diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" --- "a/trainer_log.jsonl" +++ "b/trainer_log.jsonl" @@ -11664,3 +11664,618 @@ {"current_steps": 58230, "total_steps": 61300, "loss": 0.0044, "lr": 3.8129084124848e-07, "epoch": 9.499184339314844, "percentage": 94.99, "elapsed_time": "16:03:23", "remaining_time": "0:50:47", "throughput": 2174.21, "total_tokens": 125675824} {"current_steps": 58235, "total_steps": 61300, "loss": 0.1249, "lr": 3.800534195413069e-07, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "16:03:35", "remaining_time": "0:50:42", "throughput": 2173.91, "total_tokens": 125686064} {"current_steps": 58235, "total_steps": 61300, "eval_loss": 0.19253920018672943, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "16:13:04", "remaining_time": "0:51:12", "throughput": 2152.75, "total_tokens": 125686064} +{"current_steps": 58240, "total_steps": 61300, "loss": 0.1592, "lr": 3.788179936519226e-07, "epoch": 9.500815660685156, "percentage": 95.01, "elapsed_time": "16:13:20", "remaining_time": "0:51:08", "throughput": 2152.35, "total_tokens": 125697296} +{"current_steps": 58245, "total_steps": 61300, "loss": 0.0057, "lr": 3.775845636804776e-07, "epoch": 9.50163132137031, "percentage": 95.02, "elapsed_time": "16:13:33", "remaining_time": "0:51:03", "throughput": 2152.05, "total_tokens": 125708688} +{"current_steps": 58250, "total_steps": 61300, "loss": 0.0042, "lr": 3.7635312972696404e-07, "epoch": 9.502446982055465, "percentage": 95.02, "elapsed_time": "16:13:46", "remaining_time": "0:50:59", "throughput": 2151.75, "total_tokens": 125719792} +{"current_steps": 58255, "total_steps": 61300, "loss": 0.0058, "lr": 3.751236918912021e-07, "epoch": 9.50326264274062, "percentage": 95.03, "elapsed_time": "16:13:58", "remaining_time": "0:50:54", "throughput": 2151.48, "total_tokens": 125729680} +{"current_steps": 58260, "total_steps": 61300, "loss": 0.171, "lr": 3.7389625027285936e-07, "epoch": 9.504078303425775, "percentage": 95.04, "elapsed_time": "16:14:10", "remaining_time": "0:50:49", "throughput": 2151.21, "total_tokens": 125739472} +{"current_steps": 58265, "total_steps": 61300, "loss": 0.0024, "lr": 3.726708049714367e-07, "epoch": 9.50489396411093, "percentage": 95.05, "elapsed_time": "16:14:25", "remaining_time": "0:50:45", "throughput": 2150.89, "total_tokens": 125751952} +{"current_steps": 58270, "total_steps": 61300, "loss": 0.0378, "lr": 3.714473560862797e-07, "epoch": 9.505709624796085, "percentage": 95.06, "elapsed_time": "16:14:38", "remaining_time": "0:50:40", "throughput": 2150.58, "total_tokens": 125762992} +{"current_steps": 58275, "total_steps": 61300, "loss": 0.2106, "lr": 3.702259037165617e-07, "epoch": 9.50652528548124, "percentage": 95.07, "elapsed_time": "16:14:52", "remaining_time": "0:50:36", "throughput": 2150.27, "total_tokens": 125774480} +{"current_steps": 58280, "total_steps": 61300, "loss": 0.0538, "lr": 3.690064479613009e-07, "epoch": 9.507340946166394, "percentage": 95.07, "elapsed_time": "16:15:05", "remaining_time": "0:50:31", "throughput": 2149.98, "total_tokens": 125784944} +{"current_steps": 58285, "total_steps": 61300, "loss": 0.2103, "lr": 3.67788988919357e-07, "epoch": 9.50815660685155, "percentage": 95.08, "elapsed_time": "16:15:17", "remaining_time": "0:50:27", "throughput": 2149.7, "total_tokens": 125795120} +{"current_steps": 58290, "total_steps": 61300, "loss": 0.1609, "lr": 3.665735266894177e-07, "epoch": 9.508972267536706, "percentage": 95.09, "elapsed_time": "16:15:31", "remaining_time": "0:50:22", "throughput": 2149.39, "total_tokens": 125806640} +{"current_steps": 58295, "total_steps": 61300, "loss": 0.036, "lr": 3.653600613700209e-07, "epoch": 9.50978792822186, "percentage": 95.1, "elapsed_time": "16:15:44", "remaining_time": "0:50:17", "throughput": 2149.09, "total_tokens": 125817712} +{"current_steps": 58300, "total_steps": 61300, "loss": 0.2522, "lr": 3.6414859305952955e-07, "epoch": 9.510603588907015, "percentage": 95.11, "elapsed_time": "16:15:58", "remaining_time": "0:50:13", "throughput": 2148.77, "total_tokens": 125829008} +{"current_steps": 58305, "total_steps": 61300, "loss": 0.1678, "lr": 3.629391218561512e-07, "epoch": 9.51141924959217, "percentage": 95.11, "elapsed_time": "16:16:11", "remaining_time": "0:50:08", "throughput": 2148.47, "total_tokens": 125840016} +{"current_steps": 58310, "total_steps": 61300, "loss": 0.0045, "lr": 3.6173164785794076e-07, "epoch": 9.512234910277325, "percentage": 95.12, "elapsed_time": "16:16:24", "remaining_time": "0:50:04", "throughput": 2148.18, "total_tokens": 125850608} +{"current_steps": 58315, "total_steps": 61300, "loss": 0.0976, "lr": 3.605261711627728e-07, "epoch": 9.513050570962479, "percentage": 95.13, "elapsed_time": "16:16:39", "remaining_time": "0:49:59", "throughput": 2147.85, "total_tokens": 125863312} +{"current_steps": 58320, "total_steps": 61300, "loss": 0.0034, "lr": 3.593226918683745e-07, "epoch": 9.513866231647635, "percentage": 95.14, "elapsed_time": "16:16:53", "remaining_time": "0:49:55", "throughput": 2147.53, "total_tokens": 125874960} +{"current_steps": 58325, "total_steps": 61300, "loss": 0.006, "lr": 3.5812121007230414e-07, "epoch": 9.51468189233279, "percentage": 95.15, "elapsed_time": "16:17:06", "remaining_time": "0:49:50", "throughput": 2147.24, "total_tokens": 125885264} +{"current_steps": 58330, "total_steps": 61300, "loss": 0.1345, "lr": 3.569217258719587e-07, "epoch": 9.515497553017944, "percentage": 95.15, "elapsed_time": "16:17:20", "remaining_time": "0:49:45", "throughput": 2146.93, "total_tokens": 125896624} +{"current_steps": 58335, "total_steps": 61300, "loss": 0.1631, "lr": 3.557242393645771e-07, "epoch": 9.5163132137031, "percentage": 95.16, "elapsed_time": "16:17:33", "remaining_time": "0:49:41", "throughput": 2146.64, "total_tokens": 125907056} +{"current_steps": 58340, "total_steps": 61300, "loss": 0.2797, "lr": 3.5452875064723445e-07, "epoch": 9.517128874388254, "percentage": 95.17, "elapsed_time": "16:17:45", "remaining_time": "0:49:36", "throughput": 2146.35, "total_tokens": 125917616} +{"current_steps": 58345, "total_steps": 61300, "loss": 0.2073, "lr": 3.5333525981683937e-07, "epoch": 9.51794453507341, "percentage": 95.18, "elapsed_time": "16:17:58", "remaining_time": "0:49:31", "throughput": 2146.06, "total_tokens": 125927984} +{"current_steps": 58350, "total_steps": 61300, "loss": 0.106, "lr": 3.521437669701422e-07, "epoch": 9.518760195758565, "percentage": 95.19, "elapsed_time": "16:18:11", "remaining_time": "0:49:27", "throughput": 2145.77, "total_tokens": 125938736} +{"current_steps": 58355, "total_steps": 61300, "loss": 0.2638, "lr": 3.5095427220373513e-07, "epoch": 9.51957585644372, "percentage": 95.2, "elapsed_time": "16:18:23", "remaining_time": "0:49:22", "throughput": 2145.51, "total_tokens": 125948816} +{"current_steps": 58360, "total_steps": 61300, "loss": 0.0036, "lr": 3.497667756140438e-07, "epoch": 9.520391517128875, "percentage": 95.2, "elapsed_time": "16:18:36", "remaining_time": "0:49:17", "throughput": 2145.22, "total_tokens": 125959504} +{"current_steps": 58365, "total_steps": 61300, "loss": 0.0325, "lr": 3.4858127729733015e-07, "epoch": 9.521207177814029, "percentage": 95.21, "elapsed_time": "16:18:51", "remaining_time": "0:49:13", "throughput": 2144.89, "total_tokens": 125971504} +{"current_steps": 58370, "total_steps": 61300, "loss": 0.0682, "lr": 3.473977773496978e-07, "epoch": 9.522022838499185, "percentage": 95.22, "elapsed_time": "16:19:03", "remaining_time": "0:49:08", "throughput": 2144.6, "total_tokens": 125981840} +{"current_steps": 58375, "total_steps": 61300, "loss": 0.1356, "lr": 3.462162758670895e-07, "epoch": 9.522838499184338, "percentage": 95.23, "elapsed_time": "16:19:16", "remaining_time": "0:49:04", "throughput": 2144.31, "total_tokens": 125992432} +{"current_steps": 58380, "total_steps": 61300, "loss": 0.3046, "lr": 3.4503677294527857e-07, "epoch": 9.523654159869494, "percentage": 95.24, "elapsed_time": "16:19:28", "remaining_time": "0:48:59", "throughput": 2144.03, "total_tokens": 126002576} +{"current_steps": 58385, "total_steps": 61300, "loss": 0.0091, "lr": 3.438592686798886e-07, "epoch": 9.52446982055465, "percentage": 95.24, "elapsed_time": "16:19:40", "remaining_time": "0:48:54", "throughput": 2143.76, "total_tokens": 126011920} +{"current_steps": 58390, "total_steps": 61300, "loss": 0.0039, "lr": 3.4268376316636816e-07, "epoch": 9.525285481239804, "percentage": 95.25, "elapsed_time": "16:19:54", "remaining_time": "0:48:50", "throughput": 2143.46, "total_tokens": 126022864} +{"current_steps": 58395, "total_steps": 61300, "loss": 0.0023, "lr": 3.4151025650001056e-07, "epoch": 9.52610114192496, "percentage": 95.26, "elapsed_time": "16:20:08", "remaining_time": "0:48:45", "throughput": 2143.13, "total_tokens": 126034960} +{"current_steps": 58400, "total_steps": 61300, "loss": 0.0151, "lr": 3.4033874877595074e-07, "epoch": 9.526916802610113, "percentage": 95.27, "elapsed_time": "16:20:22", "remaining_time": "0:48:40", "throughput": 2142.82, "total_tokens": 126046672} +{"current_steps": 58405, "total_steps": 61300, "loss": 0.0068, "lr": 3.3916924008915163e-07, "epoch": 9.52773246329527, "percentage": 95.28, "elapsed_time": "16:20:36", "remaining_time": "0:48:36", "throughput": 2142.51, "total_tokens": 126058000} +{"current_steps": 58410, "total_steps": 61300, "loss": 0.003, "lr": 3.3800173053442354e-07, "epoch": 9.528548123980425, "percentage": 95.29, "elapsed_time": "16:20:49", "remaining_time": "0:48:31", "throughput": 2142.23, "total_tokens": 126068496} +{"current_steps": 58415, "total_steps": 61300, "loss": 0.0331, "lr": 3.3683622020640736e-07, "epoch": 9.529363784665579, "percentage": 95.29, "elapsed_time": "16:21:01", "remaining_time": "0:48:27", "throughput": 2141.96, "total_tokens": 126078544} +{"current_steps": 58420, "total_steps": 61300, "loss": 0.318, "lr": 3.356727091995859e-07, "epoch": 9.530179445350734, "percentage": 95.3, "elapsed_time": "16:21:14", "remaining_time": "0:48:22", "throughput": 2141.66, "total_tokens": 126089712} +{"current_steps": 58425, "total_steps": 61300, "loss": 0.0792, "lr": 3.3451119760828374e-07, "epoch": 9.530995106035888, "percentage": 95.31, "elapsed_time": "16:21:27", "remaining_time": "0:48:17", "throughput": 2141.37, "total_tokens": 126100656} +{"current_steps": 58430, "total_steps": 61300, "loss": 0.2102, "lr": 3.333516855266533e-07, "epoch": 9.531810766721044, "percentage": 95.32, "elapsed_time": "16:21:40", "remaining_time": "0:48:13", "throughput": 2141.08, "total_tokens": 126111376} +{"current_steps": 58435, "total_steps": 61300, "loss": 0.0088, "lr": 3.321941730486916e-07, "epoch": 9.5326264274062, "percentage": 95.33, "elapsed_time": "16:21:54", "remaining_time": "0:48:08", "throughput": 2140.78, "total_tokens": 126122640} +{"current_steps": 58440, "total_steps": 61300, "loss": 0.0088, "lr": 3.3103866026823473e-07, "epoch": 9.533442088091354, "percentage": 95.33, "elapsed_time": "16:22:06", "remaining_time": "0:48:03", "throughput": 2140.51, "total_tokens": 126132432} +{"current_steps": 58445, "total_steps": 61300, "loss": 0.0028, "lr": 3.2988514727895217e-07, "epoch": 9.53425774877651, "percentage": 95.34, "elapsed_time": "16:22:19", "remaining_time": "0:47:59", "throughput": 2140.22, "total_tokens": 126142576} +{"current_steps": 58450, "total_steps": 61300, "loss": 0.0036, "lr": 3.287336341743524e-07, "epoch": 9.535073409461663, "percentage": 95.35, "elapsed_time": "16:22:32", "remaining_time": "0:47:54", "throughput": 2139.91, "total_tokens": 126153552} +{"current_steps": 58455, "total_steps": 61300, "loss": 0.1672, "lr": 3.275841210477887e-07, "epoch": 9.535889070146819, "percentage": 95.36, "elapsed_time": "16:22:46", "remaining_time": "0:47:49", "throughput": 2139.6, "total_tokens": 126165072} +{"current_steps": 58460, "total_steps": 61300, "loss": 0.007, "lr": 3.264366079924419e-07, "epoch": 9.536704730831975, "percentage": 95.37, "elapsed_time": "16:22:59", "remaining_time": "0:47:45", "throughput": 2139.32, "total_tokens": 126175696} +{"current_steps": 58465, "total_steps": 61300, "loss": 0.0553, "lr": 3.252910951013349e-07, "epoch": 9.537520391517129, "percentage": 95.38, "elapsed_time": "16:23:13", "remaining_time": "0:47:40", "throughput": 2139.01, "total_tokens": 126187088} +{"current_steps": 58470, "total_steps": 61300, "loss": 0.1925, "lr": 3.2414758246733234e-07, "epoch": 9.538336052202284, "percentage": 95.38, "elapsed_time": "16:23:26", "remaining_time": "0:47:35", "throughput": 2138.71, "total_tokens": 126198480} +{"current_steps": 58475, "total_steps": 61300, "loss": 0.0052, "lr": 3.2300607018312944e-07, "epoch": 9.539151712887438, "percentage": 95.39, "elapsed_time": "16:23:40", "remaining_time": "0:47:31", "throughput": 2138.4, "total_tokens": 126209904} +{"current_steps": 58480, "total_steps": 61300, "loss": 0.0042, "lr": 3.2186655834126335e-07, "epoch": 9.539967373572594, "percentage": 95.4, "elapsed_time": "16:23:52", "remaining_time": "0:47:26", "throughput": 2138.13, "total_tokens": 126219792} +{"current_steps": 58485, "total_steps": 61300, "loss": 0.0105, "lr": 3.207290470341101e-07, "epoch": 9.540783034257748, "percentage": 95.41, "elapsed_time": "16:24:05", "remaining_time": "0:47:21", "throughput": 2137.84, "total_tokens": 126230256} +{"current_steps": 58490, "total_steps": 61300, "loss": 0.1066, "lr": 3.1959353635388214e-07, "epoch": 9.541598694942904, "percentage": 95.42, "elapsed_time": "16:24:18", "remaining_time": "0:47:17", "throughput": 2137.55, "total_tokens": 126241136} +{"current_steps": 58495, "total_steps": 61300, "loss": 0.0069, "lr": 3.1846002639263074e-07, "epoch": 9.54241435562806, "percentage": 95.42, "elapsed_time": "16:24:32", "remaining_time": "0:47:12", "throughput": 2137.25, "total_tokens": 126252048} +{"current_steps": 58500, "total_steps": 61300, "loss": 0.1113, "lr": 3.17328517242238e-07, "epoch": 9.543230016313213, "percentage": 95.43, "elapsed_time": "16:24:44", "remaining_time": "0:47:07", "throughput": 2136.98, "total_tokens": 126262320} +{"current_steps": 58505, "total_steps": 61300, "loss": 0.3361, "lr": 3.161990089944389e-07, "epoch": 9.544045676998369, "percentage": 95.44, "elapsed_time": "16:24:56", "remaining_time": "0:47:03", "throughput": 2136.7, "total_tokens": 126272464} +{"current_steps": 58510, "total_steps": 61300, "loss": 0.0036, "lr": 3.150715017407907e-07, "epoch": 9.544861337683523, "percentage": 95.45, "elapsed_time": "16:25:10", "remaining_time": "0:46:58", "throughput": 2136.4, "total_tokens": 126283984} +{"current_steps": 58515, "total_steps": 61300, "loss": 0.0155, "lr": 3.1394599557269534e-07, "epoch": 9.545676998368679, "percentage": 95.46, "elapsed_time": "16:25:24", "remaining_time": "0:46:53", "throughput": 2136.1, "total_tokens": 126295024} +{"current_steps": 58520, "total_steps": 61300, "loss": 0.0909, "lr": 3.128224905813965e-07, "epoch": 9.546492659053834, "percentage": 95.46, "elapsed_time": "16:25:36", "remaining_time": "0:46:49", "throughput": 2135.82, "total_tokens": 126305296} +{"current_steps": 58525, "total_steps": 61300, "loss": 0.0051, "lr": 3.1170098685796565e-07, "epoch": 9.547308319738988, "percentage": 95.47, "elapsed_time": "16:25:50", "remaining_time": "0:46:44", "throughput": 2135.51, "total_tokens": 126317264} +{"current_steps": 58530, "total_steps": 61300, "loss": 0.0893, "lr": 3.1058148449331914e-07, "epoch": 9.548123980424144, "percentage": 95.48, "elapsed_time": "16:26:02", "remaining_time": "0:46:39", "throughput": 2135.25, "total_tokens": 126326640} +{"current_steps": 58535, "total_steps": 61300, "loss": 0.007, "lr": 3.09463983578212e-07, "epoch": 9.548939641109298, "percentage": 95.49, "elapsed_time": "16:26:15", "remaining_time": "0:46:35", "throughput": 2134.96, "total_tokens": 126337840} +{"current_steps": 58540, "total_steps": 61300, "loss": 0.1863, "lr": 3.0834848420323305e-07, "epoch": 9.549755301794454, "percentage": 95.5, "elapsed_time": "16:26:27", "remaining_time": "0:46:30", "throughput": 2134.69, "total_tokens": 126347792} +{"current_steps": 58545, "total_steps": 61300, "loss": 0.0073, "lr": 3.0723498645880976e-07, "epoch": 9.550570962479608, "percentage": 95.51, "elapsed_time": "16:26:41", "remaining_time": "0:46:25", "throughput": 2134.39, "total_tokens": 126359344} +{"current_steps": 58550, "total_steps": 61300, "loss": 0.1916, "lr": 3.061234904352089e-07, "epoch": 9.551386623164763, "percentage": 95.51, "elapsed_time": "16:26:54", "remaining_time": "0:46:21", "throughput": 2134.11, "total_tokens": 126370064} +{"current_steps": 58555, "total_steps": 61300, "loss": 0.0049, "lr": 3.0501399622253344e-07, "epoch": 9.552202283849919, "percentage": 95.52, "elapsed_time": "16:27:06", "remaining_time": "0:46:16", "throughput": 2133.86, "total_tokens": 126380080} +{"current_steps": 58560, "total_steps": 61300, "loss": 0.0072, "lr": 3.0390650391072527e-07, "epoch": 9.553017944535073, "percentage": 95.53, "elapsed_time": "16:27:18", "remaining_time": "0:46:11", "throughput": 2133.58, "total_tokens": 126390864} +{"current_steps": 58565, "total_steps": 61300, "loss": 0.0576, "lr": 3.028010135895598e-07, "epoch": 9.553833605220229, "percentage": 95.54, "elapsed_time": "16:27:32", "remaining_time": "0:46:07", "throughput": 2133.28, "total_tokens": 126402224} +{"current_steps": 58570, "total_steps": 61300, "loss": 0.0036, "lr": 3.016975253486598e-07, "epoch": 9.554649265905383, "percentage": 95.55, "elapsed_time": "16:27:44", "remaining_time": "0:46:02", "throughput": 2133.01, "total_tokens": 126412464} +{"current_steps": 58575, "total_steps": 61300, "loss": 0.0124, "lr": 3.0059603927747313e-07, "epoch": 9.555464926590538, "percentage": 95.55, "elapsed_time": "16:27:58", "remaining_time": "0:45:57", "throughput": 2132.7, "total_tokens": 126423600} +{"current_steps": 58580, "total_steps": 61300, "loss": 0.064, "lr": 2.9949655546529785e-07, "epoch": 9.556280587275694, "percentage": 95.56, "elapsed_time": "16:28:12", "remaining_time": "0:45:53", "throughput": 2132.4, "total_tokens": 126434928} +{"current_steps": 58585, "total_steps": 61300, "loss": 0.0051, "lr": 2.9839907400125986e-07, "epoch": 9.557096247960848, "percentage": 95.57, "elapsed_time": "16:28:24", "remaining_time": "0:45:48", "throughput": 2132.13, "total_tokens": 126444944} +{"current_steps": 58590, "total_steps": 61300, "loss": 0.1052, "lr": 2.973035949743269e-07, "epoch": 9.557911908646004, "percentage": 95.58, "elapsed_time": "16:28:38", "remaining_time": "0:45:43", "throughput": 2131.83, "total_tokens": 126456208} +{"current_steps": 58595, "total_steps": 61300, "loss": 0.0034, "lr": 2.9621011847330293e-07, "epoch": 9.558727569331158, "percentage": 95.59, "elapsed_time": "16:28:51", "remaining_time": "0:45:38", "throughput": 2131.54, "total_tokens": 126467312} +{"current_steps": 58600, "total_steps": 61300, "loss": 0.0099, "lr": 2.951186445868337e-07, "epoch": 9.559543230016313, "percentage": 95.6, "elapsed_time": "16:29:03", "remaining_time": "0:45:34", "throughput": 2131.27, "total_tokens": 126476656} +{"current_steps": 58605, "total_steps": 61300, "loss": 0.2067, "lr": 2.940291734034012e-07, "epoch": 9.560358890701469, "percentage": 95.6, "elapsed_time": "16:29:16", "remaining_time": "0:45:29", "throughput": 2130.98, "total_tokens": 126487920} +{"current_steps": 58610, "total_steps": 61300, "loss": 0.0046, "lr": 2.929417050113181e-07, "epoch": 9.561174551386623, "percentage": 95.61, "elapsed_time": "16:29:30", "remaining_time": "0:45:24", "throughput": 2130.69, "total_tokens": 126499216} +{"current_steps": 58615, "total_steps": 61300, "loss": 0.0045, "lr": 2.918562394987445e-07, "epoch": 9.561990212071779, "percentage": 95.62, "elapsed_time": "16:29:43", "remaining_time": "0:45:20", "throughput": 2130.4, "total_tokens": 126509936} +{"current_steps": 58620, "total_steps": 61300, "loss": 0.1327, "lr": 2.907727769536683e-07, "epoch": 9.562805872756933, "percentage": 95.63, "elapsed_time": "16:29:57", "remaining_time": "0:45:15", "throughput": 2130.08, "total_tokens": 126521776} +{"current_steps": 58625, "total_steps": 61300, "loss": 0.0051, "lr": 2.8969131746392763e-07, "epoch": 9.563621533442088, "percentage": 95.64, "elapsed_time": "16:30:10", "remaining_time": "0:45:10", "throughput": 2129.8, "total_tokens": 126532464} +{"current_steps": 58630, "total_steps": 61300, "loss": 0.0843, "lr": 2.886118611171884e-07, "epoch": 9.564437194127244, "percentage": 95.64, "elapsed_time": "16:30:23", "remaining_time": "0:45:06", "throughput": 2129.51, "total_tokens": 126542992} +{"current_steps": 58635, "total_steps": 61300, "loss": 0.1096, "lr": 2.875344080009529e-07, "epoch": 9.565252854812398, "percentage": 95.65, "elapsed_time": "16:30:36", "remaining_time": "0:45:01", "throughput": 2129.23, "total_tokens": 126553680} +{"current_steps": 58640, "total_steps": 61300, "loss": 0.0046, "lr": 2.8645895820257065e-07, "epoch": 9.566068515497554, "percentage": 95.66, "elapsed_time": "16:30:48", "remaining_time": "0:44:56", "throughput": 2128.97, "total_tokens": 126563440} +{"current_steps": 58645, "total_steps": 61300, "loss": 0.1721, "lr": 2.8538551180921913e-07, "epoch": 9.566884176182707, "percentage": 95.67, "elapsed_time": "16:31:01", "remaining_time": "0:44:51", "throughput": 2128.68, "total_tokens": 126573904} +{"current_steps": 58650, "total_steps": 61300, "loss": 0.2517, "lr": 2.8431406890792045e-07, "epoch": 9.567699836867863, "percentage": 95.68, "elapsed_time": "16:31:13", "remaining_time": "0:44:47", "throughput": 2128.4, "total_tokens": 126584560} +{"current_steps": 58655, "total_steps": 61300, "loss": 0.0046, "lr": 2.8324462958552735e-07, "epoch": 9.568515497553017, "percentage": 95.69, "elapsed_time": "16:31:27", "remaining_time": "0:44:42", "throughput": 2128.1, "total_tokens": 126595632} +{"current_steps": 58660, "total_steps": 61300, "loss": 0.0056, "lr": 2.821771939287371e-07, "epoch": 9.569331158238173, "percentage": 95.69, "elapsed_time": "16:31:40", "remaining_time": "0:44:37", "throughput": 2127.81, "total_tokens": 126606800} +{"current_steps": 58665, "total_steps": 61300, "loss": 0.102, "lr": 2.811117620240833e-07, "epoch": 9.570146818923329, "percentage": 95.7, "elapsed_time": "16:31:54", "remaining_time": "0:44:33", "throughput": 2127.51, "total_tokens": 126617808} +{"current_steps": 58670, "total_steps": 61300, "loss": 0.2518, "lr": 2.800483339579274e-07, "epoch": 9.570962479608482, "percentage": 95.71, "elapsed_time": "16:32:07", "remaining_time": "0:44:28", "throughput": 2127.22, "total_tokens": 126628720} +{"current_steps": 58675, "total_steps": 61300, "loss": 0.0066, "lr": 2.789869098164838e-07, "epoch": 9.571778140293638, "percentage": 95.72, "elapsed_time": "16:32:21", "remaining_time": "0:44:23", "throughput": 2126.93, "total_tokens": 126639664} +{"current_steps": 58680, "total_steps": 61300, "loss": 0.0032, "lr": 2.779274896857947e-07, "epoch": 9.572593800978792, "percentage": 95.73, "elapsed_time": "16:32:34", "remaining_time": "0:44:19", "throughput": 2126.64, "total_tokens": 126650736} +{"current_steps": 58685, "total_steps": 61300, "loss": 0.16, "lr": 2.768700736517416e-07, "epoch": 9.573409461663948, "percentage": 95.73, "elapsed_time": "16:32:48", "remaining_time": "0:44:14", "throughput": 2126.34, "total_tokens": 126662224} +{"current_steps": 58690, "total_steps": 61300, "loss": 0.0052, "lr": 2.7581466180004454e-07, "epoch": 9.574225122349104, "percentage": 95.74, "elapsed_time": "16:33:01", "remaining_time": "0:44:09", "throughput": 2126.05, "total_tokens": 126673040} +{"current_steps": 58695, "total_steps": 61300, "loss": 0.0087, "lr": 2.747612542162603e-07, "epoch": 9.575040783034257, "percentage": 95.75, "elapsed_time": "16:33:14", "remaining_time": "0:44:04", "throughput": 2125.77, "total_tokens": 126683824} +{"current_steps": 58700, "total_steps": 61300, "loss": 0.0068, "lr": 2.737098509857816e-07, "epoch": 9.575856443719413, "percentage": 95.76, "elapsed_time": "16:33:25", "remaining_time": "0:44:00", "throughput": 2125.52, "total_tokens": 126693488} +{"current_steps": 58705, "total_steps": 61300, "loss": 0.2255, "lr": 2.726604521938458e-07, "epoch": 9.576672104404567, "percentage": 95.77, "elapsed_time": "16:33:38", "remaining_time": "0:43:55", "throughput": 2125.24, "total_tokens": 126703888} +{"current_steps": 58710, "total_steps": 61300, "loss": 0.1504, "lr": 2.716130579255155e-07, "epoch": 9.577487765089723, "percentage": 95.77, "elapsed_time": "16:33:52", "remaining_time": "0:43:50", "throughput": 2124.94, "total_tokens": 126715440} +{"current_steps": 58715, "total_steps": 61300, "loss": 0.2826, "lr": 2.7056766826570045e-07, "epoch": 9.578303425774878, "percentage": 95.78, "elapsed_time": "16:34:04", "remaining_time": "0:43:45", "throughput": 2124.67, "total_tokens": 126725680} +{"current_steps": 58720, "total_steps": 61300, "loss": 0.0382, "lr": 2.6952428329914956e-07, "epoch": 9.579119086460032, "percentage": 95.79, "elapsed_time": "16:34:17", "remaining_time": "0:43:41", "throughput": 2124.39, "total_tokens": 126736144} +{"current_steps": 58725, "total_steps": 61300, "loss": 0.0664, "lr": 2.684829031104397e-07, "epoch": 9.579934747145188, "percentage": 95.8, "elapsed_time": "16:34:31", "remaining_time": "0:43:36", "throughput": 2124.09, "total_tokens": 126747504} +{"current_steps": 58730, "total_steps": 61300, "loss": 0.0955, "lr": 2.6744352778399204e-07, "epoch": 9.580750407830342, "percentage": 95.81, "elapsed_time": "16:34:44", "remaining_time": "0:43:31", "throughput": 2123.81, "total_tokens": 126757904} +{"current_steps": 58735, "total_steps": 61300, "loss": 0.006, "lr": 2.6640615740406436e-07, "epoch": 9.581566068515498, "percentage": 95.82, "elapsed_time": "16:34:56", "remaining_time": "0:43:27", "throughput": 2123.53, "total_tokens": 126768400} +{"current_steps": 58740, "total_steps": 61300, "loss": 0.2567, "lr": 2.6537079205475323e-07, "epoch": 9.582381729200652, "percentage": 95.82, "elapsed_time": "16:35:10", "remaining_time": "0:43:22", "throughput": 2123.24, "total_tokens": 126779440} +{"current_steps": 58745, "total_steps": 61300, "loss": 0.1049, "lr": 2.6433743181998316e-07, "epoch": 9.583197389885807, "percentage": 95.83, "elapsed_time": "16:35:23", "remaining_time": "0:43:17", "throughput": 2122.95, "total_tokens": 126790672} +{"current_steps": 58750, "total_steps": 61300, "loss": 0.0074, "lr": 2.633060767835316e-07, "epoch": 9.584013050570963, "percentage": 95.84, "elapsed_time": "16:35:35", "remaining_time": "0:43:12", "throughput": 2122.69, "total_tokens": 126799824} +{"current_steps": 58755, "total_steps": 61300, "loss": 0.0064, "lr": 2.6227672702900106e-07, "epoch": 9.584828711256117, "percentage": 95.85, "elapsed_time": "16:35:49", "remaining_time": "0:43:08", "throughput": 2122.39, "total_tokens": 126811248} +{"current_steps": 58760, "total_steps": 61300, "loss": 0.2699, "lr": 2.61249382639836e-07, "epoch": 9.585644371941273, "percentage": 95.86, "elapsed_time": "16:36:02", "remaining_time": "0:43:03", "throughput": 2122.09, "total_tokens": 126822256} +{"current_steps": 58765, "total_steps": 61300, "loss": 0.1239, "lr": 2.6022404369931976e-07, "epoch": 9.586460032626427, "percentage": 95.86, "elapsed_time": "16:36:16", "remaining_time": "0:42:58", "throughput": 2121.79, "total_tokens": 126833840} +{"current_steps": 58770, "total_steps": 61300, "loss": 0.0034, "lr": 2.592007102905719e-07, "epoch": 9.587275693311582, "percentage": 95.87, "elapsed_time": "16:36:31", "remaining_time": "0:42:53", "throughput": 2121.48, "total_tokens": 126846160} +{"current_steps": 58775, "total_steps": 61300, "loss": 0.0056, "lr": 2.581793824965484e-07, "epoch": 9.588091353996738, "percentage": 95.88, "elapsed_time": "16:36:45", "remaining_time": "0:42:49", "throughput": 2121.16, "total_tokens": 126857904} +{"current_steps": 58780, "total_steps": 61300, "loss": 0.0447, "lr": 2.5716006040004123e-07, "epoch": 9.588907014681892, "percentage": 95.89, "elapsed_time": "16:36:59", "remaining_time": "0:42:44", "throughput": 2120.87, "total_tokens": 126869232} +{"current_steps": 58785, "total_steps": 61300, "loss": 0.0054, "lr": 2.5614274408368444e-07, "epoch": 9.589722675367048, "percentage": 95.9, "elapsed_time": "16:37:13", "remaining_time": "0:42:39", "throughput": 2120.57, "total_tokens": 126880784} +{"current_steps": 58790, "total_steps": 61300, "loss": 0.0184, "lr": 2.5512743362994527e-07, "epoch": 9.590538336052202, "percentage": 95.91, "elapsed_time": "16:37:26", "remaining_time": "0:42:35", "throughput": 2120.28, "total_tokens": 126891600} +{"current_steps": 58795, "total_steps": 61300, "loss": 0.1118, "lr": 2.541141291211302e-07, "epoch": 9.591353996737357, "percentage": 95.91, "elapsed_time": "16:37:40", "remaining_time": "0:42:30", "throughput": 2119.99, "total_tokens": 126903056} +{"current_steps": 58800, "total_steps": 61300, "loss": 0.0585, "lr": 2.5310283063938457e-07, "epoch": 9.592169657422513, "percentage": 95.92, "elapsed_time": "16:37:53", "remaining_time": "0:42:25", "throughput": 2119.71, "total_tokens": 126914032} +{"current_steps": 58805, "total_steps": 61300, "loss": 0.2212, "lr": 2.5209353826668726e-07, "epoch": 9.592985318107667, "percentage": 95.93, "elapsed_time": "16:38:05", "remaining_time": "0:42:20", "throughput": 2119.44, "total_tokens": 126923920} +{"current_steps": 58810, "total_steps": 61300, "loss": 0.0046, "lr": 2.510862520848589e-07, "epoch": 9.593800978792823, "percentage": 95.94, "elapsed_time": "16:38:19", "remaining_time": "0:42:16", "throughput": 2119.14, "total_tokens": 126935216} +{"current_steps": 58815, "total_steps": 61300, "loss": 0.0042, "lr": 2.500809721755509e-07, "epoch": 9.594616639477977, "percentage": 95.95, "elapsed_time": "16:38:31", "remaining_time": "0:42:11", "throughput": 2118.89, "total_tokens": 126944752} +{"current_steps": 58820, "total_steps": 61300, "loss": 0.0914, "lr": 2.490776986202592e-07, "epoch": 9.595432300163132, "percentage": 95.95, "elapsed_time": "16:38:44", "remaining_time": "0:42:06", "throughput": 2118.6, "total_tokens": 126955856} +{"current_steps": 58825, "total_steps": 61300, "loss": 0.0081, "lr": 2.480764315003159e-07, "epoch": 9.596247960848288, "percentage": 95.96, "elapsed_time": "16:38:57", "remaining_time": "0:42:01", "throughput": 2118.32, "total_tokens": 126966064} +{"current_steps": 58830, "total_steps": 61300, "loss": 0.116, "lr": 2.470771708968866e-07, "epoch": 9.597063621533442, "percentage": 95.97, "elapsed_time": "16:39:10", "remaining_time": "0:41:57", "throughput": 2118.03, "total_tokens": 126977424} +{"current_steps": 58835, "total_steps": 61300, "loss": 0.1095, "lr": 2.4607991689097607e-07, "epoch": 9.597879282218598, "percentage": 95.98, "elapsed_time": "16:39:23", "remaining_time": "0:41:52", "throughput": 2117.77, "total_tokens": 126987728} +{"current_steps": 58840, "total_steps": 61300, "loss": 0.1991, "lr": 2.4508466956343066e-07, "epoch": 9.598694942903752, "percentage": 95.99, "elapsed_time": "16:39:36", "remaining_time": "0:41:47", "throughput": 2117.48, "total_tokens": 126999536} +{"current_steps": 58845, "total_steps": 61300, "loss": 0.1479, "lr": 2.4409142899492474e-07, "epoch": 9.599510603588907, "percentage": 96.0, "elapsed_time": "16:39:50", "remaining_time": "0:41:42", "throughput": 2117.19, "total_tokens": 127010384} +{"current_steps": 58850, "total_steps": 61300, "loss": 0.0055, "lr": 2.4310019526597726e-07, "epoch": 9.600326264274061, "percentage": 96.0, "elapsed_time": "16:40:01", "remaining_time": "0:41:37", "throughput": 2116.94, "total_tokens": 127020176} +{"current_steps": 58855, "total_steps": 61300, "loss": 0.0673, "lr": 2.4211096845694336e-07, "epoch": 9.601141924959217, "percentage": 96.01, "elapsed_time": "16:40:13", "remaining_time": "0:41:33", "throughput": 2116.68, "total_tokens": 127030192} +{"current_steps": 58860, "total_steps": 61300, "loss": 0.0073, "lr": 2.411237486480145e-07, "epoch": 9.601957585644373, "percentage": 96.02, "elapsed_time": "16:40:27", "remaining_time": "0:41:28", "throughput": 2116.39, "total_tokens": 127041808} +{"current_steps": 58865, "total_steps": 61300, "loss": 0.089, "lr": 2.4013853591922097e-07, "epoch": 9.602773246329527, "percentage": 96.03, "elapsed_time": "16:40:40", "remaining_time": "0:41:23", "throughput": 2116.11, "total_tokens": 127052400} +{"current_steps": 58870, "total_steps": 61300, "loss": 0.1119, "lr": 2.391553303504296e-07, "epoch": 9.603588907014682, "percentage": 96.04, "elapsed_time": "16:40:53", "remaining_time": "0:41:18", "throughput": 2115.84, "total_tokens": 127063056} +{"current_steps": 58875, "total_steps": 61300, "loss": 0.094, "lr": 2.3817413202134041e-07, "epoch": 9.604404567699836, "percentage": 96.04, "elapsed_time": "16:41:06", "remaining_time": "0:41:14", "throughput": 2115.56, "total_tokens": 127073840} +{"current_steps": 58880, "total_steps": 61300, "loss": 0.079, "lr": 2.3719494101149543e-07, "epoch": 9.605220228384992, "percentage": 96.05, "elapsed_time": "16:41:19", "remaining_time": "0:41:09", "throughput": 2115.28, "total_tokens": 127084656} +{"current_steps": 58885, "total_steps": 61300, "loss": 0.008, "lr": 2.3621775740027553e-07, "epoch": 9.606035889070148, "percentage": 96.06, "elapsed_time": "16:41:32", "remaining_time": "0:41:04", "throughput": 2115.0, "total_tokens": 127095984} +{"current_steps": 58890, "total_steps": 61300, "loss": 0.0222, "lr": 2.3524258126689235e-07, "epoch": 9.606851549755302, "percentage": 96.07, "elapsed_time": "16:41:44", "remaining_time": "0:40:59", "throughput": 2114.73, "total_tokens": 127105776} +{"current_steps": 58895, "total_steps": 61300, "loss": 0.1309, "lr": 2.3426941269040213e-07, "epoch": 9.607667210440457, "percentage": 96.08, "elapsed_time": "16:41:58", "remaining_time": "0:40:54", "throughput": 2114.43, "total_tokens": 127117424} +{"current_steps": 58900, "total_steps": 61300, "loss": 0.0962, "lr": 2.3329825174969455e-07, "epoch": 9.608482871125611, "percentage": 96.08, "elapsed_time": "16:42:11", "remaining_time": "0:40:50", "throughput": 2114.16, "total_tokens": 127128240} +{"current_steps": 58905, "total_steps": 61300, "loss": 0.0089, "lr": 2.3232909852349273e-07, "epoch": 9.609298531810767, "percentage": 96.09, "elapsed_time": "16:42:26", "remaining_time": "0:40:45", "throughput": 2113.85, "total_tokens": 127140176} +{"current_steps": 58910, "total_steps": 61300, "loss": 0.0106, "lr": 2.3136195309036435e-07, "epoch": 9.61011419249592, "percentage": 96.1, "elapsed_time": "16:42:37", "remaining_time": "0:40:40", "throughput": 2113.62, "total_tokens": 127149392} +{"current_steps": 58915, "total_steps": 61300, "loss": 0.0066, "lr": 2.303968155287134e-07, "epoch": 9.610929853181077, "percentage": 96.11, "elapsed_time": "16:42:50", "remaining_time": "0:40:35", "throughput": 2113.33, "total_tokens": 127160496} +{"current_steps": 58920, "total_steps": 61300, "loss": 0.0062, "lr": 2.294336859167745e-07, "epoch": 9.611745513866232, "percentage": 96.12, "elapsed_time": "16:43:03", "remaining_time": "0:40:31", "throughput": 2113.06, "total_tokens": 127170544} +{"current_steps": 58925, "total_steps": 61300, "loss": 0.1002, "lr": 2.2847256433262686e-07, "epoch": 9.612561174551386, "percentage": 96.13, "elapsed_time": "16:43:17", "remaining_time": "0:40:26", "throughput": 2112.74, "total_tokens": 127182992} +{"current_steps": 58930, "total_steps": 61300, "loss": 0.1272, "lr": 2.2751345085418042e-07, "epoch": 9.613376835236542, "percentage": 96.13, "elapsed_time": "16:43:31", "remaining_time": "0:40:21", "throughput": 2112.45, "total_tokens": 127194320} +{"current_steps": 58935, "total_steps": 61300, "loss": 0.1013, "lr": 2.265563455591896e-07, "epoch": 9.614192495921696, "percentage": 96.14, "elapsed_time": "16:43:45", "remaining_time": "0:40:16", "throughput": 2112.16, "total_tokens": 127205776} +{"current_steps": 58940, "total_steps": 61300, "loss": 0.1296, "lr": 2.2560124852523955e-07, "epoch": 9.615008156606851, "percentage": 96.15, "elapsed_time": "16:43:59", "remaining_time": "0:40:12", "throughput": 2111.86, "total_tokens": 127217264} +{"current_steps": 58945, "total_steps": 61300, "loss": 0.1324, "lr": 2.246481598297573e-07, "epoch": 9.615823817292007, "percentage": 96.16, "elapsed_time": "16:44:14", "remaining_time": "0:40:07", "throughput": 2111.55, "total_tokens": 127229584} +{"current_steps": 58950, "total_steps": 61300, "loss": 0.126, "lr": 2.2369707955000318e-07, "epoch": 9.616639477977161, "percentage": 96.17, "elapsed_time": "16:44:26", "remaining_time": "0:40:02", "throughput": 2111.28, "total_tokens": 127239824} +{"current_steps": 58955, "total_steps": 61300, "loss": 0.082, "lr": 2.2274800776307946e-07, "epoch": 9.617455138662317, "percentage": 96.17, "elapsed_time": "16:44:39", "remaining_time": "0:39:57", "throughput": 2111.0, "total_tokens": 127250672} +{"current_steps": 58960, "total_steps": 61300, "loss": 0.1262, "lr": 2.2180094454591903e-07, "epoch": 9.61827079934747, "percentage": 96.18, "elapsed_time": "16:44:52", "remaining_time": "0:39:52", "throughput": 2110.73, "total_tokens": 127260496} +{"current_steps": 58965, "total_steps": 61300, "loss": 0.1803, "lr": 2.2085588997529938e-07, "epoch": 9.619086460032626, "percentage": 96.19, "elapsed_time": "16:45:06", "remaining_time": "0:39:48", "throughput": 2110.44, "total_tokens": 127272336} +{"current_steps": 58970, "total_steps": 61300, "loss": 0.0042, "lr": 2.1991284412782864e-07, "epoch": 9.619902120717782, "percentage": 96.2, "elapsed_time": "16:45:20", "remaining_time": "0:39:43", "throughput": 2110.14, "total_tokens": 127284368} +{"current_steps": 58975, "total_steps": 61300, "loss": 0.0773, "lr": 2.18971807079954e-07, "epoch": 9.620717781402936, "percentage": 96.21, "elapsed_time": "16:45:32", "remaining_time": "0:39:38", "throughput": 2109.89, "total_tokens": 127294032} +{"current_steps": 58980, "total_steps": 61300, "loss": 0.1303, "lr": 2.1803277890796447e-07, "epoch": 9.621533442088092, "percentage": 96.22, "elapsed_time": "16:45:44", "remaining_time": "0:39:33", "throughput": 2109.63, "total_tokens": 127304080} +{"current_steps": 58985, "total_steps": 61300, "loss": 0.0539, "lr": 2.170957596879797e-07, "epoch": 9.622349102773246, "percentage": 96.22, "elapsed_time": "16:45:58", "remaining_time": "0:39:28", "throughput": 2109.32, "total_tokens": 127315888} +{"current_steps": 58990, "total_steps": 61300, "loss": 0.0056, "lr": 2.1616074949595832e-07, "epoch": 9.623164763458401, "percentage": 96.23, "elapsed_time": "16:46:11", "remaining_time": "0:39:24", "throughput": 2109.05, "total_tokens": 127326864} +{"current_steps": 58995, "total_steps": 61300, "loss": 0.011, "lr": 2.1522774840770087e-07, "epoch": 9.623980424143557, "percentage": 96.24, "elapsed_time": "16:46:23", "remaining_time": "0:39:19", "throughput": 2108.79, "total_tokens": 127336368} +{"current_steps": 59000, "total_steps": 61300, "loss": 0.0277, "lr": 2.1429675649883575e-07, "epoch": 9.624796084828711, "percentage": 96.25, "elapsed_time": "16:46:37", "remaining_time": "0:39:14", "throughput": 2108.51, "total_tokens": 127347824} +{"current_steps": 59005, "total_steps": 61300, "loss": 0.1964, "lr": 2.1336777384484141e-07, "epoch": 9.625611745513867, "percentage": 96.26, "elapsed_time": "16:46:47", "remaining_time": "0:39:09", "throughput": 2108.28, "total_tokens": 127356656} +{"current_steps": 59010, "total_steps": 61300, "loss": 0.2314, "lr": 2.1244080052101879e-07, "epoch": 9.62642740619902, "percentage": 96.26, "elapsed_time": "16:47:00", "remaining_time": "0:39:04", "throughput": 2108.0, "total_tokens": 127367120} +{"current_steps": 59015, "total_steps": 61300, "loss": 0.0108, "lr": 2.115158366025133e-07, "epoch": 9.627243066884176, "percentage": 96.27, "elapsed_time": "16:47:14", "remaining_time": "0:38:59", "throughput": 2107.71, "total_tokens": 127378800} +{"current_steps": 59020, "total_steps": 61300, "loss": 0.1045, "lr": 2.1059288216431217e-07, "epoch": 9.62805872756933, "percentage": 96.28, "elapsed_time": "16:47:27", "remaining_time": "0:38:55", "throughput": 2107.44, "total_tokens": 127390000} +{"current_steps": 59025, "total_steps": 61300, "loss": 0.0032, "lr": 2.0967193728123334e-07, "epoch": 9.628874388254486, "percentage": 96.29, "elapsed_time": "16:47:40", "remaining_time": "0:38:50", "throughput": 2107.18, "total_tokens": 127400144} +{"current_steps": 59030, "total_steps": 61300, "loss": 0.0743, "lr": 2.0875300202793101e-07, "epoch": 9.629690048939642, "percentage": 96.3, "elapsed_time": "16:47:53", "remaining_time": "0:38:45", "throughput": 2106.89, "total_tokens": 127411568} +{"current_steps": 59035, "total_steps": 61300, "loss": 0.0704, "lr": 2.0783607647889837e-07, "epoch": 9.630505709624796, "percentage": 96.31, "elapsed_time": "16:48:05", "remaining_time": "0:38:40", "throughput": 2106.64, "total_tokens": 127421520} +{"current_steps": 59040, "total_steps": 61300, "loss": 0.1032, "lr": 2.0692116070847035e-07, "epoch": 9.631321370309951, "percentage": 96.31, "elapsed_time": "16:48:19", "remaining_time": "0:38:35", "throughput": 2106.34, "total_tokens": 127433424} +{"current_steps": 59045, "total_steps": 61300, "loss": 0.0048, "lr": 2.0600825479080986e-07, "epoch": 9.632137030995105, "percentage": 96.32, "elapsed_time": "16:48:32", "remaining_time": "0:38:31", "throughput": 2106.08, "total_tokens": 127443408} +{"current_steps": 59050, "total_steps": 61300, "loss": 0.0084, "lr": 2.0509735879992442e-07, "epoch": 9.632952691680261, "percentage": 96.33, "elapsed_time": "16:48:45", "remaining_time": "0:38:26", "throughput": 2105.8, "total_tokens": 127454256} +{"current_steps": 59055, "total_steps": 61300, "loss": 0.1546, "lr": 2.041884728096549e-07, "epoch": 9.633768352365417, "percentage": 96.34, "elapsed_time": "16:48:57", "remaining_time": "0:38:21", "throughput": 2105.53, "total_tokens": 127464624} +{"current_steps": 59060, "total_steps": 61300, "loss": 0.0904, "lr": 2.0328159689368133e-07, "epoch": 9.63458401305057, "percentage": 96.35, "elapsed_time": "16:49:09", "remaining_time": "0:38:16", "throughput": 2105.29, "total_tokens": 127474192} +{"current_steps": 59065, "total_steps": 61300, "loss": 0.0083, "lr": 2.0237673112551704e-07, "epoch": 9.635399673735726, "percentage": 96.35, "elapsed_time": "16:49:20", "remaining_time": "0:38:11", "throughput": 2105.06, "total_tokens": 127483056} +{"current_steps": 59070, "total_steps": 61300, "loss": 0.1021, "lr": 2.0147387557851727e-07, "epoch": 9.63621533442088, "percentage": 96.36, "elapsed_time": "16:49:32", "remaining_time": "0:38:06", "throughput": 2104.79, "total_tokens": 127493360} +{"current_steps": 59075, "total_steps": 61300, "loss": 0.1274, "lr": 2.005730303258735e-07, "epoch": 9.637030995106036, "percentage": 96.37, "elapsed_time": "16:49:45", "remaining_time": "0:38:01", "throughput": 2104.53, "total_tokens": 127503728} +{"current_steps": 59080, "total_steps": 61300, "loss": 0.0038, "lr": 1.9967419544060784e-07, "epoch": 9.63784665579119, "percentage": 96.38, "elapsed_time": "16:49:58", "remaining_time": "0:37:57", "throughput": 2104.25, "total_tokens": 127514672} +{"current_steps": 59085, "total_steps": 61300, "loss": 0.0049, "lr": 1.987773709955898e-07, "epoch": 9.638662316476346, "percentage": 96.39, "elapsed_time": "16:50:11", "remaining_time": "0:37:52", "throughput": 2103.97, "total_tokens": 127525200} +{"current_steps": 59090, "total_steps": 61300, "loss": 0.1041, "lr": 1.9788255706351678e-07, "epoch": 9.639477977161501, "percentage": 96.39, "elapsed_time": "16:50:24", "remaining_time": "0:37:47", "throughput": 2103.7, "total_tokens": 127535824} +{"current_steps": 59095, "total_steps": 61300, "loss": 0.0148, "lr": 1.9698975371693075e-07, "epoch": 9.640293637846655, "percentage": 96.4, "elapsed_time": "16:50:37", "remaining_time": "0:37:42", "throughput": 2103.42, "total_tokens": 127546960} +{"current_steps": 59100, "total_steps": 61300, "loss": 0.0097, "lr": 1.9609896102820157e-07, "epoch": 9.641109298531811, "percentage": 96.41, "elapsed_time": "16:50:50", "remaining_time": "0:37:37", "throughput": 2103.15, "total_tokens": 127557680} +{"current_steps": 59105, "total_steps": 61300, "loss": 0.0218, "lr": 1.9521017906954654e-07, "epoch": 9.641924959216965, "percentage": 96.42, "elapsed_time": "16:51:03", "remaining_time": "0:37:32", "throughput": 2102.89, "total_tokens": 127567696} +{"current_steps": 59110, "total_steps": 61300, "loss": 0.1024, "lr": 1.9432340791301073e-07, "epoch": 9.64274061990212, "percentage": 96.43, "elapsed_time": "16:51:16", "remaining_time": "0:37:28", "throughput": 2102.61, "total_tokens": 127578736} +{"current_steps": 59115, "total_steps": 61300, "loss": 0.0236, "lr": 1.9343864763048392e-07, "epoch": 9.643556280587276, "percentage": 96.44, "elapsed_time": "16:51:30", "remaining_time": "0:37:23", "throughput": 2102.32, "total_tokens": 127590224} +{"current_steps": 59120, "total_steps": 61300, "loss": 0.0045, "lr": 1.925558982936865e-07, "epoch": 9.64437194127243, "percentage": 96.44, "elapsed_time": "16:51:43", "remaining_time": "0:37:18", "throughput": 2102.04, "total_tokens": 127601328} +{"current_steps": 59125, "total_steps": 61300, "loss": 0.0041, "lr": 1.916751599741806e-07, "epoch": 9.645187601957586, "percentage": 96.45, "elapsed_time": "16:51:57", "remaining_time": "0:37:13", "throughput": 2101.75, "total_tokens": 127612464} +{"current_steps": 59130, "total_steps": 61300, "loss": 0.0048, "lr": 1.90796432743362e-07, "epoch": 9.64600326264274, "percentage": 96.46, "elapsed_time": "16:52:09", "remaining_time": "0:37:08", "throughput": 2101.49, "total_tokens": 127622864} +{"current_steps": 59135, "total_steps": 61300, "loss": 0.0504, "lr": 1.8991971667246533e-07, "epoch": 9.646818923327896, "percentage": 96.47, "elapsed_time": "16:52:23", "remaining_time": "0:37:03", "throughput": 2101.19, "total_tokens": 127634000} +{"current_steps": 59140, "total_steps": 61300, "loss": 0.0101, "lr": 1.8904501183256152e-07, "epoch": 9.647634584013051, "percentage": 96.48, "elapsed_time": "16:52:37", "remaining_time": "0:36:59", "throughput": 2100.91, "total_tokens": 127645264} +{"current_steps": 59145, "total_steps": 61300, "loss": 0.0049, "lr": 1.8817231829455773e-07, "epoch": 9.648450244698205, "percentage": 96.48, "elapsed_time": "16:52:49", "remaining_time": "0:36:54", "throughput": 2100.65, "total_tokens": 127655376} +{"current_steps": 59150, "total_steps": 61300, "loss": 0.2531, "lr": 1.8730163612920015e-07, "epoch": 9.649265905383361, "percentage": 96.49, "elapsed_time": "16:53:01", "remaining_time": "0:36:49", "throughput": 2100.39, "total_tokens": 127665584} +{"current_steps": 59155, "total_steps": 61300, "loss": 0.1174, "lr": 1.8643296540707121e-07, "epoch": 9.650081566068515, "percentage": 96.5, "elapsed_time": "16:53:14", "remaining_time": "0:36:44", "throughput": 2100.12, "total_tokens": 127675920} +{"current_steps": 59160, "total_steps": 61300, "loss": 0.005, "lr": 1.855663061985896e-07, "epoch": 9.65089722675367, "percentage": 96.51, "elapsed_time": "16:53:27", "remaining_time": "0:36:39", "throughput": 2099.85, "total_tokens": 127686928} +{"current_steps": 59165, "total_steps": 61300, "loss": 0.0042, "lr": 1.8470165857401023e-07, "epoch": 9.651712887438826, "percentage": 96.52, "elapsed_time": "16:53:40", "remaining_time": "0:36:34", "throughput": 2099.59, "total_tokens": 127697296} +{"current_steps": 59170, "total_steps": 61300, "loss": 0.1246, "lr": 1.8383902260342422e-07, "epoch": 9.65252854812398, "percentage": 96.53, "elapsed_time": "16:53:52", "remaining_time": "0:36:29", "throughput": 2099.33, "total_tokens": 127707312} +{"current_steps": 59175, "total_steps": 61300, "loss": 0.0052, "lr": 1.8297839835676456e-07, "epoch": 9.653344208809136, "percentage": 96.53, "elapsed_time": "16:54:06", "remaining_time": "0:36:25", "throughput": 2099.02, "total_tokens": 127719056} +{"current_steps": 59180, "total_steps": 61300, "loss": 0.092, "lr": 1.8211978590379486e-07, "epoch": 9.65415986949429, "percentage": 96.54, "elapsed_time": "16:54:21", "remaining_time": "0:36:20", "throughput": 2098.72, "total_tokens": 127730864} +{"current_steps": 59185, "total_steps": 61300, "loss": 0.0627, "lr": 1.8126318531412056e-07, "epoch": 9.654975530179446, "percentage": 96.55, "elapsed_time": "16:54:33", "remaining_time": "0:36:15", "throughput": 2098.47, "total_tokens": 127740944} +{"current_steps": 59190, "total_steps": 61300, "loss": 0.0032, "lr": 1.8040859665718057e-07, "epoch": 9.655791190864601, "percentage": 96.56, "elapsed_time": "16:54:46", "remaining_time": "0:36:10", "throughput": 2098.19, "total_tokens": 127752016} +{"current_steps": 59195, "total_steps": 61300, "loss": 0.0033, "lr": 1.795560200022528e-07, "epoch": 9.656606851549755, "percentage": 96.57, "elapsed_time": "16:54:59", "remaining_time": "0:36:05", "throughput": 2097.93, "total_tokens": 127762480} +{"current_steps": 59200, "total_steps": 61300, "loss": 0.095, "lr": 1.7870545541845418e-07, "epoch": 9.65742251223491, "percentage": 96.57, "elapsed_time": "16:55:12", "remaining_time": "0:36:00", "throughput": 2097.64, "total_tokens": 127773232} +{"current_steps": 59205, "total_steps": 61300, "loss": 0.0082, "lr": 1.7785690297473234e-07, "epoch": 9.658238172920065, "percentage": 96.58, "elapsed_time": "16:55:26", "remaining_time": "0:35:55", "throughput": 2097.36, "total_tokens": 127784112} +{"current_steps": 59210, "total_steps": 61300, "loss": 0.1416, "lr": 1.770103627398767e-07, "epoch": 9.65905383360522, "percentage": 96.59, "elapsed_time": "16:55:39", "remaining_time": "0:35:51", "throughput": 2097.07, "total_tokens": 127795600} +{"current_steps": 59215, "total_steps": 61300, "loss": 0.1384, "lr": 1.7616583478251013e-07, "epoch": 9.659869494290374, "percentage": 96.6, "elapsed_time": "16:55:52", "remaining_time": "0:35:46", "throughput": 2096.82, "total_tokens": 127805648} +{"current_steps": 59220, "total_steps": 61300, "loss": 0.014, "lr": 1.7532331917109457e-07, "epoch": 9.66068515497553, "percentage": 96.61, "elapsed_time": "16:56:05", "remaining_time": "0:35:41", "throughput": 2096.55, "total_tokens": 127816560} +{"current_steps": 59225, "total_steps": 61300, "loss": 0.1847, "lr": 1.7448281597393368e-07, "epoch": 9.661500815660686, "percentage": 96.62, "elapsed_time": "16:56:19", "remaining_time": "0:35:36", "throughput": 2096.25, "total_tokens": 127828784} +{"current_steps": 59230, "total_steps": 61300, "loss": 0.0053, "lr": 1.736443252591563e-07, "epoch": 9.66231647634584, "percentage": 96.62, "elapsed_time": "16:56:32", "remaining_time": "0:35:31", "throughput": 2095.98, "total_tokens": 127839088} +{"current_steps": 59235, "total_steps": 61300, "loss": 0.0703, "lr": 1.7280784709473862e-07, "epoch": 9.663132137030995, "percentage": 96.63, "elapsed_time": "16:56:43", "remaining_time": "0:35:26", "throughput": 2095.76, "total_tokens": 127848016} +{"current_steps": 59240, "total_steps": 61300, "loss": 0.0819, "lr": 1.719733815484903e-07, "epoch": 9.66394779771615, "percentage": 96.64, "elapsed_time": "16:56:56", "remaining_time": "0:35:21", "throughput": 2095.49, "total_tokens": 127858320} +{"current_steps": 59245, "total_steps": 61300, "loss": 0.2399, "lr": 1.7114092868805443e-07, "epoch": 9.664763458401305, "percentage": 96.65, "elapsed_time": "16:57:09", "remaining_time": "0:35:16", "throughput": 2095.2, "total_tokens": 127869936} +{"current_steps": 59250, "total_steps": 61300, "loss": 0.008, "lr": 1.7031048858091313e-07, "epoch": 9.66557911908646, "percentage": 96.66, "elapsed_time": "16:57:23", "remaining_time": "0:35:12", "throughput": 2094.92, "total_tokens": 127881040} +{"current_steps": 59255, "total_steps": 61300, "loss": 0.2172, "lr": 1.6948206129439037e-07, "epoch": 9.666394779771615, "percentage": 96.66, "elapsed_time": "16:57:36", "remaining_time": "0:35:07", "throughput": 2094.66, "total_tokens": 127891792} +{"current_steps": 59260, "total_steps": 61300, "loss": 0.2944, "lr": 1.6865564689564074e-07, "epoch": 9.66721044045677, "percentage": 96.67, "elapsed_time": "16:57:50", "remaining_time": "0:35:02", "throughput": 2094.36, "total_tokens": 127903376} +{"current_steps": 59265, "total_steps": 61300, "loss": 0.0104, "lr": 1.6783124545165785e-07, "epoch": 9.668026101141924, "percentage": 96.68, "elapsed_time": "16:58:03", "remaining_time": "0:34:57", "throughput": 2094.09, "total_tokens": 127914576} +{"current_steps": 59270, "total_steps": 61300, "loss": 0.0044, "lr": 1.6700885702926882e-07, "epoch": 9.66884176182708, "percentage": 96.69, "elapsed_time": "16:58:15", "remaining_time": "0:34:52", "throughput": 2093.83, "total_tokens": 127924784} +{"current_steps": 59275, "total_steps": 61300, "loss": 0.0936, "lr": 1.6618848169514533e-07, "epoch": 9.669657422512234, "percentage": 96.7, "elapsed_time": "16:58:28", "remaining_time": "0:34:47", "throughput": 2093.58, "total_tokens": 127934800} +{"current_steps": 59280, "total_steps": 61300, "loss": 0.1346, "lr": 1.6537011951578974e-07, "epoch": 9.67047308319739, "percentage": 96.7, "elapsed_time": "16:58:41", "remaining_time": "0:34:42", "throughput": 2093.31, "total_tokens": 127945584} +{"current_steps": 59285, "total_steps": 61300, "loss": 0.1261, "lr": 1.645537705575406e-07, "epoch": 9.671288743882545, "percentage": 96.71, "elapsed_time": "16:58:54", "remaining_time": "0:34:37", "throughput": 2093.04, "total_tokens": 127956272} +{"current_steps": 59290, "total_steps": 61300, "loss": 0.0086, "lr": 1.6373943488657562e-07, "epoch": 9.6721044045677, "percentage": 96.72, "elapsed_time": "16:59:06", "remaining_time": "0:34:32", "throughput": 2092.78, "total_tokens": 127966672} +{"current_steps": 59295, "total_steps": 61300, "loss": 0.321, "lr": 1.6292711256891134e-07, "epoch": 9.672920065252855, "percentage": 96.73, "elapsed_time": "16:59:20", "remaining_time": "0:34:28", "throughput": 2092.5, "total_tokens": 127978032} +{"current_steps": 59300, "total_steps": 61300, "loss": 0.008, "lr": 1.6211680367039793e-07, "epoch": 9.673735725938009, "percentage": 96.74, "elapsed_time": "16:59:33", "remaining_time": "0:34:23", "throughput": 2092.23, "total_tokens": 127989072} +{"current_steps": 59305, "total_steps": 61300, "loss": 0.0023, "lr": 1.6130850825672173e-07, "epoch": 9.674551386623165, "percentage": 96.75, "elapsed_time": "16:59:46", "remaining_time": "0:34:18", "throughput": 2091.96, "total_tokens": 127999568} +{"current_steps": 59310, "total_steps": 61300, "loss": 0.0055, "lr": 1.6050222639340807e-07, "epoch": 9.67536704730832, "percentage": 96.75, "elapsed_time": "16:59:59", "remaining_time": "0:34:13", "throughput": 2091.68, "total_tokens": 128010256} +{"current_steps": 59315, "total_steps": 61300, "loss": 0.0036, "lr": 1.5969795814581856e-07, "epoch": 9.676182707993474, "percentage": 96.76, "elapsed_time": "17:00:11", "remaining_time": "0:34:08", "throughput": 2091.44, "total_tokens": 128020176} +{"current_steps": 59320, "total_steps": 61300, "loss": 0.0796, "lr": 1.5889570357915108e-07, "epoch": 9.67699836867863, "percentage": 96.77, "elapsed_time": "17:00:26", "remaining_time": "0:34:03", "throughput": 2091.13, "total_tokens": 128032496} +{"current_steps": 59325, "total_steps": 61300, "loss": 0.0038, "lr": 1.5809546275843968e-07, "epoch": 9.677814029363784, "percentage": 96.78, "elapsed_time": "17:00:39", "remaining_time": "0:33:58", "throughput": 2090.85, "total_tokens": 128043632} +{"current_steps": 59330, "total_steps": 61300, "loss": 0.1232, "lr": 1.572972357485575e-07, "epoch": 9.67862969004894, "percentage": 96.79, "elapsed_time": "17:00:53", "remaining_time": "0:33:53", "throughput": 2090.58, "total_tokens": 128054608} +{"current_steps": 59335, "total_steps": 61300, "loss": 0.0508, "lr": 1.5650102261421107e-07, "epoch": 9.679445350734095, "percentage": 96.79, "elapsed_time": "17:01:06", "remaining_time": "0:33:48", "throughput": 2090.31, "total_tokens": 128065360} +{"current_steps": 59340, "total_steps": 61300, "loss": 0.1016, "lr": 1.557068234199488e-07, "epoch": 9.68026101141925, "percentage": 96.8, "elapsed_time": "17:01:19", "remaining_time": "0:33:44", "throughput": 2090.03, "total_tokens": 128076464} +{"current_steps": 59345, "total_steps": 61300, "loss": 0.0148, "lr": 1.5491463823014697e-07, "epoch": 9.681076672104405, "percentage": 96.81, "elapsed_time": "17:01:31", "remaining_time": "0:33:39", "throughput": 2089.79, "total_tokens": 128086320} +{"current_steps": 59350, "total_steps": 61300, "loss": 0.0075, "lr": 1.5412446710902917e-07, "epoch": 9.681892332789559, "percentage": 96.82, "elapsed_time": "17:01:43", "remaining_time": "0:33:34", "throughput": 2089.54, "total_tokens": 128096208} +{"current_steps": 59355, "total_steps": 61300, "loss": 0.1193, "lr": 1.5333631012064698e-07, "epoch": 9.682707993474715, "percentage": 96.83, "elapsed_time": "17:01:57", "remaining_time": "0:33:29", "throughput": 2089.26, "total_tokens": 128107376} +{"current_steps": 59360, "total_steps": 61300, "loss": 0.0066, "lr": 1.5255016732889648e-07, "epoch": 9.68352365415987, "percentage": 96.84, "elapsed_time": "17:02:11", "remaining_time": "0:33:24", "throughput": 2088.97, "total_tokens": 128118800} +{"current_steps": 59365, "total_steps": 61300, "loss": 0.2222, "lr": 1.5176603879750173e-07, "epoch": 9.684339314845024, "percentage": 96.84, "elapsed_time": "17:02:26", "remaining_time": "0:33:19", "throughput": 2088.66, "total_tokens": 128131152} +{"current_steps": 59370, "total_steps": 61300, "loss": 0.0075, "lr": 1.509839245900313e-07, "epoch": 9.68515497553018, "percentage": 96.85, "elapsed_time": "17:02:39", "remaining_time": "0:33:14", "throughput": 2088.37, "total_tokens": 128142480} +{"current_steps": 59375, "total_steps": 61300, "loss": 0.0072, "lr": 1.5020382476988726e-07, "epoch": 9.685970636215334, "percentage": 96.86, "elapsed_time": "17:02:52", "remaining_time": "0:33:09", "throughput": 2088.12, "total_tokens": 128152816} +{"current_steps": 59380, "total_steps": 61300, "loss": 0.0064, "lr": 1.4942573940030791e-07, "epoch": 9.68678629690049, "percentage": 96.87, "elapsed_time": "17:03:05", "remaining_time": "0:33:04", "throughput": 2087.86, "total_tokens": 128163632} +{"current_steps": 59385, "total_steps": 61300, "loss": 0.0034, "lr": 1.4864966854437056e-07, "epoch": 9.687601957585644, "percentage": 96.88, "elapsed_time": "17:03:18", "remaining_time": "0:32:59", "throughput": 2087.59, "total_tokens": 128174640} +{"current_steps": 59390, "total_steps": 61300, "loss": 0.1922, "lr": 1.4787561226498048e-07, "epoch": 9.6884176182708, "percentage": 96.88, "elapsed_time": "17:03:29", "remaining_time": "0:32:54", "throughput": 2087.35, "total_tokens": 128184144} +{"current_steps": 59395, "total_steps": 61300, "loss": 0.0826, "lr": 1.4710357062489577e-07, "epoch": 9.689233278955955, "percentage": 96.89, "elapsed_time": "17:03:40", "remaining_time": "0:32:49", "throughput": 2087.13, "total_tokens": 128192976} +{"current_steps": 59400, "total_steps": 61300, "loss": 0.0056, "lr": 1.4633354368669694e-07, "epoch": 9.690048939641109, "percentage": 96.9, "elapsed_time": "17:03:54", "remaining_time": "0:32:45", "throughput": 2086.84, "total_tokens": 128204144} +{"current_steps": 59405, "total_steps": 61300, "loss": 0.0083, "lr": 1.4556553151280628e-07, "epoch": 9.690864600326265, "percentage": 96.91, "elapsed_time": "17:04:08", "remaining_time": "0:32:40", "throughput": 2086.55, "total_tokens": 128215600} +{"current_steps": 59410, "total_steps": 61300, "loss": 0.1073, "lr": 1.447995341654851e-07, "epoch": 9.691680261011419, "percentage": 96.92, "elapsed_time": "17:04:22", "remaining_time": "0:32:35", "throughput": 2086.27, "total_tokens": 128226672} +{"current_steps": 59415, "total_steps": 61300, "loss": 0.1257, "lr": 1.4403555170682816e-07, "epoch": 9.692495921696574, "percentage": 96.92, "elapsed_time": "17:04:35", "remaining_time": "0:32:30", "throughput": 2086.0, "total_tokens": 128237936} +{"current_steps": 59420, "total_steps": 61300, "loss": 0.1063, "lr": 1.4327358419876646e-07, "epoch": 9.69331158238173, "percentage": 96.93, "elapsed_time": "17:04:48", "remaining_time": "0:32:25", "throughput": 2085.73, "total_tokens": 128248688} +{"current_steps": 59425, "total_steps": 61300, "loss": 0.0057, "lr": 1.4251363170307008e-07, "epoch": 9.694127243066884, "percentage": 96.94, "elapsed_time": "17:05:01", "remaining_time": "0:32:20", "throughput": 2085.46, "total_tokens": 128259440} +{"current_steps": 59430, "total_steps": 61300, "loss": 0.0613, "lr": 1.4175569428134527e-07, "epoch": 9.69494290375204, "percentage": 96.95, "elapsed_time": "17:05:13", "remaining_time": "0:32:15", "throughput": 2085.22, "total_tokens": 128268880} +{"current_steps": 59435, "total_steps": 61300, "loss": 0.0046, "lr": 1.4099977199503178e-07, "epoch": 9.695758564437194, "percentage": 96.96, "elapsed_time": "17:05:24", "remaining_time": "0:32:10", "throughput": 2085.0, "total_tokens": 128277744} +{"current_steps": 59440, "total_steps": 61300, "loss": 0.094, "lr": 1.4024586490540837e-07, "epoch": 9.69657422512235, "percentage": 96.97, "elapsed_time": "17:05:37", "remaining_time": "0:32:05", "throughput": 2084.73, "total_tokens": 128288176} +{"current_steps": 59445, "total_steps": 61300, "loss": 0.0041, "lr": 1.3949397307359557e-07, "epoch": 9.697389885807503, "percentage": 96.97, "elapsed_time": "17:05:49", "remaining_time": "0:32:00", "throughput": 2084.48, "total_tokens": 128298672} +{"current_steps": 59450, "total_steps": 61300, "loss": 0.0053, "lr": 1.3874409656054189e-07, "epoch": 9.698205546492659, "percentage": 96.98, "elapsed_time": "17:06:02", "remaining_time": "0:31:55", "throughput": 2084.21, "total_tokens": 128309264} +{"current_steps": 59455, "total_steps": 61300, "loss": 0.1419, "lr": 1.3799623542703478e-07, "epoch": 9.699021207177815, "percentage": 96.99, "elapsed_time": "17:06:16", "remaining_time": "0:31:50", "throughput": 2083.94, "total_tokens": 128320656} +{"current_steps": 59460, "total_steps": 61300, "loss": 0.0062, "lr": 1.3725038973370076e-07, "epoch": 9.699836867862969, "percentage": 97.0, "elapsed_time": "17:06:29", "remaining_time": "0:31:45", "throughput": 2083.66, "total_tokens": 128332016} +{"current_steps": 59465, "total_steps": 61300, "loss": 0.009, "lr": 1.3650655954100532e-07, "epoch": 9.700652528548124, "percentage": 97.01, "elapsed_time": "17:06:42", "remaining_time": "0:31:40", "throughput": 2083.41, "total_tokens": 128342448} +{"current_steps": 59470, "total_steps": 61300, "loss": 0.0933, "lr": 1.3576474490924195e-07, "epoch": 9.701468189233278, "percentage": 97.01, "elapsed_time": "17:06:54", "remaining_time": "0:31:35", "throughput": 2083.15, "total_tokens": 128352368} +{"current_steps": 59475, "total_steps": 61300, "loss": 0.3689, "lr": 1.3502494589855142e-07, "epoch": 9.702283849918434, "percentage": 97.02, "elapsed_time": "17:07:06", "remaining_time": "0:31:31", "throughput": 2082.91, "total_tokens": 128361488} +{"current_steps": 59480, "total_steps": 61300, "loss": 0.215, "lr": 1.3428716256889962e-07, "epoch": 9.70309951060359, "percentage": 97.03, "elapsed_time": "17:07:18", "remaining_time": "0:31:26", "throughput": 2082.66, "total_tokens": 128371632} +{"current_steps": 59485, "total_steps": 61300, "loss": 0.2728, "lr": 1.3355139498009706e-07, "epoch": 9.703915171288743, "percentage": 97.04, "elapsed_time": "17:07:29", "remaining_time": "0:31:21", "throughput": 2082.44, "total_tokens": 128380688} +{"current_steps": 59490, "total_steps": 61300, "loss": 0.205, "lr": 1.3281764319179046e-07, "epoch": 9.7047308319739, "percentage": 97.05, "elapsed_time": "17:07:41", "remaining_time": "0:31:16", "throughput": 2082.19, "total_tokens": 128390480} +{"current_steps": 59495, "total_steps": 61300, "loss": 0.2241, "lr": 1.320859072634628e-07, "epoch": 9.705546492659053, "percentage": 97.06, "elapsed_time": "17:07:54", "remaining_time": "0:31:11", "throughput": 2081.91, "total_tokens": 128401712} +{"current_steps": 59500, "total_steps": 61300, "loss": 0.0063, "lr": 1.3135618725442778e-07, "epoch": 9.706362153344209, "percentage": 97.06, "elapsed_time": "17:08:08", "remaining_time": "0:31:06", "throughput": 2081.64, "total_tokens": 128413040} +{"current_steps": 59505, "total_steps": 61300, "loss": 0.1098, "lr": 1.3062848322384357e-07, "epoch": 9.707177814029365, "percentage": 97.07, "elapsed_time": "17:08:19", "remaining_time": "0:31:01", "throughput": 2081.41, "total_tokens": 128421744} +{"current_steps": 59510, "total_steps": 61300, "loss": 0.1651, "lr": 1.2990279523069916e-07, "epoch": 9.707993474714518, "percentage": 97.08, "elapsed_time": "17:08:32", "remaining_time": "0:30:56", "throughput": 2081.15, "total_tokens": 128432528} +{"current_steps": 59515, "total_steps": 61300, "loss": 0.0069, "lr": 1.291791233338252e-07, "epoch": 9.708809135399674, "percentage": 97.09, "elapsed_time": "17:08:45", "remaining_time": "0:30:51", "throughput": 2080.88, "total_tokens": 128443664} +{"current_steps": 59520, "total_steps": 61300, "loss": 0.0029, "lr": 1.2845746759188314e-07, "epoch": 9.709624796084828, "percentage": 97.1, "elapsed_time": "17:08:58", "remaining_time": "0:30:46", "throughput": 2080.62, "total_tokens": 128454256} +{"current_steps": 59525, "total_steps": 61300, "loss": 0.0193, "lr": 1.277378280633762e-07, "epoch": 9.710440456769984, "percentage": 97.1, "elapsed_time": "17:09:13", "remaining_time": "0:30:41", "throughput": 2080.31, "total_tokens": 128466768} +{"current_steps": 59530, "total_steps": 61300, "loss": 0.1477, "lr": 1.27020204806641e-07, "epoch": 9.71125611745514, "percentage": 97.11, "elapsed_time": "17:09:26", "remaining_time": "0:30:36", "throughput": 2080.06, "total_tokens": 128477264} +{"current_steps": 59535, "total_steps": 61300, "loss": 0.1438, "lr": 1.2630459787985326e-07, "epoch": 9.712071778140293, "percentage": 97.12, "elapsed_time": "17:09:40", "remaining_time": "0:30:31", "throughput": 2079.77, "total_tokens": 128489040} +{"current_steps": 59540, "total_steps": 61300, "loss": 0.0041, "lr": 1.2559100734102214e-07, "epoch": 9.71288743882545, "percentage": 97.13, "elapsed_time": "17:09:53", "remaining_time": "0:30:26", "throughput": 2079.5, "total_tokens": 128500176} +{"current_steps": 59545, "total_steps": 61300, "loss": 0.1518, "lr": 1.248794332479958e-07, "epoch": 9.713703099510603, "percentage": 97.14, "elapsed_time": "17:10:05", "remaining_time": "0:30:21", "throughput": 2079.25, "total_tokens": 128510096} +{"current_steps": 59550, "total_steps": 61300, "loss": 0.0938, "lr": 1.2416987565845861e-07, "epoch": 9.714518760195759, "percentage": 97.15, "elapsed_time": "17:10:19", "remaining_time": "0:30:16", "throughput": 2078.98, "total_tokens": 128520976} +{"current_steps": 59555, "total_steps": 61300, "loss": 0.2037, "lr": 1.2346233462992852e-07, "epoch": 9.715334420880914, "percentage": 97.15, "elapsed_time": "17:10:32", "remaining_time": "0:30:11", "throughput": 2078.7, "total_tokens": 128532080} +{"current_steps": 59560, "total_steps": 61300, "loss": 0.154, "lr": 1.2275681021976515e-07, "epoch": 9.716150081566068, "percentage": 97.16, "elapsed_time": "17:10:47", "remaining_time": "0:30:06", "throughput": 2078.41, "total_tokens": 128544176} +{"current_steps": 59565, "total_steps": 61300, "loss": 0.0787, "lr": 1.220533024851589e-07, "epoch": 9.716965742251224, "percentage": 97.17, "elapsed_time": "17:11:01", "remaining_time": "0:30:01", "throughput": 2078.13, "total_tokens": 128555472} +{"current_steps": 59570, "total_steps": 61300, "loss": 0.0298, "lr": 1.213518114831419e-07, "epoch": 9.717781402936378, "percentage": 97.18, "elapsed_time": "17:11:13", "remaining_time": "0:29:56", "throughput": 2077.88, "total_tokens": 128565968} +{"current_steps": 59575, "total_steps": 61300, "loss": 0.3807, "lr": 1.206523372705798e-07, "epoch": 9.718597063621534, "percentage": 97.19, "elapsed_time": "17:11:26", "remaining_time": "0:29:51", "throughput": 2077.63, "total_tokens": 128576528} +{"current_steps": 59580, "total_steps": 61300, "loss": 0.0076, "lr": 1.199548799041772e-07, "epoch": 9.719412724306688, "percentage": 97.19, "elapsed_time": "17:11:38", "remaining_time": "0:29:46", "throughput": 2077.38, "total_tokens": 128586928} +{"current_steps": 59585, "total_steps": 61300, "loss": 0.0785, "lr": 1.1925943944047225e-07, "epoch": 9.720228384991843, "percentage": 97.2, "elapsed_time": "17:11:53", "remaining_time": "0:29:42", "throughput": 2077.07, "total_tokens": 128599280} +{"current_steps": 59590, "total_steps": 61300, "loss": 0.005, "lr": 1.1856601593583928e-07, "epoch": 9.721044045676999, "percentage": 97.21, "elapsed_time": "17:12:06", "remaining_time": "0:29:37", "throughput": 2076.82, "total_tokens": 128609424} +{"current_steps": 59595, "total_steps": 61300, "loss": 0.0034, "lr": 1.1787460944649443e-07, "epoch": 9.721859706362153, "percentage": 97.22, "elapsed_time": "17:12:19", "remaining_time": "0:29:32", "throughput": 2076.55, "total_tokens": 128620368} +{"current_steps": 59600, "total_steps": 61300, "loss": 0.0339, "lr": 1.1718522002848175e-07, "epoch": 9.722675367047309, "percentage": 97.23, "elapsed_time": "17:12:33", "remaining_time": "0:29:27", "throughput": 2076.28, "total_tokens": 128631792} +{"current_steps": 59605, "total_steps": 61300, "loss": 0.0056, "lr": 1.164978477376899e-07, "epoch": 9.723491027732463, "percentage": 97.23, "elapsed_time": "17:12:44", "remaining_time": "0:29:22", "throughput": 2076.04, "total_tokens": 128641584} +{"current_steps": 59610, "total_steps": 61300, "loss": 0.327, "lr": 1.1581249262984096e-07, "epoch": 9.724306688417618, "percentage": 97.24, "elapsed_time": "17:12:57", "remaining_time": "0:29:17", "throughput": 2075.79, "total_tokens": 128651824} +{"current_steps": 59615, "total_steps": 61300, "loss": 0.2225, "lr": 1.1512915476049325e-07, "epoch": 9.725122349102774, "percentage": 97.25, "elapsed_time": "17:13:09", "remaining_time": "0:29:12", "throughput": 2075.54, "total_tokens": 128661616} +{"current_steps": 59620, "total_steps": 61300, "loss": 0.0051, "lr": 1.1444783418503857e-07, "epoch": 9.725938009787928, "percentage": 97.26, "elapsed_time": "17:13:22", "remaining_time": "0:29:07", "throughput": 2075.28, "total_tokens": 128671952} +{"current_steps": 59625, "total_steps": 61300, "loss": 0.0033, "lr": 1.1376853095871332e-07, "epoch": 9.726753670473084, "percentage": 97.27, "elapsed_time": "17:13:35", "remaining_time": "0:29:02", "throughput": 2075.01, "total_tokens": 128682928} +{"current_steps": 59630, "total_steps": 61300, "loss": 0.3166, "lr": 1.1309124513657899e-07, "epoch": 9.727569331158238, "percentage": 97.28, "elapsed_time": "17:13:47", "remaining_time": "0:28:57", "throughput": 2074.76, "total_tokens": 128692592} +{"current_steps": 59635, "total_steps": 61300, "loss": 0.0091, "lr": 1.124159767735472e-07, "epoch": 9.728384991843393, "percentage": 97.28, "elapsed_time": "17:14:00", "remaining_time": "0:28:52", "throughput": 2074.51, "total_tokens": 128703280} +{"current_steps": 59640, "total_steps": 61300, "loss": 0.0031, "lr": 1.1174272592435197e-07, "epoch": 9.729200652528547, "percentage": 97.29, "elapsed_time": "17:14:13", "remaining_time": "0:28:47", "throughput": 2074.24, "total_tokens": 128713904} +{"current_steps": 59645, "total_steps": 61300, "loss": 0.0097, "lr": 1.1107149264357186e-07, "epoch": 9.730016313213703, "percentage": 97.3, "elapsed_time": "17:14:25", "remaining_time": "0:28:42", "throughput": 2074.0, "total_tokens": 128723696} +{"current_steps": 59650, "total_steps": 61300, "loss": 0.006, "lr": 1.1040227698562445e-07, "epoch": 9.730831973898859, "percentage": 97.31, "elapsed_time": "17:14:38", "remaining_time": "0:28:37", "throughput": 2073.74, "total_tokens": 128735120} +{"current_steps": 59655, "total_steps": 61300, "loss": 0.1014, "lr": 1.0973507900475521e-07, "epoch": 9.731647634584013, "percentage": 97.32, "elapsed_time": "17:14:51", "remaining_time": "0:28:32", "throughput": 2073.49, "total_tokens": 128745232} +{"current_steps": 59660, "total_steps": 61300, "loss": 0.0428, "lr": 1.0906989875505425e-07, "epoch": 9.732463295269168, "percentage": 97.32, "elapsed_time": "17:15:03", "remaining_time": "0:28:27", "throughput": 2073.23, "total_tokens": 128755856} +{"current_steps": 59665, "total_steps": 61300, "loss": 0.0038, "lr": 1.0840673629044228e-07, "epoch": 9.733278955954322, "percentage": 97.33, "elapsed_time": "17:15:16", "remaining_time": "0:28:22", "throughput": 2072.98, "total_tokens": 128766768} +{"current_steps": 59670, "total_steps": 61300, "loss": 0.0743, "lr": 1.0774559166467912e-07, "epoch": 9.734094616639478, "percentage": 97.34, "elapsed_time": "17:15:30", "remaining_time": "0:28:17", "throughput": 2072.71, "total_tokens": 128778448} +{"current_steps": 59675, "total_steps": 61300, "loss": 0.049, "lr": 1.0708646493135799e-07, "epoch": 9.734910277324634, "percentage": 97.35, "elapsed_time": "17:15:42", "remaining_time": "0:28:12", "throughput": 2072.45, "total_tokens": 128788176} +{"current_steps": 59680, "total_steps": 61300, "loss": 0.0056, "lr": 1.0642935614391392e-07, "epoch": 9.735725938009788, "percentage": 97.36, "elapsed_time": "17:15:56", "remaining_time": "0:28:07", "throughput": 2072.19, "total_tokens": 128799280} +{"current_steps": 59685, "total_steps": 61300, "loss": 0.0036, "lr": 1.0577426535561541e-07, "epoch": 9.736541598694943, "percentage": 97.37, "elapsed_time": "17:16:08", "remaining_time": "0:28:02", "throughput": 2071.95, "total_tokens": 128808752} +{"current_steps": 59690, "total_steps": 61300, "loss": 0.0432, "lr": 1.0512119261956999e-07, "epoch": 9.737357259380097, "percentage": 97.37, "elapsed_time": "17:16:21", "remaining_time": "0:27:57", "throughput": 2071.68, "total_tokens": 128819728} +{"current_steps": 59695, "total_steps": 61300, "loss": 0.0774, "lr": 1.0447013798871308e-07, "epoch": 9.738172920065253, "percentage": 97.38, "elapsed_time": "17:16:35", "remaining_time": "0:27:52", "throughput": 2071.4, "total_tokens": 128831440} +{"current_steps": 59700, "total_steps": 61300, "loss": 0.0072, "lr": 1.0382110151582469e-07, "epoch": 9.738988580750409, "percentage": 97.39, "elapsed_time": "17:16:47", "remaining_time": "0:27:47", "throughput": 2071.17, "total_tokens": 128841200} +{"current_steps": 59705, "total_steps": 61300, "loss": 0.0052, "lr": 1.0317408325352107e-07, "epoch": 9.739804241435563, "percentage": 97.4, "elapsed_time": "17:17:00", "remaining_time": "0:27:42", "throughput": 2070.91, "total_tokens": 128852112} +{"current_steps": 59710, "total_steps": 61300, "loss": 0.0048, "lr": 1.0252908325425192e-07, "epoch": 9.740619902120718, "percentage": 97.41, "elapsed_time": "17:17:15", "remaining_time": "0:27:37", "throughput": 2070.6, "total_tokens": 128864592} +{"current_steps": 59715, "total_steps": 61300, "loss": 0.0045, "lr": 1.018861015703032e-07, "epoch": 9.741435562805872, "percentage": 97.41, "elapsed_time": "17:17:29", "remaining_time": "0:27:32", "throughput": 2070.32, "total_tokens": 128876272} +{"current_steps": 59720, "total_steps": 61300, "loss": 0.0062, "lr": 1.0124513825379989e-07, "epoch": 9.742251223491028, "percentage": 97.42, "elapsed_time": "17:17:42", "remaining_time": "0:27:27", "throughput": 2070.07, "total_tokens": 128887056} +{"current_steps": 59725, "total_steps": 61300, "loss": 0.1659, "lr": 1.0060619335669764e-07, "epoch": 9.743066884176184, "percentage": 97.43, "elapsed_time": "17:17:55", "remaining_time": "0:27:22", "throughput": 2069.8, "total_tokens": 128898128} +{"current_steps": 59730, "total_steps": 61300, "loss": 0.0051, "lr": 9.996926693079945e-08, "epoch": 9.743882544861338, "percentage": 97.44, "elapsed_time": "17:18:09", "remaining_time": "0:27:17", "throughput": 2069.53, "total_tokens": 128909040} +{"current_steps": 59735, "total_steps": 61300, "loss": 0.1583, "lr": 9.93343590277307e-08, "epoch": 9.744698205546493, "percentage": 97.45, "elapsed_time": "17:18:20", "remaining_time": "0:27:12", "throughput": 2069.3, "total_tokens": 128918288} +{"current_steps": 59740, "total_steps": 61300, "loss": 0.0231, "lr": 9.870146969896688e-08, "epoch": 9.745513866231647, "percentage": 97.46, "elapsed_time": "17:18:33", "remaining_time": "0:27:07", "throughput": 2069.04, "total_tokens": 128929584} +{"current_steps": 59745, "total_steps": 61300, "loss": 0.0092, "lr": 9.807059899580861e-08, "epoch": 9.746329526916803, "percentage": 97.46, "elapsed_time": "17:18:46", "remaining_time": "0:27:02", "throughput": 2068.77, "total_tokens": 128940208} +{"current_steps": 59750, "total_steps": 61300, "loss": 0.1955, "lr": 9.744174696939834e-08, "epoch": 9.747145187601957, "percentage": 97.47, "elapsed_time": "17:18:59", "remaining_time": "0:26:57", "throughput": 2068.53, "total_tokens": 128950224} +{"current_steps": 59755, "total_steps": 61300, "loss": 0.004, "lr": 9.681491367071193e-08, "epoch": 9.747960848287113, "percentage": 97.48, "elapsed_time": "17:19:12", "remaining_time": "0:26:52", "throughput": 2068.26, "total_tokens": 128961072} +{"current_steps": 59760, "total_steps": 61300, "loss": 0.0045, "lr": 9.619009915056987e-08, "epoch": 9.748776508972268, "percentage": 97.49, "elapsed_time": "17:19:26", "remaining_time": "0:26:47", "throughput": 2067.98, "total_tokens": 128972528} +{"current_steps": 59765, "total_steps": 61300, "loss": 0.3243, "lr": 9.556730345961773e-08, "epoch": 9.749592169657422, "percentage": 97.5, "elapsed_time": "17:19:38", "remaining_time": "0:26:42", "throughput": 2067.74, "total_tokens": 128982480} +{"current_steps": 59770, "total_steps": 61300, "loss": 0.0811, "lr": 9.494652664834292e-08, "epoch": 9.750407830342578, "percentage": 97.5, "elapsed_time": "17:19:50", "remaining_time": "0:26:37", "throughput": 2067.5, "total_tokens": 128992304} +{"current_steps": 59775, "total_steps": 61300, "loss": 0.1513, "lr": 9.432776876707183e-08, "epoch": 9.751223491027732, "percentage": 97.51, "elapsed_time": "17:20:03", "remaining_time": "0:26:32", "throughput": 2067.24, "total_tokens": 129003344} +{"current_steps": 59780, "total_steps": 61300, "loss": 0.0618, "lr": 9.371102986595881e-08, "epoch": 9.752039151712887, "percentage": 97.52, "elapsed_time": "17:20:16", "remaining_time": "0:26:27", "throughput": 2066.97, "total_tokens": 129014224} +{"current_steps": 59785, "total_steps": 61300, "loss": 0.0683, "lr": 9.309630999500551e-08, "epoch": 9.752854812398043, "percentage": 97.53, "elapsed_time": "17:20:28", "remaining_time": "0:26:21", "throughput": 2066.74, "total_tokens": 129024016} +{"current_steps": 59790, "total_steps": 61300, "loss": 0.0056, "lr": 9.248360920404154e-08, "epoch": 9.753670473083197, "percentage": 97.54, "elapsed_time": "17:20:40", "remaining_time": "0:26:16", "throughput": 2066.5, "total_tokens": 129033840} +{"current_steps": 59795, "total_steps": 61300, "loss": 0.0074, "lr": 9.187292754273269e-08, "epoch": 9.754486133768353, "percentage": 97.54, "elapsed_time": "17:20:53", "remaining_time": "0:26:11", "throughput": 2066.24, "total_tokens": 129044848} +{"current_steps": 59800, "total_steps": 61300, "loss": 0.0106, "lr": 9.126426506058938e-08, "epoch": 9.755301794453507, "percentage": 97.55, "elapsed_time": "17:21:07", "remaining_time": "0:26:06", "throughput": 2065.98, "total_tokens": 129055664} +{"current_steps": 59805, "total_steps": 61300, "loss": 0.2729, "lr": 9.06576218069527e-08, "epoch": 9.756117455138662, "percentage": 97.56, "elapsed_time": "17:21:20", "remaining_time": "0:26:01", "throughput": 2065.72, "total_tokens": 129066288} +{"current_steps": 59810, "total_steps": 61300, "loss": 0.0641, "lr": 9.005299783099441e-08, "epoch": 9.756933115823816, "percentage": 97.57, "elapsed_time": "17:21:31", "remaining_time": "0:25:56", "throughput": 2065.49, "total_tokens": 129076016} +{"current_steps": 59815, "total_steps": 61300, "loss": 0.0031, "lr": 8.945039318173365e-08, "epoch": 9.757748776508972, "percentage": 97.58, "elapsed_time": "17:21:44", "remaining_time": "0:25:51", "throughput": 2065.22, "total_tokens": 129086704} +{"current_steps": 59820, "total_steps": 61300, "loss": 0.0098, "lr": 8.884980790801745e-08, "epoch": 9.758564437194128, "percentage": 97.59, "elapsed_time": "17:21:56", "remaining_time": "0:25:46", "throughput": 2064.99, "total_tokens": 129096560} +{"current_steps": 59825, "total_steps": 61300, "loss": 0.079, "lr": 8.825124205853463e-08, "epoch": 9.759380097879282, "percentage": 97.59, "elapsed_time": "17:22:10", "remaining_time": "0:25:41", "throughput": 2064.72, "total_tokens": 129107984} +{"current_steps": 59830, "total_steps": 61300, "loss": 0.0819, "lr": 8.76546956818075e-08, "epoch": 9.760195758564437, "percentage": 97.6, "elapsed_time": "17:22:23", "remaining_time": "0:25:36", "throughput": 2064.46, "total_tokens": 129118352} +{"current_steps": 59835, "total_steps": 61300, "loss": 0.0078, "lr": 8.706016882619461e-08, "epoch": 9.761011419249591, "percentage": 97.61, "elapsed_time": "17:22:36", "remaining_time": "0:25:31", "throughput": 2064.2, "total_tokens": 129129072} +{"current_steps": 59840, "total_steps": 61300, "loss": 0.01, "lr": 8.646766153989072e-08, "epoch": 9.761827079934747, "percentage": 97.62, "elapsed_time": "17:22:50", "remaining_time": "0:25:26", "throughput": 2063.93, "total_tokens": 129140496} +{"current_steps": 59845, "total_steps": 61300, "loss": 0.0041, "lr": 8.587717387092686e-08, "epoch": 9.762642740619903, "percentage": 97.63, "elapsed_time": "17:23:03", "remaining_time": "0:25:21", "throughput": 2063.66, "total_tokens": 129151952} +{"current_steps": 59850, "total_steps": 61300, "loss": 0.1406, "lr": 8.528870586717308e-08, "epoch": 9.763458401305057, "percentage": 97.63, "elapsed_time": "17:23:19", "remaining_time": "0:25:16", "throughput": 2063.35, "total_tokens": 129165008} +{"current_steps": 59855, "total_steps": 61300, "loss": 0.1201, "lr": 8.470225757633565e-08, "epoch": 9.764274061990212, "percentage": 97.64, "elapsed_time": "17:23:33", "remaining_time": "0:25:11", "throughput": 2063.08, "total_tokens": 129176272} +{"current_steps": 59860, "total_steps": 61300, "loss": 0.0254, "lr": 8.411782904594879e-08, "epoch": 9.765089722675366, "percentage": 97.65, "elapsed_time": "17:23:46", "remaining_time": "0:25:06", "throughput": 2062.82, "total_tokens": 129187504} +{"current_steps": 59865, "total_steps": 61300, "loss": 0.0052, "lr": 8.3535420323394e-08, "epoch": 9.765905383360522, "percentage": 97.66, "elapsed_time": "17:24:00", "remaining_time": "0:25:01", "throughput": 2062.55, "total_tokens": 129198928} +{"current_steps": 59870, "total_steps": 61300, "loss": 0.0036, "lr": 8.295503145588357e-08, "epoch": 9.766721044045678, "percentage": 97.67, "elapsed_time": "17:24:14", "remaining_time": "0:24:56", "throughput": 2062.26, "total_tokens": 129211024} +{"current_steps": 59875, "total_steps": 61300, "loss": 0.0678, "lr": 8.237666249046593e-08, "epoch": 9.767536704730832, "percentage": 97.68, "elapsed_time": "17:24:28", "remaining_time": "0:24:51", "throughput": 2062.0, "total_tokens": 129222096} +{"current_steps": 59880, "total_steps": 61300, "loss": 0.2141, "lr": 8.180031347402583e-08, "epoch": 9.768352365415987, "percentage": 97.68, "elapsed_time": "17:24:41", "remaining_time": "0:24:46", "throughput": 2061.73, "total_tokens": 129232880} +{"current_steps": 59885, "total_steps": 61300, "loss": 0.0047, "lr": 8.122598445328699e-08, "epoch": 9.769168026101141, "percentage": 97.69, "elapsed_time": "17:24:55", "remaining_time": "0:24:41", "throughput": 2061.46, "total_tokens": 129244560} +{"current_steps": 59890, "total_steps": 61300, "loss": 0.0919, "lr": 8.065367547480384e-08, "epoch": 9.769983686786297, "percentage": 97.7, "elapsed_time": "17:25:09", "remaining_time": "0:24:36", "throughput": 2061.2, "total_tokens": 129255824} +{"current_steps": 59895, "total_steps": 61300, "loss": 0.0922, "lr": 8.008338658497538e-08, "epoch": 9.770799347471453, "percentage": 97.71, "elapsed_time": "17:25:23", "remaining_time": "0:24:31", "throughput": 2060.92, "total_tokens": 129267248} +{"current_steps": 59900, "total_steps": 61300, "loss": 0.0105, "lr": 7.95151178300313e-08, "epoch": 9.771615008156607, "percentage": 97.72, "elapsed_time": "17:25:35", "remaining_time": "0:24:26", "throughput": 2060.68, "total_tokens": 129277616} +{"current_steps": 59905, "total_steps": 61300, "loss": 0.0049, "lr": 7.894886925603473e-08, "epoch": 9.772430668841762, "percentage": 97.72, "elapsed_time": "17:25:48", "remaining_time": "0:24:21", "throughput": 2060.43, "total_tokens": 129288112} +{"current_steps": 59910, "total_steps": 61300, "loss": 0.2076, "lr": 7.838464090889342e-08, "epoch": 9.773246329526916, "percentage": 97.73, "elapsed_time": "17:26:00", "remaining_time": "0:24:16", "throughput": 2060.18, "total_tokens": 129298064} +{"current_steps": 59915, "total_steps": 61300, "loss": 0.0025, "lr": 7.782243283434299e-08, "epoch": 9.774061990212072, "percentage": 97.74, "elapsed_time": "17:26:11", "remaining_time": "0:24:11", "throughput": 2059.96, "total_tokens": 129307408} +{"current_steps": 59920, "total_steps": 61300, "loss": 0.1182, "lr": 7.726224507795809e-08, "epoch": 9.774877650897226, "percentage": 97.75, "elapsed_time": "17:26:24", "remaining_time": "0:24:05", "throughput": 2059.7, "total_tokens": 129318128} +{"current_steps": 59925, "total_steps": 61300, "loss": 0.0035, "lr": 7.67040776851552e-08, "epoch": 9.775693311582382, "percentage": 97.76, "elapsed_time": "17:26:37", "remaining_time": "0:24:00", "throughput": 2059.46, "total_tokens": 129328080} +{"current_steps": 59930, "total_steps": 61300, "loss": 0.1037, "lr": 7.614793070117865e-08, "epoch": 9.776508972267537, "percentage": 97.77, "elapsed_time": "17:26:50", "remaining_time": "0:23:55", "throughput": 2059.2, "total_tokens": 129339120} +{"current_steps": 59935, "total_steps": 61300, "loss": 0.1949, "lr": 7.559380417111184e-08, "epoch": 9.777324632952691, "percentage": 97.77, "elapsed_time": "17:27:02", "remaining_time": "0:23:50", "throughput": 2058.96, "total_tokens": 129349648} +{"current_steps": 59940, "total_steps": 61300, "loss": 0.0053, "lr": 7.504169813987716e-08, "epoch": 9.778140293637847, "percentage": 97.78, "elapsed_time": "17:27:15", "remaining_time": "0:23:45", "throughput": 2058.7, "total_tokens": 129360400} +{"current_steps": 59945, "total_steps": 61300, "loss": 0.1654, "lr": 7.449161265223048e-08, "epoch": 9.778955954323001, "percentage": 97.79, "elapsed_time": "17:27:31", "remaining_time": "0:23:40", "throughput": 2058.4, "total_tokens": 129373168} +{"current_steps": 59950, "total_steps": 61300, "loss": 0.1162, "lr": 7.394354775276391e-08, "epoch": 9.779771615008157, "percentage": 97.8, "elapsed_time": "17:27:43", "remaining_time": "0:23:35", "throughput": 2058.17, "total_tokens": 129382736} +{"current_steps": 59955, "total_steps": 61300, "loss": 0.1244, "lr": 7.339750348590857e-08, "epoch": 9.780587275693312, "percentage": 97.81, "elapsed_time": "17:27:56", "remaining_time": "0:23:30", "throughput": 2057.9, "total_tokens": 129394160} +{"current_steps": 59960, "total_steps": 61300, "loss": 0.0699, "lr": 7.285347989592628e-08, "epoch": 9.781402936378466, "percentage": 97.81, "elapsed_time": "17:28:10", "remaining_time": "0:23:25", "throughput": 2057.63, "total_tokens": 129405744} +{"current_steps": 59965, "total_steps": 61300, "loss": 0.0067, "lr": 7.231147702692065e-08, "epoch": 9.782218597063622, "percentage": 97.82, "elapsed_time": "17:28:23", "remaining_time": "0:23:20", "throughput": 2057.38, "total_tokens": 129416368} +{"current_steps": 59970, "total_steps": 61300, "loss": 0.0042, "lr": 7.177149492282876e-08, "epoch": 9.783034257748776, "percentage": 97.83, "elapsed_time": "17:28:36", "remaining_time": "0:23:15", "throughput": 2057.13, "total_tokens": 129426928} +{"current_steps": 59975, "total_steps": 61300, "loss": 0.168, "lr": 7.123353362742391e-08, "epoch": 9.783849918433932, "percentage": 97.84, "elapsed_time": "17:28:50", "remaining_time": "0:23:10", "throughput": 2056.85, "total_tokens": 129438896} +{"current_steps": 59980, "total_steps": 61300, "loss": 0.0073, "lr": 7.069759318431567e-08, "epoch": 9.784665579119086, "percentage": 97.85, "elapsed_time": "17:29:03", "remaining_time": "0:23:05", "throughput": 2056.6, "total_tokens": 129449808} +{"current_steps": 59985, "total_steps": 61300, "loss": 0.0472, "lr": 7.016367363694986e-08, "epoch": 9.785481239804241, "percentage": 97.85, "elapsed_time": "17:29:17", "remaining_time": "0:23:00", "throughput": 2056.32, "total_tokens": 129461232} +{"current_steps": 59990, "total_steps": 61300, "loss": 0.1873, "lr": 6.963177502861129e-08, "epoch": 9.786296900489397, "percentage": 97.86, "elapsed_time": "17:29:30", "remaining_time": "0:22:55", "throughput": 2056.06, "total_tokens": 129471984} +{"current_steps": 59995, "total_steps": 61300, "loss": 0.0062, "lr": 6.910189740241269e-08, "epoch": 9.78711256117455, "percentage": 97.87, "elapsed_time": "17:29:44", "remaining_time": "0:22:50", "throughput": 2055.8, "total_tokens": 129483088} +{"current_steps": 60000, "total_steps": 61300, "loss": 0.0078, "lr": 6.857404080131691e-08, "epoch": 9.787928221859707, "percentage": 97.88, "elapsed_time": "17:29:55", "remaining_time": "0:22:44", "throughput": 2055.58, "total_tokens": 129492144} +{"current_steps": 60005, "total_steps": 61300, "loss": 0.0402, "lr": 6.804820526810917e-08, "epoch": 9.78874388254486, "percentage": 97.89, "elapsed_time": "17:30:07", "remaining_time": "0:22:39", "throughput": 2055.34, "total_tokens": 129502128} +{"current_steps": 60010, "total_steps": 61300, "loss": 0.1213, "lr": 6.75243908454165e-08, "epoch": 9.789559543230016, "percentage": 97.9, "elapsed_time": "17:30:20", "remaining_time": "0:22:34", "throughput": 2055.09, "total_tokens": 129512848} +{"current_steps": 60015, "total_steps": 61300, "loss": 0.0793, "lr": 6.700259757570216e-08, "epoch": 9.790375203915172, "percentage": 97.9, "elapsed_time": "17:30:33", "remaining_time": "0:22:29", "throughput": 2054.84, "total_tokens": 129522992} +{"current_steps": 60020, "total_steps": 61300, "loss": 0.0076, "lr": 6.648282550126562e-08, "epoch": 9.791190864600326, "percentage": 97.91, "elapsed_time": "17:30:45", "remaining_time": "0:22:24", "throughput": 2054.6, "total_tokens": 129533328} +{"current_steps": 60025, "total_steps": 61300, "loss": 0.0035, "lr": 6.59650746642454e-08, "epoch": 9.792006525285482, "percentage": 97.92, "elapsed_time": "17:30:56", "remaining_time": "0:22:19", "throughput": 2054.38, "total_tokens": 129542768} +{"current_steps": 60030, "total_steps": 61300, "loss": 0.1718, "lr": 6.544934510660794e-08, "epoch": 9.792822185970635, "percentage": 97.93, "elapsed_time": "17:31:11", "remaining_time": "0:22:14", "throughput": 2054.09, "total_tokens": 129554448} +{"current_steps": 60035, "total_steps": 61300, "loss": 0.009, "lr": 6.493563687016424e-08, "epoch": 9.793637846655791, "percentage": 97.94, "elapsed_time": "17:31:26", "remaining_time": "0:22:09", "throughput": 2053.8, "total_tokens": 129566736} +{"current_steps": 60040, "total_steps": 61300, "loss": 0.0081, "lr": 6.442394999655599e-08, "epoch": 9.794453507340947, "percentage": 97.94, "elapsed_time": "17:31:39", "remaining_time": "0:22:04", "throughput": 2053.54, "total_tokens": 129577392} +{"current_steps": 60045, "total_steps": 61300, "loss": 0.0058, "lr": 6.391428452726389e-08, "epoch": 9.7952691680261, "percentage": 97.95, "elapsed_time": "17:31:52", "remaining_time": "0:21:59", "throughput": 2053.29, "total_tokens": 129588080} +{"current_steps": 60050, "total_steps": 61300, "loss": 0.1011, "lr": 6.340664050360767e-08, "epoch": 9.796084828711257, "percentage": 97.96, "elapsed_time": "17:32:05", "remaining_time": "0:21:54", "throughput": 2053.03, "total_tokens": 129599312} +{"current_steps": 60055, "total_steps": 61300, "loss": 0.1297, "lr": 6.29010179667322e-08, "epoch": 9.79690048939641, "percentage": 97.97, "elapsed_time": "17:32:17", "remaining_time": "0:21:48", "throughput": 2052.8, "total_tokens": 129609488} +{"current_steps": 60060, "total_steps": 61300, "loss": 0.0944, "lr": 6.239741695763246e-08, "epoch": 9.797716150081566, "percentage": 97.98, "elapsed_time": "17:32:31", "remaining_time": "0:21:43", "throughput": 2052.53, "total_tokens": 129620944} +{"current_steps": 60065, "total_steps": 61300, "loss": 0.0069, "lr": 6.189583751712857e-08, "epoch": 9.798531810766722, "percentage": 97.99, "elapsed_time": "17:32:45", "remaining_time": "0:21:38", "throughput": 2052.27, "total_tokens": 129631920} +{"current_steps": 60070, "total_steps": 61300, "loss": 0.0051, "lr": 6.139627968588524e-08, "epoch": 9.799347471451876, "percentage": 97.99, "elapsed_time": "17:32:59", "remaining_time": "0:21:33", "throughput": 2052.0, "total_tokens": 129643696} +{"current_steps": 60075, "total_steps": 61300, "loss": 0.1105, "lr": 6.089874350439506e-08, "epoch": 9.800163132137031, "percentage": 98.0, "elapsed_time": "17:33:12", "remaining_time": "0:21:28", "throughput": 2051.74, "total_tokens": 129655184} +{"current_steps": 60080, "total_steps": 61300, "loss": 0.0031, "lr": 6.040322901299245e-08, "epoch": 9.800978792822185, "percentage": 98.01, "elapsed_time": "17:33:24", "remaining_time": "0:21:23", "throughput": 2051.51, "total_tokens": 129665008} +{"current_steps": 60085, "total_steps": 61300, "loss": 0.0027, "lr": 5.990973625184526e-08, "epoch": 9.801794453507341, "percentage": 98.02, "elapsed_time": "17:33:36", "remaining_time": "0:21:18", "throughput": 2051.28, "total_tokens": 129675344} +{"current_steps": 60090, "total_steps": 61300, "loss": 0.2226, "lr": 5.9418265260960394e-08, "epoch": 9.802610114192497, "percentage": 98.03, "elapsed_time": "17:33:51", "remaining_time": "0:21:13", "throughput": 2051.0, "total_tokens": 129687120} +{"current_steps": 60095, "total_steps": 61300, "loss": 0.0097, "lr": 5.892881608017819e-08, "epoch": 9.80342577487765, "percentage": 98.03, "elapsed_time": "17:34:04", "remaining_time": "0:21:08", "throughput": 2050.75, "total_tokens": 129697936} +{"current_steps": 60100, "total_steps": 61300, "loss": 0.0071, "lr": 5.844138874917526e-08, "epoch": 9.804241435562806, "percentage": 98.04, "elapsed_time": "17:34:15", "remaining_time": "0:21:03", "throughput": 2050.52, "total_tokens": 129707312} +{"current_steps": 60105, "total_steps": 61300, "loss": 0.0053, "lr": 5.795598330746721e-08, "epoch": 9.80505709624796, "percentage": 98.05, "elapsed_time": "17:34:28", "remaining_time": "0:20:57", "throughput": 2050.27, "total_tokens": 129718256} +{"current_steps": 60110, "total_steps": 61300, "loss": 0.0087, "lr": 5.747259979440034e-08, "epoch": 9.805872756933116, "percentage": 98.06, "elapsed_time": "17:34:41", "remaining_time": "0:20:52", "throughput": 2050.04, "total_tokens": 129728336} +{"current_steps": 60115, "total_steps": 61300, "loss": 0.0075, "lr": 5.699123824916275e-08, "epoch": 9.80668841761827, "percentage": 98.07, "elapsed_time": "17:34:53", "remaining_time": "0:20:47", "throughput": 2049.79, "total_tokens": 129738960} +{"current_steps": 60120, "total_steps": 61300, "loss": 0.1868, "lr": 5.6511898710776e-08, "epoch": 9.807504078303426, "percentage": 98.08, "elapsed_time": "17:35:05", "remaining_time": "0:20:42", "throughput": 2049.55, "total_tokens": 129748752} +{"current_steps": 60125, "total_steps": 61300, "loss": 0.0052, "lr": 5.603458121809513e-08, "epoch": 9.808319738988581, "percentage": 98.08, "elapsed_time": "17:35:18", "remaining_time": "0:20:37", "throughput": 2049.31, "total_tokens": 129758864} +{"current_steps": 60130, "total_steps": 61300, "loss": 0.1611, "lr": 5.555928580981418e-08, "epoch": 9.809135399673735, "percentage": 98.09, "elapsed_time": "17:35:29", "remaining_time": "0:20:32", "throughput": 2049.08, "total_tokens": 129768112} +{"current_steps": 60135, "total_steps": 61300, "loss": 0.0076, "lr": 5.5086012524466216e-08, "epoch": 9.809951060358891, "percentage": 98.1, "elapsed_time": "17:35:43", "remaining_time": "0:20:27", "throughput": 2048.82, "total_tokens": 129779440} +{"current_steps": 60140, "total_steps": 61300, "loss": 0.0782, "lr": 5.4614761400414996e-08, "epoch": 9.810766721044045, "percentage": 98.11, "elapsed_time": "17:35:56", "remaining_time": "0:20:22", "throughput": 2048.57, "total_tokens": 129790320} +{"current_steps": 60145, "total_steps": 61300, "loss": 0.1056, "lr": 5.414553247586329e-08, "epoch": 9.8115823817292, "percentage": 98.12, "elapsed_time": "17:36:08", "remaining_time": "0:20:16", "throughput": 2048.35, "total_tokens": 129799792} +{"current_steps": 60150, "total_steps": 61300, "loss": 0.18, "lr": 5.367832578884735e-08, "epoch": 9.812398042414356, "percentage": 98.12, "elapsed_time": "17:36:22", "remaining_time": "0:20:11", "throughput": 2048.08, "total_tokens": 129811472} +{"current_steps": 60155, "total_steps": 61300, "loss": 0.0047, "lr": 5.3213141377245205e-08, "epoch": 9.81321370309951, "percentage": 98.13, "elapsed_time": "17:36:35", "remaining_time": "0:20:06", "throughput": 2047.81, "total_tokens": 129822512} +{"current_steps": 60160, "total_steps": 61300, "loss": 0.0061, "lr": 5.2749979278762794e-08, "epoch": 9.814029363784666, "percentage": 98.14, "elapsed_time": "17:36:50", "remaining_time": "0:20:01", "throughput": 2047.53, "total_tokens": 129834608} +{"current_steps": 60165, "total_steps": 61300, "loss": 0.1253, "lr": 5.228883953094788e-08, "epoch": 9.81484502446982, "percentage": 98.15, "elapsed_time": "17:37:02", "remaining_time": "0:19:56", "throughput": 2047.29, "total_tokens": 129845008} +{"current_steps": 60170, "total_steps": 61300, "loss": 0.1164, "lr": 5.182972217118165e-08, "epoch": 9.815660685154976, "percentage": 98.16, "elapsed_time": "17:37:15", "remaining_time": "0:19:51", "throughput": 2047.05, "total_tokens": 129854928} +{"current_steps": 60175, "total_steps": 61300, "loss": 0.0292, "lr": 5.137262723668712e-08, "epoch": 9.81647634584013, "percentage": 98.16, "elapsed_time": "17:37:28", "remaining_time": "0:19:46", "throughput": 2046.79, "total_tokens": 129865904} +{"current_steps": 60180, "total_steps": 61300, "loss": 0.1108, "lr": 5.0917554764515206e-08, "epoch": 9.817292006525285, "percentage": 98.17, "elapsed_time": "17:37:43", "remaining_time": "0:19:41", "throughput": 2046.52, "total_tokens": 129878288} +{"current_steps": 60185, "total_steps": 61300, "loss": 0.0695, "lr": 5.0464504791553066e-08, "epoch": 9.818107667210441, "percentage": 98.18, "elapsed_time": "17:37:57", "remaining_time": "0:19:36", "throughput": 2046.23, "total_tokens": 129890512} +{"current_steps": 60190, "total_steps": 61300, "loss": 0.1822, "lr": 5.001347735453521e-08, "epoch": 9.818923327895595, "percentage": 98.19, "elapsed_time": "17:38:10", "remaining_time": "0:19:30", "throughput": 2046.0, "total_tokens": 129900560} +{"current_steps": 60195, "total_steps": 61300, "loss": 0.0029, "lr": 4.95644724900185e-08, "epoch": 9.81973898858075, "percentage": 98.2, "elapsed_time": "17:38:24", "remaining_time": "0:19:25", "throughput": 2045.72, "total_tokens": 129912272} +{"current_steps": 60200, "total_steps": 61300, "loss": 0.1059, "lr": 4.91174902344016e-08, "epoch": 9.820554649265905, "percentage": 98.21, "elapsed_time": "17:38:37", "remaining_time": "0:19:20", "throughput": 2045.47, "total_tokens": 129923120} +{"current_steps": 60205, "total_steps": 61300, "loss": 0.0031, "lr": 4.867253062391941e-08, "epoch": 9.82137030995106, "percentage": 98.21, "elapsed_time": "17:38:52", "remaining_time": "0:19:15", "throughput": 2045.18, "total_tokens": 129935280} +{"current_steps": 60210, "total_steps": 61300, "loss": 0.0025, "lr": 4.822959369464586e-08, "epoch": 9.822185970636216, "percentage": 98.22, "elapsed_time": "17:39:05", "remaining_time": "0:19:10", "throughput": 2044.93, "total_tokens": 129946032} +{"current_steps": 60215, "total_steps": 61300, "loss": 0.0115, "lr": 4.7788679482485556e-08, "epoch": 9.82300163132137, "percentage": 98.23, "elapsed_time": "17:39:18", "remaining_time": "0:19:05", "throughput": 2044.67, "total_tokens": 129956784} +{"current_steps": 60220, "total_steps": 61300, "loss": 0.0046, "lr": 4.734978802318213e-08, "epoch": 9.823817292006526, "percentage": 98.24, "elapsed_time": "17:39:31", "remaining_time": "0:19:00", "throughput": 2044.42, "total_tokens": 129967504} +{"current_steps": 60225, "total_steps": 61300, "loss": 0.1095, "lr": 4.69129193523099e-08, "epoch": 9.82463295269168, "percentage": 98.25, "elapsed_time": "17:39:44", "remaining_time": "0:18:54", "throughput": 2044.17, "total_tokens": 129977840} +{"current_steps": 60230, "total_steps": 61300, "loss": 0.0092, "lr": 4.6478073505290544e-08, "epoch": 9.825448613376835, "percentage": 98.25, "elapsed_time": "17:39:57", "remaining_time": "0:18:49", "throughput": 2043.93, "total_tokens": 129988080} +{"current_steps": 60235, "total_steps": 61300, "loss": 0.0033, "lr": 4.6045250517370854e-08, "epoch": 9.826264274061991, "percentage": 98.26, "elapsed_time": "17:40:11", "remaining_time": "0:18:44", "throughput": 2043.66, "total_tokens": 129999728} +{"current_steps": 60240, "total_steps": 61300, "loss": 0.0932, "lr": 4.561445042363666e-08, "epoch": 9.827079934747145, "percentage": 98.27, "elapsed_time": "17:40:23", "remaining_time": "0:18:39", "throughput": 2043.42, "total_tokens": 130010352} +{"current_steps": 60245, "total_steps": 61300, "loss": 0.1038, "lr": 4.518567325901279e-08, "epoch": 9.8278955954323, "percentage": 98.28, "elapsed_time": "17:40:37", "remaining_time": "0:18:34", "throughput": 2043.16, "total_tokens": 130021776} +{"current_steps": 60250, "total_steps": 61300, "loss": 0.0047, "lr": 4.475891905825758e-08, "epoch": 9.828711256117455, "percentage": 98.29, "elapsed_time": "17:40:50", "remaining_time": "0:18:29", "throughput": 2042.92, "total_tokens": 130032304} +{"current_steps": 60255, "total_steps": 61300, "loss": 0.1281, "lr": 4.4334187855968326e-08, "epoch": 9.82952691680261, "percentage": 98.3, "elapsed_time": "17:41:02", "remaining_time": "0:18:24", "throughput": 2042.69, "total_tokens": 130041840} +{"current_steps": 60260, "total_steps": 61300, "loss": 0.0048, "lr": 4.391147968657028e-08, "epoch": 9.830342577487766, "percentage": 98.3, "elapsed_time": "17:41:13", "remaining_time": "0:18:18", "throughput": 2042.47, "total_tokens": 130051216} +{"current_steps": 60265, "total_steps": 61300, "loss": 0.0249, "lr": 4.3490794584336024e-08, "epoch": 9.83115823817292, "percentage": 98.31, "elapsed_time": "17:41:26", "remaining_time": "0:18:13", "throughput": 2042.21, "total_tokens": 130061872} +{"current_steps": 60270, "total_steps": 61300, "loss": 0.0035, "lr": 4.307213258336606e-08, "epoch": 9.831973898858076, "percentage": 98.32, "elapsed_time": "17:41:40", "remaining_time": "0:18:08", "throughput": 2041.96, "total_tokens": 130072944} +{"current_steps": 60275, "total_steps": 61300, "loss": 0.1361, "lr": 4.2655493717597137e-08, "epoch": 9.83278955954323, "percentage": 98.33, "elapsed_time": "17:41:51", "remaining_time": "0:18:03", "throughput": 2041.74, "total_tokens": 130082704} +{"current_steps": 60280, "total_steps": 61300, "loss": 0.0055, "lr": 4.224087802080778e-08, "epoch": 9.833605220228385, "percentage": 98.34, "elapsed_time": "17:42:05", "remaining_time": "0:17:58", "throughput": 2041.47, "total_tokens": 130093936} +{"current_steps": 60285, "total_steps": 61300, "loss": 0.0049, "lr": 4.182828552660722e-08, "epoch": 9.83442088091354, "percentage": 98.34, "elapsed_time": "17:42:17", "remaining_time": "0:17:53", "throughput": 2041.24, "total_tokens": 130103888} +{"current_steps": 60290, "total_steps": 61300, "loss": 0.005, "lr": 4.141771626844093e-08, "epoch": 9.835236541598695, "percentage": 98.35, "elapsed_time": "17:42:30", "remaining_time": "0:17:47", "throughput": 2040.99, "total_tokens": 130114864} +{"current_steps": 60295, "total_steps": 61300, "loss": 0.1241, "lr": 4.100917027959617e-08, "epoch": 9.83605220228385, "percentage": 98.36, "elapsed_time": "17:42:43", "remaining_time": "0:17:42", "throughput": 2040.74, "total_tokens": 130125136} +{"current_steps": 60300, "total_steps": 61300, "loss": 0.0072, "lr": 4.0602647593185325e-08, "epoch": 9.836867862969005, "percentage": 98.37, "elapsed_time": "17:42:56", "remaining_time": "0:17:37", "throughput": 2040.49, "total_tokens": 130136240} +{"current_steps": 60305, "total_steps": 61300, "loss": 0.1205, "lr": 4.0198148242168163e-08, "epoch": 9.83768352365416, "percentage": 98.38, "elapsed_time": "17:43:09", "remaining_time": "0:17:32", "throughput": 2040.25, "total_tokens": 130146864} +{"current_steps": 60310, "total_steps": 61300, "loss": 0.0067, "lr": 3.979567225933234e-08, "epoch": 9.838499184339314, "percentage": 98.38, "elapsed_time": "17:43:21", "remaining_time": "0:17:27", "throughput": 2040.03, "total_tokens": 130156560} +{"current_steps": 60315, "total_steps": 61300, "loss": 0.2939, "lr": 3.939521967730731e-08, "epoch": 9.83931484502447, "percentage": 98.39, "elapsed_time": "17:43:34", "remaining_time": "0:17:22", "throughput": 2039.77, "total_tokens": 130167664} +{"current_steps": 60320, "total_steps": 61300, "loss": 0.1693, "lr": 3.8996790528555985e-08, "epoch": 9.840130505709626, "percentage": 98.4, "elapsed_time": "17:43:48", "remaining_time": "0:17:17", "throughput": 2039.51, "total_tokens": 130178992} +{"current_steps": 60325, "total_steps": 61300, "loss": 0.1008, "lr": 3.860038484537476e-08, "epoch": 9.84094616639478, "percentage": 98.41, "elapsed_time": "17:44:00", "remaining_time": "0:17:11", "throughput": 2039.28, "total_tokens": 130188944} +{"current_steps": 60330, "total_steps": 61300, "loss": 0.0969, "lr": 3.820600265989904e-08, "epoch": 9.841761827079935, "percentage": 98.42, "elapsed_time": "17:44:13", "remaining_time": "0:17:06", "throughput": 2039.03, "total_tokens": 130199408} +{"current_steps": 60335, "total_steps": 61300, "loss": 0.0939, "lr": 3.78136440040977e-08, "epoch": 9.84257748776509, "percentage": 98.43, "elapsed_time": "17:44:27", "remaining_time": "0:17:01", "throughput": 2038.77, "total_tokens": 130211152} +{"current_steps": 60340, "total_steps": 61300, "loss": 0.0939, "lr": 3.742330890978141e-08, "epoch": 9.843393148450245, "percentage": 98.43, "elapsed_time": "17:44:40", "remaining_time": "0:16:56", "throughput": 2038.51, "total_tokens": 130222192} +{"current_steps": 60345, "total_steps": 61300, "loss": 0.0094, "lr": 3.703499740859151e-08, "epoch": 9.844208809135399, "percentage": 98.44, "elapsed_time": "17:44:54", "remaining_time": "0:16:51", "throughput": 2038.26, "total_tokens": 130232912} +{"current_steps": 60350, "total_steps": 61300, "loss": 0.0043, "lr": 3.6648709532002835e-08, "epoch": 9.845024469820554, "percentage": 98.45, "elapsed_time": "17:45:06", "remaining_time": "0:16:45", "throughput": 2038.03, "total_tokens": 130242704} +{"current_steps": 60355, "total_steps": 61300, "loss": 0.0423, "lr": 3.6264445311334774e-08, "epoch": 9.84584013050571, "percentage": 98.46, "elapsed_time": "17:45:19", "remaining_time": "0:16:40", "throughput": 2037.78, "total_tokens": 130254224} +{"current_steps": 60360, "total_steps": 61300, "loss": 0.1178, "lr": 3.588220477773463e-08, "epoch": 9.846655791190864, "percentage": 98.47, "elapsed_time": "17:45:33", "remaining_time": "0:16:35", "throughput": 2037.52, "total_tokens": 130265392} +{"current_steps": 60365, "total_steps": 61300, "loss": 0.0045, "lr": 3.5501987962191505e-08, "epoch": 9.84747145187602, "percentage": 98.47, "elapsed_time": "17:45:46", "remaining_time": "0:16:30", "throughput": 2037.28, "total_tokens": 130276048} +{"current_steps": 60370, "total_steps": 61300, "loss": 0.0026, "lr": 3.5123794895522425e-08, "epoch": 9.848287112561174, "percentage": 98.48, "elapsed_time": "17:45:59", "remaining_time": "0:16:25", "throughput": 2037.02, "total_tokens": 130287472} +{"current_steps": 60375, "total_steps": 61300, "loss": 0.0049, "lr": 3.4747625608391735e-08, "epoch": 9.84910277324633, "percentage": 98.49, "elapsed_time": "17:46:13", "remaining_time": "0:16:20", "throughput": 2036.75, "total_tokens": 130298832} +{"current_steps": 60380, "total_steps": 61300, "loss": 0.0038, "lr": 3.4373480131288936e-08, "epoch": 9.849918433931485, "percentage": 98.5, "elapsed_time": "17:46:25", "remaining_time": "0:16:14", "throughput": 2036.52, "total_tokens": 130308432} +{"current_steps": 60385, "total_steps": 61300, "loss": 0.1483, "lr": 3.400135849454811e-08, "epoch": 9.850734094616639, "percentage": 98.51, "elapsed_time": "17:46:38", "remaining_time": "0:16:09", "throughput": 2036.28, "total_tokens": 130318544} +{"current_steps": 60390, "total_steps": 61300, "loss": 0.2281, "lr": 3.363126072833123e-08, "epoch": 9.851549755301795, "percentage": 98.52, "elapsed_time": "17:46:50", "remaining_time": "0:16:04", "throughput": 2036.05, "total_tokens": 130328176} +{"current_steps": 60395, "total_steps": 61300, "loss": 0.1049, "lr": 3.326318686264485e-08, "epoch": 9.852365415986949, "percentage": 98.52, "elapsed_time": "17:47:03", "remaining_time": "0:15:59", "throughput": 2035.81, "total_tokens": 130338896} +{"current_steps": 60400, "total_steps": 61300, "loss": 0.0933, "lr": 3.2897136927323436e-08, "epoch": 9.853181076672104, "percentage": 98.53, "elapsed_time": "17:47:16", "remaining_time": "0:15:54", "throughput": 2035.55, "total_tokens": 130350160} +{"current_steps": 60405, "total_steps": 61300, "loss": 0.004, "lr": 3.253311095204048e-08, "epoch": 9.85399673735726, "percentage": 98.54, "elapsed_time": "17:47:29", "remaining_time": "0:15:49", "throughput": 2035.3, "total_tokens": 130360976} +{"current_steps": 60410, "total_steps": 61300, "loss": 0.0029, "lr": 3.2171108966308486e-08, "epoch": 9.854812398042414, "percentage": 98.55, "elapsed_time": "17:47:42", "remaining_time": "0:15:43", "throughput": 2035.07, "total_tokens": 130371184} +{"current_steps": 60415, "total_steps": 61300, "loss": 0.0056, "lr": 3.1811130999473415e-08, "epoch": 9.85562805872757, "percentage": 98.56, "elapsed_time": "17:47:54", "remaining_time": "0:15:38", "throughput": 2034.84, "total_tokens": 130381168} +{"current_steps": 60420, "total_steps": 61300, "loss": 0.0039, "lr": 3.145317708071194e-08, "epoch": 9.856443719412724, "percentage": 98.56, "elapsed_time": "17:48:05", "remaining_time": "0:15:33", "throughput": 2034.62, "total_tokens": 130390544} +{"current_steps": 60425, "total_steps": 61300, "loss": 0.0036, "lr": 3.1097247239048057e-08, "epoch": 9.85725938009788, "percentage": 98.57, "elapsed_time": "17:48:18", "remaining_time": "0:15:28", "throughput": 2034.38, "total_tokens": 130401232} +{"current_steps": 60430, "total_steps": 61300, "loss": 0.0031, "lr": 3.074334150333091e-08, "epoch": 9.858075040783035, "percentage": 98.58, "elapsed_time": "17:48:32", "remaining_time": "0:15:23", "throughput": 2034.13, "total_tokens": 130412560} +{"current_steps": 60435, "total_steps": 61300, "loss": 0.0875, "lr": 3.039145990225145e-08, "epoch": 9.858890701468189, "percentage": 98.59, "elapsed_time": "17:48:45", "remaining_time": "0:15:17", "throughput": 2033.88, "total_tokens": 130423472} +{"current_steps": 60440, "total_steps": 61300, "loss": 0.0062, "lr": 3.0041602464334076e-08, "epoch": 9.859706362153345, "percentage": 98.6, "elapsed_time": "17:48:57", "remaining_time": "0:15:12", "throughput": 2033.65, "total_tokens": 130433008} +{"current_steps": 60445, "total_steps": 61300, "loss": 0.1105, "lr": 2.9693769217942203e-08, "epoch": 9.860522022838499, "percentage": 98.61, "elapsed_time": "17:49:12", "remaining_time": "0:15:07", "throughput": 2033.37, "total_tokens": 130445776} +{"current_steps": 60450, "total_steps": 61300, "loss": 0.2335, "lr": 2.9347960191269952e-08, "epoch": 9.861337683523654, "percentage": 98.61, "elapsed_time": "17:49:25", "remaining_time": "0:15:02", "throughput": 2033.13, "total_tokens": 130456720} +{"current_steps": 60455, "total_steps": 61300, "loss": 0.0091, "lr": 2.900417541235323e-08, "epoch": 9.86215334420881, "percentage": 98.62, "elapsed_time": "17:49:39", "remaining_time": "0:14:57", "throughput": 2032.88, "total_tokens": 130468176} +{"current_steps": 60460, "total_steps": 61300, "loss": 0.0154, "lr": 2.8662414909058634e-08, "epoch": 9.862969004893964, "percentage": 98.63, "elapsed_time": "17:49:52", "remaining_time": "0:14:51", "throughput": 2032.63, "total_tokens": 130479344} +{"current_steps": 60465, "total_steps": 61300, "loss": 0.0159, "lr": 2.8322678709094553e-08, "epoch": 9.86378466557912, "percentage": 98.64, "elapsed_time": "17:50:06", "remaining_time": "0:14:46", "throughput": 2032.37, "total_tokens": 130490672} +{"current_steps": 60470, "total_steps": 61300, "loss": 0.0036, "lr": 2.7984966839997294e-08, "epoch": 9.864600326264274, "percentage": 98.65, "elapsed_time": "17:50:20", "remaining_time": "0:14:41", "throughput": 2032.11, "total_tokens": 130502160} +{"current_steps": 60475, "total_steps": 61300, "loss": 0.0029, "lr": 2.7649279329142185e-08, "epoch": 9.86541598694943, "percentage": 98.65, "elapsed_time": "17:50:34", "remaining_time": "0:14:36", "throughput": 2031.85, "total_tokens": 130514160} +{"current_steps": 60480, "total_steps": 61300, "loss": 0.1149, "lr": 2.7315616203749118e-08, "epoch": 9.866231647634583, "percentage": 98.66, "elapsed_time": "17:50:46", "remaining_time": "0:14:31", "throughput": 2031.61, "total_tokens": 130524336} +{"current_steps": 60485, "total_steps": 61300, "loss": 0.171, "lr": 2.6983977490860345e-08, "epoch": 9.867047308319739, "percentage": 98.67, "elapsed_time": "17:51:00", "remaining_time": "0:14:25", "throughput": 2031.36, "total_tokens": 130535440} +{"current_steps": 60490, "total_steps": 61300, "loss": 0.1006, "lr": 2.6654363217362698e-08, "epoch": 9.867862969004895, "percentage": 98.68, "elapsed_time": "17:51:13", "remaining_time": "0:14:20", "throughput": 2031.11, "total_tokens": 130546832} +{"current_steps": 60495, "total_steps": 61300, "loss": 0.0058, "lr": 2.632677340997647e-08, "epoch": 9.868678629690049, "percentage": 98.69, "elapsed_time": "17:51:26", "remaining_time": "0:14:15", "throughput": 2030.87, "total_tokens": 130557168} +{"current_steps": 60500, "total_steps": 61300, "loss": 0.0071, "lr": 2.6001208095258188e-08, "epoch": 9.869494290375204, "percentage": 98.69, "elapsed_time": "17:51:39", "remaining_time": "0:14:10", "throughput": 2030.63, "total_tokens": 130567664} +{"current_steps": 60505, "total_steps": 61300, "loss": 0.0044, "lr": 2.5677667299597863e-08, "epoch": 9.870309951060358, "percentage": 98.7, "elapsed_time": "17:51:51", "remaining_time": "0:14:05", "throughput": 2030.4, "total_tokens": 130577520} +{"current_steps": 60510, "total_steps": 61300, "loss": 0.0052, "lr": 2.5356151049221734e-08, "epoch": 9.871125611745514, "percentage": 98.71, "elapsed_time": "17:52:05", "remaining_time": "0:13:59", "throughput": 2030.13, "total_tokens": 130589328} +{"current_steps": 60515, "total_steps": 61300, "loss": 0.0888, "lr": 2.5036659370197836e-08, "epoch": 9.87194127243067, "percentage": 98.72, "elapsed_time": "17:52:18", "remaining_time": "0:13:54", "throughput": 2029.9, "total_tokens": 130599760} +{"current_steps": 60520, "total_steps": 61300, "loss": 0.008, "lr": 2.4719192288424896e-08, "epoch": 9.872756933115824, "percentage": 98.73, "elapsed_time": "17:52:31", "remaining_time": "0:13:49", "throughput": 2029.65, "total_tokens": 130610576} +{"current_steps": 60525, "total_steps": 61300, "loss": 0.063, "lr": 2.440374982963789e-08, "epoch": 9.87357259380098, "percentage": 98.74, "elapsed_time": "17:52:43", "remaining_time": "0:13:44", "throughput": 2029.43, "total_tokens": 130621168} +{"current_steps": 60530, "total_steps": 61300, "loss": 0.0063, "lr": 2.409033201940525e-08, "epoch": 9.874388254486133, "percentage": 98.74, "elapsed_time": "17:52:55", "remaining_time": "0:13:38", "throughput": 2029.21, "total_tokens": 130630736} +{"current_steps": 60535, "total_steps": 61300, "loss": 0.0713, "lr": 2.3778938883139977e-08, "epoch": 9.875203915171289, "percentage": 98.75, "elapsed_time": "17:53:08", "remaining_time": "0:13:33", "throughput": 2028.96, "total_tokens": 130641840} +{"current_steps": 60540, "total_steps": 61300, "loss": 0.0062, "lr": 2.3469570446080223e-08, "epoch": 9.876019575856443, "percentage": 98.76, "elapsed_time": "17:53:21", "remaining_time": "0:13:28", "throughput": 2028.71, "total_tokens": 130652816} +{"current_steps": 60545, "total_steps": 61300, "loss": 0.0074, "lr": 2.3162226733305925e-08, "epoch": 9.876835236541599, "percentage": 98.77, "elapsed_time": "17:53:34", "remaining_time": "0:13:23", "throughput": 2028.47, "total_tokens": 130663248} +{"current_steps": 60550, "total_steps": 61300, "loss": 0.0311, "lr": 2.2856907769736037e-08, "epoch": 9.877650897226754, "percentage": 98.78, "elapsed_time": "17:53:48", "remaining_time": "0:13:18", "throughput": 2028.22, "total_tokens": 130675184} +{"current_steps": 60555, "total_steps": 61300, "loss": 0.0079, "lr": 2.255361358011465e-08, "epoch": 9.878466557911908, "percentage": 98.78, "elapsed_time": "17:54:02", "remaining_time": "0:13:12", "throughput": 2027.96, "total_tokens": 130686576} +{"current_steps": 60560, "total_steps": 61300, "loss": 0.0038, "lr": 2.2252344189033213e-08, "epoch": 9.879282218597064, "percentage": 98.79, "elapsed_time": "17:54:14", "remaining_time": "0:13:07", "throughput": 2027.74, "total_tokens": 130696240} +{"current_steps": 60565, "total_steps": 61300, "loss": 0.0101, "lr": 2.1953099620911076e-08, "epoch": 9.880097879282218, "percentage": 98.8, "elapsed_time": "17:54:26", "remaining_time": "0:13:02", "throughput": 2027.51, "total_tokens": 130706064} +{"current_steps": 60570, "total_steps": 61300, "loss": 0.0063, "lr": 2.165587990000939e-08, "epoch": 9.880913539967374, "percentage": 98.81, "elapsed_time": "17:54:39", "remaining_time": "0:12:57", "throughput": 2027.26, "total_tokens": 130716720} +{"current_steps": 60575, "total_steps": 61300, "loss": 0.1446, "lr": 2.1360685050419994e-08, "epoch": 9.88172920065253, "percentage": 98.82, "elapsed_time": "17:54:51", "remaining_time": "0:12:51", "throughput": 2027.04, "total_tokens": 130726288} +{"current_steps": 60580, "total_steps": 61300, "loss": 0.0055, "lr": 2.106751509607374e-08, "epoch": 9.882544861337683, "percentage": 98.83, "elapsed_time": "17:55:03", "remaining_time": "0:12:46", "throughput": 2026.81, "total_tokens": 130736368} +{"current_steps": 60585, "total_steps": 61300, "loss": 0.1237, "lr": 2.0776370060737737e-08, "epoch": 9.883360522022839, "percentage": 98.83, "elapsed_time": "17:55:15", "remaining_time": "0:12:41", "throughput": 2026.59, "total_tokens": 130746160} +{"current_steps": 60590, "total_steps": 61300, "loss": 0.0123, "lr": 2.0487249968012546e-08, "epoch": 9.884176182707993, "percentage": 98.84, "elapsed_time": "17:55:26", "remaining_time": "0:12:36", "throughput": 2026.38, "total_tokens": 130755728} +{"current_steps": 60595, "total_steps": 61300, "loss": 0.0051, "lr": 2.020015484133497e-08, "epoch": 9.884991843393149, "percentage": 98.85, "elapsed_time": "17:55:40", "remaining_time": "0:12:30", "throughput": 2026.12, "total_tokens": 130767088} +{"current_steps": 60600, "total_steps": 61300, "loss": 0.0079, "lr": 1.9915084703980845e-08, "epoch": 9.885807504078304, "percentage": 98.86, "elapsed_time": "17:55:52", "remaining_time": "0:12:25", "throughput": 2025.89, "total_tokens": 130776944} +{"current_steps": 60605, "total_steps": 61300, "loss": 0.0172, "lr": 1.9632039579053907e-08, "epoch": 9.886623164763458, "percentage": 98.87, "elapsed_time": "17:56:04", "remaining_time": "0:12:20", "throughput": 2025.67, "total_tokens": 130786480} +{"current_steps": 60610, "total_steps": 61300, "loss": 0.0161, "lr": 1.935101948950524e-08, "epoch": 9.887438825448614, "percentage": 98.87, "elapsed_time": "17:56:18", "remaining_time": "0:12:15", "throughput": 2025.41, "total_tokens": 130797968} +{"current_steps": 60615, "total_steps": 61300, "loss": 0.0844, "lr": 1.9072024458113847e-08, "epoch": 9.888254486133768, "percentage": 98.88, "elapsed_time": "17:56:30", "remaining_time": "0:12:09", "throughput": 2025.18, "total_tokens": 130808272} +{"current_steps": 60620, "total_steps": 61300, "loss": 0.1519, "lr": 1.8795054507494967e-08, "epoch": 9.889070146818923, "percentage": 98.89, "elapsed_time": "17:56:42", "remaining_time": "0:12:04", "throughput": 2024.97, "total_tokens": 130817488} +{"current_steps": 60625, "total_steps": 61300, "loss": 0.0036, "lr": 1.852010966010287e-08, "epoch": 9.88988580750408, "percentage": 98.9, "elapsed_time": "17:56:55", "remaining_time": "0:11:59", "throughput": 2024.73, "total_tokens": 130828432} +{"current_steps": 60630, "total_steps": 61300, "loss": 0.129, "lr": 1.8247189938225274e-08, "epoch": 9.890701468189233, "percentage": 98.91, "elapsed_time": "17:57:07", "remaining_time": "0:11:54", "throughput": 2024.49, "total_tokens": 130838416} +{"current_steps": 60635, "total_steps": 61300, "loss": 0.0052, "lr": 1.7976295363988927e-08, "epoch": 9.891517128874389, "percentage": 98.92, "elapsed_time": "17:57:19", "remaining_time": "0:11:48", "throughput": 2024.27, "total_tokens": 130847920} +{"current_steps": 60640, "total_steps": 61300, "loss": 0.2132, "lr": 1.7707425959348488e-08, "epoch": 9.892332789559543, "percentage": 98.92, "elapsed_time": "17:57:32", "remaining_time": "0:11:43", "throughput": 2024.02, "total_tokens": 130859184} +{"current_steps": 60645, "total_steps": 61300, "loss": 0.0067, "lr": 1.744058174610319e-08, "epoch": 9.893148450244698, "percentage": 98.93, "elapsed_time": "17:57:45", "remaining_time": "0:11:38", "throughput": 2023.78, "total_tokens": 130869808} +{"current_steps": 60650, "total_steps": 61300, "loss": 0.0046, "lr": 1.7175762745885727e-08, "epoch": 9.893964110929852, "percentage": 98.94, "elapsed_time": "17:57:59", "remaining_time": "0:11:33", "throughput": 2023.53, "total_tokens": 130880912} +{"current_steps": 60655, "total_steps": 61300, "loss": 0.0115, "lr": 1.6912968980162257e-08, "epoch": 9.894779771615008, "percentage": 98.95, "elapsed_time": "17:58:13", "remaining_time": "0:11:27", "throughput": 2023.28, "total_tokens": 130892336} +{"current_steps": 60660, "total_steps": 61300, "loss": 0.0078, "lr": 1.665220047023519e-08, "epoch": 9.895595432300164, "percentage": 98.96, "elapsed_time": "17:58:23", "remaining_time": "0:11:22", "throughput": 2023.08, "total_tokens": 130900752} +{"current_steps": 60665, "total_steps": 61300, "loss": 0.1296, "lr": 1.639345723724872e-08, "epoch": 9.896411092985318, "percentage": 98.96, "elapsed_time": "17:58:36", "remaining_time": "0:11:17", "throughput": 2022.83, "total_tokens": 130911600} +{"current_steps": 60670, "total_steps": 61300, "loss": 0.0045, "lr": 1.6136739302169412e-08, "epoch": 9.897226753670473, "percentage": 98.97, "elapsed_time": "17:58:50", "remaining_time": "0:11:12", "throughput": 2022.58, "total_tokens": 130922640} +{"current_steps": 60675, "total_steps": 61300, "loss": 0.0549, "lr": 1.588204668581672e-08, "epoch": 9.898042414355627, "percentage": 98.98, "elapsed_time": "17:59:03", "remaining_time": "0:11:06", "throughput": 2022.34, "total_tokens": 130933136} +{"current_steps": 60680, "total_steps": 61300, "loss": 0.02, "lr": 1.5629379408832468e-08, "epoch": 9.898858075040783, "percentage": 98.99, "elapsed_time": "17:59:17", "remaining_time": "0:11:01", "throughput": 2022.09, "total_tokens": 130944336} +{"current_steps": 60685, "total_steps": 61300, "loss": 0.1066, "lr": 1.537873749169749e-08, "epoch": 9.899673735725939, "percentage": 99.0, "elapsed_time": "17:59:27", "remaining_time": "0:10:56", "throughput": 2021.89, "total_tokens": 130952848} +{"current_steps": 60690, "total_steps": 61300, "loss": 0.1251, "lr": 1.513012095473443e-08, "epoch": 9.900489396411093, "percentage": 99.0, "elapsed_time": "17:59:40", "remaining_time": "0:10:51", "throughput": 2021.65, "total_tokens": 130963536} +{"current_steps": 60695, "total_steps": 61300, "loss": 0.23, "lr": 1.4883529818096598e-08, "epoch": 9.901305057096248, "percentage": 99.01, "elapsed_time": "17:59:53", "remaining_time": "0:10:45", "throughput": 2021.41, "total_tokens": 130973840} +{"current_steps": 60700, "total_steps": 61300, "loss": 0.0043, "lr": 1.4638964101773568e-08, "epoch": 9.902120717781402, "percentage": 99.02, "elapsed_time": "18:00:05", "remaining_time": "0:10:40", "throughput": 2021.18, "total_tokens": 130984304} +{"current_steps": 60705, "total_steps": 61300, "loss": 0.0057, "lr": 1.4396423825588367e-08, "epoch": 9.902936378466558, "percentage": 99.03, "elapsed_time": "18:00:19", "remaining_time": "0:10:35", "throughput": 2020.93, "total_tokens": 130995504} +{"current_steps": 60710, "total_steps": 61300, "loss": 0.1106, "lr": 1.4155909009205826e-08, "epoch": 9.903752039151712, "percentage": 99.04, "elapsed_time": "18:00:32", "remaining_time": "0:10:30", "throughput": 2020.69, "total_tokens": 131005968} +{"current_steps": 60715, "total_steps": 61300, "loss": 0.0043, "lr": 1.3917419672124233e-08, "epoch": 9.904567699836868, "percentage": 99.05, "elapsed_time": "18:00:46", "remaining_time": "0:10:24", "throughput": 2020.44, "total_tokens": 131018160} +{"current_steps": 60720, "total_steps": 61300, "loss": 0.0835, "lr": 1.368095583367257e-08, "epoch": 9.905383360522023, "percentage": 99.05, "elapsed_time": "18:00:59", "remaining_time": "0:10:19", "throughput": 2020.2, "total_tokens": 131029008} +{"current_steps": 60725, "total_steps": 61300, "loss": 0.0512, "lr": 1.3446517513021617e-08, "epoch": 9.906199021207177, "percentage": 99.06, "elapsed_time": "18:01:11", "remaining_time": "0:10:14", "throughput": 2019.97, "total_tokens": 131038960} +{"current_steps": 60730, "total_steps": 61300, "loss": 0.0058, "lr": 1.321410472917839e-08, "epoch": 9.907014681892333, "percentage": 99.07, "elapsed_time": "18:01:25", "remaining_time": "0:10:08", "throughput": 2019.73, "total_tokens": 131050160} +{"current_steps": 60735, "total_steps": 61300, "loss": 0.0256, "lr": 1.2983717500977822e-08, "epoch": 9.907830342577487, "percentage": 99.08, "elapsed_time": "18:01:37", "remaining_time": "0:10:03", "throughput": 2019.51, "total_tokens": 131060048} +{"current_steps": 60740, "total_steps": 61300, "loss": 0.1848, "lr": 1.275535584710219e-08, "epoch": 9.908646003262643, "percentage": 99.09, "elapsed_time": "18:01:48", "remaining_time": "0:09:58", "throughput": 2019.29, "total_tokens": 131069360} +{"current_steps": 60745, "total_steps": 61300, "loss": 0.0065, "lr": 1.2529019786061691e-08, "epoch": 9.909461663947798, "percentage": 99.09, "elapsed_time": "18:02:01", "remaining_time": "0:09:53", "throughput": 2019.06, "total_tokens": 131079888} +{"current_steps": 60750, "total_steps": 61300, "loss": 0.0058, "lr": 1.2304709336205533e-08, "epoch": 9.910277324632952, "percentage": 99.1, "elapsed_time": "18:02:14", "remaining_time": "0:09:47", "throughput": 2018.82, "total_tokens": 131090512} +{"current_steps": 60755, "total_steps": 61300, "loss": 0.1885, "lr": 1.2082424515713619e-08, "epoch": 9.911092985318108, "percentage": 99.11, "elapsed_time": "18:02:28", "remaining_time": "0:09:42", "throughput": 2018.54, "total_tokens": 131101680} +{"current_steps": 60760, "total_steps": 61300, "loss": 0.0615, "lr": 1.1862165342607645e-08, "epoch": 9.911908646003262, "percentage": 99.12, "elapsed_time": "18:02:41", "remaining_time": "0:09:37", "throughput": 2018.31, "total_tokens": 131112336} +{"current_steps": 60765, "total_steps": 61300, "loss": 0.0077, "lr": 1.1643931834745548e-08, "epoch": 9.912724306688418, "percentage": 99.13, "elapsed_time": "18:02:54", "remaining_time": "0:09:32", "throughput": 2018.06, "total_tokens": 131123088} +{"current_steps": 60770, "total_steps": 61300, "loss": 0.0498, "lr": 1.1427724009813179e-08, "epoch": 9.913539967373573, "percentage": 99.14, "elapsed_time": "18:03:06", "remaining_time": "0:09:26", "throughput": 2017.85, "total_tokens": 131132368} +{"current_steps": 60775, "total_steps": 61300, "loss": 0.0106, "lr": 1.1213541885340962e-08, "epoch": 9.914355628058727, "percentage": 99.14, "elapsed_time": "18:03:19", "remaining_time": "0:09:21", "throughput": 2017.6, "total_tokens": 131143600} +{"current_steps": 60780, "total_steps": 61300, "loss": 0.0036, "lr": 1.1001385478692783e-08, "epoch": 9.915171288743883, "percentage": 99.15, "elapsed_time": "18:03:32", "remaining_time": "0:09:16", "throughput": 2017.37, "total_tokens": 131153872} +{"current_steps": 60785, "total_steps": 61300, "loss": 0.0977, "lr": 1.0791254807063223e-08, "epoch": 9.915986949429037, "percentage": 99.16, "elapsed_time": "18:03:45", "remaining_time": "0:09:10", "throughput": 2017.12, "total_tokens": 131164848} +{"current_steps": 60790, "total_steps": 61300, "loss": 0.0057, "lr": 1.0583149887488653e-08, "epoch": 9.916802610114193, "percentage": 99.17, "elapsed_time": "18:03:58", "remaining_time": "0:09:05", "throughput": 2016.89, "total_tokens": 131175280} +{"current_steps": 60795, "total_steps": 61300, "loss": 0.0042, "lr": 1.0377070736838912e-08, "epoch": 9.917618270799348, "percentage": 99.18, "elapsed_time": "18:04:11", "remaining_time": "0:09:00", "throughput": 2016.65, "total_tokens": 131185776} +{"current_steps": 60800, "total_steps": 61300, "loss": 0.0479, "lr": 1.017301737182008e-08, "epoch": 9.918433931484502, "percentage": 99.18, "elapsed_time": "18:04:24", "remaining_time": "0:08:55", "throughput": 2016.4, "total_tokens": 131196944} +{"current_steps": 60805, "total_steps": 61300, "loss": 0.0048, "lr": 9.970989808974485e-09, "epoch": 9.919249592169658, "percentage": 99.19, "elapsed_time": "18:04:38", "remaining_time": "0:08:49", "throughput": 2016.15, "total_tokens": 131208752} +{"current_steps": 60810, "total_steps": 61300, "loss": 0.007, "lr": 9.77098806467791e-09, "epoch": 9.920065252854812, "percentage": 99.2, "elapsed_time": "18:04:49", "remaining_time": "0:08:44", "throughput": 2015.95, "total_tokens": 131217360} +{"current_steps": 60815, "total_steps": 61300, "loss": 0.003, "lr": 9.573012155145166e-09, "epoch": 9.920880913539968, "percentage": 99.21, "elapsed_time": "18:05:02", "remaining_time": "0:08:39", "throughput": 2015.7, "total_tokens": 131228304} +{"current_steps": 60820, "total_steps": 61300, "loss": 0.0324, "lr": 9.37706209642175e-09, "epoch": 9.921696574225122, "percentage": 99.22, "elapsed_time": "18:05:16", "remaining_time": "0:08:33", "throughput": 2015.46, "total_tokens": 131239568} +{"current_steps": 60825, "total_steps": 61300, "loss": 0.1684, "lr": 9.183137904397732e-09, "epoch": 9.922512234910277, "percentage": 99.23, "elapsed_time": "18:05:29", "remaining_time": "0:08:28", "throughput": 2015.22, "total_tokens": 131250576} +{"current_steps": 60830, "total_steps": 61300, "loss": 0.0946, "lr": 8.991239594788315e-09, "epoch": 9.923327895595433, "percentage": 99.23, "elapsed_time": "18:05:43", "remaining_time": "0:08:23", "throughput": 2014.97, "total_tokens": 131261616} +{"current_steps": 60835, "total_steps": 61300, "loss": 0.1195, "lr": 8.801367183153276e-09, "epoch": 9.924143556280587, "percentage": 99.24, "elapsed_time": "18:05:56", "remaining_time": "0:08:18", "throughput": 2014.73, "total_tokens": 131272400} +{"current_steps": 60840, "total_steps": 61300, "loss": 0.1882, "lr": 8.61352068488308e-09, "epoch": 9.924959216965743, "percentage": 99.25, "elapsed_time": "18:06:09", "remaining_time": "0:08:12", "throughput": 2014.49, "total_tokens": 131283280} +{"current_steps": 60845, "total_steps": 61300, "loss": 0.005, "lr": 8.427700115207216e-09, "epoch": 9.925774877650896, "percentage": 99.26, "elapsed_time": "18:06:22", "remaining_time": "0:08:07", "throughput": 2014.26, "total_tokens": 131293808} +{"current_steps": 60850, "total_steps": 61300, "loss": 0.0054, "lr": 8.243905489185855e-09, "epoch": 9.926590538336052, "percentage": 99.27, "elapsed_time": "18:06:34", "remaining_time": "0:08:02", "throughput": 2014.05, "total_tokens": 131304016} +{"current_steps": 60855, "total_steps": 61300, "loss": 0.1467, "lr": 8.062136821723742e-09, "epoch": 9.927406199021208, "percentage": 99.27, "elapsed_time": "18:06:46", "remaining_time": "0:07:56", "throughput": 2013.82, "total_tokens": 131314032} +{"current_steps": 60860, "total_steps": 61300, "loss": 0.1236, "lr": 7.882394127550763e-09, "epoch": 9.928221859706362, "percentage": 99.28, "elapsed_time": "18:06:58", "remaining_time": "0:07:51", "throughput": 2013.6, "total_tokens": 131324112} +{"current_steps": 60865, "total_steps": 61300, "loss": 0.1006, "lr": 7.704677421238593e-09, "epoch": 9.929037520391518, "percentage": 99.29, "elapsed_time": "18:07:11", "remaining_time": "0:07:46", "throughput": 2013.37, "total_tokens": 131334352} +{"current_steps": 60870, "total_steps": 61300, "loss": 0.2849, "lr": 7.528986717195152e-09, "epoch": 9.929853181076671, "percentage": 99.3, "elapsed_time": "18:07:23", "remaining_time": "0:07:40", "throughput": 2013.14, "total_tokens": 131344656} +{"current_steps": 60875, "total_steps": 61300, "loss": 0.0323, "lr": 7.355322029661826e-09, "epoch": 9.930668841761827, "percentage": 99.31, "elapsed_time": "18:07:37", "remaining_time": "0:07:35", "throughput": 2012.9, "total_tokens": 131355984} +{"current_steps": 60880, "total_steps": 61300, "loss": 0.0141, "lr": 7.183683372719019e-09, "epoch": 9.931484502446983, "percentage": 99.31, "elapsed_time": "18:07:50", "remaining_time": "0:07:30", "throughput": 2012.66, "total_tokens": 131367056} +{"current_steps": 60885, "total_steps": 61300, "loss": 0.0777, "lr": 7.0140707602805995e-09, "epoch": 9.932300163132137, "percentage": 99.32, "elapsed_time": "18:08:03", "remaining_time": "0:07:24", "throughput": 2012.41, "total_tokens": 131378192} +{"current_steps": 60890, "total_steps": 61300, "loss": 0.2534, "lr": 6.846484206091131e-09, "epoch": 9.933115823817293, "percentage": 99.33, "elapsed_time": "18:08:16", "remaining_time": "0:07:19", "throughput": 2012.18, "total_tokens": 131389040} +{"current_steps": 60895, "total_steps": 61300, "loss": 0.0498, "lr": 6.6809237237425156e-09, "epoch": 9.933931484502446, "percentage": 99.34, "elapsed_time": "18:08:29", "remaining_time": "0:07:14", "throughput": 2011.96, "total_tokens": 131399664} +{"current_steps": 60900, "total_steps": 61300, "loss": 0.0091, "lr": 6.517389326651801e-09, "epoch": 9.934747145187602, "percentage": 99.35, "elapsed_time": "18:08:41", "remaining_time": "0:07:09", "throughput": 2011.73, "total_tokens": 131409680} +{"current_steps": 60905, "total_steps": 61300, "loss": 0.006, "lr": 6.3558810280778254e-09, "epoch": 9.935562805872756, "percentage": 99.36, "elapsed_time": "18:08:54", "remaining_time": "0:07:03", "throughput": 2011.5, "total_tokens": 131420240} +{"current_steps": 60910, "total_steps": 61300, "loss": 0.0073, "lr": 6.196398841112893e-09, "epoch": 9.936378466557912, "percentage": 99.36, "elapsed_time": "18:09:05", "remaining_time": "0:06:58", "throughput": 2011.29, "total_tokens": 131429488} +{"current_steps": 60915, "total_steps": 61300, "loss": 0.1406, "lr": 6.038942778685553e-09, "epoch": 9.937194127243067, "percentage": 99.37, "elapsed_time": "18:09:18", "remaining_time": "0:06:53", "throughput": 2011.06, "total_tokens": 131439792} +{"current_steps": 60920, "total_steps": 61300, "loss": 0.0762, "lr": 5.883512853557816e-09, "epoch": 9.938009787928221, "percentage": 99.38, "elapsed_time": "18:09:29", "remaining_time": "0:06:47", "throughput": 2010.85, "total_tokens": 131448976} +{"current_steps": 60925, "total_steps": 61300, "loss": 0.0109, "lr": 5.730109078330714e-09, "epoch": 9.938825448613377, "percentage": 99.39, "elapsed_time": "18:09:42", "remaining_time": "0:06:42", "throughput": 2010.62, "total_tokens": 131459088} +{"current_steps": 60930, "total_steps": 61300, "loss": 0.0796, "lr": 5.578731465444298e-09, "epoch": 9.939641109298531, "percentage": 99.4, "elapsed_time": "18:09:55", "remaining_time": "0:06:37", "throughput": 2010.38, "total_tokens": 131470096} +{"current_steps": 60935, "total_steps": 61300, "loss": 0.1152, "lr": 5.429380027163755e-09, "epoch": 9.940456769983687, "percentage": 99.4, "elapsed_time": "18:10:07", "remaining_time": "0:06:31", "throughput": 2010.17, "total_tokens": 131479376} +{"current_steps": 60940, "total_steps": 61300, "loss": 0.0122, "lr": 5.2820547755988434e-09, "epoch": 9.941272430668842, "percentage": 99.41, "elapsed_time": "18:10:22", "remaining_time": "0:06:26", "throughput": 2009.9, "total_tokens": 131491792} +{"current_steps": 60945, "total_steps": 61300, "loss": 0.0021, "lr": 5.1367557226927875e-09, "epoch": 9.942088091353996, "percentage": 99.42, "elapsed_time": "18:10:34", "remaining_time": "0:06:21", "throughput": 2009.67, "total_tokens": 131502512} +{"current_steps": 60950, "total_steps": 61300, "loss": 0.2115, "lr": 4.9934828802250535e-09, "epoch": 9.942903752039152, "percentage": 99.43, "elapsed_time": "18:10:48", "remaining_time": "0:06:15", "throughput": 2009.42, "total_tokens": 131514224} +{"current_steps": 60955, "total_steps": 61300, "loss": 0.096, "lr": 4.852236259805798e-09, "epoch": 9.943719412724306, "percentage": 99.44, "elapsed_time": "18:11:02", "remaining_time": "0:06:10", "throughput": 2009.16, "total_tokens": 131525840} +{"current_steps": 60960, "total_steps": 61300, "loss": 0.0079, "lr": 4.7130158728925236e-09, "epoch": 9.944535073409462, "percentage": 99.45, "elapsed_time": "18:11:15", "remaining_time": "0:06:05", "throughput": 2008.94, "total_tokens": 131536208} +{"current_steps": 60965, "total_steps": 61300, "loss": 0.1114, "lr": 4.575821730765095e-09, "epoch": 9.945350734094617, "percentage": 99.45, "elapsed_time": "18:11:29", "remaining_time": "0:05:59", "throughput": 2008.69, "total_tokens": 131547344} +{"current_steps": 60970, "total_steps": 61300, "loss": 0.0839, "lr": 4.440653844545173e-09, "epoch": 9.946166394779771, "percentage": 99.46, "elapsed_time": "18:11:43", "remaining_time": "0:05:54", "throughput": 2008.43, "total_tokens": 131558544} +{"current_steps": 60975, "total_steps": 61300, "loss": 0.1256, "lr": 4.307512225196209e-09, "epoch": 9.946982055464927, "percentage": 99.47, "elapsed_time": "18:11:55", "remaining_time": "0:05:49", "throughput": 2008.2, "total_tokens": 131569136} +{"current_steps": 60980, "total_steps": 61300, "loss": 0.1248, "lr": 4.176396883504019e-09, "epoch": 9.947797716150081, "percentage": 99.48, "elapsed_time": "18:12:10", "remaining_time": "0:05:43", "throughput": 2007.94, "total_tokens": 131580848} +{"current_steps": 60985, "total_steps": 61300, "loss": 0.0022, "lr": 4.047307830101765e-09, "epoch": 9.948613376835237, "percentage": 99.49, "elapsed_time": "18:12:23", "remaining_time": "0:05:38", "throughput": 2007.71, "total_tokens": 131591664} +{"current_steps": 60990, "total_steps": 61300, "loss": 0.1028, "lr": 3.9202450754533e-09, "epoch": 9.949429037520392, "percentage": 99.49, "elapsed_time": "18:12:35", "remaining_time": "0:05:33", "throughput": 2007.48, "total_tokens": 131602032} +{"current_steps": 60995, "total_steps": 61300, "loss": 0.1077, "lr": 3.79520862985594e-09, "epoch": 9.950244698205546, "percentage": 99.5, "elapsed_time": "18:12:49", "remaining_time": "0:05:27", "throughput": 2007.24, "total_tokens": 131613520} +{"current_steps": 61000, "total_steps": 61300, "loss": 0.0221, "lr": 3.6721985034515738e-09, "epoch": 9.951060358890702, "percentage": 99.51, "elapsed_time": "18:13:02", "remaining_time": "0:05:22", "throughput": 2007.0, "total_tokens": 131624624} +{"current_steps": 61005, "total_steps": 61300, "loss": 0.0057, "lr": 3.5512147062072287e-09, "epoch": 9.951876019575856, "percentage": 99.52, "elapsed_time": "18:13:14", "remaining_time": "0:05:17", "throughput": 2006.79, "total_tokens": 131634416} +{"current_steps": 61010, "total_steps": 61300, "loss": 0.0025, "lr": 3.4322572479345005e-09, "epoch": 9.952691680261012, "percentage": 99.53, "elapsed_time": "18:13:27", "remaining_time": "0:05:11", "throughput": 2006.55, "total_tokens": 131645232} +{"current_steps": 61015, "total_steps": 61300, "loss": 0.1842, "lr": 3.3153261382729008e-09, "epoch": 9.953507340946166, "percentage": 99.54, "elapsed_time": "18:13:40", "remaining_time": "0:05:06", "throughput": 2006.32, "total_tokens": 131655824} +{"current_steps": 61020, "total_steps": 61300, "loss": 0.0044, "lr": 3.2004213867009582e-09, "epoch": 9.954323001631321, "percentage": 99.54, "elapsed_time": "18:13:53", "remaining_time": "0:05:01", "throughput": 2006.09, "total_tokens": 131666640} +{"current_steps": 61025, "total_steps": 61300, "loss": 0.0048, "lr": 3.0875430025362197e-09, "epoch": 9.955138662316477, "percentage": 99.55, "elapsed_time": "18:14:04", "remaining_time": "0:04:55", "throughput": 2005.9, "total_tokens": 131675120} +{"current_steps": 61030, "total_steps": 61300, "loss": 0.08, "lr": 2.9766909949296983e-09, "epoch": 9.955954323001631, "percentage": 99.56, "elapsed_time": "18:14:17", "remaining_time": "0:04:50", "throughput": 2005.65, "total_tokens": 131686096} +{"current_steps": 61035, "total_steps": 61300, "loss": 0.0041, "lr": 2.8678653728658746e-09, "epoch": 9.956769983686787, "percentage": 99.57, "elapsed_time": "18:14:32", "remaining_time": "0:04:45", "throughput": 2005.39, "total_tokens": 131697968} +{"current_steps": 61040, "total_steps": 61300, "loss": 0.1066, "lr": 2.761066145168245e-09, "epoch": 9.95758564437194, "percentage": 99.58, "elapsed_time": "18:14:45", "remaining_time": "0:04:39", "throughput": 2005.15, "total_tokens": 131709168} +{"current_steps": 61045, "total_steps": 61300, "loss": 0.2007, "lr": 2.656293320490999e-09, "epoch": 9.958401305057096, "percentage": 99.58, "elapsed_time": "18:14:59", "remaining_time": "0:04:34", "throughput": 2004.91, "total_tokens": 131720656} +{"current_steps": 61050, "total_steps": 61300, "loss": 0.0086, "lr": 2.5535469073301176e-09, "epoch": 9.959216965742252, "percentage": 99.59, "elapsed_time": "18:15:12", "remaining_time": "0:04:29", "throughput": 2004.67, "total_tokens": 131731536} +{"current_steps": 61055, "total_steps": 61300, "loss": 0.0055, "lr": 2.4528269140150497e-09, "epoch": 9.960032626427406, "percentage": 99.6, "elapsed_time": "18:15:26", "remaining_time": "0:04:23", "throughput": 2004.42, "total_tokens": 131742928} +{"current_steps": 61060, "total_steps": 61300, "loss": 0.0622, "lr": 2.354133348711485e-09, "epoch": 9.960848287112562, "percentage": 99.61, "elapsed_time": "18:15:37", "remaining_time": "0:04:18", "throughput": 2004.23, "total_tokens": 131752496} +{"current_steps": 61065, "total_steps": 61300, "loss": 0.0055, "lr": 2.2574662194158047e-09, "epoch": 9.961663947797716, "percentage": 99.62, "elapsed_time": "18:15:50", "remaining_time": "0:04:13", "throughput": 2003.99, "total_tokens": 131764048} +{"current_steps": 61070, "total_steps": 61300, "loss": 0.0688, "lr": 2.1628255339689596e-09, "epoch": 9.962479608482871, "percentage": 99.62, "elapsed_time": "18:16:03", "remaining_time": "0:04:07", "throughput": 2003.77, "total_tokens": 131774352} +{"current_steps": 61075, "total_steps": 61300, "loss": 0.0081, "lr": 2.0702113000425903e-09, "epoch": 9.963295269168025, "percentage": 99.63, "elapsed_time": "18:16:14", "remaining_time": "0:04:02", "throughput": 2003.56, "total_tokens": 131783696} +{"current_steps": 61080, "total_steps": 61300, "loss": 0.0128, "lr": 1.979623525141805e-09, "epoch": 9.964110929853181, "percentage": 99.64, "elapsed_time": "18:16:28", "remaining_time": "0:03:56", "throughput": 2003.32, "total_tokens": 131795696} +{"current_steps": 61085, "total_steps": 61300, "loss": 0.0053, "lr": 1.891062216610728e-09, "epoch": 9.964926590538337, "percentage": 99.65, "elapsed_time": "18:16:40", "remaining_time": "0:03:51", "throughput": 2003.1, "total_tokens": 131805616} +{"current_steps": 61090, "total_steps": 61300, "loss": 0.1396, "lr": 1.804527381629728e-09, "epoch": 9.96574225122349, "percentage": 99.66, "elapsed_time": "18:16:52", "remaining_time": "0:03:46", "throughput": 2002.9, "total_tokens": 131815056} +{"current_steps": 61095, "total_steps": 61300, "loss": 0.0044, "lr": 1.7200190272126382e-09, "epoch": 9.966557911908646, "percentage": 99.67, "elapsed_time": "18:17:04", "remaining_time": "0:03:40", "throughput": 2002.67, "total_tokens": 131825392} +{"current_steps": 61100, "total_steps": 61300, "loss": 0.0852, "lr": 1.6375371602123103e-09, "epoch": 9.9673735725938, "percentage": 99.67, "elapsed_time": "18:17:17", "remaining_time": "0:03:35", "throughput": 2002.44, "total_tokens": 131836144} +{"current_steps": 61105, "total_steps": 61300, "loss": 0.0615, "lr": 1.5570817873122868e-09, "epoch": 9.968189233278956, "percentage": 99.68, "elapsed_time": "18:17:30", "remaining_time": "0:03:30", "throughput": 2002.2, "total_tokens": 131846672} +{"current_steps": 61110, "total_steps": 61300, "loss": 0.3261, "lr": 1.4786529150379036e-09, "epoch": 9.969004893964112, "percentage": 99.69, "elapsed_time": "18:17:45", "remaining_time": "0:03:24", "throughput": 2001.94, "total_tokens": 131858544} +{"current_steps": 61115, "total_steps": 61300, "loss": 0.097, "lr": 1.4022505497424122e-09, "epoch": 9.969820554649266, "percentage": 99.7, "elapsed_time": "18:17:58", "remaining_time": "0:03:19", "throughput": 2001.71, "total_tokens": 131869296} +{"current_steps": 61120, "total_steps": 61300, "loss": 0.0165, "lr": 1.3278746976236322e-09, "epoch": 9.970636215334421, "percentage": 99.71, "elapsed_time": "18:18:10", "remaining_time": "0:03:14", "throughput": 2001.48, "total_tokens": 131879376} +{"current_steps": 61125, "total_steps": 61300, "loss": 0.0055, "lr": 1.255525364710075e-09, "epoch": 9.971451876019575, "percentage": 99.71, "elapsed_time": "18:18:24", "remaining_time": "0:03:08", "throughput": 2001.24, "total_tokens": 131890768} +{"current_steps": 61130, "total_steps": 61300, "loss": 0.0039, "lr": 1.1852025568637183e-09, "epoch": 9.97226753670473, "percentage": 99.72, "elapsed_time": "18:18:36", "remaining_time": "0:03:03", "throughput": 2001.02, "total_tokens": 131901104} +{"current_steps": 61135, "total_steps": 61300, "loss": 0.2061, "lr": 1.116906279791108e-09, "epoch": 9.973083197389887, "percentage": 99.73, "elapsed_time": "18:18:50", "remaining_time": "0:02:57", "throughput": 2000.78, "total_tokens": 131912208} +{"current_steps": 61140, "total_steps": 61300, "loss": 0.1843, "lr": 1.0506365390211547e-09, "epoch": 9.97389885807504, "percentage": 99.74, "elapsed_time": "18:19:03", "remaining_time": "0:02:52", "throughput": 2000.54, "total_tokens": 131923472} +{"current_steps": 61145, "total_steps": 61300, "loss": 0.3352, "lr": 9.863933399328895e-10, "epoch": 9.974714518760196, "percentage": 99.75, "elapsed_time": "18:19:16", "remaining_time": "0:02:47", "throughput": 2000.31, "total_tokens": 131934384} +{"current_steps": 61150, "total_steps": 61300, "loss": 0.1085, "lr": 9.241766877304825e-10, "epoch": 9.97553017944535, "percentage": 99.76, "elapsed_time": "18:19:29", "remaining_time": "0:02:41", "throughput": 2000.08, "total_tokens": 131944784} +{"current_steps": 61155, "total_steps": 61300, "loss": 0.0992, "lr": 8.639865874571218e-10, "epoch": 9.976345840130506, "percentage": 99.76, "elapsed_time": "18:19:42", "remaining_time": "0:02:36", "throughput": 1999.85, "total_tokens": 131955088} +{"current_steps": 61160, "total_steps": 61300, "loss": 0.1173, "lr": 8.058230439950132e-10, "epoch": 9.977161500815662, "percentage": 99.77, "elapsed_time": "18:19:55", "remaining_time": "0:02:31", "throughput": 1999.62, "total_tokens": 131966384} +{"current_steps": 61165, "total_steps": 61300, "loss": 0.0584, "lr": 7.496860620570534e-10, "epoch": 9.977977161500815, "percentage": 99.78, "elapsed_time": "18:20:09", "remaining_time": "0:02:25", "throughput": 1999.38, "total_tokens": 131977200} +{"current_steps": 61170, "total_steps": 61300, "loss": 0.0748, "lr": 6.955756461951568e-10, "epoch": 9.978792822185971, "percentage": 99.79, "elapsed_time": "18:20:23", "remaining_time": "0:02:20", "throughput": 1999.13, "total_tokens": 131988848} +{"current_steps": 61175, "total_steps": 61300, "loss": 0.066, "lr": 6.434918007947044e-10, "epoch": 9.979608482871125, "percentage": 99.8, "elapsed_time": "18:20:37", "remaining_time": "0:02:14", "throughput": 1998.88, "total_tokens": 132000752} +{"current_steps": 61180, "total_steps": 61300, "loss": 0.0055, "lr": 5.934345300773192e-10, "epoch": 9.98042414355628, "percentage": 99.8, "elapsed_time": "18:20:49", "remaining_time": "0:02:09", "throughput": 1998.67, "total_tokens": 132010544} +{"current_steps": 61185, "total_steps": 61300, "loss": 0.0827, "lr": 5.454038381008664e-10, "epoch": 9.981239804241435, "percentage": 99.81, "elapsed_time": "18:21:02", "remaining_time": "0:02:04", "throughput": 1998.43, "total_tokens": 132021552} +{"current_steps": 61190, "total_steps": 61300, "loss": 0.2025, "lr": 4.993997287622287e-10, "epoch": 9.98205546492659, "percentage": 99.82, "elapsed_time": "18:21:15", "remaining_time": "0:01:58", "throughput": 1998.2, "total_tokens": 132032752} +{"current_steps": 61195, "total_steps": 61300, "loss": 0.0046, "lr": 4.554222057889801e-10, "epoch": 9.982871125611746, "percentage": 99.83, "elapsed_time": "18:21:28", "remaining_time": "0:01:53", "throughput": 1997.97, "total_tokens": 132043536} +{"current_steps": 61200, "total_steps": 61300, "loss": 0.0163, "lr": 4.1347127274493635e-10, "epoch": 9.9836867862969, "percentage": 99.84, "elapsed_time": "18:21:41", "remaining_time": "0:01:48", "throughput": 1997.75, "total_tokens": 132053840} +{"current_steps": 61205, "total_steps": 61300, "loss": 0.0111, "lr": 3.735469330301555e-10, "epoch": 9.984502446982056, "percentage": 99.85, "elapsed_time": "18:21:54", "remaining_time": "0:01:42", "throughput": 1997.52, "total_tokens": 132064400} +{"current_steps": 61210, "total_steps": 61300, "loss": 0.1199, "lr": 3.356491898837133e-10, "epoch": 9.98531810766721, "percentage": 99.85, "elapsed_time": "18:22:05", "remaining_time": "0:01:37", "throughput": 1997.33, "total_tokens": 132073552} +{"current_steps": 61215, "total_steps": 61300, "loss": 0.0062, "lr": 2.997780463753763e-10, "epoch": 9.986133768352365, "percentage": 99.86, "elapsed_time": "18:22:18", "remaining_time": "0:01:31", "throughput": 1997.09, "total_tokens": 132084400} +{"current_steps": 61220, "total_steps": 61300, "loss": 0.0056, "lr": 2.659335054139289e-10, "epoch": 9.986949429037521, "percentage": 99.87, "elapsed_time": "18:22:32", "remaining_time": "0:01:26", "throughput": 1996.85, "total_tokens": 132095856} +{"current_steps": 61225, "total_steps": 61300, "loss": 0.0772, "lr": 2.341155697471731e-10, "epoch": 9.987765089722675, "percentage": 99.88, "elapsed_time": "18:22:47", "remaining_time": "0:01:21", "throughput": 1996.59, "total_tokens": 132108368} +{"current_steps": 61230, "total_steps": 61300, "loss": 0.1241, "lr": 2.043242419452751e-10, "epoch": 9.98858075040783, "percentage": 99.89, "elapsed_time": "18:23:01", "remaining_time": "0:01:15", "throughput": 1996.33, "total_tokens": 132120432} +{"current_steps": 61235, "total_steps": 61300, "loss": 0.024, "lr": 1.7655952443129675e-10, "epoch": 9.989396411092985, "percentage": 99.89, "elapsed_time": "18:23:15", "remaining_time": "0:01:10", "throughput": 1996.1, "total_tokens": 132131568} +{"current_steps": 61240, "total_steps": 61300, "loss": 0.083, "lr": 1.5082141945343963e-10, "epoch": 9.99021207177814, "percentage": 99.9, "elapsed_time": "18:23:28", "remaining_time": "0:01:04", "throughput": 1995.86, "total_tokens": 132142992} +{"current_steps": 61245, "total_steps": 61300, "loss": 0.0029, "lr": 1.2710992909892306e-10, "epoch": 9.991027732463294, "percentage": 99.91, "elapsed_time": "18:23:41", "remaining_time": "0:00:59", "throughput": 1995.64, "total_tokens": 132153520} +{"current_steps": 61250, "total_steps": 61300, "loss": 0.0069, "lr": 1.0542505528565727e-10, "epoch": 9.99184339314845, "percentage": 99.92, "elapsed_time": "18:23:54", "remaining_time": "0:00:54", "throughput": 1995.4, "total_tokens": 132164368} +{"current_steps": 61255, "total_steps": 61300, "loss": 0.0032, "lr": 8.57667997788969e-11, "epoch": 9.992659053833606, "percentage": 99.93, "elapsed_time": "18:24:07", "remaining_time": "0:00:48", "throughput": 1995.18, "total_tokens": 132174992} +{"current_steps": 61260, "total_steps": 61300, "loss": 0.0041, "lr": 6.813516416626087e-11, "epoch": 9.99347471451876, "percentage": 99.93, "elapsed_time": "18:24:20", "remaining_time": "0:00:43", "throughput": 1994.94, "total_tokens": 132186320} +{"current_steps": 61265, "total_steps": 61300, "loss": 0.0359, "lr": 5.2530149877161315e-11, "epoch": 9.994290375203915, "percentage": 99.94, "elapsed_time": "18:24:35", "remaining_time": "0:00:37", "throughput": 1994.69, "total_tokens": 132198000} +{"current_steps": 61270, "total_steps": 61300, "loss": 0.0831, "lr": 3.895175818002805e-11, "epoch": 9.99510603588907, "percentage": 99.95, "elapsed_time": "18:24:49", "remaining_time": "0:00:32", "throughput": 1994.44, "total_tokens": 132209840} +{"current_steps": 61275, "total_steps": 61300, "loss": 0.0034, "lr": 2.7399990173981872e-11, "epoch": 9.995921696574225, "percentage": 99.96, "elapsed_time": "18:25:02", "remaining_time": "0:00:27", "throughput": 1994.21, "total_tokens": 132220848} +{"current_steps": 61280, "total_steps": 61300, "loss": 0.2133, "lr": 1.7874846797161228e-11, "epoch": 9.99673735725938, "percentage": 99.97, "elapsed_time": "18:25:14", "remaining_time": "0:00:21", "throughput": 1993.99, "total_tokens": 132230384} +{"current_steps": 61285, "total_steps": 61300, "loss": 0.1674, "lr": 1.0376328818395564e-11, "epoch": 9.997553017944535, "percentage": 99.98, "elapsed_time": "18:25:27", "remaining_time": "0:00:16", "throughput": 1993.77, "total_tokens": 132241200} +{"current_steps": 61290, "total_steps": 61300, "loss": 0.2153, "lr": 4.90443684553199e-12, "epoch": 9.99836867862969, "percentage": 99.98, "elapsed_time": "18:25:40", "remaining_time": "0:00:10", "throughput": 1993.54, "total_tokens": 132251664} +{"current_steps": 61295, "total_steps": 61300, "loss": 0.0041, "lr": 1.4591713254352712e-12, "epoch": 9.999184339314844, "percentage": 99.99, "elapsed_time": "18:25:53", "remaining_time": "0:00:05", "throughput": 1993.31, "total_tokens": 132262576} +{"current_steps": 61300, "total_steps": 61300, "loss": 0.0941, "lr": 4.053253843672167e-14, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "18:26:05", "remaining_time": "0:00:00", "throughput": 1993.09, "total_tokens": 132272272} +{"current_steps": 61300, "total_steps": 61300, "eval_loss": 0.1923980414867401, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "18:35:33", "remaining_time": "0:00:00", "throughput": 1976.16, "total_tokens": 132272272} +{"current_steps": 61300, "total_steps": 61300, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "18:35:35", "remaining_time": "0:00:00", "throughput": 1976.13, "total_tokens": 132272272}