{"current_steps": 1, "total_steps": 755, "loss": 4.1255, "lr": 4.999978357111178e-05, "epoch": 0.006617038875103391, "percentage": 0.13, "elapsed_time": "0:00:24", "remaining_time": "5:11:47", "throughput": 10565.37, "total_tokens": 262144} {"current_steps": 2, "total_steps": 755, "loss": 3.9338, "lr": 4.9999134288194436e-05, "epoch": 0.013234077750206782, "percentage": 0.26, "elapsed_time": "0:00:48", "remaining_time": "5:05:23", "throughput": 10772.89, "total_tokens": 524288} {"current_steps": 3, "total_steps": 755, "loss": 4.6172, "lr": 4.9998052162489854e-05, "epoch": 0.019851116625310174, "percentage": 0.4, "elapsed_time": "0:01:12", "remaining_time": "5:03:17", "throughput": 10832.9, "total_tokens": 786432} {"current_steps": 4, "total_steps": 755, "loss": 2.6262, "lr": 4.999653721273429e-05, "epoch": 0.026468155500413565, "percentage": 0.53, "elapsed_time": "0:01:36", "remaining_time": "5:02:44", "throughput": 10838.27, "total_tokens": 1048576} {"current_steps": 5, "total_steps": 755, "loss": 2.308, "lr": 4.999458946515808e-05, "epoch": 0.033085194375516956, "percentage": 0.66, "elapsed_time": "0:02:00", "remaining_time": "5:01:59", "throughput": 10850.62, "total_tokens": 1310720} {"current_steps": 6, "total_steps": 755, "loss": 2.2825, "lr": 4.99922089534851e-05, "epoch": 0.03970223325062035, "percentage": 0.79, "elapsed_time": "0:02:24", "remaining_time": "5:01:11", "throughput": 10864.85, "total_tokens": 1572864} {"current_steps": 7, "total_steps": 755, "loss": 2.2304, "lr": 4.998939571893228e-05, "epoch": 0.04631927212572374, "percentage": 0.93, "elapsed_time": "0:02:48", "remaining_time": "4:59:53", "throughput": 10897.34, "total_tokens": 1835008} {"current_steps": 8, "total_steps": 755, "loss": 1.9455, "lr": 4.998614981020884e-05, "epoch": 0.05293631100082713, "percentage": 1.06, "elapsed_time": "0:03:12", "remaining_time": "4:59:16", "throughput": 10905.21, "total_tokens": 2097152} {"current_steps": 9, "total_steps": 755, "loss": 1.963, "lr": 4.998247128351545e-05, "epoch": 0.05955334987593052, "percentage": 1.19, "elapsed_time": "0:03:35", "remaining_time": "4:57:56", "throughput": 10939.64, "total_tokens": 2359296} {"current_steps": 10, "total_steps": 755, "loss": 1.8786, "lr": 4.997836020254328e-05, "epoch": 0.06617038875103391, "percentage": 1.32, "elapsed_time": "0:03:58", "remaining_time": "4:56:37", "throughput": 10973.19, "total_tokens": 2621440} {"current_steps": 11, "total_steps": 755, "loss": 1.7801, "lr": 4.9973816638472846e-05, "epoch": 0.07278742762613731, "percentage": 1.46, "elapsed_time": "0:04:22", "remaining_time": "4:55:44", "throughput": 10991.49, "total_tokens": 2883584} {"current_steps": 12, "total_steps": 755, "loss": 1.7482, "lr": 4.996884066997284e-05, "epoch": 0.0794044665012407, "percentage": 1.59, "elapsed_time": "0:04:45", "remaining_time": "4:54:50", "throughput": 11009.84, "total_tokens": 3145728} {"current_steps": 13, "total_steps": 755, "loss": 1.6573, "lr": 4.9963432383198726e-05, "epoch": 0.08602150537634409, "percentage": 1.72, "elapsed_time": "0:05:09", "remaining_time": "4:54:01", "throughput": 11025.54, "total_tokens": 3407872} {"current_steps": 14, "total_steps": 755, "loss": 1.6604, "lr": 4.995759187179126e-05, "epoch": 0.09263854425144748, "percentage": 1.85, "elapsed_time": "0:05:32", "remaining_time": "4:53:24", "throughput": 11033.96, "total_tokens": 3670016} {"current_steps": 15, "total_steps": 755, "loss": 1.6604, "lr": 4.995131923687488e-05, "epoch": 0.09925558312655088, "percentage": 1.99, "elapsed_time": "0:05:56", "remaining_time": "4:52:43", "throughput": 11044.78, "total_tokens": 3932160} {"current_steps": 16, "total_steps": 755, "loss": 1.593, "lr": 4.9944614587055925e-05, "epoch": 0.10587262200165426, "percentage": 2.12, "elapsed_time": "0:06:19", "remaining_time": "4:52:05", "throughput": 11053.92, "total_tokens": 4194304} {"current_steps": 17, "total_steps": 755, "loss": 1.6175, "lr": 4.993747803842081e-05, "epoch": 0.11248966087675766, "percentage": 2.25, "elapsed_time": "0:06:42", "remaining_time": "4:51:21", "throughput": 11066.75, "total_tokens": 4456448} {"current_steps": 18, "total_steps": 755, "loss": 1.6198, "lr": 4.992990971453394e-05, "epoch": 0.11910669975186104, "percentage": 2.38, "elapsed_time": "0:07:06", "remaining_time": "4:50:49", "throughput": 11071.92, "total_tokens": 4718592} {"current_steps": 19, "total_steps": 755, "loss": 1.5829, "lr": 4.9921909746435633e-05, "epoch": 0.12572373862696443, "percentage": 2.52, "elapsed_time": "0:07:29", "remaining_time": "4:50:07", "throughput": 11083.93, "total_tokens": 4980736} {"current_steps": 20, "total_steps": 755, "loss": 1.6012, "lr": 4.991347827263982e-05, "epoch": 0.13234077750206782, "percentage": 2.65, "elapsed_time": "0:07:52", "remaining_time": "4:49:25", "throughput": 11095.15, "total_tokens": 5242880} {"current_steps": 21, "total_steps": 755, "loss": 1.5498, "lr": 4.990461543913168e-05, "epoch": 0.13895781637717122, "percentage": 2.78, "elapsed_time": "0:08:15", "remaining_time": "4:48:45", "throughput": 11106.05, "total_tokens": 5505024} {"current_steps": 22, "total_steps": 755, "loss": 1.535, "lr": 4.9895321399365044e-05, "epoch": 0.14557485525227462, "percentage": 2.91, "elapsed_time": "0:08:38", "remaining_time": "4:48:06", "throughput": 11115.68, "total_tokens": 5767168} {"current_steps": 23, "total_steps": 755, "loss": 1.5611, "lr": 4.988559631425983e-05, "epoch": 0.152191894127378, "percentage": 3.05, "elapsed_time": "0:09:01", "remaining_time": "4:47:28", "throughput": 11125.31, "total_tokens": 6029312} {"current_steps": 24, "total_steps": 755, "loss": 1.5242, "lr": 4.987544035219917e-05, "epoch": 0.1588089330024814, "percentage": 3.18, "elapsed_time": "0:09:25", "remaining_time": "4:46:54", "throughput": 11131.85, "total_tokens": 6291456} {"current_steps": 25, "total_steps": 755, "loss": 1.5061, "lr": 4.9864853689026556e-05, "epoch": 0.1654259718775848, "percentage": 3.31, "elapsed_time": "0:09:48", "remaining_time": "4:46:16", "throughput": 11141.17, "total_tokens": 6553600} {"current_steps": 26, "total_steps": 755, "loss": 1.536, "lr": 4.985383650804277e-05, "epoch": 0.17204301075268819, "percentage": 3.44, "elapsed_time": "0:10:11", "remaining_time": "4:45:39", "throughput": 11149.7, "total_tokens": 6815744} {"current_steps": 27, "total_steps": 755, "loss": 1.4935, "lr": 4.984238900000271e-05, "epoch": 0.17866004962779156, "percentage": 3.58, "elapsed_time": "0:10:34", "remaining_time": "4:45:03", "throughput": 11158.08, "total_tokens": 7077888} {"current_steps": 28, "total_steps": 755, "loss": 1.5301, "lr": 4.983051136311209e-05, "epoch": 0.18527708850289495, "percentage": 3.71, "elapsed_time": "0:10:57", "remaining_time": "4:44:28", "throughput": 11165.66, "total_tokens": 7340032} {"current_steps": 29, "total_steps": 755, "loss": 1.5233, "lr": 4.9818203803024e-05, "epoch": 0.19189412737799835, "percentage": 3.84, "elapsed_time": "0:11:20", "remaining_time": "4:43:53", "throughput": 11172.78, "total_tokens": 7602176} {"current_steps": 30, "total_steps": 755, "loss": 1.5468, "lr": 4.9805466532835376e-05, "epoch": 0.19851116625310175, "percentage": 3.97, "elapsed_time": "0:11:43", "remaining_time": "4:43:19", "throughput": 11180.07, "total_tokens": 7864320} {"current_steps": 31, "total_steps": 755, "loss": 1.5449, "lr": 4.9792299773083276e-05, "epoch": 0.20512820512820512, "percentage": 4.11, "elapsed_time": "0:12:06", "remaining_time": "4:42:46", "throughput": 11186.42, "total_tokens": 8126464} {"current_steps": 32, "total_steps": 755, "loss": 1.4934, "lr": 4.9778703751741076e-05, "epoch": 0.21174524400330852, "percentage": 4.24, "elapsed_time": "0:12:29", "remaining_time": "4:42:13", "throughput": 11192.57, "total_tokens": 8388608} {"current_steps": 33, "total_steps": 755, "loss": 1.4751, "lr": 4.9764678704214506e-05, "epoch": 0.21836228287841192, "percentage": 4.37, "elapsed_time": "0:12:52", "remaining_time": "4:41:40", "throughput": 11198.85, "total_tokens": 8650752} {"current_steps": 34, "total_steps": 755, "loss": 1.4769, "lr": 4.9750224873337605e-05, "epoch": 0.22497932175351532, "percentage": 4.5, "elapsed_time": "0:13:15", "remaining_time": "4:41:09", "throughput": 11204.29, "total_tokens": 8912896} {"current_steps": 35, "total_steps": 755, "loss": 1.4546, "lr": 4.973534250936851e-05, "epoch": 0.23159636062861869, "percentage": 4.64, "elapsed_time": "0:13:38", "remaining_time": "4:40:38", "throughput": 11209.29, "total_tokens": 9175040} {"current_steps": 36, "total_steps": 755, "loss": 1.4923, "lr": 4.9720031869985084e-05, "epoch": 0.23821339950372208, "percentage": 4.77, "elapsed_time": "0:14:01", "remaining_time": "4:40:07", "throughput": 11214.32, "total_tokens": 9437184} {"current_steps": 37, "total_steps": 755, "loss": 1.4334, "lr": 4.970429322028051e-05, "epoch": 0.24483043837882548, "percentage": 4.9, "elapsed_time": "0:14:24", "remaining_time": "4:39:35", "throughput": 11219.75, "total_tokens": 9699328} {"current_steps": 38, "total_steps": 755, "loss": 1.4343, "lr": 4.968812683275866e-05, "epoch": 0.25144747725392885, "percentage": 5.03, "elapsed_time": "0:14:47", "remaining_time": "4:39:06", "throughput": 11223.73, "total_tokens": 9961472} {"current_steps": 39, "total_steps": 755, "loss": 1.4491, "lr": 4.96715329873294e-05, "epoch": 0.25806451612903225, "percentage": 5.17, "elapsed_time": "0:15:10", "remaining_time": "4:38:36", "throughput": 11227.98, "total_tokens": 10223616} {"current_steps": 40, "total_steps": 755, "loss": 1.4349, "lr": 4.965451197130373e-05, "epoch": 0.26468155500413565, "percentage": 5.3, "elapsed_time": "0:15:33", "remaining_time": "4:38:08", "throughput": 11231.05, "total_tokens": 10485760} {"current_steps": 41, "total_steps": 755, "loss": 1.4435, "lr": 4.963706407938881e-05, "epoch": 0.27129859387923905, "percentage": 5.43, "elapsed_time": "0:15:56", "remaining_time": "4:37:39", "throughput": 11234.84, "total_tokens": 10747904} {"current_steps": 42, "total_steps": 755, "loss": 1.4503, "lr": 4.961918961368287e-05, "epoch": 0.27791563275434245, "percentage": 5.56, "elapsed_time": "0:16:19", "remaining_time": "4:37:10", "throughput": 11238.62, "total_tokens": 11010048} {"current_steps": 43, "total_steps": 755, "loss": 1.448, "lr": 4.960088888366998e-05, "epoch": 0.28453267162944584, "percentage": 5.7, "elapsed_time": "0:16:42", "remaining_time": "4:36:41", "throughput": 11242.61, "total_tokens": 11272192} {"current_steps": 44, "total_steps": 755, "loss": 1.4384, "lr": 4.9582162206214654e-05, "epoch": 0.29114971050454924, "percentage": 5.83, "elapsed_time": "0:17:05", "remaining_time": "4:36:13", "throughput": 11245.97, "total_tokens": 11534336} {"current_steps": 45, "total_steps": 755, "loss": 1.4198, "lr": 4.956300990555643e-05, "epoch": 0.2977667493796526, "percentage": 5.96, "elapsed_time": "0:17:28", "remaining_time": "4:35:45", "throughput": 11249.07, "total_tokens": 11796480} {"current_steps": 46, "total_steps": 755, "loss": 1.4054, "lr": 4.9543432313304184e-05, "epoch": 0.304383788254756, "percentage": 6.09, "elapsed_time": "0:17:51", "remaining_time": "4:35:17", "throughput": 11252.12, "total_tokens": 12058624} {"current_steps": 47, "total_steps": 755, "loss": 1.421, "lr": 4.9523429768430445e-05, "epoch": 0.3110008271298594, "percentage": 6.23, "elapsed_time": "0:18:14", "remaining_time": "4:34:49", "throughput": 11255.23, "total_tokens": 12320768} {"current_steps": 48, "total_steps": 755, "loss": 1.4524, "lr": 4.950300261726549e-05, "epoch": 0.3176178660049628, "percentage": 6.36, "elapsed_time": "0:18:37", "remaining_time": "4:34:22", "throughput": 11258.27, "total_tokens": 12582912} {"current_steps": 49, "total_steps": 755, "loss": 1.4334, "lr": 4.9482151213491386e-05, "epoch": 0.3242349048800662, "percentage": 6.49, "elapsed_time": "0:19:00", "remaining_time": "4:33:55", "throughput": 11260.79, "total_tokens": 12845056} {"current_steps": 50, "total_steps": 755, "loss": 1.4294, "lr": 4.9460875918135804e-05, "epoch": 0.3308519437551696, "percentage": 6.62, "elapsed_time": "0:19:23", "remaining_time": "4:33:28", "throughput": 11262.99, "total_tokens": 13107200} {"current_steps": 51, "total_steps": 755, "loss": 1.427, "lr": 4.943917709956584e-05, "epoch": 0.337468982630273, "percentage": 6.75, "elapsed_time": "0:19:46", "remaining_time": "4:33:01", "throughput": 11265.74, "total_tokens": 13369344} {"current_steps": 52, "total_steps": 755, "loss": 1.4264, "lr": 4.941705513348157e-05, "epoch": 0.34408602150537637, "percentage": 6.89, "elapsed_time": "0:20:09", "remaining_time": "4:32:35", "throughput": 11267.67, "total_tokens": 13631488} {"current_steps": 53, "total_steps": 755, "loss": 1.4107, "lr": 4.939451040290961e-05, "epoch": 0.3507030603804797, "percentage": 7.02, "elapsed_time": "0:20:32", "remaining_time": "4:32:09", "throughput": 11269.54, "total_tokens": 13893632} {"current_steps": 54, "total_steps": 755, "loss": 1.4037, "lr": 4.937154329819644e-05, "epoch": 0.3573200992555831, "percentage": 7.15, "elapsed_time": "0:20:55", "remaining_time": "4:31:44", "throughput": 11270.98, "total_tokens": 14155776} {"current_steps": 55, "total_steps": 755, "loss": 1.4029, "lr": 4.934815421700165e-05, "epoch": 0.3639371381306865, "percentage": 7.28, "elapsed_time": "0:21:18", "remaining_time": "4:31:18", "throughput": 11272.91, "total_tokens": 14417920} {"current_steps": 56, "total_steps": 755, "loss": 1.4067, "lr": 4.932434356429106e-05, "epoch": 0.3705541770057899, "percentage": 7.42, "elapsed_time": "0:21:42", "remaining_time": "4:30:51", "throughput": 11274.96, "total_tokens": 14680064} {"current_steps": 57, "total_steps": 755, "loss": 1.4375, "lr": 4.930011175232973e-05, "epoch": 0.3771712158808933, "percentage": 7.55, "elapsed_time": "0:22:05", "remaining_time": "4:30:26", "throughput": 11276.69, "total_tokens": 14942208} {"current_steps": 58, "total_steps": 755, "loss": 1.3993, "lr": 4.927545920067479e-05, "epoch": 0.3837882547559967, "percentage": 7.68, "elapsed_time": "0:22:28", "remaining_time": "4:29:59", "throughput": 11278.7, "total_tokens": 15204352} {"current_steps": 59, "total_steps": 755, "loss": 1.3742, "lr": 4.925038633616818e-05, "epoch": 0.3904052936311001, "percentage": 7.81, "elapsed_time": "0:22:51", "remaining_time": "4:29:34", "throughput": 11280.4, "total_tokens": 15466496} {"current_steps": 60, "total_steps": 755, "loss": 1.4176, "lr": 4.9224893592929275e-05, "epoch": 0.3970223325062035, "percentage": 7.95, "elapsed_time": "0:23:14", "remaining_time": "4:29:08", "throughput": 11281.99, "total_tokens": 15728640} {"current_steps": 61, "total_steps": 755, "loss": 1.4201, "lr": 4.9198981412347364e-05, "epoch": 0.40363937138130684, "percentage": 8.08, "elapsed_time": "0:23:37", "remaining_time": "4:28:43", "throughput": 11283.64, "total_tokens": 15990784} {"current_steps": 62, "total_steps": 755, "loss": 1.3719, "lr": 4.917265024307401e-05, "epoch": 0.41025641025641024, "percentage": 8.21, "elapsed_time": "0:24:00", "remaining_time": "4:28:18", "throughput": 11284.84, "total_tokens": 16252928} {"current_steps": 63, "total_steps": 755, "loss": 1.3925, "lr": 4.914590054101526e-05, "epoch": 0.41687344913151364, "percentage": 8.34, "elapsed_time": "0:24:23", "remaining_time": "4:27:52", "throughput": 11286.41, "total_tokens": 16515072} {"current_steps": 64, "total_steps": 755, "loss": 1.3785, "lr": 4.911873276932376e-05, "epoch": 0.42349048800661704, "percentage": 8.48, "elapsed_time": "0:24:46", "remaining_time": "4:27:27", "throughput": 11287.49, "total_tokens": 16777216} {"current_steps": 65, "total_steps": 755, "loss": 1.4097, "lr": 4.909114739839079e-05, "epoch": 0.43010752688172044, "percentage": 8.61, "elapsed_time": "0:25:09", "remaining_time": "4:27:02", "throughput": 11288.92, "total_tokens": 17039360} {"current_steps": 66, "total_steps": 755, "loss": 1.3738, "lr": 4.906314490583802e-05, "epoch": 0.43672456575682383, "percentage": 8.74, "elapsed_time": "0:25:32", "remaining_time": "4:26:36", "throughput": 11290.92, "total_tokens": 17301504} {"current_steps": 67, "total_steps": 755, "loss": 1.3846, "lr": 4.903472577650934e-05, "epoch": 0.44334160463192723, "percentage": 8.87, "elapsed_time": "0:25:55", "remaining_time": "4:26:11", "throughput": 11292.52, "total_tokens": 17563648} {"current_steps": 68, "total_steps": 755, "loss": 1.3833, "lr": 4.900589050246237e-05, "epoch": 0.44995864350703063, "percentage": 9.01, "elapsed_time": "0:26:18", "remaining_time": "4:25:45", "throughput": 11294.19, "total_tokens": 17825792} {"current_steps": 69, "total_steps": 755, "loss": 1.3909, "lr": 4.897663958296002e-05, "epoch": 0.456575682382134, "percentage": 9.14, "elapsed_time": "0:26:41", "remaining_time": "4:25:20", "throughput": 11295.78, "total_tokens": 18087936} {"current_steps": 70, "total_steps": 755, "loss": 1.393, "lr": 4.894697352446182e-05, "epoch": 0.46319272125723737, "percentage": 9.27, "elapsed_time": "0:27:04", "remaining_time": "4:24:55", "throughput": 11297.09, "total_tokens": 18350080} {"current_steps": 71, "total_steps": 755, "loss": 1.413, "lr": 4.891689284061513e-05, "epoch": 0.46980976013234077, "percentage": 9.4, "elapsed_time": "0:27:27", "remaining_time": "4:24:29", "throughput": 11298.67, "total_tokens": 18612224} {"current_steps": 72, "total_steps": 755, "loss": 1.3945, "lr": 4.888639805224626e-05, "epoch": 0.47642679900744417, "percentage": 9.54, "elapsed_time": "0:27:50", "remaining_time": "4:24:04", "throughput": 11299.88, "total_tokens": 18874368} {"current_steps": 73, "total_steps": 755, "loss": 1.3905, "lr": 4.885548968735147e-05, "epoch": 0.48304383788254757, "percentage": 9.67, "elapsed_time": "0:28:13", "remaining_time": "4:23:39", "throughput": 11301.03, "total_tokens": 19136512} {"current_steps": 74, "total_steps": 755, "loss": 1.3601, "lr": 4.882416828108781e-05, "epoch": 0.48966087675765096, "percentage": 9.8, "elapsed_time": "0:28:36", "remaining_time": "4:23:14", "throughput": 11302.38, "total_tokens": 19398656} {"current_steps": 75, "total_steps": 755, "loss": 1.3564, "lr": 4.879243437576383e-05, "epoch": 0.49627791563275436, "percentage": 9.93, "elapsed_time": "0:28:59", "remaining_time": "4:22:50", "throughput": 11303.56, "total_tokens": 19660800} {"current_steps": 76, "total_steps": 755, "loss": 1.3718, "lr": 4.8760288520830254e-05, "epoch": 0.5028949545078577, "percentage": 10.07, "elapsed_time": "0:29:22", "remaining_time": "4:22:25", "throughput": 11304.7, "total_tokens": 19922944} {"current_steps": 77, "total_steps": 755, "loss": 1.3985, "lr": 4.8727731272870406e-05, "epoch": 0.5095119933829612, "percentage": 10.2, "elapsed_time": "0:29:45", "remaining_time": "4:22:00", "throughput": 11305.62, "total_tokens": 20185088} {"current_steps": 78, "total_steps": 755, "loss": 1.375, "lr": 4.8694763195590606e-05, "epoch": 0.5161290322580645, "percentage": 10.33, "elapsed_time": "0:30:08", "remaining_time": "4:21:36", "throughput": 11306.63, "total_tokens": 20447232} {"current_steps": 79, "total_steps": 755, "loss": 1.3442, "lr": 4.866138485981041e-05, "epoch": 0.522746071133168, "percentage": 10.46, "elapsed_time": "0:30:31", "remaining_time": "4:21:11", "throughput": 11307.53, "total_tokens": 20709376} {"current_steps": 80, "total_steps": 755, "loss": 1.3567, "lr": 4.862759684345269e-05, "epoch": 0.5293631100082713, "percentage": 10.6, "elapsed_time": "0:30:54", "remaining_time": "4:20:47", "throughput": 11308.65, "total_tokens": 20971520} {"current_steps": 81, "total_steps": 755, "loss": 1.3772, "lr": 4.859339973153368e-05, "epoch": 0.5359801488833746, "percentage": 10.73, "elapsed_time": "0:31:17", "remaining_time": "4:20:22", "throughput": 11309.41, "total_tokens": 21233664} {"current_steps": 82, "total_steps": 755, "loss": 1.3527, "lr": 4.855879411615282e-05, "epoch": 0.5425971877584781, "percentage": 10.86, "elapsed_time": "0:31:40", "remaining_time": "4:19:58", "throughput": 11310.43, "total_tokens": 21495808} {"current_steps": 83, "total_steps": 755, "loss": 1.3317, "lr": 4.8523780596482475e-05, "epoch": 0.5492142266335814, "percentage": 10.99, "elapsed_time": "0:32:03", "remaining_time": "4:19:33", "throughput": 11311.48, "total_tokens": 21757952} {"current_steps": 84, "total_steps": 755, "loss": 1.383, "lr": 4.848835977875764e-05, "epoch": 0.5558312655086849, "percentage": 11.13, "elapsed_time": "0:32:26", "remaining_time": "4:19:08", "throughput": 11312.65, "total_tokens": 22020096} {"current_steps": 85, "total_steps": 755, "loss": 1.3401, "lr": 4.8452532276265364e-05, "epoch": 0.5624483043837882, "percentage": 11.26, "elapsed_time": "0:32:49", "remaining_time": "4:18:44", "throughput": 11313.62, "total_tokens": 22282240} {"current_steps": 86, "total_steps": 755, "loss": 1.3231, "lr": 4.8416298709334156e-05, "epoch": 0.5690653432588917, "percentage": 11.39, "elapsed_time": "0:33:12", "remaining_time": "4:18:19", "throughput": 11314.51, "total_tokens": 22544384} {"current_steps": 87, "total_steps": 755, "loss": 1.3651, "lr": 4.837965970532328e-05, "epoch": 0.575682382133995, "percentage": 11.52, "elapsed_time": "0:33:35", "remaining_time": "4:17:55", "throughput": 11315.18, "total_tokens": 22806528} {"current_steps": 88, "total_steps": 755, "loss": 1.3357, "lr": 4.8342615898611854e-05, "epoch": 0.5822994210090985, "percentage": 11.66, "elapsed_time": "0:33:58", "remaining_time": "4:17:31", "throughput": 11315.83, "total_tokens": 23068672} {"current_steps": 89, "total_steps": 755, "loss": 1.3445, "lr": 4.8305167930587844e-05, "epoch": 0.5889164598842018, "percentage": 11.79, "elapsed_time": "0:34:21", "remaining_time": "4:17:07", "throughput": 11316.61, "total_tokens": 23330816} {"current_steps": 90, "total_steps": 755, "loss": 1.3455, "lr": 4.8267316449637054e-05, "epoch": 0.5955334987593052, "percentage": 11.92, "elapsed_time": "0:34:44", "remaining_time": "4:16:43", "throughput": 11317.57, "total_tokens": 23592960} {"current_steps": 91, "total_steps": 755, "loss": 1.3531, "lr": 4.8229062111131764e-05, "epoch": 0.6021505376344086, "percentage": 12.05, "elapsed_time": "0:35:07", "remaining_time": "4:16:18", "throughput": 11318.43, "total_tokens": 23855104} {"current_steps": 92, "total_steps": 755, "loss": 1.3499, "lr": 4.8190405577419506e-05, "epoch": 0.608767576509512, "percentage": 12.19, "elapsed_time": "0:35:30", "remaining_time": "4:15:54", "throughput": 11319.21, "total_tokens": 24117248} {"current_steps": 93, "total_steps": 755, "loss": 1.3197, "lr": 4.815134751781153e-05, "epoch": 0.6153846153846154, "percentage": 12.32, "elapsed_time": "0:35:53", "remaining_time": "4:15:30", "throughput": 11320.07, "total_tokens": 24379392} {"current_steps": 94, "total_steps": 755, "loss": 1.3649, "lr": 4.8111888608571234e-05, "epoch": 0.6220016542597188, "percentage": 12.45, "elapsed_time": "0:36:16", "remaining_time": "4:15:05", "throughput": 11320.91, "total_tokens": 24641536} {"current_steps": 95, "total_steps": 755, "loss": 1.3297, "lr": 4.8072029532902426e-05, "epoch": 0.6286186931348222, "percentage": 12.58, "elapsed_time": "0:36:39", "remaining_time": "4:14:41", "throughput": 11321.68, "total_tokens": 24903680} {"current_steps": 96, "total_steps": 755, "loss": 1.3152, "lr": 4.803177098093757e-05, "epoch": 0.6352357320099256, "percentage": 12.72, "elapsed_time": "0:37:02", "remaining_time": "4:14:17", "throughput": 11322.34, "total_tokens": 25165824} {"current_steps": 97, "total_steps": 755, "loss": 1.3153, "lr": 4.7991113649725734e-05, "epoch": 0.6418527708850289, "percentage": 12.85, "elapsed_time": "0:37:25", "remaining_time": "4:13:53", "throughput": 11323.11, "total_tokens": 25427968} {"current_steps": 98, "total_steps": 755, "loss": 1.331, "lr": 4.795005824322061e-05, "epoch": 0.6484698097601324, "percentage": 12.98, "elapsed_time": "0:37:48", "remaining_time": "4:13:29", "throughput": 11323.93, "total_tokens": 25690112} {"current_steps": 99, "total_steps": 755, "loss": 1.3385, "lr": 4.7908605472268266e-05, "epoch": 0.6550868486352357, "percentage": 13.11, "elapsed_time": "0:38:11", "remaining_time": "4:13:04", "throughput": 11324.84, "total_tokens": 25952256} {"current_steps": 100, "total_steps": 755, "loss": 1.348, "lr": 4.786675605459487e-05, "epoch": 0.6617038875103392, "percentage": 13.25, "elapsed_time": "0:38:34", "remaining_time": "4:12:40", "throughput": 11325.44, "total_tokens": 26214400} {"current_steps": 101, "total_steps": 755, "loss": 1.3192, "lr": 4.782451071479428e-05, "epoch": 0.6683209263854425, "percentage": 13.38, "elapsed_time": "0:38:57", "remaining_time": "4:12:16", "throughput": 11326.09, "total_tokens": 26476544} {"current_steps": 102, "total_steps": 755, "loss": 1.3322, "lr": 4.7781870184315435e-05, "epoch": 0.674937965260546, "percentage": 13.51, "elapsed_time": "0:39:20", "remaining_time": "4:11:52", "throughput": 11326.73, "total_tokens": 26738688} {"current_steps": 103, "total_steps": 755, "loss": 1.3335, "lr": 4.773883520144974e-05, "epoch": 0.6815550041356493, "percentage": 13.64, "elapsed_time": "0:39:43", "remaining_time": "4:11:28", "throughput": 11327.43, "total_tokens": 27000832} {"current_steps": 104, "total_steps": 755, "loss": 1.3127, "lr": 4.769540651131828e-05, "epoch": 0.6881720430107527, "percentage": 13.77, "elapsed_time": "0:40:06", "remaining_time": "4:11:04", "throughput": 11328.25, "total_tokens": 27262976} {"current_steps": 105, "total_steps": 755, "loss": 1.3312, "lr": 4.76515848658589e-05, "epoch": 0.6947890818858561, "percentage": 13.91, "elapsed_time": "0:40:29", "remaining_time": "4:10:40", "throughput": 11328.9, "total_tokens": 27525120} {"current_steps": 106, "total_steps": 755, "loss": 1.3019, "lr": 4.760737102381321e-05, "epoch": 0.7014061207609594, "percentage": 14.04, "elapsed_time": "0:40:52", "remaining_time": "4:10:16", "throughput": 11329.64, "total_tokens": 27787264} {"current_steps": 107, "total_steps": 755, "loss": 1.3257, "lr": 4.756276575071342e-05, "epoch": 0.7080231596360629, "percentage": 14.17, "elapsed_time": "0:41:15", "remaining_time": "4:09:52", "throughput": 11330.29, "total_tokens": 28049408} {"current_steps": 108, "total_steps": 755, "loss": 1.3216, "lr": 4.75177698188691e-05, "epoch": 0.7146401985111662, "percentage": 14.3, "elapsed_time": "0:41:38", "remaining_time": "4:09:28", "throughput": 11331.1, "total_tokens": 28311552} {"current_steps": 109, "total_steps": 755, "loss": 1.3088, "lr": 4.7472384007353804e-05, "epoch": 0.7212572373862697, "percentage": 14.44, "elapsed_time": "0:42:01", "remaining_time": "4:09:04", "throughput": 11331.57, "total_tokens": 28573696} {"current_steps": 110, "total_steps": 755, "loss": 1.3371, "lr": 4.7426609101991605e-05, "epoch": 0.727874276261373, "percentage": 14.57, "elapsed_time": "0:42:24", "remaining_time": "4:08:40", "throughput": 11332.25, "total_tokens": 28835840} {"current_steps": 111, "total_steps": 755, "loss": 1.3364, "lr": 4.7380445895343445e-05, "epoch": 0.7344913151364765, "percentage": 14.7, "elapsed_time": "0:42:47", "remaining_time": "4:08:16", "throughput": 11332.86, "total_tokens": 29097984} {"current_steps": 112, "total_steps": 755, "loss": 1.354, "lr": 4.7333895186693445e-05, "epoch": 0.7411083540115798, "percentage": 14.83, "elapsed_time": "0:43:10", "remaining_time": "4:07:52", "throughput": 11333.6, "total_tokens": 29360128} {"current_steps": 113, "total_steps": 755, "loss": 1.2943, "lr": 4.728695778203505e-05, "epoch": 0.7477253928866832, "percentage": 14.97, "elapsed_time": "0:43:33", "remaining_time": "4:07:28", "throughput": 11334.25, "total_tokens": 29622272} {"current_steps": 114, "total_steps": 755, "loss": 1.2989, "lr": 4.723963449405709e-05, "epoch": 0.7543424317617866, "percentage": 15.1, "elapsed_time": "0:43:56", "remaining_time": "4:07:04", "throughput": 11334.84, "total_tokens": 29884416} {"current_steps": 115, "total_steps": 755, "loss": 1.2922, "lr": 4.719192614212969e-05, "epoch": 0.76095947063689, "percentage": 15.23, "elapsed_time": "0:44:19", "remaining_time": "4:06:40", "throughput": 11335.32, "total_tokens": 30146560} {"current_steps": 116, "total_steps": 755, "loss": 1.3166, "lr": 4.7143833552290104e-05, "epoch": 0.7675765095119934, "percentage": 15.36, "elapsed_time": "0:44:42", "remaining_time": "4:06:16", "throughput": 11335.92, "total_tokens": 30408704} {"current_steps": 117, "total_steps": 755, "loss": 1.2922, "lr": 4.709535755722839e-05, "epoch": 0.7741935483870968, "percentage": 15.5, "elapsed_time": "0:45:05", "remaining_time": "4:05:53", "throughput": 11336.46, "total_tokens": 30670848} {"current_steps": 118, "total_steps": 755, "loss": 1.2983, "lr": 4.704649899627299e-05, "epoch": 0.7808105872622002, "percentage": 15.63, "elapsed_time": "0:45:28", "remaining_time": "4:05:29", "throughput": 11337.05, "total_tokens": 30932992} {"current_steps": 119, "total_steps": 755, "loss": 1.3065, "lr": 4.6997258715376234e-05, "epoch": 0.7874276261373035, "percentage": 15.76, "elapsed_time": "0:45:51", "remaining_time": "4:05:05", "throughput": 11337.6, "total_tokens": 31195136} {"current_steps": 120, "total_steps": 755, "loss": 1.3114, "lr": 4.694763756709967e-05, "epoch": 0.794044665012407, "percentage": 15.89, "elapsed_time": "0:46:14", "remaining_time": "4:04:41", "throughput": 11338.11, "total_tokens": 31457280} {"current_steps": 121, "total_steps": 755, "loss": 1.2915, "lr": 4.689763641059929e-05, "epoch": 0.8006617038875103, "percentage": 16.03, "elapsed_time": "0:46:37", "remaining_time": "4:04:17", "throughput": 11338.62, "total_tokens": 31719424} {"current_steps": 122, "total_steps": 755, "loss": 1.3179, "lr": 4.684725611161067e-05, "epoch": 0.8072787427626137, "percentage": 16.16, "elapsed_time": "0:47:00", "remaining_time": "4:03:54", "throughput": 11339.14, "total_tokens": 31981568} {"current_steps": 123, "total_steps": 755, "loss": 1.2868, "lr": 4.679649754243398e-05, "epoch": 0.8138957816377171, "percentage": 16.29, "elapsed_time": "0:47:23", "remaining_time": "4:03:30", "throughput": 11339.6, "total_tokens": 32243712} {"current_steps": 124, "total_steps": 755, "loss": 1.2975, "lr": 4.6745361581918866e-05, "epoch": 0.8205128205128205, "percentage": 16.42, "elapsed_time": "0:47:46", "remaining_time": "4:03:06", "throughput": 11340.01, "total_tokens": 32505856} {"current_steps": 125, "total_steps": 755, "loss": 1.3087, "lr": 4.669384911544927e-05, "epoch": 0.8271298593879239, "percentage": 16.56, "elapsed_time": "0:48:09", "remaining_time": "4:02:42", "throughput": 11340.46, "total_tokens": 32768000} {"current_steps": 126, "total_steps": 755, "loss": 1.308, "lr": 4.664196103492805e-05, "epoch": 0.8337468982630273, "percentage": 16.69, "elapsed_time": "0:48:32", "remaining_time": "4:02:19", "throughput": 11341.04, "total_tokens": 33030144} {"current_steps": 127, "total_steps": 755, "loss": 1.2818, "lr": 4.658969823876157e-05, "epoch": 0.8403639371381307, "percentage": 16.82, "elapsed_time": "0:48:55", "remaining_time": "4:01:55", "throughput": 11341.49, "total_tokens": 33292288} {"current_steps": 128, "total_steps": 755, "loss": 1.3057, "lr": 4.6537061631844144e-05, "epoch": 0.8469809760132341, "percentage": 16.95, "elapsed_time": "0:49:18", "remaining_time": "4:01:31", "throughput": 11341.89, "total_tokens": 33554432} {"current_steps": 129, "total_steps": 755, "loss": 1.2772, "lr": 4.648405212554236e-05, "epoch": 0.8535980148883374, "percentage": 17.09, "elapsed_time": "0:49:41", "remaining_time": "4:01:08", "throughput": 11342.23, "total_tokens": 33816576} {"current_steps": 130, "total_steps": 755, "loss": 1.2704, "lr": 4.6430670637679295e-05, "epoch": 0.8602150537634409, "percentage": 17.22, "elapsed_time": "0:50:04", "remaining_time": "4:00:44", "throughput": 11342.62, "total_tokens": 34078720} {"current_steps": 131, "total_steps": 755, "loss": 1.3038, "lr": 4.637691809251863e-05, "epoch": 0.8668320926385442, "percentage": 17.35, "elapsed_time": "0:50:27", "remaining_time": "4:00:21", "throughput": 11342.97, "total_tokens": 34340864} {"current_steps": 132, "total_steps": 755, "loss": 1.2951, "lr": 4.6322795420748664e-05, "epoch": 0.8734491315136477, "percentage": 17.48, "elapsed_time": "0:50:50", "remaining_time": "3:59:57", "throughput": 11343.36, "total_tokens": 34603008} {"current_steps": 133, "total_steps": 755, "loss": 1.3082, "lr": 4.626830355946616e-05, "epoch": 0.880066170388751, "percentage": 17.62, "elapsed_time": "0:51:13", "remaining_time": "3:59:33", "throughput": 11343.9, "total_tokens": 34865152} {"current_steps": 134, "total_steps": 755, "loss": 1.2849, "lr": 4.621344345216017e-05, "epoch": 0.8866832092638545, "percentage": 17.75, "elapsed_time": "0:51:36", "remaining_time": "3:59:10", "throughput": 11344.17, "total_tokens": 35127296} {"current_steps": 135, "total_steps": 755, "loss": 1.2785, "lr": 4.615821604869564e-05, "epoch": 0.8933002481389578, "percentage": 17.88, "elapsed_time": "0:51:59", "remaining_time": "3:58:46", "throughput": 11344.48, "total_tokens": 35389440} {"current_steps": 136, "total_steps": 755, "loss": 1.2919, "lr": 4.6102622305297015e-05, "epoch": 0.8999172870140613, "percentage": 18.01, "elapsed_time": "0:52:22", "remaining_time": "3:58:23", "throughput": 11344.86, "total_tokens": 35651584} {"current_steps": 137, "total_steps": 755, "loss": 1.2626, "lr": 4.604666318453167e-05, "epoch": 0.9065343258891646, "percentage": 18.15, "elapsed_time": "0:52:45", "remaining_time": "3:57:59", "throughput": 11345.18, "total_tokens": 35913728} {"current_steps": 138, "total_steps": 755, "loss": 1.2615, "lr": 4.5990339655293215e-05, "epoch": 0.913151364764268, "percentage": 18.28, "elapsed_time": "0:53:08", "remaining_time": "3:57:36", "throughput": 11345.54, "total_tokens": 36175872} {"current_steps": 139, "total_steps": 755, "loss": 1.2641, "lr": 4.593365269278477e-05, "epoch": 0.9197684036393714, "percentage": 18.41, "elapsed_time": "0:53:31", "remaining_time": "3:57:12", "throughput": 11345.83, "total_tokens": 36438016} {"current_steps": 140, "total_steps": 755, "loss": 1.2617, "lr": 4.587660327850203e-05, "epoch": 0.9263854425144747, "percentage": 18.54, "elapsed_time": "0:53:54", "remaining_time": "3:56:48", "throughput": 11346.29, "total_tokens": 36700160} {"current_steps": 141, "total_steps": 755, "loss": 1.2723, "lr": 4.581919240021629e-05, "epoch": 0.9330024813895782, "percentage": 18.68, "elapsed_time": "0:54:17", "remaining_time": "3:56:25", "throughput": 11346.65, "total_tokens": 36962304} {"current_steps": 142, "total_steps": 755, "loss": 1.2753, "lr": 4.576142105195737e-05, "epoch": 0.9396195202646815, "percentage": 18.81, "elapsed_time": "0:54:40", "remaining_time": "3:56:01", "throughput": 11346.98, "total_tokens": 37224448} {"current_steps": 143, "total_steps": 755, "loss": 1.2878, "lr": 4.570329023399636e-05, "epoch": 0.946236559139785, "percentage": 18.94, "elapsed_time": "0:55:03", "remaining_time": "3:55:38", "throughput": 11347.29, "total_tokens": 37486592} {"current_steps": 144, "total_steps": 755, "loss": 1.2946, "lr": 4.564480095282832e-05, "epoch": 0.9528535980148883, "percentage": 19.07, "elapsed_time": "0:55:26", "remaining_time": "3:55:14", "throughput": 11347.59, "total_tokens": 37748736} {"current_steps": 145, "total_steps": 755, "loss": 1.2962, "lr": 4.5585954221154856e-05, "epoch": 0.9594706368899917, "percentage": 19.21, "elapsed_time": "0:55:49", "remaining_time": "3:54:51", "throughput": 11347.8, "total_tokens": 38010880} {"current_steps": 146, "total_steps": 755, "loss": 1.2372, "lr": 4.552675105786659e-05, "epoch": 0.9660876757650951, "percentage": 19.34, "elapsed_time": "0:56:12", "remaining_time": "3:54:27", "throughput": 11348.22, "total_tokens": 38273024} {"current_steps": 147, "total_steps": 755, "loss": 1.2469, "lr": 4.546719248802551e-05, "epoch": 0.9727047146401985, "percentage": 19.47, "elapsed_time": "0:56:35", "remaining_time": "3:54:04", "throughput": 11348.75, "total_tokens": 38535168} {"current_steps": 148, "total_steps": 755, "loss": 1.2951, "lr": 4.540727954284721e-05, "epoch": 0.9793217535153019, "percentage": 19.6, "elapsed_time": "0:56:58", "remaining_time": "3:53:40", "throughput": 11349.12, "total_tokens": 38797312} {"current_steps": 149, "total_steps": 755, "loss": 1.2973, "lr": 4.534701325968308e-05, "epoch": 0.9859387923904053, "percentage": 19.74, "elapsed_time": "0:57:21", "remaining_time": "3:53:17", "throughput": 11349.34, "total_tokens": 39059456} {"current_steps": 150, "total_steps": 755, "loss": 1.263, "lr": 4.528639468200226e-05, "epoch": 0.9925558312655087, "percentage": 19.87, "elapsed_time": "0:57:44", "remaining_time": "3:52:53", "throughput": 11349.65, "total_tokens": 39321600} {"current_steps": 151, "total_steps": 755, "loss": 1.2337, "lr": 4.522542485937369e-05, "epoch": 0.9991728701406121, "percentage": 20.0, "elapsed_time": "0:58:07", "remaining_time": "3:52:30", "throughput": 11349.89, "total_tokens": 39583744} {"current_steps": 152, "total_steps": 755, "loss": 1.2248, "lr": 4.5164104847447825e-05, "epoch": 1.0, "percentage": 20.13, "elapsed_time": "0:58:10", "remaining_time": "3:50:46", "throughput": 11350.07, "total_tokens": 39616512} {"current_steps": 153, "total_steps": 755, "loss": 0.8764, "lr": 4.5102435707938434e-05, "epoch": 1.0066170388751035, "percentage": 20.26, "elapsed_time": "0:58:33", "remaining_time": "3:50:24", "throughput": 11350.36, "total_tokens": 39878656} {"current_steps": 154, "total_steps": 755, "loss": 0.8615, "lr": 4.5040418508604185e-05, "epoch": 1.0132340777502067, "percentage": 20.4, "elapsed_time": "0:58:56", "remaining_time": "3:50:01", "throughput": 11350.63, "total_tokens": 40140800} {"current_steps": 155, "total_steps": 755, "loss": 0.8845, "lr": 4.497805432323015e-05, "epoch": 1.0198511166253101, "percentage": 20.53, "elapsed_time": "0:59:19", "remaining_time": "3:49:38", "throughput": 11350.84, "total_tokens": 40402944} {"current_steps": 156, "total_steps": 755, "loss": 0.8799, "lr": 4.491534423160923e-05, "epoch": 1.0264681555004136, "percentage": 20.66, "elapsed_time": "0:59:42", "remaining_time": "3:49:15", "throughput": 11351.16, "total_tokens": 40665088} {"current_steps": 157, "total_steps": 755, "loss": 0.8701, "lr": 4.485228931952347e-05, "epoch": 1.033085194375517, "percentage": 20.79, "elapsed_time": "1:00:05", "remaining_time": "3:48:53", "throughput": 11351.32, "total_tokens": 40927232} {"current_steps": 158, "total_steps": 755, "loss": 0.8248, "lr": 4.4788890678725224e-05, "epoch": 1.0397022332506203, "percentage": 20.93, "elapsed_time": "1:00:28", "remaining_time": "3:48:30", "throughput": 11351.75, "total_tokens": 41189376} {"current_steps": 159, "total_steps": 755, "loss": 0.8326, "lr": 4.472514940691828e-05, "epoch": 1.0463192721257237, "percentage": 21.06, "elapsed_time": "1:00:51", "remaining_time": "3:48:07", "throughput": 11352.1, "total_tokens": 41451520} {"current_steps": 160, "total_steps": 755, "loss": 0.8359, "lr": 4.466106660773885e-05, "epoch": 1.0529363110008272, "percentage": 21.19, "elapsed_time": "1:01:14", "remaining_time": "3:47:44", "throughput": 11352.42, "total_tokens": 41713664} {"current_steps": 161, "total_steps": 755, "loss": 0.8182, "lr": 4.4596643390736444e-05, "epoch": 1.0595533498759304, "percentage": 21.32, "elapsed_time": "1:01:37", "remaining_time": "3:47:21", "throughput": 11352.75, "total_tokens": 41975808} {"current_steps": 162, "total_steps": 755, "loss": 0.8189, "lr": 4.4531880871354683e-05, "epoch": 1.0661703887510339, "percentage": 21.46, "elapsed_time": "1:02:00", "remaining_time": "3:46:58", "throughput": 11353.05, "total_tokens": 42237952} {"current_steps": 163, "total_steps": 755, "loss": 0.7864, "lr": 4.446678017091198e-05, "epoch": 1.0727874276261373, "percentage": 21.59, "elapsed_time": "1:02:23", "remaining_time": "3:46:35", "throughput": 11353.32, "total_tokens": 42500096} {"current_steps": 164, "total_steps": 755, "loss": 0.8014, "lr": 4.4401342416582106e-05, "epoch": 1.0794044665012408, "percentage": 21.72, "elapsed_time": "1:02:46", "remaining_time": "3:46:12", "throughput": 11353.55, "total_tokens": 42762240} {"current_steps": 165, "total_steps": 755, "loss": 0.7991, "lr": 4.43355687413747e-05, "epoch": 1.086021505376344, "percentage": 21.85, "elapsed_time": "1:03:09", "remaining_time": "3:45:50", "throughput": 11353.64, "total_tokens": 43024384} {"current_steps": 166, "total_steps": 755, "loss": 0.8213, "lr": 4.4269460284115624e-05, "epoch": 1.0926385442514475, "percentage": 21.99, "elapsed_time": "1:03:32", "remaining_time": "3:45:27", "throughput": 11353.77, "total_tokens": 43286528} {"current_steps": 167, "total_steps": 755, "loss": 0.7971, "lr": 4.420301818942728e-05, "epoch": 1.099255583126551, "percentage": 22.12, "elapsed_time": "1:03:55", "remaining_time": "3:45:04", "throughput": 11354.15, "total_tokens": 43548672} {"current_steps": 168, "total_steps": 755, "loss": 0.8253, "lr": 4.413624360770876e-05, "epoch": 1.1058726220016544, "percentage": 22.25, "elapsed_time": "1:04:18", "remaining_time": "3:44:41", "throughput": 11354.32, "total_tokens": 43810816} {"current_steps": 169, "total_steps": 755, "loss": 0.7985, "lr": 4.406913769511594e-05, "epoch": 1.1124896608767576, "percentage": 22.38, "elapsed_time": "1:04:41", "remaining_time": "3:44:18", "throughput": 11354.63, "total_tokens": 44072960} {"current_steps": 170, "total_steps": 755, "loss": 0.7995, "lr": 4.4001701613541456e-05, "epoch": 1.119106699751861, "percentage": 22.52, "elapsed_time": "1:05:04", "remaining_time": "3:43:56", "throughput": 11354.86, "total_tokens": 44335104} {"current_steps": 171, "total_steps": 755, "loss": 0.8307, "lr": 4.393393653059462e-05, "epoch": 1.1257237386269645, "percentage": 22.65, "elapsed_time": "1:05:27", "remaining_time": "3:43:33", "throughput": 11355.12, "total_tokens": 44597248} {"current_steps": 172, "total_steps": 755, "loss": 0.8032, "lr": 4.386584361958115e-05, "epoch": 1.1323407775020677, "percentage": 22.78, "elapsed_time": "1:05:50", "remaining_time": "3:43:10", "throughput": 11355.27, "total_tokens": 44859392} {"current_steps": 173, "total_steps": 755, "loss": 0.7937, "lr": 4.379742405948288e-05, "epoch": 1.1389578163771712, "percentage": 22.91, "elapsed_time": "1:06:13", "remaining_time": "3:42:47", "throughput": 11355.62, "total_tokens": 45121536} {"current_steps": 174, "total_steps": 755, "loss": 0.8142, "lr": 4.372867903493737e-05, "epoch": 1.1455748552522746, "percentage": 23.05, "elapsed_time": "1:06:36", "remaining_time": "3:42:24", "throughput": 11355.8, "total_tokens": 45383680} {"current_steps": 175, "total_steps": 755, "loss": 0.7912, "lr": 4.3659609736217344e-05, "epoch": 1.152191894127378, "percentage": 23.18, "elapsed_time": "1:06:59", "remaining_time": "3:42:01", "throughput": 11355.93, "total_tokens": 45645824} {"current_steps": 176, "total_steps": 755, "loss": 0.8177, "lr": 4.359021735921013e-05, "epoch": 1.1588089330024813, "percentage": 23.31, "elapsed_time": "1:07:22", "remaining_time": "3:41:39", "throughput": 11356.11, "total_tokens": 45907968} {"current_steps": 177, "total_steps": 755, "loss": 0.7996, "lr": 4.352050310539694e-05, "epoch": 1.1654259718775848, "percentage": 23.44, "elapsed_time": "1:07:45", "remaining_time": "3:41:16", "throughput": 11356.28, "total_tokens": 46170112} {"current_steps": 178, "total_steps": 755, "loss": 0.8202, "lr": 4.345046818183203e-05, "epoch": 1.1720430107526882, "percentage": 23.58, "elapsed_time": "1:08:08", "remaining_time": "3:40:53", "throughput": 11356.46, "total_tokens": 46432256} {"current_steps": 179, "total_steps": 755, "loss": 0.8198, "lr": 4.3380113801121854e-05, "epoch": 1.1786600496277915, "percentage": 23.71, "elapsed_time": "1:08:31", "remaining_time": "3:40:30", "throughput": 11356.57, "total_tokens": 46694400} {"current_steps": 180, "total_steps": 755, "loss": 0.8209, "lr": 4.330944118140407e-05, "epoch": 1.185277088502895, "percentage": 23.84, "elapsed_time": "1:08:54", "remaining_time": "3:40:07", "throughput": 11356.8, "total_tokens": 46956544} {"current_steps": 181, "total_steps": 755, "loss": 0.8307, "lr": 4.3238451546326367e-05, "epoch": 1.1918941273779984, "percentage": 23.97, "elapsed_time": "1:09:17", "remaining_time": "3:39:45", "throughput": 11357.0, "total_tokens": 47218688} {"current_steps": 182, "total_steps": 755, "loss": 0.8271, "lr": 4.3167146125025385e-05, "epoch": 1.1985111662531018, "percentage": 24.11, "elapsed_time": "1:09:40", "remaining_time": "3:39:22", "throughput": 11357.18, "total_tokens": 47480832} {"current_steps": 183, "total_steps": 755, "loss": 0.7997, "lr": 4.309552615210536e-05, "epoch": 1.205128205128205, "percentage": 24.24, "elapsed_time": "1:10:03", "remaining_time": "3:38:59", "throughput": 11357.32, "total_tokens": 47742976} {"current_steps": 184, "total_steps": 755, "loss": 0.8127, "lr": 4.302359286761679e-05, "epoch": 1.2117452440033085, "percentage": 24.37, "elapsed_time": "1:10:27", "remaining_time": "3:38:38", "throughput": 11356.28, "total_tokens": 48005120} {"current_steps": 185, "total_steps": 755, "loss": 0.7802, "lr": 4.295134751703493e-05, "epoch": 1.218362282878412, "percentage": 24.5, "elapsed_time": "1:10:50", "remaining_time": "3:38:16", "throughput": 11355.56, "total_tokens": 48267264} {"current_steps": 186, "total_steps": 755, "loss": 0.8212, "lr": 4.287879135123826e-05, "epoch": 1.2249793217535152, "percentage": 24.64, "elapsed_time": "1:11:13", "remaining_time": "3:37:53", "throughput": 11355.8, "total_tokens": 48529408} {"current_steps": 187, "total_steps": 755, "loss": 0.8111, "lr": 4.2805925626486796e-05, "epoch": 1.2315963606286187, "percentage": 24.77, "elapsed_time": "1:11:36", "remaining_time": "3:37:30", "throughput": 11356.0, "total_tokens": 48791552} {"current_steps": 188, "total_steps": 755, "loss": 0.8189, "lr": 4.2732751604400364e-05, "epoch": 1.2382133995037221, "percentage": 24.9, "elapsed_time": "1:11:59", "remaining_time": "3:37:07", "throughput": 11356.06, "total_tokens": 49053696} {"current_steps": 189, "total_steps": 755, "loss": 0.7794, "lr": 4.2659270551936756e-05, "epoch": 1.2448304383788256, "percentage": 25.03, "elapsed_time": "1:12:22", "remaining_time": "3:36:44", "throughput": 11356.25, "total_tokens": 49315840} {"current_steps": 190, "total_steps": 755, "loss": 0.8014, "lr": 4.2585483741369755e-05, "epoch": 1.2514474772539288, "percentage": 25.17, "elapsed_time": "1:12:45", "remaining_time": "3:36:21", "throughput": 11356.5, "total_tokens": 49577984} {"current_steps": 191, "total_steps": 755, "loss": 0.8084, "lr": 4.251139245026716e-05, "epoch": 1.2580645161290323, "percentage": 25.3, "elapsed_time": "1:13:08", "remaining_time": "3:35:58", "throughput": 11356.76, "total_tokens": 49840128} {"current_steps": 192, "total_steps": 755, "loss": 0.7981, "lr": 4.243699796146863e-05, "epoch": 1.2646815550041357, "percentage": 25.43, "elapsed_time": "1:13:31", "remaining_time": "3:35:36", "throughput": 11356.91, "total_tokens": 50102272} {"current_steps": 193, "total_steps": 755, "loss": 0.8091, "lr": 4.236230156306348e-05, "epoch": 1.271298593879239, "percentage": 25.56, "elapsed_time": "1:13:54", "remaining_time": "3:35:13", "throughput": 11356.97, "total_tokens": 50364416} {"current_steps": 194, "total_steps": 755, "loss": 0.7932, "lr": 4.2287304548368386e-05, "epoch": 1.2779156327543424, "percentage": 25.7, "elapsed_time": "1:14:17", "remaining_time": "3:34:50", "throughput": 11357.07, "total_tokens": 50626560} {"current_steps": 195, "total_steps": 755, "loss": 0.8324, "lr": 4.2212008215905e-05, "epoch": 1.2845326716294458, "percentage": 25.83, "elapsed_time": "1:14:40", "remaining_time": "3:34:27", "throughput": 11357.25, "total_tokens": 50888704} {"current_steps": 196, "total_steps": 755, "loss": 0.7849, "lr": 4.213641386937743e-05, "epoch": 1.2911497105045493, "percentage": 25.96, "elapsed_time": "1:15:03", "remaining_time": "3:34:04", "throughput": 11357.45, "total_tokens": 51150848} {"current_steps": 197, "total_steps": 755, "loss": 0.8401, "lr": 4.206052281764973e-05, "epoch": 1.2977667493796525, "percentage": 26.09, "elapsed_time": "1:15:26", "remaining_time": "3:33:42", "throughput": 11357.55, "total_tokens": 51412992} {"current_steps": 198, "total_steps": 755, "loss": 0.8336, "lr": 4.198433637472314e-05, "epoch": 1.304383788254756, "percentage": 26.23, "elapsed_time": "1:15:49", "remaining_time": "3:33:19", "throughput": 11357.69, "total_tokens": 51675136} {"current_steps": 199, "total_steps": 755, "loss": 0.8028, "lr": 4.190785585971346e-05, "epoch": 1.3110008271298594, "percentage": 26.36, "elapsed_time": "1:16:12", "remaining_time": "3:32:56", "throughput": 11357.72, "total_tokens": 51937280} {"current_steps": 200, "total_steps": 755, "loss": 0.7752, "lr": 4.1831082596828106e-05, "epoch": 1.3176178660049627, "percentage": 26.49, "elapsed_time": "1:16:35", "remaining_time": "3:32:33", "throughput": 11357.91, "total_tokens": 52199424} {"current_steps": 201, "total_steps": 755, "loss": 0.8043, "lr": 4.1754017915343234e-05, "epoch": 1.3242349048800661, "percentage": 26.62, "elapsed_time": "1:16:58", "remaining_time": "3:32:10", "throughput": 11358.06, "total_tokens": 52461568} {"current_steps": 202, "total_steps": 755, "loss": 0.8111, "lr": 4.167666314958071e-05, "epoch": 1.3308519437551696, "percentage": 26.75, "elapsed_time": "1:17:21", "remaining_time": "3:31:47", "throughput": 11358.16, "total_tokens": 52723712} {"current_steps": 203, "total_steps": 755, "loss": 0.8395, "lr": 4.159901963888502e-05, "epoch": 1.337468982630273, "percentage": 26.89, "elapsed_time": "1:17:44", "remaining_time": "3:31:24", "throughput": 11358.28, "total_tokens": 52985856} {"current_steps": 204, "total_steps": 755, "loss": 0.8308, "lr": 4.152108872760004e-05, "epoch": 1.3440860215053765, "percentage": 27.02, "elapsed_time": "1:18:07", "remaining_time": "3:31:02", "throughput": 11358.45, "total_tokens": 53248000} {"current_steps": 205, "total_steps": 755, "loss": 0.8207, "lr": 4.144287176504582e-05, "epoch": 1.3507030603804797, "percentage": 27.15, "elapsed_time": "1:18:31", "remaining_time": "3:30:39", "throughput": 11358.47, "total_tokens": 53510144} {"current_steps": 206, "total_steps": 755, "loss": 0.7787, "lr": 4.136437010549518e-05, "epoch": 1.3573200992555832, "percentage": 27.28, "elapsed_time": "1:18:54", "remaining_time": "3:30:16", "throughput": 11358.63, "total_tokens": 53772288} {"current_steps": 207, "total_steps": 755, "loss": 0.8136, "lr": 4.1285585108150273e-05, "epoch": 1.3639371381306864, "percentage": 27.42, "elapsed_time": "1:19:17", "remaining_time": "3:29:53", "throughput": 11358.77, "total_tokens": 54034432} {"current_steps": 208, "total_steps": 755, "loss": 0.8263, "lr": 4.120651813711905e-05, "epoch": 1.3705541770057899, "percentage": 27.55, "elapsed_time": "1:19:40", "remaining_time": "3:29:30", "throughput": 11358.81, "total_tokens": 54296576} {"current_steps": 209, "total_steps": 755, "loss": 0.8093, "lr": 4.112717056139164e-05, "epoch": 1.3771712158808933, "percentage": 27.68, "elapsed_time": "1:20:03", "remaining_time": "3:29:07", "throughput": 11358.96, "total_tokens": 54558720} {"current_steps": 210, "total_steps": 755, "loss": 0.8271, "lr": 4.104754375481664e-05, "epoch": 1.3837882547559968, "percentage": 27.81, "elapsed_time": "1:20:26", "remaining_time": "3:28:46", "throughput": 11358.21, "total_tokens": 54820864} {"current_steps": 211, "total_steps": 755, "loss": 0.8186, "lr": 4.096763909607737e-05, "epoch": 1.3904052936311002, "percentage": 27.95, "elapsed_time": "1:20:49", "remaining_time": "3:28:23", "throughput": 11358.4, "total_tokens": 55083008} {"current_steps": 212, "total_steps": 755, "loss": 0.8396, "lr": 4.088745796866793e-05, "epoch": 1.3970223325062034, "percentage": 28.08, "elapsed_time": "1:21:12", "remaining_time": "3:28:00", "throughput": 11358.52, "total_tokens": 55345152} {"current_steps": 213, "total_steps": 755, "loss": 0.8152, "lr": 4.08070017608693e-05, "epoch": 1.403639371381307, "percentage": 28.21, "elapsed_time": "1:21:35", "remaining_time": "3:27:37", "throughput": 11358.71, "total_tokens": 55607296} {"current_steps": 214, "total_steps": 755, "loss": 0.7969, "lr": 4.072627186572531e-05, "epoch": 1.4102564102564101, "percentage": 28.34, "elapsed_time": "1:21:58", "remaining_time": "3:27:14", "throughput": 11358.88, "total_tokens": 55869440} {"current_steps": 215, "total_steps": 755, "loss": 0.8065, "lr": 4.064526968101844e-05, "epoch": 1.4168734491315136, "percentage": 28.48, "elapsed_time": "1:22:21", "remaining_time": "3:26:51", "throughput": 11359.05, "total_tokens": 56131584} {"current_steps": 216, "total_steps": 755, "loss": 0.7936, "lr": 4.056399660924575e-05, "epoch": 1.423490488006617, "percentage": 28.61, "elapsed_time": "1:22:44", "remaining_time": "3:26:28", "throughput": 11359.33, "total_tokens": 56393728} {"current_steps": 217, "total_steps": 755, "loss": 0.8085, "lr": 4.048245405759446e-05, "epoch": 1.4301075268817205, "percentage": 28.74, "elapsed_time": "1:23:07", "remaining_time": "3:26:05", "throughput": 11359.41, "total_tokens": 56655872} {"current_steps": 218, "total_steps": 755, "loss": 0.8019, "lr": 4.040064343791767e-05, "epoch": 1.436724565756824, "percentage": 28.87, "elapsed_time": "1:23:30", "remaining_time": "3:25:42", "throughput": 11359.55, "total_tokens": 56918016} {"current_steps": 219, "total_steps": 755, "loss": 0.8216, "lr": 4.0318566166709925e-05, "epoch": 1.4433416046319272, "percentage": 29.01, "elapsed_time": "1:23:53", "remaining_time": "3:25:19", "throughput": 11359.79, "total_tokens": 57180160} {"current_steps": 220, "total_steps": 755, "loss": 0.7965, "lr": 4.023622366508261e-05, "epoch": 1.4499586435070306, "percentage": 29.14, "elapsed_time": "1:24:16", "remaining_time": "3:24:56", "throughput": 11360.04, "total_tokens": 57442304} {"current_steps": 221, "total_steps": 755, "loss": 0.8342, "lr": 4.0153617358739406e-05, "epoch": 1.4565756823821339, "percentage": 29.27, "elapsed_time": "1:24:39", "remaining_time": "3:24:33", "throughput": 11360.23, "total_tokens": 57704448} {"current_steps": 222, "total_steps": 755, "loss": 0.8135, "lr": 4.0070748677951605e-05, "epoch": 1.4631927212572373, "percentage": 29.4, "elapsed_time": "1:25:02", "remaining_time": "3:24:10", "throughput": 11360.42, "total_tokens": 57966592} {"current_steps": 223, "total_steps": 755, "loss": 0.8088, "lr": 3.998761905753333e-05, "epoch": 1.4698097601323408, "percentage": 29.54, "elapsed_time": "1:25:25", "remaining_time": "3:23:47", "throughput": 11360.57, "total_tokens": 58228736} {"current_steps": 224, "total_steps": 755, "loss": 0.835, "lr": 3.9904229936816674e-05, "epoch": 1.4764267990074442, "percentage": 29.67, "elapsed_time": "1:25:48", "remaining_time": "3:23:24", "throughput": 11360.73, "total_tokens": 58490880} {"current_steps": 225, "total_steps": 755, "loss": 0.8474, "lr": 3.9820582759626825e-05, "epoch": 1.4830438378825477, "percentage": 29.8, "elapsed_time": "1:26:11", "remaining_time": "3:23:01", "throughput": 11360.82, "total_tokens": 58753024} {"current_steps": 226, "total_steps": 755, "loss": 0.8173, "lr": 3.973667897425701e-05, "epoch": 1.489660876757651, "percentage": 29.93, "elapsed_time": "1:26:34", "remaining_time": "3:22:38", "throughput": 11360.91, "total_tokens": 59015168} {"current_steps": 227, "total_steps": 755, "loss": 0.8013, "lr": 3.9652520033443485e-05, "epoch": 1.4962779156327544, "percentage": 30.07, "elapsed_time": "1:26:57", "remaining_time": "3:22:16", "throughput": 11360.98, "total_tokens": 59277312} {"current_steps": 228, "total_steps": 755, "loss": 0.8303, "lr": 3.956810739434032e-05, "epoch": 1.5028949545078576, "percentage": 30.2, "elapsed_time": "1:27:20", "remaining_time": "3:21:53", "throughput": 11361.2, "total_tokens": 59539456} {"current_steps": 229, "total_steps": 755, "loss": 0.8558, "lr": 3.948344251849421e-05, "epoch": 1.509511993382961, "percentage": 30.33, "elapsed_time": "1:27:43", "remaining_time": "3:21:30", "throughput": 11361.38, "total_tokens": 59801600} {"current_steps": 230, "total_steps": 755, "loss": 0.8157, "lr": 3.9398526871819154e-05, "epoch": 1.5161290322580645, "percentage": 30.46, "elapsed_time": "1:28:06", "remaining_time": "3:21:07", "throughput": 11361.47, "total_tokens": 60063744} {"current_steps": 231, "total_steps": 755, "loss": 0.8222, "lr": 3.931336192457106e-05, "epoch": 1.522746071133168, "percentage": 30.6, "elapsed_time": "1:28:29", "remaining_time": "3:20:44", "throughput": 11361.67, "total_tokens": 60325888} {"current_steps": 232, "total_steps": 755, "loss": 0.8088, "lr": 3.9227949151322326e-05, "epoch": 1.5293631100082714, "percentage": 30.73, "elapsed_time": "1:28:52", "remaining_time": "3:20:21", "throughput": 11361.76, "total_tokens": 60588032} {"current_steps": 233, "total_steps": 755, "loss": 0.7982, "lr": 3.914229003093627e-05, "epoch": 1.5359801488833746, "percentage": 30.86, "elapsed_time": "1:29:15", "remaining_time": "3:19:58", "throughput": 11361.93, "total_tokens": 60850176} {"current_steps": 234, "total_steps": 755, "loss": 0.8156, "lr": 3.905638604654156e-05, "epoch": 1.542597187758478, "percentage": 30.99, "elapsed_time": "1:29:38", "remaining_time": "3:19:35", "throughput": 11362.04, "total_tokens": 61112320} {"current_steps": 235, "total_steps": 755, "loss": 0.8215, "lr": 3.897023868550649e-05, "epoch": 1.5492142266335813, "percentage": 31.13, "elapsed_time": "1:30:01", "remaining_time": "3:19:12", "throughput": 11362.13, "total_tokens": 61374464} {"current_steps": 236, "total_steps": 755, "loss": 0.8386, "lr": 3.8883849439413265e-05, "epoch": 1.5558312655086848, "percentage": 31.26, "elapsed_time": "1:30:24", "remaining_time": "3:18:49", "throughput": 11362.32, "total_tokens": 61636608} {"current_steps": 237, "total_steps": 755, "loss": 0.8461, "lr": 3.879721980403217e-05, "epoch": 1.5624483043837882, "percentage": 31.39, "elapsed_time": "1:30:47", "remaining_time": "3:18:26", "throughput": 11362.44, "total_tokens": 61898752} {"current_steps": 238, "total_steps": 755, "loss": 0.8469, "lr": 3.871035127929566e-05, "epoch": 1.5690653432588917, "percentage": 31.52, "elapsed_time": "1:31:10", "remaining_time": "3:18:03", "throughput": 11362.5, "total_tokens": 62160896} {"current_steps": 239, "total_steps": 755, "loss": 0.8082, "lr": 3.8623245369272385e-05, "epoch": 1.5756823821339951, "percentage": 31.66, "elapsed_time": "1:31:33", "remaining_time": "3:17:40", "throughput": 11362.59, "total_tokens": 62423040} {"current_steps": 240, "total_steps": 755, "loss": 0.8326, "lr": 3.853590358214119e-05, "epoch": 1.5822994210090986, "percentage": 31.79, "elapsed_time": "1:31:56", "remaining_time": "3:17:18", "throughput": 11362.63, "total_tokens": 62685184} {"current_steps": 241, "total_steps": 755, "loss": 0.818, "lr": 3.844832743016491e-05, "epoch": 1.5889164598842018, "percentage": 31.92, "elapsed_time": "1:32:19", "remaining_time": "3:16:55", "throughput": 11362.63, "total_tokens": 62947328} {"current_steps": 242, "total_steps": 755, "loss": 0.8083, "lr": 3.83605184296643e-05, "epoch": 1.595533498759305, "percentage": 32.05, "elapsed_time": "1:32:42", "remaining_time": "3:16:32", "throughput": 11362.76, "total_tokens": 63209472} {"current_steps": 243, "total_steps": 755, "loss": 0.8474, "lr": 3.8272478100991714e-05, "epoch": 1.6021505376344085, "percentage": 32.19, "elapsed_time": "1:33:05", "remaining_time": "3:16:09", "throughput": 11362.92, "total_tokens": 63471616} {"current_steps": 244, "total_steps": 755, "loss": 0.8199, "lr": 3.818420796850478e-05, "epoch": 1.608767576509512, "percentage": 32.32, "elapsed_time": "1:33:28", "remaining_time": "3:15:46", "throughput": 11363.1, "total_tokens": 63733760} {"current_steps": 245, "total_steps": 755, "loss": 0.8254, "lr": 3.809570956054004e-05, "epoch": 1.6153846153846154, "percentage": 32.45, "elapsed_time": "1:33:51", "remaining_time": "3:15:23", "throughput": 11363.23, "total_tokens": 63995904} {"current_steps": 246, "total_steps": 755, "loss": 0.8381, "lr": 3.800698440938644e-05, "epoch": 1.6220016542597189, "percentage": 32.58, "elapsed_time": "1:34:14", "remaining_time": "3:15:00", "throughput": 11363.37, "total_tokens": 64258048} {"current_steps": 247, "total_steps": 755, "loss": 0.8477, "lr": 3.791803405125885e-05, "epoch": 1.6286186931348223, "percentage": 32.72, "elapsed_time": "1:34:37", "remaining_time": "3:14:37", "throughput": 11363.47, "total_tokens": 64520192} {"current_steps": 248, "total_steps": 755, "loss": 0.8227, "lr": 3.782886002627145e-05, "epoch": 1.6352357320099256, "percentage": 32.85, "elapsed_time": "1:35:00", "remaining_time": "3:14:14", "throughput": 11363.57, "total_tokens": 64782336} {"current_steps": 249, "total_steps": 755, "loss": 0.7957, "lr": 3.773946387841103e-05, "epoch": 1.6418527708850288, "percentage": 32.98, "elapsed_time": "1:35:23", "remaining_time": "3:13:51", "throughput": 11363.75, "total_tokens": 65044480} {"current_steps": 250, "total_steps": 755, "loss": 0.8186, "lr": 3.764984715551032e-05, "epoch": 1.6484698097601322, "percentage": 33.11, "elapsed_time": "1:35:46", "remaining_time": "3:13:28", "throughput": 11363.82, "total_tokens": 65306624} {"current_steps": 251, "total_steps": 755, "loss": 0.8042, "lr": 3.756001140922112e-05, "epoch": 1.6550868486352357, "percentage": 33.25, "elapsed_time": "1:36:09", "remaining_time": "3:13:05", "throughput": 11364.02, "total_tokens": 65568768} {"current_steps": 252, "total_steps": 755, "loss": 0.8556, "lr": 3.74699581949875e-05, "epoch": 1.6617038875103392, "percentage": 33.38, "elapsed_time": "1:36:32", "remaining_time": "3:12:42", "throughput": 11364.1, "total_tokens": 65830912} {"current_steps": 253, "total_steps": 755, "loss": 0.852, "lr": 3.737968907201882e-05, "epoch": 1.6683209263854426, "percentage": 33.51, "elapsed_time": "1:36:55", "remaining_time": "3:12:19", "throughput": 11364.24, "total_tokens": 66093056} {"current_steps": 254, "total_steps": 755, "loss": 0.8295, "lr": 3.728920560326275e-05, "epoch": 1.674937965260546, "percentage": 33.64, "elapsed_time": "1:37:18", "remaining_time": "3:11:56", "throughput": 11364.36, "total_tokens": 66355200} {"current_steps": 255, "total_steps": 755, "loss": 0.8421, "lr": 3.719850935537821e-05, "epoch": 1.6815550041356493, "percentage": 33.77, "elapsed_time": "1:37:41", "remaining_time": "3:11:33", "throughput": 11364.47, "total_tokens": 66617344} {"current_steps": 256, "total_steps": 755, "loss": 0.8308, "lr": 3.710760189870825e-05, "epoch": 1.6881720430107527, "percentage": 33.91, "elapsed_time": "1:38:04", "remaining_time": "3:11:11", "throughput": 11364.53, "total_tokens": 66879488} {"current_steps": 257, "total_steps": 755, "loss": 0.8416, "lr": 3.701648480725286e-05, "epoch": 1.694789081885856, "percentage": 34.04, "elapsed_time": "1:38:27", "remaining_time": "3:10:48", "throughput": 11364.64, "total_tokens": 67141632} {"current_steps": 258, "total_steps": 755, "loss": 0.8209, "lr": 3.692515965864169e-05, "epoch": 1.7014061207609594, "percentage": 34.17, "elapsed_time": "1:38:50", "remaining_time": "3:10:25", "throughput": 11364.78, "total_tokens": 67403776} {"current_steps": 259, "total_steps": 755, "loss": 0.8638, "lr": 3.683362803410678e-05, "epoch": 1.7080231596360629, "percentage": 34.3, "elapsed_time": "1:39:13", "remaining_time": "3:10:02", "throughput": 11364.96, "total_tokens": 67665920} {"current_steps": 260, "total_steps": 755, "loss": 0.818, "lr": 3.674189151845515e-05, "epoch": 1.7146401985111663, "percentage": 34.44, "elapsed_time": "1:39:36", "remaining_time": "3:09:39", "throughput": 11365.13, "total_tokens": 67928064} {"current_steps": 261, "total_steps": 755, "loss": 0.7977, "lr": 3.6649951700041366e-05, "epoch": 1.7212572373862698, "percentage": 34.57, "elapsed_time": "1:39:59", "remaining_time": "3:09:16", "throughput": 11365.31, "total_tokens": 68190208} {"current_steps": 262, "total_steps": 755, "loss": 0.8338, "lr": 3.6557810170740034e-05, "epoch": 1.727874276261373, "percentage": 34.7, "elapsed_time": "1:40:22", "remaining_time": "3:08:53", "throughput": 11365.46, "total_tokens": 68452352} {"current_steps": 263, "total_steps": 755, "loss": 0.8522, "lr": 3.646546852591827e-05, "epoch": 1.7344913151364765, "percentage": 34.83, "elapsed_time": "1:40:45", "remaining_time": "3:08:30", "throughput": 11365.52, "total_tokens": 68714496} {"current_steps": 264, "total_steps": 755, "loss": 0.8307, "lr": 3.637292836440802e-05, "epoch": 1.7411083540115797, "percentage": 34.97, "elapsed_time": "1:41:08", "remaining_time": "3:08:07", "throughput": 11365.63, "total_tokens": 68976640} {"current_steps": 265, "total_steps": 755, "loss": 0.8315, "lr": 3.6280191288478436e-05, "epoch": 1.7477253928866832, "percentage": 35.1, "elapsed_time": "1:41:31", "remaining_time": "3:07:44", "throughput": 11365.71, "total_tokens": 69238784} {"current_steps": 266, "total_steps": 755, "loss": 0.8594, "lr": 3.61872589038081e-05, "epoch": 1.7543424317617866, "percentage": 35.23, "elapsed_time": "1:41:54", "remaining_time": "3:07:21", "throughput": 11365.79, "total_tokens": 69500928} {"current_steps": 267, "total_steps": 755, "loss": 0.8398, "lr": 3.6094132819457205e-05, "epoch": 1.76095947063689, "percentage": 35.36, "elapsed_time": "1:42:17", "remaining_time": "3:06:58", "throughput": 11365.92, "total_tokens": 69763072} {"current_steps": 268, "total_steps": 755, "loss": 0.8626, "lr": 3.600081464783977e-05, "epoch": 1.7675765095119935, "percentage": 35.5, "elapsed_time": "1:42:40", "remaining_time": "3:06:35", "throughput": 11366.05, "total_tokens": 70025216} {"current_steps": 269, "total_steps": 755, "loss": 0.7914, "lr": 3.5907306004695636e-05, "epoch": 1.7741935483870968, "percentage": 35.63, "elapsed_time": "1:43:03", "remaining_time": "3:06:12", "throughput": 11366.09, "total_tokens": 70287360} {"current_steps": 270, "total_steps": 755, "loss": 0.8104, "lr": 3.5813608509062526e-05, "epoch": 1.7808105872622002, "percentage": 35.76, "elapsed_time": "1:43:26", "remaining_time": "3:05:49", "throughput": 11366.19, "total_tokens": 70549504} {"current_steps": 271, "total_steps": 755, "loss": 0.8375, "lr": 3.5719723783248045e-05, "epoch": 1.7874276261373034, "percentage": 35.89, "elapsed_time": "1:43:49", "remaining_time": "3:05:26", "throughput": 11366.31, "total_tokens": 70811648} {"current_steps": 272, "total_steps": 755, "loss": 0.8168, "lr": 3.5625653452801525e-05, "epoch": 1.794044665012407, "percentage": 36.03, "elapsed_time": "1:44:12", "remaining_time": "3:05:03", "throughput": 11366.42, "total_tokens": 71073792} {"current_steps": 273, "total_steps": 755, "loss": 0.796, "lr": 3.553139914648593e-05, "epoch": 1.8006617038875103, "percentage": 36.16, "elapsed_time": "1:44:35", "remaining_time": "3:04:40", "throughput": 11366.52, "total_tokens": 71335936} {"current_steps": 274, "total_steps": 755, "loss": 0.8127, "lr": 3.543696249624965e-05, "epoch": 1.8072787427626138, "percentage": 36.29, "elapsed_time": "1:44:58", "remaining_time": "3:04:17", "throughput": 11366.6, "total_tokens": 71598080} {"current_steps": 275, "total_steps": 755, "loss": 0.8211, "lr": 3.534234513719821e-05, "epoch": 1.8138957816377173, "percentage": 36.42, "elapsed_time": "1:45:21", "remaining_time": "3:03:54", "throughput": 11366.77, "total_tokens": 71860224} {"current_steps": 276, "total_steps": 755, "loss": 0.8212, "lr": 3.5247548707565986e-05, "epoch": 1.8205128205128205, "percentage": 36.56, "elapsed_time": "1:45:44", "remaining_time": "3:03:31", "throughput": 11366.86, "total_tokens": 72122368} {"current_steps": 277, "total_steps": 755, "loss": 0.8215, "lr": 3.5152574848687875e-05, "epoch": 1.827129859387924, "percentage": 36.69, "elapsed_time": "1:46:07", "remaining_time": "3:03:08", "throughput": 11367.0, "total_tokens": 72384512} {"current_steps": 278, "total_steps": 755, "loss": 0.8219, "lr": 3.505742520497079e-05, "epoch": 1.8337468982630272, "percentage": 36.82, "elapsed_time": "1:46:30", "remaining_time": "3:02:45", "throughput": 11367.11, "total_tokens": 72646656} {"current_steps": 279, "total_steps": 755, "loss": 0.7913, "lr": 3.496210142386527e-05, "epoch": 1.8403639371381306, "percentage": 36.95, "elapsed_time": "1:46:53", "remaining_time": "3:02:22", "throughput": 11367.21, "total_tokens": 72908800} {"current_steps": 280, "total_steps": 755, "loss": 0.8401, "lr": 3.4866605155836915e-05, "epoch": 1.846980976013234, "percentage": 37.09, "elapsed_time": "1:47:16", "remaining_time": "3:01:59", "throughput": 11367.28, "total_tokens": 73170944} {"current_steps": 281, "total_steps": 755, "loss": 0.8375, "lr": 3.47709380543378e-05, "epoch": 1.8535980148883375, "percentage": 37.22, "elapsed_time": "1:47:39", "remaining_time": "3:01:36", "throughput": 11367.4, "total_tokens": 73433088} {"current_steps": 282, "total_steps": 755, "loss": 0.8306, "lr": 3.46751017757779e-05, "epoch": 1.860215053763441, "percentage": 37.35, "elapsed_time": "1:48:03", "remaining_time": "3:01:13", "throughput": 11367.44, "total_tokens": 73695232} {"current_steps": 283, "total_steps": 755, "loss": 0.8293, "lr": 3.457909797949633e-05, "epoch": 1.8668320926385442, "percentage": 37.48, "elapsed_time": "1:48:26", "remaining_time": "3:00:51", "throughput": 11367.52, "total_tokens": 73957376} {"current_steps": 284, "total_steps": 755, "loss": 0.8133, "lr": 3.448292832773269e-05, "epoch": 1.8734491315136477, "percentage": 37.62, "elapsed_time": "1:48:48", "remaining_time": "3:00:28", "throughput": 11367.69, "total_tokens": 74219520} {"current_steps": 285, "total_steps": 755, "loss": 0.8237, "lr": 3.438659448559825e-05, "epoch": 1.880066170388751, "percentage": 37.75, "elapsed_time": "1:49:11", "remaining_time": "3:00:04", "throughput": 11367.84, "total_tokens": 74481664} {"current_steps": 286, "total_steps": 755, "loss": 0.8272, "lr": 3.4290098121047114e-05, "epoch": 1.8866832092638544, "percentage": 37.88, "elapsed_time": "1:49:34", "remaining_time": "2:59:41", "throughput": 11368.02, "total_tokens": 74743808} {"current_steps": 287, "total_steps": 755, "loss": 0.8134, "lr": 3.419344090484736e-05, "epoch": 1.8933002481389578, "percentage": 38.01, "elapsed_time": "1:49:57", "remaining_time": "2:59:19", "throughput": 11368.08, "total_tokens": 75005952} {"current_steps": 288, "total_steps": 755, "loss": 0.8285, "lr": 3.409662451055208e-05, "epoch": 1.8999172870140613, "percentage": 38.15, "elapsed_time": "1:50:20", "remaining_time": "2:58:56", "throughput": 11368.14, "total_tokens": 75268096} {"current_steps": 289, "total_steps": 755, "loss": 0.8103, "lr": 3.3999650614470445e-05, "epoch": 1.9065343258891647, "percentage": 38.28, "elapsed_time": "1:50:43", "remaining_time": "2:58:33", "throughput": 11368.27, "total_tokens": 75530240} {"current_steps": 290, "total_steps": 755, "loss": 0.8357, "lr": 3.390252089563867e-05, "epoch": 1.913151364764268, "percentage": 38.41, "elapsed_time": "1:51:06", "remaining_time": "2:58:10", "throughput": 11368.39, "total_tokens": 75792384} {"current_steps": 291, "total_steps": 755, "loss": 0.8315, "lr": 3.3805237035790924e-05, "epoch": 1.9197684036393714, "percentage": 38.54, "elapsed_time": "1:51:29", "remaining_time": "2:57:47", "throughput": 11368.52, "total_tokens": 76054528} {"current_steps": 292, "total_steps": 755, "loss": 0.8288, "lr": 3.3707800719330184e-05, "epoch": 1.9263854425144746, "percentage": 38.68, "elapsed_time": "1:51:52", "remaining_time": "2:57:24", "throughput": 11368.61, "total_tokens": 76316672} {"current_steps": 293, "total_steps": 755, "loss": 0.806, "lr": 3.361021363329917e-05, "epoch": 1.933002481389578, "percentage": 38.81, "elapsed_time": "1:52:15", "remaining_time": "2:57:01", "throughput": 11368.66, "total_tokens": 76578816} {"current_steps": 294, "total_steps": 755, "loss": 0.8304, "lr": 3.351247746735103e-05, "epoch": 1.9396195202646815, "percentage": 38.94, "elapsed_time": "1:52:38", "remaining_time": "2:56:38", "throughput": 11368.69, "total_tokens": 76840960} {"current_steps": 295, "total_steps": 755, "loss": 0.8155, "lr": 3.341459391372016e-05, "epoch": 1.946236559139785, "percentage": 39.07, "elapsed_time": "1:53:02", "remaining_time": "2:56:15", "throughput": 11368.74, "total_tokens": 77103104} {"current_steps": 296, "total_steps": 755, "loss": 0.8155, "lr": 3.331656466719284e-05, "epoch": 1.9528535980148884, "percentage": 39.21, "elapsed_time": "1:53:25", "remaining_time": "2:55:52", "throughput": 11368.8, "total_tokens": 77365248} {"current_steps": 297, "total_steps": 755, "loss": 0.8303, "lr": 3.321839142507794e-05, "epoch": 1.9594706368899917, "percentage": 39.34, "elapsed_time": "1:53:48", "remaining_time": "2:55:29", "throughput": 11368.9, "total_tokens": 77627392} {"current_steps": 298, "total_steps": 755, "loss": 0.8032, "lr": 3.312007588717751e-05, "epoch": 1.9660876757650951, "percentage": 39.47, "elapsed_time": "1:54:11", "remaining_time": "2:55:06", "throughput": 11368.94, "total_tokens": 77889536} {"current_steps": 299, "total_steps": 755, "loss": 0.8294, "lr": 3.302161975575736e-05, "epoch": 1.9727047146401984, "percentage": 39.6, "elapsed_time": "1:54:34", "remaining_time": "2:54:43", "throughput": 11369.0, "total_tokens": 78151680} {"current_steps": 300, "total_steps": 755, "loss": 0.8063, "lr": 3.292302473551757e-05, "epoch": 1.9793217535153018, "percentage": 39.74, "elapsed_time": "1:54:57", "remaining_time": "2:54:20", "throughput": 11369.06, "total_tokens": 78413824} {"current_steps": 301, "total_steps": 755, "loss": 0.838, "lr": 3.2824292533562996e-05, "epoch": 1.9859387923904053, "percentage": 39.87, "elapsed_time": "1:55:20", "remaining_time": "2:53:57", "throughput": 11369.16, "total_tokens": 78675968} {"current_steps": 302, "total_steps": 755, "loss": 0.8241, "lr": 3.272542485937369e-05, "epoch": 1.9925558312655087, "percentage": 40.0, "elapsed_time": "1:55:43", "remaining_time": "2:53:34", "throughput": 11369.19, "total_tokens": 78938112} {"current_steps": 303, "total_steps": 755, "loss": 0.8247, "lr": 3.262642342477531e-05, "epoch": 1.9991728701406122, "percentage": 40.13, "elapsed_time": "1:56:06", "remaining_time": "2:53:11", "throughput": 11369.25, "total_tokens": 79200256} {"current_steps": 304, "total_steps": 755, "loss": 0.7627, "lr": 3.252728994390951e-05, "epoch": 2.0, "percentage": 40.26, "elapsed_time": "1:56:09", "remaining_time": "2:52:18", "throughput": 11369.32, "total_tokens": 79233024} {"current_steps": 305, "total_steps": 755, "loss": 0.4339, "lr": 3.2428026133204184e-05, "epoch": 2.0066170388751035, "percentage": 40.4, "elapsed_time": "1:56:32", "remaining_time": "2:51:56", "throughput": 11369.43, "total_tokens": 79495168} {"current_steps": 306, "total_steps": 755, "loss": 0.3822, "lr": 3.232863371134385e-05, "epoch": 2.013234077750207, "percentage": 40.53, "elapsed_time": "1:56:55", "remaining_time": "2:51:33", "throughput": 11369.46, "total_tokens": 79757312} {"current_steps": 307, "total_steps": 755, "loss": 0.3884, "lr": 3.2229114399239816e-05, "epoch": 2.0198511166253104, "percentage": 40.66, "elapsed_time": "1:57:18", "remaining_time": "2:51:10", "throughput": 11369.51, "total_tokens": 80019456} {"current_steps": 308, "total_steps": 755, "loss": 0.3673, "lr": 3.21294699200004e-05, "epoch": 2.0264681555004134, "percentage": 40.79, "elapsed_time": "1:57:41", "remaining_time": "2:50:47", "throughput": 11369.64, "total_tokens": 80281600} {"current_steps": 309, "total_steps": 755, "loss": 0.3706, "lr": 3.202970199890111e-05, "epoch": 2.033085194375517, "percentage": 40.93, "elapsed_time": "1:58:04", "remaining_time": "2:50:24", "throughput": 11369.75, "total_tokens": 80543744} {"current_steps": 310, "total_steps": 755, "loss": 0.355, "lr": 3.1929812363354766e-05, "epoch": 2.0397022332506203, "percentage": 41.06, "elapsed_time": "1:58:27", "remaining_time": "2:50:01", "throughput": 11369.88, "total_tokens": 80805888} {"current_steps": 311, "total_steps": 755, "loss": 0.319, "lr": 3.18298027428816e-05, "epoch": 2.0463192721257237, "percentage": 41.19, "elapsed_time": "1:58:50", "remaining_time": "2:49:39", "throughput": 11369.99, "total_tokens": 81068032} {"current_steps": 312, "total_steps": 755, "loss": 0.3391, "lr": 3.172967486907928e-05, "epoch": 2.052936311000827, "percentage": 41.32, "elapsed_time": "1:59:12", "remaining_time": "2:49:16", "throughput": 11370.13, "total_tokens": 81330176} {"current_steps": 313, "total_steps": 755, "loss": 0.3541, "lr": 3.1629430475592955e-05, "epoch": 2.0595533498759306, "percentage": 41.46, "elapsed_time": "1:59:36", "remaining_time": "2:48:53", "throughput": 11370.16, "total_tokens": 81592320} {"current_steps": 314, "total_steps": 755, "loss": 0.3352, "lr": 3.1529071298085236e-05, "epoch": 2.066170388751034, "percentage": 41.59, "elapsed_time": "1:59:59", "remaining_time": "2:48:30", "throughput": 11370.19, "total_tokens": 81854464} {"current_steps": 315, "total_steps": 755, "loss": 0.3281, "lr": 3.142859907420615e-05, "epoch": 2.072787427626137, "percentage": 41.72, "elapsed_time": "2:00:22", "remaining_time": "2:48:07", "throughput": 11370.28, "total_tokens": 82116608} {"current_steps": 316, "total_steps": 755, "loss": 0.3001, "lr": 3.132801554356303e-05, "epoch": 2.0794044665012406, "percentage": 41.85, "elapsed_time": "2:00:45", "remaining_time": "2:47:45", "throughput": 11370.37, "total_tokens": 82378752} {"current_steps": 317, "total_steps": 755, "loss": 0.3256, "lr": 3.122732244769041e-05, "epoch": 2.086021505376344, "percentage": 41.99, "elapsed_time": "2:01:08", "remaining_time": "2:47:22", "throughput": 11370.44, "total_tokens": 82640896} {"current_steps": 318, "total_steps": 755, "loss": 0.3314, "lr": 3.1126521530019874e-05, "epoch": 2.0926385442514475, "percentage": 42.12, "elapsed_time": "2:01:31", "remaining_time": "2:46:59", "throughput": 11370.51, "total_tokens": 82903040} {"current_steps": 319, "total_steps": 755, "loss": 0.3223, "lr": 3.102561453584987e-05, "epoch": 2.099255583126551, "percentage": 42.25, "elapsed_time": "2:01:54", "remaining_time": "2:46:36", "throughput": 11370.58, "total_tokens": 83165184} {"current_steps": 320, "total_steps": 755, "loss": 0.3128, "lr": 3.092460321231547e-05, "epoch": 2.1058726220016544, "percentage": 42.38, "elapsed_time": "2:02:17", "remaining_time": "2:46:13", "throughput": 11370.69, "total_tokens": 83427328} {"current_steps": 321, "total_steps": 755, "loss": 0.2898, "lr": 3.0823489308358174e-05, "epoch": 2.112489660876758, "percentage": 42.52, "elapsed_time": "2:02:40", "remaining_time": "2:45:51", "throughput": 11370.64, "total_tokens": 83689472} {"current_steps": 322, "total_steps": 755, "loss": 0.3104, "lr": 3.072227457469554e-05, "epoch": 2.119106699751861, "percentage": 42.65, "elapsed_time": "2:03:03", "remaining_time": "2:45:28", "throughput": 11370.71, "total_tokens": 83951616} {"current_steps": 323, "total_steps": 755, "loss": 0.3207, "lr": 3.062096076379097e-05, "epoch": 2.1257237386269643, "percentage": 42.78, "elapsed_time": "2:03:26", "remaining_time": "2:45:05", "throughput": 11370.78, "total_tokens": 84213760} {"current_steps": 324, "total_steps": 755, "loss": 0.301, "lr": 3.0519549629823286e-05, "epoch": 2.1323407775020677, "percentage": 42.91, "elapsed_time": "2:03:49", "remaining_time": "2:44:42", "throughput": 11370.89, "total_tokens": 84475904} {"current_steps": 325, "total_steps": 755, "loss": 0.3116, "lr": 3.0418042928656414e-05, "epoch": 2.138957816377171, "percentage": 43.05, "elapsed_time": "2:04:12", "remaining_time": "2:44:19", "throughput": 11370.92, "total_tokens": 84738048} {"current_steps": 326, "total_steps": 755, "loss": 0.3103, "lr": 3.0316442417808954e-05, "epoch": 2.1455748552522746, "percentage": 43.18, "elapsed_time": "2:04:35", "remaining_time": "2:43:57", "throughput": 11370.95, "total_tokens": 85000192} {"current_steps": 327, "total_steps": 755, "loss": 0.2903, "lr": 3.0214749856423745e-05, "epoch": 2.152191894127378, "percentage": 43.31, "elapsed_time": "2:04:58", "remaining_time": "2:43:34", "throughput": 11371.01, "total_tokens": 85262336} {"current_steps": 328, "total_steps": 755, "loss": 0.2805, "lr": 3.0112967005237443e-05, "epoch": 2.1588089330024816, "percentage": 43.44, "elapsed_time": "2:05:21", "remaining_time": "2:43:11", "throughput": 11370.98, "total_tokens": 85524480} {"current_steps": 329, "total_steps": 755, "loss": 0.2949, "lr": 3.0011095626549977e-05, "epoch": 2.1654259718775846, "percentage": 43.58, "elapsed_time": "2:05:44", "remaining_time": "2:42:48", "throughput": 11371.08, "total_tokens": 85786624} {"current_steps": 330, "total_steps": 755, "loss": 0.3336, "lr": 2.990913748419411e-05, "epoch": 2.172043010752688, "percentage": 43.71, "elapsed_time": "2:06:07", "remaining_time": "2:42:25", "throughput": 11371.1, "total_tokens": 86048768} {"current_steps": 331, "total_steps": 755, "loss": 0.33, "lr": 2.9807094343504804e-05, "epoch": 2.1786600496277915, "percentage": 43.84, "elapsed_time": "2:06:30", "remaining_time": "2:42:02", "throughput": 11371.19, "total_tokens": 86310912} {"current_steps": 332, "total_steps": 755, "loss": 0.3159, "lr": 2.9704967971288755e-05, "epoch": 2.185277088502895, "percentage": 43.97, "elapsed_time": "2:06:53", "remaining_time": "2:41:40", "throughput": 11371.22, "total_tokens": 86573056} {"current_steps": 333, "total_steps": 755, "loss": 0.2962, "lr": 2.9602760135793735e-05, "epoch": 2.1918941273779984, "percentage": 44.11, "elapsed_time": "2:07:16", "remaining_time": "2:41:17", "throughput": 11371.21, "total_tokens": 86835200} {"current_steps": 334, "total_steps": 755, "loss": 0.2863, "lr": 2.9500472606677994e-05, "epoch": 2.198511166253102, "percentage": 44.24, "elapsed_time": "2:07:39", "remaining_time": "2:40:54", "throughput": 11371.29, "total_tokens": 87097344} {"current_steps": 335, "total_steps": 755, "loss": 0.3101, "lr": 2.9398107154979638e-05, "epoch": 2.2051282051282053, "percentage": 44.37, "elapsed_time": "2:08:02", "remaining_time": "2:40:31", "throughput": 11371.36, "total_tokens": 87359488} {"current_steps": 336, "total_steps": 755, "loss": 0.3145, "lr": 2.9295665553085937e-05, "epoch": 2.2117452440033087, "percentage": 44.5, "elapsed_time": "2:08:25", "remaining_time": "2:40:08", "throughput": 11371.44, "total_tokens": 87621632} {"current_steps": 337, "total_steps": 755, "loss": 0.2981, "lr": 2.919314957470265e-05, "epoch": 2.2183622828784118, "percentage": 44.64, "elapsed_time": "2:08:48", "remaining_time": "2:39:45", "throughput": 11371.51, "total_tokens": 87883776} {"current_steps": 338, "total_steps": 755, "loss": 0.305, "lr": 2.909056099482332e-05, "epoch": 2.224979321753515, "percentage": 44.77, "elapsed_time": "2:09:11", "remaining_time": "2:39:23", "throughput": 11371.54, "total_tokens": 88145920} {"current_steps": 339, "total_steps": 755, "loss": 0.296, "lr": 2.8987901589698517e-05, "epoch": 2.2315963606286187, "percentage": 44.9, "elapsed_time": "2:09:34", "remaining_time": "2:39:00", "throughput": 11371.64, "total_tokens": 88408064} {"current_steps": 340, "total_steps": 755, "loss": 0.3042, "lr": 2.8885173136805127e-05, "epoch": 2.238213399503722, "percentage": 45.03, "elapsed_time": "2:09:57", "remaining_time": "2:38:37", "throughput": 11371.65, "total_tokens": 88670208} {"current_steps": 341, "total_steps": 755, "loss": 0.3151, "lr": 2.8782377414815532e-05, "epoch": 2.2448304383788256, "percentage": 45.17, "elapsed_time": "2:10:20", "remaining_time": "2:38:14", "throughput": 11371.68, "total_tokens": 88932352} {"current_steps": 342, "total_steps": 755, "loss": 0.2969, "lr": 2.867951620356684e-05, "epoch": 2.251447477253929, "percentage": 45.3, "elapsed_time": "2:10:43", "remaining_time": "2:37:51", "throughput": 11371.76, "total_tokens": 89194496} {"current_steps": 343, "total_steps": 755, "loss": 0.3004, "lr": 2.8576591284030058e-05, "epoch": 2.258064516129032, "percentage": 45.43, "elapsed_time": "2:11:06", "remaining_time": "2:37:28", "throughput": 11371.85, "total_tokens": 89456640} {"current_steps": 344, "total_steps": 755, "loss": 0.3203, "lr": 2.847360443827926e-05, "epoch": 2.2646815550041355, "percentage": 45.56, "elapsed_time": "2:11:29", "remaining_time": "2:37:06", "throughput": 11371.92, "total_tokens": 89718784} {"current_steps": 345, "total_steps": 755, "loss": 0.3264, "lr": 2.837055744946072e-05, "epoch": 2.271298593879239, "percentage": 45.7, "elapsed_time": "2:11:52", "remaining_time": "2:36:43", "throughput": 11372.04, "total_tokens": 89980928} {"current_steps": 346, "total_steps": 755, "loss": 0.3076, "lr": 2.826745210176207e-05, "epoch": 2.2779156327543424, "percentage": 45.83, "elapsed_time": "2:12:15", "remaining_time": "2:36:20", "throughput": 11372.1, "total_tokens": 90243072} {"current_steps": 347, "total_steps": 755, "loss": 0.321, "lr": 2.8164290180381365e-05, "epoch": 2.284532671629446, "percentage": 45.96, "elapsed_time": "2:12:38", "remaining_time": "2:35:57", "throughput": 11372.22, "total_tokens": 90505216} {"current_steps": 348, "total_steps": 755, "loss": 0.3185, "lr": 2.8061073471496195e-05, "epoch": 2.2911497105045493, "percentage": 46.09, "elapsed_time": "2:13:01", "remaining_time": "2:35:34", "throughput": 11372.23, "total_tokens": 90767360} {"current_steps": 349, "total_steps": 755, "loss": 0.3285, "lr": 2.795780376223277e-05, "epoch": 2.2977667493796528, "percentage": 46.23, "elapsed_time": "2:13:24", "remaining_time": "2:35:11", "throughput": 11372.27, "total_tokens": 91029504} {"current_steps": 350, "total_steps": 755, "loss": 0.303, "lr": 2.7854482840634965e-05, "epoch": 2.304383788254756, "percentage": 46.36, "elapsed_time": "2:13:47", "remaining_time": "2:34:48", "throughput": 11372.36, "total_tokens": 91291648} {"current_steps": 351, "total_steps": 755, "loss": 0.312, "lr": 2.7751112495633345e-05, "epoch": 2.311000827129859, "percentage": 46.49, "elapsed_time": "2:14:10", "remaining_time": "2:34:26", "throughput": 11372.43, "total_tokens": 91553792} {"current_steps": 352, "total_steps": 755, "loss": 0.3129, "lr": 2.764769451701421e-05, "epoch": 2.3176178660049627, "percentage": 46.62, "elapsed_time": "2:14:33", "remaining_time": "2:34:03", "throughput": 11372.53, "total_tokens": 91815936} {"current_steps": 353, "total_steps": 755, "loss": 0.3206, "lr": 2.7544230695388634e-05, "epoch": 2.324234904880066, "percentage": 46.75, "elapsed_time": "2:14:56", "remaining_time": "2:33:40", "throughput": 11372.6, "total_tokens": 92078080} {"current_steps": 354, "total_steps": 755, "loss": 0.3189, "lr": 2.744072282216139e-05, "epoch": 2.3308519437551696, "percentage": 46.89, "elapsed_time": "2:15:19", "remaining_time": "2:33:17", "throughput": 11372.68, "total_tokens": 92340224} {"current_steps": 355, "total_steps": 755, "loss": 0.3192, "lr": 2.73371726895e-05, "epoch": 2.337468982630273, "percentage": 47.02, "elapsed_time": "2:15:42", "remaining_time": "2:32:54", "throughput": 11372.74, "total_tokens": 92602368} {"current_steps": 356, "total_steps": 755, "loss": 0.3015, "lr": 2.7233582090303674e-05, "epoch": 2.3440860215053765, "percentage": 47.15, "elapsed_time": "2:16:05", "remaining_time": "2:32:31", "throughput": 11372.72, "total_tokens": 92864512} {"current_steps": 357, "total_steps": 755, "loss": 0.3168, "lr": 2.7129952818172256e-05, "epoch": 2.3507030603804795, "percentage": 47.28, "elapsed_time": "2:16:28", "remaining_time": "2:32:09", "throughput": 11372.72, "total_tokens": 93126656} {"current_steps": 358, "total_steps": 755, "loss": 0.303, "lr": 2.702628666737521e-05, "epoch": 2.357320099255583, "percentage": 47.42, "elapsed_time": "2:16:51", "remaining_time": "2:31:46", "throughput": 11372.75, "total_tokens": 93388800} {"current_steps": 359, "total_steps": 755, "loss": 0.2991, "lr": 2.692258543282052e-05, "epoch": 2.3639371381306864, "percentage": 47.55, "elapsed_time": "2:17:14", "remaining_time": "2:31:23", "throughput": 11372.76, "total_tokens": 93650944} {"current_steps": 360, "total_steps": 755, "loss": 0.3166, "lr": 2.68188509100236e-05, "epoch": 2.37055417700579, "percentage": 47.68, "elapsed_time": "2:17:37", "remaining_time": "2:31:00", "throughput": 11372.82, "total_tokens": 93913088} {"current_steps": 361, "total_steps": 755, "loss": 0.3199, "lr": 2.671508489507626e-05, "epoch": 2.3771712158808933, "percentage": 47.81, "elapsed_time": "2:18:00", "remaining_time": "2:30:37", "throughput": 11372.89, "total_tokens": 94175232} {"current_steps": 362, "total_steps": 755, "loss": 0.3152, "lr": 2.6611289184615558e-05, "epoch": 2.3837882547559968, "percentage": 47.95, "elapsed_time": "2:18:23", "remaining_time": "2:30:14", "throughput": 11372.92, "total_tokens": 94437376} {"current_steps": 363, "total_steps": 755, "loss": 0.3098, "lr": 2.6507465575792707e-05, "epoch": 2.3904052936311, "percentage": 48.08, "elapsed_time": "2:18:46", "remaining_time": "2:29:51", "throughput": 11372.96, "total_tokens": 94699520} {"current_steps": 364, "total_steps": 755, "loss": 0.3196, "lr": 2.6403615866241964e-05, "epoch": 2.3970223325062037, "percentage": 48.21, "elapsed_time": "2:19:09", "remaining_time": "2:29:29", "throughput": 11373.0, "total_tokens": 94961664} {"current_steps": 365, "total_steps": 755, "loss": 0.3031, "lr": 2.6299741854049508e-05, "epoch": 2.4036393713813067, "percentage": 48.34, "elapsed_time": "2:19:32", "remaining_time": "2:29:06", "throughput": 11373.07, "total_tokens": 95223808} {"current_steps": 366, "total_steps": 755, "loss": 0.3095, "lr": 2.6195845337722303e-05, "epoch": 2.41025641025641, "percentage": 48.48, "elapsed_time": "2:19:55", "remaining_time": "2:28:43", "throughput": 11373.12, "total_tokens": 95485952} {"current_steps": 367, "total_steps": 755, "loss": 0.3082, "lr": 2.6091928116156938e-05, "epoch": 2.4168734491315136, "percentage": 48.61, "elapsed_time": "2:20:18", "remaining_time": "2:28:20", "throughput": 11373.19, "total_tokens": 95748096} {"current_steps": 368, "total_steps": 755, "loss": 0.3046, "lr": 2.598799198860853e-05, "epoch": 2.423490488006617, "percentage": 48.74, "elapsed_time": "2:20:41", "remaining_time": "2:27:57", "throughput": 11373.22, "total_tokens": 96010240} {"current_steps": 369, "total_steps": 755, "loss": 0.3248, "lr": 2.5884038754659497e-05, "epoch": 2.4301075268817205, "percentage": 48.87, "elapsed_time": "2:21:04", "remaining_time": "2:27:34", "throughput": 11373.27, "total_tokens": 96272384} {"current_steps": 370, "total_steps": 755, "loss": 0.3049, "lr": 2.5780070214188478e-05, "epoch": 2.436724565756824, "percentage": 49.01, "elapsed_time": "2:21:27", "remaining_time": "2:27:11", "throughput": 11373.29, "total_tokens": 96534528} {"current_steps": 371, "total_steps": 755, "loss": 0.3142, "lr": 2.5676088167339128e-05, "epoch": 2.4433416046319274, "percentage": 49.14, "elapsed_time": "2:21:50", "remaining_time": "2:26:49", "throughput": 11373.36, "total_tokens": 96796672} {"current_steps": 372, "total_steps": 755, "loss": 0.3193, "lr": 2.5572094414488944e-05, "epoch": 2.4499586435070304, "percentage": 49.27, "elapsed_time": "2:22:13", "remaining_time": "2:26:26", "throughput": 11373.38, "total_tokens": 97058816} {"current_steps": 373, "total_steps": 755, "loss": 0.3082, "lr": 2.5468090756218117e-05, "epoch": 2.456575682382134, "percentage": 49.4, "elapsed_time": "2:22:36", "remaining_time": "2:26:03", "throughput": 11373.44, "total_tokens": 97320960} {"current_steps": 374, "total_steps": 755, "loss": 0.3145, "lr": 2.5364078993278335e-05, "epoch": 2.4631927212572373, "percentage": 49.54, "elapsed_time": "2:22:59", "remaining_time": "2:25:40", "throughput": 11373.5, "total_tokens": 97583104} {"current_steps": 375, "total_steps": 755, "loss": 0.3283, "lr": 2.526006092656161e-05, "epoch": 2.4698097601323408, "percentage": 49.67, "elapsed_time": "2:23:22", "remaining_time": "2:25:17", "throughput": 11373.55, "total_tokens": 97845248} {"current_steps": 376, "total_steps": 755, "loss": 0.3151, "lr": 2.5156038357069106e-05, "epoch": 2.4764267990074442, "percentage": 49.8, "elapsed_time": "2:23:45", "remaining_time": "2:24:54", "throughput": 11373.66, "total_tokens": 98107392} {"current_steps": 377, "total_steps": 755, "loss": 0.3168, "lr": 2.5052013085879955e-05, "epoch": 2.4830438378825477, "percentage": 49.93, "elapsed_time": "2:24:08", "remaining_time": "2:24:31", "throughput": 11373.69, "total_tokens": 98369536} {"current_steps": 378, "total_steps": 755, "loss": 0.3169, "lr": 2.494798691412005e-05, "epoch": 2.489660876757651, "percentage": 50.07, "elapsed_time": "2:24:31", "remaining_time": "2:24:08", "throughput": 11373.77, "total_tokens": 98631680} {"current_steps": 379, "total_steps": 755, "loss": 0.3072, "lr": 2.4843961642930904e-05, "epoch": 2.4962779156327546, "percentage": 50.2, "elapsed_time": "2:24:54", "remaining_time": "2:23:46", "throughput": 11373.78, "total_tokens": 98893824} {"current_steps": 380, "total_steps": 755, "loss": 0.2986, "lr": 2.4739939073438397e-05, "epoch": 2.5028949545078576, "percentage": 50.33, "elapsed_time": "2:25:17", "remaining_time": "2:23:23", "throughput": 11373.86, "total_tokens": 99155968} {"current_steps": 381, "total_steps": 755, "loss": 0.3063, "lr": 2.463592100672168e-05, "epoch": 2.509511993382961, "percentage": 50.46, "elapsed_time": "2:25:40", "remaining_time": "2:23:00", "throughput": 11373.94, "total_tokens": 99418112} {"current_steps": 382, "total_steps": 755, "loss": 0.2996, "lr": 2.4531909243781885e-05, "epoch": 2.5161290322580645, "percentage": 50.6, "elapsed_time": "2:26:03", "remaining_time": "2:22:37", "throughput": 11374.06, "total_tokens": 99680256} {"current_steps": 383, "total_steps": 755, "loss": 0.3178, "lr": 2.442790558551106e-05, "epoch": 2.522746071133168, "percentage": 50.73, "elapsed_time": "2:26:26", "remaining_time": "2:22:14", "throughput": 11374.1, "total_tokens": 99942400} {"current_steps": 384, "total_steps": 755, "loss": 0.317, "lr": 2.4323911832660874e-05, "epoch": 2.5293631100082714, "percentage": 50.86, "elapsed_time": "2:26:49", "remaining_time": "2:21:51", "throughput": 11374.11, "total_tokens": 100204544} {"current_steps": 385, "total_steps": 755, "loss": 0.3103, "lr": 2.4219929785811518e-05, "epoch": 2.5359801488833744, "percentage": 50.99, "elapsed_time": "2:27:12", "remaining_time": "2:21:28", "throughput": 11374.18, "total_tokens": 100466688} {"current_steps": 386, "total_steps": 755, "loss": 0.311, "lr": 2.4115961245340505e-05, "epoch": 2.542597187758478, "percentage": 51.13, "elapsed_time": "2:27:35", "remaining_time": "2:21:05", "throughput": 11374.22, "total_tokens": 100728832} {"current_steps": 387, "total_steps": 755, "loss": 0.323, "lr": 2.401200801139148e-05, "epoch": 2.5492142266335813, "percentage": 51.26, "elapsed_time": "2:27:58", "remaining_time": "2:20:42", "throughput": 11374.26, "total_tokens": 100990976} {"current_steps": 388, "total_steps": 755, "loss": 0.3182, "lr": 2.3908071883843068e-05, "epoch": 2.555831265508685, "percentage": 51.39, "elapsed_time": "2:28:21", "remaining_time": "2:20:20", "throughput": 11374.32, "total_tokens": 101253120} {"current_steps": 389, "total_steps": 755, "loss": 0.3139, "lr": 2.38041546622777e-05, "epoch": 2.5624483043837882, "percentage": 51.52, "elapsed_time": "2:28:44", "remaining_time": "2:19:57", "throughput": 11374.37, "total_tokens": 101515264} {"current_steps": 390, "total_steps": 755, "loss": 0.3395, "lr": 2.3700258145950495e-05, "epoch": 2.5690653432588917, "percentage": 51.66, "elapsed_time": "2:29:07", "remaining_time": "2:19:34", "throughput": 11374.44, "total_tokens": 101777408} {"current_steps": 391, "total_steps": 755, "loss": 0.3164, "lr": 2.359638413375804e-05, "epoch": 2.575682382133995, "percentage": 51.79, "elapsed_time": "2:29:30", "remaining_time": "2:19:11", "throughput": 11374.57, "total_tokens": 102039552} {"current_steps": 392, "total_steps": 755, "loss": 0.2995, "lr": 2.349253442420731e-05, "epoch": 2.5822994210090986, "percentage": 51.92, "elapsed_time": "2:29:53", "remaining_time": "2:18:48", "throughput": 11374.6, "total_tokens": 102301696} {"current_steps": 393, "total_steps": 755, "loss": 0.2966, "lr": 2.338871081538445e-05, "epoch": 2.588916459884202, "percentage": 52.05, "elapsed_time": "2:30:16", "remaining_time": "2:18:25", "throughput": 11374.65, "total_tokens": 102563840} {"current_steps": 394, "total_steps": 755, "loss": 0.3088, "lr": 2.3284915104923752e-05, "epoch": 2.595533498759305, "percentage": 52.19, "elapsed_time": "2:30:39", "remaining_time": "2:18:02", "throughput": 11374.71, "total_tokens": 102825984} {"current_steps": 395, "total_steps": 755, "loss": 0.324, "lr": 2.3181149089976405e-05, "epoch": 2.6021505376344085, "percentage": 52.32, "elapsed_time": "2:31:02", "remaining_time": "2:17:39", "throughput": 11374.76, "total_tokens": 103088128} {"current_steps": 396, "total_steps": 755, "loss": 0.3127, "lr": 2.3077414567179494e-05, "epoch": 2.608767576509512, "percentage": 52.45, "elapsed_time": "2:31:25", "remaining_time": "2:17:16", "throughput": 11374.83, "total_tokens": 103350272} {"current_steps": 397, "total_steps": 755, "loss": 0.3021, "lr": 2.2973713332624796e-05, "epoch": 2.6153846153846154, "percentage": 52.58, "elapsed_time": "2:31:48", "remaining_time": "2:16:54", "throughput": 11374.83, "total_tokens": 103612416} {"current_steps": 398, "total_steps": 755, "loss": 0.3107, "lr": 2.2870047181827743e-05, "epoch": 2.622001654259719, "percentage": 52.72, "elapsed_time": "2:32:11", "remaining_time": "2:16:31", "throughput": 11374.93, "total_tokens": 103874560} {"current_steps": 399, "total_steps": 755, "loss": 0.3287, "lr": 2.2766417909696332e-05, "epoch": 2.6286186931348223, "percentage": 52.85, "elapsed_time": "2:32:34", "remaining_time": "2:16:08", "throughput": 11374.99, "total_tokens": 104136704} {"current_steps": 400, "total_steps": 755, "loss": 0.3065, "lr": 2.2662827310499995e-05, "epoch": 2.6352357320099253, "percentage": 52.98, "elapsed_time": "2:32:57", "remaining_time": "2:15:45", "throughput": 11375.04, "total_tokens": 104398848} {"current_steps": 401, "total_steps": 755, "loss": 0.3067, "lr": 2.2559277177838612e-05, "epoch": 2.641852770885029, "percentage": 53.11, "elapsed_time": "2:33:20", "remaining_time": "2:15:22", "throughput": 11375.08, "total_tokens": 104660992} {"current_steps": 402, "total_steps": 755, "loss": 0.3216, "lr": 2.2455769304611365e-05, "epoch": 2.6484698097601322, "percentage": 53.25, "elapsed_time": "2:33:43", "remaining_time": "2:14:59", "throughput": 11375.13, "total_tokens": 104923136} {"current_steps": 403, "total_steps": 755, "loss": 0.3066, "lr": 2.2352305482985793e-05, "epoch": 2.6550868486352357, "percentage": 53.38, "elapsed_time": "2:34:06", "remaining_time": "2:14:36", "throughput": 11375.18, "total_tokens": 105185280} {"current_steps": 404, "total_steps": 755, "loss": 0.3049, "lr": 2.224888750436666e-05, "epoch": 2.661703887510339, "percentage": 53.51, "elapsed_time": "2:34:29", "remaining_time": "2:14:13", "throughput": 11375.2, "total_tokens": 105447424} {"current_steps": 405, "total_steps": 755, "loss": 0.3176, "lr": 2.2145517159365044e-05, "epoch": 2.6683209263854426, "percentage": 53.64, "elapsed_time": "2:34:52", "remaining_time": "2:13:50", "throughput": 11375.25, "total_tokens": 105709568} {"current_steps": 406, "total_steps": 755, "loss": 0.3256, "lr": 2.2042196237767233e-05, "epoch": 2.674937965260546, "percentage": 53.77, "elapsed_time": "2:35:15", "remaining_time": "2:13:28", "throughput": 11375.35, "total_tokens": 105971712} {"current_steps": 407, "total_steps": 755, "loss": 0.3325, "lr": 2.1938926528503807e-05, "epoch": 2.6815550041356495, "percentage": 53.91, "elapsed_time": "2:35:38", "remaining_time": "2:13:05", "throughput": 11375.46, "total_tokens": 106233856} {"current_steps": 408, "total_steps": 755, "loss": 0.3034, "lr": 2.183570981961864e-05, "epoch": 2.688172043010753, "percentage": 54.04, "elapsed_time": "2:36:01", "remaining_time": "2:12:42", "throughput": 11375.48, "total_tokens": 106496000} {"current_steps": 409, "total_steps": 755, "loss": 0.3134, "lr": 2.173254789823794e-05, "epoch": 2.694789081885856, "percentage": 54.17, "elapsed_time": "2:36:24", "remaining_time": "2:12:19", "throughput": 11375.5, "total_tokens": 106758144} {"current_steps": 410, "total_steps": 755, "loss": 0.3219, "lr": 2.162944255053928e-05, "epoch": 2.7014061207609594, "percentage": 54.3, "elapsed_time": "2:36:47", "remaining_time": "2:11:56", "throughput": 11375.57, "total_tokens": 107020288} {"current_steps": 411, "total_steps": 755, "loss": 0.3123, "lr": 2.1526395561720742e-05, "epoch": 2.708023159636063, "percentage": 54.44, "elapsed_time": "2:37:11", "remaining_time": "2:11:33", "throughput": 11375.36, "total_tokens": 107282432} {"current_steps": 412, "total_steps": 755, "loss": 0.3312, "lr": 2.1423408715969948e-05, "epoch": 2.7146401985111663, "percentage": 54.57, "elapsed_time": "2:37:34", "remaining_time": "2:11:11", "throughput": 11375.09, "total_tokens": 107544576} {"current_steps": 413, "total_steps": 755, "loss": 0.3022, "lr": 2.132048379643316e-05, "epoch": 2.72125723738627, "percentage": 54.7, "elapsed_time": "2:37:57", "remaining_time": "2:10:48", "throughput": 11374.93, "total_tokens": 107806720} {"current_steps": 414, "total_steps": 755, "loss": 0.2983, "lr": 2.1217622585184474e-05, "epoch": 2.727874276261373, "percentage": 54.83, "elapsed_time": "2:38:20", "remaining_time": "2:10:25", "throughput": 11374.64, "total_tokens": 108068864} {"current_steps": 415, "total_steps": 755, "loss": 0.3199, "lr": 2.1114826863194882e-05, "epoch": 2.7344913151364763, "percentage": 54.97, "elapsed_time": "2:38:43", "remaining_time": "2:10:02", "throughput": 11374.71, "total_tokens": 108331008} {"current_steps": 416, "total_steps": 755, "loss": 0.3112, "lr": 2.101209841030149e-05, "epoch": 2.7411083540115797, "percentage": 55.1, "elapsed_time": "2:39:06", "remaining_time": "2:09:39", "throughput": 11374.72, "total_tokens": 108593152} {"current_steps": 417, "total_steps": 755, "loss": 0.3024, "lr": 2.090943900517669e-05, "epoch": 2.747725392886683, "percentage": 55.23, "elapsed_time": "2:39:29", "remaining_time": "2:09:16", "throughput": 11374.76, "total_tokens": 108855296} {"current_steps": 418, "total_steps": 755, "loss": 0.3161, "lr": 2.0806850425297363e-05, "epoch": 2.7543424317617866, "percentage": 55.36, "elapsed_time": "2:39:52", "remaining_time": "2:08:54", "throughput": 11374.79, "total_tokens": 109117440} {"current_steps": 419, "total_steps": 755, "loss": 0.3052, "lr": 2.070433444691407e-05, "epoch": 2.76095947063689, "percentage": 55.5, "elapsed_time": "2:40:15", "remaining_time": "2:08:31", "throughput": 11374.84, "total_tokens": 109379584} {"current_steps": 420, "total_steps": 755, "loss": 0.3108, "lr": 2.060189284502037e-05, "epoch": 2.7675765095119935, "percentage": 55.63, "elapsed_time": "2:40:38", "remaining_time": "2:08:08", "throughput": 11374.89, "total_tokens": 109641728} {"current_steps": 421, "total_steps": 755, "loss": 0.2953, "lr": 2.049952739332201e-05, "epoch": 2.774193548387097, "percentage": 55.76, "elapsed_time": "2:41:01", "remaining_time": "2:07:45", "throughput": 11374.97, "total_tokens": 109903872} {"current_steps": 422, "total_steps": 755, "loss": 0.3272, "lr": 2.039723986420628e-05, "epoch": 2.7808105872622004, "percentage": 55.89, "elapsed_time": "2:41:24", "remaining_time": "2:07:22", "throughput": 11375.04, "total_tokens": 110166016} {"current_steps": 423, "total_steps": 755, "loss": 0.3181, "lr": 2.029503202871125e-05, "epoch": 2.7874276261373034, "percentage": 56.03, "elapsed_time": "2:41:47", "remaining_time": "2:06:59", "throughput": 11375.1, "total_tokens": 110428160} {"current_steps": 424, "total_steps": 755, "loss": 0.3256, "lr": 2.01929056564952e-05, "epoch": 2.794044665012407, "percentage": 56.16, "elapsed_time": "2:42:10", "remaining_time": "2:06:36", "throughput": 11375.15, "total_tokens": 110690304} {"current_steps": 425, "total_steps": 755, "loss": 0.3363, "lr": 2.0090862515805898e-05, "epoch": 2.8006617038875103, "percentage": 56.29, "elapsed_time": "2:42:33", "remaining_time": "2:06:13", "throughput": 11375.23, "total_tokens": 110952448} {"current_steps": 426, "total_steps": 755, "loss": 0.2958, "lr": 1.9988904373450018e-05, "epoch": 2.807278742762614, "percentage": 56.42, "elapsed_time": "2:42:56", "remaining_time": "2:05:50", "throughput": 11375.29, "total_tokens": 111214592} {"current_steps": 427, "total_steps": 755, "loss": 0.3208, "lr": 1.9887032994762563e-05, "epoch": 2.8138957816377173, "percentage": 56.56, "elapsed_time": "2:43:19", "remaining_time": "2:05:27", "throughput": 11375.35, "total_tokens": 111476736} {"current_steps": 428, "total_steps": 755, "loss": 0.3161, "lr": 1.9785250143576254e-05, "epoch": 2.8205128205128203, "percentage": 56.69, "elapsed_time": "2:43:42", "remaining_time": "2:05:04", "throughput": 11375.35, "total_tokens": 111738880} {"current_steps": 429, "total_steps": 755, "loss": 0.3021, "lr": 1.9683557582191055e-05, "epoch": 2.8271298593879237, "percentage": 56.82, "elapsed_time": "2:44:05", "remaining_time": "2:04:41", "throughput": 11375.37, "total_tokens": 112001024} {"current_steps": 430, "total_steps": 755, "loss": 0.3092, "lr": 1.9581957071343592e-05, "epoch": 2.833746898263027, "percentage": 56.95, "elapsed_time": "2:44:28", "remaining_time": "2:04:19", "throughput": 11375.46, "total_tokens": 112263168} {"current_steps": 431, "total_steps": 755, "loss": 0.3126, "lr": 1.9480450370176726e-05, "epoch": 2.8403639371381306, "percentage": 57.09, "elapsed_time": "2:44:51", "remaining_time": "2:03:56", "throughput": 11375.52, "total_tokens": 112525312} {"current_steps": 432, "total_steps": 755, "loss": 0.3112, "lr": 1.9379039236209037e-05, "epoch": 2.846980976013234, "percentage": 57.22, "elapsed_time": "2:45:14", "remaining_time": "2:03:33", "throughput": 11375.6, "total_tokens": 112787456} {"current_steps": 433, "total_steps": 755, "loss": 0.3033, "lr": 1.9277725425304467e-05, "epoch": 2.8535980148883375, "percentage": 57.35, "elapsed_time": "2:45:37", "remaining_time": "2:03:10", "throughput": 11375.66, "total_tokens": 113049600} {"current_steps": 434, "total_steps": 755, "loss": 0.2997, "lr": 1.917651069164183e-05, "epoch": 2.860215053763441, "percentage": 57.48, "elapsed_time": "2:46:00", "remaining_time": "2:02:47", "throughput": 11375.74, "total_tokens": 113311744} {"current_steps": 435, "total_steps": 755, "loss": 0.316, "lr": 1.9075396787684533e-05, "epoch": 2.8668320926385444, "percentage": 57.62, "elapsed_time": "2:46:23", "remaining_time": "2:02:24", "throughput": 11375.84, "total_tokens": 113573888} {"current_steps": 436, "total_steps": 755, "loss": 0.3023, "lr": 1.8974385464150136e-05, "epoch": 2.873449131513648, "percentage": 57.75, "elapsed_time": "2:46:46", "remaining_time": "2:02:01", "throughput": 11375.86, "total_tokens": 113836032} {"current_steps": 437, "total_steps": 755, "loss": 0.3204, "lr": 1.8873478469980125e-05, "epoch": 2.880066170388751, "percentage": 57.88, "elapsed_time": "2:47:09", "remaining_time": "2:01:38", "throughput": 11375.92, "total_tokens": 114098176} {"current_steps": 438, "total_steps": 755, "loss": 0.3178, "lr": 1.8772677552309596e-05, "epoch": 2.8866832092638544, "percentage": 58.01, "elapsed_time": "2:47:32", "remaining_time": "2:01:15", "throughput": 11375.97, "total_tokens": 114360320} {"current_steps": 439, "total_steps": 755, "loss": 0.3326, "lr": 1.8671984456436968e-05, "epoch": 2.893300248138958, "percentage": 58.15, "elapsed_time": "2:47:55", "remaining_time": "2:00:52", "throughput": 11376.03, "total_tokens": 114622464} {"current_steps": 440, "total_steps": 755, "loss": 0.3219, "lr": 1.8571400925793855e-05, "epoch": 2.8999172870140613, "percentage": 58.28, "elapsed_time": "2:48:18", "remaining_time": "2:00:29", "throughput": 11376.09, "total_tokens": 114884608} {"current_steps": 441, "total_steps": 755, "loss": 0.2923, "lr": 1.8470928701914763e-05, "epoch": 2.9065343258891647, "percentage": 58.41, "elapsed_time": "2:48:41", "remaining_time": "2:00:06", "throughput": 11376.13, "total_tokens": 115146752} {"current_steps": 442, "total_steps": 755, "loss": 0.3005, "lr": 1.8370569524407054e-05, "epoch": 2.9131513647642677, "percentage": 58.54, "elapsed_time": "2:49:04", "remaining_time": "1:59:43", "throughput": 11376.17, "total_tokens": 115408896} {"current_steps": 443, "total_steps": 755, "loss": 0.2856, "lr": 1.8270325130920728e-05, "epoch": 2.919768403639371, "percentage": 58.68, "elapsed_time": "2:49:27", "remaining_time": "1:59:21", "throughput": 11376.26, "total_tokens": 115671040} {"current_steps": 444, "total_steps": 755, "loss": 0.3134, "lr": 1.817019725711841e-05, "epoch": 2.9263854425144746, "percentage": 58.81, "elapsed_time": "2:49:50", "remaining_time": "1:58:58", "throughput": 11376.28, "total_tokens": 115933184} {"current_steps": 445, "total_steps": 755, "loss": 0.3024, "lr": 1.807018763664524e-05, "epoch": 2.933002481389578, "percentage": 58.94, "elapsed_time": "2:50:13", "remaining_time": "1:58:35", "throughput": 11376.32, "total_tokens": 116195328} {"current_steps": 446, "total_steps": 755, "loss": 0.2955, "lr": 1.7970298001098897e-05, "epoch": 2.9396195202646815, "percentage": 59.07, "elapsed_time": "2:50:36", "remaining_time": "1:58:12", "throughput": 11376.34, "total_tokens": 116457472} {"current_steps": 447, "total_steps": 755, "loss": 0.3129, "lr": 1.787053007999961e-05, "epoch": 2.946236559139785, "percentage": 59.21, "elapsed_time": "2:50:59", "remaining_time": "1:57:49", "throughput": 11376.4, "total_tokens": 116719616} {"current_steps": 448, "total_steps": 755, "loss": 0.3243, "lr": 1.7770885600760183e-05, "epoch": 2.9528535980148884, "percentage": 59.34, "elapsed_time": "2:51:22", "remaining_time": "1:57:26", "throughput": 11376.44, "total_tokens": 116981760} {"current_steps": 449, "total_steps": 755, "loss": 0.3005, "lr": 1.7671366288656152e-05, "epoch": 2.959470636889992, "percentage": 59.47, "elapsed_time": "2:51:45", "remaining_time": "1:57:03", "throughput": 11376.47, "total_tokens": 117243904} {"current_steps": 450, "total_steps": 755, "loss": 0.3065, "lr": 1.7571973866795815e-05, "epoch": 2.9660876757650954, "percentage": 59.6, "elapsed_time": "2:52:08", "remaining_time": "1:56:40", "throughput": 11376.45, "total_tokens": 117506048} {"current_steps": 451, "total_steps": 755, "loss": 0.3231, "lr": 1.7472710056090502e-05, "epoch": 2.9727047146401984, "percentage": 59.74, "elapsed_time": "2:52:31", "remaining_time": "1:56:17", "throughput": 11376.49, "total_tokens": 117768192} {"current_steps": 452, "total_steps": 755, "loss": 0.3114, "lr": 1.7373576575224686e-05, "epoch": 2.979321753515302, "percentage": 59.87, "elapsed_time": "2:52:54", "remaining_time": "1:55:54", "throughput": 11376.56, "total_tokens": 118030336} {"current_steps": 453, "total_steps": 755, "loss": 0.308, "lr": 1.7274575140626318e-05, "epoch": 2.9859387923904053, "percentage": 60.0, "elapsed_time": "2:53:17", "remaining_time": "1:55:31", "throughput": 11376.63, "total_tokens": 118292480} {"current_steps": 454, "total_steps": 755, "loss": 0.3112, "lr": 1.7175707466437007e-05, "epoch": 2.9925558312655087, "percentage": 60.13, "elapsed_time": "2:53:40", "remaining_time": "1:55:08", "throughput": 11376.69, "total_tokens": 118554624} {"current_steps": 455, "total_steps": 755, "loss": 0.3087, "lr": 1.7076975264482434e-05, "epoch": 2.999172870140612, "percentage": 60.26, "elapsed_time": "2:54:03", "remaining_time": "1:54:46", "throughput": 11376.73, "total_tokens": 118816768} {"current_steps": 456, "total_steps": 755, "loss": 0.2879, "lr": 1.6978380244242647e-05, "epoch": 3.0, "percentage": 60.4, "elapsed_time": "2:54:06", "remaining_time": "1:54:09", "throughput": 11376.78, "total_tokens": 118849536} {"current_steps": 457, "total_steps": 755, "loss": 0.0983, "lr": 1.6879924112822505e-05, "epoch": 3.0066170388751035, "percentage": 60.53, "elapsed_time": "2:54:29", "remaining_time": "1:53:47", "throughput": 11376.79, "total_tokens": 119111680} {"current_steps": 458, "total_steps": 755, "loss": 0.0967, "lr": 1.678160857492207e-05, "epoch": 3.013234077750207, "percentage": 60.66, "elapsed_time": "2:54:52", "remaining_time": "1:53:24", "throughput": 11376.83, "total_tokens": 119373824} {"current_steps": 459, "total_steps": 755, "loss": 0.0938, "lr": 1.6683435332807172e-05, "epoch": 3.0198511166253104, "percentage": 60.79, "elapsed_time": "2:55:15", "remaining_time": "1:53:01", "throughput": 11376.9, "total_tokens": 119635968} {"current_steps": 460, "total_steps": 755, "loss": 0.0829, "lr": 1.658540608627985e-05, "epoch": 3.0264681555004134, "percentage": 60.93, "elapsed_time": "2:55:38", "remaining_time": "1:52:38", "throughput": 11376.94, "total_tokens": 119898112} {"current_steps": 461, "total_steps": 755, "loss": 0.0883, "lr": 1.6487522532648962e-05, "epoch": 3.033085194375517, "percentage": 61.06, "elapsed_time": "2:56:01", "remaining_time": "1:52:15", "throughput": 11376.95, "total_tokens": 120160256} {"current_steps": 462, "total_steps": 755, "loss": 0.0798, "lr": 1.6389786366700836e-05, "epoch": 3.0397022332506203, "percentage": 61.19, "elapsed_time": "2:56:24", "remaining_time": "1:51:52", "throughput": 11376.99, "total_tokens": 120422400} {"current_steps": 463, "total_steps": 755, "loss": 0.0784, "lr": 1.629219928066982e-05, "epoch": 3.0463192721257237, "percentage": 61.32, "elapsed_time": "2:56:47", "remaining_time": "1:51:29", "throughput": 11377.01, "total_tokens": 120684544} {"current_steps": 464, "total_steps": 755, "loss": 0.0934, "lr": 1.619476296420909e-05, "epoch": 3.052936311000827, "percentage": 61.46, "elapsed_time": "2:57:10", "remaining_time": "1:51:07", "throughput": 11377.07, "total_tokens": 120946688} {"current_steps": 465, "total_steps": 755, "loss": 0.0857, "lr": 1.6097479104361326e-05, "epoch": 3.0595533498759306, "percentage": 61.59, "elapsed_time": "2:57:33", "remaining_time": "1:50:44", "throughput": 11377.13, "total_tokens": 121208832} {"current_steps": 466, "total_steps": 755, "loss": 0.0781, "lr": 1.6000349385529557e-05, "epoch": 3.066170388751034, "percentage": 61.72, "elapsed_time": "2:57:56", "remaining_time": "1:50:21", "throughput": 11377.15, "total_tokens": 121470976} {"current_steps": 467, "total_steps": 755, "loss": 0.0886, "lr": 1.5903375489447925e-05, "epoch": 3.072787427626137, "percentage": 61.85, "elapsed_time": "2:58:19", "remaining_time": "1:49:58", "throughput": 11377.23, "total_tokens": 121733120} {"current_steps": 468, "total_steps": 755, "loss": 0.0758, "lr": 1.5806559095152652e-05, "epoch": 3.0794044665012406, "percentage": 61.99, "elapsed_time": "2:58:42", "remaining_time": "1:49:35", "throughput": 11377.28, "total_tokens": 121995264} {"current_steps": 469, "total_steps": 755, "loss": 0.076, "lr": 1.570990187895289e-05, "epoch": 3.086021505376344, "percentage": 62.12, "elapsed_time": "2:59:05", "remaining_time": "1:49:12", "throughput": 11377.26, "total_tokens": 122257408} {"current_steps": 470, "total_steps": 755, "loss": 0.0804, "lr": 1.561340551440176e-05, "epoch": 3.0926385442514475, "percentage": 62.25, "elapsed_time": "2:59:28", "remaining_time": "1:48:49", "throughput": 11377.31, "total_tokens": 122519552} {"current_steps": 471, "total_steps": 755, "loss": 0.0812, "lr": 1.5517071672267314e-05, "epoch": 3.099255583126551, "percentage": 62.38, "elapsed_time": "2:59:51", "remaining_time": "1:48:27", "throughput": 11377.37, "total_tokens": 122781696} {"current_steps": 472, "total_steps": 755, "loss": 0.0774, "lr": 1.542090202050368e-05, "epoch": 3.1058726220016544, "percentage": 62.52, "elapsed_time": "3:00:14", "remaining_time": "1:48:04", "throughput": 11377.4, "total_tokens": 123043840} {"current_steps": 473, "total_steps": 755, "loss": 0.0803, "lr": 1.532489822422211e-05, "epoch": 3.112489660876758, "percentage": 62.65, "elapsed_time": "3:00:37", "remaining_time": "1:47:41", "throughput": 11377.42, "total_tokens": 123305984} {"current_steps": 474, "total_steps": 755, "loss": 0.0731, "lr": 1.5229061945662198e-05, "epoch": 3.119106699751861, "percentage": 62.78, "elapsed_time": "3:01:00", "remaining_time": "1:47:18", "throughput": 11377.4, "total_tokens": 123568128} {"current_steps": 475, "total_steps": 755, "loss": 0.0733, "lr": 1.5133394844163093e-05, "epoch": 3.1257237386269643, "percentage": 62.91, "elapsed_time": "3:01:23", "remaining_time": "1:46:55", "throughput": 11377.4, "total_tokens": 123830272} {"current_steps": 476, "total_steps": 755, "loss": 0.0815, "lr": 1.503789857613473e-05, "epoch": 3.1323407775020677, "percentage": 63.05, "elapsed_time": "3:01:46", "remaining_time": "1:46:32", "throughput": 11377.45, "total_tokens": 124092416} {"current_steps": 477, "total_steps": 755, "loss": 0.0698, "lr": 1.4942574795029213e-05, "epoch": 3.138957816377171, "percentage": 63.18, "elapsed_time": "3:02:09", "remaining_time": "1:46:10", "throughput": 11377.46, "total_tokens": 124354560} {"current_steps": 478, "total_steps": 755, "loss": 0.0701, "lr": 1.4847425151312127e-05, "epoch": 3.1455748552522746, "percentage": 63.31, "elapsed_time": "3:02:32", "remaining_time": "1:45:47", "throughput": 11377.46, "total_tokens": 124616704} {"current_steps": 479, "total_steps": 755, "loss": 0.072, "lr": 1.4752451292434016e-05, "epoch": 3.152191894127378, "percentage": 63.44, "elapsed_time": "3:02:55", "remaining_time": "1:45:24", "throughput": 11377.49, "total_tokens": 124878848} {"current_steps": 480, "total_steps": 755, "loss": 0.0723, "lr": 1.4657654862801798e-05, "epoch": 3.1588089330024816, "percentage": 63.58, "elapsed_time": "3:03:18", "remaining_time": "1:45:01", "throughput": 11377.5, "total_tokens": 125140992} {"current_steps": 481, "total_steps": 755, "loss": 0.0718, "lr": 1.4563037503750366e-05, "epoch": 3.1654259718775846, "percentage": 63.71, "elapsed_time": "3:03:41", "remaining_time": "1:44:38", "throughput": 11377.55, "total_tokens": 125403136} {"current_steps": 482, "total_steps": 755, "loss": 0.0724, "lr": 1.446860085351407e-05, "epoch": 3.172043010752688, "percentage": 63.84, "elapsed_time": "3:04:05", "remaining_time": "1:44:15", "throughput": 11377.54, "total_tokens": 125665280} {"current_steps": 483, "total_steps": 755, "loss": 0.0696, "lr": 1.4374346547198486e-05, "epoch": 3.1786600496277915, "percentage": 63.97, "elapsed_time": "3:04:28", "remaining_time": "1:43:52", "throughput": 11377.54, "total_tokens": 125927424} {"current_steps": 484, "total_steps": 755, "loss": 0.073, "lr": 1.4280276216751956e-05, "epoch": 3.185277088502895, "percentage": 64.11, "elapsed_time": "3:04:51", "remaining_time": "1:43:30", "throughput": 11377.57, "total_tokens": 126189568} {"current_steps": 485, "total_steps": 755, "loss": 0.0723, "lr": 1.4186391490937481e-05, "epoch": 3.1918941273779984, "percentage": 64.24, "elapsed_time": "3:05:14", "remaining_time": "1:43:07", "throughput": 11377.61, "total_tokens": 126451712} {"current_steps": 486, "total_steps": 755, "loss": 0.0711, "lr": 1.4092693995304368e-05, "epoch": 3.198511166253102, "percentage": 64.37, "elapsed_time": "3:05:37", "remaining_time": "1:42:44", "throughput": 11377.63, "total_tokens": 126713856} {"current_steps": 487, "total_steps": 755, "loss": 0.0719, "lr": 1.3999185352160231e-05, "epoch": 3.2051282051282053, "percentage": 64.5, "elapsed_time": "3:06:00", "remaining_time": "1:42:21", "throughput": 11377.64, "total_tokens": 126976000} {"current_steps": 488, "total_steps": 755, "loss": 0.0737, "lr": 1.3905867180542803e-05, "epoch": 3.2117452440033087, "percentage": 64.64, "elapsed_time": "3:06:23", "remaining_time": "1:41:58", "throughput": 11377.63, "total_tokens": 127238144} {"current_steps": 489, "total_steps": 755, "loss": 0.0727, "lr": 1.3812741096191905e-05, "epoch": 3.2183622828784118, "percentage": 64.77, "elapsed_time": "3:06:46", "remaining_time": "1:41:35", "throughput": 11377.63, "total_tokens": 127500288} {"current_steps": 490, "total_steps": 755, "loss": 0.0694, "lr": 1.3719808711521573e-05, "epoch": 3.224979321753515, "percentage": 64.9, "elapsed_time": "3:07:09", "remaining_time": "1:41:12", "throughput": 11377.65, "total_tokens": 127762432} {"current_steps": 491, "total_steps": 755, "loss": 0.0661, "lr": 1.3627071635591976e-05, "epoch": 3.2315963606286187, "percentage": 65.03, "elapsed_time": "3:07:32", "remaining_time": "1:40:50", "throughput": 11377.66, "total_tokens": 128024576} {"current_steps": 492, "total_steps": 755, "loss": 0.0719, "lr": 1.353453147408174e-05, "epoch": 3.238213399503722, "percentage": 65.17, "elapsed_time": "3:07:55", "remaining_time": "1:40:27", "throughput": 11377.64, "total_tokens": 128286720} {"current_steps": 493, "total_steps": 755, "loss": 0.0707, "lr": 1.344218982925996e-05, "epoch": 3.2448304383788256, "percentage": 65.3, "elapsed_time": "3:08:18", "remaining_time": "1:40:04", "throughput": 11377.67, "total_tokens": 128548864} {"current_steps": 494, "total_steps": 755, "loss": 0.0678, "lr": 1.3350048299958645e-05, "epoch": 3.251447477253929, "percentage": 65.43, "elapsed_time": "3:08:41", "remaining_time": "1:39:41", "throughput": 11377.73, "total_tokens": 128811008} {"current_steps": 495, "total_steps": 755, "loss": 0.0633, "lr": 1.3258108481544849e-05, "epoch": 3.258064516129032, "percentage": 65.56, "elapsed_time": "3:09:04", "remaining_time": "1:39:18", "throughput": 11377.74, "total_tokens": 129073152} {"current_steps": 496, "total_steps": 755, "loss": 0.071, "lr": 1.3166371965893226e-05, "epoch": 3.2646815550041355, "percentage": 65.7, "elapsed_time": "3:09:27", "remaining_time": "1:38:55", "throughput": 11377.77, "total_tokens": 129335296} {"current_steps": 497, "total_steps": 755, "loss": 0.07, "lr": 1.3074840341358318e-05, "epoch": 3.271298593879239, "percentage": 65.83, "elapsed_time": "3:09:50", "remaining_time": "1:38:32", "throughput": 11377.82, "total_tokens": 129597440} {"current_steps": 498, "total_steps": 755, "loss": 0.0691, "lr": 1.2983515192747153e-05, "epoch": 3.2779156327543424, "percentage": 65.96, "elapsed_time": "3:10:13", "remaining_time": "1:38:10", "throughput": 11377.84, "total_tokens": 129859584} {"current_steps": 499, "total_steps": 755, "loss": 0.0635, "lr": 1.2892398101291759e-05, "epoch": 3.284532671629446, "percentage": 66.09, "elapsed_time": "3:10:36", "remaining_time": "1:37:47", "throughput": 11377.84, "total_tokens": 130121728} {"current_steps": 500, "total_steps": 755, "loss": 0.0637, "lr": 1.2801490644621789e-05, "epoch": 3.2911497105045493, "percentage": 66.23, "elapsed_time": "3:10:59", "remaining_time": "1:37:24", "throughput": 11377.84, "total_tokens": 130383872} {"current_steps": 501, "total_steps": 755, "loss": 0.0674, "lr": 1.271079439673726e-05, "epoch": 3.2977667493796528, "percentage": 66.36, "elapsed_time": "3:11:22", "remaining_time": "1:37:01", "throughput": 11377.86, "total_tokens": 130646016} {"current_steps": 502, "total_steps": 755, "loss": 0.0655, "lr": 1.2620310927981176e-05, "epoch": 3.304383788254756, "percentage": 66.49, "elapsed_time": "3:11:45", "remaining_time": "1:36:38", "throughput": 11377.9, "total_tokens": 130908160} {"current_steps": 503, "total_steps": 755, "loss": 0.065, "lr": 1.2530041805012504e-05, "epoch": 3.311000827129859, "percentage": 66.62, "elapsed_time": "3:12:08", "remaining_time": "1:36:15", "throughput": 11377.92, "total_tokens": 131170304} {"current_steps": 504, "total_steps": 755, "loss": 0.0686, "lr": 1.2439988590778872e-05, "epoch": 3.3176178660049627, "percentage": 66.75, "elapsed_time": "3:12:31", "remaining_time": "1:35:52", "throughput": 11377.95, "total_tokens": 131432448} {"current_steps": 505, "total_steps": 755, "loss": 0.0676, "lr": 1.235015284448969e-05, "epoch": 3.324234904880066, "percentage": 66.89, "elapsed_time": "3:12:54", "remaining_time": "1:35:29", "throughput": 11378.01, "total_tokens": 131694592} {"current_steps": 506, "total_steps": 755, "loss": 0.0658, "lr": 1.2260536121588978e-05, "epoch": 3.3308519437551696, "percentage": 67.02, "elapsed_time": "3:13:17", "remaining_time": "1:35:07", "throughput": 11378.03, "total_tokens": 131956736} {"current_steps": 507, "total_steps": 755, "loss": 0.0644, "lr": 1.2171139973728566e-05, "epoch": 3.337468982630273, "percentage": 67.15, "elapsed_time": "3:13:40", "remaining_time": "1:34:44", "throughput": 11378.08, "total_tokens": 132218880} {"current_steps": 508, "total_steps": 755, "loss": 0.0653, "lr": 1.2081965948741162e-05, "epoch": 3.3440860215053765, "percentage": 67.28, "elapsed_time": "3:14:03", "remaining_time": "1:34:21", "throughput": 11378.13, "total_tokens": 132481024} {"current_steps": 509, "total_steps": 755, "loss": 0.0697, "lr": 1.1993015590613573e-05, "epoch": 3.3507030603804795, "percentage": 67.42, "elapsed_time": "3:14:26", "remaining_time": "1:33:58", "throughput": 11378.19, "total_tokens": 132743168} {"current_steps": 510, "total_steps": 755, "loss": 0.065, "lr": 1.1904290439459973e-05, "epoch": 3.357320099255583, "percentage": 67.55, "elapsed_time": "3:14:49", "remaining_time": "1:33:35", "throughput": 11378.23, "total_tokens": 133005312} {"current_steps": 511, "total_steps": 755, "loss": 0.0646, "lr": 1.1815792031495224e-05, "epoch": 3.3639371381306864, "percentage": 67.68, "elapsed_time": "3:15:12", "remaining_time": "1:33:12", "throughput": 11378.23, "total_tokens": 133267456} {"current_steps": 512, "total_steps": 755, "loss": 0.0645, "lr": 1.172752189900829e-05, "epoch": 3.37055417700579, "percentage": 67.81, "elapsed_time": "3:15:35", "remaining_time": "1:32:49", "throughput": 11378.27, "total_tokens": 133529600} {"current_steps": 513, "total_steps": 755, "loss": 0.0659, "lr": 1.1639481570335692e-05, "epoch": 3.3771712158808933, "percentage": 67.95, "elapsed_time": "3:15:58", "remaining_time": "1:32:26", "throughput": 11378.31, "total_tokens": 133791744} {"current_steps": 514, "total_steps": 755, "loss": 0.0744, "lr": 1.1551672569835095e-05, "epoch": 3.3837882547559968, "percentage": 68.08, "elapsed_time": "3:16:21", "remaining_time": "1:32:04", "throughput": 11378.36, "total_tokens": 134053888} {"current_steps": 515, "total_steps": 755, "loss": 0.0743, "lr": 1.1464096417858822e-05, "epoch": 3.3904052936311, "percentage": 68.21, "elapsed_time": "3:16:44", "remaining_time": "1:31:41", "throughput": 11378.37, "total_tokens": 134316032} {"current_steps": 516, "total_steps": 755, "loss": 0.0667, "lr": 1.1376754630727616e-05, "epoch": 3.3970223325062037, "percentage": 68.34, "elapsed_time": "3:17:07", "remaining_time": "1:31:18", "throughput": 11378.38, "total_tokens": 134578176} {"current_steps": 517, "total_steps": 755, "loss": 0.0674, "lr": 1.1289648720704347e-05, "epoch": 3.4036393713813067, "percentage": 68.48, "elapsed_time": "3:17:30", "remaining_time": "1:30:55", "throughput": 11378.43, "total_tokens": 134840320} {"current_steps": 518, "total_steps": 755, "loss": 0.0629, "lr": 1.1202780195967836e-05, "epoch": 3.41025641025641, "percentage": 68.61, "elapsed_time": "3:17:53", "remaining_time": "1:30:32", "throughput": 11378.44, "total_tokens": 135102464} {"current_steps": 519, "total_steps": 755, "loss": 0.0723, "lr": 1.111615056058674e-05, "epoch": 3.4168734491315136, "percentage": 68.74, "elapsed_time": "3:18:16", "remaining_time": "1:30:09", "throughput": 11378.49, "total_tokens": 135364608} {"current_steps": 520, "total_steps": 755, "loss": 0.0677, "lr": 1.102976131449352e-05, "epoch": 3.423490488006617, "percentage": 68.87, "elapsed_time": "3:18:39", "remaining_time": "1:29:46", "throughput": 11378.52, "total_tokens": 135626752} {"current_steps": 521, "total_steps": 755, "loss": 0.0657, "lr": 1.0943613953458448e-05, "epoch": 3.4301075268817205, "percentage": 69.01, "elapsed_time": "3:19:02", "remaining_time": "1:29:23", "throughput": 11378.57, "total_tokens": 135888896} {"current_steps": 522, "total_steps": 755, "loss": 0.0646, "lr": 1.0857709969063734e-05, "epoch": 3.436724565756824, "percentage": 69.14, "elapsed_time": "3:19:25", "remaining_time": "1:29:00", "throughput": 11378.6, "total_tokens": 136151040} {"current_steps": 523, "total_steps": 755, "loss": 0.068, "lr": 1.0772050848677682e-05, "epoch": 3.4433416046319274, "percentage": 69.27, "elapsed_time": "3:19:48", "remaining_time": "1:28:38", "throughput": 11378.63, "total_tokens": 136413184} {"current_steps": 524, "total_steps": 755, "loss": 0.0642, "lr": 1.0686638075428947e-05, "epoch": 3.4499586435070304, "percentage": 69.4, "elapsed_time": "3:20:11", "remaining_time": "1:28:15", "throughput": 11378.63, "total_tokens": 136675328} {"current_steps": 525, "total_steps": 755, "loss": 0.0685, "lr": 1.0601473128180855e-05, "epoch": 3.456575682382134, "percentage": 69.54, "elapsed_time": "3:20:34", "remaining_time": "1:27:52", "throughput": 11378.66, "total_tokens": 136937472} {"current_steps": 526, "total_steps": 755, "loss": 0.0648, "lr": 1.0516557481505795e-05, "epoch": 3.4631927212572373, "percentage": 69.67, "elapsed_time": "3:20:57", "remaining_time": "1:27:29", "throughput": 11378.65, "total_tokens": 137199616} {"current_steps": 527, "total_steps": 755, "loss": 0.0759, "lr": 1.0431892605659685e-05, "epoch": 3.4698097601323408, "percentage": 69.8, "elapsed_time": "3:21:20", "remaining_time": "1:27:06", "throughput": 11378.63, "total_tokens": 137461760} {"current_steps": 528, "total_steps": 755, "loss": 0.0703, "lr": 1.034747996655652e-05, "epoch": 3.4764267990074442, "percentage": 69.93, "elapsed_time": "3:21:43", "remaining_time": "1:26:43", "throughput": 11378.64, "total_tokens": 137723904} {"current_steps": 529, "total_steps": 755, "loss": 0.0675, "lr": 1.0263321025742991e-05, "epoch": 3.4830438378825477, "percentage": 70.07, "elapsed_time": "3:22:06", "remaining_time": "1:26:20", "throughput": 11378.67, "total_tokens": 137986048} {"current_steps": 530, "total_steps": 755, "loss": 0.0697, "lr": 1.0179417240373183e-05, "epoch": 3.489660876757651, "percentage": 70.2, "elapsed_time": "3:22:29", "remaining_time": "1:25:57", "throughput": 11378.74, "total_tokens": 138248192} {"current_steps": 531, "total_steps": 755, "loss": 0.0654, "lr": 1.009577006318333e-05, "epoch": 3.4962779156327546, "percentage": 70.33, "elapsed_time": "3:22:52", "remaining_time": "1:25:34", "throughput": 11378.77, "total_tokens": 138510336} {"current_steps": 532, "total_steps": 755, "loss": 0.0636, "lr": 1.0012380942466673e-05, "epoch": 3.5028949545078576, "percentage": 70.46, "elapsed_time": "3:23:15", "remaining_time": "1:25:12", "throughput": 11378.79, "total_tokens": 138772480} {"current_steps": 533, "total_steps": 755, "loss": 0.0634, "lr": 9.929251322048397e-06, "epoch": 3.509511993382961, "percentage": 70.6, "elapsed_time": "3:23:38", "remaining_time": "1:24:49", "throughput": 11378.84, "total_tokens": 139034624} {"current_steps": 534, "total_steps": 755, "loss": 0.0656, "lr": 9.8463826412606e-06, "epoch": 3.5161290322580645, "percentage": 70.73, "elapsed_time": "3:24:01", "remaining_time": "1:24:26", "throughput": 11378.86, "total_tokens": 139296768} {"current_steps": 535, "total_steps": 755, "loss": 0.0645, "lr": 9.763776334917399e-06, "epoch": 3.522746071133168, "percentage": 70.86, "elapsed_time": "3:24:24", "remaining_time": "1:24:03", "throughput": 11378.88, "total_tokens": 139558912} {"current_steps": 536, "total_steps": 755, "loss": 0.0634, "lr": 9.681433833290079e-06, "epoch": 3.5293631100082714, "percentage": 70.99, "elapsed_time": "3:24:47", "remaining_time": "1:23:40", "throughput": 11378.89, "total_tokens": 139821056} {"current_steps": 537, "total_steps": 755, "loss": 0.0605, "lr": 9.599356562082329e-06, "epoch": 3.5359801488833744, "percentage": 71.13, "elapsed_time": "3:25:10", "remaining_time": "1:23:17", "throughput": 11378.91, "total_tokens": 140083200} {"current_steps": 538, "total_steps": 755, "loss": 0.0651, "lr": 9.517545942405548e-06, "epoch": 3.542597187758478, "percentage": 71.26, "elapsed_time": "3:25:33", "remaining_time": "1:22:54", "throughput": 11378.93, "total_tokens": 140345344} {"current_steps": 539, "total_steps": 755, "loss": 0.0613, "lr": 9.436003390754258e-06, "epoch": 3.5492142266335813, "percentage": 71.39, "elapsed_time": "3:25:56", "remaining_time": "1:22:31", "throughput": 11378.96, "total_tokens": 140607488} {"current_steps": 540, "total_steps": 755, "loss": 0.0667, "lr": 9.354730318981562e-06, "epoch": 3.555831265508685, "percentage": 71.52, "elapsed_time": "3:26:19", "remaining_time": "1:22:09", "throughput": 11378.96, "total_tokens": 140869632} {"current_steps": 541, "total_steps": 755, "loss": 0.0627, "lr": 9.273728134274701e-06, "epoch": 3.5624483043837882, "percentage": 71.66, "elapsed_time": "3:26:42", "remaining_time": "1:21:46", "throughput": 11378.97, "total_tokens": 141131776} {"current_steps": 542, "total_steps": 755, "loss": 0.0636, "lr": 9.192998239130699e-06, "epoch": 3.5690653432588917, "percentage": 71.79, "elapsed_time": "3:27:05", "remaining_time": "1:21:23", "throughput": 11379.01, "total_tokens": 141393920} {"current_steps": 543, "total_steps": 755, "loss": 0.0623, "lr": 9.112542031332075e-06, "epoch": 3.575682382133995, "percentage": 71.92, "elapsed_time": "3:27:28", "remaining_time": "1:21:00", "throughput": 11379.0, "total_tokens": 141656064} {"current_steps": 544, "total_steps": 755, "loss": 0.0607, "lr": 9.032360903922635e-06, "epoch": 3.5822994210090986, "percentage": 72.05, "elapsed_time": "3:27:51", "remaining_time": "1:20:37", "throughput": 11379.02, "total_tokens": 141918208} {"current_steps": 545, "total_steps": 755, "loss": 0.0638, "lr": 8.95245624518336e-06, "epoch": 3.588916459884202, "percentage": 72.19, "elapsed_time": "3:28:14", "remaining_time": "1:20:14", "throughput": 11379.03, "total_tokens": 142180352} {"current_steps": 546, "total_steps": 755, "loss": 0.0638, "lr": 8.872829438608368e-06, "epoch": 3.595533498759305, "percentage": 72.32, "elapsed_time": "3:28:37", "remaining_time": "1:19:51", "throughput": 11379.07, "total_tokens": 142442496} {"current_steps": 547, "total_steps": 755, "loss": 0.0603, "lr": 8.793481862880953e-06, "epoch": 3.6021505376344085, "percentage": 72.45, "elapsed_time": "3:29:00", "remaining_time": "1:19:28", "throughput": 11379.09, "total_tokens": 142704640} {"current_steps": 548, "total_steps": 755, "loss": 0.0626, "lr": 8.714414891849737e-06, "epoch": 3.608767576509512, "percentage": 72.58, "elapsed_time": "3:29:23", "remaining_time": "1:19:05", "throughput": 11379.11, "total_tokens": 142966784} {"current_steps": 549, "total_steps": 755, "loss": 0.067, "lr": 8.63562989450482e-06, "epoch": 3.6153846153846154, "percentage": 72.72, "elapsed_time": "3:29:47", "remaining_time": "1:18:42", "throughput": 11379.12, "total_tokens": 143228928} {"current_steps": 550, "total_steps": 755, "loss": 0.0635, "lr": 8.55712823495419e-06, "epoch": 3.622001654259719, "percentage": 72.85, "elapsed_time": "3:30:10", "remaining_time": "1:18:20", "throughput": 11379.09, "total_tokens": 143491072} {"current_steps": 551, "total_steps": 755, "loss": 0.0628, "lr": 8.478911272399964e-06, "epoch": 3.6286186931348223, "percentage": 72.98, "elapsed_time": "3:30:33", "remaining_time": "1:17:57", "throughput": 11379.12, "total_tokens": 143753216} {"current_steps": 552, "total_steps": 755, "loss": 0.064, "lr": 8.400980361114985e-06, "epoch": 3.6352357320099253, "percentage": 73.11, "elapsed_time": "3:30:56", "remaining_time": "1:17:34", "throughput": 11379.1, "total_tokens": 144015360} {"current_steps": 553, "total_steps": 755, "loss": 0.0632, "lr": 8.323336850419289e-06, "epoch": 3.641852770885029, "percentage": 73.25, "elapsed_time": "3:31:19", "remaining_time": "1:17:11", "throughput": 11379.12, "total_tokens": 144277504} {"current_steps": 554, "total_steps": 755, "loss": 0.058, "lr": 8.245982084656765e-06, "epoch": 3.6484698097601322, "percentage": 73.38, "elapsed_time": "3:31:42", "remaining_time": "1:16:48", "throughput": 11379.15, "total_tokens": 144539648} {"current_steps": 555, "total_steps": 755, "loss": 0.0603, "lr": 8.168917403171891e-06, "epoch": 3.6550868486352357, "percentage": 73.51, "elapsed_time": "3:32:05", "remaining_time": "1:16:25", "throughput": 11379.14, "total_tokens": 144801792} {"current_steps": 556, "total_steps": 755, "loss": 0.0632, "lr": 8.092144140286539e-06, "epoch": 3.661703887510339, "percentage": 73.64, "elapsed_time": "3:32:28", "remaining_time": "1:16:02", "throughput": 11379.14, "total_tokens": 145063936} {"current_steps": 557, "total_steps": 755, "loss": 0.0597, "lr": 8.015663625276864e-06, "epoch": 3.6683209263854426, "percentage": 73.77, "elapsed_time": "3:32:51", "remaining_time": "1:15:39", "throughput": 11379.17, "total_tokens": 145326080} {"current_steps": 558, "total_steps": 755, "loss": 0.0658, "lr": 7.939477182350277e-06, "epoch": 3.674937965260546, "percentage": 73.91, "elapsed_time": "3:33:14", "remaining_time": "1:15:16", "throughput": 11379.17, "total_tokens": 145588224} {"current_steps": 559, "total_steps": 755, "loss": 0.0632, "lr": 7.863586130622574e-06, "epoch": 3.6815550041356495, "percentage": 74.04, "elapsed_time": "3:33:37", "remaining_time": "1:14:54", "throughput": 11379.16, "total_tokens": 145850368} {"current_steps": 560, "total_steps": 755, "loss": 0.0617, "lr": 7.787991784095e-06, "epoch": 3.688172043010753, "percentage": 74.17, "elapsed_time": "3:34:00", "remaining_time": "1:14:31", "throughput": 11379.17, "total_tokens": 146112512} {"current_steps": 561, "total_steps": 755, "loss": 0.0609, "lr": 7.712695451631621e-06, "epoch": 3.694789081885856, "percentage": 74.3, "elapsed_time": "3:34:23", "remaining_time": "1:14:08", "throughput": 11379.22, "total_tokens": 146374656} {"current_steps": 562, "total_steps": 755, "loss": 0.0603, "lr": 7.637698436936524e-06, "epoch": 3.7014061207609594, "percentage": 74.44, "elapsed_time": "3:34:46", "remaining_time": "1:13:45", "throughput": 11379.24, "total_tokens": 146636800} {"current_steps": 563, "total_steps": 755, "loss": 0.0629, "lr": 7.563002038531383e-06, "epoch": 3.708023159636063, "percentage": 74.57, "elapsed_time": "3:35:09", "remaining_time": "1:13:22", "throughput": 11379.26, "total_tokens": 146898944} {"current_steps": 564, "total_steps": 755, "loss": 0.0637, "lr": 7.488607549732843e-06, "epoch": 3.7146401985111663, "percentage": 74.7, "elapsed_time": "3:35:32", "remaining_time": "1:12:59", "throughput": 11379.31, "total_tokens": 147161088} {"current_steps": 565, "total_steps": 755, "loss": 0.0633, "lr": 7.414516258630244e-06, "epoch": 3.72125723738627, "percentage": 74.83, "elapsed_time": "3:35:55", "remaining_time": "1:12:36", "throughput": 11379.31, "total_tokens": 147423232} {"current_steps": 566, "total_steps": 755, "loss": 0.0657, "lr": 7.340729448063252e-06, "epoch": 3.727874276261373, "percentage": 74.97, "elapsed_time": "3:36:18", "remaining_time": "1:12:13", "throughput": 11379.28, "total_tokens": 147685376} {"current_steps": 567, "total_steps": 755, "loss": 0.0658, "lr": 7.267248395599632e-06, "epoch": 3.7344913151364763, "percentage": 75.1, "elapsed_time": "3:36:41", "remaining_time": "1:11:50", "throughput": 11379.27, "total_tokens": 147947520} {"current_steps": 568, "total_steps": 755, "loss": 0.0552, "lr": 7.1940743735132126e-06, "epoch": 3.7411083540115797, "percentage": 75.23, "elapsed_time": "3:37:04", "remaining_time": "1:11:27", "throughput": 11379.31, "total_tokens": 148209664} {"current_steps": 569, "total_steps": 755, "loss": 0.0644, "lr": 7.121208648761743e-06, "epoch": 3.747725392886683, "percentage": 75.36, "elapsed_time": "3:37:27", "remaining_time": "1:11:05", "throughput": 11379.3, "total_tokens": 148471808} {"current_steps": 570, "total_steps": 755, "loss": 0.0598, "lr": 7.048652482965079e-06, "epoch": 3.7543424317617866, "percentage": 75.5, "elapsed_time": "3:37:50", "remaining_time": "1:10:42", "throughput": 11379.28, "total_tokens": 148733952} {"current_steps": 571, "total_steps": 755, "loss": 0.0603, "lr": 6.9764071323832145e-06, "epoch": 3.76095947063689, "percentage": 75.63, "elapsed_time": "3:38:13", "remaining_time": "1:10:19", "throughput": 11379.3, "total_tokens": 148996096} {"current_steps": 572, "total_steps": 755, "loss": 0.0592, "lr": 6.904473847894652e-06, "epoch": 3.7675765095119935, "percentage": 75.76, "elapsed_time": "3:38:36", "remaining_time": "1:09:56", "throughput": 11379.34, "total_tokens": 149258240} {"current_steps": 573, "total_steps": 755, "loss": 0.0611, "lr": 6.832853874974629e-06, "epoch": 3.774193548387097, "percentage": 75.89, "elapsed_time": "3:38:59", "remaining_time": "1:09:33", "throughput": 11379.36, "total_tokens": 149520384} {"current_steps": 574, "total_steps": 755, "loss": 0.0634, "lr": 6.761548453673647e-06, "epoch": 3.7808105872622004, "percentage": 76.03, "elapsed_time": "3:39:22", "remaining_time": "1:09:10", "throughput": 11379.36, "total_tokens": 149782528} {"current_steps": 575, "total_steps": 755, "loss": 0.0594, "lr": 6.690558818595943e-06, "epoch": 3.7874276261373034, "percentage": 76.16, "elapsed_time": "3:39:45", "remaining_time": "1:08:47", "throughput": 11379.38, "total_tokens": 150044672} {"current_steps": 576, "total_steps": 755, "loss": 0.0649, "lr": 6.619886198878142e-06, "epoch": 3.794044665012407, "percentage": 76.29, "elapsed_time": "3:40:08", "remaining_time": "1:08:24", "throughput": 11379.4, "total_tokens": 150306816} {"current_steps": 577, "total_steps": 755, "loss": 0.0615, "lr": 6.549531818167981e-06, "epoch": 3.8006617038875103, "percentage": 76.42, "elapsed_time": "3:40:31", "remaining_time": "1:08:01", "throughput": 11379.43, "total_tokens": 150568960} {"current_steps": 578, "total_steps": 755, "loss": 0.0527, "lr": 6.479496894603066e-06, "epoch": 3.807278742762614, "percentage": 76.56, "elapsed_time": "3:40:54", "remaining_time": "1:07:38", "throughput": 11379.46, "total_tokens": 150831104} {"current_steps": 579, "total_steps": 755, "loss": 0.0576, "lr": 6.409782640789874e-06, "epoch": 3.8138957816377173, "percentage": 76.69, "elapsed_time": "3:41:17", "remaining_time": "1:07:16", "throughput": 11379.47, "total_tokens": 151093248} {"current_steps": 580, "total_steps": 755, "loss": 0.0659, "lr": 6.340390263782655e-06, "epoch": 3.8205128205128203, "percentage": 76.82, "elapsed_time": "3:41:40", "remaining_time": "1:06:53", "throughput": 11379.5, "total_tokens": 151355392} {"current_steps": 581, "total_steps": 755, "loss": 0.0634, "lr": 6.271320965062638e-06, "epoch": 3.8271298593879237, "percentage": 76.95, "elapsed_time": "3:42:03", "remaining_time": "1:06:30", "throughput": 11379.47, "total_tokens": 151617536} {"current_steps": 582, "total_steps": 755, "loss": 0.0582, "lr": 6.202575940517122e-06, "epoch": 3.833746898263027, "percentage": 77.09, "elapsed_time": "3:42:26", "remaining_time": "1:06:07", "throughput": 11379.48, "total_tokens": 151879680} {"current_steps": 583, "total_steps": 755, "loss": 0.0607, "lr": 6.134156380418857e-06, "epoch": 3.8403639371381306, "percentage": 77.22, "elapsed_time": "3:42:49", "remaining_time": "1:05:44", "throughput": 11379.47, "total_tokens": 152141824} {"current_steps": 584, "total_steps": 755, "loss": 0.0572, "lr": 6.066063469405384e-06, "epoch": 3.846980976013234, "percentage": 77.35, "elapsed_time": "3:43:12", "remaining_time": "1:05:21", "throughput": 11379.48, "total_tokens": 152403968} {"current_steps": 585, "total_steps": 755, "loss": 0.056, "lr": 5.998298386458545e-06, "epoch": 3.8535980148883375, "percentage": 77.48, "elapsed_time": "3:43:35", "remaining_time": "1:04:58", "throughput": 11379.45, "total_tokens": 152666112} {"current_steps": 586, "total_steps": 755, "loss": 0.0608, "lr": 5.9308623048840685e-06, "epoch": 3.860215053763441, "percentage": 77.62, "elapsed_time": "3:43:59", "remaining_time": "1:04:35", "throughput": 11379.43, "total_tokens": 152928256} {"current_steps": 587, "total_steps": 755, "loss": 0.0617, "lr": 5.863756392291248e-06, "epoch": 3.8668320926385444, "percentage": 77.75, "elapsed_time": "3:44:22", "remaining_time": "1:04:12", "throughput": 11379.45, "total_tokens": 153190400} {"current_steps": 588, "total_steps": 755, "loss": 0.0688, "lr": 5.796981810572724e-06, "epoch": 3.873449131513648, "percentage": 77.88, "elapsed_time": "3:44:45", "remaining_time": "1:03:49", "throughput": 11379.47, "total_tokens": 153452544} {"current_steps": 589, "total_steps": 755, "loss": 0.0547, "lr": 5.7305397158843725e-06, "epoch": 3.880066170388751, "percentage": 78.01, "elapsed_time": "3:45:08", "remaining_time": "1:03:27", "throughput": 11379.47, "total_tokens": 153714688} {"current_steps": 590, "total_steps": 755, "loss": 0.0629, "lr": 5.664431258625305e-06, "epoch": 3.8866832092638544, "percentage": 78.15, "elapsed_time": "3:45:31", "remaining_time": "1:03:04", "throughput": 11379.49, "total_tokens": 153976832} {"current_steps": 591, "total_steps": 755, "loss": 0.0543, "lr": 5.598657583417896e-06, "epoch": 3.893300248138958, "percentage": 78.28, "elapsed_time": "3:45:54", "remaining_time": "1:02:41", "throughput": 11379.52, "total_tokens": 154238976} {"current_steps": 592, "total_steps": 755, "loss": 0.0595, "lr": 5.533219829088021e-06, "epoch": 3.8999172870140613, "percentage": 78.41, "elapsed_time": "3:46:17", "remaining_time": "1:02:18", "throughput": 11379.54, "total_tokens": 154501120} {"current_steps": 593, "total_steps": 755, "loss": 0.058, "lr": 5.468119128645319e-06, "epoch": 3.9065343258891647, "percentage": 78.54, "elapsed_time": "3:46:40", "remaining_time": "1:01:55", "throughput": 11379.55, "total_tokens": 154763264} {"current_steps": 594, "total_steps": 755, "loss": 0.0579, "lr": 5.403356609263563e-06, "epoch": 3.9131513647642677, "percentage": 78.68, "elapsed_time": "3:47:03", "remaining_time": "1:01:32", "throughput": 11379.56, "total_tokens": 155025408} {"current_steps": 595, "total_steps": 755, "loss": 0.0603, "lr": 5.338933392261159e-06, "epoch": 3.919768403639371, "percentage": 78.81, "elapsed_time": "3:47:26", "remaining_time": "1:01:09", "throughput": 11379.56, "total_tokens": 155287552} {"current_steps": 596, "total_steps": 755, "loss": 0.057, "lr": 5.274850593081726e-06, "epoch": 3.9263854425144746, "percentage": 78.94, "elapsed_time": "3:47:49", "remaining_time": "1:00:46", "throughput": 11379.57, "total_tokens": 155549696} {"current_steps": 597, "total_steps": 755, "loss": 0.0531, "lr": 5.2111093212747845e-06, "epoch": 3.933002481389578, "percentage": 79.07, "elapsed_time": "3:48:12", "remaining_time": "1:00:23", "throughput": 11379.58, "total_tokens": 155811840} {"current_steps": 598, "total_steps": 755, "loss": 0.0642, "lr": 5.147710680476536e-06, "epoch": 3.9396195202646815, "percentage": 79.21, "elapsed_time": "3:48:35", "remaining_time": "1:00:00", "throughput": 11379.57, "total_tokens": 156073984} {"current_steps": 599, "total_steps": 755, "loss": 0.0605, "lr": 5.0846557683907755e-06, "epoch": 3.946236559139785, "percentage": 79.34, "elapsed_time": "3:48:58", "remaining_time": "0:59:37", "throughput": 11379.56, "total_tokens": 156336128} {"current_steps": 600, "total_steps": 755, "loss": 0.0594, "lr": 5.02194567676986e-06, "epoch": 3.9528535980148884, "percentage": 79.47, "elapsed_time": "3:49:21", "remaining_time": "0:59:15", "throughput": 11379.57, "total_tokens": 156598272} {"current_steps": 601, "total_steps": 755, "loss": 0.0575, "lr": 4.959581491395823e-06, "epoch": 3.959470636889992, "percentage": 79.6, "elapsed_time": "3:49:44", "remaining_time": "0:58:52", "throughput": 11379.6, "total_tokens": 156860416} {"current_steps": 602, "total_steps": 755, "loss": 0.0554, "lr": 4.897564292061568e-06, "epoch": 3.9660876757650954, "percentage": 79.74, "elapsed_time": "3:50:07", "remaining_time": "0:58:29", "throughput": 11379.58, "total_tokens": 157122560} {"current_steps": 603, "total_steps": 755, "loss": 0.0646, "lr": 4.835895152552178e-06, "epoch": 3.9727047146401984, "percentage": 79.87, "elapsed_time": "3:50:30", "remaining_time": "0:58:06", "throughput": 11379.6, "total_tokens": 157384704} {"current_steps": 604, "total_steps": 755, "loss": 0.0545, "lr": 4.7745751406263165e-06, "epoch": 3.979321753515302, "percentage": 80.0, "elapsed_time": "3:50:53", "remaining_time": "0:57:43", "throughput": 11379.6, "total_tokens": 157646848} {"current_steps": 605, "total_steps": 755, "loss": 0.058, "lr": 4.713605317997741e-06, "epoch": 3.9859387923904053, "percentage": 80.13, "elapsed_time": "3:51:16", "remaining_time": "0:57:20", "throughput": 11379.61, "total_tokens": 157908992} {"current_steps": 606, "total_steps": 755, "loss": 0.0602, "lr": 4.652986740316928e-06, "epoch": 3.9925558312655087, "percentage": 80.26, "elapsed_time": "3:51:39", "remaining_time": "0:56:57", "throughput": 11379.61, "total_tokens": 158171136} {"current_steps": 607, "total_steps": 755, "loss": 0.0609, "lr": 4.592720457152788e-06, "epoch": 3.999172870140612, "percentage": 80.4, "elapsed_time": "3:52:02", "remaining_time": "0:56:34", "throughput": 11379.64, "total_tokens": 158433280} {"current_steps": 608, "total_steps": 755, "loss": 0.0496, "lr": 4.532807511974491e-06, "epoch": 4.0, "percentage": 80.53, "elapsed_time": "3:52:05", "remaining_time": "0:56:06", "throughput": 11379.69, "total_tokens": 158466048} {"current_steps": 609, "total_steps": 755, "loss": 0.0156, "lr": 4.47324894213341e-06, "epoch": 4.0066170388751035, "percentage": 80.66, "elapsed_time": "3:52:28", "remaining_time": "0:55:43", "throughput": 11379.65, "total_tokens": 158728192} {"current_steps": 610, "total_steps": 755, "loss": 0.0178, "lr": 4.414045778845144e-06, "epoch": 4.013234077750207, "percentage": 80.79, "elapsed_time": "3:52:51", "remaining_time": "0:55:21", "throughput": 11379.64, "total_tokens": 158990336} {"current_steps": 611, "total_steps": 755, "loss": 0.0149, "lr": 4.355199047171685e-06, "epoch": 4.01985111662531, "percentage": 80.93, "elapsed_time": "3:53:14", "remaining_time": "0:54:58", "throughput": 11379.63, "total_tokens": 159252480} {"current_steps": 612, "total_steps": 755, "loss": 0.0167, "lr": 4.2967097660036456e-06, "epoch": 4.026468155500414, "percentage": 81.06, "elapsed_time": "3:53:37", "remaining_time": "0:54:35", "throughput": 11379.67, "total_tokens": 159514624} {"current_steps": 613, "total_steps": 755, "loss": 0.0145, "lr": 4.238578948042632e-06, "epoch": 4.033085194375517, "percentage": 81.19, "elapsed_time": "3:54:00", "remaining_time": "0:54:12", "throughput": 11379.68, "total_tokens": 159776768} {"current_steps": 614, "total_steps": 755, "loss": 0.0146, "lr": 4.180807599783712e-06, "epoch": 4.039702233250621, "percentage": 81.32, "elapsed_time": "3:54:23", "remaining_time": "0:53:49", "throughput": 11379.69, "total_tokens": 160038912} {"current_steps": 615, "total_steps": 755, "loss": 0.0128, "lr": 4.123396721497977e-06, "epoch": 4.046319272125724, "percentage": 81.46, "elapsed_time": "3:54:46", "remaining_time": "0:53:26", "throughput": 11379.69, "total_tokens": 160301056} {"current_steps": 616, "total_steps": 755, "loss": 0.014, "lr": 4.066347307215235e-06, "epoch": 4.052936311000827, "percentage": 81.59, "elapsed_time": "3:55:09", "remaining_time": "0:53:03", "throughput": 11379.45, "total_tokens": 160563200} {"current_steps": 617, "total_steps": 755, "loss": 0.0128, "lr": 4.009660344706786e-06, "epoch": 4.05955334987593, "percentage": 81.72, "elapsed_time": "3:55:32", "remaining_time": "0:52:41", "throughput": 11379.48, "total_tokens": 160825344} {"current_steps": 618, "total_steps": 755, "loss": 0.0117, "lr": 3.9533368154683365e-06, "epoch": 4.066170388751034, "percentage": 81.85, "elapsed_time": "3:55:55", "remaining_time": "0:52:18", "throughput": 11379.48, "total_tokens": 161087488} {"current_steps": 619, "total_steps": 755, "loss": 0.0117, "lr": 3.8973776947029864e-06, "epoch": 4.072787427626137, "percentage": 81.99, "elapsed_time": "3:56:18", "remaining_time": "0:51:55", "throughput": 11379.52, "total_tokens": 161349632} {"current_steps": 620, "total_steps": 755, "loss": 0.0113, "lr": 3.8417839513043645e-06, "epoch": 4.079404466501241, "percentage": 82.12, "elapsed_time": "3:56:41", "remaining_time": "0:51:32", "throughput": 11379.53, "total_tokens": 161611776} {"current_steps": 621, "total_steps": 755, "loss": 0.0124, "lr": 3.7865565478398314e-06, "epoch": 4.086021505376344, "percentage": 82.25, "elapsed_time": "3:57:05", "remaining_time": "0:51:09", "throughput": 11379.52, "total_tokens": 161873920} {"current_steps": 622, "total_steps": 755, "loss": 0.0114, "lr": 3.7316964405338357e-06, "epoch": 4.0926385442514475, "percentage": 82.38, "elapsed_time": "3:57:28", "remaining_time": "0:50:46", "throughput": 11379.51, "total_tokens": 162136064} {"current_steps": 623, "total_steps": 755, "loss": 0.0107, "lr": 3.6772045792513336e-06, "epoch": 4.099255583126551, "percentage": 82.52, "elapsed_time": "3:57:51", "remaining_time": "0:50:23", "throughput": 11379.52, "total_tokens": 162398208} {"current_steps": 624, "total_steps": 755, "loss": 0.0099, "lr": 3.6230819074813737e-06, "epoch": 4.105872622001654, "percentage": 82.65, "elapsed_time": "3:58:14", "remaining_time": "0:50:00", "throughput": 11379.51, "total_tokens": 162660352} {"current_steps": 625, "total_steps": 755, "loss": 0.0113, "lr": 3.5693293623207086e-06, "epoch": 4.112489660876758, "percentage": 82.78, "elapsed_time": "3:58:37", "remaining_time": "0:49:37", "throughput": 11379.51, "total_tokens": 162922496} {"current_steps": 626, "total_steps": 755, "loss": 0.0122, "lr": 3.515947874457648e-06, "epoch": 4.119106699751861, "percentage": 82.91, "elapsed_time": "3:59:00", "remaining_time": "0:49:15", "throughput": 11379.51, "total_tokens": 163184640} {"current_steps": 627, "total_steps": 755, "loss": 0.0116, "lr": 3.4629383681558576e-06, "epoch": 4.125723738626965, "percentage": 83.05, "elapsed_time": "3:59:23", "remaining_time": "0:48:52", "throughput": 11379.52, "total_tokens": 163446784} {"current_steps": 628, "total_steps": 755, "loss": 0.0115, "lr": 3.4103017612384323e-06, "epoch": 4.132340777502068, "percentage": 83.18, "elapsed_time": "3:59:46", "remaining_time": "0:48:29", "throughput": 11379.52, "total_tokens": 163708928} {"current_steps": 629, "total_steps": 755, "loss": 0.0123, "lr": 3.358038965071955e-06, "epoch": 4.138957816377172, "percentage": 83.31, "elapsed_time": "4:00:09", "remaining_time": "0:48:06", "throughput": 11379.53, "total_tokens": 163971072} {"current_steps": 630, "total_steps": 755, "loss": 0.012, "lr": 3.3061508845507323e-06, "epoch": 4.145574855252274, "percentage": 83.44, "elapsed_time": "4:00:32", "remaining_time": "0:47:43", "throughput": 11379.56, "total_tokens": 164233216} {"current_steps": 631, "total_steps": 755, "loss": 0.0109, "lr": 3.254638418081132e-06, "epoch": 4.152191894127378, "percentage": 83.58, "elapsed_time": "4:00:55", "remaining_time": "0:47:20", "throughput": 11379.55, "total_tokens": 164495360} {"current_steps": 632, "total_steps": 755, "loss": 0.0117, "lr": 3.2035024575660237e-06, "epoch": 4.158808933002481, "percentage": 83.71, "elapsed_time": "4:01:18", "remaining_time": "0:46:57", "throughput": 11379.56, "total_tokens": 164757504} {"current_steps": 633, "total_steps": 755, "loss": 0.011, "lr": 3.152743888389334e-06, "epoch": 4.165425971877585, "percentage": 83.84, "elapsed_time": "4:01:41", "remaining_time": "0:46:34", "throughput": 11379.56, "total_tokens": 165019648} {"current_steps": 634, "total_steps": 755, "loss": 0.0119, "lr": 3.1023635894007085e-06, "epoch": 4.172043010752688, "percentage": 83.97, "elapsed_time": "4:02:04", "remaining_time": "0:46:12", "throughput": 11379.57, "total_tokens": 165281792} {"current_steps": 635, "total_steps": 755, "loss": 0.012, "lr": 3.0523624329003324e-06, "epoch": 4.1786600496277915, "percentage": 84.11, "elapsed_time": "4:02:27", "remaining_time": "0:45:49", "throughput": 11379.56, "total_tokens": 165543936} {"current_steps": 636, "total_steps": 755, "loss": 0.0111, "lr": 3.002741284623764e-06, "epoch": 4.185277088502895, "percentage": 84.24, "elapsed_time": "4:02:50", "remaining_time": "0:45:26", "throughput": 11379.53, "total_tokens": 165806080} {"current_steps": 637, "total_steps": 755, "loss": 0.0118, "lr": 2.953501003727019e-06, "epoch": 4.191894127377998, "percentage": 84.37, "elapsed_time": "4:03:13", "remaining_time": "0:45:03", "throughput": 11379.53, "total_tokens": 166068224} {"current_steps": 638, "total_steps": 755, "loss": 0.0106, "lr": 2.904642442771616e-06, "epoch": 4.198511166253102, "percentage": 84.5, "elapsed_time": "4:03:36", "remaining_time": "0:44:40", "throughput": 11379.54, "total_tokens": 166330368} {"current_steps": 639, "total_steps": 755, "loss": 0.0108, "lr": 2.8561664477098985e-06, "epoch": 4.205128205128205, "percentage": 84.64, "elapsed_time": "4:03:59", "remaining_time": "0:44:17", "throughput": 11379.56, "total_tokens": 166592512} {"current_steps": 640, "total_steps": 755, "loss": 0.0108, "lr": 2.8080738578703054e-06, "epoch": 4.211745244003309, "percentage": 84.77, "elapsed_time": "4:04:22", "remaining_time": "0:43:54", "throughput": 11379.4, "total_tokens": 166854656} {"current_steps": 641, "total_steps": 755, "loss": 0.0113, "lr": 2.7603655059429077e-06, "epoch": 4.218362282878412, "percentage": 84.9, "elapsed_time": "4:04:46", "remaining_time": "0:43:31", "throughput": 11379.23, "total_tokens": 167116800} {"current_steps": 642, "total_steps": 755, "loss": 0.0108, "lr": 2.7130422179649563e-06, "epoch": 4.224979321753516, "percentage": 85.03, "elapsed_time": "4:05:09", "remaining_time": "0:43:08", "throughput": 11379.23, "total_tokens": 167378944} {"current_steps": 643, "total_steps": 755, "loss": 0.0096, "lr": 2.666104813306558e-06, "epoch": 4.231596360628619, "percentage": 85.17, "elapsed_time": "4:05:32", "remaining_time": "0:42:46", "throughput": 11378.99, "total_tokens": 167641088} {"current_steps": 644, "total_steps": 755, "loss": 0.0115, "lr": 2.619554104656563e-06, "epoch": 4.238213399503722, "percentage": 85.3, "elapsed_time": "4:05:55", "remaining_time": "0:42:23", "throughput": 11379.0, "total_tokens": 167903232} {"current_steps": 645, "total_steps": 755, "loss": 0.0098, "lr": 2.5733908980083988e-06, "epoch": 4.244830438378825, "percentage": 85.43, "elapsed_time": "4:06:18", "remaining_time": "0:42:00", "throughput": 11378.98, "total_tokens": 168165376} {"current_steps": 646, "total_steps": 755, "loss": 0.0105, "lr": 2.527615992646201e-06, "epoch": 4.251447477253929, "percentage": 85.56, "elapsed_time": "4:06:41", "remaining_time": "0:41:37", "throughput": 11379.01, "total_tokens": 168427520} {"current_steps": 647, "total_steps": 755, "loss": 0.0119, "lr": 2.4822301811309066e-06, "epoch": 4.258064516129032, "percentage": 85.7, "elapsed_time": "4:07:04", "remaining_time": "0:41:14", "throughput": 11379.0, "total_tokens": 168689664} {"current_steps": 648, "total_steps": 755, "loss": 0.0108, "lr": 2.437234249286588e-06, "epoch": 4.2646815550041355, "percentage": 85.83, "elapsed_time": "4:07:27", "remaining_time": "0:40:51", "throughput": 11379.0, "total_tokens": 168951808} {"current_steps": 649, "total_steps": 755, "loss": 0.0104, "lr": 2.3926289761867892e-06, "epoch": 4.271298593879239, "percentage": 85.96, "elapsed_time": "4:07:50", "remaining_time": "0:40:28", "throughput": 11379.04, "total_tokens": 169213952} {"current_steps": 650, "total_steps": 755, "loss": 0.0101, "lr": 2.348415134141102e-06, "epoch": 4.277915632754342, "percentage": 86.09, "elapsed_time": "4:08:13", "remaining_time": "0:40:05", "throughput": 11379.04, "total_tokens": 169476096} {"current_steps": 651, "total_steps": 755, "loss": 0.0114, "lr": 2.304593488681725e-06, "epoch": 4.284532671629446, "percentage": 86.23, "elapsed_time": "4:08:36", "remaining_time": "0:39:43", "throughput": 11379.03, "total_tokens": 169738240} {"current_steps": 652, "total_steps": 755, "loss": 0.0098, "lr": 2.2611647985502636e-06, "epoch": 4.291149710504549, "percentage": 86.36, "elapsed_time": "4:08:59", "remaining_time": "0:39:20", "throughput": 11379.05, "total_tokens": 170000384} {"current_steps": 653, "total_steps": 755, "loss": 0.0103, "lr": 2.218129815684572e-06, "epoch": 4.297766749379653, "percentage": 86.49, "elapsed_time": "4:09:22", "remaining_time": "0:38:57", "throughput": 11379.02, "total_tokens": 170262528} {"current_steps": 654, "total_steps": 755, "loss": 0.0111, "lr": 2.1754892852057174e-06, "epoch": 4.304383788254756, "percentage": 86.62, "elapsed_time": "4:09:45", "remaining_time": "0:38:34", "throughput": 11379.02, "total_tokens": 170524672} {"current_steps": 655, "total_steps": 755, "loss": 0.0116, "lr": 2.133243945405128e-06, "epoch": 4.31100082712986, "percentage": 86.75, "elapsed_time": "4:10:08", "remaining_time": "0:38:11", "throughput": 11379.02, "total_tokens": 170786816} {"current_steps": 656, "total_steps": 755, "loss": 0.0101, "lr": 2.0913945277317384e-06, "epoch": 4.317617866004963, "percentage": 86.89, "elapsed_time": "4:10:31", "remaining_time": "0:37:48", "throughput": 11379.01, "total_tokens": 171048960} {"current_steps": 657, "total_steps": 755, "loss": 0.0117, "lr": 2.0499417567794e-06, "epoch": 4.324234904880067, "percentage": 87.02, "elapsed_time": "4:10:54", "remaining_time": "0:37:25", "throughput": 11379.03, "total_tokens": 171311104} {"current_steps": 658, "total_steps": 755, "loss": 0.0098, "lr": 2.0088863502742665e-06, "epoch": 4.330851943755169, "percentage": 87.15, "elapsed_time": "4:11:18", "remaining_time": "0:37:02", "throughput": 11379.03, "total_tokens": 171573248} {"current_steps": 659, "total_steps": 755, "loss": 0.011, "lr": 1.968229019062437e-06, "epoch": 4.337468982630273, "percentage": 87.28, "elapsed_time": "4:11:41", "remaining_time": "0:36:39", "throughput": 11379.02, "total_tokens": 171835392} {"current_steps": 660, "total_steps": 755, "loss": 0.0106, "lr": 1.927970467097573e-06, "epoch": 4.344086021505376, "percentage": 87.42, "elapsed_time": "4:12:04", "remaining_time": "0:36:16", "throughput": 11379.03, "total_tokens": 172097536} {"current_steps": 661, "total_steps": 755, "loss": 0.0109, "lr": 1.8881113914287735e-06, "epoch": 4.3507030603804795, "percentage": 87.55, "elapsed_time": "4:12:27", "remaining_time": "0:35:54", "throughput": 11379.05, "total_tokens": 172359680} {"current_steps": 662, "total_steps": 755, "loss": 0.0085, "lr": 1.8486524821884705e-06, "epoch": 4.357320099255583, "percentage": 87.68, "elapsed_time": "4:12:50", "remaining_time": "0:35:31", "throughput": 11379.08, "total_tokens": 172621824} {"current_steps": 663, "total_steps": 755, "loss": 0.0105, "lr": 1.8095944225804961e-06, "epoch": 4.363937138130686, "percentage": 87.81, "elapsed_time": "4:13:13", "remaining_time": "0:35:08", "throughput": 11379.08, "total_tokens": 172883968} {"current_steps": 664, "total_steps": 755, "loss": 0.01, "lr": 1.7709378888682404e-06, "epoch": 4.37055417700579, "percentage": 87.95, "elapsed_time": "4:13:36", "remaining_time": "0:34:45", "throughput": 11379.11, "total_tokens": 173146112} {"current_steps": 665, "total_steps": 755, "loss": 0.0091, "lr": 1.732683550362954e-06, "epoch": 4.377171215880893, "percentage": 88.08, "elapsed_time": "4:13:59", "remaining_time": "0:34:22", "throughput": 11379.08, "total_tokens": 173408256} {"current_steps": 666, "total_steps": 755, "loss": 0.0103, "lr": 1.6948320694121527e-06, "epoch": 4.383788254755997, "percentage": 88.21, "elapsed_time": "4:14:22", "remaining_time": "0:33:59", "throughput": 11379.1, "total_tokens": 173670400} {"current_steps": 667, "total_steps": 755, "loss": 0.0089, "lr": 1.6573841013881486e-06, "epoch": 4.3904052936311, "percentage": 88.34, "elapsed_time": "4:14:45", "remaining_time": "0:33:36", "throughput": 11379.11, "total_tokens": 173932544} {"current_steps": 668, "total_steps": 755, "loss": 0.0098, "lr": 1.6203402946767198e-06, "epoch": 4.397022332506204, "percentage": 88.48, "elapsed_time": "4:15:08", "remaining_time": "0:33:13", "throughput": 11379.11, "total_tokens": 174194688} {"current_steps": 669, "total_steps": 755, "loss": 0.0109, "lr": 1.5837012906658484e-06, "epoch": 4.403639371381307, "percentage": 88.61, "elapsed_time": "4:15:31", "remaining_time": "0:32:50", "throughput": 11379.1, "total_tokens": 174456832} {"current_steps": 670, "total_steps": 755, "loss": 0.0107, "lr": 1.5474677237346468e-06, "epoch": 4.410256410256411, "percentage": 88.74, "elapsed_time": "4:15:54", "remaining_time": "0:32:27", "throughput": 11379.08, "total_tokens": 174718976} {"current_steps": 671, "total_steps": 755, "loss": 0.0113, "lr": 1.5116402212423664e-06, "epoch": 4.416873449131514, "percentage": 88.87, "elapsed_time": "4:16:17", "remaining_time": "0:32:05", "throughput": 11379.08, "total_tokens": 174981120} {"current_steps": 672, "total_steps": 755, "loss": 0.0089, "lr": 1.4762194035175286e-06, "epoch": 4.4234904880066175, "percentage": 89.01, "elapsed_time": "4:16:40", "remaining_time": "0:31:42", "throughput": 11379.11, "total_tokens": 175243264} {"current_steps": 673, "total_steps": 755, "loss": 0.0104, "lr": 1.4412058838471908e-06, "epoch": 4.43010752688172, "percentage": 89.14, "elapsed_time": "4:17:03", "remaining_time": "0:31:19", "throughput": 11379.13, "total_tokens": 175505408} {"current_steps": 674, "total_steps": 755, "loss": 0.011, "lr": 1.406600268466321e-06, "epoch": 4.4367245657568235, "percentage": 89.27, "elapsed_time": "4:17:26", "remaining_time": "0:30:56", "throughput": 11379.12, "total_tokens": 175767552} {"current_steps": 675, "total_steps": 755, "loss": 0.01, "lr": 1.3724031565473112e-06, "epoch": 4.443341604631927, "percentage": 89.4, "elapsed_time": "4:17:49", "remaining_time": "0:30:33", "throughput": 11379.14, "total_tokens": 176029696} {"current_steps": 676, "total_steps": 755, "loss": 0.0122, "lr": 1.3386151401895919e-06, "epoch": 4.44995864350703, "percentage": 89.54, "elapsed_time": "4:18:12", "remaining_time": "0:30:10", "throughput": 11379.17, "total_tokens": 176291840} {"current_steps": 677, "total_steps": 755, "loss": 0.0114, "lr": 1.3052368044093904e-06, "epoch": 4.456575682382134, "percentage": 89.67, "elapsed_time": "4:18:35", "remaining_time": "0:29:47", "throughput": 11379.21, "total_tokens": 176553984} {"current_steps": 678, "total_steps": 755, "loss": 0.0101, "lr": 1.272268727129597e-06, "epoch": 4.463192721257237, "percentage": 89.8, "elapsed_time": "4:18:58", "remaining_time": "0:29:24", "throughput": 11379.24, "total_tokens": 176816128} {"current_steps": 679, "total_steps": 755, "loss": 0.01, "lr": 1.23971147916975e-06, "epoch": 4.469809760132341, "percentage": 89.93, "elapsed_time": "4:19:21", "remaining_time": "0:29:01", "throughput": 11379.24, "total_tokens": 177078272} {"current_steps": 680, "total_steps": 755, "loss": 0.0109, "lr": 1.2075656242361732e-06, "epoch": 4.476426799007444, "percentage": 90.07, "elapsed_time": "4:19:44", "remaining_time": "0:28:38", "throughput": 11379.24, "total_tokens": 177340416} {"current_steps": 681, "total_steps": 755, "loss": 0.0097, "lr": 1.1758317189121987e-06, "epoch": 4.483043837882548, "percentage": 90.2, "elapsed_time": "4:20:07", "remaining_time": "0:28:15", "throughput": 11379.27, "total_tokens": 177602560} {"current_steps": 682, "total_steps": 755, "loss": 0.0095, "lr": 1.144510312648528e-06, "epoch": 4.489660876757651, "percentage": 90.33, "elapsed_time": "4:20:30", "remaining_time": "0:27:53", "throughput": 11379.28, "total_tokens": 177864704} {"current_steps": 683, "total_steps": 755, "loss": 0.0103, "lr": 1.1136019477537397e-06, "epoch": 4.496277915632755, "percentage": 90.46, "elapsed_time": "4:20:53", "remaining_time": "0:27:30", "throughput": 11379.29, "total_tokens": 178126848} {"current_steps": 684, "total_steps": 755, "loss": 0.0096, "lr": 1.0831071593848747e-06, "epoch": 4.502894954507858, "percentage": 90.6, "elapsed_time": "4:21:16", "remaining_time": "0:27:07", "throughput": 11379.33, "total_tokens": 178388992} {"current_steps": 685, "total_steps": 755, "loss": 0.0121, "lr": 1.0530264755381824e-06, "epoch": 4.5095119933829615, "percentage": 90.73, "elapsed_time": "4:21:39", "remaining_time": "0:26:44", "throughput": 11379.33, "total_tokens": 178651136} {"current_steps": 686, "total_steps": 755, "loss": 0.0098, "lr": 1.0233604170399813e-06, "epoch": 4.516129032258064, "percentage": 90.86, "elapsed_time": "4:22:02", "remaining_time": "0:26:21", "throughput": 11379.36, "total_tokens": 178913280} {"current_steps": 687, "total_steps": 755, "loss": 0.0116, "lr": 9.941094975376374e-07, "epoch": 4.522746071133168, "percentage": 90.99, "elapsed_time": "4:22:25", "remaining_time": "0:25:58", "throughput": 11379.36, "total_tokens": 179175424} {"current_steps": 688, "total_steps": 755, "loss": 0.0101, "lr": 9.652742234906698e-07, "epoch": 4.529363110008271, "percentage": 91.13, "elapsed_time": "4:22:48", "remaining_time": "0:25:35", "throughput": 11379.34, "total_tokens": 179437568} {"current_steps": 689, "total_steps": 755, "loss": 0.0106, "lr": 9.368550941619786e-07, "epoch": 4.535980148883374, "percentage": 91.26, "elapsed_time": "4:23:11", "remaining_time": "0:25:12", "throughput": 11379.34, "total_tokens": 179699712} {"current_steps": 690, "total_steps": 755, "loss": 0.01, "lr": 9.088526016092142e-07, "epoch": 4.542597187758478, "percentage": 91.39, "elapsed_time": "4:23:34", "remaining_time": "0:24:49", "throughput": 11379.35, "total_tokens": 179961856} {"current_steps": 691, "total_steps": 755, "loss": 0.0099, "lr": 8.812672306762415e-07, "epoch": 4.549214226633581, "percentage": 91.52, "elapsed_time": "4:23:57", "remaining_time": "0:24:26", "throughput": 11379.35, "total_tokens": 180224000} {"current_steps": 692, "total_steps": 755, "loss": 0.0092, "lr": 8.540994589847501e-07, "epoch": 4.555831265508685, "percentage": 91.66, "elapsed_time": "4:24:20", "remaining_time": "0:24:03", "throughput": 11379.34, "total_tokens": 180486144} {"current_steps": 693, "total_steps": 755, "loss": 0.0103, "lr": 8.273497569259935e-07, "epoch": 4.562448304383788, "percentage": 91.79, "elapsed_time": "4:24:43", "remaining_time": "0:23:41", "throughput": 11379.36, "total_tokens": 180748288} {"current_steps": 694, "total_steps": 755, "loss": 0.0108, "lr": 8.010185876526328e-07, "epoch": 4.569065343258892, "percentage": 91.92, "elapsed_time": "4:25:06", "remaining_time": "0:23:18", "throughput": 11379.39, "total_tokens": 181010432} {"current_steps": 695, "total_steps": 755, "loss": 0.0109, "lr": 7.751064070707248e-07, "epoch": 4.575682382133995, "percentage": 92.05, "elapsed_time": "4:25:29", "remaining_time": "0:22:55", "throughput": 11379.4, "total_tokens": 181272576} {"current_steps": 696, "total_steps": 755, "loss": 0.0104, "lr": 7.496136638318218e-07, "epoch": 4.582299421009099, "percentage": 92.19, "elapsed_time": "4:25:52", "remaining_time": "0:22:32", "throughput": 11379.4, "total_tokens": 181534720} {"current_steps": 697, "total_steps": 755, "loss": 0.0101, "lr": 7.245407993252101e-07, "epoch": 4.588916459884202, "percentage": 92.32, "elapsed_time": "4:26:15", "remaining_time": "0:22:09", "throughput": 11379.42, "total_tokens": 181796864} {"current_steps": 698, "total_steps": 755, "loss": 0.0107, "lr": 6.998882476702662e-07, "epoch": 4.5955334987593055, "percentage": 92.45, "elapsed_time": "4:26:38", "remaining_time": "0:21:46", "throughput": 11379.47, "total_tokens": 182059008} {"current_steps": 699, "total_steps": 755, "loss": 0.0101, "lr": 6.756564357089379e-07, "epoch": 4.602150537634409, "percentage": 92.58, "elapsed_time": "4:27:01", "remaining_time": "0:21:23", "throughput": 11379.5, "total_tokens": 182321152} {"current_steps": 700, "total_steps": 755, "loss": 0.0095, "lr": 6.51845782998356e-07, "epoch": 4.608767576509512, "percentage": 92.72, "elapsed_time": "4:27:24", "remaining_time": "0:21:00", "throughput": 11379.5, "total_tokens": 182583296} {"current_steps": 701, "total_steps": 755, "loss": 0.0108, "lr": 6.28456701803562e-07, "epoch": 4.615384615384615, "percentage": 92.85, "elapsed_time": "4:27:47", "remaining_time": "0:20:37", "throughput": 11379.54, "total_tokens": 182845440} {"current_steps": 702, "total_steps": 755, "loss": 0.0115, "lr": 6.054895970903945e-07, "epoch": 4.622001654259718, "percentage": 92.98, "elapsed_time": "4:28:10", "remaining_time": "0:20:14", "throughput": 11379.57, "total_tokens": 183107584} {"current_steps": 703, "total_steps": 755, "loss": 0.0091, "lr": 5.829448665184339e-07, "epoch": 4.628618693134822, "percentage": 93.11, "elapsed_time": "4:28:33", "remaining_time": "0:19:51", "throughput": 11379.59, "total_tokens": 183369728} {"current_steps": 704, "total_steps": 755, "loss": 0.0094, "lr": 5.608229004341686e-07, "epoch": 4.635235732009925, "percentage": 93.25, "elapsed_time": "4:28:56", "remaining_time": "0:19:29", "throughput": 11379.61, "total_tokens": 183631872} {"current_steps": 705, "total_steps": 755, "loss": 0.0113, "lr": 5.391240818642007e-07, "epoch": 4.641852770885029, "percentage": 93.38, "elapsed_time": "4:29:19", "remaining_time": "0:19:06", "throughput": 11379.61, "total_tokens": 183894016} {"current_steps": 706, "total_steps": 755, "loss": 0.0109, "lr": 5.178487865086179e-07, "epoch": 4.648469809760132, "percentage": 93.51, "elapsed_time": "4:29:42", "remaining_time": "0:18:43", "throughput": 11379.62, "total_tokens": 184156160} {"current_steps": 707, "total_steps": 755, "loss": 0.0107, "lr": 4.96997382734507e-07, "epoch": 4.655086848635236, "percentage": 93.64, "elapsed_time": "4:30:06", "remaining_time": "0:18:20", "throughput": 11379.61, "total_tokens": 184418304} {"current_steps": 708, "total_steps": 755, "loss": 0.0098, "lr": 4.7657023156955636e-07, "epoch": 4.661703887510339, "percentage": 93.77, "elapsed_time": "4:30:29", "remaining_time": "0:17:57", "throughput": 11379.61, "total_tokens": 184680448} {"current_steps": 709, "total_steps": 755, "loss": 0.0092, "lr": 4.5656768669582183e-07, "epoch": 4.668320926385443, "percentage": 93.91, "elapsed_time": "4:30:52", "remaining_time": "0:17:34", "throughput": 11379.63, "total_tokens": 184942592} {"current_steps": 710, "total_steps": 755, "loss": 0.0103, "lr": 4.3699009444357344e-07, "epoch": 4.674937965260546, "percentage": 94.04, "elapsed_time": "4:31:15", "remaining_time": "0:17:11", "throughput": 11379.65, "total_tokens": 185204736} {"current_steps": 711, "total_steps": 755, "loss": 0.0113, "lr": 4.1783779378534727e-07, "epoch": 4.6815550041356495, "percentage": 94.17, "elapsed_time": "4:31:38", "remaining_time": "0:16:48", "throughput": 11379.66, "total_tokens": 185466880} {"current_steps": 712, "total_steps": 755, "loss": 0.0108, "lr": 3.9911111633002543e-07, "epoch": 4.688172043010753, "percentage": 94.3, "elapsed_time": "4:32:01", "remaining_time": "0:16:25", "throughput": 11379.68, "total_tokens": 185729024} {"current_steps": 713, "total_steps": 755, "loss": 0.009, "lr": 3.8081038631713195e-07, "epoch": 4.694789081885856, "percentage": 94.44, "elapsed_time": "4:32:24", "remaining_time": "0:16:02", "throughput": 11379.69, "total_tokens": 185991168} {"current_steps": 714, "total_steps": 755, "loss": 0.0103, "lr": 3.6293592061119596e-07, "epoch": 4.701406120760959, "percentage": 94.57, "elapsed_time": "4:32:47", "remaining_time": "0:15:39", "throughput": 11379.71, "total_tokens": 186253312} {"current_steps": 715, "total_steps": 755, "loss": 0.0108, "lr": 3.454880286962781e-07, "epoch": 4.708023159636063, "percentage": 94.7, "elapsed_time": "4:33:10", "remaining_time": "0:15:16", "throughput": 11379.72, "total_tokens": 186515456} {"current_steps": 716, "total_steps": 755, "loss": 0.0121, "lr": 3.2846701267060243e-07, "epoch": 4.714640198511166, "percentage": 94.83, "elapsed_time": "4:33:33", "remaining_time": "0:14:54", "throughput": 11379.69, "total_tokens": 186777600} {"current_steps": 717, "total_steps": 755, "loss": 0.0091, "lr": 3.1187316724133885e-07, "epoch": 4.721257237386269, "percentage": 94.97, "elapsed_time": "4:33:56", "remaining_time": "0:14:31", "throughput": 11379.72, "total_tokens": 187039744} {"current_steps": 718, "total_steps": 755, "loss": 0.0109, "lr": 2.957067797194929e-07, "epoch": 4.727874276261373, "percentage": 95.1, "elapsed_time": "4:34:19", "remaining_time": "0:14:08", "throughput": 11379.73, "total_tokens": 187301888} {"current_steps": 719, "total_steps": 755, "loss": 0.011, "lr": 2.799681300149154e-07, "epoch": 4.734491315136476, "percentage": 95.23, "elapsed_time": "4:34:42", "remaining_time": "0:13:45", "throughput": 11379.75, "total_tokens": 187564032} {"current_steps": 720, "total_steps": 755, "loss": 0.01, "lr": 2.646574906314925e-07, "epoch": 4.74110835401158, "percentage": 95.36, "elapsed_time": "4:35:05", "remaining_time": "0:13:22", "throughput": 11379.77, "total_tokens": 187826176} {"current_steps": 721, "total_steps": 755, "loss": 0.0096, "lr": 2.497751266623938e-07, "epoch": 4.747725392886683, "percentage": 95.5, "elapsed_time": "4:35:28", "remaining_time": "0:12:59", "throughput": 11379.79, "total_tokens": 188088320} {"current_steps": 722, "total_steps": 755, "loss": 0.0116, "lr": 2.3532129578549834e-07, "epoch": 4.754342431761787, "percentage": 95.63, "elapsed_time": "4:35:51", "remaining_time": "0:12:36", "throughput": 11379.81, "total_tokens": 188350464} {"current_steps": 723, "total_steps": 755, "loss": 0.0091, "lr": 2.212962482589287e-07, "epoch": 4.76095947063689, "percentage": 95.76, "elapsed_time": "4:36:14", "remaining_time": "0:12:13", "throughput": 11379.81, "total_tokens": 188612608} {"current_steps": 724, "total_steps": 755, "loss": 0.0105, "lr": 2.0770022691672387e-07, "epoch": 4.7675765095119935, "percentage": 95.89, "elapsed_time": "4:36:37", "remaining_time": "0:11:50", "throughput": 11379.8, "total_tokens": 188874752} {"current_steps": 725, "total_steps": 755, "loss": 0.0101, "lr": 1.9453346716462317e-07, "epoch": 4.774193548387097, "percentage": 96.03, "elapsed_time": "4:37:00", "remaining_time": "0:11:27", "throughput": 11379.81, "total_tokens": 189136896} {"current_steps": 726, "total_steps": 755, "loss": 0.011, "lr": 1.8179619697600292e-07, "epoch": 4.7808105872622, "percentage": 96.16, "elapsed_time": "4:37:23", "remaining_time": "0:11:04", "throughput": 11379.8, "total_tokens": 189399040} {"current_steps": 727, "total_steps": 755, "loss": 0.0093, "lr": 1.6948863688791837e-07, "epoch": 4.787427626137304, "percentage": 96.29, "elapsed_time": "4:37:46", "remaining_time": "0:10:41", "throughput": 11379.81, "total_tokens": 189661184} {"current_steps": 728, "total_steps": 755, "loss": 0.0096, "lr": 1.576109999972958e-07, "epoch": 4.794044665012407, "percentage": 96.42, "elapsed_time": "4:38:09", "remaining_time": "0:10:18", "throughput": 11379.8, "total_tokens": 189923328} {"current_steps": 729, "total_steps": 755, "loss": 0.0106, "lr": 1.4616349195723245e-07, "epoch": 4.80066170388751, "percentage": 96.56, "elapsed_time": "4:38:32", "remaining_time": "0:09:56", "throughput": 11379.8, "total_tokens": 190185472} {"current_steps": 730, "total_steps": 755, "loss": 0.0105, "lr": 1.351463109734441e-07, "epoch": 4.807278742762613, "percentage": 96.69, "elapsed_time": "4:38:55", "remaining_time": "0:09:33", "throughput": 11379.8, "total_tokens": 190447616} {"current_steps": 731, "total_steps": 755, "loss": 0.0095, "lr": 1.2455964780083152e-07, "epoch": 4.813895781637717, "percentage": 96.82, "elapsed_time": "4:39:18", "remaining_time": "0:09:10", "throughput": 11379.77, "total_tokens": 190709760} {"current_steps": 732, "total_steps": 755, "loss": 0.009, "lr": 1.1440368574017202e-07, "epoch": 4.82051282051282, "percentage": 96.95, "elapsed_time": "4:39:41", "remaining_time": "0:08:47", "throughput": 11379.75, "total_tokens": 190971904} {"current_steps": 733, "total_steps": 755, "loss": 0.0109, "lr": 1.0467860063495538e-07, "epoch": 4.827129859387924, "percentage": 97.09, "elapsed_time": "4:40:04", "remaining_time": "0:08:24", "throughput": 11379.74, "total_tokens": 191234048} {"current_steps": 734, "total_steps": 755, "loss": 0.0094, "lr": 9.538456086832237e-08, "epoch": 4.833746898263027, "percentage": 97.22, "elapsed_time": "4:40:27", "remaining_time": "0:08:01", "throughput": 11379.75, "total_tokens": 191496192} {"current_steps": 735, "total_steps": 755, "loss": 0.0115, "lr": 8.652172736017816e-08, "epoch": 4.840363937138131, "percentage": 97.35, "elapsed_time": "4:40:50", "remaining_time": "0:07:38", "throughput": 11379.75, "total_tokens": 191758336} {"current_steps": 736, "total_steps": 755, "loss": 0.011, "lr": 7.809025356436961e-08, "epoch": 4.846980976013234, "percentage": 97.48, "elapsed_time": "4:41:13", "remaining_time": "0:07:15", "throughput": 11379.76, "total_tokens": 192020480} {"current_steps": 737, "total_steps": 755, "loss": 0.0105, "lr": 7.009028546606233e-08, "epoch": 4.8535980148883375, "percentage": 97.62, "elapsed_time": "4:41:36", "remaining_time": "0:06:52", "throughput": 11379.78, "total_tokens": 192282624} {"current_steps": 738, "total_steps": 755, "loss": 0.011, "lr": 6.252196157919276e-08, "epoch": 4.860215053763441, "percentage": 97.75, "elapsed_time": "4:41:59", "remaining_time": "0:06:29", "throughput": 11379.8, "total_tokens": 192544768} {"current_steps": 739, "total_steps": 755, "loss": 0.0113, "lr": 5.538541294407285e-08, "epoch": 4.866832092638544, "percentage": 97.88, "elapsed_time": "4:42:22", "remaining_time": "0:06:06", "throughput": 11379.79, "total_tokens": 192806912} {"current_steps": 740, "total_steps": 755, "loss": 0.0106, "lr": 4.868076312512515e-08, "epoch": 4.873449131513648, "percentage": 98.01, "elapsed_time": "4:42:45", "remaining_time": "0:05:43", "throughput": 11379.81, "total_tokens": 193069056} {"current_steps": 741, "total_steps": 755, "loss": 0.0091, "lr": 4.240812820874296e-08, "epoch": 4.880066170388751, "percentage": 98.15, "elapsed_time": "4:43:08", "remaining_time": "0:05:20", "throughput": 11379.81, "total_tokens": 193331200} {"current_steps": 742, "total_steps": 755, "loss": 0.011, "lr": 3.656761680127796e-08, "epoch": 4.886683209263855, "percentage": 98.28, "elapsed_time": "4:43:32", "remaining_time": "0:04:58", "throughput": 11379.8, "total_tokens": 193593344} {"current_steps": 743, "total_steps": 755, "loss": 0.0103, "lr": 3.1159330027161204e-08, "epoch": 4.893300248138958, "percentage": 98.41, "elapsed_time": "4:43:55", "remaining_time": "0:04:35", "throughput": 11379.82, "total_tokens": 193855488} {"current_steps": 744, "total_steps": 755, "loss": 0.0097, "lr": 2.618336152715728e-08, "epoch": 4.899917287014061, "percentage": 98.54, "elapsed_time": "4:44:18", "remaining_time": "0:04:12", "throughput": 11379.84, "total_tokens": 194117632} {"current_steps": 745, "total_steps": 755, "loss": 0.0097, "lr": 2.1639797456723952e-08, "epoch": 4.906534325889164, "percentage": 98.68, "elapsed_time": "4:44:41", "remaining_time": "0:03:49", "throughput": 11379.86, "total_tokens": 194379776} {"current_steps": 746, "total_steps": 755, "loss": 0.01, "lr": 1.752871648454668e-08, "epoch": 4.913151364764268, "percentage": 98.81, "elapsed_time": "4:45:04", "remaining_time": "0:03:26", "throughput": 11379.85, "total_tokens": 194641920} {"current_steps": 747, "total_steps": 755, "loss": 0.0097, "lr": 1.3850189791161927e-08, "epoch": 4.919768403639371, "percentage": 98.94, "elapsed_time": "4:45:27", "remaining_time": "0:03:03", "throughput": 11379.87, "total_tokens": 194904064} {"current_steps": 748, "total_steps": 755, "loss": 0.0108, "lr": 1.0604281067724819e-08, "epoch": 4.926385442514475, "percentage": 99.07, "elapsed_time": "4:45:50", "remaining_time": "0:02:40", "throughput": 11379.88, "total_tokens": 195166208} {"current_steps": 749, "total_steps": 755, "loss": 0.0096, "lr": 7.791046514907252e-09, "epoch": 4.933002481389578, "percentage": 99.21, "elapsed_time": "4:46:13", "remaining_time": "0:02:17", "throughput": 11379.92, "total_tokens": 195428352} {"current_steps": 750, "total_steps": 755, "loss": 0.011, "lr": 5.41053484192644e-09, "epoch": 4.9396195202646815, "percentage": 99.34, "elapsed_time": "4:46:36", "remaining_time": "0:01:54", "throughput": 11379.92, "total_tokens": 195690496} {"current_steps": 751, "total_steps": 755, "loss": 0.0098, "lr": 3.462787265703926e-09, "epoch": 4.946236559139785, "percentage": 99.47, "elapsed_time": "4:46:59", "remaining_time": "0:01:31", "throughput": 11379.94, "total_tokens": 195952640} {"current_steps": 752, "total_steps": 755, "loss": 0.0089, "lr": 1.9478375101467104e-09, "epoch": 4.9528535980148884, "percentage": 99.6, "elapsed_time": "4:47:22", "remaining_time": "0:01:08", "throughput": 11379.94, "total_tokens": 196214784} {"current_steps": 753, "total_steps": 755, "loss": 0.0087, "lr": 8.657118055643843e-10, "epoch": 4.959470636889992, "percentage": 99.74, "elapsed_time": "4:47:45", "remaining_time": "0:00:45", "throughput": 11379.95, "total_tokens": 196476928} {"current_steps": 754, "total_steps": 755, "loss": 0.0114, "lr": 2.164288882194887e-10, "epoch": 4.966087675765095, "percentage": 99.87, "elapsed_time": "4:48:08", "remaining_time": "0:00:22", "throughput": 11379.98, "total_tokens": 196739072} {"current_steps": 755, "total_steps": 755, "loss": 0.0101, "lr": 0.0, "epoch": 4.972704714640199, "percentage": 100.0, "elapsed_time": "4:48:31", "remaining_time": "0:00:00", "throughput": 11379.98, "total_tokens": 197001216}