diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" --- "a/trainer_log.jsonl" +++ "b/trainer_log.jsonl" @@ -1,876 +1,32 @@ -{"current_steps": 1, "total_steps": 875, "loss": 12.0862, "learning_rate": 5.000000000000001e-07, "epoch": 0.005702066999287242, "percentage": 0.11, "elapsed_time": "0:00:13", "remaining_time": "3:21:17", "throughput": "460.83", "total_tokens": 6368} -{"current_steps": 2, "total_steps": 875, "loss": 12.1914, "learning_rate": 1.0000000000000002e-06, "epoch": 0.011404133998574484, "percentage": 0.23, "elapsed_time": "0:00:26", "remaining_time": "3:16:23", "throughput": "458.74", "total_tokens": 12384} -{"current_steps": 3, "total_steps": 875, "loss": 11.9748, "learning_rate": 1.5e-06, "epoch": 0.017106200997861726, "percentage": 0.34, "elapsed_time": "0:00:40", "remaining_time": "3:14:34", "throughput": "463.69", "total_tokens": 18624} -{"current_steps": 4, "total_steps": 875, "loss": 11.5009, "learning_rate": 2.0000000000000003e-06, "epoch": 0.022808267997148968, "percentage": 0.46, "elapsed_time": "0:00:53", "remaining_time": "3:13:33", "throughput": "477.90", "total_tokens": 25488} -{"current_steps": 5, "total_steps": 875, "loss": 8.7827, "learning_rate": 2.5e-06, "epoch": 0.02851033499643621, "percentage": 0.57, "elapsed_time": "0:01:06", "remaining_time": "3:12:46", "throughput": "486.91", "total_tokens": 32368} -{"current_steps": 6, "total_steps": 875, "loss": 6.5054, "learning_rate": 3e-06, "epoch": 0.03421240199572345, "percentage": 0.69, "elapsed_time": "0:01:19", "remaining_time": "3:12:13", "throughput": "489.84", "total_tokens": 39008} -{"current_steps": 7, "total_steps": 875, "loss": 5.2127, "learning_rate": 3.5e-06, "epoch": 0.03991446899501069, "percentage": 0.8, "elapsed_time": "0:01:32", "remaining_time": "3:11:46", "throughput": "495.55", "total_tokens": 45984} -{"current_steps": 8, "total_steps": 875, "loss": 2.749, "learning_rate": 4.000000000000001e-06, "epoch": 0.045616535994297935, "percentage": 0.91, "elapsed_time": "0:01:45", "remaining_time": "3:11:24", "throughput": "496.90", "total_tokens": 52656} -{"current_steps": 9, "total_steps": 875, "loss": 1.0344, "learning_rate": 4.5e-06, "epoch": 0.05131860299358518, "percentage": 1.03, "elapsed_time": "0:01:59", "remaining_time": "3:11:03", "throughput": "498.68", "total_tokens": 59408} -{"current_steps": 10, "total_steps": 875, "loss": 0.6484, "learning_rate": 5e-06, "epoch": 0.05702066999287242, "percentage": 1.14, "elapsed_time": "0:02:12", "remaining_time": "3:10:43", "throughput": "499.62", "total_tokens": 66096} -{"current_steps": 11, "total_steps": 875, "loss": 1.8744, "learning_rate": 4.999983511654997e-06, "epoch": 0.06272273699215966, "percentage": 1.26, "elapsed_time": "0:02:25", "remaining_time": "3:10:26", "throughput": "499.01", "total_tokens": 72592} -{"current_steps": 12, "total_steps": 875, "loss": 0.4507, "learning_rate": 4.999934046837479e-06, "epoch": 0.0684248039914469, "percentage": 1.37, "elapsed_time": "0:02:38", "remaining_time": "3:10:08", "throughput": "500.88", "total_tokens": 79456} -{"current_steps": 13, "total_steps": 875, "loss": 1.6065, "learning_rate": 4.99985160619992e-06, "epoch": 0.07412687099073414, "percentage": 1.49, "elapsed_time": "0:02:51", "remaining_time": "3:09:51", "throughput": "500.68", "total_tokens": 86016} -{"current_steps": 14, "total_steps": 875, "loss": 1.647, "learning_rate": 4.99973619082977e-06, "epoch": 0.07982893799002139, "percentage": 1.6, "elapsed_time": "0:03:04", "remaining_time": "3:09:34", "throughput": "499.23", "total_tokens": 92336} -{"current_steps": 15, "total_steps": 875, "loss": 0.4799, "learning_rate": 4.999587802249433e-06, "epoch": 0.08553100498930863, "percentage": 1.71, "elapsed_time": "0:03:18", "remaining_time": "3:09:19", "throughput": "500.26", "total_tokens": 99120} -{"current_steps": 16, "total_steps": 875, "loss": 0.5683, "learning_rate": 4.999406442416258e-06, "epoch": 0.09123307198859587, "percentage": 1.83, "elapsed_time": "0:03:31", "remaining_time": "3:09:05", "throughput": "500.24", "total_tokens": 105712} -{"current_steps": 17, "total_steps": 875, "loss": 1.1372, "learning_rate": 4.9991921137225e-06, "epoch": 0.09693513898788311, "percentage": 1.94, "elapsed_time": "0:03:44", "remaining_time": "3:08:49", "throughput": "501.06", "total_tokens": 112480} -{"current_steps": 18, "total_steps": 875, "loss": 0.3574, "learning_rate": 4.998944818995301e-06, "epoch": 0.10263720598717035, "percentage": 2.06, "elapsed_time": "0:03:57", "remaining_time": "3:08:34", "throughput": "501.32", "total_tokens": 119136} -{"current_steps": 19, "total_steps": 875, "loss": 0.3492, "learning_rate": 4.9986645614966465e-06, "epoch": 0.1083392729864576, "percentage": 2.17, "elapsed_time": "0:04:10", "remaining_time": "3:08:20", "throughput": "500.88", "total_tokens": 125632} -{"current_steps": 20, "total_steps": 875, "loss": 1.0766, "learning_rate": 4.998351344923323e-06, "epoch": 0.11404133998574484, "percentage": 2.29, "elapsed_time": "0:04:24", "remaining_time": "3:08:06", "throughput": "500.77", "total_tokens": 132208} -{"current_steps": 21, "total_steps": 875, "loss": 0.3635, "learning_rate": 4.998005173406865e-06, "epoch": 0.11974340698503208, "percentage": 2.4, "elapsed_time": "0:04:37", "remaining_time": "3:07:52", "throughput": "500.11", "total_tokens": 138624} -{"current_steps": 22, "total_steps": 875, "loss": 1.5452, "learning_rate": 4.997626051513512e-06, "epoch": 0.12544547398431932, "percentage": 2.51, "elapsed_time": "0:04:50", "remaining_time": "3:07:37", "throughput": "499.58", "total_tokens": 145056} -{"current_steps": 23, "total_steps": 875, "loss": 0.9203, "learning_rate": 4.997213984244138e-06, "epoch": 0.13114754098360656, "percentage": 2.63, "elapsed_time": "0:05:03", "remaining_time": "3:07:24", "throughput": "499.73", "total_tokens": 151696} -{"current_steps": 24, "total_steps": 875, "loss": 0.3603, "learning_rate": 4.9967689770341885e-06, "epoch": 0.1368496079828938, "percentage": 2.74, "elapsed_time": "0:05:16", "remaining_time": "3:07:10", "throughput": "499.10", "total_tokens": 158080} -{"current_steps": 25, "total_steps": 875, "loss": 0.7598, "learning_rate": 4.996291035753608e-06, "epoch": 0.14255167498218105, "percentage": 2.86, "elapsed_time": "0:05:29", "remaining_time": "3:06:56", "throughput": "498.84", "total_tokens": 164560} -{"current_steps": 26, "total_steps": 875, "loss": 0.5039, "learning_rate": 4.995780166706768e-06, "epoch": 0.1482537419814683, "percentage": 2.97, "elapsed_time": "0:05:43", "remaining_time": "3:06:42", "throughput": "499.32", "total_tokens": 171296} -{"current_steps": 27, "total_steps": 875, "loss": 0.4744, "learning_rate": 4.995236376632373e-06, "epoch": 0.15395580898075553, "percentage": 3.09, "elapsed_time": "0:05:56", "remaining_time": "3:06:28", "throughput": "498.81", "total_tokens": 177696} -{"current_steps": 28, "total_steps": 875, "loss": 0.3387, "learning_rate": 4.994659672703384e-06, "epoch": 0.15965787598004277, "percentage": 3.2, "elapsed_time": "0:06:09", "remaining_time": "3:06:14", "throughput": "499.12", "total_tokens": 184384} -{"current_steps": 29, "total_steps": 875, "loss": 0.3363, "learning_rate": 4.994050062526915e-06, "epoch": 0.16535994297933002, "percentage": 3.31, "elapsed_time": "0:06:22", "remaining_time": "3:06:00", "throughput": "498.57", "total_tokens": 190736} -{"current_steps": 30, "total_steps": 875, "loss": 0.2842, "learning_rate": 4.993407554144137e-06, "epoch": 0.17106200997861726, "percentage": 3.43, "elapsed_time": "0:06:35", "remaining_time": "3:05:46", "throughput": "498.62", "total_tokens": 197328} -{"current_steps": 31, "total_steps": 875, "loss": 0.2779, "learning_rate": 4.992732156030169e-06, "epoch": 0.1767640769779045, "percentage": 3.54, "elapsed_time": "0:06:48", "remaining_time": "3:05:33", "throughput": "499.09", "total_tokens": 204096} -{"current_steps": 32, "total_steps": 875, "loss": 0.242, "learning_rate": 4.992023877093969e-06, "epoch": 0.18246614397719174, "percentage": 3.66, "elapsed_time": "0:07:02", "remaining_time": "3:05:19", "throughput": "498.53", "total_tokens": 210432} -{"current_steps": 33, "total_steps": 875, "loss": 0.2279, "learning_rate": 4.991282726678215e-06, "epoch": 0.18816821097647898, "percentage": 3.77, "elapsed_time": "0:07:15", "remaining_time": "3:05:05", "throughput": "498.72", "total_tokens": 217072} -{"current_steps": 34, "total_steps": 875, "loss": 0.1862, "learning_rate": 4.990508714559182e-06, "epoch": 0.19387027797576623, "percentage": 3.89, "elapsed_time": "0:07:28", "remaining_time": "3:04:52", "throughput": "498.79", "total_tokens": 223680} -{"current_steps": 35, "total_steps": 875, "loss": 0.2974, "learning_rate": 4.989701850946613e-06, "epoch": 0.19957234497505347, "percentage": 4.0, "elapsed_time": "0:07:41", "remaining_time": "3:04:39", "throughput": "498.82", "total_tokens": 230272} -{"current_steps": 36, "total_steps": 875, "loss": 0.182, "learning_rate": 4.988862146483585e-06, "epoch": 0.2052744119743407, "percentage": 4.11, "elapsed_time": "0:07:54", "remaining_time": "3:04:26", "throughput": "498.95", "total_tokens": 236912} -{"current_steps": 37, "total_steps": 875, "loss": 0.1516, "learning_rate": 4.9879896122463675e-06, "epoch": 0.21097647897362795, "percentage": 4.23, "elapsed_time": "0:08:07", "remaining_time": "3:04:12", "throughput": "498.82", "total_tokens": 243424} -{"current_steps": 38, "total_steps": 875, "loss": 0.2325, "learning_rate": 4.987084259744276e-06, "epoch": 0.2166785459729152, "percentage": 4.34, "elapsed_time": "0:08:21", "remaining_time": "3:03:59", "throughput": "499.38", "total_tokens": 250288} -{"current_steps": 39, "total_steps": 875, "loss": 0.1389, "learning_rate": 4.986146100919522e-06, "epoch": 0.22238061297220243, "percentage": 4.46, "elapsed_time": "0:08:34", "remaining_time": "3:03:45", "throughput": "498.94", "total_tokens": 256640} -{"current_steps": 40, "total_steps": 875, "loss": 0.2076, "learning_rate": 4.985175148147057e-06, "epoch": 0.22808267997148968, "percentage": 4.57, "elapsed_time": "0:08:47", "remaining_time": "3:03:32", "throughput": "499.21", "total_tokens": 263360} -{"current_steps": 41, "total_steps": 875, "loss": 0.1476, "learning_rate": 4.9841714142344015e-06, "epoch": 0.23378474697077692, "percentage": 4.69, "elapsed_time": "0:09:00", "remaining_time": "3:03:19", "throughput": "499.87", "total_tokens": 270304} -{"current_steps": 42, "total_steps": 875, "loss": 0.159, "learning_rate": 4.9831349124214855e-06, "epoch": 0.23948681397006416, "percentage": 4.8, "elapsed_time": "0:09:13", "remaining_time": "3:03:06", "throughput": "499.62", "total_tokens": 276752} -{"current_steps": 43, "total_steps": 875, "loss": 0.1761, "learning_rate": 4.982065656380468e-06, "epoch": 0.2451888809693514, "percentage": 4.91, "elapsed_time": "0:09:27", "remaining_time": "3:02:53", "throughput": "499.54", "total_tokens": 283296} -{"current_steps": 44, "total_steps": 875, "loss": 0.1581, "learning_rate": 4.980963660215561e-06, "epoch": 0.25089094796863864, "percentage": 5.03, "elapsed_time": "0:09:40", "remaining_time": "3:02:39", "throughput": "499.57", "total_tokens": 289888} -{"current_steps": 45, "total_steps": 875, "loss": 0.1454, "learning_rate": 4.979828938462836e-06, "epoch": 0.25659301496792586, "percentage": 5.14, "elapsed_time": "0:09:53", "remaining_time": "3:02:25", "throughput": "499.67", "total_tokens": 296528} -{"current_steps": 46, "total_steps": 875, "loss": 0.1823, "learning_rate": 4.9786615060900415e-06, "epoch": 0.26229508196721313, "percentage": 5.26, "elapsed_time": "0:10:06", "remaining_time": "3:02:12", "throughput": "499.84", "total_tokens": 303216} -{"current_steps": 47, "total_steps": 875, "loss": 0.2675, "learning_rate": 4.9774613784964e-06, "epoch": 0.26799714896650034, "percentage": 5.37, "elapsed_time": "0:10:19", "remaining_time": "3:01:58", "throughput": "500.12", "total_tokens": 309968} -{"current_steps": 48, "total_steps": 875, "loss": 0.1482, "learning_rate": 4.976228571512405e-06, "epoch": 0.2736992159657876, "percentage": 5.49, "elapsed_time": "0:10:32", "remaining_time": "3:01:45", "throughput": "500.03", "total_tokens": 316512} -{"current_steps": 49, "total_steps": 875, "loss": 0.1258, "learning_rate": 4.9749631013996146e-06, "epoch": 0.2794012829650748, "percentage": 5.6, "elapsed_time": "0:10:46", "remaining_time": "3:01:32", "throughput": "499.91", "total_tokens": 323008} -{"current_steps": 50, "total_steps": 875, "loss": 0.1921, "learning_rate": 4.973664984850435e-06, "epoch": 0.2851033499643621, "percentage": 5.71, "elapsed_time": "0:10:59", "remaining_time": "3:01:18", "throughput": "500.36", "total_tokens": 329888} -{"current_steps": 51, "total_steps": 875, "loss": 0.1491, "learning_rate": 4.9723342389879e-06, "epoch": 0.2908054169636493, "percentage": 5.83, "elapsed_time": "0:11:12", "remaining_time": "3:01:04", "throughput": "500.38", "total_tokens": 336480} -{"current_steps": 52, "total_steps": 875, "loss": 0.1186, "learning_rate": 4.970970881365449e-06, "epoch": 0.2965074839629366, "percentage": 5.94, "elapsed_time": "0:11:25", "remaining_time": "3:00:51", "throughput": "500.27", "total_tokens": 342992} -{"current_steps": 53, "total_steps": 875, "loss": 0.2011, "learning_rate": 4.96957492996669e-06, "epoch": 0.3022095509622238, "percentage": 6.06, "elapsed_time": "0:11:38", "remaining_time": "3:00:37", "throughput": "500.55", "total_tokens": 349776} -{"current_steps": 54, "total_steps": 875, "loss": 0.1301, "learning_rate": 4.968146403205164e-06, "epoch": 0.30791161796151106, "percentage": 6.17, "elapsed_time": "0:11:51", "remaining_time": "3:00:23", "throughput": "500.66", "total_tokens": 356432} -{"current_steps": 55, "total_steps": 875, "loss": 0.1563, "learning_rate": 4.966685319924105e-06, "epoch": 0.3136136849607983, "percentage": 6.29, "elapsed_time": "0:12:05", "remaining_time": "3:00:10", "throughput": "500.06", "total_tokens": 362592} -{"current_steps": 56, "total_steps": 875, "loss": 0.1667, "learning_rate": 4.965191699396192e-06, "epoch": 0.31931575196008555, "percentage": 6.4, "elapsed_time": "0:12:18", "remaining_time": "2:59:57", "throughput": "499.87", "total_tokens": 369040} -{"current_steps": 57, "total_steps": 875, "loss": 0.134, "learning_rate": 4.9636655613232866e-06, "epoch": 0.32501781895937276, "percentage": 6.51, "elapsed_time": "0:12:31", "remaining_time": "2:59:43", "throughput": "499.79", "total_tokens": 375552} -{"current_steps": 58, "total_steps": 875, "loss": 0.1753, "learning_rate": 4.962106925836182e-06, "epoch": 0.33071988595866003, "percentage": 6.63, "elapsed_time": "0:12:44", "remaining_time": "2:59:30", "throughput": "500.01", "total_tokens": 382304} -{"current_steps": 59, "total_steps": 875, "loss": 0.1381, "learning_rate": 4.960515813494335e-06, "epoch": 0.33642195295794725, "percentage": 6.74, "elapsed_time": "0:12:57", "remaining_time": "2:59:16", "throughput": "500.11", "total_tokens": 388960} -{"current_steps": 60, "total_steps": 875, "loss": 0.0927, "learning_rate": 4.958892245285594e-06, "epoch": 0.3421240199572345, "percentage": 6.86, "elapsed_time": "0:13:10", "remaining_time": "2:59:03", "throughput": "500.54", "total_tokens": 395888} -{"current_steps": 61, "total_steps": 875, "loss": 0.1608, "learning_rate": 4.957236242625918e-06, "epoch": 0.34782608695652173, "percentage": 6.97, "elapsed_time": "0:13:24", "remaining_time": "2:58:50", "throughput": "500.48", "total_tokens": 402432} -{"current_steps": 62, "total_steps": 875, "loss": 0.1219, "learning_rate": 4.955547827359103e-06, "epoch": 0.353528153955809, "percentage": 7.09, "elapsed_time": "0:13:37", "remaining_time": "2:58:36", "throughput": "500.25", "total_tokens": 408832} -{"current_steps": 63, "total_steps": 875, "loss": 0.1674, "learning_rate": 4.953827021756489e-06, "epoch": 0.3592302209550962, "percentage": 7.2, "elapsed_time": "0:13:50", "remaining_time": "2:58:23", "throughput": "500.03", "total_tokens": 415232} -{"current_steps": 64, "total_steps": 875, "loss": 0.1413, "learning_rate": 4.952073848516663e-06, "epoch": 0.3649322879543835, "percentage": 7.31, "elapsed_time": "0:14:03", "remaining_time": "2:58:09", "throughput": "499.70", "total_tokens": 421536} -{"current_steps": 65, "total_steps": 875, "loss": 0.1515, "learning_rate": 4.950288330765167e-06, "epoch": 0.3706343549536707, "percentage": 7.43, "elapsed_time": "0:14:16", "remaining_time": "2:57:56", "throughput": "499.78", "total_tokens": 428176} -{"current_steps": 66, "total_steps": 875, "loss": 0.1904, "learning_rate": 4.948470492054186e-06, "epoch": 0.37633642195295797, "percentage": 7.54, "elapsed_time": "0:14:29", "remaining_time": "2:57:42", "throughput": "499.60", "total_tokens": 434592} -{"current_steps": 67, "total_steps": 875, "loss": 0.1283, "learning_rate": 4.946620356362243e-06, "epoch": 0.3820384889522452, "percentage": 7.66, "elapsed_time": "0:14:43", "remaining_time": "2:57:29", "throughput": "499.32", "total_tokens": 440912} -{"current_steps": 68, "total_steps": 875, "loss": 0.1686, "learning_rate": 4.944737948093876e-06, "epoch": 0.38774055595153245, "percentage": 7.77, "elapsed_time": "0:14:56", "remaining_time": "2:57:15", "throughput": "499.03", "total_tokens": 447232} -{"current_steps": 69, "total_steps": 875, "loss": 0.1451, "learning_rate": 4.942823292079325e-06, "epoch": 0.39344262295081966, "percentage": 7.89, "elapsed_time": "0:15:09", "remaining_time": "2:57:02", "throughput": "499.17", "total_tokens": 453920} -{"current_steps": 70, "total_steps": 875, "loss": 0.1635, "learning_rate": 4.9408764135741955e-06, "epoch": 0.39914468995010693, "percentage": 8.0, "elapsed_time": "0:15:22", "remaining_time": "2:56:49", "throughput": "498.98", "total_tokens": 460320} -{"current_steps": 71, "total_steps": 875, "loss": 0.1182, "learning_rate": 4.9388973382591325e-06, "epoch": 0.40484675694939415, "percentage": 8.11, "elapsed_time": "0:15:35", "remaining_time": "2:56:35", "throughput": "498.89", "total_tokens": 466816} -{"current_steps": 72, "total_steps": 875, "loss": 0.1328, "learning_rate": 4.936886092239475e-06, "epoch": 0.4105488239486814, "percentage": 8.23, "elapsed_time": "0:15:48", "remaining_time": "2:56:22", "throughput": "499.01", "total_tokens": 473488} -{"current_steps": 73, "total_steps": 875, "loss": 0.1312, "learning_rate": 4.9348427020449206e-06, "epoch": 0.41625089094796863, "percentage": 8.34, "elapsed_time": "0:16:02", "remaining_time": "2:56:08", "throughput": "499.57", "total_tokens": 480592} -{"current_steps": 74, "total_steps": 875, "loss": 0.1439, "learning_rate": 4.932767194629164e-06, "epoch": 0.4219529579472559, "percentage": 8.46, "elapsed_time": "0:16:15", "remaining_time": "2:55:55", "throughput": "500.00", "total_tokens": 487584} -{"current_steps": 75, "total_steps": 875, "loss": 0.1534, "learning_rate": 4.9306595973695545e-06, "epoch": 0.4276550249465431, "percentage": 8.57, "elapsed_time": "0:16:28", "remaining_time": "2:55:42", "throughput": "500.24", "total_tokens": 494400} -{"current_steps": 76, "total_steps": 875, "loss": 0.1159, "learning_rate": 4.928519938066723e-06, "epoch": 0.4333570919458304, "percentage": 8.69, "elapsed_time": "0:16:41", "remaining_time": "2:55:28", "throughput": "499.87", "total_tokens": 500624} -{"current_steps": 77, "total_steps": 875, "loss": 0.1291, "learning_rate": 4.926348244944221e-06, "epoch": 0.4390591589451176, "percentage": 8.8, "elapsed_time": "0:16:54", "remaining_time": "2:55:15", "throughput": "499.84", "total_tokens": 507168} -{"current_steps": 78, "total_steps": 875, "loss": 0.145, "learning_rate": 4.924144546648151e-06, "epoch": 0.44476122594440487, "percentage": 8.91, "elapsed_time": "0:17:07", "remaining_time": "2:55:02", "throughput": "500.06", "total_tokens": 513968} -{"current_steps": 79, "total_steps": 875, "loss": 0.1155, "learning_rate": 4.9219088722467825e-06, "epoch": 0.4504632929436921, "percentage": 9.03, "elapsed_time": "0:17:20", "remaining_time": "2:54:48", "throughput": "499.95", "total_tokens": 520432} -{"current_steps": 80, "total_steps": 875, "loss": 0.1153, "learning_rate": 4.91964125123017e-06, "epoch": 0.45616535994297935, "percentage": 9.14, "elapsed_time": "0:17:34", "remaining_time": "2:54:35", "throughput": "500.30", "total_tokens": 527392} -{"current_steps": 81, "total_steps": 875, "loss": 0.1673, "learning_rate": 4.917341713509772e-06, "epoch": 0.46186742694226657, "percentage": 9.26, "elapsed_time": "0:17:47", "remaining_time": "2:54:22", "throughput": "500.05", "total_tokens": 533712} -{"current_steps": 82, "total_steps": 875, "loss": 0.2122, "learning_rate": 4.915010289418042e-06, "epoch": 0.46756949394155384, "percentage": 9.37, "elapsed_time": "0:18:00", "remaining_time": "2:54:09", "throughput": "500.28", "total_tokens": 540544} -{"current_steps": 83, "total_steps": 875, "loss": 0.1092, "learning_rate": 4.912647009708041e-06, "epoch": 0.47327156094084105, "percentage": 9.49, "elapsed_time": "0:18:13", "remaining_time": "2:53:55", "throughput": "500.01", "total_tokens": 546832} -{"current_steps": 84, "total_steps": 875, "loss": 0.148, "learning_rate": 4.910251905553025e-06, "epoch": 0.4789736279401283, "percentage": 9.6, "elapsed_time": "0:18:26", "remaining_time": "2:53:42", "throughput": "500.34", "total_tokens": 553776} -{"current_steps": 85, "total_steps": 875, "loss": 0.1237, "learning_rate": 4.907825008546039e-06, "epoch": 0.48467569493941554, "percentage": 9.71, "elapsed_time": "0:18:39", "remaining_time": "2:53:28", "throughput": "500.21", "total_tokens": 560208} -{"current_steps": 86, "total_steps": 875, "loss": 0.106, "learning_rate": 4.905366350699493e-06, "epoch": 0.4903777619387028, "percentage": 9.83, "elapsed_time": "0:18:53", "remaining_time": "2:53:15", "throughput": "500.12", "total_tokens": 566688} -{"current_steps": 87, "total_steps": 875, "loss": 0.1131, "learning_rate": 4.902875964444746e-06, "epoch": 0.49607982893799, "percentage": 9.94, "elapsed_time": "0:19:06", "remaining_time": "2:53:02", "throughput": "500.04", "total_tokens": 573184} -{"current_steps": 88, "total_steps": 875, "loss": 0.1343, "learning_rate": 4.900353882631679e-06, "epoch": 0.5017818959372773, "percentage": 10.06, "elapsed_time": "0:19:19", "remaining_time": "2:52:49", "throughput": "500.17", "total_tokens": 579920} -{"current_steps": 89, "total_steps": 875, "loss": 0.0873, "learning_rate": 4.897800138528254e-06, "epoch": 0.5074839629365645, "percentage": 10.17, "elapsed_time": "0:19:32", "remaining_time": "2:52:35", "throughput": "500.47", "total_tokens": 586864} -{"current_steps": 90, "total_steps": 875, "loss": 0.1412, "learning_rate": 4.8952147658200815e-06, "epoch": 0.5131860299358517, "percentage": 10.29, "elapsed_time": "0:19:45", "remaining_time": "2:52:22", "throughput": "500.42", "total_tokens": 593392} -{"current_steps": 91, "total_steps": 875, "loss": 0.0983, "learning_rate": 4.892597798609976e-06, "epoch": 0.518888096935139, "percentage": 10.4, "elapsed_time": "0:19:58", "remaining_time": "2:52:09", "throughput": "500.30", "total_tokens": 599824} -{"current_steps": 92, "total_steps": 875, "loss": 0.1322, "learning_rate": 4.889949271417504e-06, "epoch": 0.5245901639344263, "percentage": 10.51, "elapsed_time": "0:20:12", "remaining_time": "2:51:56", "throughput": "500.27", "total_tokens": 606384} -{"current_steps": 93, "total_steps": 875, "loss": 0.1345, "learning_rate": 4.88726921917853e-06, "epoch": 0.5302922309337135, "percentage": 10.63, "elapsed_time": "0:20:25", "remaining_time": "2:51:42", "throughput": "500.63", "total_tokens": 613408} -{"current_steps": 94, "total_steps": 875, "loss": 0.1367, "learning_rate": 4.884557677244755e-06, "epoch": 0.5359942979330007, "percentage": 10.74, "elapsed_time": "0:20:38", "remaining_time": "2:51:29", "throughput": "500.72", "total_tokens": 620096} -{"current_steps": 95, "total_steps": 875, "loss": 0.1228, "learning_rate": 4.8818146813832475e-06, "epoch": 0.5416963649322879, "percentage": 10.86, "elapsed_time": "0:20:51", "remaining_time": "2:51:16", "throughput": "500.49", "total_tokens": 626400} -{"current_steps": 96, "total_steps": 875, "loss": 0.2031, "learning_rate": 4.879040267775981e-06, "epoch": 0.5473984319315752, "percentage": 10.97, "elapsed_time": "0:21:04", "remaining_time": "2:51:03", "throughput": "500.56", "total_tokens": 633088} -{"current_steps": 97, "total_steps": 875, "loss": 0.1235, "learning_rate": 4.8762344730193445e-06, "epoch": 0.5531004989308624, "percentage": 11.09, "elapsed_time": "0:21:17", "remaining_time": "2:50:49", "throughput": "500.49", "total_tokens": 639584} -{"current_steps": 98, "total_steps": 875, "loss": 0.1136, "learning_rate": 4.873397334123667e-06, "epoch": 0.5588025659301497, "percentage": 11.2, "elapsed_time": "0:21:31", "remaining_time": "2:50:36", "throughput": "500.48", "total_tokens": 646160} -{"current_steps": 99, "total_steps": 875, "loss": 0.1065, "learning_rate": 4.87052888851273e-06, "epoch": 0.5645046329294369, "percentage": 11.31, "elapsed_time": "0:21:44", "remaining_time": "2:50:23", "throughput": "500.67", "total_tokens": 652992} -{"current_steps": 100, "total_steps": 875, "loss": 0.1489, "learning_rate": 4.867629174023269e-06, "epoch": 0.5702066999287242, "percentage": 11.43, "elapsed_time": "0:21:57", "remaining_time": "2:50:09", "throughput": "500.95", "total_tokens": 659952} -{"current_steps": 101, "total_steps": 875, "loss": 0.1057, "learning_rate": 4.864698228904479e-06, "epoch": 0.5759087669280114, "percentage": 11.54, "elapsed_time": "0:22:10", "remaining_time": "2:49:56", "throughput": "500.84", "total_tokens": 666400} -{"current_steps": 102, "total_steps": 875, "loss": 0.1382, "learning_rate": 4.861736091817506e-06, "epoch": 0.5816108339272986, "percentage": 11.66, "elapsed_time": "0:22:23", "remaining_time": "2:49:43", "throughput": "500.86", "total_tokens": 673008} -{"current_steps": 103, "total_steps": 875, "loss": 0.119, "learning_rate": 4.858742801834943e-06, "epoch": 0.5873129009265858, "percentage": 11.77, "elapsed_time": "0:22:36", "remaining_time": "2:49:30", "throughput": "500.91", "total_tokens": 679680} -{"current_steps": 104, "total_steps": 875, "loss": 0.1058, "learning_rate": 4.855718398440306e-06, "epoch": 0.5930149679258732, "percentage": 11.89, "elapsed_time": "0:22:50", "remaining_time": "2:49:16", "throughput": "500.69", "total_tokens": 685968} -{"current_steps": 105, "total_steps": 875, "loss": 0.0622, "learning_rate": 4.852662921527523e-06, "epoch": 0.5987170349251604, "percentage": 12.0, "elapsed_time": "0:23:03", "remaining_time": "2:49:03", "throughput": "500.65", "total_tokens": 692496} -{"current_steps": 106, "total_steps": 875, "loss": 0.08, "learning_rate": 4.849576411400397e-06, "epoch": 0.6044191019244476, "percentage": 12.11, "elapsed_time": "0:23:16", "remaining_time": "2:48:50", "throughput": "500.62", "total_tokens": 699040} -{"current_steps": 107, "total_steps": 875, "loss": 0.1147, "learning_rate": 4.846458908772085e-06, "epoch": 0.6101211689237348, "percentage": 12.23, "elapsed_time": "0:23:29", "remaining_time": "2:48:36", "throughput": "500.74", "total_tokens": 705792} -{"current_steps": 108, "total_steps": 875, "loss": 0.1084, "learning_rate": 4.843310454764553e-06, "epoch": 0.6158232359230221, "percentage": 12.34, "elapsed_time": "0:23:42", "remaining_time": "2:48:23", "throughput": "501.11", "total_tokens": 712912} -{"current_steps": 109, "total_steps": 875, "loss": 0.1195, "learning_rate": 4.840131090908038e-06, "epoch": 0.6215253029223093, "percentage": 12.46, "elapsed_time": "0:23:55", "remaining_time": "2:48:10", "throughput": "501.10", "total_tokens": 719488} -{"current_steps": 110, "total_steps": 875, "loss": 0.0877, "learning_rate": 4.8369208591405e-06, "epoch": 0.6272273699215966, "percentage": 12.57, "elapsed_time": "0:24:08", "remaining_time": "2:47:56", "throughput": "500.96", "total_tokens": 725872} -{"current_steps": 111, "total_steps": 875, "loss": 0.1405, "learning_rate": 4.833679801807064e-06, "epoch": 0.6329294369208838, "percentage": 12.69, "elapsed_time": "0:24:22", "remaining_time": "2:47:43", "throughput": "500.87", "total_tokens": 732336} -{"current_steps": 112, "total_steps": 875, "loss": 0.1014, "learning_rate": 4.8304079616594684e-06, "epoch": 0.6386315039201711, "percentage": 12.8, "elapsed_time": "0:24:35", "remaining_time": "2:47:30", "throughput": "501.06", "total_tokens": 739200} -{"current_steps": 113, "total_steps": 875, "loss": 0.1094, "learning_rate": 4.827105381855496e-06, "epoch": 0.6443335709194583, "percentage": 12.91, "elapsed_time": "0:24:48", "remaining_time": "2:47:17", "throughput": "500.91", "total_tokens": 745568} -{"current_steps": 114, "total_steps": 875, "loss": 0.1301, "learning_rate": 4.823772105958408e-06, "epoch": 0.6500356379187455, "percentage": 13.03, "elapsed_time": "0:25:01", "remaining_time": "2:47:03", "throughput": "500.72", "total_tokens": 751872} -{"current_steps": 115, "total_steps": 875, "loss": 0.0939, "learning_rate": 4.820408177936365e-06, "epoch": 0.6557377049180327, "percentage": 13.14, "elapsed_time": "0:25:14", "remaining_time": "2:46:50", "throughput": "500.93", "total_tokens": 758784} -{"current_steps": 116, "total_steps": 875, "loss": 0.122, "learning_rate": 4.817013642161853e-06, "epoch": 0.6614397719173201, "percentage": 13.26, "elapsed_time": "0:25:27", "remaining_time": "2:46:37", "throughput": "501.05", "total_tokens": 765552} -{"current_steps": 117, "total_steps": 875, "loss": 0.1296, "learning_rate": 4.8135885434110935e-06, "epoch": 0.6671418389166073, "percentage": 13.37, "elapsed_time": "0:25:41", "remaining_time": "2:46:23", "throughput": "501.02", "total_tokens": 772096} -{"current_steps": 118, "total_steps": 875, "loss": 0.108, "learning_rate": 4.810132926863454e-06, "epoch": 0.6728439059158945, "percentage": 13.49, "elapsed_time": "0:25:54", "remaining_time": "2:46:10", "throughput": "500.90", "total_tokens": 778512} -{"current_steps": 119, "total_steps": 875, "loss": 0.0779, "learning_rate": 4.8066468381008525e-06, "epoch": 0.6785459729151817, "percentage": 13.6, "elapsed_time": "0:26:07", "remaining_time": "2:45:57", "throughput": "500.84", "total_tokens": 784992} -{"current_steps": 120, "total_steps": 875, "loss": 0.1358, "learning_rate": 4.803130323107157e-06, "epoch": 0.684248039914469, "percentage": 13.71, "elapsed_time": "0:26:20", "remaining_time": "2:45:44", "throughput": "500.72", "total_tokens": 791392} -{"current_steps": 121, "total_steps": 875, "loss": 0.1485, "learning_rate": 4.799583428267577e-06, "epoch": 0.6899501069137562, "percentage": 13.83, "elapsed_time": "0:26:33", "remaining_time": "2:45:30", "throughput": "500.93", "total_tokens": 798320} -{"current_steps": 122, "total_steps": 875, "loss": 0.09, "learning_rate": 4.796006200368054e-06, "epoch": 0.6956521739130435, "percentage": 13.94, "elapsed_time": "0:26:46", "remaining_time": "2:45:17", "throughput": "500.93", "total_tokens": 804896} -{"current_steps": 123, "total_steps": 875, "loss": 0.108, "learning_rate": 4.792398686594641e-06, "epoch": 0.7013542409123307, "percentage": 14.06, "elapsed_time": "0:26:59", "remaining_time": "2:45:04", "throughput": "500.94", "total_tokens": 811504} -{"current_steps": 124, "total_steps": 875, "loss": 0.1557, "learning_rate": 4.788760934532883e-06, "epoch": 0.707056307911618, "percentage": 14.17, "elapsed_time": "0:27:13", "remaining_time": "2:44:50", "throughput": "500.99", "total_tokens": 818176} -{"current_steps": 125, "total_steps": 875, "loss": 0.1206, "learning_rate": 4.785092992167192e-06, "epoch": 0.7127583749109052, "percentage": 14.29, "elapsed_time": "0:27:26", "remaining_time": "2:44:37", "throughput": "500.69", "total_tokens": 824272} -{"current_steps": 126, "total_steps": 875, "loss": 0.0977, "learning_rate": 4.7813949078802035e-06, "epoch": 0.7184604419101924, "percentage": 14.4, "elapsed_time": "0:27:39", "remaining_time": "2:44:24", "throughput": "500.57", "total_tokens": 830656} -{"current_steps": 127, "total_steps": 875, "loss": 0.1223, "learning_rate": 4.777666730452151e-06, "epoch": 0.7241625089094796, "percentage": 14.51, "elapsed_time": "0:27:52", "remaining_time": "2:44:11", "throughput": "500.83", "total_tokens": 837680} -{"current_steps": 128, "total_steps": 875, "loss": 0.1751, "learning_rate": 4.773908509060214e-06, "epoch": 0.729864575908767, "percentage": 14.63, "elapsed_time": "0:28:05", "remaining_time": "2:43:57", "throughput": "501.04", "total_tokens": 844624} -{"current_steps": 129, "total_steps": 875, "loss": 0.1016, "learning_rate": 4.770120293277876e-06, "epoch": 0.7355666429080542, "percentage": 14.74, "elapsed_time": "0:28:18", "remaining_time": "2:43:44", "throughput": "501.10", "total_tokens": 851312} -{"current_steps": 130, "total_steps": 875, "loss": 0.1351, "learning_rate": 4.766302133074261e-06, "epoch": 0.7412687099073414, "percentage": 14.86, "elapsed_time": "0:28:32", "remaining_time": "2:43:31", "throughput": "501.30", "total_tokens": 858256} -{"current_steps": 131, "total_steps": 875, "loss": 0.0891, "learning_rate": 4.762454078813483e-06, "epoch": 0.7469707769066286, "percentage": 14.97, "elapsed_time": "0:28:45", "remaining_time": "2:43:18", "throughput": "501.34", "total_tokens": 864912} -{"current_steps": 132, "total_steps": 875, "loss": 0.07, "learning_rate": 4.758576181253981e-06, "epoch": 0.7526728439059159, "percentage": 15.09, "elapsed_time": "0:28:58", "remaining_time": "2:43:04", "throughput": "501.37", "total_tokens": 871552} -{"current_steps": 133, "total_steps": 875, "loss": 0.1325, "learning_rate": 4.7546684915478445e-06, "epoch": 0.7583749109052031, "percentage": 15.2, "elapsed_time": "0:29:11", "remaining_time": "2:42:51", "throughput": "501.42", "total_tokens": 878256} -{"current_steps": 134, "total_steps": 875, "loss": 0.1074, "learning_rate": 4.750731061240143e-06, "epoch": 0.7640769779044904, "percentage": 15.31, "elapsed_time": "0:29:24", "remaining_time": "2:42:38", "throughput": "501.63", "total_tokens": 885216} -{"current_steps": 135, "total_steps": 875, "loss": 0.0949, "learning_rate": 4.746763942268243e-06, "epoch": 0.7697790449037776, "percentage": 15.43, "elapsed_time": "0:29:37", "remaining_time": "2:42:25", "throughput": "501.49", "total_tokens": 891552} -{"current_steps": 136, "total_steps": 875, "loss": 0.0813, "learning_rate": 4.742767186961126e-06, "epoch": 0.7754811119030649, "percentage": 15.54, "elapsed_time": "0:29:50", "remaining_time": "2:42:11", "throughput": "501.64", "total_tokens": 898432} -{"current_steps": 137, "total_steps": 875, "loss": 0.092, "learning_rate": 4.738740848038695e-06, "epoch": 0.7811831789023521, "percentage": 15.66, "elapsed_time": "0:30:04", "remaining_time": "2:41:58", "throughput": "501.72", "total_tokens": 905184} -{"current_steps": 138, "total_steps": 875, "loss": 0.0679, "learning_rate": 4.7346849786110835e-06, "epoch": 0.7868852459016393, "percentage": 15.77, "elapsed_time": "0:30:17", "remaining_time": "2:41:45", "throughput": "501.77", "total_tokens": 911856} -{"current_steps": 139, "total_steps": 875, "loss": 0.1234, "learning_rate": 4.730599632177952e-06, "epoch": 0.7925873129009265, "percentage": 15.89, "elapsed_time": "0:30:30", "remaining_time": "2:41:32", "throughput": "501.69", "total_tokens": 918320} -{"current_steps": 140, "total_steps": 875, "loss": 0.1281, "learning_rate": 4.726484862627779e-06, "epoch": 0.7982893799002139, "percentage": 16.0, "elapsed_time": "0:30:43", "remaining_time": "2:41:18", "throughput": "502.03", "total_tokens": 925536} -{"current_steps": 141, "total_steps": 875, "loss": 0.0834, "learning_rate": 4.7223407242371595e-06, "epoch": 0.8039914468995011, "percentage": 16.11, "elapsed_time": "0:30:56", "remaining_time": "2:41:05", "throughput": "501.99", "total_tokens": 932064} -{"current_steps": 142, "total_steps": 875, "loss": 0.0863, "learning_rate": 4.718167271670078e-06, "epoch": 0.8096935138987883, "percentage": 16.23, "elapsed_time": "0:31:09", "remaining_time": "2:40:52", "throughput": "502.00", "total_tokens": 938688} -{"current_steps": 143, "total_steps": 875, "loss": 0.0503, "learning_rate": 4.713964559977196e-06, "epoch": 0.8153955808980755, "percentage": 16.34, "elapsed_time": "0:31:23", "remaining_time": "2:40:39", "throughput": "502.08", "total_tokens": 945456} -{"current_steps": 144, "total_steps": 875, "loss": 0.1619, "learning_rate": 4.709732644595122e-06, "epoch": 0.8210976478973628, "percentage": 16.46, "elapsed_time": "0:31:36", "remaining_time": "2:40:25", "throughput": "501.99", "total_tokens": 951872} -{"current_steps": 145, "total_steps": 875, "loss": 0.1112, "learning_rate": 4.7054715813456795e-06, "epoch": 0.82679971489665, "percentage": 16.57, "elapsed_time": "0:31:49", "remaining_time": "2:40:12", "throughput": "501.90", "total_tokens": 958320} -{"current_steps": 146, "total_steps": 875, "loss": 0.0939, "learning_rate": 4.701181426435174e-06, "epoch": 0.8325017818959373, "percentage": 16.69, "elapsed_time": "0:32:02", "remaining_time": "2:39:59", "throughput": "501.95", "total_tokens": 965008} -{"current_steps": 147, "total_steps": 875, "loss": 0.0549, "learning_rate": 4.69686223645365e-06, "epoch": 0.8382038488952245, "percentage": 16.8, "elapsed_time": "0:32:15", "remaining_time": "2:39:46", "throughput": "501.90", "total_tokens": 971520} -{"current_steps": 148, "total_steps": 875, "loss": 0.1128, "learning_rate": 4.692514068374142e-06, "epoch": 0.8439059158945118, "percentage": 16.91, "elapsed_time": "0:32:28", "remaining_time": "2:39:32", "throughput": "502.11", "total_tokens": 978512} -{"current_steps": 149, "total_steps": 875, "loss": 0.0862, "learning_rate": 4.688136979551926e-06, "epoch": 0.849607982893799, "percentage": 17.03, "elapsed_time": "0:32:41", "remaining_time": "2:39:19", "throughput": "502.18", "total_tokens": 985264} -{"current_steps": 150, "total_steps": 875, "loss": 0.0769, "learning_rate": 4.683731027723764e-06, "epoch": 0.8553100498930862, "percentage": 17.14, "elapsed_time": "0:32:55", "remaining_time": "2:39:06", "throughput": "502.02", "total_tokens": 991552} -{"current_steps": 151, "total_steps": 875, "loss": 0.1199, "learning_rate": 4.679296271007138e-06, "epoch": 0.8610121168923734, "percentage": 17.26, "elapsed_time": "0:33:08", "remaining_time": "2:38:53", "throughput": "501.97", "total_tokens": 998064} -{"current_steps": 152, "total_steps": 875, "loss": 0.093, "learning_rate": 4.674832767899486e-06, "epoch": 0.8667141838916608, "percentage": 17.37, "elapsed_time": "0:33:21", "remaining_time": "2:38:39", "throughput": "502.07", "total_tokens": 1004864} -{"current_steps": 153, "total_steps": 875, "loss": 0.0903, "learning_rate": 4.670340577277433e-06, "epoch": 0.872416250890948, "percentage": 17.49, "elapsed_time": "0:33:34", "remaining_time": "2:38:26", "throughput": "502.12", "total_tokens": 1011568} -{"current_steps": 154, "total_steps": 875, "loss": 0.0877, "learning_rate": 4.665819758396009e-06, "epoch": 0.8781183178902352, "percentage": 17.6, "elapsed_time": "0:33:47", "remaining_time": "2:38:13", "throughput": "502.19", "total_tokens": 1018320} -{"current_steps": 155, "total_steps": 875, "loss": 0.1049, "learning_rate": 4.661270370887872e-06, "epoch": 0.8838203848895224, "percentage": 17.71, "elapsed_time": "0:34:00", "remaining_time": "2:38:00", "throughput": "502.05", "total_tokens": 1024640} -{"current_steps": 156, "total_steps": 875, "loss": 0.1052, "learning_rate": 4.656692474762518e-06, "epoch": 0.8895224518888097, "percentage": 17.83, "elapsed_time": "0:34:14", "remaining_time": "2:37:47", "throughput": "502.09", "total_tokens": 1031312} -{"current_steps": 157, "total_steps": 875, "loss": 0.1196, "learning_rate": 4.652086130405492e-06, "epoch": 0.895224518888097, "percentage": 17.94, "elapsed_time": "0:34:27", "remaining_time": "2:37:33", "throughput": "502.10", "total_tokens": 1037936} -{"current_steps": 158, "total_steps": 875, "loss": 0.0427, "learning_rate": 4.647451398577589e-06, "epoch": 0.9009265858873842, "percentage": 18.06, "elapsed_time": "0:34:40", "remaining_time": "2:37:20", "throughput": "502.08", "total_tokens": 1044496} -{"current_steps": 159, "total_steps": 875, "loss": 0.0764, "learning_rate": 4.642788340414056e-06, "epoch": 0.9066286528866714, "percentage": 18.17, "elapsed_time": "0:34:53", "remaining_time": "2:37:07", "throughput": "502.25", "total_tokens": 1051456} -{"current_steps": 160, "total_steps": 875, "loss": 0.0812, "learning_rate": 4.638097017423783e-06, "epoch": 0.9123307198859587, "percentage": 18.29, "elapsed_time": "0:35:06", "remaining_time": "2:36:54", "throughput": "502.20", "total_tokens": 1057952} -{"current_steps": 161, "total_steps": 875, "loss": 0.0807, "learning_rate": 4.63337749148849e-06, "epoch": 0.9180327868852459, "percentage": 18.4, "elapsed_time": "0:35:19", "remaining_time": "2:36:40", "throughput": "502.42", "total_tokens": 1065024} -{"current_steps": 162, "total_steps": 875, "loss": 0.1475, "learning_rate": 4.628629824861915e-06, "epoch": 0.9237348538845331, "percentage": 18.51, "elapsed_time": "0:35:32", "remaining_time": "2:36:27", "throughput": "502.58", "total_tokens": 1071968} -{"current_steps": 163, "total_steps": 875, "loss": 0.0507, "learning_rate": 4.62385408016899e-06, "epoch": 0.9294369208838203, "percentage": 18.63, "elapsed_time": "0:35:46", "remaining_time": "2:36:14", "throughput": "502.42", "total_tokens": 1078256} -{"current_steps": 164, "total_steps": 875, "loss": 0.1015, "learning_rate": 4.619050320405017e-06, "epoch": 0.9351389878831077, "percentage": 18.74, "elapsed_time": "0:35:59", "remaining_time": "2:36:01", "throughput": "502.37", "total_tokens": 1084752} -{"current_steps": 165, "total_steps": 875, "loss": 0.0957, "learning_rate": 4.614218608934834e-06, "epoch": 0.9408410548823949, "percentage": 18.86, "elapsed_time": "0:36:12", "remaining_time": "2:35:47", "throughput": "502.38", "total_tokens": 1091376} -{"current_steps": 166, "total_steps": 875, "loss": 0.1327, "learning_rate": 4.609359009491981e-06, "epoch": 0.9465431218816821, "percentage": 18.97, "elapsed_time": "0:36:25", "remaining_time": "2:35:34", "throughput": "502.47", "total_tokens": 1098176} -{"current_steps": 167, "total_steps": 875, "loss": 0.0782, "learning_rate": 4.60447158617786e-06, "epoch": 0.9522451888809693, "percentage": 19.09, "elapsed_time": "0:36:38", "remaining_time": "2:35:21", "throughput": "502.50", "total_tokens": 1104848} -{"current_steps": 168, "total_steps": 875, "loss": 0.0768, "learning_rate": 4.599556403460889e-06, "epoch": 0.9579472558802566, "percentage": 19.2, "elapsed_time": "0:36:51", "remaining_time": "2:35:08", "throughput": "502.35", "total_tokens": 1111120} -{"current_steps": 169, "total_steps": 875, "loss": 0.033, "learning_rate": 4.59461352617565e-06, "epoch": 0.9636493228795439, "percentage": 19.31, "elapsed_time": "0:37:05", "remaining_time": "2:34:55", "throughput": "502.22", "total_tokens": 1117440} -{"current_steps": 170, "total_steps": 875, "loss": 0.1295, "learning_rate": 4.589643019522036e-06, "epoch": 0.9693513898788311, "percentage": 19.43, "elapsed_time": "0:37:18", "remaining_time": "2:34:41", "throughput": "502.18", "total_tokens": 1123968} -{"current_steps": 171, "total_steps": 875, "loss": 0.1216, "learning_rate": 4.584644949064391e-06, "epoch": 0.9750534568781183, "percentage": 19.54, "elapsed_time": "0:37:31", "remaining_time": "2:34:28", "throughput": "502.22", "total_tokens": 1130656} -{"current_steps": 172, "total_steps": 875, "loss": 0.0896, "learning_rate": 4.579619380730642e-06, "epoch": 0.9807555238774056, "percentage": 19.66, "elapsed_time": "0:37:44", "remaining_time": "2:34:15", "throughput": "502.14", "total_tokens": 1137088} -{"current_steps": 173, "total_steps": 875, "loss": 0.101, "learning_rate": 4.574566380811432e-06, "epoch": 0.9864575908766928, "percentage": 19.77, "elapsed_time": "0:37:57", "remaining_time": "2:34:02", "throughput": "502.30", "total_tokens": 1144064} -{"current_steps": 174, "total_steps": 875, "loss": 0.0787, "learning_rate": 4.569486015959247e-06, "epoch": 0.99215965787598, "percentage": 19.89, "elapsed_time": "0:38:10", "remaining_time": "2:33:49", "throughput": "502.25", "total_tokens": 1150560} -{"current_steps": 175, "total_steps": 875, "loss": 0.1118, "learning_rate": 4.564378353187533e-06, "epoch": 0.9978617248752673, "percentage": 20.0, "elapsed_time": "0:38:23", "remaining_time": "2:33:35", "throughput": "502.26", "total_tokens": 1157184} -{"current_steps": 176, "total_steps": 875, "loss": 0.0671, "learning_rate": 4.5592434598698144e-06, "epoch": 1.0035637918745546, "percentage": 20.11, "elapsed_time": "0:38:37", "remaining_time": "2:33:22", "throughput": "502.22", "total_tokens": 1163712} -{"current_steps": 177, "total_steps": 875, "loss": 0.0862, "learning_rate": 4.5540814037388056e-06, "epoch": 1.0092658588738417, "percentage": 20.23, "elapsed_time": "0:38:50", "remaining_time": "2:33:09", "throughput": "502.29", "total_tokens": 1170480} -{"current_steps": 178, "total_steps": 875, "loss": 0.0385, "learning_rate": 4.548892252885518e-06, "epoch": 1.014967925873129, "percentage": 20.34, "elapsed_time": "0:39:03", "remaining_time": "2:32:56", "throughput": "502.15", "total_tokens": 1176768} -{"current_steps": 179, "total_steps": 875, "loss": 0.0557, "learning_rate": 4.543676075758356e-06, "epoch": 1.0206699928724163, "percentage": 20.46, "elapsed_time": "0:39:16", "remaining_time": "2:32:43", "throughput": "502.21", "total_tokens": 1183520} -{"current_steps": 180, "total_steps": 875, "loss": 0.0692, "learning_rate": 4.538432941162227e-06, "epoch": 1.0263720598717034, "percentage": 20.57, "elapsed_time": "0:39:29", "remaining_time": "2:32:29", "throughput": "502.15", "total_tokens": 1189968} -{"current_steps": 181, "total_steps": 875, "loss": 0.1001, "learning_rate": 4.533162918257615e-06, "epoch": 1.0320741268709908, "percentage": 20.69, "elapsed_time": "0:39:42", "remaining_time": "2:32:16", "throughput": "502.09", "total_tokens": 1196432} -{"current_steps": 182, "total_steps": 875, "loss": 0.0782, "learning_rate": 4.5278660765596885e-06, "epoch": 1.037776193870278, "percentage": 20.8, "elapsed_time": "0:39:56", "remaining_time": "2:32:03", "throughput": "502.08", "total_tokens": 1203024} -{"current_steps": 183, "total_steps": 875, "loss": 0.0324, "learning_rate": 4.522542485937369e-06, "epoch": 1.0434782608695652, "percentage": 20.91, "elapsed_time": "0:40:09", "remaining_time": "2:31:50", "throughput": "502.13", "total_tokens": 1209744} -{"current_steps": 184, "total_steps": 875, "loss": 0.0671, "learning_rate": 4.517192216612415e-06, "epoch": 1.0491803278688525, "percentage": 21.03, "elapsed_time": "0:40:22", "remaining_time": "2:31:37", "throughput": "502.02", "total_tokens": 1216080} -{"current_steps": 185, "total_steps": 875, "loss": 0.051, "learning_rate": 4.511815339158497e-06, "epoch": 1.0548823948681396, "percentage": 21.14, "elapsed_time": "0:40:35", "remaining_time": "2:31:23", "throughput": "502.29", "total_tokens": 1223328} -{"current_steps": 186, "total_steps": 875, "loss": 0.0565, "learning_rate": 4.506411924500263e-06, "epoch": 1.060584461867427, "percentage": 21.26, "elapsed_time": "0:40:48", "remaining_time": "2:31:10", "throughput": "502.39", "total_tokens": 1230192} -{"current_steps": 187, "total_steps": 875, "loss": 0.0393, "learning_rate": 4.500982043912404e-06, "epoch": 1.0662865288667143, "percentage": 21.37, "elapsed_time": "0:41:01", "remaining_time": "2:30:57", "throughput": "502.46", "total_tokens": 1236992} -{"current_steps": 188, "total_steps": 875, "loss": 0.0922, "learning_rate": 4.495525769018717e-06, "epoch": 1.0719885958660014, "percentage": 21.49, "elapsed_time": "0:41:15", "remaining_time": "2:30:44", "throughput": "502.53", "total_tokens": 1243776} -{"current_steps": 189, "total_steps": 875, "loss": 0.0518, "learning_rate": 4.490043171791155e-06, "epoch": 1.0776906628652887, "percentage": 21.6, "elapsed_time": "0:41:28", "remaining_time": "2:30:31", "throughput": "502.68", "total_tokens": 1250752} -{"current_steps": 190, "total_steps": 875, "loss": 0.0894, "learning_rate": 4.484534324548883e-06, "epoch": 1.0833927298645758, "percentage": 21.71, "elapsed_time": "0:41:41", "remaining_time": "2:30:17", "throughput": "502.67", "total_tokens": 1257344} -{"current_steps": 191, "total_steps": 875, "loss": 0.0631, "learning_rate": 4.47899929995732e-06, "epoch": 1.0890947968638631, "percentage": 21.83, "elapsed_time": "0:41:54", "remaining_time": "2:30:04", "throughput": "502.71", "total_tokens": 1264064} -{"current_steps": 192, "total_steps": 875, "loss": 0.0464, "learning_rate": 4.47343817102718e-06, "epoch": 1.0947968638631504, "percentage": 21.94, "elapsed_time": "0:42:07", "remaining_time": "2:29:51", "throughput": "502.69", "total_tokens": 1270608} -{"current_steps": 193, "total_steps": 875, "loss": 0.0652, "learning_rate": 4.4678510111135154e-06, "epoch": 1.1004989308624376, "percentage": 22.06, "elapsed_time": "0:42:20", "remaining_time": "2:29:38", "throughput": "502.62", "total_tokens": 1277056} -{"current_steps": 194, "total_steps": 875, "loss": 0.0317, "learning_rate": 4.462237893914742e-06, "epoch": 1.1062009978617249, "percentage": 22.17, "elapsed_time": "0:42:33", "remaining_time": "2:29:25", "throughput": "502.66", "total_tokens": 1283776} -{"current_steps": 195, "total_steps": 875, "loss": 0.0485, "learning_rate": 4.456598893471668e-06, "epoch": 1.1119030648610122, "percentage": 22.29, "elapsed_time": "0:42:47", "remaining_time": "2:29:11", "throughput": "502.66", "total_tokens": 1290368} -{"current_steps": 196, "total_steps": 875, "loss": 0.0325, "learning_rate": 4.450934084166524e-06, "epoch": 1.1176051318602993, "percentage": 22.4, "elapsed_time": "0:43:00", "remaining_time": "2:28:58", "throughput": "502.68", "total_tokens": 1297040} -{"current_steps": 197, "total_steps": 875, "loss": 0.0753, "learning_rate": 4.445243540721972e-06, "epoch": 1.1233071988595866, "percentage": 22.51, "elapsed_time": "0:43:13", "remaining_time": "2:28:45", "throughput": "502.76", "total_tokens": 1303856} -{"current_steps": 198, "total_steps": 875, "loss": 0.0159, "learning_rate": 4.439527338200129e-06, "epoch": 1.129009265858874, "percentage": 22.63, "elapsed_time": "0:43:26", "remaining_time": "2:28:32", "throughput": "502.73", "total_tokens": 1310384} -{"current_steps": 199, "total_steps": 875, "loss": 0.0718, "learning_rate": 4.433785552001569e-06, "epoch": 1.134711332858161, "percentage": 22.74, "elapsed_time": "0:43:39", "remaining_time": "2:28:19", "throughput": "502.72", "total_tokens": 1316976} -{"current_steps": 200, "total_steps": 875, "loss": 0.0491, "learning_rate": 4.428018257864333e-06, "epoch": 1.1404133998574484, "percentage": 22.86, "elapsed_time": "0:43:52", "remaining_time": "2:28:05", "throughput": "502.69", "total_tokens": 1323520} -{"current_steps": 201, "total_steps": 875, "loss": 0.0608, "learning_rate": 4.422225531862929e-06, "epoch": 1.1461154668567355, "percentage": 22.97, "elapsed_time": "0:44:06", "remaining_time": "2:27:52", "throughput": "502.64", "total_tokens": 1329984} -{"current_steps": 202, "total_steps": 875, "loss": 0.0631, "learning_rate": 4.416407450407332e-06, "epoch": 1.1518175338560228, "percentage": 23.09, "elapsed_time": "0:44:19", "remaining_time": "2:27:39", "throughput": "502.68", "total_tokens": 1336704} -{"current_steps": 203, "total_steps": 875, "loss": 0.024, "learning_rate": 4.4105640902419665e-06, "epoch": 1.1575196008553101, "percentage": 23.2, "elapsed_time": "0:44:32", "remaining_time": "2:27:26", "throughput": "502.69", "total_tokens": 1343344} -{"current_steps": 204, "total_steps": 875, "loss": 0.0453, "learning_rate": 4.404695528444704e-06, "epoch": 1.1632216678545972, "percentage": 23.31, "elapsed_time": "0:44:45", "remaining_time": "2:27:13", "throughput": "502.76", "total_tokens": 1350144} -{"current_steps": 205, "total_steps": 875, "loss": 0.0345, "learning_rate": 4.398801842425842e-06, "epoch": 1.1689237348538846, "percentage": 23.43, "elapsed_time": "0:44:58", "remaining_time": "2:26:59", "throughput": "502.73", "total_tokens": 1356672} -{"current_steps": 206, "total_steps": 875, "loss": 0.015, "learning_rate": 4.392883109927083e-06, "epoch": 1.1746258018531717, "percentage": 23.54, "elapsed_time": "0:45:11", "remaining_time": "2:26:46", "throughput": "502.70", "total_tokens": 1363200} -{"current_steps": 207, "total_steps": 875, "loss": 0.0731, "learning_rate": 4.3869394090205105e-06, "epoch": 1.180327868852459, "percentage": 23.66, "elapsed_time": "0:45:24", "remaining_time": "2:26:33", "throughput": "502.55", "total_tokens": 1369408} -{"current_steps": 208, "total_steps": 875, "loss": 0.056, "learning_rate": 4.380970818107556e-06, "epoch": 1.1860299358517463, "percentage": 23.77, "elapsed_time": "0:45:38", "remaining_time": "2:26:20", "throughput": "502.72", "total_tokens": 1376480} -{"current_steps": 209, "total_steps": 875, "loss": 0.1013, "learning_rate": 4.374977415917969e-06, "epoch": 1.1917320028510334, "percentage": 23.89, "elapsed_time": "0:45:51", "remaining_time": "2:26:07", "throughput": "502.67", "total_tokens": 1382944} -{"current_steps": 210, "total_steps": 875, "loss": 0.0254, "learning_rate": 4.368959281508776e-06, "epoch": 1.1974340698503207, "percentage": 24.0, "elapsed_time": "0:46:04", "remaining_time": "2:25:53", "throughput": "502.76", "total_tokens": 1389824} -{"current_steps": 211, "total_steps": 875, "loss": 0.0526, "learning_rate": 4.3629164942632385e-06, "epoch": 1.203136136849608, "percentage": 24.11, "elapsed_time": "0:46:17", "remaining_time": "2:25:40", "throughput": "502.76", "total_tokens": 1396448} -{"current_steps": 212, "total_steps": 875, "loss": 0.037, "learning_rate": 4.356849133889805e-06, "epoch": 1.2088382038488952, "percentage": 24.23, "elapsed_time": "0:46:30", "remaining_time": "2:25:27", "throughput": "502.73", "total_tokens": 1402976} -{"current_steps": 213, "total_steps": 875, "loss": 0.0438, "learning_rate": 4.350757280421061e-06, "epoch": 1.2145402708481825, "percentage": 24.34, "elapsed_time": "0:46:43", "remaining_time": "2:25:14", "throughput": "502.75", "total_tokens": 1409648} -{"current_steps": 214, "total_steps": 875, "loss": 0.0496, "learning_rate": 4.34464101421267e-06, "epoch": 1.2202423378474698, "percentage": 24.46, "elapsed_time": "0:46:56", "remaining_time": "2:25:01", "throughput": "502.78", "total_tokens": 1416320} -{"current_steps": 215, "total_steps": 875, "loss": 0.0453, "learning_rate": 4.3385004159423195e-06, "epoch": 1.225944404846757, "percentage": 24.57, "elapsed_time": "0:47:10", "remaining_time": "2:24:47", "throughput": "502.72", "total_tokens": 1422768} -{"current_steps": 216, "total_steps": 875, "loss": 0.0428, "learning_rate": 4.332335566608651e-06, "epoch": 1.2316464718460443, "percentage": 24.69, "elapsed_time": "0:47:23", "remaining_time": "2:24:34", "throughput": "502.72", "total_tokens": 1429392} -{"current_steps": 217, "total_steps": 875, "loss": 0.113, "learning_rate": 4.3261465475301956e-06, "epoch": 1.2373485388453314, "percentage": 24.8, "elapsed_time": "0:47:36", "remaining_time": "2:24:21", "throughput": "502.67", "total_tokens": 1435872} -{"current_steps": 218, "total_steps": 875, "loss": 0.0934, "learning_rate": 4.319933440344298e-06, "epoch": 1.2430506058446187, "percentage": 24.91, "elapsed_time": "0:47:49", "remaining_time": "2:24:08", "throughput": "502.86", "total_tokens": 1443024} -{"current_steps": 219, "total_steps": 875, "loss": 0.0495, "learning_rate": 4.313696327006042e-06, "epoch": 1.248752672843906, "percentage": 25.03, "elapsed_time": "0:48:02", "remaining_time": "2:23:55", "throughput": "502.81", "total_tokens": 1449488} -{"current_steps": 220, "total_steps": 875, "loss": 0.0962, "learning_rate": 4.307435289787169e-06, "epoch": 1.2544547398431931, "percentage": 25.14, "elapsed_time": "0:48:15", "remaining_time": "2:23:41", "throughput": "502.71", "total_tokens": 1455808} -{"current_steps": 221, "total_steps": 875, "loss": 0.0546, "learning_rate": 4.301150411274993e-06, "epoch": 1.2601568068424804, "percentage": 25.26, "elapsed_time": "0:48:29", "remaining_time": "2:23:28", "throughput": "502.73", "total_tokens": 1462480} -{"current_steps": 222, "total_steps": 875, "loss": 0.0321, "learning_rate": 4.294841774371308e-06, "epoch": 1.2658588738417675, "percentage": 25.37, "elapsed_time": "0:48:42", "remaining_time": "2:23:15", "throughput": "502.64", "total_tokens": 1468832} -{"current_steps": 223, "total_steps": 875, "loss": 0.042, "learning_rate": 4.288509462291302e-06, "epoch": 1.2715609408410549, "percentage": 25.49, "elapsed_time": "0:48:55", "remaining_time": "2:23:02", "throughput": "502.64", "total_tokens": 1475440} -{"current_steps": 224, "total_steps": 875, "loss": 0.0554, "learning_rate": 4.282153558562451e-06, "epoch": 1.2772630078403422, "percentage": 25.6, "elapsed_time": "0:49:08", "remaining_time": "2:22:49", "throughput": "502.74", "total_tokens": 1482336} -{"current_steps": 225, "total_steps": 875, "loss": 0.0263, "learning_rate": 4.2757741470234214e-06, "epoch": 1.2829650748396293, "percentage": 25.71, "elapsed_time": "0:49:21", "remaining_time": "2:22:35", "throughput": "502.92", "total_tokens": 1489472} -{"current_steps": 226, "total_steps": 875, "loss": 0.0433, "learning_rate": 4.269371311822965e-06, "epoch": 1.2886671418389166, "percentage": 25.83, "elapsed_time": "0:49:34", "remaining_time": "2:22:22", "throughput": "502.99", "total_tokens": 1496304} -{"current_steps": 227, "total_steps": 875, "loss": 0.0569, "learning_rate": 4.262945137418806e-06, "epoch": 1.2943692088382037, "percentage": 25.94, "elapsed_time": "0:49:47", "remaining_time": "2:22:09", "throughput": "502.98", "total_tokens": 1502896} -{"current_steps": 228, "total_steps": 875, "loss": 0.0532, "learning_rate": 4.256495708576527e-06, "epoch": 1.300071275837491, "percentage": 26.06, "elapsed_time": "0:50:01", "remaining_time": "2:21:56", "throughput": "503.22", "total_tokens": 1510224} -{"current_steps": 229, "total_steps": 875, "loss": 0.0155, "learning_rate": 4.250023110368458e-06, "epoch": 1.3057733428367784, "percentage": 26.17, "elapsed_time": "0:50:14", "remaining_time": "2:21:43", "throughput": "503.14", "total_tokens": 1516624} -{"current_steps": 230, "total_steps": 875, "loss": 0.0277, "learning_rate": 4.243527428172541e-06, "epoch": 1.3114754098360657, "percentage": 26.29, "elapsed_time": "0:50:27", "remaining_time": "2:21:30", "throughput": "503.09", "total_tokens": 1523088} -{"current_steps": 231, "total_steps": 875, "loss": 0.074, "learning_rate": 4.237008747671218e-06, "epoch": 1.3171774768353528, "percentage": 26.4, "elapsed_time": "0:50:40", "remaining_time": "2:21:16", "throughput": "503.17", "total_tokens": 1529936} -{"current_steps": 232, "total_steps": 875, "loss": 0.0861, "learning_rate": 4.230467154850289e-06, "epoch": 1.3228795438346401, "percentage": 26.51, "elapsed_time": "0:50:53", "remaining_time": "2:21:03", "throughput": "503.09", "total_tokens": 1536320} -{"current_steps": 233, "total_steps": 875, "loss": 0.0669, "learning_rate": 4.2239027359977885e-06, "epoch": 1.3285816108339272, "percentage": 26.63, "elapsed_time": "0:51:06", "remaining_time": "2:20:50", "throughput": "503.13", "total_tokens": 1543056} -{"current_steps": 234, "total_steps": 875, "loss": 0.0703, "learning_rate": 4.217315577702836e-06, "epoch": 1.3342836778332146, "percentage": 26.74, "elapsed_time": "0:51:20", "remaining_time": "2:20:37", "throughput": "503.12", "total_tokens": 1549664} -{"current_steps": 235, "total_steps": 875, "loss": 0.0172, "learning_rate": 4.210705766854505e-06, "epoch": 1.3399857448325019, "percentage": 26.86, "elapsed_time": "0:51:33", "remaining_time": "2:20:24", "throughput": "503.16", "total_tokens": 1556384} -{"current_steps": 236, "total_steps": 875, "loss": 0.1336, "learning_rate": 4.2040733906406664e-06, "epoch": 1.345687811831789, "percentage": 26.97, "elapsed_time": "0:51:46", "remaining_time": "2:20:10", "throughput": "503.23", "total_tokens": 1563216} -{"current_steps": 237, "total_steps": 875, "loss": 0.0207, "learning_rate": 4.197418536546846e-06, "epoch": 1.3513898788310763, "percentage": 27.09, "elapsed_time": "0:51:59", "remaining_time": "2:19:57", "throughput": "503.17", "total_tokens": 1569664} -{"current_steps": 238, "total_steps": 875, "loss": 0.0815, "learning_rate": 4.190741292355071e-06, "epoch": 1.3570919458303634, "percentage": 27.2, "elapsed_time": "0:52:12", "remaining_time": "2:19:44", "throughput": "503.23", "total_tokens": 1576464} -{"current_steps": 239, "total_steps": 875, "loss": 0.0453, "learning_rate": 4.184041746142702e-06, "epoch": 1.3627940128296507, "percentage": 27.31, "elapsed_time": "0:52:25", "remaining_time": "2:19:31", "throughput": "503.15", "total_tokens": 1582816} -{"current_steps": 240, "total_steps": 875, "loss": 0.0791, "learning_rate": 4.177319986281285e-06, "epoch": 1.368496079828938, "percentage": 27.43, "elapsed_time": "0:52:38", "remaining_time": "2:19:18", "throughput": "503.12", "total_tokens": 1589344} -{"current_steps": 241, "total_steps": 875, "loss": 0.0344, "learning_rate": 4.170576101435377e-06, "epoch": 1.3741981468282252, "percentage": 27.54, "elapsed_time": "0:52:52", "remaining_time": "2:19:04", "throughput": "503.10", "total_tokens": 1595888} -{"current_steps": 242, "total_steps": 875, "loss": 0.0532, "learning_rate": 4.163810180561376e-06, "epoch": 1.3799002138275125, "percentage": 27.66, "elapsed_time": "0:53:05", "remaining_time": "2:18:51", "throughput": "503.17", "total_tokens": 1602736} -{"current_steps": 243, "total_steps": 875, "loss": 0.0574, "learning_rate": 4.157022312906352e-06, "epoch": 1.3856022808267996, "percentage": 27.77, "elapsed_time": "0:53:18", "remaining_time": "2:18:38", "throughput": "503.20", "total_tokens": 1609456} -{"current_steps": 244, "total_steps": 875, "loss": 0.1002, "learning_rate": 4.150212588006871e-06, "epoch": 1.391304347826087, "percentage": 27.89, "elapsed_time": "0:53:31", "remaining_time": "2:18:25", "throughput": "503.19", "total_tokens": 1616032} -{"current_steps": 245, "total_steps": 875, "loss": 0.0314, "learning_rate": 4.143381095687805e-06, "epoch": 1.3970064148253742, "percentage": 28.0, "elapsed_time": "0:53:44", "remaining_time": "2:18:12", "throughput": "503.23", "total_tokens": 1622800} -{"current_steps": 246, "total_steps": 875, "loss": 0.0689, "learning_rate": 4.1365279260611575e-06, "epoch": 1.4027084818246616, "percentage": 28.11, "elapsed_time": "0:53:57", "remaining_time": "2:17:59", "throughput": "503.18", "total_tokens": 1629248} -{"current_steps": 247, "total_steps": 875, "loss": 0.0587, "learning_rate": 4.129653169524867e-06, "epoch": 1.4084105488239487, "percentage": 28.23, "elapsed_time": "0:54:11", "remaining_time": "2:17:45", "throughput": "503.08", "total_tokens": 1635568} -{"current_steps": 248, "total_steps": 875, "loss": 0.0433, "learning_rate": 4.12275691676162e-06, "epoch": 1.414112615823236, "percentage": 28.34, "elapsed_time": "0:54:24", "remaining_time": "2:17:32", "throughput": "503.09", "total_tokens": 1642208} -{"current_steps": 249, "total_steps": 875, "loss": 0.0306, "learning_rate": 4.115839258737654e-06, "epoch": 1.419814682822523, "percentage": 28.46, "elapsed_time": "0:54:37", "remaining_time": "2:17:19", "throughput": "503.06", "total_tokens": 1648720} -{"current_steps": 250, "total_steps": 875, "loss": 0.0454, "learning_rate": 4.108900286701553e-06, "epoch": 1.4255167498218104, "percentage": 28.57, "elapsed_time": "0:54:50", "remaining_time": "2:17:06", "throughput": "503.05", "total_tokens": 1655296} -{"current_steps": 251, "total_steps": 875, "loss": 0.0464, "learning_rate": 4.101940092183048e-06, "epoch": 1.4312188168210978, "percentage": 28.69, "elapsed_time": "0:55:03", "remaining_time": "2:16:53", "throughput": "503.16", "total_tokens": 1662272} -{"current_steps": 252, "total_steps": 875, "loss": 0.0578, "learning_rate": 4.094958766991812e-06, "epoch": 1.4369208838203849, "percentage": 28.8, "elapsed_time": "0:55:16", "remaining_time": "2:16:39", "throughput": "503.24", "total_tokens": 1669168} -{"current_steps": 253, "total_steps": 875, "loss": 0.0369, "learning_rate": 4.087956403216243e-06, "epoch": 1.4426229508196722, "percentage": 28.91, "elapsed_time": "0:55:29", "remaining_time": "2:16:26", "throughput": "503.14", "total_tokens": 1675440} -{"current_steps": 254, "total_steps": 875, "loss": 0.0686, "learning_rate": 4.080933093222253e-06, "epoch": 1.4483250178189593, "percentage": 29.03, "elapsed_time": "0:55:43", "remaining_time": "2:16:13", "throughput": "503.14", "total_tokens": 1682080} -{"current_steps": 255, "total_steps": 875, "loss": 0.0873, "learning_rate": 4.073888929652048e-06, "epoch": 1.4540270848182466, "percentage": 29.14, "elapsed_time": "0:55:56", "remaining_time": "2:16:00", "throughput": "503.20", "total_tokens": 1688896} -{"current_steps": 256, "total_steps": 875, "loss": 0.0466, "learning_rate": 4.066824005422907e-06, "epoch": 1.459729151817534, "percentage": 29.26, "elapsed_time": "0:56:09", "remaining_time": "2:15:47", "throughput": "503.27", "total_tokens": 1695760} -{"current_steps": 257, "total_steps": 875, "loss": 0.0349, "learning_rate": 4.059738413725958e-06, "epoch": 1.465431218816821, "percentage": 29.37, "elapsed_time": "0:56:22", "remaining_time": "2:15:34", "throughput": "503.26", "total_tokens": 1702352} -{"current_steps": 258, "total_steps": 875, "loss": 0.061, "learning_rate": 4.0526322480249435e-06, "epoch": 1.4711332858161084, "percentage": 29.49, "elapsed_time": "0:56:35", "remaining_time": "2:15:20", "throughput": "503.31", "total_tokens": 1709120} -{"current_steps": 259, "total_steps": 875, "loss": 0.0801, "learning_rate": 4.045505602054995e-06, "epoch": 1.4768353528153955, "percentage": 29.6, "elapsed_time": "0:56:48", "remaining_time": "2:15:07", "throughput": "503.38", "total_tokens": 1716000} -{"current_steps": 260, "total_steps": 875, "loss": 0.0406, "learning_rate": 4.0383585698213874e-06, "epoch": 1.4825374198146828, "percentage": 29.71, "elapsed_time": "0:57:02", "remaining_time": "2:14:54", "throughput": "503.22", "total_tokens": 1722080} -{"current_steps": 261, "total_steps": 875, "loss": 0.0417, "learning_rate": 4.03119124559831e-06, "epoch": 1.4882394868139701, "percentage": 29.83, "elapsed_time": "0:57:15", "remaining_time": "2:14:41", "throughput": "503.30", "total_tokens": 1728960} -{"current_steps": 262, "total_steps": 875, "loss": 0.0178, "learning_rate": 4.0240037239276146e-06, "epoch": 1.4939415538132574, "percentage": 29.94, "elapsed_time": "0:57:28", "remaining_time": "2:14:28", "throughput": "503.25", "total_tokens": 1735408} -{"current_steps": 263, "total_steps": 875, "loss": 0.0238, "learning_rate": 4.016796099617569e-06, "epoch": 1.4996436208125445, "percentage": 30.06, "elapsed_time": "0:57:41", "remaining_time": "2:14:15", "throughput": "503.25", "total_tokens": 1742032} -{"current_steps": 264, "total_steps": 875, "loss": 0.0842, "learning_rate": 4.009568467741611e-06, "epoch": 1.5053456878118316, "percentage": 30.17, "elapsed_time": "0:57:54", "remaining_time": "2:14:01", "throughput": "503.30", "total_tokens": 1748848} -{"current_steps": 265, "total_steps": 875, "loss": 0.0354, "learning_rate": 4.002320923637091e-06, "epoch": 1.511047754811119, "percentage": 30.29, "elapsed_time": "0:58:07", "remaining_time": "2:13:48", "throughput": "503.34", "total_tokens": 1755584} -{"current_steps": 266, "total_steps": 875, "loss": 0.072, "learning_rate": 3.995053562904015e-06, "epoch": 1.5167498218104063, "percentage": 30.4, "elapsed_time": "0:58:21", "remaining_time": "2:13:35", "throughput": "503.41", "total_tokens": 1762464} -{"current_steps": 267, "total_steps": 875, "loss": 0.0297, "learning_rate": 3.987766481403785e-06, "epoch": 1.5224518888096936, "percentage": 30.51, "elapsed_time": "0:58:34", "remaining_time": "2:13:22", "throughput": "503.39", "total_tokens": 1769008} -{"current_steps": 268, "total_steps": 875, "loss": 0.0355, "learning_rate": 3.98045977525793e-06, "epoch": 1.5281539558089807, "percentage": 30.63, "elapsed_time": "0:58:47", "remaining_time": "2:13:09", "throughput": "503.44", "total_tokens": 1775808} -{"current_steps": 269, "total_steps": 875, "loss": 0.0669, "learning_rate": 3.973133540846844e-06, "epoch": 1.533856022808268, "percentage": 30.74, "elapsed_time": "0:59:00", "remaining_time": "2:12:56", "throughput": "503.43", "total_tokens": 1782416} -{"current_steps": 270, "total_steps": 875, "loss": 0.0622, "learning_rate": 3.965787874808513e-06, "epoch": 1.5395580898075552, "percentage": 30.86, "elapsed_time": "0:59:13", "remaining_time": "2:12:42", "throughput": "503.42", "total_tokens": 1788960} -{"current_steps": 271, "total_steps": 875, "loss": 0.0436, "learning_rate": 3.958422874037236e-06, "epoch": 1.5452601568068425, "percentage": 30.97, "elapsed_time": "0:59:26", "remaining_time": "2:12:29", "throughput": "503.42", "total_tokens": 1795600} -{"current_steps": 272, "total_steps": 875, "loss": 0.0265, "learning_rate": 3.951038635682352e-06, "epoch": 1.5509622238061298, "percentage": 31.09, "elapsed_time": "0:59:39", "remaining_time": "2:12:16", "throughput": "503.40", "total_tokens": 1802144} -{"current_steps": 273, "total_steps": 875, "loss": 0.0165, "learning_rate": 3.943635257146959e-06, "epoch": 1.5566642908054171, "percentage": 31.2, "elapsed_time": "0:59:53", "remaining_time": "2:12:03", "throughput": "503.37", "total_tokens": 1808656} -{"current_steps": 274, "total_steps": 875, "loss": 0.0246, "learning_rate": 3.936212836086621e-06, "epoch": 1.5623663578047042, "percentage": 31.31, "elapsed_time": "1:00:06", "remaining_time": "2:11:50", "throughput": "503.39", "total_tokens": 1815360} -{"current_steps": 275, "total_steps": 875, "loss": 0.0929, "learning_rate": 3.928771470408092e-06, "epoch": 1.5680684248039913, "percentage": 31.43, "elapsed_time": "1:00:19", "remaining_time": "2:11:36", "throughput": "503.41", "total_tokens": 1822048} -{"current_steps": 276, "total_steps": 875, "loss": 0.0591, "learning_rate": 3.921311258268013e-06, "epoch": 1.5737704918032787, "percentage": 31.54, "elapsed_time": "1:00:32", "remaining_time": "2:11:23", "throughput": "503.34", "total_tokens": 1828416} -{"current_steps": 277, "total_steps": 875, "loss": 0.0479, "learning_rate": 3.913832298071629e-06, "epoch": 1.579472558802566, "percentage": 31.66, "elapsed_time": "1:00:45", "remaining_time": "2:11:10", "throughput": "503.33", "total_tokens": 1835008} -{"current_steps": 278, "total_steps": 875, "loss": 0.0414, "learning_rate": 3.906334688471479e-06, "epoch": 1.5851746258018533, "percentage": 31.77, "elapsed_time": "1:00:58", "remaining_time": "2:10:57", "throughput": "503.30", "total_tokens": 1841536} -{"current_steps": 279, "total_steps": 875, "loss": 0.0591, "learning_rate": 3.8988185283661005e-06, "epoch": 1.5908766928011404, "percentage": 31.89, "elapsed_time": "1:01:12", "remaining_time": "2:10:44", "throughput": "503.28", "total_tokens": 1848064} -{"current_steps": 280, "total_steps": 875, "loss": 0.0797, "learning_rate": 3.891283916898729e-06, "epoch": 1.5965787598004275, "percentage": 32.0, "elapsed_time": "1:01:25", "remaining_time": "2:10:31", "throughput": "503.26", "total_tokens": 1854640} -{"current_steps": 281, "total_steps": 875, "loss": 0.0338, "learning_rate": 3.88373095345598e-06, "epoch": 1.6022808267997148, "percentage": 32.11, "elapsed_time": "1:01:38", "remaining_time": "2:10:17", "throughput": "503.24", "total_tokens": 1861184} -{"current_steps": 282, "total_steps": 875, "loss": 0.0764, "learning_rate": 3.876159737666552e-06, "epoch": 1.6079828937990022, "percentage": 32.23, "elapsed_time": "1:01:51", "remaining_time": "2:10:04", "throughput": "503.26", "total_tokens": 1867856} -{"current_steps": 283, "total_steps": 875, "loss": 0.0835, "learning_rate": 3.868570369399894e-06, "epoch": 1.6136849607982895, "percentage": 32.34, "elapsed_time": "1:02:04", "remaining_time": "2:09:51", "throughput": "503.34", "total_tokens": 1874768} -{"current_steps": 284, "total_steps": 875, "loss": 0.0644, "learning_rate": 3.860962948764906e-06, "epoch": 1.6193870277975766, "percentage": 32.46, "elapsed_time": "1:02:17", "remaining_time": "2:09:38", "throughput": "503.36", "total_tokens": 1881488} -{"current_steps": 285, "total_steps": 875, "loss": 0.0265, "learning_rate": 3.85333757610861e-06, "epoch": 1.6250890947968637, "percentage": 32.57, "elapsed_time": "1:02:30", "remaining_time": "2:09:25", "throughput": "503.34", "total_tokens": 1888032} -{"current_steps": 286, "total_steps": 875, "loss": 0.0934, "learning_rate": 3.845694352014825e-06, "epoch": 1.630791161796151, "percentage": 32.69, "elapsed_time": "1:02:44", "remaining_time": "2:09:12", "throughput": "503.44", "total_tokens": 1895008} -{"current_steps": 287, "total_steps": 875, "loss": 0.0436, "learning_rate": 3.838033377302844e-06, "epoch": 1.6364932287954383, "percentage": 32.8, "elapsed_time": "1:02:57", "remaining_time": "2:08:58", "throughput": "503.37", "total_tokens": 1901392} -{"current_steps": 288, "total_steps": 875, "loss": 0.0461, "learning_rate": 3.8303547530261025e-06, "epoch": 1.6421952957947257, "percentage": 32.91, "elapsed_time": "1:03:10", "remaining_time": "2:08:45", "throughput": "503.35", "total_tokens": 1907936} -{"current_steps": 289, "total_steps": 875, "loss": 0.0521, "learning_rate": 3.8226585804708435e-06, "epoch": 1.6478973627940128, "percentage": 33.03, "elapsed_time": "1:03:23", "remaining_time": "2:08:32", "throughput": "503.37", "total_tokens": 1914608} -{"current_steps": 290, "total_steps": 875, "loss": 0.0282, "learning_rate": 3.814944961154788e-06, "epoch": 1.6535994297933, "percentage": 33.14, "elapsed_time": "1:03:36", "remaining_time": "2:08:19", "throughput": "503.27", "total_tokens": 1920848} -{"current_steps": 291, "total_steps": 875, "loss": 0.0408, "learning_rate": 3.807213996825788e-06, "epoch": 1.6593014967925872, "percentage": 33.26, "elapsed_time": "1:03:49", "remaining_time": "2:08:06", "throughput": "503.30", "total_tokens": 1927600} -{"current_steps": 292, "total_steps": 875, "loss": 0.0435, "learning_rate": 3.799465789460491e-06, "epoch": 1.6650035637918745, "percentage": 33.37, "elapsed_time": "1:04:03", "remaining_time": "2:07:52", "throughput": "503.27", "total_tokens": 1934096} -{"current_steps": 293, "total_steps": 875, "loss": 0.0459, "learning_rate": 3.791700441262987e-06, "epoch": 1.6707056307911619, "percentage": 33.49, "elapsed_time": "1:04:16", "remaining_time": "2:07:39", "throughput": "503.30", "total_tokens": 1940816} -{"current_steps": 294, "total_steps": 875, "loss": 0.046, "learning_rate": 3.7839180546634703e-06, "epoch": 1.6764076977904492, "percentage": 33.6, "elapsed_time": "1:04:29", "remaining_time": "2:07:26", "throughput": "503.29", "total_tokens": 1947392} -{"current_steps": 295, "total_steps": 875, "loss": 0.0338, "learning_rate": 3.77611873231688e-06, "epoch": 1.6821097647897363, "percentage": 33.71, "elapsed_time": "1:04:42", "remaining_time": "2:07:13", "throughput": "503.35", "total_tokens": 1954272} -{"current_steps": 296, "total_steps": 875, "loss": 0.0304, "learning_rate": 3.7683025771015515e-06, "epoch": 1.6878118317890234, "percentage": 33.83, "elapsed_time": "1:04:55", "remaining_time": "2:07:00", "throughput": "503.29", "total_tokens": 1960640} -{"current_steps": 297, "total_steps": 875, "loss": 0.0652, "learning_rate": 3.760469692117854e-06, "epoch": 1.6935138987883107, "percentage": 33.94, "elapsed_time": "1:05:08", "remaining_time": "2:06:47", "throughput": "503.33", "total_tokens": 1967440} -{"current_steps": 298, "total_steps": 875, "loss": 0.0233, "learning_rate": 3.7526201806868372e-06, "epoch": 1.699215965787598, "percentage": 34.06, "elapsed_time": "1:05:21", "remaining_time": "2:06:33", "throughput": "503.31", "total_tokens": 1973968} -{"current_steps": 299, "total_steps": 875, "loss": 0.0447, "learning_rate": 3.744754146348862e-06, "epoch": 1.7049180327868854, "percentage": 34.17, "elapsed_time": "1:05:35", "remaining_time": "2:06:20", "throughput": "503.29", "total_tokens": 1980496} -{"current_steps": 300, "total_steps": 875, "loss": 0.0599, "learning_rate": 3.736871692862239e-06, "epoch": 1.7106200997861725, "percentage": 34.29, "elapsed_time": "1:05:48", "remaining_time": "2:06:07", "throughput": "503.30", "total_tokens": 1987184} -{"current_steps": 301, "total_steps": 875, "loss": 0.0607, "learning_rate": 3.7289729242018584e-06, "epoch": 1.7163221667854596, "percentage": 34.4, "elapsed_time": "1:06:01", "remaining_time": "2:05:54", "throughput": "503.34", "total_tokens": 1993968} -{"current_steps": 302, "total_steps": 875, "loss": 0.0449, "learning_rate": 3.721057944557819e-06, "epoch": 1.722024233784747, "percentage": 34.51, "elapsed_time": "1:06:14", "remaining_time": "2:05:41", "throughput": "503.35", "total_tokens": 2000640} -{"current_steps": 303, "total_steps": 875, "loss": 0.0294, "learning_rate": 3.713126858334052e-06, "epoch": 1.7277263007840342, "percentage": 34.63, "elapsed_time": "1:06:27", "remaining_time": "2:05:28", "throughput": "503.24", "total_tokens": 2006784} -{"current_steps": 304, "total_steps": 875, "loss": 0.058, "learning_rate": 3.705179770146946e-06, "epoch": 1.7334283677833215, "percentage": 34.74, "elapsed_time": "1:06:40", "remaining_time": "2:05:14", "throughput": "503.21", "total_tokens": 2013280} -{"current_steps": 305, "total_steps": 875, "loss": 0.0774, "learning_rate": 3.6972167848239677e-06, "epoch": 1.7391304347826086, "percentage": 34.86, "elapsed_time": "1:06:54", "remaining_time": "2:05:01", "throughput": "503.23", "total_tokens": 2019984} -{"current_steps": 306, "total_steps": 875, "loss": 0.0718, "learning_rate": 3.689238007402275e-06, "epoch": 1.744832501781896, "percentage": 34.97, "elapsed_time": "1:07:07", "remaining_time": "2:04:48", "throughput": "503.23", "total_tokens": 2026624} -{"current_steps": 307, "total_steps": 875, "loss": 0.0642, "learning_rate": 3.6812435431273375e-06, "epoch": 1.750534568781183, "percentage": 35.09, "elapsed_time": "1:07:20", "remaining_time": "2:04:35", "throughput": "503.21", "total_tokens": 2033136} -{"current_steps": 308, "total_steps": 875, "loss": 0.0992, "learning_rate": 3.673233497451541e-06, "epoch": 1.7562366357804704, "percentage": 35.2, "elapsed_time": "1:07:33", "remaining_time": "2:04:22", "throughput": "503.19", "total_tokens": 2039680} -{"current_steps": 309, "total_steps": 875, "loss": 0.0325, "learning_rate": 3.6652079760328045e-06, "epoch": 1.7619387027797577, "percentage": 35.31, "elapsed_time": "1:07:46", "remaining_time": "2:04:08", "throughput": "503.14", "total_tokens": 2046096} -{"current_steps": 310, "total_steps": 875, "loss": 0.0403, "learning_rate": 3.6571670847331802e-06, "epoch": 1.767640769779045, "percentage": 35.43, "elapsed_time": "1:07:59", "remaining_time": "2:03:55", "throughput": "503.07", "total_tokens": 2052432} -{"current_steps": 311, "total_steps": 875, "loss": 0.0619, "learning_rate": 3.6491109296174604e-06, "epoch": 1.7733428367783322, "percentage": 35.54, "elapsed_time": "1:08:12", "remaining_time": "2:03:42", "throughput": "503.02", "total_tokens": 2058848} -{"current_steps": 312, "total_steps": 875, "loss": 0.0609, "learning_rate": 3.6410396169517763e-06, "epoch": 1.7790449037776193, "percentage": 35.66, "elapsed_time": "1:08:26", "remaining_time": "2:03:29", "throughput": "502.99", "total_tokens": 2065344} -{"current_steps": 313, "total_steps": 875, "loss": 0.0523, "learning_rate": 3.632953253202199e-06, "epoch": 1.7847469707769066, "percentage": 35.77, "elapsed_time": "1:08:39", "remaining_time": "2:03:16", "throughput": "502.93", "total_tokens": 2071696} -{"current_steps": 314, "total_steps": 875, "loss": 0.0481, "learning_rate": 3.624851945033332e-06, "epoch": 1.790449037776194, "percentage": 35.89, "elapsed_time": "1:08:52", "remaining_time": "2:03:03", "throughput": "503.03", "total_tokens": 2078736} -{"current_steps": 315, "total_steps": 875, "loss": 0.0353, "learning_rate": 3.6167357993069075e-06, "epoch": 1.7961511047754812, "percentage": 36.0, "elapsed_time": "1:09:05", "remaining_time": "2:02:49", "throughput": "502.96", "total_tokens": 2085088} -{"current_steps": 316, "total_steps": 875, "loss": 0.0408, "learning_rate": 3.608604923080373e-06, "epoch": 1.8018531717747683, "percentage": 36.11, "elapsed_time": "1:09:18", "remaining_time": "2:02:36", "throughput": "502.92", "total_tokens": 2091504} -{"current_steps": 317, "total_steps": 875, "loss": 0.0368, "learning_rate": 3.6004594236054837e-06, "epoch": 1.8075552387740554, "percentage": 36.23, "elapsed_time": "1:09:31", "remaining_time": "2:02:23", "throughput": "502.88", "total_tokens": 2097984} -{"current_steps": 318, "total_steps": 875, "loss": 0.0614, "learning_rate": 3.592299408326883e-06, "epoch": 1.8132573057733428, "percentage": 36.34, "elapsed_time": "1:09:45", "remaining_time": "2:02:10", "throughput": "502.87", "total_tokens": 2104560} -{"current_steps": 319, "total_steps": 875, "loss": 0.0328, "learning_rate": 3.584124984880689e-06, "epoch": 1.81895937277263, "percentage": 36.46, "elapsed_time": "1:09:58", "remaining_time": "2:01:57", "throughput": "502.79", "total_tokens": 2110832} -{"current_steps": 320, "total_steps": 875, "loss": 0.0658, "learning_rate": 3.5759362610930733e-06, "epoch": 1.8246614397719174, "percentage": 36.57, "elapsed_time": "1:10:11", "remaining_time": "2:01:44", "throughput": "502.69", "total_tokens": 2117008} -{"current_steps": 321, "total_steps": 875, "loss": 0.0491, "learning_rate": 3.5677333449788376e-06, "epoch": 1.8303635067712045, "percentage": 36.69, "elapsed_time": "1:10:24", "remaining_time": "2:01:30", "throughput": "502.61", "total_tokens": 2123312} -{"current_steps": 322, "total_steps": 875, "loss": 0.0411, "learning_rate": 3.5595163447399912e-06, "epoch": 1.8360655737704918, "percentage": 36.8, "elapsed_time": "1:10:37", "remaining_time": "2:01:17", "throughput": "502.60", "total_tokens": 2129872} -{"current_steps": 323, "total_steps": 875, "loss": 0.0281, "learning_rate": 3.551285368764321e-06, "epoch": 1.841767640769779, "percentage": 36.91, "elapsed_time": "1:10:50", "remaining_time": "2:01:04", "throughput": "502.65", "total_tokens": 2136688} -{"current_steps": 324, "total_steps": 875, "loss": 0.0319, "learning_rate": 3.5430405256239653e-06, "epoch": 1.8474697077690663, "percentage": 37.03, "elapsed_time": "1:11:04", "remaining_time": "2:00:51", "throughput": "502.62", "total_tokens": 2143184} -{"current_steps": 325, "total_steps": 875, "loss": 0.0919, "learning_rate": 3.5347819240739783e-06, "epoch": 1.8531717747683536, "percentage": 37.14, "elapsed_time": "1:11:17", "remaining_time": "2:00:38", "throughput": "502.60", "total_tokens": 2149712} -{"current_steps": 326, "total_steps": 875, "loss": 0.069, "learning_rate": 3.5265096730508972e-06, "epoch": 1.858873841767641, "percentage": 37.26, "elapsed_time": "1:11:30", "remaining_time": "2:00:25", "throughput": "502.63", "total_tokens": 2156432} -{"current_steps": 327, "total_steps": 875, "loss": 0.0615, "learning_rate": 3.5182238816713055e-06, "epoch": 1.864575908766928, "percentage": 37.37, "elapsed_time": "1:11:43", "remaining_time": "2:00:11", "throughput": "502.64", "total_tokens": 2163088} -{"current_steps": 328, "total_steps": 875, "loss": 0.046, "learning_rate": 3.509924659230392e-06, "epoch": 1.8702779757662151, "percentage": 37.49, "elapsed_time": "1:11:56", "remaining_time": "1:59:58", "throughput": "502.63", "total_tokens": 2169664} -{"current_steps": 329, "total_steps": 875, "loss": 0.0317, "learning_rate": 3.5016121152005123e-06, "epoch": 1.8759800427655025, "percentage": 37.6, "elapsed_time": "1:12:09", "remaining_time": "1:59:45", "throughput": "502.63", "total_tokens": 2176272} -{"current_steps": 330, "total_steps": 875, "loss": 0.0614, "learning_rate": 3.4932863592297393e-06, "epoch": 1.8816821097647898, "percentage": 37.71, "elapsed_time": "1:12:22", "remaining_time": "1:59:32", "throughput": "502.60", "total_tokens": 2182736} -{"current_steps": 331, "total_steps": 875, "loss": 0.0651, "learning_rate": 3.4849475011404242e-06, "epoch": 1.887384176764077, "percentage": 37.83, "elapsed_time": "1:12:36", "remaining_time": "1:59:19", "throughput": "502.70", "total_tokens": 2189824} -{"current_steps": 332, "total_steps": 875, "loss": 0.0283, "learning_rate": 3.4765956509277416e-06, "epoch": 1.8930862437633642, "percentage": 37.94, "elapsed_time": "1:12:49", "remaining_time": "1:59:06", "throughput": "502.70", "total_tokens": 2196400} -{"current_steps": 333, "total_steps": 875, "loss": 0.0406, "learning_rate": 3.4682309187582425e-06, "epoch": 1.8987883107626513, "percentage": 38.06, "elapsed_time": "1:13:02", "remaining_time": "1:58:52", "throughput": "502.67", "total_tokens": 2202896} -{"current_steps": 334, "total_steps": 875, "loss": 0.029, "learning_rate": 3.459853414968398e-06, "epoch": 1.9044903777619386, "percentage": 38.17, "elapsed_time": "1:13:15", "remaining_time": "1:58:39", "throughput": "502.68", "total_tokens": 2209552} -{"current_steps": 335, "total_steps": 875, "loss": 0.0202, "learning_rate": 3.451463250063146e-06, "epoch": 1.910192444761226, "percentage": 38.29, "elapsed_time": "1:13:28", "remaining_time": "1:58:26", "throughput": "502.62", "total_tokens": 2215920} -{"current_steps": 336, "total_steps": 875, "loss": 0.0246, "learning_rate": 3.443060534714434e-06, "epoch": 1.9158945117605133, "percentage": 38.4, "elapsed_time": "1:13:41", "remaining_time": "1:58:13", "throughput": "502.59", "total_tokens": 2222384} -{"current_steps": 337, "total_steps": 875, "loss": 0.0755, "learning_rate": 3.4346453797597577e-06, "epoch": 1.9215965787598004, "percentage": 38.51, "elapsed_time": "1:13:54", "remaining_time": "1:58:00", "throughput": "502.56", "total_tokens": 2228864} -{"current_steps": 338, "total_steps": 875, "loss": 0.0162, "learning_rate": 3.4262178962006994e-06, "epoch": 1.9272986457590877, "percentage": 38.63, "elapsed_time": "1:14:08", "remaining_time": "1:57:47", "throughput": "502.53", "total_tokens": 2235328} -{"current_steps": 339, "total_steps": 875, "loss": 0.0127, "learning_rate": 3.4177781952014646e-06, "epoch": 1.9330007127583748, "percentage": 38.74, "elapsed_time": "1:14:21", "remaining_time": "1:57:33", "throughput": "502.49", "total_tokens": 2241760} -{"current_steps": 340, "total_steps": 875, "loss": 0.0225, "learning_rate": 3.409326388087414e-06, "epoch": 1.9387027797576621, "percentage": 38.86, "elapsed_time": "1:14:34", "remaining_time": "1:57:20", "throughput": "502.40", "total_tokens": 2247968} -{"current_steps": 341, "total_steps": 875, "loss": 0.0556, "learning_rate": 3.400862586343597e-06, "epoch": 1.9444048467569495, "percentage": 38.97, "elapsed_time": "1:14:47", "remaining_time": "1:57:07", "throughput": "502.39", "total_tokens": 2254528} -{"current_steps": 342, "total_steps": 875, "loss": 0.0282, "learning_rate": 3.3923869016132816e-06, "epoch": 1.9501069137562368, "percentage": 39.09, "elapsed_time": "1:15:00", "remaining_time": "1:56:54", "throughput": "502.34", "total_tokens": 2260928} -{"current_steps": 343, "total_steps": 875, "loss": 0.0222, "learning_rate": 3.3838994456964774e-06, "epoch": 1.955808980755524, "percentage": 39.2, "elapsed_time": "1:15:13", "remaining_time": "1:56:41", "throughput": "502.45", "total_tokens": 2268016} -{"current_steps": 344, "total_steps": 875, "loss": 0.0387, "learning_rate": 3.375400330548466e-06, "epoch": 1.961511047754811, "percentage": 39.31, "elapsed_time": "1:15:27", "remaining_time": "1:56:27", "throughput": "502.44", "total_tokens": 2274592} -{"current_steps": 345, "total_steps": 875, "loss": 0.0589, "learning_rate": 3.3668896682783216e-06, "epoch": 1.9672131147540983, "percentage": 39.43, "elapsed_time": "1:15:40", "remaining_time": "1:56:14", "throughput": "502.45", "total_tokens": 2281216} -{"current_steps": 346, "total_steps": 875, "loss": 0.1223, "learning_rate": 3.358367571147433e-06, "epoch": 1.9729151817533856, "percentage": 39.54, "elapsed_time": "1:15:53", "remaining_time": "1:56:01", "throughput": "502.41", "total_tokens": 2287680} -{"current_steps": 347, "total_steps": 875, "loss": 0.0546, "learning_rate": 3.3498341515680216e-06, "epoch": 1.978617248752673, "percentage": 39.66, "elapsed_time": "1:16:06", "remaining_time": "1:55:48", "throughput": "502.48", "total_tokens": 2294592} -{"current_steps": 348, "total_steps": 875, "loss": 0.0686, "learning_rate": 3.3412895221016605e-06, "epoch": 1.98431931575196, "percentage": 39.77, "elapsed_time": "1:16:19", "remaining_time": "1:55:35", "throughput": "502.46", "total_tokens": 2301120} -{"current_steps": 349, "total_steps": 875, "loss": 0.0316, "learning_rate": 3.3327337954577893e-06, "epoch": 1.9900213827512472, "percentage": 39.89, "elapsed_time": "1:16:32", "remaining_time": "1:55:22", "throughput": "502.42", "total_tokens": 2307552} -{"current_steps": 350, "total_steps": 875, "loss": 0.036, "learning_rate": 3.324167084492226e-06, "epoch": 1.9957234497505345, "percentage": 40.0, "elapsed_time": "1:16:45", "remaining_time": "1:55:08", "throughput": "502.40", "total_tokens": 2314048} -{"current_steps": 351, "total_steps": 875, "loss": 0.0681, "learning_rate": 3.315589502205678e-06, "epoch": 2.001425516749822, "percentage": 40.11, "elapsed_time": "1:16:59", "remaining_time": "1:54:55", "throughput": "502.46", "total_tokens": 2320912} -{"current_steps": 352, "total_steps": 875, "loss": 0.0133, "learning_rate": 3.3070011617422564e-06, "epoch": 2.007127583749109, "percentage": 40.23, "elapsed_time": "1:17:12", "remaining_time": "1:54:42", "throughput": "502.45", "total_tokens": 2327488} -{"current_steps": 353, "total_steps": 875, "loss": 0.0086, "learning_rate": 3.2984021763879757e-06, "epoch": 2.0128296507483965, "percentage": 40.34, "elapsed_time": "1:17:25", "remaining_time": "1:54:29", "throughput": "502.52", "total_tokens": 2334432} -{"current_steps": 354, "total_steps": 875, "loss": 0.0066, "learning_rate": 3.2897926595692663e-06, "epoch": 2.0185317177476834, "percentage": 40.46, "elapsed_time": "1:17:38", "remaining_time": "1:54:16", "throughput": "502.54", "total_tokens": 2341136} -{"current_steps": 355, "total_steps": 875, "loss": 0.0137, "learning_rate": 3.281172724851476e-06, "epoch": 2.0242337847469707, "percentage": 40.57, "elapsed_time": "1:17:51", "remaining_time": "1:54:03", "throughput": "502.53", "total_tokens": 2347680} -{"current_steps": 356, "total_steps": 875, "loss": 0.0104, "learning_rate": 3.272542485937369e-06, "epoch": 2.029935851746258, "percentage": 40.69, "elapsed_time": "1:18:04", "remaining_time": "1:53:49", "throughput": "502.54", "total_tokens": 2354352} -{"current_steps": 357, "total_steps": 875, "loss": 0.029, "learning_rate": 3.2639020566656316e-06, "epoch": 2.0356379187455453, "percentage": 40.8, "elapsed_time": "1:18:18", "remaining_time": "1:53:36", "throughput": "502.53", "total_tokens": 2360912} -{"current_steps": 358, "total_steps": 875, "loss": 0.0628, "learning_rate": 3.2552515510093674e-06, "epoch": 2.0413399857448327, "percentage": 40.91, "elapsed_time": "1:18:31", "remaining_time": "1:53:23", "throughput": "502.53", "total_tokens": 2367552} -{"current_steps": 359, "total_steps": 875, "loss": 0.0492, "learning_rate": 3.2465910830745926e-06, "epoch": 2.0470420527441195, "percentage": 41.03, "elapsed_time": "1:18:44", "remaining_time": "1:53:10", "throughput": "502.47", "total_tokens": 2373888} -{"current_steps": 360, "total_steps": 875, "loss": 0.0217, "learning_rate": 3.2379207670987352e-06, "epoch": 2.052744119743407, "percentage": 41.14, "elapsed_time": "1:18:57", "remaining_time": "1:52:57", "throughput": "502.48", "total_tokens": 2380528} -{"current_steps": 361, "total_steps": 875, "loss": 0.01, "learning_rate": 3.2292407174491224e-06, "epoch": 2.058446186742694, "percentage": 41.26, "elapsed_time": "1:19:10", "remaining_time": "1:52:44", "throughput": "502.58", "total_tokens": 2387584} -{"current_steps": 362, "total_steps": 875, "loss": 0.0193, "learning_rate": 3.2205510486214783e-06, "epoch": 2.0641482537419815, "percentage": 41.37, "elapsed_time": "1:19:23", "remaining_time": "1:52:30", "throughput": "502.65", "total_tokens": 2394560} -{"current_steps": 363, "total_steps": 875, "loss": 0.016, "learning_rate": 3.211851875238408e-06, "epoch": 2.069850320741269, "percentage": 41.49, "elapsed_time": "1:19:36", "remaining_time": "1:52:17", "throughput": "502.67", "total_tokens": 2401232} -{"current_steps": 364, "total_steps": 875, "loss": 0.0025, "learning_rate": 3.2031433120478894e-06, "epoch": 2.075552387740556, "percentage": 41.6, "elapsed_time": "1:19:50", "remaining_time": "1:52:04", "throughput": "502.68", "total_tokens": 2407888} -{"current_steps": 365, "total_steps": 875, "loss": 0.002, "learning_rate": 3.1944254739217584e-06, "epoch": 2.081254454739843, "percentage": 41.71, "elapsed_time": "1:20:03", "remaining_time": "1:51:51", "throughput": "502.63", "total_tokens": 2414288} -{"current_steps": 366, "total_steps": 875, "loss": 0.0113, "learning_rate": 3.1856984758541924e-06, "epoch": 2.0869565217391304, "percentage": 41.83, "elapsed_time": "1:20:16", "remaining_time": "1:51:38", "throughput": "502.61", "total_tokens": 2420768} -{"current_steps": 367, "total_steps": 875, "loss": 0.0047, "learning_rate": 3.176962432960197e-06, "epoch": 2.0926585887384177, "percentage": 41.94, "elapsed_time": "1:20:29", "remaining_time": "1:51:25", "throughput": "502.59", "total_tokens": 2427280} -{"current_steps": 368, "total_steps": 875, "loss": 0.0186, "learning_rate": 3.1682174604740808e-06, "epoch": 2.098360655737705, "percentage": 42.06, "elapsed_time": "1:20:42", "remaining_time": "1:51:11", "throughput": "502.57", "total_tokens": 2433824} -{"current_steps": 369, "total_steps": 875, "loss": 0.0033, "learning_rate": 3.159463673747945e-06, "epoch": 2.1040627227369924, "percentage": 42.17, "elapsed_time": "1:20:55", "remaining_time": "1:50:58", "throughput": "502.57", "total_tokens": 2440416} -{"current_steps": 370, "total_steps": 875, "loss": 0.0344, "learning_rate": 3.150701188250153e-06, "epoch": 2.1097647897362792, "percentage": 42.29, "elapsed_time": "1:21:09", "remaining_time": "1:50:45", "throughput": "502.55", "total_tokens": 2446928} -{"current_steps": 371, "total_steps": 875, "loss": 0.0362, "learning_rate": 3.141930119563812e-06, "epoch": 2.1154668567355666, "percentage": 42.4, "elapsed_time": "1:21:22", "remaining_time": "1:50:32", "throughput": "502.58", "total_tokens": 2453664} -{"current_steps": 372, "total_steps": 875, "loss": 0.0009, "learning_rate": 3.133150583385247e-06, "epoch": 2.121168923734854, "percentage": 42.51, "elapsed_time": "1:21:35", "remaining_time": "1:50:19", "throughput": "502.57", "total_tokens": 2460256} -{"current_steps": 373, "total_steps": 875, "loss": 0.0317, "learning_rate": 3.1243626955224766e-06, "epoch": 2.126870990734141, "percentage": 42.63, "elapsed_time": "1:21:48", "remaining_time": "1:50:06", "throughput": "502.58", "total_tokens": 2466912} -{"current_steps": 374, "total_steps": 875, "loss": 0.0158, "learning_rate": 3.1155665718936806e-06, "epoch": 2.1325730577334285, "percentage": 42.74, "elapsed_time": "1:22:01", "remaining_time": "1:49:52", "throughput": "502.66", "total_tokens": 2473936} -{"current_steps": 375, "total_steps": 875, "loss": 0.0154, "learning_rate": 3.106762328525677e-06, "epoch": 2.1382751247327154, "percentage": 42.86, "elapsed_time": "1:22:14", "remaining_time": "1:49:39", "throughput": "502.68", "total_tokens": 2480640} -{"current_steps": 376, "total_steps": 875, "loss": 0.0178, "learning_rate": 3.0979500815523865e-06, "epoch": 2.1439771917320027, "percentage": 42.97, "elapsed_time": "1:22:27", "remaining_time": "1:49:26", "throughput": "502.66", "total_tokens": 2487152} -{"current_steps": 377, "total_steps": 875, "loss": 0.0686, "learning_rate": 3.089129947213305e-06, "epoch": 2.14967925873129, "percentage": 43.09, "elapsed_time": "1:22:41", "remaining_time": "1:49:13", "throughput": "502.64", "total_tokens": 2493664} -{"current_steps": 378, "total_steps": 875, "loss": 0.0289, "learning_rate": 3.0803020418519666e-06, "epoch": 2.1553813257305774, "percentage": 43.2, "elapsed_time": "1:22:54", "remaining_time": "1:49:00", "throughput": "502.66", "total_tokens": 2500336} -{"current_steps": 379, "total_steps": 875, "loss": 0.0122, "learning_rate": 3.071466481914409e-06, "epoch": 2.1610833927298647, "percentage": 43.31, "elapsed_time": "1:23:07", "remaining_time": "1:48:47", "throughput": "502.74", "total_tokens": 2507360} -{"current_steps": 380, "total_steps": 875, "loss": 0.0258, "learning_rate": 3.0626233839476434e-06, "epoch": 2.1667854597291516, "percentage": 43.43, "elapsed_time": "1:23:20", "remaining_time": "1:48:33", "throughput": "502.72", "total_tokens": 2513872} -{"current_steps": 381, "total_steps": 875, "loss": 0.0033, "learning_rate": 3.053772864598108e-06, "epoch": 2.172487526728439, "percentage": 43.54, "elapsed_time": "1:23:33", "remaining_time": "1:48:20", "throughput": "502.66", "total_tokens": 2520208} -{"current_steps": 382, "total_steps": 875, "loss": 0.01, "learning_rate": 3.0449150406101367e-06, "epoch": 2.1781895937277262, "percentage": 43.66, "elapsed_time": "1:23:46", "remaining_time": "1:48:07", "throughput": "502.65", "total_tokens": 2526752} -{"current_steps": 383, "total_steps": 875, "loss": 0.0185, "learning_rate": 3.0360500288244155e-06, "epoch": 2.1838916607270136, "percentage": 43.77, "elapsed_time": "1:24:00", "remaining_time": "1:47:54", "throughput": "502.53", "total_tokens": 2532784} -{"current_steps": 384, "total_steps": 875, "loss": 0.0171, "learning_rate": 3.0271779461764427e-06, "epoch": 2.189593727726301, "percentage": 43.89, "elapsed_time": "1:24:13", "remaining_time": "1:47:41", "throughput": "502.55", "total_tokens": 2539456} -{"current_steps": 385, "total_steps": 875, "loss": 0.0049, "learning_rate": 3.018298909694986e-06, "epoch": 2.1952957947255882, "percentage": 44.0, "elapsed_time": "1:24:26", "remaining_time": "1:47:28", "throughput": "502.56", "total_tokens": 2546144} -{"current_steps": 386, "total_steps": 875, "loss": 0.0044, "learning_rate": 3.00941303650054e-06, "epoch": 2.200997861724875, "percentage": 44.11, "elapsed_time": "1:24:39", "remaining_time": "1:47:14", "throughput": "502.56", "total_tokens": 2552768} -{"current_steps": 387, "total_steps": 875, "loss": 0.0218, "learning_rate": 3.0005204438037767e-06, "epoch": 2.2066999287241624, "percentage": 44.23, "elapsed_time": "1:24:52", "remaining_time": "1:47:01", "throughput": "502.54", "total_tokens": 2559248} -{"current_steps": 388, "total_steps": 875, "loss": 0.026, "learning_rate": 2.991621248904007e-06, "epoch": 2.2124019957234498, "percentage": 44.34, "elapsed_time": "1:25:05", "remaining_time": "1:46:48", "throughput": "502.59", "total_tokens": 2566096} -{"current_steps": 389, "total_steps": 875, "loss": 0.0037, "learning_rate": 2.9827155691876266e-06, "epoch": 2.218104062722737, "percentage": 44.46, "elapsed_time": "1:25:18", "remaining_time": "1:46:35", "throughput": "502.63", "total_tokens": 2572944} -{"current_steps": 390, "total_steps": 875, "loss": 0.0031, "learning_rate": 2.973803522126571e-06, "epoch": 2.2238061297220244, "percentage": 44.57, "elapsed_time": "1:25:32", "remaining_time": "1:46:22", "throughput": "502.64", "total_tokens": 2579600} -{"current_steps": 391, "total_steps": 875, "loss": 0.0188, "learning_rate": 2.964885225276767e-06, "epoch": 2.2295081967213113, "percentage": 44.69, "elapsed_time": "1:25:45", "remaining_time": "1:46:09", "throughput": "502.72", "total_tokens": 2586624} -{"current_steps": 392, "total_steps": 875, "loss": 0.0302, "learning_rate": 2.9559607962765773e-06, "epoch": 2.2352102637205986, "percentage": 44.8, "elapsed_time": "1:25:58", "remaining_time": "1:45:55", "throughput": "502.79", "total_tokens": 2593600} -{"current_steps": 393, "total_steps": 875, "loss": 0.0205, "learning_rate": 2.947030352845255e-06, "epoch": 2.240912330719886, "percentage": 44.91, "elapsed_time": "1:26:11", "remaining_time": "1:45:42", "throughput": "502.79", "total_tokens": 2600224} -{"current_steps": 394, "total_steps": 875, "loss": 0.0347, "learning_rate": 2.9380940127813834e-06, "epoch": 2.2466143977191733, "percentage": 45.03, "elapsed_time": "1:26:24", "remaining_time": "1:45:29", "throughput": "502.77", "total_tokens": 2606704} -{"current_steps": 395, "total_steps": 875, "loss": 0.065, "learning_rate": 2.9291518939613317e-06, "epoch": 2.2523164647184606, "percentage": 45.14, "elapsed_time": "1:26:37", "remaining_time": "1:45:16", "throughput": "502.67", "total_tokens": 2612816} -{"current_steps": 396, "total_steps": 875, "loss": 0.0662, "learning_rate": 2.9202041143376895e-06, "epoch": 2.258018531717748, "percentage": 45.26, "elapsed_time": "1:26:51", "remaining_time": "1:45:03", "throughput": "502.75", "total_tokens": 2619840} -{"current_steps": 397, "total_steps": 875, "loss": 0.0348, "learning_rate": 2.9112507919377213e-06, "epoch": 2.263720598717035, "percentage": 45.37, "elapsed_time": "1:27:04", "remaining_time": "1:44:50", "throughput": "502.74", "total_tokens": 2626400} -{"current_steps": 398, "total_steps": 875, "loss": 0.0105, "learning_rate": 2.9022920448618e-06, "epoch": 2.269422665716322, "percentage": 45.49, "elapsed_time": "1:27:17", "remaining_time": "1:44:36", "throughput": "502.72", "total_tokens": 2632928} -{"current_steps": 399, "total_steps": 875, "loss": 0.0478, "learning_rate": 2.893327991281857e-06, "epoch": 2.2751247327156094, "percentage": 45.6, "elapsed_time": "1:27:30", "remaining_time": "1:44:23", "throughput": "502.71", "total_tokens": 2639488} -{"current_steps": 400, "total_steps": 875, "loss": 0.0048, "learning_rate": 2.8843587494398177e-06, "epoch": 2.2808267997148968, "percentage": 45.71, "elapsed_time": "1:27:43", "remaining_time": "1:44:10", "throughput": "502.64", "total_tokens": 2645696} -{"current_steps": 401, "total_steps": 875, "loss": 0.0416, "learning_rate": 2.8753844376460462e-06, "epoch": 2.2865288667141836, "percentage": 45.83, "elapsed_time": "1:27:56", "remaining_time": "1:43:57", "throughput": "502.72", "total_tokens": 2652768} -{"current_steps": 402, "total_steps": 875, "loss": 0.009, "learning_rate": 2.8664051742777803e-06, "epoch": 2.292230933713471, "percentage": 45.94, "elapsed_time": "1:28:09", "remaining_time": "1:43:44", "throughput": "502.76", "total_tokens": 2659600} -{"current_steps": 403, "total_steps": 875, "loss": 0.0145, "learning_rate": 2.857421077777576e-06, "epoch": 2.2979330007127583, "percentage": 46.06, "elapsed_time": "1:28:23", "remaining_time": "1:43:31", "throughput": "502.84", "total_tokens": 2666608} -{"current_steps": 404, "total_steps": 875, "loss": 0.0239, "learning_rate": 2.8484322666517373e-06, "epoch": 2.3036350677120456, "percentage": 46.17, "elapsed_time": "1:28:36", "remaining_time": "1:43:17", "throughput": "502.87", "total_tokens": 2673408} -{"current_steps": 405, "total_steps": 875, "loss": 0.0151, "learning_rate": 2.83943885946876e-06, "epoch": 2.309337134711333, "percentage": 46.29, "elapsed_time": "1:28:49", "remaining_time": "1:43:04", "throughput": "502.84", "total_tokens": 2679824} -{"current_steps": 406, "total_steps": 875, "loss": 0.0597, "learning_rate": 2.8304409748577655e-06, "epoch": 2.3150392017106203, "percentage": 46.4, "elapsed_time": "1:29:02", "remaining_time": "1:42:51", "throughput": "502.87", "total_tokens": 2686608} -{"current_steps": 407, "total_steps": 875, "loss": 0.0213, "learning_rate": 2.821438731506933e-06, "epoch": 2.320741268709907, "percentage": 46.51, "elapsed_time": "1:29:15", "remaining_time": "1:42:38", "throughput": "502.96", "total_tokens": 2693728} -{"current_steps": 408, "total_steps": 875, "loss": 0.0197, "learning_rate": 2.8124322481619388e-06, "epoch": 2.3264433357091945, "percentage": 46.63, "elapsed_time": "1:29:28", "remaining_time": "1:42:25", "throughput": "502.94", "total_tokens": 2700240} -{"current_steps": 409, "total_steps": 875, "loss": 0.0435, "learning_rate": 2.803421643624386e-06, "epoch": 2.332145402708482, "percentage": 46.74, "elapsed_time": "1:29:42", "remaining_time": "1:42:12", "throughput": "502.90", "total_tokens": 2706592} -{"current_steps": 410, "total_steps": 875, "loss": 0.0127, "learning_rate": 2.7944070367502404e-06, "epoch": 2.337847469707769, "percentage": 46.86, "elapsed_time": "1:29:55", "remaining_time": "1:41:58", "throughput": "502.85", "total_tokens": 2712960} -{"current_steps": 411, "total_steps": 875, "loss": 0.0123, "learning_rate": 2.7853885464482594e-06, "epoch": 2.3435495367070565, "percentage": 46.97, "elapsed_time": "1:30:08", "remaining_time": "1:41:45", "throughput": "502.86", "total_tokens": 2719648} -{"current_steps": 412, "total_steps": 875, "loss": 0.0331, "learning_rate": 2.7763662916784285e-06, "epoch": 2.3492516037063433, "percentage": 47.09, "elapsed_time": "1:30:21", "remaining_time": "1:41:32", "throughput": "502.94", "total_tokens": 2726672} -{"current_steps": 413, "total_steps": 875, "loss": 0.0507, "learning_rate": 2.767340391450384e-06, "epoch": 2.3549536707056307, "percentage": 47.2, "elapsed_time": "1:30:34", "remaining_time": "1:41:19", "throughput": "502.98", "total_tokens": 2733520} -{"current_steps": 414, "total_steps": 875, "loss": 0.0447, "learning_rate": 2.758310964821855e-06, "epoch": 2.360655737704918, "percentage": 47.31, "elapsed_time": "1:30:47", "remaining_time": "1:41:06", "throughput": "502.99", "total_tokens": 2740208} -{"current_steps": 415, "total_steps": 875, "loss": 0.0252, "learning_rate": 2.7492781308970805e-06, "epoch": 2.3663578047042053, "percentage": 47.43, "elapsed_time": "1:31:00", "remaining_time": "1:40:53", "throughput": "502.95", "total_tokens": 2746560} -{"current_steps": 416, "total_steps": 875, "loss": 0.0117, "learning_rate": 2.7402420088252472e-06, "epoch": 2.3720598717034926, "percentage": 47.54, "elapsed_time": "1:31:14", "remaining_time": "1:40:39", "throughput": "502.85", "total_tokens": 2752672} -{"current_steps": 417, "total_steps": 875, "loss": 0.0149, "learning_rate": 2.7312027177989132e-06, "epoch": 2.37776193870278, "percentage": 47.66, "elapsed_time": "1:31:27", "remaining_time": "1:40:26", "throughput": "502.83", "total_tokens": 2759168} -{"current_steps": 418, "total_steps": 875, "loss": 0.0038, "learning_rate": 2.7221603770524374e-06, "epoch": 2.383464005702067, "percentage": 47.77, "elapsed_time": "1:31:40", "remaining_time": "1:40:13", "throughput": "502.81", "total_tokens": 2765680} -{"current_steps": 419, "total_steps": 875, "loss": 0.0374, "learning_rate": 2.713115105860407e-06, "epoch": 2.389166072701354, "percentage": 47.89, "elapsed_time": "1:31:53", "remaining_time": "1:40:00", "throughput": "502.85", "total_tokens": 2772480} -{"current_steps": 420, "total_steps": 875, "loss": 0.0246, "learning_rate": 2.7040670235360643e-06, "epoch": 2.3948681397006415, "percentage": 48.0, "elapsed_time": "1:32:06", "remaining_time": "1:39:47", "throughput": "502.84", "total_tokens": 2779072} -{"current_steps": 421, "total_steps": 875, "loss": 0.0363, "learning_rate": 2.6950162494297316e-06, "epoch": 2.400570206699929, "percentage": 48.11, "elapsed_time": "1:32:19", "remaining_time": "1:39:34", "throughput": "502.81", "total_tokens": 2785536} -{"current_steps": 422, "total_steps": 875, "loss": 0.0197, "learning_rate": 2.6859629029272365e-06, "epoch": 2.406272273699216, "percentage": 48.23, "elapsed_time": "1:32:33", "remaining_time": "1:39:20", "throughput": "502.82", "total_tokens": 2792192} -{"current_steps": 423, "total_steps": 875, "loss": 0.0113, "learning_rate": 2.676907103448341e-06, "epoch": 2.411974340698503, "percentage": 48.34, "elapsed_time": "1:32:46", "remaining_time": "1:39:07", "throughput": "502.86", "total_tokens": 2798992} -{"current_steps": 424, "total_steps": 875, "loss": 0.0255, "learning_rate": 2.667848970445161e-06, "epoch": 2.4176764076977904, "percentage": 48.46, "elapsed_time": "1:32:59", "remaining_time": "1:38:54", "throughput": "502.81", "total_tokens": 2805360} -{"current_steps": 425, "total_steps": 875, "loss": 0.0184, "learning_rate": 2.658788623400595e-06, "epoch": 2.4233784746970777, "percentage": 48.57, "elapsed_time": "1:33:12", "remaining_time": "1:38:41", "throughput": "502.82", "total_tokens": 2812000} -{"current_steps": 426, "total_steps": 875, "loss": 0.0397, "learning_rate": 2.6497261818267438e-06, "epoch": 2.429080541696365, "percentage": 48.69, "elapsed_time": "1:33:25", "remaining_time": "1:38:28", "throughput": "502.84", "total_tokens": 2818752} -{"current_steps": 427, "total_steps": 875, "loss": 0.0242, "learning_rate": 2.6406617652633405e-06, "epoch": 2.4347826086956523, "percentage": 48.8, "elapsed_time": "1:33:38", "remaining_time": "1:38:15", "throughput": "502.89", "total_tokens": 2825616} -{"current_steps": 428, "total_steps": 875, "loss": 0.0168, "learning_rate": 2.6315954932761645e-06, "epoch": 2.4404846756949397, "percentage": 48.91, "elapsed_time": "1:33:51", "remaining_time": "1:38:01", "throughput": "502.91", "total_tokens": 2832384} -{"current_steps": 429, "total_steps": 875, "loss": 0.0034, "learning_rate": 2.6225274854554733e-06, "epoch": 2.4461867426942265, "percentage": 49.03, "elapsed_time": "1:34:05", "remaining_time": "1:37:48", "throughput": "502.94", "total_tokens": 2839152} -{"current_steps": 430, "total_steps": 875, "loss": 0.0063, "learning_rate": 2.61345786141442e-06, "epoch": 2.451888809693514, "percentage": 49.14, "elapsed_time": "1:34:18", "remaining_time": "1:37:35", "throughput": "502.95", "total_tokens": 2845856} -{"current_steps": 431, "total_steps": 875, "loss": 0.0229, "learning_rate": 2.6043867407874774e-06, "epoch": 2.457590876692801, "percentage": 49.26, "elapsed_time": "1:34:31", "remaining_time": "1:37:22", "throughput": "503.00", "total_tokens": 2852736} -{"current_steps": 432, "total_steps": 875, "loss": 0.0047, "learning_rate": 2.5953142432288573e-06, "epoch": 2.4632929436920885, "percentage": 49.37, "elapsed_time": "1:34:44", "remaining_time": "1:37:09", "throughput": "503.02", "total_tokens": 2859456} -{"current_steps": 433, "total_steps": 875, "loss": 0.0271, "learning_rate": 2.5862404884109366e-06, "epoch": 2.4689950106913754, "percentage": 49.49, "elapsed_time": "1:34:57", "remaining_time": "1:36:56", "throughput": "503.01", "total_tokens": 2866016} -{"current_steps": 434, "total_steps": 875, "loss": 0.0041, "learning_rate": 2.5771655960226753e-06, "epoch": 2.4746970776906627, "percentage": 49.6, "elapsed_time": "1:35:10", "remaining_time": "1:36:43", "throughput": "502.98", "total_tokens": 2872448} -{"current_steps": 435, "total_steps": 875, "loss": 0.015, "learning_rate": 2.568089685768038e-06, "epoch": 2.48039914468995, "percentage": 49.71, "elapsed_time": "1:35:24", "remaining_time": "1:36:29", "throughput": "502.98", "total_tokens": 2879088} -{"current_steps": 436, "total_steps": 875, "loss": 0.042, "learning_rate": 2.559012877364417e-06, "epoch": 2.4861012116892374, "percentage": 49.83, "elapsed_time": "1:35:37", "remaining_time": "1:36:16", "throughput": "502.93", "total_tokens": 2885408} -{"current_steps": 437, "total_steps": 875, "loss": 0.0099, "learning_rate": 2.54993529054105e-06, "epoch": 2.4918032786885247, "percentage": 49.94, "elapsed_time": "1:35:50", "remaining_time": "1:36:03", "throughput": "502.91", "total_tokens": 2891936} -{"current_steps": 438, "total_steps": 875, "loss": 0.0215, "learning_rate": 2.5408570450374452e-06, "epoch": 2.497505345687812, "percentage": 50.06, "elapsed_time": "1:36:03", "remaining_time": "1:35:50", "throughput": "502.87", "total_tokens": 2898304} -{"current_steps": 439, "total_steps": 875, "loss": 0.0013, "learning_rate": 2.531778260601796e-06, "epoch": 2.5032074126870993, "percentage": 50.17, "elapsed_time": "1:36:16", "remaining_time": "1:35:37", "throughput": "502.92", "total_tokens": 2905200} -{"current_steps": 440, "total_steps": 875, "loss": 0.0248, "learning_rate": 2.522699056989408e-06, "epoch": 2.5089094796863862, "percentage": 50.29, "elapsed_time": "1:36:29", "remaining_time": "1:35:24", "throughput": "502.89", "total_tokens": 2911648} -{"current_steps": 441, "total_steps": 875, "loss": 0.034, "learning_rate": 2.5136195539611135e-06, "epoch": 2.5146115466856735, "percentage": 50.4, "elapsed_time": "1:36:42", "remaining_time": "1:35:10", "throughput": "502.99", "total_tokens": 2918864} -{"current_steps": 442, "total_steps": 875, "loss": 0.0484, "learning_rate": 2.5045398712816954e-06, "epoch": 2.520313613684961, "percentage": 50.51, "elapsed_time": "1:36:56", "remaining_time": "1:34:57", "throughput": "503.02", "total_tokens": 2925648} -{"current_steps": 443, "total_steps": 875, "loss": 0.0519, "learning_rate": 2.4954601287183054e-06, "epoch": 2.526015680684248, "percentage": 50.63, "elapsed_time": "1:37:09", "remaining_time": "1:34:44", "throughput": "503.04", "total_tokens": 2932368} -{"current_steps": 444, "total_steps": 875, "loss": 0.0088, "learning_rate": 2.4863804460388877e-06, "epoch": 2.531717747683535, "percentage": 50.74, "elapsed_time": "1:37:22", "remaining_time": "1:34:31", "throughput": "503.00", "total_tokens": 2938752} -{"current_steps": 445, "total_steps": 875, "loss": 0.0249, "learning_rate": 2.4773009430105923e-06, "epoch": 2.5374198146828224, "percentage": 50.86, "elapsed_time": "1:37:35", "remaining_time": "1:34:18", "throughput": "502.99", "total_tokens": 2945280} -{"current_steps": 446, "total_steps": 875, "loss": 0.0041, "learning_rate": 2.468221739398205e-06, "epoch": 2.5431218816821097, "percentage": 50.97, "elapsed_time": "1:37:48", "remaining_time": "1:34:05", "throughput": "503.01", "total_tokens": 2952048} -{"current_steps": 447, "total_steps": 875, "loss": 0.0058, "learning_rate": 2.459142954962555e-06, "epoch": 2.548823948681397, "percentage": 51.09, "elapsed_time": "1:38:01", "remaining_time": "1:33:51", "throughput": "503.04", "total_tokens": 2958848} -{"current_steps": 448, "total_steps": 875, "loss": 0.0053, "learning_rate": 2.4500647094589507e-06, "epoch": 2.5545260156806844, "percentage": 51.2, "elapsed_time": "1:38:15", "remaining_time": "1:33:38", "throughput": "503.01", "total_tokens": 2965264} -{"current_steps": 449, "total_steps": 875, "loss": 0.0212, "learning_rate": 2.4409871226355835e-06, "epoch": 2.5602280826799717, "percentage": 51.31, "elapsed_time": "1:38:28", "remaining_time": "1:33:25", "throughput": "503.02", "total_tokens": 2971920} -{"current_steps": 450, "total_steps": 875, "loss": 0.0074, "learning_rate": 2.4319103142319624e-06, "epoch": 2.5659301496792586, "percentage": 51.43, "elapsed_time": "1:38:41", "remaining_time": "1:33:12", "throughput": "502.99", "total_tokens": 2978368} -{"current_steps": 451, "total_steps": 875, "loss": 0.0075, "learning_rate": 2.422834403977325e-06, "epoch": 2.571632216678546, "percentage": 51.54, "elapsed_time": "1:38:54", "remaining_time": "1:32:59", "throughput": "503.02", "total_tokens": 2985168} -{"current_steps": 452, "total_steps": 875, "loss": 0.0119, "learning_rate": 2.413759511589064e-06, "epoch": 2.5773342836778332, "percentage": 51.66, "elapsed_time": "1:39:07", "remaining_time": "1:32:46", "throughput": "503.01", "total_tokens": 2991744} -{"current_steps": 453, "total_steps": 875, "loss": 0.0231, "learning_rate": 2.404685756771143e-06, "epoch": 2.5830363506771206, "percentage": 51.77, "elapsed_time": "1:39:20", "remaining_time": "1:32:32", "throughput": "503.01", "total_tokens": 2998320} -{"current_steps": 454, "total_steps": 875, "loss": 0.0046, "learning_rate": 2.3956132592125234e-06, "epoch": 2.5887384176764074, "percentage": 51.89, "elapsed_time": "1:39:33", "remaining_time": "1:32:19", "throughput": "503.03", "total_tokens": 3005056} -{"current_steps": 455, "total_steps": 875, "loss": 0.0071, "learning_rate": 2.3865421385855807e-06, "epoch": 2.5944404846756948, "percentage": 52.0, "elapsed_time": "1:39:47", "remaining_time": "1:32:06", "throughput": "503.03", "total_tokens": 3011696} -{"current_steps": 456, "total_steps": 875, "loss": 0.0148, "learning_rate": 2.3774725145445276e-06, "epoch": 2.600142551674982, "percentage": 52.11, "elapsed_time": "1:40:00", "remaining_time": "1:31:53", "throughput": "503.05", "total_tokens": 3018416} -{"current_steps": 457, "total_steps": 875, "loss": 0.0011, "learning_rate": 2.3684045067238363e-06, "epoch": 2.6058446186742694, "percentage": 52.23, "elapsed_time": "1:40:13", "remaining_time": "1:31:40", "throughput": "503.05", "total_tokens": 3025040} -{"current_steps": 458, "total_steps": 875, "loss": 0.005, "learning_rate": 2.359338234736661e-06, "epoch": 2.6115466856735567, "percentage": 52.34, "elapsed_time": "1:40:26", "remaining_time": "1:31:27", "throughput": "503.02", "total_tokens": 3031472} -{"current_steps": 459, "total_steps": 875, "loss": 0.0348, "learning_rate": 2.3502738181732566e-06, "epoch": 2.617248752672844, "percentage": 52.46, "elapsed_time": "1:40:39", "remaining_time": "1:31:13", "throughput": "503.03", "total_tokens": 3038176} -{"current_steps": 460, "total_steps": 875, "loss": 0.0024, "learning_rate": 2.341211376599406e-06, "epoch": 2.6229508196721314, "percentage": 52.57, "elapsed_time": "1:40:52", "remaining_time": "1:31:00", "throughput": "503.00", "total_tokens": 3044592} -{"current_steps": 461, "total_steps": 875, "loss": 0.0013, "learning_rate": 2.3321510295548396e-06, "epoch": 2.6286528866714183, "percentage": 52.69, "elapsed_time": "1:41:06", "remaining_time": "1:30:47", "throughput": "502.96", "total_tokens": 3050976} -{"current_steps": 462, "total_steps": 875, "loss": 0.0408, "learning_rate": 2.32309289655166e-06, "epoch": 2.6343549536707056, "percentage": 52.8, "elapsed_time": "1:41:19", "remaining_time": "1:30:34", "throughput": "502.96", "total_tokens": 3057568} -{"current_steps": 463, "total_steps": 875, "loss": 0.0069, "learning_rate": 2.3140370970727644e-06, "epoch": 2.640057020669993, "percentage": 52.91, "elapsed_time": "1:41:32", "remaining_time": "1:30:21", "throughput": "502.98", "total_tokens": 3064288} -{"current_steps": 464, "total_steps": 875, "loss": 0.0382, "learning_rate": 2.30498375057027e-06, "epoch": 2.6457590876692803, "percentage": 53.03, "elapsed_time": "1:41:45", "remaining_time": "1:30:08", "throughput": "502.96", "total_tokens": 3070832} -{"current_steps": 465, "total_steps": 875, "loss": 0.0179, "learning_rate": 2.2959329764639366e-06, "epoch": 2.651461154668567, "percentage": 53.14, "elapsed_time": "1:41:58", "remaining_time": "1:29:54", "throughput": "502.89", "total_tokens": 3076992} -{"current_steps": 466, "total_steps": 875, "loss": 0.0073, "learning_rate": 2.286884894139594e-06, "epoch": 2.6571632216678545, "percentage": 53.26, "elapsed_time": "1:42:11", "remaining_time": "1:29:41", "throughput": "502.89", "total_tokens": 3083632} -{"current_steps": 467, "total_steps": 875, "loss": 0.06, "learning_rate": 2.2778396229475634e-06, "epoch": 2.662865288667142, "percentage": 53.37, "elapsed_time": "1:42:24", "remaining_time": "1:29:28", "throughput": "502.87", "total_tokens": 3090128} -{"current_steps": 468, "total_steps": 875, "loss": 0.0443, "learning_rate": 2.2687972822010885e-06, "epoch": 2.668567355666429, "percentage": 53.49, "elapsed_time": "1:42:38", "remaining_time": "1:29:15", "throughput": "502.88", "total_tokens": 3096768} -{"current_steps": 469, "total_steps": 875, "loss": 0.0082, "learning_rate": 2.259757991174753e-06, "epoch": 2.6742694226657164, "percentage": 53.6, "elapsed_time": "1:42:51", "remaining_time": "1:29:02", "throughput": "502.83", "total_tokens": 3103104} -{"current_steps": 470, "total_steps": 875, "loss": 0.0036, "learning_rate": 2.2507218691029204e-06, "epoch": 2.6799714896650038, "percentage": 53.71, "elapsed_time": "1:43:04", "remaining_time": "1:28:49", "throughput": "502.81", "total_tokens": 3109616} -{"current_steps": 471, "total_steps": 875, "loss": 0.0129, "learning_rate": 2.2416890351781452e-06, "epoch": 2.6856735566642906, "percentage": 53.83, "elapsed_time": "1:43:17", "remaining_time": "1:28:35", "throughput": "502.85", "total_tokens": 3116432} -{"current_steps": 472, "total_steps": 875, "loss": 0.0122, "learning_rate": 2.2326596085496166e-06, "epoch": 2.691375623663578, "percentage": 53.94, "elapsed_time": "1:43:30", "remaining_time": "1:28:22", "throughput": "502.88", "total_tokens": 3123232} -{"current_steps": 473, "total_steps": 875, "loss": 0.0285, "learning_rate": 2.2236337083215727e-06, "epoch": 2.6970776906628653, "percentage": 54.06, "elapsed_time": "1:43:43", "remaining_time": "1:28:09", "throughput": "502.85", "total_tokens": 3129664} -{"current_steps": 474, "total_steps": 875, "loss": 0.0132, "learning_rate": 2.2146114535517415e-06, "epoch": 2.7027797576621526, "percentage": 54.17, "elapsed_time": "1:43:57", "remaining_time": "1:27:56", "throughput": "502.82", "total_tokens": 3136128} -{"current_steps": 475, "total_steps": 875, "loss": 0.0359, "learning_rate": 2.20559296324976e-06, "epoch": 2.7084818246614395, "percentage": 54.29, "elapsed_time": "1:44:10", "remaining_time": "1:27:43", "throughput": "502.86", "total_tokens": 3142960} -{"current_steps": 476, "total_steps": 875, "loss": 0.0039, "learning_rate": 2.1965783563756148e-06, "epoch": 2.714183891660727, "percentage": 54.4, "elapsed_time": "1:44:23", "remaining_time": "1:27:30", "throughput": "502.80", "total_tokens": 3149216} -{"current_steps": 477, "total_steps": 875, "loss": 0.0151, "learning_rate": 2.1875677518380616e-06, "epoch": 2.719885958660014, "percentage": 54.51, "elapsed_time": "1:44:36", "remaining_time": "1:27:17", "throughput": "502.80", "total_tokens": 3155840} -{"current_steps": 478, "total_steps": 875, "loss": 0.0406, "learning_rate": 2.178561268493068e-06, "epoch": 2.7255880256593015, "percentage": 54.63, "elapsed_time": "1:44:49", "remaining_time": "1:27:03", "throughput": "502.76", "total_tokens": 3162176} -{"current_steps": 479, "total_steps": 875, "loss": 0.0055, "learning_rate": 2.1695590251422353e-06, "epoch": 2.731290092658589, "percentage": 54.74, "elapsed_time": "1:45:02", "remaining_time": "1:26:50", "throughput": "502.71", "total_tokens": 3168528} -{"current_steps": 480, "total_steps": 875, "loss": 0.0414, "learning_rate": 2.1605611405312406e-06, "epoch": 2.736992159657876, "percentage": 54.86, "elapsed_time": "1:45:16", "remaining_time": "1:26:37", "throughput": "502.74", "total_tokens": 3175296} -{"current_steps": 481, "total_steps": 875, "loss": 0.0199, "learning_rate": 2.1515677333482635e-06, "epoch": 2.7426942266571634, "percentage": 54.97, "elapsed_time": "1:45:29", "remaining_time": "1:26:24", "throughput": "502.77", "total_tokens": 3182112} -{"current_steps": 482, "total_steps": 875, "loss": 0.0141, "learning_rate": 2.1425789222224254e-06, "epoch": 2.7483962936564503, "percentage": 55.09, "elapsed_time": "1:45:42", "remaining_time": "1:26:11", "throughput": "502.82", "total_tokens": 3189008} -{"current_steps": 483, "total_steps": 875, "loss": 0.0281, "learning_rate": 2.13359482572222e-06, "epoch": 2.7540983606557377, "percentage": 55.2, "elapsed_time": "1:45:55", "remaining_time": "1:25:58", "throughput": "502.76", "total_tokens": 3195280} -{"current_steps": 484, "total_steps": 875, "loss": 0.0273, "learning_rate": 2.124615562353955e-06, "epoch": 2.759800427655025, "percentage": 55.31, "elapsed_time": "1:46:08", "remaining_time": "1:25:44", "throughput": "502.75", "total_tokens": 3201840} -{"current_steps": 485, "total_steps": 875, "loss": 0.0048, "learning_rate": 2.115641250560183e-06, "epoch": 2.7655024946543123, "percentage": 55.43, "elapsed_time": "1:46:21", "remaining_time": "1:25:31", "throughput": "502.69", "total_tokens": 3208048} -{"current_steps": 486, "total_steps": 875, "loss": 0.0312, "learning_rate": 2.106672008718144e-06, "epoch": 2.771204561653599, "percentage": 55.54, "elapsed_time": "1:46:34", "remaining_time": "1:25:18", "throughput": "502.64", "total_tokens": 3214368} -{"current_steps": 487, "total_steps": 875, "loss": 0.011, "learning_rate": 2.0977079551382006e-06, "epoch": 2.7769066286528865, "percentage": 55.66, "elapsed_time": "1:46:48", "remaining_time": "1:25:05", "throughput": "502.65", "total_tokens": 3221008} -{"current_steps": 488, "total_steps": 875, "loss": 0.0109, "learning_rate": 2.08874920806228e-06, "epoch": 2.782608695652174, "percentage": 55.77, "elapsed_time": "1:47:01", "remaining_time": "1:24:52", "throughput": "502.64", "total_tokens": 3227584} -{"current_steps": 489, "total_steps": 875, "loss": 0.0051, "learning_rate": 2.079795885662311e-06, "epoch": 2.788310762651461, "percentage": 55.89, "elapsed_time": "1:47:14", "remaining_time": "1:24:39", "throughput": "502.65", "total_tokens": 3234224} -{"current_steps": 490, "total_steps": 875, "loss": 0.0033, "learning_rate": 2.07084810603867e-06, "epoch": 2.7940128296507485, "percentage": 56.0, "elapsed_time": "1:47:27", "remaining_time": "1:24:25", "throughput": "502.60", "total_tokens": 3240544} -{"current_steps": 491, "total_steps": 875, "loss": 0.0228, "learning_rate": 2.0619059872186174e-06, "epoch": 2.799714896650036, "percentage": 56.11, "elapsed_time": "1:47:40", "remaining_time": "1:24:12", "throughput": "502.60", "total_tokens": 3247120} -{"current_steps": 492, "total_steps": 875, "loss": 0.0192, "learning_rate": 2.0529696471547455e-06, "epoch": 2.805416963649323, "percentage": 56.23, "elapsed_time": "1:47:53", "remaining_time": "1:23:59", "throughput": "502.60", "total_tokens": 3253744} -{"current_steps": 493, "total_steps": 875, "loss": 0.0067, "learning_rate": 2.044039203723423e-06, "epoch": 2.81111903064861, "percentage": 56.34, "elapsed_time": "1:48:07", "remaining_time": "1:23:46", "throughput": "502.62", "total_tokens": 3260512} -{"current_steps": 494, "total_steps": 875, "loss": 0.0558, "learning_rate": 2.035114774723233e-06, "epoch": 2.8168210976478973, "percentage": 56.46, "elapsed_time": "1:48:20", "remaining_time": "1:23:33", "throughput": "502.60", "total_tokens": 3267008} -{"current_steps": 495, "total_steps": 875, "loss": 0.0247, "learning_rate": 2.02619647787343e-06, "epoch": 2.8225231646471847, "percentage": 56.57, "elapsed_time": "1:48:33", "remaining_time": "1:23:20", "throughput": "502.62", "total_tokens": 3273696} -{"current_steps": 496, "total_steps": 875, "loss": 0.0501, "learning_rate": 2.017284430812374e-06, "epoch": 2.828225231646472, "percentage": 56.69, "elapsed_time": "1:48:46", "remaining_time": "1:23:06", "throughput": "502.62", "total_tokens": 3280368} -{"current_steps": 497, "total_steps": 875, "loss": 0.0268, "learning_rate": 2.008378751095994e-06, "epoch": 2.833927298645759, "percentage": 56.8, "elapsed_time": "1:48:59", "remaining_time": "1:22:53", "throughput": "502.66", "total_tokens": 3287200} -{"current_steps": 498, "total_steps": 875, "loss": 0.0323, "learning_rate": 1.9994795561962237e-06, "epoch": 2.839629365645046, "percentage": 56.91, "elapsed_time": "1:49:12", "remaining_time": "1:22:40", "throughput": "502.63", "total_tokens": 3293648} -{"current_steps": 499, "total_steps": 875, "loss": 0.0469, "learning_rate": 1.990586963499461e-06, "epoch": 2.8453314326443335, "percentage": 57.03, "elapsed_time": "1:49:25", "remaining_time": "1:22:27", "throughput": "502.67", "total_tokens": 3300496} -{"current_steps": 500, "total_steps": 875, "loss": 0.06, "learning_rate": 1.981701090305014e-06, "epoch": 2.851033499643621, "percentage": 57.14, "elapsed_time": "1:49:39", "remaining_time": "1:22:14", "throughput": "502.60", "total_tokens": 3306624} -{"current_steps": 501, "total_steps": 875, "loss": 0.0153, "learning_rate": 1.9728220538235577e-06, "epoch": 2.856735566642908, "percentage": 57.26, "elapsed_time": "1:49:52", "remaining_time": "1:22:01", "throughput": "502.61", "total_tokens": 3313312} -{"current_steps": 502, "total_steps": 875, "loss": 0.0019, "learning_rate": 1.963949971175585e-06, "epoch": 2.8624376336421955, "percentage": 57.37, "elapsed_time": "1:50:05", "remaining_time": "1:21:47", "throughput": "502.60", "total_tokens": 3319872} -{"current_steps": 503, "total_steps": 875, "loss": 0.0037, "learning_rate": 1.955084959389864e-06, "epoch": 2.8681397006414824, "percentage": 57.49, "elapsed_time": "1:50:18", "remaining_time": "1:21:34", "throughput": "502.57", "total_tokens": 3326288} -{"current_steps": 504, "total_steps": 875, "loss": 0.0091, "learning_rate": 1.9462271354018925e-06, "epoch": 2.8738417676407697, "percentage": 57.6, "elapsed_time": "1:50:31", "remaining_time": "1:21:21", "throughput": "502.56", "total_tokens": 3332816} -{"current_steps": 505, "total_steps": 875, "loss": 0.0038, "learning_rate": 1.937376616052357e-06, "epoch": 2.879543834640057, "percentage": 57.71, "elapsed_time": "1:50:44", "remaining_time": "1:21:08", "throughput": "502.53", "total_tokens": 3339248} -{"current_steps": 506, "total_steps": 875, "loss": 0.0026, "learning_rate": 1.9285335180855906e-06, "epoch": 2.8852459016393444, "percentage": 57.83, "elapsed_time": "1:50:58", "remaining_time": "1:20:55", "throughput": "502.47", "total_tokens": 3345440} -{"current_steps": 507, "total_steps": 875, "loss": 0.0198, "learning_rate": 1.9196979581480347e-06, "epoch": 2.8909479686386312, "percentage": 57.94, "elapsed_time": "1:51:11", "remaining_time": "1:20:42", "throughput": "502.49", "total_tokens": 3352176} -{"current_steps": 508, "total_steps": 875, "loss": 0.0372, "learning_rate": 1.9108700527866954e-06, "epoch": 2.8966500356379186, "percentage": 58.06, "elapsed_time": "1:51:24", "remaining_time": "1:20:29", "throughput": "502.48", "total_tokens": 3358720} -{"current_steps": 509, "total_steps": 875, "loss": 0.0063, "learning_rate": 1.9020499184476137e-06, "epoch": 2.902352102637206, "percentage": 58.17, "elapsed_time": "1:51:37", "remaining_time": "1:20:15", "throughput": "502.50", "total_tokens": 3365472} -{"current_steps": 510, "total_steps": 875, "loss": 0.0034, "learning_rate": 1.8932376714743237e-06, "epoch": 2.908054169636493, "percentage": 58.29, "elapsed_time": "1:51:50", "remaining_time": "1:20:02", "throughput": "502.45", "total_tokens": 3371728} -{"current_steps": 511, "total_steps": 875, "loss": 0.0049, "learning_rate": 1.88443342810632e-06, "epoch": 2.9137562366357805, "percentage": 58.4, "elapsed_time": "1:52:03", "remaining_time": "1:19:49", "throughput": "502.49", "total_tokens": 3378608} -{"current_steps": 512, "total_steps": 875, "loss": 0.0236, "learning_rate": 1.8756373044775238e-06, "epoch": 2.919458303635068, "percentage": 58.51, "elapsed_time": "1:52:16", "remaining_time": "1:19:36", "throughput": "502.50", "total_tokens": 3385280} -{"current_steps": 513, "total_steps": 875, "loss": 0.0326, "learning_rate": 1.8668494166147532e-06, "epoch": 2.925160370634355, "percentage": 58.63, "elapsed_time": "1:52:30", "remaining_time": "1:19:23", "throughput": "502.49", "total_tokens": 3391872} -{"current_steps": 514, "total_steps": 875, "loss": 0.0349, "learning_rate": 1.8580698804361886e-06, "epoch": 2.930862437633642, "percentage": 58.74, "elapsed_time": "1:52:43", "remaining_time": "1:19:10", "throughput": "502.50", "total_tokens": 3398512} -{"current_steps": 515, "total_steps": 875, "loss": 0.0034, "learning_rate": 1.8492988117498478e-06, "epoch": 2.9365645046329294, "percentage": 58.86, "elapsed_time": "1:52:56", "remaining_time": "1:18:56", "throughput": "502.54", "total_tokens": 3405376} -{"current_steps": 516, "total_steps": 875, "loss": 0.0309, "learning_rate": 1.840536326252055e-06, "epoch": 2.9422665716322167, "percentage": 58.97, "elapsed_time": "1:53:09", "remaining_time": "1:18:43", "throughput": "502.57", "total_tokens": 3412192} -{"current_steps": 517, "total_steps": 875, "loss": 0.0185, "learning_rate": 1.8317825395259199e-06, "epoch": 2.947968638631504, "percentage": 59.09, "elapsed_time": "1:53:22", "remaining_time": "1:18:30", "throughput": "502.58", "total_tokens": 3418896} -{"current_steps": 518, "total_steps": 875, "loss": 0.0054, "learning_rate": 1.8230375670398037e-06, "epoch": 2.953670705630791, "percentage": 59.2, "elapsed_time": "1:53:35", "remaining_time": "1:18:17", "throughput": "502.57", "total_tokens": 3425456} -{"current_steps": 519, "total_steps": 875, "loss": 0.0076, "learning_rate": 1.8143015241458082e-06, "epoch": 2.9593727726300783, "percentage": 59.31, "elapsed_time": "1:53:48", "remaining_time": "1:18:04", "throughput": "502.62", "total_tokens": 3432384} -{"current_steps": 520, "total_steps": 875, "loss": 0.0191, "learning_rate": 1.8055745260782415e-06, "epoch": 2.9650748396293656, "percentage": 59.43, "elapsed_time": "1:54:02", "remaining_time": "1:17:51", "throughput": "502.61", "total_tokens": 3438928} -{"current_steps": 521, "total_steps": 875, "loss": 0.0348, "learning_rate": 1.7968566879521112e-06, "epoch": 2.970776906628653, "percentage": 59.54, "elapsed_time": "1:54:15", "remaining_time": "1:17:37", "throughput": "502.59", "total_tokens": 3445424} -{"current_steps": 522, "total_steps": 875, "loss": 0.0166, "learning_rate": 1.7881481247615923e-06, "epoch": 2.9764789736279402, "percentage": 59.66, "elapsed_time": "1:54:28", "remaining_time": "1:17:24", "throughput": "502.61", "total_tokens": 3452176} -{"current_steps": 523, "total_steps": 875, "loss": 0.0322, "learning_rate": 1.779448951378523e-06, "epoch": 2.9821810406272276, "percentage": 59.77, "elapsed_time": "1:54:41", "remaining_time": "1:17:11", "throughput": "502.63", "total_tokens": 3458912} -{"current_steps": 524, "total_steps": 875, "loss": 0.0063, "learning_rate": 1.7707592825508776e-06, "epoch": 2.987883107626515, "percentage": 59.89, "elapsed_time": "1:54:54", "remaining_time": "1:16:58", "throughput": "502.58", "total_tokens": 3465136} -{"current_steps": 525, "total_steps": 875, "loss": 0.0021, "learning_rate": 1.7620792329012656e-06, "epoch": 2.9935851746258018, "percentage": 60.0, "elapsed_time": "1:55:07", "remaining_time": "1:16:45", "throughput": "502.60", "total_tokens": 3471920} -{"current_steps": 526, "total_steps": 875, "loss": 0.0116, "learning_rate": 1.7534089169254076e-06, "epoch": 2.999287241625089, "percentage": 60.11, "elapsed_time": "1:55:21", "remaining_time": "1:16:32", "throughput": "502.61", "total_tokens": 3478608} -{"current_steps": 527, "total_steps": 875, "loss": 0.0027, "learning_rate": 1.7447484489906332e-06, "epoch": 3.0049893086243764, "percentage": 60.23, "elapsed_time": "1:55:34", "remaining_time": "1:16:18", "throughput": "502.62", "total_tokens": 3485232} -{"current_steps": 528, "total_steps": 875, "loss": 0.0076, "learning_rate": 1.7360979433343686e-06, "epoch": 3.0106913756236637, "percentage": 60.34, "elapsed_time": "1:55:47", "remaining_time": "1:16:05", "throughput": "502.61", "total_tokens": 3491840} -{"current_steps": 529, "total_steps": 875, "loss": 0.006, "learning_rate": 1.7274575140626318e-06, "epoch": 3.0163934426229506, "percentage": 60.46, "elapsed_time": "1:56:00", "remaining_time": "1:15:52", "throughput": "502.68", "total_tokens": 3498896} -{"current_steps": 530, "total_steps": 875, "loss": 0.0008, "learning_rate": 1.7188272751485246e-06, "epoch": 3.022095509622238, "percentage": 60.57, "elapsed_time": "1:56:13", "remaining_time": "1:15:39", "throughput": "502.68", "total_tokens": 3505488} -{"current_steps": 531, "total_steps": 875, "loss": 0.0139, "learning_rate": 1.710207340430734e-06, "epoch": 3.0277975766215253, "percentage": 60.69, "elapsed_time": "1:56:26", "remaining_time": "1:15:26", "throughput": "502.68", "total_tokens": 3512144} -{"current_steps": 532, "total_steps": 875, "loss": 0.0123, "learning_rate": 1.7015978236120245e-06, "epoch": 3.0334996436208126, "percentage": 60.8, "elapsed_time": "1:56:39", "remaining_time": "1:15:13", "throughput": "502.72", "total_tokens": 3519008} -{"current_steps": 533, "total_steps": 875, "loss": 0.0004, "learning_rate": 1.6929988382577442e-06, "epoch": 3.0392017106201, "percentage": 60.91, "elapsed_time": "1:56:53", "remaining_time": "1:14:59", "throughput": "502.69", "total_tokens": 3525408} -{"current_steps": 534, "total_steps": 875, "loss": 0.0005, "learning_rate": 1.6844104977943219e-06, "epoch": 3.0449037776193872, "percentage": 61.03, "elapsed_time": "1:57:06", "remaining_time": "1:14:46", "throughput": "502.65", "total_tokens": 3531744} -{"current_steps": 535, "total_steps": 875, "loss": 0.0025, "learning_rate": 1.6758329155077746e-06, "epoch": 3.050605844618674, "percentage": 61.14, "elapsed_time": "1:57:19", "remaining_time": "1:14:33", "throughput": "502.63", "total_tokens": 3538240} -{"current_steps": 536, "total_steps": 875, "loss": 0.0008, "learning_rate": 1.667266204542211e-06, "epoch": 3.0563079116179614, "percentage": 61.26, "elapsed_time": "1:57:32", "remaining_time": "1:14:20", "throughput": "502.64", "total_tokens": 3544944} -{"current_steps": 537, "total_steps": 875, "loss": 0.0004, "learning_rate": 1.6587104778983397e-06, "epoch": 3.0620099786172488, "percentage": 61.37, "elapsed_time": "1:57:45", "remaining_time": "1:14:07", "throughput": "502.66", "total_tokens": 3551664} -{"current_steps": 538, "total_steps": 875, "loss": 0.0003, "learning_rate": 1.650165848431979e-06, "epoch": 3.067712045616536, "percentage": 61.49, "elapsed_time": "1:57:58", "remaining_time": "1:13:54", "throughput": "502.67", "total_tokens": 3558368} -{"current_steps": 539, "total_steps": 875, "loss": 0.0092, "learning_rate": 1.641632428852568e-06, "epoch": 3.0734141126158234, "percentage": 61.6, "elapsed_time": "1:58:12", "remaining_time": "1:13:41", "throughput": "502.66", "total_tokens": 3564912} -{"current_steps": 540, "total_steps": 875, "loss": 0.009, "learning_rate": 1.633110331721679e-06, "epoch": 3.0791161796151103, "percentage": 61.71, "elapsed_time": "1:58:25", "remaining_time": "1:13:27", "throughput": "502.69", "total_tokens": 3571760} -{"current_steps": 541, "total_steps": 875, "loss": 0.0356, "learning_rate": 1.624599669451535e-06, "epoch": 3.0848182466143976, "percentage": 61.83, "elapsed_time": "1:58:38", "remaining_time": "1:13:14", "throughput": "502.73", "total_tokens": 3578608} -{"current_steps": 542, "total_steps": 875, "loss": 0.0009, "learning_rate": 1.6161005543035234e-06, "epoch": 3.090520313613685, "percentage": 61.94, "elapsed_time": "1:58:51", "remaining_time": "1:13:01", "throughput": "502.78", "total_tokens": 3585568} -{"current_steps": 543, "total_steps": 875, "loss": 0.0006, "learning_rate": 1.6076130983867194e-06, "epoch": 3.0962223806129723, "percentage": 62.06, "elapsed_time": "1:59:04", "remaining_time": "1:12:48", "throughput": "502.81", "total_tokens": 3592448} -{"current_steps": 544, "total_steps": 875, "loss": 0.0007, "learning_rate": 1.5991374136564033e-06, "epoch": 3.1019244476122596, "percentage": 62.17, "elapsed_time": "1:59:17", "remaining_time": "1:12:35", "throughput": "502.79", "total_tokens": 3598896} -{"current_steps": 545, "total_steps": 875, "loss": 0.0006, "learning_rate": 1.5906736119125871e-06, "epoch": 3.1076265146115465, "percentage": 62.29, "elapsed_time": "1:59:30", "remaining_time": "1:12:22", "throughput": "502.81", "total_tokens": 3605664} -{"current_steps": 546, "total_steps": 875, "loss": 0.0005, "learning_rate": 1.582221804798536e-06, "epoch": 3.113328581610834, "percentage": 62.4, "elapsed_time": "1:59:44", "remaining_time": "1:12:08", "throughput": "502.81", "total_tokens": 3612272} -{"current_steps": 547, "total_steps": 875, "loss": 0.0002, "learning_rate": 1.5737821037993016e-06, "epoch": 3.119030648610121, "percentage": 62.51, "elapsed_time": "1:59:57", "remaining_time": "1:11:55", "throughput": "502.83", "total_tokens": 3618992} -{"current_steps": 548, "total_steps": 875, "loss": 0.0004, "learning_rate": 1.565354620240243e-06, "epoch": 3.1247327156094085, "percentage": 62.63, "elapsed_time": "2:00:10", "remaining_time": "1:11:42", "throughput": "502.82", "total_tokens": 3625584} -{"current_steps": 549, "total_steps": 875, "loss": 0.0002, "learning_rate": 1.5569394652855674e-06, "epoch": 3.130434782608696, "percentage": 62.74, "elapsed_time": "2:00:23", "remaining_time": "1:11:29", "throughput": "502.79", "total_tokens": 3631936} -{"current_steps": 550, "total_steps": 875, "loss": 0.0085, "learning_rate": 1.5485367499368547e-06, "epoch": 3.1361368496079827, "percentage": 62.86, "elapsed_time": "2:00:36", "remaining_time": "1:11:16", "throughput": "502.80", "total_tokens": 3638640} -{"current_steps": 551, "total_steps": 875, "loss": 0.0007, "learning_rate": 1.5401465850316038e-06, "epoch": 3.14183891660727, "percentage": 62.97, "elapsed_time": "2:00:49", "remaining_time": "1:11:03", "throughput": "502.80", "total_tokens": 3645248} -{"current_steps": 552, "total_steps": 875, "loss": 0.002, "learning_rate": 1.5317690812417583e-06, "epoch": 3.1475409836065573, "percentage": 63.09, "elapsed_time": "2:01:03", "remaining_time": "1:10:49", "throughput": "502.78", "total_tokens": 3651696} -{"current_steps": 553, "total_steps": 875, "loss": 0.0005, "learning_rate": 1.5234043490722588e-06, "epoch": 3.1532430506058446, "percentage": 63.2, "elapsed_time": "2:01:16", "remaining_time": "1:10:36", "throughput": "502.78", "total_tokens": 3658368} -{"current_steps": 554, "total_steps": 875, "loss": 0.0002, "learning_rate": 1.5150524988595764e-06, "epoch": 3.158945117605132, "percentage": 63.31, "elapsed_time": "2:01:29", "remaining_time": "1:10:23", "throughput": "502.78", "total_tokens": 3664944} -{"current_steps": 555, "total_steps": 875, "loss": 0.002, "learning_rate": 1.5067136407702615e-06, "epoch": 3.1646471846044193, "percentage": 63.43, "elapsed_time": "2:01:42", "remaining_time": "1:10:10", "throughput": "502.79", "total_tokens": 3671632} -{"current_steps": 556, "total_steps": 875, "loss": 0.0001, "learning_rate": 1.4983878847994888e-06, "epoch": 3.170349251603706, "percentage": 63.54, "elapsed_time": "2:01:55", "remaining_time": "1:09:57", "throughput": "502.79", "total_tokens": 3678288} -{"current_steps": 557, "total_steps": 875, "loss": 0.0002, "learning_rate": 1.4900753407696087e-06, "epoch": 3.1760513186029935, "percentage": 63.66, "elapsed_time": "2:02:08", "remaining_time": "1:09:44", "throughput": "502.80", "total_tokens": 3684976} -{"current_steps": 558, "total_steps": 875, "loss": 0.0003, "learning_rate": 1.4817761183286949e-06, "epoch": 3.181753385602281, "percentage": 63.77, "elapsed_time": "2:02:22", "remaining_time": "1:09:31", "throughput": "502.86", "total_tokens": 3692000} -{"current_steps": 559, "total_steps": 875, "loss": 0.0312, "learning_rate": 1.4734903269491036e-06, "epoch": 3.187455452601568, "percentage": 63.89, "elapsed_time": "2:02:35", "remaining_time": "1:09:17", "throughput": "502.86", "total_tokens": 3698608} -{"current_steps": 560, "total_steps": 875, "loss": 0.0003, "learning_rate": 1.4652180759260224e-06, "epoch": 3.1931575196008555, "percentage": 64.0, "elapsed_time": "2:02:48", "remaining_time": "1:09:04", "throughput": "502.87", "total_tokens": 3705328} -{"current_steps": 561, "total_steps": 875, "loss": 0.0001, "learning_rate": 1.4569594743760362e-06, "epoch": 3.1988595866001424, "percentage": 64.11, "elapsed_time": "2:03:01", "remaining_time": "1:08:51", "throughput": "502.88", "total_tokens": 3711952} -{"current_steps": 562, "total_steps": 875, "loss": 0.0475, "learning_rate": 1.4487146312356797e-06, "epoch": 3.2045616535994297, "percentage": 64.23, "elapsed_time": "2:03:14", "remaining_time": "1:08:38", "throughput": "502.86", "total_tokens": 3718432} -{"current_steps": 563, "total_steps": 875, "loss": 0.0016, "learning_rate": 1.4404836552600102e-06, "epoch": 3.210263720598717, "percentage": 64.34, "elapsed_time": "2:03:27", "remaining_time": "1:08:25", "throughput": "502.84", "total_tokens": 3724880} -{"current_steps": 564, "total_steps": 875, "loss": 0.0002, "learning_rate": 1.4322666550211628e-06, "epoch": 3.2159657875980043, "percentage": 64.46, "elapsed_time": "2:03:40", "remaining_time": "1:08:12", "throughput": "502.84", "total_tokens": 3731504} -{"current_steps": 565, "total_steps": 875, "loss": 0.0002, "learning_rate": 1.4240637389069284e-06, "epoch": 3.2216678545972917, "percentage": 64.57, "elapsed_time": "2:03:54", "remaining_time": "1:07:58", "throughput": "502.79", "total_tokens": 3737728} -{"current_steps": 566, "total_steps": 875, "loss": 0.014, "learning_rate": 1.4158750151193118e-06, "epoch": 3.227369921596579, "percentage": 64.69, "elapsed_time": "2:04:07", "remaining_time": "1:07:45", "throughput": "502.77", "total_tokens": 3744256} -{"current_steps": 567, "total_steps": 875, "loss": 0.043, "learning_rate": 1.4077005916731178e-06, "epoch": 3.233071988595866, "percentage": 64.8, "elapsed_time": "2:04:20", "remaining_time": "1:07:32", "throughput": "502.79", "total_tokens": 3751008} -{"current_steps": 568, "total_steps": 875, "loss": 0.0283, "learning_rate": 1.399540576394517e-06, "epoch": 3.238774055595153, "percentage": 64.91, "elapsed_time": "2:04:33", "remaining_time": "1:07:19", "throughput": "502.83", "total_tokens": 3757888} -{"current_steps": 569, "total_steps": 875, "loss": 0.0137, "learning_rate": 1.3913950769196275e-06, "epoch": 3.2444761225944405, "percentage": 65.03, "elapsed_time": "2:04:46", "remaining_time": "1:07:06", "throughput": "502.82", "total_tokens": 3764400} -{"current_steps": 570, "total_steps": 875, "loss": 0.0249, "learning_rate": 1.3832642006930935e-06, "epoch": 3.250178189593728, "percentage": 65.14, "elapsed_time": "2:04:59", "remaining_time": "1:06:53", "throughput": "502.79", "total_tokens": 3770816} -{"current_steps": 571, "total_steps": 875, "loss": 0.0014, "learning_rate": 1.375148054966669e-06, "epoch": 3.2558802565930147, "percentage": 65.26, "elapsed_time": "2:05:12", "remaining_time": "1:06:39", "throughput": "502.78", "total_tokens": 3777360} -{"current_steps": 572, "total_steps": 875, "loss": 0.0034, "learning_rate": 1.3670467467978016e-06, "epoch": 3.261582323592302, "percentage": 65.37, "elapsed_time": "2:05:26", "remaining_time": "1:06:26", "throughput": "502.78", "total_tokens": 3783968} -{"current_steps": 573, "total_steps": 875, "loss": 0.0073, "learning_rate": 1.3589603830482246e-06, "epoch": 3.2672843905915894, "percentage": 65.49, "elapsed_time": "2:05:39", "remaining_time": "1:06:13", "throughput": "502.76", "total_tokens": 3790448} -{"current_steps": 574, "total_steps": 875, "loss": 0.0147, "learning_rate": 1.3508890703825406e-06, "epoch": 3.2729864575908767, "percentage": 65.6, "elapsed_time": "2:05:52", "remaining_time": "1:06:00", "throughput": "502.75", "total_tokens": 3796992} -{"current_steps": 575, "total_steps": 875, "loss": 0.0019, "learning_rate": 1.342832915266821e-06, "epoch": 3.278688524590164, "percentage": 65.71, "elapsed_time": "2:06:05", "remaining_time": "1:05:47", "throughput": "502.74", "total_tokens": 3803488} -{"current_steps": 576, "total_steps": 875, "loss": 0.0025, "learning_rate": 1.334792023967196e-06, "epoch": 3.2843905915894513, "percentage": 65.83, "elapsed_time": "2:06:18", "remaining_time": "1:05:34", "throughput": "502.77", "total_tokens": 3810304} -{"current_steps": 577, "total_steps": 875, "loss": 0.0018, "learning_rate": 1.3267665025484597e-06, "epoch": 3.2900926585887382, "percentage": 65.94, "elapsed_time": "2:06:31", "remaining_time": "1:05:20", "throughput": "502.79", "total_tokens": 3817072} -{"current_steps": 578, "total_steps": 875, "loss": 0.0023, "learning_rate": 1.3187564568726642e-06, "epoch": 3.2957947255880256, "percentage": 66.06, "elapsed_time": "2:06:44", "remaining_time": "1:05:07", "throughput": "502.84", "total_tokens": 3824064} -{"current_steps": 579, "total_steps": 875, "loss": 0.0077, "learning_rate": 1.3107619925977262e-06, "epoch": 3.301496792587313, "percentage": 66.17, "elapsed_time": "2:06:58", "remaining_time": "1:04:54", "throughput": "502.86", "total_tokens": 3830848} -{"current_steps": 580, "total_steps": 875, "loss": 0.0014, "learning_rate": 1.3027832151760328e-06, "epoch": 3.3071988595866, "percentage": 66.29, "elapsed_time": "2:07:11", "remaining_time": "1:04:41", "throughput": "502.89", "total_tokens": 3837696} -{"current_steps": 581, "total_steps": 875, "loss": 0.0037, "learning_rate": 1.2948202298530544e-06, "epoch": 3.3129009265858875, "percentage": 66.4, "elapsed_time": "2:07:24", "remaining_time": "1:04:28", "throughput": "502.86", "total_tokens": 3844096} -{"current_steps": 582, "total_steps": 875, "loss": 0.016, "learning_rate": 1.2868731416659492e-06, "epoch": 3.3186029935851744, "percentage": 66.51, "elapsed_time": "2:07:37", "remaining_time": "1:04:15", "throughput": "502.82", "total_tokens": 3850432} -{"current_steps": 583, "total_steps": 875, "loss": 0.0014, "learning_rate": 1.2789420554421823e-06, "epoch": 3.3243050605844617, "percentage": 66.63, "elapsed_time": "2:07:50", "remaining_time": "1:04:01", "throughput": "502.82", "total_tokens": 3856992} -{"current_steps": 584, "total_steps": 875, "loss": 0.0307, "learning_rate": 1.2710270757981418e-06, "epoch": 3.330007127583749, "percentage": 66.74, "elapsed_time": "2:08:03", "remaining_time": "1:03:48", "throughput": "502.83", "total_tokens": 3863664} -{"current_steps": 585, "total_steps": 875, "loss": 0.0011, "learning_rate": 1.263128307137762e-06, "epoch": 3.3357091945830364, "percentage": 66.86, "elapsed_time": "2:08:17", "remaining_time": "1:03:35", "throughput": "502.86", "total_tokens": 3870512} -{"current_steps": 586, "total_steps": 875, "loss": 0.0187, "learning_rate": 1.255245853651139e-06, "epoch": 3.3414112615823237, "percentage": 66.97, "elapsed_time": "2:08:30", "remaining_time": "1:03:22", "throughput": "502.87", "total_tokens": 3877264} -{"current_steps": 587, "total_steps": 875, "loss": 0.0092, "learning_rate": 1.2473798193131634e-06, "epoch": 3.347113328581611, "percentage": 67.09, "elapsed_time": "2:08:43", "remaining_time": "1:03:09", "throughput": "502.88", "total_tokens": 3883936} -{"current_steps": 588, "total_steps": 875, "loss": 0.0016, "learning_rate": 1.2395303078821466e-06, "epoch": 3.352815395580898, "percentage": 67.2, "elapsed_time": "2:08:56", "remaining_time": "1:02:56", "throughput": "502.87", "total_tokens": 3890464} -{"current_steps": 589, "total_steps": 875, "loss": 0.0118, "learning_rate": 1.2316974228984489e-06, "epoch": 3.3585174625801852, "percentage": 67.31, "elapsed_time": "2:09:09", "remaining_time": "1:02:43", "throughput": "502.82", "total_tokens": 3896720} -{"current_steps": 590, "total_steps": 875, "loss": 0.0227, "learning_rate": 1.22388126768312e-06, "epoch": 3.3642195295794726, "percentage": 67.43, "elapsed_time": "2:09:22", "remaining_time": "1:02:29", "throughput": "502.84", "total_tokens": 3903440} -{"current_steps": 591, "total_steps": 875, "loss": 0.0084, "learning_rate": 1.2160819453365301e-06, "epoch": 3.36992159657876, "percentage": 67.54, "elapsed_time": "2:09:35", "remaining_time": "1:02:16", "throughput": "502.84", "total_tokens": 3910112} -{"current_steps": 592, "total_steps": 875, "loss": 0.019, "learning_rate": 1.2082995587370136e-06, "epoch": 3.375623663578047, "percentage": 67.66, "elapsed_time": "2:09:49", "remaining_time": "1:02:03", "throughput": "502.84", "total_tokens": 3916704} -{"current_steps": 593, "total_steps": 875, "loss": 0.0073, "learning_rate": 1.2005342105395094e-06, "epoch": 3.381325730577334, "percentage": 67.77, "elapsed_time": "2:10:02", "remaining_time": "1:01:50", "throughput": "502.82", "total_tokens": 3923136} -{"current_steps": 594, "total_steps": 875, "loss": 0.0009, "learning_rate": 1.1927860031742116e-06, "epoch": 3.3870277975766214, "percentage": 67.89, "elapsed_time": "2:10:15", "remaining_time": "1:01:37", "throughput": "502.81", "total_tokens": 3929696} -{"current_steps": 595, "total_steps": 875, "loss": 0.0117, "learning_rate": 1.1850550388452125e-06, "epoch": 3.3927298645759087, "percentage": 68.0, "elapsed_time": "2:10:28", "remaining_time": "1:01:24", "throughput": "502.77", "total_tokens": 3936016} -{"current_steps": 596, "total_steps": 875, "loss": 0.017, "learning_rate": 1.177341419529157e-06, "epoch": 3.398431931575196, "percentage": 68.11, "elapsed_time": "2:10:41", "remaining_time": "1:01:10", "throughput": "502.75", "total_tokens": 3942480} -{"current_steps": 597, "total_steps": 875, "loss": 0.0054, "learning_rate": 1.1696452469738984e-06, "epoch": 3.4041339985744834, "percentage": 68.23, "elapsed_time": "2:10:54", "remaining_time": "1:00:57", "throughput": "502.73", "total_tokens": 3948928} -{"current_steps": 598, "total_steps": 875, "loss": 0.0041, "learning_rate": 1.1619666226971565e-06, "epoch": 3.4098360655737707, "percentage": 68.34, "elapsed_time": "2:11:08", "remaining_time": "1:00:44", "throughput": "502.70", "total_tokens": 3955248} -{"current_steps": 599, "total_steps": 875, "loss": 0.002, "learning_rate": 1.1543056479851755e-06, "epoch": 3.4155381325730576, "percentage": 68.46, "elapsed_time": "2:11:21", "remaining_time": "1:00:31", "throughput": "502.68", "total_tokens": 3961760} -{"current_steps": 600, "total_steps": 875, "loss": 0.0022, "learning_rate": 1.1466624238913907e-06, "epoch": 3.421240199572345, "percentage": 68.57, "elapsed_time": "2:11:34", "remaining_time": "1:00:18", "throughput": "502.65", "total_tokens": 3968112} -{"current_steps": 601, "total_steps": 875, "loss": 0.0004, "learning_rate": 1.1390370512350936e-06, "epoch": 3.4269422665716323, "percentage": 68.69, "elapsed_time": "2:11:47", "remaining_time": "1:00:05", "throughput": "502.67", "total_tokens": 3974864} -{"current_steps": 602, "total_steps": 875, "loss": 0.0148, "learning_rate": 1.1314296306001065e-06, "epoch": 3.4326443335709196, "percentage": 68.8, "elapsed_time": "2:12:00", "remaining_time": "0:59:51", "throughput": "502.64", "total_tokens": 3981296} -{"current_steps": 603, "total_steps": 875, "loss": 0.049, "learning_rate": 1.1238402623334494e-06, "epoch": 3.4383464005702065, "percentage": 68.91, "elapsed_time": "2:12:13", "remaining_time": "0:59:38", "throughput": "502.61", "total_tokens": 3987648} -{"current_steps": 604, "total_steps": 875, "loss": 0.0027, "learning_rate": 1.1162690465440198e-06, "epoch": 3.444048467569494, "percentage": 69.03, "elapsed_time": "2:12:27", "remaining_time": "0:59:25", "throughput": "502.60", "total_tokens": 3994208} -{"current_steps": 605, "total_steps": 875, "loss": 0.0007, "learning_rate": 1.1087160831012713e-06, "epoch": 3.449750534568781, "percentage": 69.14, "elapsed_time": "2:12:40", "remaining_time": "0:59:12", "throughput": "502.66", "total_tokens": 4001280} -{"current_steps": 606, "total_steps": 875, "loss": 0.006, "learning_rate": 1.1011814716338995e-06, "epoch": 3.4554526015680684, "percentage": 69.26, "elapsed_time": "2:12:53", "remaining_time": "0:58:59", "throughput": "502.69", "total_tokens": 4008128} -{"current_steps": 607, "total_steps": 875, "loss": 0.0066, "learning_rate": 1.093665311528521e-06, "epoch": 3.4611546685673558, "percentage": 69.37, "elapsed_time": "2:13:06", "remaining_time": "0:58:46", "throughput": "502.71", "total_tokens": 4014848} -{"current_steps": 608, "total_steps": 875, "loss": 0.0255, "learning_rate": 1.0861677019283717e-06, "epoch": 3.466856735566643, "percentage": 69.49, "elapsed_time": "2:13:19", "remaining_time": "0:58:32", "throughput": "502.68", "total_tokens": 4021296} -{"current_steps": 609, "total_steps": 875, "loss": 0.0075, "learning_rate": 1.0786887417319867e-06, "epoch": 3.47255880256593, "percentage": 69.6, "elapsed_time": "2:13:32", "remaining_time": "0:58:19", "throughput": "502.68", "total_tokens": 4027872} -{"current_steps": 610, "total_steps": 875, "loss": 0.0068, "learning_rate": 1.0712285295919092e-06, "epoch": 3.4782608695652173, "percentage": 69.71, "elapsed_time": "2:13:45", "remaining_time": "0:58:06", "throughput": "502.72", "total_tokens": 4034768} -{"current_steps": 611, "total_steps": 875, "loss": 0.0008, "learning_rate": 1.0637871639133793e-06, "epoch": 3.4839629365645046, "percentage": 69.83, "elapsed_time": "2:13:59", "remaining_time": "0:57:53", "throughput": "502.72", "total_tokens": 4041408} -{"current_steps": 612, "total_steps": 875, "loss": 0.0132, "learning_rate": 1.056364742853043e-06, "epoch": 3.489665003563792, "percentage": 69.94, "elapsed_time": "2:14:12", "remaining_time": "0:57:40", "throughput": "502.75", "total_tokens": 4048256} -{"current_steps": 613, "total_steps": 875, "loss": 0.0009, "learning_rate": 1.048961364317648e-06, "epoch": 3.4953670705630793, "percentage": 70.06, "elapsed_time": "2:14:25", "remaining_time": "0:57:27", "throughput": "502.79", "total_tokens": 4055184} -{"current_steps": 614, "total_steps": 875, "loss": 0.0009, "learning_rate": 1.0415771259627646e-06, "epoch": 3.501069137562366, "percentage": 70.17, "elapsed_time": "2:14:38", "remaining_time": "0:57:14", "throughput": "502.80", "total_tokens": 4061904} -{"current_steps": 615, "total_steps": 875, "loss": 0.0006, "learning_rate": 1.034212125191487e-06, "epoch": 3.5067712045616535, "percentage": 70.29, "elapsed_time": "2:14:51", "remaining_time": "0:57:00", "throughput": "502.81", "total_tokens": 4068560} -{"current_steps": 616, "total_steps": 875, "loss": 0.001, "learning_rate": 1.0268664591531557e-06, "epoch": 3.512473271560941, "percentage": 70.4, "elapsed_time": "2:15:04", "remaining_time": "0:56:47", "throughput": "502.79", "total_tokens": 4075072} -{"current_steps": 617, "total_steps": 875, "loss": 0.0219, "learning_rate": 1.0195402247420705e-06, "epoch": 3.518175338560228, "percentage": 70.51, "elapsed_time": "2:15:17", "remaining_time": "0:56:34", "throughput": "502.81", "total_tokens": 4081840} -{"current_steps": 618, "total_steps": 875, "loss": 0.0006, "learning_rate": 1.012233518596216e-06, "epoch": 3.5238774055595155, "percentage": 70.63, "elapsed_time": "2:15:31", "remaining_time": "0:56:21", "throughput": "502.82", "total_tokens": 4088512} -{"current_steps": 619, "total_steps": 875, "loss": 0.036, "learning_rate": 1.0049464370959846e-06, "epoch": 3.5295794725588028, "percentage": 70.74, "elapsed_time": "2:15:44", "remaining_time": "0:56:08", "throughput": "502.83", "total_tokens": 4095168} -{"current_steps": 620, "total_steps": 875, "loss": 0.0034, "learning_rate": 9.97679076362909e-07, "epoch": 3.5352815395580897, "percentage": 70.86, "elapsed_time": "2:15:57", "remaining_time": "0:55:55", "throughput": "502.87", "total_tokens": 4102112} -{"current_steps": 621, "total_steps": 875, "loss": 0.0039, "learning_rate": 9.904315322583894e-07, "epoch": 3.540983606557377, "percentage": 70.97, "elapsed_time": "2:16:10", "remaining_time": "0:55:41", "throughput": "502.83", "total_tokens": 4108432} -{"current_steps": 622, "total_steps": 875, "loss": 0.0011, "learning_rate": 9.832039003824317e-07, "epoch": 3.5466856735566643, "percentage": 71.09, "elapsed_time": "2:16:23", "remaining_time": "0:55:28", "throughput": "502.84", "total_tokens": 4115152} -{"current_steps": 623, "total_steps": 875, "loss": 0.0017, "learning_rate": 9.759962760723856e-07, "epoch": 3.5523877405559516, "percentage": 71.2, "elapsed_time": "2:16:36", "remaining_time": "0:55:15", "throughput": "502.84", "total_tokens": 4121696} -{"current_steps": 624, "total_steps": 875, "loss": 0.0057, "learning_rate": 9.6880875440169e-07, "epoch": 3.5580898075552385, "percentage": 71.31, "elapsed_time": "2:16:50", "remaining_time": "0:55:02", "throughput": "502.82", "total_tokens": 4128160} -{"current_steps": 625, "total_steps": 875, "loss": 0.0199, "learning_rate": 9.616414301786128e-07, "epoch": 3.563791874554526, "percentage": 71.43, "elapsed_time": "2:17:03", "remaining_time": "0:54:49", "throughput": "502.84", "total_tokens": 4134912} -{"current_steps": 626, "total_steps": 875, "loss": 0.0294, "learning_rate": 9.544943979450067e-07, "epoch": 3.569493941553813, "percentage": 71.54, "elapsed_time": "2:17:16", "remaining_time": "0:54:36", "throughput": "502.83", "total_tokens": 4141504} -{"current_steps": 627, "total_steps": 875, "loss": 0.0124, "learning_rate": 9.473677519750568e-07, "epoch": 3.5751960085531005, "percentage": 71.66, "elapsed_time": "2:17:29", "remaining_time": "0:54:22", "throughput": "502.83", "total_tokens": 4148144} -{"current_steps": 628, "total_steps": 875, "loss": 0.0058, "learning_rate": 9.40261586274043e-07, "epoch": 3.580898075552388, "percentage": 71.77, "elapsed_time": "2:17:42", "remaining_time": "0:54:09", "throughput": "502.85", "total_tokens": 4154880} -{"current_steps": 629, "total_steps": 875, "loss": 0.0113, "learning_rate": 9.331759945770935e-07, "epoch": 3.586600142551675, "percentage": 71.89, "elapsed_time": "2:17:55", "remaining_time": "0:53:56", "throughput": "502.94", "total_tokens": 4162240} -{"current_steps": 630, "total_steps": 875, "loss": 0.0058, "learning_rate": 9.261110703479531e-07, "epoch": 3.5923022095509625, "percentage": 72.0, "elapsed_time": "2:18:08", "remaining_time": "0:53:43", "throughput": "502.96", "total_tokens": 4169008} -{"current_steps": 631, "total_steps": 875, "loss": 0.0019, "learning_rate": 9.190669067777475e-07, "epoch": 3.5980042765502493, "percentage": 72.11, "elapsed_time": "2:18:22", "remaining_time": "0:53:30", "throughput": "502.94", "total_tokens": 4175488} -{"current_steps": 632, "total_steps": 875, "loss": 0.0443, "learning_rate": 9.120435967837571e-07, "epoch": 3.6037063435495367, "percentage": 72.23, "elapsed_time": "2:18:35", "remaining_time": "0:53:17", "throughput": "502.96", "total_tokens": 4182208} -{"current_steps": 633, "total_steps": 875, "loss": 0.0246, "learning_rate": 9.050412330081885e-07, "epoch": 3.609408410548824, "percentage": 72.34, "elapsed_time": "2:18:48", "remaining_time": "0:53:04", "throughput": "502.92", "total_tokens": 4188512} -{"current_steps": 634, "total_steps": 875, "loss": 0.0039, "learning_rate": 8.980599078169528e-07, "epoch": 3.6151104775481113, "percentage": 72.46, "elapsed_time": "2:19:01", "remaining_time": "0:52:50", "throughput": "502.90", "total_tokens": 4194992} -{"current_steps": 635, "total_steps": 875, "loss": 0.0302, "learning_rate": 8.910997132984481e-07, "epoch": 3.620812544547398, "percentage": 72.57, "elapsed_time": "2:19:14", "remaining_time": "0:52:37", "throughput": "502.90", "total_tokens": 4201632} -{"current_steps": 636, "total_steps": 875, "loss": 0.0039, "learning_rate": 8.841607412623471e-07, "epoch": 3.6265146115466855, "percentage": 72.69, "elapsed_time": "2:19:27", "remaining_time": "0:52:24", "throughput": "502.89", "total_tokens": 4208096} -{"current_steps": 637, "total_steps": 875, "loss": 0.0096, "learning_rate": 8.772430832383797e-07, "epoch": 3.632216678545973, "percentage": 72.8, "elapsed_time": "2:19:41", "remaining_time": "0:52:11", "throughput": "502.89", "total_tokens": 4214720} -{"current_steps": 638, "total_steps": 875, "loss": 0.0314, "learning_rate": 8.703468304751342e-07, "epoch": 3.63791874554526, "percentage": 72.91, "elapsed_time": "2:19:54", "remaining_time": "0:51:58", "throughput": "502.88", "total_tokens": 4221280} -{"current_steps": 639, "total_steps": 875, "loss": 0.0301, "learning_rate": 8.634720739388433e-07, "epoch": 3.6436208125445475, "percentage": 73.03, "elapsed_time": "2:20:07", "remaining_time": "0:51:45", "throughput": "502.86", "total_tokens": 4227744} -{"current_steps": 640, "total_steps": 875, "loss": 0.0012, "learning_rate": 8.566189043121953e-07, "epoch": 3.649322879543835, "percentage": 73.14, "elapsed_time": "2:20:20", "remaining_time": "0:51:31", "throughput": "502.85", "total_tokens": 4234240} -{"current_steps": 641, "total_steps": 875, "loss": 0.001, "learning_rate": 8.49787411993129e-07, "epoch": 3.655024946543122, "percentage": 73.26, "elapsed_time": "2:20:33", "remaining_time": "0:51:18", "throughput": "502.82", "total_tokens": 4240640} -{"current_steps": 642, "total_steps": 875, "loss": 0.0053, "learning_rate": 8.429776870936485e-07, "epoch": 3.660727013542409, "percentage": 73.37, "elapsed_time": "2:20:46", "remaining_time": "0:51:05", "throughput": "502.82", "total_tokens": 4247232} -{"current_steps": 643, "total_steps": 875, "loss": 0.0107, "learning_rate": 8.361898194386251e-07, "epoch": 3.6664290805416964, "percentage": 73.49, "elapsed_time": "2:20:59", "remaining_time": "0:50:52", "throughput": "502.88", "total_tokens": 4254368} -{"current_steps": 644, "total_steps": 875, "loss": 0.0016, "learning_rate": 8.294238985646244e-07, "epoch": 3.6721311475409837, "percentage": 73.6, "elapsed_time": "2:21:13", "remaining_time": "0:50:39", "throughput": "502.88", "total_tokens": 4260992} -{"current_steps": 645, "total_steps": 875, "loss": 0.0109, "learning_rate": 8.22680013718715e-07, "epoch": 3.677833214540271, "percentage": 73.71, "elapsed_time": "2:21:26", "remaining_time": "0:50:26", "throughput": "502.89", "total_tokens": 4267632} -{"current_steps": 646, "total_steps": 875, "loss": 0.0107, "learning_rate": 8.159582538572985e-07, "epoch": 3.683535281539558, "percentage": 73.83, "elapsed_time": "2:21:39", "remaining_time": "0:50:12", "throughput": "502.86", "total_tokens": 4274032} -{"current_steps": 647, "total_steps": 875, "loss": 0.0013, "learning_rate": 8.092587076449304e-07, "epoch": 3.689237348538845, "percentage": 73.94, "elapsed_time": "2:21:52", "remaining_time": "0:49:59", "throughput": "502.86", "total_tokens": 4280608} -{"current_steps": 648, "total_steps": 875, "loss": 0.0097, "learning_rate": 8.025814634531545e-07, "epoch": 3.6949394155381325, "percentage": 74.06, "elapsed_time": "2:22:05", "remaining_time": "0:49:46", "throughput": "502.91", "total_tokens": 4287632} -{"current_steps": 649, "total_steps": 875, "loss": 0.0082, "learning_rate": 7.959266093593343e-07, "epoch": 3.70064148253742, "percentage": 74.17, "elapsed_time": "2:22:18", "remaining_time": "0:49:33", "throughput": "502.94", "total_tokens": 4294560} -{"current_steps": 650, "total_steps": 875, "loss": 0.0209, "learning_rate": 7.892942331454959e-07, "epoch": 3.706343549536707, "percentage": 74.29, "elapsed_time": "2:22:32", "remaining_time": "0:49:20", "throughput": "502.91", "total_tokens": 4300880} -{"current_steps": 651, "total_steps": 875, "loss": 0.0014, "learning_rate": 7.826844222971644e-07, "epoch": 3.7120456165359945, "percentage": 74.4, "elapsed_time": "2:22:45", "remaining_time": "0:49:07", "throughput": "502.94", "total_tokens": 4307776} -{"current_steps": 652, "total_steps": 875, "loss": 0.019, "learning_rate": 7.760972640022127e-07, "epoch": 3.7177476835352814, "percentage": 74.51, "elapsed_time": "2:22:58", "remaining_time": "0:48:54", "throughput": "502.93", "total_tokens": 4314304} -{"current_steps": 653, "total_steps": 875, "loss": 0.0187, "learning_rate": 7.695328451497111e-07, "epoch": 3.7234497505345687, "percentage": 74.63, "elapsed_time": "2:23:11", "remaining_time": "0:48:40", "throughput": "502.90", "total_tokens": 4320656} -{"current_steps": 654, "total_steps": 875, "loss": 0.0118, "learning_rate": 7.629912523287833e-07, "epoch": 3.729151817533856, "percentage": 74.74, "elapsed_time": "2:23:24", "remaining_time": "0:48:27", "throughput": "502.87", "total_tokens": 4327056} -{"current_steps": 655, "total_steps": 875, "loss": 0.0027, "learning_rate": 7.564725718274601e-07, "epoch": 3.7348538845331434, "percentage": 74.86, "elapsed_time": "2:23:37", "remaining_time": "0:48:14", "throughput": "502.88", "total_tokens": 4333712} -{"current_steps": 656, "total_steps": 875, "loss": 0.0088, "learning_rate": 7.49976889631544e-07, "epoch": 3.7405559515324303, "percentage": 74.97, "elapsed_time": "2:23:50", "remaining_time": "0:48:01", "throughput": "502.88", "total_tokens": 4340336} -{"current_steps": 657, "total_steps": 875, "loss": 0.0252, "learning_rate": 7.435042914234733e-07, "epoch": 3.7462580185317176, "percentage": 75.09, "elapsed_time": "2:24:04", "remaining_time": "0:47:48", "throughput": "502.85", "total_tokens": 4346688} -{"current_steps": 658, "total_steps": 875, "loss": 0.003, "learning_rate": 7.370548625811954e-07, "epoch": 3.751960085531005, "percentage": 75.2, "elapsed_time": "2:24:17", "remaining_time": "0:47:35", "throughput": "502.87", "total_tokens": 4353440} -{"current_steps": 659, "total_steps": 875, "loss": 0.0149, "learning_rate": 7.306286881770361e-07, "epoch": 3.7576621525302922, "percentage": 75.31, "elapsed_time": "2:24:30", "remaining_time": "0:47:21", "throughput": "502.85", "total_tokens": 4359952} -{"current_steps": 660, "total_steps": 875, "loss": 0.0009, "learning_rate": 7.242258529765794e-07, "epoch": 3.7633642195295796, "percentage": 75.43, "elapsed_time": "2:24:43", "remaining_time": "0:47:08", "throughput": "502.86", "total_tokens": 4366672} -{"current_steps": 661, "total_steps": 875, "loss": 0.0023, "learning_rate": 7.178464414375496e-07, "epoch": 3.769066286528867, "percentage": 75.54, "elapsed_time": "2:24:56", "remaining_time": "0:46:55", "throughput": "502.85", "total_tokens": 4373136} -{"current_steps": 662, "total_steps": 875, "loss": 0.0062, "learning_rate": 7.114905377086989e-07, "epoch": 3.774768353528154, "percentage": 75.66, "elapsed_time": "2:25:09", "remaining_time": "0:46:42", "throughput": "502.81", "total_tokens": 4379392} -{"current_steps": 663, "total_steps": 875, "loss": 0.0077, "learning_rate": 7.051582256286929e-07, "epoch": 3.780470420527441, "percentage": 75.77, "elapsed_time": "2:25:23", "remaining_time": "0:46:29", "throughput": "502.84", "total_tokens": 4386320} -{"current_steps": 664, "total_steps": 875, "loss": 0.0091, "learning_rate": 6.98849588725009e-07, "epoch": 3.7861724875267284, "percentage": 75.89, "elapsed_time": "2:25:36", "remaining_time": "0:46:16", "throughput": "502.85", "total_tokens": 4393008} -{"current_steps": 665, "total_steps": 875, "loss": 0.0027, "learning_rate": 6.925647102128319e-07, "epoch": 3.7918745545260157, "percentage": 76.0, "elapsed_time": "2:25:49", "remaining_time": "0:46:02", "throughput": "502.86", "total_tokens": 4399680} -{"current_steps": 666, "total_steps": 875, "loss": 0.0048, "learning_rate": 6.863036729939593e-07, "epoch": 3.797576621525303, "percentage": 76.11, "elapsed_time": "2:26:02", "remaining_time": "0:45:49", "throughput": "502.89", "total_tokens": 4406624} -{"current_steps": 667, "total_steps": 875, "loss": 0.0084, "learning_rate": 6.800665596557027e-07, "epoch": 3.80327868852459, "percentage": 76.23, "elapsed_time": "2:26:15", "remaining_time": "0:45:36", "throughput": "502.89", "total_tokens": 4413200} -{"current_steps": 668, "total_steps": 875, "loss": 0.0037, "learning_rate": 6.738534524698057e-07, "epoch": 3.8089807555238773, "percentage": 76.34, "elapsed_time": "2:26:28", "remaining_time": "0:45:23", "throughput": "502.88", "total_tokens": 4419728} -{"current_steps": 669, "total_steps": 875, "loss": 0.0013, "learning_rate": 6.676644333913496e-07, "epoch": 3.8146828225231646, "percentage": 76.46, "elapsed_time": "2:26:41", "remaining_time": "0:45:10", "throughput": "502.88", "total_tokens": 4426320} -{"current_steps": 670, "total_steps": 875, "loss": 0.0099, "learning_rate": 6.614995840576816e-07, "epoch": 3.820384889522452, "percentage": 76.57, "elapsed_time": "2:26:55", "remaining_time": "0:44:57", "throughput": "502.83", "total_tokens": 4432480} -{"current_steps": 671, "total_steps": 875, "loss": 0.0004, "learning_rate": 6.553589857873304e-07, "epoch": 3.8260869565217392, "percentage": 76.69, "elapsed_time": "2:27:08", "remaining_time": "0:44:44", "throughput": "502.79", "total_tokens": 4438784} -{"current_steps": 672, "total_steps": 875, "loss": 0.0196, "learning_rate": 6.4924271957894e-07, "epoch": 3.8317890235210266, "percentage": 76.8, "elapsed_time": "2:27:21", "remaining_time": "0:44:30", "throughput": "502.77", "total_tokens": 4445200} -{"current_steps": 673, "total_steps": 875, "loss": 0.0013, "learning_rate": 6.431508661101954e-07, "epoch": 3.8374910905203135, "percentage": 76.91, "elapsed_time": "2:27:34", "remaining_time": "0:44:17", "throughput": "502.75", "total_tokens": 4451616} -{"current_steps": 674, "total_steps": 875, "loss": 0.0008, "learning_rate": 6.370835057367622e-07, "epoch": 3.8431931575196008, "percentage": 77.03, "elapsed_time": "2:27:47", "remaining_time": "0:44:04", "throughput": "502.70", "total_tokens": 4457808} -{"current_steps": 675, "total_steps": 875, "loss": 0.0177, "learning_rate": 6.31040718491224e-07, "epoch": 3.848895224518888, "percentage": 77.14, "elapsed_time": "2:28:00", "remaining_time": "0:43:51", "throughput": "502.70", "total_tokens": 4464448} -{"current_steps": 676, "total_steps": 875, "loss": 0.0148, "learning_rate": 6.250225840820315e-07, "epoch": 3.8545972915181754, "percentage": 77.26, "elapsed_time": "2:28:14", "remaining_time": "0:43:38", "throughput": "502.71", "total_tokens": 4471168} -{"current_steps": 677, "total_steps": 875, "loss": 0.0012, "learning_rate": 6.190291818924449e-07, "epoch": 3.8602993585174623, "percentage": 77.37, "elapsed_time": "2:28:27", "remaining_time": "0:43:25", "throughput": "502.67", "total_tokens": 4477424} -{"current_steps": 678, "total_steps": 875, "loss": 0.0031, "learning_rate": 6.130605909794907e-07, "epoch": 3.8660014255167496, "percentage": 77.49, "elapsed_time": "2:28:40", "remaining_time": "0:43:11", "throughput": "502.68", "total_tokens": 4484080} -{"current_steps": 679, "total_steps": 875, "loss": 0.0024, "learning_rate": 6.071168900729171e-07, "epoch": 3.871703492516037, "percentage": 77.6, "elapsed_time": "2:28:53", "remaining_time": "0:42:58", "throughput": "502.69", "total_tokens": 4490832} -{"current_steps": 680, "total_steps": 875, "loss": 0.0008, "learning_rate": 6.011981575741583e-07, "epoch": 3.8774055595153243, "percentage": 77.71, "elapsed_time": "2:29:06", "remaining_time": "0:42:45", "throughput": "502.70", "total_tokens": 4497472} -{"current_steps": 681, "total_steps": 875, "loss": 0.0042, "learning_rate": 5.953044715552967e-07, "epoch": 3.8831076265146116, "percentage": 77.83, "elapsed_time": "2:29:19", "remaining_time": "0:42:32", "throughput": "502.69", "total_tokens": 4504064} -{"current_steps": 682, "total_steps": 875, "loss": 0.0235, "learning_rate": 5.894359097580343e-07, "epoch": 3.888809693513899, "percentage": 77.94, "elapsed_time": "2:29:33", "remaining_time": "0:42:19", "throughput": "502.74", "total_tokens": 4511136} -{"current_steps": 683, "total_steps": 875, "loss": 0.0029, "learning_rate": 5.835925495926684e-07, "epoch": 3.8945117605131863, "percentage": 78.06, "elapsed_time": "2:29:46", "remaining_time": "0:42:06", "throughput": "502.79", "total_tokens": 4518176} -{"current_steps": 684, "total_steps": 875, "loss": 0.0037, "learning_rate": 5.777744681370709e-07, "epoch": 3.900213827512473, "percentage": 78.17, "elapsed_time": "2:29:59", "remaining_time": "0:41:52", "throughput": "502.77", "total_tokens": 4524592} -{"current_steps": 685, "total_steps": 875, "loss": 0.0145, "learning_rate": 5.719817421356686e-07, "epoch": 3.9059158945117605, "percentage": 78.29, "elapsed_time": "2:30:12", "remaining_time": "0:41:39", "throughput": "502.77", "total_tokens": 4531216} -{"current_steps": 686, "total_steps": 875, "loss": 0.0093, "learning_rate": 5.662144479984322e-07, "epoch": 3.911617961511048, "percentage": 78.4, "elapsed_time": "2:30:25", "remaining_time": "0:41:26", "throughput": "502.77", "total_tokens": 4537776} -{"current_steps": 687, "total_steps": 875, "loss": 0.0066, "learning_rate": 5.604726617998721e-07, "epoch": 3.917320028510335, "percentage": 78.51, "elapsed_time": "2:30:38", "remaining_time": "0:41:13", "throughput": "502.75", "total_tokens": 4544272} -{"current_steps": 688, "total_steps": 875, "loss": 0.001, "learning_rate": 5.54756459278028e-07, "epoch": 3.923022095509622, "percentage": 78.63, "elapsed_time": "2:30:51", "remaining_time": "0:41:00", "throughput": "502.74", "total_tokens": 4550736} -{"current_steps": 689, "total_steps": 875, "loss": 0.0029, "learning_rate": 5.490659158334774e-07, "epoch": 3.9287241625089093, "percentage": 78.74, "elapsed_time": "2:31:05", "remaining_time": "0:40:47", "throughput": "502.70", "total_tokens": 4557024} -{"current_steps": 690, "total_steps": 875, "loss": 0.0232, "learning_rate": 5.434011065283326e-07, "epoch": 3.9344262295081966, "percentage": 78.86, "elapsed_time": "2:31:18", "remaining_time": "0:40:34", "throughput": "502.71", "total_tokens": 4563712} -{"current_steps": 691, "total_steps": 875, "loss": 0.0004, "learning_rate": 5.377621060852595e-07, "epoch": 3.940128296507484, "percentage": 78.97, "elapsed_time": "2:31:31", "remaining_time": "0:40:20", "throughput": "502.71", "total_tokens": 4570336} -{"current_steps": 692, "total_steps": 875, "loss": 0.0003, "learning_rate": 5.321489888864848e-07, "epoch": 3.9458303635067713, "percentage": 79.09, "elapsed_time": "2:31:44", "remaining_time": "0:40:07", "throughput": "502.72", "total_tokens": 4577008} -{"current_steps": 693, "total_steps": 875, "loss": 0.0011, "learning_rate": 5.2656182897282e-07, "epoch": 3.9515324305060586, "percentage": 79.2, "elapsed_time": "2:31:57", "remaining_time": "0:39:54", "throughput": "502.73", "total_tokens": 4583744} -{"current_steps": 694, "total_steps": 875, "loss": 0.0009, "learning_rate": 5.210007000426812e-07, "epoch": 3.957234497505346, "percentage": 79.31, "elapsed_time": "2:32:10", "remaining_time": "0:39:41", "throughput": "502.74", "total_tokens": 4590432} -{"current_steps": 695, "total_steps": 875, "loss": 0.0009, "learning_rate": 5.154656754511175e-07, "epoch": 3.962936564504633, "percentage": 79.43, "elapsed_time": "2:32:24", "remaining_time": "0:39:28", "throughput": "502.71", "total_tokens": 4596816} -{"current_steps": 696, "total_steps": 875, "loss": 0.0039, "learning_rate": 5.099568282088446e-07, "epoch": 3.96863863150392, "percentage": 79.54, "elapsed_time": "2:32:37", "remaining_time": "0:39:15", "throughput": "502.72", "total_tokens": 4603536} -{"current_steps": 697, "total_steps": 875, "loss": 0.0109, "learning_rate": 5.044742309812833e-07, "epoch": 3.9743406985032075, "percentage": 79.66, "elapsed_time": "2:32:50", "remaining_time": "0:39:01", "throughput": "502.72", "total_tokens": 4610128} -{"current_steps": 698, "total_steps": 875, "loss": 0.0455, "learning_rate": 4.990179560875963e-07, "epoch": 3.980042765502495, "percentage": 79.77, "elapsed_time": "2:33:03", "remaining_time": "0:38:48", "throughput": "502.68", "total_tokens": 4616400} -{"current_steps": 699, "total_steps": 875, "loss": 0.0003, "learning_rate": 4.935880754997377e-07, "epoch": 3.9857448325017817, "percentage": 79.89, "elapsed_time": "2:33:16", "remaining_time": "0:38:35", "throughput": "502.63", "total_tokens": 4622544} -{"current_steps": 700, "total_steps": 875, "loss": 0.0004, "learning_rate": 4.881846608415028e-07, "epoch": 3.991446899501069, "percentage": 80.0, "elapsed_time": "2:33:29", "remaining_time": "0:38:22", "throughput": "502.61", "total_tokens": 4628928} -{"current_steps": 701, "total_steps": 875, "loss": 0.0003, "learning_rate": 4.828077833875849e-07, "epoch": 3.9971489665003563, "percentage": 80.11, "elapsed_time": "2:33:42", "remaining_time": "0:38:09", "throughput": "502.58", "total_tokens": 4635312} -{"current_steps": 702, "total_steps": 875, "loss": 0.0006, "learning_rate": 4.774575140626317e-07, "epoch": 4.002851033499644, "percentage": 80.23, "elapsed_time": "2:33:56", "remaining_time": "0:37:56", "throughput": "502.56", "total_tokens": 4641696} -{"current_steps": 703, "total_steps": 875, "loss": 0.0041, "learning_rate": 4.7213392344031215e-07, "epoch": 4.008553100498931, "percentage": 80.34, "elapsed_time": "2:34:09", "remaining_time": "0:37:42", "throughput": "502.61", "total_tokens": 4648800} -{"current_steps": 704, "total_steps": 875, "loss": 0.0017, "learning_rate": 4.6683708174238506e-07, "epoch": 4.014255167498218, "percentage": 80.46, "elapsed_time": "2:34:22", "remaining_time": "0:37:29", "throughput": "502.61", "total_tokens": 4655392} -{"current_steps": 705, "total_steps": 875, "loss": 0.0003, "learning_rate": 4.6156705883777434e-07, "epoch": 4.019957234497506, "percentage": 80.57, "elapsed_time": "2:34:35", "remaining_time": "0:37:16", "throughput": "502.59", "total_tokens": 4661808} -{"current_steps": 706, "total_steps": 875, "loss": 0.0101, "learning_rate": 4.5632392424164367e-07, "epoch": 4.025659301496793, "percentage": 80.69, "elapsed_time": "2:34:48", "remaining_time": "0:37:03", "throughput": "502.61", "total_tokens": 4668576} -{"current_steps": 707, "total_steps": 875, "loss": 0.0206, "learning_rate": 4.511077471144831e-07, "epoch": 4.031361368496079, "percentage": 80.8, "elapsed_time": "2:35:01", "remaining_time": "0:36:50", "throughput": "502.58", "total_tokens": 4674944} -{"current_steps": 708, "total_steps": 875, "loss": 0.0058, "learning_rate": 4.4591859626119447e-07, "epoch": 4.037063435495367, "percentage": 80.91, "elapsed_time": "2:35:15", "remaining_time": "0:36:37", "throughput": "502.61", "total_tokens": 4681840} -{"current_steps": 709, "total_steps": 875, "loss": 0.0007, "learning_rate": 4.4075654013018635e-07, "epoch": 4.042765502494654, "percentage": 81.03, "elapsed_time": "2:35:28", "remaining_time": "0:36:24", "throughput": "502.62", "total_tokens": 4688528} -{"current_steps": 710, "total_steps": 875, "loss": 0.0035, "learning_rate": 4.3562164681246825e-07, "epoch": 4.048467569493941, "percentage": 81.14, "elapsed_time": "2:35:41", "remaining_time": "0:36:10", "throughput": "502.60", "total_tokens": 4694992} -{"current_steps": 711, "total_steps": 875, "loss": 0.0074, "learning_rate": 4.3051398404075436e-07, "epoch": 4.054169636493229, "percentage": 81.26, "elapsed_time": "2:35:54", "remaining_time": "0:35:57", "throughput": "502.58", "total_tokens": 4701328} -{"current_steps": 712, "total_steps": 875, "loss": 0.0002, "learning_rate": 4.254336191885683e-07, "epoch": 4.059871703492516, "percentage": 81.37, "elapsed_time": "2:36:07", "remaining_time": "0:35:44", "throughput": "502.56", "total_tokens": 4707808} -{"current_steps": 713, "total_steps": 875, "loss": 0.001, "learning_rate": 4.203806192693588e-07, "epoch": 4.065573770491803, "percentage": 81.49, "elapsed_time": "2:36:20", "remaining_time": "0:35:31", "throughput": "502.58", "total_tokens": 4714592} -{"current_steps": 714, "total_steps": 875, "loss": 0.0004, "learning_rate": 4.1535505093560885e-07, "epoch": 4.071275837491091, "percentage": 81.6, "elapsed_time": "2:36:33", "remaining_time": "0:35:18", "throughput": "502.60", "total_tokens": 4721408} -{"current_steps": 715, "total_steps": 875, "loss": 0.0044, "learning_rate": 4.103569804779642e-07, "epoch": 4.076977904490378, "percentage": 81.71, "elapsed_time": "2:36:47", "remaining_time": "0:35:05", "throughput": "502.62", "total_tokens": 4728224} -{"current_steps": 716, "total_steps": 875, "loss": 0.0065, "learning_rate": 4.0538647382435017e-07, "epoch": 4.082679971489665, "percentage": 81.83, "elapsed_time": "2:37:00", "remaining_time": "0:34:51", "throughput": "502.65", "total_tokens": 4735040} -{"current_steps": 717, "total_steps": 875, "loss": 0.0004, "learning_rate": 4.0044359653911183e-07, "epoch": 4.088382038488953, "percentage": 81.94, "elapsed_time": "2:37:13", "remaining_time": "0:34:38", "throughput": "502.64", "total_tokens": 4741584} -{"current_steps": 718, "total_steps": 875, "loss": 0.0044, "learning_rate": 3.955284138221402e-07, "epoch": 4.094084105488239, "percentage": 82.06, "elapsed_time": "2:37:26", "remaining_time": "0:34:25", "throughput": "502.63", "total_tokens": 4748160} -{"current_steps": 719, "total_steps": 875, "loss": 0.0111, "learning_rate": 3.9064099050802024e-07, "epoch": 4.099786172487526, "percentage": 82.17, "elapsed_time": "2:37:39", "remaining_time": "0:34:12", "throughput": "502.63", "total_tokens": 4754752} -{"current_steps": 720, "total_steps": 875, "loss": 0.0123, "learning_rate": 3.85781391065167e-07, "epoch": 4.105488239486814, "percentage": 82.29, "elapsed_time": "2:37:52", "remaining_time": "0:33:59", "throughput": "502.61", "total_tokens": 4761168} -{"current_steps": 721, "total_steps": 875, "loss": 0.0011, "learning_rate": 3.809496795949838e-07, "epoch": 4.111190306486101, "percentage": 82.4, "elapsed_time": "2:38:05", "remaining_time": "0:33:46", "throughput": "502.57", "total_tokens": 4767376} -{"current_steps": 722, "total_steps": 875, "loss": 0.0002, "learning_rate": 3.7614591983100995e-07, "epoch": 4.116892373485388, "percentage": 82.51, "elapsed_time": "2:38:19", "remaining_time": "0:33:32", "throughput": "502.60", "total_tokens": 4774224} -{"current_steps": 723, "total_steps": 875, "loss": 0.002, "learning_rate": 3.713701751380855e-07, "epoch": 4.122594440484676, "percentage": 82.63, "elapsed_time": "2:38:32", "remaining_time": "0:33:19", "throughput": "502.58", "total_tokens": 4780656} -{"current_steps": 724, "total_steps": 875, "loss": 0.004, "learning_rate": 3.666225085115108e-07, "epoch": 4.128296507483963, "percentage": 82.74, "elapsed_time": "2:38:45", "remaining_time": "0:33:06", "throughput": "502.54", "total_tokens": 4786944} -{"current_steps": 725, "total_steps": 875, "loss": 0.001, "learning_rate": 3.619029825762177e-07, "epoch": 4.13399857448325, "percentage": 82.86, "elapsed_time": "2:38:58", "remaining_time": "0:32:53", "throughput": "502.54", "total_tokens": 4793488} -{"current_steps": 726, "total_steps": 875, "loss": 0.0013, "learning_rate": 3.5721165958594345e-07, "epoch": 4.139700641482538, "percentage": 82.97, "elapsed_time": "2:39:11", "remaining_time": "0:32:40", "throughput": "502.51", "total_tokens": 4799872} -{"current_steps": 727, "total_steps": 875, "loss": 0.0002, "learning_rate": 3.525486014224108e-07, "epoch": 4.145402708481825, "percentage": 83.09, "elapsed_time": "2:39:24", "remaining_time": "0:32:27", "throughput": "502.53", "total_tokens": 4806656} -{"current_steps": 728, "total_steps": 875, "loss": 0.0006, "learning_rate": 3.479138695945086e-07, "epoch": 4.151104775481112, "percentage": 83.2, "elapsed_time": "2:39:38", "remaining_time": "0:32:14", "throughput": "502.55", "total_tokens": 4813408} -{"current_steps": 729, "total_steps": 875, "loss": 0.0011, "learning_rate": 3.433075252374826e-07, "epoch": 4.156806842480399, "percentage": 83.31, "elapsed_time": "2:39:51", "remaining_time": "0:32:00", "throughput": "502.53", "total_tokens": 4819904} -{"current_steps": 730, "total_steps": 875, "loss": 0.0046, "learning_rate": 3.3872962911212836e-07, "epoch": 4.162508909479686, "percentage": 83.43, "elapsed_time": "2:40:04", "remaining_time": "0:31:47", "throughput": "502.57", "total_tokens": 4826848} -{"current_steps": 731, "total_steps": 875, "loss": 0.0026, "learning_rate": 3.341802416039913e-07, "epoch": 4.168210976478973, "percentage": 83.54, "elapsed_time": "2:40:17", "remaining_time": "0:31:34", "throughput": "502.59", "total_tokens": 4833648} -{"current_steps": 732, "total_steps": 875, "loss": 0.0045, "learning_rate": 3.296594227225677e-07, "epoch": 4.173913043478261, "percentage": 83.66, "elapsed_time": "2:40:30", "remaining_time": "0:31:21", "throughput": "502.56", "total_tokens": 4840000} -{"current_steps": 733, "total_steps": 875, "loss": 0.0154, "learning_rate": 3.2516723210051476e-07, "epoch": 4.179615110477548, "percentage": 83.77, "elapsed_time": "2:40:43", "remaining_time": "0:31:08", "throughput": "502.55", "total_tokens": 4846544} -{"current_steps": 734, "total_steps": 875, "loss": 0.0009, "learning_rate": 3.20703728992863e-07, "epoch": 4.185317177476835, "percentage": 83.89, "elapsed_time": "2:40:56", "remaining_time": "0:30:55", "throughput": "502.57", "total_tokens": 4853344} -{"current_steps": 735, "total_steps": 875, "loss": 0.0002, "learning_rate": 3.162689722762366e-07, "epoch": 4.191019244476123, "percentage": 84.0, "elapsed_time": "2:41:10", "remaining_time": "0:30:41", "throughput": "502.58", "total_tokens": 4860016} -{"current_steps": 736, "total_steps": 875, "loss": 0.0005, "learning_rate": 3.118630204480741e-07, "epoch": 4.19672131147541, "percentage": 84.11, "elapsed_time": "2:41:23", "remaining_time": "0:30:28", "throughput": "502.60", "total_tokens": 4866816} -{"current_steps": 737, "total_steps": 875, "loss": 0.0021, "learning_rate": 3.0748593162585853e-07, "epoch": 4.202423378474697, "percentage": 84.23, "elapsed_time": "2:41:36", "remaining_time": "0:30:15", "throughput": "502.57", "total_tokens": 4873168} -{"current_steps": 738, "total_steps": 875, "loss": 0.0006, "learning_rate": 3.0313776354635005e-07, "epoch": 4.208125445473985, "percentage": 84.34, "elapsed_time": "2:41:49", "remaining_time": "0:30:02", "throughput": "502.57", "total_tokens": 4879776} -{"current_steps": 739, "total_steps": 875, "loss": 0.0359, "learning_rate": 2.988185735648258e-07, "epoch": 4.213827512473271, "percentage": 84.46, "elapsed_time": "2:42:02", "remaining_time": "0:29:49", "throughput": "502.61", "total_tokens": 4886720} -{"current_steps": 740, "total_steps": 875, "loss": 0.0002, "learning_rate": 2.9452841865432126e-07, "epoch": 4.2195295794725585, "percentage": 84.57, "elapsed_time": "2:42:15", "remaining_time": "0:29:36", "throughput": "502.61", "total_tokens": 4893376} -{"current_steps": 741, "total_steps": 875, "loss": 0.0093, "learning_rate": 2.902673554048793e-07, "epoch": 4.225231646471846, "percentage": 84.69, "elapsed_time": "2:42:29", "remaining_time": "0:29:22", "throughput": "502.61", "total_tokens": 4899984} -{"current_steps": 742, "total_steps": 875, "loss": 0.0011, "learning_rate": 2.8603544002280463e-07, "epoch": 4.230933713471133, "percentage": 84.8, "elapsed_time": "2:42:42", "remaining_time": "0:29:09", "throughput": "502.63", "total_tokens": 4906800} -{"current_steps": 743, "total_steps": 875, "loss": 0.0014, "learning_rate": 2.818327283299227e-07, "epoch": 4.23663578047042, "percentage": 84.91, "elapsed_time": "2:42:55", "remaining_time": "0:28:56", "throughput": "502.62", "total_tokens": 4913296} -{"current_steps": 744, "total_steps": 875, "loss": 0.0041, "learning_rate": 2.7765927576284076e-07, "epoch": 4.242337847469708, "percentage": 85.03, "elapsed_time": "2:43:08", "remaining_time": "0:28:43", "throughput": "502.61", "total_tokens": 4919808} -{"current_steps": 745, "total_steps": 875, "loss": 0.0077, "learning_rate": 2.735151373722214e-07, "epoch": 4.248039914468995, "percentage": 85.14, "elapsed_time": "2:43:21", "remaining_time": "0:28:30", "throughput": "502.59", "total_tokens": 4926176} -{"current_steps": 746, "total_steps": 875, "loss": 0.0005, "learning_rate": 2.694003678220489e-07, "epoch": 4.253741981468282, "percentage": 85.26, "elapsed_time": "2:43:34", "remaining_time": "0:28:17", "throughput": "502.55", "total_tokens": 4932480} -{"current_steps": 747, "total_steps": 875, "loss": 0.0015, "learning_rate": 2.6531502138891665e-07, "epoch": 4.25944404846757, "percentage": 85.37, "elapsed_time": "2:43:47", "remaining_time": "0:28:04", "throughput": "502.56", "total_tokens": 4939104} -{"current_steps": 748, "total_steps": 875, "loss": 0.0072, "learning_rate": 2.612591519613053e-07, "epoch": 4.265146115466857, "percentage": 85.49, "elapsed_time": "2:44:01", "remaining_time": "0:27:50", "throughput": "502.56", "total_tokens": 4945728} -{"current_steps": 749, "total_steps": 875, "loss": 0.001, "learning_rate": 2.5723281303887545e-07, "epoch": 4.270848182466144, "percentage": 85.6, "elapsed_time": "2:44:14", "remaining_time": "0:27:37", "throughput": "502.55", "total_tokens": 4952240} -{"current_steps": 750, "total_steps": 875, "loss": 0.0043, "learning_rate": 2.5323605773175775e-07, "epoch": 4.276550249465431, "percentage": 85.71, "elapsed_time": "2:44:27", "remaining_time": "0:27:24", "throughput": "502.54", "total_tokens": 4958752} -{"current_steps": 751, "total_steps": 875, "loss": 0.003, "learning_rate": 2.4926893875985766e-07, "epoch": 4.282252316464718, "percentage": 85.83, "elapsed_time": "2:44:40", "remaining_time": "0:27:11", "throughput": "502.54", "total_tokens": 4965376} -{"current_steps": 752, "total_steps": 875, "loss": 0.0047, "learning_rate": 2.4533150845215514e-07, "epoch": 4.2879543834640055, "percentage": 85.94, "elapsed_time": "2:44:53", "remaining_time": "0:26:58", "throughput": "502.51", "total_tokens": 4971680} -{"current_steps": 753, "total_steps": 875, "loss": 0.0004, "learning_rate": 2.414238187460191e-07, "epoch": 4.293656450463293, "percentage": 86.06, "elapsed_time": "2:45:06", "remaining_time": "0:26:45", "throughput": "502.52", "total_tokens": 4978368} -{"current_steps": 754, "total_steps": 875, "loss": 0.0004, "learning_rate": 2.3754592118651748e-07, "epoch": 4.29935851746258, "percentage": 86.17, "elapsed_time": "2:45:20", "remaining_time": "0:26:31", "throughput": "502.50", "total_tokens": 4984816} -{"current_steps": 755, "total_steps": 875, "loss": 0.0036, "learning_rate": 2.336978669257406e-07, "epoch": 4.3050605844618675, "percentage": 86.29, "elapsed_time": "2:45:33", "remaining_time": "0:26:18", "throughput": "502.52", "total_tokens": 4991648} -{"current_steps": 756, "total_steps": 875, "loss": 0.0004, "learning_rate": 2.2987970672212506e-07, "epoch": 4.310762651461155, "percentage": 86.4, "elapsed_time": "2:45:46", "remaining_time": "0:26:05", "throughput": "502.49", "total_tokens": 4997904} -{"current_steps": 757, "total_steps": 875, "loss": 0.0003, "learning_rate": 2.26091490939786e-07, "epoch": 4.316464718460442, "percentage": 86.51, "elapsed_time": "2:45:59", "remaining_time": "0:25:52", "throughput": "502.49", "total_tokens": 5004592} -{"current_steps": 758, "total_steps": 875, "loss": 0.0089, "learning_rate": 2.2233326954785e-07, "epoch": 4.322166785459729, "percentage": 86.63, "elapsed_time": "2:46:12", "remaining_time": "0:25:39", "throughput": "502.49", "total_tokens": 5011152} -{"current_steps": 759, "total_steps": 875, "loss": 0.0002, "learning_rate": 2.186050921197974e-07, "epoch": 4.327868852459017, "percentage": 86.74, "elapsed_time": "2:46:25", "remaining_time": "0:25:26", "throughput": "502.50", "total_tokens": 5017888} -{"current_steps": 760, "total_steps": 875, "loss": 0.0002, "learning_rate": 2.149070078328089e-07, "epoch": 4.333570919458303, "percentage": 86.86, "elapsed_time": "2:46:38", "remaining_time": "0:25:12", "throughput": "502.52", "total_tokens": 5024656} -{"current_steps": 761, "total_steps": 875, "loss": 0.0033, "learning_rate": 2.1123906546711675e-07, "epoch": 4.3392729864575905, "percentage": 86.97, "elapsed_time": "2:46:52", "remaining_time": "0:24:59", "throughput": "502.49", "total_tokens": 5030944} -{"current_steps": 762, "total_steps": 875, "loss": 0.0109, "learning_rate": 2.0760131340536006e-07, "epoch": 4.344975053456878, "percentage": 87.09, "elapsed_time": "2:47:05", "remaining_time": "0:24:46", "throughput": "502.49", "total_tokens": 5037584} -{"current_steps": 763, "total_steps": 875, "loss": 0.0031, "learning_rate": 2.0399379963194715e-07, "epoch": 4.350677120456165, "percentage": 87.2, "elapsed_time": "2:47:18", "remaining_time": "0:24:33", "throughput": "502.46", "total_tokens": 5043904} -{"current_steps": 764, "total_steps": 875, "loss": 0.0005, "learning_rate": 2.004165717324233e-07, "epoch": 4.3563791874554525, "percentage": 87.31, "elapsed_time": "2:47:31", "remaining_time": "0:24:20", "throughput": "502.43", "total_tokens": 5050256} -{"current_steps": 765, "total_steps": 875, "loss": 0.0006, "learning_rate": 1.9686967689284354e-07, "epoch": 4.36208125445474, "percentage": 87.43, "elapsed_time": "2:47:44", "remaining_time": "0:24:07", "throughput": "502.45", "total_tokens": 5057056} -{"current_steps": 766, "total_steps": 875, "loss": 0.0035, "learning_rate": 1.9335316189914826e-07, "epoch": 4.367783321454027, "percentage": 87.54, "elapsed_time": "2:47:57", "remaining_time": "0:23:54", "throughput": "502.43", "total_tokens": 5063472} -{"current_steps": 767, "total_steps": 875, "loss": 0.0143, "learning_rate": 1.8986707313654707e-07, "epoch": 4.3734853884533145, "percentage": 87.66, "elapsed_time": "2:48:11", "remaining_time": "0:23:40", "throughput": "502.44", "total_tokens": 5070160} -{"current_steps": 768, "total_steps": 875, "loss": 0.0037, "learning_rate": 1.864114565889069e-07, "epoch": 4.379187455452602, "percentage": 87.77, "elapsed_time": "2:48:24", "remaining_time": "0:23:27", "throughput": "502.44", "total_tokens": 5076784} -{"current_steps": 769, "total_steps": 875, "loss": 0.0082, "learning_rate": 1.8298635783814743e-07, "epoch": 4.384889522451889, "percentage": 87.89, "elapsed_time": "2:48:37", "remaining_time": "0:23:14", "throughput": "502.43", "total_tokens": 5083280} -{"current_steps": 770, "total_steps": 875, "loss": 0.0003, "learning_rate": 1.7959182206363502e-07, "epoch": 4.3905915894511764, "percentage": 88.0, "elapsed_time": "2:48:50", "remaining_time": "0:23:01", "throughput": "502.42", "total_tokens": 5089824} -{"current_steps": 771, "total_steps": 875, "loss": 0.0156, "learning_rate": 1.7622789404159318e-07, "epoch": 4.396293656450463, "percentage": 88.11, "elapsed_time": "2:49:03", "remaining_time": "0:22:48", "throughput": "502.40", "total_tokens": 5096176} -{"current_steps": 772, "total_steps": 875, "loss": 0.0003, "learning_rate": 1.728946181445043e-07, "epoch": 4.40199572344975, "percentage": 88.23, "elapsed_time": "2:49:16", "remaining_time": "0:22:35", "throughput": "502.40", "total_tokens": 5102784} -{"current_steps": 773, "total_steps": 875, "loss": 0.0028, "learning_rate": 1.6959203834053224e-07, "epoch": 4.4076977904490375, "percentage": 88.34, "elapsed_time": "2:49:29", "remaining_time": "0:22:21", "throughput": "502.41", "total_tokens": 5109504} -{"current_steps": 774, "total_steps": 875, "loss": 0.0002, "learning_rate": 1.6632019819293632e-07, "epoch": 4.413399857448325, "percentage": 88.46, "elapsed_time": "2:49:43", "remaining_time": "0:22:08", "throughput": "502.42", "total_tokens": 5116240} -{"current_steps": 775, "total_steps": 875, "loss": 0.0109, "learning_rate": 1.6307914085950117e-07, "epoch": 4.419101924447612, "percentage": 88.57, "elapsed_time": "2:49:56", "remaining_time": "0:21:55", "throughput": "502.40", "total_tokens": 5122576} -{"current_steps": 776, "total_steps": 875, "loss": 0.0214, "learning_rate": 1.5986890909196224e-07, "epoch": 4.4248039914468995, "percentage": 88.69, "elapsed_time": "2:50:09", "remaining_time": "0:21:42", "throughput": "502.38", "total_tokens": 5128976} -{"current_steps": 777, "total_steps": 875, "loss": 0.0004, "learning_rate": 1.5668954523544776e-07, "epoch": 4.430506058446187, "percentage": 88.8, "elapsed_time": "2:50:22", "remaining_time": "0:21:29", "throughput": "502.36", "total_tokens": 5135456} -{"current_steps": 778, "total_steps": 875, "loss": 0.0034, "learning_rate": 1.535410912279159e-07, "epoch": 4.436208125445474, "percentage": 88.91, "elapsed_time": "2:50:35", "remaining_time": "0:21:16", "throughput": "502.36", "total_tokens": 5142000} -{"current_steps": 779, "total_steps": 875, "loss": 0.0014, "learning_rate": 1.504235885996036e-07, "epoch": 4.4419101924447615, "percentage": 89.03, "elapsed_time": "2:50:48", "remaining_time": "0:21:03", "throughput": "502.37", "total_tokens": 5148704} -{"current_steps": 780, "total_steps": 875, "loss": 0.0012, "learning_rate": 1.4733707847247814e-07, "epoch": 4.447612259444049, "percentage": 89.14, "elapsed_time": "2:51:02", "remaining_time": "0:20:49", "throughput": "502.38", "total_tokens": 5155472} -{"current_steps": 781, "total_steps": 875, "loss": 0.0009, "learning_rate": 1.4428160155969402e-07, "epoch": 4.453314326443335, "percentage": 89.26, "elapsed_time": "2:51:15", "remaining_time": "0:20:36", "throughput": "502.38", "total_tokens": 5162096} -{"current_steps": 782, "total_steps": 875, "loss": 0.0038, "learning_rate": 1.4125719816505761e-07, "epoch": 4.459016393442623, "percentage": 89.37, "elapsed_time": "2:51:28", "remaining_time": "0:20:23", "throughput": "502.41", "total_tokens": 5168944} -{"current_steps": 783, "total_steps": 875, "loss": 0.0003, "learning_rate": 1.3826390818249434e-07, "epoch": 4.46471846044191, "percentage": 89.49, "elapsed_time": "2:51:41", "remaining_time": "0:20:10", "throughput": "502.39", "total_tokens": 5175328} -{"current_steps": 784, "total_steps": 875, "loss": 0.0009, "learning_rate": 1.3530177109552233e-07, "epoch": 4.470420527441197, "percentage": 89.6, "elapsed_time": "2:51:54", "remaining_time": "0:19:57", "throughput": "502.40", "total_tokens": 5182032} -{"current_steps": 785, "total_steps": 875, "loss": 0.012, "learning_rate": 1.3237082597673173e-07, "epoch": 4.4761225944404845, "percentage": 89.71, "elapsed_time": "2:52:07", "remaining_time": "0:19:44", "throughput": "502.45", "total_tokens": 5189200} -{"current_steps": 786, "total_steps": 875, "loss": 0.0003, "learning_rate": 1.294711114872707e-07, "epoch": 4.481824661439772, "percentage": 89.83, "elapsed_time": "2:52:20", "remaining_time": "0:19:30", "throughput": "502.47", "total_tokens": 5195968} -{"current_steps": 787, "total_steps": 875, "loss": 0.0001, "learning_rate": 1.2660266587633334e-07, "epoch": 4.487526728439059, "percentage": 89.94, "elapsed_time": "2:52:34", "remaining_time": "0:19:17", "throughput": "502.46", "total_tokens": 5202528} -{"current_steps": 788, "total_steps": 875, "loss": 0.0066, "learning_rate": 1.2376552698065647e-07, "epoch": 4.4932287954383465, "percentage": 90.06, "elapsed_time": "2:52:47", "remaining_time": "0:19:04", "throughput": "502.44", "total_tokens": 5208944} -{"current_steps": 789, "total_steps": 875, "loss": 0.0001, "learning_rate": 1.2095973222401914e-07, "epoch": 4.498930862437634, "percentage": 90.17, "elapsed_time": "2:53:00", "remaining_time": "0:18:51", "throughput": "502.48", "total_tokens": 5215888} -{"current_steps": 790, "total_steps": 875, "loss": 0.0008, "learning_rate": 1.1818531861675226e-07, "epoch": 4.504632929436921, "percentage": 90.29, "elapsed_time": "2:53:13", "remaining_time": "0:18:38", "throughput": "502.49", "total_tokens": 5222608} -{"current_steps": 791, "total_steps": 875, "loss": 0.0001, "learning_rate": 1.1544232275524592e-07, "epoch": 4.5103349964362085, "percentage": 90.4, "elapsed_time": "2:53:26", "remaining_time": "0:18:25", "throughput": "502.52", "total_tokens": 5229600} -{"current_steps": 792, "total_steps": 875, "loss": 0.0001, "learning_rate": 1.1273078082147059e-07, "epoch": 4.516037063435496, "percentage": 90.51, "elapsed_time": "2:53:39", "remaining_time": "0:18:11", "throughput": "502.54", "total_tokens": 5236368} -{"current_steps": 793, "total_steps": 875, "loss": 0.0007, "learning_rate": 1.1005072858249616e-07, "epoch": 4.521739130434782, "percentage": 90.63, "elapsed_time": "2:53:52", "remaining_time": "0:17:58", "throughput": "502.57", "total_tokens": 5243296} -{"current_steps": 794, "total_steps": 875, "loss": 0.0003, "learning_rate": 1.0740220139002445e-07, "epoch": 4.52744119743407, "percentage": 90.74, "elapsed_time": "2:54:06", "remaining_time": "0:17:45", "throughput": "502.57", "total_tokens": 5249952} -{"current_steps": 795, "total_steps": 875, "loss": 0.0034, "learning_rate": 1.0478523417991882e-07, "epoch": 4.533143264433357, "percentage": 90.86, "elapsed_time": "2:54:19", "remaining_time": "0:17:32", "throughput": "502.65", "total_tokens": 5257328} -{"current_steps": 796, "total_steps": 875, "loss": 0.0004, "learning_rate": 1.0219986147174705e-07, "epoch": 4.538845331432644, "percentage": 90.97, "elapsed_time": "2:54:32", "remaining_time": "0:17:19", "throughput": "502.71", "total_tokens": 5264608} -{"current_steps": 797, "total_steps": 875, "loss": 0.0003, "learning_rate": 9.964611736832109e-08, "epoch": 4.544547398431932, "percentage": 91.09, "elapsed_time": "2:54:45", "remaining_time": "0:17:06", "throughput": "502.68", "total_tokens": 5270928} -{"current_steps": 798, "total_steps": 875, "loss": 0.0002, "learning_rate": 9.712403555525357e-08, "epoch": 4.550249465431219, "percentage": 91.2, "elapsed_time": "2:54:58", "remaining_time": "0:16:53", "throughput": "502.67", "total_tokens": 5277408} -{"current_steps": 799, "total_steps": 875, "loss": 0.0097, "learning_rate": 9.463364930050762e-08, "epoch": 4.555951532430506, "percentage": 91.31, "elapsed_time": "2:55:11", "remaining_time": "0:16:39", "throughput": "502.70", "total_tokens": 5284304} -{"current_steps": 800, "total_steps": 875, "loss": 0.0002, "learning_rate": 9.217499145396187e-08, "epoch": 4.5616535994297935, "percentage": 91.43, "elapsed_time": "2:55:25", "remaining_time": "0:16:26", "throughput": "502.69", "total_tokens": 5290816} -{"current_steps": 801, "total_steps": 875, "loss": 0.0029, "learning_rate": 8.97480944469753e-08, "epoch": 4.567355666429081, "percentage": 91.54, "elapsed_time": "2:55:38", "remaining_time": "0:16:13", "throughput": "502.71", "total_tokens": 5297680} -{"current_steps": 802, "total_steps": 875, "loss": 0.0059, "learning_rate": 8.73529902919601e-08, "epoch": 4.573057733428367, "percentage": 91.66, "elapsed_time": "2:55:51", "remaining_time": "0:16:00", "throughput": "502.73", "total_tokens": 5304464} -{"current_steps": 803, "total_steps": 875, "loss": 0.0001, "learning_rate": 8.498971058195887e-08, "epoch": 4.578759800427655, "percentage": 91.77, "elapsed_time": "2:56:04", "remaining_time": "0:15:47", "throughput": "502.73", "total_tokens": 5311072} -{"current_steps": 804, "total_steps": 875, "loss": 0.0004, "learning_rate": 8.265828649022867e-08, "epoch": 4.584461867426942, "percentage": 91.89, "elapsed_time": "2:56:17", "remaining_time": "0:15:34", "throughput": "502.74", "total_tokens": 5317776} -{"current_steps": 805, "total_steps": 875, "loss": 0.0002, "learning_rate": 8.035874876982957e-08, "epoch": 4.590163934426229, "percentage": 92.0, "elapsed_time": "2:56:30", "remaining_time": "0:15:20", "throughput": "502.71", "total_tokens": 5324160} -{"current_steps": 806, "total_steps": 875, "loss": 0.004, "learning_rate": 7.809112775321869e-08, "epoch": 4.595866001425517, "percentage": 92.11, "elapsed_time": "2:56:43", "remaining_time": "0:15:07", "throughput": "502.71", "total_tokens": 5330768} -{"current_steps": 807, "total_steps": 875, "loss": 0.0013, "learning_rate": 7.585545335184935e-08, "epoch": 4.601568068424804, "percentage": 92.23, "elapsed_time": "2:56:57", "remaining_time": "0:14:54", "throughput": "502.71", "total_tokens": 5337376} -{"current_steps": 808, "total_steps": 875, "loss": 0.0011, "learning_rate": 7.365175505577915e-08, "epoch": 4.607270135424091, "percentage": 92.34, "elapsed_time": "2:57:10", "remaining_time": "0:14:41", "throughput": "502.72", "total_tokens": 5344080} -{"current_steps": 809, "total_steps": 875, "loss": 0.0017, "learning_rate": 7.148006193327783e-08, "epoch": 4.612972202423379, "percentage": 92.46, "elapsed_time": "2:57:23", "remaining_time": "0:14:28", "throughput": "502.70", "total_tokens": 5350448} -{"current_steps": 810, "total_steps": 875, "loss": 0.0049, "learning_rate": 6.93404026304459e-08, "epoch": 4.618674269422666, "percentage": 92.57, "elapsed_time": "2:57:36", "remaining_time": "0:14:15", "throughput": "502.67", "total_tokens": 5356800} -{"current_steps": 811, "total_steps": 875, "loss": 0.0047, "learning_rate": 6.723280537083571e-08, "epoch": 4.624376336421953, "percentage": 92.69, "elapsed_time": "2:57:49", "remaining_time": "0:14:02", "throughput": "502.64", "total_tokens": 5363056} -{"current_steps": 812, "total_steps": 875, "loss": 0.0001, "learning_rate": 6.515729795508019e-08, "epoch": 4.6300784034212406, "percentage": 92.8, "elapsed_time": "2:58:02", "remaining_time": "0:13:48", "throughput": "502.60", "total_tokens": 5369280} -{"current_steps": 813, "total_steps": 875, "loss": 0.0002, "learning_rate": 6.311390776052529e-08, "epoch": 4.635780470420528, "percentage": 92.91, "elapsed_time": "2:58:16", "remaining_time": "0:13:35", "throughput": "502.62", "total_tokens": 5376016} -{"current_steps": 814, "total_steps": 875, "loss": 0.0003, "learning_rate": 6.110266174086859e-08, "epoch": 4.641482537419814, "percentage": 93.03, "elapsed_time": "2:58:29", "remaining_time": "0:13:22", "throughput": "502.63", "total_tokens": 5382768} -{"current_steps": 815, "total_steps": 875, "loss": 0.0098, "learning_rate": 5.912358642580496e-08, "epoch": 4.647184604419102, "percentage": 93.14, "elapsed_time": "2:58:42", "remaining_time": "0:13:09", "throughput": "502.61", "total_tokens": 5389200} -{"current_steps": 816, "total_steps": 875, "loss": 0.0014, "learning_rate": 5.717670792067587e-08, "epoch": 4.652886671418389, "percentage": 93.26, "elapsed_time": "2:58:55", "remaining_time": "0:12:56", "throughput": "502.61", "total_tokens": 5395776} -{"current_steps": 817, "total_steps": 875, "loss": 0.0006, "learning_rate": 5.526205190612449e-08, "epoch": 4.658588738417676, "percentage": 93.37, "elapsed_time": "2:59:08", "remaining_time": "0:12:43", "throughput": "502.64", "total_tokens": 5402688} -{"current_steps": 818, "total_steps": 875, "loss": 0.0099, "learning_rate": 5.337964363775816e-08, "epoch": 4.664290805416964, "percentage": 93.49, "elapsed_time": "2:59:21", "remaining_time": "0:12:29", "throughput": "502.62", "total_tokens": 5409152} -{"current_steps": 819, "total_steps": 875, "loss": 0.0019, "learning_rate": 5.1529507945814185e-08, "epoch": 4.669992872416251, "percentage": 93.6, "elapsed_time": "2:59:34", "remaining_time": "0:12:16", "throughput": "502.62", "total_tokens": 5415744} -{"current_steps": 820, "total_steps": 875, "loss": 0.0009, "learning_rate": 4.971166923483372e-08, "epoch": 4.675694939415538, "percentage": 93.71, "elapsed_time": "2:59:48", "remaining_time": "0:12:03", "throughput": "502.59", "total_tokens": 5422048} -{"current_steps": 821, "total_steps": 875, "loss": 0.0189, "learning_rate": 4.792615148333735e-08, "epoch": 4.681397006414826, "percentage": 93.83, "elapsed_time": "3:00:01", "remaining_time": "0:11:50", "throughput": "502.57", "total_tokens": 5428368} -{"current_steps": 822, "total_steps": 875, "loss": 0.0001, "learning_rate": 4.617297824351219e-08, "epoch": 4.687099073414113, "percentage": 93.94, "elapsed_time": "3:00:14", "remaining_time": "0:11:37", "throughput": "502.56", "total_tokens": 5434960} -{"current_steps": 823, "total_steps": 875, "loss": 0.0075, "learning_rate": 4.4452172640897515e-08, "epoch": 4.6928011404134, "percentage": 94.06, "elapsed_time": "3:00:27", "remaining_time": "0:11:24", "throughput": "502.58", "total_tokens": 5441776} -{"current_steps": 824, "total_steps": 875, "loss": 0.0004, "learning_rate": 4.2763757374083006e-08, "epoch": 4.698503207412687, "percentage": 94.17, "elapsed_time": "3:00:40", "remaining_time": "0:11:10", "throughput": "502.62", "total_tokens": 5448768} -{"current_steps": 825, "total_steps": 875, "loss": 0.0002, "learning_rate": 4.110775471440703e-08, "epoch": 4.704205274411974, "percentage": 94.29, "elapsed_time": "3:00:53", "remaining_time": "0:10:57", "throughput": "502.63", "total_tokens": 5455472} -{"current_steps": 826, "total_steps": 875, "loss": 0.0004, "learning_rate": 3.948418650566499e-08, "epoch": 4.709907341411261, "percentage": 94.4, "elapsed_time": "3:01:07", "remaining_time": "0:10:44", "throughput": "502.61", "total_tokens": 5461856} -{"current_steps": 827, "total_steps": 875, "loss": 0.0015, "learning_rate": 3.7893074163817824e-08, "epoch": 4.715609408410549, "percentage": 94.51, "elapsed_time": "3:01:20", "remaining_time": "0:10:31", "throughput": "502.62", "total_tokens": 5468608} -{"current_steps": 828, "total_steps": 875, "loss": 0.0002, "learning_rate": 3.633443867671393e-08, "epoch": 4.721311475409836, "percentage": 94.63, "elapsed_time": "3:01:33", "remaining_time": "0:10:18", "throughput": "502.62", "total_tokens": 5475216} -{"current_steps": 829, "total_steps": 875, "loss": 0.0137, "learning_rate": 3.4808300603808574e-08, "epoch": 4.727013542409123, "percentage": 94.74, "elapsed_time": "3:01:46", "remaining_time": "0:10:05", "throughput": "502.63", "total_tokens": 5481952} -{"current_steps": 830, "total_steps": 875, "loss": 0.0004, "learning_rate": 3.331468007589489e-08, "epoch": 4.732715609408411, "percentage": 94.86, "elapsed_time": "3:01:59", "remaining_time": "0:09:52", "throughput": "502.64", "total_tokens": 5488720} -{"current_steps": 831, "total_steps": 875, "loss": 0.0006, "learning_rate": 3.18535967948369e-08, "epoch": 4.738417676407698, "percentage": 94.97, "elapsed_time": "3:02:12", "remaining_time": "0:09:38", "throughput": "502.65", "total_tokens": 5495440} -{"current_steps": 832, "total_steps": 875, "loss": 0.0003, "learning_rate": 3.042507003331141e-08, "epoch": 4.744119743406985, "percentage": 95.09, "elapsed_time": "3:02:25", "remaining_time": "0:09:25", "throughput": "502.64", "total_tokens": 5501840} -{"current_steps": 833, "total_steps": 875, "loss": 0.0006, "learning_rate": 2.902911863455121e-08, "epoch": 4.749821810406273, "percentage": 95.2, "elapsed_time": "3:02:39", "remaining_time": "0:09:12", "throughput": "502.61", "total_tokens": 5508192} -{"current_steps": 834, "total_steps": 875, "loss": 0.0064, "learning_rate": 2.7665761012099777e-08, "epoch": 4.75552387740556, "percentage": 95.31, "elapsed_time": "3:02:52", "remaining_time": "0:08:59", "throughput": "502.61", "total_tokens": 5514832} -{"current_steps": 835, "total_steps": 875, "loss": 0.01, "learning_rate": 2.6335015149565324e-08, "epoch": 4.761225944404847, "percentage": 95.43, "elapsed_time": "3:03:05", "remaining_time": "0:08:46", "throughput": "502.56", "total_tokens": 5520832} -{"current_steps": 836, "total_steps": 875, "loss": 0.0047, "learning_rate": 2.5036898600385716e-08, "epoch": 4.766928011404134, "percentage": 95.54, "elapsed_time": "3:03:18", "remaining_time": "0:08:33", "throughput": "502.54", "total_tokens": 5527200} -{"current_steps": 837, "total_steps": 875, "loss": 0.0004, "learning_rate": 2.377142848759506e-08, "epoch": 4.772630078403421, "percentage": 95.66, "elapsed_time": "3:03:31", "remaining_time": "0:08:19", "throughput": "502.52", "total_tokens": 5533664} -{"current_steps": 838, "total_steps": 875, "loss": 0.0004, "learning_rate": 2.2538621503600255e-08, "epoch": 4.778332145402708, "percentage": 95.77, "elapsed_time": "3:03:44", "remaining_time": "0:08:06", "throughput": "502.53", "total_tokens": 5540400} -{"current_steps": 839, "total_steps": 875, "loss": 0.0018, "learning_rate": 2.1338493909958956e-08, "epoch": 4.784034212401996, "percentage": 95.89, "elapsed_time": "3:03:58", "remaining_time": "0:07:53", "throughput": "502.55", "total_tokens": 5547152} -{"current_steps": 840, "total_steps": 875, "loss": 0.0003, "learning_rate": 2.017106153716475e-08, "epoch": 4.789736279401283, "percentage": 96.0, "elapsed_time": "3:04:11", "remaining_time": "0:07:40", "throughput": "502.55", "total_tokens": 5553792} -{"current_steps": 841, "total_steps": 875, "loss": 0.0093, "learning_rate": 1.9036339784440082e-08, "epoch": 4.79543834640057, "percentage": 96.11, "elapsed_time": "3:04:24", "remaining_time": "0:07:27", "throughput": "502.53", "total_tokens": 5560144} -{"current_steps": 842, "total_steps": 875, "loss": 0.0007, "learning_rate": 1.793434361953228e-08, "epoch": 4.801140413399858, "percentage": 96.23, "elapsed_time": "3:04:37", "remaining_time": "0:07:14", "throughput": "502.52", "total_tokens": 5566640} -{"current_steps": 843, "total_steps": 875, "loss": 0.0043, "learning_rate": 1.6865087578515073e-08, "epoch": 4.806842480399145, "percentage": 96.34, "elapsed_time": "3:04:50", "remaining_time": "0:07:00", "throughput": "502.53", "total_tokens": 5573424} -{"current_steps": 844, "total_steps": 875, "loss": 0.0001, "learning_rate": 1.5828585765599315e-08, "epoch": 4.812544547398432, "percentage": 96.46, "elapsed_time": "3:05:03", "remaining_time": "0:06:47", "throughput": "502.55", "total_tokens": 5580208} -{"current_steps": 845, "total_steps": 875, "loss": 0.0001, "learning_rate": 1.482485185294369e-08, "epoch": 4.818246614397719, "percentage": 96.57, "elapsed_time": "3:05:16", "remaining_time": "0:06:34", "throughput": "502.54", "total_tokens": 5586720} -{"current_steps": 846, "total_steps": 875, "loss": 0.0001, "learning_rate": 1.3853899080477628e-08, "epoch": 4.823948681397006, "percentage": 96.69, "elapsed_time": "3:05:30", "remaining_time": "0:06:21", "throughput": "502.52", "total_tokens": 5593120} -{"current_steps": 847, "total_steps": 875, "loss": 0.0046, "learning_rate": 1.291574025572423e-08, "epoch": 4.829650748396293, "percentage": 96.8, "elapsed_time": "3:05:43", "remaining_time": "0:06:08", "throughput": "502.55", "total_tokens": 5600016} -{"current_steps": 848, "total_steps": 875, "loss": 0.0001, "learning_rate": 1.2010387753632891e-08, "epoch": 4.835352815395581, "percentage": 96.91, "elapsed_time": "3:05:56", "remaining_time": "0:05:55", "throughput": "502.56", "total_tokens": 5606800} -{"current_steps": 849, "total_steps": 875, "loss": 0.0025, "learning_rate": 1.1137853516414999e-08, "epoch": 4.841054882394868, "percentage": 97.03, "elapsed_time": "3:06:09", "remaining_time": "0:05:42", "throughput": "502.54", "total_tokens": 5613200} -{"current_steps": 850, "total_steps": 875, "loss": 0.0002, "learning_rate": 1.0298149053387107e-08, "epoch": 4.846756949394155, "percentage": 97.14, "elapsed_time": "3:06:22", "remaining_time": "0:05:28", "throughput": "502.54", "total_tokens": 5619792} -{"current_steps": 851, "total_steps": 875, "loss": 0.0002, "learning_rate": 9.491285440818288e-09, "epoch": 4.852459016393443, "percentage": 97.26, "elapsed_time": "3:06:35", "remaining_time": "0:05:15", "throughput": "502.57", "total_tokens": 5626720} -{"current_steps": 852, "total_steps": 875, "loss": 0.0002, "learning_rate": 8.717273321785513e-09, "epoch": 4.85816108339273, "percentage": 97.37, "elapsed_time": "3:06:49", "remaining_time": "0:05:02", "throughput": "502.57", "total_tokens": 5633328} -{"current_steps": 853, "total_steps": 875, "loss": 0.0005, "learning_rate": 7.976122906031559e-09, "epoch": 4.863863150392017, "percentage": 97.49, "elapsed_time": "3:07:02", "remaining_time": "0:04:49", "throughput": "502.60", "total_tokens": 5640240} -{"current_steps": 854, "total_steps": 875, "loss": 0.002, "learning_rate": 7.267843969831767e-09, "epoch": 4.869565217391305, "percentage": 97.6, "elapsed_time": "3:07:15", "remaining_time": "0:04:36", "throughput": "502.57", "total_tokens": 5646608} -{"current_steps": 855, "total_steps": 875, "loss": 0.0052, "learning_rate": 6.592445855863883e-09, "epoch": 4.875267284390592, "percentage": 97.71, "elapsed_time": "3:07:28", "remaining_time": "0:04:23", "throughput": "502.61", "total_tokens": 5653632} -{"current_steps": 856, "total_steps": 875, "loss": 0.0001, "learning_rate": 5.949937473085643e-09, "epoch": 4.880969351389879, "percentage": 97.83, "elapsed_time": "3:07:41", "remaining_time": "0:04:09", "throughput": "502.64", "total_tokens": 5660576} -{"current_steps": 857, "total_steps": 875, "loss": 0.0032, "learning_rate": 5.340327296616821e-09, "epoch": 4.886671418389166, "percentage": 97.94, "elapsed_time": "3:07:54", "remaining_time": "0:03:56", "throughput": "502.65", "total_tokens": 5667312} -{"current_steps": 858, "total_steps": 875, "loss": 0.0003, "learning_rate": 4.763623367627645e-09, "epoch": 4.892373485388453, "percentage": 98.06, "elapsed_time": "3:08:07", "remaining_time": "0:03:43", "throughput": "502.66", "total_tokens": 5673984} -{"current_steps": 859, "total_steps": 875, "loss": 0.0003, "learning_rate": 4.219833293233333e-09, "epoch": 4.89807555238774, "percentage": 98.17, "elapsed_time": "3:08:21", "remaining_time": "0:03:30", "throughput": "502.65", "total_tokens": 5680448} -{"current_steps": 860, "total_steps": 875, "loss": 0.0001, "learning_rate": 3.7089642463922217e-09, "epoch": 4.903777619387028, "percentage": 98.29, "elapsed_time": "3:08:34", "remaining_time": "0:03:17", "throughput": "502.66", "total_tokens": 5687248} -{"current_steps": 861, "total_steps": 875, "loss": 0.0006, "learning_rate": 3.231022965812236e-09, "epoch": 4.909479686386315, "percentage": 98.4, "elapsed_time": "3:08:47", "remaining_time": "0:03:04", "throughput": "502.66", "total_tokens": 5693792} -{"current_steps": 862, "total_steps": 875, "loss": 0.0044, "learning_rate": 2.7860157558620703e-09, "epoch": 4.915181753385602, "percentage": 98.51, "elapsed_time": "3:09:00", "remaining_time": "0:02:51", "throughput": "502.65", "total_tokens": 5700368} -{"current_steps": 863, "total_steps": 875, "loss": 0.0007, "learning_rate": 2.3739484864879203e-09, "epoch": 4.92088382038489, "percentage": 98.63, "elapsed_time": "3:09:13", "remaining_time": "0:02:37", "throughput": "502.63", "total_tokens": 5706672} -{"current_steps": 864, "total_steps": 875, "loss": 0.0004, "learning_rate": 1.9948265931352128e-09, "epoch": 4.926585887384177, "percentage": 98.74, "elapsed_time": "3:09:26", "remaining_time": "0:02:24", "throughput": "502.68", "total_tokens": 5713840} -{"current_steps": 865, "total_steps": 875, "loss": 0.0067, "learning_rate": 1.6486550766783849e-09, "epoch": 4.932287954383464, "percentage": 98.86, "elapsed_time": "3:09:40", "remaining_time": "0:02:11", "throughput": "502.66", "total_tokens": 5720272} -{"current_steps": 866, "total_steps": 875, "loss": 0.0005, "learning_rate": 1.3354385033534368e-09, "epoch": 4.937990021382751, "percentage": 98.97, "elapsed_time": "3:09:53", "remaining_time": "0:01:58", "throughput": "502.67", "total_tokens": 5727040} -{"current_steps": 867, "total_steps": 875, "loss": 0.0017, "learning_rate": 1.055181004698813e-09, "epoch": 4.943692088382038, "percentage": 99.09, "elapsed_time": "3:10:06", "remaining_time": "0:01:45", "throughput": "502.68", "total_tokens": 5733696} -{"current_steps": 868, "total_steps": 875, "loss": 0.0065, "learning_rate": 8.07886277500447e-10, "epoch": 4.949394155381325, "percentage": 99.2, "elapsed_time": "3:10:19", "remaining_time": "0:01:32", "throughput": "502.65", "total_tokens": 5740064} -{"current_steps": 869, "total_steps": 875, "loss": 0.0009, "learning_rate": 5.935575837429097e-10, "epoch": 4.955096222380613, "percentage": 99.31, "elapsed_time": "3:10:32", "remaining_time": "0:01:18", "throughput": "502.65", "total_tokens": 5746624} -{"current_steps": 870, "total_steps": 875, "loss": 0.0001, "learning_rate": 4.1219775056666746e-10, "epoch": 4.9607982893799, "percentage": 99.43, "elapsed_time": "3:10:45", "remaining_time": "0:01:05", "throughput": "502.67", "total_tokens": 5753456} -{"current_steps": 871, "total_steps": 875, "loss": 0.0096, "learning_rate": 2.638091702303336e-10, "epoch": 4.966500356379187, "percentage": 99.54, "elapsed_time": "3:10:58", "remaining_time": "0:00:52", "throughput": "502.65", "total_tokens": 5759808} -{"current_steps": 872, "total_steps": 875, "loss": 0.0099, "learning_rate": 1.4839380007986014e-10, "epoch": 4.972202423378475, "percentage": 99.66, "elapsed_time": "3:11:12", "remaining_time": "0:00:39", "throughput": "502.63", "total_tokens": 5766288} -{"current_steps": 873, "total_steps": 875, "loss": 0.0004, "learning_rate": 6.595316252161476e-11, "epoch": 4.977904490377762, "percentage": 99.77, "elapsed_time": "3:11:25", "remaining_time": "0:00:26", "throughput": "502.63", "total_tokens": 5772848} -{"current_steps": 874, "total_steps": 875, "loss": 0.0026, "learning_rate": 1.6488345003506933e-11, "epoch": 4.983606557377049, "percentage": 99.89, "elapsed_time": "3:11:38", "remaining_time": "0:00:13", "throughput": "502.64", "total_tokens": 5779552} -{"current_steps": 875, "total_steps": 875, "loss": 0.0029, "learning_rate": 0.0, "epoch": 4.989308624376337, "percentage": 100.0, "elapsed_time": "3:11:51", "remaining_time": "0:00:00", "throughput": "502.64", "total_tokens": 5786192} -{"current_steps": 875, "total_steps": 875, "epoch": 4.989308624376337, "percentage": 100.0, "elapsed_time": "3:12:52", "remaining_time": "0:00:00", "throughput": "499.99", "total_tokens": 5786192} +{"current_steps": 5, "total_steps": 160, "percentage": 3.12, "elapsed_time": "0:00:00", "remaining_time": "0:00:10"} +{"current_steps": 10, "total_steps": 160, "percentage": 6.25, "elapsed_time": "0:00:00", "remaining_time": "0:00:11"} +{"current_steps": 15, "total_steps": 160, "percentage": 9.38, "elapsed_time": "0:00:01", "remaining_time": "0:00:11"} +{"current_steps": 20, "total_steps": 160, "percentage": 12.5, "elapsed_time": "0:00:01", "remaining_time": "0:00:10"} +{"current_steps": 25, "total_steps": 160, "percentage": 15.62, "elapsed_time": "0:00:01", "remaining_time": "0:00:10"} +{"current_steps": 30, "total_steps": 160, "percentage": 18.75, "elapsed_time": "0:00:02", "remaining_time": "0:00:10"} +{"current_steps": 35, "total_steps": 160, "percentage": 21.88, "elapsed_time": "0:00:02", "remaining_time": "0:00:09"} +{"current_steps": 40, "total_steps": 160, "percentage": 25.0, "elapsed_time": "0:00:03", "remaining_time": "0:00:09"} +{"current_steps": 45, "total_steps": 160, "percentage": 28.12, "elapsed_time": "0:00:03", "remaining_time": "0:00:09"} +{"current_steps": 50, "total_steps": 160, "percentage": 31.25, "elapsed_time": "0:00:03", "remaining_time": "0:00:08"} +{"current_steps": 55, "total_steps": 160, "percentage": 34.38, "elapsed_time": "0:00:04", "remaining_time": "0:00:08"} +{"current_steps": 60, "total_steps": 160, "percentage": 37.5, "elapsed_time": "0:00:04", "remaining_time": "0:00:07"} +{"current_steps": 65, "total_steps": 160, "percentage": 40.62, "elapsed_time": "0:00:05", "remaining_time": "0:00:07"} +{"current_steps": 70, "total_steps": 160, "percentage": 43.75, "elapsed_time": "0:00:05", "remaining_time": "0:00:07"} +{"current_steps": 75, "total_steps": 160, "percentage": 46.88, "elapsed_time": "0:00:06", "remaining_time": "0:00:06"} +{"current_steps": 80, "total_steps": 160, "percentage": 50.0, "elapsed_time": "0:00:06", "remaining_time": "0:00:06"} +{"current_steps": 85, "total_steps": 160, "percentage": 53.12, "elapsed_time": "0:00:06", "remaining_time": "0:00:06"} +{"current_steps": 90, "total_steps": 160, "percentage": 56.25, "elapsed_time": "0:00:07", "remaining_time": "0:00:05"} +{"current_steps": 95, "total_steps": 160, "percentage": 59.38, "elapsed_time": "0:00:07", "remaining_time": "0:00:05"} +{"current_steps": 100, "total_steps": 160, "percentage": 62.5, "elapsed_time": "0:00:08", "remaining_time": "0:00:04"} +{"current_steps": 105, "total_steps": 160, "percentage": 65.62, "elapsed_time": "0:00:08", "remaining_time": "0:00:04"} +{"current_steps": 110, "total_steps": 160, "percentage": 68.75, "elapsed_time": "0:00:08", "remaining_time": "0:00:04"} +{"current_steps": 115, "total_steps": 160, "percentage": 71.88, "elapsed_time": "0:00:09", "remaining_time": "0:00:03"} +{"current_steps": 120, "total_steps": 160, "percentage": 75.0, "elapsed_time": "0:00:09", "remaining_time": "0:00:03"} +{"current_steps": 125, "total_steps": 160, "percentage": 78.12, "elapsed_time": "0:00:10", "remaining_time": "0:00:02"} +{"current_steps": 130, "total_steps": 160, "percentage": 81.25, "elapsed_time": "0:00:10", "remaining_time": "0:00:02"} +{"current_steps": 135, "total_steps": 160, "percentage": 84.38, "elapsed_time": "0:00:10", "remaining_time": "0:00:02"} +{"current_steps": 140, "total_steps": 160, "percentage": 87.5, "elapsed_time": "0:00:11", "remaining_time": "0:00:01"} +{"current_steps": 145, "total_steps": 160, "percentage": 90.62, "elapsed_time": "0:00:11", "remaining_time": "0:00:01"} +{"current_steps": 150, "total_steps": 160, "percentage": 93.75, "elapsed_time": "0:00:12", "remaining_time": "0:00:00"} +{"current_steps": 155, "total_steps": 160, "percentage": 96.88, "elapsed_time": "0:00:12", "remaining_time": "0:00:00"} +{"current_steps": 160, "total_steps": 160, "percentage": 100.0, "elapsed_time": "0:00:12", "remaining_time": "0:00:00"}