train_mrpc_42_1760623646 / trainer_log.jsonl
rbelanec's picture
Training in progress, step 9086
b675801 verified
{"current_steps": 5, "total_steps": 16520, "loss": 5.4417, "lr": 2.421307506053269e-06, "epoch": 0.006053268765133172, "percentage": 0.03, "elapsed_time": "0:00:01", "remaining_time": "1:17:42", "throughput": 1496.28, "total_tokens": 2112}
{"current_steps": 10, "total_steps": 16520, "loss": 3.6997, "lr": 5.447941888619855e-06, "epoch": 0.012106537530266344, "percentage": 0.06, "elapsed_time": "0:00:02", "remaining_time": "1:04:54", "throughput": 1790.61, "total_tokens": 4224}
{"current_steps": 15, "total_steps": 16520, "loss": 2.6049, "lr": 8.47457627118644e-06, "epoch": 0.018159806295399514, "percentage": 0.09, "elapsed_time": "0:00:03", "remaining_time": "1:01:21", "throughput": 1941.75, "total_tokens": 6496}
{"current_steps": 20, "total_steps": 16520, "loss": 1.428, "lr": 1.1501210653753027e-05, "epoch": 0.024213075060532687, "percentage": 0.12, "elapsed_time": "0:00:04", "remaining_time": "0:58:10", "throughput": 1996.71, "total_tokens": 8448}
{"current_steps": 25, "total_steps": 16520, "loss": 0.6101, "lr": 1.4527845036319614e-05, "epoch": 0.03026634382566586, "percentage": 0.15, "elapsed_time": "0:00:05", "remaining_time": "0:56:34", "throughput": 2027.73, "total_tokens": 10432}
{"current_steps": 30, "total_steps": 16520, "loss": 0.3564, "lr": 1.7554479418886197e-05, "epoch": 0.03631961259079903, "percentage": 0.18, "elapsed_time": "0:00:06", "remaining_time": "0:55:47", "throughput": 2049.29, "total_tokens": 12480}
{"current_steps": 35, "total_steps": 16520, "loss": 0.3669, "lr": 2.0581113801452784e-05, "epoch": 0.0423728813559322, "percentage": 0.21, "elapsed_time": "0:00:07", "remaining_time": "0:55:26", "throughput": 2061.8, "total_tokens": 14560}
{"current_steps": 40, "total_steps": 16520, "loss": 0.2869, "lr": 2.360774818401937e-05, "epoch": 0.048426150121065374, "percentage": 0.24, "elapsed_time": "0:00:08", "remaining_time": "0:55:11", "throughput": 2078.2, "total_tokens": 16704}
{"current_steps": 45, "total_steps": 16520, "loss": 0.1942, "lr": 2.6634382566585957e-05, "epoch": 0.05447941888619855, "percentage": 0.27, "elapsed_time": "0:00:09", "remaining_time": "0:55:00", "throughput": 2090.96, "total_tokens": 18848}
{"current_steps": 50, "total_steps": 16520, "loss": 0.4274, "lr": 2.9661016949152544e-05, "epoch": 0.06053268765133172, "percentage": 0.3, "elapsed_time": "0:00:09", "remaining_time": "0:54:48", "throughput": 2093.29, "total_tokens": 20896}
{"current_steps": 55, "total_steps": 16520, "loss": 0.3679, "lr": 3.268765133171913e-05, "epoch": 0.06658595641646489, "percentage": 0.33, "elapsed_time": "0:00:10", "remaining_time": "0:54:41", "throughput": 2102.13, "total_tokens": 23040}
{"current_steps": 60, "total_steps": 16520, "loss": 0.2162, "lr": 3.571428571428571e-05, "epoch": 0.07263922518159806, "percentage": 0.36, "elapsed_time": "0:00:11", "remaining_time": "0:54:34", "throughput": 2109.81, "total_tokens": 25184}
{"current_steps": 65, "total_steps": 16520, "loss": 0.1987, "lr": 3.8740920096852304e-05, "epoch": 0.07869249394673124, "percentage": 0.39, "elapsed_time": "0:00:12", "remaining_time": "0:54:18", "throughput": 2107.89, "total_tokens": 27136}
{"current_steps": 70, "total_steps": 16520, "loss": 0.3221, "lr": 4.1767554479418883e-05, "epoch": 0.0847457627118644, "percentage": 0.42, "elapsed_time": "0:00:13", "remaining_time": "0:53:58", "throughput": 2110.48, "total_tokens": 29088}
{"current_steps": 75, "total_steps": 16520, "loss": 0.582, "lr": 4.479418886198548e-05, "epoch": 0.09079903147699758, "percentage": 0.45, "elapsed_time": "0:00:14", "remaining_time": "0:53:58", "throughput": 2120.78, "total_tokens": 31328}
{"current_steps": 80, "total_steps": 16520, "loss": 0.2182, "lr": 4.782082324455206e-05, "epoch": 0.09685230024213075, "percentage": 0.48, "elapsed_time": "0:00:15", "remaining_time": "0:53:55", "throughput": 2123.73, "total_tokens": 33440}
{"current_steps": 85, "total_steps": 16520, "loss": 0.2829, "lr": 5.084745762711865e-05, "epoch": 0.10290556900726393, "percentage": 0.51, "elapsed_time": "0:00:16", "remaining_time": "0:53:44", "throughput": 2118.14, "total_tokens": 35328}
{"current_steps": 90, "total_steps": 16520, "loss": 0.2242, "lr": 5.387409200968523e-05, "epoch": 0.1089588377723971, "percentage": 0.54, "elapsed_time": "0:00:17", "remaining_time": "0:53:37", "throughput": 2120.81, "total_tokens": 37376}
{"current_steps": 95, "total_steps": 16520, "loss": 0.3255, "lr": 5.690072639225182e-05, "epoch": 0.11501210653753027, "percentage": 0.58, "elapsed_time": "0:00:18", "remaining_time": "0:53:34", "throughput": 2118.88, "total_tokens": 39392}
{"current_steps": 100, "total_steps": 16520, "loss": 0.2332, "lr": 5.99273607748184e-05, "epoch": 0.12106537530266344, "percentage": 0.61, "elapsed_time": "0:00:19", "remaining_time": "0:53:36", "throughput": 2125.59, "total_tokens": 41632}
{"current_steps": 105, "total_steps": 16520, "loss": 0.2042, "lr": 6.2953995157385e-05, "epoch": 0.1271186440677966, "percentage": 0.64, "elapsed_time": "0:00:20", "remaining_time": "0:53:33", "throughput": 2123.61, "total_tokens": 43648}
{"current_steps": 110, "total_steps": 16520, "loss": 0.3258, "lr": 6.598062953995157e-05, "epoch": 0.13317191283292978, "percentage": 0.67, "elapsed_time": "0:00:21", "remaining_time": "0:53:25", "throughput": 2121.95, "total_tokens": 45600}
{"current_steps": 115, "total_steps": 16520, "loss": 0.2531, "lr": 6.900726392251816e-05, "epoch": 0.13922518159806296, "percentage": 0.7, "elapsed_time": "0:00:22", "remaining_time": "0:53:20", "throughput": 2124.97, "total_tokens": 47680}
{"current_steps": 120, "total_steps": 16520, "loss": 0.215, "lr": 7.203389830508474e-05, "epoch": 0.14527845036319612, "percentage": 0.73, "elapsed_time": "0:00:23", "remaining_time": "0:53:18", "throughput": 2123.34, "total_tokens": 49696}
{"current_steps": 125, "total_steps": 16520, "loss": 0.2133, "lr": 7.506053268765134e-05, "epoch": 0.1513317191283293, "percentage": 0.76, "elapsed_time": "0:00:24", "remaining_time": "0:53:12", "throughput": 2121.78, "total_tokens": 51648}
{"current_steps": 130, "total_steps": 16520, "loss": 0.252, "lr": 7.808716707021792e-05, "epoch": 0.15738498789346247, "percentage": 0.79, "elapsed_time": "0:00:25", "remaining_time": "0:53:07", "throughput": 2121.31, "total_tokens": 53632}
{"current_steps": 135, "total_steps": 16520, "loss": 0.249, "lr": 8.11138014527845e-05, "epoch": 0.16343825665859565, "percentage": 0.82, "elapsed_time": "0:00:26", "remaining_time": "0:52:59", "throughput": 2122.1, "total_tokens": 55584}
{"current_steps": 140, "total_steps": 16520, "loss": 0.2098, "lr": 8.414043583535109e-05, "epoch": 0.1694915254237288, "percentage": 0.85, "elapsed_time": "0:00:27", "remaining_time": "0:52:57", "throughput": 2120.66, "total_tokens": 57600}
{"current_steps": 145, "total_steps": 16520, "loss": 0.2411, "lr": 8.716707021791768e-05, "epoch": 0.17554479418886199, "percentage": 0.88, "elapsed_time": "0:00:28", "remaining_time": "0:52:56", "throughput": 2118.5, "total_tokens": 59584}
{"current_steps": 150, "total_steps": 16520, "loss": 0.3887, "lr": 9.019370460048426e-05, "epoch": 0.18159806295399517, "percentage": 0.91, "elapsed_time": "0:00:29", "remaining_time": "0:52:55", "throughput": 2119.26, "total_tokens": 61664}
{"current_steps": 155, "total_steps": 16520, "loss": 0.2362, "lr": 9.322033898305085e-05, "epoch": 0.18765133171912832, "percentage": 0.94, "elapsed_time": "0:00:30", "remaining_time": "0:52:54", "throughput": 2118.05, "total_tokens": 63680}
{"current_steps": 160, "total_steps": 16520, "loss": 0.2147, "lr": 9.624697336561744e-05, "epoch": 0.1937046004842615, "percentage": 0.97, "elapsed_time": "0:00:31", "remaining_time": "0:52:55", "throughput": 2118.67, "total_tokens": 65792}
{"current_steps": 165, "total_steps": 16520, "loss": 0.2505, "lr": 9.927360774818402e-05, "epoch": 0.19975786924939468, "percentage": 1.0, "elapsed_time": "0:00:32", "remaining_time": "0:52:54", "throughput": 2120.93, "total_tokens": 67936}
{"current_steps": 170, "total_steps": 16520, "loss": 0.2819, "lr": 0.00010230024213075061, "epoch": 0.20581113801452786, "percentage": 1.03, "elapsed_time": "0:00:32", "remaining_time": "0:52:53", "throughput": 2120.81, "total_tokens": 69984}
{"current_steps": 175, "total_steps": 16520, "loss": 0.2583, "lr": 0.0001053268765133172, "epoch": 0.211864406779661, "percentage": 1.06, "elapsed_time": "0:00:33", "remaining_time": "0:52:52", "throughput": 2119.95, "total_tokens": 72000}
{"current_steps": 180, "total_steps": 16520, "loss": 0.2419, "lr": 0.00010835351089588378, "epoch": 0.2179176755447942, "percentage": 1.09, "elapsed_time": "0:00:34", "remaining_time": "0:52:49", "throughput": 2121.08, "total_tokens": 74048}
{"current_steps": 185, "total_steps": 16520, "loss": 0.2854, "lr": 0.00011138014527845036, "epoch": 0.22397094430992737, "percentage": 1.12, "elapsed_time": "0:00:35", "remaining_time": "0:52:50", "throughput": 2123.85, "total_tokens": 76256}
{"current_steps": 190, "total_steps": 16520, "loss": 0.219, "lr": 0.00011440677966101696, "epoch": 0.23002421307506055, "percentage": 1.15, "elapsed_time": "0:00:36", "remaining_time": "0:52:46", "throughput": 2124.33, "total_tokens": 78272}
{"current_steps": 195, "total_steps": 16520, "loss": 0.1586, "lr": 0.00011743341404358354, "epoch": 0.2360774818401937, "percentage": 1.18, "elapsed_time": "0:00:37", "remaining_time": "0:52:44", "throughput": 2126.86, "total_tokens": 80384}
{"current_steps": 200, "total_steps": 16520, "loss": 0.2412, "lr": 0.00012046004842615012, "epoch": 0.24213075060532688, "percentage": 1.21, "elapsed_time": "0:00:38", "remaining_time": "0:52:43", "throughput": 2127.24, "total_tokens": 82464}
{"current_steps": 205, "total_steps": 16520, "loss": 0.3085, "lr": 0.0001234866828087167, "epoch": 0.24818401937046006, "percentage": 1.24, "elapsed_time": "0:00:39", "remaining_time": "0:52:42", "throughput": 2128.31, "total_tokens": 84576}
{"current_steps": 210, "total_steps": 16520, "loss": 0.1652, "lr": 0.00012651331719128328, "epoch": 0.2542372881355932, "percentage": 1.27, "elapsed_time": "0:00:40", "remaining_time": "0:52:41", "throughput": 2128.02, "total_tokens": 86624}
{"current_steps": 215, "total_steps": 16520, "loss": 0.3305, "lr": 0.00012953995157384988, "epoch": 0.2602905569007264, "percentage": 1.3, "elapsed_time": "0:00:41", "remaining_time": "0:52:35", "throughput": 2127.73, "total_tokens": 88544}
{"current_steps": 220, "total_steps": 16520, "loss": 0.2227, "lr": 0.00013256658595641648, "epoch": 0.26634382566585957, "percentage": 1.33, "elapsed_time": "0:00:42", "remaining_time": "0:52:35", "throughput": 2126.65, "total_tokens": 90560}
{"current_steps": 225, "total_steps": 16520, "loss": 0.238, "lr": 0.00013559322033898305, "epoch": 0.27239709443099275, "percentage": 1.36, "elapsed_time": "0:00:43", "remaining_time": "0:52:32", "throughput": 2126.88, "total_tokens": 92576}
{"current_steps": 230, "total_steps": 16520, "loss": 0.2162, "lr": 0.00013861985472154965, "epoch": 0.2784503631961259, "percentage": 1.39, "elapsed_time": "0:00:44", "remaining_time": "0:52:29", "throughput": 2127.1, "total_tokens": 94592}
{"current_steps": 235, "total_steps": 16520, "loss": 0.3768, "lr": 0.00014164648910411622, "epoch": 0.2845036319612591, "percentage": 1.42, "elapsed_time": "0:00:45", "remaining_time": "0:52:27", "throughput": 2128.77, "total_tokens": 96704}
{"current_steps": 240, "total_steps": 16520, "loss": 0.2554, "lr": 0.00014467312348668282, "epoch": 0.29055690072639223, "percentage": 1.45, "elapsed_time": "0:00:46", "remaining_time": "0:52:25", "throughput": 2129.7, "total_tokens": 98752}
{"current_steps": 245, "total_steps": 16520, "loss": 0.2073, "lr": 0.0001476997578692494, "epoch": 0.2966101694915254, "percentage": 1.48, "elapsed_time": "0:00:47", "remaining_time": "0:52:24", "throughput": 2128.21, "total_tokens": 100736}
{"current_steps": 250, "total_steps": 16520, "loss": 0.2716, "lr": 0.00015072639225181597, "epoch": 0.3026634382566586, "percentage": 1.51, "elapsed_time": "0:00:48", "remaining_time": "0:52:19", "throughput": 2129.08, "total_tokens": 102720}
{"current_steps": 255, "total_steps": 16520, "loss": 0.2154, "lr": 0.00015375302663438257, "epoch": 0.30871670702179177, "percentage": 1.54, "elapsed_time": "0:00:49", "remaining_time": "0:52:19", "throughput": 2129.35, "total_tokens": 104800}
{"current_steps": 260, "total_steps": 16520, "loss": 0.2346, "lr": 0.00015677966101694914, "epoch": 0.31476997578692495, "percentage": 1.57, "elapsed_time": "0:00:50", "remaining_time": "0:52:16", "throughput": 2127.95, "total_tokens": 106720}
{"current_steps": 265, "total_steps": 16520, "loss": 0.2084, "lr": 0.00015980629539951574, "epoch": 0.32082324455205813, "percentage": 1.6, "elapsed_time": "0:00:51", "remaining_time": "0:52:13", "throughput": 2128.23, "total_tokens": 108736}
{"current_steps": 270, "total_steps": 16520, "loss": 0.2086, "lr": 0.00016283292978208234, "epoch": 0.3268765133171913, "percentage": 1.63, "elapsed_time": "0:00:52", "remaining_time": "0:52:14", "throughput": 2129.06, "total_tokens": 110880}
{"current_steps": 275, "total_steps": 16520, "loss": 0.1754, "lr": 0.00016585956416464892, "epoch": 0.33292978208232443, "percentage": 1.66, "elapsed_time": "0:00:52", "remaining_time": "0:52:10", "throughput": 2129.82, "total_tokens": 112864}
{"current_steps": 280, "total_steps": 16520, "loss": 0.2682, "lr": 0.0001688861985472155, "epoch": 0.3389830508474576, "percentage": 1.69, "elapsed_time": "0:00:53", "remaining_time": "0:52:08", "throughput": 2130.59, "total_tokens": 114912}
{"current_steps": 285, "total_steps": 16520, "loss": 0.217, "lr": 0.0001719128329297821, "epoch": 0.3450363196125908, "percentage": 1.73, "elapsed_time": "0:00:54", "remaining_time": "0:52:05", "throughput": 2130.37, "total_tokens": 116896}
{"current_steps": 290, "total_steps": 16520, "loss": 0.2003, "lr": 0.00017493946731234866, "epoch": 0.35108958837772397, "percentage": 1.76, "elapsed_time": "0:00:55", "remaining_time": "0:52:05", "throughput": 2129.57, "total_tokens": 118912}
{"current_steps": 295, "total_steps": 16520, "loss": 0.2461, "lr": 0.00017796610169491526, "epoch": 0.35714285714285715, "percentage": 1.79, "elapsed_time": "0:00:56", "remaining_time": "0:52:05", "throughput": 2130.83, "total_tokens": 121088}
{"current_steps": 300, "total_steps": 16520, "loss": 0.1799, "lr": 0.00018099273607748184, "epoch": 0.36319612590799033, "percentage": 1.82, "elapsed_time": "0:00:57", "remaining_time": "0:52:03", "throughput": 2130.62, "total_tokens": 123072}
{"current_steps": 305, "total_steps": 16520, "loss": 0.1564, "lr": 0.00018401937046004844, "epoch": 0.3692493946731235, "percentage": 1.85, "elapsed_time": "0:00:58", "remaining_time": "0:52:01", "throughput": 2130.28, "total_tokens": 125088}
{"current_steps": 310, "total_steps": 16520, "loss": 0.2199, "lr": 0.00018704600484261504, "epoch": 0.37530266343825663, "percentage": 1.88, "elapsed_time": "0:00:59", "remaining_time": "0:51:57", "throughput": 2129.62, "total_tokens": 126976}
{"current_steps": 315, "total_steps": 16520, "loss": 0.1978, "lr": 0.0001900726392251816, "epoch": 0.3813559322033898, "percentage": 1.91, "elapsed_time": "0:01:00", "remaining_time": "0:51:57", "throughput": 2129.84, "total_tokens": 129056}
{"current_steps": 320, "total_steps": 16520, "loss": 0.247, "lr": 0.00019309927360774818, "epoch": 0.387409200968523, "percentage": 1.94, "elapsed_time": "0:01:01", "remaining_time": "0:51:56", "throughput": 2130.47, "total_tokens": 131168}
{"current_steps": 325, "total_steps": 16520, "loss": 0.21, "lr": 0.00019612590799031475, "epoch": 0.3934624697336562, "percentage": 1.97, "elapsed_time": "0:01:02", "remaining_time": "0:51:53", "throughput": 2130.25, "total_tokens": 133088}
{"current_steps": 330, "total_steps": 16520, "loss": 0.1416, "lr": 0.00019915254237288136, "epoch": 0.39951573849878935, "percentage": 2.0, "elapsed_time": "0:01:03", "remaining_time": "0:51:53", "throughput": 2132.18, "total_tokens": 135296}
{"current_steps": 335, "total_steps": 16520, "loss": 0.2237, "lr": 0.00020217917675544796, "epoch": 0.40556900726392253, "percentage": 2.03, "elapsed_time": "0:01:04", "remaining_time": "0:51:52", "throughput": 2132.27, "total_tokens": 137376}
{"current_steps": 340, "total_steps": 16520, "loss": 0.3265, "lr": 0.00020520581113801453, "epoch": 0.4116222760290557, "percentage": 2.06, "elapsed_time": "0:01:05", "remaining_time": "0:51:52", "throughput": 2133.72, "total_tokens": 139552}
{"current_steps": 345, "total_steps": 16520, "loss": 1.3241, "lr": 0.00020823244552058113, "epoch": 0.41767554479418884, "percentage": 2.09, "elapsed_time": "0:01:06", "remaining_time": "0:51:50", "throughput": 2132.61, "total_tokens": 141472}
{"current_steps": 350, "total_steps": 16520, "loss": 0.2352, "lr": 0.00021125907990314773, "epoch": 0.423728813559322, "percentage": 2.12, "elapsed_time": "0:01:07", "remaining_time": "0:51:49", "throughput": 2131.92, "total_tokens": 143488}
{"current_steps": 355, "total_steps": 16520, "loss": 0.3946, "lr": 0.00021428571428571427, "epoch": 0.4297820823244552, "percentage": 2.15, "elapsed_time": "0:01:08", "remaining_time": "0:51:49", "throughput": 2133.73, "total_tokens": 145728}
{"current_steps": 360, "total_steps": 16520, "loss": 0.1253, "lr": 0.00021731234866828087, "epoch": 0.4358353510895884, "percentage": 2.18, "elapsed_time": "0:01:09", "remaining_time": "0:51:48", "throughput": 2132.31, "total_tokens": 147680}
{"current_steps": 365, "total_steps": 16520, "loss": 0.231, "lr": 0.00022033898305084745, "epoch": 0.44188861985472155, "percentage": 2.21, "elapsed_time": "0:01:10", "remaining_time": "0:51:45", "throughput": 2132.1, "total_tokens": 149600}
{"current_steps": 370, "total_steps": 16520, "loss": 0.2617, "lr": 0.00022336561743341405, "epoch": 0.44794188861985473, "percentage": 2.24, "elapsed_time": "0:01:11", "remaining_time": "0:51:43", "throughput": 2132.32, "total_tokens": 151616}
{"current_steps": 375, "total_steps": 16520, "loss": 0.2236, "lr": 0.00022639225181598065, "epoch": 0.4539951573849879, "percentage": 2.27, "elapsed_time": "0:01:12", "remaining_time": "0:51:41", "throughput": 2131.75, "total_tokens": 153568}
{"current_steps": 380, "total_steps": 16520, "loss": 0.2038, "lr": 0.00022941888619854722, "epoch": 0.4600484261501211, "percentage": 2.3, "elapsed_time": "0:01:12", "remaining_time": "0:51:39", "throughput": 2132.66, "total_tokens": 155648}
{"current_steps": 385, "total_steps": 16520, "loss": 0.2117, "lr": 0.00023244552058111382, "epoch": 0.4661016949152542, "percentage": 2.33, "elapsed_time": "0:01:13", "remaining_time": "0:51:37", "throughput": 2132.05, "total_tokens": 157600}
{"current_steps": 390, "total_steps": 16520, "loss": 0.1818, "lr": 0.00023547215496368037, "epoch": 0.4721549636803874, "percentage": 2.36, "elapsed_time": "0:01:14", "remaining_time": "0:51:35", "throughput": 2131.09, "total_tokens": 159520}
{"current_steps": 395, "total_steps": 16520, "loss": 0.1676, "lr": 0.00023849878934624697, "epoch": 0.4782082324455206, "percentage": 2.39, "elapsed_time": "0:01:15", "remaining_time": "0:51:34", "throughput": 2131.27, "total_tokens": 161536}
{"current_steps": 400, "total_steps": 16520, "loss": 0.3178, "lr": 0.00024152542372881357, "epoch": 0.48426150121065376, "percentage": 2.42, "elapsed_time": "0:01:16", "remaining_time": "0:51:32", "throughput": 2131.4, "total_tokens": 163552}
{"current_steps": 405, "total_steps": 16520, "loss": 0.1985, "lr": 0.00024455205811138017, "epoch": 0.49031476997578693, "percentage": 2.45, "elapsed_time": "0:01:17", "remaining_time": "0:51:31", "throughput": 2131.13, "total_tokens": 165600}
{"current_steps": 410, "total_steps": 16520, "loss": 0.3253, "lr": 0.0002475786924939467, "epoch": 0.4963680387409201, "percentage": 2.48, "elapsed_time": "0:01:18", "remaining_time": "0:51:31", "throughput": 2130.99, "total_tokens": 167680}
{"current_steps": 415, "total_steps": 16520, "loss": 0.2757, "lr": 0.0002506053268765133, "epoch": 0.5024213075060533, "percentage": 2.51, "elapsed_time": "0:01:19", "remaining_time": "0:51:32", "throughput": 2132.58, "total_tokens": 169920}
{"current_steps": 420, "total_steps": 16520, "loss": 0.1768, "lr": 0.0002536319612590799, "epoch": 0.5084745762711864, "percentage": 2.54, "elapsed_time": "0:01:20", "remaining_time": "0:51:31", "throughput": 2132.02, "total_tokens": 171936}
{"current_steps": 425, "total_steps": 16520, "loss": 0.2078, "lr": 0.0002566585956416465, "epoch": 0.5145278450363197, "percentage": 2.57, "elapsed_time": "0:01:21", "remaining_time": "0:51:30", "throughput": 2132.24, "total_tokens": 173984}
{"current_steps": 430, "total_steps": 16520, "loss": 0.2023, "lr": 0.00025968523002421306, "epoch": 0.5205811138014528, "percentage": 2.6, "elapsed_time": "0:01:22", "remaining_time": "0:51:29", "throughput": 2133.07, "total_tokens": 176128}
{"current_steps": 435, "total_steps": 16520, "loss": 0.1755, "lr": 0.0002627118644067797, "epoch": 0.5266343825665859, "percentage": 2.63, "elapsed_time": "0:01:23", "remaining_time": "0:51:29", "throughput": 2133.52, "total_tokens": 178240}
{"current_steps": 440, "total_steps": 16520, "loss": 0.2801, "lr": 0.00026573849878934626, "epoch": 0.5326876513317191, "percentage": 2.66, "elapsed_time": "0:01:24", "remaining_time": "0:51:28", "throughput": 2134.17, "total_tokens": 180384}
{"current_steps": 445, "total_steps": 16520, "loss": 0.2367, "lr": 0.0002687651331719128, "epoch": 0.5387409200968523, "percentage": 2.69, "elapsed_time": "0:01:25", "remaining_time": "0:51:27", "throughput": 2133.89, "total_tokens": 182368}
{"current_steps": 450, "total_steps": 16520, "loss": 0.2463, "lr": 0.0002717917675544794, "epoch": 0.5447941888619855, "percentage": 2.72, "elapsed_time": "0:01:26", "remaining_time": "0:51:25", "throughput": 2134.32, "total_tokens": 184416}
{"current_steps": 455, "total_steps": 16520, "loss": 0.2049, "lr": 0.000274818401937046, "epoch": 0.5508474576271186, "percentage": 2.75, "elapsed_time": "0:01:27", "remaining_time": "0:51:24", "throughput": 2135.24, "total_tokens": 186528}
{"current_steps": 460, "total_steps": 16520, "loss": 4.8814, "lr": 0.0002778450363196126, "epoch": 0.5569007263922519, "percentage": 2.78, "elapsed_time": "0:01:28", "remaining_time": "0:51:22", "throughput": 2135.34, "total_tokens": 188544}
{"current_steps": 465, "total_steps": 16520, "loss": 7.897, "lr": 0.00028087167070217915, "epoch": 0.562953995157385, "percentage": 2.81, "elapsed_time": "0:01:29", "remaining_time": "0:51:21", "throughput": 2135.45, "total_tokens": 190560}
{"current_steps": 470, "total_steps": 16520, "loss": 0.1665, "lr": 0.0002838983050847458, "epoch": 0.5690072639225182, "percentage": 2.85, "elapsed_time": "0:01:30", "remaining_time": "0:51:18", "throughput": 2135.8, "total_tokens": 192544}
{"current_steps": 475, "total_steps": 16520, "loss": 0.3254, "lr": 0.00028692493946731235, "epoch": 0.5750605326876513, "percentage": 2.88, "elapsed_time": "0:01:31", "remaining_time": "0:51:17", "throughput": 2136.77, "total_tokens": 194656}
{"current_steps": 480, "total_steps": 16520, "loss": 0.3847, "lr": 0.0002899515738498789, "epoch": 0.5811138014527845, "percentage": 2.91, "elapsed_time": "0:01:32", "remaining_time": "0:51:16", "throughput": 2136.22, "total_tokens": 196672}
{"current_steps": 485, "total_steps": 16520, "loss": 0.1794, "lr": 0.00029297820823244555, "epoch": 0.5871670702179177, "percentage": 2.94, "elapsed_time": "0:01:33", "remaining_time": "0:51:15", "throughput": 2135.4, "total_tokens": 198656}
{"current_steps": 490, "total_steps": 16520, "loss": 0.2712, "lr": 0.0002960048426150121, "epoch": 0.5932203389830508, "percentage": 2.97, "elapsed_time": "0:01:33", "remaining_time": "0:51:13", "throughput": 2136.62, "total_tokens": 200736}
{"current_steps": 495, "total_steps": 16520, "loss": 0.1639, "lr": 0.0002990314769975787, "epoch": 0.5992736077481841, "percentage": 3.0, "elapsed_time": "0:01:34", "remaining_time": "0:51:11", "throughput": 2136.71, "total_tokens": 202752}
{"current_steps": 500, "total_steps": 16520, "loss": 0.232, "lr": 0.00030205811138014525, "epoch": 0.6053268765133172, "percentage": 3.03, "elapsed_time": "0:01:35", "remaining_time": "0:51:11", "throughput": 2136.17, "total_tokens": 204768}
{"current_steps": 505, "total_steps": 16520, "loss": 0.1452, "lr": 0.0003050847457627119, "epoch": 0.6113801452784504, "percentage": 3.06, "elapsed_time": "0:01:36", "remaining_time": "0:51:09", "throughput": 2136.25, "total_tokens": 206784}
{"current_steps": 510, "total_steps": 16520, "loss": 0.2376, "lr": 0.00030811138014527845, "epoch": 0.6174334140435835, "percentage": 3.09, "elapsed_time": "0:01:37", "remaining_time": "0:51:08", "throughput": 2135.78, "total_tokens": 208736}
{"current_steps": 515, "total_steps": 16520, "loss": 0.163, "lr": 0.00031113801452784505, "epoch": 0.6234866828087167, "percentage": 3.12, "elapsed_time": "0:01:38", "remaining_time": "0:51:07", "throughput": 2135.84, "total_tokens": 210816}
{"current_steps": 520, "total_steps": 16520, "loss": 0.1778, "lr": 0.00031416464891041165, "epoch": 0.6295399515738499, "percentage": 3.15, "elapsed_time": "0:01:39", "remaining_time": "0:51:06", "throughput": 2135.93, "total_tokens": 212896}
{"current_steps": 525, "total_steps": 16520, "loss": 0.2018, "lr": 0.0003171912832929782, "epoch": 0.635593220338983, "percentage": 3.18, "elapsed_time": "0:01:40", "remaining_time": "0:51:05", "throughput": 2136.55, "total_tokens": 214976}
{"current_steps": 530, "total_steps": 16520, "loss": 0.1343, "lr": 0.0003202179176755448, "epoch": 0.6416464891041163, "percentage": 3.21, "elapsed_time": "0:01:41", "remaining_time": "0:51:03", "throughput": 2137.15, "total_tokens": 216992}
{"current_steps": 535, "total_steps": 16520, "loss": 0.1804, "lr": 0.0003232445520581114, "epoch": 0.6476997578692494, "percentage": 3.24, "elapsed_time": "0:01:42", "remaining_time": "0:51:02", "throughput": 2136.11, "total_tokens": 218944}
{"current_steps": 540, "total_steps": 16520, "loss": 0.351, "lr": 0.000326271186440678, "epoch": 0.6537530266343826, "percentage": 3.27, "elapsed_time": "0:01:43", "remaining_time": "0:51:01", "throughput": 2135.66, "total_tokens": 220960}
{"current_steps": 545, "total_steps": 16520, "loss": 0.1837, "lr": 0.00032929782082324454, "epoch": 0.6598062953995157, "percentage": 3.3, "elapsed_time": "0:01:44", "remaining_time": "0:51:01", "throughput": 2135.45, "total_tokens": 223008}
{"current_steps": 550, "total_steps": 16520, "loss": 0.1771, "lr": 0.0003323244552058112, "epoch": 0.6658595641646489, "percentage": 3.33, "elapsed_time": "0:01:45", "remaining_time": "0:51:00", "throughput": 2135.51, "total_tokens": 225088}
{"current_steps": 555, "total_steps": 16520, "loss": 0.1631, "lr": 0.00033535108958837774, "epoch": 0.6719128329297821, "percentage": 3.36, "elapsed_time": "0:01:46", "remaining_time": "0:50:59", "throughput": 2135.81, "total_tokens": 227136}
{"current_steps": 560, "total_steps": 16520, "loss": 0.1583, "lr": 0.0003383777239709443, "epoch": 0.6779661016949152, "percentage": 3.39, "elapsed_time": "0:01:47", "remaining_time": "0:50:57", "throughput": 2135.38, "total_tokens": 229088}
{"current_steps": 565, "total_steps": 16520, "loss": 0.1487, "lr": 0.0003414043583535109, "epoch": 0.6840193704600485, "percentage": 3.42, "elapsed_time": "0:01:48", "remaining_time": "0:50:56", "throughput": 2135.42, "total_tokens": 231168}
{"current_steps": 570, "total_steps": 16520, "loss": 0.1537, "lr": 0.0003444309927360775, "epoch": 0.6900726392251816, "percentage": 3.45, "elapsed_time": "0:01:49", "remaining_time": "0:50:56", "throughput": 2135.54, "total_tokens": 233280}
{"current_steps": 575, "total_steps": 16520, "loss": 0.2042, "lr": 0.0003474576271186441, "epoch": 0.6961259079903148, "percentage": 3.48, "elapsed_time": "0:01:50", "remaining_time": "0:50:55", "throughput": 2135.12, "total_tokens": 235296}
{"current_steps": 580, "total_steps": 16520, "loss": 0.179, "lr": 0.00035048426150121063, "epoch": 0.7021791767554479, "percentage": 3.51, "elapsed_time": "0:01:51", "remaining_time": "0:50:54", "throughput": 2135.47, "total_tokens": 237376}
{"current_steps": 585, "total_steps": 16520, "loss": 0.1851, "lr": 0.0003535108958837773, "epoch": 0.7082324455205811, "percentage": 3.54, "elapsed_time": "0:01:52", "remaining_time": "0:50:52", "throughput": 2135.54, "total_tokens": 239328}
{"current_steps": 590, "total_steps": 16520, "loss": 0.1831, "lr": 0.00035653753026634383, "epoch": 0.7142857142857143, "percentage": 3.57, "elapsed_time": "0:01:53", "remaining_time": "0:50:51", "throughput": 2135.85, "total_tokens": 241408}
{"current_steps": 595, "total_steps": 16520, "loss": 0.1824, "lr": 0.0003595641646489104, "epoch": 0.7203389830508474, "percentage": 3.6, "elapsed_time": "0:01:54", "remaining_time": "0:50:51", "throughput": 2136.14, "total_tokens": 243520}
{"current_steps": 600, "total_steps": 16520, "loss": 0.2132, "lr": 0.00036259079903147703, "epoch": 0.7263922518159807, "percentage": 3.63, "elapsed_time": "0:01:54", "remaining_time": "0:50:49", "throughput": 2136.43, "total_tokens": 245504}
{"current_steps": 605, "total_steps": 16520, "loss": 0.0955, "lr": 0.0003656174334140436, "epoch": 0.7324455205811138, "percentage": 3.66, "elapsed_time": "0:01:55", "remaining_time": "0:50:48", "throughput": 2136.72, "total_tokens": 247616}
{"current_steps": 610, "total_steps": 16520, "loss": 0.1934, "lr": 0.0003686440677966102, "epoch": 0.738498789346247, "percentage": 3.69, "elapsed_time": "0:01:56", "remaining_time": "0:50:46", "throughput": 2136.3, "total_tokens": 249504}
{"current_steps": 615, "total_steps": 16520, "loss": 0.2009, "lr": 0.0003716707021791768, "epoch": 0.7445520581113801, "percentage": 3.72, "elapsed_time": "0:01:57", "remaining_time": "0:50:44", "throughput": 2136.34, "total_tokens": 251520}
{"current_steps": 620, "total_steps": 16520, "loss": 0.2983, "lr": 0.0003746973365617434, "epoch": 0.7506053268765133, "percentage": 3.75, "elapsed_time": "0:01:58", "remaining_time": "0:50:44", "throughput": 2137.32, "total_tokens": 253696}
{"current_steps": 625, "total_steps": 16520, "loss": 0.1194, "lr": 0.0003777239709443099, "epoch": 0.7566585956416465, "percentage": 3.78, "elapsed_time": "0:01:59", "remaining_time": "0:50:42", "throughput": 2136.45, "total_tokens": 255584}
{"current_steps": 630, "total_steps": 16520, "loss": 0.176, "lr": 0.00038075060532687647, "epoch": 0.7627118644067796, "percentage": 3.81, "elapsed_time": "0:02:00", "remaining_time": "0:50:41", "throughput": 2136.01, "total_tokens": 257600}
{"current_steps": 635, "total_steps": 16520, "loss": 0.0992, "lr": 0.0003837772397094431, "epoch": 0.7687651331719129, "percentage": 3.84, "elapsed_time": "0:02:01", "remaining_time": "0:50:39", "throughput": 2135.38, "total_tokens": 259456}
{"current_steps": 640, "total_steps": 16520, "loss": 0.2416, "lr": 0.00038680387409200967, "epoch": 0.774818401937046, "percentage": 3.87, "elapsed_time": "0:02:02", "remaining_time": "0:50:39", "throughput": 2136.32, "total_tokens": 261664}
{"current_steps": 645, "total_steps": 16520, "loss": 0.2997, "lr": 0.00038983050847457627, "epoch": 0.7808716707021792, "percentage": 3.9, "elapsed_time": "0:02:03", "remaining_time": "0:50:37", "throughput": 2136.16, "total_tokens": 263648}
{"current_steps": 650, "total_steps": 16520, "loss": 0.1547, "lr": 0.0003928571428571429, "epoch": 0.7869249394673123, "percentage": 3.93, "elapsed_time": "0:02:04", "remaining_time": "0:50:36", "throughput": 2135.7, "total_tokens": 265600}
{"current_steps": 655, "total_steps": 16520, "loss": 0.204, "lr": 0.0003958837772397095, "epoch": 0.7929782082324455, "percentage": 3.96, "elapsed_time": "0:02:05", "remaining_time": "0:50:35", "throughput": 2136.42, "total_tokens": 267712}
{"current_steps": 660, "total_steps": 16520, "loss": 0.1794, "lr": 0.000398910411622276, "epoch": 0.7990314769975787, "percentage": 4.0, "elapsed_time": "0:02:06", "remaining_time": "0:50:33", "throughput": 2136.26, "total_tokens": 269696}
{"current_steps": 665, "total_steps": 16520, "loss": 0.3065, "lr": 0.0004019370460048426, "epoch": 0.8050847457627118, "percentage": 4.03, "elapsed_time": "0:02:07", "remaining_time": "0:50:33", "throughput": 2137.35, "total_tokens": 271936}
{"current_steps": 670, "total_steps": 16520, "loss": 0.1815, "lr": 0.0004049636803874092, "epoch": 0.8111380145278451, "percentage": 4.06, "elapsed_time": "0:02:08", "remaining_time": "0:50:32", "throughput": 2137.35, "total_tokens": 274016}
{"current_steps": 675, "total_steps": 16520, "loss": 0.1426, "lr": 0.00040799031476997577, "epoch": 0.8171912832929782, "percentage": 4.09, "elapsed_time": "0:02:09", "remaining_time": "0:50:32", "throughput": 2137.81, "total_tokens": 276160}
{"current_steps": 680, "total_steps": 16520, "loss": 0.1228, "lr": 0.0004110169491525424, "epoch": 0.8232445520581114, "percentage": 4.12, "elapsed_time": "0:02:10", "remaining_time": "0:50:31", "throughput": 2138.05, "total_tokens": 278208}
{"current_steps": 685, "total_steps": 16520, "loss": 0.1385, "lr": 0.00041404358353510897, "epoch": 0.8292978208232445, "percentage": 4.15, "elapsed_time": "0:02:11", "remaining_time": "0:50:29", "throughput": 2138.27, "total_tokens": 280192}
{"current_steps": 690, "total_steps": 16520, "loss": 0.2285, "lr": 0.00041707021791767557, "epoch": 0.8353510895883777, "percentage": 4.18, "elapsed_time": "0:02:11", "remaining_time": "0:50:27", "throughput": 2138.13, "total_tokens": 282176}
{"current_steps": 695, "total_steps": 16520, "loss": 0.2555, "lr": 0.0004200968523002421, "epoch": 0.8414043583535109, "percentage": 4.21, "elapsed_time": "0:02:12", "remaining_time": "0:50:26", "throughput": 2137.94, "total_tokens": 284160}
{"current_steps": 700, "total_steps": 16520, "loss": 0.2582, "lr": 0.0004231234866828087, "epoch": 0.847457627118644, "percentage": 4.24, "elapsed_time": "0:02:13", "remaining_time": "0:50:25", "throughput": 2138.18, "total_tokens": 286208}
{"current_steps": 705, "total_steps": 16520, "loss": 0.2, "lr": 0.0004261501210653753, "epoch": 0.8535108958837773, "percentage": 4.27, "elapsed_time": "0:02:14", "remaining_time": "0:50:23", "throughput": 2138.0, "total_tokens": 288192}
{"current_steps": 710, "total_steps": 16520, "loss": 0.199, "lr": 0.00042917675544794186, "epoch": 0.8595641646489104, "percentage": 4.3, "elapsed_time": "0:02:15", "remaining_time": "0:50:23", "throughput": 2137.62, "total_tokens": 290208}
{"current_steps": 715, "total_steps": 16520, "loss": 0.2015, "lr": 0.0004322033898305085, "epoch": 0.8656174334140436, "percentage": 4.33, "elapsed_time": "0:02:16", "remaining_time": "0:50:19", "throughput": 2137.7, "total_tokens": 292032}
{"current_steps": 720, "total_steps": 16520, "loss": 0.2049, "lr": 0.00043523002421307506, "epoch": 0.8716707021791767, "percentage": 4.36, "elapsed_time": "0:02:17", "remaining_time": "0:50:18", "throughput": 2138.1, "total_tokens": 294112}
{"current_steps": 725, "total_steps": 16520, "loss": 0.1843, "lr": 0.00043825665859564166, "epoch": 0.8777239709443099, "percentage": 4.39, "elapsed_time": "0:02:18", "remaining_time": "0:50:17", "throughput": 2138.13, "total_tokens": 296128}
{"current_steps": 730, "total_steps": 16520, "loss": 0.1987, "lr": 0.00044128329297820826, "epoch": 0.8837772397094431, "percentage": 4.42, "elapsed_time": "0:02:19", "remaining_time": "0:50:16", "throughput": 2138.0, "total_tokens": 298112}
{"current_steps": 735, "total_steps": 16520, "loss": 0.1606, "lr": 0.0004443099273607748, "epoch": 0.8898305084745762, "percentage": 4.45, "elapsed_time": "0:02:20", "remaining_time": "0:50:15", "throughput": 2138.96, "total_tokens": 300352}
{"current_steps": 740, "total_steps": 16520, "loss": 0.1507, "lr": 0.0004473365617433414, "epoch": 0.8958837772397095, "percentage": 4.48, "elapsed_time": "0:02:21", "remaining_time": "0:50:15", "throughput": 2139.19, "total_tokens": 302464}
{"current_steps": 745, "total_steps": 16520, "loss": 0.1957, "lr": 0.000450363196125908, "epoch": 0.9019370460048426, "percentage": 4.51, "elapsed_time": "0:02:22", "remaining_time": "0:50:13", "throughput": 2139.04, "total_tokens": 304448}
{"current_steps": 750, "total_steps": 16520, "loss": 0.2272, "lr": 0.0004533898305084746, "epoch": 0.9079903147699758, "percentage": 4.54, "elapsed_time": "0:02:23", "remaining_time": "0:50:12", "throughput": 2138.5, "total_tokens": 306368}
{"current_steps": 755, "total_steps": 16520, "loss": 0.0984, "lr": 0.00045641646489104115, "epoch": 0.914043583535109, "percentage": 4.57, "elapsed_time": "0:02:24", "remaining_time": "0:50:11", "throughput": 2138.73, "total_tokens": 308416}
{"current_steps": 760, "total_steps": 16520, "loss": 0.1901, "lr": 0.00045944309927360775, "epoch": 0.9200968523002422, "percentage": 4.6, "elapsed_time": "0:02:25", "remaining_time": "0:50:09", "throughput": 2139.38, "total_tokens": 310496}
{"current_steps": 765, "total_steps": 16520, "loss": 0.2412, "lr": 0.00046246973365617435, "epoch": 0.9261501210653753, "percentage": 4.63, "elapsed_time": "0:02:26", "remaining_time": "0:50:09", "throughput": 2139.75, "total_tokens": 312640}
{"current_steps": 770, "total_steps": 16520, "loss": 0.1026, "lr": 0.0004654963680387409, "epoch": 0.9322033898305084, "percentage": 4.66, "elapsed_time": "0:02:27", "remaining_time": "0:50:07", "throughput": 2139.61, "total_tokens": 314624}
{"current_steps": 775, "total_steps": 16520, "loss": 0.1363, "lr": 0.0004685230024213075, "epoch": 0.9382566585956417, "percentage": 4.69, "elapsed_time": "0:02:28", "remaining_time": "0:50:07", "throughput": 2139.62, "total_tokens": 316704}
{"current_steps": 780, "total_steps": 16520, "loss": 0.2153, "lr": 0.0004715496368038741, "epoch": 0.9443099273607748, "percentage": 4.72, "elapsed_time": "0:02:28", "remaining_time": "0:50:05", "throughput": 2139.64, "total_tokens": 318720}
{"current_steps": 785, "total_steps": 16520, "loss": 0.1072, "lr": 0.0004745762711864407, "epoch": 0.950363196125908, "percentage": 4.75, "elapsed_time": "0:02:29", "remaining_time": "0:50:04", "throughput": 2139.66, "total_tokens": 320736}
{"current_steps": 790, "total_steps": 16520, "loss": 0.1463, "lr": 0.00047760290556900724, "epoch": 0.9564164648910412, "percentage": 4.78, "elapsed_time": "0:02:30", "remaining_time": "0:50:04", "throughput": 2139.29, "total_tokens": 322752}
{"current_steps": 795, "total_steps": 16520, "loss": 0.1468, "lr": 0.0004806295399515739, "epoch": 0.9624697336561744, "percentage": 4.81, "elapsed_time": "0:02:31", "remaining_time": "0:50:03", "throughput": 2139.45, "total_tokens": 324864}
{"current_steps": 800, "total_steps": 16520, "loss": 0.1557, "lr": 0.00048365617433414045, "epoch": 0.9685230024213075, "percentage": 4.84, "elapsed_time": "0:02:32", "remaining_time": "0:50:02", "throughput": 2139.27, "total_tokens": 326848}
{"current_steps": 805, "total_steps": 16520, "loss": 0.1733, "lr": 0.00048668280871670705, "epoch": 0.9745762711864406, "percentage": 4.87, "elapsed_time": "0:02:33", "remaining_time": "0:50:01", "throughput": 2138.95, "total_tokens": 328864}
{"current_steps": 810, "total_steps": 16520, "loss": 0.1013, "lr": 0.0004897094430992736, "epoch": 0.9806295399515739, "percentage": 4.9, "elapsed_time": "0:02:34", "remaining_time": "0:50:00", "throughput": 2139.52, "total_tokens": 330944}
{"current_steps": 815, "total_steps": 16520, "loss": 0.1549, "lr": 0.0004927360774818402, "epoch": 0.986682808716707, "percentage": 4.93, "elapsed_time": "0:02:35", "remaining_time": "0:49:59", "throughput": 2139.35, "total_tokens": 332992}
{"current_steps": 820, "total_steps": 16520, "loss": 0.1736, "lr": 0.0004957627118644068, "epoch": 0.9927360774818402, "percentage": 4.96, "elapsed_time": "0:02:36", "remaining_time": "0:49:58", "throughput": 2138.96, "total_tokens": 335008}
{"current_steps": 825, "total_steps": 16520, "loss": 0.1409, "lr": 0.0004987893462469734, "epoch": 0.9987893462469734, "percentage": 4.99, "elapsed_time": "0:02:37", "remaining_time": "0:49:58", "throughput": 2139.8, "total_tokens": 337248}
{"current_steps": 826, "total_steps": 16520, "eval_loss": 0.15065602958202362, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:02:45", "remaining_time": "0:52:27", "throughput": 2036.23, "total_tokens": 337344}
{"current_steps": 830, "total_steps": 16520, "loss": 0.1342, "lr": 0.0005018159806295399, "epoch": 1.0048426150121066, "percentage": 5.02, "elapsed_time": "0:02:47", "remaining_time": "0:52:42", "throughput": 2026.24, "total_tokens": 339008}
{"current_steps": 835, "total_steps": 16520, "loss": 0.1008, "lr": 0.0005048426150121066, "epoch": 1.0108958837772397, "percentage": 5.05, "elapsed_time": "0:02:48", "remaining_time": "0:52:41", "throughput": 2026.2, "total_tokens": 341024}
{"current_steps": 840, "total_steps": 16520, "loss": 0.1051, "lr": 0.0005078692493946732, "epoch": 1.0169491525423728, "percentage": 5.08, "elapsed_time": "0:02:49", "remaining_time": "0:52:39", "throughput": 2026.62, "total_tokens": 343072}
{"current_steps": 845, "total_steps": 16520, "loss": 0.0892, "lr": 0.0005108958837772397, "epoch": 1.023002421307506, "percentage": 5.12, "elapsed_time": "0:02:50", "remaining_time": "0:52:38", "throughput": 2027.37, "total_tokens": 345184}
{"current_steps": 850, "total_steps": 16520, "loss": 0.1673, "lr": 0.0005139225181598063, "epoch": 1.0290556900726393, "percentage": 5.15, "elapsed_time": "0:02:51", "remaining_time": "0:52:36", "throughput": 2027.65, "total_tokens": 347136}
{"current_steps": 855, "total_steps": 16520, "loss": 0.0951, "lr": 0.0005169491525423729, "epoch": 1.0351089588377724, "percentage": 5.18, "elapsed_time": "0:02:52", "remaining_time": "0:52:34", "throughput": 2028.89, "total_tokens": 349280}
{"current_steps": 860, "total_steps": 16520, "loss": 0.1675, "lr": 0.0005199757869249395, "epoch": 1.0411622276029056, "percentage": 5.21, "elapsed_time": "0:02:53", "remaining_time": "0:52:32", "throughput": 2029.97, "total_tokens": 351456}
{"current_steps": 865, "total_steps": 16520, "loss": 0.1077, "lr": 0.0005230024213075061, "epoch": 1.0472154963680387, "percentage": 5.24, "elapsed_time": "0:02:54", "remaining_time": "0:52:30", "throughput": 2030.41, "total_tokens": 353504}
{"current_steps": 870, "total_steps": 16520, "loss": 0.2996, "lr": 0.0005260290556900727, "epoch": 1.053268765133172, "percentage": 5.27, "elapsed_time": "0:02:55", "remaining_time": "0:52:28", "throughput": 2031.16, "total_tokens": 355552}
{"current_steps": 875, "total_steps": 16520, "loss": 0.1503, "lr": 0.0005290556900726392, "epoch": 1.0593220338983051, "percentage": 5.3, "elapsed_time": "0:02:55", "remaining_time": "0:52:26", "throughput": 2031.43, "total_tokens": 357440}
{"current_steps": 880, "total_steps": 16520, "loss": 0.1604, "lr": 0.0005320823244552058, "epoch": 1.0653753026634383, "percentage": 5.33, "elapsed_time": "0:02:56", "remaining_time": "0:52:24", "throughput": 2031.72, "total_tokens": 359456}
{"current_steps": 885, "total_steps": 16520, "loss": 0.1479, "lr": 0.0005351089588377725, "epoch": 1.0714285714285714, "percentage": 5.36, "elapsed_time": "0:02:57", "remaining_time": "0:52:22", "throughput": 2032.14, "total_tokens": 361504}
{"current_steps": 890, "total_steps": 16520, "loss": 0.1426, "lr": 0.000538135593220339, "epoch": 1.0774818401937045, "percentage": 5.39, "elapsed_time": "0:02:58", "remaining_time": "0:52:20", "throughput": 2032.55, "total_tokens": 363488}
{"current_steps": 895, "total_steps": 16520, "loss": 0.1295, "lr": 0.0005411622276029056, "epoch": 1.0835351089588379, "percentage": 5.42, "elapsed_time": "0:02:59", "remaining_time": "0:52:19", "throughput": 2033.14, "total_tokens": 365600}
{"current_steps": 900, "total_steps": 16520, "loss": 0.1906, "lr": 0.0005441888619854722, "epoch": 1.089588377723971, "percentage": 5.45, "elapsed_time": "0:03:00", "remaining_time": "0:52:17", "throughput": 2033.7, "total_tokens": 367616}
{"current_steps": 905, "total_steps": 16520, "loss": 0.1639, "lr": 0.0005472154963680388, "epoch": 1.0956416464891041, "percentage": 5.48, "elapsed_time": "0:03:01", "remaining_time": "0:52:15", "throughput": 2034.55, "total_tokens": 369696}
{"current_steps": 910, "total_steps": 16520, "loss": 0.2004, "lr": 0.0005502421307506054, "epoch": 1.1016949152542372, "percentage": 5.51, "elapsed_time": "0:03:02", "remaining_time": "0:52:13", "throughput": 2034.95, "total_tokens": 371680}
{"current_steps": 915, "total_steps": 16520, "loss": 0.175, "lr": 0.000553268765133172, "epoch": 1.1077481840193704, "percentage": 5.54, "elapsed_time": "0:03:03", "remaining_time": "0:52:11", "throughput": 2035.61, "total_tokens": 373792}
{"current_steps": 920, "total_steps": 16520, "loss": 0.1796, "lr": 0.0005562953995157385, "epoch": 1.1138014527845037, "percentage": 5.57, "elapsed_time": "0:03:04", "remaining_time": "0:52:10", "throughput": 2036.46, "total_tokens": 375936}
{"current_steps": 925, "total_steps": 16520, "loss": 0.1604, "lr": 0.0005593220338983051, "epoch": 1.1198547215496368, "percentage": 5.6, "elapsed_time": "0:03:05", "remaining_time": "0:52:08", "throughput": 2036.99, "total_tokens": 377952}
{"current_steps": 930, "total_steps": 16520, "loss": 0.1645, "lr": 0.0005623486682808717, "epoch": 1.12590799031477, "percentage": 5.63, "elapsed_time": "0:03:06", "remaining_time": "0:52:06", "throughput": 2037.37, "total_tokens": 380000}
{"current_steps": 935, "total_steps": 16520, "loss": 0.1434, "lr": 0.0005653753026634383, "epoch": 1.131961259079903, "percentage": 5.66, "elapsed_time": "0:03:07", "remaining_time": "0:52:05", "throughput": 2037.91, "total_tokens": 382080}
{"current_steps": 940, "total_steps": 16520, "loss": 0.2028, "lr": 0.0005684019370460049, "epoch": 1.1380145278450362, "percentage": 5.69, "elapsed_time": "0:03:08", "remaining_time": "0:52:03", "throughput": 2038.71, "total_tokens": 384224}
{"current_steps": 945, "total_steps": 16520, "loss": 0.1564, "lr": 0.0005714285714285714, "epoch": 1.1440677966101696, "percentage": 5.72, "elapsed_time": "0:03:09", "remaining_time": "0:52:01", "throughput": 2039.66, "total_tokens": 386272}
{"current_steps": 950, "total_steps": 16520, "loss": 0.1259, "lr": 0.0005744552058111381, "epoch": 1.1501210653753027, "percentage": 5.75, "elapsed_time": "0:03:10", "remaining_time": "0:51:59", "throughput": 2040.01, "total_tokens": 388320}
{"current_steps": 955, "total_steps": 16520, "loss": 0.0988, "lr": 0.0005774818401937047, "epoch": 1.1561743341404358, "percentage": 5.78, "elapsed_time": "0:03:11", "remaining_time": "0:51:57", "throughput": 2040.36, "total_tokens": 390240}
{"current_steps": 960, "total_steps": 16520, "loss": 0.1973, "lr": 0.0005805084745762712, "epoch": 1.162227602905569, "percentage": 5.81, "elapsed_time": "0:03:12", "remaining_time": "0:51:54", "throughput": 2040.69, "total_tokens": 392160}
{"current_steps": 965, "total_steps": 16520, "loss": 0.1624, "lr": 0.0005835351089588378, "epoch": 1.1682808716707023, "percentage": 5.84, "elapsed_time": "0:03:13", "remaining_time": "0:51:53", "throughput": 2040.91, "total_tokens": 394176}
{"current_steps": 970, "total_steps": 16520, "loss": 0.0823, "lr": 0.0005865617433414044, "epoch": 1.1743341404358354, "percentage": 5.87, "elapsed_time": "0:03:14", "remaining_time": "0:51:51", "throughput": 2041.67, "total_tokens": 396320}
{"current_steps": 975, "total_steps": 16520, "loss": 0.2204, "lr": 0.000589588377723971, "epoch": 1.1803874092009685, "percentage": 5.9, "elapsed_time": "0:03:15", "remaining_time": "0:51:50", "throughput": 2042.29, "total_tokens": 398432}
{"current_steps": 980, "total_steps": 16520, "loss": 0.1167, "lr": 0.0005926150121065376, "epoch": 1.1864406779661016, "percentage": 5.93, "elapsed_time": "0:03:16", "remaining_time": "0:51:48", "throughput": 2042.74, "total_tokens": 400384}
{"current_steps": 985, "total_steps": 16520, "loss": 0.1358, "lr": 0.0005956416464891042, "epoch": 1.192493946731235, "percentage": 5.96, "elapsed_time": "0:03:16", "remaining_time": "0:51:45", "throughput": 2042.92, "total_tokens": 402208}
{"current_steps": 990, "total_steps": 16520, "loss": 0.0964, "lr": 0.0005986682808716707, "epoch": 1.1985472154963681, "percentage": 5.99, "elapsed_time": "0:03:17", "remaining_time": "0:51:42", "throughput": 2043.67, "total_tokens": 404224}
{"current_steps": 995, "total_steps": 16520, "loss": 0.1853, "lr": 0.0006016949152542373, "epoch": 1.2046004842615012, "percentage": 6.02, "elapsed_time": "0:03:18", "remaining_time": "0:51:40", "throughput": 2044.43, "total_tokens": 406304}
{"current_steps": 1000, "total_steps": 16520, "loss": 0.1722, "lr": 0.000604721549636804, "epoch": 1.2106537530266344, "percentage": 6.05, "elapsed_time": "0:03:19", "remaining_time": "0:51:39", "throughput": 2045.34, "total_tokens": 408512}
{"current_steps": 1005, "total_steps": 16520, "loss": 0.1194, "lr": 0.0006077481840193705, "epoch": 1.2167070217917675, "percentage": 6.08, "elapsed_time": "0:03:20", "remaining_time": "0:51:38", "throughput": 2045.8, "total_tokens": 410592}
{"current_steps": 1010, "total_steps": 16520, "loss": 0.1401, "lr": 0.0006107748184019371, "epoch": 1.2227602905569008, "percentage": 6.11, "elapsed_time": "0:03:21", "remaining_time": "0:51:37", "throughput": 2046.68, "total_tokens": 412800}
{"current_steps": 1015, "total_steps": 16520, "loss": 0.1419, "lr": 0.0006138014527845037, "epoch": 1.228813559322034, "percentage": 6.14, "elapsed_time": "0:03:22", "remaining_time": "0:51:35", "throughput": 2047.0, "total_tokens": 414784}
{"current_steps": 1020, "total_steps": 16520, "loss": 0.1099, "lr": 0.0006168280871670703, "epoch": 1.234866828087167, "percentage": 6.17, "elapsed_time": "0:03:23", "remaining_time": "0:51:33", "throughput": 2047.31, "total_tokens": 416768}
{"current_steps": 1025, "total_steps": 16520, "loss": 0.101, "lr": 0.0006198547215496369, "epoch": 1.2409200968523002, "percentage": 6.2, "elapsed_time": "0:03:24", "remaining_time": "0:51:31", "throughput": 2047.62, "total_tokens": 418752}
{"current_steps": 1030, "total_steps": 16520, "loss": 0.143, "lr": 0.0006228813559322035, "epoch": 1.2469733656174333, "percentage": 6.23, "elapsed_time": "0:03:25", "remaining_time": "0:51:29", "throughput": 2048.05, "total_tokens": 420704}
{"current_steps": 1035, "total_steps": 16520, "loss": 0.1281, "lr": 0.00062590799031477, "epoch": 1.2530266343825667, "percentage": 6.27, "elapsed_time": "0:03:26", "remaining_time": "0:51:27", "throughput": 2048.49, "total_tokens": 422784}
{"current_steps": 1040, "total_steps": 16520, "loss": 0.1075, "lr": 0.0006289346246973365, "epoch": 1.2590799031476998, "percentage": 6.3, "elapsed_time": "0:03:27", "remaining_time": "0:51:26", "throughput": 2048.42, "total_tokens": 424736}
{"current_steps": 1045, "total_steps": 16520, "loss": 0.085, "lr": 0.0006319612590799033, "epoch": 1.265133171912833, "percentage": 6.33, "elapsed_time": "0:03:28", "remaining_time": "0:51:24", "throughput": 2048.72, "total_tokens": 426784}
{"current_steps": 1050, "total_steps": 16520, "loss": 0.1761, "lr": 0.0006349878934624698, "epoch": 1.271186440677966, "percentage": 6.36, "elapsed_time": "0:03:29", "remaining_time": "0:51:23", "throughput": 2049.58, "total_tokens": 428992}
{"current_steps": 1055, "total_steps": 16520, "loss": 0.1502, "lr": 0.0006380145278450364, "epoch": 1.2772397094430992, "percentage": 6.39, "elapsed_time": "0:03:30", "remaining_time": "0:51:22", "throughput": 2049.51, "total_tokens": 430944}
{"current_steps": 1060, "total_steps": 16520, "loss": 0.114, "lr": 0.0006410411622276028, "epoch": 1.2832929782082325, "percentage": 6.42, "elapsed_time": "0:03:31", "remaining_time": "0:51:20", "throughput": 2049.72, "total_tokens": 432992}
{"current_steps": 1065, "total_steps": 16520, "loss": 0.1187, "lr": 0.0006440677966101694, "epoch": 1.2893462469733656, "percentage": 6.45, "elapsed_time": "0:03:32", "remaining_time": "0:51:19", "throughput": 2050.77, "total_tokens": 435232}
{"current_steps": 1070, "total_steps": 16520, "loss": 0.2164, "lr": 0.0006470944309927362, "epoch": 1.2953995157384988, "percentage": 6.48, "elapsed_time": "0:03:33", "remaining_time": "0:51:18", "throughput": 2051.57, "total_tokens": 437344}
{"current_steps": 1075, "total_steps": 16520, "loss": 0.1209, "lr": 0.0006501210653753026, "epoch": 1.3014527845036319, "percentage": 6.51, "elapsed_time": "0:03:34", "remaining_time": "0:51:16", "throughput": 2052.11, "total_tokens": 439456}
{"current_steps": 1080, "total_steps": 16520, "loss": 0.1087, "lr": 0.0006531476997578692, "epoch": 1.307506053268765, "percentage": 6.54, "elapsed_time": "0:03:35", "remaining_time": "0:51:14", "throughput": 2052.39, "total_tokens": 441440}
{"current_steps": 1085, "total_steps": 16520, "loss": 0.2086, "lr": 0.0006561743341404358, "epoch": 1.3135593220338984, "percentage": 6.57, "elapsed_time": "0:03:36", "remaining_time": "0:51:13", "throughput": 2052.68, "total_tokens": 443488}
{"current_steps": 1090, "total_steps": 16520, "loss": 0.1044, "lr": 0.0006592009685230024, "epoch": 1.3196125907990315, "percentage": 6.6, "elapsed_time": "0:03:36", "remaining_time": "0:51:11", "throughput": 2052.83, "total_tokens": 445440}
{"current_steps": 1095, "total_steps": 16520, "loss": 0.1258, "lr": 0.000662227602905569, "epoch": 1.3256658595641646, "percentage": 6.63, "elapsed_time": "0:03:37", "remaining_time": "0:51:10", "throughput": 2053.31, "total_tokens": 447552}
{"current_steps": 1100, "total_steps": 16520, "loss": 0.1203, "lr": 0.0006652542372881356, "epoch": 1.331719128329298, "percentage": 6.66, "elapsed_time": "0:03:38", "remaining_time": "0:51:09", "throughput": 2054.17, "total_tokens": 449760}
{"current_steps": 1105, "total_steps": 16520, "loss": 0.141, "lr": 0.0006682808716707021, "epoch": 1.3377723970944309, "percentage": 6.69, "elapsed_time": "0:03:39", "remaining_time": "0:51:07", "throughput": 2054.43, "total_tokens": 451744}
{"current_steps": 1110, "total_steps": 16520, "loss": 0.0558, "lr": 0.0006713075060532687, "epoch": 1.3438256658595642, "percentage": 6.72, "elapsed_time": "0:03:40", "remaining_time": "0:51:06", "throughput": 2054.95, "total_tokens": 453856}
{"current_steps": 1115, "total_steps": 16520, "loss": 0.0477, "lr": 0.0006743341404358354, "epoch": 1.3498789346246973, "percentage": 6.75, "elapsed_time": "0:03:41", "remaining_time": "0:51:04", "throughput": 2055.32, "total_tokens": 455872}
{"current_steps": 1120, "total_steps": 16520, "loss": 0.1039, "lr": 0.0006773607748184019, "epoch": 1.3559322033898304, "percentage": 6.78, "elapsed_time": "0:03:42", "remaining_time": "0:51:03", "throughput": 2056.1, "total_tokens": 458080}
{"current_steps": 1125, "total_steps": 16520, "loss": 0.2055, "lr": 0.0006803874092009685, "epoch": 1.3619854721549638, "percentage": 6.81, "elapsed_time": "0:03:43", "remaining_time": "0:51:01", "throughput": 2056.59, "total_tokens": 460128}
{"current_steps": 1130, "total_steps": 16520, "loss": 0.0979, "lr": 0.0006834140435835351, "epoch": 1.368038740920097, "percentage": 6.84, "elapsed_time": "0:03:44", "remaining_time": "0:51:00", "throughput": 2056.84, "total_tokens": 462176}
{"current_steps": 1135, "total_steps": 16520, "loss": 0.241, "lr": 0.0006864406779661016, "epoch": 1.37409200968523, "percentage": 6.87, "elapsed_time": "0:03:45", "remaining_time": "0:50:59", "throughput": 2057.44, "total_tokens": 464320}
{"current_steps": 1140, "total_steps": 16520, "loss": 0.1324, "lr": 0.0006894673123486683, "epoch": 1.3801452784503632, "percentage": 6.9, "elapsed_time": "0:03:46", "remaining_time": "0:50:57", "throughput": 2057.56, "total_tokens": 466336}
{"current_steps": 1145, "total_steps": 16520, "loss": 0.1041, "lr": 0.0006924939467312349, "epoch": 1.3861985472154963, "percentage": 6.93, "elapsed_time": "0:03:47", "remaining_time": "0:50:56", "throughput": 2057.91, "total_tokens": 468352}
{"current_steps": 1150, "total_steps": 16520, "loss": 0.1324, "lr": 0.0006955205811138014, "epoch": 1.3922518159806296, "percentage": 6.96, "elapsed_time": "0:03:48", "remaining_time": "0:50:54", "throughput": 2058.27, "total_tokens": 470432}
{"current_steps": 1155, "total_steps": 16520, "loss": 0.1479, "lr": 0.000698547215496368, "epoch": 1.3983050847457628, "percentage": 6.99, "elapsed_time": "0:03:49", "remaining_time": "0:50:52", "throughput": 2058.5, "total_tokens": 472416}
{"current_steps": 1160, "total_steps": 16520, "loss": 0.2043, "lr": 0.0007015738498789347, "epoch": 1.4043583535108959, "percentage": 7.02, "elapsed_time": "0:03:50", "remaining_time": "0:50:51", "throughput": 2058.85, "total_tokens": 474432}
{"current_steps": 1165, "total_steps": 16520, "loss": 0.129, "lr": 0.0007046004842615012, "epoch": 1.410411622276029, "percentage": 7.05, "elapsed_time": "0:03:51", "remaining_time": "0:50:49", "throughput": 2058.95, "total_tokens": 476384}
{"current_steps": 1170, "total_steps": 16520, "loss": 0.1356, "lr": 0.0007076271186440678, "epoch": 1.4164648910411621, "percentage": 7.08, "elapsed_time": "0:03:52", "remaining_time": "0:50:47", "throughput": 2059.52, "total_tokens": 478400}
{"current_steps": 1175, "total_steps": 16520, "loss": 0.1471, "lr": 0.0007106537530266343, "epoch": 1.4225181598062955, "percentage": 7.11, "elapsed_time": "0:03:53", "remaining_time": "0:50:46", "throughput": 2059.4, "total_tokens": 480352}
{"current_steps": 1180, "total_steps": 16520, "loss": 0.0799, "lr": 0.0007136803874092009, "epoch": 1.4285714285714286, "percentage": 7.14, "elapsed_time": "0:03:54", "remaining_time": "0:50:43", "throughput": 2059.5, "total_tokens": 482240}
{"current_steps": 1185, "total_steps": 16520, "loss": 0.1252, "lr": 0.0007167070217917676, "epoch": 1.4346246973365617, "percentage": 7.17, "elapsed_time": "0:03:55", "remaining_time": "0:50:42", "throughput": 2059.96, "total_tokens": 484352}
{"current_steps": 1190, "total_steps": 16520, "loss": 0.0769, "lr": 0.0007197336561743341, "epoch": 1.4406779661016949, "percentage": 7.2, "elapsed_time": "0:03:56", "remaining_time": "0:50:41", "throughput": 2060.04, "total_tokens": 486304}
{"current_steps": 1195, "total_steps": 16520, "loss": 0.11, "lr": 0.0007227602905569007, "epoch": 1.446731234866828, "percentage": 7.23, "elapsed_time": "0:03:57", "remaining_time": "0:50:39", "throughput": 2060.71, "total_tokens": 488416}
{"current_steps": 1200, "total_steps": 16520, "loss": 0.0958, "lr": 0.0007257869249394673, "epoch": 1.4527845036319613, "percentage": 7.26, "elapsed_time": "0:03:57", "remaining_time": "0:50:37", "throughput": 2060.91, "total_tokens": 490400}
{"current_steps": 1205, "total_steps": 16520, "loss": 0.0539, "lr": 0.0007288135593220338, "epoch": 1.4588377723970944, "percentage": 7.29, "elapsed_time": "0:03:58", "remaining_time": "0:50:35", "throughput": 2061.11, "total_tokens": 492256}
{"current_steps": 1210, "total_steps": 16520, "loss": 0.2617, "lr": 0.0007318401937046005, "epoch": 1.4648910411622276, "percentage": 7.32, "elapsed_time": "0:03:59", "remaining_time": "0:50:34", "throughput": 2061.09, "total_tokens": 494240}
{"current_steps": 1215, "total_steps": 16520, "loss": 0.1269, "lr": 0.0007348668280871671, "epoch": 1.4709443099273607, "percentage": 7.35, "elapsed_time": "0:04:00", "remaining_time": "0:50:32", "throughput": 2061.4, "total_tokens": 496256}
{"current_steps": 1220, "total_steps": 16520, "loss": 0.1992, "lr": 0.0007378934624697336, "epoch": 1.4769975786924938, "percentage": 7.38, "elapsed_time": "0:04:01", "remaining_time": "0:50:31", "throughput": 2062.06, "total_tokens": 498432}
{"current_steps": 1225, "total_steps": 16520, "loss": 0.1331, "lr": 0.0007409200968523002, "epoch": 1.4830508474576272, "percentage": 7.42, "elapsed_time": "0:04:02", "remaining_time": "0:50:29", "throughput": 2062.48, "total_tokens": 500416}
{"current_steps": 1230, "total_steps": 16520, "loss": 0.202, "lr": 0.0007439467312348669, "epoch": 1.4891041162227603, "percentage": 7.45, "elapsed_time": "0:04:03", "remaining_time": "0:50:27", "throughput": 2062.69, "total_tokens": 502400}
{"current_steps": 1235, "total_steps": 16520, "loss": 0.0887, "lr": 0.0007469733656174334, "epoch": 1.4951573849878934, "percentage": 7.48, "elapsed_time": "0:04:04", "remaining_time": "0:50:25", "throughput": 2062.89, "total_tokens": 504320}
{"current_steps": 1240, "total_steps": 16520, "loss": 0.161, "lr": 0.00075, "epoch": 1.5012106537530268, "percentage": 7.51, "elapsed_time": "0:04:05", "remaining_time": "0:50:23", "throughput": 2063.62, "total_tokens": 506400}
{"current_steps": 1245, "total_steps": 16520, "loss": 0.1338, "lr": 0.0007530266343825666, "epoch": 1.5072639225181597, "percentage": 7.54, "elapsed_time": "0:04:06", "remaining_time": "0:50:22", "throughput": 2063.73, "total_tokens": 508416}
{"current_steps": 1250, "total_steps": 16520, "loss": 0.0843, "lr": 0.0007560532687651331, "epoch": 1.513317191283293, "percentage": 7.57, "elapsed_time": "0:04:07", "remaining_time": "0:50:21", "throughput": 2064.25, "total_tokens": 510560}
{"current_steps": 1255, "total_steps": 16520, "loss": 0.1771, "lr": 0.0007590799031476998, "epoch": 1.5193704600484261, "percentage": 7.6, "elapsed_time": "0:04:08", "remaining_time": "0:50:20", "throughput": 2064.67, "total_tokens": 512672}
{"current_steps": 1260, "total_steps": 16520, "loss": 0.1632, "lr": 0.0007621065375302664, "epoch": 1.5254237288135593, "percentage": 7.63, "elapsed_time": "0:04:09", "remaining_time": "0:50:18", "throughput": 2065.09, "total_tokens": 514752}
{"current_steps": 1265, "total_steps": 16520, "loss": 0.1801, "lr": 0.0007651331719128329, "epoch": 1.5314769975786926, "percentage": 7.66, "elapsed_time": "0:04:10", "remaining_time": "0:50:16", "throughput": 2065.6, "total_tokens": 516768}
{"current_steps": 1270, "total_steps": 16520, "loss": 0.1485, "lr": 0.0007681598062953995, "epoch": 1.5375302663438255, "percentage": 7.69, "elapsed_time": "0:04:11", "remaining_time": "0:50:15", "throughput": 2065.54, "total_tokens": 518752}
{"current_steps": 1275, "total_steps": 16520, "loss": 0.1578, "lr": 0.0007711864406779662, "epoch": 1.5435835351089588, "percentage": 7.72, "elapsed_time": "0:04:12", "remaining_time": "0:50:14", "throughput": 2066.33, "total_tokens": 521024}
{"current_steps": 1280, "total_steps": 16520, "loss": 0.1345, "lr": 0.0007742130750605327, "epoch": 1.549636803874092, "percentage": 7.75, "elapsed_time": "0:04:13", "remaining_time": "0:50:13", "throughput": 2066.5, "total_tokens": 523072}
{"current_steps": 1285, "total_steps": 16520, "loss": 0.127, "lr": 0.0007772397094430993, "epoch": 1.555690072639225, "percentage": 7.78, "elapsed_time": "0:04:14", "remaining_time": "0:50:12", "throughput": 2067.13, "total_tokens": 525248}
{"current_steps": 1290, "total_steps": 16520, "loss": 0.1321, "lr": 0.0007802663438256659, "epoch": 1.5617433414043584, "percentage": 7.81, "elapsed_time": "0:04:15", "remaining_time": "0:50:11", "throughput": 2067.65, "total_tokens": 527424}
{"current_steps": 1295, "total_steps": 16520, "loss": 0.1281, "lr": 0.0007832929782082324, "epoch": 1.5677966101694916, "percentage": 7.84, "elapsed_time": "0:04:16", "remaining_time": "0:50:10", "throughput": 2068.05, "total_tokens": 529504}
{"current_steps": 1300, "total_steps": 16520, "loss": 0.0515, "lr": 0.0007863196125907991, "epoch": 1.5738498789346247, "percentage": 7.87, "elapsed_time": "0:04:16", "remaining_time": "0:50:08", "throughput": 2068.22, "total_tokens": 531488}
{"current_steps": 1305, "total_steps": 16520, "loss": 0.232, "lr": 0.0007893462469733657, "epoch": 1.5799031476997578, "percentage": 7.9, "elapsed_time": "0:04:17", "remaining_time": "0:50:07", "throughput": 2068.6, "total_tokens": 533600}
{"current_steps": 1310, "total_steps": 16520, "loss": 0.1193, "lr": 0.0007923728813559322, "epoch": 1.585956416464891, "percentage": 7.93, "elapsed_time": "0:04:18", "remaining_time": "0:50:06", "throughput": 2069.01, "total_tokens": 535680}
{"current_steps": 1315, "total_steps": 16520, "loss": 0.0937, "lr": 0.0007953995157384988, "epoch": 1.5920096852300243, "percentage": 7.96, "elapsed_time": "0:04:19", "remaining_time": "0:50:04", "throughput": 2069.19, "total_tokens": 537728}
{"current_steps": 1320, "total_steps": 16520, "loss": 0.1804, "lr": 0.0007984261501210653, "epoch": 1.5980629539951574, "percentage": 7.99, "elapsed_time": "0:04:20", "remaining_time": "0:50:03", "throughput": 2069.57, "total_tokens": 539776}
{"current_steps": 1325, "total_steps": 16520, "loss": 0.1315, "lr": 0.000801452784503632, "epoch": 1.6041162227602905, "percentage": 8.02, "elapsed_time": "0:04:21", "remaining_time": "0:50:01", "throughput": 2070.13, "total_tokens": 541824}
{"current_steps": 1330, "total_steps": 16520, "loss": 0.0968, "lr": 0.0008044794188861986, "epoch": 1.6101694915254239, "percentage": 8.05, "elapsed_time": "0:04:22", "remaining_time": "0:49:59", "throughput": 2070.3, "total_tokens": 543808}
{"current_steps": 1335, "total_steps": 16520, "loss": 0.1159, "lr": 0.0008075060532687651, "epoch": 1.6162227602905568, "percentage": 8.08, "elapsed_time": "0:04:23", "remaining_time": "0:49:58", "throughput": 2070.47, "total_tokens": 545792}
{"current_steps": 1340, "total_steps": 16520, "loss": 0.1593, "lr": 0.0008105326876513317, "epoch": 1.6222760290556901, "percentage": 8.11, "elapsed_time": "0:04:24", "remaining_time": "0:49:57", "throughput": 2070.81, "total_tokens": 547904}
{"current_steps": 1345, "total_steps": 16520, "loss": 0.1224, "lr": 0.0008135593220338984, "epoch": 1.6283292978208233, "percentage": 8.14, "elapsed_time": "0:04:25", "remaining_time": "0:49:56", "throughput": 2071.08, "total_tokens": 549984}
{"current_steps": 1350, "total_steps": 16520, "loss": 0.1289, "lr": 0.0008165859564164649, "epoch": 1.6343825665859564, "percentage": 8.17, "elapsed_time": "0:04:26", "remaining_time": "0:49:54", "throughput": 2071.23, "total_tokens": 551968}
{"current_steps": 1355, "total_steps": 16520, "loss": 0.1241, "lr": 0.0008196125907990315, "epoch": 1.6404358353510897, "percentage": 8.2, "elapsed_time": "0:04:27", "remaining_time": "0:49:53", "throughput": 2071.59, "total_tokens": 554080}
{"current_steps": 1360, "total_steps": 16520, "loss": 0.1467, "lr": 0.0008226392251815981, "epoch": 1.6464891041162226, "percentage": 8.23, "elapsed_time": "0:04:28", "remaining_time": "0:49:52", "throughput": 2071.75, "total_tokens": 556128}
{"current_steps": 1365, "total_steps": 16520, "loss": 0.1047, "lr": 0.0008256658595641646, "epoch": 1.652542372881356, "percentage": 8.26, "elapsed_time": "0:04:29", "remaining_time": "0:49:50", "throughput": 2072.11, "total_tokens": 558208}
{"current_steps": 1370, "total_steps": 16520, "loss": 0.0818, "lr": 0.0008286924939467313, "epoch": 1.658595641646489, "percentage": 8.29, "elapsed_time": "0:04:30", "remaining_time": "0:49:49", "throughput": 2072.58, "total_tokens": 560352}
{"current_steps": 1375, "total_steps": 16520, "loss": 0.1534, "lr": 0.0008317191283292979, "epoch": 1.6646489104116222, "percentage": 8.32, "elapsed_time": "0:04:31", "remaining_time": "0:49:48", "throughput": 2072.72, "total_tokens": 562336}
{"current_steps": 1380, "total_steps": 16520, "loss": 0.122, "lr": 0.0008347457627118644, "epoch": 1.6707021791767556, "percentage": 8.35, "elapsed_time": "0:04:32", "remaining_time": "0:49:47", "throughput": 2072.87, "total_tokens": 564384}
{"current_steps": 1385, "total_steps": 16520, "loss": 0.0938, "lr": 0.000837772397094431, "epoch": 1.6767554479418885, "percentage": 8.38, "elapsed_time": "0:04:33", "remaining_time": "0:49:45", "throughput": 2073.19, "total_tokens": 566432}
{"current_steps": 1390, "total_steps": 16520, "loss": 0.1278, "lr": 0.0008407990314769976, "epoch": 1.6828087167070218, "percentage": 8.41, "elapsed_time": "0:04:34", "remaining_time": "0:49:43", "throughput": 2073.22, "total_tokens": 568320}
{"current_steps": 1395, "total_steps": 16520, "loss": 0.2684, "lr": 0.0008438256658595642, "epoch": 1.688861985472155, "percentage": 8.44, "elapsed_time": "0:04:35", "remaining_time": "0:49:42", "throughput": 2073.46, "total_tokens": 570400}
{"current_steps": 1400, "total_steps": 16520, "loss": 0.0559, "lr": 0.0008468523002421308, "epoch": 1.694915254237288, "percentage": 8.47, "elapsed_time": "0:04:36", "remaining_time": "0:49:41", "throughput": 2073.51, "total_tokens": 572448}
{"current_steps": 1405, "total_steps": 16520, "loss": 0.0755, "lr": 0.0008498789346246974, "epoch": 1.7009685230024214, "percentage": 8.5, "elapsed_time": "0:04:36", "remaining_time": "0:49:39", "throughput": 2074.02, "total_tokens": 574496}
{"current_steps": 1410, "total_steps": 16520, "loss": 0.1698, "lr": 0.0008529055690072639, "epoch": 1.7070217917675545, "percentage": 8.54, "elapsed_time": "0:04:37", "remaining_time": "0:49:38", "throughput": 2074.33, "total_tokens": 576512}
{"current_steps": 1415, "total_steps": 16520, "loss": 0.1943, "lr": 0.0008559322033898306, "epoch": 1.7130750605326877, "percentage": 8.57, "elapsed_time": "0:04:38", "remaining_time": "0:49:36", "throughput": 2074.64, "total_tokens": 578560}
{"current_steps": 1420, "total_steps": 16520, "loss": 0.117, "lr": 0.0008589588377723972, "epoch": 1.7191283292978208, "percentage": 8.6, "elapsed_time": "0:04:39", "remaining_time": "0:49:35", "throughput": 2074.59, "total_tokens": 580480}
{"current_steps": 1425, "total_steps": 16520, "loss": 0.1239, "lr": 0.0008619854721549637, "epoch": 1.725181598062954, "percentage": 8.63, "elapsed_time": "0:04:40", "remaining_time": "0:49:33", "throughput": 2074.71, "total_tokens": 582464}
{"current_steps": 1430, "total_steps": 16520, "loss": 0.1393, "lr": 0.0008650121065375303, "epoch": 1.7312348668280872, "percentage": 8.66, "elapsed_time": "0:04:41", "remaining_time": "0:49:32", "throughput": 2074.98, "total_tokens": 584576}
{"current_steps": 1435, "total_steps": 16520, "loss": 0.1191, "lr": 0.0008680387409200968, "epoch": 1.7372881355932204, "percentage": 8.69, "elapsed_time": "0:04:42", "remaining_time": "0:49:31", "throughput": 2075.41, "total_tokens": 586624}
{"current_steps": 1440, "total_steps": 16520, "loss": 0.1019, "lr": 0.0008710653753026635, "epoch": 1.7433414043583535, "percentage": 8.72, "elapsed_time": "0:04:43", "remaining_time": "0:49:30", "throughput": 2075.61, "total_tokens": 588704}
{"current_steps": 1445, "total_steps": 16520, "loss": 0.1518, "lr": 0.0008740920096852301, "epoch": 1.7493946731234868, "percentage": 8.75, "elapsed_time": "0:04:44", "remaining_time": "0:49:28", "throughput": 2076.01, "total_tokens": 590656}
{"current_steps": 1450, "total_steps": 16520, "loss": 0.1495, "lr": 0.0008771186440677966, "epoch": 1.7554479418886197, "percentage": 8.78, "elapsed_time": "0:04:45", "remaining_time": "0:49:26", "throughput": 2076.42, "total_tokens": 592736}
{"current_steps": 1455, "total_steps": 16520, "loss": 0.0689, "lr": 0.0008801452784503632, "epoch": 1.761501210653753, "percentage": 8.81, "elapsed_time": "0:04:46", "remaining_time": "0:49:25", "throughput": 2076.64, "total_tokens": 594752}
{"current_steps": 1460, "total_steps": 16520, "loss": 0.0838, "lr": 0.0008831719128329298, "epoch": 1.7675544794188862, "percentage": 8.84, "elapsed_time": "0:04:47", "remaining_time": "0:49:24", "throughput": 2076.95, "total_tokens": 596864}
{"current_steps": 1465, "total_steps": 16520, "loss": 0.1203, "lr": 0.0008861985472154964, "epoch": 1.7736077481840193, "percentage": 8.87, "elapsed_time": "0:04:48", "remaining_time": "0:49:23", "throughput": 2077.13, "total_tokens": 598944}
{"current_steps": 1470, "total_steps": 16520, "loss": 0.1368, "lr": 0.000889225181598063, "epoch": 1.7796610169491527, "percentage": 8.9, "elapsed_time": "0:04:49", "remaining_time": "0:49:21", "throughput": 2077.43, "total_tokens": 600928}
{"current_steps": 1475, "total_steps": 16520, "loss": 0.1987, "lr": 0.0008922518159806296, "epoch": 1.7857142857142856, "percentage": 8.93, "elapsed_time": "0:04:50", "remaining_time": "0:49:20", "throughput": 2077.81, "total_tokens": 603008}
{"current_steps": 1480, "total_steps": 16520, "loss": 0.1045, "lr": 0.0008952784503631961, "epoch": 1.791767554479419, "percentage": 8.96, "elapsed_time": "0:04:51", "remaining_time": "0:49:18", "throughput": 2078.01, "total_tokens": 605024}
{"current_steps": 1485, "total_steps": 16520, "loss": 0.1181, "lr": 0.0008983050847457628, "epoch": 1.797820823244552, "percentage": 8.99, "elapsed_time": "0:04:52", "remaining_time": "0:49:17", "throughput": 2078.22, "total_tokens": 607104}
{"current_steps": 1490, "total_steps": 16520, "loss": 0.1658, "lr": 0.0009013317191283294, "epoch": 1.8038740920096852, "percentage": 9.02, "elapsed_time": "0:04:53", "remaining_time": "0:49:16", "throughput": 2078.52, "total_tokens": 609216}
{"current_steps": 1495, "total_steps": 16520, "loss": 0.1818, "lr": 0.0009043583535108959, "epoch": 1.8099273607748185, "percentage": 9.05, "elapsed_time": "0:04:54", "remaining_time": "0:49:15", "throughput": 2078.37, "total_tokens": 611168}
{"current_steps": 1500, "total_steps": 16520, "loss": 0.1301, "lr": 0.0009073849878934625, "epoch": 1.8159806295399514, "percentage": 9.08, "elapsed_time": "0:04:54", "remaining_time": "0:49:13", "throughput": 2078.18, "total_tokens": 613056}
{"current_steps": 1505, "total_steps": 16520, "loss": 0.1386, "lr": 0.0009104116222760291, "epoch": 1.8220338983050848, "percentage": 9.11, "elapsed_time": "0:04:55", "remaining_time": "0:49:12", "throughput": 2078.72, "total_tokens": 615264}
{"current_steps": 1510, "total_steps": 16520, "loss": 0.1231, "lr": 0.0009134382566585957, "epoch": 1.828087167070218, "percentage": 9.14, "elapsed_time": "0:04:56", "remaining_time": "0:49:11", "throughput": 2078.73, "total_tokens": 617280}
{"current_steps": 1515, "total_steps": 16520, "loss": 0.1386, "lr": 0.0009164648910411623, "epoch": 1.834140435835351, "percentage": 9.17, "elapsed_time": "0:04:57", "remaining_time": "0:49:10", "throughput": 2078.73, "total_tokens": 619168}
{"current_steps": 1520, "total_steps": 16520, "loss": 0.1188, "lr": 0.0009194915254237289, "epoch": 1.8401937046004844, "percentage": 9.2, "elapsed_time": "0:04:58", "remaining_time": "0:49:08", "throughput": 2078.95, "total_tokens": 621184}
{"current_steps": 1525, "total_steps": 16520, "loss": 0.0551, "lr": 0.0009225181598062954, "epoch": 1.8462469733656173, "percentage": 9.23, "elapsed_time": "0:04:59", "remaining_time": "0:49:07", "throughput": 2079.16, "total_tokens": 623264}
{"current_steps": 1530, "total_steps": 16520, "loss": 0.2043, "lr": 0.000925544794188862, "epoch": 1.8523002421307506, "percentage": 9.26, "elapsed_time": "0:05:00", "remaining_time": "0:49:06", "throughput": 2079.82, "total_tokens": 625472}
{"current_steps": 1535, "total_steps": 16520, "loss": 0.1001, "lr": 0.0009285714285714287, "epoch": 1.8583535108958837, "percentage": 9.29, "elapsed_time": "0:05:01", "remaining_time": "0:49:05", "throughput": 2080.11, "total_tokens": 627584}
{"current_steps": 1540, "total_steps": 16520, "loss": 0.1809, "lr": 0.0009315980629539952, "epoch": 1.8644067796610169, "percentage": 9.32, "elapsed_time": "0:05:02", "remaining_time": "0:49:04", "throughput": 2080.49, "total_tokens": 629728}
{"current_steps": 1545, "total_steps": 16520, "loss": 0.1257, "lr": 0.0009346246973365618, "epoch": 1.8704600484261502, "percentage": 9.35, "elapsed_time": "0:05:03", "remaining_time": "0:49:02", "throughput": 2080.67, "total_tokens": 631744}
{"current_steps": 1550, "total_steps": 16520, "loss": 0.1123, "lr": 0.0009376513317191284, "epoch": 1.8765133171912833, "percentage": 9.38, "elapsed_time": "0:05:04", "remaining_time": "0:49:01", "throughput": 2080.95, "total_tokens": 633856}
{"current_steps": 1555, "total_steps": 16520, "loss": 0.1116, "lr": 0.000940677966101695, "epoch": 1.8825665859564165, "percentage": 9.41, "elapsed_time": "0:05:05", "remaining_time": "0:49:00", "throughput": 2081.22, "total_tokens": 635968}
{"current_steps": 1560, "total_steps": 16520, "loss": 0.1599, "lr": 0.0009437046004842616, "epoch": 1.8886198547215496, "percentage": 9.44, "elapsed_time": "0:05:06", "remaining_time": "0:48:59", "throughput": 2081.23, "total_tokens": 637984}
{"current_steps": 1565, "total_steps": 16520, "loss": 0.1482, "lr": 0.000946731234866828, "epoch": 1.8946731234866827, "percentage": 9.47, "elapsed_time": "0:05:07", "remaining_time": "0:48:58", "throughput": 2081.41, "total_tokens": 640000}
{"current_steps": 1570, "total_steps": 16520, "loss": 0.1716, "lr": 0.0009497578692493947, "epoch": 1.900726392251816, "percentage": 9.5, "elapsed_time": "0:05:08", "remaining_time": "0:48:57", "throughput": 2081.85, "total_tokens": 642176}
{"current_steps": 1575, "total_steps": 16520, "loss": 0.1893, "lr": 0.0009527845036319613, "epoch": 1.9067796610169492, "percentage": 9.53, "elapsed_time": "0:05:09", "remaining_time": "0:48:55", "throughput": 2081.94, "total_tokens": 644160}
{"current_steps": 1580, "total_steps": 16520, "loss": 0.1551, "lr": 0.0009558111380145279, "epoch": 1.9128329297820823, "percentage": 9.56, "elapsed_time": "0:05:10", "remaining_time": "0:48:54", "throughput": 2082.22, "total_tokens": 646272}
{"current_steps": 1585, "total_steps": 16520, "loss": 0.1008, "lr": 0.0009588377723970945, "epoch": 1.9188861985472156, "percentage": 9.59, "elapsed_time": "0:05:11", "remaining_time": "0:48:53", "throughput": 2082.4, "total_tokens": 648288}
{"current_steps": 1590, "total_steps": 16520, "loss": 0.133, "lr": 0.000961864406779661, "epoch": 1.9249394673123486, "percentage": 9.62, "elapsed_time": "0:05:12", "remaining_time": "0:48:52", "throughput": 2082.78, "total_tokens": 650464}
{"current_steps": 1595, "total_steps": 16520, "loss": 0.1033, "lr": 0.0009648910411622275, "epoch": 1.930992736077482, "percentage": 9.65, "elapsed_time": "0:05:13", "remaining_time": "0:48:51", "throughput": 2083.14, "total_tokens": 652608}
{"current_steps": 1600, "total_steps": 16520, "loss": 0.1, "lr": 0.0009679176755447943, "epoch": 1.937046004842615, "percentage": 9.69, "elapsed_time": "0:05:14", "remaining_time": "0:48:50", "throughput": 2083.32, "total_tokens": 654624}
{"current_steps": 1605, "total_steps": 16520, "loss": 0.1525, "lr": 0.0009709443099273609, "epoch": 1.9430992736077481, "percentage": 9.72, "elapsed_time": "0:05:15", "remaining_time": "0:48:48", "throughput": 2083.33, "total_tokens": 656640}
{"current_steps": 1610, "total_steps": 16520, "loss": 0.1286, "lr": 0.0009739709443099273, "epoch": 1.9491525423728815, "percentage": 9.75, "elapsed_time": "0:05:16", "remaining_time": "0:48:47", "throughput": 2083.32, "total_tokens": 658528}
{"current_steps": 1615, "total_steps": 16520, "loss": 0.2488, "lr": 0.000976997578692494, "epoch": 1.9552058111380144, "percentage": 9.78, "elapsed_time": "0:05:17", "remaining_time": "0:48:46", "throughput": 2083.84, "total_tokens": 660736}
{"current_steps": 1620, "total_steps": 16520, "loss": 0.1765, "lr": 0.0009800242130750605, "epoch": 1.9612590799031477, "percentage": 9.81, "elapsed_time": "0:05:18", "remaining_time": "0:48:45", "throughput": 2084.0, "total_tokens": 662816}
{"current_steps": 1625, "total_steps": 16520, "loss": 0.2478, "lr": 0.0009830508474576271, "epoch": 1.9673123486682809, "percentage": 9.84, "elapsed_time": "0:05:18", "remaining_time": "0:48:43", "throughput": 2083.92, "total_tokens": 664672}
{"current_steps": 1630, "total_steps": 16520, "loss": 0.1506, "lr": 0.0009860774818401937, "epoch": 1.973365617433414, "percentage": 9.87, "elapsed_time": "0:05:19", "remaining_time": "0:48:42", "throughput": 2084.01, "total_tokens": 666656}
{"current_steps": 1635, "total_steps": 16520, "loss": 0.1355, "lr": 0.0009891041162227603, "epoch": 1.9794188861985473, "percentage": 9.9, "elapsed_time": "0:05:20", "remaining_time": "0:48:41", "throughput": 2084.02, "total_tokens": 668672}
{"current_steps": 1640, "total_steps": 16520, "loss": 0.1575, "lr": 0.000992130750605327, "epoch": 1.9854721549636802, "percentage": 9.93, "elapsed_time": "0:05:21", "remaining_time": "0:48:39", "throughput": 2084.04, "total_tokens": 670624}
{"current_steps": 1645, "total_steps": 16520, "loss": 0.0741, "lr": 0.0009951573849878933, "epoch": 1.9915254237288136, "percentage": 9.96, "elapsed_time": "0:05:22", "remaining_time": "0:48:38", "throughput": 2084.13, "total_tokens": 672672}
{"current_steps": 1650, "total_steps": 16520, "loss": 0.1145, "lr": 0.0009981840193704601, "epoch": 1.9975786924939467, "percentage": 9.99, "elapsed_time": "0:05:23", "remaining_time": "0:48:37", "throughput": 2084.69, "total_tokens": 674848}
{"current_steps": 1652, "total_steps": 16520, "eval_loss": 0.12094023823738098, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:05:31", "remaining_time": "0:49:47", "throughput": 2034.34, "total_tokens": 675368}
{"current_steps": 1655, "total_steps": 16520, "loss": 0.1444, "lr": 0.0009999999553527582, "epoch": 2.00363196125908, "percentage": 10.02, "elapsed_time": "0:05:33", "remaining_time": "0:49:54", "throughput": 2029.1, "total_tokens": 676584}
{"current_steps": 1660, "total_steps": 16520, "loss": 0.1281, "lr": 0.0009999994530713798, "epoch": 2.009685230024213, "percentage": 10.05, "elapsed_time": "0:05:34", "remaining_time": "0:49:54", "throughput": 2029.12, "total_tokens": 678664}
{"current_steps": 1665, "total_steps": 16520, "loss": 0.1115, "lr": 0.0009999983927001335, "epoch": 2.015738498789346, "percentage": 10.08, "elapsed_time": "0:05:35", "remaining_time": "0:49:52", "throughput": 2029.27, "total_tokens": 680680}
{"current_steps": 1670, "total_steps": 16520, "loss": 0.1057, "lr": 0.0009999967742402027, "epoch": 2.0217917675544794, "percentage": 10.11, "elapsed_time": "0:05:36", "remaining_time": "0:49:50", "throughput": 2029.56, "total_tokens": 682568}
{"current_steps": 1675, "total_steps": 16520, "loss": 0.1071, "lr": 0.000999994597693394, "epoch": 2.0278450363196128, "percentage": 10.14, "elapsed_time": "0:05:37", "remaining_time": "0:49:48", "throughput": 2029.86, "total_tokens": 684584}
{"current_steps": 1680, "total_steps": 16520, "loss": 0.0518, "lr": 0.0009999918630621365, "epoch": 2.0338983050847457, "percentage": 10.17, "elapsed_time": "0:05:38", "remaining_time": "0:49:47", "throughput": 2030.08, "total_tokens": 686504}
{"current_steps": 1685, "total_steps": 16520, "loss": 0.1165, "lr": 0.000999988570349483, "epoch": 2.039951573849879, "percentage": 10.2, "elapsed_time": "0:05:39", "remaining_time": "0:49:45", "throughput": 2030.38, "total_tokens": 688584}
{"current_steps": 1690, "total_steps": 16520, "loss": 0.0662, "lr": 0.0009999847195591082, "epoch": 2.046004842615012, "percentage": 10.23, "elapsed_time": "0:05:40", "remaining_time": "0:49:44", "throughput": 2030.77, "total_tokens": 690696}
{"current_steps": 1695, "total_steps": 16520, "loss": 0.1278, "lr": 0.000999980310695311, "epoch": 2.0520581113801453, "percentage": 10.26, "elapsed_time": "0:05:41", "remaining_time": "0:49:43", "throughput": 2031.31, "total_tokens": 692872}
{"current_steps": 1700, "total_steps": 16520, "loss": 0.1202, "lr": 0.000999975343763012, "epoch": 2.0581113801452786, "percentage": 10.29, "elapsed_time": "0:05:42", "remaining_time": "0:49:42", "throughput": 2031.53, "total_tokens": 694920}
{"current_steps": 1705, "total_steps": 16520, "loss": 0.1069, "lr": 0.0009999698187677553, "epoch": 2.0641646489104115, "percentage": 10.32, "elapsed_time": "0:05:43", "remaining_time": "0:49:40", "throughput": 2031.97, "total_tokens": 697064}
{"current_steps": 1710, "total_steps": 16520, "loss": 0.1036, "lr": 0.000999963735715708, "epoch": 2.070217917675545, "percentage": 10.35, "elapsed_time": "0:05:44", "remaining_time": "0:49:39", "throughput": 2032.59, "total_tokens": 699304}
{"current_steps": 1715, "total_steps": 16520, "loss": 0.0608, "lr": 0.0009999570946136595, "epoch": 2.0762711864406778, "percentage": 10.38, "elapsed_time": "0:05:45", "remaining_time": "0:49:38", "throughput": 2032.89, "total_tokens": 701384}
{"current_steps": 1720, "total_steps": 16520, "loss": 0.0844, "lr": 0.0009999498954690225, "epoch": 2.082324455205811, "percentage": 10.41, "elapsed_time": "0:05:45", "remaining_time": "0:49:37", "throughput": 2033.27, "total_tokens": 703496}
{"current_steps": 1725, "total_steps": 16520, "loss": 0.1326, "lr": 0.000999942138289833, "epoch": 2.0883777239709445, "percentage": 10.44, "elapsed_time": "0:05:46", "remaining_time": "0:49:35", "throughput": 2033.57, "total_tokens": 705576}
{"current_steps": 1730, "total_steps": 16520, "loss": 0.2219, "lr": 0.000999933823084749, "epoch": 2.0944309927360774, "percentage": 10.47, "elapsed_time": "0:05:47", "remaining_time": "0:49:34", "throughput": 2033.75, "total_tokens": 707624}
{"current_steps": 1735, "total_steps": 16520, "loss": 0.2039, "lr": 0.0009999249498630518, "epoch": 2.1004842615012107, "percentage": 10.5, "elapsed_time": "0:05:48", "remaining_time": "0:49:33", "throughput": 2034.2, "total_tokens": 709704}
{"current_steps": 1740, "total_steps": 16520, "loss": 0.1549, "lr": 0.0009999155186346457, "epoch": 2.106537530266344, "percentage": 10.53, "elapsed_time": "0:05:49", "remaining_time": "0:49:31", "throughput": 2034.42, "total_tokens": 711752}
{"current_steps": 1745, "total_steps": 16520, "loss": 0.1036, "lr": 0.0009999055294100578, "epoch": 2.112590799031477, "percentage": 10.56, "elapsed_time": "0:05:50", "remaining_time": "0:49:30", "throughput": 2034.76, "total_tokens": 713832}
{"current_steps": 1750, "total_steps": 16520, "loss": 0.1065, "lr": 0.0009998949822004376, "epoch": 2.1186440677966103, "percentage": 10.59, "elapsed_time": "0:05:51", "remaining_time": "0:49:28", "throughput": 2035.01, "total_tokens": 715848}
{"current_steps": 1755, "total_steps": 16520, "loss": 0.1971, "lr": 0.0009998838770175576, "epoch": 2.124697336561743, "percentage": 10.62, "elapsed_time": "0:05:52", "remaining_time": "0:49:27", "throughput": 2035.27, "total_tokens": 717800}
{"current_steps": 1760, "total_steps": 16520, "loss": 0.1246, "lr": 0.0009998722138738131, "epoch": 2.1307506053268765, "percentage": 10.65, "elapsed_time": "0:05:53", "remaining_time": "0:49:25", "throughput": 2035.46, "total_tokens": 719784}
{"current_steps": 1765, "total_steps": 16520, "loss": 0.8498, "lr": 0.000999859992782223, "epoch": 2.13680387409201, "percentage": 10.68, "elapsed_time": "0:05:54", "remaining_time": "0:49:24", "throughput": 2035.81, "total_tokens": 721832}
{"current_steps": 1770, "total_steps": 16520, "loss": 0.0999, "lr": 0.0009998472137564276, "epoch": 2.142857142857143, "percentage": 10.71, "elapsed_time": "0:05:55", "remaining_time": "0:49:22", "throughput": 2036.08, "total_tokens": 723912}
{"current_steps": 1775, "total_steps": 16520, "loss": 0.1921, "lr": 0.0009998338768106908, "epoch": 2.148910411622276, "percentage": 10.74, "elapsed_time": "0:05:56", "remaining_time": "0:49:21", "throughput": 2036.51, "total_tokens": 725960}
{"current_steps": 1780, "total_steps": 16520, "loss": 0.1311, "lr": 0.000999819981959899, "epoch": 2.154963680387409, "percentage": 10.77, "elapsed_time": "0:05:57", "remaining_time": "0:49:19", "throughput": 2036.54, "total_tokens": 727880}
{"current_steps": 1785, "total_steps": 16520, "loss": 0.1479, "lr": 0.0009998055292195615, "epoch": 2.1610169491525424, "percentage": 10.81, "elapsed_time": "0:05:58", "remaining_time": "0:49:18", "throughput": 2037.05, "total_tokens": 730056}
{"current_steps": 1790, "total_steps": 16520, "loss": 0.0943, "lr": 0.00099979051860581, "epoch": 2.1670702179176757, "percentage": 10.84, "elapsed_time": "0:05:59", "remaining_time": "0:49:16", "throughput": 2037.32, "total_tokens": 732072}
{"current_steps": 1795, "total_steps": 16520, "loss": 0.1107, "lr": 0.0009997749501353991, "epoch": 2.1731234866828086, "percentage": 10.87, "elapsed_time": "0:06:00", "remaining_time": "0:49:14", "throughput": 2037.56, "total_tokens": 733960}
{"current_steps": 1800, "total_steps": 16520, "loss": 0.1785, "lr": 0.0009997588238257061, "epoch": 2.179176755447942, "percentage": 10.9, "elapsed_time": "0:06:01", "remaining_time": "0:49:13", "throughput": 2037.98, "total_tokens": 736104}
{"current_steps": 1805, "total_steps": 16520, "loss": 0.131, "lr": 0.000999742139694731, "epoch": 2.185230024213075, "percentage": 10.93, "elapsed_time": "0:06:02", "remaining_time": "0:49:12", "throughput": 2038.25, "total_tokens": 738120}
{"current_steps": 1810, "total_steps": 16520, "loss": 0.1741, "lr": 0.0009997248977610957, "epoch": 2.1912832929782082, "percentage": 10.96, "elapsed_time": "0:06:03", "remaining_time": "0:49:10", "throughput": 2038.5, "total_tokens": 740136}
{"current_steps": 1815, "total_steps": 16520, "loss": 0.1368, "lr": 0.000999707098044046, "epoch": 2.1973365617433416, "percentage": 10.99, "elapsed_time": "0:06:04", "remaining_time": "0:49:09", "throughput": 2038.93, "total_tokens": 742280}
{"current_steps": 1820, "total_steps": 16520, "loss": 0.0652, "lr": 0.0009996887405634496, "epoch": 2.2033898305084745, "percentage": 11.02, "elapsed_time": "0:06:04", "remaining_time": "0:49:08", "throughput": 2039.27, "total_tokens": 744328}
{"current_steps": 1825, "total_steps": 16520, "loss": 0.1313, "lr": 0.0009996698253397964, "epoch": 2.209443099273608, "percentage": 11.05, "elapsed_time": "0:06:05", "remaining_time": "0:49:06", "throughput": 2039.39, "total_tokens": 746344}
{"current_steps": 1830, "total_steps": 16520, "loss": 0.1058, "lr": 0.0009996503523941993, "epoch": 2.2154963680387407, "percentage": 11.08, "elapsed_time": "0:06:06", "remaining_time": "0:49:05", "throughput": 2039.81, "total_tokens": 748456}
{"current_steps": 1835, "total_steps": 16520, "loss": 0.0946, "lr": 0.0009996303217483938, "epoch": 2.221549636803874, "percentage": 11.11, "elapsed_time": "0:06:07", "remaining_time": "0:49:04", "throughput": 2040.15, "total_tokens": 750568}
{"current_steps": 1840, "total_steps": 16520, "loss": 0.1193, "lr": 0.0009996097334247374, "epoch": 2.2276029055690074, "percentage": 11.14, "elapsed_time": "0:06:08", "remaining_time": "0:49:03", "throughput": 2040.5, "total_tokens": 752712}
{"current_steps": 1845, "total_steps": 16520, "loss": 0.1017, "lr": 0.0009995885874462109, "epoch": 2.2336561743341403, "percentage": 11.17, "elapsed_time": "0:06:09", "remaining_time": "0:49:01", "throughput": 2041.12, "total_tokens": 754888}
{"current_steps": 1850, "total_steps": 16520, "loss": 0.1035, "lr": 0.0009995668838364165, "epoch": 2.2397094430992737, "percentage": 11.2, "elapsed_time": "0:06:10", "remaining_time": "0:49:00", "throughput": 2041.69, "total_tokens": 757064}
{"current_steps": 1855, "total_steps": 16520, "loss": 0.108, "lr": 0.0009995446226195796, "epoch": 2.2457627118644066, "percentage": 11.23, "elapsed_time": "0:06:11", "remaining_time": "0:48:59", "throughput": 2041.66, "total_tokens": 759016}
{"current_steps": 1860, "total_steps": 16520, "loss": 0.1926, "lr": 0.000999521803820548, "epoch": 2.25181598062954, "percentage": 11.26, "elapsed_time": "0:06:12", "remaining_time": "0:48:57", "throughput": 2042.07, "total_tokens": 761160}
{"current_steps": 1865, "total_steps": 16520, "loss": 0.0862, "lr": 0.0009994984274647911, "epoch": 2.2578692493946733, "percentage": 11.29, "elapsed_time": "0:06:13", "remaining_time": "0:48:56", "throughput": 2042.39, "total_tokens": 763208}
{"current_steps": 1870, "total_steps": 16520, "loss": 0.1805, "lr": 0.0009994744935784017, "epoch": 2.263922518159806, "percentage": 11.32, "elapsed_time": "0:06:14", "remaining_time": "0:48:55", "throughput": 2042.85, "total_tokens": 765352}
{"current_steps": 1875, "total_steps": 16520, "loss": 0.1471, "lr": 0.0009994500021880937, "epoch": 2.2699757869249395, "percentage": 11.35, "elapsed_time": "0:06:15", "remaining_time": "0:48:53", "throughput": 2043.02, "total_tokens": 767272}
{"current_steps": 1880, "total_steps": 16520, "loss": 0.1154, "lr": 0.0009994249533212046, "epoch": 2.2760290556900724, "percentage": 11.38, "elapsed_time": "0:06:16", "remaining_time": "0:48:51", "throughput": 2043.2, "total_tokens": 769256}
{"current_steps": 1885, "total_steps": 16520, "loss": 0.0984, "lr": 0.0009993993470056928, "epoch": 2.2820823244552058, "percentage": 11.41, "elapsed_time": "0:06:17", "remaining_time": "0:48:50", "throughput": 2043.53, "total_tokens": 771368}
{"current_steps": 1890, "total_steps": 16520, "loss": 0.1148, "lr": 0.0009993731832701402, "epoch": 2.288135593220339, "percentage": 11.44, "elapsed_time": "0:06:18", "remaining_time": "0:48:49", "throughput": 2043.77, "total_tokens": 773448}
{"current_steps": 1895, "total_steps": 16520, "loss": 0.0715, "lr": 0.0009993464621437498, "epoch": 2.294188861985472, "percentage": 11.47, "elapsed_time": "0:06:19", "remaining_time": "0:48:48", "throughput": 2044.23, "total_tokens": 775624}
{"current_steps": 1900, "total_steps": 16520, "loss": 0.0919, "lr": 0.0009993191836563475, "epoch": 2.3002421307506054, "percentage": 11.5, "elapsed_time": "0:06:20", "remaining_time": "0:48:46", "throughput": 2044.54, "total_tokens": 777672}
{"current_steps": 1905, "total_steps": 16520, "loss": 0.1667, "lr": 0.000999291347838381, "epoch": 2.3062953995157383, "percentage": 11.53, "elapsed_time": "0:06:21", "remaining_time": "0:48:45", "throughput": 2044.79, "total_tokens": 779752}
{"current_steps": 1910, "total_steps": 16520, "loss": 0.1351, "lr": 0.00099926295472092, "epoch": 2.3123486682808716, "percentage": 11.56, "elapsed_time": "0:06:22", "remaining_time": "0:48:43", "throughput": 2045.03, "total_tokens": 781704}
{"current_steps": 1915, "total_steps": 16520, "loss": 0.162, "lr": 0.0009992340043356563, "epoch": 2.318401937046005, "percentage": 11.59, "elapsed_time": "0:06:23", "remaining_time": "0:48:42", "throughput": 2045.13, "total_tokens": 783656}
{"current_steps": 1920, "total_steps": 16520, "loss": 0.1185, "lr": 0.0009992044967149039, "epoch": 2.324455205811138, "percentage": 11.62, "elapsed_time": "0:06:24", "remaining_time": "0:48:41", "throughput": 2045.23, "total_tokens": 785672}
{"current_steps": 1925, "total_steps": 16520, "loss": 0.1626, "lr": 0.0009991744318915987, "epoch": 2.330508474576271, "percentage": 11.65, "elapsed_time": "0:06:25", "remaining_time": "0:48:39", "throughput": 2045.47, "total_tokens": 787752}
{"current_steps": 1930, "total_steps": 16520, "loss": 0.1575, "lr": 0.0009991438098992983, "epoch": 2.3365617433414045, "percentage": 11.68, "elapsed_time": "0:06:26", "remaining_time": "0:48:38", "throughput": 2045.5, "total_tokens": 789736}
{"current_steps": 1935, "total_steps": 16520, "loss": 0.1182, "lr": 0.0009991126307721824, "epoch": 2.3426150121065374, "percentage": 11.71, "elapsed_time": "0:06:27", "remaining_time": "0:48:37", "throughput": 2045.66, "total_tokens": 791720}
{"current_steps": 1940, "total_steps": 16520, "loss": 0.0781, "lr": 0.000999080894545053, "epoch": 2.348668280871671, "percentage": 11.74, "elapsed_time": "0:06:27", "remaining_time": "0:48:35", "throughput": 2046.04, "total_tokens": 793864}
{"current_steps": 1945, "total_steps": 16520, "loss": 0.1106, "lr": 0.0009990486012533327, "epoch": 2.3547215496368037, "percentage": 11.77, "elapsed_time": "0:06:28", "remaining_time": "0:48:34", "throughput": 2046.14, "total_tokens": 795816}
{"current_steps": 1950, "total_steps": 16520, "loss": 0.2057, "lr": 0.000999015750933067, "epoch": 2.360774818401937, "percentage": 11.8, "elapsed_time": "0:06:29", "remaining_time": "0:48:33", "throughput": 2046.31, "total_tokens": 797864}
{"current_steps": 1955, "total_steps": 16520, "loss": 0.183, "lr": 0.0009989823436209232, "epoch": 2.3668280871670704, "percentage": 11.83, "elapsed_time": "0:06:30", "remaining_time": "0:48:31", "throughput": 2046.53, "total_tokens": 799816}
{"current_steps": 1960, "total_steps": 16520, "loss": 0.1626, "lr": 0.0009989483793541893, "epoch": 2.3728813559322033, "percentage": 11.86, "elapsed_time": "0:06:31", "remaining_time": "0:48:30", "throughput": 2046.76, "total_tokens": 801896}
{"current_steps": 1965, "total_steps": 16520, "loss": 0.1192, "lr": 0.000998913858170776, "epoch": 2.3789346246973366, "percentage": 11.89, "elapsed_time": "0:06:32", "remaining_time": "0:48:28", "throughput": 2046.99, "total_tokens": 803848}
{"current_steps": 1970, "total_steps": 16520, "loss": 0.1265, "lr": 0.0009988787801092148, "epoch": 2.38498789346247, "percentage": 11.92, "elapsed_time": "0:06:33", "remaining_time": "0:48:27", "throughput": 2047.21, "total_tokens": 805864}
{"current_steps": 1975, "total_steps": 16520, "loss": 0.1379, "lr": 0.0009988431452086595, "epoch": 2.391041162227603, "percentage": 11.96, "elapsed_time": "0:06:34", "remaining_time": "0:48:26", "throughput": 2047.5, "total_tokens": 807976}
{"current_steps": 1980, "total_steps": 16520, "loss": 0.0727, "lr": 0.000998806953508885, "epoch": 2.3970944309927362, "percentage": 11.99, "elapsed_time": "0:06:35", "remaining_time": "0:48:24", "throughput": 2047.65, "total_tokens": 809960}
{"current_steps": 1985, "total_steps": 16520, "loss": 0.0878, "lr": 0.000998770205050288, "epoch": 2.403147699757869, "percentage": 12.02, "elapsed_time": "0:06:36", "remaining_time": "0:48:23", "throughput": 2048.08, "total_tokens": 812136}
{"current_steps": 1990, "total_steps": 16520, "loss": 0.1242, "lr": 0.0009987328998738857, "epoch": 2.4092009685230025, "percentage": 12.05, "elapsed_time": "0:06:37", "remaining_time": "0:48:22", "throughput": 2048.31, "total_tokens": 814216}
{"current_steps": 1995, "total_steps": 16520, "loss": 0.1291, "lr": 0.0009986950380213183, "epoch": 2.415254237288136, "percentage": 12.08, "elapsed_time": "0:06:38", "remaining_time": "0:48:21", "throughput": 2048.51, "total_tokens": 816232}
{"current_steps": 2000, "total_steps": 16520, "loss": 0.1393, "lr": 0.0009986566195348458, "epoch": 2.4213075060532687, "percentage": 12.11, "elapsed_time": "0:06:39", "remaining_time": "0:48:19", "throughput": 2048.58, "total_tokens": 818248}
{"current_steps": 2005, "total_steps": 16520, "loss": 0.1849, "lr": 0.0009986176444573508, "epoch": 2.427360774818402, "percentage": 12.14, "elapsed_time": "0:06:40", "remaining_time": "0:48:18", "throughput": 2048.8, "total_tokens": 820328}
{"current_steps": 2010, "total_steps": 16520, "loss": 0.0656, "lr": 0.0009985781128323359, "epoch": 2.433414043583535, "percentage": 12.17, "elapsed_time": "0:06:41", "remaining_time": "0:48:17", "throughput": 2048.96, "total_tokens": 822376}
{"current_steps": 2015, "total_steps": 16520, "loss": 0.1081, "lr": 0.0009985380247039262, "epoch": 2.4394673123486683, "percentage": 12.2, "elapsed_time": "0:06:42", "remaining_time": "0:48:16", "throughput": 2049.18, "total_tokens": 824456}
{"current_steps": 2020, "total_steps": 16520, "loss": 0.0551, "lr": 0.0009984973801168667, "epoch": 2.4455205811138017, "percentage": 12.23, "elapsed_time": "0:06:43", "remaining_time": "0:48:14", "throughput": 2049.39, "total_tokens": 826472}
{"current_steps": 2025, "total_steps": 16520, "loss": 0.0861, "lr": 0.0009984561791165246, "epoch": 2.4515738498789346, "percentage": 12.26, "elapsed_time": "0:06:44", "remaining_time": "0:48:13", "throughput": 2049.61, "total_tokens": 828488}
{"current_steps": 2030, "total_steps": 16520, "loss": 0.1361, "lr": 0.0009984144217488873, "epoch": 2.457627118644068, "percentage": 12.29, "elapsed_time": "0:06:45", "remaining_time": "0:48:12", "throughput": 2050.02, "total_tokens": 830600}
{"current_steps": 2035, "total_steps": 16520, "loss": 0.1795, "lr": 0.000998372108060564, "epoch": 2.463680387409201, "percentage": 12.32, "elapsed_time": "0:06:46", "remaining_time": "0:48:10", "throughput": 2049.97, "total_tokens": 832552}
{"current_steps": 2040, "total_steps": 16520, "loss": 0.0965, "lr": 0.0009983292380987838, "epoch": 2.469733656174334, "percentage": 12.35, "elapsed_time": "0:06:47", "remaining_time": "0:48:09", "throughput": 2050.31, "total_tokens": 834632}
{"current_steps": 2045, "total_steps": 16520, "loss": 0.1163, "lr": 0.000998285811911398, "epoch": 2.4757869249394675, "percentage": 12.38, "elapsed_time": "0:06:48", "remaining_time": "0:48:08", "throughput": 2050.88, "total_tokens": 836904}
{"current_steps": 2050, "total_steps": 16520, "loss": 0.1329, "lr": 0.0009982418295468776, "epoch": 2.4818401937046004, "percentage": 12.41, "elapsed_time": "0:06:49", "remaining_time": "0:48:07", "throughput": 2051.24, "total_tokens": 839016}
{"current_steps": 2055, "total_steps": 16520, "loss": 0.1047, "lr": 0.0009981972910543151, "epoch": 2.4878934624697338, "percentage": 12.44, "elapsed_time": "0:06:49", "remaining_time": "0:48:05", "throughput": 2051.45, "total_tokens": 841096}
{"current_steps": 2060, "total_steps": 16520, "loss": 0.1338, "lr": 0.0009981521964834235, "epoch": 2.4939467312348667, "percentage": 12.47, "elapsed_time": "0:06:50", "remaining_time": "0:48:04", "throughput": 2051.57, "total_tokens": 843080}
{"current_steps": 2065, "total_steps": 16520, "loss": 0.0792, "lr": 0.0009981065458845367, "epoch": 2.5, "percentage": 12.5, "elapsed_time": "0:06:51", "remaining_time": "0:48:03", "throughput": 2052.04, "total_tokens": 845224}
{"current_steps": 2070, "total_steps": 16520, "loss": 0.1301, "lr": 0.0009980603393086086, "epoch": 2.5060532687651333, "percentage": 12.53, "elapsed_time": "0:06:52", "remaining_time": "0:48:02", "throughput": 2052.31, "total_tokens": 847336}
{"current_steps": 2075, "total_steps": 16520, "loss": 0.0985, "lr": 0.0009980135768072143, "epoch": 2.5121065375302662, "percentage": 12.56, "elapsed_time": "0:06:53", "remaining_time": "0:48:00", "throughput": 2052.32, "total_tokens": 849320}
{"current_steps": 2080, "total_steps": 16520, "loss": 0.1424, "lr": 0.0009979662584325493, "epoch": 2.5181598062953996, "percentage": 12.59, "elapsed_time": "0:06:54", "remaining_time": "0:47:59", "throughput": 2052.46, "total_tokens": 851368}
{"current_steps": 2085, "total_steps": 16520, "loss": 0.1453, "lr": 0.0009979183842374294, "epoch": 2.5242130750605325, "percentage": 12.62, "elapsed_time": "0:06:55", "remaining_time": "0:47:58", "throughput": 2052.67, "total_tokens": 853448}
{"current_steps": 2090, "total_steps": 16520, "loss": 0.0904, "lr": 0.000997869954275291, "epoch": 2.530266343825666, "percentage": 12.65, "elapsed_time": "0:06:56", "remaining_time": "0:47:57", "throughput": 2052.91, "total_tokens": 855496}
{"current_steps": 2095, "total_steps": 16520, "loss": 0.0732, "lr": 0.0009978209686001902, "epoch": 2.536319612590799, "percentage": 12.68, "elapsed_time": "0:06:57", "remaining_time": "0:47:56", "throughput": 2053.12, "total_tokens": 857608}
{"current_steps": 2100, "total_steps": 16520, "loss": 0.0949, "lr": 0.0009977714272668046, "epoch": 2.542372881355932, "percentage": 12.71, "elapsed_time": "0:06:58", "remaining_time": "0:47:54", "throughput": 2053.52, "total_tokens": 859720}
{"current_steps": 2105, "total_steps": 16520, "loss": 0.0849, "lr": 0.0009977213303304306, "epoch": 2.5484261501210654, "percentage": 12.74, "elapsed_time": "0:06:59", "remaining_time": "0:47:53", "throughput": 2053.58, "total_tokens": 861736}
{"current_steps": 2110, "total_steps": 16520, "loss": 0.0598, "lr": 0.000997670677846986, "epoch": 2.5544794188861983, "percentage": 12.77, "elapsed_time": "0:07:00", "remaining_time": "0:47:52", "throughput": 2053.91, "total_tokens": 863880}
{"current_steps": 2115, "total_steps": 16520, "loss": 0.1704, "lr": 0.0009976194698730078, "epoch": 2.5605326876513317, "percentage": 12.8, "elapsed_time": "0:07:01", "remaining_time": "0:47:51", "throughput": 2053.89, "total_tokens": 865864}
{"current_steps": 2120, "total_steps": 16520, "loss": 0.2083, "lr": 0.0009975677064656535, "epoch": 2.566585956416465, "percentage": 12.83, "elapsed_time": "0:07:02", "remaining_time": "0:47:49", "throughput": 2054.21, "total_tokens": 867944}
{"current_steps": 2125, "total_steps": 16520, "loss": 0.1589, "lr": 0.0009975153876827009, "epoch": 2.572639225181598, "percentage": 12.86, "elapsed_time": "0:07:03", "remaining_time": "0:47:48", "throughput": 2054.46, "total_tokens": 869992}
{"current_steps": 2130, "total_steps": 16520, "loss": 0.1494, "lr": 0.0009974625135825462, "epoch": 2.5786924939467313, "percentage": 12.89, "elapsed_time": "0:07:04", "remaining_time": "0:47:47", "throughput": 2054.66, "total_tokens": 872072}
{"current_steps": 2135, "total_steps": 16520, "loss": 0.124, "lr": 0.0009974090842242071, "epoch": 2.584745762711864, "percentage": 12.92, "elapsed_time": "0:07:05", "remaining_time": "0:47:46", "throughput": 2054.92, "total_tokens": 874120}
{"current_steps": 2140, "total_steps": 16520, "loss": 0.1077, "lr": 0.0009973550996673203, "epoch": 2.5907990314769975, "percentage": 12.95, "elapsed_time": "0:07:06", "remaining_time": "0:47:44", "throughput": 2054.93, "total_tokens": 876104}
{"current_steps": 2145, "total_steps": 16520, "loss": 0.1377, "lr": 0.0009973005599721424, "epoch": 2.596852300242131, "percentage": 12.98, "elapsed_time": "0:07:07", "remaining_time": "0:47:43", "throughput": 2055.46, "total_tokens": 878248}
{"current_steps": 2150, "total_steps": 16520, "loss": 0.1422, "lr": 0.0009972454651995498, "epoch": 2.6029055690072638, "percentage": 13.01, "elapsed_time": "0:07:08", "remaining_time": "0:47:42", "throughput": 2055.64, "total_tokens": 880264}
{"current_steps": 2155, "total_steps": 16520, "loss": 0.096, "lr": 0.0009971898154110376, "epoch": 2.608958837772397, "percentage": 13.04, "elapsed_time": "0:07:09", "remaining_time": "0:47:41", "throughput": 2056.23, "total_tokens": 882568}
{"current_steps": 2160, "total_steps": 16520, "loss": 0.1164, "lr": 0.0009971336106687218, "epoch": 2.61501210653753, "percentage": 13.08, "elapsed_time": "0:07:10", "remaining_time": "0:47:40", "throughput": 2056.51, "total_tokens": 884712}
{"current_steps": 2165, "total_steps": 16520, "loss": 0.1362, "lr": 0.0009970768510353366, "epoch": 2.6210653753026634, "percentage": 13.11, "elapsed_time": "0:07:11", "remaining_time": "0:47:38", "throughput": 2056.83, "total_tokens": 886856}
{"current_steps": 2170, "total_steps": 16520, "loss": 0.0964, "lr": 0.0009970195365742358, "epoch": 2.6271186440677967, "percentage": 13.14, "elapsed_time": "0:07:12", "remaining_time": "0:47:37", "throughput": 2057.22, "total_tokens": 889064}
{"current_steps": 2175, "total_steps": 16520, "loss": 0.1166, "lr": 0.0009969616673493932, "epoch": 2.6331719128329296, "percentage": 13.17, "elapsed_time": "0:07:13", "remaining_time": "0:47:36", "throughput": 2057.4, "total_tokens": 891080}
{"current_steps": 2180, "total_steps": 16520, "loss": 0.1621, "lr": 0.000996903243425401, "epoch": 2.639225181598063, "percentage": 13.2, "elapsed_time": "0:07:14", "remaining_time": "0:47:34", "throughput": 2057.58, "total_tokens": 893032}
{"current_steps": 2185, "total_steps": 16520, "loss": 0.0888, "lr": 0.0009968442648674713, "epoch": 2.645278450363196, "percentage": 13.23, "elapsed_time": "0:07:14", "remaining_time": "0:47:33", "throughput": 2057.65, "total_tokens": 894920}
{"current_steps": 2190, "total_steps": 16520, "loss": 0.1281, "lr": 0.0009967847317414343, "epoch": 2.651331719128329, "percentage": 13.26, "elapsed_time": "0:07:15", "remaining_time": "0:47:31", "throughput": 2057.76, "total_tokens": 896840}
{"current_steps": 2195, "total_steps": 16520, "loss": 0.0607, "lr": 0.00099672464411374, "epoch": 2.6573849878934626, "percentage": 13.29, "elapsed_time": "0:07:16", "remaining_time": "0:47:30", "throughput": 2057.77, "total_tokens": 898760}
{"current_steps": 2200, "total_steps": 16520, "loss": 0.0914, "lr": 0.0009966640020514573, "epoch": 2.663438256658596, "percentage": 13.32, "elapsed_time": "0:07:17", "remaining_time": "0:47:28", "throughput": 2057.88, "total_tokens": 900680}
{"current_steps": 2205, "total_steps": 16520, "loss": 0.0639, "lr": 0.0009966028056222734, "epoch": 2.669491525423729, "percentage": 13.35, "elapsed_time": "0:07:18", "remaining_time": "0:47:27", "throughput": 2058.01, "total_tokens": 902728}
{"current_steps": 2210, "total_steps": 16520, "loss": 0.0979, "lr": 0.0009965410548944944, "epoch": 2.6755447941888617, "percentage": 13.38, "elapsed_time": "0:07:19", "remaining_time": "0:47:26", "throughput": 2058.31, "total_tokens": 904808}
{"current_steps": 2215, "total_steps": 16520, "loss": 0.1082, "lr": 0.0009964787499370457, "epoch": 2.681598062953995, "percentage": 13.41, "elapsed_time": "0:07:20", "remaining_time": "0:47:25", "throughput": 2058.38, "total_tokens": 906824}
{"current_steps": 2220, "total_steps": 16520, "loss": 0.0962, "lr": 0.0009964158908194708, "epoch": 2.6876513317191284, "percentage": 13.44, "elapsed_time": "0:07:21", "remaining_time": "0:47:23", "throughput": 2058.68, "total_tokens": 908904}
{"current_steps": 2225, "total_steps": 16520, "loss": 0.1768, "lr": 0.0009963524776119316, "epoch": 2.6937046004842617, "percentage": 13.47, "elapsed_time": "0:07:22", "remaining_time": "0:47:22", "throughput": 2058.94, "total_tokens": 910984}
{"current_steps": 2230, "total_steps": 16520, "loss": 0.1368, "lr": 0.0009962885103852093, "epoch": 2.6997578692493946, "percentage": 13.5, "elapsed_time": "0:07:23", "remaining_time": "0:47:21", "throughput": 2059.06, "total_tokens": 912968}
{"current_steps": 2235, "total_steps": 16520, "loss": 0.1255, "lr": 0.0009962239892107024, "epoch": 2.705811138014528, "percentage": 13.53, "elapsed_time": "0:07:24", "remaining_time": "0:47:20", "throughput": 2059.24, "total_tokens": 915048}
{"current_steps": 2240, "total_steps": 16520, "loss": 0.1165, "lr": 0.0009961589141604282, "epoch": 2.711864406779661, "percentage": 13.56, "elapsed_time": "0:07:25", "remaining_time": "0:47:18", "throughput": 2059.66, "total_tokens": 917160}
{"current_steps": 2245, "total_steps": 16520, "loss": 0.1215, "lr": 0.0009960932853070223, "epoch": 2.7179176755447942, "percentage": 13.59, "elapsed_time": "0:07:26", "remaining_time": "0:47:17", "throughput": 2059.64, "total_tokens": 919080}
{"current_steps": 2250, "total_steps": 16520, "loss": 0.1027, "lr": 0.0009960271027237386, "epoch": 2.7239709443099276, "percentage": 13.62, "elapsed_time": "0:07:27", "remaining_time": "0:47:16", "throughput": 2059.88, "total_tokens": 921128}
{"current_steps": 2255, "total_steps": 16520, "loss": 0.0704, "lr": 0.0009959603664844486, "epoch": 2.7300242130750605, "percentage": 13.65, "elapsed_time": "0:07:28", "remaining_time": "0:47:14", "throughput": 2060.0, "total_tokens": 923176}
{"current_steps": 2260, "total_steps": 16520, "loss": 0.0952, "lr": 0.000995893076663642, "epoch": 2.736077481840194, "percentage": 13.68, "elapsed_time": "0:07:29", "remaining_time": "0:47:13", "throughput": 2060.24, "total_tokens": 925288}
{"current_steps": 2265, "total_steps": 16520, "loss": 0.0958, "lr": 0.0009958252333364267, "epoch": 2.7421307506053267, "percentage": 13.71, "elapsed_time": "0:07:30", "remaining_time": "0:47:12", "throughput": 2060.35, "total_tokens": 927336}
{"current_steps": 2270, "total_steps": 16520, "loss": 0.1498, "lr": 0.0009957568365785278, "epoch": 2.74818401937046, "percentage": 13.74, "elapsed_time": "0:07:31", "remaining_time": "0:47:11", "throughput": 2060.52, "total_tokens": 929416}
{"current_steps": 2275, "total_steps": 16520, "loss": 0.0773, "lr": 0.0009956878864662887, "epoch": 2.7542372881355934, "percentage": 13.77, "elapsed_time": "0:07:31", "remaining_time": "0:47:10", "throughput": 2060.5, "total_tokens": 931336}
{"current_steps": 2280, "total_steps": 16520, "loss": 0.0874, "lr": 0.00099561838307667, "epoch": 2.7602905569007263, "percentage": 13.8, "elapsed_time": "0:07:32", "remaining_time": "0:47:08", "throughput": 2060.73, "total_tokens": 933384}
{"current_steps": 2285, "total_steps": 16520, "loss": 0.0929, "lr": 0.0009955483264872502, "epoch": 2.7663438256658597, "percentage": 13.83, "elapsed_time": "0:07:33", "remaining_time": "0:47:07", "throughput": 2060.85, "total_tokens": 935432}
{"current_steps": 2290, "total_steps": 16520, "loss": 0.1015, "lr": 0.0009954777167762252, "epoch": 2.7723970944309926, "percentage": 13.86, "elapsed_time": "0:07:34", "remaining_time": "0:47:06", "throughput": 2061.08, "total_tokens": 937480}
{"current_steps": 2295, "total_steps": 16520, "loss": 0.0837, "lr": 0.000995406554022408, "epoch": 2.778450363196126, "percentage": 13.89, "elapsed_time": "0:07:35", "remaining_time": "0:47:04", "throughput": 2061.18, "total_tokens": 939336}
{"current_steps": 2300, "total_steps": 16520, "loss": 0.0921, "lr": 0.0009953348383052291, "epoch": 2.7845036319612593, "percentage": 13.92, "elapsed_time": "0:07:36", "remaining_time": "0:47:03", "throughput": 2061.23, "total_tokens": 941288}
{"current_steps": 2305, "total_steps": 16520, "loss": 0.087, "lr": 0.0009952625697047365, "epoch": 2.790556900726392, "percentage": 13.95, "elapsed_time": "0:07:37", "remaining_time": "0:47:02", "throughput": 2061.39, "total_tokens": 943368}
{"current_steps": 2310, "total_steps": 16520, "loss": 0.1261, "lr": 0.0009951897483015948, "epoch": 2.7966101694915255, "percentage": 13.98, "elapsed_time": "0:07:38", "remaining_time": "0:47:00", "throughput": 2061.61, "total_tokens": 945352}
{"current_steps": 2315, "total_steps": 16520, "loss": 0.0744, "lr": 0.0009951163741770861, "epoch": 2.8026634382566584, "percentage": 14.01, "elapsed_time": "0:07:39", "remaining_time": "0:46:59", "throughput": 2061.84, "total_tokens": 947464}
{"current_steps": 2320, "total_steps": 16520, "loss": 0.1569, "lr": 0.0009950424474131088, "epoch": 2.8087167070217918, "percentage": 14.04, "elapsed_time": "0:07:40", "remaining_time": "0:46:58", "throughput": 2062.06, "total_tokens": 949576}
{"current_steps": 2325, "total_steps": 16520, "loss": 0.1168, "lr": 0.000994967968092179, "epoch": 2.814769975786925, "percentage": 14.07, "elapsed_time": "0:07:41", "remaining_time": "0:46:57", "throughput": 2062.06, "total_tokens": 951560}
{"current_steps": 2330, "total_steps": 16520, "loss": 0.1034, "lr": 0.0009948929362974287, "epoch": 2.820823244552058, "percentage": 14.1, "elapsed_time": "0:07:42", "remaining_time": "0:46:56", "throughput": 2062.11, "total_tokens": 953576}
{"current_steps": 2335, "total_steps": 16520, "loss": 0.1166, "lr": 0.0009948173521126071, "epoch": 2.8268765133171914, "percentage": 14.13, "elapsed_time": "0:07:43", "remaining_time": "0:46:54", "throughput": 2062.27, "total_tokens": 955464}
{"current_steps": 2340, "total_steps": 16520, "loss": 0.0746, "lr": 0.00099474121562208, "epoch": 2.8329297820823243, "percentage": 14.16, "elapsed_time": "0:07:44", "remaining_time": "0:46:53", "throughput": 2062.5, "total_tokens": 957576}
{"current_steps": 2345, "total_steps": 16520, "loss": 0.0863, "lr": 0.0009946645269108293, "epoch": 2.8389830508474576, "percentage": 14.19, "elapsed_time": "0:07:45", "remaining_time": "0:46:52", "throughput": 2062.84, "total_tokens": 959688}
{"current_steps": 2350, "total_steps": 16520, "loss": 0.0855, "lr": 0.0009945872860644537, "epoch": 2.845036319612591, "percentage": 14.23, "elapsed_time": "0:07:46", "remaining_time": "0:46:51", "throughput": 2062.99, "total_tokens": 961768}
{"current_steps": 2355, "total_steps": 16520, "loss": 0.0744, "lr": 0.0009945094931691678, "epoch": 2.851089588377724, "percentage": 14.26, "elapsed_time": "0:07:47", "remaining_time": "0:46:49", "throughput": 2062.93, "total_tokens": 963720}
{"current_steps": 2360, "total_steps": 16520, "loss": 0.0853, "lr": 0.0009944311483118023, "epoch": 2.857142857142857, "percentage": 14.29, "elapsed_time": "0:07:48", "remaining_time": "0:46:48", "throughput": 2063.03, "total_tokens": 965704}
{"current_steps": 2365, "total_steps": 16520, "loss": 0.1966, "lr": 0.0009943522515798047, "epoch": 2.86319612590799, "percentage": 14.32, "elapsed_time": "0:07:49", "remaining_time": "0:46:47", "throughput": 2063.2, "total_tokens": 967784}
{"current_steps": 2370, "total_steps": 16520, "loss": 0.1242, "lr": 0.0009942728030612378, "epoch": 2.8692493946731235, "percentage": 14.35, "elapsed_time": "0:07:50", "remaining_time": "0:46:46", "throughput": 2063.53, "total_tokens": 969960}
{"current_steps": 2375, "total_steps": 16520, "loss": 0.0725, "lr": 0.0009941928028447805, "epoch": 2.875302663438257, "percentage": 14.38, "elapsed_time": "0:07:51", "remaining_time": "0:46:45", "throughput": 2063.89, "total_tokens": 972168}
{"current_steps": 2380, "total_steps": 16520, "loss": 0.2029, "lr": 0.0009941122510197277, "epoch": 2.8813559322033897, "percentage": 14.41, "elapsed_time": "0:07:51", "remaining_time": "0:46:44", "throughput": 2064.22, "total_tokens": 974280}
{"current_steps": 2385, "total_steps": 16520, "loss": 0.0634, "lr": 0.0009940311476759895, "epoch": 2.887409200968523, "percentage": 14.44, "elapsed_time": "0:07:52", "remaining_time": "0:46:42", "throughput": 2064.61, "total_tokens": 976424}
{"current_steps": 2390, "total_steps": 16520, "loss": 0.1744, "lr": 0.0009939494929040922, "epoch": 2.893462469733656, "percentage": 14.47, "elapsed_time": "0:07:53", "remaining_time": "0:46:41", "throughput": 2064.77, "total_tokens": 978504}
{"current_steps": 2395, "total_steps": 16520, "loss": 0.1355, "lr": 0.0009938672867951773, "epoch": 2.8995157384987893, "percentage": 14.5, "elapsed_time": "0:07:54", "remaining_time": "0:46:40", "throughput": 2064.87, "total_tokens": 980552}
{"current_steps": 2400, "total_steps": 16520, "loss": 0.075, "lr": 0.0009937845294410012, "epoch": 2.9055690072639226, "percentage": 14.53, "elapsed_time": "0:07:55", "remaining_time": "0:46:39", "throughput": 2064.91, "total_tokens": 982568}
{"current_steps": 2405, "total_steps": 16520, "loss": 0.1539, "lr": 0.000993701220933937, "epoch": 2.9116222760290555, "percentage": 14.56, "elapsed_time": "0:07:56", "remaining_time": "0:46:38", "throughput": 2064.96, "total_tokens": 984584}
{"current_steps": 2410, "total_steps": 16520, "loss": 0.1337, "lr": 0.000993617361366971, "epoch": 2.917675544794189, "percentage": 14.59, "elapsed_time": "0:07:57", "remaining_time": "0:46:37", "throughput": 2064.87, "total_tokens": 986536}
{"current_steps": 2415, "total_steps": 16520, "loss": 0.0879, "lr": 0.0009935329508337066, "epoch": 2.923728813559322, "percentage": 14.62, "elapsed_time": "0:07:58", "remaining_time": "0:46:35", "throughput": 2065.15, "total_tokens": 988616}
{"current_steps": 2420, "total_steps": 16520, "loss": 0.1501, "lr": 0.0009934479894283606, "epoch": 2.929782082324455, "percentage": 14.65, "elapsed_time": "0:07:59", "remaining_time": "0:46:34", "throughput": 2065.3, "total_tokens": 990568}
{"current_steps": 2425, "total_steps": 16520, "loss": 0.0681, "lr": 0.0009933624772457657, "epoch": 2.9358353510895885, "percentage": 14.68, "elapsed_time": "0:08:00", "remaining_time": "0:46:33", "throughput": 2065.4, "total_tokens": 992616}
{"current_steps": 2430, "total_steps": 16520, "loss": 0.1534, "lr": 0.0009932764143813686, "epoch": 2.9418886198547214, "percentage": 14.71, "elapsed_time": "0:08:01", "remaining_time": "0:46:32", "throughput": 2065.62, "total_tokens": 994760}
{"current_steps": 2435, "total_steps": 16520, "loss": 0.0788, "lr": 0.0009931898009312313, "epoch": 2.9479418886198547, "percentage": 14.74, "elapsed_time": "0:08:02", "remaining_time": "0:46:31", "throughput": 2065.66, "total_tokens": 996712}
{"current_steps": 2440, "total_steps": 16520, "loss": 0.0655, "lr": 0.00099310263699203, "epoch": 2.9539951573849876, "percentage": 14.77, "elapsed_time": "0:08:03", "remaining_time": "0:46:29", "throughput": 2065.87, "total_tokens": 998824}
{"current_steps": 2445, "total_steps": 16520, "loss": 0.1404, "lr": 0.0009930149226610554, "epoch": 2.960048426150121, "percentage": 14.8, "elapsed_time": "0:08:04", "remaining_time": "0:46:28", "throughput": 2065.94, "total_tokens": 1000808}
{"current_steps": 2450, "total_steps": 16520, "loss": 0.161, "lr": 0.0009929266580362126, "epoch": 2.9661016949152543, "percentage": 14.83, "elapsed_time": "0:08:05", "remaining_time": "0:46:27", "throughput": 2066.13, "total_tokens": 1002856}
{"current_steps": 2455, "total_steps": 16520, "loss": 0.1161, "lr": 0.000992837843216021, "epoch": 2.9721549636803877, "percentage": 14.86, "elapsed_time": "0:08:06", "remaining_time": "0:46:26", "throughput": 2066.21, "total_tokens": 1004840}
{"current_steps": 2460, "total_steps": 16520, "loss": 0.0608, "lr": 0.0009927484782996138, "epoch": 2.9782082324455206, "percentage": 14.89, "elapsed_time": "0:08:07", "remaining_time": "0:46:24", "throughput": 2066.28, "total_tokens": 1006824}
{"current_steps": 2465, "total_steps": 16520, "loss": 0.1124, "lr": 0.0009926585633867385, "epoch": 2.9842615012106535, "percentage": 14.92, "elapsed_time": "0:08:08", "remaining_time": "0:46:23", "throughput": 2066.32, "total_tokens": 1008776}
{"current_steps": 2470, "total_steps": 16520, "loss": 0.0176, "lr": 0.0009925680985777565, "epoch": 2.990314769975787, "percentage": 14.95, "elapsed_time": "0:08:09", "remaining_time": "0:46:22", "throughput": 2066.57, "total_tokens": 1010920}
{"current_steps": 2475, "total_steps": 16520, "loss": 0.1094, "lr": 0.0009924770839736428, "epoch": 2.99636803874092, "percentage": 14.98, "elapsed_time": "0:08:10", "remaining_time": "0:46:21", "throughput": 2066.95, "total_tokens": 1013128}
{"current_steps": 2478, "total_steps": 16520, "eval_loss": 0.12253114581108093, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "0:08:19", "remaining_time": "0:47:08", "throughput": 2031.14, "total_tokens": 1014008}
{"current_steps": 2480, "total_steps": 16520, "loss": 0.3097, "lr": 0.0009923855196759862, "epoch": 3.002421307506053, "percentage": 15.01, "elapsed_time": "0:08:20", "remaining_time": "0:47:13", "throughput": 2027.68, "total_tokens": 1014808}
{"current_steps": 2485, "total_steps": 16520, "loss": 0.0575, "lr": 0.000992293405786989, "epoch": 3.0084745762711864, "percentage": 15.04, "elapsed_time": "0:08:21", "remaining_time": "0:47:12", "throughput": 2027.66, "total_tokens": 1016824}
{"current_steps": 2490, "total_steps": 16520, "loss": 0.087, "lr": 0.000992200742409467, "epoch": 3.0145278450363198, "percentage": 15.07, "elapsed_time": "0:08:22", "remaining_time": "0:47:11", "throughput": 2028.27, "total_tokens": 1019160}
{"current_steps": 2495, "total_steps": 16520, "loss": 0.0558, "lr": 0.0009921075296468493, "epoch": 3.0205811138014527, "percentage": 15.1, "elapsed_time": "0:08:23", "remaining_time": "0:47:09", "throughput": 2028.7, "total_tokens": 1021304}
{"current_steps": 2500, "total_steps": 16520, "loss": 0.0667, "lr": 0.0009920137676031782, "epoch": 3.026634382566586, "percentage": 15.13, "elapsed_time": "0:08:24", "remaining_time": "0:47:08", "throughput": 2029.06, "total_tokens": 1023416}
{"current_steps": 2505, "total_steps": 16520, "loss": 0.1068, "lr": 0.0009919194563831092, "epoch": 3.032687651331719, "percentage": 15.16, "elapsed_time": "0:08:25", "remaining_time": "0:47:07", "throughput": 2029.22, "total_tokens": 1025464}
{"current_steps": 2510, "total_steps": 16520, "loss": 0.1413, "lr": 0.0009918245960919105, "epoch": 3.0387409200968523, "percentage": 15.19, "elapsed_time": "0:08:26", "remaining_time": "0:47:05", "throughput": 2029.16, "total_tokens": 1027320}
{"current_steps": 2515, "total_steps": 16520, "loss": 0.2291, "lr": 0.0009917291868354636, "epoch": 3.0447941888619856, "percentage": 15.22, "elapsed_time": "0:08:27", "remaining_time": "0:47:04", "throughput": 2029.3, "total_tokens": 1029240}
{"current_steps": 2520, "total_steps": 16520, "loss": 0.0714, "lr": 0.0009916332287202621, "epoch": 3.0508474576271185, "percentage": 15.25, "elapsed_time": "0:08:28", "remaining_time": "0:47:03", "throughput": 2029.4, "total_tokens": 1031256}
{"current_steps": 2525, "total_steps": 16520, "loss": 0.1251, "lr": 0.000991536721853413, "epoch": 3.056900726392252, "percentage": 15.28, "elapsed_time": "0:08:29", "remaining_time": "0:47:01", "throughput": 2029.54, "total_tokens": 1033240}
{"current_steps": 2530, "total_steps": 16520, "loss": 0.1258, "lr": 0.0009914396663426354, "epoch": 3.062953995157385, "percentage": 15.31, "elapsed_time": "0:08:30", "remaining_time": "0:47:00", "throughput": 2029.93, "total_tokens": 1035448}
{"current_steps": 2535, "total_steps": 16520, "loss": 0.0929, "lr": 0.0009913420622962605, "epoch": 3.069007263922518, "percentage": 15.35, "elapsed_time": "0:08:31", "remaining_time": "0:46:59", "throughput": 2029.97, "total_tokens": 1037432}
{"current_steps": 2540, "total_steps": 16520, "loss": 0.081, "lr": 0.0009912439098232323, "epoch": 3.0750605326876514, "percentage": 15.38, "elapsed_time": "0:08:32", "remaining_time": "0:46:58", "throughput": 2030.17, "total_tokens": 1039544}
{"current_steps": 2545, "total_steps": 16520, "loss": 0.1456, "lr": 0.0009911452090331067, "epoch": 3.0811138014527844, "percentage": 15.41, "elapsed_time": "0:08:32", "remaining_time": "0:46:56", "throughput": 2030.36, "total_tokens": 1041560}
{"current_steps": 2550, "total_steps": 16520, "loss": 0.0688, "lr": 0.0009910459600360518, "epoch": 3.0871670702179177, "percentage": 15.44, "elapsed_time": "0:08:33", "remaining_time": "0:46:55", "throughput": 2030.63, "total_tokens": 1043704}
{"current_steps": 2555, "total_steps": 16520, "loss": 0.1038, "lr": 0.0009909461629428473, "epoch": 3.093220338983051, "percentage": 15.47, "elapsed_time": "0:08:34", "remaining_time": "0:46:54", "throughput": 2030.76, "total_tokens": 1045688}
{"current_steps": 2560, "total_steps": 16520, "loss": 0.0509, "lr": 0.0009908458178648847, "epoch": 3.099273607748184, "percentage": 15.5, "elapsed_time": "0:08:35", "remaining_time": "0:46:53", "throughput": 2030.86, "total_tokens": 1047704}
{"current_steps": 2565, "total_steps": 16520, "loss": 0.1221, "lr": 0.0009907449249141674, "epoch": 3.1053268765133173, "percentage": 15.53, "elapsed_time": "0:08:36", "remaining_time": "0:46:51", "throughput": 2030.95, "total_tokens": 1049592}
{"current_steps": 2570, "total_steps": 16520, "loss": 0.1639, "lr": 0.00099064348420331, "epoch": 3.11138014527845, "percentage": 15.56, "elapsed_time": "0:08:37", "remaining_time": "0:46:50", "throughput": 2031.26, "total_tokens": 1051672}
{"current_steps": 2575, "total_steps": 16520, "loss": 0.1195, "lr": 0.000990541495845539, "epoch": 3.1174334140435835, "percentage": 15.59, "elapsed_time": "0:08:38", "remaining_time": "0:46:48", "throughput": 2031.35, "total_tokens": 1053624}
{"current_steps": 2580, "total_steps": 16520, "loss": 0.1331, "lr": 0.0009904389599546916, "epoch": 3.123486682808717, "percentage": 15.62, "elapsed_time": "0:08:39", "remaining_time": "0:46:47", "throughput": 2031.41, "total_tokens": 1055576}
{"current_steps": 2585, "total_steps": 16520, "loss": 0.0994, "lr": 0.0009903358766452167, "epoch": 3.12953995157385, "percentage": 15.65, "elapsed_time": "0:08:40", "remaining_time": "0:46:46", "throughput": 2031.5, "total_tokens": 1057592}
{"current_steps": 2590, "total_steps": 16520, "loss": 0.1711, "lr": 0.0009902322460321735, "epoch": 3.135593220338983, "percentage": 15.68, "elapsed_time": "0:08:41", "remaining_time": "0:46:45", "throughput": 2031.63, "total_tokens": 1059576}
{"current_steps": 2595, "total_steps": 16520, "loss": 0.1641, "lr": 0.000990128068231233, "epoch": 3.141646489104116, "percentage": 15.71, "elapsed_time": "0:08:42", "remaining_time": "0:46:43", "throughput": 2031.78, "total_tokens": 1061624}
{"current_steps": 2600, "total_steps": 16520, "loss": 0.1137, "lr": 0.0009900233433586762, "epoch": 3.1476997578692494, "percentage": 15.74, "elapsed_time": "0:08:43", "remaining_time": "0:46:42", "throughput": 2031.98, "total_tokens": 1063704}
{"current_steps": 2605, "total_steps": 16520, "loss": 0.0821, "lr": 0.000989918071531395, "epoch": 3.1537530266343827, "percentage": 15.77, "elapsed_time": "0:08:44", "remaining_time": "0:46:41", "throughput": 2032.22, "total_tokens": 1065752}
{"current_steps": 2610, "total_steps": 16520, "loss": 0.1135, "lr": 0.0009898122528668918, "epoch": 3.1598062953995156, "percentage": 15.8, "elapsed_time": "0:08:45", "remaining_time": "0:46:39", "throughput": 2032.31, "total_tokens": 1067640}
{"current_steps": 2615, "total_steps": 16520, "loss": 0.1066, "lr": 0.0009897058874832794, "epoch": 3.165859564164649, "percentage": 15.83, "elapsed_time": "0:08:46", "remaining_time": "0:46:38", "throughput": 2032.45, "total_tokens": 1069688}
{"current_steps": 2620, "total_steps": 16520, "loss": 0.1019, "lr": 0.000989598975499281, "epoch": 3.171912832929782, "percentage": 15.86, "elapsed_time": "0:08:47", "remaining_time": "0:46:37", "throughput": 2032.66, "total_tokens": 1071800}
{"current_steps": 2625, "total_steps": 16520, "loss": 0.1011, "lr": 0.0009894915170342296, "epoch": 3.1779661016949152, "percentage": 15.89, "elapsed_time": "0:08:48", "remaining_time": "0:46:36", "throughput": 2032.96, "total_tokens": 1073944}
{"current_steps": 2630, "total_steps": 16520, "loss": 0.0988, "lr": 0.0009893835122080682, "epoch": 3.1840193704600486, "percentage": 15.92, "elapsed_time": "0:08:49", "remaining_time": "0:46:34", "throughput": 2033.21, "total_tokens": 1075992}
{"current_steps": 2635, "total_steps": 16520, "loss": 0.0577, "lr": 0.0009892749611413497, "epoch": 3.1900726392251815, "percentage": 15.95, "elapsed_time": "0:08:50", "remaining_time": "0:46:33", "throughput": 2033.34, "total_tokens": 1077976}
{"current_steps": 2640, "total_steps": 16520, "loss": 0.1443, "lr": 0.0009891658639552367, "epoch": 3.196125907990315, "percentage": 15.98, "elapsed_time": "0:08:51", "remaining_time": "0:46:32", "throughput": 2033.59, "total_tokens": 1080088}
{"current_steps": 2645, "total_steps": 16520, "loss": 0.1198, "lr": 0.0009890562207715019, "epoch": 3.2021791767554477, "percentage": 16.01, "elapsed_time": "0:08:52", "remaining_time": "0:46:31", "throughput": 2033.79, "total_tokens": 1082168}
{"current_steps": 2650, "total_steps": 16520, "loss": 0.0843, "lr": 0.0009889460317125264, "epoch": 3.208232445520581, "percentage": 16.04, "elapsed_time": "0:08:53", "remaining_time": "0:46:30", "throughput": 2033.94, "total_tokens": 1084216}
{"current_steps": 2655, "total_steps": 16520, "loss": 0.1385, "lr": 0.0009888352969013013, "epoch": 3.2142857142857144, "percentage": 16.07, "elapsed_time": "0:08:54", "remaining_time": "0:46:29", "throughput": 2034.37, "total_tokens": 1086488}
{"current_steps": 2660, "total_steps": 16520, "loss": 0.1101, "lr": 0.0009887240164614265, "epoch": 3.2203389830508473, "percentage": 16.1, "elapsed_time": "0:08:55", "remaining_time": "0:46:27", "throughput": 2034.67, "total_tokens": 1088632}
{"current_steps": 2665, "total_steps": 16520, "loss": 0.1615, "lr": 0.0009886121905171115, "epoch": 3.2263922518159807, "percentage": 16.13, "elapsed_time": "0:08:56", "remaining_time": "0:46:26", "throughput": 2034.96, "total_tokens": 1090776}
{"current_steps": 2670, "total_steps": 16520, "loss": 0.0542, "lr": 0.000988499819193174, "epoch": 3.232445520581114, "percentage": 16.16, "elapsed_time": "0:08:57", "remaining_time": "0:46:25", "throughput": 2035.35, "total_tokens": 1092984}
{"current_steps": 2675, "total_steps": 16520, "loss": 0.1361, "lr": 0.0009883869026150408, "epoch": 3.238498789346247, "percentage": 16.19, "elapsed_time": "0:08:57", "remaining_time": "0:46:24", "throughput": 2035.47, "total_tokens": 1094904}
{"current_steps": 2680, "total_steps": 16520, "loss": 0.1208, "lr": 0.0009882734409087472, "epoch": 3.2445520581113803, "percentage": 16.22, "elapsed_time": "0:08:58", "remaining_time": "0:46:22", "throughput": 2035.55, "total_tokens": 1096728}
{"current_steps": 2685, "total_steps": 16520, "loss": 0.0537, "lr": 0.0009881594342009373, "epoch": 3.250605326876513, "percentage": 16.25, "elapsed_time": "0:08:59", "remaining_time": "0:46:21", "throughput": 2036.01, "total_tokens": 1099000}
{"current_steps": 2690, "total_steps": 16520, "loss": 0.162, "lr": 0.0009880448826188625, "epoch": 3.2566585956416465, "percentage": 16.28, "elapsed_time": "0:09:00", "remaining_time": "0:46:20", "throughput": 2036.39, "total_tokens": 1101144}
{"current_steps": 2695, "total_steps": 16520, "loss": 0.1488, "lr": 0.000987929786290384, "epoch": 3.26271186440678, "percentage": 16.31, "elapsed_time": "0:09:01", "remaining_time": "0:46:18", "throughput": 2036.57, "total_tokens": 1103160}
{"current_steps": 2700, "total_steps": 16520, "loss": 0.1033, "lr": 0.0009878141453439696, "epoch": 3.2687651331719128, "percentage": 16.34, "elapsed_time": "0:09:02", "remaining_time": "0:46:17", "throughput": 2036.6, "total_tokens": 1105144}
{"current_steps": 2705, "total_steps": 16520, "loss": 0.047, "lr": 0.0009876979599086953, "epoch": 3.274818401937046, "percentage": 16.37, "elapsed_time": "0:09:03", "remaining_time": "0:46:16", "throughput": 2036.78, "total_tokens": 1107224}
{"current_steps": 2710, "total_steps": 16520, "loss": 0.0807, "lr": 0.0009875812301142455, "epoch": 3.280871670702179, "percentage": 16.4, "elapsed_time": "0:09:04", "remaining_time": "0:46:15", "throughput": 2037.11, "total_tokens": 1109336}
{"current_steps": 2715, "total_steps": 16520, "loss": 0.153, "lr": 0.0009874639560909118, "epoch": 3.2869249394673123, "percentage": 16.43, "elapsed_time": "0:09:05", "remaining_time": "0:46:13", "throughput": 2037.4, "total_tokens": 1111480}
{"current_steps": 2720, "total_steps": 16520, "loss": 0.0482, "lr": 0.0009873461379695928, "epoch": 3.2929782082324457, "percentage": 16.46, "elapsed_time": "0:09:06", "remaining_time": "0:46:12", "throughput": 2037.48, "total_tokens": 1113496}
{"current_steps": 2725, "total_steps": 16520, "loss": 0.173, "lr": 0.0009872277758817955, "epoch": 3.2990314769975786, "percentage": 16.5, "elapsed_time": "0:09:07", "remaining_time": "0:46:11", "throughput": 2037.44, "total_tokens": 1115384}
{"current_steps": 2730, "total_steps": 16520, "loss": 0.0826, "lr": 0.000987108869959633, "epoch": 3.305084745762712, "percentage": 16.53, "elapsed_time": "0:09:08", "remaining_time": "0:46:10", "throughput": 2037.66, "total_tokens": 1117432}
{"current_steps": 2735, "total_steps": 16520, "loss": 0.1199, "lr": 0.0009869894203358256, "epoch": 3.3111380145278453, "percentage": 16.56, "elapsed_time": "0:09:09", "remaining_time": "0:46:08", "throughput": 2037.79, "total_tokens": 1119416}
{"current_steps": 2740, "total_steps": 16520, "loss": 0.0878, "lr": 0.000986869427143701, "epoch": 3.317191283292978, "percentage": 16.59, "elapsed_time": "0:09:10", "remaining_time": "0:46:07", "throughput": 2038.16, "total_tokens": 1121560}
{"current_steps": 2745, "total_steps": 16520, "loss": 0.1583, "lr": 0.0009867488905171934, "epoch": 3.3232445520581115, "percentage": 16.62, "elapsed_time": "0:09:11", "remaining_time": "0:46:06", "throughput": 2038.55, "total_tokens": 1123736}
{"current_steps": 2750, "total_steps": 16520, "loss": 0.0659, "lr": 0.0009866278105908433, "epoch": 3.3292978208232444, "percentage": 16.65, "elapsed_time": "0:09:12", "remaining_time": "0:46:05", "throughput": 2038.74, "total_tokens": 1125816}
{"current_steps": 2755, "total_steps": 16520, "loss": 0.1166, "lr": 0.0009865061874997976, "epoch": 3.335351089588378, "percentage": 16.68, "elapsed_time": "0:09:13", "remaining_time": "0:46:03", "throughput": 2038.97, "total_tokens": 1127928}
{"current_steps": 2760, "total_steps": 16520, "loss": 0.1891, "lr": 0.0009863840213798103, "epoch": 3.341404358353511, "percentage": 16.71, "elapsed_time": "0:09:14", "remaining_time": "0:46:02", "throughput": 2039.16, "total_tokens": 1130008}
{"current_steps": 2765, "total_steps": 16520, "loss": 0.1023, "lr": 0.0009862613123672404, "epoch": 3.347457627118644, "percentage": 16.74, "elapsed_time": "0:09:15", "remaining_time": "0:46:01", "throughput": 2039.39, "total_tokens": 1132120}
{"current_steps": 2770, "total_steps": 16520, "loss": 0.2032, "lr": 0.0009861380605990535, "epoch": 3.3535108958837774, "percentage": 16.77, "elapsed_time": "0:09:16", "remaining_time": "0:46:00", "throughput": 2039.61, "total_tokens": 1134232}
{"current_steps": 2775, "total_steps": 16520, "loss": 0.0937, "lr": 0.0009860142662128208, "epoch": 3.3595641646489103, "percentage": 16.8, "elapsed_time": "0:09:17", "remaining_time": "0:45:59", "throughput": 2039.74, "total_tokens": 1136216}
{"current_steps": 2780, "total_steps": 16520, "loss": 0.1259, "lr": 0.0009858899293467196, "epoch": 3.3656174334140436, "percentage": 16.83, "elapsed_time": "0:09:18", "remaining_time": "0:45:57", "throughput": 2039.96, "total_tokens": 1138328}
{"current_steps": 2785, "total_steps": 16520, "loss": 0.0899, "lr": 0.0009857650501395318, "epoch": 3.371670702179177, "percentage": 16.86, "elapsed_time": "0:09:18", "remaining_time": "0:45:56", "throughput": 2040.0, "total_tokens": 1140312}
{"current_steps": 2790, "total_steps": 16520, "loss": 0.1088, "lr": 0.0009856396287306454, "epoch": 3.37772397094431, "percentage": 16.89, "elapsed_time": "0:09:19", "remaining_time": "0:45:55", "throughput": 2039.98, "total_tokens": 1142264}
{"current_steps": 2795, "total_steps": 16520, "loss": 0.1494, "lr": 0.0009855136652600536, "epoch": 3.383777239709443, "percentage": 16.92, "elapsed_time": "0:09:20", "remaining_time": "0:45:54", "throughput": 2040.0, "total_tokens": 1144120}
{"current_steps": 2800, "total_steps": 16520, "loss": 0.1572, "lr": 0.0009853871598683541, "epoch": 3.389830508474576, "percentage": 16.95, "elapsed_time": "0:09:21", "remaining_time": "0:45:52", "throughput": 2040.09, "total_tokens": 1146136}
{"current_steps": 2805, "total_steps": 16520, "loss": 0.0593, "lr": 0.00098526011269675, "epoch": 3.3958837772397095, "percentage": 16.98, "elapsed_time": "0:09:22", "remaining_time": "0:45:51", "throughput": 2040.26, "total_tokens": 1148152}
{"current_steps": 2810, "total_steps": 16520, "loss": 0.1162, "lr": 0.0009851325238870493, "epoch": 3.401937046004843, "percentage": 17.01, "elapsed_time": "0:09:23", "remaining_time": "0:45:50", "throughput": 2040.54, "total_tokens": 1150296}
{"current_steps": 2815, "total_steps": 16520, "loss": 0.1027, "lr": 0.0009850043935816632, "epoch": 3.4079903147699757, "percentage": 17.04, "elapsed_time": "0:09:24", "remaining_time": "0:45:49", "throughput": 2040.57, "total_tokens": 1152280}
{"current_steps": 2820, "total_steps": 16520, "loss": 0.1241, "lr": 0.0009848757219236093, "epoch": 3.414043583535109, "percentage": 17.07, "elapsed_time": "0:09:25", "remaining_time": "0:45:47", "throughput": 2040.83, "total_tokens": 1154360}
{"current_steps": 2825, "total_steps": 16520, "loss": 0.1616, "lr": 0.000984746509056508, "epoch": 3.420096852300242, "percentage": 17.1, "elapsed_time": "0:09:26", "remaining_time": "0:45:46", "throughput": 2041.01, "total_tokens": 1156440}
{"current_steps": 2830, "total_steps": 16520, "loss": 0.3154, "lr": 0.0009846167551245842, "epoch": 3.4261501210653753, "percentage": 17.13, "elapsed_time": "0:09:27", "remaining_time": "0:45:45", "throughput": 2041.23, "total_tokens": 1158552}
{"current_steps": 2835, "total_steps": 16520, "loss": 0.0984, "lr": 0.0009844864602726671, "epoch": 3.4322033898305087, "percentage": 17.16, "elapsed_time": "0:09:28", "remaining_time": "0:45:44", "throughput": 2041.41, "total_tokens": 1160632}
{"current_steps": 2840, "total_steps": 16520, "loss": 0.0732, "lr": 0.0009843556246461888, "epoch": 3.4382566585956416, "percentage": 17.19, "elapsed_time": "0:09:29", "remaining_time": "0:45:43", "throughput": 2041.67, "total_tokens": 1162712}
{"current_steps": 2845, "total_steps": 16520, "loss": 0.0649, "lr": 0.000984224248391186, "epoch": 3.444309927360775, "percentage": 17.22, "elapsed_time": "0:09:30", "remaining_time": "0:45:41", "throughput": 2041.74, "total_tokens": 1164664}
{"current_steps": 2850, "total_steps": 16520, "loss": 0.0498, "lr": 0.0009840923316542984, "epoch": 3.450363196125908, "percentage": 17.25, "elapsed_time": "0:09:31", "remaining_time": "0:45:40", "throughput": 2041.81, "total_tokens": 1166680}
{"current_steps": 2855, "total_steps": 16520, "loss": 0.0908, "lr": 0.0009839598745827686, "epoch": 3.456416464891041, "percentage": 17.28, "elapsed_time": "0:09:32", "remaining_time": "0:45:39", "throughput": 2041.89, "total_tokens": 1168632}
{"current_steps": 2860, "total_steps": 16520, "loss": 0.2581, "lr": 0.0009838268773244428, "epoch": 3.4624697336561745, "percentage": 17.31, "elapsed_time": "0:09:33", "remaining_time": "0:45:38", "throughput": 2041.86, "total_tokens": 1170584}
{"current_steps": 2865, "total_steps": 16520, "loss": 0.0912, "lr": 0.00098369334002777, "epoch": 3.4685230024213074, "percentage": 17.34, "elapsed_time": "0:09:34", "remaining_time": "0:45:37", "throughput": 2041.98, "total_tokens": 1172632}
{"current_steps": 2870, "total_steps": 16520, "loss": 0.0641, "lr": 0.000983559262841802, "epoch": 3.4745762711864407, "percentage": 17.37, "elapsed_time": "0:09:35", "remaining_time": "0:45:35", "throughput": 2042.05, "total_tokens": 1174584}
{"current_steps": 2875, "total_steps": 16520, "loss": 0.0663, "lr": 0.0009834246459161935, "epoch": 3.4806295399515736, "percentage": 17.4, "elapsed_time": "0:09:36", "remaining_time": "0:45:34", "throughput": 2042.21, "total_tokens": 1176472}
{"current_steps": 2880, "total_steps": 16520, "loss": 0.0909, "lr": 0.0009832894894012008, "epoch": 3.486682808716707, "percentage": 17.43, "elapsed_time": "0:09:37", "remaining_time": "0:45:32", "throughput": 2042.28, "total_tokens": 1178424}
{"current_steps": 2885, "total_steps": 16520, "loss": 0.0788, "lr": 0.0009831537934476835, "epoch": 3.4927360774818403, "percentage": 17.46, "elapsed_time": "0:09:37", "remaining_time": "0:45:31", "throughput": 2042.59, "total_tokens": 1180536}
{"current_steps": 2890, "total_steps": 16520, "loss": 0.0724, "lr": 0.0009830175582071024, "epoch": 3.4987893462469732, "percentage": 17.49, "elapsed_time": "0:09:38", "remaining_time": "0:45:30", "throughput": 2042.79, "total_tokens": 1182520}
{"current_steps": 2895, "total_steps": 16520, "loss": 0.0731, "lr": 0.000982880783831521, "epoch": 3.5048426150121066, "percentage": 17.52, "elapsed_time": "0:09:39", "remaining_time": "0:45:28", "throughput": 2043.05, "total_tokens": 1184600}
{"current_steps": 2900, "total_steps": 16520, "loss": 0.0594, "lr": 0.0009827434704736042, "epoch": 3.5108958837772395, "percentage": 17.55, "elapsed_time": "0:09:40", "remaining_time": "0:45:27", "throughput": 2043.13, "total_tokens": 1186552}
{"current_steps": 2905, "total_steps": 16520, "loss": 0.027, "lr": 0.0009826056182866186, "epoch": 3.516949152542373, "percentage": 17.58, "elapsed_time": "0:09:41", "remaining_time": "0:45:26", "throughput": 2043.24, "total_tokens": 1188536}
{"current_steps": 2910, "total_steps": 16520, "loss": 0.1178, "lr": 0.0009824672274244323, "epoch": 3.523002421307506, "percentage": 17.62, "elapsed_time": "0:09:42", "remaining_time": "0:45:25", "throughput": 2043.36, "total_tokens": 1190584}
{"current_steps": 2915, "total_steps": 16520, "loss": 0.1426, "lr": 0.000982328298041514, "epoch": 3.529055690072639, "percentage": 17.65, "elapsed_time": "0:09:43", "remaining_time": "0:45:23", "throughput": 2043.66, "total_tokens": 1192696}
{"current_steps": 2920, "total_steps": 16520, "loss": 0.1626, "lr": 0.0009821888302929344, "epoch": 3.5351089588377724, "percentage": 17.68, "elapsed_time": "0:09:44", "remaining_time": "0:45:22", "throughput": 2043.83, "total_tokens": 1194776}
{"current_steps": 2925, "total_steps": 16520, "loss": 0.0984, "lr": 0.000982048824334365, "epoch": 3.5411622276029053, "percentage": 17.71, "elapsed_time": "0:09:45", "remaining_time": "0:45:21", "throughput": 2044.15, "total_tokens": 1196920}
{"current_steps": 2930, "total_steps": 16520, "loss": 0.1208, "lr": 0.0009819082803220773, "epoch": 3.5472154963680387, "percentage": 17.74, "elapsed_time": "0:09:46", "remaining_time": "0:45:20", "throughput": 2044.55, "total_tokens": 1199160}
{"current_steps": 2935, "total_steps": 16520, "loss": 0.1066, "lr": 0.0009817671984129442, "epoch": 3.553268765133172, "percentage": 17.77, "elapsed_time": "0:09:47", "remaining_time": "0:45:19", "throughput": 2044.8, "total_tokens": 1201240}
{"current_steps": 2940, "total_steps": 16520, "loss": 0.125, "lr": 0.0009816255787644386, "epoch": 3.559322033898305, "percentage": 17.8, "elapsed_time": "0:09:48", "remaining_time": "0:45:17", "throughput": 2044.86, "total_tokens": 1203256}
{"current_steps": 2945, "total_steps": 16520, "loss": 0.1368, "lr": 0.0009814834215346334, "epoch": 3.5653753026634383, "percentage": 17.83, "elapsed_time": "0:09:49", "remaining_time": "0:45:16", "throughput": 2045.12, "total_tokens": 1205400}
{"current_steps": 2950, "total_steps": 16520, "loss": 0.0863, "lr": 0.000981340726882202, "epoch": 3.571428571428571, "percentage": 17.86, "elapsed_time": "0:09:50", "remaining_time": "0:45:15", "throughput": 2045.23, "total_tokens": 1207448}
{"current_steps": 2955, "total_steps": 16520, "loss": 0.1151, "lr": 0.0009811974949664175, "epoch": 3.5774818401937045, "percentage": 17.89, "elapsed_time": "0:09:51", "remaining_time": "0:45:14", "throughput": 2045.61, "total_tokens": 1209624}
{"current_steps": 2960, "total_steps": 16520, "loss": 0.0757, "lr": 0.0009810537259471524, "epoch": 3.583535108958838, "percentage": 17.92, "elapsed_time": "0:09:52", "remaining_time": "0:45:13", "throughput": 2045.82, "total_tokens": 1211736}
{"current_steps": 2965, "total_steps": 16520, "loss": 0.1584, "lr": 0.0009809094199848792, "epoch": 3.589588377723971, "percentage": 17.95, "elapsed_time": "0:09:53", "remaining_time": "0:45:12", "throughput": 2046.07, "total_tokens": 1213880}
{"current_steps": 2970, "total_steps": 16520, "loss": 0.043, "lr": 0.0009807645772406694, "epoch": 3.595641646489104, "percentage": 17.98, "elapsed_time": "0:09:54", "remaining_time": "0:45:10", "throughput": 2046.26, "total_tokens": 1215864}
{"current_steps": 2975, "total_steps": 16520, "loss": 0.0617, "lr": 0.0009806191978761936, "epoch": 3.601694915254237, "percentage": 18.01, "elapsed_time": "0:09:55", "remaining_time": "0:45:09", "throughput": 2046.47, "total_tokens": 1217976}
{"current_steps": 2980, "total_steps": 16520, "loss": 0.0569, "lr": 0.0009804732820537215, "epoch": 3.6077481840193704, "percentage": 18.04, "elapsed_time": "0:09:56", "remaining_time": "0:45:08", "throughput": 2046.62, "total_tokens": 1219928}
{"current_steps": 2985, "total_steps": 16520, "loss": 0.0758, "lr": 0.0009803268299361217, "epoch": 3.6138014527845037, "percentage": 18.07, "elapsed_time": "0:09:56", "remaining_time": "0:45:06", "throughput": 2046.68, "total_tokens": 1221816}
{"current_steps": 2990, "total_steps": 16520, "loss": 0.0831, "lr": 0.0009801798416868613, "epoch": 3.619854721549637, "percentage": 18.1, "elapsed_time": "0:09:57", "remaining_time": "0:45:05", "throughput": 2046.88, "total_tokens": 1223928}
{"current_steps": 2995, "total_steps": 16520, "loss": 0.0944, "lr": 0.0009800323174700054, "epoch": 3.62590799031477, "percentage": 18.13, "elapsed_time": "0:09:58", "remaining_time": "0:45:04", "throughput": 2046.94, "total_tokens": 1225816}
{"current_steps": 3000, "total_steps": 16520, "loss": 0.0942, "lr": 0.0009798842574502181, "epoch": 3.6319612590799033, "percentage": 18.16, "elapsed_time": "0:09:59", "remaining_time": "0:45:03", "throughput": 2047.26, "total_tokens": 1227960}
{"current_steps": 3005, "total_steps": 16520, "loss": 0.0646, "lr": 0.000979735661792761, "epoch": 3.638014527845036, "percentage": 18.19, "elapsed_time": "0:10:00", "remaining_time": "0:45:01", "throughput": 2047.37, "total_tokens": 1229944}
{"current_steps": 3010, "total_steps": 16520, "loss": 0.0755, "lr": 0.000979586530663494, "epoch": 3.6440677966101696, "percentage": 18.22, "elapsed_time": "0:10:01", "remaining_time": "0:45:00", "throughput": 2047.47, "total_tokens": 1231928}
{"current_steps": 3015, "total_steps": 16520, "loss": 0.1141, "lr": 0.000979436864228874, "epoch": 3.650121065375303, "percentage": 18.25, "elapsed_time": "0:10:02", "remaining_time": "0:44:59", "throughput": 2047.8, "total_tokens": 1234072}
{"current_steps": 3020, "total_steps": 16520, "loss": 0.1175, "lr": 0.0009792866626559562, "epoch": 3.656174334140436, "percentage": 18.28, "elapsed_time": "0:10:03", "remaining_time": "0:44:58", "throughput": 2048.05, "total_tokens": 1236184}
{"current_steps": 3025, "total_steps": 16520, "loss": 0.0715, "lr": 0.0009791359261123926, "epoch": 3.662227602905569, "percentage": 18.31, "elapsed_time": "0:10:04", "remaining_time": "0:44:57", "throughput": 2048.35, "total_tokens": 1238392}
{"current_steps": 3030, "total_steps": 16520, "loss": 0.0862, "lr": 0.0009789846547664325, "epoch": 3.668280871670702, "percentage": 18.34, "elapsed_time": "0:10:05", "remaining_time": "0:44:56", "throughput": 2048.5, "total_tokens": 1240472}
{"current_steps": 3035, "total_steps": 16520, "loss": 0.0934, "lr": 0.0009788328487869218, "epoch": 3.6743341404358354, "percentage": 18.37, "elapsed_time": "0:10:06", "remaining_time": "0:44:54", "throughput": 2048.69, "total_tokens": 1242552}
{"current_steps": 3040, "total_steps": 16520, "loss": 0.0693, "lr": 0.0009786805083433039, "epoch": 3.6803874092009687, "percentage": 18.4, "elapsed_time": "0:10:07", "remaining_time": "0:44:53", "throughput": 2048.8, "total_tokens": 1244600}
{"current_steps": 3045, "total_steps": 16520, "loss": 0.0567, "lr": 0.000978527633605618, "epoch": 3.6864406779661016, "percentage": 18.43, "elapsed_time": "0:10:08", "remaining_time": "0:44:52", "throughput": 2049.08, "total_tokens": 1246776}
{"current_steps": 3050, "total_steps": 16520, "loss": 0.1049, "lr": 0.0009783742247445, "epoch": 3.692493946731235, "percentage": 18.46, "elapsed_time": "0:10:09", "remaining_time": "0:44:51", "throughput": 2049.18, "total_tokens": 1248824}
{"current_steps": 3055, "total_steps": 16520, "loss": 0.0739, "lr": 0.000978220281931182, "epoch": 3.698547215496368, "percentage": 18.49, "elapsed_time": "0:10:10", "remaining_time": "0:44:50", "throughput": 2049.41, "total_tokens": 1250904}
{"current_steps": 3060, "total_steps": 16520, "loss": 0.112, "lr": 0.0009780658053374924, "epoch": 3.7046004842615012, "percentage": 18.52, "elapsed_time": "0:10:11", "remaining_time": "0:44:48", "throughput": 2049.55, "total_tokens": 1252920}
{"current_steps": 3065, "total_steps": 16520, "loss": 0.1039, "lr": 0.0009779107951358543, "epoch": 3.7106537530266346, "percentage": 18.55, "elapsed_time": "0:10:12", "remaining_time": "0:44:47", "throughput": 2049.83, "total_tokens": 1255096}
{"current_steps": 3070, "total_steps": 16520, "loss": 0.0864, "lr": 0.0009777552514992876, "epoch": 3.7167070217917675, "percentage": 18.58, "elapsed_time": "0:10:13", "remaining_time": "0:44:46", "throughput": 2050.02, "total_tokens": 1257144}
{"current_steps": 3075, "total_steps": 16520, "loss": 0.0439, "lr": 0.0009775991746014073, "epoch": 3.722760290556901, "percentage": 18.61, "elapsed_time": "0:10:14", "remaining_time": "0:44:45", "throughput": 2050.07, "total_tokens": 1259160}
{"current_steps": 3080, "total_steps": 16520, "loss": 0.0681, "lr": 0.0009774425646164229, "epoch": 3.7288135593220337, "percentage": 18.64, "elapsed_time": "0:10:15", "remaining_time": "0:44:44", "throughput": 2050.27, "total_tokens": 1261304}
{"current_steps": 3085, "total_steps": 16520, "loss": 0.1305, "lr": 0.00097728542171914, "epoch": 3.734866828087167, "percentage": 18.67, "elapsed_time": "0:10:16", "remaining_time": "0:44:43", "throughput": 2050.55, "total_tokens": 1263384}
{"current_steps": 3090, "total_steps": 16520, "loss": 0.0152, "lr": 0.000977127746084958, "epoch": 3.7409200968523004, "percentage": 18.7, "elapsed_time": "0:10:17", "remaining_time": "0:44:42", "throughput": 2050.74, "total_tokens": 1265496}
{"current_steps": 3095, "total_steps": 16520, "loss": 0.083, "lr": 0.0009769695378898722, "epoch": 3.7469733656174333, "percentage": 18.73, "elapsed_time": "0:10:18", "remaining_time": "0:44:40", "throughput": 2050.79, "total_tokens": 1267512}
{"current_steps": 3100, "total_steps": 16520, "loss": 0.0885, "lr": 0.000976810797310471, "epoch": 3.7530266343825667, "percentage": 18.77, "elapsed_time": "0:10:19", "remaining_time": "0:44:39", "throughput": 2050.83, "total_tokens": 1269528}
{"current_steps": 3105, "total_steps": 16520, "loss": 0.1067, "lr": 0.0009766515245239376, "epoch": 3.7590799031476996, "percentage": 18.8, "elapsed_time": "0:10:19", "remaining_time": "0:44:38", "throughput": 2051.05, "total_tokens": 1271608}
{"current_steps": 3110, "total_steps": 16520, "loss": 0.0923, "lr": 0.0009764917197080494, "epoch": 3.765133171912833, "percentage": 18.83, "elapsed_time": "0:10:20", "remaining_time": "0:44:37", "throughput": 2051.11, "total_tokens": 1273624}
{"current_steps": 3115, "total_steps": 16520, "loss": 0.1081, "lr": 0.0009763313830411775, "epoch": 3.7711864406779663, "percentage": 18.86, "elapsed_time": "0:10:21", "remaining_time": "0:44:36", "throughput": 2051.16, "total_tokens": 1275576}
{"current_steps": 3120, "total_steps": 16520, "loss": 0.1084, "lr": 0.0009761705147022868, "epoch": 3.777239709443099, "percentage": 18.89, "elapsed_time": "0:10:22", "remaining_time": "0:44:34", "throughput": 2051.39, "total_tokens": 1277656}
{"current_steps": 3125, "total_steps": 16520, "loss": 0.1042, "lr": 0.0009760091148709352, "epoch": 3.7832929782082325, "percentage": 18.92, "elapsed_time": "0:10:23", "remaining_time": "0:44:33", "throughput": 2051.47, "total_tokens": 1279576}
{"current_steps": 3130, "total_steps": 16520, "loss": 0.1056, "lr": 0.000975847183727274, "epoch": 3.7893462469733654, "percentage": 18.95, "elapsed_time": "0:10:24", "remaining_time": "0:44:32", "throughput": 2051.53, "total_tokens": 1281592}
{"current_steps": 3135, "total_steps": 16520, "loss": 0.1939, "lr": 0.0009756847214520482, "epoch": 3.7953995157384988, "percentage": 18.98, "elapsed_time": "0:10:25", "remaining_time": "0:44:31", "throughput": 2051.76, "total_tokens": 1283736}
{"current_steps": 3140, "total_steps": 16520, "loss": 0.1504, "lr": 0.0009755217282265945, "epoch": 3.801452784503632, "percentage": 19.01, "elapsed_time": "0:10:26", "remaining_time": "0:44:30", "throughput": 2051.99, "total_tokens": 1285816}
{"current_steps": 3145, "total_steps": 16520, "loss": 0.0459, "lr": 0.0009753582042328433, "epoch": 3.807506053268765, "percentage": 19.04, "elapsed_time": "0:10:27", "remaining_time": "0:44:29", "throughput": 2052.26, "total_tokens": 1287992}
{"current_steps": 3150, "total_steps": 16520, "loss": 0.1182, "lr": 0.0009751941496533165, "epoch": 3.8135593220338984, "percentage": 19.07, "elapsed_time": "0:10:28", "remaining_time": "0:44:27", "throughput": 2052.39, "total_tokens": 1290008}
{"current_steps": 3155, "total_steps": 16520, "loss": 0.1386, "lr": 0.0009750295646711293, "epoch": 3.8196125907990313, "percentage": 19.1, "elapsed_time": "0:10:29", "remaining_time": "0:44:26", "throughput": 2052.49, "total_tokens": 1291992}
{"current_steps": 3160, "total_steps": 16520, "loss": 0.076, "lr": 0.0009748644494699879, "epoch": 3.8256658595641646, "percentage": 19.13, "elapsed_time": "0:10:30", "remaining_time": "0:44:25", "throughput": 2052.71, "total_tokens": 1294072}
{"current_steps": 3165, "total_steps": 16520, "loss": 0.0594, "lr": 0.0009746988042341906, "epoch": 3.831719128329298, "percentage": 19.16, "elapsed_time": "0:10:31", "remaining_time": "0:44:24", "throughput": 2052.84, "total_tokens": 1296088}
{"current_steps": 3170, "total_steps": 16520, "loss": 0.0919, "lr": 0.0009745326291486279, "epoch": 3.837772397094431, "percentage": 19.19, "elapsed_time": "0:10:32", "remaining_time": "0:44:22", "throughput": 2052.88, "total_tokens": 1298104}
{"current_steps": 3175, "total_steps": 16520, "loss": 0.1128, "lr": 0.000974365924398781, "epoch": 3.843825665859564, "percentage": 19.22, "elapsed_time": "0:10:33", "remaining_time": "0:44:21", "throughput": 2053.02, "total_tokens": 1300184}
{"current_steps": 3180, "total_steps": 16520, "loss": 0.1264, "lr": 0.0009741986901707227, "epoch": 3.849878934624697, "percentage": 19.25, "elapsed_time": "0:10:34", "remaining_time": "0:44:20", "throughput": 2053.21, "total_tokens": 1302328}
{"current_steps": 3185, "total_steps": 16520, "loss": 0.0485, "lr": 0.0009740309266511166, "epoch": 3.8559322033898304, "percentage": 19.28, "elapsed_time": "0:10:35", "remaining_time": "0:44:19", "throughput": 2053.39, "total_tokens": 1304440}
{"current_steps": 3190, "total_steps": 16520, "loss": 0.1015, "lr": 0.000973862634027217, "epoch": 3.861985472154964, "percentage": 19.31, "elapsed_time": "0:10:36", "remaining_time": "0:44:18", "throughput": 2053.58, "total_tokens": 1306520}
{"current_steps": 3195, "total_steps": 16520, "loss": 0.0355, "lr": 0.0009736938124868693, "epoch": 3.8680387409200967, "percentage": 19.34, "elapsed_time": "0:10:37", "remaining_time": "0:44:17", "throughput": 2053.7, "total_tokens": 1308536}
{"current_steps": 3200, "total_steps": 16520, "loss": 0.0801, "lr": 0.0009735244622185084, "epoch": 3.87409200968523, "percentage": 19.37, "elapsed_time": "0:10:38", "remaining_time": "0:44:16", "throughput": 2053.88, "total_tokens": 1310648}
{"current_steps": 3205, "total_steps": 16520, "loss": 0.0293, "lr": 0.0009733545834111602, "epoch": 3.880145278450363, "percentage": 19.4, "elapsed_time": "0:10:39", "remaining_time": "0:44:14", "throughput": 2053.98, "total_tokens": 1312632}
{"current_steps": 3210, "total_steps": 16520, "loss": 0.2717, "lr": 0.00097318417625444, "epoch": 3.8861985472154963, "percentage": 19.43, "elapsed_time": "0:10:40", "remaining_time": "0:44:13", "throughput": 2054.06, "total_tokens": 1314616}
{"current_steps": 3215, "total_steps": 16520, "loss": 0.0642, "lr": 0.0009730132409385533, "epoch": 3.8922518159806296, "percentage": 19.46, "elapsed_time": "0:10:40", "remaining_time": "0:44:12", "throughput": 2054.32, "total_tokens": 1316728}
{"current_steps": 3220, "total_steps": 16520, "loss": 0.0824, "lr": 0.0009728417776542944, "epoch": 3.898305084745763, "percentage": 19.49, "elapsed_time": "0:10:41", "remaining_time": "0:44:11", "throughput": 2054.52, "total_tokens": 1318808}
{"current_steps": 3225, "total_steps": 16520, "loss": 0.11, "lr": 0.0009726697865930476, "epoch": 3.904358353510896, "percentage": 19.52, "elapsed_time": "0:10:42", "remaining_time": "0:44:10", "throughput": 2054.77, "total_tokens": 1320984}
{"current_steps": 3230, "total_steps": 16520, "loss": 0.0831, "lr": 0.0009724972679467863, "epoch": 3.910411622276029, "percentage": 19.55, "elapsed_time": "0:10:43", "remaining_time": "0:44:09", "throughput": 2054.94, "total_tokens": 1323096}
{"current_steps": 3235, "total_steps": 16520, "loss": 0.0582, "lr": 0.000972324221908072, "epoch": 3.916464891041162, "percentage": 19.58, "elapsed_time": "0:10:44", "remaining_time": "0:44:07", "throughput": 2054.94, "total_tokens": 1325016}
{"current_steps": 3240, "total_steps": 16520, "loss": 0.1503, "lr": 0.0009721506486700558, "epoch": 3.9225181598062955, "percentage": 19.61, "elapsed_time": "0:10:45", "remaining_time": "0:44:06", "throughput": 2055.02, "total_tokens": 1327064}
{"current_steps": 3245, "total_steps": 16520, "loss": 0.0728, "lr": 0.0009719765484264767, "epoch": 3.928571428571429, "percentage": 19.64, "elapsed_time": "0:10:46", "remaining_time": "0:44:05", "throughput": 2055.11, "total_tokens": 1329112}
{"current_steps": 3250, "total_steps": 16520, "loss": 0.158, "lr": 0.000971801921371662, "epoch": 3.9346246973365617, "percentage": 19.67, "elapsed_time": "0:10:47", "remaining_time": "0:44:04", "throughput": 2055.2, "total_tokens": 1331096}
{"current_steps": 3255, "total_steps": 16520, "loss": 0.0621, "lr": 0.0009716267677005272, "epoch": 3.940677966101695, "percentage": 19.7, "elapsed_time": "0:10:48", "remaining_time": "0:44:03", "throughput": 2055.3, "total_tokens": 1333144}
{"current_steps": 3260, "total_steps": 16520, "loss": 0.0789, "lr": 0.0009714510876085757, "epoch": 3.946731234866828, "percentage": 19.73, "elapsed_time": "0:10:49", "remaining_time": "0:44:02", "throughput": 2055.34, "total_tokens": 1335096}
{"current_steps": 3265, "total_steps": 16520, "loss": 0.0741, "lr": 0.0009712748812918979, "epoch": 3.9527845036319613, "percentage": 19.76, "elapsed_time": "0:10:50", "remaining_time": "0:44:01", "throughput": 2055.47, "total_tokens": 1337176}
{"current_steps": 3270, "total_steps": 16520, "loss": 0.2058, "lr": 0.000971098148947172, "epoch": 3.9588377723970947, "percentage": 19.79, "elapsed_time": "0:10:51", "remaining_time": "0:43:59", "throughput": 2055.67, "total_tokens": 1339320}
{"current_steps": 3275, "total_steps": 16520, "loss": 0.0638, "lr": 0.0009709208907716635, "epoch": 3.9648910411622276, "percentage": 19.82, "elapsed_time": "0:10:52", "remaining_time": "0:43:58", "throughput": 2055.88, "total_tokens": 1341464}
{"current_steps": 3280, "total_steps": 16520, "loss": 0.1507, "lr": 0.0009707431069632243, "epoch": 3.970944309927361, "percentage": 19.85, "elapsed_time": "0:10:53", "remaining_time": "0:43:57", "throughput": 2055.92, "total_tokens": 1343480}
{"current_steps": 3285, "total_steps": 16520, "loss": 0.0574, "lr": 0.0009705647977202936, "epoch": 3.976997578692494, "percentage": 19.88, "elapsed_time": "0:10:54", "remaining_time": "0:43:56", "throughput": 2056.01, "total_tokens": 1345528}
{"current_steps": 3290, "total_steps": 16520, "loss": 0.0673, "lr": 0.0009703859632418966, "epoch": 3.983050847457627, "percentage": 19.92, "elapsed_time": "0:10:55", "remaining_time": "0:43:55", "throughput": 2056.09, "total_tokens": 1347576}
{"current_steps": 3295, "total_steps": 16520, "loss": 0.0478, "lr": 0.000970206603727645, "epoch": 3.9891041162227605, "percentage": 19.95, "elapsed_time": "0:10:56", "remaining_time": "0:43:54", "throughput": 2056.34, "total_tokens": 1349752}
{"current_steps": 3300, "total_steps": 16520, "loss": 0.1364, "lr": 0.0009700267193777363, "epoch": 3.9951573849878934, "percentage": 19.98, "elapsed_time": "0:10:57", "remaining_time": "0:43:53", "throughput": 2056.56, "total_tokens": 1351896}
{"current_steps": 3304, "total_steps": 16520, "eval_loss": 0.10221010446548462, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:11:06", "remaining_time": "0:44:24", "throughput": 2031.87, "total_tokens": 1353224}
{"current_steps": 3305, "total_steps": 16520, "loss": 0.1328, "lr": 0.0009698463103929542, "epoch": 4.001210653753026, "percentage": 20.01, "elapsed_time": "0:11:07", "remaining_time": "0:44:27", "throughput": 2029.16, "total_tokens": 1353640}
{"current_steps": 3310, "total_steps": 16520, "loss": 0.0669, "lr": 0.0009696653769746677, "epoch": 4.00726392251816, "percentage": 20.04, "elapsed_time": "0:11:08", "remaining_time": "0:44:26", "throughput": 2029.19, "total_tokens": 1355624}
{"current_steps": 3315, "total_steps": 16520, "loss": 0.0461, "lr": 0.0009694839193248314, "epoch": 4.013317191283293, "percentage": 20.07, "elapsed_time": "0:11:09", "remaining_time": "0:44:25", "throughput": 2029.34, "total_tokens": 1357704}
{"current_steps": 3320, "total_steps": 16520, "loss": 0.0738, "lr": 0.0009693019376459846, "epoch": 4.019370460048426, "percentage": 20.1, "elapsed_time": "0:11:10", "remaining_time": "0:44:23", "throughput": 2029.57, "total_tokens": 1359848}
{"current_steps": 3325, "total_steps": 16520, "loss": 0.088, "lr": 0.000969119432141252, "epoch": 4.02542372881356, "percentage": 20.13, "elapsed_time": "0:11:10", "remaining_time": "0:44:22", "throughput": 2029.85, "total_tokens": 1361992}
{"current_steps": 3330, "total_steps": 16520, "loss": 0.1729, "lr": 0.0009689364030143426, "epoch": 4.031476997578692, "percentage": 20.16, "elapsed_time": "0:11:11", "remaining_time": "0:44:21", "throughput": 2030.01, "total_tokens": 1364072}
{"current_steps": 3335, "total_steps": 16520, "loss": 0.0724, "lr": 0.0009687528504695501, "epoch": 4.0375302663438255, "percentage": 20.19, "elapsed_time": "0:11:12", "remaining_time": "0:44:20", "throughput": 2030.04, "total_tokens": 1366056}
{"current_steps": 3340, "total_steps": 16520, "loss": 0.0898, "lr": 0.0009685687747117524, "epoch": 4.043583535108959, "percentage": 20.22, "elapsed_time": "0:11:13", "remaining_time": "0:44:19", "throughput": 2030.19, "total_tokens": 1368136}
{"current_steps": 3345, "total_steps": 16520, "loss": 0.117, "lr": 0.0009683841759464113, "epoch": 4.049636803874092, "percentage": 20.25, "elapsed_time": "0:11:14", "remaining_time": "0:44:18", "throughput": 2030.49, "total_tokens": 1370344}
{"current_steps": 3350, "total_steps": 16520, "loss": 0.0492, "lr": 0.0009681990543795723, "epoch": 4.0556900726392255, "percentage": 20.28, "elapsed_time": "0:11:15", "remaining_time": "0:44:16", "throughput": 2030.52, "total_tokens": 1372264}
{"current_steps": 3355, "total_steps": 16520, "loss": 0.1406, "lr": 0.0009680134102178648, "epoch": 4.061743341404358, "percentage": 20.31, "elapsed_time": "0:11:16", "remaining_time": "0:44:15", "throughput": 2030.54, "total_tokens": 1374248}
{"current_steps": 3360, "total_steps": 16520, "loss": 0.0979, "lr": 0.0009678272436685014, "epoch": 4.067796610169491, "percentage": 20.34, "elapsed_time": "0:11:17", "remaining_time": "0:44:14", "throughput": 2030.73, "total_tokens": 1376328}
{"current_steps": 3365, "total_steps": 16520, "loss": 0.1586, "lr": 0.0009676405549392771, "epoch": 4.073849878934625, "percentage": 20.37, "elapsed_time": "0:11:18", "remaining_time": "0:44:13", "throughput": 2031.04, "total_tokens": 1378408}
{"current_steps": 3370, "total_steps": 16520, "loss": 0.1289, "lr": 0.0009674533442385709, "epoch": 4.079903147699758, "percentage": 20.4, "elapsed_time": "0:11:19", "remaining_time": "0:44:11", "throughput": 2031.06, "total_tokens": 1380296}
{"current_steps": 3375, "total_steps": 16520, "loss": 0.0841, "lr": 0.0009672656117753434, "epoch": 4.085956416464891, "percentage": 20.43, "elapsed_time": "0:11:20", "remaining_time": "0:44:10", "throughput": 2031.15, "total_tokens": 1382280}
{"current_steps": 3380, "total_steps": 16520, "loss": 0.0438, "lr": 0.0009670773577591383, "epoch": 4.092009685230024, "percentage": 20.46, "elapsed_time": "0:11:21", "remaining_time": "0:44:09", "throughput": 2031.3, "total_tokens": 1384360}
{"current_steps": 3385, "total_steps": 16520, "loss": 0.0894, "lr": 0.0009668885824000809, "epoch": 4.098062953995157, "percentage": 20.49, "elapsed_time": "0:11:22", "remaining_time": "0:44:08", "throughput": 2031.49, "total_tokens": 1386408}
{"current_steps": 3390, "total_steps": 16520, "loss": 0.0301, "lr": 0.0009666992859088788, "epoch": 4.1041162227602905, "percentage": 20.52, "elapsed_time": "0:11:23", "remaining_time": "0:44:07", "throughput": 2031.68, "total_tokens": 1388520}
{"current_steps": 3395, "total_steps": 16520, "loss": 0.1115, "lr": 0.0009665094684968213, "epoch": 4.110169491525424, "percentage": 20.55, "elapsed_time": "0:11:24", "remaining_time": "0:44:05", "throughput": 2031.79, "total_tokens": 1390440}
{"current_steps": 3400, "total_steps": 16520, "loss": 0.0988, "lr": 0.0009663191303757785, "epoch": 4.116222760290557, "percentage": 20.58, "elapsed_time": "0:11:25", "remaining_time": "0:44:04", "throughput": 2031.93, "total_tokens": 1392456}
{"current_steps": 3405, "total_steps": 16520, "loss": 0.0638, "lr": 0.0009661282717582028, "epoch": 4.12227602905569, "percentage": 20.61, "elapsed_time": "0:11:26", "remaining_time": "0:44:03", "throughput": 2032.24, "total_tokens": 1394696}
{"current_steps": 3410, "total_steps": 16520, "loss": 0.1201, "lr": 0.0009659368928571264, "epoch": 4.128329297820823, "percentage": 20.64, "elapsed_time": "0:11:27", "remaining_time": "0:44:01", "throughput": 2032.38, "total_tokens": 1396648}
{"current_steps": 3415, "total_steps": 16520, "loss": 0.0748, "lr": 0.000965744993886163, "epoch": 4.134382566585956, "percentage": 20.67, "elapsed_time": "0:11:28", "remaining_time": "0:44:00", "throughput": 2032.49, "total_tokens": 1398696}
{"current_steps": 3420, "total_steps": 16520, "loss": 0.0816, "lr": 0.0009655525750595067, "epoch": 4.14043583535109, "percentage": 20.7, "elapsed_time": "0:11:29", "remaining_time": "0:43:59", "throughput": 2032.77, "total_tokens": 1400904}
{"current_steps": 3425, "total_steps": 16520, "loss": 0.0758, "lr": 0.0009653596365919315, "epoch": 4.146489104116223, "percentage": 20.73, "elapsed_time": "0:11:30", "remaining_time": "0:43:58", "throughput": 2032.95, "total_tokens": 1403016}
{"current_steps": 3430, "total_steps": 16520, "loss": 0.0953, "lr": 0.0009651661786987919, "epoch": 4.1525423728813555, "percentage": 20.76, "elapsed_time": "0:11:31", "remaining_time": "0:43:57", "throughput": 2033.1, "total_tokens": 1405032}
{"current_steps": 3435, "total_steps": 16520, "loss": 0.0937, "lr": 0.0009649722015960218, "epoch": 4.158595641646489, "percentage": 20.79, "elapsed_time": "0:11:32", "remaining_time": "0:43:56", "throughput": 2033.28, "total_tokens": 1407080}
{"current_steps": 3440, "total_steps": 16520, "loss": 0.0833, "lr": 0.0009647777055001347, "epoch": 4.164648910411622, "percentage": 20.82, "elapsed_time": "0:11:32", "remaining_time": "0:43:54", "throughput": 2033.38, "total_tokens": 1409064}
{"current_steps": 3445, "total_steps": 16520, "loss": 0.0603, "lr": 0.0009645826906282233, "epoch": 4.170702179176756, "percentage": 20.85, "elapsed_time": "0:11:33", "remaining_time": "0:43:53", "throughput": 2033.59, "total_tokens": 1411144}
{"current_steps": 3450, "total_steps": 16520, "loss": 0.053, "lr": 0.0009643871571979599, "epoch": 4.176755447941889, "percentage": 20.88, "elapsed_time": "0:11:34", "remaining_time": "0:43:52", "throughput": 2033.86, "total_tokens": 1413320}
{"current_steps": 3455, "total_steps": 16520, "loss": 0.1344, "lr": 0.0009641911054275949, "epoch": 4.182808716707021, "percentage": 20.91, "elapsed_time": "0:11:35", "remaining_time": "0:43:51", "throughput": 2034.0, "total_tokens": 1415336}
{"current_steps": 3460, "total_steps": 16520, "loss": 0.0592, "lr": 0.0009639945355359576, "epoch": 4.188861985472155, "percentage": 20.94, "elapsed_time": "0:11:36", "remaining_time": "0:43:50", "throughput": 2034.11, "total_tokens": 1417384}
{"current_steps": 3465, "total_steps": 16520, "loss": 0.1662, "lr": 0.0009637974477424556, "epoch": 4.194915254237288, "percentage": 20.97, "elapsed_time": "0:11:37", "remaining_time": "0:43:48", "throughput": 2034.17, "total_tokens": 1419336}
{"current_steps": 3470, "total_steps": 16520, "loss": 0.0725, "lr": 0.0009635998422670744, "epoch": 4.200968523002421, "percentage": 21.0, "elapsed_time": "0:11:38", "remaining_time": "0:43:47", "throughput": 2034.28, "total_tokens": 1421384}
{"current_steps": 3475, "total_steps": 16520, "loss": 0.0899, "lr": 0.0009634017193303777, "epoch": 4.207021791767555, "percentage": 21.04, "elapsed_time": "0:11:39", "remaining_time": "0:43:46", "throughput": 2034.4, "total_tokens": 1423368}
{"current_steps": 3480, "total_steps": 16520, "loss": 0.1054, "lr": 0.0009632030791535063, "epoch": 4.213075060532688, "percentage": 21.07, "elapsed_time": "0:11:40", "remaining_time": "0:43:44", "throughput": 2034.49, "total_tokens": 1425224}
{"current_steps": 3485, "total_steps": 16520, "loss": 0.0627, "lr": 0.0009630039219581788, "epoch": 4.219128329297821, "percentage": 21.1, "elapsed_time": "0:11:41", "remaining_time": "0:43:43", "throughput": 2034.64, "total_tokens": 1427304}
{"current_steps": 3490, "total_steps": 16520, "loss": 0.0913, "lr": 0.0009628042479666905, "epoch": 4.225181598062954, "percentage": 21.13, "elapsed_time": "0:11:42", "remaining_time": "0:43:42", "throughput": 2034.78, "total_tokens": 1429320}
{"current_steps": 3495, "total_steps": 16520, "loss": 0.1044, "lr": 0.0009626040574019139, "epoch": 4.231234866828087, "percentage": 21.16, "elapsed_time": "0:11:43", "remaining_time": "0:43:41", "throughput": 2034.97, "total_tokens": 1431368}
{"current_steps": 3500, "total_steps": 16520, "loss": 0.0737, "lr": 0.0009624033504872977, "epoch": 4.237288135593221, "percentage": 21.19, "elapsed_time": "0:11:44", "remaining_time": "0:43:39", "throughput": 2035.11, "total_tokens": 1433320}
{"current_steps": 3505, "total_steps": 16520, "loss": 0.0667, "lr": 0.0009622021274468673, "epoch": 4.243341404358354, "percentage": 21.22, "elapsed_time": "0:11:45", "remaining_time": "0:43:38", "throughput": 2035.38, "total_tokens": 1435528}
{"current_steps": 3510, "total_steps": 16520, "loss": 0.0981, "lr": 0.0009620003885052239, "epoch": 4.249394673123486, "percentage": 21.25, "elapsed_time": "0:11:46", "remaining_time": "0:43:37", "throughput": 2035.48, "total_tokens": 1437512}
{"current_steps": 3515, "total_steps": 16520, "loss": 0.156, "lr": 0.0009617981338875448, "epoch": 4.25544794188862, "percentage": 21.28, "elapsed_time": "0:11:47", "remaining_time": "0:43:36", "throughput": 2035.63, "total_tokens": 1439528}
{"current_steps": 3520, "total_steps": 16520, "loss": 0.0921, "lr": 0.0009615953638195826, "epoch": 4.261501210653753, "percentage": 21.31, "elapsed_time": "0:11:48", "remaining_time": "0:43:35", "throughput": 2035.89, "total_tokens": 1441704}
{"current_steps": 3525, "total_steps": 16520, "loss": 0.0944, "lr": 0.0009613920785276655, "epoch": 4.267554479418886, "percentage": 21.34, "elapsed_time": "0:11:49", "remaining_time": "0:43:34", "throughput": 2036.15, "total_tokens": 1443880}
{"current_steps": 3530, "total_steps": 16520, "loss": 0.1207, "lr": 0.0009611882782386967, "epoch": 4.27360774818402, "percentage": 21.37, "elapsed_time": "0:11:50", "remaining_time": "0:43:33", "throughput": 2036.22, "total_tokens": 1445896}
{"current_steps": 3535, "total_steps": 16520, "loss": 0.0869, "lr": 0.000960983963180154, "epoch": 4.279661016949152, "percentage": 21.4, "elapsed_time": "0:11:50", "remaining_time": "0:43:31", "throughput": 2036.27, "total_tokens": 1447784}
{"current_steps": 3540, "total_steps": 16520, "loss": 0.1486, "lr": 0.0009607791335800902, "epoch": 4.285714285714286, "percentage": 21.43, "elapsed_time": "0:11:51", "remaining_time": "0:43:30", "throughput": 2036.46, "total_tokens": 1449896}
{"current_steps": 3545, "total_steps": 16520, "loss": 0.0369, "lr": 0.000960573789667132, "epoch": 4.291767554479419, "percentage": 21.46, "elapsed_time": "0:11:52", "remaining_time": "0:43:29", "throughput": 2036.45, "total_tokens": 1451848}
{"current_steps": 3550, "total_steps": 16520, "loss": 0.1061, "lr": 0.0009603679316704805, "epoch": 4.297820823244552, "percentage": 21.49, "elapsed_time": "0:11:53", "remaining_time": "0:43:28", "throughput": 2036.67, "total_tokens": 1453928}
{"current_steps": 3555, "total_steps": 16520, "loss": 0.1413, "lr": 0.0009601615598199104, "epoch": 4.303874092009686, "percentage": 21.52, "elapsed_time": "0:11:54", "remaining_time": "0:43:26", "throughput": 2036.81, "total_tokens": 1455944}
{"current_steps": 3560, "total_steps": 16520, "loss": 0.0868, "lr": 0.0009599546743457701, "epoch": 4.309927360774818, "percentage": 21.55, "elapsed_time": "0:11:55", "remaining_time": "0:43:25", "throughput": 2036.87, "total_tokens": 1457896}
{"current_steps": 3565, "total_steps": 16520, "loss": 0.0721, "lr": 0.0009597472754789814, "epoch": 4.315980629539951, "percentage": 21.58, "elapsed_time": "0:11:56", "remaining_time": "0:43:24", "throughput": 2036.94, "total_tokens": 1459848}
{"current_steps": 3570, "total_steps": 16520, "loss": 0.0348, "lr": 0.0009595393634510385, "epoch": 4.322033898305085, "percentage": 21.61, "elapsed_time": "0:11:57", "remaining_time": "0:43:23", "throughput": 2037.07, "total_tokens": 1461800}
{"current_steps": 3575, "total_steps": 16520, "loss": 0.0423, "lr": 0.0009593309384940092, "epoch": 4.328087167070218, "percentage": 21.64, "elapsed_time": "0:11:58", "remaining_time": "0:43:21", "throughput": 2037.2, "total_tokens": 1463752}
{"current_steps": 3580, "total_steps": 16520, "loss": 0.0641, "lr": 0.0009591220008405334, "epoch": 4.3341404358353515, "percentage": 21.67, "elapsed_time": "0:11:59", "remaining_time": "0:43:20", "throughput": 2037.38, "total_tokens": 1465800}
{"current_steps": 3585, "total_steps": 16520, "loss": 0.0719, "lr": 0.0009589125507238233, "epoch": 4.340193704600484, "percentage": 21.7, "elapsed_time": "0:12:00", "remaining_time": "0:43:19", "throughput": 2037.55, "total_tokens": 1467912}
{"current_steps": 3590, "total_steps": 16520, "loss": 0.0734, "lr": 0.0009587025883776632, "epoch": 4.346246973365617, "percentage": 21.73, "elapsed_time": "0:12:01", "remaining_time": "0:43:18", "throughput": 2037.64, "total_tokens": 1469832}
{"current_steps": 3595, "total_steps": 16520, "loss": 0.0688, "lr": 0.0009584921140364089, "epoch": 4.352300242130751, "percentage": 21.76, "elapsed_time": "0:12:02", "remaining_time": "0:43:16", "throughput": 2037.78, "total_tokens": 1471848}
{"current_steps": 3600, "total_steps": 16520, "loss": 0.1008, "lr": 0.0009582811279349881, "epoch": 4.358353510895884, "percentage": 21.79, "elapsed_time": "0:12:03", "remaining_time": "0:43:15", "throughput": 2037.87, "total_tokens": 1473832}
{"current_steps": 3605, "total_steps": 16520, "loss": 0.0995, "lr": 0.0009580696303088993, "epoch": 4.364406779661017, "percentage": 21.82, "elapsed_time": "0:12:04", "remaining_time": "0:43:14", "throughput": 2038.0, "total_tokens": 1475784}
{"current_steps": 3610, "total_steps": 16520, "loss": 0.0828, "lr": 0.000957857621394212, "epoch": 4.37046004842615, "percentage": 21.85, "elapsed_time": "0:12:05", "remaining_time": "0:43:13", "throughput": 2038.22, "total_tokens": 1477960}
{"current_steps": 3615, "total_steps": 16520, "loss": 0.1106, "lr": 0.0009576451014275669, "epoch": 4.376513317191283, "percentage": 21.88, "elapsed_time": "0:12:06", "remaining_time": "0:43:11", "throughput": 2038.36, "total_tokens": 1479912}
{"current_steps": 3620, "total_steps": 16520, "loss": 0.0452, "lr": 0.0009574320706461746, "epoch": 4.3825665859564165, "percentage": 21.91, "elapsed_time": "0:12:06", "remaining_time": "0:43:10", "throughput": 2038.39, "total_tokens": 1481896}
{"current_steps": 3625, "total_steps": 16520, "loss": 0.0462, "lr": 0.0009572185292878157, "epoch": 4.38861985472155, "percentage": 21.94, "elapsed_time": "0:12:07", "remaining_time": "0:43:09", "throughput": 2038.57, "total_tokens": 1484008}
{"current_steps": 3630, "total_steps": 16520, "loss": 0.0771, "lr": 0.0009570044775908412, "epoch": 4.394673123486683, "percentage": 21.97, "elapsed_time": "0:12:08", "remaining_time": "0:43:08", "throughput": 2038.51, "total_tokens": 1485864}
{"current_steps": 3635, "total_steps": 16520, "loss": 0.0659, "lr": 0.0009567899157941715, "epoch": 4.400726392251816, "percentage": 22.0, "elapsed_time": "0:12:09", "remaining_time": "0:43:07", "throughput": 2038.77, "total_tokens": 1488072}
{"current_steps": 3640, "total_steps": 16520, "loss": 0.0931, "lr": 0.0009565748441372966, "epoch": 4.406779661016949, "percentage": 22.03, "elapsed_time": "0:12:10", "remaining_time": "0:43:06", "throughput": 2039.07, "total_tokens": 1490312}
{"current_steps": 3645, "total_steps": 16520, "loss": 0.0736, "lr": 0.000956359262860275, "epoch": 4.412832929782082, "percentage": 22.06, "elapsed_time": "0:12:11", "remaining_time": "0:43:04", "throughput": 2039.21, "total_tokens": 1492328}
{"current_steps": 3650, "total_steps": 16520, "loss": 0.1267, "lr": 0.000956143172203735, "epoch": 4.418886198547216, "percentage": 22.09, "elapsed_time": "0:12:12", "remaining_time": "0:43:03", "throughput": 2039.42, "total_tokens": 1494472}
{"current_steps": 3655, "total_steps": 16520, "loss": 0.1006, "lr": 0.0009559265724088723, "epoch": 4.424939467312349, "percentage": 22.12, "elapsed_time": "0:12:13", "remaining_time": "0:43:02", "throughput": 2039.56, "total_tokens": 1496552}
{"current_steps": 3660, "total_steps": 16520, "loss": 0.1198, "lr": 0.0009557094637174517, "epoch": 4.4309927360774815, "percentage": 22.15, "elapsed_time": "0:12:14", "remaining_time": "0:43:01", "throughput": 2039.66, "total_tokens": 1498536}
{"current_steps": 3665, "total_steps": 16520, "loss": 0.0718, "lr": 0.0009554918463718057, "epoch": 4.437046004842615, "percentage": 22.19, "elapsed_time": "0:12:15", "remaining_time": "0:43:00", "throughput": 2039.82, "total_tokens": 1500584}
{"current_steps": 3670, "total_steps": 16520, "loss": 0.0546, "lr": 0.0009552737206148347, "epoch": 4.443099273607748, "percentage": 22.22, "elapsed_time": "0:12:16", "remaining_time": "0:42:59", "throughput": 2039.95, "total_tokens": 1502600}
{"current_steps": 3675, "total_steps": 16520, "loss": 0.0474, "lr": 0.0009550550866900065, "epoch": 4.4491525423728815, "percentage": 22.25, "elapsed_time": "0:12:17", "remaining_time": "0:42:57", "throughput": 2040.06, "total_tokens": 1504648}
{"current_steps": 3680, "total_steps": 16520, "loss": 0.1256, "lr": 0.0009548359448413563, "epoch": 4.455205811138015, "percentage": 22.28, "elapsed_time": "0:12:18", "remaining_time": "0:42:56", "throughput": 2040.07, "total_tokens": 1506504}
{"current_steps": 3685, "total_steps": 16520, "loss": 0.0632, "lr": 0.0009546162953134858, "epoch": 4.461259079903147, "percentage": 22.31, "elapsed_time": "0:12:19", "remaining_time": "0:42:55", "throughput": 2040.2, "total_tokens": 1508520}
{"current_steps": 3690, "total_steps": 16520, "loss": 0.1588, "lr": 0.0009543961383515636, "epoch": 4.467312348668281, "percentage": 22.34, "elapsed_time": "0:12:20", "remaining_time": "0:42:54", "throughput": 2040.37, "total_tokens": 1510536}
{"current_steps": 3695, "total_steps": 16520, "loss": 0.0488, "lr": 0.0009541754742013252, "epoch": 4.473365617433414, "percentage": 22.37, "elapsed_time": "0:12:21", "remaining_time": "0:42:52", "throughput": 2040.58, "total_tokens": 1512616}
{"current_steps": 3700, "total_steps": 16520, "loss": 0.0529, "lr": 0.000953954303109071, "epoch": 4.479418886198547, "percentage": 22.4, "elapsed_time": "0:12:22", "remaining_time": "0:42:51", "throughput": 2040.67, "total_tokens": 1514664}
{"current_steps": 3705, "total_steps": 16520, "loss": 0.045, "lr": 0.0009537326253216684, "epoch": 4.485472154963681, "percentage": 22.43, "elapsed_time": "0:12:23", "remaining_time": "0:42:51", "throughput": 2040.07, "total_tokens": 1516648}
{"current_steps": 3710, "total_steps": 16520, "loss": 0.0328, "lr": 0.0009535104410865499, "epoch": 4.491525423728813, "percentage": 22.46, "elapsed_time": "0:12:24", "remaining_time": "0:42:50", "throughput": 2040.38, "total_tokens": 1518888}
{"current_steps": 3715, "total_steps": 16520, "loss": 0.1423, "lr": 0.000953287750651713, "epoch": 4.4975786924939465, "percentage": 22.49, "elapsed_time": "0:12:25", "remaining_time": "0:42:49", "throughput": 2040.61, "total_tokens": 1520936}
{"current_steps": 3720, "total_steps": 16520, "loss": 0.0448, "lr": 0.000953064554265721, "epoch": 4.50363196125908, "percentage": 22.52, "elapsed_time": "0:12:26", "remaining_time": "0:42:47", "throughput": 2040.74, "total_tokens": 1523016}
{"current_steps": 3725, "total_steps": 16520, "loss": 0.1189, "lr": 0.0009528408521777012, "epoch": 4.509685230024213, "percentage": 22.55, "elapsed_time": "0:12:27", "remaining_time": "0:42:46", "throughput": 2040.82, "total_tokens": 1525000}
{"current_steps": 3730, "total_steps": 16520, "loss": 0.067, "lr": 0.0009526166446373457, "epoch": 4.5157384987893465, "percentage": 22.58, "elapsed_time": "0:12:28", "remaining_time": "0:42:45", "throughput": 2040.99, "total_tokens": 1527112}
{"current_steps": 3735, "total_steps": 16520, "loss": 0.1638, "lr": 0.0009523919318949105, "epoch": 4.521791767554479, "percentage": 22.61, "elapsed_time": "0:12:29", "remaining_time": "0:42:44", "throughput": 2041.09, "total_tokens": 1529160}
{"current_steps": 3740, "total_steps": 16520, "loss": 0.0713, "lr": 0.0009521667142012159, "epoch": 4.527845036319612, "percentage": 22.64, "elapsed_time": "0:12:30", "remaining_time": "0:42:43", "throughput": 2041.18, "total_tokens": 1531208}
{"current_steps": 3745, "total_steps": 16520, "loss": 0.1333, "lr": 0.0009519409918076456, "epoch": 4.533898305084746, "percentage": 22.67, "elapsed_time": "0:12:31", "remaining_time": "0:42:42", "throughput": 2041.37, "total_tokens": 1533288}
{"current_steps": 3750, "total_steps": 16520, "loss": 0.1179, "lr": 0.0009517147649661464, "epoch": 4.539951573849879, "percentage": 22.7, "elapsed_time": "0:12:32", "remaining_time": "0:42:40", "throughput": 2041.4, "total_tokens": 1535240}
{"current_steps": 3755, "total_steps": 16520, "loss": 0.0773, "lr": 0.0009514880339292285, "epoch": 4.546004842615012, "percentage": 22.73, "elapsed_time": "0:12:32", "remaining_time": "0:42:39", "throughput": 2041.48, "total_tokens": 1537224}
{"current_steps": 3760, "total_steps": 16520, "loss": 0.0857, "lr": 0.0009512607989499649, "epoch": 4.552058111380145, "percentage": 22.76, "elapsed_time": "0:12:33", "remaining_time": "0:42:38", "throughput": 2041.71, "total_tokens": 1539400}
{"current_steps": 3765, "total_steps": 16520, "loss": 0.0893, "lr": 0.0009510330602819908, "epoch": 4.558111380145278, "percentage": 22.79, "elapsed_time": "0:12:34", "remaining_time": "0:42:37", "throughput": 2041.72, "total_tokens": 1541320}
{"current_steps": 3770, "total_steps": 16520, "loss": 0.1012, "lr": 0.0009508048181795039, "epoch": 4.5641646489104115, "percentage": 22.82, "elapsed_time": "0:12:35", "remaining_time": "0:42:36", "throughput": 2041.88, "total_tokens": 1543432}
{"current_steps": 3775, "total_steps": 16520, "loss": 0.1221, "lr": 0.0009505760728972637, "epoch": 4.570217917675545, "percentage": 22.85, "elapsed_time": "0:12:36", "remaining_time": "0:42:35", "throughput": 2041.85, "total_tokens": 1545320}
{"current_steps": 3780, "total_steps": 16520, "loss": 0.0961, "lr": 0.0009503468246905911, "epoch": 4.576271186440678, "percentage": 22.88, "elapsed_time": "0:12:37", "remaining_time": "0:42:34", "throughput": 2041.94, "total_tokens": 1547368}
{"current_steps": 3785, "total_steps": 16520, "loss": 0.1166, "lr": 0.0009501170738153686, "epoch": 4.582324455205811, "percentage": 22.91, "elapsed_time": "0:12:38", "remaining_time": "0:42:32", "throughput": 2042.05, "total_tokens": 1549320}
{"current_steps": 3790, "total_steps": 16520, "loss": 0.1115, "lr": 0.0009498868205280401, "epoch": 4.588377723970944, "percentage": 22.94, "elapsed_time": "0:12:39", "remaining_time": "0:42:31", "throughput": 2042.27, "total_tokens": 1551432}
{"current_steps": 3795, "total_steps": 16520, "loss": 0.0933, "lr": 0.0009496560650856096, "epoch": 4.594430992736077, "percentage": 22.97, "elapsed_time": "0:12:40", "remaining_time": "0:42:30", "throughput": 2042.39, "total_tokens": 1553448}
{"current_steps": 3800, "total_steps": 16520, "loss": 0.0654, "lr": 0.0009494248077456421, "epoch": 4.600484261501211, "percentage": 23.0, "elapsed_time": "0:12:41", "remaining_time": "0:42:29", "throughput": 2042.62, "total_tokens": 1555560}
{"current_steps": 3805, "total_steps": 16520, "loss": 0.0518, "lr": 0.0009491930487662626, "epoch": 4.606537530266344, "percentage": 23.03, "elapsed_time": "0:12:42", "remaining_time": "0:42:28", "throughput": 2042.84, "total_tokens": 1557672}
{"current_steps": 3810, "total_steps": 16520, "loss": 0.0696, "lr": 0.000948960788406156, "epoch": 4.6125907990314765, "percentage": 23.06, "elapsed_time": "0:12:43", "remaining_time": "0:42:26", "throughput": 2042.84, "total_tokens": 1559656}
{"current_steps": 3815, "total_steps": 16520, "loss": 0.0918, "lr": 0.000948728026924567, "epoch": 4.61864406779661, "percentage": 23.09, "elapsed_time": "0:12:44", "remaining_time": "0:42:25", "throughput": 2042.95, "total_tokens": 1561736}
{"current_steps": 3820, "total_steps": 16520, "loss": 0.0698, "lr": 0.0009484947645812993, "epoch": 4.624697336561743, "percentage": 23.12, "elapsed_time": "0:12:45", "remaining_time": "0:42:24", "throughput": 2043.17, "total_tokens": 1563848}
{"current_steps": 3825, "total_steps": 16520, "loss": 0.0842, "lr": 0.0009482610016367161, "epoch": 4.6307506053268765, "percentage": 23.15, "elapsed_time": "0:12:46", "remaining_time": "0:42:23", "throughput": 2043.33, "total_tokens": 1565960}
{"current_steps": 3830, "total_steps": 16520, "loss": 0.0875, "lr": 0.0009480267383517393, "epoch": 4.63680387409201, "percentage": 23.18, "elapsed_time": "0:12:47", "remaining_time": "0:42:22", "throughput": 2043.67, "total_tokens": 1568264}
{"current_steps": 3835, "total_steps": 16520, "loss": 0.0853, "lr": 0.0009477919749878487, "epoch": 4.642857142857143, "percentage": 23.21, "elapsed_time": "0:12:48", "remaining_time": "0:42:21", "throughput": 2043.82, "total_tokens": 1570376}
{"current_steps": 3840, "total_steps": 16520, "loss": 0.1636, "lr": 0.0009475567118070829, "epoch": 4.648910411622276, "percentage": 23.24, "elapsed_time": "0:12:49", "remaining_time": "0:42:20", "throughput": 2044.01, "total_tokens": 1572552}
{"current_steps": 3845, "total_steps": 16520, "loss": 0.1079, "lr": 0.0009473209490720384, "epoch": 4.654963680387409, "percentage": 23.27, "elapsed_time": "0:12:50", "remaining_time": "0:42:19", "throughput": 2044.27, "total_tokens": 1574696}
{"current_steps": 3850, "total_steps": 16520, "loss": 0.1526, "lr": 0.0009470846870458687, "epoch": 4.661016949152542, "percentage": 23.31, "elapsed_time": "0:12:51", "remaining_time": "0:42:18", "throughput": 2044.43, "total_tokens": 1576808}
{"current_steps": 3855, "total_steps": 16520, "loss": 0.0824, "lr": 0.0009468479259922852, "epoch": 4.667070217917676, "percentage": 23.34, "elapsed_time": "0:12:52", "remaining_time": "0:42:16", "throughput": 2044.5, "total_tokens": 1578728}
{"current_steps": 3860, "total_steps": 16520, "loss": 0.0667, "lr": 0.000946610666175556, "epoch": 4.673123486682809, "percentage": 23.37, "elapsed_time": "0:12:53", "remaining_time": "0:42:15", "throughput": 2044.58, "total_tokens": 1580776}
{"current_steps": 3865, "total_steps": 16520, "loss": 0.0457, "lr": 0.0009463729078605061, "epoch": 4.6791767554479415, "percentage": 23.4, "elapsed_time": "0:12:54", "remaining_time": "0:42:14", "throughput": 2044.69, "total_tokens": 1582792}
{"current_steps": 3870, "total_steps": 16520, "loss": 0.0507, "lr": 0.0009461346513125167, "epoch": 4.685230024213075, "percentage": 23.43, "elapsed_time": "0:12:55", "remaining_time": "0:42:13", "throughput": 2044.96, "total_tokens": 1584968}
{"current_steps": 3875, "total_steps": 16520, "loss": 0.0855, "lr": 0.0009458958967975251, "epoch": 4.691283292978208, "percentage": 23.46, "elapsed_time": "0:12:56", "remaining_time": "0:42:12", "throughput": 2045.06, "total_tokens": 1587048}
{"current_steps": 3880, "total_steps": 16520, "loss": 0.1418, "lr": 0.0009456566445820247, "epoch": 4.697336561743342, "percentage": 23.49, "elapsed_time": "0:12:57", "remaining_time": "0:42:11", "throughput": 2045.19, "total_tokens": 1589160}
{"current_steps": 3885, "total_steps": 16520, "loss": 0.0538, "lr": 0.0009454168949330644, "epoch": 4.703389830508475, "percentage": 23.52, "elapsed_time": "0:12:57", "remaining_time": "0:42:10", "throughput": 2045.4, "total_tokens": 1591272}
{"current_steps": 3890, "total_steps": 16520, "loss": 0.0931, "lr": 0.000945176648118248, "epoch": 4.709443099273607, "percentage": 23.55, "elapsed_time": "0:12:58", "remaining_time": "0:42:08", "throughput": 2045.52, "total_tokens": 1593224}
{"current_steps": 3895, "total_steps": 16520, "loss": 0.0948, "lr": 0.0009449359044057344, "epoch": 4.715496368038741, "percentage": 23.58, "elapsed_time": "0:12:59", "remaining_time": "0:42:07", "throughput": 2045.63, "total_tokens": 1595304}
{"current_steps": 3900, "total_steps": 16520, "loss": 0.0454, "lr": 0.0009446946640642371, "epoch": 4.721549636803874, "percentage": 23.61, "elapsed_time": "0:13:00", "remaining_time": "0:42:06", "throughput": 2045.82, "total_tokens": 1597448}
{"current_steps": 3905, "total_steps": 16520, "loss": 0.1158, "lr": 0.0009444529273630243, "epoch": 4.727602905569007, "percentage": 23.64, "elapsed_time": "0:13:01", "remaining_time": "0:42:05", "throughput": 2045.86, "total_tokens": 1599464}
{"current_steps": 3910, "total_steps": 16520, "loss": 0.1498, "lr": 0.0009442106945719176, "epoch": 4.733656174334141, "percentage": 23.67, "elapsed_time": "0:13:02", "remaining_time": "0:42:04", "throughput": 2045.98, "total_tokens": 1601480}
{"current_steps": 3915, "total_steps": 16520, "loss": 0.0773, "lr": 0.0009439679659612926, "epoch": 4.739709443099273, "percentage": 23.7, "elapsed_time": "0:13:03", "remaining_time": "0:42:03", "throughput": 2046.09, "total_tokens": 1603496}
{"current_steps": 3920, "total_steps": 16520, "loss": 0.1825, "lr": 0.0009437247418020787, "epoch": 4.745762711864407, "percentage": 23.73, "elapsed_time": "0:13:04", "remaining_time": "0:42:02", "throughput": 2046.31, "total_tokens": 1605672}
{"current_steps": 3925, "total_steps": 16520, "loss": 0.1177, "lr": 0.0009434810223657576, "epoch": 4.75181598062954, "percentage": 23.76, "elapsed_time": "0:13:05", "remaining_time": "0:42:01", "throughput": 2046.6, "total_tokens": 1607944}
{"current_steps": 3930, "total_steps": 16520, "loss": 0.1041, "lr": 0.0009432368079243647, "epoch": 4.757869249394673, "percentage": 23.79, "elapsed_time": "0:13:06", "remaining_time": "0:42:00", "throughput": 2046.68, "total_tokens": 1609992}
{"current_steps": 3935, "total_steps": 16520, "loss": 0.1067, "lr": 0.0009429920987504872, "epoch": 4.763922518159807, "percentage": 23.82, "elapsed_time": "0:13:07", "remaining_time": "0:41:58", "throughput": 2046.79, "total_tokens": 1612008}
{"current_steps": 3940, "total_steps": 16520, "loss": 0.1699, "lr": 0.0009427468951172651, "epoch": 4.76997578692494, "percentage": 23.85, "elapsed_time": "0:13:08", "remaining_time": "0:41:57", "throughput": 2046.84, "total_tokens": 1614024}
{"current_steps": 3945, "total_steps": 16520, "loss": 0.056, "lr": 0.0009425011972983899, "epoch": 4.776029055690072, "percentage": 23.88, "elapsed_time": "0:13:09", "remaining_time": "0:41:56", "throughput": 2047.02, "total_tokens": 1616168}
{"current_steps": 3950, "total_steps": 16520, "loss": 0.0677, "lr": 0.0009422550055681047, "epoch": 4.782082324455206, "percentage": 23.91, "elapsed_time": "0:13:10", "remaining_time": "0:41:55", "throughput": 2047.09, "total_tokens": 1618152}
{"current_steps": 3955, "total_steps": 16520, "loss": 0.1133, "lr": 0.0009420083202012042, "epoch": 4.788135593220339, "percentage": 23.94, "elapsed_time": "0:13:11", "remaining_time": "0:41:54", "throughput": 2047.24, "total_tokens": 1620264}
{"current_steps": 3960, "total_steps": 16520, "loss": 0.1382, "lr": 0.0009417611414730339, "epoch": 4.7941888619854724, "percentage": 23.97, "elapsed_time": "0:13:12", "remaining_time": "0:41:53", "throughput": 2047.35, "total_tokens": 1622312}
{"current_steps": 3965, "total_steps": 16520, "loss": 0.1538, "lr": 0.0009415134696594898, "epoch": 4.800242130750606, "percentage": 24.0, "elapsed_time": "0:13:13", "remaining_time": "0:41:52", "throughput": 2047.54, "total_tokens": 1624488}
{"current_steps": 3970, "total_steps": 16520, "loss": 0.0845, "lr": 0.0009412653050370188, "epoch": 4.806295399515738, "percentage": 24.03, "elapsed_time": "0:13:14", "remaining_time": "0:41:51", "throughput": 2047.72, "total_tokens": 1626568}
{"current_steps": 3975, "total_steps": 16520, "loss": 0.0926, "lr": 0.0009410166478826172, "epoch": 4.812348668280872, "percentage": 24.06, "elapsed_time": "0:13:15", "remaining_time": "0:41:49", "throughput": 2047.79, "total_tokens": 1628552}
{"current_steps": 3980, "total_steps": 16520, "loss": 0.1099, "lr": 0.0009407674984738315, "epoch": 4.818401937046005, "percentage": 24.09, "elapsed_time": "0:13:16", "remaining_time": "0:41:48", "throughput": 2048.04, "total_tokens": 1630792}
{"current_steps": 3985, "total_steps": 16520, "loss": 0.1263, "lr": 0.0009405178570887576, "epoch": 4.824455205811138, "percentage": 24.12, "elapsed_time": "0:13:17", "remaining_time": "0:41:47", "throughput": 2048.04, "total_tokens": 1632712}
{"current_steps": 3990, "total_steps": 16520, "loss": 0.0431, "lr": 0.0009402677240060402, "epoch": 4.830508474576272, "percentage": 24.15, "elapsed_time": "0:13:18", "remaining_time": "0:41:46", "throughput": 2048.18, "total_tokens": 1634824}
{"current_steps": 3995, "total_steps": 16520, "loss": 0.0796, "lr": 0.0009400170995048734, "epoch": 4.836561743341404, "percentage": 24.18, "elapsed_time": "0:13:19", "remaining_time": "0:41:45", "throughput": 2048.36, "total_tokens": 1636968}
{"current_steps": 4000, "total_steps": 16520, "loss": 0.0419, "lr": 0.0009397659838649994, "epoch": 4.842615012106537, "percentage": 24.21, "elapsed_time": "0:13:20", "remaining_time": "0:41:44", "throughput": 2048.53, "total_tokens": 1639112}
{"current_steps": 4005, "total_steps": 16520, "loss": 0.1404, "lr": 0.0009395143773667088, "epoch": 4.848668280871671, "percentage": 24.24, "elapsed_time": "0:13:21", "remaining_time": "0:41:43", "throughput": 2048.59, "total_tokens": 1641096}
{"current_steps": 4010, "total_steps": 16520, "loss": 0.0686, "lr": 0.0009392622802908396, "epoch": 4.854721549636804, "percentage": 24.27, "elapsed_time": "0:13:22", "remaining_time": "0:41:42", "throughput": 2048.76, "total_tokens": 1643240}
{"current_steps": 4015, "total_steps": 16520, "loss": 0.0882, "lr": 0.0009390096929187781, "epoch": 4.8607748184019375, "percentage": 24.3, "elapsed_time": "0:13:23", "remaining_time": "0:41:41", "throughput": 2049.0, "total_tokens": 1645384}
{"current_steps": 4020, "total_steps": 16520, "loss": 0.0577, "lr": 0.0009387566155324574, "epoch": 4.86682808716707, "percentage": 24.33, "elapsed_time": "0:13:23", "remaining_time": "0:41:39", "throughput": 2049.14, "total_tokens": 1647496}
{"current_steps": 4025, "total_steps": 16520, "loss": 0.0349, "lr": 0.0009385030484143576, "epoch": 4.872881355932203, "percentage": 24.36, "elapsed_time": "0:13:24", "remaining_time": "0:41:38", "throughput": 2049.25, "total_tokens": 1649576}
{"current_steps": 4030, "total_steps": 16520, "loss": 0.0464, "lr": 0.0009382489918475056, "epoch": 4.878934624697337, "percentage": 24.39, "elapsed_time": "0:13:25", "remaining_time": "0:41:37", "throughput": 2049.32, "total_tokens": 1651560}
{"current_steps": 4035, "total_steps": 16520, "loss": 0.0728, "lr": 0.0009379944461154746, "epoch": 4.88498789346247, "percentage": 24.42, "elapsed_time": "0:13:26", "remaining_time": "0:41:36", "throughput": 2049.33, "total_tokens": 1653544}
{"current_steps": 4040, "total_steps": 16520, "loss": 0.0757, "lr": 0.0009377394115023835, "epoch": 4.891041162227603, "percentage": 24.46, "elapsed_time": "0:13:27", "remaining_time": "0:41:35", "throughput": 2049.44, "total_tokens": 1655624}
{"current_steps": 4045, "total_steps": 16520, "loss": 0.0565, "lr": 0.000937483888292897, "epoch": 4.897094430992736, "percentage": 24.49, "elapsed_time": "0:13:28", "remaining_time": "0:41:34", "throughput": 2049.51, "total_tokens": 1657672}
{"current_steps": 4050, "total_steps": 16520, "loss": 0.0351, "lr": 0.0009372278767722257, "epoch": 4.903147699757869, "percentage": 24.52, "elapsed_time": "0:13:29", "remaining_time": "0:41:33", "throughput": 2049.58, "total_tokens": 1659656}
{"current_steps": 4055, "total_steps": 16520, "loss": 0.0408, "lr": 0.0009369713772261242, "epoch": 4.9092009685230025, "percentage": 24.55, "elapsed_time": "0:13:30", "remaining_time": "0:41:32", "throughput": 2049.65, "total_tokens": 1661704}
{"current_steps": 4060, "total_steps": 16520, "loss": 0.0866, "lr": 0.0009367143899408928, "epoch": 4.915254237288136, "percentage": 24.58, "elapsed_time": "0:13:31", "remaining_time": "0:41:31", "throughput": 2049.72, "total_tokens": 1663752}
{"current_steps": 4065, "total_steps": 16520, "loss": 0.1057, "lr": 0.0009364569152033757, "epoch": 4.921307506053269, "percentage": 24.61, "elapsed_time": "0:13:32", "remaining_time": "0:41:30", "throughput": 2049.92, "total_tokens": 1665928}
{"current_steps": 4070, "total_steps": 16520, "loss": 0.0816, "lr": 0.0009361989533009611, "epoch": 4.927360774818402, "percentage": 24.64, "elapsed_time": "0:13:33", "remaining_time": "0:41:28", "throughput": 2050.02, "total_tokens": 1667944}
{"current_steps": 4075, "total_steps": 16520, "loss": 0.196, "lr": 0.0009359405045215815, "epoch": 4.933414043583535, "percentage": 24.67, "elapsed_time": "0:13:34", "remaining_time": "0:41:27", "throughput": 2050.09, "total_tokens": 1669928}
{"current_steps": 4080, "total_steps": 16520, "loss": 0.1198, "lr": 0.0009356815691537124, "epoch": 4.939467312348668, "percentage": 24.7, "elapsed_time": "0:13:35", "remaining_time": "0:41:26", "throughput": 2050.22, "total_tokens": 1672040}
{"current_steps": 4085, "total_steps": 16520, "loss": 0.142, "lr": 0.0009354221474863725, "epoch": 4.945520581113802, "percentage": 24.73, "elapsed_time": "0:13:36", "remaining_time": "0:41:25", "throughput": 2050.33, "total_tokens": 1674120}
{"current_steps": 4090, "total_steps": 16520, "loss": 0.0761, "lr": 0.0009351622398091232, "epoch": 4.951573849878935, "percentage": 24.76, "elapsed_time": "0:13:37", "remaining_time": "0:41:24", "throughput": 2050.33, "total_tokens": 1676040}
{"current_steps": 4095, "total_steps": 16520, "loss": 0.1269, "lr": 0.0009349018464120686, "epoch": 4.9576271186440675, "percentage": 24.79, "elapsed_time": "0:13:38", "remaining_time": "0:41:23", "throughput": 2050.44, "total_tokens": 1678152}
{"current_steps": 4100, "total_steps": 16520, "loss": 0.1069, "lr": 0.0009346409675858549, "epoch": 4.963680387409201, "percentage": 24.82, "elapsed_time": "0:13:39", "remaining_time": "0:41:22", "throughput": 2050.64, "total_tokens": 1680264}
{"current_steps": 4105, "total_steps": 16520, "loss": 0.0983, "lr": 0.0009343796036216701, "epoch": 4.969733656174334, "percentage": 24.85, "elapsed_time": "0:13:40", "remaining_time": "0:41:21", "throughput": 2050.78, "total_tokens": 1682376}
{"current_steps": 4110, "total_steps": 16520, "loss": 0.0981, "lr": 0.0009341177548112436, "epoch": 4.9757869249394675, "percentage": 24.88, "elapsed_time": "0:13:41", "remaining_time": "0:41:19", "throughput": 2050.85, "total_tokens": 1684424}
{"current_steps": 4115, "total_steps": 16520, "loss": 0.066, "lr": 0.000933855421446846, "epoch": 4.981840193704601, "percentage": 24.91, "elapsed_time": "0:13:42", "remaining_time": "0:41:18", "throughput": 2050.81, "total_tokens": 1686248}
{"current_steps": 4120, "total_steps": 16520, "loss": 0.112, "lr": 0.000933592603821289, "epoch": 4.987893462469733, "percentage": 24.94, "elapsed_time": "0:13:43", "remaining_time": "0:41:17", "throughput": 2050.91, "total_tokens": 1688328}
{"current_steps": 4125, "total_steps": 16520, "loss": 0.0492, "lr": 0.0009333293022279244, "epoch": 4.993946731234867, "percentage": 24.97, "elapsed_time": "0:13:44", "remaining_time": "0:41:16", "throughput": 2051.15, "total_tokens": 1690536}
{"current_steps": 4130, "total_steps": 16520, "loss": 0.1092, "lr": 0.0009330655169606446, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:13:45", "remaining_time": "0:41:15", "throughput": 2051.12, "total_tokens": 1692320}
{"current_steps": 4130, "total_steps": 16520, "eval_loss": 0.08863091468811035, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:13:53", "remaining_time": "0:41:39", "throughput": 2031.57, "total_tokens": 1692320}
{"current_steps": 4135, "total_steps": 16520, "loss": 0.0651, "lr": 0.0009328012483138816, "epoch": 5.006053268765133, "percentage": 25.03, "elapsed_time": "0:13:54", "remaining_time": "0:41:40", "throughput": 2029.37, "total_tokens": 1694304}
{"current_steps": 4140, "total_steps": 16520, "loss": 0.0423, "lr": 0.000932536496582607, "epoch": 5.012106537530267, "percentage": 25.06, "elapsed_time": "0:13:55", "remaining_time": "0:41:39", "throughput": 2029.42, "total_tokens": 1696192}
{"current_steps": 4145, "total_steps": 16520, "loss": 0.0802, "lr": 0.0009322712620623318, "epoch": 5.018159806295399, "percentage": 25.09, "elapsed_time": "0:13:56", "remaining_time": "0:41:38", "throughput": 2029.55, "total_tokens": 1698272}
{"current_steps": 4150, "total_steps": 16520, "loss": 0.0488, "lr": 0.0009320055450491056, "epoch": 5.0242130750605325, "percentage": 25.12, "elapsed_time": "0:13:57", "remaining_time": "0:41:37", "throughput": 2029.7, "total_tokens": 1700320}
{"current_steps": 4155, "total_steps": 16520, "loss": 0.0798, "lr": 0.0009317393458395166, "epoch": 5.030266343825666, "percentage": 25.15, "elapsed_time": "0:13:58", "remaining_time": "0:41:35", "throughput": 2029.79, "total_tokens": 1702240}
{"current_steps": 4160, "total_steps": 16520, "loss": 0.0771, "lr": 0.0009314726647306915, "epoch": 5.036319612590799, "percentage": 25.18, "elapsed_time": "0:13:59", "remaining_time": "0:41:34", "throughput": 2029.89, "total_tokens": 1704288}
{"current_steps": 4165, "total_steps": 16520, "loss": 0.0616, "lr": 0.0009312055020202945, "epoch": 5.0423728813559325, "percentage": 25.21, "elapsed_time": "0:14:00", "remaining_time": "0:41:33", "throughput": 2030.04, "total_tokens": 1706400}
{"current_steps": 4170, "total_steps": 16520, "loss": 0.1094, "lr": 0.0009309378580065277, "epoch": 5.048426150121065, "percentage": 25.24, "elapsed_time": "0:14:01", "remaining_time": "0:41:32", "throughput": 2030.2, "total_tokens": 1708448}
{"current_steps": 4175, "total_steps": 16520, "loss": 0.0196, "lr": 0.00093066973298813, "epoch": 5.054479418886198, "percentage": 25.27, "elapsed_time": "0:14:02", "remaining_time": "0:41:31", "throughput": 2030.35, "total_tokens": 1710560}
{"current_steps": 4180, "total_steps": 16520, "loss": 0.143, "lr": 0.0009304011272643775, "epoch": 5.060532687651332, "percentage": 25.3, "elapsed_time": "0:14:03", "remaining_time": "0:41:29", "throughput": 2030.64, "total_tokens": 1712704}
{"current_steps": 4185, "total_steps": 16520, "loss": 0.0788, "lr": 0.0009301320411350829, "epoch": 5.066585956416465, "percentage": 25.33, "elapsed_time": "0:14:04", "remaining_time": "0:41:28", "throughput": 2030.8, "total_tokens": 1714720}
{"current_steps": 4190, "total_steps": 16520, "loss": 0.1021, "lr": 0.0009298624749005951, "epoch": 5.072639225181598, "percentage": 25.36, "elapsed_time": "0:14:05", "remaining_time": "0:41:27", "throughput": 2031.0, "total_tokens": 1716896}
{"current_steps": 4195, "total_steps": 16520, "loss": 0.1489, "lr": 0.0009295924288617987, "epoch": 5.078692493946731, "percentage": 25.39, "elapsed_time": "0:14:06", "remaining_time": "0:41:26", "throughput": 2031.16, "total_tokens": 1718944}
{"current_steps": 4200, "total_steps": 16520, "loss": 0.0728, "lr": 0.0009293219033201138, "epoch": 5.084745762711864, "percentage": 25.42, "elapsed_time": "0:14:07", "remaining_time": "0:41:25", "throughput": 2031.24, "total_tokens": 1720928}
{"current_steps": 4205, "total_steps": 16520, "loss": 0.1314, "lr": 0.000929050898577496, "epoch": 5.0907990314769975, "percentage": 25.45, "elapsed_time": "0:14:08", "remaining_time": "0:41:23", "throughput": 2031.46, "total_tokens": 1722976}
{"current_steps": 4210, "total_steps": 16520, "loss": 0.0501, "lr": 0.0009287794149364357, "epoch": 5.096852300242131, "percentage": 25.48, "elapsed_time": "0:14:09", "remaining_time": "0:41:22", "throughput": 2031.58, "total_tokens": 1724992}
{"current_steps": 4215, "total_steps": 16520, "loss": 0.0295, "lr": 0.0009285074526999577, "epoch": 5.102905569007264, "percentage": 25.51, "elapsed_time": "0:14:10", "remaining_time": "0:41:21", "throughput": 2031.7, "total_tokens": 1727072}
{"current_steps": 4220, "total_steps": 16520, "loss": 0.0274, "lr": 0.0009282350121716208, "epoch": 5.108958837772397, "percentage": 25.54, "elapsed_time": "0:14:11", "remaining_time": "0:41:20", "throughput": 2031.93, "total_tokens": 1729280}
{"current_steps": 4225, "total_steps": 16520, "loss": 0.1358, "lr": 0.0009279620936555184, "epoch": 5.11501210653753, "percentage": 25.58, "elapsed_time": "0:14:12", "remaining_time": "0:41:19", "throughput": 2032.12, "total_tokens": 1731424}
{"current_steps": 4230, "total_steps": 16520, "loss": 0.0601, "lr": 0.0009276886974562768, "epoch": 5.121065375302663, "percentage": 25.61, "elapsed_time": "0:14:13", "remaining_time": "0:41:18", "throughput": 2032.3, "total_tokens": 1733568}
{"current_steps": 4235, "total_steps": 16520, "loss": 0.169, "lr": 0.0009274148238790554, "epoch": 5.127118644067797, "percentage": 25.64, "elapsed_time": "0:14:13", "remaining_time": "0:41:17", "throughput": 2032.45, "total_tokens": 1735616}
{"current_steps": 4240, "total_steps": 16520, "loss": 0.0964, "lr": 0.0009271404732295469, "epoch": 5.13317191283293, "percentage": 25.67, "elapsed_time": "0:14:14", "remaining_time": "0:41:16", "throughput": 2032.66, "total_tokens": 1737792}
{"current_steps": 4245, "total_steps": 16520, "loss": 0.091, "lr": 0.0009268656458139762, "epoch": 5.1392251815980625, "percentage": 25.7, "elapsed_time": "0:14:15", "remaining_time": "0:41:14", "throughput": 2032.76, "total_tokens": 1739840}
{"current_steps": 4250, "total_steps": 16520, "loss": 0.0972, "lr": 0.0009265903419391005, "epoch": 5.145278450363196, "percentage": 25.73, "elapsed_time": "0:14:16", "remaining_time": "0:41:13", "throughput": 2032.77, "total_tokens": 1741632}
{"current_steps": 4255, "total_steps": 16520, "loss": 0.1021, "lr": 0.0009263145619122086, "epoch": 5.151331719128329, "percentage": 25.76, "elapsed_time": "0:14:17", "remaining_time": "0:41:12", "throughput": 2032.87, "total_tokens": 1743680}
{"current_steps": 4260, "total_steps": 16520, "loss": 0.0354, "lr": 0.0009260383060411211, "epoch": 5.157384987893463, "percentage": 25.79, "elapsed_time": "0:14:18", "remaining_time": "0:41:11", "throughput": 2033.02, "total_tokens": 1745696}
{"current_steps": 4265, "total_steps": 16520, "loss": 0.0428, "lr": 0.0009257615746341894, "epoch": 5.163438256658596, "percentage": 25.82, "elapsed_time": "0:14:19", "remaining_time": "0:41:10", "throughput": 2033.08, "total_tokens": 1747712}
{"current_steps": 4270, "total_steps": 16520, "loss": 0.0949, "lr": 0.0009254843680002958, "epoch": 5.169491525423728, "percentage": 25.85, "elapsed_time": "0:14:20", "remaining_time": "0:41:08", "throughput": 2033.2, "total_tokens": 1749792}
{"current_steps": 4275, "total_steps": 16520, "loss": 0.0891, "lr": 0.0009252066864488531, "epoch": 5.175544794188862, "percentage": 25.88, "elapsed_time": "0:14:21", "remaining_time": "0:41:07", "throughput": 2033.22, "total_tokens": 1751776}
{"current_steps": 4280, "total_steps": 16520, "loss": 0.0632, "lr": 0.0009249285302898042, "epoch": 5.181598062953995, "percentage": 25.91, "elapsed_time": "0:14:22", "remaining_time": "0:41:06", "throughput": 2033.34, "total_tokens": 1753792}
{"current_steps": 4285, "total_steps": 16520, "loss": 0.0649, "lr": 0.0009246498998336218, "epoch": 5.187651331719128, "percentage": 25.94, "elapsed_time": "0:14:23", "remaining_time": "0:41:05", "throughput": 2033.47, "total_tokens": 1755840}
{"current_steps": 4290, "total_steps": 16520, "loss": 0.0846, "lr": 0.0009243707953913077, "epoch": 5.193704600484262, "percentage": 25.97, "elapsed_time": "0:14:24", "remaining_time": "0:41:04", "throughput": 2033.56, "total_tokens": 1757824}
{"current_steps": 4295, "total_steps": 16520, "loss": 0.0814, "lr": 0.0009240912172743932, "epoch": 5.199757869249395, "percentage": 26.0, "elapsed_time": "0:14:25", "remaining_time": "0:41:03", "throughput": 2033.65, "total_tokens": 1759808}
{"current_steps": 4300, "total_steps": 16520, "loss": 0.039, "lr": 0.0009238111657949378, "epoch": 5.2058111380145276, "percentage": 26.03, "elapsed_time": "0:14:26", "remaining_time": "0:41:01", "throughput": 2033.74, "total_tokens": 1761792}
{"current_steps": 4305, "total_steps": 16520, "loss": 0.1175, "lr": 0.0009235306412655298, "epoch": 5.211864406779661, "percentage": 26.06, "elapsed_time": "0:14:27", "remaining_time": "0:41:00", "throughput": 2033.84, "total_tokens": 1763808}
{"current_steps": 4310, "total_steps": 16520, "loss": 0.0682, "lr": 0.0009232496439992852, "epoch": 5.217917675544794, "percentage": 26.09, "elapsed_time": "0:14:28", "remaining_time": "0:40:59", "throughput": 2034.08, "total_tokens": 1765952}
{"current_steps": 4315, "total_steps": 16520, "loss": 0.0271, "lr": 0.0009229681743098482, "epoch": 5.223970944309928, "percentage": 26.12, "elapsed_time": "0:14:29", "remaining_time": "0:40:58", "throughput": 2034.2, "total_tokens": 1768032}
{"current_steps": 4320, "total_steps": 16520, "loss": 0.1173, "lr": 0.0009226862325113894, "epoch": 5.230024213075061, "percentage": 26.15, "elapsed_time": "0:14:30", "remaining_time": "0:40:57", "throughput": 2034.23, "total_tokens": 1770016}
{"current_steps": 4325, "total_steps": 16520, "loss": 0.0472, "lr": 0.000922403818918607, "epoch": 5.236077481840193, "percentage": 26.18, "elapsed_time": "0:14:31", "remaining_time": "0:40:56", "throughput": 2034.31, "total_tokens": 1772064}
{"current_steps": 4330, "total_steps": 16520, "loss": 0.048, "lr": 0.000922120933846726, "epoch": 5.242130750605327, "percentage": 26.21, "elapsed_time": "0:14:32", "remaining_time": "0:40:54", "throughput": 2034.37, "total_tokens": 1774016}
{"current_steps": 4335, "total_steps": 16520, "loss": 0.095, "lr": 0.0009218375776114969, "epoch": 5.24818401937046, "percentage": 26.24, "elapsed_time": "0:14:33", "remaining_time": "0:40:53", "throughput": 2034.65, "total_tokens": 1776256}
{"current_steps": 4340, "total_steps": 16520, "loss": 0.1396, "lr": 0.0009215537505291968, "epoch": 5.254237288135593, "percentage": 26.27, "elapsed_time": "0:14:33", "remaining_time": "0:40:52", "throughput": 2034.76, "total_tokens": 1778144}
{"current_steps": 4345, "total_steps": 16520, "loss": 0.1031, "lr": 0.0009212694529166279, "epoch": 5.260290556900727, "percentage": 26.3, "elapsed_time": "0:14:34", "remaining_time": "0:40:51", "throughput": 2034.84, "total_tokens": 1780000}
{"current_steps": 4350, "total_steps": 16520, "loss": 0.0367, "lr": 0.0009209846850911179, "epoch": 5.266343825665859, "percentage": 26.33, "elapsed_time": "0:14:35", "remaining_time": "0:40:50", "throughput": 2035.0, "total_tokens": 1782112}
{"current_steps": 4355, "total_steps": 16520, "loss": 0.0919, "lr": 0.0009206994473705193, "epoch": 5.272397094430993, "percentage": 26.36, "elapsed_time": "0:14:36", "remaining_time": "0:40:48", "throughput": 2035.18, "total_tokens": 1784256}
{"current_steps": 4360, "total_steps": 16520, "loss": 0.1053, "lr": 0.0009204137400732089, "epoch": 5.278450363196126, "percentage": 26.39, "elapsed_time": "0:14:37", "remaining_time": "0:40:47", "throughput": 2035.36, "total_tokens": 1786400}
{"current_steps": 4365, "total_steps": 16520, "loss": 0.0748, "lr": 0.0009201275635180877, "epoch": 5.284503631961259, "percentage": 26.42, "elapsed_time": "0:14:38", "remaining_time": "0:40:46", "throughput": 2035.5, "total_tokens": 1788448}
{"current_steps": 4370, "total_steps": 16520, "loss": 0.0497, "lr": 0.0009198409180245806, "epoch": 5.290556900726393, "percentage": 26.45, "elapsed_time": "0:14:39", "remaining_time": "0:40:45", "throughput": 2035.61, "total_tokens": 1790528}
{"current_steps": 4375, "total_steps": 16520, "loss": 0.0948, "lr": 0.0009195538039126358, "epoch": 5.296610169491525, "percentage": 26.48, "elapsed_time": "0:14:40", "remaining_time": "0:40:44", "throughput": 2035.82, "total_tokens": 1792640}
{"current_steps": 4380, "total_steps": 16520, "loss": 0.0733, "lr": 0.0009192662215027245, "epoch": 5.302663438256658, "percentage": 26.51, "elapsed_time": "0:14:41", "remaining_time": "0:40:43", "throughput": 2036.01, "total_tokens": 1794816}
{"current_steps": 4385, "total_steps": 16520, "loss": 0.1273, "lr": 0.0009189781711158411, "epoch": 5.308716707021792, "percentage": 26.54, "elapsed_time": "0:14:42", "remaining_time": "0:40:42", "throughput": 2036.19, "total_tokens": 1796960}
{"current_steps": 4390, "total_steps": 16520, "loss": 0.0652, "lr": 0.0009186896530735016, "epoch": 5.314769975786925, "percentage": 26.57, "elapsed_time": "0:14:43", "remaining_time": "0:40:40", "throughput": 2036.2, "total_tokens": 1798816}
{"current_steps": 4395, "total_steps": 16520, "loss": 0.0885, "lr": 0.0009184006676977443, "epoch": 5.3208232445520585, "percentage": 26.6, "elapsed_time": "0:14:44", "remaining_time": "0:40:39", "throughput": 2036.3, "total_tokens": 1800896}
{"current_steps": 4400, "total_steps": 16520, "loss": 0.0612, "lr": 0.0009181112153111295, "epoch": 5.326876513317191, "percentage": 26.63, "elapsed_time": "0:14:45", "remaining_time": "0:40:38", "throughput": 2036.58, "total_tokens": 1803168}
{"current_steps": 4405, "total_steps": 16520, "loss": 0.0731, "lr": 0.0009178212962367382, "epoch": 5.332929782082324, "percentage": 26.66, "elapsed_time": "0:14:46", "remaining_time": "0:40:37", "throughput": 2036.69, "total_tokens": 1805248}
{"current_steps": 4410, "total_steps": 16520, "loss": 0.0882, "lr": 0.0009175309107981726, "epoch": 5.338983050847458, "percentage": 26.69, "elapsed_time": "0:14:47", "remaining_time": "0:40:36", "throughput": 2036.81, "total_tokens": 1807328}
{"current_steps": 4415, "total_steps": 16520, "loss": 0.0672, "lr": 0.0009172400593195554, "epoch": 5.345036319612591, "percentage": 26.73, "elapsed_time": "0:14:48", "remaining_time": "0:40:35", "throughput": 2036.92, "total_tokens": 1809344}
{"current_steps": 4420, "total_steps": 16520, "loss": 0.0491, "lr": 0.0009169487421255294, "epoch": 5.351089588377724, "percentage": 26.76, "elapsed_time": "0:14:49", "remaining_time": "0:40:34", "throughput": 2037.18, "total_tokens": 1811616}
{"current_steps": 4425, "total_steps": 16520, "loss": 0.1436, "lr": 0.0009166569595412575, "epoch": 5.357142857142857, "percentage": 26.79, "elapsed_time": "0:14:50", "remaining_time": "0:40:33", "throughput": 2037.29, "total_tokens": 1813600}
{"current_steps": 4430, "total_steps": 16520, "loss": 0.1426, "lr": 0.0009163647118924217, "epoch": 5.36319612590799, "percentage": 26.82, "elapsed_time": "0:14:51", "remaining_time": "0:40:32", "throughput": 2037.35, "total_tokens": 1815616}
{"current_steps": 4435, "total_steps": 16520, "loss": 0.1337, "lr": 0.0009160719995052233, "epoch": 5.3692493946731235, "percentage": 26.85, "elapsed_time": "0:14:52", "remaining_time": "0:40:30", "throughput": 2037.52, "total_tokens": 1817696}
{"current_steps": 4440, "total_steps": 16520, "loss": 0.1094, "lr": 0.0009157788227063823, "epoch": 5.375302663438257, "percentage": 26.88, "elapsed_time": "0:14:53", "remaining_time": "0:40:29", "throughput": 2037.76, "total_tokens": 1819936}
{"current_steps": 4445, "total_steps": 16520, "loss": 0.1413, "lr": 0.0009154851818231371, "epoch": 5.38135593220339, "percentage": 26.91, "elapsed_time": "0:14:54", "remaining_time": "0:40:28", "throughput": 2037.89, "total_tokens": 1822048}
{"current_steps": 4450, "total_steps": 16520, "loss": 0.091, "lr": 0.000915191077183244, "epoch": 5.387409200968523, "percentage": 26.94, "elapsed_time": "0:14:55", "remaining_time": "0:40:27", "throughput": 2037.94, "total_tokens": 1824064}
{"current_steps": 4455, "total_steps": 16520, "loss": 0.0539, "lr": 0.0009148965091149771, "epoch": 5.393462469733656, "percentage": 26.97, "elapsed_time": "0:14:55", "remaining_time": "0:40:26", "throughput": 2038.11, "total_tokens": 1826144}
{"current_steps": 4460, "total_steps": 16520, "loss": 0.0704, "lr": 0.0009146014779471274, "epoch": 5.399515738498789, "percentage": 27.0, "elapsed_time": "0:14:56", "remaining_time": "0:40:25", "throughput": 2038.25, "total_tokens": 1828192}
{"current_steps": 4465, "total_steps": 16520, "loss": 0.0731, "lr": 0.0009143059840090035, "epoch": 5.405569007263923, "percentage": 27.03, "elapsed_time": "0:14:57", "remaining_time": "0:40:24", "throughput": 2038.45, "total_tokens": 1830368}
{"current_steps": 4470, "total_steps": 16520, "loss": 0.0885, "lr": 0.0009140100276304298, "epoch": 5.411622276029056, "percentage": 27.06, "elapsed_time": "0:14:58", "remaining_time": "0:40:23", "throughput": 2038.59, "total_tokens": 1832416}
{"current_steps": 4475, "total_steps": 16520, "loss": 0.1437, "lr": 0.000913713609141747, "epoch": 5.4176755447941884, "percentage": 27.09, "elapsed_time": "0:14:59", "remaining_time": "0:40:21", "throughput": 2038.79, "total_tokens": 1834528}
{"current_steps": 4480, "total_steps": 16520, "loss": 0.1431, "lr": 0.0009134167288738123, "epoch": 5.423728813559322, "percentage": 27.12, "elapsed_time": "0:15:00", "remaining_time": "0:40:20", "throughput": 2038.87, "total_tokens": 1836576}
{"current_steps": 4485, "total_steps": 16520, "loss": 0.0903, "lr": 0.0009131193871579975, "epoch": 5.429782082324455, "percentage": 27.15, "elapsed_time": "0:15:01", "remaining_time": "0:40:19", "throughput": 2039.01, "total_tokens": 1838688}
{"current_steps": 4490, "total_steps": 16520, "loss": 0.0626, "lr": 0.0009128215843261897, "epoch": 5.4358353510895885, "percentage": 27.18, "elapsed_time": "0:15:02", "remaining_time": "0:40:18", "throughput": 2039.09, "total_tokens": 1840736}
{"current_steps": 4495, "total_steps": 16520, "loss": 0.1325, "lr": 0.0009125233207107908, "epoch": 5.441888619854722, "percentage": 27.21, "elapsed_time": "0:15:03", "remaining_time": "0:40:17", "throughput": 2039.26, "total_tokens": 1842880}
{"current_steps": 4500, "total_steps": 16520, "loss": 0.0712, "lr": 0.000912224596644717, "epoch": 5.447941888619855, "percentage": 27.24, "elapsed_time": "0:15:04", "remaining_time": "0:40:16", "throughput": 2039.46, "total_tokens": 1844992}
{"current_steps": 4505, "total_steps": 16520, "loss": 0.0903, "lr": 0.0009119254124613984, "epoch": 5.453995157384988, "percentage": 27.27, "elapsed_time": "0:15:05", "remaining_time": "0:40:15", "throughput": 2039.59, "total_tokens": 1847040}
{"current_steps": 4510, "total_steps": 16520, "loss": 0.0821, "lr": 0.0009116257684947789, "epoch": 5.460048426150121, "percentage": 27.3, "elapsed_time": "0:15:06", "remaining_time": "0:40:14", "throughput": 2039.8, "total_tokens": 1849248}
{"current_steps": 4515, "total_steps": 16520, "loss": 0.0844, "lr": 0.0009113256650793149, "epoch": 5.466101694915254, "percentage": 27.33, "elapsed_time": "0:15:07", "remaining_time": "0:40:13", "throughput": 2039.85, "total_tokens": 1851200}
{"current_steps": 4520, "total_steps": 16520, "loss": 0.0856, "lr": 0.0009110251025499766, "epoch": 5.472154963680388, "percentage": 27.36, "elapsed_time": "0:15:08", "remaining_time": "0:40:11", "throughput": 2039.92, "total_tokens": 1853184}
{"current_steps": 4525, "total_steps": 16520, "loss": 0.0142, "lr": 0.0009107240812422459, "epoch": 5.478208232445521, "percentage": 27.39, "elapsed_time": "0:15:09", "remaining_time": "0:40:10", "throughput": 2040.18, "total_tokens": 1855424}
{"current_steps": 4530, "total_steps": 16520, "loss": 0.0326, "lr": 0.0009104226014921171, "epoch": 5.4842615012106535, "percentage": 27.42, "elapsed_time": "0:15:10", "remaining_time": "0:40:09", "throughput": 2040.31, "total_tokens": 1857408}
{"current_steps": 4535, "total_steps": 16520, "loss": 0.049, "lr": 0.0009101206636360962, "epoch": 5.490314769975787, "percentage": 27.45, "elapsed_time": "0:15:11", "remaining_time": "0:40:08", "throughput": 2040.42, "total_tokens": 1859488}
{"current_steps": 4540, "total_steps": 16520, "loss": 0.0375, "lr": 0.0009098182680112006, "epoch": 5.49636803874092, "percentage": 27.48, "elapsed_time": "0:15:12", "remaining_time": "0:40:07", "throughput": 2040.5, "total_tokens": 1861472}
{"current_steps": 4545, "total_steps": 16520, "loss": 0.1416, "lr": 0.0009095154149549583, "epoch": 5.5024213075060535, "percentage": 27.51, "elapsed_time": "0:15:13", "remaining_time": "0:40:06", "throughput": 2040.52, "total_tokens": 1863456}
{"current_steps": 4550, "total_steps": 16520, "loss": 0.0972, "lr": 0.0009092121048054081, "epoch": 5.508474576271187, "percentage": 27.54, "elapsed_time": "0:15:14", "remaining_time": "0:40:05", "throughput": 2040.69, "total_tokens": 1865568}
{"current_steps": 4555, "total_steps": 16520, "loss": 0.0577, "lr": 0.0009089083379010994, "epoch": 5.514527845036319, "percentage": 27.57, "elapsed_time": "0:15:15", "remaining_time": "0:40:03", "throughput": 2040.77, "total_tokens": 1867616}
{"current_steps": 4560, "total_steps": 16520, "loss": 0.1049, "lr": 0.0009086041145810906, "epoch": 5.520581113801453, "percentage": 27.6, "elapsed_time": "0:15:16", "remaining_time": "0:40:02", "throughput": 2040.81, "total_tokens": 1869568}
{"current_steps": 4565, "total_steps": 16520, "loss": 0.161, "lr": 0.00090829943518495, "epoch": 5.526634382566586, "percentage": 27.63, "elapsed_time": "0:15:17", "remaining_time": "0:40:01", "throughput": 2040.95, "total_tokens": 1871552}
{"current_steps": 4570, "total_steps": 16520, "loss": 0.0827, "lr": 0.0009079943000527553, "epoch": 5.532687651331719, "percentage": 27.66, "elapsed_time": "0:15:17", "remaining_time": "0:40:00", "throughput": 2041.08, "total_tokens": 1873664}
{"current_steps": 4575, "total_steps": 16520, "loss": 0.1136, "lr": 0.0009076887095250924, "epoch": 5.538740920096853, "percentage": 27.69, "elapsed_time": "0:15:18", "remaining_time": "0:39:59", "throughput": 2041.19, "total_tokens": 1875680}
{"current_steps": 4580, "total_steps": 16520, "loss": 0.0721, "lr": 0.0009073826639430554, "epoch": 5.544794188861985, "percentage": 27.72, "elapsed_time": "0:15:19", "remaining_time": "0:39:58", "throughput": 2041.32, "total_tokens": 1877728}
{"current_steps": 4585, "total_steps": 16520, "loss": 0.0598, "lr": 0.0009070761636482465, "epoch": 5.5508474576271185, "percentage": 27.75, "elapsed_time": "0:15:20", "remaining_time": "0:39:56", "throughput": 2041.37, "total_tokens": 1879744}
{"current_steps": 4590, "total_steps": 16520, "loss": 0.0896, "lr": 0.0009067692089827759, "epoch": 5.556900726392252, "percentage": 27.78, "elapsed_time": "0:15:21", "remaining_time": "0:39:55", "throughput": 2041.45, "total_tokens": 1881728}
{"current_steps": 4595, "total_steps": 16520, "loss": 0.0407, "lr": 0.0009064618002892604, "epoch": 5.562953995157385, "percentage": 27.81, "elapsed_time": "0:15:22", "remaining_time": "0:39:54", "throughput": 2041.61, "total_tokens": 1883904}
{"current_steps": 4600, "total_steps": 16520, "loss": 0.0614, "lr": 0.0009061539379108235, "epoch": 5.5690072639225185, "percentage": 27.85, "elapsed_time": "0:15:23", "remaining_time": "0:39:53", "throughput": 2041.75, "total_tokens": 1886016}
{"current_steps": 4605, "total_steps": 16520, "loss": 0.0616, "lr": 0.0009058456221910956, "epoch": 5.575060532687651, "percentage": 27.88, "elapsed_time": "0:15:24", "remaining_time": "0:39:52", "throughput": 2041.79, "total_tokens": 1888032}
{"current_steps": 4610, "total_steps": 16520, "loss": 0.0743, "lr": 0.0009055368534742125, "epoch": 5.581113801452784, "percentage": 27.91, "elapsed_time": "0:15:25", "remaining_time": "0:39:51", "throughput": 2041.87, "total_tokens": 1890080}
{"current_steps": 4615, "total_steps": 16520, "loss": 0.0317, "lr": 0.0009052276321048165, "epoch": 5.587167070217918, "percentage": 27.94, "elapsed_time": "0:15:26", "remaining_time": "0:39:50", "throughput": 2041.86, "total_tokens": 1892032}
{"current_steps": 4620, "total_steps": 16520, "loss": 0.1353, "lr": 0.000904917958428054, "epoch": 5.593220338983051, "percentage": 27.97, "elapsed_time": "0:15:27", "remaining_time": "0:39:49", "throughput": 2042.01, "total_tokens": 1894176}
{"current_steps": 4625, "total_steps": 16520, "loss": 0.0773, "lr": 0.0009046078327895774, "epoch": 5.599273607748184, "percentage": 28.0, "elapsed_time": "0:15:28", "remaining_time": "0:39:48", "throughput": 2042.05, "total_tokens": 1896192}
{"current_steps": 4630, "total_steps": 16520, "loss": 0.125, "lr": 0.0009042972555355427, "epoch": 5.605326876513317, "percentage": 28.03, "elapsed_time": "0:15:29", "remaining_time": "0:39:47", "throughput": 2042.09, "total_tokens": 1898208}
{"current_steps": 4635, "total_steps": 16520, "loss": 0.069, "lr": 0.0009039862270126103, "epoch": 5.61138014527845, "percentage": 28.06, "elapsed_time": "0:15:30", "remaining_time": "0:39:46", "throughput": 2042.23, "total_tokens": 1900320}
{"current_steps": 4640, "total_steps": 16520, "loss": 0.0903, "lr": 0.0009036747475679444, "epoch": 5.6174334140435835, "percentage": 28.09, "elapsed_time": "0:15:31", "remaining_time": "0:39:45", "throughput": 2042.23, "total_tokens": 1902464}
{"current_steps": 4645, "total_steps": 16520, "loss": 0.1104, "lr": 0.0009033628175492126, "epoch": 5.623486682808717, "percentage": 28.12, "elapsed_time": "0:15:32", "remaining_time": "0:39:44", "throughput": 2042.24, "total_tokens": 1904448}
{"current_steps": 4650, "total_steps": 16520, "loss": 0.1279, "lr": 0.0009030504373045849, "epoch": 5.62953995157385, "percentage": 28.15, "elapsed_time": "0:15:33", "remaining_time": "0:39:42", "throughput": 2042.32, "total_tokens": 1906432}
{"current_steps": 4655, "total_steps": 16520, "loss": 0.0616, "lr": 0.0009027376071827345, "epoch": 5.635593220338983, "percentage": 28.18, "elapsed_time": "0:15:34", "remaining_time": "0:39:41", "throughput": 2042.37, "total_tokens": 1908384}
{"current_steps": 4660, "total_steps": 16520, "loss": 0.0631, "lr": 0.0009024243275328361, "epoch": 5.641646489104116, "percentage": 28.21, "elapsed_time": "0:15:35", "remaining_time": "0:39:40", "throughput": 2042.5, "total_tokens": 1910464}
{"current_steps": 4665, "total_steps": 16520, "loss": 0.1261, "lr": 0.0009021105987045668, "epoch": 5.647699757869249, "percentage": 28.24, "elapsed_time": "0:15:36", "remaining_time": "0:39:39", "throughput": 2042.63, "total_tokens": 1912512}
{"current_steps": 4670, "total_steps": 16520, "loss": 0.0677, "lr": 0.0009017964210481046, "epoch": 5.653753026634383, "percentage": 28.27, "elapsed_time": "0:15:37", "remaining_time": "0:39:38", "throughput": 2042.65, "total_tokens": 1914432}
{"current_steps": 4675, "total_steps": 16520, "loss": 0.0753, "lr": 0.0009014817949141286, "epoch": 5.659806295399516, "percentage": 28.3, "elapsed_time": "0:15:38", "remaining_time": "0:39:37", "throughput": 2042.74, "total_tokens": 1916448}
{"current_steps": 4680, "total_steps": 16520, "loss": 0.0626, "lr": 0.0009011667206538185, "epoch": 5.6658595641646485, "percentage": 28.33, "elapsed_time": "0:15:39", "remaining_time": "0:39:35", "throughput": 2042.75, "total_tokens": 1918368}
{"current_steps": 4685, "total_steps": 16520, "loss": 0.0905, "lr": 0.0009008511986188544, "epoch": 5.671912832929782, "percentage": 28.36, "elapsed_time": "0:15:40", "remaining_time": "0:39:34", "throughput": 2042.97, "total_tokens": 1920576}
{"current_steps": 4690, "total_steps": 16520, "loss": 0.0941, "lr": 0.0009005352291614157, "epoch": 5.677966101694915, "percentage": 28.39, "elapsed_time": "0:15:41", "remaining_time": "0:39:33", "throughput": 2043.09, "total_tokens": 1922624}
{"current_steps": 4695, "total_steps": 16520, "loss": 0.0358, "lr": 0.0009002188126341815, "epoch": 5.684019370460049, "percentage": 28.42, "elapsed_time": "0:15:41", "remaining_time": "0:39:32", "throughput": 2043.19, "total_tokens": 1924640}
{"current_steps": 4700, "total_steps": 16520, "loss": 0.0323, "lr": 0.0008999019493903301, "epoch": 5.690072639225182, "percentage": 28.45, "elapsed_time": "0:15:42", "remaining_time": "0:39:31", "throughput": 2043.29, "total_tokens": 1926720}
{"current_steps": 4705, "total_steps": 16520, "loss": 0.0618, "lr": 0.0008995846397835381, "epoch": 5.696125907990314, "percentage": 28.48, "elapsed_time": "0:15:43", "remaining_time": "0:39:30", "throughput": 2043.34, "total_tokens": 1928736}
{"current_steps": 4710, "total_steps": 16520, "loss": 0.1373, "lr": 0.0008992668841679804, "epoch": 5.702179176755448, "percentage": 28.51, "elapsed_time": "0:15:44", "remaining_time": "0:39:29", "throughput": 2043.55, "total_tokens": 1930880}
{"current_steps": 4715, "total_steps": 16520, "loss": 0.0828, "lr": 0.0008989486828983299, "epoch": 5.708232445520581, "percentage": 28.54, "elapsed_time": "0:15:45", "remaining_time": "0:39:28", "throughput": 2043.68, "total_tokens": 1932928}
{"current_steps": 4720, "total_steps": 16520, "loss": 0.0731, "lr": 0.0008986300363297566, "epoch": 5.714285714285714, "percentage": 28.57, "elapsed_time": "0:15:46", "remaining_time": "0:39:26", "throughput": 2043.77, "total_tokens": 1934944}
{"current_steps": 4725, "total_steps": 16520, "loss": 0.0914, "lr": 0.000898310944817928, "epoch": 5.720338983050848, "percentage": 28.6, "elapsed_time": "0:15:47", "remaining_time": "0:39:25", "throughput": 2043.93, "total_tokens": 1936992}
{"current_steps": 4730, "total_steps": 16520, "loss": 0.0649, "lr": 0.0008979914087190078, "epoch": 5.72639225181598, "percentage": 28.63, "elapsed_time": "0:15:48", "remaining_time": "0:39:24", "throughput": 2044.06, "total_tokens": 1938976}
{"current_steps": 4735, "total_steps": 16520, "loss": 0.11, "lr": 0.0008976714283896561, "epoch": 5.732445520581114, "percentage": 28.66, "elapsed_time": "0:15:49", "remaining_time": "0:39:23", "throughput": 2044.18, "total_tokens": 1941024}
{"current_steps": 4740, "total_steps": 16520, "loss": 0.1787, "lr": 0.0008973510041870288, "epoch": 5.738498789346247, "percentage": 28.69, "elapsed_time": "0:15:50", "remaining_time": "0:39:22", "throughput": 2044.25, "total_tokens": 1943008}
{"current_steps": 4745, "total_steps": 16520, "loss": 0.0769, "lr": 0.0008970301364687774, "epoch": 5.74455205811138, "percentage": 28.72, "elapsed_time": "0:15:51", "remaining_time": "0:39:21", "throughput": 2044.3, "total_tokens": 1945024}
{"current_steps": 4750, "total_steps": 16520, "loss": 0.0724, "lr": 0.0008967088255930484, "epoch": 5.750605326876514, "percentage": 28.75, "elapsed_time": "0:15:52", "remaining_time": "0:39:19", "throughput": 2044.45, "total_tokens": 1947104}
{"current_steps": 4755, "total_steps": 16520, "loss": 0.0887, "lr": 0.0008963870719184828, "epoch": 5.756658595641646, "percentage": 28.78, "elapsed_time": "0:15:53", "remaining_time": "0:39:18", "throughput": 2044.5, "total_tokens": 1949120}
{"current_steps": 4760, "total_steps": 16520, "loss": 0.0623, "lr": 0.0008960648758042158, "epoch": 5.762711864406779, "percentage": 28.81, "elapsed_time": "0:15:54", "remaining_time": "0:39:17", "throughput": 2044.6, "total_tokens": 1951136}
{"current_steps": 4765, "total_steps": 16520, "loss": 0.0772, "lr": 0.0008957422376098767, "epoch": 5.768765133171913, "percentage": 28.84, "elapsed_time": "0:15:55", "remaining_time": "0:39:16", "throughput": 2044.75, "total_tokens": 1953280}
{"current_steps": 4770, "total_steps": 16520, "loss": 0.0795, "lr": 0.0008954191576955881, "epoch": 5.774818401937046, "percentage": 28.87, "elapsed_time": "0:15:56", "remaining_time": "0:39:15", "throughput": 2044.83, "total_tokens": 1955328}
{"current_steps": 4775, "total_steps": 16520, "loss": 0.0918, "lr": 0.0008950956364219657, "epoch": 5.780871670702179, "percentage": 28.9, "elapsed_time": "0:15:57", "remaining_time": "0:39:14", "throughput": 2044.92, "total_tokens": 1957408}
{"current_steps": 4780, "total_steps": 16520, "loss": 0.1592, "lr": 0.0008947716741501177, "epoch": 5.786924939467312, "percentage": 28.93, "elapsed_time": "0:15:58", "remaining_time": "0:39:13", "throughput": 2045.04, "total_tokens": 1959392}
{"current_steps": 4785, "total_steps": 16520, "loss": 0.0627, "lr": 0.0008944472712416447, "epoch": 5.792978208232445, "percentage": 28.96, "elapsed_time": "0:15:59", "remaining_time": "0:39:12", "throughput": 2045.17, "total_tokens": 1961504}
{"current_steps": 4790, "total_steps": 16520, "loss": 0.1395, "lr": 0.0008941224280586389, "epoch": 5.799031476997579, "percentage": 29.0, "elapsed_time": "0:16:00", "remaining_time": "0:39:10", "throughput": 2045.23, "total_tokens": 1963488}
{"current_steps": 4795, "total_steps": 16520, "loss": 0.0894, "lr": 0.0008937971449636842, "epoch": 5.805084745762712, "percentage": 29.03, "elapsed_time": "0:16:00", "remaining_time": "0:39:09", "throughput": 2045.4, "total_tokens": 1965600}
{"current_steps": 4800, "total_steps": 16520, "loss": 0.0867, "lr": 0.0008934714223198554, "epoch": 5.811138014527845, "percentage": 29.06, "elapsed_time": "0:16:01", "remaining_time": "0:39:08", "throughput": 2045.5, "total_tokens": 1967680}
{"current_steps": 4805, "total_steps": 16520, "loss": 0.0251, "lr": 0.0008931452604907178, "epoch": 5.817191283292978, "percentage": 29.09, "elapsed_time": "0:16:02", "remaining_time": "0:39:07", "throughput": 2045.62, "total_tokens": 1969728}
{"current_steps": 4810, "total_steps": 16520, "loss": 0.0815, "lr": 0.0008928186598403272, "epoch": 5.823244552058111, "percentage": 29.12, "elapsed_time": "0:16:03", "remaining_time": "0:39:06", "throughput": 2045.72, "total_tokens": 1971680}
{"current_steps": 4815, "total_steps": 16520, "loss": 0.1801, "lr": 0.0008924916207332287, "epoch": 5.829297820823244, "percentage": 29.15, "elapsed_time": "0:16:04", "remaining_time": "0:39:05", "throughput": 2045.73, "total_tokens": 1973600}
{"current_steps": 4820, "total_steps": 16520, "loss": 0.115, "lr": 0.0008921641435344576, "epoch": 5.835351089588378, "percentage": 29.18, "elapsed_time": "0:16:05", "remaining_time": "0:39:04", "throughput": 2045.74, "total_tokens": 1975584}
{"current_steps": 4825, "total_steps": 16520, "loss": 0.0623, "lr": 0.0008918362286095374, "epoch": 5.841404358353511, "percentage": 29.21, "elapsed_time": "0:16:06", "remaining_time": "0:39:03", "throughput": 2045.81, "total_tokens": 1977632}
{"current_steps": 4830, "total_steps": 16520, "loss": 0.0606, "lr": 0.0008915078763244804, "epoch": 5.847457627118644, "percentage": 29.24, "elapsed_time": "0:16:07", "remaining_time": "0:39:01", "throughput": 2045.88, "total_tokens": 1979616}
{"current_steps": 4835, "total_steps": 16520, "loss": 0.0752, "lr": 0.0008911790870457874, "epoch": 5.853510895883777, "percentage": 29.27, "elapsed_time": "0:16:08", "remaining_time": "0:39:00", "throughput": 2045.97, "total_tokens": 1981632}
{"current_steps": 4840, "total_steps": 16520, "loss": 0.0969, "lr": 0.0008908498611404468, "epoch": 5.85956416464891, "percentage": 29.3, "elapsed_time": "0:16:09", "remaining_time": "0:38:59", "throughput": 2046.1, "total_tokens": 1983712}
{"current_steps": 4845, "total_steps": 16520, "loss": 0.0324, "lr": 0.000890520198975934, "epoch": 5.865617433414044, "percentage": 29.33, "elapsed_time": "0:16:10", "remaining_time": "0:38:58", "throughput": 2046.14, "total_tokens": 1985728}
{"current_steps": 4850, "total_steps": 16520, "loss": 0.1031, "lr": 0.0008901901009202118, "epoch": 5.871670702179177, "percentage": 29.36, "elapsed_time": "0:16:11", "remaining_time": "0:38:57", "throughput": 2046.27, "total_tokens": 1987840}
{"current_steps": 4855, "total_steps": 16520, "loss": 0.0884, "lr": 0.0008898595673417294, "epoch": 5.877723970944309, "percentage": 29.39, "elapsed_time": "0:16:12", "remaining_time": "0:38:56", "throughput": 2046.33, "total_tokens": 1989760}
{"current_steps": 4860, "total_steps": 16520, "loss": 0.0631, "lr": 0.0008895285986094219, "epoch": 5.883777239709443, "percentage": 29.42, "elapsed_time": "0:16:13", "remaining_time": "0:38:55", "throughput": 2046.34, "total_tokens": 1991744}
{"current_steps": 4865, "total_steps": 16520, "loss": 0.0434, "lr": 0.0008891971950927104, "epoch": 5.889830508474576, "percentage": 29.45, "elapsed_time": "0:16:14", "remaining_time": "0:38:54", "throughput": 2046.33, "total_tokens": 1993696}
{"current_steps": 4870, "total_steps": 16520, "loss": 0.0995, "lr": 0.0008888653571615014, "epoch": 5.8958837772397095, "percentage": 29.48, "elapsed_time": "0:16:15", "remaining_time": "0:38:52", "throughput": 2046.45, "total_tokens": 1995808}
{"current_steps": 4875, "total_steps": 16520, "loss": 0.17, "lr": 0.0008885330851861858, "epoch": 5.901937046004843, "percentage": 29.51, "elapsed_time": "0:16:16", "remaining_time": "0:38:51", "throughput": 2046.59, "total_tokens": 1997952}
{"current_steps": 4880, "total_steps": 16520, "loss": 0.0677, "lr": 0.0008882003795376393, "epoch": 5.907990314769976, "percentage": 29.54, "elapsed_time": "0:16:17", "remaining_time": "0:38:50", "throughput": 2046.71, "total_tokens": 2000064}
{"current_steps": 4885, "total_steps": 16520, "loss": 0.0141, "lr": 0.0008878672405872217, "epoch": 5.914043583535109, "percentage": 29.57, "elapsed_time": "0:16:18", "remaining_time": "0:38:49", "throughput": 2046.86, "total_tokens": 2002208}
{"current_steps": 4890, "total_steps": 16520, "loss": 0.0768, "lr": 0.0008875336687067763, "epoch": 5.920096852300242, "percentage": 29.6, "elapsed_time": "0:16:19", "remaining_time": "0:38:48", "throughput": 2046.93, "total_tokens": 2004256}
{"current_steps": 4895, "total_steps": 16520, "loss": 0.0583, "lr": 0.0008871996642686298, "epoch": 5.926150121065375, "percentage": 29.63, "elapsed_time": "0:16:20", "remaining_time": "0:38:47", "throughput": 2046.97, "total_tokens": 2006208}
{"current_steps": 4900, "total_steps": 16520, "loss": 0.0854, "lr": 0.0008868652276455913, "epoch": 5.932203389830509, "percentage": 29.66, "elapsed_time": "0:16:21", "remaining_time": "0:38:46", "throughput": 2047.09, "total_tokens": 2008256}
{"current_steps": 4905, "total_steps": 16520, "loss": 0.1328, "lr": 0.0008865303592109528, "epoch": 5.938256658595642, "percentage": 29.69, "elapsed_time": "0:16:22", "remaining_time": "0:38:45", "throughput": 2047.26, "total_tokens": 2010432}
{"current_steps": 4910, "total_steps": 16520, "loss": 0.1135, "lr": 0.000886195059338488, "epoch": 5.9443099273607745, "percentage": 29.72, "elapsed_time": "0:16:22", "remaining_time": "0:38:44", "throughput": 2047.44, "total_tokens": 2012608}
{"current_steps": 4915, "total_steps": 16520, "loss": 0.0356, "lr": 0.0008858593284024523, "epoch": 5.950363196125908, "percentage": 29.75, "elapsed_time": "0:16:23", "remaining_time": "0:38:43", "throughput": 2047.53, "total_tokens": 2014624}
{"current_steps": 4920, "total_steps": 16520, "loss": 0.1127, "lr": 0.0008855231667775822, "epoch": 5.956416464891041, "percentage": 29.78, "elapsed_time": "0:16:24", "remaining_time": "0:38:42", "throughput": 2047.57, "total_tokens": 2016640}
{"current_steps": 4925, "total_steps": 16520, "loss": 0.0719, "lr": 0.0008851865748390948, "epoch": 5.9624697336561745, "percentage": 29.81, "elapsed_time": "0:16:25", "remaining_time": "0:38:41", "throughput": 2047.63, "total_tokens": 2018688}
{"current_steps": 4930, "total_steps": 16520, "loss": 0.1254, "lr": 0.0008848495529626877, "epoch": 5.968523002421308, "percentage": 29.84, "elapsed_time": "0:16:26", "remaining_time": "0:38:39", "throughput": 2047.74, "total_tokens": 2020608}
{"current_steps": 4935, "total_steps": 16520, "loss": 0.0752, "lr": 0.0008845121015245383, "epoch": 5.97457627118644, "percentage": 29.87, "elapsed_time": "0:16:27", "remaining_time": "0:38:38", "throughput": 2047.83, "total_tokens": 2022688}
{"current_steps": 4940, "total_steps": 16520, "loss": 0.0513, "lr": 0.0008841742209013035, "epoch": 5.980629539951574, "percentage": 29.9, "elapsed_time": "0:16:28", "remaining_time": "0:38:37", "throughput": 2047.89, "total_tokens": 2024608}
{"current_steps": 4945, "total_steps": 16520, "loss": 0.0646, "lr": 0.0008838359114701189, "epoch": 5.986682808716707, "percentage": 29.93, "elapsed_time": "0:16:29", "remaining_time": "0:38:36", "throughput": 2047.93, "total_tokens": 2026560}
{"current_steps": 4950, "total_steps": 16520, "loss": 0.089, "lr": 0.0008834971736085995, "epoch": 5.99273607748184, "percentage": 29.96, "elapsed_time": "0:16:30", "remaining_time": "0:38:35", "throughput": 2047.98, "total_tokens": 2028416}
{"current_steps": 4955, "total_steps": 16520, "loss": 0.0769, "lr": 0.0008831580076948378, "epoch": 5.998789346246974, "percentage": 29.99, "elapsed_time": "0:16:31", "remaining_time": "0:38:33", "throughput": 2048.07, "total_tokens": 2030400}
{"current_steps": 4956, "total_steps": 16520, "eval_loss": 0.09009363502264023, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:16:39", "remaining_time": "0:38:52", "throughput": 2031.6, "total_tokens": 2030488}
{"current_steps": 4960, "total_steps": 16520, "loss": 0.0679, "lr": 0.0008828184141074043, "epoch": 6.004842615012106, "percentage": 30.02, "elapsed_time": "0:16:41", "remaining_time": "0:38:53", "throughput": 2029.7, "total_tokens": 2032184}
{"current_steps": 4965, "total_steps": 16520, "loss": 0.0566, "lr": 0.000882478393225347, "epoch": 6.0108958837772395, "percentage": 30.05, "elapsed_time": "0:16:42", "remaining_time": "0:38:52", "throughput": 2029.69, "total_tokens": 2034104}
{"current_steps": 4970, "total_steps": 16520, "loss": 0.0725, "lr": 0.0008821379454281909, "epoch": 6.016949152542373, "percentage": 30.08, "elapsed_time": "0:16:43", "remaining_time": "0:38:51", "throughput": 2029.88, "total_tokens": 2036280}
{"current_steps": 4975, "total_steps": 16520, "loss": 0.1478, "lr": 0.000881797071095937, "epoch": 6.023002421307506, "percentage": 30.12, "elapsed_time": "0:16:44", "remaining_time": "0:38:50", "throughput": 2030.01, "total_tokens": 2038328}
{"current_steps": 4980, "total_steps": 16520, "loss": 0.0383, "lr": 0.000881455770609063, "epoch": 6.0290556900726395, "percentage": 30.15, "elapsed_time": "0:16:45", "remaining_time": "0:38:48", "throughput": 2030.12, "total_tokens": 2040376}
{"current_steps": 4985, "total_steps": 16520, "loss": 0.1154, "lr": 0.0008811140443485217, "epoch": 6.035108958837772, "percentage": 30.18, "elapsed_time": "0:16:45", "remaining_time": "0:38:47", "throughput": 2030.15, "total_tokens": 2042264}
{"current_steps": 4990, "total_steps": 16520, "loss": 0.0417, "lr": 0.0008807718926957418, "epoch": 6.041162227602905, "percentage": 30.21, "elapsed_time": "0:16:46", "remaining_time": "0:38:46", "throughput": 2030.31, "total_tokens": 2044376}
{"current_steps": 4995, "total_steps": 16520, "loss": 0.0701, "lr": 0.0008804293160326262, "epoch": 6.047215496368039, "percentage": 30.24, "elapsed_time": "0:16:47", "remaining_time": "0:38:45", "throughput": 2030.41, "total_tokens": 2046328}
{"current_steps": 5000, "total_steps": 16520, "loss": 0.0236, "lr": 0.0008800863147415528, "epoch": 6.053268765133172, "percentage": 30.27, "elapsed_time": "0:16:48", "remaining_time": "0:38:44", "throughput": 2030.45, "total_tokens": 2048280}
{"current_steps": 5005, "total_steps": 16520, "loss": 0.1158, "lr": 0.0008797428892053725, "epoch": 6.059322033898305, "percentage": 30.3, "elapsed_time": "0:16:49", "remaining_time": "0:38:43", "throughput": 2030.61, "total_tokens": 2050360}
{"current_steps": 5010, "total_steps": 16520, "loss": 0.078, "lr": 0.000879399039807411, "epoch": 6.065375302663438, "percentage": 30.33, "elapsed_time": "0:16:50", "remaining_time": "0:38:42", "throughput": 2030.79, "total_tokens": 2052536}
{"current_steps": 5015, "total_steps": 16520, "loss": 0.0456, "lr": 0.0008790547669314659, "epoch": 6.071428571428571, "percentage": 30.36, "elapsed_time": "0:16:51", "remaining_time": "0:38:40", "throughput": 2030.91, "total_tokens": 2054648}
{"current_steps": 5020, "total_steps": 16520, "loss": 0.0743, "lr": 0.0008787100709618086, "epoch": 6.0774818401937045, "percentage": 30.39, "elapsed_time": "0:16:52", "remaining_time": "0:38:39", "throughput": 2031.12, "total_tokens": 2056856}
{"current_steps": 5025, "total_steps": 16520, "loss": 0.0783, "lr": 0.0008783649522831815, "epoch": 6.083535108958838, "percentage": 30.42, "elapsed_time": "0:16:53", "remaining_time": "0:38:38", "throughput": 2031.17, "total_tokens": 2058872}
{"current_steps": 5030, "total_steps": 16520, "loss": 0.0655, "lr": 0.0008780194112808002, "epoch": 6.089588377723971, "percentage": 30.45, "elapsed_time": "0:16:54", "remaining_time": "0:38:37", "throughput": 2031.27, "total_tokens": 2060888}
{"current_steps": 5035, "total_steps": 16520, "loss": 0.0869, "lr": 0.0008776734483403505, "epoch": 6.095641646489105, "percentage": 30.48, "elapsed_time": "0:16:55", "remaining_time": "0:38:36", "throughput": 2031.34, "total_tokens": 2062936}
{"current_steps": 5040, "total_steps": 16520, "loss": 0.049, "lr": 0.0008773270638479897, "epoch": 6.101694915254237, "percentage": 30.51, "elapsed_time": "0:16:56", "remaining_time": "0:38:35", "throughput": 2031.42, "total_tokens": 2064920}
{"current_steps": 5045, "total_steps": 16520, "loss": 0.083, "lr": 0.0008769802581903458, "epoch": 6.10774818401937, "percentage": 30.54, "elapsed_time": "0:16:57", "remaining_time": "0:38:34", "throughput": 2031.55, "total_tokens": 2067000}
{"current_steps": 5050, "total_steps": 16520, "loss": 0.0289, "lr": 0.0008766330317545164, "epoch": 6.113801452784504, "percentage": 30.57, "elapsed_time": "0:16:58", "remaining_time": "0:38:33", "throughput": 2031.66, "total_tokens": 2069048}
{"current_steps": 5055, "total_steps": 16520, "loss": 0.0829, "lr": 0.0008762853849280692, "epoch": 6.119854721549637, "percentage": 30.6, "elapsed_time": "0:16:59", "remaining_time": "0:38:31", "throughput": 2031.76, "total_tokens": 2071128}
{"current_steps": 5060, "total_steps": 16520, "loss": 0.0859, "lr": 0.0008759373180990411, "epoch": 6.12590799031477, "percentage": 30.63, "elapsed_time": "0:17:00", "remaining_time": "0:38:30", "throughput": 2031.83, "total_tokens": 2073176}
{"current_steps": 5065, "total_steps": 16520, "loss": 0.1116, "lr": 0.0008755888316559373, "epoch": 6.131961259079903, "percentage": 30.66, "elapsed_time": "0:17:01", "remaining_time": "0:38:29", "throughput": 2031.9, "total_tokens": 2075160}
{"current_steps": 5070, "total_steps": 16520, "loss": 0.1135, "lr": 0.000875239925987732, "epoch": 6.138014527845036, "percentage": 30.69, "elapsed_time": "0:17:02", "remaining_time": "0:38:28", "throughput": 2032.0, "total_tokens": 2077240}
{"current_steps": 5075, "total_steps": 16520, "loss": 0.0753, "lr": 0.0008748906014838671, "epoch": 6.1440677966101696, "percentage": 30.72, "elapsed_time": "0:17:03", "remaining_time": "0:38:27", "throughput": 2032.13, "total_tokens": 2079352}
{"current_steps": 5080, "total_steps": 16520, "loss": 0.0567, "lr": 0.0008745408585342518, "epoch": 6.150121065375303, "percentage": 30.75, "elapsed_time": "0:17:04", "remaining_time": "0:38:26", "throughput": 2032.17, "total_tokens": 2081304}
{"current_steps": 5085, "total_steps": 16520, "loss": 0.0828, "lr": 0.0008741906975292626, "epoch": 6.156174334140436, "percentage": 30.78, "elapsed_time": "0:17:05", "remaining_time": "0:38:25", "throughput": 2032.24, "total_tokens": 2083224}
{"current_steps": 5090, "total_steps": 16520, "loss": 0.124, "lr": 0.0008738401188597424, "epoch": 6.162227602905569, "percentage": 30.81, "elapsed_time": "0:17:06", "remaining_time": "0:38:24", "throughput": 2032.49, "total_tokens": 2085464}
{"current_steps": 5095, "total_steps": 16520, "loss": 0.0322, "lr": 0.0008734891229170007, "epoch": 6.168280871670702, "percentage": 30.84, "elapsed_time": "0:17:07", "remaining_time": "0:38:23", "throughput": 2032.64, "total_tokens": 2087608}
{"current_steps": 5100, "total_steps": 16520, "loss": 0.108, "lr": 0.0008731377100928123, "epoch": 6.174334140435835, "percentage": 30.87, "elapsed_time": "0:17:07", "remaining_time": "0:38:21", "throughput": 2032.7, "total_tokens": 2089592}
{"current_steps": 5105, "total_steps": 16520, "loss": 0.1506, "lr": 0.0008727858807794176, "epoch": 6.180387409200969, "percentage": 30.9, "elapsed_time": "0:17:08", "remaining_time": "0:38:20", "throughput": 2032.86, "total_tokens": 2091768}
{"current_steps": 5110, "total_steps": 16520, "loss": 0.0423, "lr": 0.0008724336353695216, "epoch": 6.186440677966102, "percentage": 30.93, "elapsed_time": "0:17:09", "remaining_time": "0:38:19", "throughput": 2032.96, "total_tokens": 2093784}
{"current_steps": 5115, "total_steps": 16520, "loss": 0.0945, "lr": 0.000872080974256294, "epoch": 6.1924939467312345, "percentage": 30.96, "elapsed_time": "0:17:10", "remaining_time": "0:38:18", "throughput": 2033.05, "total_tokens": 2095864}
{"current_steps": 5120, "total_steps": 16520, "loss": 0.0458, "lr": 0.0008717278978333687, "epoch": 6.198547215496368, "percentage": 30.99, "elapsed_time": "0:17:11", "remaining_time": "0:38:17", "throughput": 2033.18, "total_tokens": 2097976}
{"current_steps": 5125, "total_steps": 16520, "loss": 0.03, "lr": 0.0008713744064948425, "epoch": 6.204600484261501, "percentage": 31.02, "elapsed_time": "0:17:12", "remaining_time": "0:38:16", "throughput": 2033.36, "total_tokens": 2100088}
{"current_steps": 5130, "total_steps": 16520, "loss": 0.0304, "lr": 0.0008710205006352759, "epoch": 6.210653753026635, "percentage": 31.05, "elapsed_time": "0:17:13", "remaining_time": "0:38:15", "throughput": 2033.48, "total_tokens": 2102136}
{"current_steps": 5135, "total_steps": 16520, "loss": 0.0717, "lr": 0.0008706661806496918, "epoch": 6.216707021791768, "percentage": 31.08, "elapsed_time": "0:17:14", "remaining_time": "0:38:14", "throughput": 2033.61, "total_tokens": 2104184}
{"current_steps": 5140, "total_steps": 16520, "loss": 0.0805, "lr": 0.0008703114469335755, "epoch": 6.2227602905569, "percentage": 31.11, "elapsed_time": "0:17:15", "remaining_time": "0:38:12", "throughput": 2033.74, "total_tokens": 2106232}
{"current_steps": 5145, "total_steps": 16520, "loss": 0.0676, "lr": 0.0008699562998828738, "epoch": 6.228813559322034, "percentage": 31.14, "elapsed_time": "0:17:16", "remaining_time": "0:38:11", "throughput": 2033.81, "total_tokens": 2108152}
{"current_steps": 5150, "total_steps": 16520, "loss": 0.0731, "lr": 0.0008696007398939954, "epoch": 6.234866828087167, "percentage": 31.17, "elapsed_time": "0:17:17", "remaining_time": "0:38:10", "throughput": 2033.93, "total_tokens": 2110264}
{"current_steps": 5155, "total_steps": 16520, "loss": 0.076, "lr": 0.0008692447673638094, "epoch": 6.2409200968523, "percentage": 31.2, "elapsed_time": "0:17:18", "remaining_time": "0:38:09", "throughput": 2033.98, "total_tokens": 2112280}
{"current_steps": 5160, "total_steps": 16520, "loss": 0.0408, "lr": 0.0008688883826896457, "epoch": 6.246973365617434, "percentage": 31.23, "elapsed_time": "0:17:19", "remaining_time": "0:38:08", "throughput": 2034.09, "total_tokens": 2114392}
{"current_steps": 5165, "total_steps": 16520, "loss": 0.087, "lr": 0.0008685315862692937, "epoch": 6.253026634382566, "percentage": 31.27, "elapsed_time": "0:17:20", "remaining_time": "0:38:07", "throughput": 2034.24, "total_tokens": 2116472}
{"current_steps": 5170, "total_steps": 16520, "loss": 0.042, "lr": 0.0008681743785010032, "epoch": 6.2590799031477, "percentage": 31.3, "elapsed_time": "0:17:21", "remaining_time": "0:38:06", "throughput": 2034.37, "total_tokens": 2118584}
{"current_steps": 5175, "total_steps": 16520, "loss": 0.0414, "lr": 0.0008678167597834825, "epoch": 6.265133171912833, "percentage": 31.33, "elapsed_time": "0:17:22", "remaining_time": "0:38:05", "throughput": 2034.47, "total_tokens": 2120664}
{"current_steps": 5180, "total_steps": 16520, "loss": 0.1453, "lr": 0.000867458730515899, "epoch": 6.271186440677966, "percentage": 31.36, "elapsed_time": "0:17:23", "remaining_time": "0:38:04", "throughput": 2034.52, "total_tokens": 2122680}
{"current_steps": 5185, "total_steps": 16520, "loss": 0.0587, "lr": 0.0008671002910978778, "epoch": 6.2772397094431, "percentage": 31.39, "elapsed_time": "0:17:24", "remaining_time": "0:38:02", "throughput": 2034.61, "total_tokens": 2124696}
{"current_steps": 5190, "total_steps": 16520, "loss": 0.0341, "lr": 0.0008667414419295025, "epoch": 6.283292978208232, "percentage": 31.42, "elapsed_time": "0:17:25", "remaining_time": "0:38:01", "throughput": 2034.76, "total_tokens": 2126776}
{"current_steps": 5195, "total_steps": 16520, "loss": 0.0808, "lr": 0.0008663821834113135, "epoch": 6.289346246973365, "percentage": 31.45, "elapsed_time": "0:17:26", "remaining_time": "0:38:00", "throughput": 2034.92, "total_tokens": 2128952}
{"current_steps": 5200, "total_steps": 16520, "loss": 0.0663, "lr": 0.0008660225159443085, "epoch": 6.295399515738499, "percentage": 31.48, "elapsed_time": "0:17:27", "remaining_time": "0:37:59", "throughput": 2034.99, "total_tokens": 2130936}
{"current_steps": 5205, "total_steps": 16520, "loss": 0.0789, "lr": 0.0008656624399299413, "epoch": 6.301452784503632, "percentage": 31.51, "elapsed_time": "0:17:28", "remaining_time": "0:37:58", "throughput": 2035.05, "total_tokens": 2132920}
{"current_steps": 5210, "total_steps": 16520, "loss": 0.1255, "lr": 0.000865301955770122, "epoch": 6.3075060532687655, "percentage": 31.54, "elapsed_time": "0:17:29", "remaining_time": "0:37:57", "throughput": 2035.24, "total_tokens": 2135064}
{"current_steps": 5215, "total_steps": 16520, "loss": 0.1238, "lr": 0.0008649410638672159, "epoch": 6.313559322033898, "percentage": 31.57, "elapsed_time": "0:17:29", "remaining_time": "0:37:56", "throughput": 2035.32, "total_tokens": 2137080}
{"current_steps": 5220, "total_steps": 16520, "loss": 0.0573, "lr": 0.0008645797646240441, "epoch": 6.319612590799031, "percentage": 31.6, "elapsed_time": "0:17:30", "remaining_time": "0:37:55", "throughput": 2035.36, "total_tokens": 2139032}
{"current_steps": 5225, "total_steps": 16520, "loss": 0.0904, "lr": 0.0008642180584438817, "epoch": 6.325665859564165, "percentage": 31.63, "elapsed_time": "0:17:31", "remaining_time": "0:37:53", "throughput": 2035.49, "total_tokens": 2141144}
{"current_steps": 5230, "total_steps": 16520, "loss": 0.0475, "lr": 0.0008638559457304582, "epoch": 6.331719128329298, "percentage": 31.66, "elapsed_time": "0:17:32", "remaining_time": "0:37:52", "throughput": 2035.64, "total_tokens": 2143320}
{"current_steps": 5235, "total_steps": 16520, "loss": 0.0317, "lr": 0.000863493426887957, "epoch": 6.337772397094431, "percentage": 31.69, "elapsed_time": "0:17:33", "remaining_time": "0:37:51", "throughput": 2035.8, "total_tokens": 2145496}
{"current_steps": 5240, "total_steps": 16520, "loss": 0.0427, "lr": 0.0008631305023210147, "epoch": 6.343825665859564, "percentage": 31.72, "elapsed_time": "0:17:34", "remaining_time": "0:37:50", "throughput": 2035.87, "total_tokens": 2147544}
{"current_steps": 5245, "total_steps": 16520, "loss": 0.06, "lr": 0.0008627671724347207, "epoch": 6.349878934624697, "percentage": 31.75, "elapsed_time": "0:17:35", "remaining_time": "0:37:49", "throughput": 2035.91, "total_tokens": 2149560}
{"current_steps": 5250, "total_steps": 16520, "loss": 0.0518, "lr": 0.000862403437634617, "epoch": 6.3559322033898304, "percentage": 31.78, "elapsed_time": "0:17:36", "remaining_time": "0:37:48", "throughput": 2036.06, "total_tokens": 2151704}
{"current_steps": 5255, "total_steps": 16520, "loss": 0.1109, "lr": 0.0008620392983266975, "epoch": 6.361985472154964, "percentage": 31.81, "elapsed_time": "0:17:37", "remaining_time": "0:37:47", "throughput": 2036.21, "total_tokens": 2153784}
{"current_steps": 5260, "total_steps": 16520, "loss": 0.0945, "lr": 0.0008616747549174077, "epoch": 6.368038740920097, "percentage": 31.84, "elapsed_time": "0:17:38", "remaining_time": "0:37:46", "throughput": 2036.28, "total_tokens": 2155832}
{"current_steps": 5265, "total_steps": 16520, "loss": 0.0299, "lr": 0.0008613098078136437, "epoch": 6.37409200968523, "percentage": 31.87, "elapsed_time": "0:17:39", "remaining_time": "0:37:45", "throughput": 2036.32, "total_tokens": 2157848}
{"current_steps": 5270, "total_steps": 16520, "loss": 0.1032, "lr": 0.0008609444574227526, "epoch": 6.380145278450363, "percentage": 31.9, "elapsed_time": "0:17:40", "remaining_time": "0:37:44", "throughput": 2036.37, "total_tokens": 2159736}
{"current_steps": 5275, "total_steps": 16520, "loss": 0.0552, "lr": 0.0008605787041525315, "epoch": 6.386198547215496, "percentage": 31.93, "elapsed_time": "0:17:41", "remaining_time": "0:37:42", "throughput": 2036.41, "total_tokens": 2161624}
{"current_steps": 5280, "total_steps": 16520, "loss": 0.0886, "lr": 0.0008602125484112274, "epoch": 6.39225181598063, "percentage": 31.96, "elapsed_time": "0:17:42", "remaining_time": "0:37:41", "throughput": 2036.5, "total_tokens": 2163640}
{"current_steps": 5285, "total_steps": 16520, "loss": 0.1191, "lr": 0.0008598459906075362, "epoch": 6.398305084745763, "percentage": 31.99, "elapsed_time": "0:17:43", "remaining_time": "0:37:40", "throughput": 2036.53, "total_tokens": 2165592}
{"current_steps": 5290, "total_steps": 16520, "loss": 0.0538, "lr": 0.000859479031150603, "epoch": 6.404358353510895, "percentage": 32.02, "elapsed_time": "0:17:44", "remaining_time": "0:37:39", "throughput": 2036.62, "total_tokens": 2167608}
{"current_steps": 5295, "total_steps": 16520, "loss": 0.0836, "lr": 0.0008591116704500207, "epoch": 6.410411622276029, "percentage": 32.05, "elapsed_time": "0:17:45", "remaining_time": "0:37:38", "throughput": 2036.67, "total_tokens": 2169496}
{"current_steps": 5300, "total_steps": 16520, "loss": 0.0722, "lr": 0.0008587439089158304, "epoch": 6.416464891041162, "percentage": 32.08, "elapsed_time": "0:17:46", "remaining_time": "0:37:37", "throughput": 2036.81, "total_tokens": 2171640}
{"current_steps": 5305, "total_steps": 16520, "loss": 0.0496, "lr": 0.0008583757469585205, "epoch": 6.4225181598062955, "percentage": 32.11, "elapsed_time": "0:17:47", "remaining_time": "0:37:36", "throughput": 2036.88, "total_tokens": 2173688}
{"current_steps": 5310, "total_steps": 16520, "loss": 0.0524, "lr": 0.0008580071849890264, "epoch": 6.428571428571429, "percentage": 32.14, "elapsed_time": "0:17:48", "remaining_time": "0:37:34", "throughput": 2036.93, "total_tokens": 2175704}
{"current_steps": 5315, "total_steps": 16520, "loss": 0.0637, "lr": 0.0008576382234187299, "epoch": 6.434624697336561, "percentage": 32.17, "elapsed_time": "0:17:49", "remaining_time": "0:37:33", "throughput": 2037.0, "total_tokens": 2177752}
{"current_steps": 5320, "total_steps": 16520, "loss": 0.1104, "lr": 0.0008572688626594591, "epoch": 6.440677966101695, "percentage": 32.2, "elapsed_time": "0:17:50", "remaining_time": "0:37:32", "throughput": 2037.04, "total_tokens": 2179768}
{"current_steps": 5325, "total_steps": 16520, "loss": 0.1086, "lr": 0.0008568991031234869, "epoch": 6.446731234866828, "percentage": 32.23, "elapsed_time": "0:17:51", "remaining_time": "0:37:31", "throughput": 2037.26, "total_tokens": 2182008}
{"current_steps": 5330, "total_steps": 16520, "loss": 0.0433, "lr": 0.0008565289452235325, "epoch": 6.452784503631961, "percentage": 32.26, "elapsed_time": "0:17:52", "remaining_time": "0:37:30", "throughput": 2037.39, "total_tokens": 2184120}
{"current_steps": 5335, "total_steps": 16520, "loss": 0.1054, "lr": 0.0008561583893727588, "epoch": 6.458837772397095, "percentage": 32.29, "elapsed_time": "0:17:53", "remaining_time": "0:37:29", "throughput": 2037.51, "total_tokens": 2186264}
{"current_steps": 5340, "total_steps": 16520, "loss": 0.0908, "lr": 0.0008557874359847732, "epoch": 6.464891041162228, "percentage": 32.32, "elapsed_time": "0:17:53", "remaining_time": "0:37:28", "throughput": 2037.63, "total_tokens": 2188312}
{"current_steps": 5345, "total_steps": 16520, "loss": 0.1028, "lr": 0.0008554160854736268, "epoch": 6.4709443099273605, "percentage": 32.35, "elapsed_time": "0:17:54", "remaining_time": "0:37:27", "throughput": 2037.65, "total_tokens": 2190232}
{"current_steps": 5350, "total_steps": 16520, "loss": 0.0661, "lr": 0.0008550443382538139, "epoch": 6.476997578692494, "percentage": 32.38, "elapsed_time": "0:17:55", "remaining_time": "0:37:26", "throughput": 2037.69, "total_tokens": 2192248}
{"current_steps": 5355, "total_steps": 16520, "loss": 0.0754, "lr": 0.0008546721947402718, "epoch": 6.483050847457627, "percentage": 32.42, "elapsed_time": "0:17:56", "remaining_time": "0:37:25", "throughput": 2037.86, "total_tokens": 2194392}
{"current_steps": 5360, "total_steps": 16520, "loss": 0.081, "lr": 0.0008542996553483799, "epoch": 6.4891041162227605, "percentage": 32.45, "elapsed_time": "0:17:57", "remaining_time": "0:37:23", "throughput": 2038.03, "total_tokens": 2196504}
{"current_steps": 5365, "total_steps": 16520, "loss": 0.0623, "lr": 0.0008539267204939596, "epoch": 6.495157384987894, "percentage": 32.48, "elapsed_time": "0:17:58", "remaining_time": "0:37:22", "throughput": 2038.19, "total_tokens": 2198488}
{"current_steps": 5370, "total_steps": 16520, "loss": 0.0341, "lr": 0.0008535533905932737, "epoch": 6.501210653753026, "percentage": 32.51, "elapsed_time": "0:17:59", "remaining_time": "0:37:21", "throughput": 2038.31, "total_tokens": 2200536}
{"current_steps": 5375, "total_steps": 16520, "loss": 0.1343, "lr": 0.0008531796660630262, "epoch": 6.50726392251816, "percentage": 32.54, "elapsed_time": "0:18:00", "remaining_time": "0:37:20", "throughput": 2038.48, "total_tokens": 2202712}
{"current_steps": 5380, "total_steps": 16520, "loss": 0.1257, "lr": 0.0008528055473203607, "epoch": 6.513317191283293, "percentage": 32.57, "elapsed_time": "0:18:01", "remaining_time": "0:37:19", "throughput": 2038.54, "total_tokens": 2204760}
{"current_steps": 5385, "total_steps": 16520, "loss": 0.0533, "lr": 0.0008524310347828619, "epoch": 6.519370460048426, "percentage": 32.6, "elapsed_time": "0:18:02", "remaining_time": "0:37:18", "throughput": 2038.68, "total_tokens": 2206904}
{"current_steps": 5390, "total_steps": 16520, "loss": 0.0571, "lr": 0.0008520561288685533, "epoch": 6.52542372881356, "percentage": 32.63, "elapsed_time": "0:18:03", "remaining_time": "0:37:17", "throughput": 2038.82, "total_tokens": 2208984}
{"current_steps": 5395, "total_steps": 16520, "loss": 0.1208, "lr": 0.000851680829995898, "epoch": 6.531476997578692, "percentage": 32.66, "elapsed_time": "0:18:04", "remaining_time": "0:37:16", "throughput": 2038.96, "total_tokens": 2211128}
{"current_steps": 5400, "total_steps": 16520, "loss": 0.0262, "lr": 0.0008513051385837971, "epoch": 6.5375302663438255, "percentage": 32.69, "elapsed_time": "0:18:05", "remaining_time": "0:37:15", "throughput": 2039.0, "total_tokens": 2213144}
{"current_steps": 5405, "total_steps": 16520, "loss": 0.0584, "lr": 0.0008509290550515907, "epoch": 6.543583535108959, "percentage": 32.72, "elapsed_time": "0:18:06", "remaining_time": "0:37:14", "throughput": 2039.04, "total_tokens": 2215160}
{"current_steps": 5410, "total_steps": 16520, "loss": 0.0494, "lr": 0.0008505525798190557, "epoch": 6.549636803874092, "percentage": 32.75, "elapsed_time": "0:18:07", "remaining_time": "0:37:12", "throughput": 2039.11, "total_tokens": 2217144}
{"current_steps": 5415, "total_steps": 16520, "loss": 0.1015, "lr": 0.0008501757133064066, "epoch": 6.5556900726392255, "percentage": 32.78, "elapsed_time": "0:18:08", "remaining_time": "0:37:11", "throughput": 2039.32, "total_tokens": 2219320}
{"current_steps": 5420, "total_steps": 16520, "loss": 0.0564, "lr": 0.0008497984559342946, "epoch": 6.561743341404358, "percentage": 32.81, "elapsed_time": "0:18:09", "remaining_time": "0:37:10", "throughput": 2039.34, "total_tokens": 2221240}
{"current_steps": 5425, "total_steps": 16520, "loss": 0.11, "lr": 0.0008494208081238074, "epoch": 6.567796610169491, "percentage": 32.84, "elapsed_time": "0:18:10", "remaining_time": "0:37:09", "throughput": 2039.46, "total_tokens": 2223384}
{"current_steps": 5430, "total_steps": 16520, "loss": 0.0314, "lr": 0.0008490427702964683, "epoch": 6.573849878934625, "percentage": 32.87, "elapsed_time": "0:18:11", "remaining_time": "0:37:08", "throughput": 2039.55, "total_tokens": 2225336}
{"current_steps": 5435, "total_steps": 16520, "loss": 0.0829, "lr": 0.0008486643428742356, "epoch": 6.579903147699758, "percentage": 32.9, "elapsed_time": "0:18:12", "remaining_time": "0:37:07", "throughput": 2039.61, "total_tokens": 2227384}
{"current_steps": 5440, "total_steps": 16520, "loss": 0.0413, "lr": 0.0008482855262795031, "epoch": 6.585956416464891, "percentage": 32.93, "elapsed_time": "0:18:12", "remaining_time": "0:37:06", "throughput": 2039.67, "total_tokens": 2229304}
{"current_steps": 5445, "total_steps": 16520, "loss": 0.024, "lr": 0.0008479063209350985, "epoch": 6.592009685230024, "percentage": 32.96, "elapsed_time": "0:18:13", "remaining_time": "0:37:05", "throughput": 2039.81, "total_tokens": 2231448}
{"current_steps": 5450, "total_steps": 16520, "loss": 0.1241, "lr": 0.0008475267272642837, "epoch": 6.598062953995157, "percentage": 32.99, "elapsed_time": "0:18:14", "remaining_time": "0:37:03", "throughput": 2039.93, "total_tokens": 2233560}
{"current_steps": 5455, "total_steps": 16520, "loss": 0.0286, "lr": 0.000847146745690754, "epoch": 6.6041162227602905, "percentage": 33.02, "elapsed_time": "0:18:15", "remaining_time": "0:37:02", "throughput": 2039.99, "total_tokens": 2235544}
{"current_steps": 5460, "total_steps": 16520, "loss": 0.0367, "lr": 0.0008467663766386372, "epoch": 6.610169491525424, "percentage": 33.05, "elapsed_time": "0:18:16", "remaining_time": "0:37:01", "throughput": 2040.13, "total_tokens": 2237624}
{"current_steps": 5465, "total_steps": 16520, "loss": 0.0977, "lr": 0.0008463856205324945, "epoch": 6.616222760290557, "percentage": 33.08, "elapsed_time": "0:18:17", "remaining_time": "0:37:00", "throughput": 2040.32, "total_tokens": 2239864}
{"current_steps": 5470, "total_steps": 16520, "loss": 0.0459, "lr": 0.0008460044777973181, "epoch": 6.622276029055691, "percentage": 33.11, "elapsed_time": "0:18:18", "remaining_time": "0:36:59", "throughput": 2040.34, "total_tokens": 2241848}
{"current_steps": 5475, "total_steps": 16520, "loss": 0.0973, "lr": 0.0008456229488585327, "epoch": 6.628329297820823, "percentage": 33.14, "elapsed_time": "0:18:19", "remaining_time": "0:36:58", "throughput": 2040.45, "total_tokens": 2243896}
{"current_steps": 5480, "total_steps": 16520, "loss": 0.0461, "lr": 0.0008452410341419935, "epoch": 6.634382566585956, "percentage": 33.17, "elapsed_time": "0:18:20", "remaining_time": "0:36:57", "throughput": 2040.56, "total_tokens": 2246008}
{"current_steps": 5485, "total_steps": 16520, "loss": 0.1058, "lr": 0.0008448587340739864, "epoch": 6.64043583535109, "percentage": 33.2, "elapsed_time": "0:18:21", "remaining_time": "0:36:56", "throughput": 2040.7, "total_tokens": 2248184}
{"current_steps": 5490, "total_steps": 16520, "loss": 0.1146, "lr": 0.0008444760490812275, "epoch": 6.646489104116223, "percentage": 33.23, "elapsed_time": "0:18:22", "remaining_time": "0:36:55", "throughput": 2040.72, "total_tokens": 2250168}
{"current_steps": 5495, "total_steps": 16520, "loss": 0.0514, "lr": 0.0008440929795908625, "epoch": 6.652542372881356, "percentage": 33.26, "elapsed_time": "0:18:23", "remaining_time": "0:36:54", "throughput": 2040.78, "total_tokens": 2252152}
{"current_steps": 5500, "total_steps": 16520, "loss": 0.0707, "lr": 0.0008437095260304661, "epoch": 6.658595641646489, "percentage": 33.29, "elapsed_time": "0:18:24", "remaining_time": "0:36:53", "throughput": 2040.82, "total_tokens": 2254168}
{"current_steps": 5505, "total_steps": 16520, "loss": 0.056, "lr": 0.000843325688828042, "epoch": 6.664648910411622, "percentage": 33.32, "elapsed_time": "0:18:25", "remaining_time": "0:36:51", "throughput": 2040.84, "total_tokens": 2256088}
{"current_steps": 5510, "total_steps": 16520, "loss": 0.1446, "lr": 0.000842941468412022, "epoch": 6.670702179176756, "percentage": 33.35, "elapsed_time": "0:18:26", "remaining_time": "0:36:50", "throughput": 2040.89, "total_tokens": 2258008}
{"current_steps": 5515, "total_steps": 16520, "loss": 0.1133, "lr": 0.0008425568652112658, "epoch": 6.676755447941889, "percentage": 33.38, "elapsed_time": "0:18:27", "remaining_time": "0:36:49", "throughput": 2041.04, "total_tokens": 2260184}
{"current_steps": 5520, "total_steps": 16520, "loss": 0.0812, "lr": 0.0008421718796550597, "epoch": 6.682808716707022, "percentage": 33.41, "elapsed_time": "0:18:28", "remaining_time": "0:36:48", "throughput": 2041.12, "total_tokens": 2262200}
{"current_steps": 5525, "total_steps": 16520, "loss": 0.0268, "lr": 0.0008417865121731176, "epoch": 6.688861985472155, "percentage": 33.44, "elapsed_time": "0:18:29", "remaining_time": "0:36:47", "throughput": 2041.24, "total_tokens": 2264248}
{"current_steps": 5530, "total_steps": 16520, "loss": 0.1088, "lr": 0.0008414007631955791, "epoch": 6.694915254237288, "percentage": 33.47, "elapsed_time": "0:18:30", "remaining_time": "0:36:46", "throughput": 2041.39, "total_tokens": 2266424}
{"current_steps": 5535, "total_steps": 16520, "loss": 0.0837, "lr": 0.0008410146331530102, "epoch": 6.700968523002421, "percentage": 33.5, "elapsed_time": "0:18:31", "remaining_time": "0:36:45", "throughput": 2041.55, "total_tokens": 2268536}
{"current_steps": 5540, "total_steps": 16520, "loss": 0.1123, "lr": 0.0008406281224764016, "epoch": 6.707021791767555, "percentage": 33.54, "elapsed_time": "0:18:32", "remaining_time": "0:36:44", "throughput": 2041.71, "total_tokens": 2270712}
{"current_steps": 5545, "total_steps": 16520, "loss": 0.0494, "lr": 0.0008402412315971692, "epoch": 6.713075060532688, "percentage": 33.57, "elapsed_time": "0:18:33", "remaining_time": "0:36:43", "throughput": 2041.74, "total_tokens": 2272600}
{"current_steps": 5550, "total_steps": 16520, "loss": 0.0546, "lr": 0.0008398539609471534, "epoch": 6.719128329297821, "percentage": 33.6, "elapsed_time": "0:18:34", "remaining_time": "0:36:41", "throughput": 2041.81, "total_tokens": 2274584}
{"current_steps": 5555, "total_steps": 16520, "loss": 0.0881, "lr": 0.0008394663109586183, "epoch": 6.725181598062954, "percentage": 33.63, "elapsed_time": "0:18:34", "remaining_time": "0:36:40", "throughput": 2041.87, "total_tokens": 2276568}
{"current_steps": 5560, "total_steps": 16520, "loss": 0.101, "lr": 0.0008390782820642513, "epoch": 6.731234866828087, "percentage": 33.66, "elapsed_time": "0:18:35", "remaining_time": "0:36:39", "throughput": 2041.9, "total_tokens": 2278584}
{"current_steps": 5565, "total_steps": 16520, "loss": 0.0518, "lr": 0.000838689874697163, "epoch": 6.737288135593221, "percentage": 33.69, "elapsed_time": "0:18:36", "remaining_time": "0:36:38", "throughput": 2041.95, "total_tokens": 2280632}
{"current_steps": 5570, "total_steps": 16520, "loss": 0.1202, "lr": 0.0008383010892908862, "epoch": 6.743341404358354, "percentage": 33.72, "elapsed_time": "0:18:37", "remaining_time": "0:36:37", "throughput": 2041.98, "total_tokens": 2282648}
{"current_steps": 5575, "total_steps": 16520, "loss": 0.0741, "lr": 0.0008379119262793757, "epoch": 6.749394673123486, "percentage": 33.75, "elapsed_time": "0:18:38", "remaining_time": "0:36:36", "throughput": 2042.04, "total_tokens": 2284632}
{"current_steps": 5580, "total_steps": 16520, "loss": 0.1466, "lr": 0.0008375223860970078, "epoch": 6.75544794188862, "percentage": 33.78, "elapsed_time": "0:18:39", "remaining_time": "0:36:35", "throughput": 2042.08, "total_tokens": 2286584}
{"current_steps": 5585, "total_steps": 16520, "loss": 0.0577, "lr": 0.0008371324691785802, "epoch": 6.761501210653753, "percentage": 33.81, "elapsed_time": "0:18:40", "remaining_time": "0:36:34", "throughput": 2042.21, "total_tokens": 2288728}
{"current_steps": 5590, "total_steps": 16520, "loss": 0.0721, "lr": 0.0008367421759593105, "epoch": 6.767554479418886, "percentage": 33.84, "elapsed_time": "0:18:41", "remaining_time": "0:36:33", "throughput": 2042.29, "total_tokens": 2290744}
{"current_steps": 5595, "total_steps": 16520, "loss": 0.0891, "lr": 0.0008363515068748364, "epoch": 6.77360774818402, "percentage": 33.87, "elapsed_time": "0:18:42", "remaining_time": "0:36:31", "throughput": 2042.37, "total_tokens": 2292696}
{"current_steps": 5600, "total_steps": 16520, "loss": 0.0295, "lr": 0.0008359604623612156, "epoch": 6.779661016949152, "percentage": 33.9, "elapsed_time": "0:18:43", "remaining_time": "0:36:30", "throughput": 2042.4, "total_tokens": 2294520}
{"current_steps": 5605, "total_steps": 16520, "loss": 0.0713, "lr": 0.0008355690428549245, "epoch": 6.785714285714286, "percentage": 33.93, "elapsed_time": "0:18:44", "remaining_time": "0:36:29", "throughput": 2042.46, "total_tokens": 2296568}
{"current_steps": 5610, "total_steps": 16520, "loss": 0.1842, "lr": 0.0008351772487928577, "epoch": 6.791767554479419, "percentage": 33.96, "elapsed_time": "0:18:45", "remaining_time": "0:36:28", "throughput": 2042.49, "total_tokens": 2298520}
{"current_steps": 5615, "total_steps": 16520, "loss": 0.0199, "lr": 0.0008347850806123289, "epoch": 6.797820823244552, "percentage": 33.99, "elapsed_time": "0:18:46", "remaining_time": "0:36:27", "throughput": 2042.67, "total_tokens": 2300760}
{"current_steps": 5620, "total_steps": 16520, "loss": 0.0488, "lr": 0.0008343925387510683, "epoch": 6.803874092009686, "percentage": 34.02, "elapsed_time": "0:18:47", "remaining_time": "0:36:26", "throughput": 2042.8, "total_tokens": 2302904}
{"current_steps": 5625, "total_steps": 16520, "loss": 0.0851, "lr": 0.0008339996236472236, "epoch": 6.809927360774818, "percentage": 34.05, "elapsed_time": "0:18:48", "remaining_time": "0:36:25", "throughput": 2042.81, "total_tokens": 2304888}
{"current_steps": 5630, "total_steps": 16520, "loss": 0.0849, "lr": 0.0008336063357393595, "epoch": 6.815980629539951, "percentage": 34.08, "elapsed_time": "0:18:49", "remaining_time": "0:36:24", "throughput": 2042.84, "total_tokens": 2306776}
{"current_steps": 5635, "total_steps": 16520, "loss": 0.0764, "lr": 0.0008332126754664563, "epoch": 6.822033898305085, "percentage": 34.11, "elapsed_time": "0:18:50", "remaining_time": "0:36:23", "throughput": 2042.98, "total_tokens": 2308920}
{"current_steps": 5640, "total_steps": 16520, "loss": 0.074, "lr": 0.0008328186432679101, "epoch": 6.828087167070218, "percentage": 34.14, "elapsed_time": "0:18:51", "remaining_time": "0:36:22", "throughput": 2043.06, "total_tokens": 2310936}
{"current_steps": 5645, "total_steps": 16520, "loss": 0.0784, "lr": 0.0008324242395835322, "epoch": 6.8341404358353515, "percentage": 34.17, "elapsed_time": "0:18:52", "remaining_time": "0:36:20", "throughput": 2043.07, "total_tokens": 2312856}
{"current_steps": 5650, "total_steps": 16520, "loss": 0.0453, "lr": 0.0008320294648535483, "epoch": 6.840193704600484, "percentage": 34.2, "elapsed_time": "0:18:52", "remaining_time": "0:36:19", "throughput": 2043.13, "total_tokens": 2314776}
{"current_steps": 5655, "total_steps": 16520, "loss": 0.121, "lr": 0.0008316343195185987, "epoch": 6.846246973365617, "percentage": 34.23, "elapsed_time": "0:18:53", "remaining_time": "0:36:18", "throughput": 2043.14, "total_tokens": 2316760}
{"current_steps": 5660, "total_steps": 16520, "loss": 0.0856, "lr": 0.0008312388040197368, "epoch": 6.852300242130751, "percentage": 34.26, "elapsed_time": "0:18:54", "remaining_time": "0:36:17", "throughput": 2043.23, "total_tokens": 2318840}
{"current_steps": 5665, "total_steps": 16520, "loss": 0.0642, "lr": 0.0008308429187984297, "epoch": 6.858353510895884, "percentage": 34.29, "elapsed_time": "0:18:55", "remaining_time": "0:36:16", "throughput": 2043.28, "total_tokens": 2320824}
{"current_steps": 5670, "total_steps": 16520, "loss": 0.0498, "lr": 0.0008304466642965569, "epoch": 6.864406779661017, "percentage": 34.32, "elapsed_time": "0:18:56", "remaining_time": "0:36:15", "throughput": 2043.34, "total_tokens": 2322808}
{"current_steps": 5675, "total_steps": 16520, "loss": 0.0724, "lr": 0.0008300500409564102, "epoch": 6.87046004842615, "percentage": 34.35, "elapsed_time": "0:18:57", "remaining_time": "0:36:14", "throughput": 2043.42, "total_tokens": 2324888}
{"current_steps": 5680, "total_steps": 16520, "loss": 0.1365, "lr": 0.0008296530492206926, "epoch": 6.876513317191283, "percentage": 34.38, "elapsed_time": "0:18:58", "remaining_time": "0:36:13", "throughput": 2043.5, "total_tokens": 2326840}
{"current_steps": 5685, "total_steps": 16520, "loss": 0.0882, "lr": 0.0008292556895325194, "epoch": 6.8825665859564165, "percentage": 34.41, "elapsed_time": "0:18:59", "remaining_time": "0:36:11", "throughput": 2043.59, "total_tokens": 2328920}
{"current_steps": 5690, "total_steps": 16520, "loss": 0.084, "lr": 0.0008288579623354154, "epoch": 6.88861985472155, "percentage": 34.44, "elapsed_time": "0:19:00", "remaining_time": "0:36:10", "throughput": 2043.57, "total_tokens": 2330808}
{"current_steps": 5695, "total_steps": 16520, "loss": 0.0413, "lr": 0.0008284598680733162, "epoch": 6.894673123486683, "percentage": 34.47, "elapsed_time": "0:19:01", "remaining_time": "0:36:09", "throughput": 2043.68, "total_tokens": 2332920}
{"current_steps": 5700, "total_steps": 16520, "loss": 0.0837, "lr": 0.0008280614071905672, "epoch": 6.900726392251816, "percentage": 34.5, "elapsed_time": "0:19:02", "remaining_time": "0:36:08", "throughput": 2043.86, "total_tokens": 2335128}
{"current_steps": 5705, "total_steps": 16520, "loss": 0.0524, "lr": 0.0008276625801319227, "epoch": 6.906779661016949, "percentage": 34.53, "elapsed_time": "0:19:03", "remaining_time": "0:36:07", "throughput": 2043.89, "total_tokens": 2337080}
{"current_steps": 5710, "total_steps": 16520, "loss": 0.1826, "lr": 0.0008272633873425459, "epoch": 6.912832929782082, "percentage": 34.56, "elapsed_time": "0:19:04", "remaining_time": "0:36:06", "throughput": 2044.0, "total_tokens": 2339224}
{"current_steps": 5715, "total_steps": 16520, "loss": 0.0863, "lr": 0.0008268638292680084, "epoch": 6.918886198547216, "percentage": 34.59, "elapsed_time": "0:19:05", "remaining_time": "0:36:05", "throughput": 2044.1, "total_tokens": 2341336}
{"current_steps": 5720, "total_steps": 16520, "loss": 0.0782, "lr": 0.0008264639063542889, "epoch": 6.924939467312349, "percentage": 34.62, "elapsed_time": "0:19:06", "remaining_time": "0:36:04", "throughput": 2044.17, "total_tokens": 2343384}
{"current_steps": 5725, "total_steps": 16520, "loss": 0.1298, "lr": 0.0008260636190477741, "epoch": 6.9309927360774815, "percentage": 34.65, "elapsed_time": "0:19:07", "remaining_time": "0:36:03", "throughput": 2044.2, "total_tokens": 2345336}
{"current_steps": 5730, "total_steps": 16520, "loss": 0.0656, "lr": 0.000825662967795257, "epoch": 6.937046004842615, "percentage": 34.69, "elapsed_time": "0:19:08", "remaining_time": "0:36:02", "throughput": 2044.31, "total_tokens": 2347384}
{"current_steps": 5735, "total_steps": 16520, "loss": 0.0177, "lr": 0.0008252619530439369, "epoch": 6.943099273607748, "percentage": 34.72, "elapsed_time": "0:19:09", "remaining_time": "0:36:01", "throughput": 2044.37, "total_tokens": 2349432}
{"current_steps": 5740, "total_steps": 16520, "loss": 0.0562, "lr": 0.0008248605752414187, "epoch": 6.9491525423728815, "percentage": 34.75, "elapsed_time": "0:19:10", "remaining_time": "0:36:00", "throughput": 2044.45, "total_tokens": 2351512}
{"current_steps": 5745, "total_steps": 16520, "loss": 0.0565, "lr": 0.0008244588348357126, "epoch": 6.955205811138015, "percentage": 34.78, "elapsed_time": "0:19:11", "remaining_time": "0:35:58", "throughput": 2044.51, "total_tokens": 2353496}
{"current_steps": 5750, "total_steps": 16520, "loss": 0.1098, "lr": 0.0008240567322752337, "epoch": 6.961259079903147, "percentage": 34.81, "elapsed_time": "0:19:12", "remaining_time": "0:35:57", "throughput": 2044.57, "total_tokens": 2355576}
{"current_steps": 5755, "total_steps": 16520, "loss": 0.0826, "lr": 0.0008236542680088015, "epoch": 6.967312348668281, "percentage": 34.84, "elapsed_time": "0:19:13", "remaining_time": "0:35:56", "throughput": 2044.7, "total_tokens": 2357656}
{"current_steps": 5760, "total_steps": 16520, "loss": 0.0882, "lr": 0.0008232514424856384, "epoch": 6.973365617433414, "percentage": 34.87, "elapsed_time": "0:19:13", "remaining_time": "0:35:55", "throughput": 2044.77, "total_tokens": 2359608}
{"current_steps": 5765, "total_steps": 16520, "loss": 0.0785, "lr": 0.0008228482561553709, "epoch": 6.979418886198547, "percentage": 34.9, "elapsed_time": "0:19:14", "remaining_time": "0:35:54", "throughput": 2044.87, "total_tokens": 2361656}
{"current_steps": 5770, "total_steps": 16520, "loss": 0.0827, "lr": 0.000822444709468028, "epoch": 6.985472154963681, "percentage": 34.93, "elapsed_time": "0:19:15", "remaining_time": "0:35:53", "throughput": 2044.95, "total_tokens": 2363672}
{"current_steps": 5775, "total_steps": 16520, "loss": 0.022, "lr": 0.0008220408028740407, "epoch": 6.991525423728813, "percentage": 34.96, "elapsed_time": "0:19:16", "remaining_time": "0:35:52", "throughput": 2044.98, "total_tokens": 2365560}
{"current_steps": 5780, "total_steps": 16520, "loss": 0.0402, "lr": 0.0008216365368242418, "epoch": 6.9975786924939465, "percentage": 34.99, "elapsed_time": "0:19:17", "remaining_time": "0:35:51", "throughput": 2045.05, "total_tokens": 2367544}
{"current_steps": 5782, "total_steps": 16520, "eval_loss": 0.12482118606567383, "epoch": 7.0, "percentage": 35.0, "elapsed_time": "0:19:25", "remaining_time": "0:36:05", "throughput": 2030.96, "total_tokens": 2368032}
{"current_steps": 5785, "total_steps": 16520, "loss": 0.0389, "lr": 0.0008212319117698654, "epoch": 7.00363196125908, "percentage": 35.02, "elapsed_time": "0:19:27", "remaining_time": "0:36:06", "throughput": 2029.33, "total_tokens": 2369184}
{"current_steps": 5790, "total_steps": 16520, "loss": 0.0595, "lr": 0.0008208269281625465, "epoch": 7.009685230024213, "percentage": 35.05, "elapsed_time": "0:19:28", "remaining_time": "0:36:05", "throughput": 2029.34, "total_tokens": 2371168}
{"current_steps": 5795, "total_steps": 16520, "loss": 0.05, "lr": 0.0008204215864543197, "epoch": 7.0157384987893465, "percentage": 35.08, "elapsed_time": "0:19:29", "remaining_time": "0:36:04", "throughput": 2029.45, "total_tokens": 2373280}
{"current_steps": 5800, "total_steps": 16520, "loss": 0.0961, "lr": 0.0008200158870976198, "epoch": 7.021791767554479, "percentage": 35.11, "elapsed_time": "0:19:30", "remaining_time": "0:36:03", "throughput": 2029.62, "total_tokens": 2375424}
{"current_steps": 5805, "total_steps": 16520, "loss": 0.0677, "lr": 0.0008196098305452809, "epoch": 7.027845036319612, "percentage": 35.14, "elapsed_time": "0:19:31", "remaining_time": "0:36:02", "throughput": 2029.68, "total_tokens": 2377472}
{"current_steps": 5810, "total_steps": 16520, "loss": 0.0459, "lr": 0.0008192034172505355, "epoch": 7.033898305084746, "percentage": 35.17, "elapsed_time": "0:19:32", "remaining_time": "0:36:01", "throughput": 2029.77, "total_tokens": 2379552}
{"current_steps": 5815, "total_steps": 16520, "loss": 0.0742, "lr": 0.0008187966476670143, "epoch": 7.039951573849879, "percentage": 35.2, "elapsed_time": "0:19:33", "remaining_time": "0:35:59", "throughput": 2029.85, "total_tokens": 2381376}
{"current_steps": 5820, "total_steps": 16520, "loss": 0.1829, "lr": 0.0008183895222487458, "epoch": 7.046004842615012, "percentage": 35.23, "elapsed_time": "0:19:34", "remaining_time": "0:35:58", "throughput": 2029.89, "total_tokens": 2383392}
{"current_steps": 5825, "total_steps": 16520, "loss": 0.0557, "lr": 0.0008179820414501556, "epoch": 7.052058111380146, "percentage": 35.26, "elapsed_time": "0:19:35", "remaining_time": "0:35:57", "throughput": 2029.97, "total_tokens": 2385408}
{"current_steps": 5830, "total_steps": 16520, "loss": 0.0435, "lr": 0.0008175742057260661, "epoch": 7.058111380145278, "percentage": 35.29, "elapsed_time": "0:19:36", "remaining_time": "0:35:56", "throughput": 2030.15, "total_tokens": 2387552}
{"current_steps": 5835, "total_steps": 16520, "loss": 0.0456, "lr": 0.0008171660155316958, "epoch": 7.0641646489104115, "percentage": 35.32, "elapsed_time": "0:19:36", "remaining_time": "0:35:55", "throughput": 2030.26, "total_tokens": 2389600}
{"current_steps": 5840, "total_steps": 16520, "loss": 0.1101, "lr": 0.0008167574713226586, "epoch": 7.070217917675545, "percentage": 35.35, "elapsed_time": "0:19:37", "remaining_time": "0:35:54", "throughput": 2030.3, "total_tokens": 2391616}
{"current_steps": 5845, "total_steps": 16520, "loss": 0.0387, "lr": 0.0008163485735549641, "epoch": 7.076271186440678, "percentage": 35.38, "elapsed_time": "0:19:38", "remaining_time": "0:35:53", "throughput": 2030.39, "total_tokens": 2393632}
{"current_steps": 5850, "total_steps": 16520, "loss": 0.0531, "lr": 0.0008159393226850158, "epoch": 7.0823244552058116, "percentage": 35.41, "elapsed_time": "0:19:39", "remaining_time": "0:35:51", "throughput": 2030.44, "total_tokens": 2395616}
{"current_steps": 5855, "total_steps": 16520, "loss": 0.0772, "lr": 0.000815529719169612, "epoch": 7.088377723970944, "percentage": 35.44, "elapsed_time": "0:19:40", "remaining_time": "0:35:50", "throughput": 2030.47, "total_tokens": 2397632}
{"current_steps": 5860, "total_steps": 16520, "loss": 0.0534, "lr": 0.0008151197634659445, "epoch": 7.094430992736077, "percentage": 35.47, "elapsed_time": "0:19:41", "remaining_time": "0:35:49", "throughput": 2030.49, "total_tokens": 2399552}
{"current_steps": 5865, "total_steps": 16520, "loss": 0.0339, "lr": 0.0008147094560315977, "epoch": 7.100484261501211, "percentage": 35.5, "elapsed_time": "0:19:42", "remaining_time": "0:35:48", "throughput": 2030.58, "total_tokens": 2401568}
{"current_steps": 5870, "total_steps": 16520, "loss": 0.0727, "lr": 0.000814298797324549, "epoch": 7.106537530266344, "percentage": 35.53, "elapsed_time": "0:19:43", "remaining_time": "0:35:47", "throughput": 2030.68, "total_tokens": 2403616}
{"current_steps": 5875, "total_steps": 16520, "loss": 0.0564, "lr": 0.0008138877878031681, "epoch": 7.112590799031477, "percentage": 35.56, "elapsed_time": "0:19:44", "remaining_time": "0:35:46", "throughput": 2030.94, "total_tokens": 2405952}
{"current_steps": 5880, "total_steps": 16520, "loss": 0.0439, "lr": 0.0008134764279262157, "epoch": 7.11864406779661, "percentage": 35.59, "elapsed_time": "0:19:45", "remaining_time": "0:35:45", "throughput": 2030.98, "total_tokens": 2407968}
{"current_steps": 5885, "total_steps": 16520, "loss": 0.0246, "lr": 0.000813064718152844, "epoch": 7.124697336561743, "percentage": 35.62, "elapsed_time": "0:19:46", "remaining_time": "0:35:44", "throughput": 2031.02, "total_tokens": 2409856}
{"current_steps": 5890, "total_steps": 16520, "loss": 0.0682, "lr": 0.0008126526589425956, "epoch": 7.1307506053268765, "percentage": 35.65, "elapsed_time": "0:19:47", "remaining_time": "0:35:43", "throughput": 2031.08, "total_tokens": 2411904}
{"current_steps": 5895, "total_steps": 16520, "loss": 0.0252, "lr": 0.000812240250755403, "epoch": 7.13680387409201, "percentage": 35.68, "elapsed_time": "0:19:48", "remaining_time": "0:35:42", "throughput": 2031.14, "total_tokens": 2413952}
{"current_steps": 5900, "total_steps": 16520, "loss": 0.0096, "lr": 0.0008118274940515886, "epoch": 7.142857142857143, "percentage": 35.71, "elapsed_time": "0:19:49", "remaining_time": "0:35:40", "throughput": 2031.23, "total_tokens": 2416032}
{"current_steps": 5905, "total_steps": 16520, "loss": 0.0155, "lr": 0.0008114143892918635, "epoch": 7.148910411622276, "percentage": 35.74, "elapsed_time": "0:19:50", "remaining_time": "0:35:39", "throughput": 2031.31, "total_tokens": 2418112}
{"current_steps": 5910, "total_steps": 16520, "loss": 0.0347, "lr": 0.0008110009369373273, "epoch": 7.154963680387409, "percentage": 35.77, "elapsed_time": "0:19:51", "remaining_time": "0:35:38", "throughput": 2031.35, "total_tokens": 2420128}
{"current_steps": 5915, "total_steps": 16520, "loss": 0.015, "lr": 0.0008105871374494676, "epoch": 7.161016949152542, "percentage": 35.81, "elapsed_time": "0:19:52", "remaining_time": "0:35:37", "throughput": 2031.55, "total_tokens": 2422368}
{"current_steps": 5920, "total_steps": 16520, "loss": 0.0886, "lr": 0.0008101729912901595, "epoch": 7.167070217917676, "percentage": 35.84, "elapsed_time": "0:19:53", "remaining_time": "0:35:36", "throughput": 2031.55, "total_tokens": 2424224}
{"current_steps": 5925, "total_steps": 16520, "loss": 0.0515, "lr": 0.0008097584989216653, "epoch": 7.173123486682809, "percentage": 35.87, "elapsed_time": "0:19:54", "remaining_time": "0:35:35", "throughput": 2031.59, "total_tokens": 2426112}
{"current_steps": 5930, "total_steps": 16520, "loss": 0.1281, "lr": 0.0008093436608066334, "epoch": 7.1791767554479415, "percentage": 35.9, "elapsed_time": "0:19:55", "remaining_time": "0:35:34", "throughput": 2031.73, "total_tokens": 2428288}
{"current_steps": 5935, "total_steps": 16520, "loss": 0.0416, "lr": 0.000808928477408098, "epoch": 7.185230024213075, "percentage": 35.93, "elapsed_time": "0:19:56", "remaining_time": "0:35:33", "throughput": 2031.81, "total_tokens": 2430304}
{"current_steps": 5940, "total_steps": 16520, "loss": 0.0272, "lr": 0.000808512949189479, "epoch": 7.191283292978208, "percentage": 35.96, "elapsed_time": "0:19:57", "remaining_time": "0:35:32", "throughput": 2031.87, "total_tokens": 2432352}
{"current_steps": 5945, "total_steps": 16520, "loss": 0.0571, "lr": 0.0008080970766145812, "epoch": 7.197336561743342, "percentage": 35.99, "elapsed_time": "0:19:58", "remaining_time": "0:35:31", "throughput": 2032.05, "total_tokens": 2434496}
{"current_steps": 5950, "total_steps": 16520, "loss": 0.0674, "lr": 0.0008076808601475935, "epoch": 7.203389830508475, "percentage": 36.02, "elapsed_time": "0:19:59", "remaining_time": "0:35:30", "throughput": 2032.2, "total_tokens": 2436672}
{"current_steps": 5955, "total_steps": 16520, "loss": 0.1656, "lr": 0.000807264300253089, "epoch": 7.209443099273607, "percentage": 36.05, "elapsed_time": "0:20:00", "remaining_time": "0:35:28", "throughput": 2032.38, "total_tokens": 2438880}
{"current_steps": 5960, "total_steps": 16520, "loss": 0.1315, "lr": 0.0008068473973960237, "epoch": 7.215496368038741, "percentage": 36.08, "elapsed_time": "0:20:00", "remaining_time": "0:35:27", "throughput": 2032.46, "total_tokens": 2440896}
{"current_steps": 5965, "total_steps": 16520, "loss": 0.0159, "lr": 0.0008064301520417367, "epoch": 7.221549636803874, "percentage": 36.11, "elapsed_time": "0:20:01", "remaining_time": "0:35:26", "throughput": 2032.5, "total_tokens": 2442848}
{"current_steps": 5970, "total_steps": 16520, "loss": 0.0328, "lr": 0.0008060125646559494, "epoch": 7.227602905569007, "percentage": 36.14, "elapsed_time": "0:20:02", "remaining_time": "0:35:25", "throughput": 2032.68, "total_tokens": 2445056}
{"current_steps": 5975, "total_steps": 16520, "loss": 0.0521, "lr": 0.0008055946357047647, "epoch": 7.233656174334141, "percentage": 36.17, "elapsed_time": "0:20:03", "remaining_time": "0:35:24", "throughput": 2032.79, "total_tokens": 2447104}
{"current_steps": 5980, "total_steps": 16520, "loss": 0.0933, "lr": 0.0008051763656546672, "epoch": 7.239709443099273, "percentage": 36.2, "elapsed_time": "0:20:04", "remaining_time": "0:35:23", "throughput": 2032.92, "total_tokens": 2449248}
{"current_steps": 5985, "total_steps": 16520, "loss": 0.0408, "lr": 0.0008047577549725218, "epoch": 7.245762711864407, "percentage": 36.23, "elapsed_time": "0:20:05", "remaining_time": "0:35:22", "throughput": 2033.01, "total_tokens": 2451360}
{"current_steps": 5990, "total_steps": 16520, "loss": 0.1201, "lr": 0.0008043388041255737, "epoch": 7.25181598062954, "percentage": 36.26, "elapsed_time": "0:20:06", "remaining_time": "0:35:21", "throughput": 2033.14, "total_tokens": 2453504}
{"current_steps": 5995, "total_steps": 16520, "loss": 0.062, "lr": 0.0008039195135814481, "epoch": 7.257869249394673, "percentage": 36.29, "elapsed_time": "0:20:07", "remaining_time": "0:35:20", "throughput": 2033.2, "total_tokens": 2455488}
{"current_steps": 6000, "total_steps": 16520, "loss": 0.0514, "lr": 0.0008034998838081489, "epoch": 7.263922518159807, "percentage": 36.32, "elapsed_time": "0:20:08", "remaining_time": "0:35:19", "throughput": 2033.24, "total_tokens": 2457504}
{"current_steps": 6005, "total_steps": 16520, "loss": 0.1043, "lr": 0.0008030799152740589, "epoch": 7.269975786924939, "percentage": 36.35, "elapsed_time": "0:20:09", "remaining_time": "0:35:18", "throughput": 2033.4, "total_tokens": 2459680}
{"current_steps": 6010, "total_steps": 16520, "loss": 0.053, "lr": 0.0008026596084479391, "epoch": 7.276029055690072, "percentage": 36.38, "elapsed_time": "0:20:10", "remaining_time": "0:35:17", "throughput": 2033.51, "total_tokens": 2461792}
{"current_steps": 6015, "total_steps": 16520, "loss": 0.1224, "lr": 0.0008022389637989278, "epoch": 7.282082324455206, "percentage": 36.41, "elapsed_time": "0:20:11", "remaining_time": "0:35:16", "throughput": 2033.66, "total_tokens": 2463968}
{"current_steps": 6020, "total_steps": 16520, "loss": 0.0593, "lr": 0.0008018179817965407, "epoch": 7.288135593220339, "percentage": 36.44, "elapsed_time": "0:20:12", "remaining_time": "0:35:14", "throughput": 2033.73, "total_tokens": 2466016}
{"current_steps": 6025, "total_steps": 16520, "loss": 0.0571, "lr": 0.0008013966629106697, "epoch": 7.2941888619854724, "percentage": 36.47, "elapsed_time": "0:20:13", "remaining_time": "0:35:13", "throughput": 2033.74, "total_tokens": 2467936}
{"current_steps": 6030, "total_steps": 16520, "loss": 0.1274, "lr": 0.0008009750076115831, "epoch": 7.300242130750606, "percentage": 36.5, "elapsed_time": "0:20:14", "remaining_time": "0:35:12", "throughput": 2033.88, "total_tokens": 2470048}
{"current_steps": 6035, "total_steps": 16520, "loss": 0.0608, "lr": 0.0008005530163699246, "epoch": 7.306295399515738, "percentage": 36.53, "elapsed_time": "0:20:15", "remaining_time": "0:35:11", "throughput": 2033.94, "total_tokens": 2472096}
{"current_steps": 6040, "total_steps": 16520, "loss": 0.0522, "lr": 0.0008001306896567125, "epoch": 7.312348668280872, "percentage": 36.56, "elapsed_time": "0:20:16", "remaining_time": "0:35:10", "throughput": 2034.0, "total_tokens": 2474080}
{"current_steps": 6045, "total_steps": 16520, "loss": 0.0938, "lr": 0.0007997080279433402, "epoch": 7.318401937046005, "percentage": 36.59, "elapsed_time": "0:20:17", "remaining_time": "0:35:09", "throughput": 2034.15, "total_tokens": 2476192}
{"current_steps": 6050, "total_steps": 16520, "loss": 0.047, "lr": 0.0007992850317015743, "epoch": 7.324455205811138, "percentage": 36.62, "elapsed_time": "0:20:18", "remaining_time": "0:35:08", "throughput": 2034.26, "total_tokens": 2478304}
{"current_steps": 6055, "total_steps": 16520, "loss": 0.0907, "lr": 0.0007988617014035553, "epoch": 7.330508474576272, "percentage": 36.65, "elapsed_time": "0:20:19", "remaining_time": "0:35:07", "throughput": 2034.3, "total_tokens": 2480192}
{"current_steps": 6060, "total_steps": 16520, "loss": 0.0326, "lr": 0.0007984380375217964, "epoch": 7.336561743341404, "percentage": 36.68, "elapsed_time": "0:20:20", "remaining_time": "0:35:06", "throughput": 2034.41, "total_tokens": 2482304}
{"current_steps": 6065, "total_steps": 16520, "loss": 0.0392, "lr": 0.0007980140405291831, "epoch": 7.342615012106537, "percentage": 36.71, "elapsed_time": "0:20:21", "remaining_time": "0:35:04", "throughput": 2034.51, "total_tokens": 2484352}
{"current_steps": 6070, "total_steps": 16520, "loss": 0.0466, "lr": 0.000797589710898973, "epoch": 7.348668280871671, "percentage": 36.74, "elapsed_time": "0:20:22", "remaining_time": "0:35:03", "throughput": 2034.64, "total_tokens": 2486432}
{"current_steps": 6075, "total_steps": 16520, "loss": 0.0388, "lr": 0.0007971650491047944, "epoch": 7.354721549636804, "percentage": 36.77, "elapsed_time": "0:20:23", "remaining_time": "0:35:02", "throughput": 2034.72, "total_tokens": 2488512}
{"current_steps": 6080, "total_steps": 16520, "loss": 0.0232, "lr": 0.000796740055620647, "epoch": 7.3607748184019375, "percentage": 36.8, "elapsed_time": "0:20:23", "remaining_time": "0:35:01", "throughput": 2034.88, "total_tokens": 2490592}
{"current_steps": 6085, "total_steps": 16520, "loss": 0.0247, "lr": 0.0007963147309209002, "epoch": 7.36682808716707, "percentage": 36.83, "elapsed_time": "0:20:24", "remaining_time": "0:35:00", "throughput": 2034.98, "total_tokens": 2492640}
{"current_steps": 6090, "total_steps": 16520, "loss": 0.0692, "lr": 0.0007958890754802937, "epoch": 7.372881355932203, "percentage": 36.86, "elapsed_time": "0:20:25", "remaining_time": "0:34:59", "throughput": 2035.06, "total_tokens": 2494720}
{"current_steps": 6095, "total_steps": 16520, "loss": 0.0368, "lr": 0.0007954630897739356, "epoch": 7.378934624697337, "percentage": 36.89, "elapsed_time": "0:20:26", "remaining_time": "0:34:58", "throughput": 2035.16, "total_tokens": 2496768}
{"current_steps": 6100, "total_steps": 16520, "loss": 0.0319, "lr": 0.0007950367742773032, "epoch": 7.38498789346247, "percentage": 36.92, "elapsed_time": "0:20:27", "remaining_time": "0:34:57", "throughput": 2035.26, "total_tokens": 2498752}
{"current_steps": 6105, "total_steps": 16520, "loss": 0.0409, "lr": 0.0007946101294662418, "epoch": 7.391041162227603, "percentage": 36.96, "elapsed_time": "0:20:28", "remaining_time": "0:34:56", "throughput": 2035.39, "total_tokens": 2500896}
{"current_steps": 6110, "total_steps": 16520, "loss": 0.0774, "lr": 0.0007941831558169641, "epoch": 7.397094430992736, "percentage": 36.99, "elapsed_time": "0:20:29", "remaining_time": "0:34:54", "throughput": 2035.51, "total_tokens": 2502912}
{"current_steps": 6115, "total_steps": 16520, "loss": 0.089, "lr": 0.0007937558538060501, "epoch": 7.403147699757869, "percentage": 37.02, "elapsed_time": "0:20:30", "remaining_time": "0:34:53", "throughput": 2035.57, "total_tokens": 2504960}
{"current_steps": 6120, "total_steps": 16520, "loss": 0.0781, "lr": 0.0007933282239104459, "epoch": 7.4092009685230025, "percentage": 37.05, "elapsed_time": "0:20:31", "remaining_time": "0:34:52", "throughput": 2035.7, "total_tokens": 2507072}
{"current_steps": 6125, "total_steps": 16520, "loss": 0.0508, "lr": 0.0007929002666074642, "epoch": 7.415254237288136, "percentage": 37.08, "elapsed_time": "0:20:32", "remaining_time": "0:34:51", "throughput": 2035.76, "total_tokens": 2509120}
{"current_steps": 6130, "total_steps": 16520, "loss": 0.0386, "lr": 0.0007924719823747825, "epoch": 7.421307506053269, "percentage": 37.11, "elapsed_time": "0:20:33", "remaining_time": "0:34:50", "throughput": 2035.89, "total_tokens": 2511136}
{"current_steps": 6135, "total_steps": 16520, "loss": 0.0431, "lr": 0.0007920433716904436, "epoch": 7.427360774818402, "percentage": 37.14, "elapsed_time": "0:20:34", "remaining_time": "0:34:49", "throughput": 2036.01, "total_tokens": 2513088}
{"current_steps": 6140, "total_steps": 16520, "loss": 0.0224, "lr": 0.0007916144350328547, "epoch": 7.433414043583535, "percentage": 37.17, "elapsed_time": "0:20:35", "remaining_time": "0:34:48", "throughput": 2036.03, "total_tokens": 2515072}
{"current_steps": 6145, "total_steps": 16520, "loss": 0.0436, "lr": 0.0007911851728807864, "epoch": 7.439467312348668, "percentage": 37.2, "elapsed_time": "0:20:36", "remaining_time": "0:34:47", "throughput": 2036.07, "total_tokens": 2517088}
{"current_steps": 6150, "total_steps": 16520, "loss": 0.024, "lr": 0.0007907555857133734, "epoch": 7.445520581113802, "percentage": 37.23, "elapsed_time": "0:20:37", "remaining_time": "0:34:46", "throughput": 2036.19, "total_tokens": 2519168}
{"current_steps": 6155, "total_steps": 16520, "loss": 0.0101, "lr": 0.0007903256740101123, "epoch": 7.451573849878935, "percentage": 37.26, "elapsed_time": "0:20:38", "remaining_time": "0:34:45", "throughput": 2036.26, "total_tokens": 2521216}
{"current_steps": 6160, "total_steps": 16520, "loss": 0.0645, "lr": 0.0007898954382508627, "epoch": 7.4576271186440675, "percentage": 37.29, "elapsed_time": "0:20:39", "remaining_time": "0:34:43", "throughput": 2036.31, "total_tokens": 2523264}
{"current_steps": 6165, "total_steps": 16520, "loss": 0.0524, "lr": 0.0007894648789158452, "epoch": 7.463680387409201, "percentage": 37.32, "elapsed_time": "0:20:40", "remaining_time": "0:34:42", "throughput": 2036.37, "total_tokens": 2525248}
{"current_steps": 6170, "total_steps": 16520, "loss": 0.0379, "lr": 0.0007890339964856423, "epoch": 7.469733656174334, "percentage": 37.35, "elapsed_time": "0:20:41", "remaining_time": "0:34:41", "throughput": 2036.48, "total_tokens": 2527360}
{"current_steps": 6175, "total_steps": 16520, "loss": 0.0986, "lr": 0.0007886027914411964, "epoch": 7.4757869249394675, "percentage": 37.38, "elapsed_time": "0:20:41", "remaining_time": "0:34:40", "throughput": 2036.55, "total_tokens": 2529376}
{"current_steps": 6180, "total_steps": 16520, "loss": 0.0983, "lr": 0.0007881712642638108, "epoch": 7.481840193704601, "percentage": 37.41, "elapsed_time": "0:20:42", "remaining_time": "0:34:39", "throughput": 2036.61, "total_tokens": 2531424}
{"current_steps": 6185, "total_steps": 16520, "loss": 0.0419, "lr": 0.0007877394154351475, "epoch": 7.487893462469733, "percentage": 37.44, "elapsed_time": "0:20:43", "remaining_time": "0:34:38", "throughput": 2036.67, "total_tokens": 2533344}
{"current_steps": 6190, "total_steps": 16520, "loss": 0.167, "lr": 0.0007873072454372282, "epoch": 7.493946731234867, "percentage": 37.47, "elapsed_time": "0:20:44", "remaining_time": "0:34:37", "throughput": 2036.77, "total_tokens": 2535456}
{"current_steps": 6195, "total_steps": 16520, "loss": 0.0356, "lr": 0.0007868747547524327, "epoch": 7.5, "percentage": 37.5, "elapsed_time": "0:20:45", "remaining_time": "0:34:36", "throughput": 2036.83, "total_tokens": 2537504}
{"current_steps": 6200, "total_steps": 16520, "loss": 0.0623, "lr": 0.0007864419438634989, "epoch": 7.506053268765133, "percentage": 37.53, "elapsed_time": "0:20:46", "remaining_time": "0:34:35", "throughput": 2036.89, "total_tokens": 2539488}
{"current_steps": 6205, "total_steps": 16520, "loss": 0.0382, "lr": 0.0007860088132535221, "epoch": 7.512106537530267, "percentage": 37.56, "elapsed_time": "0:20:47", "remaining_time": "0:34:34", "throughput": 2036.9, "total_tokens": 2541472}
{"current_steps": 6210, "total_steps": 16520, "loss": 0.0171, "lr": 0.0007855753634059544, "epoch": 7.518159806295399, "percentage": 37.59, "elapsed_time": "0:20:48", "remaining_time": "0:34:33", "throughput": 2037.02, "total_tokens": 2543616}
{"current_steps": 6215, "total_steps": 16520, "loss": 0.0216, "lr": 0.0007851415948046042, "epoch": 7.5242130750605325, "percentage": 37.62, "elapsed_time": "0:20:49", "remaining_time": "0:34:32", "throughput": 2037.07, "total_tokens": 2545600}
{"current_steps": 6220, "total_steps": 16520, "loss": 0.0197, "lr": 0.0007847075079336357, "epoch": 7.530266343825666, "percentage": 37.65, "elapsed_time": "0:20:50", "remaining_time": "0:34:30", "throughput": 2037.17, "total_tokens": 2547712}
{"current_steps": 6225, "total_steps": 16520, "loss": 0.0554, "lr": 0.0007842731032775687, "epoch": 7.536319612590799, "percentage": 37.68, "elapsed_time": "0:20:51", "remaining_time": "0:34:29", "throughput": 2037.3, "total_tokens": 2549856}
{"current_steps": 6230, "total_steps": 16520, "loss": 0.0347, "lr": 0.0007838383813212773, "epoch": 7.5423728813559325, "percentage": 37.71, "elapsed_time": "0:20:52", "remaining_time": "0:34:28", "throughput": 2037.34, "total_tokens": 2551872}
{"current_steps": 6235, "total_steps": 16520, "loss": 0.0328, "lr": 0.0007834033425499896, "epoch": 7.548426150121065, "percentage": 37.74, "elapsed_time": "0:20:53", "remaining_time": "0:34:27", "throughput": 2037.4, "total_tokens": 2553920}
{"current_steps": 6240, "total_steps": 16520, "loss": 0.1369, "lr": 0.0007829679874492879, "epoch": 7.554479418886198, "percentage": 37.77, "elapsed_time": "0:20:54", "remaining_time": "0:34:26", "throughput": 2037.43, "total_tokens": 2555872}
{"current_steps": 6245, "total_steps": 16520, "loss": 0.3002, "lr": 0.0007825323165051072, "epoch": 7.560532687651332, "percentage": 37.8, "elapsed_time": "0:20:55", "remaining_time": "0:34:25", "throughput": 2037.47, "total_tokens": 2557888}
{"current_steps": 6250, "total_steps": 16520, "loss": 0.0538, "lr": 0.000782096330203735, "epoch": 7.566585956416465, "percentage": 37.83, "elapsed_time": "0:20:56", "remaining_time": "0:34:24", "throughput": 2037.53, "total_tokens": 2559936}
{"current_steps": 6255, "total_steps": 16520, "loss": 0.0225, "lr": 0.000781660029031811, "epoch": 7.572639225181598, "percentage": 37.86, "elapsed_time": "0:20:57", "remaining_time": "0:34:23", "throughput": 2037.56, "total_tokens": 2561952}
{"current_steps": 6260, "total_steps": 16520, "loss": 0.1535, "lr": 0.0007812234134763263, "epoch": 7.578692493946731, "percentage": 37.89, "elapsed_time": "0:20:58", "remaining_time": "0:34:22", "throughput": 2037.71, "total_tokens": 2564096}
{"current_steps": 6265, "total_steps": 16520, "loss": 0.1032, "lr": 0.0007807864840246227, "epoch": 7.584745762711864, "percentage": 37.92, "elapsed_time": "0:20:59", "remaining_time": "0:34:21", "throughput": 2037.72, "total_tokens": 2566016}
{"current_steps": 6270, "total_steps": 16520, "loss": 0.1003, "lr": 0.0007803492411643928, "epoch": 7.5907990314769975, "percentage": 37.95, "elapsed_time": "0:21:00", "remaining_time": "0:34:20", "throughput": 2037.78, "total_tokens": 2568064}
{"current_steps": 6275, "total_steps": 16520, "loss": 0.0866, "lr": 0.0007799116853836784, "epoch": 7.596852300242131, "percentage": 37.98, "elapsed_time": "0:21:01", "remaining_time": "0:34:19", "throughput": 2037.86, "total_tokens": 2570176}
{"current_steps": 6280, "total_steps": 16520, "loss": 0.1185, "lr": 0.0007794738171708713, "epoch": 7.602905569007264, "percentage": 38.01, "elapsed_time": "0:21:02", "remaining_time": "0:34:18", "throughput": 2037.9, "total_tokens": 2572128}
{"current_steps": 6285, "total_steps": 16520, "loss": 0.0593, "lr": 0.0007790356370147115, "epoch": 7.608958837772397, "percentage": 38.04, "elapsed_time": "0:21:03", "remaining_time": "0:34:16", "throughput": 2038.01, "total_tokens": 2574144}
{"current_steps": 6290, "total_steps": 16520, "loss": 0.0652, "lr": 0.0007785971454042873, "epoch": 7.61501210653753, "percentage": 38.08, "elapsed_time": "0:21:04", "remaining_time": "0:34:15", "throughput": 2038.15, "total_tokens": 2576256}
{"current_steps": 6295, "total_steps": 16520, "loss": 0.0658, "lr": 0.0007781583428290346, "epoch": 7.621065375302663, "percentage": 38.11, "elapsed_time": "0:21:04", "remaining_time": "0:34:14", "throughput": 2038.22, "total_tokens": 2578272}
{"current_steps": 6300, "total_steps": 16520, "loss": 0.1055, "lr": 0.0007777192297787367, "epoch": 7.627118644067797, "percentage": 38.14, "elapsed_time": "0:21:05", "remaining_time": "0:34:13", "throughput": 2038.34, "total_tokens": 2580416}
{"current_steps": 6305, "total_steps": 16520, "loss": 0.0938, "lr": 0.000777279806743523, "epoch": 7.63317191283293, "percentage": 38.17, "elapsed_time": "0:21:06", "remaining_time": "0:34:12", "throughput": 2038.46, "total_tokens": 2582496}
{"current_steps": 6310, "total_steps": 16520, "loss": 0.0219, "lr": 0.0007768400742138694, "epoch": 7.6392251815980625, "percentage": 38.2, "elapsed_time": "0:21:07", "remaining_time": "0:34:11", "throughput": 2038.56, "total_tokens": 2584576}
{"current_steps": 6315, "total_steps": 16520, "loss": 0.0222, "lr": 0.0007764000326805966, "epoch": 7.645278450363196, "percentage": 38.23, "elapsed_time": "0:21:08", "remaining_time": "0:34:10", "throughput": 2038.73, "total_tokens": 2586816}
{"current_steps": 6320, "total_steps": 16520, "loss": 0.0597, "lr": 0.0007759596826348712, "epoch": 7.651331719128329, "percentage": 38.26, "elapsed_time": "0:21:09", "remaining_time": "0:34:09", "throughput": 2038.86, "total_tokens": 2588992}
{"current_steps": 6325, "total_steps": 16520, "loss": 0.0283, "lr": 0.0007755190245682027, "epoch": 7.657384987893463, "percentage": 38.29, "elapsed_time": "0:21:10", "remaining_time": "0:34:08", "throughput": 2038.98, "total_tokens": 2591072}
{"current_steps": 6330, "total_steps": 16520, "loss": 0.017, "lr": 0.000775078058972446, "epoch": 7.663438256658596, "percentage": 38.32, "elapsed_time": "0:21:11", "remaining_time": "0:34:07", "throughput": 2039.1, "total_tokens": 2593248}
{"current_steps": 6335, "total_steps": 16520, "loss": 0.0205, "lr": 0.0007746367863397981, "epoch": 7.669491525423728, "percentage": 38.35, "elapsed_time": "0:21:12", "remaining_time": "0:34:06", "throughput": 2039.09, "total_tokens": 2595136}
{"current_steps": 6340, "total_steps": 16520, "loss": 0.1407, "lr": 0.0007741952071627992, "epoch": 7.675544794188862, "percentage": 38.38, "elapsed_time": "0:21:13", "remaining_time": "0:34:05", "throughput": 2039.18, "total_tokens": 2597120}
{"current_steps": 6345, "total_steps": 16520, "loss": 0.1057, "lr": 0.0007737533219343314, "epoch": 7.681598062953995, "percentage": 38.41, "elapsed_time": "0:21:14", "remaining_time": "0:34:03", "throughput": 2039.24, "total_tokens": 2599168}
{"current_steps": 6350, "total_steps": 16520, "loss": 0.0993, "lr": 0.0007733111311476189, "epoch": 7.687651331719128, "percentage": 38.44, "elapsed_time": "0:21:15", "remaining_time": "0:34:02", "throughput": 2039.31, "total_tokens": 2601184}
{"current_steps": 6355, "total_steps": 16520, "loss": 0.0984, "lr": 0.0007728686352962264, "epoch": 7.693704600484262, "percentage": 38.47, "elapsed_time": "0:21:16", "remaining_time": "0:34:01", "throughput": 2039.45, "total_tokens": 2603360}
{"current_steps": 6360, "total_steps": 16520, "loss": 0.0755, "lr": 0.0007724258348740595, "epoch": 7.699757869249394, "percentage": 38.5, "elapsed_time": "0:21:17", "remaining_time": "0:34:00", "throughput": 2039.53, "total_tokens": 2605376}
{"current_steps": 6365, "total_steps": 16520, "loss": 0.0864, "lr": 0.0007719827303753633, "epoch": 7.7058111380145276, "percentage": 38.53, "elapsed_time": "0:21:18", "remaining_time": "0:33:59", "throughput": 2039.64, "total_tokens": 2607456}
{"current_steps": 6370, "total_steps": 16520, "loss": 0.0462, "lr": 0.0007715393222947232, "epoch": 7.711864406779661, "percentage": 38.56, "elapsed_time": "0:21:19", "remaining_time": "0:33:58", "throughput": 2039.73, "total_tokens": 2609504}
{"current_steps": 6375, "total_steps": 16520, "loss": 0.0961, "lr": 0.0007710956111270621, "epoch": 7.717917675544794, "percentage": 38.59, "elapsed_time": "0:21:20", "remaining_time": "0:33:57", "throughput": 2039.75, "total_tokens": 2611488}
{"current_steps": 6380, "total_steps": 16520, "loss": 0.0805, "lr": 0.0007706515973676425, "epoch": 7.723970944309928, "percentage": 38.62, "elapsed_time": "0:21:21", "remaining_time": "0:33:56", "throughput": 2039.8, "total_tokens": 2613472}
{"current_steps": 6385, "total_steps": 16520, "loss": 0.0768, "lr": 0.0007702072815120637, "epoch": 7.73002421307506, "percentage": 38.65, "elapsed_time": "0:21:22", "remaining_time": "0:33:55", "throughput": 2039.87, "total_tokens": 2615552}
{"current_steps": 6390, "total_steps": 16520, "loss": 0.087, "lr": 0.0007697626640562631, "epoch": 7.736077481840193, "percentage": 38.68, "elapsed_time": "0:21:23", "remaining_time": "0:33:54", "throughput": 2039.95, "total_tokens": 2617632}
{"current_steps": 6395, "total_steps": 16520, "loss": 0.0426, "lr": 0.0007693177454965139, "epoch": 7.742130750605327, "percentage": 38.71, "elapsed_time": "0:21:24", "remaining_time": "0:33:53", "throughput": 2039.97, "total_tokens": 2619552}
{"current_steps": 6400, "total_steps": 16520, "loss": 0.0669, "lr": 0.0007688725263294259, "epoch": 7.74818401937046, "percentage": 38.74, "elapsed_time": "0:21:25", "remaining_time": "0:33:52", "throughput": 2040.11, "total_tokens": 2621728}
{"current_steps": 6405, "total_steps": 16520, "loss": 0.0941, "lr": 0.0007684270070519439, "epoch": 7.754237288135593, "percentage": 38.77, "elapsed_time": "0:21:26", "remaining_time": "0:33:50", "throughput": 2040.09, "total_tokens": 2623680}
{"current_steps": 6410, "total_steps": 16520, "loss": 0.0307, "lr": 0.0007679811881613483, "epoch": 7.760290556900727, "percentage": 38.8, "elapsed_time": "0:21:27", "remaining_time": "0:33:49", "throughput": 2040.14, "total_tokens": 2625728}
{"current_steps": 6415, "total_steps": 16520, "loss": 0.1365, "lr": 0.000767535070155254, "epoch": 7.766343825665859, "percentage": 38.83, "elapsed_time": "0:21:27", "remaining_time": "0:33:48", "throughput": 2040.21, "total_tokens": 2627744}
{"current_steps": 6420, "total_steps": 16520, "loss": 0.0869, "lr": 0.0007670886535316086, "epoch": 7.772397094430993, "percentage": 38.86, "elapsed_time": "0:21:28", "remaining_time": "0:33:47", "throughput": 2040.3, "total_tokens": 2629856}
{"current_steps": 6425, "total_steps": 16520, "loss": 0.071, "lr": 0.0007666419387886945, "epoch": 7.778450363196126, "percentage": 38.89, "elapsed_time": "0:21:29", "remaining_time": "0:33:46", "throughput": 2040.37, "total_tokens": 2631936}
{"current_steps": 6430, "total_steps": 16520, "loss": 0.0758, "lr": 0.0007661949264251261, "epoch": 7.784503631961259, "percentage": 38.92, "elapsed_time": "0:21:30", "remaining_time": "0:33:45", "throughput": 2040.43, "total_tokens": 2633984}
{"current_steps": 6435, "total_steps": 16520, "loss": 0.0648, "lr": 0.0007657476169398497, "epoch": 7.790556900726393, "percentage": 38.95, "elapsed_time": "0:21:31", "remaining_time": "0:33:44", "throughput": 2040.57, "total_tokens": 2636192}
{"current_steps": 6440, "total_steps": 16520, "loss": 0.069, "lr": 0.0007653000108321442, "epoch": 7.796610169491525, "percentage": 38.98, "elapsed_time": "0:21:32", "remaining_time": "0:33:43", "throughput": 2040.69, "total_tokens": 2638336}
{"current_steps": 6445, "total_steps": 16520, "loss": 0.0574, "lr": 0.0007648521086016185, "epoch": 7.802663438256658, "percentage": 39.01, "elapsed_time": "0:21:33", "remaining_time": "0:33:42", "throughput": 2040.68, "total_tokens": 2640288}
{"current_steps": 6450, "total_steps": 16520, "loss": 0.1027, "lr": 0.0007644039107482128, "epoch": 7.808716707021792, "percentage": 39.04, "elapsed_time": "0:21:34", "remaining_time": "0:33:41", "throughput": 2040.73, "total_tokens": 2642336}
{"current_steps": 6455, "total_steps": 16520, "loss": 0.0161, "lr": 0.000763955417772197, "epoch": 7.814769975786925, "percentage": 39.07, "elapsed_time": "0:21:35", "remaining_time": "0:33:40", "throughput": 2040.87, "total_tokens": 2644512}
{"current_steps": 6460, "total_steps": 16520, "loss": 0.055, "lr": 0.0007635066301741703, "epoch": 7.8208232445520585, "percentage": 39.1, "elapsed_time": "0:21:36", "remaining_time": "0:33:39", "throughput": 2040.98, "total_tokens": 2646592}
{"current_steps": 6465, "total_steps": 16520, "loss": 0.0582, "lr": 0.000763057548455061, "epoch": 7.826876513317191, "percentage": 39.13, "elapsed_time": "0:21:37", "remaining_time": "0:33:38", "throughput": 2041.1, "total_tokens": 2648736}
{"current_steps": 6470, "total_steps": 16520, "loss": 0.0508, "lr": 0.0007626081731161254, "epoch": 7.832929782082324, "percentage": 39.16, "elapsed_time": "0:21:38", "remaining_time": "0:33:37", "throughput": 2041.18, "total_tokens": 2650816}
{"current_steps": 6475, "total_steps": 16520, "loss": 0.1816, "lr": 0.000762158504658948, "epoch": 7.838983050847458, "percentage": 39.19, "elapsed_time": "0:21:39", "remaining_time": "0:33:36", "throughput": 2041.21, "total_tokens": 2652704}
{"current_steps": 6480, "total_steps": 16520, "loss": 0.051, "lr": 0.0007617085435854398, "epoch": 7.845036319612591, "percentage": 39.23, "elapsed_time": "0:21:40", "remaining_time": "0:33:35", "throughput": 2041.24, "total_tokens": 2654720}
{"current_steps": 6485, "total_steps": 16520, "loss": 0.0528, "lr": 0.0007612582903978391, "epoch": 7.851089588377724, "percentage": 39.26, "elapsed_time": "0:21:41", "remaining_time": "0:33:33", "throughput": 2041.25, "total_tokens": 2656640}
{"current_steps": 6490, "total_steps": 16520, "loss": 0.0486, "lr": 0.0007608077455987099, "epoch": 7.857142857142857, "percentage": 39.29, "elapsed_time": "0:21:42", "remaining_time": "0:33:32", "throughput": 2041.34, "total_tokens": 2658752}
{"current_steps": 6495, "total_steps": 16520, "loss": 0.0911, "lr": 0.0007603569096909413, "epoch": 7.86319612590799, "percentage": 39.32, "elapsed_time": "0:21:43", "remaining_time": "0:33:31", "throughput": 2041.36, "total_tokens": 2660704}
{"current_steps": 6500, "total_steps": 16520, "loss": 0.0273, "lr": 0.0007599057831777483, "epoch": 7.8692493946731235, "percentage": 39.35, "elapsed_time": "0:21:44", "remaining_time": "0:33:30", "throughput": 2041.45, "total_tokens": 2662816}
{"current_steps": 6505, "total_steps": 16520, "loss": 0.0603, "lr": 0.0007594543665626694, "epoch": 7.875302663438257, "percentage": 39.38, "elapsed_time": "0:21:45", "remaining_time": "0:33:29", "throughput": 2041.5, "total_tokens": 2664800}
{"current_steps": 6510, "total_steps": 16520, "loss": 0.0329, "lr": 0.0007590026603495674, "epoch": 7.88135593220339, "percentage": 39.41, "elapsed_time": "0:21:46", "remaining_time": "0:33:28", "throughput": 2041.53, "total_tokens": 2666816}
{"current_steps": 6515, "total_steps": 16520, "loss": 0.0298, "lr": 0.000758550665042628, "epoch": 7.8874092009685235, "percentage": 39.44, "elapsed_time": "0:21:47", "remaining_time": "0:33:27", "throughput": 2041.64, "total_tokens": 2668864}
{"current_steps": 6520, "total_steps": 16520, "loss": 0.0659, "lr": 0.00075809838114636, "epoch": 7.893462469733656, "percentage": 39.47, "elapsed_time": "0:21:48", "remaining_time": "0:33:26", "throughput": 2041.69, "total_tokens": 2670912}
{"current_steps": 6525, "total_steps": 16520, "loss": 0.1116, "lr": 0.000757645809165594, "epoch": 7.899515738498789, "percentage": 39.5, "elapsed_time": "0:21:49", "remaining_time": "0:33:25", "throughput": 2041.78, "total_tokens": 2672896}
{"current_steps": 6530, "total_steps": 16520, "loss": 0.097, "lr": 0.0007571929496054819, "epoch": 7.905569007263923, "percentage": 39.53, "elapsed_time": "0:21:50", "remaining_time": "0:33:24", "throughput": 2041.88, "total_tokens": 2674976}
{"current_steps": 6535, "total_steps": 16520, "loss": 0.069, "lr": 0.0007567398029714973, "epoch": 7.911622276029056, "percentage": 39.56, "elapsed_time": "0:21:50", "remaining_time": "0:33:23", "throughput": 2041.91, "total_tokens": 2676928}
{"current_steps": 6540, "total_steps": 16520, "loss": 0.0256, "lr": 0.0007562863697694337, "epoch": 7.917675544794189, "percentage": 39.59, "elapsed_time": "0:21:51", "remaining_time": "0:33:22", "throughput": 2041.96, "total_tokens": 2678912}
{"current_steps": 6545, "total_steps": 16520, "loss": 0.1193, "lr": 0.0007558326505054047, "epoch": 7.923728813559322, "percentage": 39.62, "elapsed_time": "0:21:52", "remaining_time": "0:33:20", "throughput": 2042.01, "total_tokens": 2680896}
{"current_steps": 6550, "total_steps": 16520, "loss": 0.0185, "lr": 0.0007553786456858429, "epoch": 7.929782082324455, "percentage": 39.65, "elapsed_time": "0:21:53", "remaining_time": "0:33:19", "throughput": 2042.04, "total_tokens": 2682784}
{"current_steps": 6555, "total_steps": 16520, "loss": 0.0657, "lr": 0.0007549243558174998, "epoch": 7.9358353510895885, "percentage": 39.68, "elapsed_time": "0:21:54", "remaining_time": "0:33:18", "throughput": 2042.05, "total_tokens": 2684768}
{"current_steps": 6560, "total_steps": 16520, "loss": 0.1477, "lr": 0.0007544697814074455, "epoch": 7.941888619854722, "percentage": 39.71, "elapsed_time": "0:21:55", "remaining_time": "0:33:17", "throughput": 2042.07, "total_tokens": 2686784}
{"current_steps": 6565, "total_steps": 16520, "loss": 0.1259, "lr": 0.0007540149229630671, "epoch": 7.947941888619855, "percentage": 39.74, "elapsed_time": "0:21:56", "remaining_time": "0:33:16", "throughput": 2042.25, "total_tokens": 2689024}
{"current_steps": 6570, "total_steps": 16520, "loss": 0.0972, "lr": 0.0007535597809920687, "epoch": 7.953995157384988, "percentage": 39.77, "elapsed_time": "0:21:57", "remaining_time": "0:33:15", "throughput": 2042.28, "total_tokens": 2690976}
{"current_steps": 6575, "total_steps": 16520, "loss": 0.033, "lr": 0.0007531043560024713, "epoch": 7.960048426150121, "percentage": 39.8, "elapsed_time": "0:21:58", "remaining_time": "0:33:14", "throughput": 2042.43, "total_tokens": 2693120}
{"current_steps": 6580, "total_steps": 16520, "loss": 0.0608, "lr": 0.0007526486485026118, "epoch": 7.966101694915254, "percentage": 39.83, "elapsed_time": "0:21:59", "remaining_time": "0:33:13", "throughput": 2042.55, "total_tokens": 2695296}
{"current_steps": 6585, "total_steps": 16520, "loss": 0.0439, "lr": 0.0007521926590011419, "epoch": 7.972154963680388, "percentage": 39.86, "elapsed_time": "0:22:00", "remaining_time": "0:33:12", "throughput": 2042.58, "total_tokens": 2697312}
{"current_steps": 6590, "total_steps": 16520, "loss": 0.0378, "lr": 0.0007517363880070284, "epoch": 7.978208232445521, "percentage": 39.89, "elapsed_time": "0:22:01", "remaining_time": "0:33:11", "throughput": 2042.63, "total_tokens": 2699360}
{"current_steps": 6595, "total_steps": 16520, "loss": 0.0285, "lr": 0.0007512798360295525, "epoch": 7.9842615012106535, "percentage": 39.92, "elapsed_time": "0:22:02", "remaining_time": "0:33:10", "throughput": 2042.68, "total_tokens": 2701344}
{"current_steps": 6600, "total_steps": 16520, "loss": 0.0347, "lr": 0.000750823003578309, "epoch": 7.990314769975787, "percentage": 39.95, "elapsed_time": "0:22:03", "remaining_time": "0:33:09", "throughput": 2042.81, "total_tokens": 2703520}
{"current_steps": 6605, "total_steps": 16520, "loss": 0.1207, "lr": 0.0007503658911632051, "epoch": 7.99636803874092, "percentage": 39.98, "elapsed_time": "0:22:04", "remaining_time": "0:33:08", "throughput": 2042.91, "total_tokens": 2705632}
{"current_steps": 6608, "total_steps": 16520, "eval_loss": 0.097122423350811, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:22:12", "remaining_time": "0:33:19", "throughput": 2030.62, "total_tokens": 2706552}
{"current_steps": 6610, "total_steps": 16520, "loss": 0.0133, "lr": 0.0007499084992944611, "epoch": 8.002421307506053, "percentage": 40.01, "elapsed_time": "0:22:14", "remaining_time": "0:33:20", "throughput": 2029.23, "total_tokens": 2707256}
{"current_steps": 6615, "total_steps": 16520, "loss": 0.0805, "lr": 0.0007494508284826093, "epoch": 8.008474576271187, "percentage": 40.04, "elapsed_time": "0:22:15", "remaining_time": "0:33:19", "throughput": 2029.31, "total_tokens": 2709496}
{"current_steps": 6620, "total_steps": 16520, "loss": 0.0559, "lr": 0.000748992879238493, "epoch": 8.01452784503632, "percentage": 40.07, "elapsed_time": "0:22:16", "remaining_time": "0:33:18", "throughput": 2029.4, "total_tokens": 2711544}
{"current_steps": 6625, "total_steps": 16520, "loss": 0.0269, "lr": 0.0007485346520732665, "epoch": 8.020581113801454, "percentage": 40.1, "elapsed_time": "0:22:17", "remaining_time": "0:33:17", "throughput": 2029.44, "total_tokens": 2713560}
{"current_steps": 6630, "total_steps": 16520, "loss": 0.0724, "lr": 0.0007480761474983942, "epoch": 8.026634382566586, "percentage": 40.13, "elapsed_time": "0:22:18", "remaining_time": "0:33:16", "throughput": 2029.48, "total_tokens": 2715576}
{"current_steps": 6635, "total_steps": 16520, "loss": 0.0366, "lr": 0.0007476173660256501, "epoch": 8.032687651331718, "percentage": 40.16, "elapsed_time": "0:22:19", "remaining_time": "0:33:14", "throughput": 2029.62, "total_tokens": 2717816}
{"current_steps": 6640, "total_steps": 16520, "loss": 0.0464, "lr": 0.0007471583081671175, "epoch": 8.038740920096853, "percentage": 40.19, "elapsed_time": "0:22:20", "remaining_time": "0:33:13", "throughput": 2029.71, "total_tokens": 2719864}
{"current_steps": 6645, "total_steps": 16520, "loss": 0.0591, "lr": 0.000746698974435188, "epoch": 8.044794188861985, "percentage": 40.22, "elapsed_time": "0:22:20", "remaining_time": "0:33:12", "throughput": 2029.73, "total_tokens": 2721720}
{"current_steps": 6650, "total_steps": 16520, "loss": 0.0583, "lr": 0.000746239365342561, "epoch": 8.05084745762712, "percentage": 40.25, "elapsed_time": "0:22:21", "remaining_time": "0:33:11", "throughput": 2029.85, "total_tokens": 2723800}
{"current_steps": 6655, "total_steps": 16520, "loss": 0.0279, "lr": 0.0007457794814022435, "epoch": 8.056900726392252, "percentage": 40.28, "elapsed_time": "0:22:22", "remaining_time": "0:33:10", "throughput": 2029.9, "total_tokens": 2725848}
{"current_steps": 6660, "total_steps": 16520, "loss": 0.0286, "lr": 0.0007453193231275493, "epoch": 8.062953995157384, "percentage": 40.31, "elapsed_time": "0:22:23", "remaining_time": "0:33:09", "throughput": 2029.96, "total_tokens": 2727832}
{"current_steps": 6665, "total_steps": 16520, "loss": 0.063, "lr": 0.0007448588910320983, "epoch": 8.069007263922519, "percentage": 40.35, "elapsed_time": "0:22:24", "remaining_time": "0:33:08", "throughput": 2029.97, "total_tokens": 2729752}
{"current_steps": 6670, "total_steps": 16520, "loss": 0.0315, "lr": 0.0007443981856298158, "epoch": 8.075060532687651, "percentage": 40.38, "elapsed_time": "0:22:25", "remaining_time": "0:33:07", "throughput": 2030.07, "total_tokens": 2731864}
{"current_steps": 6675, "total_steps": 16520, "loss": 0.0438, "lr": 0.0007439372074349328, "epoch": 8.081113801452785, "percentage": 40.41, "elapsed_time": "0:22:26", "remaining_time": "0:33:06", "throughput": 2030.06, "total_tokens": 2733816}
{"current_steps": 6680, "total_steps": 16520, "loss": 0.0443, "lr": 0.000743475956961984, "epoch": 8.087167070217918, "percentage": 40.44, "elapsed_time": "0:22:27", "remaining_time": "0:33:05", "throughput": 2030.14, "total_tokens": 2735832}
{"current_steps": 6685, "total_steps": 16520, "loss": 0.0196, "lr": 0.0007430144347258087, "epoch": 8.09322033898305, "percentage": 40.47, "elapsed_time": "0:22:28", "remaining_time": "0:33:04", "throughput": 2030.28, "total_tokens": 2738040}
{"current_steps": 6690, "total_steps": 16520, "loss": 0.0313, "lr": 0.0007425526412415488, "epoch": 8.099273607748184, "percentage": 40.5, "elapsed_time": "0:22:29", "remaining_time": "0:33:03", "throughput": 2030.34, "total_tokens": 2740088}
{"current_steps": 6695, "total_steps": 16520, "loss": 0.0142, "lr": 0.0007420905770246499, "epoch": 8.105326876513317, "percentage": 40.53, "elapsed_time": "0:22:30", "remaining_time": "0:33:01", "throughput": 2030.43, "total_tokens": 2742136}
{"current_steps": 6700, "total_steps": 16520, "loss": 0.1802, "lr": 0.0007416282425908589, "epoch": 8.111380145278451, "percentage": 40.56, "elapsed_time": "0:22:31", "remaining_time": "0:33:00", "throughput": 2030.54, "total_tokens": 2744216}
{"current_steps": 6705, "total_steps": 16520, "loss": 0.0745, "lr": 0.0007411656384562251, "epoch": 8.117433414043584, "percentage": 40.59, "elapsed_time": "0:22:32", "remaining_time": "0:32:59", "throughput": 2030.6, "total_tokens": 2746200}
{"current_steps": 6710, "total_steps": 16520, "loss": 0.0166, "lr": 0.0007407027651370979, "epoch": 8.123486682808716, "percentage": 40.62, "elapsed_time": "0:22:33", "remaining_time": "0:32:58", "throughput": 2030.65, "total_tokens": 2748248}
{"current_steps": 6715, "total_steps": 16520, "loss": 0.1347, "lr": 0.000740239623150128, "epoch": 8.12953995157385, "percentage": 40.65, "elapsed_time": "0:22:34", "remaining_time": "0:32:57", "throughput": 2030.73, "total_tokens": 2750296}
{"current_steps": 6720, "total_steps": 16520, "loss": 0.0719, "lr": 0.0007397762130122657, "epoch": 8.135593220338983, "percentage": 40.68, "elapsed_time": "0:22:35", "remaining_time": "0:32:56", "throughput": 2030.79, "total_tokens": 2752280}
{"current_steps": 6725, "total_steps": 16520, "loss": 0.1247, "lr": 0.0007393125352407605, "epoch": 8.141646489104117, "percentage": 40.71, "elapsed_time": "0:22:36", "remaining_time": "0:32:55", "throughput": 2030.89, "total_tokens": 2754424}
{"current_steps": 6730, "total_steps": 16520, "loss": 0.055, "lr": 0.0007388485903531606, "epoch": 8.14769975786925, "percentage": 40.74, "elapsed_time": "0:22:37", "remaining_time": "0:32:54", "throughput": 2030.89, "total_tokens": 2756312}
{"current_steps": 6735, "total_steps": 16520, "loss": 0.0578, "lr": 0.0007383843788673125, "epoch": 8.153753026634382, "percentage": 40.77, "elapsed_time": "0:22:38", "remaining_time": "0:32:53", "throughput": 2030.92, "total_tokens": 2758328}
{"current_steps": 6740, "total_steps": 16520, "loss": 0.0675, "lr": 0.0007379199013013604, "epoch": 8.159806295399516, "percentage": 40.8, "elapsed_time": "0:22:39", "remaining_time": "0:32:52", "throughput": 2030.84, "total_tokens": 2760408}
{"current_steps": 6745, "total_steps": 16520, "loss": 0.0406, "lr": 0.0007374551581737451, "epoch": 8.165859564164649, "percentage": 40.83, "elapsed_time": "0:22:40", "remaining_time": "0:32:51", "throughput": 2030.85, "total_tokens": 2762392}
{"current_steps": 6750, "total_steps": 16520, "loss": 0.0255, "lr": 0.0007369901500032042, "epoch": 8.171912832929783, "percentage": 40.86, "elapsed_time": "0:22:41", "remaining_time": "0:32:50", "throughput": 2030.97, "total_tokens": 2764472}
{"current_steps": 6755, "total_steps": 16520, "loss": 0.0376, "lr": 0.0007365248773087707, "epoch": 8.177966101694915, "percentage": 40.89, "elapsed_time": "0:22:42", "remaining_time": "0:32:49", "throughput": 2031.05, "total_tokens": 2766552}
{"current_steps": 6760, "total_steps": 16520, "loss": 0.0467, "lr": 0.0007360593406097734, "epoch": 8.184019370460048, "percentage": 40.92, "elapsed_time": "0:22:43", "remaining_time": "0:32:48", "throughput": 2031.14, "total_tokens": 2768664}
{"current_steps": 6765, "total_steps": 16520, "loss": 0.1073, "lr": 0.0007355935404258354, "epoch": 8.190072639225182, "percentage": 40.95, "elapsed_time": "0:22:44", "remaining_time": "0:32:46", "throughput": 2031.26, "total_tokens": 2770744}
{"current_steps": 6770, "total_steps": 16520, "loss": 0.0588, "lr": 0.0007351274772768739, "epoch": 8.196125907990314, "percentage": 40.98, "elapsed_time": "0:22:44", "remaining_time": "0:32:45", "throughput": 2031.27, "total_tokens": 2772664}
{"current_steps": 6775, "total_steps": 16520, "loss": 0.0495, "lr": 0.0007346611516830997, "epoch": 8.202179176755449, "percentage": 41.01, "elapsed_time": "0:22:45", "remaining_time": "0:32:44", "throughput": 2031.35, "total_tokens": 2774744}
{"current_steps": 6780, "total_steps": 16520, "loss": 0.0149, "lr": 0.0007341945641650169, "epoch": 8.208232445520581, "percentage": 41.04, "elapsed_time": "0:22:46", "remaining_time": "0:32:43", "throughput": 2031.48, "total_tokens": 2776920}
{"current_steps": 6785, "total_steps": 16520, "loss": 0.0125, "lr": 0.0007337277152434211, "epoch": 8.214285714285714, "percentage": 41.07, "elapsed_time": "0:22:47", "remaining_time": "0:32:42", "throughput": 2031.6, "total_tokens": 2779064}
{"current_steps": 6790, "total_steps": 16520, "loss": 0.0587, "lr": 0.0007332606054394006, "epoch": 8.220338983050848, "percentage": 41.1, "elapsed_time": "0:22:48", "remaining_time": "0:32:41", "throughput": 2031.7, "total_tokens": 2781176}
{"current_steps": 6795, "total_steps": 16520, "loss": 0.0185, "lr": 0.000732793235274334, "epoch": 8.22639225181598, "percentage": 41.13, "elapsed_time": "0:22:49", "remaining_time": "0:32:40", "throughput": 2031.79, "total_tokens": 2783288}
{"current_steps": 6800, "total_steps": 16520, "loss": 0.0173, "lr": 0.0007323256052698915, "epoch": 8.232445520581114, "percentage": 41.16, "elapsed_time": "0:22:50", "remaining_time": "0:32:39", "throughput": 2031.88, "total_tokens": 2785400}
{"current_steps": 6805, "total_steps": 16520, "loss": 0.0673, "lr": 0.0007318577159480327, "epoch": 8.238498789346247, "percentage": 41.19, "elapsed_time": "0:22:51", "remaining_time": "0:32:38", "throughput": 2031.95, "total_tokens": 2787480}
{"current_steps": 6810, "total_steps": 16520, "loss": 0.0111, "lr": 0.0007313895678310064, "epoch": 8.24455205811138, "percentage": 41.22, "elapsed_time": "0:22:52", "remaining_time": "0:32:37", "throughput": 2032.05, "total_tokens": 2789528}
{"current_steps": 6815, "total_steps": 16520, "loss": 0.1154, "lr": 0.0007309211614413508, "epoch": 8.250605326876514, "percentage": 41.25, "elapsed_time": "0:22:53", "remaining_time": "0:32:36", "throughput": 2032.1, "total_tokens": 2791576}
{"current_steps": 6820, "total_steps": 16520, "loss": 0.0711, "lr": 0.0007304524973018923, "epoch": 8.256658595641646, "percentage": 41.28, "elapsed_time": "0:22:54", "remaining_time": "0:32:35", "throughput": 2032.24, "total_tokens": 2793688}
{"current_steps": 6825, "total_steps": 16520, "loss": 0.0742, "lr": 0.0007299835759357449, "epoch": 8.26271186440678, "percentage": 41.31, "elapsed_time": "0:22:55", "remaining_time": "0:32:34", "throughput": 2032.33, "total_tokens": 2795736}
{"current_steps": 6830, "total_steps": 16520, "loss": 0.0066, "lr": 0.0007295143978663095, "epoch": 8.268765133171913, "percentage": 41.34, "elapsed_time": "0:22:56", "remaining_time": "0:32:33", "throughput": 2032.43, "total_tokens": 2797848}
{"current_steps": 6835, "total_steps": 16520, "loss": 0.1225, "lr": 0.000729044963617274, "epoch": 8.274818401937045, "percentage": 41.37, "elapsed_time": "0:22:57", "remaining_time": "0:32:31", "throughput": 2032.5, "total_tokens": 2799928}
{"current_steps": 6840, "total_steps": 16520, "loss": 0.0291, "lr": 0.0007285752737126117, "epoch": 8.28087167070218, "percentage": 41.4, "elapsed_time": "0:22:58", "remaining_time": "0:32:30", "throughput": 2032.54, "total_tokens": 2801944}
{"current_steps": 6845, "total_steps": 16520, "loss": 0.0906, "lr": 0.0007281053286765816, "epoch": 8.286924939467312, "percentage": 41.43, "elapsed_time": "0:22:59", "remaining_time": "0:32:29", "throughput": 2032.62, "total_tokens": 2804024}
{"current_steps": 6850, "total_steps": 16520, "loss": 0.0548, "lr": 0.0007276351290337274, "epoch": 8.292978208232446, "percentage": 41.46, "elapsed_time": "0:23:00", "remaining_time": "0:32:28", "throughput": 2032.74, "total_tokens": 2806200}
{"current_steps": 6855, "total_steps": 16520, "loss": 0.0337, "lr": 0.0007271646753088769, "epoch": 8.299031476997579, "percentage": 41.5, "elapsed_time": "0:23:01", "remaining_time": "0:32:27", "throughput": 2032.75, "total_tokens": 2808184}
{"current_steps": 6860, "total_steps": 16520, "loss": 0.0581, "lr": 0.000726693968027142, "epoch": 8.305084745762711, "percentage": 41.53, "elapsed_time": "0:23:02", "remaining_time": "0:32:26", "throughput": 2032.8, "total_tokens": 2810104}
{"current_steps": 6865, "total_steps": 16520, "loss": 0.0785, "lr": 0.0007262230077139169, "epoch": 8.311138014527845, "percentage": 41.56, "elapsed_time": "0:23:03", "remaining_time": "0:32:25", "throughput": 2032.84, "total_tokens": 2812120}
{"current_steps": 6870, "total_steps": 16520, "loss": 0.0719, "lr": 0.0007257517948948784, "epoch": 8.317191283292978, "percentage": 41.59, "elapsed_time": "0:23:04", "remaining_time": "0:32:24", "throughput": 2032.93, "total_tokens": 2814232}
{"current_steps": 6875, "total_steps": 16520, "loss": 0.0615, "lr": 0.0007252803300959855, "epoch": 8.323244552058112, "percentage": 41.62, "elapsed_time": "0:23:05", "remaining_time": "0:32:23", "throughput": 2032.98, "total_tokens": 2816216}
{"current_steps": 6880, "total_steps": 16520, "loss": 0.0451, "lr": 0.0007248086138434782, "epoch": 8.329297820823244, "percentage": 41.65, "elapsed_time": "0:23:06", "remaining_time": "0:32:22", "throughput": 2033.06, "total_tokens": 2818296}
{"current_steps": 6885, "total_steps": 16520, "loss": 0.0917, "lr": 0.0007243366466638771, "epoch": 8.335351089588377, "percentage": 41.68, "elapsed_time": "0:23:07", "remaining_time": "0:32:21", "throughput": 2033.13, "total_tokens": 2820312}
{"current_steps": 6890, "total_steps": 16520, "loss": 0.0487, "lr": 0.0007238644290839829, "epoch": 8.341404358353511, "percentage": 41.71, "elapsed_time": "0:23:08", "remaining_time": "0:32:20", "throughput": 2033.28, "total_tokens": 2822520}
{"current_steps": 6895, "total_steps": 16520, "loss": 0.034, "lr": 0.0007233919616308762, "epoch": 8.347457627118644, "percentage": 41.74, "elapsed_time": "0:23:09", "remaining_time": "0:32:19", "throughput": 2033.44, "total_tokens": 2824696}
{"current_steps": 6900, "total_steps": 16520, "loss": 0.0132, "lr": 0.000722919244831916, "epoch": 8.353510895883778, "percentage": 41.77, "elapsed_time": "0:23:10", "remaining_time": "0:32:18", "throughput": 2033.54, "total_tokens": 2826744}
{"current_steps": 6905, "total_steps": 16520, "loss": 0.0194, "lr": 0.0007224462792147396, "epoch": 8.35956416464891, "percentage": 41.8, "elapsed_time": "0:23:11", "remaining_time": "0:32:16", "throughput": 2033.59, "total_tokens": 2828792}
{"current_steps": 6910, "total_steps": 16520, "loss": 0.0552, "lr": 0.0007219730653072625, "epoch": 8.365617433414043, "percentage": 41.83, "elapsed_time": "0:23:11", "remaining_time": "0:32:15", "throughput": 2033.71, "total_tokens": 2830904}
{"current_steps": 6915, "total_steps": 16520, "loss": 0.0355, "lr": 0.0007214996036376769, "epoch": 8.371670702179177, "percentage": 41.86, "elapsed_time": "0:23:12", "remaining_time": "0:32:14", "throughput": 2033.78, "total_tokens": 2832984}
{"current_steps": 6920, "total_steps": 16520, "loss": 0.0251, "lr": 0.0007210258947344517, "epoch": 8.37772397094431, "percentage": 41.89, "elapsed_time": "0:23:13", "remaining_time": "0:32:13", "throughput": 2033.86, "total_tokens": 2835000}
{"current_steps": 6925, "total_steps": 16520, "loss": 0.0654, "lr": 0.0007205519391263319, "epoch": 8.383777239709444, "percentage": 41.92, "elapsed_time": "0:23:14", "remaining_time": "0:32:12", "throughput": 2033.91, "total_tokens": 2837048}
{"current_steps": 6930, "total_steps": 16520, "loss": 0.0435, "lr": 0.0007200777373423375, "epoch": 8.389830508474576, "percentage": 41.95, "elapsed_time": "0:23:15", "remaining_time": "0:32:11", "throughput": 2034.0, "total_tokens": 2839160}
{"current_steps": 6935, "total_steps": 16520, "loss": 0.129, "lr": 0.0007196032899117635, "epoch": 8.39588377723971, "percentage": 41.98, "elapsed_time": "0:23:16", "remaining_time": "0:32:10", "throughput": 2034.06, "total_tokens": 2841208}
{"current_steps": 6940, "total_steps": 16520, "loss": 0.0236, "lr": 0.0007191285973641795, "epoch": 8.401937046004843, "percentage": 42.01, "elapsed_time": "0:23:17", "remaining_time": "0:32:09", "throughput": 2034.15, "total_tokens": 2843320}
{"current_steps": 6945, "total_steps": 16520, "loss": 0.0907, "lr": 0.0007186536602294277, "epoch": 8.407990314769975, "percentage": 42.04, "elapsed_time": "0:23:18", "remaining_time": "0:32:08", "throughput": 2034.24, "total_tokens": 2845368}
{"current_steps": 6950, "total_steps": 16520, "loss": 0.0522, "lr": 0.0007181784790376243, "epoch": 8.41404358353511, "percentage": 42.07, "elapsed_time": "0:23:19", "remaining_time": "0:32:07", "throughput": 2034.31, "total_tokens": 2847384}
{"current_steps": 6955, "total_steps": 16520, "loss": 0.0665, "lr": 0.0007177030543191573, "epoch": 8.420096852300242, "percentage": 42.1, "elapsed_time": "0:23:20", "remaining_time": "0:32:06", "throughput": 2034.36, "total_tokens": 2849368}
{"current_steps": 6960, "total_steps": 16520, "loss": 0.043, "lr": 0.0007172273866046869, "epoch": 8.426150121065376, "percentage": 42.13, "elapsed_time": "0:23:21", "remaining_time": "0:32:05", "throughput": 2034.43, "total_tokens": 2851384}
{"current_steps": 6965, "total_steps": 16520, "loss": 0.0457, "lr": 0.0007167514764251442, "epoch": 8.432203389830509, "percentage": 42.16, "elapsed_time": "0:23:22", "remaining_time": "0:32:04", "throughput": 2034.43, "total_tokens": 2853336}
{"current_steps": 6970, "total_steps": 16520, "loss": 0.0459, "lr": 0.0007162753243117311, "epoch": 8.438256658595641, "percentage": 42.19, "elapsed_time": "0:23:23", "remaining_time": "0:32:02", "throughput": 2034.54, "total_tokens": 2855352}
{"current_steps": 6975, "total_steps": 16520, "loss": 0.0407, "lr": 0.0007157989307959195, "epoch": 8.444309927360775, "percentage": 42.22, "elapsed_time": "0:23:24", "remaining_time": "0:32:01", "throughput": 2034.58, "total_tokens": 2857368}
{"current_steps": 6980, "total_steps": 16520, "loss": 0.0307, "lr": 0.0007153222964094508, "epoch": 8.450363196125908, "percentage": 42.25, "elapsed_time": "0:23:25", "remaining_time": "0:32:00", "throughput": 2034.71, "total_tokens": 2859416}
{"current_steps": 6985, "total_steps": 16520, "loss": 0.0922, "lr": 0.0007148454216843352, "epoch": 8.456416464891042, "percentage": 42.28, "elapsed_time": "0:23:26", "remaining_time": "0:31:59", "throughput": 2034.76, "total_tokens": 2861464}
{"current_steps": 6990, "total_steps": 16520, "loss": 0.0723, "lr": 0.0007143683071528513, "epoch": 8.462469733656174, "percentage": 42.31, "elapsed_time": "0:23:27", "remaining_time": "0:31:58", "throughput": 2034.87, "total_tokens": 2863608}
{"current_steps": 6995, "total_steps": 16520, "loss": 0.0151, "lr": 0.000713890953347545, "epoch": 8.468523002421307, "percentage": 42.34, "elapsed_time": "0:23:28", "remaining_time": "0:31:57", "throughput": 2035.0, "total_tokens": 2865688}
{"current_steps": 7000, "total_steps": 16520, "loss": 0.0483, "lr": 0.0007134133608012299, "epoch": 8.474576271186441, "percentage": 42.37, "elapsed_time": "0:23:29", "remaining_time": "0:31:56", "throughput": 2035.04, "total_tokens": 2867640}
{"current_steps": 7005, "total_steps": 16520, "loss": 0.0498, "lr": 0.0007129355300469854, "epoch": 8.480629539951574, "percentage": 42.4, "elapsed_time": "0:23:30", "remaining_time": "0:31:55", "throughput": 2035.05, "total_tokens": 2869624}
{"current_steps": 7010, "total_steps": 16520, "loss": 0.0202, "lr": 0.0007124574616181573, "epoch": 8.486682808716708, "percentage": 42.43, "elapsed_time": "0:23:31", "remaining_time": "0:31:54", "throughput": 2035.18, "total_tokens": 2871768}
{"current_steps": 7015, "total_steps": 16520, "loss": 0.026, "lr": 0.0007119791560483562, "epoch": 8.49273607748184, "percentage": 42.46, "elapsed_time": "0:23:32", "remaining_time": "0:31:53", "throughput": 2035.25, "total_tokens": 2873784}
{"current_steps": 7020, "total_steps": 16520, "loss": 0.0837, "lr": 0.0007115006138714579, "epoch": 8.498789346246973, "percentage": 42.49, "elapsed_time": "0:23:32", "remaining_time": "0:31:52", "throughput": 2035.3, "total_tokens": 2875832}
{"current_steps": 7025, "total_steps": 16520, "loss": 0.0765, "lr": 0.000711021835621602, "epoch": 8.504842615012107, "percentage": 42.52, "elapsed_time": "0:23:33", "remaining_time": "0:31:51", "throughput": 2035.35, "total_tokens": 2877816}
{"current_steps": 7030, "total_steps": 16520, "loss": 0.0517, "lr": 0.0007105428218331917, "epoch": 8.51089588377724, "percentage": 42.55, "elapsed_time": "0:23:34", "remaining_time": "0:31:50", "throughput": 2035.47, "total_tokens": 2879960}
{"current_steps": 7035, "total_steps": 16520, "loss": 0.0517, "lr": 0.000710063573040893, "epoch": 8.516949152542374, "percentage": 42.58, "elapsed_time": "0:23:35", "remaining_time": "0:31:48", "throughput": 2035.54, "total_tokens": 2882040}
{"current_steps": 7040, "total_steps": 16520, "loss": 0.0365, "lr": 0.0007095840897796342, "epoch": 8.523002421307506, "percentage": 42.62, "elapsed_time": "0:23:36", "remaining_time": "0:31:47", "throughput": 2035.69, "total_tokens": 2884248}
{"current_steps": 7045, "total_steps": 16520, "loss": 0.0951, "lr": 0.0007091043725846055, "epoch": 8.529055690072639, "percentage": 42.65, "elapsed_time": "0:23:37", "remaining_time": "0:31:46", "throughput": 2035.76, "total_tokens": 2886264}
{"current_steps": 7050, "total_steps": 16520, "loss": 0.0381, "lr": 0.0007086244219912583, "epoch": 8.535108958837773, "percentage": 42.68, "elapsed_time": "0:23:38", "remaining_time": "0:31:45", "throughput": 2035.81, "total_tokens": 2888248}
{"current_steps": 7055, "total_steps": 16520, "loss": 0.0264, "lr": 0.0007081442385353041, "epoch": 8.541162227602905, "percentage": 42.71, "elapsed_time": "0:23:39", "remaining_time": "0:31:44", "throughput": 2035.84, "total_tokens": 2890072}
{"current_steps": 7060, "total_steps": 16520, "loss": 0.0752, "lr": 0.0007076638227527142, "epoch": 8.54721549636804, "percentage": 42.74, "elapsed_time": "0:23:40", "remaining_time": "0:31:43", "throughput": 2035.92, "total_tokens": 2892184}
{"current_steps": 7065, "total_steps": 16520, "loss": 0.0995, "lr": 0.0007071831751797202, "epoch": 8.553268765133172, "percentage": 42.77, "elapsed_time": "0:23:41", "remaining_time": "0:31:42", "throughput": 2035.97, "total_tokens": 2894232}
{"current_steps": 7070, "total_steps": 16520, "loss": 0.296, "lr": 0.0007067022963528113, "epoch": 8.559322033898304, "percentage": 42.8, "elapsed_time": "0:23:42", "remaining_time": "0:31:41", "throughput": 2035.99, "total_tokens": 2896216}
{"current_steps": 7075, "total_steps": 16520, "loss": 0.0623, "lr": 0.0007062211868087356, "epoch": 8.565375302663439, "percentage": 42.83, "elapsed_time": "0:23:43", "remaining_time": "0:31:40", "throughput": 2036.0, "total_tokens": 2898072}
{"current_steps": 7080, "total_steps": 16520, "loss": 0.0539, "lr": 0.0007057398470844981, "epoch": 8.571428571428571, "percentage": 42.86, "elapsed_time": "0:23:44", "remaining_time": "0:31:39", "throughput": 2036.05, "total_tokens": 2900056}
{"current_steps": 7085, "total_steps": 16520, "loss": 0.0389, "lr": 0.0007052582777173613, "epoch": 8.577481840193705, "percentage": 42.89, "elapsed_time": "0:23:45", "remaining_time": "0:31:38", "throughput": 2036.11, "total_tokens": 2902072}
{"current_steps": 7090, "total_steps": 16520, "loss": 0.0691, "lr": 0.0007047764792448435, "epoch": 8.583535108958838, "percentage": 42.92, "elapsed_time": "0:23:46", "remaining_time": "0:31:36", "throughput": 2036.2, "total_tokens": 2904120}
{"current_steps": 7095, "total_steps": 16520, "loss": 0.0847, "lr": 0.0007042944522047193, "epoch": 8.58958837772397, "percentage": 42.95, "elapsed_time": "0:23:47", "remaining_time": "0:31:35", "throughput": 2036.26, "total_tokens": 2906136}
{"current_steps": 7100, "total_steps": 16520, "loss": 0.0559, "lr": 0.0007038121971350178, "epoch": 8.595641646489105, "percentage": 42.98, "elapsed_time": "0:23:48", "remaining_time": "0:31:34", "throughput": 2036.34, "total_tokens": 2908120}
{"current_steps": 7105, "total_steps": 16520, "loss": 0.1023, "lr": 0.0007033297145740229, "epoch": 8.601694915254237, "percentage": 43.01, "elapsed_time": "0:23:49", "remaining_time": "0:31:33", "throughput": 2036.43, "total_tokens": 2910232}
{"current_steps": 7110, "total_steps": 16520, "loss": 0.1118, "lr": 0.0007028470050602729, "epoch": 8.607748184019371, "percentage": 43.04, "elapsed_time": "0:23:50", "remaining_time": "0:31:32", "throughput": 2036.52, "total_tokens": 2912344}
{"current_steps": 7115, "total_steps": 16520, "loss": 0.0548, "lr": 0.0007023640691325585, "epoch": 8.613801452784504, "percentage": 43.07, "elapsed_time": "0:23:51", "remaining_time": "0:31:31", "throughput": 2036.59, "total_tokens": 2914424}
{"current_steps": 7120, "total_steps": 16520, "loss": 0.0738, "lr": 0.0007018809073299238, "epoch": 8.619854721549636, "percentage": 43.1, "elapsed_time": "0:23:51", "remaining_time": "0:31:30", "throughput": 2036.67, "total_tokens": 2916408}
{"current_steps": 7125, "total_steps": 16520, "loss": 0.0619, "lr": 0.0007013975201916647, "epoch": 8.62590799031477, "percentage": 43.13, "elapsed_time": "0:23:52", "remaining_time": "0:31:29", "throughput": 2036.74, "total_tokens": 2918232}
{"current_steps": 7130, "total_steps": 16520, "loss": 0.0559, "lr": 0.0007009139082573288, "epoch": 8.631961259079903, "percentage": 43.16, "elapsed_time": "0:23:53", "remaining_time": "0:31:28", "throughput": 2036.8, "total_tokens": 2920248}
{"current_steps": 7135, "total_steps": 16520, "loss": 0.0623, "lr": 0.0007004300720667145, "epoch": 8.638014527845037, "percentage": 43.19, "elapsed_time": "0:23:54", "remaining_time": "0:31:27", "throughput": 2036.83, "total_tokens": 2922200}
{"current_steps": 7140, "total_steps": 16520, "loss": 0.0611, "lr": 0.0006999460121598705, "epoch": 8.64406779661017, "percentage": 43.22, "elapsed_time": "0:23:55", "remaining_time": "0:31:26", "throughput": 2036.9, "total_tokens": 2924280}
{"current_steps": 7145, "total_steps": 16520, "loss": 0.0511, "lr": 0.0006994617290770953, "epoch": 8.650121065375302, "percentage": 43.25, "elapsed_time": "0:23:56", "remaining_time": "0:31:25", "throughput": 2036.95, "total_tokens": 2926360}
{"current_steps": 7150, "total_steps": 16520, "loss": 0.0675, "lr": 0.0006989772233589366, "epoch": 8.656174334140436, "percentage": 43.28, "elapsed_time": "0:23:57", "remaining_time": "0:31:23", "throughput": 2037.06, "total_tokens": 2928504}
{"current_steps": 7155, "total_steps": 16520, "loss": 0.0558, "lr": 0.0006984924955461901, "epoch": 8.662227602905569, "percentage": 43.31, "elapsed_time": "0:23:58", "remaining_time": "0:31:22", "throughput": 2037.11, "total_tokens": 2930488}
{"current_steps": 7160, "total_steps": 16520, "loss": 0.0784, "lr": 0.0006980075461799002, "epoch": 8.668280871670703, "percentage": 43.34, "elapsed_time": "0:23:59", "remaining_time": "0:31:21", "throughput": 2037.25, "total_tokens": 2932664}
{"current_steps": 7165, "total_steps": 16520, "loss": 0.0518, "lr": 0.0006975223758013577, "epoch": 8.674334140435835, "percentage": 43.37, "elapsed_time": "0:24:00", "remaining_time": "0:31:20", "throughput": 2037.38, "total_tokens": 2934840}
{"current_steps": 7170, "total_steps": 16520, "loss": 0.0143, "lr": 0.0006970369849521007, "epoch": 8.680387409200968, "percentage": 43.4, "elapsed_time": "0:24:01", "remaining_time": "0:31:19", "throughput": 2037.43, "total_tokens": 2936824}
{"current_steps": 7175, "total_steps": 16520, "loss": 0.0621, "lr": 0.0006965513741739135, "epoch": 8.686440677966102, "percentage": 43.43, "elapsed_time": "0:24:02", "remaining_time": "0:31:18", "throughput": 2037.54, "total_tokens": 2938936}
{"current_steps": 7180, "total_steps": 16520, "loss": 0.0878, "lr": 0.0006960655440088251, "epoch": 8.692493946731235, "percentage": 43.46, "elapsed_time": "0:24:03", "remaining_time": "0:31:17", "throughput": 2037.63, "total_tokens": 2940920}
{"current_steps": 7185, "total_steps": 16520, "loss": 0.0614, "lr": 0.0006955794949991104, "epoch": 8.698547215496369, "percentage": 43.49, "elapsed_time": "0:24:04", "remaining_time": "0:31:16", "throughput": 2037.68, "total_tokens": 2942968}
{"current_steps": 7190, "total_steps": 16520, "loss": 0.0216, "lr": 0.0006950932276872877, "epoch": 8.704600484261501, "percentage": 43.52, "elapsed_time": "0:24:05", "remaining_time": "0:31:15", "throughput": 2037.73, "total_tokens": 2945016}
{"current_steps": 7195, "total_steps": 16520, "loss": 0.0969, "lr": 0.0006946067426161195, "epoch": 8.710653753026634, "percentage": 43.55, "elapsed_time": "0:24:06", "remaining_time": "0:31:14", "throughput": 2037.79, "total_tokens": 2947032}
{"current_steps": 7200, "total_steps": 16520, "loss": 0.0643, "lr": 0.0006941200403286109, "epoch": 8.716707021791768, "percentage": 43.58, "elapsed_time": "0:24:07", "remaining_time": "0:31:13", "throughput": 2037.85, "total_tokens": 2949080}
{"current_steps": 7205, "total_steps": 16520, "loss": 0.0598, "lr": 0.00069363312136801, "epoch": 8.7227602905569, "percentage": 43.61, "elapsed_time": "0:24:08", "remaining_time": "0:31:12", "throughput": 2037.94, "total_tokens": 2951224}
{"current_steps": 7210, "total_steps": 16520, "loss": 0.0981, "lr": 0.0006931459862778063, "epoch": 8.728813559322035, "percentage": 43.64, "elapsed_time": "0:24:09", "remaining_time": "0:31:11", "throughput": 2037.94, "total_tokens": 2953208}
{"current_steps": 7215, "total_steps": 16520, "loss": 0.051, "lr": 0.0006926586356017309, "epoch": 8.734866828087167, "percentage": 43.67, "elapsed_time": "0:24:10", "remaining_time": "0:31:10", "throughput": 2038.05, "total_tokens": 2955352}
{"current_steps": 7220, "total_steps": 16520, "loss": 0.081, "lr": 0.0006921710698837551, "epoch": 8.7409200968523, "percentage": 43.7, "elapsed_time": "0:24:11", "remaining_time": "0:31:09", "throughput": 2038.16, "total_tokens": 2957496}
{"current_steps": 7225, "total_steps": 16520, "loss": 0.0499, "lr": 0.0006916832896680908, "epoch": 8.746973365617434, "percentage": 43.73, "elapsed_time": "0:24:12", "remaining_time": "0:31:08", "throughput": 2038.22, "total_tokens": 2959512}
{"current_steps": 7230, "total_steps": 16520, "loss": 0.0217, "lr": 0.0006911952954991888, "epoch": 8.753026634382566, "percentage": 43.77, "elapsed_time": "0:24:12", "remaining_time": "0:31:06", "throughput": 2038.27, "total_tokens": 2961432}
{"current_steps": 7235, "total_steps": 16520, "loss": 0.0873, "lr": 0.0006907070879217387, "epoch": 8.7590799031477, "percentage": 43.8, "elapsed_time": "0:24:13", "remaining_time": "0:31:05", "throughput": 2038.35, "total_tokens": 2963480}
{"current_steps": 7240, "total_steps": 16520, "loss": 0.0504, "lr": 0.0006902186674806689, "epoch": 8.765133171912833, "percentage": 43.83, "elapsed_time": "0:24:14", "remaining_time": "0:31:04", "throughput": 2038.4, "total_tokens": 2965528}
{"current_steps": 7245, "total_steps": 16520, "loss": 0.0199, "lr": 0.0006897300347211446, "epoch": 8.771186440677965, "percentage": 43.86, "elapsed_time": "0:24:15", "remaining_time": "0:31:03", "throughput": 2038.43, "total_tokens": 2967480}
{"current_steps": 7250, "total_steps": 16520, "loss": 0.0354, "lr": 0.0006892411901885687, "epoch": 8.7772397094431, "percentage": 43.89, "elapsed_time": "0:24:16", "remaining_time": "0:31:02", "throughput": 2038.53, "total_tokens": 2969624}
{"current_steps": 7255, "total_steps": 16520, "loss": 0.0236, "lr": 0.0006887521344285801, "epoch": 8.783292978208232, "percentage": 43.92, "elapsed_time": "0:24:17", "remaining_time": "0:31:01", "throughput": 2038.65, "total_tokens": 2971800}
{"current_steps": 7260, "total_steps": 16520, "loss": 0.1197, "lr": 0.0006882628679870531, "epoch": 8.789346246973366, "percentage": 43.95, "elapsed_time": "0:24:18", "remaining_time": "0:31:00", "throughput": 2038.7, "total_tokens": 2973848}
{"current_steps": 7265, "total_steps": 16520, "loss": 0.066, "lr": 0.0006877733914100983, "epoch": 8.795399515738499, "percentage": 43.98, "elapsed_time": "0:24:19", "remaining_time": "0:30:59", "throughput": 2038.8, "total_tokens": 2975992}
{"current_steps": 7270, "total_steps": 16520, "loss": 0.0225, "lr": 0.0006872837052440597, "epoch": 8.801452784503631, "percentage": 44.01, "elapsed_time": "0:24:20", "remaining_time": "0:30:58", "throughput": 2038.87, "total_tokens": 2978072}
{"current_steps": 7275, "total_steps": 16520, "loss": 0.1296, "lr": 0.0006867938100355157, "epoch": 8.807506053268765, "percentage": 44.04, "elapsed_time": "0:24:21", "remaining_time": "0:30:57", "throughput": 2038.88, "total_tokens": 2980056}
{"current_steps": 7280, "total_steps": 16520, "loss": 0.0578, "lr": 0.000686303706331278, "epoch": 8.813559322033898, "percentage": 44.07, "elapsed_time": "0:24:22", "remaining_time": "0:30:56", "throughput": 2038.93, "total_tokens": 2982104}
{"current_steps": 7285, "total_steps": 16520, "loss": 0.0438, "lr": 0.000685813394678391, "epoch": 8.819612590799032, "percentage": 44.1, "elapsed_time": "0:24:23", "remaining_time": "0:30:55", "throughput": 2038.96, "total_tokens": 2984120}
{"current_steps": 7290, "total_steps": 16520, "loss": 0.0799, "lr": 0.0006853228756241314, "epoch": 8.825665859564165, "percentage": 44.13, "elapsed_time": "0:24:24", "remaining_time": "0:30:54", "throughput": 2039.06, "total_tokens": 2986200}
{"current_steps": 7295, "total_steps": 16520, "loss": 0.0463, "lr": 0.0006848321497160073, "epoch": 8.831719128329297, "percentage": 44.16, "elapsed_time": "0:24:25", "remaining_time": "0:30:53", "throughput": 2039.22, "total_tokens": 2988408}
{"current_steps": 7300, "total_steps": 16520, "loss": 0.0822, "lr": 0.0006843412175017572, "epoch": 8.837772397094431, "percentage": 44.19, "elapsed_time": "0:24:26", "remaining_time": "0:30:52", "throughput": 2039.24, "total_tokens": 2990392}
{"current_steps": 7305, "total_steps": 16520, "loss": 0.1199, "lr": 0.0006838500795293505, "epoch": 8.843825665859564, "percentage": 44.22, "elapsed_time": "0:24:27", "remaining_time": "0:30:51", "throughput": 2039.31, "total_tokens": 2992472}
{"current_steps": 7310, "total_steps": 16520, "loss": 0.0472, "lr": 0.0006833587363469864, "epoch": 8.849878934624698, "percentage": 44.25, "elapsed_time": "0:24:28", "remaining_time": "0:30:49", "throughput": 2039.37, "total_tokens": 2994424}
{"current_steps": 7315, "total_steps": 16520, "loss": 0.0322, "lr": 0.0006828671885030922, "epoch": 8.85593220338983, "percentage": 44.28, "elapsed_time": "0:24:29", "remaining_time": "0:30:48", "throughput": 2039.36, "total_tokens": 2996312}
{"current_steps": 7320, "total_steps": 16520, "loss": 0.0602, "lr": 0.0006823754365463246, "epoch": 8.861985472154963, "percentage": 44.31, "elapsed_time": "0:24:30", "remaining_time": "0:30:47", "throughput": 2039.42, "total_tokens": 2998392}
{"current_steps": 7325, "total_steps": 16520, "loss": 0.0635, "lr": 0.0006818834810255678, "epoch": 8.868038740920097, "percentage": 44.34, "elapsed_time": "0:24:31", "remaining_time": "0:30:46", "throughput": 2039.52, "total_tokens": 3000536}
{"current_steps": 7330, "total_steps": 16520, "loss": 0.1453, "lr": 0.0006813913224899329, "epoch": 8.87409200968523, "percentage": 44.37, "elapsed_time": "0:24:32", "remaining_time": "0:30:45", "throughput": 2039.64, "total_tokens": 3002648}
{"current_steps": 7335, "total_steps": 16520, "loss": 0.0795, "lr": 0.0006808989614887582, "epoch": 8.880145278450364, "percentage": 44.4, "elapsed_time": "0:24:33", "remaining_time": "0:30:44", "throughput": 2039.75, "total_tokens": 3004792}
{"current_steps": 7340, "total_steps": 16520, "loss": 0.103, "lr": 0.0006804063985716074, "epoch": 8.886198547215496, "percentage": 44.43, "elapsed_time": "0:24:34", "remaining_time": "0:30:43", "throughput": 2039.83, "total_tokens": 3006936}
{"current_steps": 7345, "total_steps": 16520, "loss": 0.047, "lr": 0.0006799136342882701, "epoch": 8.892251815980629, "percentage": 44.46, "elapsed_time": "0:24:35", "remaining_time": "0:30:42", "throughput": 2039.86, "total_tokens": 3008824}
{"current_steps": 7350, "total_steps": 16520, "loss": 0.0233, "lr": 0.0006794206691887603, "epoch": 8.898305084745763, "percentage": 44.49, "elapsed_time": "0:24:36", "remaining_time": "0:30:41", "throughput": 2039.97, "total_tokens": 3011000}
{"current_steps": 7355, "total_steps": 16520, "loss": 0.0438, "lr": 0.0006789275038233163, "epoch": 8.904358353510895, "percentage": 44.52, "elapsed_time": "0:24:36", "remaining_time": "0:30:40", "throughput": 2040.07, "total_tokens": 3013080}
{"current_steps": 7360, "total_steps": 16520, "loss": 0.0203, "lr": 0.0006784341387423996, "epoch": 8.91041162227603, "percentage": 44.55, "elapsed_time": "0:24:37", "remaining_time": "0:30:39", "throughput": 2040.14, "total_tokens": 3015032}
{"current_steps": 7365, "total_steps": 16520, "loss": 0.0434, "lr": 0.0006779405744966955, "epoch": 8.916464891041162, "percentage": 44.58, "elapsed_time": "0:24:38", "remaining_time": "0:30:38", "throughput": 2040.22, "total_tokens": 3017080}
{"current_steps": 7370, "total_steps": 16520, "loss": 0.0176, "lr": 0.0006774468116371106, "epoch": 8.922518159806295, "percentage": 44.61, "elapsed_time": "0:24:39", "remaining_time": "0:30:37", "throughput": 2040.34, "total_tokens": 3019256}
{"current_steps": 7375, "total_steps": 16520, "loss": 0.0166, "lr": 0.0006769528507147736, "epoch": 8.928571428571429, "percentage": 44.64, "elapsed_time": "0:24:40", "remaining_time": "0:30:36", "throughput": 2040.4, "total_tokens": 3021272}
{"current_steps": 7380, "total_steps": 16520, "loss": 0.1433, "lr": 0.000676458692281034, "epoch": 8.934624697336561, "percentage": 44.67, "elapsed_time": "0:24:41", "remaining_time": "0:30:35", "throughput": 2040.43, "total_tokens": 3023224}
{"current_steps": 7385, "total_steps": 16520, "loss": 0.0692, "lr": 0.0006759643368874628, "epoch": 8.940677966101696, "percentage": 44.7, "elapsed_time": "0:24:42", "remaining_time": "0:30:33", "throughput": 2040.48, "total_tokens": 3025272}
{"current_steps": 7390, "total_steps": 16520, "loss": 0.0948, "lr": 0.0006754697850858498, "epoch": 8.946731234866828, "percentage": 44.73, "elapsed_time": "0:24:43", "remaining_time": "0:30:32", "throughput": 2040.52, "total_tokens": 3027256}
{"current_steps": 7395, "total_steps": 16520, "loss": 0.0186, "lr": 0.0006749750374282038, "epoch": 8.95278450363196, "percentage": 44.76, "elapsed_time": "0:24:44", "remaining_time": "0:30:31", "throughput": 2040.56, "total_tokens": 3029272}
{"current_steps": 7400, "total_steps": 16520, "loss": 0.0554, "lr": 0.0006744800944667531, "epoch": 8.958837772397095, "percentage": 44.79, "elapsed_time": "0:24:45", "remaining_time": "0:30:30", "throughput": 2040.62, "total_tokens": 3031352}
{"current_steps": 7405, "total_steps": 16520, "loss": 0.0926, "lr": 0.0006739849567539436, "epoch": 8.964891041162227, "percentage": 44.82, "elapsed_time": "0:24:46", "remaining_time": "0:30:29", "throughput": 2040.65, "total_tokens": 3033368}
{"current_steps": 7410, "total_steps": 16520, "loss": 0.0412, "lr": 0.0006734896248424387, "epoch": 8.970944309927361, "percentage": 44.85, "elapsed_time": "0:24:47", "remaining_time": "0:30:28", "throughput": 2040.69, "total_tokens": 3035416}
{"current_steps": 7415, "total_steps": 16520, "loss": 0.0171, "lr": 0.0006729940992851182, "epoch": 8.976997578692494, "percentage": 44.88, "elapsed_time": "0:24:48", "remaining_time": "0:30:27", "throughput": 2040.75, "total_tokens": 3037496}
{"current_steps": 7420, "total_steps": 16520, "loss": 0.0655, "lr": 0.0006724983806350784, "epoch": 8.983050847457626, "percentage": 44.92, "elapsed_time": "0:24:49", "remaining_time": "0:30:26", "throughput": 2040.86, "total_tokens": 3039608}
{"current_steps": 7425, "total_steps": 16520, "loss": 0.1267, "lr": 0.000672002469445631, "epoch": 8.98910411622276, "percentage": 44.95, "elapsed_time": "0:24:50", "remaining_time": "0:30:25", "throughput": 2040.94, "total_tokens": 3041592}
{"current_steps": 7430, "total_steps": 16520, "loss": 0.0485, "lr": 0.0006715063662703027, "epoch": 8.995157384987893, "percentage": 44.98, "elapsed_time": "0:24:51", "remaining_time": "0:30:24", "throughput": 2040.99, "total_tokens": 3043640}
{"current_steps": 7434, "total_steps": 16520, "eval_loss": 0.09706028550863266, "epoch": 9.0, "percentage": 45.0, "elapsed_time": "0:24:59", "remaining_time": "0:30:33", "throughput": 2030.11, "total_tokens": 3044984}
{"current_steps": 7435, "total_steps": 16520, "loss": 0.0596, "lr": 0.0006710100716628344, "epoch": 9.001210653753027, "percentage": 45.01, "elapsed_time": "0:25:01", "remaining_time": "0:30:34", "throughput": 2028.82, "total_tokens": 3045368}
{"current_steps": 7440, "total_steps": 16520, "loss": 0.0877, "lr": 0.0006705135861771805, "epoch": 9.00726392251816, "percentage": 45.04, "elapsed_time": "0:25:02", "remaining_time": "0:30:33", "throughput": 2028.8, "total_tokens": 3047384}
{"current_steps": 7445, "total_steps": 16520, "loss": 0.0203, "lr": 0.0006700169103675089, "epoch": 9.013317191283292, "percentage": 45.07, "elapsed_time": "0:25:02", "remaining_time": "0:30:32", "throughput": 2028.84, "total_tokens": 3049304}
{"current_steps": 7450, "total_steps": 16520, "loss": 0.0559, "lr": 0.0006695200447881996, "epoch": 9.019370460048426, "percentage": 45.1, "elapsed_time": "0:25:04", "remaining_time": "0:30:31", "throughput": 2028.57, "total_tokens": 3051448}
{"current_steps": 7455, "total_steps": 16520, "loss": 0.0661, "lr": 0.0006690229899938445, "epoch": 9.025423728813559, "percentage": 45.13, "elapsed_time": "0:25:05", "remaining_time": "0:30:30", "throughput": 2028.6, "total_tokens": 3053464}
{"current_steps": 7460, "total_steps": 16520, "loss": 0.0564, "lr": 0.0006685257465392467, "epoch": 9.031476997578693, "percentage": 45.16, "elapsed_time": "0:25:06", "remaining_time": "0:30:29", "throughput": 2028.7, "total_tokens": 3055544}
{"current_steps": 7465, "total_steps": 16520, "loss": 0.0487, "lr": 0.0006680283149794196, "epoch": 9.037530266343826, "percentage": 45.19, "elapsed_time": "0:25:07", "remaining_time": "0:30:28", "throughput": 2028.76, "total_tokens": 3057560}
{"current_steps": 7470, "total_steps": 16520, "loss": 0.0057, "lr": 0.0006675306958695874, "epoch": 9.043583535108958, "percentage": 45.22, "elapsed_time": "0:25:08", "remaining_time": "0:30:27", "throughput": 2028.83, "total_tokens": 3059640}
{"current_steps": 7475, "total_steps": 16520, "loss": 0.0927, "lr": 0.0006670328897651827, "epoch": 9.049636803874092, "percentage": 45.25, "elapsed_time": "0:25:09", "remaining_time": "0:30:26", "throughput": 2028.88, "total_tokens": 3061688}
{"current_steps": 7480, "total_steps": 16520, "loss": 0.033, "lr": 0.0006665348972218469, "epoch": 9.055690072639225, "percentage": 45.28, "elapsed_time": "0:25:10", "remaining_time": "0:30:24", "throughput": 2029.0, "total_tokens": 3063864}
{"current_steps": 7485, "total_steps": 16520, "loss": 0.0078, "lr": 0.0006660367187954304, "epoch": 9.061743341404359, "percentage": 45.31, "elapsed_time": "0:25:11", "remaining_time": "0:30:23", "throughput": 2029.14, "total_tokens": 3066072}
{"current_steps": 7490, "total_steps": 16520, "loss": 0.0616, "lr": 0.0006655383550419902, "epoch": 9.067796610169491, "percentage": 45.34, "elapsed_time": "0:25:12", "remaining_time": "0:30:22", "throughput": 2029.23, "total_tokens": 3068216}
{"current_steps": 7495, "total_steps": 16520, "loss": 0.0315, "lr": 0.0006650398065177905, "epoch": 9.073849878934624, "percentage": 45.37, "elapsed_time": "0:25:12", "remaining_time": "0:30:21", "throughput": 2029.29, "total_tokens": 3070296}
{"current_steps": 7500, "total_steps": 16520, "loss": 0.0173, "lr": 0.0006645410737793015, "epoch": 9.079903147699758, "percentage": 45.4, "elapsed_time": "0:25:13", "remaining_time": "0:30:20", "throughput": 2029.34, "total_tokens": 3072344}
{"current_steps": 7505, "total_steps": 16520, "loss": 0.0332, "lr": 0.0006640421573831994, "epoch": 9.08595641646489, "percentage": 45.43, "elapsed_time": "0:25:14", "remaining_time": "0:30:19", "throughput": 2029.47, "total_tokens": 3074520}
{"current_steps": 7510, "total_steps": 16520, "loss": 0.0337, "lr": 0.000663543057886365, "epoch": 9.092009685230025, "percentage": 45.46, "elapsed_time": "0:25:15", "remaining_time": "0:30:18", "throughput": 2029.5, "total_tokens": 3076472}
{"current_steps": 7515, "total_steps": 16520, "loss": 0.0252, "lr": 0.0006630437758458838, "epoch": 9.098062953995157, "percentage": 45.49, "elapsed_time": "0:25:16", "remaining_time": "0:30:17", "throughput": 2029.58, "total_tokens": 3078584}
{"current_steps": 7520, "total_steps": 16520, "loss": 0.0235, "lr": 0.0006625443118190447, "epoch": 9.104116222760291, "percentage": 45.52, "elapsed_time": "0:25:17", "remaining_time": "0:30:16", "throughput": 2029.63, "total_tokens": 3080568}
{"current_steps": 7525, "total_steps": 16520, "loss": 0.0427, "lr": 0.0006620446663633402, "epoch": 9.110169491525424, "percentage": 45.55, "elapsed_time": "0:25:18", "remaining_time": "0:30:15", "throughput": 2029.68, "total_tokens": 3082616}
{"current_steps": 7530, "total_steps": 16520, "loss": 0.0358, "lr": 0.000661544840036465, "epoch": 9.116222760290556, "percentage": 45.58, "elapsed_time": "0:25:19", "remaining_time": "0:30:14", "throughput": 2029.76, "total_tokens": 3084664}
{"current_steps": 7535, "total_steps": 16520, "loss": 0.0272, "lr": 0.0006610448333963155, "epoch": 9.12227602905569, "percentage": 45.61, "elapsed_time": "0:25:20", "remaining_time": "0:30:13", "throughput": 2029.84, "total_tokens": 3086712}
{"current_steps": 7540, "total_steps": 16520, "loss": 0.046, "lr": 0.0006605446470009899, "epoch": 9.128329297820823, "percentage": 45.64, "elapsed_time": "0:25:21", "remaining_time": "0:30:12", "throughput": 2029.89, "total_tokens": 3088696}
{"current_steps": 7545, "total_steps": 16520, "loss": 0.0852, "lr": 0.0006600442814087865, "epoch": 9.134382566585957, "percentage": 45.67, "elapsed_time": "0:25:22", "remaining_time": "0:30:11", "throughput": 2029.92, "total_tokens": 3090712}
{"current_steps": 7550, "total_steps": 16520, "loss": 0.0543, "lr": 0.0006595437371782039, "epoch": 9.14043583535109, "percentage": 45.7, "elapsed_time": "0:25:23", "remaining_time": "0:30:10", "throughput": 2029.95, "total_tokens": 3092728}
{"current_steps": 7555, "total_steps": 16520, "loss": 0.0955, "lr": 0.0006590430148679399, "epoch": 9.146489104116222, "percentage": 45.73, "elapsed_time": "0:25:24", "remaining_time": "0:30:09", "throughput": 2030.01, "total_tokens": 3094808}
{"current_steps": 7560, "total_steps": 16520, "loss": 0.0104, "lr": 0.0006585421150368914, "epoch": 9.152542372881356, "percentage": 45.76, "elapsed_time": "0:25:25", "remaining_time": "0:30:08", "throughput": 2030.11, "total_tokens": 3096952}
{"current_steps": 7565, "total_steps": 16520, "loss": 0.0247, "lr": 0.0006580410382441533, "epoch": 9.158595641646489, "percentage": 45.79, "elapsed_time": "0:25:26", "remaining_time": "0:30:06", "throughput": 2030.22, "total_tokens": 3099064}
{"current_steps": 7570, "total_steps": 16520, "loss": 0.0291, "lr": 0.0006575397850490179, "epoch": 9.164648910411623, "percentage": 45.82, "elapsed_time": "0:25:27", "remaining_time": "0:30:05", "throughput": 2030.32, "total_tokens": 3101176}
{"current_steps": 7575, "total_steps": 16520, "loss": 0.0964, "lr": 0.0006570383560109745, "epoch": 9.170702179176756, "percentage": 45.85, "elapsed_time": "0:25:28", "remaining_time": "0:30:04", "throughput": 2030.37, "total_tokens": 3103160}
{"current_steps": 7580, "total_steps": 16520, "loss": 0.0123, "lr": 0.0006565367516897084, "epoch": 9.176755447941888, "percentage": 45.88, "elapsed_time": "0:25:29", "remaining_time": "0:30:03", "throughput": 2030.45, "total_tokens": 3105272}
{"current_steps": 7585, "total_steps": 16520, "loss": 0.0522, "lr": 0.0006560349726451012, "epoch": 9.182808716707022, "percentage": 45.91, "elapsed_time": "0:25:30", "remaining_time": "0:30:02", "throughput": 2030.55, "total_tokens": 3107416}
{"current_steps": 7590, "total_steps": 16520, "loss": 0.0428, "lr": 0.0006555330194372288, "epoch": 9.188861985472155, "percentage": 45.94, "elapsed_time": "0:25:31", "remaining_time": "0:30:01", "throughput": 2030.62, "total_tokens": 3109432}
{"current_steps": 7595, "total_steps": 16520, "loss": 0.0518, "lr": 0.000655030892626362, "epoch": 9.194915254237289, "percentage": 45.97, "elapsed_time": "0:25:32", "remaining_time": "0:30:00", "throughput": 2030.63, "total_tokens": 3111352}
{"current_steps": 7600, "total_steps": 16520, "loss": 0.0597, "lr": 0.000654528592772965, "epoch": 9.200968523002421, "percentage": 46.0, "elapsed_time": "0:25:33", "remaining_time": "0:29:59", "throughput": 2030.64, "total_tokens": 3113272}
{"current_steps": 7605, "total_steps": 16520, "loss": 0.063, "lr": 0.0006540261204376953, "epoch": 9.207021791767554, "percentage": 46.04, "elapsed_time": "0:25:34", "remaining_time": "0:29:58", "throughput": 2030.69, "total_tokens": 3115256}
{"current_steps": 7610, "total_steps": 16520, "loss": 0.0179, "lr": 0.0006535234761814033, "epoch": 9.213075060532688, "percentage": 46.07, "elapsed_time": "0:25:35", "remaining_time": "0:29:57", "throughput": 2030.74, "total_tokens": 3117304}
{"current_steps": 7615, "total_steps": 16520, "loss": 0.0677, "lr": 0.0006530206605651307, "epoch": 9.21912832929782, "percentage": 46.1, "elapsed_time": "0:25:36", "remaining_time": "0:29:56", "throughput": 2030.82, "total_tokens": 3119352}
{"current_steps": 7620, "total_steps": 16520, "loss": 0.0111, "lr": 0.0006525176741501108, "epoch": 9.225181598062955, "percentage": 46.13, "elapsed_time": "0:25:36", "remaining_time": "0:29:55", "throughput": 2030.87, "total_tokens": 3121400}
{"current_steps": 7625, "total_steps": 16520, "loss": 0.0105, "lr": 0.0006520145174977674, "epoch": 9.231234866828087, "percentage": 46.16, "elapsed_time": "0:25:37", "remaining_time": "0:29:54", "throughput": 2030.96, "total_tokens": 3123448}
{"current_steps": 7630, "total_steps": 16520, "loss": 0.0468, "lr": 0.0006515111911697143, "epoch": 9.23728813559322, "percentage": 46.19, "elapsed_time": "0:25:38", "remaining_time": "0:29:53", "throughput": 2031.04, "total_tokens": 3125560}
{"current_steps": 7635, "total_steps": 16520, "loss": 0.014, "lr": 0.0006510076957277549, "epoch": 9.243341404358354, "percentage": 46.22, "elapsed_time": "0:25:39", "remaining_time": "0:29:51", "throughput": 2031.11, "total_tokens": 3127576}
{"current_steps": 7640, "total_steps": 16520, "loss": 0.0487, "lr": 0.0006505040317338809, "epoch": 9.249394673123486, "percentage": 46.25, "elapsed_time": "0:25:40", "remaining_time": "0:29:50", "throughput": 2031.23, "total_tokens": 3129720}
{"current_steps": 7645, "total_steps": 16520, "loss": 0.0854, "lr": 0.000650000199750273, "epoch": 9.25544794188862, "percentage": 46.28, "elapsed_time": "0:25:41", "remaining_time": "0:29:49", "throughput": 2031.33, "total_tokens": 3131864}
{"current_steps": 7650, "total_steps": 16520, "loss": 0.0679, "lr": 0.0006494962003392986, "epoch": 9.261501210653753, "percentage": 46.31, "elapsed_time": "0:25:42", "remaining_time": "0:29:48", "throughput": 2031.4, "total_tokens": 3133944}
{"current_steps": 7655, "total_steps": 16520, "loss": 0.0866, "lr": 0.0006489920340635121, "epoch": 9.267554479418886, "percentage": 46.34, "elapsed_time": "0:25:43", "remaining_time": "0:29:47", "throughput": 2031.5, "total_tokens": 3136088}
{"current_steps": 7660, "total_steps": 16520, "loss": 0.0965, "lr": 0.0006484877014856546, "epoch": 9.27360774818402, "percentage": 46.37, "elapsed_time": "0:25:44", "remaining_time": "0:29:46", "throughput": 2031.63, "total_tokens": 3138296}
{"current_steps": 7665, "total_steps": 16520, "loss": 0.0252, "lr": 0.0006479832031686521, "epoch": 9.279661016949152, "percentage": 46.4, "elapsed_time": "0:25:45", "remaining_time": "0:29:45", "throughput": 2031.65, "total_tokens": 3140280}
{"current_steps": 7670, "total_steps": 16520, "loss": 0.0775, "lr": 0.0006474785396756164, "epoch": 9.285714285714286, "percentage": 46.43, "elapsed_time": "0:25:46", "remaining_time": "0:29:44", "throughput": 2031.7, "total_tokens": 3142360}
{"current_steps": 7675, "total_steps": 16520, "loss": 0.0205, "lr": 0.0006469737115698433, "epoch": 9.291767554479419, "percentage": 46.46, "elapsed_time": "0:25:47", "remaining_time": "0:29:43", "throughput": 2031.78, "total_tokens": 3144408}
{"current_steps": 7680, "total_steps": 16520, "loss": 0.0097, "lr": 0.000646468719414812, "epoch": 9.297820823244551, "percentage": 46.49, "elapsed_time": "0:25:48", "remaining_time": "0:29:42", "throughput": 2031.77, "total_tokens": 3146360}
{"current_steps": 7685, "total_steps": 16520, "loss": 0.0648, "lr": 0.0006459635637741852, "epoch": 9.303874092009686, "percentage": 46.52, "elapsed_time": "0:25:49", "remaining_time": "0:29:41", "throughput": 2031.88, "total_tokens": 3148536}
{"current_steps": 7690, "total_steps": 16520, "loss": 0.083, "lr": 0.0006454582452118083, "epoch": 9.309927360774818, "percentage": 46.55, "elapsed_time": "0:25:50", "remaining_time": "0:29:40", "throughput": 2031.95, "total_tokens": 3150616}
{"current_steps": 7695, "total_steps": 16520, "loss": 0.0072, "lr": 0.0006449527642917079, "epoch": 9.315980629539952, "percentage": 46.58, "elapsed_time": "0:25:51", "remaining_time": "0:29:39", "throughput": 2032.01, "total_tokens": 3152568}
{"current_steps": 7700, "total_steps": 16520, "loss": 0.0222, "lr": 0.0006444471215780925, "epoch": 9.322033898305085, "percentage": 46.61, "elapsed_time": "0:25:52", "remaining_time": "0:29:38", "throughput": 2032.06, "total_tokens": 3154616}
{"current_steps": 7705, "total_steps": 16520, "loss": 0.0936, "lr": 0.0006439413176353506, "epoch": 9.328087167070217, "percentage": 46.64, "elapsed_time": "0:25:53", "remaining_time": "0:29:37", "throughput": 2032.08, "total_tokens": 3156568}
{"current_steps": 7710, "total_steps": 16520, "loss": 0.0419, "lr": 0.0006434353530280511, "epoch": 9.334140435835351, "percentage": 46.67, "elapsed_time": "0:25:54", "remaining_time": "0:29:36", "throughput": 2032.14, "total_tokens": 3158584}
{"current_steps": 7715, "total_steps": 16520, "loss": 0.0597, "lr": 0.0006429292283209418, "epoch": 9.340193704600484, "percentage": 46.7, "elapsed_time": "0:25:55", "remaining_time": "0:29:34", "throughput": 2032.13, "total_tokens": 3160472}
{"current_steps": 7720, "total_steps": 16520, "loss": 0.0265, "lr": 0.0006424229440789496, "epoch": 9.346246973365618, "percentage": 46.73, "elapsed_time": "0:25:56", "remaining_time": "0:29:33", "throughput": 2032.21, "total_tokens": 3162520}
{"current_steps": 7725, "total_steps": 16520, "loss": 0.0672, "lr": 0.0006419165008671795, "epoch": 9.35230024213075, "percentage": 46.76, "elapsed_time": "0:25:57", "remaining_time": "0:29:32", "throughput": 2032.29, "total_tokens": 3164632}
{"current_steps": 7730, "total_steps": 16520, "loss": 0.015, "lr": 0.0006414098992509138, "epoch": 9.358353510895883, "percentage": 46.79, "elapsed_time": "0:25:58", "remaining_time": "0:29:31", "throughput": 2032.34, "total_tokens": 3166680}
{"current_steps": 7735, "total_steps": 16520, "loss": 0.0894, "lr": 0.0006409031397956114, "epoch": 9.364406779661017, "percentage": 46.82, "elapsed_time": "0:25:59", "remaining_time": "0:29:30", "throughput": 2032.37, "total_tokens": 3168632}
{"current_steps": 7740, "total_steps": 16520, "loss": 0.0489, "lr": 0.0006403962230669074, "epoch": 9.37046004842615, "percentage": 46.85, "elapsed_time": "0:26:00", "remaining_time": "0:29:29", "throughput": 2032.45, "total_tokens": 3170680}
{"current_steps": 7745, "total_steps": 16520, "loss": 0.0671, "lr": 0.0006398891496306127, "epoch": 9.376513317191284, "percentage": 46.88, "elapsed_time": "0:26:01", "remaining_time": "0:29:28", "throughput": 2032.49, "total_tokens": 3172728}
{"current_steps": 7750, "total_steps": 16520, "loss": 0.0545, "lr": 0.0006393819200527133, "epoch": 9.382566585956416, "percentage": 46.91, "elapsed_time": "0:26:01", "remaining_time": "0:29:27", "throughput": 2032.53, "total_tokens": 3174712}
{"current_steps": 7755, "total_steps": 16520, "loss": 0.0597, "lr": 0.0006388745348993688, "epoch": 9.388619854721549, "percentage": 46.94, "elapsed_time": "0:26:02", "remaining_time": "0:29:26", "throughput": 2032.56, "total_tokens": 3176728}
{"current_steps": 7760, "total_steps": 16520, "loss": 0.1258, "lr": 0.0006383669947369133, "epoch": 9.394673123486683, "percentage": 46.97, "elapsed_time": "0:26:03", "remaining_time": "0:29:25", "throughput": 2032.67, "total_tokens": 3178904}
{"current_steps": 7765, "total_steps": 16520, "loss": 0.0452, "lr": 0.0006378593001318529, "epoch": 9.400726392251816, "percentage": 47.0, "elapsed_time": "0:26:04", "remaining_time": "0:29:24", "throughput": 2032.77, "total_tokens": 3180984}
{"current_steps": 7770, "total_steps": 16520, "loss": 0.076, "lr": 0.0006373514516508672, "epoch": 9.40677966101695, "percentage": 47.03, "elapsed_time": "0:26:05", "remaining_time": "0:29:23", "throughput": 2032.88, "total_tokens": 3183096}
{"current_steps": 7775, "total_steps": 16520, "loss": 0.1046, "lr": 0.0006368434498608066, "epoch": 9.412832929782082, "percentage": 47.06, "elapsed_time": "0:26:06", "remaining_time": "0:29:22", "throughput": 2032.95, "total_tokens": 3185112}
{"current_steps": 7780, "total_steps": 16520, "loss": 0.0287, "lr": 0.0006363352953286932, "epoch": 9.418886198547215, "percentage": 47.09, "elapsed_time": "0:26:07", "remaining_time": "0:29:21", "throughput": 2033.06, "total_tokens": 3187288}
{"current_steps": 7785, "total_steps": 16520, "loss": 0.0803, "lr": 0.0006358269886217194, "epoch": 9.424939467312349, "percentage": 47.12, "elapsed_time": "0:26:08", "remaining_time": "0:29:20", "throughput": 2033.15, "total_tokens": 3189368}
{"current_steps": 7790, "total_steps": 16520, "loss": 0.0381, "lr": 0.0006353185303072475, "epoch": 9.430992736077481, "percentage": 47.15, "elapsed_time": "0:26:09", "remaining_time": "0:29:19", "throughput": 2033.18, "total_tokens": 3191384}
{"current_steps": 7795, "total_steps": 16520, "loss": 0.0244, "lr": 0.0006348099209528089, "epoch": 9.437046004842616, "percentage": 47.19, "elapsed_time": "0:26:10", "remaining_time": "0:29:18", "throughput": 2033.22, "total_tokens": 3193432}
{"current_steps": 7800, "total_steps": 16520, "loss": 0.0857, "lr": 0.0006343011611261037, "epoch": 9.443099273607748, "percentage": 47.22, "elapsed_time": "0:26:11", "remaining_time": "0:29:16", "throughput": 2033.3, "total_tokens": 3195480}
{"current_steps": 7805, "total_steps": 16520, "loss": 0.0059, "lr": 0.0006337922513949999, "epoch": 9.44915254237288, "percentage": 47.25, "elapsed_time": "0:26:12", "remaining_time": "0:29:15", "throughput": 2033.43, "total_tokens": 3197624}
{"current_steps": 7810, "total_steps": 16520, "loss": 0.0369, "lr": 0.0006332831923275328, "epoch": 9.455205811138015, "percentage": 47.28, "elapsed_time": "0:26:13", "remaining_time": "0:29:14", "throughput": 2033.49, "total_tokens": 3199704}
{"current_steps": 7815, "total_steps": 16520, "loss": 0.0152, "lr": 0.0006327739844919047, "epoch": 9.461259079903147, "percentage": 47.31, "elapsed_time": "0:26:14", "remaining_time": "0:29:13", "throughput": 2033.61, "total_tokens": 3201880}
{"current_steps": 7820, "total_steps": 16520, "loss": 0.0346, "lr": 0.0006322646284564836, "epoch": 9.467312348668282, "percentage": 47.34, "elapsed_time": "0:26:15", "remaining_time": "0:29:12", "throughput": 2033.67, "total_tokens": 3203960}
{"current_steps": 7825, "total_steps": 16520, "loss": 0.0347, "lr": 0.0006317551247898026, "epoch": 9.473365617433414, "percentage": 47.37, "elapsed_time": "0:26:16", "remaining_time": "0:29:11", "throughput": 2033.75, "total_tokens": 3206008}
{"current_steps": 7830, "total_steps": 16520, "loss": 0.0646, "lr": 0.0006312454740605607, "epoch": 9.479418886198546, "percentage": 47.4, "elapsed_time": "0:26:17", "remaining_time": "0:29:10", "throughput": 2033.78, "total_tokens": 3208024}
{"current_steps": 7835, "total_steps": 16520, "loss": 0.0945, "lr": 0.0006307356768376198, "epoch": 9.48547215496368, "percentage": 47.43, "elapsed_time": "0:26:18", "remaining_time": "0:29:09", "throughput": 2033.84, "total_tokens": 3210104}
{"current_steps": 7840, "total_steps": 16520, "loss": 0.0082, "lr": 0.000630225733690006, "epoch": 9.491525423728813, "percentage": 47.46, "elapsed_time": "0:26:19", "remaining_time": "0:29:08", "throughput": 2033.94, "total_tokens": 3212184}
{"current_steps": 7845, "total_steps": 16520, "loss": 0.0397, "lr": 0.0006297156451869081, "epoch": 9.497578692493947, "percentage": 47.49, "elapsed_time": "0:26:20", "remaining_time": "0:29:07", "throughput": 2034.04, "total_tokens": 3214328}
{"current_steps": 7850, "total_steps": 16520, "loss": 0.0154, "lr": 0.0006292054118976773, "epoch": 9.50363196125908, "percentage": 47.52, "elapsed_time": "0:26:21", "remaining_time": "0:29:06", "throughput": 2034.08, "total_tokens": 3216376}
{"current_steps": 7855, "total_steps": 16520, "loss": 0.0097, "lr": 0.0006286950343918262, "epoch": 9.509685230024212, "percentage": 47.55, "elapsed_time": "0:26:22", "remaining_time": "0:29:05", "throughput": 2034.13, "total_tokens": 3218424}
{"current_steps": 7860, "total_steps": 16520, "loss": 0.0288, "lr": 0.0006281845132390284, "epoch": 9.515738498789347, "percentage": 47.58, "elapsed_time": "0:26:23", "remaining_time": "0:29:04", "throughput": 2034.26, "total_tokens": 3220568}
{"current_steps": 7865, "total_steps": 16520, "loss": 0.0249, "lr": 0.0006276738490091179, "epoch": 9.521791767554479, "percentage": 47.61, "elapsed_time": "0:26:24", "remaining_time": "0:29:03", "throughput": 2034.35, "total_tokens": 3222744}
{"current_steps": 7870, "total_steps": 16520, "loss": 0.014, "lr": 0.0006271630422720885, "epoch": 9.527845036319613, "percentage": 47.64, "elapsed_time": "0:26:25", "remaining_time": "0:29:02", "throughput": 2034.38, "total_tokens": 3224696}
{"current_steps": 7875, "total_steps": 16520, "loss": 0.0904, "lr": 0.0006266520935980929, "epoch": 9.533898305084746, "percentage": 47.67, "elapsed_time": "0:26:26", "remaining_time": "0:29:01", "throughput": 2034.42, "total_tokens": 3226744}
{"current_steps": 7880, "total_steps": 16520, "loss": 0.0624, "lr": 0.0006261410035574422, "epoch": 9.539951573849878, "percentage": 47.7, "elapsed_time": "0:26:27", "remaining_time": "0:29:00", "throughput": 2034.43, "total_tokens": 3228664}
{"current_steps": 7885, "total_steps": 16520, "loss": 0.0267, "lr": 0.0006256297727206054, "epoch": 9.546004842615012, "percentage": 47.73, "elapsed_time": "0:26:27", "remaining_time": "0:28:59", "throughput": 2034.51, "total_tokens": 3230776}
{"current_steps": 7890, "total_steps": 16520, "loss": 0.0369, "lr": 0.0006251184016582088, "epoch": 9.552058111380145, "percentage": 47.76, "elapsed_time": "0:26:28", "remaining_time": "0:28:57", "throughput": 2034.54, "total_tokens": 3232728}
{"current_steps": 7895, "total_steps": 16520, "loss": 0.016, "lr": 0.0006246068909410347, "epoch": 9.558111380145279, "percentage": 47.79, "elapsed_time": "0:26:29", "remaining_time": "0:28:56", "throughput": 2034.56, "total_tokens": 3234616}
{"current_steps": 7900, "total_steps": 16520, "loss": 0.0948, "lr": 0.000624095241140022, "epoch": 9.564164648910412, "percentage": 47.82, "elapsed_time": "0:26:30", "remaining_time": "0:28:55", "throughput": 2034.64, "total_tokens": 3236728}
{"current_steps": 7905, "total_steps": 16520, "loss": 0.0347, "lr": 0.000623583452826264, "epoch": 9.570217917675544, "percentage": 47.85, "elapsed_time": "0:26:31", "remaining_time": "0:28:54", "throughput": 2034.67, "total_tokens": 3238744}
{"current_steps": 7910, "total_steps": 16520, "loss": 0.0445, "lr": 0.0006230715265710097, "epoch": 9.576271186440678, "percentage": 47.88, "elapsed_time": "0:26:32", "remaining_time": "0:28:53", "throughput": 2034.77, "total_tokens": 3240888}
{"current_steps": 7915, "total_steps": 16520, "loss": 0.0677, "lr": 0.0006225594629456609, "epoch": 9.58232445520581, "percentage": 47.91, "elapsed_time": "0:26:33", "remaining_time": "0:28:52", "throughput": 2034.85, "total_tokens": 3242936}
{"current_steps": 7920, "total_steps": 16520, "loss": 0.0985, "lr": 0.0006220472625217734, "epoch": 9.588377723970945, "percentage": 47.94, "elapsed_time": "0:26:34", "remaining_time": "0:28:51", "throughput": 2034.89, "total_tokens": 3244920}
{"current_steps": 7925, "total_steps": 16520, "loss": 0.0122, "lr": 0.0006215349258710558, "epoch": 9.594430992736077, "percentage": 47.97, "elapsed_time": "0:26:35", "remaining_time": "0:28:50", "throughput": 2034.95, "total_tokens": 3247000}
{"current_steps": 7930, "total_steps": 16520, "loss": 0.0099, "lr": 0.0006210224535653683, "epoch": 9.600484261501212, "percentage": 48.0, "elapsed_time": "0:26:36", "remaining_time": "0:28:49", "throughput": 2035.03, "total_tokens": 3249112}
{"current_steps": 7935, "total_steps": 16520, "loss": 0.0456, "lr": 0.0006205098461767226, "epoch": 9.606537530266344, "percentage": 48.03, "elapsed_time": "0:26:37", "remaining_time": "0:28:48", "throughput": 2035.06, "total_tokens": 3251128}
{"current_steps": 7940, "total_steps": 16520, "loss": 0.0882, "lr": 0.0006199971042772816, "epoch": 9.612590799031477, "percentage": 48.06, "elapsed_time": "0:26:38", "remaining_time": "0:28:47", "throughput": 2035.09, "total_tokens": 3253144}
{"current_steps": 7945, "total_steps": 16520, "loss": 0.0339, "lr": 0.0006194842284393579, "epoch": 9.61864406779661, "percentage": 48.09, "elapsed_time": "0:26:39", "remaining_time": "0:28:46", "throughput": 2035.06, "total_tokens": 3255064}
{"current_steps": 7950, "total_steps": 16520, "loss": 0.0451, "lr": 0.0006189712192354137, "epoch": 9.624697336561743, "percentage": 48.12, "elapsed_time": "0:26:40", "remaining_time": "0:28:45", "throughput": 2035.11, "total_tokens": 3257112}
{"current_steps": 7955, "total_steps": 16520, "loss": 0.0225, "lr": 0.0006184580772380602, "epoch": 9.630750605326877, "percentage": 48.15, "elapsed_time": "0:26:41", "remaining_time": "0:28:44", "throughput": 2035.21, "total_tokens": 3259288}
{"current_steps": 7960, "total_steps": 16520, "loss": 0.1249, "lr": 0.0006179448030200567, "epoch": 9.63680387409201, "percentage": 48.18, "elapsed_time": "0:26:42", "remaining_time": "0:28:43", "throughput": 2035.22, "total_tokens": 3261208}
{"current_steps": 7965, "total_steps": 16520, "loss": 0.0281, "lr": 0.00061743139715431, "epoch": 9.642857142857142, "percentage": 48.21, "elapsed_time": "0:26:43", "remaining_time": "0:28:42", "throughput": 2035.28, "total_tokens": 3263224}
{"current_steps": 7970, "total_steps": 16520, "loss": 0.0144, "lr": 0.0006169178602138741, "epoch": 9.648910411622277, "percentage": 48.24, "elapsed_time": "0:26:44", "remaining_time": "0:28:41", "throughput": 2035.39, "total_tokens": 3265368}
{"current_steps": 7975, "total_steps": 16520, "loss": 0.113, "lr": 0.0006164041927719491, "epoch": 9.654963680387409, "percentage": 48.27, "elapsed_time": "0:26:45", "remaining_time": "0:28:39", "throughput": 2035.5, "total_tokens": 3267448}
{"current_steps": 7980, "total_steps": 16520, "loss": 0.0772, "lr": 0.0006158903954018808, "epoch": 9.661016949152543, "percentage": 48.31, "elapsed_time": "0:26:46", "remaining_time": "0:28:38", "throughput": 2035.55, "total_tokens": 3269496}
{"current_steps": 7985, "total_steps": 16520, "loss": 0.0101, "lr": 0.0006153764686771601, "epoch": 9.667070217917676, "percentage": 48.34, "elapsed_time": "0:26:47", "remaining_time": "0:28:37", "throughput": 2035.59, "total_tokens": 3271480}
{"current_steps": 7990, "total_steps": 16520, "loss": 0.0613, "lr": 0.000614862413171422, "epoch": 9.673123486682808, "percentage": 48.37, "elapsed_time": "0:26:48", "remaining_time": "0:28:36", "throughput": 2035.63, "total_tokens": 3273528}
{"current_steps": 7995, "total_steps": 16520, "loss": 0.0926, "lr": 0.0006143482294584459, "epoch": 9.679176755447942, "percentage": 48.4, "elapsed_time": "0:26:49", "remaining_time": "0:28:35", "throughput": 2035.71, "total_tokens": 3275640}
{"current_steps": 8000, "total_steps": 16520, "loss": 0.0342, "lr": 0.0006138339181121534, "epoch": 9.685230024213075, "percentage": 48.43, "elapsed_time": "0:26:50", "remaining_time": "0:28:34", "throughput": 2035.72, "total_tokens": 3277560}
{"current_steps": 8005, "total_steps": 16520, "loss": 0.0421, "lr": 0.0006133194797066092, "epoch": 9.69128329297821, "percentage": 48.46, "elapsed_time": "0:26:50", "remaining_time": "0:28:33", "throughput": 2035.84, "total_tokens": 3279704}
{"current_steps": 8010, "total_steps": 16520, "loss": 0.0699, "lr": 0.0006128049148160198, "epoch": 9.697336561743342, "percentage": 48.49, "elapsed_time": "0:26:51", "remaining_time": "0:28:32", "throughput": 2035.89, "total_tokens": 3281688}
{"current_steps": 8015, "total_steps": 16520, "loss": 0.0403, "lr": 0.0006122902240147327, "epoch": 9.703389830508474, "percentage": 48.52, "elapsed_time": "0:26:52", "remaining_time": "0:28:31", "throughput": 2035.92, "total_tokens": 3283672}
{"current_steps": 8020, "total_steps": 16520, "loss": 0.0544, "lr": 0.000611775407877236, "epoch": 9.709443099273608, "percentage": 48.55, "elapsed_time": "0:26:53", "remaining_time": "0:28:30", "throughput": 2035.98, "total_tokens": 3285688}
{"current_steps": 8025, "total_steps": 16520, "loss": 0.034, "lr": 0.0006112604669781572, "epoch": 9.71549636803874, "percentage": 48.58, "elapsed_time": "0:26:54", "remaining_time": "0:28:29", "throughput": 2036.09, "total_tokens": 3287864}
{"current_steps": 8030, "total_steps": 16520, "loss": 0.0762, "lr": 0.0006107454018922641, "epoch": 9.721549636803875, "percentage": 48.61, "elapsed_time": "0:26:55", "remaining_time": "0:28:28", "throughput": 2036.12, "total_tokens": 3289752}
{"current_steps": 8035, "total_steps": 16520, "loss": 0.0591, "lr": 0.0006102302131944623, "epoch": 9.727602905569007, "percentage": 48.64, "elapsed_time": "0:26:56", "remaining_time": "0:28:27", "throughput": 2036.17, "total_tokens": 3291768}
{"current_steps": 8040, "total_steps": 16520, "loss": 0.0213, "lr": 0.0006097149014597957, "epoch": 9.73365617433414, "percentage": 48.67, "elapsed_time": "0:26:57", "remaining_time": "0:28:26", "throughput": 2036.32, "total_tokens": 3293976}
{"current_steps": 8045, "total_steps": 16520, "loss": 0.0562, "lr": 0.0006091994672634453, "epoch": 9.739709443099274, "percentage": 48.7, "elapsed_time": "0:26:58", "remaining_time": "0:28:25", "throughput": 2036.38, "total_tokens": 3296056}
{"current_steps": 8050, "total_steps": 16520, "loss": 0.0283, "lr": 0.0006086839111807291, "epoch": 9.745762711864407, "percentage": 48.73, "elapsed_time": "0:26:59", "remaining_time": "0:28:24", "throughput": 2036.46, "total_tokens": 3298104}
{"current_steps": 8055, "total_steps": 16520, "loss": 0.0247, "lr": 0.0006081682337871009, "epoch": 9.75181598062954, "percentage": 48.76, "elapsed_time": "0:27:00", "remaining_time": "0:28:22", "throughput": 2036.5, "total_tokens": 3300024}
{"current_steps": 8060, "total_steps": 16520, "loss": 0.0355, "lr": 0.0006076524356581499, "epoch": 9.757869249394673, "percentage": 48.79, "elapsed_time": "0:27:01", "remaining_time": "0:28:21", "throughput": 2036.54, "total_tokens": 3302008}
{"current_steps": 8065, "total_steps": 16520, "loss": 0.1034, "lr": 0.0006071365173696003, "epoch": 9.763922518159806, "percentage": 48.82, "elapsed_time": "0:27:02", "remaining_time": "0:28:20", "throughput": 2036.63, "total_tokens": 3304088}
{"current_steps": 8070, "total_steps": 16520, "loss": 0.1169, "lr": 0.0006066204794973102, "epoch": 9.76997578692494, "percentage": 48.85, "elapsed_time": "0:27:03", "remaining_time": "0:28:19", "throughput": 2036.72, "total_tokens": 3306104}
{"current_steps": 8075, "total_steps": 16520, "loss": 0.0647, "lr": 0.0006061043226172713, "epoch": 9.776029055690072, "percentage": 48.88, "elapsed_time": "0:27:04", "remaining_time": "0:28:18", "throughput": 2036.85, "total_tokens": 3308312}
{"current_steps": 8080, "total_steps": 16520, "loss": 0.0758, "lr": 0.000605588047305608, "epoch": 9.782082324455207, "percentage": 48.91, "elapsed_time": "0:27:05", "remaining_time": "0:28:17", "throughput": 2036.87, "total_tokens": 3310200}
{"current_steps": 8085, "total_steps": 16520, "loss": 0.0459, "lr": 0.000605071654138577, "epoch": 9.788135593220339, "percentage": 48.94, "elapsed_time": "0:27:06", "remaining_time": "0:28:16", "throughput": 2036.95, "total_tokens": 3312312}
{"current_steps": 8090, "total_steps": 16520, "loss": 0.0402, "lr": 0.0006045551436925665, "epoch": 9.794188861985472, "percentage": 48.97, "elapsed_time": "0:27:07", "remaining_time": "0:28:15", "throughput": 2036.99, "total_tokens": 3314296}
{"current_steps": 8095, "total_steps": 16520, "loss": 0.0754, "lr": 0.0006040385165440957, "epoch": 9.800242130750606, "percentage": 49.0, "elapsed_time": "0:27:08", "remaining_time": "0:28:14", "throughput": 2037.07, "total_tokens": 3316408}
{"current_steps": 8100, "total_steps": 16520, "loss": 0.0375, "lr": 0.000603521773269814, "epoch": 9.806295399515738, "percentage": 49.03, "elapsed_time": "0:27:08", "remaining_time": "0:28:13", "throughput": 2037.1, "total_tokens": 3318424}
{"current_steps": 8105, "total_steps": 16520, "loss": 0.0604, "lr": 0.0006030049144465003, "epoch": 9.812348668280872, "percentage": 49.06, "elapsed_time": "0:27:09", "remaining_time": "0:28:12", "throughput": 2037.16, "total_tokens": 3320504}
{"current_steps": 8110, "total_steps": 16520, "loss": 0.0247, "lr": 0.0006024879406510627, "epoch": 9.818401937046005, "percentage": 49.09, "elapsed_time": "0:27:10", "remaining_time": "0:28:11", "throughput": 2037.23, "total_tokens": 3322616}
{"current_steps": 8115, "total_steps": 16520, "loss": 0.0231, "lr": 0.0006019708524605372, "epoch": 9.824455205811137, "percentage": 49.12, "elapsed_time": "0:27:11", "remaining_time": "0:28:10", "throughput": 2037.26, "total_tokens": 3324568}
{"current_steps": 8120, "total_steps": 16520, "loss": 0.0084, "lr": 0.0006014536504520881, "epoch": 9.830508474576272, "percentage": 49.15, "elapsed_time": "0:27:12", "remaining_time": "0:28:09", "throughput": 2037.29, "total_tokens": 3326584}
{"current_steps": 8125, "total_steps": 16520, "loss": 0.014, "lr": 0.0006009363352030064, "epoch": 9.836561743341404, "percentage": 49.18, "elapsed_time": "0:27:13", "remaining_time": "0:28:08", "throughput": 2037.38, "total_tokens": 3328664}
{"current_steps": 8130, "total_steps": 16520, "loss": 0.0169, "lr": 0.0006004189072907094, "epoch": 9.842615012106538, "percentage": 49.21, "elapsed_time": "0:27:14", "remaining_time": "0:28:07", "throughput": 2037.47, "total_tokens": 3330808}
{"current_steps": 8135, "total_steps": 16520, "loss": 0.0691, "lr": 0.0005999013672927405, "epoch": 9.84866828087167, "percentage": 49.24, "elapsed_time": "0:27:15", "remaining_time": "0:28:06", "throughput": 2037.52, "total_tokens": 3332856}
{"current_steps": 8140, "total_steps": 16520, "loss": 0.0612, "lr": 0.0005993837157867676, "epoch": 9.854721549636803, "percentage": 49.27, "elapsed_time": "0:27:16", "remaining_time": "0:28:04", "throughput": 2037.58, "total_tokens": 3334904}
{"current_steps": 8145, "total_steps": 16520, "loss": 0.0206, "lr": 0.0005988659533505839, "epoch": 9.860774818401937, "percentage": 49.3, "elapsed_time": "0:27:17", "remaining_time": "0:28:03", "throughput": 2037.65, "total_tokens": 3336952}
{"current_steps": 8150, "total_steps": 16520, "loss": 0.0508, "lr": 0.0005983480805621057, "epoch": 9.86682808716707, "percentage": 49.33, "elapsed_time": "0:27:18", "remaining_time": "0:28:02", "throughput": 2037.83, "total_tokens": 3339288}
{"current_steps": 8155, "total_steps": 16520, "loss": 0.0177, "lr": 0.0005978300979993729, "epoch": 9.872881355932204, "percentage": 49.36, "elapsed_time": "0:27:19", "remaining_time": "0:28:01", "throughput": 2037.87, "total_tokens": 3341208}
{"current_steps": 8160, "total_steps": 16520, "loss": 0.0737, "lr": 0.0005973120062405476, "epoch": 9.878934624697337, "percentage": 49.39, "elapsed_time": "0:27:20", "remaining_time": "0:28:00", "throughput": 2037.9, "total_tokens": 3343224}
{"current_steps": 8165, "total_steps": 16520, "loss": 0.036, "lr": 0.0005967938058639141, "epoch": 9.884987893462469, "percentage": 49.42, "elapsed_time": "0:27:21", "remaining_time": "0:27:59", "throughput": 2038.01, "total_tokens": 3345432}
{"current_steps": 8170, "total_steps": 16520, "loss": 0.0785, "lr": 0.0005962754974478775, "epoch": 9.891041162227603, "percentage": 49.46, "elapsed_time": "0:27:22", "remaining_time": "0:27:58", "throughput": 2038.07, "total_tokens": 3347448}
{"current_steps": 8175, "total_steps": 16520, "loss": 0.0246, "lr": 0.0005957570815709643, "epoch": 9.897094430992736, "percentage": 49.49, "elapsed_time": "0:27:23", "remaining_time": "0:27:57", "throughput": 2038.13, "total_tokens": 3349528}
{"current_steps": 8180, "total_steps": 16520, "loss": 0.0406, "lr": 0.0005952385588118203, "epoch": 9.90314769975787, "percentage": 49.52, "elapsed_time": "0:27:24", "remaining_time": "0:27:56", "throughput": 2038.2, "total_tokens": 3351640}
{"current_steps": 8185, "total_steps": 16520, "loss": 0.0986, "lr": 0.0005947199297492102, "epoch": 9.909200968523002, "percentage": 49.55, "elapsed_time": "0:27:25", "remaining_time": "0:27:55", "throughput": 2038.28, "total_tokens": 3353752}
{"current_steps": 8190, "total_steps": 16520, "loss": 0.0565, "lr": 0.0005942011949620186, "epoch": 9.915254237288135, "percentage": 49.58, "elapsed_time": "0:27:26", "remaining_time": "0:27:54", "throughput": 2038.35, "total_tokens": 3355864}
{"current_steps": 8195, "total_steps": 16520, "loss": 0.0136, "lr": 0.0005936823550292468, "epoch": 9.92130750605327, "percentage": 49.61, "elapsed_time": "0:27:27", "remaining_time": "0:27:53", "throughput": 2038.46, "total_tokens": 3358040}
{"current_steps": 8200, "total_steps": 16520, "loss": 0.0076, "lr": 0.0005931634105300145, "epoch": 9.927360774818402, "percentage": 49.64, "elapsed_time": "0:27:28", "remaining_time": "0:27:52", "throughput": 2038.5, "total_tokens": 3360024}
{"current_steps": 8205, "total_steps": 16520, "loss": 0.0349, "lr": 0.0005926443620435572, "epoch": 9.933414043583536, "percentage": 49.67, "elapsed_time": "0:27:29", "remaining_time": "0:27:51", "throughput": 2038.56, "total_tokens": 3362104}
{"current_steps": 8210, "total_steps": 16520, "loss": 0.0235, "lr": 0.0005921252101492273, "epoch": 9.939467312348668, "percentage": 49.7, "elapsed_time": "0:27:30", "remaining_time": "0:27:50", "throughput": 2038.6, "total_tokens": 3364024}
{"current_steps": 8215, "total_steps": 16520, "loss": 0.0197, "lr": 0.0005916059554264923, "epoch": 9.9455205811138, "percentage": 49.73, "elapsed_time": "0:27:31", "remaining_time": "0:27:49", "throughput": 2038.67, "total_tokens": 3366072}
{"current_steps": 8220, "total_steps": 16520, "loss": 0.0099, "lr": 0.0005910865984549343, "epoch": 9.951573849878935, "percentage": 49.76, "elapsed_time": "0:27:32", "remaining_time": "0:27:48", "throughput": 2038.76, "total_tokens": 3368216}
{"current_steps": 8225, "total_steps": 16520, "loss": 0.0774, "lr": 0.0005905671398142495, "epoch": 9.957627118644067, "percentage": 49.79, "elapsed_time": "0:27:33", "remaining_time": "0:27:47", "throughput": 2038.83, "total_tokens": 3370264}
{"current_steps": 8230, "total_steps": 16520, "loss": 0.1042, "lr": 0.0005900475800842481, "epoch": 9.963680387409202, "percentage": 49.82, "elapsed_time": "0:27:34", "remaining_time": "0:27:46", "throughput": 2038.84, "total_tokens": 3372248}
{"current_steps": 8235, "total_steps": 16520, "loss": 0.0869, "lr": 0.0005895279198448525, "epoch": 9.969733656174334, "percentage": 49.85, "elapsed_time": "0:27:34", "remaining_time": "0:27:44", "throughput": 2038.88, "total_tokens": 3374232}
{"current_steps": 8240, "total_steps": 16520, "loss": 0.1123, "lr": 0.0005890081596760977, "epoch": 9.975786924939467, "percentage": 49.88, "elapsed_time": "0:27:35", "remaining_time": "0:27:43", "throughput": 2038.97, "total_tokens": 3376344}
{"current_steps": 8245, "total_steps": 16520, "loss": 0.0915, "lr": 0.00058848830015813, "epoch": 9.9818401937046, "percentage": 49.91, "elapsed_time": "0:27:36", "remaining_time": "0:27:42", "throughput": 2039.11, "total_tokens": 3378552}
{"current_steps": 8250, "total_steps": 16520, "loss": 0.0111, "lr": 0.0005879683418712066, "epoch": 9.987893462469733, "percentage": 49.94, "elapsed_time": "0:27:37", "remaining_time": "0:27:41", "throughput": 2039.2, "total_tokens": 3380696}
{"current_steps": 8255, "total_steps": 16520, "loss": 0.0286, "lr": 0.0005874482853956954, "epoch": 9.993946731234868, "percentage": 49.97, "elapsed_time": "0:27:38", "remaining_time": "0:27:40", "throughput": 2039.29, "total_tokens": 3382648}
{"current_steps": 8260, "total_steps": 16520, "loss": 0.0887, "lr": 0.0005869281313120733, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:27:39", "remaining_time": "0:27:39", "throughput": 2039.23, "total_tokens": 3384288}
{"current_steps": 8260, "total_steps": 16520, "eval_loss": 0.11012570559978485, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "0:27:47", "remaining_time": "0:27:47", "throughput": 2029.5, "total_tokens": 3384288}
{"current_steps": 8265, "total_steps": 16520, "loss": 0.0227, "lr": 0.0005864078802009263, "epoch": 10.006053268765132, "percentage": 50.03, "elapsed_time": "0:27:49", "remaining_time": "0:27:47", "throughput": 2028.29, "total_tokens": 3386304}
{"current_steps": 8270, "total_steps": 16520, "loss": 0.0299, "lr": 0.000585887532642949, "epoch": 10.012106537530267, "percentage": 50.06, "elapsed_time": "0:27:50", "remaining_time": "0:27:46", "throughput": 2028.33, "total_tokens": 3388224}
{"current_steps": 8275, "total_steps": 16520, "loss": 0.0176, "lr": 0.0005853670892189433, "epoch": 10.0181598062954, "percentage": 50.09, "elapsed_time": "0:27:51", "remaining_time": "0:27:45", "throughput": 2028.35, "total_tokens": 3390240}
{"current_steps": 8280, "total_steps": 16520, "loss": 0.0424, "lr": 0.0005848465505098182, "epoch": 10.024213075060533, "percentage": 50.12, "elapsed_time": "0:27:52", "remaining_time": "0:27:44", "throughput": 2028.41, "total_tokens": 3392320}
{"current_steps": 8285, "total_steps": 16520, "loss": 0.0301, "lr": 0.0005843259170965891, "epoch": 10.030266343825666, "percentage": 50.15, "elapsed_time": "0:27:53", "remaining_time": "0:27:43", "throughput": 2028.48, "total_tokens": 3394336}
{"current_steps": 8290, "total_steps": 16520, "loss": 0.0517, "lr": 0.0005838051895603772, "epoch": 10.036319612590798, "percentage": 50.18, "elapsed_time": "0:27:54", "remaining_time": "0:27:42", "throughput": 2028.5, "total_tokens": 3396288}
{"current_steps": 8295, "total_steps": 16520, "loss": 0.0321, "lr": 0.0005832843684824086, "epoch": 10.042372881355933, "percentage": 50.21, "elapsed_time": "0:27:55", "remaining_time": "0:27:41", "throughput": 2028.6, "total_tokens": 3398432}
{"current_steps": 8300, "total_steps": 16520, "loss": 0.012, "lr": 0.0005827634544440139, "epoch": 10.048426150121065, "percentage": 50.24, "elapsed_time": "0:27:56", "remaining_time": "0:27:39", "throughput": 2028.65, "total_tokens": 3400320}
{"current_steps": 8305, "total_steps": 16520, "loss": 0.029, "lr": 0.0005822424480266275, "epoch": 10.0544794188862, "percentage": 50.27, "elapsed_time": "0:27:57", "remaining_time": "0:27:38", "throughput": 2028.71, "total_tokens": 3402432}
{"current_steps": 8310, "total_steps": 16520, "loss": 0.0351, "lr": 0.0005817213498117866, "epoch": 10.060532687651332, "percentage": 50.3, "elapsed_time": "0:27:58", "remaining_time": "0:27:37", "throughput": 2028.77, "total_tokens": 3404512}
{"current_steps": 8315, "total_steps": 16520, "loss": 0.0497, "lr": 0.0005812001603811314, "epoch": 10.066585956416464, "percentage": 50.33, "elapsed_time": "0:27:59", "remaining_time": "0:27:36", "throughput": 2028.89, "total_tokens": 3406720}
{"current_steps": 8320, "total_steps": 16520, "loss": 0.0093, "lr": 0.0005806788803164034, "epoch": 10.072639225181598, "percentage": 50.36, "elapsed_time": "0:28:00", "remaining_time": "0:27:35", "throughput": 2028.9, "total_tokens": 3408640}
{"current_steps": 8325, "total_steps": 16520, "loss": 0.0284, "lr": 0.0005801575101994455, "epoch": 10.07869249394673, "percentage": 50.39, "elapsed_time": "0:28:00", "remaining_time": "0:27:34", "throughput": 2028.95, "total_tokens": 3410656}
{"current_steps": 8330, "total_steps": 16520, "loss": 0.0156, "lr": 0.0005796360506122012, "epoch": 10.084745762711865, "percentage": 50.42, "elapsed_time": "0:28:01", "remaining_time": "0:27:33", "throughput": 2028.99, "total_tokens": 3412704}
{"current_steps": 8335, "total_steps": 16520, "loss": 0.0391, "lr": 0.0005791145021367137, "epoch": 10.090799031476998, "percentage": 50.45, "elapsed_time": "0:28:02", "remaining_time": "0:27:32", "throughput": 2029.04, "total_tokens": 3414752}
{"current_steps": 8340, "total_steps": 16520, "loss": 0.0264, "lr": 0.0005785928653551257, "epoch": 10.09685230024213, "percentage": 50.48, "elapsed_time": "0:28:03", "remaining_time": "0:27:31", "throughput": 2029.11, "total_tokens": 3416864}
{"current_steps": 8345, "total_steps": 16520, "loss": 0.0195, "lr": 0.0005780711408496777, "epoch": 10.102905569007264, "percentage": 50.51, "elapsed_time": "0:28:04", "remaining_time": "0:27:30", "throughput": 2029.12, "total_tokens": 3418848}
{"current_steps": 8350, "total_steps": 16520, "loss": 0.0591, "lr": 0.0005775493292027092, "epoch": 10.108958837772397, "percentage": 50.54, "elapsed_time": "0:28:05", "remaining_time": "0:27:29", "throughput": 2029.23, "total_tokens": 3421024}
{"current_steps": 8355, "total_steps": 16520, "loss": 0.0478, "lr": 0.0005770274309966563, "epoch": 10.115012106537531, "percentage": 50.58, "elapsed_time": "0:28:06", "remaining_time": "0:27:28", "throughput": 2029.33, "total_tokens": 3423168}
{"current_steps": 8360, "total_steps": 16520, "loss": 0.0876, "lr": 0.0005765054468140515, "epoch": 10.121065375302663, "percentage": 50.61, "elapsed_time": "0:28:07", "remaining_time": "0:27:27", "throughput": 2029.45, "total_tokens": 3425344}
{"current_steps": 8365, "total_steps": 16520, "loss": 0.0113, "lr": 0.0005759833772375241, "epoch": 10.127118644067796, "percentage": 50.64, "elapsed_time": "0:28:08", "remaining_time": "0:27:26", "throughput": 2029.52, "total_tokens": 3427392}
{"current_steps": 8370, "total_steps": 16520, "loss": 0.0297, "lr": 0.0005754612228497976, "epoch": 10.13317191283293, "percentage": 50.67, "elapsed_time": "0:28:09", "remaining_time": "0:27:25", "throughput": 2029.53, "total_tokens": 3429248}
{"current_steps": 8375, "total_steps": 16520, "loss": 0.0115, "lr": 0.0005749389842336915, "epoch": 10.139225181598063, "percentage": 50.7, "elapsed_time": "0:28:10", "remaining_time": "0:27:24", "throughput": 2029.6, "total_tokens": 3431296}
{"current_steps": 8380, "total_steps": 16520, "loss": 0.0242, "lr": 0.0005744166619721182, "epoch": 10.145278450363197, "percentage": 50.73, "elapsed_time": "0:28:11", "remaining_time": "0:27:23", "throughput": 2029.71, "total_tokens": 3433408}
{"current_steps": 8385, "total_steps": 16520, "loss": 0.0328, "lr": 0.0005738942566480839, "epoch": 10.15133171912833, "percentage": 50.76, "elapsed_time": "0:28:12", "remaining_time": "0:27:22", "throughput": 2029.85, "total_tokens": 3435648}
{"current_steps": 8390, "total_steps": 16520, "loss": 0.0082, "lr": 0.0005733717688446875, "epoch": 10.157384987893462, "percentage": 50.79, "elapsed_time": "0:28:13", "remaining_time": "0:27:21", "throughput": 2029.9, "total_tokens": 3437600}
{"current_steps": 8395, "total_steps": 16520, "loss": 0.0226, "lr": 0.0005728491991451199, "epoch": 10.163438256658596, "percentage": 50.82, "elapsed_time": "0:28:14", "remaining_time": "0:27:19", "throughput": 2030.01, "total_tokens": 3439776}
{"current_steps": 8400, "total_steps": 16520, "loss": 0.0099, "lr": 0.0005723265481326635, "epoch": 10.169491525423728, "percentage": 50.85, "elapsed_time": "0:28:15", "remaining_time": "0:27:18", "throughput": 2030.01, "total_tokens": 3441696}
{"current_steps": 8405, "total_steps": 16520, "loss": 0.0779, "lr": 0.0005718038163906913, "epoch": 10.175544794188863, "percentage": 50.88, "elapsed_time": "0:28:16", "remaining_time": "0:27:17", "throughput": 2030.04, "total_tokens": 3443648}
{"current_steps": 8410, "total_steps": 16520, "loss": 0.0393, "lr": 0.0005712810045026668, "epoch": 10.181598062953995, "percentage": 50.91, "elapsed_time": "0:28:17", "remaining_time": "0:27:16", "throughput": 2030.06, "total_tokens": 3445536}
{"current_steps": 8415, "total_steps": 16520, "loss": 0.0178, "lr": 0.0005707581130521424, "epoch": 10.187651331719128, "percentage": 50.94, "elapsed_time": "0:28:18", "remaining_time": "0:27:15", "throughput": 2030.11, "total_tokens": 3447584}
{"current_steps": 8420, "total_steps": 16520, "loss": 0.0485, "lr": 0.0005702351426227596, "epoch": 10.193704600484262, "percentage": 50.97, "elapsed_time": "0:28:19", "remaining_time": "0:27:14", "throughput": 2030.12, "total_tokens": 3449568}
{"current_steps": 8425, "total_steps": 16520, "loss": 0.1329, "lr": 0.0005697120937982481, "epoch": 10.199757869249394, "percentage": 51.0, "elapsed_time": "0:28:20", "remaining_time": "0:27:13", "throughput": 2030.19, "total_tokens": 3451680}
{"current_steps": 8430, "total_steps": 16520, "loss": 0.0158, "lr": 0.0005691889671624251, "epoch": 10.205811138014528, "percentage": 51.03, "elapsed_time": "0:28:21", "remaining_time": "0:27:12", "throughput": 2030.25, "total_tokens": 3453696}
{"current_steps": 8435, "total_steps": 16520, "loss": 0.0096, "lr": 0.0005686657632991943, "epoch": 10.211864406779661, "percentage": 51.06, "elapsed_time": "0:28:22", "remaining_time": "0:27:11", "throughput": 2030.35, "total_tokens": 3455808}
{"current_steps": 8440, "total_steps": 16520, "loss": 0.0016, "lr": 0.0005681424827925464, "epoch": 10.217917675544793, "percentage": 51.09, "elapsed_time": "0:28:23", "remaining_time": "0:27:10", "throughput": 2030.42, "total_tokens": 3457856}
{"current_steps": 8445, "total_steps": 16520, "loss": 0.0154, "lr": 0.0005676191262265568, "epoch": 10.223970944309928, "percentage": 51.12, "elapsed_time": "0:28:23", "remaining_time": "0:27:09", "throughput": 2030.5, "total_tokens": 3459904}
{"current_steps": 8450, "total_steps": 16520, "loss": 0.0083, "lr": 0.000567095694185386, "epoch": 10.23002421307506, "percentage": 51.15, "elapsed_time": "0:28:24", "remaining_time": "0:27:08", "throughput": 2030.57, "total_tokens": 3461824}
{"current_steps": 8455, "total_steps": 16520, "loss": 0.0207, "lr": 0.0005665721872532791, "epoch": 10.236077481840194, "percentage": 51.18, "elapsed_time": "0:28:25", "remaining_time": "0:27:07", "throughput": 2030.63, "total_tokens": 3463904}
{"current_steps": 8460, "total_steps": 16520, "loss": 0.0092, "lr": 0.0005660486060145646, "epoch": 10.242130750605327, "percentage": 51.21, "elapsed_time": "0:28:26", "remaining_time": "0:27:06", "throughput": 2030.71, "total_tokens": 3466048}
{"current_steps": 8465, "total_steps": 16520, "loss": 0.0068, "lr": 0.0005655249510536538, "epoch": 10.24818401937046, "percentage": 51.24, "elapsed_time": "0:28:27", "remaining_time": "0:27:05", "throughput": 2030.77, "total_tokens": 3468128}
{"current_steps": 8470, "total_steps": 16520, "loss": 0.0364, "lr": 0.0005650012229550403, "epoch": 10.254237288135593, "percentage": 51.27, "elapsed_time": "0:28:28", "remaining_time": "0:27:04", "throughput": 2030.87, "total_tokens": 3470272}
{"current_steps": 8475, "total_steps": 16520, "loss": 0.0629, "lr": 0.0005644774223032997, "epoch": 10.260290556900726, "percentage": 51.3, "elapsed_time": "0:28:29", "remaining_time": "0:27:02", "throughput": 2030.94, "total_tokens": 3472384}
{"current_steps": 8480, "total_steps": 16520, "loss": 0.0076, "lr": 0.0005639535496830881, "epoch": 10.26634382566586, "percentage": 51.33, "elapsed_time": "0:28:30", "remaining_time": "0:27:01", "throughput": 2030.94, "total_tokens": 3474336}
{"current_steps": 8485, "total_steps": 16520, "loss": 0.004, "lr": 0.0005634296056791423, "epoch": 10.272397094430993, "percentage": 51.36, "elapsed_time": "0:28:31", "remaining_time": "0:27:00", "throughput": 2031.01, "total_tokens": 3476384}
{"current_steps": 8490, "total_steps": 16520, "loss": 0.0631, "lr": 0.0005629055908762784, "epoch": 10.278450363196125, "percentage": 51.39, "elapsed_time": "0:28:32", "remaining_time": "0:26:59", "throughput": 2031.02, "total_tokens": 3478304}
{"current_steps": 8495, "total_steps": 16520, "loss": 0.0121, "lr": 0.0005623815058593921, "epoch": 10.28450363196126, "percentage": 51.42, "elapsed_time": "0:28:33", "remaining_time": "0:26:58", "throughput": 2031.08, "total_tokens": 3480384}
{"current_steps": 8500, "total_steps": 16520, "loss": 0.0628, "lr": 0.0005618573512134567, "epoch": 10.290556900726392, "percentage": 51.45, "elapsed_time": "0:28:34", "remaining_time": "0:26:57", "throughput": 2031.11, "total_tokens": 3482400}
{"current_steps": 8505, "total_steps": 16520, "loss": 0.0089, "lr": 0.000561333127523524, "epoch": 10.296610169491526, "percentage": 51.48, "elapsed_time": "0:28:35", "remaining_time": "0:26:56", "throughput": 2031.17, "total_tokens": 3484480}
{"current_steps": 8510, "total_steps": 16520, "loss": 0.0101, "lr": 0.0005608088353747221, "epoch": 10.302663438256658, "percentage": 51.51, "elapsed_time": "0:28:36", "remaining_time": "0:26:55", "throughput": 2031.18, "total_tokens": 3486464}
{"current_steps": 8515, "total_steps": 16520, "loss": 0.0158, "lr": 0.0005602844753522561, "epoch": 10.30871670702179, "percentage": 51.54, "elapsed_time": "0:28:37", "remaining_time": "0:26:54", "throughput": 2031.25, "total_tokens": 3488512}
{"current_steps": 8520, "total_steps": 16520, "loss": 0.0128, "lr": 0.0005597600480414069, "epoch": 10.314769975786925, "percentage": 51.57, "elapsed_time": "0:28:38", "remaining_time": "0:26:53", "throughput": 2031.28, "total_tokens": 3490464}
{"current_steps": 8525, "total_steps": 16520, "loss": 0.0155, "lr": 0.0005592355540275301, "epoch": 10.320823244552058, "percentage": 51.6, "elapsed_time": "0:28:39", "remaining_time": "0:26:52", "throughput": 2031.43, "total_tokens": 3492736}
{"current_steps": 8530, "total_steps": 16520, "loss": 0.0447, "lr": 0.0005587109938960558, "epoch": 10.326876513317192, "percentage": 51.63, "elapsed_time": "0:28:40", "remaining_time": "0:26:51", "throughput": 2031.5, "total_tokens": 3494848}
{"current_steps": 8535, "total_steps": 16520, "loss": 0.0239, "lr": 0.0005581863682324881, "epoch": 10.332929782082324, "percentage": 51.66, "elapsed_time": "0:28:41", "remaining_time": "0:26:50", "throughput": 2031.57, "total_tokens": 3496896}
{"current_steps": 8540, "total_steps": 16520, "loss": 0.0183, "lr": 0.0005576616776224042, "epoch": 10.338983050847457, "percentage": 51.69, "elapsed_time": "0:28:42", "remaining_time": "0:26:49", "throughput": 2031.61, "total_tokens": 3498944}
{"current_steps": 8545, "total_steps": 16520, "loss": 0.1826, "lr": 0.000557136922651454, "epoch": 10.345036319612591, "percentage": 51.73, "elapsed_time": "0:28:43", "remaining_time": "0:26:48", "throughput": 2031.72, "total_tokens": 3500992}
{"current_steps": 8550, "total_steps": 16520, "loss": 0.0265, "lr": 0.0005566121039053587, "epoch": 10.351089588377723, "percentage": 51.76, "elapsed_time": "0:28:44", "remaining_time": "0:26:47", "throughput": 2031.77, "total_tokens": 3503072}
{"current_steps": 8555, "total_steps": 16520, "loss": 0.0185, "lr": 0.000556087221969911, "epoch": 10.357142857142858, "percentage": 51.79, "elapsed_time": "0:28:45", "remaining_time": "0:26:46", "throughput": 2031.8, "total_tokens": 3505024}
{"current_steps": 8560, "total_steps": 16520, "loss": 0.0191, "lr": 0.0005555622774309744, "epoch": 10.36319612590799, "percentage": 51.82, "elapsed_time": "0:28:46", "remaining_time": "0:26:45", "throughput": 2031.88, "total_tokens": 3507072}
{"current_steps": 8565, "total_steps": 16520, "loss": 0.0179, "lr": 0.0005550372708744816, "epoch": 10.369249394673124, "percentage": 51.85, "elapsed_time": "0:28:47", "remaining_time": "0:26:44", "throughput": 2031.93, "total_tokens": 3509152}
{"current_steps": 8570, "total_steps": 16520, "loss": 0.0442, "lr": 0.0005545122028864353, "epoch": 10.375302663438257, "percentage": 51.88, "elapsed_time": "0:28:47", "remaining_time": "0:26:42", "throughput": 2032.05, "total_tokens": 3511360}
{"current_steps": 8575, "total_steps": 16520, "loss": 0.0456, "lr": 0.0005539870740529061, "epoch": 10.38135593220339, "percentage": 51.91, "elapsed_time": "0:28:48", "remaining_time": "0:26:41", "throughput": 2032.1, "total_tokens": 3513408}
{"current_steps": 8580, "total_steps": 16520, "loss": 0.0747, "lr": 0.0005534618849600329, "epoch": 10.387409200968523, "percentage": 51.94, "elapsed_time": "0:28:49", "remaining_time": "0:26:40", "throughput": 2032.1, "total_tokens": 3515328}
{"current_steps": 8585, "total_steps": 16520, "loss": 0.0118, "lr": 0.0005529366361940218, "epoch": 10.393462469733656, "percentage": 51.97, "elapsed_time": "0:28:50", "remaining_time": "0:26:39", "throughput": 2032.18, "total_tokens": 3517376}
{"current_steps": 8590, "total_steps": 16520, "loss": 0.1135, "lr": 0.0005524113283411453, "epoch": 10.39951573849879, "percentage": 52.0, "elapsed_time": "0:28:51", "remaining_time": "0:26:38", "throughput": 2032.3, "total_tokens": 3519584}
{"current_steps": 8595, "total_steps": 16520, "loss": 0.0102, "lr": 0.0005518859619877424, "epoch": 10.405569007263923, "percentage": 52.03, "elapsed_time": "0:28:52", "remaining_time": "0:26:37", "throughput": 2032.34, "total_tokens": 3521632}
{"current_steps": 8600, "total_steps": 16520, "loss": 0.0497, "lr": 0.0005513605377202167, "epoch": 10.411622276029055, "percentage": 52.06, "elapsed_time": "0:28:53", "remaining_time": "0:26:36", "throughput": 2032.47, "total_tokens": 3523840}
{"current_steps": 8605, "total_steps": 16520, "loss": 0.088, "lr": 0.000550835056125037, "epoch": 10.41767554479419, "percentage": 52.09, "elapsed_time": "0:28:54", "remaining_time": "0:26:35", "throughput": 2032.54, "total_tokens": 3525952}
{"current_steps": 8610, "total_steps": 16520, "loss": 0.0253, "lr": 0.0005503095177887355, "epoch": 10.423728813559322, "percentage": 52.12, "elapsed_time": "0:28:55", "remaining_time": "0:26:34", "throughput": 2032.66, "total_tokens": 3528160}
{"current_steps": 8615, "total_steps": 16520, "loss": 0.0947, "lr": 0.0005497839232979084, "epoch": 10.429782082324456, "percentage": 52.15, "elapsed_time": "0:28:56", "remaining_time": "0:26:33", "throughput": 2032.73, "total_tokens": 3530272}
{"current_steps": 8620, "total_steps": 16520, "loss": 0.0454, "lr": 0.0005492582732392141, "epoch": 10.435835351089588, "percentage": 52.18, "elapsed_time": "0:28:57", "remaining_time": "0:26:32", "throughput": 2032.79, "total_tokens": 3532352}
{"current_steps": 8625, "total_steps": 16520, "loss": 0.024, "lr": 0.0005487325681993732, "epoch": 10.441888619854721, "percentage": 52.21, "elapsed_time": "0:28:58", "remaining_time": "0:26:31", "throughput": 2032.8, "total_tokens": 3534336}
{"current_steps": 8630, "total_steps": 16520, "loss": 0.0363, "lr": 0.0005482068087651677, "epoch": 10.447941888619855, "percentage": 52.24, "elapsed_time": "0:28:59", "remaining_time": "0:26:30", "throughput": 2032.83, "total_tokens": 3536288}
{"current_steps": 8635, "total_steps": 16520, "loss": 0.016, "lr": 0.0005476809955234403, "epoch": 10.453995157384988, "percentage": 52.27, "elapsed_time": "0:29:00", "remaining_time": "0:26:29", "throughput": 2032.87, "total_tokens": 3538336}
{"current_steps": 8640, "total_steps": 16520, "loss": 0.0157, "lr": 0.0005471551290610938, "epoch": 10.460048426150122, "percentage": 52.3, "elapsed_time": "0:29:01", "remaining_time": "0:26:28", "throughput": 2032.94, "total_tokens": 3540448}
{"current_steps": 8645, "total_steps": 16520, "loss": 0.013, "lr": 0.00054662920996509, "epoch": 10.466101694915254, "percentage": 52.33, "elapsed_time": "0:29:02", "remaining_time": "0:26:27", "throughput": 2032.98, "total_tokens": 3542432}
{"current_steps": 8650, "total_steps": 16520, "loss": 0.0385, "lr": 0.0005461032388224501, "epoch": 10.472154963680387, "percentage": 52.36, "elapsed_time": "0:29:03", "remaining_time": "0:26:26", "throughput": 2033.03, "total_tokens": 3544352}
{"current_steps": 8655, "total_steps": 16520, "loss": 0.0426, "lr": 0.0005455772162202531, "epoch": 10.478208232445521, "percentage": 52.39, "elapsed_time": "0:29:04", "remaining_time": "0:26:25", "throughput": 2033.08, "total_tokens": 3546400}
{"current_steps": 8660, "total_steps": 16520, "loss": 0.0224, "lr": 0.0005450511427456351, "epoch": 10.484261501210653, "percentage": 52.42, "elapsed_time": "0:29:05", "remaining_time": "0:26:24", "throughput": 2033.19, "total_tokens": 3548576}
{"current_steps": 8665, "total_steps": 16520, "loss": 0.0443, "lr": 0.0005445250189857895, "epoch": 10.490314769975788, "percentage": 52.45, "elapsed_time": "0:29:06", "remaining_time": "0:26:23", "throughput": 2033.25, "total_tokens": 3550592}
{"current_steps": 8670, "total_steps": 16520, "loss": 0.0324, "lr": 0.0005439988455279656, "epoch": 10.49636803874092, "percentage": 52.48, "elapsed_time": "0:29:07", "remaining_time": "0:26:21", "throughput": 2033.29, "total_tokens": 3552576}
{"current_steps": 8675, "total_steps": 16520, "loss": 0.0607, "lr": 0.0005434726229594682, "epoch": 10.502421307506053, "percentage": 52.51, "elapsed_time": "0:29:08", "remaining_time": "0:26:20", "throughput": 2033.31, "total_tokens": 3554592}
{"current_steps": 8680, "total_steps": 16520, "loss": 0.0952, "lr": 0.000542946351867657, "epoch": 10.508474576271187, "percentage": 52.54, "elapsed_time": "0:29:09", "remaining_time": "0:26:19", "throughput": 2033.4, "total_tokens": 3556672}
{"current_steps": 8685, "total_steps": 16520, "loss": 0.0256, "lr": 0.0005424200328399456, "epoch": 10.51452784503632, "percentage": 52.57, "elapsed_time": "0:29:10", "remaining_time": "0:26:18", "throughput": 2033.49, "total_tokens": 3558784}
{"current_steps": 8690, "total_steps": 16520, "loss": 0.0417, "lr": 0.0005418936664638012, "epoch": 10.520581113801454, "percentage": 52.6, "elapsed_time": "0:29:11", "remaining_time": "0:26:17", "throughput": 2033.55, "total_tokens": 3560800}
{"current_steps": 8695, "total_steps": 16520, "loss": 0.0778, "lr": 0.0005413672533267443, "epoch": 10.526634382566586, "percentage": 52.63, "elapsed_time": "0:29:12", "remaining_time": "0:26:16", "throughput": 2033.62, "total_tokens": 3562912}
{"current_steps": 8700, "total_steps": 16520, "loss": 0.0249, "lr": 0.0005408407940163469, "epoch": 10.532687651331718, "percentage": 52.66, "elapsed_time": "0:29:12", "remaining_time": "0:26:15", "throughput": 2033.66, "total_tokens": 3564960}
{"current_steps": 8705, "total_steps": 16520, "loss": 0.1086, "lr": 0.0005403142891202329, "epoch": 10.538740920096853, "percentage": 52.69, "elapsed_time": "0:29:13", "remaining_time": "0:26:14", "throughput": 2033.68, "total_tokens": 3566848}
{"current_steps": 8710, "total_steps": 16520, "loss": 0.0947, "lr": 0.0005397877392260772, "epoch": 10.544794188861985, "percentage": 52.72, "elapsed_time": "0:29:14", "remaining_time": "0:26:13", "throughput": 2033.75, "total_tokens": 3568832}
{"current_steps": 8715, "total_steps": 16520, "loss": 0.0229, "lr": 0.0005392611449216045, "epoch": 10.55084745762712, "percentage": 52.75, "elapsed_time": "0:29:15", "remaining_time": "0:26:12", "throughput": 2033.83, "total_tokens": 3570848}
{"current_steps": 8720, "total_steps": 16520, "loss": 0.0327, "lr": 0.0005387345067945896, "epoch": 10.556900726392252, "percentage": 52.78, "elapsed_time": "0:29:16", "remaining_time": "0:26:11", "throughput": 2033.85, "total_tokens": 3572800}
{"current_steps": 8725, "total_steps": 16520, "loss": 0.0224, "lr": 0.0005382078254328558, "epoch": 10.562953995157384, "percentage": 52.81, "elapsed_time": "0:29:17", "remaining_time": "0:26:10", "throughput": 2033.93, "total_tokens": 3574912}
{"current_steps": 8730, "total_steps": 16520, "loss": 0.0229, "lr": 0.0005376811014242748, "epoch": 10.569007263922519, "percentage": 52.85, "elapsed_time": "0:29:18", "remaining_time": "0:26:09", "throughput": 2033.97, "total_tokens": 3576896}
{"current_steps": 8735, "total_steps": 16520, "loss": 0.0761, "lr": 0.0005371543353567662, "epoch": 10.575060532687651, "percentage": 52.88, "elapsed_time": "0:29:19", "remaining_time": "0:26:08", "throughput": 2034.05, "total_tokens": 3578976}
{"current_steps": 8740, "total_steps": 16520, "loss": 0.0109, "lr": 0.0005366275278182957, "epoch": 10.581113801452785, "percentage": 52.91, "elapsed_time": "0:29:20", "remaining_time": "0:26:07", "throughput": 2034.07, "total_tokens": 3580928}
{"current_steps": 8745, "total_steps": 16520, "loss": 0.0042, "lr": 0.0005361006793968764, "epoch": 10.587167070217918, "percentage": 52.94, "elapsed_time": "0:29:21", "remaining_time": "0:26:06", "throughput": 2034.15, "total_tokens": 3582976}
{"current_steps": 8750, "total_steps": 16520, "loss": 0.0264, "lr": 0.0005355737906805659, "epoch": 10.59322033898305, "percentage": 52.97, "elapsed_time": "0:29:22", "remaining_time": "0:26:05", "throughput": 2034.25, "total_tokens": 3585184}
{"current_steps": 8755, "total_steps": 16520, "loss": 0.0179, "lr": 0.0005350468622574679, "epoch": 10.599273607748184, "percentage": 53.0, "elapsed_time": "0:29:23", "remaining_time": "0:26:03", "throughput": 2034.34, "total_tokens": 3587200}
{"current_steps": 8760, "total_steps": 16520, "loss": 0.0234, "lr": 0.0005345198947157296, "epoch": 10.605326876513317, "percentage": 53.03, "elapsed_time": "0:29:24", "remaining_time": "0:26:02", "throughput": 2034.41, "total_tokens": 3589312}
{"current_steps": 8765, "total_steps": 16520, "loss": 0.0812, "lr": 0.0005339928886435423, "epoch": 10.611380145278451, "percentage": 53.06, "elapsed_time": "0:29:25", "remaining_time": "0:26:01", "throughput": 2034.46, "total_tokens": 3591392}
{"current_steps": 8770, "total_steps": 16520, "loss": 0.0253, "lr": 0.0005334658446291399, "epoch": 10.617433414043584, "percentage": 53.09, "elapsed_time": "0:29:26", "remaining_time": "0:26:00", "throughput": 2034.56, "total_tokens": 3593440}
{"current_steps": 8775, "total_steps": 16520, "loss": 0.0073, "lr": 0.0005329387632607988, "epoch": 10.623486682808716, "percentage": 53.12, "elapsed_time": "0:29:27", "remaining_time": "0:25:59", "throughput": 2034.56, "total_tokens": 3595328}
{"current_steps": 8780, "total_steps": 16520, "loss": 0.0207, "lr": 0.0005324116451268377, "epoch": 10.62953995157385, "percentage": 53.15, "elapsed_time": "0:29:28", "remaining_time": "0:25:58", "throughput": 2034.65, "total_tokens": 3597472}
{"current_steps": 8785, "total_steps": 16520, "loss": 0.0708, "lr": 0.0005318844908156154, "epoch": 10.635593220338983, "percentage": 53.18, "elapsed_time": "0:29:29", "remaining_time": "0:25:57", "throughput": 2034.73, "total_tokens": 3599584}
{"current_steps": 8790, "total_steps": 16520, "loss": 0.0043, "lr": 0.0005313573009155317, "epoch": 10.641646489104117, "percentage": 53.21, "elapsed_time": "0:29:30", "remaining_time": "0:25:56", "throughput": 2034.76, "total_tokens": 3601600}
{"current_steps": 8795, "total_steps": 16520, "loss": 0.053, "lr": 0.0005308300760150258, "epoch": 10.64769975786925, "percentage": 53.24, "elapsed_time": "0:29:31", "remaining_time": "0:25:55", "throughput": 2034.81, "total_tokens": 3603680}
{"current_steps": 8800, "total_steps": 16520, "loss": 0.0375, "lr": 0.0005303028167025762, "epoch": 10.653753026634382, "percentage": 53.27, "elapsed_time": "0:29:31", "remaining_time": "0:25:54", "throughput": 2034.85, "total_tokens": 3605728}
{"current_steps": 8805, "total_steps": 16520, "loss": 0.0616, "lr": 0.0005297755235666996, "epoch": 10.659806295399516, "percentage": 53.3, "elapsed_time": "0:29:32", "remaining_time": "0:25:53", "throughput": 2034.88, "total_tokens": 3607680}
{"current_steps": 8810, "total_steps": 16520, "loss": 0.0232, "lr": 0.0005292481971959506, "epoch": 10.665859564164649, "percentage": 53.33, "elapsed_time": "0:29:33", "remaining_time": "0:25:52", "throughput": 2034.95, "total_tokens": 3609728}
{"current_steps": 8815, "total_steps": 16520, "loss": 0.0038, "lr": 0.0005287208381789209, "epoch": 10.671912832929783, "percentage": 53.36, "elapsed_time": "0:29:34", "remaining_time": "0:25:51", "throughput": 2035.03, "total_tokens": 3611808}
{"current_steps": 8820, "total_steps": 16520, "loss": 0.0516, "lr": 0.0005281934471042387, "epoch": 10.677966101694915, "percentage": 53.39, "elapsed_time": "0:29:35", "remaining_time": "0:25:50", "throughput": 2035.06, "total_tokens": 3613696}
{"current_steps": 8825, "total_steps": 16520, "loss": 0.0453, "lr": 0.0005276660245605675, "epoch": 10.684019370460048, "percentage": 53.42, "elapsed_time": "0:29:36", "remaining_time": "0:25:49", "throughput": 2035.12, "total_tokens": 3615776}
{"current_steps": 8830, "total_steps": 16520, "loss": 0.0113, "lr": 0.0005271385711366066, "epoch": 10.690072639225182, "percentage": 53.45, "elapsed_time": "0:29:37", "remaining_time": "0:25:48", "throughput": 2035.19, "total_tokens": 3617824}
{"current_steps": 8835, "total_steps": 16520, "loss": 0.01, "lr": 0.0005266110874210893, "epoch": 10.696125907990314, "percentage": 53.48, "elapsed_time": "0:29:38", "remaining_time": "0:25:47", "throughput": 2035.23, "total_tokens": 3619808}
{"current_steps": 8840, "total_steps": 16520, "loss": 0.039, "lr": 0.0005260835740027831, "epoch": 10.702179176755449, "percentage": 53.51, "elapsed_time": "0:29:39", "remaining_time": "0:25:46", "throughput": 2035.4, "total_tokens": 3622176}
{"current_steps": 8845, "total_steps": 16520, "loss": 0.0211, "lr": 0.0005255560314704884, "epoch": 10.708232445520581, "percentage": 53.54, "elapsed_time": "0:29:40", "remaining_time": "0:25:45", "throughput": 2035.42, "total_tokens": 3624192}
{"current_steps": 8850, "total_steps": 16520, "loss": 0.0184, "lr": 0.0005250284604130379, "epoch": 10.714285714285714, "percentage": 53.57, "elapsed_time": "0:29:41", "remaining_time": "0:25:44", "throughput": 2035.53, "total_tokens": 3626400}
{"current_steps": 8855, "total_steps": 16520, "loss": 0.025, "lr": 0.0005245008614192965, "epoch": 10.720338983050848, "percentage": 53.6, "elapsed_time": "0:29:42", "remaining_time": "0:25:42", "throughput": 2035.56, "total_tokens": 3628256}
{"current_steps": 8860, "total_steps": 16520, "loss": 0.1007, "lr": 0.0005239732350781601, "epoch": 10.72639225181598, "percentage": 53.63, "elapsed_time": "0:29:43", "remaining_time": "0:25:41", "throughput": 2035.63, "total_tokens": 3630304}
{"current_steps": 8865, "total_steps": 16520, "loss": 0.0463, "lr": 0.0005234455819785554, "epoch": 10.732445520581114, "percentage": 53.66, "elapsed_time": "0:29:44", "remaining_time": "0:25:40", "throughput": 2035.67, "total_tokens": 3632352}
{"current_steps": 8870, "total_steps": 16520, "loss": 0.0404, "lr": 0.0005229179027094384, "epoch": 10.738498789346247, "percentage": 53.69, "elapsed_time": "0:29:45", "remaining_time": "0:25:39", "throughput": 2035.68, "total_tokens": 3634336}
{"current_steps": 8875, "total_steps": 16520, "loss": 0.0248, "lr": 0.0005223901978597949, "epoch": 10.74455205811138, "percentage": 53.72, "elapsed_time": "0:29:46", "remaining_time": "0:25:38", "throughput": 2035.76, "total_tokens": 3636416}
{"current_steps": 8880, "total_steps": 16520, "loss": 0.069, "lr": 0.0005218624680186389, "epoch": 10.750605326876514, "percentage": 53.75, "elapsed_time": "0:29:47", "remaining_time": "0:25:37", "throughput": 2035.82, "total_tokens": 3638432}
{"current_steps": 8885, "total_steps": 16520, "loss": 0.0141, "lr": 0.0005213347137750125, "epoch": 10.756658595641646, "percentage": 53.78, "elapsed_time": "0:29:48", "remaining_time": "0:25:36", "throughput": 2035.87, "total_tokens": 3640512}
{"current_steps": 8890, "total_steps": 16520, "loss": 0.0104, "lr": 0.0005208069357179847, "epoch": 10.76271186440678, "percentage": 53.81, "elapsed_time": "0:29:49", "remaining_time": "0:25:35", "throughput": 2035.96, "total_tokens": 3642656}
{"current_steps": 8895, "total_steps": 16520, "loss": 0.0383, "lr": 0.0005202791344366516, "epoch": 10.768765133171913, "percentage": 53.84, "elapsed_time": "0:29:50", "remaining_time": "0:25:34", "throughput": 2036.04, "total_tokens": 3644672}
{"current_steps": 8900, "total_steps": 16520, "loss": 0.0906, "lr": 0.0005197513105201349, "epoch": 10.774818401937045, "percentage": 53.87, "elapsed_time": "0:29:51", "remaining_time": "0:25:33", "throughput": 2036.08, "total_tokens": 3646720}
{"current_steps": 8905, "total_steps": 16520, "loss": 0.0541, "lr": 0.0005192234645575814, "epoch": 10.78087167070218, "percentage": 53.9, "elapsed_time": "0:29:52", "remaining_time": "0:25:32", "throughput": 2036.12, "total_tokens": 3648768}
{"current_steps": 8910, "total_steps": 16520, "loss": 0.0751, "lr": 0.0005186955971381629, "epoch": 10.786924939467312, "percentage": 53.93, "elapsed_time": "0:29:52", "remaining_time": "0:25:31", "throughput": 2036.17, "total_tokens": 3650848}
{"current_steps": 8915, "total_steps": 16520, "loss": 0.1352, "lr": 0.0005181677088510748, "epoch": 10.792978208232446, "percentage": 53.96, "elapsed_time": "0:29:53", "remaining_time": "0:25:30", "throughput": 2036.21, "total_tokens": 3652896}
{"current_steps": 8920, "total_steps": 16520, "loss": 0.0105, "lr": 0.0005176398002855362, "epoch": 10.799031476997579, "percentage": 54.0, "elapsed_time": "0:29:54", "remaining_time": "0:25:29", "throughput": 2036.26, "total_tokens": 3654944}
{"current_steps": 8925, "total_steps": 16520, "loss": 0.066, "lr": 0.0005171118720307883, "epoch": 10.805084745762711, "percentage": 54.03, "elapsed_time": "0:29:55", "remaining_time": "0:25:28", "throughput": 2036.34, "total_tokens": 3657120}
{"current_steps": 8930, "total_steps": 16520, "loss": 0.0392, "lr": 0.0005165839246760947, "epoch": 10.811138014527845, "percentage": 54.06, "elapsed_time": "0:29:56", "remaining_time": "0:25:27", "throughput": 2036.4, "total_tokens": 3659200}
{"current_steps": 8935, "total_steps": 16520, "loss": 0.069, "lr": 0.0005160559588107401, "epoch": 10.817191283292978, "percentage": 54.09, "elapsed_time": "0:29:57", "remaining_time": "0:25:26", "throughput": 2036.45, "total_tokens": 3661216}
{"current_steps": 8940, "total_steps": 16520, "loss": 0.0129, "lr": 0.0005155279750240302, "epoch": 10.823244552058112, "percentage": 54.12, "elapsed_time": "0:29:58", "remaining_time": "0:25:25", "throughput": 2036.49, "total_tokens": 3663264}
{"current_steps": 8945, "total_steps": 16520, "loss": 0.0747, "lr": 0.0005149999739052902, "epoch": 10.829297820823244, "percentage": 54.15, "elapsed_time": "0:29:59", "remaining_time": "0:25:24", "throughput": 2036.55, "total_tokens": 3665344}
{"current_steps": 8950, "total_steps": 16520, "loss": 0.0765, "lr": 0.0005144719560438651, "epoch": 10.835351089588377, "percentage": 54.18, "elapsed_time": "0:30:00", "remaining_time": "0:25:23", "throughput": 2036.6, "total_tokens": 3667296}
{"current_steps": 8955, "total_steps": 16520, "loss": 0.0659, "lr": 0.000513943922029118, "epoch": 10.841404358353511, "percentage": 54.21, "elapsed_time": "0:30:01", "remaining_time": "0:25:21", "throughput": 2036.63, "total_tokens": 3669280}
{"current_steps": 8960, "total_steps": 16520, "loss": 0.0117, "lr": 0.0005134158724504308, "epoch": 10.847457627118644, "percentage": 54.24, "elapsed_time": "0:30:02", "remaining_time": "0:25:20", "throughput": 2036.69, "total_tokens": 3671360}
{"current_steps": 8965, "total_steps": 16520, "loss": 0.0634, "lr": 0.0005128878078972023, "epoch": 10.853510895883778, "percentage": 54.27, "elapsed_time": "0:30:03", "remaining_time": "0:25:19", "throughput": 2036.73, "total_tokens": 3673344}
{"current_steps": 8970, "total_steps": 16520, "loss": 0.0643, "lr": 0.000512359728958848, "epoch": 10.85956416464891, "percentage": 54.3, "elapsed_time": "0:30:04", "remaining_time": "0:25:18", "throughput": 2036.8, "total_tokens": 3675456}
{"current_steps": 8975, "total_steps": 16520, "loss": 0.0311, "lr": 0.0005118316362247996, "epoch": 10.865617433414045, "percentage": 54.33, "elapsed_time": "0:30:05", "remaining_time": "0:25:17", "throughput": 2036.86, "total_tokens": 3677568}
{"current_steps": 8980, "total_steps": 16520, "loss": 0.0744, "lr": 0.0005113035302845043, "epoch": 10.871670702179177, "percentage": 54.36, "elapsed_time": "0:30:06", "remaining_time": "0:25:16", "throughput": 2036.88, "total_tokens": 3679520}
{"current_steps": 8985, "total_steps": 16520, "loss": 0.0983, "lr": 0.0005107754117274236, "epoch": 10.87772397094431, "percentage": 54.39, "elapsed_time": "0:30:07", "remaining_time": "0:25:15", "throughput": 2036.93, "total_tokens": 3681600}
{"current_steps": 8990, "total_steps": 16520, "loss": 0.0316, "lr": 0.0005102472811430336, "epoch": 10.883777239709444, "percentage": 54.42, "elapsed_time": "0:30:08", "remaining_time": "0:25:14", "throughput": 2036.96, "total_tokens": 3683520}
{"current_steps": 8995, "total_steps": 16520, "loss": 0.0132, "lr": 0.0005097191391208233, "epoch": 10.889830508474576, "percentage": 54.45, "elapsed_time": "0:30:09", "remaining_time": "0:25:13", "throughput": 2037.01, "total_tokens": 3685536}
{"current_steps": 9000, "total_steps": 16520, "loss": 0.0529, "lr": 0.0005091909862502953, "epoch": 10.89588377723971, "percentage": 54.48, "elapsed_time": "0:30:10", "remaining_time": "0:25:12", "throughput": 2037.04, "total_tokens": 3687552}
{"current_steps": 9005, "total_steps": 16520, "loss": 0.1022, "lr": 0.0005086628231209632, "epoch": 10.901937046004843, "percentage": 54.51, "elapsed_time": "0:30:11", "remaining_time": "0:25:11", "throughput": 2037.08, "total_tokens": 3689632}
{"current_steps": 9010, "total_steps": 16520, "loss": 0.0197, "lr": 0.0005081346503223531, "epoch": 10.907990314769975, "percentage": 54.54, "elapsed_time": "0:30:12", "remaining_time": "0:25:10", "throughput": 2037.13, "total_tokens": 3691648}
{"current_steps": 9015, "total_steps": 16520, "loss": 0.0153, "lr": 0.000507606468444001, "epoch": 10.91404358353511, "percentage": 54.57, "elapsed_time": "0:30:13", "remaining_time": "0:25:09", "throughput": 2037.18, "total_tokens": 3693728}
{"current_steps": 9020, "total_steps": 16520, "loss": 0.0562, "lr": 0.0005070782780754539, "epoch": 10.920096852300242, "percentage": 54.6, "elapsed_time": "0:30:14", "remaining_time": "0:25:08", "throughput": 2037.24, "total_tokens": 3695840}
{"current_steps": 9025, "total_steps": 16520, "loss": 0.0214, "lr": 0.0005065500798062675, "epoch": 10.926150121065376, "percentage": 54.63, "elapsed_time": "0:30:15", "remaining_time": "0:25:07", "throughput": 2037.27, "total_tokens": 3697856}
{"current_steps": 9030, "total_steps": 16520, "loss": 0.0718, "lr": 0.0005060218742260069, "epoch": 10.932203389830509, "percentage": 54.66, "elapsed_time": "0:30:16", "remaining_time": "0:25:06", "throughput": 2037.33, "total_tokens": 3699968}
{"current_steps": 9035, "total_steps": 16520, "loss": 0.0602, "lr": 0.0005054936619242448, "epoch": 10.938256658595641, "percentage": 54.69, "elapsed_time": "0:30:17", "remaining_time": "0:25:05", "throughput": 2037.43, "total_tokens": 3702080}
{"current_steps": 9040, "total_steps": 16520, "loss": 0.0792, "lr": 0.0005049654434905619, "epoch": 10.944309927360775, "percentage": 54.72, "elapsed_time": "0:30:17", "remaining_time": "0:25:04", "throughput": 2037.45, "total_tokens": 3704032}
{"current_steps": 9045, "total_steps": 16520, "loss": 0.0537, "lr": 0.0005044372195145455, "epoch": 10.950363196125908, "percentage": 54.75, "elapsed_time": "0:30:18", "remaining_time": "0:25:03", "throughput": 2037.53, "total_tokens": 3706176}
{"current_steps": 9050, "total_steps": 16520, "loss": 0.0451, "lr": 0.0005039089905857895, "epoch": 10.956416464891042, "percentage": 54.78, "elapsed_time": "0:30:19", "remaining_time": "0:25:02", "throughput": 2037.56, "total_tokens": 3708128}
{"current_steps": 9055, "total_steps": 16520, "loss": 0.026, "lr": 0.0005033807572938922, "epoch": 10.962469733656174, "percentage": 54.81, "elapsed_time": "0:30:20", "remaining_time": "0:25:01", "throughput": 2037.57, "total_tokens": 3710080}
{"current_steps": 9060, "total_steps": 16520, "loss": 0.0267, "lr": 0.0005028525202284582, "epoch": 10.968523002421307, "percentage": 54.84, "elapsed_time": "0:30:21", "remaining_time": "0:25:00", "throughput": 2037.62, "total_tokens": 3712096}
{"current_steps": 9065, "total_steps": 16520, "loss": 0.0366, "lr": 0.0005023242799790953, "epoch": 10.974576271186441, "percentage": 54.87, "elapsed_time": "0:30:22", "remaining_time": "0:24:59", "throughput": 2037.68, "total_tokens": 3714208}
{"current_steps": 9070, "total_steps": 16520, "loss": 0.0098, "lr": 0.0005017960371354155, "epoch": 10.980629539951574, "percentage": 54.9, "elapsed_time": "0:30:23", "remaining_time": "0:24:58", "throughput": 2037.78, "total_tokens": 3716384}
{"current_steps": 9075, "total_steps": 16520, "loss": 0.0279, "lr": 0.0005012677922870331, "epoch": 10.986682808716708, "percentage": 54.93, "elapsed_time": "0:30:24", "remaining_time": "0:24:56", "throughput": 2037.83, "total_tokens": 3718464}
{"current_steps": 9080, "total_steps": 16520, "loss": 0.0385, "lr": 0.0005007395460235653, "epoch": 10.99273607748184, "percentage": 54.96, "elapsed_time": "0:30:25", "remaining_time": "0:24:55", "throughput": 2037.84, "total_tokens": 3720448}
{"current_steps": 9085, "total_steps": 16520, "loss": 0.0091, "lr": 0.0005002112989346303, "epoch": 10.998789346246973, "percentage": 54.99, "elapsed_time": "0:30:26", "remaining_time": "0:24:54", "throughput": 2037.9, "total_tokens": 3722432}
{"current_steps": 9086, "total_steps": 16520, "eval_loss": 0.11754854768514633, "epoch": 11.0, "percentage": 55.0, "elapsed_time": "0:30:34", "remaining_time": "0:25:01", "throughput": 2028.99, "total_tokens": 3722552}
{"current_steps": 9090, "total_steps": 16520, "loss": 0.0053, "lr": 0.0004996830516098473, "epoch": 11.004842615012107, "percentage": 55.02, "elapsed_time": "0:30:36", "remaining_time": "0:25:01", "throughput": 2027.89, "total_tokens": 3724216}
{"current_steps": 9095, "total_steps": 16520, "loss": 0.0173, "lr": 0.0004991548046388361, "epoch": 11.01089588377724, "percentage": 55.05, "elapsed_time": "0:30:37", "remaining_time": "0:25:00", "throughput": 2027.94, "total_tokens": 3726232}