|
{"current_steps": 5, "total_steps": 243, "loss": 2.3883, "lr": 0.00019986631570270832, "epoch": 0.06116207951070336, "percentage": 2.06, "elapsed_time": "0:01:49", "remaining_time": "1:27:12", "throughput": 36.53, "total_tokens": 4016} |
|
{"current_steps": 10, "total_steps": 243, "loss": 1.4752, "lr": 0.00019932383577419432, "epoch": 0.12232415902140673, "percentage": 4.12, "elapsed_time": "0:03:39", "remaining_time": "1:25:04", "throughput": 36.29, "total_tokens": 7952} |
|
{"current_steps": 15, "total_steps": 243, "loss": 1.1174, "lr": 0.0001983664691986601, "epoch": 0.1834862385321101, "percentage": 6.17, "elapsed_time": "0:05:30", "remaining_time": "1:23:42", "throughput": 36.12, "total_tokens": 11936} |
|
{"current_steps": 20, "total_steps": 243, "loss": 0.7815, "lr": 0.00019699821500217434, "epoch": 0.24464831804281345, "percentage": 8.23, "elapsed_time": "0:07:18", "remaining_time": "1:21:32", "throughput": 36.03, "total_tokens": 15808} |
|
{"current_steps": 25, "total_steps": 243, "loss": 0.632, "lr": 0.00019522478853384155, "epoch": 0.3058103975535168, "percentage": 10.29, "elapsed_time": "0:09:09", "remaining_time": "1:19:48", "throughput": 36.22, "total_tokens": 19888} |
|
{"current_steps": 30, "total_steps": 243, "loss": 0.4603, "lr": 0.00019305359759215685, "epoch": 0.3669724770642202, "percentage": 12.35, "elapsed_time": "0:10:59", "remaining_time": "1:17:59", "throughput": 36.2, "total_tokens": 23856} |
|
{"current_steps": 35, "total_steps": 243, "loss": 0.4761, "lr": 0.00019049371148181253, "epoch": 0.42813455657492355, "percentage": 14.4, "elapsed_time": "0:12:50", "remaining_time": "1:16:19", "throughput": 36.25, "total_tokens": 27936} |
|
{"current_steps": 40, "total_steps": 243, "loss": 0.4525, "lr": 0.0001875558231302091, "epoch": 0.4892966360856269, "percentage": 16.46, "elapsed_time": "0:14:39", "remaining_time": "1:14:25", "throughput": 36.22, "total_tokens": 31872} |
|
{"current_steps": 45, "total_steps": 243, "loss": 0.4803, "lr": 0.00018425220442191495, "epoch": 0.5504587155963303, "percentage": 18.52, "elapsed_time": "0:16:28", "remaining_time": "1:12:28", "throughput": 36.12, "total_tokens": 35696} |
|
{"current_steps": 50, "total_steps": 243, "loss": 0.3933, "lr": 0.00018059665493764743, "epoch": 0.6116207951070336, "percentage": 20.58, "elapsed_time": "0:18:18", "remaining_time": "1:10:41", "throughput": 36.11, "total_tokens": 39680} |
|
{"current_steps": 55, "total_steps": 243, "loss": 0.3919, "lr": 0.0001766044443118978, "epoch": 0.672782874617737, "percentage": 22.63, "elapsed_time": "0:20:12", "remaining_time": "1:09:05", "throughput": 36.22, "total_tokens": 43920} |
|
{"current_steps": 60, "total_steps": 243, "loss": 0.3804, "lr": 0.00017229224844997928, "epoch": 0.7339449541284404, "percentage": 24.69, "elapsed_time": "0:22:06", "remaining_time": "1:07:25", "throughput": 36.31, "total_tokens": 48160} |
|
{"current_steps": 65, "total_steps": 243, "loss": 0.3576, "lr": 0.00016767807987092621, "epoch": 0.7951070336391437, "percentage": 26.75, "elapsed_time": "0:23:55", "remaining_time": "1:05:30", "throughput": 36.28, "total_tokens": 52080} |
|
{"current_steps": 70, "total_steps": 243, "loss": 0.3343, "lr": 0.00016278121246720987, "epoch": 0.8562691131498471, "percentage": 28.81, "elapsed_time": "0:25:45", "remaining_time": "1:03:39", "throughput": 36.32, "total_tokens": 56128} |
|
{"current_steps": 75, "total_steps": 243, "loss": 0.4526, "lr": 0.00015762210099555803, "epoch": 0.9174311926605505, "percentage": 30.86, "elapsed_time": "0:27:32", "remaining_time": "1:01:42", "throughput": 36.27, "total_tokens": 59952} |
|
{"current_steps": 80, "total_steps": 243, "loss": 0.4048, "lr": 0.00015222229563517385, "epoch": 0.9785932721712538, "percentage": 32.92, "elapsed_time": "0:29:21", "remaining_time": "0:59:48", "throughput": 36.24, "total_tokens": 63840} |
|
{"current_steps": 85, "total_steps": 243, "loss": 0.3599, "lr": 0.0001466043519702539, "epoch": 1.0489296636085628, "percentage": 34.98, "elapsed_time": "0:31:20", "remaining_time": "0:58:14", "throughput": 36.26, "total_tokens": 68176} |
|
{"current_steps": 90, "total_steps": 243, "loss": 0.2197, "lr": 0.00014079173677281837, "epoch": 1.110091743119266, "percentage": 37.04, "elapsed_time": "0:33:12", "remaining_time": "0:56:26", "throughput": 36.31, "total_tokens": 72336} |
|
{"current_steps": 95, "total_steps": 243, "loss": 0.1816, "lr": 0.00013480872997940905, "epoch": 1.1712538226299694, "percentage": 39.09, "elapsed_time": "0:35:02", "remaining_time": "0:54:35", "throughput": 36.33, "total_tokens": 76384} |
|
{"current_steps": 100, "total_steps": 243, "loss": 0.1839, "lr": 0.00012868032327110904, "epoch": 1.2324159021406729, "percentage": 41.15, "elapsed_time": "0:36:52", "remaining_time": "0:52:43", "throughput": 36.33, "total_tokens": 80368} |
|
{"current_steps": 105, "total_steps": 243, "loss": 0.21, "lr": 0.00012243211568052677, "epoch": 1.2935779816513762, "percentage": 43.21, "elapsed_time": "0:38:48", "remaining_time": "0:50:59", "throughput": 36.25, "total_tokens": 84400} |
|
{"current_steps": 110, "total_steps": 243, "loss": 0.2568, "lr": 0.00011609020666180575, "epoch": 1.3547400611620795, "percentage": 45.27, "elapsed_time": "0:40:37", "remaining_time": "0:49:07", "throughput": 36.24, "total_tokens": 88352} |
|
{"current_steps": 115, "total_steps": 243, "loss": 0.2049, "lr": 0.00010968108707031792, "epoch": 1.4159021406727827, "percentage": 47.33, "elapsed_time": "0:42:29", "remaining_time": "0:47:17", "throughput": 36.27, "total_tokens": 92464} |
|
{"current_steps": 120, "total_steps": 243, "loss": 0.2213, "lr": 0.00010323152850743107, "epoch": 1.4770642201834863, "percentage": 49.38, "elapsed_time": "0:44:18", "remaining_time": "0:45:24", "throughput": 36.28, "total_tokens": 96432} |
|
{"current_steps": 125, "total_steps": 243, "loss": 0.2836, "lr": 9.676847149256895e-05, "epoch": 1.5382262996941896, "percentage": 51.44, "elapsed_time": "0:46:08", "remaining_time": "0:43:33", "throughput": 36.28, "total_tokens": 100416} |
|
{"current_steps": 130, "total_steps": 243, "loss": 0.228, "lr": 9.03189129296821e-05, "epoch": 1.599388379204893, "percentage": 53.5, "elapsed_time": "0:47:58", "remaining_time": "0:41:42", "throughput": 36.28, "total_tokens": 104432} |
|
{"current_steps": 135, "total_steps": 243, "loss": 0.1778, "lr": 8.390979333819426e-05, "epoch": 1.6605504587155964, "percentage": 55.56, "elapsed_time": "0:49:48", "remaining_time": "0:39:50", "throughput": 36.28, "total_tokens": 108432} |
|
{"current_steps": 140, "total_steps": 243, "loss": 0.1871, "lr": 7.756788431947326e-05, "epoch": 1.7217125382262997, "percentage": 57.61, "elapsed_time": "0:51:36", "remaining_time": "0:37:58", "throughput": 36.27, "total_tokens": 112320} |
|
{"current_steps": 145, "total_steps": 243, "loss": 0.2289, "lr": 7.131967672889101e-05, "epoch": 1.782874617737003, "percentage": 59.67, "elapsed_time": "0:53:26", "remaining_time": "0:36:06", "throughput": 36.27, "total_tokens": 116272} |
|
{"current_steps": 150, "total_steps": 243, "loss": 0.2889, "lr": 6.519127002059095e-05, "epoch": 1.8440366972477065, "percentage": 61.73, "elapsed_time": "0:55:14", "remaining_time": "0:34:15", "throughput": 36.27, "total_tokens": 120224} |
|
{"current_steps": 155, "total_steps": 243, "loss": 0.2724, "lr": 5.920826322718165e-05, "epoch": 1.9051987767584098, "percentage": 63.79, "elapsed_time": "0:57:05", "remaining_time": "0:32:24", "throughput": 36.25, "total_tokens": 124176} |
|
{"current_steps": 160, "total_steps": 243, "loss": 0.2359, "lr": 5.339564802974615e-05, "epoch": 1.9663608562691133, "percentage": 65.84, "elapsed_time": "0:58:56", "remaining_time": "0:30:34", "throughput": 36.26, "total_tokens": 128256} |
|
{"current_steps": 165, "total_steps": 243, "loss": 0.1864, "lr": 4.777770436482617e-05, "epoch": 2.036697247706422, "percentage": 67.9, "elapsed_time": "1:00:56", "remaining_time": "0:28:48", "throughput": 36.26, "total_tokens": 132576} |
|
{"current_steps": 170, "total_steps": 243, "loss": 0.0671, "lr": 4.2377899004441966e-05, "epoch": 2.0978593272171255, "percentage": 69.96, "elapsed_time": "1:02:47", "remaining_time": "0:26:57", "throughput": 36.26, "total_tokens": 136608} |
|
{"current_steps": 175, "total_steps": 243, "loss": 0.1465, "lr": 3.721878753279017e-05, "epoch": 2.159021406727829, "percentage": 72.02, "elapsed_time": "1:04:35", "remaining_time": "0:25:05", "throughput": 36.23, "total_tokens": 140416} |
|
{"current_steps": 180, "total_steps": 243, "loss": 0.091, "lr": 3.2321920129073816e-05, "epoch": 2.220183486238532, "percentage": 74.07, "elapsed_time": "1:06:24", "remaining_time": "0:23:14", "throughput": 36.22, "total_tokens": 144336} |
|
{"current_steps": 185, "total_steps": 243, "loss": 0.114, "lr": 2.770775155002071e-05, "epoch": 2.2813455657492354, "percentage": 76.13, "elapsed_time": "1:08:14", "remaining_time": "0:21:23", "throughput": 36.21, "total_tokens": 148256} |
|
{"current_steps": 190, "total_steps": 243, "loss": 0.1381, "lr": 2.339555568810221e-05, "epoch": 2.3425076452599387, "percentage": 78.19, "elapsed_time": "1:10:06", "remaining_time": "0:19:33", "throughput": 36.23, "total_tokens": 152416} |
|
{"current_steps": 195, "total_steps": 243, "loss": 0.0799, "lr": 1.9403345062352573e-05, "epoch": 2.4036697247706424, "percentage": 80.25, "elapsed_time": "1:11:56", "remaining_time": "0:17:42", "throughput": 36.24, "total_tokens": 156400} |
|
{"current_steps": 200, "total_steps": 243, "loss": 0.0722, "lr": 1.5747795578085046e-05, "epoch": 2.4648318042813457, "percentage": 82.3, "elapsed_time": "1:13:47", "remaining_time": "0:15:52", "throughput": 36.25, "total_tokens": 160528} |
|
{"current_steps": 205, "total_steps": 243, "loss": 0.1003, "lr": 1.2444176869790925e-05, "epoch": 2.525993883792049, "percentage": 84.36, "elapsed_time": "1:15:46", "remaining_time": "0:14:02", "throughput": 36.23, "total_tokens": 164720} |
|
{"current_steps": 210, "total_steps": 243, "loss": 0.1155, "lr": 9.506288518187467e-06, "epoch": 2.5871559633027523, "percentage": 86.42, "elapsed_time": "1:17:34", "remaining_time": "0:12:11", "throughput": 36.21, "total_tokens": 168560} |
|
{"current_steps": 215, "total_steps": 243, "loss": 0.0962, "lr": 6.946402407843155e-06, "epoch": 2.6483180428134556, "percentage": 88.48, "elapsed_time": "1:19:25", "remaining_time": "0:10:20", "throughput": 36.22, "total_tokens": 172608} |
|
{"current_steps": 220, "total_steps": 243, "loss": 0.0808, "lr": 4.775211466158469e-06, "epoch": 2.709480122324159, "percentage": 90.53, "elapsed_time": "1:21:16", "remaining_time": "0:08:29", "throughput": 36.23, "total_tokens": 176656} |
|
{"current_steps": 225, "total_steps": 243, "loss": 0.1206, "lr": 3.0017849978256516e-06, "epoch": 2.770642201834862, "percentage": 92.59, "elapsed_time": "1:23:06", "remaining_time": "0:06:38", "throughput": 36.22, "total_tokens": 180608} |
|
{"current_steps": 230, "total_steps": 243, "loss": 0.1259, "lr": 1.6335308013398886e-06, "epoch": 2.8318042813455655, "percentage": 94.65, "elapsed_time": "1:24:56", "remaining_time": "0:04:48", "throughput": 36.22, "total_tokens": 184592} |
|
{"current_steps": 235, "total_steps": 243, "loss": 0.158, "lr": 6.761642258056978e-07, "epoch": 2.8929663608562692, "percentage": 96.71, "elapsed_time": "1:26:44", "remaining_time": "0:02:57", "throughput": 36.22, "total_tokens": 188496} |
|
{"current_steps": 240, "total_steps": 243, "loss": 0.062, "lr": 1.3368429729168076e-07, "epoch": 2.9541284403669725, "percentage": 98.77, "elapsed_time": "1:28:33", "remaining_time": "0:01:06", "throughput": 36.21, "total_tokens": 192368} |
|
{"current_steps": 243, "total_steps": 243, "epoch": 2.9908256880733948, "percentage": 100.0, "elapsed_time": "1:29:42", "remaining_time": "0:00:00", "throughput": 36.2, "total_tokens": 194864} |
|
|