| {"current_steps": 5, "total_steps": 1130, "loss": 9.3038, "lr": 1.7699115044247788e-06, "epoch": 0.04424778761061947, "percentage": 0.44, "elapsed_time": "0:00:02", "remaining_time": "0:10:49", "throughput": 526.76, "total_tokens": 1520} |
| {"current_steps": 10, "total_steps": 1130, "loss": 7.8011, "lr": 3.982300884955752e-06, "epoch": 0.08849557522123894, "percentage": 0.88, "elapsed_time": "0:00:03", "remaining_time": "0:06:13", "throughput": 892.43, "total_tokens": 2976} |
| {"current_steps": 15, "total_steps": 1130, "loss": 5.8089, "lr": 6.194690265486726e-06, "epoch": 0.13274336283185842, "percentage": 1.33, "elapsed_time": "0:00:03", "remaining_time": "0:04:44", "throughput": 1225.51, "total_tokens": 4688} |
| {"current_steps": 20, "total_steps": 1130, "loss": 3.2162, "lr": 8.407079646017701e-06, "epoch": 0.17699115044247787, "percentage": 1.77, "elapsed_time": "0:00:04", "remaining_time": "0:03:55", "throughput": 1360.48, "total_tokens": 5776} |
| {"current_steps": 25, "total_steps": 1130, "loss": 1.0524, "lr": 1.0619469026548673e-05, "epoch": 0.22123893805309736, "percentage": 2.21, "elapsed_time": "0:00:04", "remaining_time": "0:03:26", "throughput": 1494.56, "total_tokens": 6992} |
| {"current_steps": 30, "total_steps": 1130, "loss": 1.2224, "lr": 1.2831858407079647e-05, "epoch": 0.26548672566371684, "percentage": 2.65, "elapsed_time": "0:00:05", "remaining_time": "0:03:07", "throughput": 1627.11, "total_tokens": 8320} |
| {"current_steps": 35, "total_steps": 1130, "loss": 0.959, "lr": 1.504424778761062e-05, "epoch": 0.30973451327433627, "percentage": 3.1, "elapsed_time": "0:00:05", "remaining_time": "0:02:53", "throughput": 1718.25, "total_tokens": 9536} |
| {"current_steps": 40, "total_steps": 1130, "loss": 0.3716, "lr": 1.7256637168141594e-05, "epoch": 0.35398230088495575, "percentage": 3.54, "elapsed_time": "0:00:06", "remaining_time": "0:02:44", "throughput": 1839.02, "total_tokens": 11072} |
| {"current_steps": 45, "total_steps": 1130, "loss": 1.0354, "lr": 1.946902654867257e-05, "epoch": 0.39823008849557523, "percentage": 3.98, "elapsed_time": "0:00:06", "remaining_time": "0:02:35", "throughput": 1910.8, "total_tokens": 12320} |
| {"current_steps": 50, "total_steps": 1130, "loss": 0.3628, "lr": 2.1681415929203542e-05, "epoch": 0.4424778761061947, "percentage": 4.42, "elapsed_time": "0:00:06", "remaining_time": "0:02:28", "throughput": 1977.62, "total_tokens": 13616} |
| {"current_steps": 55, "total_steps": 1130, "loss": 0.8643, "lr": 2.3893805309734516e-05, "epoch": 0.48672566371681414, "percentage": 4.87, "elapsed_time": "0:00:07", "remaining_time": "0:02:23", "throughput": 2054.67, "total_tokens": 15104} |
| {"current_steps": 57, "total_steps": 1130, "eval_loss": 0.4547373652458191, "epoch": 0.504424778761062, "percentage": 5.04, "elapsed_time": "0:00:08", "remaining_time": "0:02:36", "throughput": 1885.22, "total_tokens": 15664} |
| {"current_steps": 60, "total_steps": 1130, "loss": 0.3507, "lr": 2.610619469026549e-05, "epoch": 0.5309734513274337, "percentage": 5.31, "elapsed_time": "0:00:11", "remaining_time": "0:03:20", "throughput": 1451.13, "total_tokens": 16352} |
| {"current_steps": 65, "total_steps": 1130, "loss": 0.3175, "lr": 2.831858407079646e-05, "epoch": 0.5752212389380531, "percentage": 5.75, "elapsed_time": "0:00:11", "remaining_time": "0:03:12", "throughput": 1520.6, "total_tokens": 17888} |
| {"current_steps": 70, "total_steps": 1130, "loss": 0.7932, "lr": 3.0530973451327434e-05, "epoch": 0.6194690265486725, "percentage": 6.19, "elapsed_time": "0:00:12", "remaining_time": "0:03:04", "throughput": 1559.53, "total_tokens": 19008} |
| {"current_steps": 75, "total_steps": 1130, "loss": 0.2819, "lr": 3.274336283185841e-05, "epoch": 0.6637168141592921, "percentage": 6.64, "elapsed_time": "0:00:12", "remaining_time": "0:02:58", "throughput": 1609.75, "total_tokens": 20480} |
| {"current_steps": 80, "total_steps": 1130, "loss": 0.5588, "lr": 3.495575221238938e-05, "epoch": 0.7079646017699115, "percentage": 7.08, "elapsed_time": "0:00:13", "remaining_time": "0:02:53", "throughput": 1662.5, "total_tokens": 22000} |
| {"current_steps": 85, "total_steps": 1130, "loss": 0.303, "lr": 3.716814159292036e-05, "epoch": 0.7522123893805309, "percentage": 7.52, "elapsed_time": "0:00:13", "remaining_time": "0:02:48", "throughput": 1709.87, "total_tokens": 23456} |
| {"current_steps": 90, "total_steps": 1130, "loss": 0.2319, "lr": 3.938053097345133e-05, "epoch": 0.7964601769911505, "percentage": 7.96, "elapsed_time": "0:00:14", "remaining_time": "0:02:44", "throughput": 1776.27, "total_tokens": 25280} |
| {"current_steps": 95, "total_steps": 1130, "loss": 0.1757, "lr": 4.15929203539823e-05, "epoch": 0.8407079646017699, "percentage": 8.41, "elapsed_time": "0:00:14", "remaining_time": "0:02:39", "throughput": 1806.62, "total_tokens": 26496} |
| {"current_steps": 100, "total_steps": 1130, "loss": 0.1669, "lr": 4.380530973451328e-05, "epoch": 0.8849557522123894, "percentage": 8.85, "elapsed_time": "0:00:15", "remaining_time": "0:02:36", "throughput": 1847.12, "total_tokens": 28016} |
| {"current_steps": 105, "total_steps": 1130, "loss": 0.538, "lr": 4.601769911504425e-05, "epoch": 0.9292035398230089, "percentage": 9.29, "elapsed_time": "0:00:15", "remaining_time": "0:02:32", "throughput": 1877.93, "total_tokens": 29344} |
| {"current_steps": 110, "total_steps": 1130, "loss": 0.2715, "lr": 4.823008849557522e-05, "epoch": 0.9734513274336283, "percentage": 9.73, "elapsed_time": "0:00:16", "remaining_time": "0:02:29", "throughput": 1897.62, "total_tokens": 30496} |
| {"current_steps": 114, "total_steps": 1130, "eval_loss": 0.5620186924934387, "epoch": 1.008849557522124, "percentage": 10.09, "elapsed_time": "0:00:17", "remaining_time": "0:02:35", "throughput": 1798.34, "total_tokens": 31304} |
| {"current_steps": 115, "total_steps": 1130, "loss": 0.2842, "lr": 4.9999880720033856e-05, "epoch": 1.0176991150442478, "percentage": 10.18, "elapsed_time": "0:00:18", "remaining_time": "0:02:46", "throughput": 1668.63, "total_tokens": 31560} |
| {"current_steps": 120, "total_steps": 1130, "loss": 0.9137, "lr": 4.999570604073014e-05, "epoch": 1.0619469026548674, "percentage": 10.62, "elapsed_time": "0:00:19", "remaining_time": "0:02:43", "throughput": 1689.77, "total_tokens": 32744} |
| {"current_steps": 125, "total_steps": 1130, "loss": 0.4827, "lr": 4.998556850128691e-05, "epoch": 1.1061946902654867, "percentage": 11.06, "elapsed_time": "0:00:19", "remaining_time": "0:02:39", "throughput": 1731.77, "total_tokens": 34440} |
| {"current_steps": 130, "total_steps": 1130, "loss": 0.4721, "lr": 4.996947052006874e-05, "epoch": 1.1504424778761062, "percentage": 11.5, "elapsed_time": "0:00:20", "remaining_time": "0:02:37", "throughput": 1763.21, "total_tokens": 35992} |
| {"current_steps": 135, "total_steps": 1130, "loss": 0.6239, "lr": 4.9947415937335635e-05, "epoch": 1.1946902654867257, "percentage": 11.95, "elapsed_time": "0:00:20", "remaining_time": "0:02:34", "throughput": 1793.69, "total_tokens": 37480} |
| {"current_steps": 140, "total_steps": 1130, "loss": 0.3049, "lr": 4.9919410014326955e-05, "epoch": 1.238938053097345, "percentage": 12.39, "elapsed_time": "0:00:21", "remaining_time": "0:02:30", "throughput": 1816.88, "total_tokens": 38776} |
| {"current_steps": 145, "total_steps": 1130, "loss": 0.2219, "lr": 4.98854594320063e-05, "epoch": 1.2831858407079646, "percentage": 12.83, "elapsed_time": "0:00:21", "remaining_time": "0:02:28", "throughput": 1851.97, "total_tokens": 40408} |
| {"current_steps": 150, "total_steps": 1130, "loss": 0.9584, "lr": 4.98455722894677e-05, "epoch": 1.3274336283185841, "percentage": 13.27, "elapsed_time": "0:00:22", "remaining_time": "0:02:25", "throughput": 1883.13, "total_tokens": 41944} |
| {"current_steps": 155, "total_steps": 1130, "loss": 0.2229, "lr": 4.979975810200359e-05, "epoch": 1.3716814159292037, "percentage": 13.72, "elapsed_time": "0:00:22", "remaining_time": "0:02:23", "throughput": 1914.5, "total_tokens": 43576} |
| {"current_steps": 160, "total_steps": 1130, "loss": 0.5863, "lr": 4.974802779883484e-05, "epoch": 1.415929203539823, "percentage": 14.16, "elapsed_time": "0:00:23", "remaining_time": "0:02:20", "throughput": 1938.76, "total_tokens": 44984} |
| {"current_steps": 165, "total_steps": 1130, "loss": 0.5308, "lr": 4.969039372050356e-05, "epoch": 1.4601769911504425, "percentage": 14.6, "elapsed_time": "0:00:23", "remaining_time": "0:02:18", "throughput": 1962.98, "total_tokens": 46424} |
| {"current_steps": 170, "total_steps": 1130, "loss": 0.3501, "lr": 4.9626869615929175e-05, "epoch": 1.504424778761062, "percentage": 15.04, "elapsed_time": "0:00:24", "remaining_time": "0:02:16", "throughput": 1981.97, "total_tokens": 47800} |
| {"current_steps": 171, "total_steps": 1130, "eval_loss": 0.2233014702796936, "epoch": 1.5132743362831858, "percentage": 15.13, "elapsed_time": "0:00:24", "remaining_time": "0:02:20", "throughput": 1921.77, "total_tokens": 48008} |
| {"current_steps": 175, "total_steps": 1130, "loss": 0.4255, "lr": 4.9557470639128554e-05, "epoch": 1.5486725663716814, "percentage": 15.49, "elapsed_time": "0:00:26", "remaining_time": "0:02:26", "throughput": 1818.03, "total_tokens": 48776} |
| {"current_steps": 180, "total_steps": 1130, "loss": 0.1645, "lr": 4.9482213345600936e-05, "epoch": 1.592920353982301, "percentage": 15.93, "elapsed_time": "0:00:27", "remaining_time": "0:02:23", "throughput": 1832.79, "total_tokens": 49960} |
| {"current_steps": 185, "total_steps": 1130, "loss": 0.0174, "lr": 4.940111568837854e-05, "epoch": 1.6371681415929205, "percentage": 16.37, "elapsed_time": "0:00:27", "remaining_time": "0:02:21", "throughput": 1860.5, "total_tokens": 51624} |
| {"current_steps": 190, "total_steps": 1130, "loss": 0.2941, "lr": 4.931419701374377e-05, "epoch": 1.6814159292035398, "percentage": 16.81, "elapsed_time": "0:00:28", "remaining_time": "0:02:19", "throughput": 1881.54, "total_tokens": 53048} |
| {"current_steps": 195, "total_steps": 1130, "loss": 1.1045, "lr": 4.922147805661402e-05, "epoch": 1.7256637168141593, "percentage": 17.26, "elapsed_time": "0:00:28", "remaining_time": "0:02:17", "throughput": 1902.76, "total_tokens": 54552} |
| {"current_steps": 200, "total_steps": 1130, "loss": 0.4722, "lr": 4.91229809355953e-05, "epoch": 1.7699115044247788, "percentage": 17.7, "elapsed_time": "0:00:29", "remaining_time": "0:02:15", "throughput": 1912.89, "total_tokens": 55656} |
| {"current_steps": 205, "total_steps": 1130, "loss": 0.3305, "lr": 4.901872914770569e-05, "epoch": 1.8141592920353982, "percentage": 18.14, "elapsed_time": "0:00:29", "remaining_time": "0:02:13", "throughput": 1929.48, "total_tokens": 56984} |
| {"current_steps": 210, "total_steps": 1130, "loss": 0.5475, "lr": 4.8908747562769995e-05, "epoch": 1.8584070796460177, "percentage": 18.58, "elapsed_time": "0:00:29", "remaining_time": "0:02:11", "throughput": 1942.48, "total_tokens": 58200} |
| {"current_steps": 215, "total_steps": 1130, "loss": 0.1367, "lr": 4.8793062417486976e-05, "epoch": 1.9026548672566372, "percentage": 19.03, "elapsed_time": "0:00:30", "remaining_time": "0:02:09", "throughput": 1958.57, "total_tokens": 59544} |
| {"current_steps": 220, "total_steps": 1130, "loss": 0.5382, "lr": 4.867170130917034e-05, "epoch": 1.9469026548672566, "percentage": 19.47, "elapsed_time": "0:00:30", "remaining_time": "0:02:07", "throughput": 1975.47, "total_tokens": 60968} |
| {"current_steps": 225, "total_steps": 1130, "loss": 0.5262, "lr": 4.8544693189165324e-05, "epoch": 1.991150442477876, "percentage": 19.91, "elapsed_time": "0:00:31", "remaining_time": "0:02:05", "throughput": 1987.88, "total_tokens": 62216} |
| {"current_steps": 228, "total_steps": 1130, "eval_loss": 0.32860472798347473, "epoch": 2.017699115044248, "percentage": 20.18, "elapsed_time": "0:00:32", "remaining_time": "0:02:08", "throughput": 1933.47, "total_tokens": 63040} |
| {"current_steps": 230, "total_steps": 1130, "loss": 0.2754, "lr": 4.841206835594222e-05, "epoch": 2.0353982300884956, "percentage": 20.35, "elapsed_time": "0:00:34", "remaining_time": "0:02:13", "throughput": 1857.13, "total_tokens": 63568} |
| {"current_steps": 235, "total_steps": 1130, "loss": 0.1062, "lr": 4.8273858447868424e-05, "epoch": 2.079646017699115, "percentage": 20.8, "elapsed_time": "0:00:34", "remaining_time": "0:02:12", "throughput": 1867.54, "total_tokens": 64800} |
| {"current_steps": 240, "total_steps": 1130, "loss": 0.4179, "lr": 4.813009643566101e-05, "epoch": 2.1238938053097347, "percentage": 21.24, "elapsed_time": "0:00:35", "remaining_time": "0:02:10", "throughput": 1882.12, "total_tokens": 66144} |
| {"current_steps": 245, "total_steps": 1130, "loss": 0.047, "lr": 4.798081661452135e-05, "epoch": 2.168141592920354, "percentage": 21.68, "elapsed_time": "0:00:35", "remaining_time": "0:02:08", "throughput": 1899.28, "total_tokens": 67600} |
| {"current_steps": 250, "total_steps": 1130, "loss": 0.3323, "lr": 4.7826054595953815e-05, "epoch": 2.2123893805309733, "percentage": 22.12, "elapsed_time": "0:00:36", "remaining_time": "0:02:06", "throughput": 1914.39, "total_tokens": 69056} |
| {"current_steps": 255, "total_steps": 1130, "loss": 0.361, "lr": 4.766584729927049e-05, "epoch": 2.256637168141593, "percentage": 22.57, "elapsed_time": "0:00:36", "remaining_time": "0:02:05", "throughput": 1925.48, "total_tokens": 70304} |
| {"current_steps": 260, "total_steps": 1130, "loss": 0.1337, "lr": 4.750023294278381e-05, "epoch": 2.3008849557522124, "percentage": 23.01, "elapsed_time": "0:00:36", "remaining_time": "0:02:03", "throughput": 1943.14, "total_tokens": 71872} |
| {"current_steps": 265, "total_steps": 1130, "loss": 0.2764, "lr": 4.732925103468944e-05, "epoch": 2.3451327433628317, "percentage": 23.45, "elapsed_time": "0:00:37", "remaining_time": "0:02:02", "throughput": 1962.26, "total_tokens": 73520} |
| {"current_steps": 270, "total_steps": 1130, "loss": 0.0771, "lr": 4.715294236364135e-05, "epoch": 2.3893805309734515, "percentage": 23.89, "elapsed_time": "0:00:37", "remaining_time": "0:02:00", "throughput": 1981.04, "total_tokens": 75184} |
| {"current_steps": 275, "total_steps": 1130, "loss": 0.0644, "lr": 4.6971348989021446e-05, "epoch": 2.433628318584071, "percentage": 24.34, "elapsed_time": "0:00:38", "remaining_time": "0:01:59", "throughput": 1993.93, "total_tokens": 76592} |
| {"current_steps": 280, "total_steps": 1130, "loss": 0.7766, "lr": 4.6784514230906146e-05, "epoch": 2.47787610619469, "percentage": 24.78, "elapsed_time": "0:00:38", "remaining_time": "0:01:57", "throughput": 1999.31, "total_tokens": 77632} |
| {"current_steps": 285, "total_steps": 1130, "loss": 0.2992, "lr": 4.659248265973205e-05, "epoch": 2.52212389380531, "percentage": 25.22, "elapsed_time": "0:00:39", "remaining_time": "0:01:56", "throughput": 2012.5, "total_tokens": 79104} |
| {"current_steps": 285, "total_steps": 1130, "eval_loss": 0.13774029910564423, "epoch": 2.52212389380531, "percentage": 25.22, "elapsed_time": "0:00:40", "remaining_time": "0:01:58", "throughput": 1973.7, "total_tokens": 79104} |
| {"current_steps": 290, "total_steps": 1130, "loss": 0.0878, "lr": 4.639530008566349e-05, "epoch": 2.566371681415929, "percentage": 25.66, "elapsed_time": "0:00:41", "remaining_time": "0:02:01", "throughput": 1916.29, "total_tokens": 80432} |
| {"current_steps": 295, "total_steps": 1130, "loss": 0.5536, "lr": 4.6193013547664255e-05, "epoch": 2.6106194690265485, "percentage": 26.11, "elapsed_time": "0:00:42", "remaining_time": "0:02:00", "throughput": 1927.33, "total_tokens": 81744} |
| {"current_steps": 300, "total_steps": 1130, "loss": 0.6957, "lr": 4.5985671302276165e-05, "epoch": 2.6548672566371683, "percentage": 26.55, "elapsed_time": "0:00:42", "remaining_time": "0:01:58", "throughput": 1938.28, "total_tokens": 83104} |
| {"current_steps": 305, "total_steps": 1130, "loss": 0.3277, "lr": 4.577332281210727e-05, "epoch": 2.6991150442477876, "percentage": 26.99, "elapsed_time": "0:00:43", "remaining_time": "0:01:57", "throughput": 1947.08, "total_tokens": 84336} |
| {"current_steps": 310, "total_steps": 1130, "loss": 0.4949, "lr": 4.55560187340322e-05, "epoch": 2.7433628318584073, "percentage": 27.43, "elapsed_time": "0:00:43", "remaining_time": "0:01:55", "throughput": 1962.23, "total_tokens": 85936} |
| {"current_steps": 315, "total_steps": 1130, "loss": 0.1694, "lr": 4.533381090710776e-05, "epoch": 2.7876106194690267, "percentage": 27.88, "elapsed_time": "0:00:44", "remaining_time": "0:01:54", "throughput": 1971.4, "total_tokens": 87232} |
| {"current_steps": 320, "total_steps": 1130, "loss": 0.0296, "lr": 4.5106752340206435e-05, "epoch": 2.831858407079646, "percentage": 28.32, "elapsed_time": "0:00:44", "remaining_time": "0:01:53", "throughput": 1977.07, "total_tokens": 88336} |
| {"current_steps": 325, "total_steps": 1130, "loss": 0.3007, "lr": 4.4874897199370805e-05, "epoch": 2.8761061946902657, "percentage": 28.76, "elapsed_time": "0:00:45", "remaining_time": "0:01:51", "throughput": 1985.82, "total_tokens": 89584} |
| {"current_steps": 330, "total_steps": 1130, "loss": 0.1205, "lr": 4.463830079489196e-05, "epoch": 2.920353982300885, "percentage": 29.2, "elapsed_time": "0:00:45", "remaining_time": "0:01:50", "throughput": 1997.61, "total_tokens": 91008} |
| {"current_steps": 335, "total_steps": 1130, "loss": 0.3998, "lr": 4.4397019568114987e-05, "epoch": 2.9646017699115044, "percentage": 29.65, "elapsed_time": "0:00:45", "remaining_time": "0:01:49", "throughput": 2006.93, "total_tokens": 92288} |
| {"current_steps": 340, "total_steps": 1130, "loss": 0.0962, "lr": 4.415111107797445e-05, "epoch": 3.0088495575221237, "percentage": 30.09, "elapsed_time": "0:00:46", "remaining_time": "0:01:48", "throughput": 2001.99, "total_tokens": 93456} |
| {"current_steps": 342, "total_steps": 1130, "eval_loss": 0.15844351053237915, "epoch": 3.0265486725663715, "percentage": 30.27, "elapsed_time": "0:00:47", "remaining_time": "0:01:49", "throughput": 1971.32, "total_tokens": 93888} |
| {"current_steps": 345, "total_steps": 1130, "loss": 0.0034, "lr": 4.390063398726356e-05, "epoch": 3.0530973451327434, "percentage": 30.53, "elapsed_time": "0:00:49", "remaining_time": "0:01:52", "throughput": 1924.62, "total_tokens": 94752} |
| {"current_steps": 350, "total_steps": 1130, "loss": 0.3721, "lr": 4.3645648048639734e-05, "epoch": 3.0973451327433628, "percentage": 30.97, "elapsed_time": "0:00:49", "remaining_time": "0:01:50", "throughput": 1932.55, "total_tokens": 96000} |
| {"current_steps": 355, "total_steps": 1130, "loss": 0.0544, "lr": 4.338621409037031e-05, "epoch": 3.1415929203539825, "percentage": 31.42, "elapsed_time": "0:00:50", "remaining_time": "0:01:49", "throughput": 1945.17, "total_tokens": 97568} |
| {"current_steps": 360, "total_steps": 1130, "loss": 0.2974, "lr": 4.312239400182166e-05, "epoch": 3.185840707964602, "percentage": 31.86, "elapsed_time": "0:00:50", "remaining_time": "0:01:48", "throughput": 1954.32, "total_tokens": 98896} |
| {"current_steps": 365, "total_steps": 1130, "loss": 0.2165, "lr": 4.285425071869511e-05, "epoch": 3.230088495575221, "percentage": 32.3, "elapsed_time": "0:00:51", "remaining_time": "0:01:47", "throughput": 1965.32, "total_tokens": 100336} |
| {"current_steps": 370, "total_steps": 1130, "loss": 0.3636, "lr": 4.258184820801331e-05, "epoch": 3.274336283185841, "percentage": 32.74, "elapsed_time": "0:00:51", "remaining_time": "0:01:45", "throughput": 1977.08, "total_tokens": 101888} |
| {"current_steps": 375, "total_steps": 1130, "loss": 0.4511, "lr": 4.230525145286057e-05, "epoch": 3.3185840707964602, "percentage": 33.19, "elapsed_time": "0:00:51", "remaining_time": "0:01:44", "throughput": 1984.47, "total_tokens": 103184} |
| {"current_steps": 380, "total_steps": 1130, "loss": 0.0776, "lr": 4.2024526436880785e-05, "epoch": 3.3628318584070795, "percentage": 33.63, "elapsed_time": "0:00:52", "remaining_time": "0:01:43", "throughput": 1995.05, "total_tokens": 104672} |
| {"current_steps": 385, "total_steps": 1130, "loss": 0.2344, "lr": 4.173974012853665e-05, "epoch": 3.4070796460176993, "percentage": 34.07, "elapsed_time": "0:00:52", "remaining_time": "0:01:42", "throughput": 2003.03, "total_tokens": 105968} |
| {"current_steps": 390, "total_steps": 1130, "loss": 0.0518, "lr": 4.1450960465134025e-05, "epoch": 3.4513274336283186, "percentage": 34.51, "elapsed_time": "0:00:53", "remaining_time": "0:01:41", "throughput": 2013.54, "total_tokens": 107472} |
| {"current_steps": 395, "total_steps": 1130, "loss": 0.0753, "lr": 4.1158256336615096e-05, "epoch": 3.495575221238938, "percentage": 34.96, "elapsed_time": "0:00:53", "remaining_time": "0:01:40", "throughput": 2019.15, "total_tokens": 108688} |
| {"current_steps": 399, "total_steps": 1130, "eval_loss": 0.3117164373397827, "epoch": 3.5309734513274336, "percentage": 35.31, "elapsed_time": "0:00:54", "remaining_time": "0:01:40", "throughput": 1999.48, "total_tokens": 109952} |
| {"current_steps": 400, "total_steps": 1130, "loss": 0.5723, "lr": 4.086169756912431e-05, "epoch": 3.5398230088495577, "percentage": 35.4, "elapsed_time": "0:00:56", "remaining_time": "0:01:43", "throughput": 1954.65, "total_tokens": 110320} |
| {"current_steps": 405, "total_steps": 1130, "loss": 0.3036, "lr": 4.056135490835098e-05, "epoch": 3.584070796460177, "percentage": 35.84, "elapsed_time": "0:00:56", "remaining_time": "0:01:41", "throughput": 1965.98, "total_tokens": 111952} |
| {"current_steps": 410, "total_steps": 1130, "loss": 0.1427, "lr": 4.025730000265251e-05, "epoch": 3.6283185840707963, "percentage": 36.28, "elapsed_time": "0:00:57", "remaining_time": "0:01:40", "throughput": 1972.02, "total_tokens": 113152} |
| {"current_steps": 415, "total_steps": 1130, "loss": 0.1798, "lr": 3.994960538596232e-05, "epoch": 3.672566371681416, "percentage": 36.73, "elapsed_time": "0:00:57", "remaining_time": "0:01:39", "throughput": 1981.66, "total_tokens": 114592} |
| {"current_steps": 420, "total_steps": 1130, "loss": 0.3672, "lr": 3.963834446048644e-05, "epoch": 3.7168141592920354, "percentage": 37.17, "elapsed_time": "0:00:58", "remaining_time": "0:01:38", "throughput": 1989.64, "total_tokens": 115936} |
| {"current_steps": 425, "total_steps": 1130, "loss": 0.1044, "lr": 3.9323591479193074e-05, "epoch": 3.7610619469026547, "percentage": 37.61, "elapsed_time": "0:00:58", "remaining_time": "0:01:37", "throughput": 1996.85, "total_tokens": 117232} |
| {"current_steps": 430, "total_steps": 1130, "loss": 0.2184, "lr": 3.90054215280991e-05, "epoch": 3.8053097345132745, "percentage": 38.05, "elapsed_time": "0:00:59", "remaining_time": "0:01:36", "throughput": 2002.97, "total_tokens": 118448} |
| {"current_steps": 435, "total_steps": 1130, "loss": 0.7422, "lr": 3.8683910508357934e-05, "epoch": 3.849557522123894, "percentage": 38.5, "elapsed_time": "0:00:59", "remaining_time": "0:01:35", "throughput": 2010.1, "total_tokens": 119760} |
| {"current_steps": 440, "total_steps": 1130, "loss": 0.0681, "lr": 3.83591351181529e-05, "epoch": 3.893805309734513, "percentage": 38.94, "elapsed_time": "0:01:00", "remaining_time": "0:01:34", "throughput": 2022.38, "total_tokens": 121488} |
| {"current_steps": 445, "total_steps": 1130, "loss": 0.3385, "lr": 3.803117283440044e-05, "epoch": 3.938053097345133, "percentage": 39.38, "elapsed_time": "0:01:00", "remaining_time": "0:01:33", "throughput": 2029.35, "total_tokens": 122816} |
| {"current_steps": 450, "total_steps": 1130, "loss": 0.0398, "lr": 3.7700101894267615e-05, "epoch": 3.982300884955752, "percentage": 39.82, "elapsed_time": "0:01:00", "remaining_time": "0:01:32", "throughput": 2039.12, "total_tokens": 124352} |
| {"current_steps": 455, "total_steps": 1130, "loss": 0.4213, "lr": 3.736600127650817e-05, "epoch": 4.0265486725663715, "percentage": 40.27, "elapsed_time": "0:01:01", "remaining_time": "0:01:31", "throughput": 2034.13, "total_tokens": 125432} |
| {"current_steps": 456, "total_steps": 1130, "eval_loss": 0.1032278910279274, "epoch": 4.035398230088496, "percentage": 40.35, "elapsed_time": "0:01:02", "remaining_time": "0:01:32", "throughput": 2010.15, "total_tokens": 125688} |
| {"current_steps": 460, "total_steps": 1130, "loss": 0.0458, "lr": 3.702895068262177e-05, "epoch": 4.070796460176991, "percentage": 40.71, "elapsed_time": "0:01:04", "remaining_time": "0:01:33", "throughput": 1969.58, "total_tokens": 126744} |
| {"current_steps": 465, "total_steps": 1130, "loss": 0.0737, "lr": 3.66890305178407e-05, "epoch": 4.115044247787611, "percentage": 41.15, "elapsed_time": "0:01:04", "remaining_time": "0:01:32", "throughput": 1979.84, "total_tokens": 128424} |
| {"current_steps": 470, "total_steps": 1130, "loss": 0.1408, "lr": 3.63463218719489e-05, "epoch": 4.15929203539823, "percentage": 41.59, "elapsed_time": "0:01:05", "remaining_time": "0:01:31", "throughput": 1985.47, "total_tokens": 129640} |
| {"current_steps": 475, "total_steps": 1130, "loss": 0.1903, "lr": 3.600090649993741e-05, "epoch": 4.20353982300885, "percentage": 42.04, "elapsed_time": "0:01:05", "remaining_time": "0:01:30", "throughput": 1993.09, "total_tokens": 131016} |
| {"current_steps": 480, "total_steps": 1130, "loss": 0.0682, "lr": 3.565286680250138e-05, "epoch": 4.247787610619469, "percentage": 42.48, "elapsed_time": "0:01:06", "remaining_time": "0:01:29", "throughput": 2002.0, "total_tokens": 132552} |
| {"current_steps": 485, "total_steps": 1130, "loss": 0.2208, "lr": 3.530228580638291e-05, "epoch": 4.292035398230088, "percentage": 42.92, "elapsed_time": "0:01:06", "remaining_time": "0:01:28", "throughput": 2005.52, "total_tokens": 133624} |
| {"current_steps": 490, "total_steps": 1130, "loss": 0.0085, "lr": 3.494924714456454e-05, "epoch": 4.336283185840708, "percentage": 43.36, "elapsed_time": "0:01:07", "remaining_time": "0:01:27", "throughput": 2017.46, "total_tokens": 135464} |
| {"current_steps": 495, "total_steps": 1130, "loss": 0.1116, "lr": 3.459383503631823e-05, "epoch": 4.380530973451328, "percentage": 43.81, "elapsed_time": "0:01:07", "remaining_time": "0:01:26", "throughput": 2022.47, "total_tokens": 136664} |
| {"current_steps": 500, "total_steps": 1130, "loss": 0.4935, "lr": 3.423613426711431e-05, "epoch": 4.424778761061947, "percentage": 44.25, "elapsed_time": "0:01:07", "remaining_time": "0:01:25", "throughput": 2025.91, "total_tokens": 137752} |
| {"current_steps": 505, "total_steps": 1130, "loss": 0.0561, "lr": 3.3876230168395525e-05, "epoch": 4.469026548672566, "percentage": 44.69, "elapsed_time": "0:01:08", "remaining_time": "0:01:24", "throughput": 2031.47, "total_tokens": 139000} |
| {"current_steps": 510, "total_steps": 1130, "loss": 0.0041, "lr": 3.3514208597220705e-05, "epoch": 4.513274336283186, "percentage": 45.13, "elapsed_time": "0:01:08", "remaining_time": "0:01:23", "throughput": 2036.24, "total_tokens": 140184} |
| {"current_steps": 513, "total_steps": 1130, "eval_loss": 0.10921850800514221, "epoch": 4.539823008849558, "percentage": 45.4, "elapsed_time": "0:01:09", "remaining_time": "0:01:24", "throughput": 2017.44, "total_tokens": 141000} |
| {"current_steps": 515, "total_steps": 1130, "loss": 0.129, "lr": 3.315015591578314e-05, "epoch": 4.557522123893805, "percentage": 45.58, "elapsed_time": "0:01:11", "remaining_time": "0:01:25", "throughput": 1982.13, "total_tokens": 141512} |
| {"current_steps": 520, "total_steps": 1130, "loss": 0.2731, "lr": 3.278415897080839e-05, "epoch": 4.601769911504425, "percentage": 46.02, "elapsed_time": "0:01:11", "remaining_time": "0:01:24", "throughput": 1988.23, "total_tokens": 142888} |
| {"current_steps": 525, "total_steps": 1130, "loss": 0.1353, "lr": 3.2416305072836557e-05, "epoch": 4.646017699115045, "percentage": 46.46, "elapsed_time": "0:01:12", "remaining_time": "0:01:23", "throughput": 1995.5, "total_tokens": 144312} |
| {"current_steps": 530, "total_steps": 1130, "loss": 0.3391, "lr": 3.204668197539385e-05, "epoch": 4.6902654867256635, "percentage": 46.9, "elapsed_time": "0:01:12", "remaining_time": "0:01:22", "throughput": 2004.77, "total_tokens": 146008} |
| {"current_steps": 535, "total_steps": 1130, "loss": 0.3179, "lr": 3.167537785405854e-05, "epoch": 4.734513274336283, "percentage": 47.35, "elapsed_time": "0:01:13", "remaining_time": "0:01:21", "throughput": 2011.35, "total_tokens": 147448} |
| {"current_steps": 540, "total_steps": 1130, "loss": 0.0135, "lr": 3.13024812854262e-05, "epoch": 4.778761061946903, "percentage": 47.79, "elapsed_time": "0:01:13", "remaining_time": "0:01:20", "throughput": 2018.93, "total_tokens": 148952} |
| {"current_steps": 545, "total_steps": 1130, "loss": 0.1094, "lr": 3.092808122597924e-05, "epoch": 4.823008849557522, "percentage": 48.23, "elapsed_time": "0:01:14", "remaining_time": "0:01:19", "throughput": 2026.55, "total_tokens": 150472} |
| {"current_steps": 550, "total_steps": 1130, "loss": 0.8798, "lr": 3.0552266990865934e-05, "epoch": 4.867256637168142, "percentage": 48.67, "elapsed_time": "0:01:14", "remaining_time": "0:01:18", "throughput": 2032.95, "total_tokens": 151880} |
| {"current_steps": 555, "total_steps": 1130, "loss": 0.1146, "lr": 3.017512823259373e-05, "epoch": 4.911504424778761, "percentage": 49.12, "elapsed_time": "0:01:15", "remaining_time": "0:01:17", "throughput": 2040.15, "total_tokens": 153336} |
| {"current_steps": 560, "total_steps": 1130, "loss": 0.0376, "lr": 2.9796754919642228e-05, "epoch": 4.95575221238938, "percentage": 49.56, "elapsed_time": "0:01:15", "remaining_time": "0:01:16", "throughput": 2045.13, "total_tokens": 154584} |
| {"current_steps": 565, "total_steps": 1130, "loss": 0.1895, "lr": 2.941723731500068e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:01:16", "remaining_time": "0:01:16", "throughput": 2045.56, "total_tokens": 155672} |
| {"current_steps": 570, "total_steps": 1130, "loss": 0.2002, "lr": 2.9036665954635266e-05, "epoch": 5.04424778761062, "percentage": 50.44, "elapsed_time": "0:01:16", "remaining_time": "0:01:15", "throughput": 2046.09, "total_tokens": 156920} |
| {"current_steps": 570, "total_steps": 1130, "eval_loss": 0.1037435531616211, "epoch": 5.04424778761062, "percentage": 50.44, "elapsed_time": "0:01:17", "remaining_time": "0:01:16", "throughput": 2025.59, "total_tokens": 156920} |
| {"current_steps": 575, "total_steps": 1130, "loss": 0.0115, "lr": 2.8655131625891274e-05, "epoch": 5.088495575221239, "percentage": 50.88, "elapsed_time": "0:01:19", "remaining_time": "0:01:16", "throughput": 2000.12, "total_tokens": 158872} |
| {"current_steps": 580, "total_steps": 1130, "loss": 0.002, "lr": 2.8272725345835278e-05, "epoch": 5.132743362831858, "percentage": 51.33, "elapsed_time": "0:01:19", "remaining_time": "0:01:15", "throughput": 2003.15, "total_tokens": 159960} |
| {"current_steps": 585, "total_steps": 1130, "loss": 0.0781, "lr": 2.7889538339542527e-05, "epoch": 5.176991150442478, "percentage": 51.77, "elapsed_time": "0:01:20", "remaining_time": "0:01:14", "throughput": 2006.59, "total_tokens": 161112} |
| {"current_steps": 590, "total_steps": 1130, "loss": 0.0835, "lr": 2.7505662018334698e-05, "epoch": 5.221238938053097, "percentage": 52.21, "elapsed_time": "0:01:20", "remaining_time": "0:01:13", "throughput": 2012.44, "total_tokens": 162472} |
| {"current_steps": 595, "total_steps": 1130, "loss": 0.3655, "lr": 2.712118795797329e-05, "epoch": 5.265486725663717, "percentage": 52.65, "elapsed_time": "0:01:21", "remaining_time": "0:01:13", "throughput": 2021.85, "total_tokens": 164216} |
| {"current_steps": 600, "total_steps": 1130, "loss": 0.0235, "lr": 2.6736207876813646e-05, "epoch": 5.3097345132743365, "percentage": 53.1, "elapsed_time": "0:01:21", "remaining_time": "0:01:12", "throughput": 2029.77, "total_tokens": 165832} |
| {"current_steps": 605, "total_steps": 1130, "loss": 0.0756, "lr": 2.635081361392513e-05, "epoch": 5.353982300884955, "percentage": 53.54, "elapsed_time": "0:01:22", "remaining_time": "0:01:11", "throughput": 2033.45, "total_tokens": 167000} |
| {"current_steps": 610, "total_steps": 1130, "loss": 0.0677, "lr": 2.596509710718235e-05, "epoch": 5.398230088495575, "percentage": 53.98, "elapsed_time": "0:01:22", "remaining_time": "0:01:10", "throughput": 2039.44, "total_tokens": 168456} |
| {"current_steps": 615, "total_steps": 1130, "loss": 0.002, "lr": 2.5579150371332956e-05, "epoch": 5.442477876106195, "percentage": 54.42, "elapsed_time": "0:01:23", "remaining_time": "0:01:09", "throughput": 2043.05, "total_tokens": 169624} |
| {"current_steps": 620, "total_steps": 1130, "loss": 0.0027, "lr": 2.5193065476046955e-05, "epoch": 5.486725663716814, "percentage": 54.87, "elapsed_time": "0:01:23", "remaining_time": "0:01:08", "throughput": 2047.49, "total_tokens": 170888} |
| {"current_steps": 625, "total_steps": 1130, "loss": 0.0287, "lr": 2.480693452395305e-05, "epoch": 5.530973451327434, "percentage": 55.31, "elapsed_time": "0:01:23", "remaining_time": "0:01:07", "throughput": 2050.88, "total_tokens": 172056} |
| {"current_steps": 627, "total_steps": 1130, "eval_loss": 0.08361060917377472, "epoch": 5.548672566371682, "percentage": 55.49, "elapsed_time": "0:01:24", "remaining_time": "0:01:08", "throughput": 2033.39, "total_tokens": 172504} |
| {"current_steps": 630, "total_steps": 1130, "loss": 0.2663, "lr": 2.4420849628667046e-05, "epoch": 5.575221238938053, "percentage": 55.75, "elapsed_time": "0:01:26", "remaining_time": "0:01:08", "throughput": 2001.9, "total_tokens": 173448} |
| {"current_steps": 635, "total_steps": 1130, "loss": 0.1753, "lr": 2.4034902892817648e-05, "epoch": 5.619469026548672, "percentage": 56.19, "elapsed_time": "0:01:27", "remaining_time": "0:01:07", "throughput": 2008.1, "total_tokens": 174872} |
| {"current_steps": 640, "total_steps": 1130, "loss": 0.0021, "lr": 2.3649186386074872e-05, "epoch": 5.663716814159292, "percentage": 56.64, "elapsed_time": "0:01:27", "remaining_time": "0:01:07", "throughput": 2015.45, "total_tokens": 176488} |
| {"current_steps": 645, "total_steps": 1130, "loss": 0.0118, "lr": 2.3263792123186353e-05, "epoch": 5.707964601769912, "percentage": 57.08, "elapsed_time": "0:01:28", "remaining_time": "0:01:06", "throughput": 2020.24, "total_tokens": 177816} |
| {"current_steps": 650, "total_steps": 1130, "loss": 0.0679, "lr": 2.2878812042026713e-05, "epoch": 5.752212389380531, "percentage": 57.52, "elapsed_time": "0:01:28", "remaining_time": "0:01:05", "throughput": 2026.23, "total_tokens": 179352} |
| {"current_steps": 655, "total_steps": 1130, "loss": 0.0226, "lr": 2.2494337981665304e-05, "epoch": 5.79646017699115, "percentage": 57.96, "elapsed_time": "0:01:28", "remaining_time": "0:01:04", "throughput": 2029.38, "total_tokens": 180504} |
| {"current_steps": 660, "total_steps": 1130, "loss": 0.161, "lr": 2.2110461660457482e-05, "epoch": 5.84070796460177, "percentage": 58.41, "elapsed_time": "0:01:29", "remaining_time": "0:01:03", "throughput": 2035.13, "total_tokens": 181976} |
| {"current_steps": 665, "total_steps": 1130, "loss": 0.1769, "lr": 2.1727274654164728e-05, "epoch": 5.88495575221239, "percentage": 58.85, "elapsed_time": "0:01:29", "remaining_time": "0:01:02", "throughput": 2037.03, "total_tokens": 183000} |
| {"current_steps": 670, "total_steps": 1130, "loss": 0.0023, "lr": 2.1344868374108732e-05, "epoch": 5.929203539823009, "percentage": 59.29, "elapsed_time": "0:01:30", "remaining_time": "0:01:01", "throughput": 2041.99, "total_tokens": 184344} |
| {"current_steps": 675, "total_steps": 1130, "loss": 0.0631, "lr": 2.096333404536474e-05, "epoch": 5.9734513274336285, "percentage": 59.73, "elapsed_time": "0:01:30", "remaining_time": "0:01:01", "throughput": 2049.09, "total_tokens": 185976} |
| {"current_steps": 680, "total_steps": 1130, "loss": 0.0005, "lr": 2.0582762684999327e-05, "epoch": 6.017699115044247, "percentage": 60.18, "elapsed_time": "0:01:31", "remaining_time": "0:01:00", "throughput": 2048.58, "total_tokens": 187312} |
| {"current_steps": 684, "total_steps": 1130, "eval_loss": 0.051821138709783554, "epoch": 6.053097345132743, "percentage": 60.53, "elapsed_time": "0:01:32", "remaining_time": "0:01:00", "throughput": 2033.01, "total_tokens": 188160} |
| {"current_steps": 685, "total_steps": 1130, "loss": 0.1977, "lr": 2.0203245080357775e-05, "epoch": 6.061946902654867, "percentage": 60.62, "elapsed_time": "0:01:34", "remaining_time": "0:01:01", "throughput": 2002.89, "total_tokens": 188512} |
| {"current_steps": 690, "total_steps": 1130, "loss": 0.009, "lr": 1.982487176740627e-05, "epoch": 6.106194690265487, "percentage": 61.06, "elapsed_time": "0:01:34", "remaining_time": "0:01:00", "throughput": 2005.67, "total_tokens": 189616} |
| {"current_steps": 695, "total_steps": 1130, "loss": 0.0074, "lr": 1.944773300913407e-05, "epoch": 6.150442477876107, "percentage": 61.5, "elapsed_time": "0:01:35", "remaining_time": "0:00:59", "throughput": 2013.13, "total_tokens": 191264} |
| {"current_steps": 700, "total_steps": 1130, "loss": 0.0018, "lr": 1.907191877402076e-05, "epoch": 6.1946902654867255, "percentage": 61.95, "elapsed_time": "0:01:35", "remaining_time": "0:00:58", "throughput": 2017.42, "total_tokens": 192576} |
| {"current_steps": 705, "total_steps": 1130, "loss": 0.0152, "lr": 1.8697518714573807e-05, "epoch": 6.238938053097345, "percentage": 62.39, "elapsed_time": "0:01:35", "remaining_time": "0:00:57", "throughput": 2022.05, "total_tokens": 193920} |
| {"current_steps": 710, "total_steps": 1130, "loss": 0.0014, "lr": 1.832462214594146e-05, "epoch": 6.283185840707965, "percentage": 62.83, "elapsed_time": "0:01:36", "remaining_time": "0:00:56", "throughput": 2026.29, "total_tokens": 195216} |
| {"current_steps": 715, "total_steps": 1130, "loss": 0.0015, "lr": 1.7953318024606157e-05, "epoch": 6.327433628318584, "percentage": 63.27, "elapsed_time": "0:01:36", "remaining_time": "0:00:56", "throughput": 2031.36, "total_tokens": 196640} |
| {"current_steps": 720, "total_steps": 1130, "loss": 0.0401, "lr": 1.7583694927163453e-05, "epoch": 6.371681415929204, "percentage": 63.72, "elapsed_time": "0:01:37", "remaining_time": "0:00:55", "throughput": 2033.48, "total_tokens": 197696} |
| {"current_steps": 725, "total_steps": 1130, "loss": 0.0005, "lr": 1.7215841029191616e-05, "epoch": 6.415929203539823, "percentage": 64.16, "elapsed_time": "0:01:37", "remaining_time": "0:00:54", "throughput": 2037.99, "total_tokens": 199040} |
| {"current_steps": 730, "total_steps": 1130, "loss": 0.0061, "lr": 1.6849844084216874e-05, "epoch": 6.460176991150442, "percentage": 64.6, "elapsed_time": "0:01:38", "remaining_time": "0:00:53", "throughput": 2046.43, "total_tokens": 200928} |
| {"current_steps": 735, "total_steps": 1130, "loss": 0.0004, "lr": 1.648579140277931e-05, "epoch": 6.504424778761062, "percentage": 65.04, "elapsed_time": "0:01:38", "remaining_time": "0:00:53", "throughput": 2054.59, "total_tokens": 202784} |
| {"current_steps": 740, "total_steps": 1130, "loss": 0.0071, "lr": 1.612376983160449e-05, "epoch": 6.548672566371682, "percentage": 65.49, "elapsed_time": "0:01:39", "remaining_time": "0:00:52", "throughput": 2058.39, "total_tokens": 204080} |
| {"current_steps": 741, "total_steps": 1130, "eval_loss": 0.012937678955495358, "epoch": 6.557522123893805, "percentage": 65.58, "elapsed_time": "0:01:40", "remaining_time": "0:00:52", "throughput": 2042.28, "total_tokens": 204240} |
| {"current_steps": 745, "total_steps": 1130, "loss": 0.0012, "lr": 1.576386573288569e-05, "epoch": 6.592920353982301, "percentage": 65.93, "elapsed_time": "0:01:41", "remaining_time": "0:00:52", "throughput": 2017.7, "total_tokens": 205296} |
| {"current_steps": 750, "total_steps": 1130, "loss": 0.0009, "lr": 1.5406164963681774e-05, "epoch": 6.6371681415929205, "percentage": 66.37, "elapsed_time": "0:01:42", "remaining_time": "0:00:51", "throughput": 2022.75, "total_tokens": 206768} |
| {"current_steps": 755, "total_steps": 1130, "loss": 0.0011, "lr": 1.5050752855435457e-05, "epoch": 6.68141592920354, "percentage": 66.81, "elapsed_time": "0:01:42", "remaining_time": "0:00:50", "throughput": 2026.57, "total_tokens": 208048} |
| {"current_steps": 760, "total_steps": 1130, "loss": 0.0132, "lr": 1.4697714193617097e-05, "epoch": 6.725663716814159, "percentage": 67.26, "elapsed_time": "0:01:43", "remaining_time": "0:00:50", "throughput": 2029.3, "total_tokens": 209200} |
| {"current_steps": 765, "total_steps": 1130, "loss": 0.0015, "lr": 1.4347133197498619e-05, "epoch": 6.769911504424779, "percentage": 67.7, "elapsed_time": "0:01:43", "remaining_time": "0:00:49", "throughput": 2032.43, "total_tokens": 210448} |
| {"current_steps": 770, "total_steps": 1130, "loss": 0.2387, "lr": 1.3999093500062587e-05, "epoch": 6.814159292035399, "percentage": 68.14, "elapsed_time": "0:01:44", "remaining_time": "0:00:48", "throughput": 2037.95, "total_tokens": 211984} |
| {"current_steps": 775, "total_steps": 1130, "loss": 0.0007, "lr": 1.3653678128051106e-05, "epoch": 6.8584070796460175, "percentage": 68.58, "elapsed_time": "0:01:44", "remaining_time": "0:00:47", "throughput": 2042.31, "total_tokens": 213328} |
| {"current_steps": 780, "total_steps": 1130, "loss": 0.0646, "lr": 1.3310969482159297e-05, "epoch": 6.902654867256637, "percentage": 69.03, "elapsed_time": "0:01:44", "remaining_time": "0:00:47", "throughput": 2044.15, "total_tokens": 214400} |
| {"current_steps": 785, "total_steps": 1130, "loss": 0.0005, "lr": 1.2971049317378237e-05, "epoch": 6.946902654867257, "percentage": 69.47, "elapsed_time": "0:01:45", "remaining_time": "0:00:46", "throughput": 2049.14, "total_tokens": 215888} |
| {"current_steps": 790, "total_steps": 1130, "loss": 0.003, "lr": 1.263399872349183e-05, "epoch": 6.991150442477876, "percentage": 69.91, "elapsed_time": "0:01:45", "remaining_time": "0:00:45", "throughput": 2056.03, "total_tokens": 217664} |
| {"current_steps": 795, "total_steps": 1130, "loss": 0.0039, "lr": 1.2299898105732385e-05, "epoch": 7.035398230088496, "percentage": 70.35, "elapsed_time": "0:01:46", "remaining_time": "0:00:44", "throughput": 2053.95, "total_tokens": 218840} |
| {"current_steps": 798, "total_steps": 1130, "eval_loss": 0.022299928590655327, "epoch": 7.061946902654867, "percentage": 70.62, "elapsed_time": "0:01:47", "remaining_time": "0:00:44", "throughput": 2040.52, "total_tokens": 219512} |
| {"current_steps": 800, "total_steps": 1130, "loss": 0.0007, "lr": 1.1968827165599564e-05, "epoch": 7.079646017699115, "percentage": 70.8, "elapsed_time": "0:01:49", "remaining_time": "0:00:45", "throughput": 2002.4, "total_tokens": 219992} |
| {"current_steps": 805, "total_steps": 1130, "loss": 0.0011, "lr": 1.1640864881847105e-05, "epoch": 7.123893805309734, "percentage": 71.24, "elapsed_time": "0:01:50", "remaining_time": "0:00:44", "throughput": 2004.75, "total_tokens": 221160} |
| {"current_steps": 810, "total_steps": 1130, "loss": 0.0003, "lr": 1.1316089491642076e-05, "epoch": 7.168141592920354, "percentage": 71.68, "elapsed_time": "0:01:50", "remaining_time": "0:00:43", "throughput": 2009.63, "total_tokens": 222696} |
| {"current_steps": 815, "total_steps": 1130, "loss": 0.0002, "lr": 1.099457847190091e-05, "epoch": 7.212389380530974, "percentage": 72.12, "elapsed_time": "0:01:51", "remaining_time": "0:00:43", "throughput": 2013.93, "total_tokens": 224088} |
| {"current_steps": 820, "total_steps": 1130, "loss": 0.0605, "lr": 1.067640852080693e-05, "epoch": 7.256637168141593, "percentage": 72.57, "elapsed_time": "0:01:51", "remaining_time": "0:00:42", "throughput": 2017.95, "total_tokens": 225432} |
| {"current_steps": 825, "total_steps": 1130, "loss": 0.0002, "lr": 1.0361655539513565e-05, "epoch": 7.300884955752212, "percentage": 73.01, "elapsed_time": "0:01:52", "remaining_time": "0:00:41", "throughput": 2021.04, "total_tokens": 226696} |
| {"current_steps": 830, "total_steps": 1130, "loss": 0.001, "lr": 1.0050394614037687e-05, "epoch": 7.345132743362832, "percentage": 73.45, "elapsed_time": "0:01:52", "remaining_time": "0:00:40", "throughput": 2026.05, "total_tokens": 228168} |
| {"current_steps": 835, "total_steps": 1130, "loss": 0.0009, "lr": 9.742699997347498e-06, "epoch": 7.389380530973451, "percentage": 73.89, "elapsed_time": "0:01:53", "remaining_time": "0:00:39", "throughput": 2030.18, "total_tokens": 229528} |
| {"current_steps": 840, "total_steps": 1130, "loss": 0.0002, "lr": 9.438645091649029e-06, "epoch": 7.433628318584071, "percentage": 74.34, "elapsed_time": "0:01:53", "remaining_time": "0:00:39", "throughput": 2035.91, "total_tokens": 231208} |
| {"current_steps": 845, "total_steps": 1130, "loss": 0.0004, "lr": 9.138302430875695e-06, "epoch": 7.477876106194691, "percentage": 74.78, "elapsed_time": "0:01:53", "remaining_time": "0:00:38", "throughput": 2038.64, "total_tokens": 232392} |
| {"current_steps": 850, "total_steps": 1130, "loss": 0.0004, "lr": 8.841743663384913e-06, "epoch": 7.522123893805309, "percentage": 75.22, "elapsed_time": "0:01:54", "remaining_time": "0:00:37", "throughput": 2040.6, "total_tokens": 233480} |
| {"current_steps": 855, "total_steps": 1130, "loss": 0.0002, "lr": 8.549039534865979e-06, "epoch": 7.566371681415929, "percentage": 75.66, "elapsed_time": "0:01:54", "remaining_time": "0:00:36", "throughput": 2047.28, "total_tokens": 235256} |
| {"current_steps": 855, "total_steps": 1130, "eval_loss": 0.021708844229578972, "epoch": 7.566371681415929, "percentage": 75.66, "elapsed_time": "0:01:55", "remaining_time": "0:00:37", "throughput": 2033.42, "total_tokens": 235256} |
| {"current_steps": 860, "total_steps": 1130, "loss": 0.0004, "lr": 8.260259871463352e-06, "epoch": 7.610619469026549, "percentage": 76.11, "elapsed_time": "0:01:57", "remaining_time": "0:00:36", "throughput": 2014.35, "total_tokens": 236744} |
| {"current_steps": 865, "total_steps": 1130, "loss": 0.0009, "lr": 7.975473563119216e-06, "epoch": 7.654867256637168, "percentage": 76.55, "elapsed_time": "0:01:57", "remaining_time": "0:00:36", "throughput": 2016.53, "total_tokens": 237880} |
| {"current_steps": 870, "total_steps": 1130, "loss": 0.0015, "lr": 7.69474854713943e-06, "epoch": 7.699115044247788, "percentage": 76.99, "elapsed_time": "0:01:58", "remaining_time": "0:00:35", "throughput": 2022.38, "total_tokens": 239544} |
| {"current_steps": 875, "total_steps": 1130, "loss": 0.0182, "lr": 7.4181517919866914e-06, "epoch": 7.743362831858407, "percentage": 77.43, "elapsed_time": "0:01:58", "remaining_time": "0:00:34", "throughput": 2027.05, "total_tokens": 241048} |
| {"current_steps": 880, "total_steps": 1130, "loss": 0.0022, "lr": 7.1457492813049e-06, "epoch": 7.787610619469026, "percentage": 77.88, "elapsed_time": "0:01:59", "remaining_time": "0:00:33", "throughput": 2030.76, "total_tokens": 242408} |
| {"current_steps": 885, "total_steps": 1130, "loss": 0.0004, "lr": 6.877605998178344e-06, "epoch": 7.831858407079646, "percentage": 78.32, "elapsed_time": "0:01:59", "remaining_time": "0:00:33", "throughput": 2033.98, "total_tokens": 243688} |
| {"current_steps": 890, "total_steps": 1130, "loss": 0.0005, "lr": 6.613785909629686e-06, "epoch": 7.876106194690266, "percentage": 78.76, "elapsed_time": "0:02:00", "remaining_time": "0:00:32", "throughput": 2039.26, "total_tokens": 245320} |
| {"current_steps": 895, "total_steps": 1130, "loss": 0.0023, "lr": 6.354351951360268e-06, "epoch": 7.920353982300885, "percentage": 79.2, "elapsed_time": "0:02:00", "remaining_time": "0:00:31", "throughput": 2041.99, "total_tokens": 246584} |
| {"current_steps": 900, "total_steps": 1130, "loss": 0.0005, "lr": 6.099366012736438e-06, "epoch": 7.964601769911504, "percentage": 79.65, "elapsed_time": "0:02:01", "remaining_time": "0:00:30", "throughput": 2046.36, "total_tokens": 248024} |
| {"current_steps": 905, "total_steps": 1130, "loss": 0.0005, "lr": 5.848888922025553e-06, "epoch": 8.008849557522124, "percentage": 80.09, "elapsed_time": "0:02:01", "remaining_time": "0:00:30", "throughput": 2043.62, "total_tokens": 249024} |
| {"current_steps": 910, "total_steps": 1130, "loss": 0.0007, "lr": 5.602980431885024e-06, "epoch": 8.053097345132743, "percentage": 80.53, "elapsed_time": "0:02:02", "remaining_time": "0:00:29", "throughput": 2048.88, "total_tokens": 250672} |
| {"current_steps": 912, "total_steps": 1130, "eval_loss": 0.013118009082973003, "epoch": 8.070796460176991, "percentage": 80.71, "elapsed_time": "0:02:03", "remaining_time": "0:00:29", "throughput": 2038.43, "total_tokens": 251392} |
| {"current_steps": 915, "total_steps": 1130, "loss": 0.0002, "lr": 5.361699205108042e-06, "epoch": 8.097345132743364, "percentage": 80.97, "elapsed_time": "0:02:05", "remaining_time": "0:00:29", "throughput": 2017.84, "total_tokens": 252368} |
| {"current_steps": 920, "total_steps": 1130, "loss": 0.0003, "lr": 5.125102800629203e-06, "epoch": 8.141592920353983, "percentage": 81.42, "elapsed_time": "0:02:05", "remaining_time": "0:00:28", "throughput": 2022.47, "total_tokens": 253920} |
| {"current_steps": 925, "total_steps": 1130, "loss": 0.0004, "lr": 4.893247659793568e-06, "epoch": 8.185840707964601, "percentage": 81.86, "elapsed_time": "0:02:05", "remaining_time": "0:00:27", "throughput": 2025.94, "total_tokens": 255248} |
| {"current_steps": 930, "total_steps": 1130, "loss": 0.0005, "lr": 4.666189092892245e-06, "epoch": 8.230088495575222, "percentage": 82.3, "elapsed_time": "0:02:06", "remaining_time": "0:00:27", "throughput": 2027.8, "total_tokens": 256336} |
| {"current_steps": 935, "total_steps": 1130, "loss": 0.0004, "lr": 4.443981265967806e-06, "epoch": 8.274336283185841, "percentage": 82.74, "elapsed_time": "0:02:06", "remaining_time": "0:00:26", "throughput": 2030.75, "total_tokens": 257648} |
| {"current_steps": 940, "total_steps": 1130, "loss": 0.0003, "lr": 4.226677187892739e-06, "epoch": 8.31858407079646, "percentage": 83.19, "elapsed_time": "0:02:07", "remaining_time": "0:00:25", "throughput": 2032.77, "total_tokens": 258752} |
| {"current_steps": 945, "total_steps": 1130, "loss": 0.0005, "lr": 4.014328697723835e-06, "epoch": 8.36283185840708, "percentage": 83.63, "elapsed_time": "0:02:07", "remaining_time": "0:00:25", "throughput": 2036.57, "total_tokens": 260144} |
| {"current_steps": 950, "total_steps": 1130, "loss": 0.0003, "lr": 3.806986452335748e-06, "epoch": 8.4070796460177, "percentage": 84.07, "elapsed_time": "0:02:08", "remaining_time": "0:00:24", "throughput": 2039.02, "total_tokens": 261328} |
| {"current_steps": 955, "total_steps": 1130, "loss": 0.0002, "lr": 3.604699914336515e-06, "epoch": 8.451327433628318, "percentage": 84.51, "elapsed_time": "0:02:08", "remaining_time": "0:00:23", "throughput": 2043.23, "total_tokens": 262784} |
| {"current_steps": 960, "total_steps": 1130, "loss": 0.0007, "lr": 3.4075173402679574e-06, "epoch": 8.495575221238939, "percentage": 84.96, "elapsed_time": "0:02:09", "remaining_time": "0:00:22", "throughput": 2048.46, "total_tokens": 264448} |
| {"current_steps": 965, "total_steps": 1130, "loss": 0.0022, "lr": 3.215485769093862e-06, "epoch": 8.539823008849558, "percentage": 85.4, "elapsed_time": "0:02:09", "remaining_time": "0:00:22", "throughput": 2052.38, "total_tokens": 265920} |
| {"current_steps": 969, "total_steps": 1130, "eval_loss": 0.014585654251277447, "epoch": 8.575221238938052, "percentage": 85.75, "elapsed_time": "0:02:10", "remaining_time": "0:00:21", "throughput": 2041.38, "total_tokens": 266784} |
| {"current_steps": 970, "total_steps": 1130, "loss": 0.0003, "lr": 3.028651010978556e-06, "epoch": 8.584070796460177, "percentage": 85.84, "elapsed_time": "0:02:12", "remaining_time": "0:00:21", "throughput": 2020.18, "total_tokens": 266992} |
| {"current_steps": 975, "total_steps": 1130, "loss": 0.0003, "lr": 2.8470576363586633e-06, "epoch": 8.628318584070797, "percentage": 86.28, "elapsed_time": "0:02:12", "remaining_time": "0:00:21", "throughput": 2025.38, "total_tokens": 268688} |
| {"current_steps": 980, "total_steps": 1130, "loss": 0.0001, "lr": 2.67074896531056e-06, "epoch": 8.672566371681416, "percentage": 86.73, "elapsed_time": "0:02:13", "remaining_time": "0:00:20", "throughput": 2028.38, "total_tokens": 270000} |
| {"current_steps": 985, "total_steps": 1130, "loss": 0.0004, "lr": 2.499767057216193e-06, "epoch": 8.716814159292035, "percentage": 87.17, "elapsed_time": "0:02:13", "remaining_time": "0:00:19", "throughput": 2029.88, "total_tokens": 271056} |
| {"current_steps": 990, "total_steps": 1130, "loss": 0.0005, "lr": 2.334152700729511e-06, "epoch": 8.761061946902656, "percentage": 87.61, "elapsed_time": "0:02:14", "remaining_time": "0:00:18", "throughput": 2034.17, "total_tokens": 272608} |
| {"current_steps": 995, "total_steps": 1130, "loss": 0.0004, "lr": 2.1739454040461794e-06, "epoch": 8.805309734513274, "percentage": 88.05, "elapsed_time": "0:02:14", "remaining_time": "0:00:18", "throughput": 2037.85, "total_tokens": 274000} |
| {"current_steps": 1000, "total_steps": 1130, "loss": 0.0005, "lr": 2.019183385478654e-06, "epoch": 8.849557522123893, "percentage": 88.5, "elapsed_time": "0:02:14", "remaining_time": "0:00:17", "throughput": 2040.19, "total_tokens": 275200} |
| {"current_steps": 1005, "total_steps": 1130, "loss": 0.0031, "lr": 1.8699035643389928e-06, "epoch": 8.893805309734514, "percentage": 88.94, "elapsed_time": "0:02:15", "remaining_time": "0:00:16", "throughput": 2042.02, "total_tokens": 276352} |
| {"current_steps": 1010, "total_steps": 1130, "loss": 0.0003, "lr": 1.7261415521315798e-06, "epoch": 8.938053097345133, "percentage": 89.38, "elapsed_time": "0:02:15", "remaining_time": "0:00:16", "throughput": 2046.29, "total_tokens": 277952} |
| {"current_steps": 1015, "total_steps": 1130, "loss": 0.0002, "lr": 1.587931644057783e-06, "epoch": 8.982300884955752, "percentage": 89.82, "elapsed_time": "0:02:16", "remaining_time": "0:00:15", "throughput": 2049.76, "total_tokens": 279328} |
| {"current_steps": 1020, "total_steps": 1130, "loss": 0.0004, "lr": 1.455306810834678e-06, "epoch": 9.026548672566372, "percentage": 90.27, "elapsed_time": "0:02:16", "remaining_time": "0:00:14", "throughput": 2048.03, "total_tokens": 280456} |
| {"current_steps": 1025, "total_steps": 1130, "loss": 0.0002, "lr": 1.3282986908296713e-06, "epoch": 9.070796460176991, "percentage": 90.71, "elapsed_time": "0:02:17", "remaining_time": "0:00:14", "throughput": 2050.77, "total_tokens": 281752} |
| {"current_steps": 1026, "total_steps": 1130, "eval_loss": 0.015441279858350754, "epoch": 9.079646017699115, "percentage": 90.8, "elapsed_time": "0:02:18", "remaining_time": "0:00:14", "throughput": 2039.6, "total_tokens": 281976} |
| {"current_steps": 1030, "total_steps": 1130, "loss": 0.0004, "lr": 1.2069375825130292e-06, "epoch": 9.11504424778761, "percentage": 91.15, "elapsed_time": "0:02:20", "remaining_time": "0:00:13", "throughput": 2021.91, "total_tokens": 283464} |
| {"current_steps": 1035, "total_steps": 1130, "loss": 0.0006, "lr": 1.091252437230003e-06, "epoch": 9.15929203539823, "percentage": 91.59, "elapsed_time": "0:02:20", "remaining_time": "0:00:12", "throughput": 2024.86, "total_tokens": 284760} |
| {"current_steps": 1040, "total_steps": 1130, "loss": 0.0004, "lr": 9.812708522943164e-07, "epoch": 9.20353982300885, "percentage": 92.04, "elapsed_time": "0:02:21", "remaining_time": "0:00:12", "throughput": 2028.07, "total_tokens": 286104} |
| {"current_steps": 1045, "total_steps": 1130, "loss": 0.0002, "lr": 8.770190644047077e-07, "epoch": 9.247787610619469, "percentage": 92.48, "elapsed_time": "0:02:21", "remaining_time": "0:00:11", "throughput": 2031.92, "total_tokens": 287672} |
| {"current_steps": 1050, "total_steps": 1130, "loss": 0.0007, "lr": 7.785219433859847e-07, "epoch": 9.29203539823009, "percentage": 92.92, "elapsed_time": "0:02:22", "remaining_time": "0:00:10", "throughput": 2034.43, "total_tokens": 288920} |
| {"current_steps": 1055, "total_steps": 1130, "loss": 0.0001, "lr": 6.858029862562343e-07, "epoch": 9.336283185840708, "percentage": 93.36, "elapsed_time": "0:02:22", "remaining_time": "0:00:10", "throughput": 2035.67, "total_tokens": 289960} |
| {"current_steps": 1060, "total_steps": 1130, "loss": 0.0003, "lr": 5.988843116214616e-07, "epoch": 9.380530973451327, "percentage": 93.81, "elapsed_time": "0:02:22", "remaining_time": "0:00:09", "throughput": 2039.98, "total_tokens": 291544} |
| {"current_steps": 1065, "total_steps": 1130, "loss": 0.0004, "lr": 5.177866543990689e-07, "epoch": 9.424778761061948, "percentage": 94.25, "elapsed_time": "0:02:23", "remaining_time": "0:00:08", "throughput": 2042.49, "total_tokens": 292808} |
| {"current_steps": 1070, "total_steps": 1130, "loss": 0.0004, "lr": 4.425293608714548e-07, "epoch": 9.469026548672566, "percentage": 94.69, "elapsed_time": "0:02:23", "remaining_time": "0:00:08", "throughput": 2044.14, "total_tokens": 293912} |
| {"current_steps": 1075, "total_steps": 1130, "loss": 0.0023, "lr": 3.7313038407083003e-07, "epoch": 9.513274336283185, "percentage": 95.13, "elapsed_time": "0:02:24", "remaining_time": "0:00:07", "throughput": 2047.84, "total_tokens": 295416} |
| {"current_steps": 1080, "total_steps": 1130, "loss": 0.0006, "lr": 3.0960627949644107e-07, "epoch": 9.557522123893806, "percentage": 95.58, "elapsed_time": "0:02:24", "remaining_time": "0:00:06", "throughput": 2051.79, "total_tokens": 297016} |
| {"current_steps": 1083, "total_steps": 1130, "eval_loss": 0.016118336468935013, "epoch": 9.584070796460177, "percentage": 95.84, "elapsed_time": "0:02:25", "remaining_time": "0:00:06", "throughput": 2041.84, "total_tokens": 297688} |
| {"current_steps": 1085, "total_steps": 1130, "loss": 0.0002, "lr": 2.5197220116515987e-07, "epoch": 9.601769911504425, "percentage": 96.02, "elapsed_time": "0:02:27", "remaining_time": "0:00:06", "throughput": 2023.63, "total_tokens": 298168} |
| {"current_steps": 1090, "total_steps": 1130, "loss": 0.0002, "lr": 2.0024189799641435e-07, "epoch": 9.646017699115044, "percentage": 96.46, "elapsed_time": "0:02:27", "remaining_time": "0:00:05", "throughput": 2027.62, "total_tokens": 299672} |
| {"current_steps": 1095, "total_steps": 1130, "loss": 0.0002, "lr": 1.5442771053230665e-07, "epoch": 9.690265486725664, "percentage": 96.9, "elapsed_time": "0:02:28", "remaining_time": "0:00:04", "throughput": 2030.87, "total_tokens": 301080} |
| {"current_steps": 1100, "total_steps": 1130, "loss": 0.0008, "lr": 1.1454056799370672e-07, "epoch": 9.734513274336283, "percentage": 97.35, "elapsed_time": "0:02:28", "remaining_time": "0:00:04", "throughput": 2034.05, "total_tokens": 302472} |
| {"current_steps": 1105, "total_steps": 1130, "loss": 0.0004, "lr": 8.058998567304633e-08, "epoch": 9.778761061946902, "percentage": 97.79, "elapsed_time": "0:02:29", "remaining_time": "0:00:03", "throughput": 2035.86, "total_tokens": 303592} |
| {"current_steps": 1110, "total_steps": 1130, "loss": 0.0002, "lr": 5.2584062664368105e-08, "epoch": 9.823008849557523, "percentage": 98.23, "elapsed_time": "0:02:29", "remaining_time": "0:00:02", "throughput": 2040.15, "total_tokens": 305224} |
| {"current_steps": 1115, "total_steps": 1130, "loss": 0.0003, "lr": 3.0529479931265535e-08, "epoch": 9.867256637168142, "percentage": 98.67, "elapsed_time": "0:02:30", "remaining_time": "0:00:02", "throughput": 2040.88, "total_tokens": 306200} |
| {"current_steps": 1120, "total_steps": 1130, "loss": 0.0004, "lr": 1.443149871309113e-08, "epoch": 9.91150442477876, "percentage": 99.12, "elapsed_time": "0:02:30", "remaining_time": "0:00:01", "throughput": 2045.38, "total_tokens": 307880} |
| {"current_steps": 1125, "total_steps": 1130, "loss": 0.0002, "lr": 4.293959269863201e-09, "epoch": 9.955752212389381, "percentage": 99.56, "elapsed_time": "0:02:30", "remaining_time": "0:00:00", "throughput": 2048.2, "total_tokens": 309240} |
| {"current_steps": 1130, "total_steps": 1130, "loss": 0.0001, "lr": 1.192799661514643e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:31", "remaining_time": "0:00:00", "throughput": 2049.4, "total_tokens": 310504} |
| {"current_steps": 1130, "total_steps": 1130, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:32", "remaining_time": "0:00:00", "throughput": 2030.09, "total_tokens": 310504} |
|
|