.75, "total_tokens": 20080520} {"current_steps": 30505, "total_steps": 33920, "loss": 0.3545, "lr": 3.0577483817229306e-07, "epoch": 17.986438679245282, "percentage": 89.93, "elapsed_time": "0:58:51", "remaining_time": "0:06:35", "throughput": 5687.8, "total_tokens": 20084008} {"current_steps": 30510, "total_steps": 33920, "loss": 0.2566, "lr": 3.0488957135659023e-07, "epoch": 17.98938679245283, "percentage": 89.95, "elapsed_time": "0:58:51", "remaining_time": "0:06:34", "throughput": 5687.78, "total_tokens": 20087080} {"current_steps": 30515, "total_steps": 33920, "loss": 0.2916, "lr": 3.040055475916087e-07, "epoch": 17.99233490566038, "percentage": 89.96, "elapsed_time": "0:58:52", "remaining_time": "0:06:34", "throughput": 5687.86, "total_tokens": 20090728} {"current_steps": 30520, "total_steps": 33920, "loss": 0.2435, "lr": 3.0312276711139675e-07, "epoch": 17.995283018867923, "percentage": 89.98, "elapsed_time": "0:58:52", "remaining_time": "0:06:33", "throughput": 5687.86, "total_tokens": 20093832} {"current_steps": 30525, "total_steps": 33920, "loss": 0.3118, "lr": 3.0224123014967353e-07, "epoch": 17.99823113207547, "percentage": 89.99, "elapsed_time": "0:58:53", "remaining_time": "0:06:32", "throughput": 5687.81, "total_tokens": 20096936} {"current_steps": 30528, "total_steps": 33920, "eval_loss": 0.6042706966400146, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "0:59:12", "remaining_time": "0:06:34", "throughput": 5657.51, "total_tokens": 20098848} {"current_steps": 30530, "total_steps": 33920, "loss": 0.237, "lr": 3.013609369398324e-07, "epoch": 18.00117924528302, "percentage": 90.01, "elapsed_time": "0:59:16", "remaining_time": "0:06:34", "throughput": 5652.02, "total_tokens": 20100064} {"current_steps": 30535, "total_steps": 33920, "loss": 0.2298, "lr": 3.004818877149318e-07, "epoch": 18.004127358490567, "percentage": 90.02, "elapsed_time": "0:59:16", "remaining_time": "0:06:34", "throughput": 5651.88, "total_tokens": 20102912} {"current_steps": 30540, "total_steps": 33920, "loss": 0.3178, "lr": 2.9960408270770624e-07, "epoch": 18.007075471698112, "percentage": 90.04, "elapsed_time": "0:59:17", "remaining_time": "0:06:33", "throughput": 5651.68, "total_tokens": 20105408} {"current_steps": 30545, "total_steps": 33920, "loss": 0.3001, "lr": 2.9872752215055755e-07, "epoch": 18.01002358490566, "percentage": 90.05, "elapsed_time": "0:59:18", "remaining_time": "0:06:33", "throughput": 5651.52, "total_tokens": 20108160} {"current_steps": 30550, "total_steps": 33920, "loss": 0.3134, "lr": 2.9785220627555844e-07, "epoch": 18.01297169811321, "percentage": 90.06, "elapsed_time": "0:59:18", "remaining_time": "0:06:32", "throughput": 5651.64, "total_tokens": 20112736} {"current_steps": 30555, "total_steps": 33920, "loss": 0.3682, "lr": 2.9697813531445295e-07, "epoch": 18.015919811320753, "percentage": 90.08, "elapsed_time": "0:59:19", "remaining_time": "0:06:31", "throughput": 5651.57, "total_tokens": 20115840} {"current_steps": 30560, "total_steps": 33920, "loss": 0.2745, "lr": 2.9610530949865433e-07, "epoch": 18.0188679245283, "percentage": 90.09, "elapsed_time": "0:59:19", "remaining_time": "0:06:31", "throughput": 5651.58, "total_tokens": 20119200} {"current_steps": 30565, "total_steps": 33920, "loss": 0.3283, "lr": 2.952337290592483e-07, "epoch": 18.02181603773585, "percentage": 90.11, "elapsed_time": "0:59:20", "remaining_time": "0:06:30", "throughput": 5651.67, "total_tokens": 20122720} {"current_steps": 30570, "total_steps": 33920, "loss": 0.266, "lr": 2.9436339422698913e-07, "epoch": 18.024764150943398, "percentage": 90.12, "elapsed_time": "0:59:21", "remaining_time": "0:06:30", "throughput": 5651.66, "total_tokens": 20125728} {"current_steps": 30575, "total_steps": 33920, "loss": 0.2899, "lr": 2.934943052323008e-07, "epoch": 18.027712264150942, "percentage": 90.14, "elapsed_time": "0:59:21", "remaining_time": "0:06:29", "throughput": 5651.68, "total_tokens": 20129216} {"current_steps": 30580, "total_steps": 33920, "loss": 0.4901, "lr": 2.926264623052799e-07, "epoch": 18.03066037735849, "percentage": 90.15, "elapsed_time": "0:59:22", "remaining_time": "0:06:29", "throughput": 5651.84, "total_tokens": 20135008} {"current_steps": 30585, "total_steps": 33920, "loss": 0.2576, "lr": 2.9175986567569036e-07, "epoch": 18.03360849056604, "percentage": 90.17, "elapsed_time": "0:59:23", "remaining_time": "0:06:28", "throughput": 5651.91, "total_tokens": 20138272} {"current_steps": 30590, "total_steps": 33920, "loss": 0.3203, "lr": 2.9089451557296755e-07, "epoch": 18.036556603773583, "percentage": 90.18, "elapsed_time": "0:59:23", "remaining_time": "0:06:27", "throughput": 5651.89, "total_tokens": 20141536} {"current_steps": 30595, "total_steps": 33920, "loss": 0.2677, "lr": 2.9003041222621706e-07, "epoch": 18.03950471698113, "percentage": 90.2, "elapsed_time": "0:59:24", "remaining_time": "0:06:27", "throughput": 5652.0, "total_tokens": 20145728} {"current_steps": 30600, "total_steps": 33920, "loss": 0.3314, "lr": 2.8916755586421375e-07, "epoch": 18.04245283018868, "percentage": 90.21, "elapsed_time": "0:59:24", "remaining_time": "0:06:26", "throughput": 5651.91, "total_tokens": 20148544} {"current_steps": 30605, "total_steps": 33920, "loss": 0.333, "lr": 2.883059467154031e-07, "epoch": 18.045400943396228, "percentage": 90.23, "elapsed_time": "0:59:25", "remaining_time": "0:06:26", "throughput": 5651.93, "total_tokens": 20151904} {"current_steps": 30610, "total_steps": 33920, "loss": 0.335, "lr": 2.8744558500789887e-07, "epoch": 18.048349056603772, "percentage": 90.24, "elapsed_time": "0:59:26", "remaining_time": "0:06:25", "throughput": 5651.94, "total_tokens": 20155264} {"current_steps": 30615, "total_steps": 33920, "loss": 0.2517, "lr": 2.8658647096948546e-07, "epoch": 18.05129716981132, "percentage": 90.26, "elapsed_time": "0:59:26", "remaining_time": "0:06:25", "throughput": 5651.9, "total_tokens": 20158240} {"current_steps": 30620, "total_steps": 33920, "loss": 0.2661, "lr": 2.8572860482761813e-07, "epoch": 18.05424528301887, "percentage": 90.27, "elapsed_time": "0:59:27", "remaining_time": "0:06:24", "throughput": 5651.89, "total_tokens": 20161344} {"current_steps": 30625, "total_steps": 33920, "loss": 0.282, "lr": 2.8487198680942017e-07, "epoch": 18.057193396226417, "percentage": 90.29, "elapsed_time": "0:59:27", "remaining_time": "0:06:23", "throughput": 5651.8, "total_tokens": 20164192} {"current_steps": 30630, "total_steps": 33920, "loss": 0.3425, "lr": 2.840166171416836e-07, "epoch": 18.06014150943396, "percentage": 90.3, "elapsed_time": "0:59:28", "remaining_time": "0:06:23", "throughput": 5651.75, "total_tokens": 20167456} {"current_steps": 30635, "total_steps": 33920, "loss": 0.2527, "lr": 2.8316249605087386e-07, "epoch": 18.06308962264151, "percentage": 90.32, "elapsed_time": "0:59:28", "remaining_time": "0:06:22", "throughput": 5651.61, "total_tokens": 20169920} {"current_steps": 30640, "total_steps": 33920, "loss": 0.494, "lr": 2.823096237631212e-07, "epoch": 18.066037735849058, "percentage": 90.33, "elapsed_time": "0:59:29", "remaining_time": "0:06:22", "throughput": 5651.58, "total_tokens": 20172896} {"current_steps": 30645, "total_steps": 33920, "loss": 0.2346, "lr": 2.814580005042283e-07, "epoch": 18.068985849056602, "percentage": 90.34, "elapsed_time": "0:59:30", "remaining_time": "0:06:21", "throughput": 5651.66, "total_tokens": 20177024} {"current_steps": 30650, "total_steps": 33920, "loss": 0.3488, "lr": 2.8060762649966435e-07, "epoch": 18.07193396226415, "percentage": 90.36, "elapsed_time": "0:59:30", "remaining_time": "0:06:20", "throughput": 5651.66, "total_tokens": 20180416} {"current_steps": 30655, "total_steps": 33920, "loss": 0.2322, "lr": 2.797585019745713e-07, "epoch": 18.0748820754717, "percentage": 90.37, "elapsed_time": "0:59:31", "remaining_time": "0:06:20", "throughput": 5651.7, "total_tokens": 20183840} {"current_steps": 30660, "total_steps": 33920, "loss": 0.4089, "lr": 2.789106271537584e-07, "epoch": 18.077830188679247, "percentage": 90.39, "elapsed_time": "0:59:31", "remaining_time": "0:06:19", "throughput": 5651.68, "total_tokens": 20186784} {"current_steps": 30665, "total_steps": 33920, "loss": 0.2981, "lr": 2.780640022617037e-07, "epoch": 18.08077830188679, "percentage": 90.4, "elapsed_time": "0:59:32", "remaining_time": "0:06:19", "throughput": 5651.61, "total_tokens": 20189440} {"current_steps": 30670, "total_steps": 33920, "loss": 0.3085, "lr": 2.772186275225547e-07, "epoch": 18.08372641509434, "percentage": 90.42, "elapsed_time": "0:59:32", "remaining_time": "0:06:18", "throughput": 5651.48, "total_tokens": 20191936} {"current_steps": 30675, "total_steps": 33920, "loss": 0.3451, "lr": 2.7637450316012836e-07, "epoch": 18.086674528301888, "percentage": 90.43, "elapsed_time": "0:59:33", "remaining_time": "0:06:18", "throughput": 5651.68, "total_tokens": 20196288} {"current_steps": 30680, "total_steps": 33920, "loss": 0.3475, "lr": 2.755316293979088e-07, "epoch": 18.089622641509433, "percentage": 90.45, "elapsed_time": "0:59:34", "remaining_time": "0:06:17", "throughput": 5651.87, "total_tokens": 20203232} {"current_steps": 30685, "total_steps": 33920, "loss": 0.3314, "lr": 2.7469000645905295e-07, "epoch": 18.09257075471698, "percentage": 90.46, "elapsed_time": "0:59:35", "remaining_time": "0:06:16", "throughput": 5651.91, "total_tokens": 20206752} {"current_steps": 30690, "total_steps": 33920, "loss": 0.3292, "lr": 2.738496345663827e-07, "epoch": 18.09551886792453, "percentage": 90.48, "elapsed_time": "0:59:35", "remaining_time": "0:06:16", "throughput": 5652.01, "total_tokens": 20210400} {"current_steps": 30695, "total_steps": 33920, "loss": 0.2567, "lr": 2.7301051394239e-07, "epoch": 18.098466981132077, "percentage": 90.49, "elapsed_time": "0:59:36", "remaining_time": "0:06:15", "throughput": 5652.01, "total_tokens": 20213664} {"current_steps": 30700, "total_steps": 33920, "loss": 0.2703, "lr": 2.72172644809236e-07, "epoch": 18.10141509433962, "percentage": 90.51, "elapsed_time": "0:59:36", "remaining_time": "0:06:15", "throughput": 5652.03, "total_tokens": 20217056} {"current_steps": 30705, "total_steps": 33920, "loss": 0.242, "lr": 2.7133602738875e-07, "epoch": 18.10436320754717, "percentage": 90.52, "elapsed_time": "0:59:37", "remaining_time": "0:06:14", "throughput": 5652.09, "total_tokens": 20220480} {"current_steps": 30710, "total_steps": 33920, "loss": 0.315, "lr": 2.7050066190242976e-07, "epoch": 18.107311320754718, "percentage": 90.54, "elapsed_time": "0:59:38", "remaining_time": "0:06:14", "throughput": 5652.32, "total_tokens": 20227424} {"current_steps": 30715, "total_steps": 33920, "loss": 0.309, "lr": 2.696665485714428e-07, "epoch": 18.110259433962263, "percentage": 90.55, "elapsed_time": "0:59:39", "remaining_time": "0:06:13", "throughput": 5652.47, "total_tokens": 20231424} {"current_steps": 30720, "total_steps": 33920, "loss": 0.295, "lr": 2.6883368761662367e-07, "epoch": 18.11320754716981, "percentage": 90.57, "elapsed_time": "0:59:39", "remaining_time": "0:06:12", "throughput": 5652.48, "total_tokens": 20234464} {"current_steps": 30725, "total_steps": 33920, "loss": 0.435, "lr": 2.680020792584759e-07, "epoch": 18.11615566037736, "percentage": 90.58, "elapsed_time": "0:59:40", "remaining_time": "0:06:12", "throughput": 5652.56, "total_tokens": 20237888} {"current_steps": 30730, "total_steps": 33920, "loss": 0.3982, "lr": 2.6717172371717113e-07, "epoch": 18.119103773584907, "percentage": 90.6, "elapsed_time": "0:59:40", "remaining_time": "0:06:11", "throughput": 5652.52, "total_tokens": 20240640} {"current_steps": 30735, "total_steps": 33920, "loss": 0.4454, "lr": 2.663426212125503e-07, "epoch": 18.122051886792452, "percentage": 90.61, "elapsed_time": "0:59:41", "remaining_time": "0:06:11", "throughput": 5652.57, "total_tokens": 20244224} {"current_steps": 30740, "total_steps": 33920, "loss": 0.3238, "lr": 2.655147719641216e-07, "epoch": 18.125, "percentage": 90.62, "elapsed_time": "0:59:42", "remaining_time": "0:06:10", "throughput": 5652.69, "total_tokens": 20248128} {"current_steps": 30745, "total_steps": 33920, "loss": 0.3743, "lr": 2.646881761910602e-07, "epoch": 18.127948113207548, "percentage": 90.64, "elapsed_time": "0:59:42", "remaining_time": "0:06:09", "throughput": 5652.82, "total_tokens": 20252160} {"current_steps": 30750, "total_steps": 33920, "loss": 0.2597, "lr": 2.638628341122135e-07, "epoch": 18.130896226415093, "percentage": 90.65, "elapsed_time": "0:59:43", "remaining_time": "0:06:09", "throughput": 5652.78, "total_tokens": 20255488} {"current_steps": 30755, "total_steps": 33920, "loss": 0.2966, "lr": 2.6303874594609314e-07, "epoch": 18.13384433962264, "percentage": 90.67, "elapsed_time": "0:59:43", "remaining_time": "0:06:08", "throughput": 5652.82, "total_tokens": 20258720} {"current_steps": 30760, "total_steps": 33920, "loss": 0.3143, "lr": 2.622159119108797e-07, "epoch": 18.13679245283019, "percentage": 90.68, "elapsed_time": "0:59:44", "remaining_time": "0:06:08", "throughput": 5652.8, "total_tokens": 20261728} {"current_steps": 30765, "total_steps": 33920, "loss": 0.1921, "lr": 2.6139433222442226e-07, "epoch": 18.139740566037737, "percentage": 90.7, "elapsed_time": "0:59:45", "remaining_time": "0:06:07", "throughput": 5652.87, "total_tokens": 20265696} {"current_steps": 30770, "total_steps": 33920, "loss": 0.2661, "lr": 2.6057400710423787e-07, "epoch": 18.142688679245282, "percentage": 90.71, "elapsed_time": "0:59:45", "remaining_time": "0:06:07", "throughput": 5653.01, "total_tokens": 20269248} {"current_steps": 30775, "total_steps": 33920, "loss": 0.3622, "lr": 2.5975493676751004e-07, "epoch": 18.14563679245283, "percentage": 90.73, "elapsed_time": "0:59:46", "remaining_time": "0:06:06", "throughput": 5653.06, "total_tokens": 20272896} {"current_steps": 30780, "total_steps": 33920, "loss": 0.2917, "lr": 2.589371214310926e-07, "epoch": 18.14858490566038, "percentage": 90.74, "elapsed_time": "0:59:46", "remaining_time": "0:06:05", "throughput": 5653.05, "total_tokens": 20275744} {"current_steps": 30785, "total_steps": 33920, "loss": 0.2928, "lr": 2.581205613115051e-07, "epoch": 18.151533018867923, "percentage": 90.76, "elapsed_time": "0:59:47", "remaining_time": "0:06:05", "throughput": 5652.92, "total_tokens": 20278368} {"current_steps": 30790, "total_steps": 33920, "loss": 0.3468, "lr": 2.573052566249357e-07, "epoch": 18.15448113207547, "percentage": 90.77, "elapsed_time": "0:59:47", "remaining_time": "0:06:04", "throughput": 5652.85, "total_tokens": 20281120} {"current_steps": 30795, "total_steps": 33920, "loss": 0.3574, "lr": 2.5649120758723945e-07, "epoch": 18.15742924528302, "percentage": 90.79, "elapsed_time": "0:59:48", "remaining_time": "0:06:04", "throughput": 5652.75, "total_tokens": 20283712} {"current_steps": 30800, "total_steps": 33920, "loss": 0.2377, "lr": 2.5567841441393906e-07, "epoch": 18.160377358490567, "percentage": 90.8, "elapsed_time": "0:59:48", "remaining_time": "0:06:03", "throughput": 5652.75, "total_tokens": 20287072} {"current_steps": 30805, "total_steps": 33920, "loss": 0.3674, "lr": 2.548668773202245e-07, "epoch": 18.163325471698112, "percentage": 90.82, "elapsed_time": "0:59:49", "remaining_time": "0:06:02", "throughput": 5652.83, "total_tokens": 20290816} {"current_steps": 30810, "total_steps": 33920, "loss": 0.2954, "lr": 2.5405659652095573e-07, "epoch": 18.16627358490566, "percentage": 90.83, "elapsed_time": "0:59:50", "remaining_time": "0:06:02", "throughput": 5652.86, "total_tokens": 20293920} {"current_steps": 30815, "total_steps": 33920, "loss": 0.3877, "lr": 2.5324757223065655e-07, "epoch": 18.16922169811321, "percentage": 90.85, "elapsed_time": "0:59:50", "remaining_time": "0:06:01", "throughput": 5653.06, "total_tokens": 20298720} {"current_steps": 30820, "total_steps": 33920, "loss": 0.2492, "lr": 2.524398046635207e-07, "epoch": 18.172169811320753, "percentage": 90.86, "elapsed_time": "0:59:51", "remaining_time": "0:06:01", "throughput": 5653.21, "total_tokens": 20303424} {"current_steps": 30825, "total_steps": 33920, "loss": 0.2431, "lr": 2.51633294033406e-07, "epoch": 18.1751179245283, "percentage": 90.88, "elapsed_time": "0:59:52", "remaining_time": "0:06:00", "throughput": 5653.2, "total_tokens": 20306400} {"current_steps": 30830, "total_steps": 33920, "loss": 0.3308, "lr": 2.5082804055384214e-07, "epoch": 18.17806603773585, "percentage": 90.89, "elapsed_time": "0:59:52", "remaining_time": "0:06:00", "throughput": 5653.22, "total_tokens": 20309440} {"current_steps": 30835, "total_steps": 33920, "loss": 0.3599, "lr": 2.50024044438022e-07, "epoch": 18.181014150943398, "percentage": 90.91, "elapsed_time": "0:59:53", "remaining_time": "0:05:59", "throughput": 5653.25, "total_tokens": 20312736} {"current_steps": 30840, "total_steps": 33920, "loss": 0.2549, "lr": 2.492213058988069e-07, "epoch": 18.183962264150942, "percentage": 90.92, "elapsed_time": "0:59:53", "remaining_time": "0:05:58", "throughput": 5653.16, "total_tokens": 20315424} {"current_steps": 30845, "total_steps": 33920, "loss": 0.3904, "lr": 2.4841982514872633e-07, "epoch": 18.18691037735849, "percentage": 90.93, "elapsed_time": "0:59:54", "remaining_time": "0:05:58", "throughput": 5653.06, "total_tokens": 20318176} {"current_steps": 30850, "total_steps": 33920, "loss": 0.4196, "lr": 2.4761960239997497e-07, "epoch": 18.18985849056604, "percentage": 90.95, "elapsed_time": "0:59:55", "remaining_time": "0:05:57", "throughput": 5653.26, "total_tokens": 20324320} {"current_steps": 30855, "total_steps": 33920, "loss": 0.1906, "lr": 2.4682063786441556e-07, "epoch": 18.192806603773583, "percentage": 90.96, "elapsed_time": "0:59:55", "remaining_time": "0:05:57", "throughput": 5653.21, "total_tokens": 20327136} {"current_steps": 30860, "total_steps": 33920, "loss": 0.2517, "lr": 2.460229317535778e-07, "epoch": 18.19575471698113, "percentage": 90.98, "elapsed_time": "0:59:56", "remaining_time": "0:05:56", "throughput": 5653.25, "total_tokens": 20330816} {"current_steps": 30865, "total_steps": 33920, "loss": 0.2761, "lr": 2.4522648427865725e-07, "epoch": 18.19870283018868, "percentage": 90.99, "elapsed_time": "0:59:56", "remaining_time": "0:05:56", "throughput": 5653.22, "total_tokens": 20333696} {"current_steps": 30870, "total_steps": 33920, "loss": 0.4167, "lr": 2.444312956505163e-07, "epoch": 18.201650943396228, "percentage": 91.01, "elapsed_time": "0:59:57", "remaining_time": "0:05:55", "throughput": 5653.25, "total_tokens": 20336768} {"current_steps": 30875, "total_steps": 33920, "loss": 0.2687, "lr": 2.4363736607968537e-07, "epoch": 18.204599056603772, "percentage": 91.02, "elapsed_time": "0:59:57", "remaining_time": "0:05:54", "throughput": 5653.2, "total_tokens": 20339552} {"current_steps": 30880, "total_steps": 33920, "loss": 0.2761, "lr": 2.428446957763608e-07, "epoch": 18.20754716981132, "percentage": 91.04, "elapsed_time": "0:59:58", "remaining_time": "0:05:54", "throughput": 5653.16, "total_tokens": 20343136} {"current_steps": 30885, "total_steps": 33920, "loss": 0.3296, "lr": 2.4205328495040535e-07, "epoch": 18.21049528301887, "percentage": 91.05, "elapsed_time": "0:59:59", "remaining_time": "0:05:53", "throughput": 5652.95, "total_tokens": 20345728} {"current_steps": 30890, "total_steps": 33920, "loss": 0.2712, "lr": 2.412631338113486e-07, "epoch": 18.213443396226417, "percentage": 91.07, "elapsed_time": "0:59:59", "remaining_time": "0:05:53", "throughput": 5652.94, "total_tokens": 20348832} {"current_steps": 30895, "total_steps": 33920, "loss": 0.3167, "lr": 2.404742425683848e-07, "epoch": 18.21639150943396, "percentage": 91.08, "elapsed_time": "1:00:00", "remaining_time": "0:05:52", "throughput": 5653.08, "total_tokens": 20352896} {"current_steps": 30900, "total_steps": 33920, "loss": 0.3657, "lr": 2.3968661143037864e-07, "epoch": 18.21933962264151, "percentage": 91.1, "elapsed_time": "1:00:00", "remaining_time": "0:05:51", "throughput": 5652.91, "total_tokens": 20355584} {"current_steps": 30905, "total_steps": 33920, "loss": 0.393, "lr": 2.3890024060585823e-07, "epoch": 18.222287735849058, "percentage": 91.11, "elapsed_time": "1:00:01", "remaining_time": "0:05:51", "throughput": 5652.98, "total_tokens": 20359072} {"current_steps": 30910, "total_steps": 33920, "loss": 0.3193, "lr": 2.3811513030301826e-07, "epoch": 18.225235849056602, "percentage": 91.13, "elapsed_time": "1:00:02", "remaining_time": "0:05:50", "throughput": 5652.88, "total_tokens": 20361696} {"current_steps": 30915, "total_steps": 33920, "loss": 0.2675, "lr": 2.373312807297201e-07, "epoch": 18.22818396226415, "percentage": 91.14, "elapsed_time": "1:00:02", "remaining_time": "0:05:50", "throughput": 5652.98, "total_tokens": 20365888} {"current_steps": 30920, "total_steps": 33920, "loss": 0.3274, "lr": 2.3654869209349007e-07, "epoch": 18.2311320754717, "percentage": 91.16, "elapsed_time": "1:00:03", "remaining_time": "0:05:49", "throughput": 5653.02, "total_tokens": 20369120} {"current_steps": 30925, "total_steps": 33920, "loss": 0.2737, "lr": 2.357673646015246e-07, "epoch": 18.234080188679247, "percentage": 91.17, "elapsed_time": "1:00:03", "remaining_time": "0:05:49", "throughput": 5652.99, "total_tokens": 20372000} {"current_steps": 30930, "total_steps": 33920, "loss": 0.3645, "lr": 2.3498729846068103e-07, "epoch": 18.23702830188679, "percentage": 91.19, "elapsed_time": "1:00:04", "remaining_time": "0:05:48", "throughput": 5653.03, "total_tokens": 20375104} {"current_steps": 30935, "total_steps": 33920, "loss": 0.2738, "lr": 2.342084938774869e-07, "epoch": 18.23997641509434, "percentage": 91.2, "elapsed_time": "1:00:04", "remaining_time": "0:05:47", "throughput": 5652.88, "total_tokens": 20377472} {"current_steps": 30940, "total_steps": 33920, "loss": 0.2884, "lr": 2.334309510581334e-07, "epoch": 18.242924528301888, "percentage": 91.21, "elapsed_time": "1:00:05", "remaining_time": "0:05:47", "throughput": 5652.65, "total_tokens": 20379744} {"current_steps": 30945, "total_steps": 33920, "loss": 0.2372, "lr": 2.3265467020847864e-07, "epoch": 18.245872641509433, "percentage": 91.23, "elapsed_time": "1:00:05", "remaining_time": "0:05:46", "throughput": 5652.5, "total_tokens": 20382144} {"current_steps": 30950, "total_steps": 33920, "loss": 0.3478, "lr": 2.31879651534046e-07, "epoch": 18.24882075471698, "percentage": 91.24, "elapsed_time": "1:00:06", "remaining_time": "0:05:46", "throughput": 5652.53, "total_tokens": 20385344} {"current_steps": 30955, "total_steps": 33920, "loss": 0.3735, "lr": 2.311058952400247e-07, "epoch": 18.25176886792453, "percentage": 91.26, "elapsed_time": "1:00:06", "remaining_time": "0:05:45", "throughput": 5652.49, "total_tokens": 20388224} {"current_steps": 30960, "total_steps": 33920, "loss": 0.2429, "lr": 2.3033340153127026e-07, "epoch": 18.254716981132077, "percentage": 91.27, "elapsed_time": "1:00:07", "remaining_time": "0:05:44", "throughput": 5652.48, "total_tokens": 20391040} {"current_steps": 30965, "total_steps": 33920, "loss": 0.2721, "lr": 2.295621706123041e-07, "epoch": 18.25766509433962, "percentage": 91.29, "elapsed_time": "1:00:08", "remaining_time": "0:05:44", "throughput": 5652.44, "total_tokens": 20394208} {"current_steps": 30970, "total_steps": 33920, "loss": 0.3591, "lr": 2.287922026873135e-07, "epoch": 18.26061320754717, "percentage": 91.3, "elapsed_time": "1:00:08", "remaining_time": "0:05:43", "throughput": 5652.43, "total_tokens": 20397248} {"current_steps": 30975, "total_steps": 33920, "loss": 0.303, "lr": 2.2802349796014923e-07, "epoch": 18.263561320754718, "percentage": 91.32, "elapsed_time": "1:00:09", "remaining_time": "0:05:43", "throughput": 5652.49, "total_tokens": 20401408} {"current_steps": 30980, "total_steps": 33920, "loss": 0.308, "lr": 2.2725605663433013e-07, "epoch": 18.266509433962263, "percentage": 91.33, "elapsed_time": "1:00:09", "remaining_time": "0:05:42", "throughput": 5652.62, "total_tokens": 20405824} {"current_steps": 30985, "total_steps": 33920, "loss": 0.2213, "lr": 2.264898789130393e-07, "epoch": 18.26945754716981, "percentage": 91.35, "elapsed_time": "1:00:10", "remaining_time": "0:05:42", "throughput": 5652.63, "total_tokens": 20408992} {"current_steps": 30990, "total_steps": 33920, "loss": 0.2893, "lr": 2.2572496499912554e-07, "epoch": 18.27240566037736, "percentage": 91.36, "elapsed_time": "1:00:11", "remaining_time": "0:05:41", "throughput": 5652.69, "total_tokens": 20412320} {"current_steps": 30995, "total_steps": 33920, "loss": 0.272, "lr": 2.2496131509510354e-07, "epoch": 18.275353773584907, "percentage": 91.38, "elapsed_time": "1:00:11", "remaining_time": "0:05:40", "throughput": 5652.69, "total_tokens": 20415488} {"current_steps": 31000, "total_steps": 33920, "loss": 0.2071, "lr": 2.2419892940315268e-07, "epoch": 18.278301886792452, "percentage": 91.39, "elapsed_time": "1:00:12", "remaining_time": "0:05:40", "throughput": 5652.76, "total_tokens": 20419136} {"current_steps": 31005, "total_steps": 33920, "loss": 0.284, "lr": 2.2343780812511819e-07, "epoch": 18.28125, "percentage": 91.41, "elapsed_time": "1:00:12", "remaining_time": "0:05:39", "throughput": 5652.77, "total_tokens": 20422112} {"current_steps": 31010, "total_steps": 33920, "loss": 0.3187, "lr": 2.2267795146250936e-07, "epoch": 18.284198113207548, "percentage": 91.42, "elapsed_time": "1:00:13", "remaining_time": "0:05:39", "throughput": 5652.7, "total_tokens": 20424896} {"current_steps": 31015, "total_steps": 33920, "loss": 0.3575, "lr": 2.2191935961650146e-07, "epoch": 18.287146226415093, "percentage": 91.44, "elapsed_time": "1:00:13", "remaining_time": "0:05:38", "throughput": 5652.58, "total_tokens": 20427392} {"current_steps": 31020, "total_steps": 33920, "loss": 0.3512, "lr": 2.2116203278793603e-07, "epoch": 18.29009433962264, "percentage": 91.45, "elapsed_time": "1:00:14", "remaining_time": "0:05:37", "throughput": 5652.66, "total_tokens": 20431168} {"current_steps": 31025, "total_steps": 33920, "loss": 0.2465, "lr": 2.2040597117731766e-07, "epoch": 18.29304245283019, "percentage": 91.47, "elapsed_time": "1:00:14", "remaining_time": "0:05:37", "throughput": 5652.57, "total_tokens": 20433824} {"current_steps": 31030, "total_steps": 33920, "loss": 0.279, "lr": 2.1965117498481793e-07, "epoch": 18.295990566037737, "percentage": 91.48, "elapsed_time": "1:00:15", "remaining_time": "0:05:36", "throughput": 5652.61, "total_tokens": 20436864} {"current_steps": 31035, "total_steps": 33920, "loss": 0.3014, "lr": 2.188976444102714e-07, "epoch": 18.298938679245282, "percentage": 91.49, "elapsed_time": "1:00:16", "remaining_time": "0:05:36", "throughput": 5652.58, "total_tokens": 20440224} {"current_steps": 31040, "total_steps": 33920, "loss": 0.4008, "lr": 2.181453796531796e-07, "epoch": 18.30188679245283, "percentage": 91.51, "elapsed_time": "1:00:16", "remaining_time": "0:05:35", "throughput": 5652.53, "total_tokens": 20443232} {"current_steps": 31045, "total_steps": 33920, "loss": 0.2953, "lr": 2.1739438091270658e-07, "epoch": 18.30483490566038, "percentage": 91.52, "elapsed_time": "1:00:17", "remaining_time": "0:05:34", "throughput": 5652.42, "total_tokens": 20445920} {"current_steps": 31050, "total_steps": 33920, "loss": 0.3937, "lr": 2.1664464838768329e-07, "epoch": 18.307783018867923, "percentage": 91.54, "elapsed_time": "1:00:17", "remaining_time": "0:05:34", "throughput": 5652.4, "total_tokens": 20449088} {"current_steps": 31055, "total_steps": 33920, "loss": 0.2997, "lr": 2.1589618227660426e-07, "epoch": 18.31073113207547, "percentage": 91.55, "elapsed_time": "1:00:18", "remaining_time": "0:05:33", "throughput": 5652.38, "total_tokens": 20452224} {"current_steps": 31060, "total_steps": 33920, "loss": 0.2861, "lr": 2.151489827776293e-07, "epoch": 18.31367924528302, "percentage": 91.57, "elapsed_time": "1:00:18", "remaining_time": "0:05:33", "throughput": 5652.32, "total_tokens": 20455392} {"current_steps": 31065, "total_steps": 33920, "loss": 0.2955, "lr": 2.1440305008858298e-07, "epoch": 18.316627358490567, "percentage": 91.58, "elapsed_time": "1:00:19", "remaining_time": "0:05:32", "throughput": 5652.2, "total_tokens": 20458336} {"current_steps": 31070, "total_steps": 33920, "loss": 0.3376, "lr": 2.1365838440695397e-07, "epoch": 18.319575471698112, "percentage": 91.6, "elapsed_time": "1:00:20", "remaining_time": "0:05:32", "throughput": 5652.11, "total_tokens": 20460960} {"current_steps": 31075, "total_steps": 33920, "loss": 0.2725, "lr": 2.129149859298957e-07, "epoch": 18.32252358490566, "percentage": 91.61, "elapsed_time": "1:00:20", "remaining_time": "0:05:31", "throughput": 5652.02, "total_tokens": 20463744} {"current_steps": 31080, "total_steps": 33920, "loss": 0.3473, "lr": 2.1217285485422622e-07, "epoch": 18.32547169811321, "percentage": 91.63, "elapsed_time": "1:00:21", "remaining_time": "0:05:30", "throughput": 5652.02, "total_tokens": 20466784} {"current_steps": 31085, "total_steps": 33920, "loss": 0.1903, "lr": 2.114319913764268e-07, "epoch": 18.328419811320753, "percentage": 91.64, "elapsed_time": "1:00:21", "remaining_time": "0:05:30", "throughput": 5652.06, "total_tokens": 20470784} {"current_steps": 31090, "total_steps": 33920, "loss": 0.3881, "lr": 2.10692395692646e-07, "epoch": 18.3313679245283, "percentage": 91.66, "elapsed_time": "1:00:22", "remaining_time": "0:05:29", "throughput": 5652.0, "total_tokens": 20473568} {"current_steps": 31095, "total_steps": 33920, "loss": 0.2965, "lr": 2.0995406799869444e-07, "epoch": 18.33431603773585, "percentage": 91.67, "elapsed_time": "1:00:22", "remaining_time": "0:05:29", "throughput": 5652.07, "total_tokens": 20476896} {"current_steps": 31100, "total_steps": 33920, "loss": 0.3841, "lr": 2.0921700849004743e-07, "epoch": 18.337264150943398, "percentage": 91.69, "elapsed_time": "1:00:23", "remaining_time": "0:05:28", "throughput": 5652.09, "total_tokens": 20480288} {"current_steps": 31105, "total_steps": 33920, "loss": 0.3356, "lr": 2.084812173618439e-07, "epoch": 18.340212264150942, "percentage": 91.7, "elapsed_time": "1:00:24", "remaining_time": "0:05:27", "throughput": 5652.13, "total_tokens": 20483456} {"current_steps": 31110, "total_steps": 33920, "loss": 0.2546, "lr": 2.0774669480888853e-07, "epoch": 18.34316037735849, "percentage": 91.72, "elapsed_time": "1:00:24", "remaining_time": "0:05:27", "throughput": 5652.02, "total_tokens": 20486048} {"current_steps": 31115, "total_steps": 33920, "loss": 0.2331, "lr": 2.0701344102564912e-07, "epoch": 18.34610849056604, "percentage": 91.73, "elapsed_time": "1:00:25", "remaining_time": "0:05:26", "throughput": 5652.02, "total_tokens": 20489216} {"current_steps": 31120, "total_steps": 33920, "loss": 0.2636, "lr": 2.062814562062576e-07, "epoch": 18.349056603773583, "percentage": 91.75, "elapsed_time": "1:00:25", "remaining_time": "0:05:26", "throughput": 5652.04, "total_tokens": 20492576} {"current_steps": 31125, "total_steps": 33920, "loss": 0.3102, "lr": 2.0555074054451063e-07, "epoch": 18.35200471698113, "percentage": 91.76, "elapsed_time": "1:00:26", "remaining_time": "0:05:25", "throughput": 5652.03, "total_tokens": 20496032} {"current_steps": 31130, "total_steps": 33920, "loss": 0.2613, "lr": 2.0482129423386843e-07, "epoch": 18.35495283018868, "percentage": 91.77, "elapsed_time": "1:00:26", "remaining_time": "0:05:25", "throughput": 5651.97, "total_tokens": 20499008} {"current_steps": 31135, "total_steps": 33920, "loss": 0.2769, "lr": 2.040931174674543e-07, "epoch": 18.357900943396228, "percentage": 91.79, "elapsed_time": "1:00:27", "remaining_time": "0:05:24", "throughput": 5652.12, "total_tokens": 20503584} {"current_steps": 31140, "total_steps": 33920, "loss": 0.268, "lr": 2.0336621043805682e-07, "epoch": 18.360849056603772, "percentage": 91.8, "elapsed_time": "1:00:28", "remaining_time": "0:05:23", "throughput": 5652.18, "total_tokens": 20507264} {"current_steps": 31145, "total_steps": 33920, "loss": 0.2399, "lr": 2.0264057333812704e-07, "epoch": 18.36379716981132, "percentage": 91.82, "elapsed_time": "1:00:28", "remaining_time": "0:05:23", "throughput": 5652.03, "total_tokens": 20509728} {"current_steps": 31150, "total_steps": 33920, "loss": 0.3001, "lr": 2.0191620635978127e-07, "epoch": 18.36674528301887, "percentage": 91.83, "elapsed_time": "1:00:29", "remaining_time": "0:05:22", "throughput": 5651.99, "total_tokens": 20512480} {"current_steps": 31155, "total_steps": 33920, "loss": 0.3345, "lr": 2.0119310969479833e-07, "epoch": 18.369693396226417, "percentage": 91.85, "elapsed_time": "1:00:29", "remaining_time": "0:05:22", "throughput": 5651.96, "total_tokens": 20515520} {"current_steps": 31160, "total_steps": 33920, "loss": 0.2886, "lr": 2.004712835346212e-07, "epoch": 18.37264150943396, "percentage": 91.86, "elapsed_time": "1:00:30", "remaining_time": "0:05:21", "throughput": 5651.84, "total_tokens": 20518400} {"current_steps": 31165, "total_steps": 33920, "loss": 0.2344, "lr": 1.99750728070357e-07, "epoch": 18.37558962264151, "percentage": 91.88, "elapsed_time": "1:00:30", "remaining_time": "0:05:20", "throughput": 5651.94, "total_tokens": 20522048} {"current_steps": 31170, "total_steps": 33920, "loss": 0.3083, "lr": 1.9903144349277536e-07, "epoch": 18.378537735849058, "percentage": 91.89, "elapsed_time": "1:00:31", "remaining_time": "0:05:20", "throughput": 5651.89, "total_tokens": 20525312} {"current_steps": 31175, "total_steps": 33920, "loss": 0.316, "lr": 1.983134299923095e-07, "epoch": 18.381485849056602, "percentage": 91.91, "elapsed_time": "1:00:32", "remaining_time": "0:05:19", "throughput": 5651.85, "total_tokens": 20528480} {"current_steps": 31180, "total_steps": 33920, "loss": 0.1829, "lr": 1.9759668775905737e-07, "epoch": 18.38443396226415, "percentage": 91.92, "elapsed_time": "1:00:33", "remaining_time": "0:05:19", "throughput": 5652.04, "total_tokens": 20534944} {"current_steps": 31185, "total_steps": 33920, "loss": 0.2321, "lr": 1.9688121698277995e-07, "epoch": 18.3873820754717, "percentage": 91.94, "elapsed_time": "1:00:33", "remaining_time": "0:05:18", "throughput": 5651.95, "total_tokens": 20537568} {"current_steps": 31190, "total_steps": 33920, "loss": 0.2692, "lr": 1.9616701785290015e-07, "epoch": 18.390330188679247, "percentage": 91.95, "elapsed_time": "1:00:34", "remaining_time": "0:05:18", "throughput": 5652.02, "total_tokens": 20541248} {"current_steps": 31195, "total_steps": 33920, "loss": 0.3523, "lr": 1.954540905585056e-07, "epoch": 18.39327830188679, "percentage": 91.97, "elapsed_time": "1:00:34", "remaining_time": "0:05:17", "throughput": 5652.06, "total_tokens": 20544384} {"current_steps": 31200, "total_steps": 33920, "loss": 0.3126, "lr": 1.9474243528834757e-07, "epoch": 18.39622641509434, "percentage": 91.98, "elapsed_time": "1:00:35", "remaining_time": "0:05:16", "throughput": 5652.15, "total_tokens": 20548096} {"current_steps": 31205, "total_steps": 33920, "loss": 0.2781, "lr": 1.9403205223083866e-07, "epoch": 18.399174528301888, "percentage": 92.0, "elapsed_time": "1:00:35", "remaining_time": "0:05:16", "throughput": 5652.2, "total_tokens": 20551328} {"current_steps": 31210, "total_steps": 33920, "loss": 0.3699, "lr": 1.9332294157405619e-07, "epoch": 18.402122641509433, "percentage": 92.01, "elapsed_time": "1:00:36", "remaining_time": "0:05:15", "throughput": 5652.32, "total_tokens": 20555680} {"current_steps": 31215, "total_steps": 33920, "loss": 0.2894, "lr": 1.926151035057411e-07, "epoch": 18.40507075471698, "percentage": 92.03, "elapsed_time": "1:00:37", "remaining_time": "0:05:15", "throughput": 5652.47, "total_tokens": 20559680} {"current_steps": 31220, "total_steps": 33920, "loss": 0.3567, "lr": 1.9190853821329626e-07, "epoch": 18.40801886792453, "percentage": 92.04, "elapsed_time": "1:00:37", "remaining_time": "0:05:14", "throughput": 5652.47, "total_tokens": 20563136} {"current_steps": 31225, "total_steps": 33920, "loss": 0.2883, "lr": 1.9120324588378757e-07, "epoch": 18.410966981132077, "percentage": 92.05, "elapsed_time": "1:00:38", "remaining_time": "0:05:14", "throughput": 5652.48, "total_tokens": 20566272} {"current_steps": 31230, "total_steps": 33920, "loss": 0.301, "lr": 1.9049922670394461e-07, "epoch": 18.41391509433962, "percentage": 92.07, "elapsed_time": "1:00:38", "remaining_time": "0:05:13", "throughput": 5652.48, "total_tokens": 20569312} {"current_steps": 31235, "total_steps": 33920, "loss": 0.2339, "lr": 1.897964808601588e-07, "epoch": 18.41686320754717, "percentage": 92.08, "elapsed_time": "1:00:39", "remaining_time": "0:05:12", "throughput": 5652.45, "total_tokens": 20572224} {"current_steps": 31240, "total_steps": 33920, "loss": 0.2335, "lr": 1.8909500853848517e-07, "epoch": 18.419811320754718, "percentage": 92.1, "elapsed_time": "1:00:40", "remaining_time": "0:05:12", "throughput": 5652.33, "total_tokens": 20574816} {"current_steps": 31245, "total_steps": 33920, "loss": 0.3102, "lr": 1.8839480992464243e-07, "epoch": 18.422759433962263, "percentage": 92.11, "elapsed_time": "1:00:40", "remaining_time": "0:05:11", "throughput": 5652.26, "total_tokens": 20577920} {"current_steps": 31250, "total_steps": 33920, "loss": 0.3214, "lr": 1.8769588520401005e-07, "epoch": 18.42570754716981, "percentage": 92.13, "elapsed_time": "1:00:41", "remaining_time": "0:05:11", "throughput": 5652.18, "total_tokens": 20580672} {"current_steps": 31255, "total_steps": 33920, "loss": 0.2898, "lr": 1.8699823456163279e-07, "epoch": 18.42865566037736, "percentage": 92.14, "elapsed_time": "1:00:41", "remaining_time": "0:05:10", "throughput": 5652.1, "total_tokens": 20583392} {"current_steps": 31260, "total_steps": 33920, "loss": 0.3057, "lr": 1.8630185818221514e-07, "epoch": 18.431603773584907, "percentage": 92.16, "elapsed_time": "1:00:42", "remaining_time": "0:05:09", "throughput": 5652.16, "total_tokens": 20586688} {"current_steps": 31265, "total_steps": 33920, "loss": 0.3355, "lr": 1.856067562501268e-07, "epoch": 18.434551886792452, "percentage": 92.17, "elapsed_time": "1:00:42", "remaining_time": "0:05:09", "throughput": 5652.2, "total_tokens": 20590272} {"current_steps": 31270, "total_steps": 33920, "loss": 0.2169, "lr": 1.8491292894939837e-07, "epoch": 18.4375, "percentage": 92.19, "elapsed_time": "1:00:43", "remaining_time": "0:05:08", "throughput": 5652.38, "total_tokens": 20594976} {"current_steps": 31275, "total_steps": 33920, "loss": 0.255, "lr": 1.8422037646372405e-07, "epoch": 18.440448113207548, "percentage": 92.2, "elapsed_time": "1:00:44", "remaining_time": "0:05:08", "throughput": 5652.52, "total_tokens": 20599040} {"current_steps": 31280, "total_steps": 33920, "loss": 0.4638, "lr": 1.8352909897645989e-07, "epoch": 18.443396226415093, "percentage": 92.22, "elapsed_time": "1:00:44", "remaining_time": "0:05:07", "throughput": 5652.41, "total_tokens": 20601600} {"current_steps": 31285, "total_steps": 33920, "loss": 0.2314, "lr": 1.8283909667062448e-07, "epoch": 18.44634433962264, "percentage": 92.23, "elapsed_time": "1:00:45", "remaining_time": "0:05:07", "throughput": 5652.56, "total_tokens": 20605376} {"current_steps": 31290, "total_steps": 33920, "loss": 0.3108, "lr": 1.82150369728899e-07, "epoch": 18.44929245283019, "percentage": 92.25, "elapsed_time": "1:00:45", "remaining_time": "0:05:06", "throughput": 5652.72, "total_tokens": 20609440} {"current_steps": 31295, "total_steps": 33920, "loss": 0.5015, "lr": 1.814629183336275e-07, "epoch": 18.452240566037737, "percentage": 92.26, "elapsed_time": "1:00:46", "remaining_time": "0:05:05", "throughput": 5652.73, "total_tokens": 20612672} {"current_steps": 31300, "total_steps": 33920, "loss": 0.3402, "lr": 1.807767426668139e-07, "epoch": 18.455188679245282, "percentage": 92.28, "elapsed_time": "1:00:47", "remaining_time": "0:05:05", "throughput": 5652.75, "total_tokens": 20615744} {"current_steps": 31305, "total_steps": 33920, "loss": 0.3054, "lr": 1.8009184291012783e-07, "epoch": 18.45813679245283, "percentage": 92.29, "elapsed_time": "1:00:47", "remaining_time": "0:05:04", "throughput": 5652.63, "total_tokens": 20618336} {"current_steps": 31310, "total_steps": 33920, "loss": 0.2605, "lr": 1.7940821924489926e-07, "epoch": 18.46108490566038, "percentage": 92.31, "elapsed_time": "1:00:48", "remaining_time": "0:05:04", "throughput": 5652.61, "total_tokens": 20621472} {"current_steps": 31315, "total_steps": 33920, "loss": 0.2885, "lr": 1.7872587185212009e-07, "epoch": 18.464033018867923, "percentage": 92.32, "elapsed_time": "1:00:48", "remaining_time": "0:05:03", "throughput": 5652.55, "total_tokens": 20624352} {"current_steps": 31320, "total_steps": 33920, "loss": 0.1905, "lr": 1.7804480091244524e-07, "epoch": 18.46698113207547, "percentage": 92.33, "elapsed_time": "1:00:49", "remaining_time": "0:05:02", "throughput": 5652.54, "total_tokens": 20627136} {"current_steps": 31325, "total_steps": 33920, "loss": 0.144, "lr": 1.7736500660619104e-07, "epoch": 18.46992924528302, "percentage": 92.35, "elapsed_time": "1:00:49", "remaining_time": "0:05:02", "throughput": 5652.69, "total_tokens": 20630976} {"current_steps": 31330, "total_steps": 33920, "loss": 0.4279, "lr": 1.766864891133352e-07, "epoch": 18.472877358490567, "percentage": 92.36, "elapsed_time": "1:00:50", "remaining_time": "0:05:01", "throughput": 5652.59, "total_tokens": 20633568} {"current_steps": 31335, "total_steps": 33920, "loss": 0.3558, "lr": 1.7600924861351843e-07, "epoch": 18.475825471698112, "percentage": 92.38, "elapsed_time": "1:00:50", "remaining_time": "0:05:01", "throughput": 5652.66, "total_tokens": 20636992} {"current_steps": 31340, "total_steps": 33920, "loss": 0.2553, "lr": 1.7533328528604398e-07, "epoch": 18.47877358490566, "percentage": 92.39, "elapsed_time": "1:00:51", "remaining_time": "0:05:00", "throughput": 5652.62, "total_tokens": 20640032} {"current_steps": 31345, "total_steps": 33920, "loss": 0.3101, "lr": 1.746585993098754e-07, "epoch": 18.48172169811321, "percentage": 92.41, "elapsed_time": "1:00:51", "remaining_time": "0:05:00", "throughput": 5652.49, "total_tokens": 20642688} {"current_steps": 31350, "total_steps": 33920, "loss": 0.2545, "lr": 1.7398519086363864e-07, "epoch": 18.484669811320753, "percentage": 92.42, "elapsed_time": "1:00:52", "remaining_time": "0:04:59", "throughput": 5652.56, "total_tokens": 20646528} {"current_steps": 31355, "total_steps": 33920, "loss": 0.3438, "lr": 1.733130601256211e-07, "epoch": 18.4876179245283, "percentage": 92.44, "elapsed_time": "1:00:53", "remaining_time": "0:04:58", "throughput": 5652.46, "total_tokens": 20649376} {"current_steps": 31360, "total_steps": 33920, "loss": 0.3083, "lr": 1.7264220727377323e-07, "epoch": 18.49056603773585, "percentage": 92.45, "elapsed_time": "1:00:53", "remaining_time": "0:04:58", "throughput": 5652.41, "total_tokens": 20652448} {"current_steps": 31365, "total_steps": 33920, "loss": 0.1776, "lr": 1.7197263248570517e-07, "epoch": 18.493514150943398, "percentage": 92.47, "elapsed_time": "1:00:54", "remaining_time": "0:04:57", "throughput": 5652.44, "total_tokens": 20655680} {"current_steps": 31370, "total_steps": 33920, "loss": 0.2724, "lr": 1.7130433593869124e-07, "epoch": 18.496462264150942, "percentage": 92.48, "elapsed_time": "1:00:54", "remaining_time": "0:04:57", "throughput": 5652.44, "total_tokens": 20658592} {"current_steps": 31375, "total_steps": 33920, "loss": 0.3661, "lr": 1.706373178096643e-07, "epoch": 18.49941037735849, "percentage": 92.5, "elapsed_time": "1:00:55", "remaining_time": "0:04:56", "throughput": 5652.48, "total_tokens": 20661760} {"current_steps": 31380, "total_steps": 33920, "loss": 0.3047, "lr": 1.6997157827522092e-07, "epoch": 18.50235849056604, "percentage": 92.51, "elapsed_time": "1:00:55", "remaining_time": "0:04:55", "throughput": 5652.47, "total_tokens": 20664928} {"current_steps": 31385, "total_steps": 33920, "loss": 0.3332, "lr": 1.6930711751161843e-07, "epoch": 18.505306603773583, "percentage": 92.53, "elapsed_time": "1:00:56", "remaining_time": "0:04:55", "throughput": 5652.68, "total_tokens": 20669152} {"current_steps": 31390, "total_steps": 33920, "loss": 0.4271, "lr": 1.6864393569477556e-07, "epoch": 18.50825471698113, "percentage": 92.54, "elapsed_time": "1:00:57", "remaining_time": "0:04:54", "throughput": 5652.72, "total_tokens": 20672448} {"current_steps": 31395, "total_steps": 33920, "loss": 0.2415, "lr": 1.6798203300027295e-07, "epoch": 18.51120283018868, "percentage": 92.56, "elapsed_time": "1:00:57", "remaining_time": "0:04:54", "throughput": 5652.68, "total_tokens": 20675296} {"current_steps": 31400, "total_steps": 33920, "loss": 0.1918, "lr": 1.6732140960335152e-07, "epoch": 18.514150943396228, "percentage": 92.57, "elapsed_time": "1:00:58", "remaining_time": "0:04:53", "throughput": 5652.65, "total_tokens": 20678368} {"current_steps": 31405, "total_steps": 33920, "loss": 0.219, "lr": 1.666620656789153e-07, "epoch": 18.517099056603772, "percentage": 92.59, "elapsed_time": "1:00:58", "remaining_time": "0:04:53", "throughput": 5652.54, "total_tokens": 20681088} {"current_steps": 31410, "total_steps": 33920, "loss": 0.3178, "lr": 1.660040014015274e-07, "epoch": 18.52004716981132, "percentage": 92.6, "elapsed_time": "1:00:59", "remaining_time": "0:04:52", "throughput": 5652.59, "total_tokens": 20684800} {"current_steps": 31415, "total_steps": 33920, "loss": 0.3978, "lr": 1.6534721694541344e-07, "epoch": 18.52299528301887, "percentage": 92.61, "elapsed_time": "1:00:59", "remaining_time": "0:04:51", "throughput": 5652.68, "total_tokens": 20688384} {"current_steps": 31420, "total_steps": 33920, "loss": 0.2508, "lr": 1.6469171248445993e-07, "epoch": 18.525943396226417, "percentage": 92.63, "elapsed_time": "1:01:00", "remaining_time": "0:04:51", "throughput": 5652.69, "total_tokens": 20691456} {"current_steps": 31425, "total_steps": 33920, "loss": 0.2799, "lr": 1.6403748819221464e-07, "epoch": 18.52889150943396, "percentage": 92.64, "elapsed_time": "1:01:01", "remaining_time": "0:04:50", "throughput": 5652.73, "total_tokens": 20694912} {"current_steps": 31430, "total_steps": 33920, "loss": 0.3064, "lr": 1.6338454424188632e-07, "epoch": 18.53183962264151, "percentage": 92.66, "elapsed_time": "1:01:01", "remaining_time": "0:04:50", "throughput": 5652.74, "total_tokens": 20698848} {"current_steps": 31435, "total_steps": 33920, "loss": 0.3453, "lr": 1.6273288080634442e-07, "epoch": 18.534787735849058, "percentage": 92.67, "elapsed_time": "1:01:02", "remaining_time": "0:04:49", "throughput": 5652.91, "total_tokens": 20702816} {"current_steps": 31440, "total_steps": 33920, "loss": 0.3503, "lr": 1.6208249805811982e-07, "epoch": 18.537735849056602, "percentage": 92.69, "elapsed_time": "1:01:02", "remaining_time": "0:04:48", "throughput": 5653.05, "total_tokens": 20706720} {"current_steps": 31445, "total_steps": 33920, "loss": 0.3267, "lr": 1.6143339616940423e-07, "epoch": 18.54068396226415, "percentage": 92.7, "elapsed_time": "1:01:03", "remaining_time": "0:04:48", "throughput": 5652.95, "total_tokens": 20709376} {"current_steps": 31450, "total_steps": 33920, "loss": 0.3574, "lr": 1.6078557531205018e-07, "epoch": 18.5436320754717, "percentage": 92.72, "elapsed_time": "1:01:04", "remaining_time": "0:04:47", "throughput": 5653.01, "total_tokens": 20713216} {"current_steps": 31455, "total_steps": 33920, "loss": 0.2175, "lr": 1.601390356575705e-07, "epoch": 18.546580188679247, "percentage": 92.73, "elapsed_time": "1:01:04", "remaining_time": "0:04:47", "throughput": 5652.89, "total_tokens": 20715936} {"current_steps": 31460, "total_steps": 33920, "loss": 0.2481, "lr": 1.5949377737713988e-07, "epoch": 18.54952830188679, "percentage": 92.75, "elapsed_time": "1:01:05", "remaining_time": "0:04:46", "throughput": 5652.91, "total_tokens": 20719296} {"current_steps": 31465, "total_steps": 33920, "loss": 0.3427, "lr": 1.5884980064159338e-07, "epoch": 18.55247641509434, "percentage": 92.76, "elapsed_time": "1:01:05", "remaining_time": "0:04:46", "throughput": 5652.86, "total_tokens": 20722144} {"current_steps": 31470, "total_steps": 33920, "loss": 0.3431, "lr": 1.5820710562142627e-07, "epoch": 18.555424528301888, "percentage": 92.78, "elapsed_time": "1:01:06", "remaining_time": "0:04:45", "throughput": 5652.93, "total_tokens": 20725568} {"current_steps": 31475, "total_steps": 33920, "loss": 0.372, "lr": 1.575656924867952e-07, "epoch": 18.558372641509433, "percentage": 92.79, "elapsed_time": "1:01:06", "remaining_time": "0:04:44", "throughput": 5652.92, "total_tokens": 20728480} {"current_steps": 31480, "total_steps": 33920, "loss": 0.2229, "lr": 1.5692556140751658e-07, "epoch": 18.56132075471698, "percentage": 92.81, "elapsed_time": "1:01:07", "remaining_time": "0:04:44", "throughput": 5652.97, "total_tokens": 20733504} {"current_steps": 31485, "total_steps": 33920, "loss": 0.1943, "lr": 1.5628671255306706e-07, "epoch": 18.56426886792453, "percentage": 92.82, "elapsed_time": "1:01:08", "remaining_time": "0:04:43", "throughput": 5653.15, "total_tokens": 20738848} {"current_steps": 31490, "total_steps": 33920, "loss": 0.2849, "lr": 1.556491460925863e-07, "epoch": 18.567216981132077, "percentage": 92.84, "elapsed_time": "1:01:09", "remaining_time": "0:04:43", "throughput": 5653.16, "total_tokens": 20742080} {"current_steps": 31495, "total_steps": 33920, "loss": 0.3311, "lr": 1.550128621948721e-07, "epoch": 18.57016509433962, "percentage": 92.85, "elapsed_time": "1:01:09", "remaining_time": "0:04:42", "throughput": 5653.05, "total_tokens": 20744832} {"current_steps": 31500, "total_steps": 33920, "loss": 0.2841, "lr": 1.5437786102838413e-07, "epoch": 18.57311320754717, "percentage": 92.87, "elapsed_time": "1:01:10", "remaining_time": "0:04:41", "throughput": 5653.04, "total_tokens": 20748064} {"current_steps": 31505, "total_steps": 33920, "loss": 0.2131, "lr": 1.5374414276124017e-07, "epoch": 18.576061320754718, "percentage": 92.88, "elapsed_time": "1:01:10", "remaining_time": "0:04:41", "throughput": 5653.05, "total_tokens": 20751136} {"current_steps": 31510, "total_steps": 33920, "loss": 0.2703, "lr": 1.5311170756122095e-07, "epoch": 18.579009433962263, "percentage": 92.9, "elapsed_time": "1:01:11", "remaining_time": "0:04:40", "throughput": 5653.18, "total_tokens": 20755072} {"current_steps": 31515, "total_steps": 33920, "loss": 0.2238, "lr": 1.5248055559576647e-07, "epoch": 18.58195754716981, "percentage": 92.91, "elapsed_time": "1:01:11", "remaining_time": "0:04:40", "throughput": 5653.09, "total_tokens": 20757728} {"current_steps": 31520, "total_steps": 33920, "loss": 0.2602, "lr": 1.5185068703197526e-07, "epoch": 18.58490566037736, "percentage": 92.92, "elapsed_time": "1:01:12", "remaining_time": "0:04:39", "throughput": 5653.08, "total_tokens": 20760960} {"current_steps": 31525, "total_steps": 33920, "loss": 0.3476, "lr": 1.5122210203661004e-07, "epoch": 18.587853773584907, "percentage": 92.94, "elapsed_time": "1:01:13", "remaining_time": "0:04:39", "throughput": 5653.07, "total_tokens": 20763968} {"current_steps": 31530, "total_steps": 33920, "loss": 0.3324, "lr": 1.505948007760899e-07, "epoch": 18.590801886792452, "percentage": 92.95, "elapsed_time": "1:01:13", "remaining_time": "0:04:38", "throughput": 5653.12, "total_tokens": 20767296} {"current_steps": 31535, "total_steps": 33920, "loss": 0.2508, "lr": 1.4996878341649647e-07, "epoch": 18.59375, "percentage": 92.97, "elapsed_time": "1:01:14", "remaining_time": "0:04:37", "throughput": 5653.11, "total_tokens": 20770304} {"current_steps": 31540, "total_steps": 33920, "loss": 0.2714, "lr": 1.493440501235699e-07, "epoch": 18.596698113207548, "percentage": 92.98, "elapsed_time": "1:01:14", "remaining_time": "0:04:37", "throughput": 5653.2, "total_tokens": 20774144} {"current_steps": 31545, "total_steps": 33920, "loss": 0.3096, "lr": 1.487206010627118e-07, "epoch": 18.599646226415093, "percentage": 93.0, "elapsed_time": "1:01:15", "remaining_time": "0:04:36", "throughput": 5653.11, "total_tokens": 20776704} {"current_steps": 31550, "total_steps": 33920, "loss": 0.1854, "lr": 1.4809843639898124e-07, "epoch": 18.60259433962264, "percentage": 93.01, "elapsed_time": "1:01:15", "remaining_time": "0:04:36", "throughput": 5652.89, "total_tokens": 20778816} {"current_steps": 31555, "total_steps": 33920, "loss": 0.2772, "lr": 1.4747755629710093e-07, "epoch": 18.60554245283019, "percentage": 93.03, "elapsed_time": "1:01:16", "remaining_time": "0:04:35", "throughput": 5652.81, "total_tokens": 20782144} {"current_steps": 31560, "total_steps": 33920, "loss": 0.2522, "lr": 1.4685796092145045e-07, "epoch": 18.608490566037737, "percentage": 93.04, "elapsed_time": "1:01:17", "remaining_time": "0:04:34", "throughput": 5652.89, "total_tokens": 20785824} {"current_steps": 31565, "total_steps": 33920, "loss": 0.1991, "lr": 1.4623965043607135e-07, "epoch": 18.611438679245282, "percentage": 93.06, "elapsed_time": "1:01:17", "remaining_time": "0:04:34", "throughput": 5652.8, "total_tokens": 20788512} {"current_steps": 31570, "total_steps": 33920, "loss": 0.2738, "lr": 1.4562262500466273e-07, "epoch": 18.61438679245283, "percentage": 93.07, "elapsed_time": "1:01:18", "remaining_time": "0:04:33", "throughput": 5652.7, "total_tokens": 20791072} {"current_steps": 31575, "total_steps": 33920, "loss": 0.3125, "lr": 1.4500688479058556e-07, "epoch": 18.61733490566038, "percentage": 93.09, "elapsed_time": "1:01:18", "remaining_time": "0:04:33", "throughput": 5652.7, "total_tokens": 20794112} {"current_steps": 31580, "total_steps": 33920, "loss": 0.3096, "lr": 1.4439242995685943e-07, "epoch": 18.620283018867923, "percentage": 93.1, "elapsed_time": "1:01:19", "remaining_time": "0:04:32", "throughput": 5652.7, "total_tokens": 20797600} {"current_steps": 31585, "total_steps": 33920, "loss": 0.3893, "lr": 1.4377926066616364e-07, "epoch": 18.62323113207547, "percentage": 93.12, "elapsed_time": "1:01:19", "remaining_time": "0:04:32", "throughput": 5652.72, "total_tokens": 20800640} {"current_steps": 31590, "total_steps": 33920, "loss": 0.238, "lr": 1.4316737708083783e-07, "epoch": 18.62617924528302, "percentage": 93.13, "elapsed_time": "1:01:20", "remaining_time": "0:04:31", "throughput": 5652.79, "total_tokens": 20804384} {"current_steps": 31595, "total_steps": 33920, "loss": 0.3017, "lr": 1.4255677936288127e-07, "epoch": 18.629127358490567, "percentage": 93.15, "elapsed_time": "1:01:20", "remaining_time": "0:04:30", "throughput": 5652.78, "total_tokens": 20807456} {"current_steps": 31600, "total_steps": 33920, "loss": 0.3664, "lr": 1.4194746767395184e-07, "epoch": 18.632075471698112, "percentage": 93.16, "elapsed_time": "1:01:21", "remaining_time": "0:04:30", "throughput": 5652.7, "total_tokens": 20810176} {"current_steps": 31605, "total_steps": 33920, "loss": 0.2649, "lr": 1.4133944217536722e-07, "epoch": 18.63502358490566, "percentage": 93.18, "elapsed_time": "1:01:22", "remaining_time": "0:04:29", "throughput": 5652.63, "total_tokens": 20812992} {"current_steps": 31610, "total_steps": 33920, "loss": 0.2098, "lr": 1.4073270302810471e-07, "epoch": 18.63797169811321, "percentage": 93.19, "elapsed_time": "1:01:22", "remaining_time": "0:04:29", "throughput": 5652.71, "total_tokens": 20816576} {"current_steps": 31615, "total_steps": 33920, "loss": 0.2744, "lr": 1.4012725039280084e-07, "epoch": 18.640919811320753, "percentage": 93.2, "elapsed_time": "1:01:23", "remaining_time": "0:04:28", "throughput": 5652.74, "total_tokens": 20819808} {"current_steps": 31620, "total_steps": 33920, "loss": 0.2978, "lr": 1.3952308442975292e-07, "epoch": 18.6438679245283, "percentage": 93.22, "elapsed_time": "1:01:23", "remaining_time": "0:04:27", "throughput": 5652.87, "total_tokens": 20823552} {"current_steps": 31625, "total_steps": 33920, "loss": 0.2867, "lr": 1.3892020529891637e-07, "epoch": 18.64681603773585, "percentage": 93.23, "elapsed_time": "1:01:24", "remaining_time": "0:04:27", "throughput": 5652.89, "total_tokens": 20826880} {"current_steps": 31630, "total_steps": 33920, "loss": 0.3328, "lr": 1.3831861315990514e-07, "epoch": 18.649764150943398, "percentage": 93.25, "elapsed_time": "1:01:24", "remaining_time": "0:04:26", "throughput": 5652.69, "total_tokens": 20829184} {"current_steps": 31635, "total_steps": 33920, "loss": 0.2415, "lr": 1.377183081719935e-07, "epoch": 18.652712264150942, "percentage": 93.26, "elapsed_time": "1:01:25", "remaining_time": "0:04:26", "throughput": 5652.61, "total_tokens": 20831808} {"current_steps": 31640, "total_steps": 33920, "loss": 0.2325, "lr": 1.3711929049411544e-07, "epoch": 18.65566037735849, "percentage": 93.28, "elapsed_time": "1:01:25", "remaining_time": "0:04:25", "throughput": 5652.66, "total_tokens": 20835328} {"current_steps": 31645, "total_steps": 33920, "loss": 0.2208, "lr": 1.365215602848624e-07, "epoch": 18.65860849056604, "percentage": 93.29, "elapsed_time": "1:01:26", "remaining_time": "0:04:25", "throughput": 5652.67, "total_tokens": 20838464} {"current_steps": 31650, "total_steps": 33920, "loss": 0.2708, "lr": 1.3592511770248727e-07, "epoch": 18.661556603773583, "percentage": 93.31, "elapsed_time": "1:01:26", "remaining_time": "0:04:24", "throughput": 5652.7, "total_tokens": 20841472} {"current_steps": 31655, "total_steps": 33920, "loss": 0.3102, "lr": 1.3532996290490041e-07, "epoch": 18.66450471698113, "percentage": 93.32, "elapsed_time": "1:01:27", "remaining_time": "0:04:23", "throughput": 5652.59, "total_tokens": 20844128} {"current_steps": 31660, "total_steps": 33920, "loss": 0.313, "lr": 1.347360960496713e-07, "epoch": 18.66745283018868, "percentage": 93.34, "elapsed_time": "1:01:28", "remaining_time": "0:04:23", "throughput": 5652.59, "total_tokens": 20847424} {"current_steps": 31665, "total_steps": 33920, "loss": 0.2812, "lr": 1.3414351729402862e-07, "epoch": 18.670400943396228, "percentage": 93.35, "elapsed_time": "1:01:28", "remaining_time": "0:04:22", "throughput": 5652.73, "total_tokens": 20851616} {"current_steps": 31670, "total_steps": 33920, "loss": 0.3361, "lr": 1.3355222679486025e-07, "epoch": 18.673349056603772, "percentage": 93.37, "elapsed_time": "1:01:29", "remaining_time": "0:04:22", "throughput": 5652.74, "total_tokens": 20854880} {"current_steps": 31675, "total_steps": 33920, "loss": 0.3138, "lr": 1.3296222470871367e-07, "epoch": 18.67629716981132, "percentage": 93.38, "elapsed_time": "1:01:29", "remaining_time": "0:04:21", "throughput": 5652.75, "total_tokens": 20857888} {"current_steps": 31680, "total_steps": 33920, "loss": 0.2537, "lr": 1.3237351119179287e-07, "epoch": 18.67924528301887, "percentage": 93.4, "elapsed_time": "1:01:30", "remaining_time": "0:04:20", "throughput": 5652.85, "total_tokens": 20861536} {"current_steps": 31685, "total_steps": 33920, "loss": 0.2684, "lr": 1.3178608639996425e-07, "epoch": 18.682193396226417, "percentage": 93.41, "elapsed_time": "1:01:30", "remaining_time": "0:04:20", "throughput": 5652.96, "total_tokens": 20865024} {"current_steps": 31690, "total_steps": 33920, "loss": 0.2398, "lr": 1.3119995048874957e-07, "epoch": 18.68514150943396, "percentage": 93.43, "elapsed_time": "1:01:31", "remaining_time": "0:04:19", "throughput": 5653.04, "total_tokens": 20868480} {"current_steps": 31695, "total_steps": 33920, "loss": 0.2951, "lr": 1.3061510361333186e-07, "epoch": 18.68808962264151, "percentage": 93.44, "elapsed_time": "1:01:32", "remaining_time": "0:04:19", "throughput": 5652.97, "total_tokens": 20871200} {"current_steps": 31700, "total_steps": 33920, "loss": 0.3776, "lr": 1.3003154592855116e-07, "epoch": 18.691037735849058, "percentage": 93.46, "elapsed_time": "1:01:32", "remaining_time": "0:04:18", "throughput": 5653.12, "total_tokens": 20875584} {"current_steps": 31705, "total_steps": 33920, "loss": 0.3801, "lr": 1.2944927758890668e-07, "epoch": 18.693985849056602, "percentage": 93.47, "elapsed_time": "1:01:33", "remaining_time": "0:04:18", "throughput": 5653.04, "total_tokens": 20878368} {"current_steps": 31710, "total_steps": 33920, "loss": 0.3346, "lr": 1.2886829874855733e-07, "epoch": 18.69693396226415, "percentage": 93.48, "elapsed_time": "1:01:33", "remaining_time": "0:04:17", "throughput": 5652.97, "total_tokens": 20881056} {"current_steps": 31715, "total_steps": 33920, "loss": 0.3651, "lr": 1.2828860956131894e-07, "epoch": 18.6998820754717, "percentage": 93.5, "elapsed_time": "1:01:34", "remaining_time": "0:04:16", "throughput": 5652.85, "total_tokens": 20883552} {"current_steps": 31720, "total_steps": 33920, "loss": 0.4373, "lr": 1.2771021018066765e-07, "epoch": 18.702830188679247, "percentage": 93.51, "elapsed_time": "1:01:34", "remaining_time": "0:04:16", "throughput": 5653.01, "total_tokens": 20887328} {"current_steps": 31725, "total_steps": 33920, "loss": 0.3102, "lr": 1.271331007597365e-07, "epoch": 18.70577830188679, "percentage": 93.53, "elapsed_time": "1:01:35", "remaining_time": "0:04:15", "throughput": 5652.88, "total_tokens": 20889984} {"current_steps": 31730, "total_steps": 33920, "loss": 0.3166, "lr": 1.2655728145131774e-07, "epoch": 18.70872641509434, "percentage": 93.54, "elapsed_time": "1:01:36", "remaining_time": "0:04:15", "throughput": 5652.82, "total_tokens": 20892864} {"current_steps": 31735, "total_steps": 33920, "loss": 0.3619, "lr": 1.2598275240786105e-07, "epoch": 18.711674528301888, "percentage": 93.56, "elapsed_time": "1:01:36", "remaining_time": "0:04:14", "throughput": 5652.96, "total_tokens": 20896704} {"current_steps": 31740, "total_steps": 33920, "loss": 0.2886, "lr": 1.254095137814776e-07, "epoch": 18.714622641509433, "percentage": 93.57, "elapsed_time": "1:01:37", "remaining_time": "0:04:13", "throughput": 5653.03, "total_tokens": 20900320} {"current_steps": 31745, "total_steps": 33920, "loss": 0.318, "lr": 1.2483756572393368e-07, "epoch": 18.71757075471698, "percentage": 93.59, "elapsed_time": "1:01:37", "remaining_time": "0:04:13", "throughput": 5653.27, "total_tokens": 20905184} {"current_steps": 31750, "total_steps": 33920, "loss": 0.3058, "lr": 1.242669083866549e-07, "epoch": 18.72051886792453, "percentage": 93.6, "elapsed_time": "1:01:38", "remaining_time": "0:04:12", "throughput": 5653.25, "total_tokens": 20908320} {"current_steps": 31755, "total_steps": 33920, "loss": 0.3514, "lr": 1.2369754192072537e-07, "epoch": 18.723466981132077, "percentage": 93.62, "elapsed_time": "1:01:38", "remaining_time": "0:04:12", "throughput": 5653.07, "total_tokens": 20910624} {"current_steps": 31760, "total_steps": 33920, "loss": 0.2971, "lr": 1.231294664768873e-07, "epoch": 18.72641509433962, "percentage": 93.63, "elapsed_time": "1:01:39", "remaining_time": "0:04:11", "throughput": 5653.11, "total_tokens": 20914016} {"current_steps": 31765, "total_steps": 33920, "loss": 0.4624, "lr": 1.225626822055409e-07, "epoch": 18.72936320754717, "percentage": 93.65, "elapsed_time": "1:01:40", "remaining_time": "0:04:11", "throughput": 5653.13, "total_tokens": 20917088} {"current_steps": 31770, "total_steps": 33920, "loss": 0.2951, "lr": 1.2199718925674508e-07, "epoch": 18.732311320754718, "percentage": 93.66, "elapsed_time": "1:01:40", "remaining_time": "0:04:10", "throughput": 5653.14, "total_tokens": 20920192} {"current_steps": 31775, "total_steps": 33920, "loss": 0.3457, "lr": 1.2143298778021616e-07, "epoch": 18.735259433962263, "percentage": 93.68, "elapsed_time": "1:01:41", "remaining_time": "0:04:09", "throughput": 5653.07, "total_tokens": 20922912} {"current_steps": 31780, "total_steps": 33920, "loss": 0.2978, "lr": 1.2087007792532967e-07, "epoch": 18.73820754716981, "percentage": 93.69, "elapsed_time": "1:01:41", "remaining_time": "0:04:09", "throughput": 5653.15, "total_tokens": 20926912} {"current_steps": 31785, "total_steps": 33920, "loss": 0.4046, "lr": 1.203084598411175e-07, "epoch": 18.74115566037736, "percentage": 93.71, "elapsed_time": "1:01:42", "remaining_time": "0:04:08", "throughput": 5653.21, "total_tokens": 20930112} {"current_steps": 31790, "total_steps": 33920, "loss": 0.2565, "lr": 1.1974813367627124e-07, "epoch": 18.744103773584907, "percentage": 93.72, "elapsed_time": "1:01:42", "remaining_time": "0:04:08", "throughput": 5653.3, "total_tokens": 20933984} {"current_steps": 31795, "total_steps": 33920, "loss": 0.3247, "lr": 1.1918909957913949e-07, "epoch": 18.747051886792452, "percentage": 93.74, "elapsed_time": "1:01:43", "remaining_time": "0:04:07", "throughput": 5653.19, "total_tokens": 20936512} {"current_steps": 31800, "total_steps": 33920, "loss": 0.3118, "lr": 1.1863135769772827e-07, "epoch": 18.75, "percentage": 93.75, "elapsed_time": "1:01:44", "remaining_time": "0:04:06", "throughput": 5653.1, "total_tokens": 20939072} {"current_steps": 31805, "total_steps": 33920, "loss": 0.2144, "lr": 1.1807490817970279e-07, "epoch": 18.752948113207548, "percentage": 93.76, "elapsed_time": "1:01:44", "remaining_time": "0:04:06", "throughput": 5653.16, "total_tokens": 20942784} {"current_steps": 31810, "total_steps": 33920, "loss": 0.4106, "lr": 1.1751975117238578e-07, "epoch": 18.755896226415093, "percentage": 93.78, "elapsed_time": "1:01:45", "remaining_time": "0:04:05", "throughput": 5653.13, "total_tokens": 20945696} {"current_steps": 31815, "total_steps": 33920, "loss": 0.3534, "lr": 1.1696588682275633e-07, "epoch": 18.75884433962264, "percentage": 93.79, "elapsed_time": "1:01:45", "remaining_time": "0:04:05", "throughput": 5653.15, "total_tokens": 20949152} {"current_steps": 31820, "total_steps": 33920, "loss": 0.418, "lr": 1.1641331527745325e-07, "epoch": 18.76179245283019, "percentage": 93.81, "elapsed_time": "1:01:46", "remaining_time": "0:04:04", "throughput": 5653.11, "total_tokens": 20952064} {"current_steps": 31825, "total_steps": 33920, "loss": 0.2496, "lr": 1.1586203668277229e-07, "epoch": 18.764740566037737, "percentage": 93.82, "elapsed_time": "1:01:46", "remaining_time": "0:04:04", "throughput": 5652.99, "total_tokens": 20954752} {"current_steps": 31830, "total_steps": 33920, "loss": 0.1909, "lr": 1.1531205118466615e-07, "epoch": 18.767688679245282, "percentage": 93.84, "elapsed_time": "1:01:47", "remaining_time": "0:04:03", "throughput": 5652.95, "total_tokens": 20957568} {"current_steps": 31835, "total_steps": 33920, "loss": 0.3017, "lr": 1.1476335892874669e-07, "epoch": 18.77063679245283, "percentage": 93.85, "elapsed_time": "1:01:47", "remaining_time": "0:04:02", "throughput": 5652.88, "total_tokens": 20960640} {"current_steps": 31840, "total_steps": 33920, "loss": 0.3018, "lr": 1.1421596006028157e-07, "epoch": 18.77358490566038, "percentage": 93.87, "elapsed_time": "1:01:48", "remaining_time": "0:04:02", "throughput": 5652.77, "total_tokens": 20963296} {"current_steps": 31845, "total_steps": 33920, "loss": 0.3012, "lr": 1.1366985472419823e-07, "epoch": 18.776533018867923, "percentage": 93.88, "elapsed_time": "1:01:49", "remaining_time": "0:04:01", "throughput": 5652.8, "total_tokens": 20966304} {"current_steps": 31850, "total_steps": 33920, "loss": 0.2614, "lr": 1.1312504306507987e-07, "epoch": 18.77948113207547, "percentage": 93.9, "elapsed_time": "1:01:49", "remaining_time": "0:04:01", "throughput": 5652.9, "total_tokens": 20969920} {"current_steps": 31855, "total_steps": 33920, "loss": 0.279, "lr": 1.1258152522716725e-07, "epoch": 18.78242924528302, "percentage": 93.91, "elapsed_time": "1:01:50", "remaining_time": "0:04:00", "throughput": 5652.82, "total_tokens": 20972576} {"current_steps": 31860, "total_steps": 33920, "loss": 0.3219, "lr": 1.1203930135435914e-07, "epoch": 18.785377358490567, "percentage": 93.93, "elapsed_time": "1:01:50", "remaining_time": "0:03:59", "throughput": 5652.89, "total_tokens": 20976384} {"current_steps": 31865, "total_steps": 33920, "loss": 0.3315, "lr": 1.1149837159021238e-07, "epoch": 18.788325471698112, "percentage": 93.94, "elapsed_time": "1:01:51", "remaining_time": "0:03:59", "throughput": 5653.01, "total_tokens": 20980640} {"current_steps": 31870, "total_steps": 33920, "loss": 0.2896, "lr": 1.1095873607793961e-07, "epoch": 18.79127358490566, "percentage": 93.96, "elapsed_time": "1:01:51", "remaining_time": "0:03:58", "throughput": 5652.97, "total_tokens": 20983424} {"current_steps": 31875, "total_steps": 33920, "loss": 0.3201, "lr": 1.1042039496041212e-07, "epoch": 18.79422169811321, "percentage": 93.97, "elapsed_time": "1:01:52", "remaining_time": "0:03:58", "throughput": 5652.97, "total_tokens": 20986336} {"current_steps": 31880, "total_steps": 33920, "loss": 0.2905, "lr": 1.0988334838015812e-07, "epoch": 18.797169811320753, "percentage": 93.99, "elapsed_time": "1:01:52", "remaining_time": "0:03:57", "throughput": 5653.04, "total_tokens": 20989696} {"current_steps": 31885, "total_steps": 33920, "loss": 0.3561, "lr": 1.0934759647936333e-07, "epoch": 18.8001179245283, "percentage": 94.0, "elapsed_time": "1:01:53", "remaining_time": "0:03:57", "throughput": 5653.05, "total_tokens": 20992736} {"current_steps": 31890, "total_steps": 33920, "loss": 0.3549, "lr": 1.0881313939986926e-07, "epoch": 18.80306603773585, "percentage": 94.02, "elapsed_time": "1:01:54", "remaining_time": "0:03:56", "throughput": 5653.2, "total_tokens": 20996544} {"current_steps": 31895, "total_steps": 33920, "loss": 0.3562, "lr": 1.0827997728317662e-07, "epoch": 18.806014150943398, "percentage": 94.03, "elapsed_time": "1:01:54", "remaining_time": "0:03:55", "throughput": 5653.38, "total_tokens": 21001152} {"current_steps": 31900, "total_steps": 33920, "loss": 0.3298, "lr": 1.0774811027044196e-07, "epoch": 18.808962264150942, "percentage": 94.04, "elapsed_time": "1:01:55", "remaining_time": "0:03:55", "throughput": 5653.31, "total_tokens": 21003840} {"current_steps": 31905, "total_steps": 33920, "loss": 0.3496, "lr": 1.0721753850247984e-07, "epoch": 18.81191037735849, "percentage": 94.06, "elapsed_time": "1:01:55", "remaining_time": "0:03:54", "throughput": 5653.27, "total_tokens": 21007168} {"current_steps": 31910, "total_steps": 33920, "loss": 0.2527, "lr": 1.0668826211976124e-07, "epoch": 18.81485849056604, "percentage": 94.07, "elapsed_time": "1:01:56", "remaining_time": "0:03:54", "throughput": 5653.26, "total_tokens": 21010112} {"current_steps": 31915, "total_steps": 33920, "loss": 0.3332, "lr": 1.0616028126241407e-07, "epoch": 18.817806603773583, "percentage": 94.09, "elapsed_time": "1:01:56", "remaining_time": "0:03:53", "throughput": 5653.21, "total_tokens": 21012896} {"current_steps": 31920, "total_steps": 33920, "loss": 0.3161, "lr": 1.0563359607022372e-07, "epoch": 18.82075471698113, "percentage": 94.1, "elapsed_time": "1:01:57", "remaining_time": "0:03:52", "throughput": 5653.2, "total_tokens": 21015840} {"current_steps": 31925, "total_steps": 33920, "loss": 0.3291, "lr": 1.05108206682632e-07, "epoch": 18.82370283018868, "percentage": 94.12, "elapsed_time": "1:01:58", "remaining_time": "0:03:52", "throughput": 5653.13, "total_tokens": 21018496} {"current_steps": 31930, "total_steps": 33920, "loss": 0.416, "lr": 1.0458411323873874e-07, "epoch": 18.826650943396228, "percentage": 94.13, "elapsed_time": "1:01:58", "remaining_time": "0:03:51", "throughput": 5653.2, "total_tokens": 21022144} {"current_steps": 31935, "total_steps": 33920, "loss": 0.3393, "lr": 1.0406131587729962e-07, "epoch": 18.829599056603772, "percentage": 94.15, "elapsed_time": "1:01:59", "remaining_time": "0:03:51", "throughput": 5653.19, "total_tokens": 21025408} {"current_steps": 31940, "total_steps": 33920, "loss": 0.2728, "lr": 1.035398147367278e-07, "epoch": 18.83254716981132, "percentage": 94.16, "elapsed_time": "1:01:59", "remaining_time": "0:03:50", "throughput": 5653.23, "total_tokens": 21028864} {"current_steps": 31945, "total_steps": 33920, "loss": 0.3146, "lr": 1.030196099550923e-07, "epoch": 18.83549528301887, "percentage": 94.18, "elapsed_time": "1:02:00", "remaining_time": "0:03:50", "throughput": 5653.23, "total_tokens": 21032032} {"current_steps": 31950, "total_steps": 33920, "loss": 0.3748, "lr": 1.0250070167011905e-07, "epoch": 18.838443396226417, "percentage": 94.19, "elapsed_time": "1:02:00", "remaining_time": "0:03:49", "throughput": 5653.36, "total_tokens": 21035808} {"current_steps": 31955, "total_steps": 33920, "loss": 0.3052, "lr": 1.0198309001919315e-07, "epoch": 18.84139150943396, "percentage": 94.21, "elapsed_time": "1:02:01", "remaining_time": "0:03:48", "throughput": 5653.43, "total_tokens": 21039616} {"current_steps": 31960, "total_steps": 33920, "loss": 0.4245, "lr": 1.0146677513935277e-07, "epoch": 18.84433962264151, "percentage": 94.22, "elapsed_time": "1:02:02", "remaining_time": "0:03:48", "throughput": 5653.32, "total_tokens": 21042368} {"current_steps": 31965, "total_steps": 33920, "loss": 0.2756, "lr": 1.0095175716729578e-07, "epoch": 18.847287735849058, "percentage": 94.24, "elapsed_time": "1:02:02", "remaining_time": "0:03:47", "throughput": 5653.41, "total_tokens": 21045984} {"current_steps": 31970, "total_steps": 33920, "loss": 0.3144, "lr": 1.004380362393742e-07, "epoch": 18.850235849056602, "percentage": 94.25, "elapsed_time": "1:02:03", "remaining_time": "0:03:47", "throughput": 5653.38, "total_tokens": 21049056} {"current_steps": 31975, "total_steps": 33920, "loss": 0.2716, "lr": 9.99256124915987e-08, "epoch": 18.85318396226415, "percentage": 94.27, "elapsed_time": "1:02:03", "remaining_time": "0:03:46", "throughput": 5653.26, "total_tokens": 21051712} {"current_steps": 31980, "total_steps": 33920, "loss": 0.2737, "lr": 9.941448605963577e-08, "epoch": 18.8561320754717, "percentage": 94.28, "elapsed_time": "1:02:04", "remaining_time": "0:03:45", "throughput": 5653.16, "total_tokens": 21054336} {"current_steps": 31985, "total_steps": 33920, "loss": 0.2659, "lr": 9.890465707880715e-08, "epoch": 18.859080188679247, "percentage": 94.3, "elapsed_time": "1:02:04", "remaining_time": "0:03:45", "throughput": 5653.19, "total_tokens": 21057536} {"current_steps": 31990, "total_steps": 33920, "loss": 0.268, "lr": 9.839612568409374e-08, "epoch": 18.86202830188679, "percentage": 94.31, "elapsed_time": "1:02:05", "remaining_time": "0:03:44", "throughput": 5653.16, "total_tokens": 21060448} {"current_steps": 31995, "total_steps": 33920, "loss": 0.2773, "lr": 9.788889201013119e-08, "epoch": 18.86497641509434, "percentage": 94.32, "elapsed_time": "1:02:06", "remaining_time": "0:03:44", "throughput": 5652.97, "total_tokens": 21062976} {"current_steps": 32000, "total_steps": 33920, "loss": 0.1921, "lr": 9.738295619121097e-08, "epoch": 18.867924528301888, "percentage": 94.34, "elapsed_time": "1:02:06", "remaining_time": "0:03:43", "throughput": 5652.93, "total_tokens": 21066144} {"current_steps": 32005, "total_steps": 33920, "loss": 0.2307, "lr": 9.687831836128203e-08, "epoch": 18.870872641509433, "percentage": 94.35, "elapsed_time": "1:02:07", "remaining_time": "0:03:43", "throughput": 5652.92, "total_tokens": 21069440} {"current_steps": 32010, "total_steps": 33920, "loss": 0.3318, "lr": 9.637497865395029e-08, "epoch": 18.87382075471698, "percentage": 94.37, "elapsed_time": "1:02:07", "remaining_time": "0:03:42", "throughput": 5653.08, "total_tokens": 21073536} {"current_steps": 32015, "total_steps": 33920, "loss": 0.2782, "lr": 9.587293720247526e-08, "epoch": 18.87676886792453, "percentage": 94.38, "elapsed_time": "1:02:08", "remaining_time": "0:03:41", "throughput": 5653.09, "total_tokens": 21076672} {"current_steps": 32020, "total_steps": 33920, "loss": 0.3116, "lr": 9.537219413977672e-08, "epoch": 18.879716981132077, "percentage": 94.4, "elapsed_time": "1:02:08", "remaining_time": "0:03:41", "throughput": 5653.26, "total_tokens": 21080672} {"current_steps": 32025, "total_steps": 33920, "loss": 0.2796, "lr": 9.487274959842696e-08, "epoch": 18.88266509433962, "percentage": 94.41, "elapsed_time": "1:02:09", "remaining_time": "0:03:40", "throughput": 5653.33, "total_tokens": 21084384} {"current_steps": 32030, "total_steps": 33920, "loss": 0.3324, "lr": 9.437460371065687e-08, "epoch": 18.88561320754717, "percentage": 94.43, "elapsed_time": "1:02:10", "remaining_time": "0:03:40", "throughput": 5653.24, "total_tokens": 21087200} {"current_steps": 32035, "total_steps": 33920, "loss": 0.2136, "lr": 9.387775660835263e-08, "epoch": 18.888561320754718, "percentage": 94.44, "elapsed_time": "1:02:10", "remaining_time": "0:03:39", "throughput": 5653.33, "total_tokens": 21090560} {"current_steps": 32040, "total_steps": 33920, "loss": 0.2969, "lr": 9.338220842305678e-08, "epoch": 18.891509433962263, "percentage": 94.46, "elapsed_time": "1:02:11", "remaining_time": "0:03:38", "throughput": 5653.37, "total_tokens": 21093728} {"current_steps": 32045, "total_steps": 33920, "loss": 0.3623, "lr": 9.288795928596661e-08, "epoch": 18.89445754716981, "percentage": 94.47, "elapsed_time": "1:02:11", "remaining_time": "0:03:38", "throughput": 5653.47, "total_tokens": 21097472} {"current_steps": 32050, "total_steps": 33920, "loss": 0.3069, "lr": 9.239500932793854e-08, "epoch": 18.89740566037736, "percentage": 94.49, "elapsed_time": "1:02:12", "remaining_time": "0:03:37", "throughput": 5653.67, "total_tokens": 21101920} {"current_steps": 32055, "total_steps": 33920, "loss": 0.3185, "lr": 9.190335867948263e-08, "epoch": 18.900353773584907, "percentage": 94.5, "elapsed_time": "1:02:12", "remaining_time": "0:03:37", "throughput": 5653.57, "total_tokens": 21104672} {"current_steps": 32060, "total_steps": 33920, "loss": 0.271, "lr": 9.141300747076476e-08, "epoch": 18.903301886792452, "percentage": 94.52, "elapsed_time": "1:02:13", "remaining_time": "0:03:36", "throughput": 5653.37, "total_tokens": 21106944} {"current_steps": 32065, "total_steps": 33920, "loss": 0.2833, "lr": 9.092395583160773e-08, "epoch": 18.90625, "percentage": 94.53, "elapsed_time": "1:02:14", "remaining_time": "0:03:36", "throughput": 5653.26, "total_tokens": 21109600} {"current_steps": 32070, "total_steps": 33920, "loss": 0.3279, "lr": 9.043620389149021e-08, "epoch": 18.909198113207548, "percentage": 94.55, "elapsed_time": "1:02:14", "remaining_time": "0:03:35", "throughput": 5653.26, "total_tokens": 21112960} {"current_steps": 32075, "total_steps": 33920, "loss": 0.3178, "lr": 8.994975177954723e-08, "epoch": 18.912146226415093, "percentage": 94.56, "elapsed_time": "1:02:15", "remaining_time": "0:03:34", "throughput": 5653.21, "total_tokens": 21115776} {"current_steps": 32080, "total_steps": 33920, "loss": 0.3191, "lr": 8.946459962456855e-08, "epoch": 18.91509433962264, "percentage": 94.58, "elapsed_time": "1:02:15", "remaining_time": "0:03:34", "throughput": 5653.27, "total_tokens": 21119296} {"current_steps": 32085, "total_steps": 33920, "loss": 0.2418, "lr": 8.89807475550003e-08, "epoch": 18.91804245283019, "percentage": 94.59, "elapsed_time": "1:02:16", "remaining_time": "0:03:33", "throughput": 5653.21, "total_tokens": 21122208} {"current_steps": 32090, "total_steps": 33920, "loss": 0.3162, "lr": 8.849819569894447e-08, "epoch": 18.920990566037737, "percentage": 94.6, "elapsed_time": "1:02:16", "remaining_time": "0:03:33", "throughput": 5653.16, "total_tokens": 21125248} {"current_steps": 32095, "total_steps": 33920, "loss": 0.2741, "lr": 8.801694418415884e-08, "epoch": 18.923938679245282, "percentage": 94.62, "elapsed_time": "1:02:17", "remaining_time": "0:03:32", "throughput": 5653.17, "total_tokens": 21128192} {"current_steps": 32100, "total_steps": 33920, "loss": 0.4065, "lr": 8.753699313805708e-08, "epoch": 18.92688679245283, "percentage": 94.63, "elapsed_time": "1:02:17", "remaining_time": "0:03:31", "throughput": 5653.14, "total_tokens": 21131200} {"current_steps": 32105, "total_steps": 33920, "loss": 0.3387, "lr": 8.705834268770753e-08, "epoch": 18.92983490566038, "percentage": 94.65, "elapsed_time": "1:02:18", "remaining_time": "0:03:31", "throughput": 5653.08, "total_tokens": 21134144} {"current_steps": 32110, "total_steps": 33920, "loss": 0.389, "lr": 8.65809929598349e-08, "epoch": 18.932783018867923, "percentage": 94.66, "elapsed_time": "1:02:19", "remaining_time": "0:03:30", "throughput": 5653.1, "total_tokens": 21137344} {"current_steps": 32115, "total_steps": 33920, "loss": 0.2981, "lr": 8.610494408082037e-08, "epoch": 18.93573113207547, "percentage": 94.68, "elapsed_time": "1:02:19", "remaining_time": "0:03:30", "throughput": 5653.07, "total_tokens": 21140512} {"current_steps": 32120, "total_steps": 33920, "loss": 0.302, "lr": 8.563019617669977e-08, "epoch": 18.93867924528302, "percentage": 94.69, "elapsed_time": "1:02:20", "remaining_time": "0:03:29", "throughput": 5653.2, "total_tokens": 21144032} {"current_steps": 32125, "total_steps": 33920, "loss": 0.4552, "lr": 8.51567493731642e-08, "epoch": 18.941627358490567, "percentage": 94.71, "elapsed_time": "1:02:20", "remaining_time": "0:03:29", "throughput": 5653.16, "total_tokens": 21146912} {"current_steps": 32130, "total_steps": 33920, "loss": 0.2838, "lr": 8.468460379556176e-08, "epoch": 18.944575471698112, "percentage": 94.72, "elapsed_time": "1:02:21", "remaining_time": "0:03:28", "throughput": 5653.24, "total_tokens": 21150848} {"current_steps": 32135, "total_steps": 33920, "loss": 0.3783, "lr": 8.421375956889355e-08, "epoch": 18.94752358490566, "percentage": 94.74, "elapsed_time": "1:02:22", "remaining_time": "0:03:27", "throughput": 5653.31, "total_tokens": 21154912} {"current_steps": 32140, "total_steps": 33920, "loss": 0.2869, "lr": 8.374421681781819e-08, "epoch": 18.95047169811321, "percentage": 94.75, "elapsed_time": "1:02:22", "remaining_time": "0:03:27", "throughput": 5653.38, "total_tokens": 21159136} {"current_steps": 32145, "total_steps": 33920, "loss": 0.4012, "lr": 8.327597566665013e-08, "epoch": 18.953419811320753, "percentage": 94.77, "elapsed_time": "1:02:23", "remaining_time": "0:03:26", "throughput": 5653.42, "total_tokens": 21162688} {"current_steps": 32150, "total_steps": 33920, "loss": 0.283, "lr": 8.280903623935688e-08, "epoch": 18.9563679245283, "percentage": 94.78, "elapsed_time": "1:02:23", "remaining_time": "0:03:26", "throughput": 5653.48, "total_tokens": 21166400} {"current_steps": 32155, "total_steps": 33920, "loss": 0.4112, "lr": 8.234339865956342e-08, "epoch": 18.95931603773585, "percentage": 94.8, "elapsed_time": "1:02:24", "remaining_time": "0:03:25", "throughput": 5653.58, "total_tokens": 21170880} {"current_steps": 32160, "total_steps": 33920, "loss": 0.3218, "lr": 8.187906305054838e-08, "epoch": 18.962264150943398, "percentage": 94.81, "elapsed_time": "1:02:25", "remaining_time": "0:03:24", "throughput": 5653.58, "total_tokens": 21173856} {"current_steps": 32165, "total_steps": 33920, "loss": 0.2773, "lr": 8.141602953524841e-08, "epoch": 18.965212264150942, "percentage": 94.83, "elapsed_time": "1:02:25", "remaining_time": "0:03:24", "throughput": 5653.53, "total_tokens": 21176896} {"current_steps": 32170, "total_steps": 33920, "loss": 0.2673, "lr": 8.095429823625212e-08, "epoch": 18.96816037735849, "percentage": 94.84, "elapsed_time": "1:02:26", "remaining_time": "0:03:23", "throughput": 5653.65, "total_tokens": 21180576} {"current_steps": 32175, "total_steps": 33920, "loss": 0.2532, "lr": 8.04938692758045e-08, "epoch": 18.97110849056604, "percentage": 94.86, "elapsed_time": "1:02:26", "remaining_time": "0:03:23", "throughput": 5653.72, "total_tokens": 21184160} {"current_steps": 32180, "total_steps": 33920, "loss": 0.3168, "lr": 8.003474277580803e-08, "epoch": 18.974056603773583, "percentage": 94.87, "elapsed_time": "1:02:27", "remaining_time": "0:03:22", "throughput": 5653.78, "total_tokens": 21187584} {"current_steps": 32185, "total_steps": 33920, "loss": 0.2607, "lr": 7.95769188578166e-08, "epoch": 18.97700471698113, "percentage": 94.89, "elapsed_time": "1:02:28", "remaining_time": "0:03:22", "throughput": 5653.73, "total_tokens": 21190592} {"current_steps": 32190, "total_steps": 33920, "loss": 0.2441, "lr": 7.912039764304213e-08, "epoch": 18.97995283018868, "percentage": 94.9, "elapsed_time": "1:02:28", "remaining_time": "0:03:21", "throughput": 5653.68, "total_tokens": 21193472} {"current_steps": 32195, "total_steps": 33920, "loss": 0.378, "lr": 7.866517925235017e-08, "epoch": 18.982900943396228, "percentage": 94.91, "elapsed_time": "1:02:29", "remaining_time": "0:03:20", "throughput": 5653.59, "total_tokens": 21196640} {"current_steps": 32200, "total_steps": 33920, "loss": 0.388, "lr": 7.821126380626154e-08, "epoch": 18.985849056603772, "percentage": 94.93, "elapsed_time": "1:02:29", "remaining_time": "0:03:20", "throughput": 5653.47, "total_tokens": 21199168} {"current_steps": 32205, "total_steps": 33920, "loss": 0.2318, "lr": 7.775865142495286e-08, "epoch": 18.98879716981132, "percentage": 94.94, "elapsed_time": "1:02:30", "remaining_time": "0:03:19", "throughput": 5653.47, "total_tokens": 21202592} {"current_steps": 32210, "total_steps": 33920, "loss": 0.3996, "lr": 7.730734222825442e-08, "epoch": 18.99174528301887, "percentage": 94.96, "elapsed_time": "1:02:30", "remaining_time": "0:03:19", "throughput": 5653.51, "total_tokens": 21206176} {"current_steps": 32215, "total_steps": 33920, "loss": 0.377, "lr": 7.68573363356534e-08, "epoch": 18.994693396226417, "percentage": 94.97, "elapsed_time": "1:02:31", "remaining_time": "0:03:18", "throughput": 5653.63, "total_tokens": 21209952} {"current_steps": 32220, "total_steps": 33920, "loss": 0.3378, "lr": 7.640863386629005e-08, "epoch": 18.99764150943396, "percentage": 94.99, "elapsed_time": "1:02:32", "remaining_time": "0:03:17", "throughput": 5653.63, "total_tokens": 21212960} {"current_steps": 32225, "total_steps": 33920, "loss": 0.2898, "lr": 7.59612349389599e-08, "epoch": 19.00058962264151, "percentage": 95.0, "elapsed_time": "1:02:33", "remaining_time": "0:03:17", "throughput": 5652.81, "total_tokens": 21215152} {"current_steps": 32230, "total_steps": 33920, "loss": 0.3032, "lr": 7.551513967211433e-08, "epoch": 19.003537735849058, "percentage": 95.02, "elapsed_time": "1:02:33", "remaining_time": "0:03:16", "throughput": 5652.79, "total_tokens": 21218544} {"current_steps": 32235, "total_steps": 33920, "loss": 0.2807, "lr": 7.507034818385883e-08, "epoch": 19.006485849056602, "percentage": 95.03, "elapsed_time": "1:02:34", "remaining_time": "0:03:16", "throughput": 5652.84, "total_tokens": 21222000} {"current_steps": 32240, "total_steps": 33920, "loss": 0.3521, "lr": 7.462686059195423e-08, "epoch": 19.00943396226415, "percentage": 95.05, "elapsed_time": "1:02:34", "remaining_time": "0:03:15", "throughput": 5652.85, "total_tokens": 21225840} {"current_steps": 32245, "total_steps": 33920, "loss": 0.2847, "lr": 7.418467701381548e-08, "epoch": 19.0123820754717, "percentage": 95.06, "elapsed_time": "1:02:35", "remaining_time": "0:03:15", "throughput": 5652.9, "total_tokens": 21229360} {"current_steps": 32250, "total_steps": 33920, "loss": 0.3094, "lr": 7.374379756651285e-08, "epoch": 19.015330188679247, "percentage": 95.08, "elapsed_time": "1:02:36", "remaining_time": "0:03:14", "throughput": 5652.84, "total_tokens": 21232176} {"current_steps": 32255, "total_steps": 33920, "loss": 0.2887, "lr": 7.330422236677015e-08, "epoch": 19.01827830188679, "percentage": 95.09, "elapsed_time": "1:02:36", "remaining_time": "0:03:13", "throughput": 5652.81, "total_tokens": 21235216} {"current_steps": 32260, "total_steps": 33920, "loss": 0.3306, "lr": 7.286595153096765e-08, "epoch": 19.02122641509434, "percentage": 95.11, "elapsed_time": "1:02:37", "remaining_time": "0:03:13", "throughput": 5652.8, "total_tokens": 21238256} {"current_steps": 32265, "total_steps": 33920, "loss": 0.2561, "lr": 7.242898517513864e-08, "epoch": 19.024174528301888, "percentage": 95.12, "elapsed_time": "1:02:37", "remaining_time": "0:03:12", "throughput": 5652.75, "total_tokens": 21241296} {"current_steps": 32270, "total_steps": 33920, "loss": 0.364, "lr": 7.199332341497333e-08, "epoch": 19.027122641509433, "percentage": 95.14, "elapsed_time": "1:02:38", "remaining_time": "0:03:12", "throughput": 5652.54, "total_tokens": 21243600} {"current_steps": 32275, "total_steps": 33920, "loss": 0.229, "lr": 7.155896636581394e-08, "epoch": 19.03007075471698, "percentage": 95.15, "elapsed_time": "1:02:38", "remaining_time": "0:03:11", "throughput": 5652.5, "total_tokens": 21246544} {"current_steps": 32280, "total_steps": 33920, "loss": 0.2356, "lr": 7.112591414265901e-08, "epoch": 19.03301886792453, "percentage": 95.17, "elapsed_time": "1:02:39", "remaining_time": "0:03:11", "throughput": 5652.58, "total_tokens": 21250576} {"current_steps": 32285, "total_steps": 33920, "loss": 0.2541, "lr": 7.069416686016018e-08, "epoch": 19.035966981132077, "percentage": 95.18, "elapsed_time": "1:02:40", "remaining_time": "0:03:10", "throughput": 5652.5, "total_tokens": 21253392} {"current_steps": 32290, "total_steps": 33920, "loss": 0.2761, "lr": 7.026372463262488e-08, "epoch": 19.03891509433962, "percentage": 95.19, "elapsed_time": "1:02:40", "remaining_time": "0:03:09", "throughput": 5652.68, "total_tokens": 21258064} {"current_steps": 32295, "total_steps": 33920, "loss": 0.3237, "lr": 6.983458757401418e-08, "epoch": 19.04186320754717, "percentage": 95.21, "elapsed_time": "1:02:41", "remaining_time": "0:03:09", "throughput": 5652.72, "total_tokens": 21261488} {"current_steps": 32300, "total_steps": 33920, "loss": 0.3082, "lr": 6.940675579794443e-08, "epoch": 19.044811320754718, "percentage": 95.22, "elapsed_time": "1:02:41", "remaining_time": "0:03:08", "throughput": 5652.73, "total_tokens": 21264624} {"current_steps": 32305, "total_steps": 33920, "loss": 0.2444, "lr": 6.898022941768612e-08, "epoch": 19.047759433962263, "percentage": 95.24, "elapsed_time": "1:02:42", "remaining_time": "0:03:08", "throughput": 5652.63, "total_tokens": 21267184} {"current_steps": 32310, "total_steps": 33920, "loss": 0.3667, "lr": 6.855500854616337e-08, "epoch": 19.05070754716981, "percentage": 95.25, "elapsed_time": "1:02:42", "remaining_time": "0:03:07", "throughput": 5652.66, "total_tokens": 21270704} {"current_steps": 32315, "total_steps": 33920, "loss": 0.3057, "lr": 6.813109329595557e-08, "epoch": 19.05365566037736, "percentage": 95.27, "elapsed_time": "1:02:43", "remaining_time": "0:03:06", "throughput": 5652.58, "total_tokens": 21273520} {"current_steps": 32320, "total_steps": 33920, "loss": 0.3025, "lr": 6.770848377929573e-08, "epoch": 19.056603773584907, "percentage": 95.28, "elapsed_time": "1:02:44", "remaining_time": "0:03:06", "throughput": 5652.61, "total_tokens": 21277040} {"current_steps": 32325, "total_steps": 33920, "loss": 0.2931, "lr": 6.728718010807156e-08, "epoch": 19.059551886792452, "percentage": 95.3, "elapsed_time": "1:02:44", "remaining_time": "0:03:05", "throughput": 5652.57, "total_tokens": 21279888} {"current_steps": 32330, "total_steps": 33920, "loss": 0.382, "lr": 6.68671823938255e-08, "epoch": 19.0625, "percentage": 95.31, "elapsed_time": "1:02:45", "remaining_time": "0:03:05", "throughput": 5652.34, "total_tokens": 21282320} {"current_steps": 32335, "total_steps": 33920, "loss": 0.2964, "lr": 6.644849074775361e-08, "epoch": 19.065448113207548, "percentage": 95.33, "elapsed_time": "1:02:45", "remaining_time": "0:03:04", "throughput": 5652.3, "total_tokens": 21285296} {"current_steps": 32340, "total_steps": 33920, "loss": 0.424, "lr": 6.603110528070667e-08, "epoch": 19.068396226415093, "percentage": 95.34, "elapsed_time": "1:02:46", "remaining_time": "0:03:04", "throughput": 5652.37, "total_tokens": 21289008} {"current_steps": 32345, "total_steps": 33920, "loss": 0.2611, "lr": 6.561502610318849e-08, "epoch": 19.07134433962264, "percentage": 95.36, "elapsed_time": "1:02:46", "remaining_time": "0:03:03", "throughput": 5652.27, "total_tokens": 21291952} {"current_steps": 32350, "total_steps": 33920, "loss": 0.2914, "lr": 6.520025332535762e-08, "epoch": 19.07429245283019, "percentage": 95.37, "elapsed_time": "1:02:47", "remaining_time": "0:03:02", "throughput": 5652.39, "total_tokens": 21295632} {"current_steps": 32355, "total_steps": 33920, "loss": 0.419, "lr": 6.47867870570279e-08, "epoch": 19.077240566037737, "percentage": 95.39, "elapsed_time": "1:02:48", "remaining_time": "0:03:02", "throughput": 5652.34, "total_tokens": 21298448} {"current_steps": 32360, "total_steps": 33920, "loss": 0.3058, "lr": 6.437462740766564e-08, "epoch": 19.080188679245282, "percentage": 95.4, "elapsed_time": "1:02:48", "remaining_time": "0:03:01", "throughput": 5652.37, "total_tokens": 21301776} {"current_steps": 32365, "total_steps": 33920, "loss": 0.3908, "lr": 6.396377448639246e-08, "epoch": 19.08313679245283, "percentage": 95.42, "elapsed_time": "1:02:49", "remaining_time": "0:03:01", "throughput": 5652.41, "total_tokens": 21305168} {"current_steps": 32370, "total_steps": 33920, "loss": 0.2703, "lr": 6.3554228401983e-08, "epoch": 19.08608490566038, "percentage": 95.43, "elapsed_time": "1:02:49", "remaining_time": "0:03:00", "throughput": 5652.34, "total_tokens": 21307856} {"current_steps": 32375, "total_steps": 33920, "loss": 0.2725, "lr": 6.314598926286663e-08, "epoch": 19.089033018867923, "percentage": 95.45, "elapsed_time": "1:02:50", "remaining_time": "0:02:59", "throughput": 5652.33, "total_tokens": 21311088} {"current_steps": 32380, "total_steps": 33920, "loss": 0.3902, "lr": 6.273905717712637e-08, "epoch": 19.09198113207547, "percentage": 95.46, "elapsed_time": "1:02:50", "remaining_time": "0:02:59", "throughput": 5652.38, "total_tokens": 21314544} {"current_steps": 32385, "total_steps": 33920, "loss": 0.2765, "lr": 6.233343225249933e-08, "epoch": 19.09492924528302, "percentage": 95.47, "elapsed_time": "1:02:51", "remaining_time": "0:02:58", "throughput": 5652.3, "total_tokens": 21317168} {"current_steps": 32390, "total_steps": 33920, "loss": 0.348, "lr": 6.192911459637519e-08, "epoch": 19.097877358490567, "percentage": 95.49, "elapsed_time": "1:02:51", "remaining_time": "0:02:58", "throughput": 5652.31, "total_tokens": 21320208} {"current_steps": 32395, "total_steps": 33920, "loss": 0.3421, "lr": 6.152610431580052e-08, "epoch": 19.100825471698112, "percentage": 95.5, "elapsed_time": "1:02:52", "remaining_time": "0:02:57", "throughput": 5652.3, "total_tokens": 21323152} {"current_steps": 32400, "total_steps": 33920, "loss": 0.3556, "lr": 6.112440151747389e-08, "epoch": 19.10377358490566, "percentage": 95.52, "elapsed_time": "1:02:53", "remaining_time": "0:02:57", "throughput": 5652.27, "total_tokens": 21326160} {"current_steps": 32405, "total_steps": 33920, "loss": 0.3095, "lr": 6.072400630774689e-08, "epoch": 19.10672169811321, "percentage": 95.53, "elapsed_time": "1:02:53", "remaining_time": "0:02:56", "throughput": 5652.29, "total_tokens": 21329264} {"current_steps": 32410, "total_steps": 33920, "loss": 0.2777, "lr": 6.032491879262637e-08, "epoch": 19.109669811320753, "percentage": 95.55, "elapsed_time": "1:02:54", "remaining_time": "0:02:55", "throughput": 5652.2, "total_tokens": 21332016} {"current_steps": 32415, "total_steps": 33920, "loss": 0.2691, "lr": 5.99271390777717e-08, "epoch": 19.1126179245283, "percentage": 95.56, "elapsed_time": "1:02:54", "remaining_time": "0:02:55", "throughput": 5652.15, "total_tokens": 21334992} {"current_steps": 32420, "total_steps": 33920, "loss": 0.2207, "lr": 5.953066726849865e-08, "epoch": 19.11556603773585, "percentage": 95.58, "elapsed_time": "1:02:55", "remaining_time": "0:02:54", "throughput": 5652.17, "total_tokens": 21338032} {"current_steps": 32425, "total_steps": 33920, "loss": 0.3282, "lr": 5.913550346977326e-08, "epoch": 19.118514150943398, "percentage": 95.59, "elapsed_time": "1:02:55", "remaining_time": "0:02:54", "throughput": 5652.23, "total_tokens": 21342032} {"current_steps": 32430, "total_steps": 33920, "loss": 0.2933, "lr": 5.874164778621683e-08, "epoch": 19.121462264150942, "percentage": 95.61, "elapsed_time": "1:02:56", "remaining_time": "0:02:53", "throughput": 5652.43, "total_tokens": 21346736} {"current_steps": 32435, "total_steps": 33920, "loss": 0.2501, "lr": 5.834910032210539e-08, "epoch": 19.12441037735849, "percentage": 95.62, "elapsed_time": "1:02:57", "remaining_time": "0:02:52", "throughput": 5652.36, "total_tokens": 21349488} {"current_steps": 32440, "total_steps": 33920, "loss": 0.4349, "lr": 5.795786118136693e-08, "epoch": 19.12735849056604, "percentage": 95.64, "elapsed_time": "1:02:57", "remaining_time": "0:02:52", "throughput": 5652.38, "total_tokens": 21352784} {"current_steps": 32445, "total_steps": 33920, "loss": 0.3724, "lr": 5.756793046758302e-08, "epoch": 19.130306603773583, "percentage": 95.65, "elapsed_time": "1:02:58", "remaining_time": "0:02:51", "throughput": 5652.22, "total_tokens": 21355248} {"current_steps": 32450, "total_steps": 33920, "loss": 0.276, "lr": 5.7179308283990544e-08, "epoch": 19.13325471698113, "percentage": 95.67, "elapsed_time": "1:02:58", "remaining_time": "0:02:51", "throughput": 5652.29, "total_tokens": 21358832} {"current_steps": 32455, "total_steps": 33920, "loss": 0.427, "lr": 5.679199473347885e-08, "epoch": 19.13620283018868, "percentage": 95.68, "elapsed_time": "1:02:59", "remaining_time": "0:02:50", "throughput": 5652.22, "total_tokens": 21361552} {"current_steps": 32460, "total_steps": 33920, "loss": 0.2596, "lr": 5.6405989918590366e-08, "epoch": 19.139150943396228, "percentage": 95.7, "elapsed_time": "1:03:00", "remaining_time": "0:02:50", "throughput": 5652.28, "total_tokens": 21365648} {"current_steps": 32465, "total_steps": 33920, "loss": 0.2447, "lr": 5.6021293941522225e-08, "epoch": 19.142099056603772, "percentage": 95.71, "elapsed_time": "1:03:00", "remaining_time": "0:02:49", "throughput": 5652.32, "total_tokens": 21369136} {"current_steps": 32470, "total_steps": 33920, "loss": 0.2511, "lr": 5.563790690412352e-08, "epoch": 19.14504716981132, "percentage": 95.73, "elapsed_time": "1:03:01", "remaining_time": "0:02:48", "throughput": 5652.35, "total_tokens": 21372304} {"current_steps": 32475, "total_steps": 33920, "loss": 0.4385, "lr": 5.525582890789805e-08, "epoch": 19.14799528301887, "percentage": 95.74, "elapsed_time": "1:03:01", "remaining_time": "0:02:48", "throughput": 5652.28, "total_tokens": 21375184} {"current_steps": 32480, "total_steps": 33920, "loss": 0.3633, "lr": 5.4875060054002115e-08, "epoch": 19.150943396226417, "percentage": 95.75, "elapsed_time": "1:03:02", "remaining_time": "0:02:47", "throughput": 5652.36, "total_tokens": 21378960} {"current_steps": 32485, "total_steps": 33920, "loss": 0.3565, "lr": 5.4495600443246755e-08, "epoch": 19.15389150943396, "percentage": 95.77, "elapsed_time": "1:03:02", "remaining_time": "0:02:47", "throughput": 5652.3, "total_tokens": 21381808} {"current_steps": 32490, "total_steps": 33920, "loss": 0.2618, "lr": 5.411745017609493e-08, "epoch": 19.15683962264151, "percentage": 95.78, "elapsed_time": "1:03:03", "remaining_time": "0:02:46", "throughput": 5652.17, "total_tokens": 21384592} {"current_steps": 32495, "total_steps": 33920, "loss": 0.2724, "lr": 5.374060935266434e-08, "epoch": 19.159787735849058, "percentage": 95.8, "elapsed_time": "1:03:04", "remaining_time": "0:02:45", "throughput": 5652.23, "total_tokens": 21388304} {"current_steps": 32500, "total_steps": 33920, "loss": 0.313, "lr": 5.3365078072724065e-08, "epoch": 19.162735849056602, "percentage": 95.81, "elapsed_time": "1:03:04", "remaining_time": "0:02:45", "throughput": 5652.32, "total_tokens": 21391824} {"current_steps": 32505, "total_steps": 33920, "loss": 0.2316, "lr": 5.299085643569846e-08, "epoch": 19.16568396226415, "percentage": 95.83, "elapsed_time": "1:03:05", "remaining_time": "0:02:44", "throughput": 5652.38, "total_tokens": 21395056} {"current_steps": 32510, "total_steps": 33920, "loss": 0.2785, "lr": 5.261794454066327e-08, "epoch": 19.1686320754717, "percentage": 95.84, "elapsed_time": "1:03:05", "remaining_time": "0:02:44", "throughput": 5652.45, "total_tokens": 21398608} {"current_steps": 32515, "total_steps": 33920, "loss": 0.2068, "lr": 5.224634248635008e-08, "epoch": 19.171580188679247, "percentage": 95.86, "elapsed_time": "1:03:06", "remaining_time": "0:02:43", "throughput": 5652.54, "total_tokens": 21402704} {"current_steps": 32520, "total_steps": 33920, "loss": 0.3764, "lr": 5.187605037114129e-08, "epoch": 19.17452830188679, "percentage": 95.87, "elapsed_time": "1:03:06", "remaining_time": "0:02:43", "throughput": 5652.64, "total_tokens": 21406352} {"current_steps": 32525, "total_steps": 33920, "loss": 0.2558, "lr": 5.15070682930735e-08, "epoch": 19.17747641509434, "percentage": 95.89, "elapsed_time": "1:03:07", "remaining_time": "0:02:42", "throughput": 5652.66, "total_tokens": 21409584} {"current_steps": 32530, "total_steps": 33920, "loss": 0.3528, "lr": 5.113939634983578e-08, "epoch": 19.180424528301888, "percentage": 95.9, "elapsed_time": "1:03:08", "remaining_time": "0:02:41", "throughput": 5652.59, "total_tokens": 21413168} {"current_steps": 32535, "total_steps": 33920, "loss": 0.2476, "lr": 5.077303463877192e-08, "epoch": 19.183372641509433, "percentage": 95.92, "elapsed_time": "1:03:08", "remaining_time": "0:02:41", "throughput": 5652.63, "total_tokens": 21416848} {"current_steps": 32540, "total_steps": 33920, "loss": 0.374, "lr": 5.040798325687601e-08, "epoch": 19.18632075471698, "percentage": 95.93, "elapsed_time": "1:03:09", "remaining_time": "0:02:40", "throughput": 5652.69, "total_tokens": 21420016} {"current_steps": 32545, "total_steps": 33920, "loss": 0.2976, "lr": 5.004424230079852e-08, "epoch": 19.18926886792453, "percentage": 95.95, "elapsed_time": "1:03:10", "remaining_time": "0:02:40", "throughput": 5652.85, "total_tokens": 21424656} {"current_steps": 32550, "total_steps": 33920, "loss": 0.3522, "lr": 4.968181186684129e-08, "epoch": 19.192216981132077, "percentage": 95.96, "elapsed_time": "1:03:10", "remaining_time": "0:02:39", "throughput": 5652.82, "total_tokens": 21427664} {"current_steps": 32555, "total_steps": 33920, "loss": 0.3396, "lr": 4.932069205095924e-08, "epoch": 19.19516509433962, "percentage": 95.98, "elapsed_time": "1:03:11", "remaining_time": "0:02:38", "throughput": 5652.77, "total_tokens": 21430448} {"current_steps": 32560, "total_steps": 33920, "loss": 0.3152, "lr": 4.896088294875978e-08, "epoch": 19.19811320754717, "percentage": 95.99, "elapsed_time": "1:03:11", "remaining_time": "0:02:38", "throughput": 5652.77, "total_tokens": 21433616} {"current_steps": 32565, "total_steps": 33920, "loss": 0.3001, "lr": 4.8602384655505044e-08, "epoch": 19.201061320754718, "percentage": 96.01, "elapsed_time": "1:03:12", "remaining_time": "0:02:37", "throughput": 5652.73, "total_tokens": 21436496} {"current_steps": 32570, "total_steps": 33920, "loss": 0.2978, "lr": 4.824519726610744e-08, "epoch": 19.204009433962263, "percentage": 96.02, "elapsed_time": "1:03:12", "remaining_time": "0:02:37", "throughput": 5652.75, "total_tokens": 21439792} {"current_steps": 32575, "total_steps": 33920, "loss": 0.3449, "lr": 4.7889320875135206e-08, "epoch": 19.20695754716981, "percentage": 96.03, "elapsed_time": "1:03:13", "remaining_time": "0:02:36", "throughput": 5652.73, "total_tokens": 21443024} {"current_steps": 32580, "total_steps": 33920, "loss": 0.2996, "lr": 4.753475557680742e-08, "epoch": 19.20990566037736, "percentage": 96.05, "elapsed_time": "1:03:13", "remaining_time": "0:02:36", "throughput": 5652.73, "total_tokens": 21446096} {"current_steps": 32585, "total_steps": 33920, "loss": 0.35, "lr": 4.718150146499734e-08, "epoch": 19.212853773584907, "percentage": 96.06, "elapsed_time": "1:03:14", "remaining_time": "0:02:35", "throughput": 5652.91, "total_tokens": 21450480} {"current_steps": 32590, "total_steps": 33920, "loss": 0.2721, "lr": 4.682955863323013e-08, "epoch": 19.215801886792452, "percentage": 96.08, "elapsed_time": "1:03:15", "remaining_time": "0:02:34", "throughput": 5652.86, "total_tokens": 21453360} {"current_steps": 32595, "total_steps": 33920, "loss": 0.3261, "lr": 4.6478927174684606e-08, "epoch": 19.21875, "percentage": 96.09, "elapsed_time": "1:03:15", "remaining_time": "0:02:34", "throughput": 5652.81, "total_tokens": 21456112} {"current_steps": 32600, "total_steps": 33920, "loss": 0.3093, "lr": 4.612960718219095e-08, "epoch": 19.221698113207548, "percentage": 96.11, "elapsed_time": "1:03:16", "remaining_time": "0:02:33", "throughput": 5652.77, "total_tokens": 21458864} {"current_steps": 32605, "total_steps": 33920, "loss": 0.2758, "lr": 4.578159874823407e-08, "epoch": 19.224646226415093, "percentage": 96.12, "elapsed_time": "1:03:16", "remaining_time": "0:02:33", "throughput": 5652.78, "total_tokens": 21462192} {"current_steps": 32610, "total_steps": 33920, "loss": 0.2303, "lr": 4.5434901964950264e-08, "epoch": 19.22759433962264, "percentage": 96.14, "elapsed_time": "1:03:17", "remaining_time": "0:02:32", "throughput": 5652.82, "total_tokens": 21465328} {"current_steps": 32615, "total_steps": 33920, "loss": 0.3314, "lr": 4.508951692412944e-08, "epoch": 19.23054245283019, "percentage": 96.15, "elapsed_time": "1:03:17", "remaining_time": "0:02:31", "throughput": 5652.82, "total_tokens": 21468752} {"current_steps": 32620, "total_steps": 33920, "loss": 0.1805, "lr": 4.4745443717213455e-08, "epoch": 19.233490566037737, "percentage": 96.17, "elapsed_time": "1:03:18", "remaining_time": "0:02:31", "throughput": 5652.71, "total_tokens": 21471696} {"current_steps": 32625, "total_steps": 33920, "loss": 0.3073, "lr": 4.4402682435296666e-08, "epoch": 19.236438679245282, "percentage": 96.18, "elapsed_time": "1:03:19", "remaining_time": "0:02:30", "throughput": 5652.73, "total_tokens": 21474928} {"current_steps": 32630, "total_steps": 33920, "loss": 0.328, "lr": 4.406123316912758e-08, "epoch": 19.23938679245283, "percentage": 96.2, "elapsed_time": "1:03:19", "remaining_time": "0:02:30", "throughput": 5652.84, "total_tokens": 21478448} {"current_steps": 32635, "total_steps": 33920, "loss": 0.3637, "lr": 4.372109600910612e-08, "epoch": 19.24233490566038, "percentage": 96.21, "elapsed_time": "1:03:20", "remaining_time": "0:02:29", "throughput": 5652.81, "total_tokens": 21481456} {"current_steps": 32640, "total_steps": 33920, "loss": 0.3251, "lr": 4.338227104528414e-08, "epoch": 19.245283018867923, "percentage": 96.23, "elapsed_time": "1:03:20", "remaining_time": "0:02:29", "throughput": 5652.97, "total_tokens": 21486000} {"current_steps": 32645, "total_steps": 33920, "loss": 0.2865, "lr": 4.304475836736821e-08, "epoch": 19.24823113207547, "percentage": 96.24, "elapsed_time": "1:03:21", "remaining_time": "0:02:28", "throughput": 5653.08, "total_tokens": 21489520} {"current_steps": 32650, "total_steps": 33920, "loss": 0.3941, "lr": 4.27085580647163e-08, "epoch": 19.25117924528302, "percentage": 96.26, "elapsed_time": "1:03:22", "remaining_time": "0:02:27", "throughput": 5653.1, "total_tokens": 21493104} {"current_steps": 32655, "total_steps": 33920, "loss": 0.3132, "lr": 4.237367022633776e-08, "epoch": 19.254127358490567, "percentage": 96.27, "elapsed_time": "1:03:22", "remaining_time": "0:02:27", "throughput": 5653.09, "total_tokens": 21496016} {"current_steps": 32660, "total_steps": 33920, "loss": 0.2877, "lr": 4.204009494089612e-08, "epoch": 19.257075471698112, "percentage": 96.29, "elapsed_time": "1:03:23", "remaining_time": "0:02:26", "throughput": 5653.12, "total_tokens": 21499632} {"current_steps": 32665, "total_steps": 33920, "loss": 0.2605, "lr": 4.170783229670739e-08, "epoch": 19.26002358490566, "percentage": 96.3, "elapsed_time": "1:03:23", "remaining_time": "0:02:26", "throughput": 5653.16, "total_tokens": 21502736} {"current_steps": 32670, "total_steps": 33920, "loss": 0.3163, "lr": 4.137688238173898e-08, "epoch": 19.26297169811321, "percentage": 96.31, "elapsed_time": "1:03:24", "remaining_time": "0:02:25", "throughput": 5653.15, "total_tokens": 21506000} {"current_steps": 32675, "total_steps": 33920, "loss": 0.2895, "lr": 4.104724528361137e-08, "epoch": 19.265919811320753, "percentage": 96.33, "elapsed_time": "1:03:24", "remaining_time": "0:02:24", "throughput": 5653.17, "total_tokens": 21509360} {"current_steps": 32680, "total_steps": 33920, "loss": 0.274, "lr": 4.071892108959752e-08, "epoch": 19.2688679245283, "percentage": 96.34, "elapsed_time": "1:03:25", "remaining_time": "0:02:24", "throughput": 5653.3, "total_tokens": 21513232} {"current_steps": 32685, "total_steps": 33920, "loss": 0.4243, "lr": 4.039190988662234e-08, "epoch": 19.27181603773585, "percentage": 96.36, "elapsed_time": "1:03:26", "remaining_time": "0:02:23", "throughput": 5653.29, "total_tokens": 21516592} {"current_steps": 32690, "total_steps": 33920, "loss": 0.4868, "lr": 4.006621176126435e-08, "epoch": 19.274764150943398, "percentage": 96.37, "elapsed_time": "1:03:26", "remaining_time": "0:02:23", "throughput": 5653.53, "total_tokens": 21522864} {"current_steps": 32695, "total_steps": 33920, "loss": 0.3448, "lr": 3.974182679975236e-08, "epoch": 19.277712264150942, "percentage": 96.39, "elapsed_time": "1:03:27", "remaining_time": "0:02:22", "throughput": 5653.67, "total_tokens": 21526544} {"current_steps": 32700, "total_steps": 33920, "loss": 0.3236, "lr": 3.941875508796933e-08, "epoch": 19.28066037735849, "percentage": 96.4, "elapsed_time": "1:03:28", "remaining_time": "0:02:22", "throughput": 5653.68, "total_tokens": 21529936} {"current_steps": 32705, "total_steps": 33920, "loss": 0.3061, "lr": 3.909699671145017e-08, "epoch": 19.28360849056604, "percentage": 96.42, "elapsed_time": "1:03:28", "remaining_time": "0:02:21", "throughput": 5653.66, "total_tokens": 21533168} {"current_steps": 32710, "total_steps": 33920, "loss": 0.2455, "lr": 3.87765517553812e-08, "epoch": 19.286556603773583, "percentage": 96.43, "elapsed_time": "1:03:29", "remaining_time": "0:02:20", "throughput": 5653.61, "total_tokens": 21535984} {"current_steps": 32715, "total_steps": 33920, "loss": 0.3099, "lr": 3.8457420304601756e-08, "epoch": 19.28950471698113, "percentage": 96.45, "elapsed_time": "1:03:29", "remaining_time": "0:02:20", "throughput": 5653.61, "total_tokens": 21538928} {"current_steps": 32720, "total_steps": 33920, "loss": 0.3078, "lr": 3.813960244360371e-08, "epoch": 19.29245283018868, "percentage": 96.46, "elapsed_time": "1:03:30", "remaining_time": "0:02:19", "throughput": 5653.73, "total_tokens": 21543152} {"current_steps": 32725, "total_steps": 33920, "loss": 0.3203, "lr": 3.7823098256529744e-08, "epoch": 19.295400943396228, "percentage": 96.48, "elapsed_time": "1:03:30", "remaining_time": "0:02:19", "throughput": 5653.79, "total_tokens": 21546448} {"current_steps": 32730, "total_steps": 33920, "loss": 0.3431, "lr": 3.750790782717673e-08, "epoch": 19.298349056603772, "percentage": 96.49, "elapsed_time": "1:03:31", "remaining_time": "0:02:18", "throughput": 5653.79, "total_tokens": 21549520} {"current_steps": 32735, "total_steps": 33920, "loss": 0.3832, "lr": 3.719403123899179e-08, "epoch": 19.30129716981132, "percentage": 96.51, "elapsed_time": "1:03:32", "remaining_time": "0:02:17", "throughput": 5653.63, "total_tokens": 21551888} {"current_steps": 32740, "total_steps": 33920, "loss": 0.3341, "lr": 3.688146857507624e-08, "epoch": 19.30424528301887, "percentage": 96.52, "elapsed_time": "1:03:32", "remaining_time": "0:02:17", "throughput": 5653.6, "total_tokens": 21554896} {"current_steps": 32745, "total_steps": 33920, "loss": 0.4191, "lr": 3.657021991818166e-08, "epoch": 19.307193396226417, "percentage": 96.54, "elapsed_time": "1:03:33", "remaining_time": "0:02:16", "throughput": 5653.69, "total_tokens": 21558960} {"current_steps": 32750, "total_steps": 33920, "loss": 0.2568, "lr": 3.626028535071213e-08, "epoch": 19.31014150943396, "percentage": 96.55, "elapsed_time": "1:03:33", "remaining_time": "0:02:16", "throughput": 5653.62, "total_tokens": 21562064} {"current_steps": 32755, "total_steps": 33920, "loss": 0.3213, "lr": 3.59516649547248e-08, "epoch": 19.31308962264151, "percentage": 96.57, "elapsed_time": "1:03:34", "remaining_time": "0:02:15", "throughput": 5653.53, "total_tokens": 21564624} {"current_steps": 32760, "total_steps": 33920, "loss": 0.2942, "lr": 3.564435881192818e-08, "epoch": 19.316037735849058, "percentage": 96.58, "elapsed_time": "1:03:34", "remaining_time": "0:02:15", "throughput": 5653.42, "total_tokens": 21567312} {"current_steps": 32765, "total_steps": 33920, "loss": 0.284, "lr": 3.5338367003682763e-08, "epoch": 19.318985849056602, "percentage": 96.59, "elapsed_time": "1:03:35", "remaining_time": "0:02:14", "throughput": 5653.34, "total_tokens": 21569904} {"current_steps": 32770, "total_steps": 33920, "loss": 0.2839, "lr": 3.5033689611000954e-08, "epoch": 19.32193396226415, "percentage": 96.61, "elapsed_time": "1:03:35", "remaining_time": "0:02:13", "throughput": 5653.32, "total_tokens": 21573008} {"current_steps": 32775, "total_steps": 33920, "loss": 0.5003, "lr": 3.473032671454768e-08, "epoch": 19.3248820754717, "percentage": 96.62, "elapsed_time": "1:03:36", "remaining_time": "0:02:13", "throughput": 5653.34, "total_tokens": 21576240} {"current_steps": 32780, "total_steps": 33920, "loss": 0.2326, "lr": 3.44282783946398e-08, "epoch": 19.327830188679247, "percentage": 96.64, "elapsed_time": "1:03:37", "remaining_time": "0:02:12", "throughput": 5653.27, "total_tokens": 21578960} {"current_steps": 32785, "total_steps": 33920, "loss": 0.2679, "lr": 3.4127544731245575e-08, "epoch": 19.33077830188679, "percentage": 96.65, "elapsed_time": "1:03:37", "remaining_time": "0:02:12", "throughput": 5653.25, "total_tokens": 21582128} {"current_steps": 32790, "total_steps": 33920, "loss": 0.2334, "lr": 3.38281258039852e-08, "epoch": 19.33372641509434, "percentage": 96.67, "elapsed_time": "1:03:38", "remaining_time": "0:02:11", "throughput": 5653.28, "total_tokens": 21585264} {"current_steps": 32795, "total_steps": 33920, "loss": 0.3433, "lr": 3.353002169213193e-08, "epoch": 19.336674528301888, "percentage": 96.68, "elapsed_time": "1:03:38", "remaining_time": "0:02:10", "throughput": 5653.34, "total_tokens": 21588688} {"current_steps": 32800, "total_steps": 33920, "loss": 0.3634, "lr": 3.32332324746093e-08, "epoch": 19.339622641509433, "percentage": 96.7, "elapsed_time": "1:03:39", "remaining_time": "0:02:10", "throughput": 5653.45, "total_tokens": 21592720} {"current_steps": 32805, "total_steps": 33920, "loss": 0.3475, "lr": 3.2937758229994455e-08, "epoch": 19.34257075471698, "percentage": 96.71, "elapsed_time": "1:03:39", "remaining_time": "0:02:09", "throughput": 5653.38, "total_tokens": 21595568} {"current_steps": 32810, "total_steps": 33920, "loss": 0.3581, "lr": 3.2643599036514815e-08, "epoch": 19.34551886792453, "percentage": 96.73, "elapsed_time": "1:03:40", "remaining_time": "0:02:09", "throughput": 5653.43, "total_tokens": 21599120} {"current_steps": 32815, "total_steps": 33920, "loss": 0.3286, "lr": 3.2350754972050316e-08, "epoch": 19.348466981132077, "percentage": 96.74, "elapsed_time": "1:03:41", "remaining_time": "0:02:08", "throughput": 5653.62, "total_tokens": 21603600} {"current_steps": 32820, "total_steps": 33920, "loss": 0.3051, "lr": 3.2059226114132815e-08, "epoch": 19.35141509433962, "percentage": 96.76, "elapsed_time": "1:03:41", "remaining_time": "0:02:08", "throughput": 5653.71, "total_tokens": 21607152} {"current_steps": 32825, "total_steps": 33920, "loss": 0.3464, "lr": 3.1769012539945575e-08, "epoch": 19.35436320754717, "percentage": 96.77, "elapsed_time": "1:03:42", "remaining_time": "0:02:07", "throughput": 5653.66, "total_tokens": 21609936} {"current_steps": 32830, "total_steps": 33920, "loss": 0.3146, "lr": 3.1480114326324364e-08, "epoch": 19.357311320754718, "percentage": 96.79, "elapsed_time": "1:03:43", "remaining_time": "0:02:06", "throughput": 5653.77, "total_tokens": 21614384} {"current_steps": 32835, "total_steps": 33920, "loss": 0.3227, "lr": 3.1192531549756325e-08, "epoch": 19.360259433962263, "percentage": 96.8, "elapsed_time": "1:03:43", "remaining_time": "0:02:06", "throughput": 5653.81, "total_tokens": 21617872} {"current_steps": 32840, "total_steps": 33920, "loss": 0.3422, "lr": 3.090626428638e-08, "epoch": 19.36320754716981, "percentage": 96.82, "elapsed_time": "1:03:44", "remaining_time": "0:02:05", "throughput": 5653.85, "total_tokens": 21621328} {"current_steps": 32845, "total_steps": 33920, "loss": 0.3451, "lr": 3.062131261198531e-08, "epoch": 19.36615566037736, "percentage": 96.83, "elapsed_time": "1:03:44", "remaining_time": "0:02:05", "throughput": 5653.86, "total_tokens": 21624432} {"current_steps": 32850, "total_steps": 33920, "loss": 0.2737, "lr": 3.033767660201525e-08, "epoch": 19.369103773584907, "percentage": 96.85, "elapsed_time": "1:03:45", "remaining_time": "0:02:04", "throughput": 5653.8, "total_tokens": 21627248} {"current_steps": 32855, "total_steps": 33920, "loss": 0.2994, "lr": 3.005535633156309e-08, "epoch": 19.372051886792452, "percentage": 96.86, "elapsed_time": "1:03:45", "remaining_time": "0:02:04", "throughput": 5653.76, "total_tokens": 21630064} {"current_steps": 32860, "total_steps": 33920, "loss": 0.2403, "lr": 2.977435187537514e-08, "epoch": 19.375, "percentage": 96.88, "elapsed_time": "1:03:46", "remaining_time": "0:02:03", "throughput": 5653.78, "total_tokens": 21633264} {"current_steps": 32865, "total_steps": 33920, "loss": 0.2793, "lr": 2.949466330784745e-08, "epoch": 19.377948113207548, "percentage": 96.89, "elapsed_time": "1:03:46", "remaining_time": "0:02:02", "throughput": 5653.84, "total_tokens": 21636656} {"current_steps": 32870, "total_steps": 33920, "loss": 0.2044, "lr": 2.921629070302967e-08, "epoch": 19.380896226415093, "percentage": 96.9, "elapsed_time": "1:03:47", "remaining_time": "0:02:02", "throughput": 5654.01, "total_tokens": 21640752} {"current_steps": 32875, "total_steps": 33920, "loss": 0.2555, "lr": 2.893923413462174e-08, "epoch": 19.38384433962264, "percentage": 96.92, "elapsed_time": "1:03:48", "remaining_time": "0:02:01", "throughput": 5654.05, "total_tokens": 21644144} {"current_steps": 32880, "total_steps": 33920, "loss": 0.3363, "lr": 2.866349367597554e-08, "epoch": 19.38679245283019, "percentage": 96.93, "elapsed_time": "1:03:48", "remaining_time": "0:02:01", "throughput": 5654.01, "total_tokens": 21646928} {"current_steps": 32885, "total_steps": 33920, "loss": 0.3627, "lr": 2.8389069400094893e-08, "epoch": 19.389740566037737, "percentage": 96.95, "elapsed_time": "1:03:49", "remaining_time": "0:02:00", "throughput": 5653.85, "total_tokens": 21649296} {"current_steps": 32890, "total_steps": 33920, "loss": 0.1841, "lr": 2.811596137963446e-08, "epoch": 19.392688679245282, "percentage": 96.96, "elapsed_time": "1:03:49", "remaining_time": "0:01:59", "throughput": 5653.77, "total_tokens": 21651984} {"current_steps": 32895, "total_steps": 33920, "loss": 0.4163, "lr": 2.7844169686900844e-08, "epoch": 19.39563679245283, "percentage": 96.98, "elapsed_time": "1:03:50", "remaining_time": "0:01:59", "throughput": 5653.77, "total_tokens": 21655120} {"current_steps": 32900, "total_steps": 33920, "loss": 0.2757, "lr": 2.7573694393852047e-08, "epoch": 19.39858490566038, "percentage": 96.99, "elapsed_time": "1:03:50", "remaining_time": "0:01:58", "throughput": 5653.7, "total_tokens": 21658224} {"current_steps": 32905, "total_steps": 33920, "loss": 0.2021, "lr": 2.7304535572098e-08, "epoch": 19.401533018867923, "percentage": 97.01, "elapsed_time": "1:03:51", "remaining_time": "0:01:58", "throughput": 5653.73, "total_tokens": 21661456} {"current_steps": 32910, "total_steps": 33920, "loss": 0.3331, "lr": 2.703669329289893e-08, "epoch": 19.40448113207547, "percentage": 97.02, "elapsed_time": "1:03:51", "remaining_time": "0:01:57", "throughput": 5653.69, "total_tokens": 21664272} {"current_steps": 32915, "total_steps": 33920, "loss": 0.2606, "lr": 2.6770167627167554e-08, "epoch": 19.40742924528302, "percentage": 97.04, "elapsed_time": "1:03:52", "remaining_time": "0:01:57", "throughput": 5653.65, "total_tokens": 21667088} {"current_steps": 32920, "total_steps": 33920, "loss": 0.4221, "lr": 2.6504958645467426e-08, "epoch": 19.410377358490567, "percentage": 97.05, "elapsed_time": "1:03:52", "remaining_time": "0:01:56", "throughput": 5653.54, "total_tokens": 21669744} {"current_steps": 32925, "total_steps": 33920, "loss": 0.3385, "lr": 2.6241066418014605e-08, "epoch": 19.413325471698112, "percentage": 97.07, "elapsed_time": "1:03:53", "remaining_time": "0:01:55", "throughput": 5653.55, "total_tokens": 21673008} {"current_steps": 32930, "total_steps": 33920, "loss": 0.2689, "lr": 2.5978491014674866e-08, "epoch": 19.41627358490566, "percentage": 97.08, "elapsed_time": "1:03:54", "remaining_time": "0:01:55", "throughput": 5653.52, "total_tokens": 21676080} {"current_steps": 32935, "total_steps": 33920, "loss": 0.2322, "lr": 2.571723250496705e-08, "epoch": 19.41922169811321, "percentage": 97.1, "elapsed_time": "1:03:54", "remaining_time": "0:01:54", "throughput": 5653.49, "total_tokens": 21679216} {"current_steps": 32940, "total_steps": 33920, "loss": 0.2334, "lr": 2.5457290958059155e-08, "epoch": 19.422169811320753, "percentage": 97.11, "elapsed_time": "1:03:55", "remaining_time": "0:01:54", "throughput": 5653.45, "total_tokens": 21682064} {"current_steps": 32945, "total_steps": 33920, "loss": 0.3414, "lr": 2.51986664427728e-08, "epoch": 19.4251179245283, "percentage": 97.13, "elapsed_time": "1:03:55", "remaining_time": "0:01:53", "throughput": 5653.41, "total_tokens": 21684912} {"current_steps": 32950, "total_steps": 33920, "loss": 0.2539, "lr": 2.4941359027579883e-08, "epoch": 19.42806603773585, "percentage": 97.14, "elapsed_time": "1:03:56", "remaining_time": "0:01:52", "throughput": 5653.43, "total_tokens": 21687920} {"current_steps": 32955, "total_steps": 33920, "loss": 0.2879, "lr": 2.468536878060368e-08, "epoch": 19.431014150943398, "percentage": 97.16, "elapsed_time": "1:03:56", "remaining_time": "0:01:52", "throughput": 5653.41, "total_tokens": 21690864} {"current_steps": 32960, "total_steps": 33920, "loss": 0.2686, "lr": 2.443069576961832e-08, "epoch": 19.433962264150942, "percentage": 97.17, "elapsed_time": "1:03:57", "remaining_time": "0:01:51", "throughput": 5653.36, "total_tokens": 21693648} {"current_steps": 32965, "total_steps": 33920, "loss": 0.3295, "lr": 2.4177340062049304e-08, "epoch": 19.43691037735849, "percentage": 97.18, "elapsed_time": "1:03:57", "remaining_time": "0:01:51", "throughput": 5653.38, "total_tokens": 21696976} {"current_steps": 32970, "total_steps": 33920, "loss": 0.2582, "lr": 2.3925301724974647e-08, "epoch": 19.43985849056604, "percentage": 97.2, "elapsed_time": "1:03:58", "remaining_time": "0:01:50", "throughput": 5653.46, "total_tokens": 21700912} {"current_steps": 32975, "total_steps": 33920, "loss": 0.1738, "lr": 2.367458082512153e-08, "epoch": 19.442806603773583, "percentage": 97.21, "elapsed_time": "1:03:59", "remaining_time": "0:01:50", "throughput": 5653.45, "total_tokens": 21704112} {"current_steps": 32980, "total_steps": 33920, "loss": 0.2444, "lr": 2.3425177428870737e-08, "epoch": 19.44575471698113, "percentage": 97.23, "elapsed_time": "1:03:59", "remaining_time": "0:01:49", "throughput": 5653.59, "total_tokens": 21708176} {"current_steps": 32985, "total_steps": 33920, "loss": 0.2761, "lr": 2.3177091602251677e-08, "epoch": 19.44870283018868, "percentage": 97.24, "elapsed_time": "1:04:00", "remaining_time": "0:01:48", "throughput": 5653.64, "total_tokens": 21711344} {"current_steps": 32990, "total_steps": 33920, "loss": 0.3634, "lr": 2.2930323410946254e-08, "epoch": 19.451650943396228, "percentage": 97.26, "elapsed_time": "1:04:00", "remaining_time": "0:01:48", "throughput": 5653.58, "total_tokens": 21714096} {"current_steps": 32995, "total_steps": 33920, "loss": 0.2577, "lr": 2.2684872920287758e-08, "epoch": 19.454599056603772, "percentage": 97.27, "elapsed_time": "1:04:01", "remaining_time": "0:01:47", "throughput": 5653.66, "total_tokens": 21717744} {"current_steps": 33000, "total_steps": 33920, "loss": 0.4002, "lr": 2.2440740195260323e-08, "epoch": 19.45754716981132, "percentage": 97.29, "elapsed_time": "1:04:01", "remaining_time": "0:01:47", "throughput": 5653.64, "total_tokens": 21720752} {"current_steps": 33005, "total_steps": 33920, "loss": 0.3104, "lr": 2.219792530049891e-08, "epoch": 19.46049528301887, "percentage": 97.3, "elapsed_time": "1:04:02", "remaining_time": "0:01:46", "throughput": 5653.74, "total_tokens": 21724784} {"current_steps": 33010, "total_steps": 33920, "loss": 0.2844, "lr": 2.1956428300290434e-08, "epoch": 19.463443396226417, "percentage": 97.32, "elapsed_time": "1:04:03", "remaining_time": "0:01:45", "throughput": 5653.71, "total_tokens": 21727728} {"current_steps": 33015, "total_steps": 33920, "loss": 0.3298, "lr": 2.1716249258570966e-08, "epoch": 19.46639150943396, "percentage": 97.33, "elapsed_time": "1:04:03", "remaining_time": "0:01:45", "throughput": 5653.7, "total_tokens": 21730960} {"current_steps": 33020, "total_steps": 33920, "loss": 0.2423, "lr": 2.1477388238930196e-08, "epoch": 19.46933962264151, "percentage": 97.35, "elapsed_time": "1:04:04", "remaining_time": "0:01:44", "throughput": 5653.77, "total_tokens": 21734480} {"current_steps": 33025, "total_steps": 33920, "loss": 0.2789, "lr": 2.1239845304606988e-08, "epoch": 19.472287735849058, "percentage": 97.36, "elapsed_time": "1:04:04", "remaining_time": "0:01:44", "throughput": 5653.7, "total_tokens": 21737392} {"current_steps": 33030, "total_steps": 33920, "loss": 0.3375, "lr": 2.100362051849214e-08, "epoch": 19.475235849056602, "percentage": 97.38, "elapsed_time": "1:04:05", "remaining_time": "0:01:43", "throughput": 5653.79, "total_tokens": 21741424} {"current_steps": 33035, "total_steps": 33920, "loss": 0.3623, "lr": 2.076871394312674e-08, "epoch": 19.47818396226415, "percentage": 97.39, "elapsed_time": "1:04:05", "remaining_time": "0:01:43", "throughput": 5653.82, "total_tokens": 21744560} {"current_steps": 33040, "total_steps": 33920, "loss": 0.3243, "lr": 2.0535125640703813e-08, "epoch": 19.4811320754717, "percentage": 97.41, "elapsed_time": "1:04:06", "remaining_time": "0:01:42", "throughput": 5653.76, "total_tokens": 21747568} {"current_steps": 33045, "total_steps": 33920, "loss": 0.2068, "lr": 2.0302855673066667e-08, "epoch": 19.484080188679247, "percentage": 97.42, "elapsed_time": "1:04:07", "remaining_time": "0:01:41", "throughput": 5653.69, "total_tokens": 21750224} {"current_steps": 33050, "total_steps": 33920, "loss": 0.2446, "lr": 2.0071904101710004e-08, "epoch": 19.48702830188679, "percentage": 97.44, "elapsed_time": "1:04:08", "remaining_time": "0:01:41", "throughput": 5653.88, "total_tokens": 21756432} {"current_steps": 33055, "total_steps": 33920, "loss": 0.2636, "lr": 1.98422709877788e-08, "epoch": 19.48997641509434, "percentage": 97.45, "elapsed_time": "1:04:08", "remaining_time": "0:01:40", "throughput": 5653.9, "total_tokens": 21759568} {"current_steps": 33060, "total_steps": 33920, "loss": 0.3139, "lr": 1.961395639206942e-08, "epoch": 19.492924528301888, "percentage": 97.46, "elapsed_time": "1:04:09", "remaining_time": "0:01:40", "throughput": 5653.85, "total_tokens": 21762640} {"current_steps": 33065, "total_steps": 33920, "loss": 0.2707, "lr": 1.9386960375029628e-08, "epoch": 19.495872641509433, "percentage": 97.48, "elapsed_time": "1:04:09", "remaining_time": "0:01:39", "throughput": 5653.84, "total_tokens": 21765616} {"current_steps": 33070, "total_steps": 33920, "loss": 0.2647, "lr": 1.9161282996757458e-08, "epoch": 19.49882075471698, "percentage": 97.49, "elapsed_time": "1:04:10", "remaining_time": "0:01:38", "throughput": 5653.93, "total_tokens": 21769552} {"current_steps": 33075, "total_steps": 33920, "loss": 0.308, "lr": 1.8936924317001225e-08, "epoch": 19.50176886792453, "percentage": 97.51, "elapsed_time": "1:04:10", "remaining_time": "0:01:38", "throughput": 5654.02, "total_tokens": 21772880} {"current_steps": 33080, "total_steps": 33920, "loss": 0.2911, "lr": 1.8713884395162308e-08, "epoch": 19.504716981132077, "percentage": 97.52, "elapsed_time": "1:04:11", "remaining_time": "0:01:37", "throughput": 5654.06, "total_tokens": 21776208} {"current_steps": 33085, "total_steps": 33920, "loss": 0.216, "lr": 1.8492163290290132e-08, "epoch": 19.50766509433962, "percentage": 97.54, "elapsed_time": "1:04:11", "remaining_time": "0:01:37", "throughput": 5653.92, "total_tokens": 21778608} {"current_steps": 33090, "total_steps": 33920, "loss": 0.2731, "lr": 1.827176106108719e-08, "epoch": 19.51061320754717, "percentage": 97.55, "elapsed_time": "1:04:12", "remaining_time": "0:01:36", "throughput": 5653.82, "total_tokens": 21781264} {"current_steps": 33095, "total_steps": 33920, "loss": 0.3999, "lr": 1.8052677765905137e-08, "epoch": 19.513561320754718, "percentage": 97.57, "elapsed_time": "1:04:13", "remaining_time": "0:01:36", "throughput": 5653.79, "total_tokens": 21784208} {"current_steps": 33100, "total_steps": 33920, "loss": 0.3224, "lr": 1.783491346274757e-08, "epoch": 19.516509433962263, "percentage": 97.58, "elapsed_time": "1:04:13", "remaining_time": "0:01:35", "throughput": 5653.73, "total_tokens": 21787088} {"current_steps": 33105, "total_steps": 33920, "loss": 0.2853, "lr": 1.7618468209268936e-08, "epoch": 19.51945754716981, "percentage": 97.6, "elapsed_time": "1:04:14", "remaining_time": "0:01:34", "throughput": 5653.84, "total_tokens": 21790768} {"current_steps": 33110, "total_steps": 33920, "loss": 0.2907, "lr": 1.7403342062773943e-08, "epoch": 19.52240566037736, "percentage": 97.61, "elapsed_time": "1:04:14", "remaining_time": "0:01:34", "throughput": 5653.78, "total_tokens": 21793488} {"current_steps": 33115, "total_steps": 33920, "loss": 0.3645, "lr": 1.718953508021759e-08, "epoch": 19.525353773584907, "percentage": 97.63, "elapsed_time": "1:04:15", "remaining_time": "0:01:33", "throughput": 5653.82, "total_tokens": 21796656} {"current_steps": 33120, "total_steps": 33920, "loss": 0.2268, "lr": 1.6977047318206262e-08, "epoch": 19.528301886792452, "percentage": 97.64, "elapsed_time": "1:04:15", "remaining_time": "0:01:33", "throughput": 5653.78, "total_tokens": 21799600} {"current_steps": 33125, "total_steps": 33920, "loss": 0.3875, "lr": 1.676587883299774e-08, "epoch": 19.53125, "percentage": 97.66, "elapsed_time": "1:04:16", "remaining_time": "0:01:32", "throughput": 5653.83, "total_tokens": 21802992} {"current_steps": 33130, "total_steps": 33920, "loss": 0.2487, "lr": 1.655602968049952e-08, "epoch": 19.534198113207548, "percentage": 97.67, "elapsed_time": "1:04:16", "remaining_time": "0:01:31", "throughput": 5653.75, "total_tokens": 21805552} {"current_steps": 33135, "total_steps": 33920, "loss": 0.5729, "lr": 1.634749991626938e-08, "epoch": 19.537146226415093, "percentage": 97.69, "elapsed_time": "1:04:17", "remaining_time": "0:01:31", "throughput": 5653.59, "total_tokens": 21807856} {"current_steps": 33140, "total_steps": 33920, "loss": 0.2389, "lr": 1.6140289595517056e-08, "epoch": 19.54009433962264, "percentage": 97.7, "elapsed_time": "1:04:17", "remaining_time": "0:01:30", "throughput": 5653.57, "total_tokens": 21810928} {"current_steps": 33145, "total_steps": 33920, "loss": 0.278, "lr": 1.5934398773102545e-08, "epoch": 19.54304245283019, "percentage": 97.72, "elapsed_time": "1:04:18", "remaining_time": "0:01:30", "throughput": 5653.43, "total_tokens": 21813296} {"current_steps": 33150, "total_steps": 33920, "loss": 0.2338, "lr": 1.5729827503536133e-08, "epoch": 19.545990566037737, "percentage": 97.73, "elapsed_time": "1:04:19", "remaining_time": "0:01:29", "throughput": 5653.47, "total_tokens": 21817264} {"current_steps": 33155, "total_steps": 33920, "loss": 0.4554, "lr": 1.5526575840978942e-08, "epoch": 19.548938679245282, "percentage": 97.74, "elapsed_time": "1:04:19", "remaining_time": "0:01:29", "throughput": 5653.4, "total_tokens": 21820048} {"current_steps": 33160, "total_steps": 33920, "loss": 0.2952, "lr": 1.532464383924237e-08, "epoch": 19.55188679245283, "percentage": 97.76, "elapsed_time": "1:04:20", "remaining_time": "0:01:28", "throughput": 5653.5, "total_tokens": 21824112} {"current_steps": 33165, "total_steps": 33920, "loss": 0.3902, "lr": 1.5124031551789208e-08, "epoch": 19.55483490566038, "percentage": 97.77, "elapsed_time": "1:04:20", "remaining_time": "0:01:27", "throughput": 5653.65, "total_tokens": 21828048} {"current_steps": 33170, "total_steps": 33920, "loss": 0.4169, "lr": 1.4924739031732527e-08, "epoch": 19.557783018867923, "percentage": 97.79, "elapsed_time": "1:04:21", "remaining_time": "0:01:27", "throughput": 5653.64, "total_tokens": 21830928} {"current_steps": 33175, "total_steps": 33920, "loss": 0.3696, "lr": 1.4726766331835118e-08, "epoch": 19.56073113207547, "percentage": 97.8, "elapsed_time": "1:04:22", "remaining_time": "0:01:26", "throughput": 5653.84, "total_tokens": 21835792} {"current_steps": 33180, "total_steps": 33920, "loss": 0.2224, "lr": 1.4530113504512278e-08, "epoch": 19.56367924528302, "percentage": 97.82, "elapsed_time": "1:04:22", "remaining_time": "0:01:26", "throughput": 5653.76, "total_tokens": 21838544} {"current_steps": 33185, "total_steps": 33920, "loss": 0.216, "lr": 1.4334780601827914e-08, "epoch": 19.566627358490567, "percentage": 97.83, "elapsed_time": "1:04:23", "remaining_time": "0:01:25", "throughput": 5653.84, "total_tokens": 21842096} {"current_steps": 33190, "total_steps": 33920, "loss": 0.3483, "lr": 1.4140767675497325e-08, "epoch": 19.569575471698112, "percentage": 97.85, "elapsed_time": "1:04:23", "remaining_time": "0:01:24", "throughput": 5653.88, "total_tokens": 21845776} {"current_steps": 33195, "total_steps": 33920, "loss": 0.3862, "lr": 1.394807477688609e-08, "epoch": 19.57252358490566, "percentage": 97.86, "elapsed_time": "1:04:24", "remaining_time": "0:01:24", "throughput": 5653.97, "total_tokens": 21849328} {"current_steps": 33200, "total_steps": 33920, "loss": 0.2353, "lr": 1.3756701957011177e-08, "epoch": 19.57547169811321, "percentage": 97.88, "elapsed_time": "1:04:24", "remaining_time": "0:01:23", "throughput": 5654.0, "total_tokens": 21852464} {"current_steps": 33205, "total_steps": 33920, "loss": 0.2538, "lr": 1.3566649266538723e-08, "epoch": 19.578419811320753, "percentage": 97.89, "elapsed_time": "1:04:25", "remaining_time": "0:01:23", "throughput": 5653.91, "total_tokens": 21855056} {"current_steps": 33210, "total_steps": 33920, "loss": 0.4268, "lr": 1.3377916755786257e-08, "epoch": 19.5813679245283, "percentage": 97.91, "elapsed_time": "1:04:26", "remaining_time": "0:01:22", "throughput": 5653.95, "total_tokens": 21858512} {"current_steps": 33215, "total_steps": 33920, "loss": 0.3171, "lr": 1.3190504474721588e-08, "epoch": 19.58431603773585, "percentage": 97.92, "elapsed_time": "1:04:26", "remaining_time": "0:01:22", "throughput": 5654.02, "total_tokens": 21862128} {"current_steps": 33220, "total_steps": 33920, "loss": 0.2404, "lr": 1.3004412472962802e-08, "epoch": 19.587264150943398, "percentage": 97.94, "elapsed_time": "1:04:27", "remaining_time": "0:01:21", "throughput": 5654.0, "total_tokens": 21864944} {"current_steps": 33225, "total_steps": 33920, "loss": 0.2404, "lr": 1.2819640799778266e-08, "epoch": 19.590212264150942, "percentage": 97.95, "elapsed_time": "1:04:27", "remaining_time": "0:01:20", "throughput": 5653.96, "total_tokens": 21867952} {"current_steps": 33230, "total_steps": 33920, "loss": 0.3266, "lr": 1.2636189504087737e-08, "epoch": 19.59316037735849, "percentage": 97.97, "elapsed_time": "1:04:28", "remaining_time": "0:01:20", "throughput": 5653.84, "total_tokens": 21870352} {"current_steps": 33235, "total_steps": 33920, "loss": 0.3808, "lr": 1.2454058634460142e-08, "epoch": 19.59610849056604, "percentage": 97.98, "elapsed_time": "1:04:28", "remaining_time": "0:01:19", "throughput": 5653.87, "total_tokens": 21873488} {"current_steps": 33240, "total_steps": 33920, "loss": 0.2503, "lr": 1.2273248239115798e-08, "epoch": 19.599056603773583, "percentage": 98.0, "elapsed_time": "1:04:29", "remaining_time": "0:01:19", "throughput": 5653.81, "total_tokens": 21876208} {"current_steps": 33245, "total_steps": 33920, "loss": 0.3629, "lr": 1.2093758365924746e-08, "epoch": 19.60200471698113, "percentage": 98.01, "elapsed_time": "1:04:29", "remaining_time": "0:01:18", "throughput": 5653.83, "total_tokens": 21879632} {"current_steps": 33250, "total_steps": 33920, "loss": 0.5949, "lr": 1.1915589062408417e-08, "epoch": 19.60495283018868, "percentage": 98.02, "elapsed_time": "1:04:30", "remaining_time": "0:01:17", "throughput": 5653.81, "total_tokens": 21882576} {"current_steps": 33255, "total_steps": 33920, "loss": 0.2428, "lr": 1.1738740375736301e-08, "epoch": 19.607900943396228, "percentage": 98.04, "elapsed_time": "1:04:30", "remaining_time": "0:01:17", "throughput": 5653.87, "total_tokens": 21885936} {"current_steps": 33260, "total_steps": 33920, "loss": 0.2147, "lr": 1.15632123527315e-08, "epoch": 19.610849056603772, "percentage": 98.05, "elapsed_time": "1:04:31", "remaining_time": "0:01:16", "throughput": 5653.71, "total_tokens": 21888400} {"current_steps": 33265, "total_steps": 33920, "loss": 0.2427, "lr": 1.1389005039865176e-08, "epoch": 19.61379716981132, "percentage": 98.07, "elapsed_time": "1:04:32", "remaining_time": "0:01:16", "throughput": 5653.59, "total_tokens": 21890960} {"current_steps": 33270, "total_steps": 33920, "loss": 0.2302, "lr": 1.1216118483259875e-08, "epoch": 19.61674528301887, "percentage": 98.08, "elapsed_time": "1:04:32", "remaining_time": "0:01:15", "throughput": 5653.52, "total_tokens": 21893712} {"current_steps": 33275, "total_steps": 33920, "loss": 0.312, "lr": 1.1044552728687319e-08, "epoch": 19.619693396226417, "percentage": 98.1, "elapsed_time": "1:04:33", "remaining_time": "0:01:15", "throughput": 5653.4, "total_tokens": 21896304} {"current_steps": 33280, "total_steps": 33920, "loss": 0.1781, "lr": 1.0874307821570618e-08, "epoch": 19.62264150943396, "percentage": 98.11, "elapsed_time": "1:04:33", "remaining_time": "0:01:14", "throughput": 5653.45, "total_tokens": 21899504} {"current_steps": 33285, "total_steps": 33920, "loss": 0.2039, "lr": 1.0705383806982606e-08, "epoch": 19.62558962264151, "percentage": 98.13, "elapsed_time": "1:04:34", "remaining_time": "0:01:13", "throughput": 5653.4, "total_tokens": 21902448} {"current_steps": 33290, "total_steps": 33920, "loss": 0.3002, "lr": 1.0537780729646952e-08, "epoch": 19.628537735849058, "percentage": 98.14, "elapsed_time": "1:04:34", "remaining_time": "0:01:13", "throughput": 5653.35, "total_tokens": 21905200} {"current_steps": 33295, "total_steps": 33920, "loss": 0.2632, "lr": 1.0371498633937605e-08, "epoch": 19.631485849056602, "percentage": 98.16, "elapsed_time": "1:04:35", "remaining_time": "0:01:12", "throughput": 5653.38, "total_tokens": 21908432} {"current_steps": 33300, "total_steps": 33920, "loss": 0.232, "lr": 1.0206537563877683e-08, "epoch": 19.63443396226415, "percentage": 98.17, "elapsed_time": "1:04:35", "remaining_time": "0:01:12", "throughput": 5653.49, "total_tokens": 21912304} {"current_steps": 33305, "total_steps": 33920, "loss": 0.3567, "lr": 1.0042897563141695e-08, "epoch": 19.6373820754717, "percentage": 98.19, "elapsed_time": "1:04:36", "remaining_time": "0:01:11", "throughput": 5653.53, "total_tokens": 21915408} {"current_steps": 33310, "total_steps": 33920, "loss": 0.3008, "lr": 9.88057867505443e-09, "epoch": 19.640330188679247, "percentage": 98.2, "elapsed_time": "1:04:36", "remaining_time": "0:01:10", "throughput": 5653.48, "total_tokens": 21918288} {"current_steps": 33315, "total_steps": 33920, "loss": 0.3639, "lr": 9.7195809425904e-09, "epoch": 19.64327830188679, "percentage": 98.22, "elapsed_time": "1:04:37", "remaining_time": "0:01:10", "throughput": 5653.58, "total_tokens": 21922480} {"current_steps": 33320, "total_steps": 33920, "loss": 0.3291, "lr": 9.559904408373844e-09, "epoch": 19.64622641509434, "percentage": 98.23, "elapsed_time": "1:04:38", "remaining_time": "0:01:09", "throughput": 5653.52, "total_tokens": 21925136} {"current_steps": 33325, "total_steps": 33920, "loss": 0.2658, "lr": 9.401549114680387e-09, "epoch": 19.649174528301888, "percentage": 98.25, "elapsed_time": "1:04:38", "remaining_time": "0:01:09", "throughput": 5653.66, "total_tokens": 21929296} {"current_steps": 33330, "total_steps": 33920, "loss": 0.4028, "lr": 9.244515103434826e-09, "epoch": 19.652122641509433, "percentage": 98.26, "elapsed_time": "1:04:39", "remaining_time": "0:01:08", "throughput": 5653.55, "total_tokens": 21932048} {"current_steps": 33335, "total_steps": 33920, "loss": 0.3923, "lr": 9.08880241621335e-09, "epoch": 19.65507075471698, "percentage": 98.28, "elapsed_time": "1:04:40", "remaining_time": "0:01:08", "throughput": 5653.93, "total_tokens": 21941648} {"current_steps": 33340, "total_steps": 33920, "loss": 0.2242, "lr": 8.934411094240758e-09, "epoch": 19.65801886792453, "percentage": 98.29, "elapsed_time": "1:04:41", "remaining_time": "0:01:07", "throughput": 5654.01, "total_tokens": 21945680} {"current_steps": 33345, "total_steps": 33920, "loss": 0.2329, "lr": 8.781341178393244e-09, "epoch": 19.660966981132077, "percentage": 98.3, "elapsed_time": "1:04:42", "remaining_time": "0:01:06", "throughput": 5654.2, "total_tokens": 21949936} {"current_steps": 33350, "total_steps": 33920, "loss": 0.2693, "lr": 8.629592709196167e-09, "epoch": 19.66391509433962, "percentage": 98.32, "elapsed_time": "1:04:42", "remaining_time": "0:01:06", "throughput": 5654.19, "total_tokens": 21952944} {"current_steps": 33355, "total_steps": 33920, "loss": 0.2872, "lr": 8.479165726826277e-09, "epoch": 19.66686320754717, "percentage": 98.33, "elapsed_time": "1:04:43", "remaining_time": "0:01:05", "throughput": 5654.13, "total_tokens": 21955632} {"current_steps": 33360, "total_steps": 33920, "loss": 0.2962, "lr": 8.330060271109496e-09, "epoch": 19.669811320754718, "percentage": 98.35, "elapsed_time": "1:04:43", "remaining_time": "0:01:05", "throughput": 5654.22, "total_tokens": 21959088} {"current_steps": 33365, "total_steps": 33920, "loss": 0.2854, "lr": 8.18227638152258e-09, "epoch": 19.672759433962263, "percentage": 98.36, "elapsed_time": "1:04:44", "remaining_time": "0:01:04", "throughput": 5654.29, "total_tokens": 21962544} {"current_steps": 33370, "total_steps": 33920, "loss": 0.2024, "lr": 8.035814097191452e-09, "epoch": 19.67570754716981, "percentage": 98.38, "elapsed_time": "1:04:44", "remaining_time": "0:01:04", "throughput": 5654.29, "total_tokens": 21965808} {"current_steps": 33375, "total_steps": 33920, "loss": 0.302, "lr": 7.890673456892317e-09, "epoch": 19.67865566037736, "percentage": 98.39, "elapsed_time": "1:04:45", "remaining_time": "0:01:03", "throughput": 5654.32, "total_tokens": 21969232} {"current_steps": 33380, "total_steps": 33920, "loss": 0.3199, "lr": 7.746854499052215e-09, "epoch": 19.681603773584907, "percentage": 98.41, "elapsed_time": "1:04:45", "remaining_time": "0:01:02", "throughput": 5654.44, "total_tokens": 21973008} {"current_steps": 33385, "total_steps": 33920, "loss": 0.3323, "lr": 7.604357261747907e-09, "epoch": 19.684551886792452, "percentage": 98.42, "elapsed_time": "1:04:46", "remaining_time": "0:01:02", "throughput": 5654.39, "total_tokens": 21975888} {"current_steps": 33390, "total_steps": 33920, "loss": 0.2802, "lr": 7.463181782705886e-09, "epoch": 19.6875, "percentage": 98.44, "elapsed_time": "1:04:47", "remaining_time": "0:01:01", "throughput": 5654.38, "total_tokens": 21978960} {"current_steps": 33395, "total_steps": 33920, "loss": 0.5767, "lr": 7.3233280993034726e-09, "epoch": 19.690448113207548, "percentage": 98.45, "elapsed_time": "1:04:47", "remaining_time": "0:01:01", "throughput": 5654.38, "total_tokens": 21982096} {"current_steps": 33400, "total_steps": 33920, "loss": 0.2984, "lr": 7.184796248567161e-09, "epoch": 19.693396226415093, "percentage": 98.47, "elapsed_time": "1:04:48", "remaining_time": "0:01:00", "throughput": 5654.56, "total_tokens": 21986480} {"current_steps": 33405, "total_steps": 33920, "loss": 0.1844, "lr": 7.047586267173723e-09, "epoch": 19.69634433962264, "percentage": 98.48, "elapsed_time": "1:04:48", "remaining_time": "0:00:59", "throughput": 5654.52, "total_tokens": 21989328} {"current_steps": 33410, "total_steps": 33920, "loss": 0.3878, "lr": 6.9116981914502114e-09, "epoch": 19.69929245283019, "percentage": 98.5, "elapsed_time": "1:04:49", "remaining_time": "0:00:59", "throughput": 5654.64, "total_tokens": 21993840} {"current_steps": 33415, "total_steps": 33920, "loss": 0.2825, "lr": 6.7771320573734036e-09, "epoch": 19.702240566037737, "percentage": 98.51, "elapsed_time": "1:04:50", "remaining_time": "0:00:58", "throughput": 5654.63, "total_tokens": 21996944} {"current_steps": 33420, "total_steps": 33920, "loss": 0.2576, "lr": 6.6438879005709114e-09, "epoch": 19.705188679245282, "percentage": 98.53, "elapsed_time": "1:04:50", "remaining_time": "0:00:58", "throughput": 5654.71, "total_tokens": 22001392} {"current_steps": 33425, "total_steps": 33920, "loss": 0.3424, "lr": 6.511965756318961e-09, "epoch": 19.70813679245283, "percentage": 98.54, "elapsed_time": "1:04:51", "remaining_time": "0:00:57", "throughput": 5654.62, "total_tokens": 22004336} {"current_steps": 33430, "total_steps": 33920, "loss": 0.3734, "lr": 6.381365659545169e-09, "epoch": 19.71108490566038, "percentage": 98.56, "elapsed_time": "1:04:51", "remaining_time": "0:00:57", "throughput": 5654.48, "total_tokens": 22006768} {"current_steps": 33435, "total_steps": 33920, "loss": 0.3722, "lr": 6.252087644825766e-09, "epoch": 19.714033018867923, "percentage": 98.57, "elapsed_time": "1:04:52", "remaining_time": "0:00:56", "throughput": 5654.51, "total_tokens": 22010160} {"current_steps": 33440, "total_steps": 33920, "loss": 0.2388, "lr": 6.124131746388373e-09, "epoch": 19.71698113207547, "percentage": 98.58, "elapsed_time": "1:04:53", "remaining_time": "0:00:55", "throughput": 5654.59, "total_tokens": 22013648} {"current_steps": 33445, "total_steps": 33920, "loss": 0.2748, "lr": 5.997497998109225e-09, "epoch": 19.71992924528302, "percentage": 98.6, "elapsed_time": "1:04:53", "remaining_time": "0:00:55", "throughput": 5654.51, "total_tokens": 22016240} {"current_steps": 33450, "total_steps": 33920, "loss": 0.2211, "lr": 5.8721864335153925e-09, "epoch": 19.722877358490567, "percentage": 98.61, "elapsed_time": "1:04:54", "remaining_time": "0:00:54", "throughput": 5654.53, "total_tokens": 22019376} {"current_steps": 33455, "total_steps": 33920, "loss": 0.2945, "lr": 5.748197085784224e-09, "epoch": 19.725825471698112, "percentage": 98.63, "elapsed_time": "1:04:54", "remaining_time": "0:00:54", "throughput": 5654.53, "total_tokens": 22022416} {"current_steps": 33460, "total_steps": 33920, "loss": 0.216, "lr": 5.62552998774113e-09, "epoch": 19.72877358490566, "percentage": 98.64, "elapsed_time": "1:04:55", "remaining_time": "0:00:53", "throughput": 5654.58, "total_tokens": 22026064} {"current_steps": 33465, "total_steps": 33920, "loss": 0.3391, "lr": 5.504185171864018e-09, "epoch": 19.73172169811321, "percentage": 98.66, "elapsed_time": "1:04:55", "remaining_time": "0:00:52", "throughput": 5654.55, "total_tokens": 22028816} {"current_steps": 33470, "total_steps": 33920, "loss": 0.3647, "lr": 5.384162670278858e-09, "epoch": 19.734669811320753, "percentage": 98.67, "elapsed_time": "1:04:56", "remaining_time": "0:00:52", "throughput": 5654.59, "total_tokens": 22032432} {"current_steps": 33475, "total_steps": 33920, "loss": 0.3746, "lr": 5.265462514762454e-09, "epoch": 19.7376179245283, "percentage": 98.69, "elapsed_time": "1:04:57", "remaining_time": "0:00:51", "throughput": 5654.64, "total_tokens": 22036528} {"current_steps": 33480, "total_steps": 33920, "loss": 0.3347, "lr": 5.148084736740777e-09, "epoch": 19.74056603773585, "percentage": 98.7, "elapsed_time": "1:04:57", "remaining_time": "0:00:51", "throughput": 5654.62, "total_tokens": 22039632} {"current_steps": 33485, "total_steps": 33920, "loss": 0.3137, "lr": 5.032029367290081e-09, "epoch": 19.743514150943398, "percentage": 98.72, "elapsed_time": "1:04:58", "remaining_time": "0:00:50", "throughput": 5654.57, "total_tokens": 22042672} {"current_steps": 33490, "total_steps": 33920, "loss": 0.3739, "lr": 4.917296437136898e-09, "epoch": 19.746462264150942, "percentage": 98.73, "elapsed_time": "1:04:58", "remaining_time": "0:00:50", "throughput": 5654.65, "total_tokens": 22045968} {"current_steps": 33495, "total_steps": 33920, "loss": 0.3236, "lr": 4.8038859766569305e-09, "epoch": 19.74941037735849, "percentage": 98.75, "elapsed_time": "1:04:59", "remaining_time": "0:00:49", "throughput": 5654.68, "total_tokens": 22049680} {"current_steps": 33500, "total_steps": 33920, "loss": 0.2395, "lr": 4.691798015876714e-09, "epoch": 19.75235849056604, "percentage": 98.76, "elapsed_time": "1:04:59", "remaining_time": "0:00:48", "throughput": 5654.74, "total_tokens": 22053104} {"current_steps": 33505, "total_steps": 33920, "loss": 0.2529, "lr": 4.581032584470846e-09, "epoch": 19.755306603773583, "percentage": 98.78, "elapsed_time": "1:05:00", "remaining_time": "0:00:48", "throughput": 5654.72, "total_tokens": 22056304} {"current_steps": 33510, "total_steps": 33920, "loss": 0.3302, "lr": 4.471589711766422e-09, "epoch": 19.75825471698113, "percentage": 98.79, "elapsed_time": "1:05:01", "remaining_time": "0:00:47", "throughput": 5654.83, "total_tokens": 22060144} {"current_steps": 33515, "total_steps": 33920, "loss": 0.2151, "lr": 4.363469426737487e-09, "epoch": 19.76120283018868, "percentage": 98.81, "elapsed_time": "1:05:01", "remaining_time": "0:00:47", "throughput": 5654.71, "total_tokens": 22062960} {"current_steps": 33520, "total_steps": 33920, "loss": 0.2887, "lr": 4.256671758010588e-09, "epoch": 19.764150943396228, "percentage": 98.82, "elapsed_time": "1:05:02", "remaining_time": "0:00:46", "throughput": 5654.69, "total_tokens": 22065776} {"current_steps": 33525, "total_steps": 33920, "loss": 0.2253, "lr": 4.151196733859775e-09, "epoch": 19.767099056603772, "percentage": 98.84, "elapsed_time": "1:05:02", "remaining_time": "0:00:45", "throughput": 5654.8, "total_tokens": 22070000} {"current_steps": 33530, "total_steps": 33920, "loss": 0.24, "lr": 4.047044382211041e-09, "epoch": 19.77004716981132, "percentage": 98.85, "elapsed_time": "1:05:03", "remaining_time": "0:00:45", "throughput": 5654.84, "total_tokens": 22073264} {"current_steps": 33535, "total_steps": 33920, "loss": 0.2669, "lr": 3.94421473063844e-09, "epoch": 19.77299528301887, "percentage": 98.86, "elapsed_time": "1:05:04", "remaining_time": "0:00:44", "throughput": 5654.81, "total_tokens": 22076368} {"current_steps": 33540, "total_steps": 33920, "loss": 0.4777, "lr": 3.842707806366863e-09, "epoch": 19.775943396226417, "percentage": 98.88, "elapsed_time": "1:05:04", "remaining_time": "0:00:44", "throughput": 5654.82, "total_tokens": 22079632} {"current_steps": 33545, "total_steps": 33920, "loss": 0.3285, "lr": 3.742523636270368e-09, "epoch": 19.77889150943396, "percentage": 98.89, "elapsed_time": "1:05:05", "remaining_time": "0:00:43", "throughput": 5654.8, "total_tokens": 22082512} {"current_steps": 33550, "total_steps": 33920, "loss": 0.2789, "lr": 3.6436622468738468e-09, "epoch": 19.78183962264151, "percentage": 98.91, "elapsed_time": "1:05:05", "remaining_time": "0:00:43", "throughput": 5654.94, "total_tokens": 22086896} {"current_steps": 33555, "total_steps": 33920, "loss": 0.3315, "lr": 3.546123664350254e-09, "epoch": 19.784787735849058, "percentage": 98.92, "elapsed_time": "1:05:06", "remaining_time": "0:00:42", "throughput": 5654.85, "total_tokens": 22089456} {"current_steps": 33560, "total_steps": 33920, "loss": 0.248, "lr": 3.449907914524486e-09, "epoch": 19.787735849056602, "percentage": 98.94, "elapsed_time": "1:05:06", "remaining_time": "0:00:41", "throughput": 5654.85, "total_tokens": 22092496} {"current_steps": 33565, "total_steps": 33920, "loss": 0.2253, "lr": 3.355015022869501e-09, "epoch": 19.79068396226415, "percentage": 98.95, "elapsed_time": "1:05:07", "remaining_time": "0:00:41", "throughput": 5654.77, "total_tokens": 22095216} {"current_steps": 33570, "total_steps": 33920, "loss": 0.3973, "lr": 3.261445014508535e-09, "epoch": 19.7936320754717, "percentage": 98.97, "elapsed_time": "1:05:07", "remaining_time": "0:00:40", "throughput": 5654.64, "total_tokens": 22097872} {"current_steps": 33575, "total_steps": 33920, "loss": 0.2419, "lr": 3.1691979142145503e-09, "epoch": 19.796580188679247, "percentage": 98.98, "elapsed_time": "1:05:08", "remaining_time": "0:00:40", "throughput": 5654.61, "total_tokens": 22100624} {"current_steps": 33580, "total_steps": 33920, "loss": 0.3073, "lr": 3.078273746410787e-09, "epoch": 19.79952830188679, "percentage": 99.0, "elapsed_time": "1:05:09", "remaining_time": "0:00:39", "throughput": 5654.77, "total_tokens": 22105808} {"current_steps": 33585, "total_steps": 33920, "loss": 0.426, "lr": 2.988672535169657e-09, "epoch": 19.80247641509434, "percentage": 99.01, "elapsed_time": "1:05:10", "remaining_time": "0:00:39", "throughput": 5654.85, "total_tokens": 22112336} {"current_steps": 33590, "total_steps": 33920, "loss": 0.3055, "lr": 2.9003943042127393e-09, "epoch": 19.805424528301888, "percentage": 99.03, "elapsed_time": "1:05:10", "remaining_time": "0:00:38", "throughput": 5654.7, "total_tokens": 22114736} {"current_steps": 33595, "total_steps": 33920, "loss": 0.2263, "lr": 2.8134390769135598e-09, "epoch": 19.808372641509433, "percentage": 99.04, "elapsed_time": "1:05:11", "remaining_time": "0:00:37", "throughput": 5654.66, "total_tokens": 22117680} {"current_steps": 33600, "total_steps": 33920, "loss": 0.3221, "lr": 2.7278068762925935e-09, "epoch": 19.81132075471698, "percentage": 99.06, "elapsed_time": "1:05:11", "remaining_time": "0:00:37", "throughput": 5654.56, "total_tokens": 22120432} {"current_steps": 33605, "total_steps": 33920, "loss": 0.2959, "lr": 2.6434977250217043e-09, "epoch": 19.81426886792453, "percentage": 99.07, "elapsed_time": "1:05:12", "remaining_time": "0:00:36", "throughput": 5654.6, "total_tokens": 22124080} {"current_steps": 33610, "total_steps": 33920, "loss": 0.3205, "lr": 2.560511645422481e-09, "epoch": 19.817216981132077, "percentage": 99.09, "elapsed_time": "1:05:13", "remaining_time": "0:00:36", "throughput": 5654.56, "total_tokens": 22127184} {"current_steps": 33615, "total_steps": 33920, "loss": 0.2803, "lr": 2.4788486594656825e-09, "epoch": 19.82016509433962, "percentage": 99.1, "elapsed_time": "1:05:13", "remaining_time": "0:00:35", "throughput": 5654.62, "total_tokens": 22130704} {"current_steps": 33620, "total_steps": 33920, "loss": 0.3116, "lr": 2.398508788771792e-09, "epoch": 19.82311320754717, "percentage": 99.12, "elapsed_time": "1:05:14", "remaining_time": "0:00:34", "throughput": 5654.57, "total_tokens": 22133648} {"current_steps": 33625, "total_steps": 33920, "loss": 0.3171, "lr": 2.3194920546110166e-09, "epoch": 19.826061320754718, "percentage": 99.13, "elapsed_time": "1:05:14", "remaining_time": "0:00:34", "throughput": 5654.68, "total_tokens": 22137712} {"current_steps": 33630, "total_steps": 33920, "loss": 0.3506, "lr": 2.2417984779032896e-09, "epoch": 19.829009433962263, "percentage": 99.15, "elapsed_time": "1:05:15", "remaining_time": "0:00:33", "throughput": 5654.84, "total_tokens": 22142192} {"current_steps": 33635, "total_steps": 33920, "loss": 0.274, "lr": 2.1654280792193782e-09, "epoch": 19.83195754716981, "percentage": 99.16, "elapsed_time": "1:05:16", "remaining_time": "0:00:33", "throughput": 5655.04, "total_tokens": 22146864} {"current_steps": 33640, "total_steps": 33920, "loss": 0.3359, "lr": 2.0903808787769987e-09, "epoch": 19.83490566037736, "percentage": 99.17, "elapsed_time": "1:05:16", "remaining_time": "0:00:32", "throughput": 5655.15, "total_tokens": 22150704} {"current_steps": 33645, "total_steps": 33920, "loss": 0.2749, "lr": 2.0166568964463673e-09, "epoch": 19.837853773584907, "percentage": 99.19, "elapsed_time": "1:05:17", "remaining_time": "0:00:32", "throughput": 5655.14, "total_tokens": 22153968} {"current_steps": 33650, "total_steps": 33920, "loss": 0.254, "lr": 1.9442561517463153e-09, "epoch": 19.840801886792452, "percentage": 99.2, "elapsed_time": "1:05:18", "remaining_time": "0:00:31", "throughput": 5655.12, "total_tokens": 22157424} {"current_steps": 33655, "total_steps": 33920, "loss": 0.2873, "lr": 1.8731786638442886e-09, "epoch": 19.84375, "percentage": 99.22, "elapsed_time": "1:05:18", "remaining_time": "0:00:30", "throughput": 5655.14, "total_tokens": 22162096} {"current_steps": 33660, "total_steps": 33920, "loss": 0.279, "lr": 1.8034244515591214e-09, "epoch": 19.846698113207548, "percentage": 99.23, "elapsed_time": "1:05:19", "remaining_time": "0:00:30", "throughput": 5654.95, "total_tokens": 22164336} {"current_steps": 33665, "total_steps": 33920, "loss": 0.2844, "lr": 1.7349935333582646e-09, "epoch": 19.849646226415093, "percentage": 99.25, "elapsed_time": "1:05:20", "remaining_time": "0:00:29", "throughput": 5654.98, "total_tokens": 22167536} {"current_steps": 33670, "total_steps": 33920, "loss": 0.241, "lr": 1.6678859273594471e-09, "epoch": 19.85259433962264, "percentage": 99.26, "elapsed_time": "1:05:20", "remaining_time": "0:00:29", "throughput": 5654.89, "total_tokens": 22170096} {"current_steps": 33675, "total_steps": 33920, "loss": 0.3039, "lr": 1.6021016513295683e-09, "epoch": 19.85554245283019, "percentage": 99.28, "elapsed_time": "1:05:21", "remaining_time": "0:00:28", "throughput": 5654.77, "total_tokens": 22172624} {"current_steps": 33680, "total_steps": 33920, "loss": 0.2798, "lr": 1.5376407226846968e-09, "epoch": 19.858490566037737, "percentage": 99.29, "elapsed_time": "1:05:21", "remaining_time": "0:00:27", "throughput": 5654.56, "total_tokens": 22174832} {"current_steps": 33685, "total_steps": 33920, "loss": 0.3391, "lr": 1.4745031584917357e-09, "epoch": 19.861438679245282, "percentage": 99.31, "elapsed_time": "1:05:22", "remaining_time": "0:00:27", "throughput": 5654.56, "total_tokens": 22177936} {"current_steps": 33690, "total_steps": 33920, "loss": 0.3127, "lr": 1.4126889754667583e-09, "epoch": 19.86438679245283, "percentage": 99.32, "elapsed_time": "1:05:22", "remaining_time": "0:00:26", "throughput": 5654.67, "total_tokens": 22181648} {"current_steps": 33695, "total_steps": 33920, "loss": 0.3793, "lr": 1.3521981899750069e-09, "epoch": 19.86733490566038, "percentage": 99.34, "elapsed_time": "1:05:23", "remaining_time": "0:00:26", "throughput": 5654.73, "total_tokens": 22185232} {"current_steps": 33700, "total_steps": 33920, "loss": 0.1927, "lr": 1.293030818032004e-09, "epoch": 19.870283018867923, "percentage": 99.35, "elapsed_time": "1:05:23", "remaining_time": "0:00:25", "throughput": 5654.81, "total_tokens": 22188656} {"current_steps": 33705, "total_steps": 33920, "loss": 0.1966, "lr": 1.2351868753018858e-09, "epoch": 19.87323113207547, "percentage": 99.37, "elapsed_time": "1:05:24", "remaining_time": "0:00:25", "throughput": 5654.83, "total_tokens": 22191600} {"current_steps": 33710, "total_steps": 33920, "loss": 0.2975, "lr": 1.1786663770996242e-09, "epoch": 19.87617924528302, "percentage": 99.38, "elapsed_time": "1:05:24", "remaining_time": "0:00:24", "throughput": 5654.87, "total_tokens": 22195120} {"current_steps": 33715, "total_steps": 33920, "loss": 0.2904, "lr": 1.1234693383893602e-09, "epoch": 19.879127358490567, "percentage": 99.4, "elapsed_time": "1:05:25", "remaining_time": "0:00:23", "throughput": 5654.95, "total_tokens": 22198928} {"current_steps": 33720, "total_steps": 33920, "loss": 0.2771, "lr": 1.0695957737844043e-09, "epoch": 19.882075471698112, "percentage": 99.41, "elapsed_time": "1:05:26", "remaining_time": "0:00:23", "throughput": 5654.93, "total_tokens": 22201904} {"current_steps": 33725, "total_steps": 33920, "loss": 0.4274, "lr": 1.0170456975483467e-09, "epoch": 19.88502358490566, "percentage": 99.43, "elapsed_time": "1:05:26", "remaining_time": "0:00:22", "throughput": 5654.91, "total_tokens": 22205104} {"current_steps": 33730, "total_steps": 33920, "loss": 0.3181, "lr": 9.658191235933922e-10, "epoch": 19.88797169811321, "percentage": 99.44, "elapsed_time": "1:05:27", "remaining_time": "0:00:22", "throughput": 5654.86, "total_tokens": 22208400} {"current_steps": 33735, "total_steps": 33920, "loss": 0.25, "lr": 9.159160654825805e-10, "epoch": 19.890919811320753, "percentage": 99.45, "elapsed_time": "1:05:27", "remaining_time": "0:00:21", "throughput": 5655.03, "total_tokens": 22212816} {"current_steps": 33740, "total_steps": 33920, "loss": 0.3072, "lr": 8.673365364281205e-10, "epoch": 19.8938679245283, "percentage": 99.47, "elapsed_time": "1:05:28", "remaining_time": "0:00:20", "throughput": 5655.03, "total_tokens": 22215824} {"current_steps": 33745, "total_steps": 33920, "loss": 0.1986, "lr": 8.200805492913911e-10, "epoch": 19.89681603773585, "percentage": 99.48, "elapsed_time": "1:05:29", "remaining_time": "0:00:20", "throughput": 5654.91, "total_tokens": 22218352} {"current_steps": 33750, "total_steps": 33920, "loss": 0.2853, "lr": 7.741481165834952e-10, "epoch": 19.899764150943398, "percentage": 99.5, "elapsed_time": "1:05:29", "remaining_time": "0:00:19", "throughput": 5654.92, "total_tokens": 22222096} {"current_steps": 33755, "total_steps": 33920, "loss": 0.2518, "lr": 7.29539250465261e-10, "epoch": 19.902712264150942, "percentage": 99.51, "elapsed_time": "1:05:30", "remaining_time": "0:00:19", "throughput": 5655.0, "total_tokens": 22225712} {"current_steps": 33760, "total_steps": 33920, "loss": 0.2716, "lr": 6.862539627472409e-10, "epoch": 19.90566037735849, "percentage": 99.53, "elapsed_time": "1:05:30", "remaining_time": "0:00:18", "throughput": 5655.0, "total_tokens": 22228752} {"current_steps": 33765, "total_steps": 33920, "loss": 0.4382, "lr": 6.442922648897121e-10, "epoch": 19.90860849056604, "percentage": 99.54, "elapsed_time": "1:05:31", "remaining_time": "0:00:18", "throughput": 5654.85, "total_tokens": 22231088} {"current_steps": 33770, "total_steps": 33920, "loss": 0.3201, "lr": 6.036541680015662e-10, "epoch": 19.911556603773583, "percentage": 99.56, "elapsed_time": "1:05:31", "remaining_time": "0:00:17", "throughput": 5654.73, "total_tokens": 22233552} {"current_steps": 33775, "total_steps": 33920, "loss": 0.2174, "lr": 5.643396828419745e-10, "epoch": 19.91450471698113, "percentage": 99.57, "elapsed_time": "1:05:32", "remaining_time": "0:00:16", "throughput": 5654.75, "total_tokens": 22236752} {"current_steps": 33780, "total_steps": 33920, "loss": 0.2702, "lr": 5.26348819819833e-10, "epoch": 19.91745283018868, "percentage": 99.59, "elapsed_time": "1:05:32", "remaining_time": "0:00:16", "throughput": 5654.84, "total_tokens": 22240272} {"current_steps": 33785, "total_steps": 33920, "loss": 0.2708, "lr": 4.896815889937622e-10, "epoch": 19.920400943396228, "percentage": 99.6, "elapsed_time": "1:05:33", "remaining_time": "0:00:15", "throughput": 5654.89, "total_tokens": 22243504} {"current_steps": 33790, "total_steps": 33920, "loss": 0.3351, "lr": 4.543380000704423e-10, "epoch": 19.923349056603772, "percentage": 99.62, "elapsed_time": "1:05:34", "remaining_time": "0:00:15", "throughput": 5654.98, "total_tokens": 22247056} {"current_steps": 33795, "total_steps": 33920, "loss": 0.3012, "lr": 4.203180624084979e-10, "epoch": 19.92629716981132, "percentage": 99.63, "elapsed_time": "1:05:34", "remaining_time": "0:00:14", "throughput": 5654.86, "total_tokens": 22249616} {"current_steps": 33800, "total_steps": 33920, "loss": 0.2986, "lr": 3.876217850146136e-10, "epoch": 19.92924528301887, "percentage": 99.65, "elapsed_time": "1:05:35", "remaining_time": "0:00:13", "throughput": 5654.83, "total_tokens": 22252496} {"current_steps": 33805, "total_steps": 33920, "loss": 0.3177, "lr": 3.56249176544643e-10, "epoch": 19.932193396226417, "percentage": 99.66, "elapsed_time": "1:05:35", "remaining_time": "0:00:13", "throughput": 5654.88, "total_tokens": 22255792} {"current_steps": 33810, "total_steps": 33920, "loss": 0.26, "lr": 3.262002453047197e-10, "epoch": 19.93514150943396, "percentage": 99.68, "elapsed_time": "1:05:36", "remaining_time": "0:00:12", "throughput": 5654.81, "total_tokens": 22258576} {"current_steps": 33815, "total_steps": 33920, "loss": 0.3009, "lr": 2.974749992512571e-10, "epoch": 19.93808962264151, "percentage": 99.69, "elapsed_time": "1:05:36", "remaining_time": "0:00:12", "throughput": 5654.66, "total_tokens": 22261328} {"current_steps": 33820, "total_steps": 33920, "loss": 0.3519, "lr": 2.700734459881726e-10, "epoch": 19.941037735849058, "percentage": 99.71, "elapsed_time": "1:05:37", "remaining_time": "0:00:11", "throughput": 5654.61, "total_tokens": 22264112} {"current_steps": 33825, "total_steps": 33920, "loss": 0.5742, "lr": 2.439955927713289e-10, "epoch": 19.943985849056602, "percentage": 99.72, "elapsed_time": "1:05:37", "remaining_time": "0:00:11", "throughput": 5654.73, "total_tokens": 22268176} {"current_steps": 33830, "total_steps": 33920, "loss": 0.2232, "lr": 2.1924144650409263e-10, "epoch": 19.94693396226415, "percentage": 99.73, "elapsed_time": "1:05:38", "remaining_time": "0:00:10", "throughput": 5654.63, "total_tokens": 22271120} {"current_steps": 33835, "total_steps": 33920, "loss": 0.2776, "lr": 1.9581101374066546e-10, "epoch": 19.9498820754717, "percentage": 99.75, "elapsed_time": "1:05:39", "remaining_time": "0:00:09", "throughput": 5654.47, "total_tokens": 22273424} {"current_steps": 33840, "total_steps": 33920, "loss": 0.2911, "lr": 1.7370430068441858e-10, "epoch": 19.952830188679247, "percentage": 99.76, "elapsed_time": "1:05:39", "remaining_time": "0:00:09", "throughput": 5654.53, "total_tokens": 22276816} {"current_steps": 33845, "total_steps": 33920, "loss": 0.4486, "lr": 1.529213131878926e-10, "epoch": 19.95577830188679, "percentage": 99.78, "elapsed_time": "1:05:40", "remaining_time": "0:00:08", "throughput": 5654.57, "total_tokens": 22280016} {"current_steps": 33850, "total_steps": 33920, "loss": 0.4143, "lr": 1.3346205675335288e-10, "epoch": 19.95872641509434, "percentage": 99.79, "elapsed_time": "1:05:40", "remaining_time": "0:00:08", "throughput": 5654.6, "total_tokens": 22283408} {"current_steps": 33855, "total_steps": 33920, "loss": 0.2756, "lr": 1.1532653653334447e-10, "epoch": 19.961674528301888, "percentage": 99.81, "elapsed_time": "1:05:41", "remaining_time": "0:00:07", "throughput": 5654.51, "total_tokens": 22286032} {"current_steps": 33860, "total_steps": 33920, "loss": 0.3083, "lr": 9.85147573284717e-11, "epoch": 19.964622641509433, "percentage": 99.82, "elapsed_time": "1:05:41", "remaining_time": "0:00:06", "throughput": 5654.56, "total_tokens": 22289744} {"current_steps": 33865, "total_steps": 33920, "loss": 0.2281, "lr": 8.302672359072894e-11, "epoch": 19.96757075471698, "percentage": 99.84, "elapsed_time": "1:05:42", "remaining_time": "0:00:06", "throughput": 5654.53, "total_tokens": 22292656} {"current_steps": 33870, "total_steps": 33920, "loss": 0.2721, "lr": 6.886243941961468e-11, "epoch": 19.97051886792453, "percentage": 99.85, "elapsed_time": "1:05:42", "remaining_time": "0:00:05", "throughput": 5654.51, "total_tokens": 22295472} {"current_steps": 33875, "total_steps": 33920, "loss": 0.2705, "lr": 5.602190856601741e-11, "epoch": 19.973466981132077, "percentage": 99.87, "elapsed_time": "1:05:43", "remaining_time": "0:00:05", "throughput": 5654.54, "total_tokens": 22299216} {"current_steps": 33880, "total_steps": 33920, "loss": 0.3063, "lr": 4.450513442888493e-11, "epoch": 19.97641509433962, "percentage": 99.88, "elapsed_time": "1:05:44", "remaining_time": "0:00:04", "throughput": 5654.58, "total_tokens": 22302512} {"current_steps": 33885, "total_steps": 33920, "loss": 0.3465, "lr": 3.4312120057999886e-11, "epoch": 19.97936320754717, "percentage": 99.9, "elapsed_time": "1:05:44", "remaining_time": "0:00:04", "throughput": 5654.46, "total_tokens": 22305008} {"current_steps": 33890, "total_steps": 33920, "loss": 0.3758, "lr": 2.5442868151204224e-11, "epoch": 19.982311320754718, "percentage": 99.91, "elapsed_time": "1:05:45", "remaining_time": "0:00:03", "throughput": 5654.43, "total_tokens": 22308336} {"current_steps": 33895, "total_steps": 33920, "loss": 0.2291, "lr": 1.7897381057729867e-11, "epoch": 19.985259433962263, "percentage": 99.93, "elapsed_time": "1:05:45", "remaining_time": "0:00:02", "throughput": 5654.34, "total_tokens": 22311120} {"current_steps": 33900, "total_steps": 33920, "loss": 0.238, "lr": 1.1675660773757813e-11, "epoch": 19.98820754716981, "percentage": 99.94, "elapsed_time": "1:05:46", "remaining_time": "0:00:02", "throughput": 5654.23, "total_tokens": 22313840} {"current_steps": 33905, "total_steps": 33920, "loss": 0.2988, "lr": 6.777708947969253e-12, "epoch": 19.99115566037736, "percentage": 99.96, "elapsed_time": "1:05:46", "remaining_time": "0:00:01", "throughput": 5654.2, "total_tokens": 22317104} {"current_steps": 33910, "total_steps": 33920, "loss": 0.3082, "lr": 3.2035268765495674e-12, "epoch": 19.994103773584907, "percentage": 99.97, "elapsed_time": "1:05:47", "remaining_time": "0:00:01", "throughput": 5654.37, "total_tokens": 22321392} {"current_steps": 33915, "total_steps": 33920, "loss": 0.3209, "lr": 9.531155059638863e-13, "epoch": 19.997051886792452, "percentage": 99.99, "elapsed_time": "1:05:48", "remaining_time": "0:00:00", "throughput": 5654.33, "total_tokens": 22324176} {"current_steps": 33920, "total_steps": 33920, "loss": 0.3651, "lr": 2.6475431291750342e-14, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:05:48", "remaining_time": "0:00:00", "throughput": 5653.98, "total_tokens": 22326528} {"current_steps": 33920, "total_steps": 33920, "eval_loss": 0.6114597916603088, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:06:07", "remaining_time": "0:00:00", "throughput": 5627.39, "total_tokens": 22326528} {"current_steps": 33920, "total_steps": 33920, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:06:10", "remaining_time": "0:00:00", "throughput": 5623.04, "total_tokens": 22326528}