|
{"current_steps": 1, "total_steps": 110, "loss": 0.8968, "lr": 4.9989804820704735e-05, "epoch": 0.009019165727170236, "percentage": 0.91, "elapsed_time": "0:02:44", "remaining_time": "4:58:29", "throughput": 12763.83, "total_tokens": 2097152} |
|
{"current_steps": 2, "total_steps": 110, "loss": 0.8202, "lr": 4.995922759815339e-05, "epoch": 0.018038331454340473, "percentage": 1.82, "elapsed_time": "0:05:20", "remaining_time": "4:48:20", "throughput": 13091.94, "total_tokens": 4194304} |
|
{"current_steps": 3, "total_steps": 110, "loss": 0.7783, "lr": 4.9908293271567286e-05, "epoch": 0.02705749718151071, "percentage": 2.73, "elapsed_time": "0:07:55", "remaining_time": "4:42:50", "throughput": 13222.77, "total_tokens": 6291456} |
|
{"current_steps": 4, "total_steps": 110, "loss": 0.7642, "lr": 4.9837043383713753e-05, "epoch": 0.036076662908680945, "percentage": 3.64, "elapsed_time": "0:10:31", "remaining_time": "4:38:50", "throughput": 13287.21, "total_tokens": 8388608} |
|
{"current_steps": 5, "total_steps": 110, "loss": 0.7475, "lr": 4.9745536047023324e-05, "epoch": 0.04509582863585118, "percentage": 4.55, "elapsed_time": "0:13:06", "remaining_time": "4:35:18", "throughput": 13330.27, "total_tokens": 10485760} |
|
{"current_steps": 6, "total_steps": 110, "loss": 0.7319, "lr": 4.963384589619233e-05, "epoch": 0.05411499436302142, "percentage": 5.45, "elapsed_time": "0:15:41", "remaining_time": "4:31:54", "throughput": 13369.02, "total_tokens": 12582912} |
|
{"current_steps": 7, "total_steps": 110, "loss": 0.7125, "lr": 4.9502064027309836e-05, "epoch": 0.06313416009019165, "percentage": 6.36, "elapsed_time": "0:18:15", "remaining_time": "4:28:42", "throughput": 13397.69, "total_tokens": 14680064} |
|
{"current_steps": 8, "total_steps": 110, "loss": 0.7117, "lr": 4.935029792355834e-05, "epoch": 0.07215332581736189, "percentage": 7.27, "elapsed_time": "0:20:50", "remaining_time": "4:25:42", "throughput": 13417.34, "total_tokens": 16777216} |
|
{"current_steps": 9, "total_steps": 110, "loss": 0.724, "lr": 4.917867136754893e-05, "epoch": 0.08117249154453213, "percentage": 8.18, "elapsed_time": "0:23:25", "remaining_time": "4:22:52", "throughput": 13429.19, "total_tokens": 18874368} |
|
{"current_steps": 10, "total_steps": 110, "loss": 0.7144, "lr": 4.898732434036244e-05, "epoch": 0.09019165727170236, "percentage": 9.09, "elapsed_time": "0:26:00", "remaining_time": "4:20:02", "throughput": 13440.96, "total_tokens": 20971520} |
|
{"current_steps": 11, "total_steps": 110, "loss": 0.697, "lr": 4.877641290737884e-05, "epoch": 0.0992108229988726, "percentage": 10.0, "elapsed_time": "0:28:35", "remaining_time": "4:17:18", "throughput": 13448.05, "total_tokens": 23068672} |
|
{"current_steps": 12, "total_steps": 110, "loss": 0.7117, "lr": 4.854610909098812e-05, "epoch": 0.10822998872604284, "percentage": 10.91, "elapsed_time": "0:31:10", "remaining_time": "4:14:37", "throughput": 13452.88, "total_tokens": 25165824} |
|
{"current_steps": 13, "total_steps": 110, "loss": 0.6996, "lr": 4.829660073028631e-05, "epoch": 0.11724915445321307, "percentage": 11.82, "elapsed_time": "0:33:45", "remaining_time": "4:11:55", "throughput": 13458.1, "total_tokens": 27262976} |
|
{"current_steps": 14, "total_steps": 110, "loss": 0.7172, "lr": 4.802809132787125e-05, "epoch": 0.1262683201803833, "percentage": 12.73, "elapsed_time": "0:36:20", "remaining_time": "4:09:15", "throughput": 13461.87, "total_tokens": 29360128} |
|
{"current_steps": 15, "total_steps": 110, "loss": 0.725, "lr": 4.774079988386296e-05, "epoch": 0.13528748590755355, "percentage": 13.64, "elapsed_time": "0:38:56", "remaining_time": "4:06:35", "throughput": 13465.5, "total_tokens": 31457280} |
|
{"current_steps": 16, "total_steps": 110, "loss": 0.7073, "lr": 4.743496071728396e-05, "epoch": 0.14430665163472378, "percentage": 14.55, "elapsed_time": "0:41:31", "remaining_time": "4:03:55", "throughput": 13469.44, "total_tokens": 33554432} |
|
{"current_steps": 17, "total_steps": 110, "loss": 0.7021, "lr": 4.711082327494536e-05, "epoch": 0.15332581736189402, "percentage": 15.45, "elapsed_time": "0:44:06", "remaining_time": "4:01:15", "throughput": 13473.17, "total_tokens": 35651584} |
|
{"current_steps": 18, "total_steps": 110, "loss": 0.6894, "lr": 4.6768651927994434e-05, "epoch": 0.16234498308906425, "percentage": 16.36, "elapsed_time": "0:46:41", "remaining_time": "3:58:39", "throughput": 13473.99, "total_tokens": 37748736} |
|
{"current_steps": 19, "total_steps": 110, "loss": 0.7031, "lr": 4.640872575628973e-05, "epoch": 0.1713641488162345, "percentage": 17.27, "elapsed_time": "0:49:17", "remaining_time": "3:56:06", "throughput": 13471.1, "total_tokens": 39845888} |
|
{"current_steps": 20, "total_steps": 110, "loss": 0.6629, "lr": 4.6031338320779534e-05, "epoch": 0.18038331454340473, "percentage": 18.18, "elapsed_time": "0:51:52", "remaining_time": "3:53:27", "throughput": 13474.21, "total_tokens": 41943040} |
|
{"current_steps": 21, "total_steps": 110, "loss": 0.6774, "lr": 4.563679742406935e-05, "epoch": 0.18940248027057496, "percentage": 19.09, "elapsed_time": "0:54:27", "remaining_time": "3:50:49", "throughput": 13476.95, "total_tokens": 44040192} |
|
{"current_steps": 22, "total_steps": 110, "loss": 0.7041, "lr": 4.522542485937369e-05, "epoch": 0.1984216459977452, "percentage": 20.0, "elapsed_time": "0:57:02", "remaining_time": "3:48:09", "throughput": 13481.25, "total_tokens": 46137344} |
|
{"current_steps": 23, "total_steps": 110, "loss": 0.6894, "lr": 4.479755614805688e-05, "epoch": 0.20744081172491544, "percentage": 20.91, "elapsed_time": "0:59:37", "remaining_time": "3:45:30", "throughput": 13484.61, "total_tokens": 48234496} |
|
{"current_steps": 24, "total_steps": 110, "loss": 0.673, "lr": 4.4353540265977064e-05, "epoch": 0.21645997745208567, "percentage": 21.82, "elapsed_time": "1:02:11", "remaining_time": "3:42:51", "throughput": 13488.41, "total_tokens": 50331648} |
|
{"current_steps": 25, "total_steps": 110, "loss": 0.6691, "lr": 4.389373935885646e-05, "epoch": 0.2254791431792559, "percentage": 22.73, "elapsed_time": "1:04:46", "remaining_time": "3:40:13", "throughput": 13490.63, "total_tokens": 52428800} |
|
{"current_steps": 26, "total_steps": 110, "loss": 0.6794, "lr": 4.341852844691012e-05, "epoch": 0.23449830890642615, "percentage": 23.64, "elapsed_time": "1:07:20", "remaining_time": "3:37:34", "throughput": 13493.84, "total_tokens": 54525952} |
|
{"current_steps": 27, "total_steps": 110, "loss": 0.6946, "lr": 4.292829511897409e-05, "epoch": 0.24351747463359638, "percentage": 24.55, "elapsed_time": "1:09:56", "remaining_time": "3:34:59", "throughput": 13493.72, "total_tokens": 56623104} |
|
{"current_steps": 28, "total_steps": 110, "loss": 0.6939, "lr": 4.242343921638234e-05, "epoch": 0.2525366403607666, "percentage": 25.45, "elapsed_time": "1:12:31", "remaining_time": "3:32:22", "throughput": 13495.64, "total_tokens": 58720256} |
|
{"current_steps": 29, "total_steps": 110, "loss": 0.6759, "lr": 4.1904372506850484e-05, "epoch": 0.2615558060879369, "percentage": 26.36, "elapsed_time": "1:15:05", "remaining_time": "3:29:44", "throughput": 13497.79, "total_tokens": 60817408} |
|
{"current_steps": 30, "total_steps": 110, "loss": 0.6856, "lr": 4.137151834863213e-05, "epoch": 0.2705749718151071, "percentage": 27.27, "elapsed_time": "1:17:45", "remaining_time": "3:27:20", "throughput": 13485.48, "total_tokens": 62914560} |
|
{"current_steps": 31, "total_steps": 110, "loss": 0.6753, "lr": 4.082531134522176e-05, "epoch": 0.27959413754227735, "percentage": 28.18, "elapsed_time": "1:20:23", "remaining_time": "3:24:53", "throughput": 13476.76, "total_tokens": 65011712} |
|
{"current_steps": 32, "total_steps": 110, "loss": 0.6769, "lr": 4.0266196990885955e-05, "epoch": 0.28861330326944756, "percentage": 29.09, "elapsed_time": "1:23:02", "remaining_time": "3:22:25", "throughput": 13467.64, "total_tokens": 67108864} |
|
{"current_steps": 33, "total_steps": 110, "loss": 0.6664, "lr": 3.969463130731183e-05, "epoch": 0.2976324689966178, "percentage": 30.0, "elapsed_time": "1:25:41", "remaining_time": "3:19:56", "throughput": 13460.91, "total_tokens": 69206016} |
|
{"current_steps": 34, "total_steps": 110, "loss": 0.6383, "lr": 3.911108047166924e-05, "epoch": 0.30665163472378804, "percentage": 30.91, "elapsed_time": "1:28:18", "remaining_time": "3:17:24", "throughput": 13456.16, "total_tokens": 71303168} |
|
{"current_steps": 35, "total_steps": 110, "loss": 0.6726, "lr": 3.851602043638994e-05, "epoch": 0.3156708004509583, "percentage": 31.82, "elapsed_time": "1:30:57", "remaining_time": "3:14:54", "throughput": 13449.18, "total_tokens": 73400320} |
|
{"current_steps": 36, "total_steps": 110, "loss": 0.6612, "lr": 3.790993654097405e-05, "epoch": 0.3246899661781285, "percentage": 32.73, "elapsed_time": "1:33:35", "remaining_time": "3:12:23", "throughput": 13443.43, "total_tokens": 75497472} |
|
{"current_steps": 37, "total_steps": 110, "loss": 0.6763, "lr": 3.72933231161401e-05, "epoch": 0.3337091319052988, "percentage": 33.64, "elapsed_time": "1:36:14", "remaining_time": "3:09:52", "throughput": 13438.4, "total_tokens": 77594624} |
|
{"current_steps": 38, "total_steps": 110, "loss": 0.6533, "lr": 3.6666683080641846e-05, "epoch": 0.342728297632469, "percentage": 34.55, "elapsed_time": "1:38:52", "remaining_time": "3:07:20", "throughput": 13433.21, "total_tokens": 79691776} |
|
{"current_steps": 39, "total_steps": 110, "loss": 0.6598, "lr": 3.603052753108053e-05, "epoch": 0.35174746335963925, "percentage": 35.45, "elapsed_time": "1:41:30", "remaining_time": "3:04:47", "throughput": 13429.21, "total_tokens": 81788928} |
|
{"current_steps": 40, "total_steps": 110, "loss": 0.6801, "lr": 3.5385375325047166e-05, "epoch": 0.36076662908680945, "percentage": 36.36, "elapsed_time": "1:44:08", "remaining_time": "3:02:15", "throughput": 13424.38, "total_tokens": 83886080} |
|
{"current_steps": 41, "total_steps": 110, "loss": 0.6668, "lr": 3.4731752657934794e-05, "epoch": 0.3697857948139797, "percentage": 37.27, "elapsed_time": "1:46:47", "remaining_time": "2:59:42", "throughput": 13420.03, "total_tokens": 85983232} |
|
{"current_steps": 42, "total_steps": 110, "loss": 0.6756, "lr": 3.4070192633766025e-05, "epoch": 0.3788049605411499, "percentage": 38.18, "elapsed_time": "1:49:25", "remaining_time": "2:57:10", "throughput": 13414.75, "total_tokens": 88080384} |
|
{"current_steps": 43, "total_steps": 110, "loss": 0.6589, "lr": 3.3401234830385756e-05, "epoch": 0.3878241262683202, "percentage": 39.09, "elapsed_time": "1:52:03", "remaining_time": "2:54:36", "throughput": 13411.37, "total_tokens": 90177536} |
|
{"current_steps": 44, "total_steps": 110, "loss": 0.6435, "lr": 3.272542485937369e-05, "epoch": 0.3968432919954904, "percentage": 40.0, "elapsed_time": "1:54:41", "remaining_time": "2:52:02", "throughput": 13408.63, "total_tokens": 92274688} |
|
{"current_steps": 45, "total_steps": 110, "loss": 0.6602, "lr": 3.2043313921035743e-05, "epoch": 0.40586245772266066, "percentage": 40.91, "elapsed_time": "1:57:19", "remaining_time": "2:49:28", "throughput": 13405.22, "total_tokens": 94371840} |
|
{"current_steps": 46, "total_steps": 110, "loss": 0.648, "lr": 3.135545835483718e-05, "epoch": 0.41488162344983087, "percentage": 41.82, "elapsed_time": "1:59:58", "remaining_time": "2:46:54", "throughput": 13401.83, "total_tokens": 96468992} |
|
{"current_steps": 47, "total_steps": 110, "loss": 0.6493, "lr": 3.0662419185644115e-05, "epoch": 0.42390078917700114, "percentage": 42.73, "elapsed_time": "2:02:36", "remaining_time": "2:44:20", "throughput": 13398.84, "total_tokens": 98566144} |
|
{"current_steps": 48, "total_steps": 110, "loss": 0.6701, "lr": 2.996476166614364e-05, "epoch": 0.43291995490417134, "percentage": 43.64, "elapsed_time": "2:05:14", "remaining_time": "2:41:46", "throughput": 13395.76, "total_tokens": 100663296} |
|
{"current_steps": 49, "total_steps": 110, "loss": 0.6674, "lr": 2.92630548158156e-05, "epoch": 0.4419391206313416, "percentage": 44.55, "elapsed_time": "2:07:52", "remaining_time": "2:39:12", "throughput": 13392.56, "total_tokens": 102760448} |
|
{"current_steps": 50, "total_steps": 110, "loss": 0.6635, "lr": 2.8557870956832132e-05, "epoch": 0.4509582863585118, "percentage": 45.45, "elapsed_time": "2:10:31", "remaining_time": "2:36:37", "throughput": 13389.71, "total_tokens": 104857600} |
|
{"current_steps": 51, "total_steps": 110, "loss": 0.6598, "lr": 2.7849785247263515e-05, "epoch": 0.4599774520856821, "percentage": 46.36, "elapsed_time": "2:13:09", "remaining_time": "2:34:02", "throughput": 13386.6, "total_tokens": 106954752} |
|
{"current_steps": 52, "total_steps": 110, "loss": 0.6732, "lr": 2.7139375211970996e-05, "epoch": 0.4689966178128523, "percentage": 47.27, "elapsed_time": "2:15:48", "remaining_time": "2:31:28", "throughput": 13383.73, "total_tokens": 109051904} |
|
{"current_steps": 53, "total_steps": 110, "loss": 0.6546, "lr": 2.6427220271569203e-05, "epoch": 0.47801578354002255, "percentage": 48.18, "elapsed_time": "2:18:26", "remaining_time": "2:28:53", "throughput": 13380.78, "total_tokens": 111149056} |
|
{"current_steps": 54, "total_steps": 110, "loss": 0.6705, "lr": 2.5713901269842404e-05, "epoch": 0.48703494926719276, "percentage": 49.09, "elapsed_time": "2:21:04", "remaining_time": "2:26:17", "throughput": 13379.1, "total_tokens": 113246208} |
|
{"current_steps": 55, "total_steps": 110, "loss": 0.6463, "lr": 2.5e-05, "epoch": 0.496054114994363, "percentage": 50.0, "elapsed_time": "2:23:42", "remaining_time": "2:23:42", "throughput": 13376.64, "total_tokens": 115343360} |
|
{"current_steps": 56, "total_steps": 110, "loss": 0.6505, "lr": 2.42860987301576e-05, "epoch": 0.5050732807215332, "percentage": 50.91, "elapsed_time": "2:26:20", "remaining_time": "2:21:06", "throughput": 13375.59, "total_tokens": 117440512} |
|
{"current_steps": 57, "total_steps": 110, "loss": 0.6524, "lr": 2.35727797284308e-05, "epoch": 0.5140924464487034, "percentage": 51.82, "elapsed_time": "2:28:58", "remaining_time": "2:18:30", "throughput": 13373.95, "total_tokens": 119537664} |
|
{"current_steps": 58, "total_steps": 110, "loss": 0.6559, "lr": 2.2860624788029013e-05, "epoch": 0.5231116121758738, "percentage": 52.73, "elapsed_time": "2:31:36", "remaining_time": "2:15:55", "throughput": 13371.57, "total_tokens": 121634816} |
|
{"current_steps": 59, "total_steps": 110, "loss": 0.6511, "lr": 2.2150214752736488e-05, "epoch": 0.532130777903044, "percentage": 53.64, "elapsed_time": "2:34:15", "remaining_time": "2:13:20", "throughput": 13368.89, "total_tokens": 123731968} |
|
{"current_steps": 60, "total_steps": 110, "loss": 0.6457, "lr": 2.1442129043167874e-05, "epoch": 0.5411499436302142, "percentage": 54.55, "elapsed_time": "2:36:53", "remaining_time": "2:10:44", "throughput": 13366.3, "total_tokens": 125829120} |
|
{"current_steps": 61, "total_steps": 110, "loss": 0.6492, "lr": 2.0736945184184405e-05, "epoch": 0.5501691093573844, "percentage": 55.45, "elapsed_time": "2:39:32", "remaining_time": "2:08:09", "throughput": 13364.48, "total_tokens": 127926272} |
|
{"current_steps": 62, "total_steps": 110, "loss": 0.6539, "lr": 2.003523833385637e-05, "epoch": 0.5591882750845547, "percentage": 56.36, "elapsed_time": "2:42:09", "remaining_time": "2:05:32", "throughput": 13363.3, "total_tokens": 130023424} |
|
{"current_steps": 63, "total_steps": 110, "loss": 0.6417, "lr": 1.9337580814355888e-05, "epoch": 0.5682074408117249, "percentage": 57.27, "elapsed_time": "2:44:47", "remaining_time": "2:02:56", "throughput": 13362.41, "total_tokens": 132120576} |
|
{"current_steps": 64, "total_steps": 110, "loss": 0.6663, "lr": 1.8644541645162834e-05, "epoch": 0.5772266065388951, "percentage": 58.18, "elapsed_time": "2:47:25", "remaining_time": "2:00:20", "throughput": 13360.92, "total_tokens": 134217728} |
|
{"current_steps": 65, "total_steps": 110, "loss": 0.6572, "lr": 1.795668607896426e-05, "epoch": 0.5862457722660653, "percentage": 59.09, "elapsed_time": "2:50:03", "remaining_time": "1:57:43", "throughput": 13360.07, "total_tokens": 136314880} |
|
{"current_steps": 66, "total_steps": 110, "loss": 0.6825, "lr": 1.7274575140626318e-05, "epoch": 0.5952649379932357, "percentage": 60.0, "elapsed_time": "2:52:41", "remaining_time": "1:55:07", "throughput": 13358.01, "total_tokens": 138412032} |
|
{"current_steps": 67, "total_steps": 110, "loss": 0.6509, "lr": 1.6598765169614243e-05, "epoch": 0.6042841037204059, "percentage": 60.91, "elapsed_time": "2:55:19", "remaining_time": "1:52:31", "throughput": 13356.51, "total_tokens": 140509184} |
|
{"current_steps": 68, "total_steps": 110, "loss": 0.6619, "lr": 1.5929807366233977e-05, "epoch": 0.6133032694475761, "percentage": 61.82, "elapsed_time": "2:57:57", "remaining_time": "1:49:55", "throughput": 13355.52, "total_tokens": 142606336} |
|
{"current_steps": 69, "total_steps": 110, "loss": 0.6759, "lr": 1.5268247342065215e-05, "epoch": 0.6223224351747464, "percentage": 62.73, "elapsed_time": "3:00:36", "remaining_time": "1:47:19", "throughput": 13352.79, "total_tokens": 144703488} |
|
{"current_steps": 70, "total_steps": 110, "loss": 0.6568, "lr": 1.4614624674952842e-05, "epoch": 0.6313416009019166, "percentage": 63.64, "elapsed_time": "3:03:14", "remaining_time": "1:44:42", "throughput": 13352.37, "total_tokens": 146800640} |
|
{"current_steps": 71, "total_steps": 110, "loss": 0.6472, "lr": 1.3969472468919461e-05, "epoch": 0.6403607666290868, "percentage": 64.55, "elapsed_time": "3:05:52", "remaining_time": "1:42:05", "throughput": 13351.5, "total_tokens": 148897792} |
|
{"current_steps": 72, "total_steps": 110, "loss": 0.6473, "lr": 1.3333316919358157e-05, "epoch": 0.649379932356257, "percentage": 65.45, "elapsed_time": "3:08:31", "remaining_time": "1:39:29", "throughput": 13349.03, "total_tokens": 150994944} |
|
{"current_steps": 73, "total_steps": 110, "loss": 0.6485, "lr": 1.2706676883859903e-05, "epoch": 0.6583990980834273, "percentage": 66.36, "elapsed_time": "3:11:09", "remaining_time": "1:36:53", "throughput": 13347.43, "total_tokens": 153092096} |
|
{"current_steps": 74, "total_steps": 110, "loss": 0.6544, "lr": 1.2090063459025955e-05, "epoch": 0.6674182638105975, "percentage": 67.27, "elapsed_time": "3:13:48", "remaining_time": "1:34:16", "throughput": 13345.97, "total_tokens": 155189248} |
|
{"current_steps": 75, "total_steps": 110, "loss": 0.6763, "lr": 1.148397956361007e-05, "epoch": 0.6764374295377678, "percentage": 68.18, "elapsed_time": "3:16:26", "remaining_time": "1:31:40", "throughput": 13344.93, "total_tokens": 157286400} |
|
{"current_steps": 76, "total_steps": 110, "loss": 0.6406, "lr": 1.0888919528330777e-05, "epoch": 0.685456595264938, "percentage": 69.09, "elapsed_time": "3:19:05", "remaining_time": "1:29:04", "throughput": 13342.47, "total_tokens": 159383552} |
|
{"current_steps": 77, "total_steps": 110, "loss": 0.6502, "lr": 1.0305368692688174e-05, "epoch": 0.6944757609921083, "percentage": 70.0, "elapsed_time": "3:21:44", "remaining_time": "1:26:27", "throughput": 13341.02, "total_tokens": 161480704} |
|
{"current_steps": 78, "total_steps": 110, "loss": 0.6495, "lr": 9.733803009114045e-06, "epoch": 0.7034949267192785, "percentage": 70.91, "elapsed_time": "3:24:22", "remaining_time": "1:23:50", "throughput": 13339.92, "total_tokens": 163577856} |
|
{"current_steps": 79, "total_steps": 110, "loss": 0.6469, "lr": 9.174688654778243e-06, "epoch": 0.7125140924464487, "percentage": 71.82, "elapsed_time": "3:27:00", "remaining_time": "1:21:13", "throughput": 13339.19, "total_tokens": 165675008} |
|
{"current_steps": 80, "total_steps": 110, "loss": 0.6642, "lr": 8.628481651367876e-06, "epoch": 0.7215332581736189, "percentage": 72.73, "elapsed_time": "3:29:38", "remaining_time": "1:18:37", "throughput": 13337.79, "total_tokens": 167772160} |
|
{"current_steps": 81, "total_steps": 110, "loss": 0.6598, "lr": 8.09562749314952e-06, "epoch": 0.7305524239007892, "percentage": 73.64, "elapsed_time": "3:32:16", "remaining_time": "1:16:00", "throughput": 13336.77, "total_tokens": 169869312} |
|
{"current_steps": 82, "total_steps": 110, "loss": 0.6461, "lr": 7.576560783617668e-06, "epoch": 0.7395715896279594, "percentage": 74.55, "elapsed_time": "3:34:55", "remaining_time": "1:13:23", "throughput": 13335.06, "total_tokens": 171966464} |
|
{"current_steps": 83, "total_steps": 110, "loss": 0.6706, "lr": 7.071704881025915e-06, "epoch": 0.7485907553551296, "percentage": 75.45, "elapsed_time": "3:37:34", "remaining_time": "1:10:46", "throughput": 13333.27, "total_tokens": 174063616} |
|
{"current_steps": 84, "total_steps": 110, "loss": 0.6768, "lr": 6.5814715530898745e-06, "epoch": 0.7576099210822999, "percentage": 76.36, "elapsed_time": "3:40:12", "remaining_time": "1:08:09", "throughput": 13332.46, "total_tokens": 176160768} |
|
{"current_steps": 85, "total_steps": 110, "loss": 0.6446, "lr": 6.106260641143546e-06, "epoch": 0.7666290868094702, "percentage": 77.27, "elapsed_time": "3:42:50", "remaining_time": "1:05:32", "throughput": 13331.91, "total_tokens": 178257920} |
|
{"current_steps": 86, "total_steps": 110, "loss": 0.6393, "lr": 5.646459734022938e-06, "epoch": 0.7756482525366404, "percentage": 78.18, "elapsed_time": "3:45:28", "remaining_time": "1:02:55", "throughput": 13331.08, "total_tokens": 180355072} |
|
{"current_steps": 87, "total_steps": 110, "loss": 0.6585, "lr": 5.202443851943126e-06, "epoch": 0.7846674182638106, "percentage": 79.09, "elapsed_time": "3:48:06", "remaining_time": "1:00:18", "throughput": 13330.39, "total_tokens": 182452224} |
|
{"current_steps": 88, "total_steps": 110, "loss": 0.6393, "lr": 4.7745751406263165e-06, "epoch": 0.7936865839909808, "percentage": 80.0, "elapsed_time": "3:50:45", "remaining_time": "0:57:41", "throughput": 13329.42, "total_tokens": 184549376} |
|
{"current_steps": 89, "total_steps": 110, "loss": 0.6613, "lr": 4.36320257593065e-06, "epoch": 0.8027057497181511, "percentage": 80.91, "elapsed_time": "3:53:22", "remaining_time": "0:55:04", "throughput": 13329.14, "total_tokens": 186646528} |
|
{"current_steps": 90, "total_steps": 110, "loss": 0.6631, "lr": 3.968661679220468e-06, "epoch": 0.8117249154453213, "percentage": 81.82, "elapsed_time": "3:56:02", "remaining_time": "0:52:27", "throughput": 13327.42, "total_tokens": 188743680} |
|
{"current_steps": 91, "total_steps": 110, "loss": 0.6356, "lr": 3.591274243710277e-06, "epoch": 0.8207440811724915, "percentage": 82.73, "elapsed_time": "3:58:40", "remaining_time": "0:49:50", "throughput": 13326.22, "total_tokens": 190840832} |
|
{"current_steps": 92, "total_steps": 110, "loss": 0.6475, "lr": 3.2313480720055745e-06, "epoch": 0.8297632468996617, "percentage": 83.64, "elapsed_time": "4:01:19", "remaining_time": "0:47:12", "throughput": 13325.12, "total_tokens": 192937984} |
|
{"current_steps": 93, "total_steps": 110, "loss": 0.6387, "lr": 2.889176725054643e-06, "epoch": 0.8387824126268321, "percentage": 84.55, "elapsed_time": "4:03:57", "remaining_time": "0:44:35", "throughput": 13324.1, "total_tokens": 195035136} |
|
{"current_steps": 94, "total_steps": 110, "loss": 0.6533, "lr": 2.565039282716045e-06, "epoch": 0.8478015783540023, "percentage": 85.45, "elapsed_time": "4:06:36", "remaining_time": "0:41:58", "throughput": 13323.33, "total_tokens": 197132288} |
|
{"current_steps": 95, "total_steps": 110, "loss": 0.6606, "lr": 2.2592001161370392e-06, "epoch": 0.8568207440811725, "percentage": 86.36, "elapsed_time": "4:09:14", "remaining_time": "0:39:21", "throughput": 13322.67, "total_tokens": 199229440} |
|
{"current_steps": 96, "total_steps": 110, "loss": 0.6667, "lr": 1.97190867212875e-06, "epoch": 0.8658399098083427, "percentage": 87.27, "elapsed_time": "4:11:52", "remaining_time": "0:36:43", "throughput": 13322.1, "total_tokens": 201326592} |
|
{"current_steps": 97, "total_steps": 110, "loss": 0.6599, "lr": 1.703399269713693e-06, "epoch": 0.874859075535513, "percentage": 88.18, "elapsed_time": "4:14:30", "remaining_time": "0:34:06", "throughput": 13321.16, "total_tokens": 203423744} |
|
{"current_steps": 98, "total_steps": 110, "loss": 0.6499, "lr": 1.4538909090118846e-06, "epoch": 0.8838782412626832, "percentage": 89.09, "elapsed_time": "4:17:09", "remaining_time": "0:31:29", "throughput": 13319.93, "total_tokens": 205520896} |
|
{"current_steps": 99, "total_steps": 110, "loss": 0.649, "lr": 1.2235870926211619e-06, "epoch": 0.8928974069898534, "percentage": 90.0, "elapsed_time": "4:19:47", "remaining_time": "0:28:51", "throughput": 13319.17, "total_tokens": 207618048} |
|
{"current_steps": 100, "total_steps": 110, "loss": 0.6551, "lr": 1.0126756596375686e-06, "epoch": 0.9019165727170236, "percentage": 90.91, "elapsed_time": "4:22:26", "remaining_time": "0:26:14", "throughput": 13318.33, "total_tokens": 209715200} |
|
{"current_steps": 101, "total_steps": 110, "loss": 0.668, "lr": 8.213286324510738e-07, "epoch": 0.910935738444194, "percentage": 91.82, "elapsed_time": "4:25:04", "remaining_time": "0:23:37", "throughput": 13317.49, "total_tokens": 211812352} |
|
{"current_steps": 102, "total_steps": 110, "loss": 0.6505, "lr": 6.497020764416633e-07, "epoch": 0.9199549041713642, "percentage": 92.73, "elapsed_time": "4:27:43", "remaining_time": "0:20:59", "throughput": 13316.86, "total_tokens": 213909504} |
|
{"current_steps": 103, "total_steps": 110, "loss": 0.6504, "lr": 4.979359726901639e-07, "epoch": 0.9289740698985344, "percentage": 93.64, "elapsed_time": "4:30:20", "remaining_time": "0:18:22", "throughput": 13317.27, "total_tokens": 216006656} |
|
{"current_steps": 104, "total_steps": 110, "loss": 0.6504, "lr": 3.6615410380767544e-07, "epoch": 0.9379932356257046, "percentage": 94.55, "elapsed_time": "4:32:57", "remaining_time": "0:15:44", "throughput": 13317.01, "total_tokens": 218103808} |
|
{"current_steps": 105, "total_steps": 110, "loss": 0.6491, "lr": 2.544639529766829e-07, "epoch": 0.9470124013528749, "percentage": 95.45, "elapsed_time": "4:35:36", "remaining_time": "0:13:07", "throughput": 13316.43, "total_tokens": 220200960} |
|
{"current_steps": 106, "total_steps": 110, "loss": 0.6449, "lr": 1.6295661628624447e-07, "epoch": 0.9560315670800451, "percentage": 96.36, "elapsed_time": "4:38:13", "remaining_time": "0:10:29", "throughput": 13316.07, "total_tokens": 222298112} |
|
{"current_steps": 107, "total_steps": 110, "loss": 0.6729, "lr": 9.170672843271666e-08, "epoch": 0.9650507328072153, "percentage": 97.27, "elapsed_time": "4:40:51", "remaining_time": "0:07:52", "throughput": 13315.82, "total_tokens": 224395264} |
|
{"current_steps": 108, "total_steps": 110, "loss": 0.6308, "lr": 4.07724018466088e-08, "epoch": 0.9740698985343855, "percentage": 98.18, "elapsed_time": "4:43:29", "remaining_time": "0:05:14", "throughput": 13315.41, "total_tokens": 226492416} |
|
{"current_steps": 109, "total_steps": 110, "loss": 0.6695, "lr": 1.0195179295269252e-08, "epoch": 0.9830890642615558, "percentage": 99.09, "elapsed_time": "4:46:08", "remaining_time": "0:02:37", "throughput": 13314.76, "total_tokens": 228589568} |
|
{"current_steps": 110, "total_steps": 110, "loss": 0.6467, "lr": 0.0, "epoch": 0.992108229988726, "percentage": 100.0, "elapsed_time": "4:48:46", "remaining_time": "0:00:00", "throughput": 13314.02, "total_tokens": 230686720} |
|
{"current_steps": 110, "total_steps": 110, "epoch": 0.992108229988726, "percentage": 100.0, "elapsed_time": "4:49:11", "remaining_time": "0:00:00", "throughput": 13294.64, "total_tokens": 230686720} |
|
|