{"current_steps": 5, "total_steps": 19080, "loss": 13.1779, "lr": 1.048218029350105e-07, "epoch": 0.002620545073375262, "percentage": 0.03, "elapsed_time": "0:00:01", "remaining_time": "1:16:19", "throughput": 2452.3, "total_tokens": 2944} {"current_steps": 10, "total_steps": 19080, "loss": 13.1134, "lr": 2.3584905660377358e-07, "epoch": 0.005241090146750524, "percentage": 0.05, "elapsed_time": "0:00:02", "remaining_time": "1:06:58", "throughput": 3234.27, "total_tokens": 6816} {"current_steps": 15, "total_steps": 19080, "loss": 13.3592, "lr": 3.6687631027253674e-07, "epoch": 0.007861635220125786, "percentage": 0.08, "elapsed_time": "0:00:02", "remaining_time": "0:59:27", "throughput": 3476.93, "total_tokens": 9760} {"current_steps": 20, "total_steps": 19080, "loss": 13.0221, "lr": 4.979035639412998e-07, "epoch": 0.010482180293501049, "percentage": 0.1, "elapsed_time": "0:00:03", "remaining_time": "0:57:58", "throughput": 3690.77, "total_tokens": 13472} {"current_steps": 25, "total_steps": 19080, "loss": 13.238, "lr": 6.28930817610063e-07, "epoch": 0.01310272536687631, "percentage": 0.13, "elapsed_time": "0:00:04", "remaining_time": "0:56:39", "throughput": 3780.56, "total_tokens": 16864} {"current_steps": 30, "total_steps": 19080, "loss": 13.2453, "lr": 7.59958071278826e-07, "epoch": 0.015723270440251572, "percentage": 0.16, "elapsed_time": "0:00:05", "remaining_time": "0:55:40", "throughput": 3868.34, "total_tokens": 20352} {"current_steps": 35, "total_steps": 19080, "loss": 13.5289, "lr": 8.90985324947589e-07, "epoch": 0.018343815513626835, "percentage": 0.18, "elapsed_time": "0:00:05", "remaining_time": "0:53:30", "throughput": 3899.65, "total_tokens": 23008} {"current_steps": 40, "total_steps": 19080, "loss": 13.3721, "lr": 1.0220125786163522e-06, "epoch": 0.020964360587002098, "percentage": 0.21, "elapsed_time": "0:00:06", "remaining_time": "0:52:32", "throughput": 3913.72, "total_tokens": 25920} {"current_steps": 45, "total_steps": 19080, "loss": 13.246, "lr": 1.1530398322851154e-06, "epoch": 0.02358490566037736, "percentage": 0.24, "elapsed_time": "0:00:07", "remaining_time": "0:51:29", "throughput": 3926.0, "total_tokens": 28672} {"current_steps": 50, "total_steps": 19080, "loss": 13.2068, "lr": 1.2840670859538784e-06, "epoch": 0.02620545073375262, "percentage": 0.26, "elapsed_time": "0:00:07", "remaining_time": "0:50:39", "throughput": 3943.02, "total_tokens": 31488} {"current_steps": 55, "total_steps": 19080, "loss": 13.1187, "lr": 1.4150943396226415e-06, "epoch": 0.028825995807127882, "percentage": 0.29, "elapsed_time": "0:00:08", "remaining_time": "0:50:08", "throughput": 3965.82, "total_tokens": 34496} {"current_steps": 60, "total_steps": 19080, "loss": 13.0994, "lr": 1.5461215932914047e-06, "epoch": 0.031446540880503145, "percentage": 0.31, "elapsed_time": "0:00:09", "remaining_time": "0:50:21", "throughput": 3999.13, "total_tokens": 38112} {"current_steps": 65, "total_steps": 19080, "loss": 13.1333, "lr": 1.677148846960168e-06, "epoch": 0.034067085953878404, "percentage": 0.34, "elapsed_time": "0:00:10", "remaining_time": "0:49:40", "throughput": 4010.36, "total_tokens": 40864} {"current_steps": 70, "total_steps": 19080, "loss": 13.0672, "lr": 1.8081761006289309e-06, "epoch": 0.03668763102725367, "percentage": 0.37, "elapsed_time": "0:00:10", "remaining_time": "0:49:38", "throughput": 4029.26, "total_tokens": 44192} {"current_steps": 75, "total_steps": 19080, "loss": 13.3934, "lr": 1.939203354297694e-06, "epoch": 0.03930817610062893, "percentage": 0.39, "elapsed_time": "0:00:11", "remaining_time": "0:49:03", "throughput": 4027.3, "total_tokens": 46784} {"current_steps": 80, "total_steps": 19080, "loss": 13.1436, "lr": 2.0702306079664572e-06, "epoch": 0.041928721174004195, "percentage": 0.42, "elapsed_time": "0:00:12", "remaining_time": "0:49:06", "throughput": 4044.65, "total_tokens": 50176} {"current_steps": 85, "total_steps": 19080, "loss": 12.9919, "lr": 2.20125786163522e-06, "epoch": 0.044549266247379454, "percentage": 0.45, "elapsed_time": "0:00:13", "remaining_time": "0:49:45", "throughput": 4071.99, "total_tokens": 54400} {"current_steps": 90, "total_steps": 19080, "loss": 13.204, "lr": 2.3322851153039836e-06, "epoch": 0.04716981132075472, "percentage": 0.47, "elapsed_time": "0:00:13", "remaining_time": "0:49:13", "throughput": 4070.9, "total_tokens": 56992} {"current_steps": 95, "total_steps": 19080, "loss": 13.03, "lr": 2.4633123689727464e-06, "epoch": 0.04979035639412998, "percentage": 0.5, "elapsed_time": "0:00:14", "remaining_time": "0:49:30", "throughput": 4097.01, "total_tokens": 60896} {"current_steps": 100, "total_steps": 19080, "loss": 13.1829, "lr": 2.5943396226415095e-06, "epoch": 0.05241090146750524, "percentage": 0.52, "elapsed_time": "0:00:15", "remaining_time": "0:49:41", "throughput": 4111.08, "total_tokens": 64576} {"current_steps": 105, "total_steps": 19080, "loss": 13.2834, "lr": 2.7253668763102727e-06, "epoch": 0.055031446540880505, "percentage": 0.55, "elapsed_time": "0:00:16", "remaining_time": "0:49:35", "throughput": 4106.57, "total_tokens": 67616} {"current_steps": 110, "total_steps": 19080, "loss": 12.7603, "lr": 2.8563941299790355e-06, "epoch": 0.057651991614255764, "percentage": 0.58, "elapsed_time": "0:00:17", "remaining_time": "0:50:26", "throughput": 4133.79, "total_tokens": 72544} {"current_steps": 115, "total_steps": 19080, "loss": 13.203, "lr": 2.987421383647799e-06, "epoch": 0.06027253668763103, "percentage": 0.6, "elapsed_time": "0:00:18", "remaining_time": "0:50:18", "throughput": 4133.11, "total_tokens": 75648} {"current_steps": 120, "total_steps": 19080, "loss": 13.1666, "lr": 3.118448637316562e-06, "epoch": 0.06289308176100629, "percentage": 0.63, "elapsed_time": "0:00:18", "remaining_time": "0:49:55", "throughput": 4133.44, "total_tokens": 78368} {"current_steps": 125, "total_steps": 19080, "loss": 12.9024, "lr": 3.249475890985325e-06, "epoch": 0.06551362683438156, "percentage": 0.66, "elapsed_time": "0:00:19", "remaining_time": "0:49:59", "throughput": 4142.98, "total_tokens": 81952} {"current_steps": 130, "total_steps": 19080, "loss": 13.169, "lr": 3.380503144654088e-06, "epoch": 0.06813417190775681, "percentage": 0.68, "elapsed_time": "0:00:20", "remaining_time": "0:49:46", "throughput": 4146.59, "total_tokens": 84960} {"current_steps": 135, "total_steps": 19080, "loss": 12.968, "lr": 3.5115303983228514e-06, "epoch": 0.07075471698113207, "percentage": 0.71, "elapsed_time": "0:00:21", "remaining_time": "0:49:52", "throughput": 4153.55, "total_tokens": 88576} {"current_steps": 140, "total_steps": 19080, "loss": 12.8387, "lr": 3.642557651991614e-06, "epoch": 0.07337526205450734, "percentage": 0.73, "elapsed_time": "0:00:22", "remaining_time": "0:50:00", "throughput": 4155.85, "total_tokens": 92160} {"current_steps": 145, "total_steps": 19080, "loss": 12.9846, "lr": 3.7735849056603773e-06, "epoch": 0.0759958071278826, "percentage": 0.76, "elapsed_time": "0:00:22", "remaining_time": "0:50:03", "throughput": 4167.22, "total_tokens": 95840} {"current_steps": 150, "total_steps": 19080, "loss": 12.8415, "lr": 3.9046121593291405e-06, "epoch": 0.07861635220125786, "percentage": 0.79, "elapsed_time": "0:00:23", "remaining_time": "0:49:53", "throughput": 4166.08, "total_tokens": 98816} {"current_steps": 155, "total_steps": 19080, "loss": 12.4809, "lr": 4.035639412997904e-06, "epoch": 0.08123689727463312, "percentage": 0.81, "elapsed_time": "0:00:24", "remaining_time": "0:50:07", "throughput": 4176.06, "total_tokens": 102880} {"current_steps": 160, "total_steps": 19080, "loss": 12.7477, "lr": 4.166666666666667e-06, "epoch": 0.08385744234800839, "percentage": 0.84, "elapsed_time": "0:00:25", "remaining_time": "0:49:59", "throughput": 4175.26, "total_tokens": 105920} {"current_steps": 165, "total_steps": 19080, "loss": 13.1675, "lr": 4.29769392033543e-06, "epoch": 0.08647798742138364, "percentage": 0.86, "elapsed_time": "0:00:26", "remaining_time": "0:49:52", "throughput": 4167.8, "total_tokens": 108800} {"current_steps": 170, "total_steps": 19080, "loss": 12.7225, "lr": 4.428721174004193e-06, "epoch": 0.08909853249475891, "percentage": 0.89, "elapsed_time": "0:00:26", "remaining_time": "0:49:45", "throughput": 4171.68, "total_tokens": 111968} {"current_steps": 175, "total_steps": 19080, "loss": 12.6803, "lr": 4.559748427672956e-06, "epoch": 0.09171907756813417, "percentage": 0.92, "elapsed_time": "0:00:27", "remaining_time": "0:49:35", "throughput": 4173.62, "total_tokens": 114976} {"current_steps": 180, "total_steps": 19080, "loss": 12.4645, "lr": 4.69077568134172e-06, "epoch": 0.09433962264150944, "percentage": 0.94, "elapsed_time": "0:00:28", "remaining_time": "0:49:19", "throughput": 4171.39, "total_tokens": 117568} {"current_steps": 185, "total_steps": 19080, "loss": 12.7697, "lr": 4.821802935010482e-06, "epoch": 0.09696016771488469, "percentage": 0.97, "elapsed_time": "0:00:28", "remaining_time": "0:49:08", "throughput": 4170.25, "total_tokens": 120384} {"current_steps": 190, "total_steps": 19080, "loss": 12.397, "lr": 4.952830188679246e-06, "epoch": 0.09958071278825996, "percentage": 1.0, "elapsed_time": "0:00:29", "remaining_time": "0:49:03", "throughput": 4178.17, "total_tokens": 123680} {"current_steps": 195, "total_steps": 19080, "loss": 12.506, "lr": 5.083857442348009e-06, "epoch": 0.10220125786163523, "percentage": 1.02, "elapsed_time": "0:00:30", "remaining_time": "0:49:05", "throughput": 4181.34, "total_tokens": 127168} {"current_steps": 200, "total_steps": 19080, "loss": 12.5835, "lr": 5.2148846960167715e-06, "epoch": 0.10482180293501048, "percentage": 1.05, "elapsed_time": "0:00:31", "remaining_time": "0:48:56", "throughput": 4184.42, "total_tokens": 130176} {"current_steps": 205, "total_steps": 19080, "loss": 12.356, "lr": 5.345911949685535e-06, "epoch": 0.10744234800838574, "percentage": 1.07, "elapsed_time": "0:00:31", "remaining_time": "0:48:49", "throughput": 4182.12, "total_tokens": 133056} {"current_steps": 210, "total_steps": 19080, "loss": 12.4765, "lr": 5.476939203354298e-06, "epoch": 0.11006289308176101, "percentage": 1.1, "elapsed_time": "0:00:32", "remaining_time": "0:48:56", "throughput": 4188.61, "total_tokens": 136864} {"current_steps": 215, "total_steps": 19080, "loss": 12.4409, "lr": 5.607966457023061e-06, "epoch": 0.11268343815513626, "percentage": 1.13, "elapsed_time": "0:00:33", "remaining_time": "0:48:52", "throughput": 4191.1, "total_tokens": 140064} {"current_steps": 220, "total_steps": 19080, "loss": 12.5948, "lr": 5.738993710691824e-06, "epoch": 0.11530398322851153, "percentage": 1.15, "elapsed_time": "0:00:34", "remaining_time": "0:48:58", "throughput": 4192.56, "total_tokens": 143712} {"current_steps": 225, "total_steps": 19080, "loss": 12.1293, "lr": 5.870020964360588e-06, "epoch": 0.1179245283018868, "percentage": 1.18, "elapsed_time": "0:00:35", "remaining_time": "0:48:56", "throughput": 4192.09, "total_tokens": 146880} {"current_steps": 230, "total_steps": 19080, "loss": 12.2451, "lr": 6.0010482180293506e-06, "epoch": 0.12054507337526206, "percentage": 1.21, "elapsed_time": "0:00:35", "remaining_time": "0:48:59", "throughput": 4197.64, "total_tokens": 150560} {"current_steps": 235, "total_steps": 19080, "loss": 12.2155, "lr": 6.132075471698113e-06, "epoch": 0.12316561844863731, "percentage": 1.23, "elapsed_time": "0:00:36", "remaining_time": "0:48:55", "throughput": 4197.38, "total_tokens": 153664} {"current_steps": 240, "total_steps": 19080, "loss": 11.9755, "lr": 6.263102725366876e-06, "epoch": 0.12578616352201258, "percentage": 1.26, "elapsed_time": "0:00:37", "remaining_time": "0:49:04", "throughput": 4200.31, "total_tokens": 157568} {"current_steps": 245, "total_steps": 19080, "loss": 12.426, "lr": 6.3941299790356405e-06, "epoch": 0.12840670859538783, "percentage": 1.28, "elapsed_time": "0:00:38", "remaining_time": "0:48:58", "throughput": 4199.6, "total_tokens": 160512} {"current_steps": 250, "total_steps": 19080, "loss": 12.1661, "lr": 6.5251572327044024e-06, "epoch": 0.1310272536687631, "percentage": 1.31, "elapsed_time": "0:00:39", "remaining_time": "0:49:07", "throughput": 4204.46, "total_tokens": 164512} {"current_steps": 255, "total_steps": 19080, "loss": 12.385, "lr": 6.656184486373165e-06, "epoch": 0.13364779874213836, "percentage": 1.34, "elapsed_time": "0:00:39", "remaining_time": "0:48:57", "throughput": 4201.82, "total_tokens": 167200} {"current_steps": 260, "total_steps": 19080, "loss": 11.7618, "lr": 6.78721174004193e-06, "epoch": 0.13626834381551362, "percentage": 1.36, "elapsed_time": "0:00:40", "remaining_time": "0:48:48", "throughput": 4200.99, "total_tokens": 169984} {"current_steps": 265, "total_steps": 19080, "loss": 12.1188, "lr": 6.918238993710692e-06, "epoch": 0.1388888888888889, "percentage": 1.39, "elapsed_time": "0:00:41", "remaining_time": "0:48:54", "throughput": 4206.0, "total_tokens": 173856} {"current_steps": 270, "total_steps": 19080, "loss": 12.0293, "lr": 7.049266247379454e-06, "epoch": 0.14150943396226415, "percentage": 1.42, "elapsed_time": "0:00:41", "remaining_time": "0:48:40", "throughput": 4202.61, "total_tokens": 176192} {"current_steps": 275, "total_steps": 19080, "loss": 11.855, "lr": 7.180293501048219e-06, "epoch": 0.1441299790356394, "percentage": 1.44, "elapsed_time": "0:00:42", "remaining_time": "0:48:44", "throughput": 4205.5, "total_tokens": 179840} {"current_steps": 280, "total_steps": 19080, "loss": 11.9037, "lr": 7.3113207547169815e-06, "epoch": 0.14675052410901468, "percentage": 1.47, "elapsed_time": "0:00:43", "remaining_time": "0:48:41", "throughput": 4205.54, "total_tokens": 182976} {"current_steps": 285, "total_steps": 19080, "loss": 11.7698, "lr": 7.442348008385745e-06, "epoch": 0.14937106918238993, "percentage": 1.49, "elapsed_time": "0:00:44", "remaining_time": "0:48:42", "throughput": 4206.4, "total_tokens": 186400} {"current_steps": 290, "total_steps": 19080, "loss": 11.9387, "lr": 7.573375262054508e-06, "epoch": 0.1519916142557652, "percentage": 1.52, "elapsed_time": "0:00:45", "remaining_time": "0:48:47", "throughput": 4209.05, "total_tokens": 190144} {"current_steps": 295, "total_steps": 19080, "loss": 11.768, "lr": 7.70440251572327e-06, "epoch": 0.15461215932914046, "percentage": 1.55, "elapsed_time": "0:00:45", "remaining_time": "0:48:44", "throughput": 4209.43, "total_tokens": 193344} {"current_steps": 300, "total_steps": 19080, "loss": 11.6262, "lr": 7.835429769392034e-06, "epoch": 0.15723270440251572, "percentage": 1.57, "elapsed_time": "0:00:46", "remaining_time": "0:48:34", "throughput": 4207.91, "total_tokens": 195904} {"current_steps": 305, "total_steps": 19080, "loss": 12.2389, "lr": 7.966457023060797e-06, "epoch": 0.159853249475891, "percentage": 1.6, "elapsed_time": "0:00:47", "remaining_time": "0:48:31", "throughput": 4205.73, "total_tokens": 198944} {"current_steps": 310, "total_steps": 19080, "loss": 11.9293, "lr": 8.09748427672956e-06, "epoch": 0.16247379454926625, "percentage": 1.62, "elapsed_time": "0:00:48", "remaining_time": "0:48:26", "throughput": 4203.64, "total_tokens": 201792} {"current_steps": 315, "total_steps": 19080, "loss": 11.5272, "lr": 8.228511530398324e-06, "epoch": 0.1650943396226415, "percentage": 1.65, "elapsed_time": "0:00:48", "remaining_time": "0:48:36", "throughput": 4208.96, "total_tokens": 206080} {"current_steps": 320, "total_steps": 19080, "loss": 11.5407, "lr": 8.359538784067087e-06, "epoch": 0.16771488469601678, "percentage": 1.68, "elapsed_time": "0:00:49", "remaining_time": "0:48:35", "throughput": 4209.91, "total_tokens": 209376} {"current_steps": 325, "total_steps": 19080, "loss": 11.7679, "lr": 8.49056603773585e-06, "epoch": 0.17033542976939203, "percentage": 1.7, "elapsed_time": "0:00:50", "remaining_time": "0:48:30", "throughput": 4206.85, "total_tokens": 212160} {"current_steps": 330, "total_steps": 19080, "loss": 11.7792, "lr": 8.621593291404612e-06, "epoch": 0.17295597484276728, "percentage": 1.73, "elapsed_time": "0:00:51", "remaining_time": "0:48:37", "throughput": 4209.8, "total_tokens": 216128} {"current_steps": 335, "total_steps": 19080, "loss": 11.7841, "lr": 8.752620545073375e-06, "epoch": 0.17557651991614256, "percentage": 1.76, "elapsed_time": "0:00:52", "remaining_time": "0:48:36", "throughput": 4205.71, "total_tokens": 219232} {"current_steps": 340, "total_steps": 19080, "loss": 11.3, "lr": 8.883647798742138e-06, "epoch": 0.17819706498951782, "percentage": 1.78, "elapsed_time": "0:00:52", "remaining_time": "0:48:34", "throughput": 4206.95, "total_tokens": 222464} {"current_steps": 345, "total_steps": 19080, "loss": 11.2149, "lr": 9.014675052410902e-06, "epoch": 0.18081761006289307, "percentage": 1.81, "elapsed_time": "0:00:53", "remaining_time": "0:48:27", "throughput": 4206.53, "total_tokens": 225184} {"current_steps": 350, "total_steps": 19080, "loss": 11.2171, "lr": 9.145702306079665e-06, "epoch": 0.18343815513626835, "percentage": 1.83, "elapsed_time": "0:00:54", "remaining_time": "0:48:21", "throughput": 4204.63, "total_tokens": 228000} {"current_steps": 355, "total_steps": 19080, "loss": 11.6321, "lr": 9.276729559748428e-06, "epoch": 0.1860587002096436, "percentage": 1.86, "elapsed_time": "0:00:54", "remaining_time": "0:48:18", "throughput": 4202.82, "total_tokens": 230944} {"current_steps": 360, "total_steps": 19080, "loss": 11.5828, "lr": 9.40775681341719e-06, "epoch": 0.18867924528301888, "percentage": 1.89, "elapsed_time": "0:00:55", "remaining_time": "0:48:11", "throughput": 4202.68, "total_tokens": 233728} {"current_steps": 365, "total_steps": 19080, "loss": 11.3689, "lr": 9.538784067085953e-06, "epoch": 0.19129979035639413, "percentage": 1.91, "elapsed_time": "0:00:56", "remaining_time": "0:48:05", "throughput": 4201.63, "total_tokens": 236480} {"current_steps": 370, "total_steps": 19080, "loss": 11.4065, "lr": 9.669811320754718e-06, "epoch": 0.19392033542976939, "percentage": 1.94, "elapsed_time": "0:00:56", "remaining_time": "0:48:02", "throughput": 4201.61, "total_tokens": 239488} {"current_steps": 375, "total_steps": 19080, "loss": 11.2907, "lr": 9.80083857442348e-06, "epoch": 0.19654088050314467, "percentage": 1.97, "elapsed_time": "0:00:57", "remaining_time": "0:47:55", "throughput": 4200.83, "total_tokens": 242144} {"current_steps": 380, "total_steps": 19080, "loss": 11.2444, "lr": 9.931865828092243e-06, "epoch": 0.19916142557651992, "percentage": 1.99, "elapsed_time": "0:00:58", "remaining_time": "0:47:52", "throughput": 4200.75, "total_tokens": 245216} {"current_steps": 385, "total_steps": 19080, "loss": 11.2937, "lr": 1.0062893081761008e-05, "epoch": 0.20178197064989517, "percentage": 2.02, "elapsed_time": "0:00:59", "remaining_time": "0:48:01", "throughput": 4206.32, "total_tokens": 249632} {"current_steps": 390, "total_steps": 19080, "loss": 10.9268, "lr": 1.019392033542977e-05, "epoch": 0.20440251572327045, "percentage": 2.04, "elapsed_time": "0:01:00", "remaining_time": "0:48:02", "throughput": 4210.93, "total_tokens": 253312} {"current_steps": 395, "total_steps": 19080, "loss": 11.2892, "lr": 1.0324947589098532e-05, "epoch": 0.2070230607966457, "percentage": 2.07, "elapsed_time": "0:01:00", "remaining_time": "0:47:59", "throughput": 4211.44, "total_tokens": 256384} {"current_steps": 400, "total_steps": 19080, "loss": 11.4064, "lr": 1.0455974842767296e-05, "epoch": 0.20964360587002095, "percentage": 2.1, "elapsed_time": "0:01:01", "remaining_time": "0:48:01", "throughput": 4209.3, "total_tokens": 259744} {"current_steps": 405, "total_steps": 19080, "loss": 10.8145, "lr": 1.0587002096436059e-05, "epoch": 0.21226415094339623, "percentage": 2.12, "elapsed_time": "0:01:02", "remaining_time": "0:48:04", "throughput": 4211.44, "total_tokens": 263456} {"current_steps": 410, "total_steps": 19080, "loss": 10.9054, "lr": 1.0718029350104822e-05, "epoch": 0.2148846960167715, "percentage": 2.15, "elapsed_time": "0:01:03", "remaining_time": "0:48:01", "throughput": 4211.95, "total_tokens": 266496} {"current_steps": 415, "total_steps": 19080, "loss": 10.7844, "lr": 1.0849056603773586e-05, "epoch": 0.21750524109014674, "percentage": 2.18, "elapsed_time": "0:01:03", "remaining_time": "0:47:57", "throughput": 4213.26, "total_tokens": 269600} {"current_steps": 420, "total_steps": 19080, "loss": 10.9401, "lr": 1.0980083857442349e-05, "epoch": 0.22012578616352202, "percentage": 2.2, "elapsed_time": "0:01:04", "remaining_time": "0:47:59", "throughput": 4214.85, "total_tokens": 273152} {"current_steps": 425, "total_steps": 19080, "loss": 10.6758, "lr": 1.1111111111111112e-05, "epoch": 0.22274633123689727, "percentage": 2.23, "elapsed_time": "0:01:05", "remaining_time": "0:48:03", "throughput": 4215.79, "total_tokens": 276992} {"current_steps": 430, "total_steps": 19080, "loss": 10.7073, "lr": 1.1242138364779874e-05, "epoch": 0.22536687631027252, "percentage": 2.25, "elapsed_time": "0:01:06", "remaining_time": "0:47:55", "throughput": 4213.36, "total_tokens": 279296} {"current_steps": 435, "total_steps": 19080, "loss": 10.5547, "lr": 1.1373165618448637e-05, "epoch": 0.2279874213836478, "percentage": 2.28, "elapsed_time": "0:01:07", "remaining_time": "0:48:00", "throughput": 4216.04, "total_tokens": 283296} {"current_steps": 440, "total_steps": 19080, "loss": 10.7927, "lr": 1.1504192872117402e-05, "epoch": 0.23060796645702306, "percentage": 2.31, "elapsed_time": "0:01:07", "remaining_time": "0:47:55", "throughput": 4214.44, "total_tokens": 286016} {"current_steps": 445, "total_steps": 19080, "loss": 10.5014, "lr": 1.1635220125786164e-05, "epoch": 0.23322851153039834, "percentage": 2.33, "elapsed_time": "0:01:08", "remaining_time": "0:47:53", "throughput": 4215.29, "total_tokens": 289248} {"current_steps": 450, "total_steps": 19080, "loss": 10.6704, "lr": 1.1766247379454927e-05, "epoch": 0.2358490566037736, "percentage": 2.36, "elapsed_time": "0:01:09", "remaining_time": "0:47:51", "throughput": 4212.39, "total_tokens": 292160} {"current_steps": 455, "total_steps": 19080, "loss": 10.437, "lr": 1.1897274633123692e-05, "epoch": 0.23846960167714884, "percentage": 2.38, "elapsed_time": "0:01:10", "remaining_time": "0:47:49", "throughput": 4211.98, "total_tokens": 295296} {"current_steps": 460, "total_steps": 19080, "loss": 10.6787, "lr": 1.2028301886792454e-05, "epoch": 0.24109014675052412, "percentage": 2.41, "elapsed_time": "0:01:11", "remaining_time": "0:47:55", "throughput": 4214.59, "total_tokens": 299360} {"current_steps": 465, "total_steps": 19080, "loss": 10.268, "lr": 1.2159329140461215e-05, "epoch": 0.24371069182389937, "percentage": 2.44, "elapsed_time": "0:01:11", "remaining_time": "0:47:57", "throughput": 4216.17, "total_tokens": 303072} {"current_steps": 470, "total_steps": 19080, "loss": 10.1776, "lr": 1.229035639412998e-05, "epoch": 0.24633123689727462, "percentage": 2.46, "elapsed_time": "0:01:12", "remaining_time": "0:48:07", "throughput": 4218.82, "total_tokens": 307616} {"current_steps": 475, "total_steps": 19080, "loss": 9.7502, "lr": 1.2421383647798743e-05, "epoch": 0.2489517819706499, "percentage": 2.49, "elapsed_time": "0:01:13", "remaining_time": "0:48:00", "throughput": 4217.45, "total_tokens": 310112} {"current_steps": 480, "total_steps": 19080, "loss": 10.4808, "lr": 1.2552410901467507e-05, "epoch": 0.25157232704402516, "percentage": 2.52, "elapsed_time": "0:01:14", "remaining_time": "0:47:59", "throughput": 4218.01, "total_tokens": 313472} {"current_steps": 485, "total_steps": 19080, "loss": 10.3421, "lr": 1.2683438155136268e-05, "epoch": 0.25419287211740044, "percentage": 2.54, "elapsed_time": "0:01:14", "remaining_time": "0:47:54", "throughput": 4216.22, "total_tokens": 316128} {"current_steps": 490, "total_steps": 19080, "loss": 10.2128, "lr": 1.2814465408805033e-05, "epoch": 0.25681341719077566, "percentage": 2.57, "elapsed_time": "0:01:15", "remaining_time": "0:47:55", "throughput": 4217.2, "total_tokens": 319584} {"current_steps": 495, "total_steps": 19080, "loss": 10.1513, "lr": 1.2945492662473795e-05, "epoch": 0.25943396226415094, "percentage": 2.59, "elapsed_time": "0:01:16", "remaining_time": "0:47:51", "throughput": 4217.27, "total_tokens": 322496} {"current_steps": 500, "total_steps": 19080, "loss": 10.1483, "lr": 1.3076519916142556e-05, "epoch": 0.2620545073375262, "percentage": 2.62, "elapsed_time": "0:01:17", "remaining_time": "0:47:44", "throughput": 4216.96, "total_tokens": 325120} {"current_steps": 505, "total_steps": 19080, "loss": 10.1027, "lr": 1.320754716981132e-05, "epoch": 0.26467505241090145, "percentage": 2.65, "elapsed_time": "0:01:17", "remaining_time": "0:47:39", "throughput": 4216.7, "total_tokens": 327840} {"current_steps": 510, "total_steps": 19080, "loss": 10.1062, "lr": 1.3338574423480085e-05, "epoch": 0.2672955974842767, "percentage": 2.67, "elapsed_time": "0:01:18", "remaining_time": "0:47:43", "throughput": 4219.2, "total_tokens": 331776} {"current_steps": 515, "total_steps": 19080, "loss": 10.4304, "lr": 1.3469601677148846e-05, "epoch": 0.269916142557652, "percentage": 2.7, "elapsed_time": "0:01:19", "remaining_time": "0:47:53", "throughput": 4221.47, "total_tokens": 336544} {"current_steps": 520, "total_steps": 19080, "loss": 10.1422, "lr": 1.360062893081761e-05, "epoch": 0.27253668763102723, "percentage": 2.73, "elapsed_time": "0:01:20", "remaining_time": "0:47:58", "throughput": 4224.76, "total_tokens": 340768} {"current_steps": 525, "total_steps": 19080, "loss": 10.0789, "lr": 1.3731656184486375e-05, "epoch": 0.2751572327044025, "percentage": 2.75, "elapsed_time": "0:01:21", "remaining_time": "0:47:53", "throughput": 4222.67, "total_tokens": 343296} {"current_steps": 530, "total_steps": 19080, "loss": 9.858, "lr": 1.3862683438155136e-05, "epoch": 0.2777777777777778, "percentage": 2.78, "elapsed_time": "0:01:22", "remaining_time": "0:47:54", "throughput": 4223.4, "total_tokens": 346848} {"current_steps": 535, "total_steps": 19080, "loss": 9.9564, "lr": 1.3993710691823899e-05, "epoch": 0.280398322851153, "percentage": 2.8, "elapsed_time": "0:01:22", "remaining_time": "0:47:50", "throughput": 4221.42, "total_tokens": 349632} {"current_steps": 540, "total_steps": 19080, "loss": 10.0428, "lr": 1.4124737945492664e-05, "epoch": 0.2830188679245283, "percentage": 2.83, "elapsed_time": "0:01:23", "remaining_time": "0:47:50", "throughput": 4222.73, "total_tokens": 353024} {"current_steps": 545, "total_steps": 19080, "loss": 9.9191, "lr": 1.4255765199161425e-05, "epoch": 0.2856394129979036, "percentage": 2.86, "elapsed_time": "0:01:24", "remaining_time": "0:47:44", "throughput": 4221.47, "total_tokens": 355552} {"current_steps": 550, "total_steps": 19080, "loss": 9.4586, "lr": 1.4386792452830189e-05, "epoch": 0.2882599580712788, "percentage": 2.88, "elapsed_time": "0:01:25", "remaining_time": "0:47:52", "throughput": 4224.21, "total_tokens": 360128} {"current_steps": 555, "total_steps": 19080, "loss": 10.0312, "lr": 1.4517819706498954e-05, "epoch": 0.2908805031446541, "percentage": 2.91, "elapsed_time": "0:01:26", "remaining_time": "0:47:50", "throughput": 4224.48, "total_tokens": 363360} {"current_steps": 560, "total_steps": 19080, "loss": 9.5334, "lr": 1.4648846960167716e-05, "epoch": 0.29350104821802936, "percentage": 2.94, "elapsed_time": "0:01:26", "remaining_time": "0:47:47", "throughput": 4222.44, "total_tokens": 366144} {"current_steps": 565, "total_steps": 19080, "loss": 10.0289, "lr": 1.4779874213836479e-05, "epoch": 0.29612159329140464, "percentage": 2.96, "elapsed_time": "0:01:27", "remaining_time": "0:47:45", "throughput": 4222.07, "total_tokens": 369216} {"current_steps": 570, "total_steps": 19080, "loss": 9.7883, "lr": 1.4910901467505242e-05, "epoch": 0.29874213836477986, "percentage": 2.99, "elapsed_time": "0:01:28", "remaining_time": "0:47:45", "throughput": 4221.27, "total_tokens": 372512} {"current_steps": 575, "total_steps": 19080, "loss": 9.519, "lr": 1.5041928721174006e-05, "epoch": 0.30136268343815514, "percentage": 3.01, "elapsed_time": "0:01:28", "remaining_time": "0:47:40", "throughput": 4218.51, "total_tokens": 374976} {"current_steps": 580, "total_steps": 19080, "loss": 9.6142, "lr": 1.5172955974842767e-05, "epoch": 0.3039832285115304, "percentage": 3.04, "elapsed_time": "0:01:29", "remaining_time": "0:47:36", "throughput": 4217.13, "total_tokens": 377632} {"current_steps": 585, "total_steps": 19080, "loss": 10.2342, "lr": 1.530398322851153e-05, "epoch": 0.30660377358490565, "percentage": 3.07, "elapsed_time": "0:01:30", "remaining_time": "0:47:34", "throughput": 4216.72, "total_tokens": 380768} {"current_steps": 590, "total_steps": 19080, "loss": 9.9699, "lr": 1.5435010482180296e-05, "epoch": 0.30922431865828093, "percentage": 3.09, "elapsed_time": "0:01:31", "remaining_time": "0:47:31", "throughput": 4214.46, "total_tokens": 383520} {"current_steps": 595, "total_steps": 19080, "loss": 9.4707, "lr": 1.5566037735849056e-05, "epoch": 0.3118448637316562, "percentage": 3.12, "elapsed_time": "0:01:31", "remaining_time": "0:47:29", "throughput": 4214.42, "total_tokens": 386496} {"current_steps": 600, "total_steps": 19080, "loss": 8.9482, "lr": 1.5697064989517822e-05, "epoch": 0.31446540880503143, "percentage": 3.14, "elapsed_time": "0:01:32", "remaining_time": "0:47:32", "throughput": 4216.27, "total_tokens": 390464} {"current_steps": 605, "total_steps": 19080, "loss": 9.6489, "lr": 1.5828092243186584e-05, "epoch": 0.3170859538784067, "percentage": 3.17, "elapsed_time": "0:01:33", "remaining_time": "0:47:29", "throughput": 4216.66, "total_tokens": 393440} {"current_steps": 610, "total_steps": 19080, "loss": 9.9533, "lr": 1.5959119496855347e-05, "epoch": 0.319706498951782, "percentage": 3.2, "elapsed_time": "0:01:34", "remaining_time": "0:47:38", "throughput": 4220.04, "total_tokens": 398336} {"current_steps": 615, "total_steps": 19080, "loss": 9.1601, "lr": 1.609014675052411e-05, "epoch": 0.3223270440251572, "percentage": 3.22, "elapsed_time": "0:01:35", "remaining_time": "0:47:37", "throughput": 4219.35, "total_tokens": 401504} {"current_steps": 620, "total_steps": 19080, "loss": 9.4581, "lr": 1.6221174004192873e-05, "epoch": 0.3249475890985325, "percentage": 3.25, "elapsed_time": "0:01:35", "remaining_time": "0:47:36", "throughput": 4219.34, "total_tokens": 404864} {"current_steps": 625, "total_steps": 19080, "loss": 9.6265, "lr": 1.6352201257861635e-05, "epoch": 0.3275681341719078, "percentage": 3.28, "elapsed_time": "0:01:36", "remaining_time": "0:47:41", "throughput": 4221.74, "total_tokens": 409056} {"current_steps": 630, "total_steps": 19080, "loss": 9.6796, "lr": 1.6483228511530398e-05, "epoch": 0.330188679245283, "percentage": 3.3, "elapsed_time": "0:01:37", "remaining_time": "0:47:40", "throughput": 4223.11, "total_tokens": 412544} {"current_steps": 635, "total_steps": 19080, "loss": 8.7238, "lr": 1.6614255765199164e-05, "epoch": 0.3328092243186583, "percentage": 3.33, "elapsed_time": "0:01:38", "remaining_time": "0:47:39", "throughput": 4221.65, "total_tokens": 415520} {"current_steps": 640, "total_steps": 19080, "loss": 9.5572, "lr": 1.6745283018867924e-05, "epoch": 0.33542976939203356, "percentage": 3.35, "elapsed_time": "0:01:39", "remaining_time": "0:47:32", "throughput": 4219.2, "total_tokens": 417760} {"current_steps": 645, "total_steps": 19080, "loss": 9.6053, "lr": 1.687631027253669e-05, "epoch": 0.3380503144654088, "percentage": 3.38, "elapsed_time": "0:01:39", "remaining_time": "0:47:35", "throughput": 4220.95, "total_tokens": 421728} {"current_steps": 650, "total_steps": 19080, "loss": 9.4238, "lr": 1.7007337526205453e-05, "epoch": 0.34067085953878407, "percentage": 3.41, "elapsed_time": "0:01:40", "remaining_time": "0:47:38", "throughput": 4222.51, "total_tokens": 425664} {"current_steps": 655, "total_steps": 19080, "loss": 9.5659, "lr": 1.7138364779874212e-05, "epoch": 0.34329140461215935, "percentage": 3.43, "elapsed_time": "0:01:41", "remaining_time": "0:47:37", "throughput": 4222.46, "total_tokens": 428896} {"current_steps": 660, "total_steps": 19080, "loss": 9.3544, "lr": 1.7269392033542978e-05, "epoch": 0.34591194968553457, "percentage": 3.46, "elapsed_time": "0:01:42", "remaining_time": "0:47:34", "throughput": 4220.79, "total_tokens": 431744} {"current_steps": 665, "total_steps": 19080, "loss": 9.335, "lr": 1.740041928721174e-05, "epoch": 0.34853249475890985, "percentage": 3.49, "elapsed_time": "0:01:43", "remaining_time": "0:47:36", "throughput": 4222.16, "total_tokens": 435520} {"current_steps": 670, "total_steps": 19080, "loss": 9.6898, "lr": 1.7531446540880504e-05, "epoch": 0.35115303983228513, "percentage": 3.51, "elapsed_time": "0:01:43", "remaining_time": "0:47:34", "throughput": 4221.66, "total_tokens": 438592} {"current_steps": 675, "total_steps": 19080, "loss": 9.4668, "lr": 1.7662473794549266e-05, "epoch": 0.35377358490566035, "percentage": 3.54, "elapsed_time": "0:01:44", "remaining_time": "0:47:32", "throughput": 4221.78, "total_tokens": 441664} {"current_steps": 680, "total_steps": 19080, "loss": 9.6701, "lr": 1.779350104821803e-05, "epoch": 0.35639412997903563, "percentage": 3.56, "elapsed_time": "0:01:45", "remaining_time": "0:47:31", "throughput": 4220.7, "total_tokens": 444832} {"current_steps": 685, "total_steps": 19080, "loss": 9.6132, "lr": 1.7924528301886792e-05, "epoch": 0.3590146750524109, "percentage": 3.59, "elapsed_time": "0:01:46", "remaining_time": "0:47:27", "throughput": 4219.41, "total_tokens": 447392} {"current_steps": 690, "total_steps": 19080, "loss": 9.5593, "lr": 1.8055555555555555e-05, "epoch": 0.36163522012578614, "percentage": 3.62, "elapsed_time": "0:01:46", "remaining_time": "0:47:25", "throughput": 4219.95, "total_tokens": 450528} {"current_steps": 695, "total_steps": 19080, "loss": 8.9773, "lr": 1.818658280922432e-05, "epoch": 0.3642557651991614, "percentage": 3.64, "elapsed_time": "0:01:47", "remaining_time": "0:47:23", "throughput": 4218.87, "total_tokens": 453504} {"current_steps": 700, "total_steps": 19080, "loss": 9.8795, "lr": 1.831761006289308e-05, "epoch": 0.3668763102725367, "percentage": 3.67, "elapsed_time": "0:01:48", "remaining_time": "0:47:20", "throughput": 4218.13, "total_tokens": 456288} {"current_steps": 705, "total_steps": 19080, "loss": 9.0254, "lr": 1.8448637316561846e-05, "epoch": 0.3694968553459119, "percentage": 3.69, "elapsed_time": "0:01:48", "remaining_time": "0:47:20", "throughput": 4218.82, "total_tokens": 459840} {"current_steps": 710, "total_steps": 19080, "loss": 9.7396, "lr": 1.857966457023061e-05, "epoch": 0.3721174004192872, "percentage": 3.72, "elapsed_time": "0:01:49", "remaining_time": "0:47:20", "throughput": 4218.41, "total_tokens": 463168} {"current_steps": 715, "total_steps": 19080, "loss": 9.4555, "lr": 1.8710691823899372e-05, "epoch": 0.3747379454926625, "percentage": 3.75, "elapsed_time": "0:01:50", "remaining_time": "0:47:18", "throughput": 4218.11, "total_tokens": 466112} {"current_steps": 720, "total_steps": 19080, "loss": 9.1798, "lr": 1.8841719077568135e-05, "epoch": 0.37735849056603776, "percentage": 3.77, "elapsed_time": "0:01:51", "remaining_time": "0:47:18", "throughput": 4219.06, "total_tokens": 469568} {"current_steps": 725, "total_steps": 19080, "loss": 8.9146, "lr": 1.8972746331236897e-05, "epoch": 0.379979035639413, "percentage": 3.8, "elapsed_time": "0:01:52", "remaining_time": "0:47:17", "throughput": 4218.64, "total_tokens": 472896} {"current_steps": 730, "total_steps": 19080, "loss": 9.0385, "lr": 1.9103773584905664e-05, "epoch": 0.38259958071278827, "percentage": 3.83, "elapsed_time": "0:01:52", "remaining_time": "0:47:15", "throughput": 4217.84, "total_tokens": 475744} {"current_steps": 735, "total_steps": 19080, "loss": 9.1064, "lr": 1.9234800838574423e-05, "epoch": 0.38522012578616355, "percentage": 3.85, "elapsed_time": "0:01:54", "remaining_time": "0:47:27", "throughput": 4218.14, "total_tokens": 481216} {"current_steps": 740, "total_steps": 19080, "loss": 9.4034, "lr": 1.936582809224319e-05, "epoch": 0.38784067085953877, "percentage": 3.88, "elapsed_time": "0:01:54", "remaining_time": "0:47:21", "throughput": 4216.94, "total_tokens": 483488} {"current_steps": 745, "total_steps": 19080, "loss": 9.1111, "lr": 1.9496855345911952e-05, "epoch": 0.39046121593291405, "percentage": 3.9, "elapsed_time": "0:01:55", "remaining_time": "0:47:21", "throughput": 4218.01, "total_tokens": 487072} {"current_steps": 750, "total_steps": 19080, "loss": 9.3099, "lr": 1.9627882599580715e-05, "epoch": 0.39308176100628933, "percentage": 3.93, "elapsed_time": "0:01:56", "remaining_time": "0:47:21", "throughput": 4219.18, "total_tokens": 490496} {"current_steps": 755, "total_steps": 19080, "loss": 9.4936, "lr": 1.9758909853249477e-05, "epoch": 0.39570230607966456, "percentage": 3.96, "elapsed_time": "0:01:57", "remaining_time": "0:47:20", "throughput": 4219.35, "total_tokens": 493824} {"current_steps": 760, "total_steps": 19080, "loss": 9.1456, "lr": 1.988993710691824e-05, "epoch": 0.39832285115303984, "percentage": 3.98, "elapsed_time": "0:01:57", "remaining_time": "0:47:15", "throughput": 4217.96, "total_tokens": 496192} {"current_steps": 765, "total_steps": 19080, "loss": 9.1475, "lr": 2.0020964360587003e-05, "epoch": 0.4009433962264151, "percentage": 4.01, "elapsed_time": "0:01:58", "remaining_time": "0:47:12", "throughput": 4216.28, "total_tokens": 498880} {"current_steps": 770, "total_steps": 19080, "loss": 9.181, "lr": 2.0151991614255766e-05, "epoch": 0.40356394129979034, "percentage": 4.04, "elapsed_time": "0:01:59", "remaining_time": "0:47:11", "throughput": 4216.22, "total_tokens": 502016} {"current_steps": 775, "total_steps": 19080, "loss": 9.0618, "lr": 2.0283018867924532e-05, "epoch": 0.4061844863731656, "percentage": 4.06, "elapsed_time": "0:01:59", "remaining_time": "0:47:09", "throughput": 4216.1, "total_tokens": 505120} {"current_steps": 780, "total_steps": 19080, "loss": 9.2836, "lr": 2.041404612159329e-05, "epoch": 0.4088050314465409, "percentage": 4.09, "elapsed_time": "0:02:00", "remaining_time": "0:47:08", "throughput": 4216.01, "total_tokens": 508256} {"current_steps": 785, "total_steps": 19080, "loss": 9.2064, "lr": 2.0545073375262054e-05, "epoch": 0.4114255765199161, "percentage": 4.11, "elapsed_time": "0:02:01", "remaining_time": "0:47:08", "throughput": 4216.11, "total_tokens": 511776} {"current_steps": 790, "total_steps": 19080, "loss": 8.5634, "lr": 2.067610062893082e-05, "epoch": 0.4140461215932914, "percentage": 4.14, "elapsed_time": "0:02:02", "remaining_time": "0:47:05", "throughput": 4215.42, "total_tokens": 514464} {"current_steps": 795, "total_steps": 19080, "loss": 9.2296, "lr": 2.080712788259958e-05, "epoch": 0.4166666666666667, "percentage": 4.17, "elapsed_time": "0:02:02", "remaining_time": "0:47:06", "throughput": 4216.88, "total_tokens": 518144} {"current_steps": 800, "total_steps": 19080, "loss": 9.2801, "lr": 2.0938155136268346e-05, "epoch": 0.4192872117400419, "percentage": 4.19, "elapsed_time": "0:02:03", "remaining_time": "0:47:02", "throughput": 4216.26, "total_tokens": 520768} {"current_steps": 805, "total_steps": 19080, "loss": 8.5923, "lr": 2.106918238993711e-05, "epoch": 0.4219077568134172, "percentage": 4.22, "elapsed_time": "0:02:04", "remaining_time": "0:47:00", "throughput": 4216.36, "total_tokens": 523808} {"current_steps": 810, "total_steps": 19080, "loss": 8.9923, "lr": 2.120020964360587e-05, "epoch": 0.42452830188679247, "percentage": 4.25, "elapsed_time": "0:02:05", "remaining_time": "0:46:59", "throughput": 4216.81, "total_tokens": 527136} {"current_steps": 815, "total_steps": 19080, "loss": 8.6378, "lr": 2.1331236897274634e-05, "epoch": 0.4271488469601677, "percentage": 4.27, "elapsed_time": "0:02:05", "remaining_time": "0:46:57", "throughput": 4217.24, "total_tokens": 530240} {"current_steps": 820, "total_steps": 19080, "loss": 8.5249, "lr": 2.1462264150943397e-05, "epoch": 0.429769392033543, "percentage": 4.3, "elapsed_time": "0:02:06", "remaining_time": "0:47:01", "throughput": 4218.96, "total_tokens": 534496} {"current_steps": 825, "total_steps": 19080, "loss": 9.1339, "lr": 2.159329140461216e-05, "epoch": 0.43238993710691825, "percentage": 4.32, "elapsed_time": "0:02:07", "remaining_time": "0:47:04", "throughput": 4220.0, "total_tokens": 538624} {"current_steps": 830, "total_steps": 19080, "loss": 8.9248, "lr": 2.1724318658280922e-05, "epoch": 0.4350104821802935, "percentage": 4.35, "elapsed_time": "0:02:08", "remaining_time": "0:47:04", "throughput": 4220.09, "total_tokens": 542112} {"current_steps": 835, "total_steps": 19080, "loss": 9.2985, "lr": 2.1855345911949688e-05, "epoch": 0.43763102725366876, "percentage": 4.38, "elapsed_time": "0:02:09", "remaining_time": "0:47:03", "throughput": 4220.03, "total_tokens": 545408} {"current_steps": 840, "total_steps": 19080, "loss": 8.658, "lr": 2.1986373165618448e-05, "epoch": 0.44025157232704404, "percentage": 4.4, "elapsed_time": "0:02:09", "remaining_time": "0:47:02", "throughput": 4219.59, "total_tokens": 548416} {"current_steps": 845, "total_steps": 19080, "loss": 8.9721, "lr": 2.2117400419287214e-05, "epoch": 0.44287211740041926, "percentage": 4.43, "elapsed_time": "0:02:10", "remaining_time": "0:46:59", "throughput": 4219.28, "total_tokens": 551264} {"current_steps": 850, "total_steps": 19080, "loss": 8.8265, "lr": 2.2248427672955977e-05, "epoch": 0.44549266247379454, "percentage": 4.45, "elapsed_time": "0:02:11", "remaining_time": "0:46:58", "throughput": 4219.42, "total_tokens": 554592} {"current_steps": 855, "total_steps": 19080, "loss": 8.9138, "lr": 2.237945492662474e-05, "epoch": 0.4481132075471698, "percentage": 4.48, "elapsed_time": "0:02:12", "remaining_time": "0:47:00", "throughput": 4219.22, "total_tokens": 558304} {"current_steps": 860, "total_steps": 19080, "loss": 8.5079, "lr": 2.2510482180293502e-05, "epoch": 0.45073375262054505, "percentage": 4.51, "elapsed_time": "0:02:13", "remaining_time": "0:46:58", "throughput": 4219.13, "total_tokens": 561248} {"current_steps": 865, "total_steps": 19080, "loss": 8.2921, "lr": 2.2641509433962265e-05, "epoch": 0.4533542976939203, "percentage": 4.53, "elapsed_time": "0:02:13", "remaining_time": "0:46:56", "throughput": 4219.27, "total_tokens": 564352} {"current_steps": 870, "total_steps": 19080, "loss": 8.5778, "lr": 2.2772536687631028e-05, "epoch": 0.4559748427672956, "percentage": 4.56, "elapsed_time": "0:02:14", "remaining_time": "0:46:56", "throughput": 4219.03, "total_tokens": 567712} {"current_steps": 875, "total_steps": 19080, "loss": 9.0935, "lr": 2.290356394129979e-05, "epoch": 0.4585953878406709, "percentage": 4.59, "elapsed_time": "0:02:15", "remaining_time": "0:46:52", "throughput": 4218.12, "total_tokens": 570240} {"current_steps": 880, "total_steps": 19080, "loss": 8.9733, "lr": 2.3034591194968556e-05, "epoch": 0.4612159329140461, "percentage": 4.61, "elapsed_time": "0:02:15", "remaining_time": "0:46:49", "throughput": 4216.88, "total_tokens": 572768} {"current_steps": 885, "total_steps": 19080, "loss": 8.5318, "lr": 2.316561844863732e-05, "epoch": 0.4638364779874214, "percentage": 4.64, "elapsed_time": "0:02:16", "remaining_time": "0:46:49", "throughput": 4218.55, "total_tokens": 576512} {"current_steps": 890, "total_steps": 19080, "loss": 8.6264, "lr": 2.329664570230608e-05, "epoch": 0.46645702306079667, "percentage": 4.66, "elapsed_time": "0:02:17", "remaining_time": "0:46:47", "throughput": 4217.12, "total_tokens": 579264} {"current_steps": 895, "total_steps": 19080, "loss": 8.8579, "lr": 2.3427672955974845e-05, "epoch": 0.4690775681341719, "percentage": 4.69, "elapsed_time": "0:02:17", "remaining_time": "0:46:42", "throughput": 4215.53, "total_tokens": 581440} {"current_steps": 900, "total_steps": 19080, "loss": 8.3018, "lr": 2.3558700209643607e-05, "epoch": 0.4716981132075472, "percentage": 4.72, "elapsed_time": "0:02:18", "remaining_time": "0:46:40", "throughput": 4215.83, "total_tokens": 584544} {"current_steps": 905, "total_steps": 19080, "loss": 8.848, "lr": 2.368972746331237e-05, "epoch": 0.47431865828092246, "percentage": 4.74, "elapsed_time": "0:02:19", "remaining_time": "0:46:41", "throughput": 4216.48, "total_tokens": 588160} {"current_steps": 910, "total_steps": 19080, "loss": 8.4685, "lr": 2.3820754716981133e-05, "epoch": 0.4769392033542977, "percentage": 4.77, "elapsed_time": "0:02:20", "remaining_time": "0:46:36", "throughput": 4214.93, "total_tokens": 590400} {"current_steps": 915, "total_steps": 19080, "loss": 8.3961, "lr": 2.39517819706499e-05, "epoch": 0.47955974842767296, "percentage": 4.8, "elapsed_time": "0:02:20", "remaining_time": "0:46:35", "throughput": 4214.88, "total_tokens": 593440} {"current_steps": 920, "total_steps": 19080, "loss": 8.0546, "lr": 2.408280922431866e-05, "epoch": 0.48218029350104824, "percentage": 4.82, "elapsed_time": "0:02:21", "remaining_time": "0:46:33", "throughput": 4214.85, "total_tokens": 596480} {"current_steps": 925, "total_steps": 19080, "loss": 8.5668, "lr": 2.421383647798742e-05, "epoch": 0.48480083857442346, "percentage": 4.85, "elapsed_time": "0:02:22", "remaining_time": "0:46:31", "throughput": 4214.19, "total_tokens": 599392} {"current_steps": 930, "total_steps": 19080, "loss": 8.4958, "lr": 2.4344863731656187e-05, "epoch": 0.48742138364779874, "percentage": 4.87, "elapsed_time": "0:02:22", "remaining_time": "0:46:30", "throughput": 4213.66, "total_tokens": 602432} {"current_steps": 935, "total_steps": 19080, "loss": 8.1065, "lr": 2.4475890985324947e-05, "epoch": 0.490041928721174, "percentage": 4.9, "elapsed_time": "0:02:23", "remaining_time": "0:46:25", "throughput": 4211.37, "total_tokens": 604512} {"current_steps": 940, "total_steps": 19080, "loss": 8.3958, "lr": 2.4606918238993713e-05, "epoch": 0.49266247379454925, "percentage": 4.93, "elapsed_time": "0:02:24", "remaining_time": "0:46:29", "throughput": 4212.55, "total_tokens": 608864} {"current_steps": 945, "total_steps": 19080, "loss": 8.0159, "lr": 2.4737945492662476e-05, "epoch": 0.49528301886792453, "percentage": 4.95, "elapsed_time": "0:02:25", "remaining_time": "0:46:29", "throughput": 4212.92, "total_tokens": 612448} {"current_steps": 950, "total_steps": 19080, "loss": 8.2597, "lr": 2.486897274633124e-05, "epoch": 0.4979035639412998, "percentage": 4.98, "elapsed_time": "0:02:26", "remaining_time": "0:46:26", "throughput": 4211.69, "total_tokens": 614944} {"current_steps": 954, "total_steps": 19080, "eval_loss": 8.478578567504883, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:02:41", "remaining_time": "0:51:01", "throughput": 3828.72, "total_tokens": 616992} {"current_steps": 955, "total_steps": 19080, "loss": 8.3431, "lr": 2.5e-05, "epoch": 0.500524109014675, "percentage": 5.01, "elapsed_time": "0:02:42", "remaining_time": "0:51:18", "throughput": 3806.52, "total_tokens": 617472} {"current_steps": 960, "total_steps": 19080, "loss": 8.2194, "lr": 2.5131027253668764e-05, "epoch": 0.5031446540880503, "percentage": 5.03, "elapsed_time": "0:02:42", "remaining_time": "0:51:14", "throughput": 3807.56, "total_tokens": 620192} {"current_steps": 965, "total_steps": 19080, "loss": 8.4424, "lr": 2.526205450733753e-05, "epoch": 0.5057651991614256, "percentage": 5.06, "elapsed_time": "0:02:43", "remaining_time": "0:51:11", "throughput": 3808.89, "total_tokens": 623232} {"current_steps": 970, "total_steps": 19080, "loss": 8.8241, "lr": 2.5393081761006293e-05, "epoch": 0.5083857442348009, "percentage": 5.08, "elapsed_time": "0:02:44", "remaining_time": "0:51:07", "throughput": 3810.27, "total_tokens": 626016} {"current_steps": 975, "total_steps": 19080, "loss": 8.4965, "lr": 2.5524109014675052e-05, "epoch": 0.5110062893081762, "percentage": 5.11, "elapsed_time": "0:02:45", "remaining_time": "0:51:05", "throughput": 3812.66, "total_tokens": 629472} {"current_steps": 980, "total_steps": 19080, "loss": 8.2748, "lr": 2.5655136268343815e-05, "epoch": 0.5136268343815513, "percentage": 5.14, "elapsed_time": "0:02:45", "remaining_time": "0:51:02", "throughput": 3814.86, "total_tokens": 632608} {"current_steps": 985, "total_steps": 19080, "loss": 8.0256, "lr": 2.578616352201258e-05, "epoch": 0.5162473794549266, "percentage": 5.16, "elapsed_time": "0:02:46", "remaining_time": "0:51:01", "throughput": 3816.99, "total_tokens": 636192} {"current_steps": 990, "total_steps": 19080, "loss": 8.2618, "lr": 2.5917190775681344e-05, "epoch": 0.5188679245283019, "percentage": 5.19, "elapsed_time": "0:02:47", "remaining_time": "0:51:03", "throughput": 3821.11, "total_tokens": 640544} {"current_steps": 995, "total_steps": 19080, "loss": 8.3303, "lr": 2.6048218029350107e-05, "epoch": 0.5214884696016772, "percentage": 5.21, "elapsed_time": "0:02:48", "remaining_time": "0:51:02", "throughput": 3824.44, "total_tokens": 644448}