train_cb_1756128976 / trainer_log.jsonl
rbelanec's picture
Training in progress, step 570
f06acae verified
{"current_steps": 5, "total_steps": 570, "loss": 1.1877, "lr": 3.5087719298245615e-06, "epoch": 0.08771929824561403, "percentage": 0.88, "elapsed_time": "0:00:02", "remaining_time": "0:05:06", "throughput": 1311.39, "total_tokens": 3552}
{"current_steps": 10, "total_steps": 570, "loss": 1.309, "lr": 7.894736842105263e-06, "epoch": 0.17543859649122806, "percentage": 1.75, "elapsed_time": "0:00:03", "remaining_time": "0:03:10", "throughput": 2134.29, "total_tokens": 7264}
{"current_steps": 15, "total_steps": 570, "loss": 1.1793, "lr": 1.2280701754385964e-05, "epoch": 0.2631578947368421, "percentage": 2.63, "elapsed_time": "0:00:04", "remaining_time": "0:02:29", "throughput": 2599.39, "total_tokens": 10528}
{"current_steps": 20, "total_steps": 570, "loss": 1.0865, "lr": 1.6666666666666667e-05, "epoch": 0.3508771929824561, "percentage": 3.51, "elapsed_time": "0:00:04", "remaining_time": "0:02:12", "throughput": 3065.51, "total_tokens": 14720}
{"current_steps": 25, "total_steps": 570, "loss": 1.2393, "lr": 2.105263157894737e-05, "epoch": 0.43859649122807015, "percentage": 4.39, "elapsed_time": "0:00:05", "remaining_time": "0:01:58", "throughput": 3309.94, "total_tokens": 18016}
{"current_steps": 29, "total_steps": 570, "eval_loss": 1.1732473373413086, "epoch": 0.5087719298245614, "percentage": 5.09, "elapsed_time": "0:00:06", "remaining_time": "0:02:01", "throughput": 3072.56, "total_tokens": 20064}
{"current_steps": 30, "total_steps": 570, "loss": 1.3136, "lr": 2.5438596491228074e-05, "epoch": 0.5263157894736842, "percentage": 5.26, "elapsed_time": "0:00:07", "remaining_time": "0:02:16", "throughput": 2723.48, "total_tokens": 20640}
{"current_steps": 35, "total_steps": 570, "loss": 1.1864, "lr": 2.9824561403508772e-05, "epoch": 0.6140350877192983, "percentage": 6.14, "elapsed_time": "0:00:08", "remaining_time": "0:02:07", "throughput": 2970.86, "total_tokens": 24800}
{"current_steps": 40, "total_steps": 570, "loss": 1.1892, "lr": 3.421052631578947e-05, "epoch": 0.7017543859649122, "percentage": 7.02, "elapsed_time": "0:00:09", "remaining_time": "0:01:59", "throughput": 3109.17, "total_tokens": 28064}
{"current_steps": 45, "total_steps": 570, "loss": 1.3389, "lr": 3.859649122807018e-05, "epoch": 0.7894736842105263, "percentage": 7.89, "elapsed_time": "0:00:09", "remaining_time": "0:01:52", "throughput": 3210.1, "total_tokens": 30944}
{"current_steps": 50, "total_steps": 570, "loss": 1.1066, "lr": 4.298245614035088e-05, "epoch": 0.8771929824561403, "percentage": 8.77, "elapsed_time": "0:00:10", "remaining_time": "0:01:46", "throughput": 3285.84, "total_tokens": 33664}
{"current_steps": 55, "total_steps": 570, "loss": 1.196, "lr": 4.736842105263158e-05, "epoch": 0.9649122807017544, "percentage": 9.65, "elapsed_time": "0:00:10", "remaining_time": "0:01:41", "throughput": 3355.63, "total_tokens": 36320}
{"current_steps": 58, "total_steps": 570, "eval_loss": 1.1732473373413086, "epoch": 1.0175438596491229, "percentage": 10.18, "elapsed_time": "0:00:12", "remaining_time": "0:01:46", "throughput": 3121.62, "total_tokens": 37832}
{"current_steps": 60, "total_steps": 570, "loss": 0.9704, "lr": 4.999812487773597e-05, "epoch": 1.0526315789473684, "percentage": 10.53, "elapsed_time": "0:00:13", "remaining_time": "0:01:53", "throughput": 2933.05, "total_tokens": 39080}
{"current_steps": 65, "total_steps": 570, "loss": 1.0932, "lr": 4.997703298253406e-05, "epoch": 1.1403508771929824, "percentage": 11.4, "elapsed_time": "0:00:14", "remaining_time": "0:01:48", "throughput": 3037.75, "total_tokens": 42536}
{"current_steps": 70, "total_steps": 570, "loss": 1.1462, "lr": 4.993252512887069e-05, "epoch": 1.2280701754385965, "percentage": 12.28, "elapsed_time": "0:00:14", "remaining_time": "0:01:44", "throughput": 3114.37, "total_tokens": 45608}
{"current_steps": 75, "total_steps": 570, "loss": 1.0703, "lr": 4.986464304284091e-05, "epoch": 1.3157894736842106, "percentage": 13.16, "elapsed_time": "0:00:15", "remaining_time": "0:01:41", "throughput": 3214.41, "total_tokens": 49352}
{"current_steps": 80, "total_steps": 570, "loss": 1.0132, "lr": 4.977345036387331e-05, "epoch": 1.4035087719298245, "percentage": 14.04, "elapsed_time": "0:00:15", "remaining_time": "0:01:37", "throughput": 3282.61, "total_tokens": 52328}
{"current_steps": 85, "total_steps": 570, "loss": 0.6503, "lr": 4.965903258506806e-05, "epoch": 1.4912280701754386, "percentage": 14.91, "elapsed_time": "0:00:16", "remaining_time": "0:01:35", "throughput": 3377.41, "total_tokens": 56328}
{"current_steps": 87, "total_steps": 570, "eval_loss": 0.559042751789093, "epoch": 1.526315789473684, "percentage": 15.26, "elapsed_time": "0:00:17", "remaining_time": "0:01:37", "throughput": 3277.72, "total_tokens": 57288}
{"current_steps": 90, "total_steps": 570, "loss": 0.6947, "lr": 4.952149697304716e-05, "epoch": 1.5789473684210527, "percentage": 15.79, "elapsed_time": "0:00:18", "remaining_time": "0:01:40", "throughput": 3148.5, "total_tokens": 59048}
{"current_steps": 95, "total_steps": 570, "loss": 0.3543, "lr": 4.9360972467392056e-05, "epoch": 1.6666666666666665, "percentage": 16.67, "elapsed_time": "0:00:19", "remaining_time": "0:01:37", "throughput": 3215.06, "total_tokens": 62504}
{"current_steps": 100, "total_steps": 570, "loss": 0.3442, "lr": 4.917760955976277e-05, "epoch": 1.7543859649122808, "percentage": 17.54, "elapsed_time": "0:00:20", "remaining_time": "0:01:34", "throughput": 3270.42, "total_tokens": 65832}
{"current_steps": 105, "total_steps": 570, "loss": 0.3672, "lr": 4.897158015281209e-05, "epoch": 1.8421052631578947, "percentage": 18.42, "elapsed_time": "0:00:20", "remaining_time": "0:01:31", "throughput": 3317.43, "total_tokens": 68808}
{"current_steps": 110, "total_steps": 570, "loss": 0.194, "lr": 4.874307739902689e-05, "epoch": 1.9298245614035088, "percentage": 19.3, "elapsed_time": "0:00:21", "remaining_time": "0:01:29", "throughput": 3367.73, "total_tokens": 71848}
{"current_steps": 115, "total_steps": 570, "loss": 0.225, "lr": 4.849231551964771e-05, "epoch": 2.017543859649123, "percentage": 20.18, "elapsed_time": "0:00:22", "remaining_time": "0:01:28", "throughput": 3321.69, "total_tokens": 74040}
{"current_steps": 116, "total_steps": 570, "eval_loss": 0.18880803883075714, "epoch": 2.0350877192982457, "percentage": 20.35, "elapsed_time": "0:00:22", "remaining_time": "0:01:29", "throughput": 3241.18, "total_tokens": 74520}
{"current_steps": 120, "total_steps": 570, "loss": 0.0831, "lr": 4.821952960383649e-05, "epoch": 2.1052631578947367, "percentage": 21.05, "elapsed_time": "0:00:24", "remaining_time": "0:01:31", "throughput": 3158.47, "total_tokens": 77272}
{"current_steps": 125, "total_steps": 570, "loss": 0.1083, "lr": 4.7924975388280524e-05, "epoch": 2.192982456140351, "percentage": 21.93, "elapsed_time": "0:00:25", "remaining_time": "0:01:29", "throughput": 3198.06, "total_tokens": 80280}
{"current_steps": 130, "total_steps": 570, "loss": 0.0922, "lr": 4.760892901743944e-05, "epoch": 2.280701754385965, "percentage": 22.81, "elapsed_time": "0:00:25", "remaining_time": "0:01:27", "throughput": 3242.24, "total_tokens": 83480}
{"current_steps": 135, "total_steps": 570, "loss": 0.1993, "lr": 4.727168678465988e-05, "epoch": 2.3684210526315788, "percentage": 23.68, "elapsed_time": "0:00:26", "remaining_time": "0:01:24", "throughput": 3273.27, "total_tokens": 86232}
{"current_steps": 140, "total_steps": 570, "loss": 0.153, "lr": 4.6913564854400595e-05, "epoch": 2.456140350877193, "percentage": 24.56, "elapsed_time": "0:00:27", "remaining_time": "0:01:22", "throughput": 3320.45, "total_tokens": 89656}
{"current_steps": 145, "total_steps": 570, "loss": 0.568, "lr": 4.6534898965828405e-05, "epoch": 2.543859649122807, "percentage": 25.44, "elapsed_time": "0:00:27", "remaining_time": "0:01:21", "throughput": 3364.87, "total_tokens": 93080}
{"current_steps": 145, "total_steps": 570, "eval_loss": 0.1757977306842804, "epoch": 2.543859649122807, "percentage": 25.44, "elapsed_time": "0:00:28", "remaining_time": "0:01:22", "throughput": 3297.43, "total_tokens": 93080}
{"current_steps": 150, "total_steps": 570, "loss": 0.1949, "lr": 4.613604411806285e-05, "epoch": 2.6315789473684212, "percentage": 26.32, "elapsed_time": "0:00:29", "remaining_time": "0:01:23", "throughput": 3228.58, "total_tokens": 96440}
{"current_steps": 155, "total_steps": 570, "loss": 0.1408, "lr": 4.5717374237364665e-05, "epoch": 2.719298245614035, "percentage": 27.19, "elapsed_time": "0:00:30", "remaining_time": "0:01:21", "throughput": 3280.08, "total_tokens": 100280}
{"current_steps": 160, "total_steps": 570, "loss": 0.1741, "lr": 4.5279281826580056e-05, "epoch": 2.807017543859649, "percentage": 28.07, "elapsed_time": "0:00:31", "remaining_time": "0:01:19", "throughput": 3316.98, "total_tokens": 103512}
{"current_steps": 165, "total_steps": 570, "loss": 0.1908, "lr": 4.482217759716946e-05, "epoch": 2.8947368421052633, "percentage": 28.95, "elapsed_time": "0:00:31", "remaining_time": "0:01:17", "throughput": 3342.08, "total_tokens": 106168}
{"current_steps": 170, "total_steps": 570, "loss": 0.1509, "lr": 4.434649008416565e-05, "epoch": 2.982456140350877, "percentage": 29.82, "elapsed_time": "0:00:32", "remaining_time": "0:01:16", "throughput": 3382.32, "total_tokens": 109624}
{"current_steps": 174, "total_steps": 570, "eval_loss": 0.16153018176555634, "epoch": 3.0526315789473686, "percentage": 30.53, "elapsed_time": "0:00:33", "remaining_time": "0:01:16", "throughput": 3311.6, "total_tokens": 111928}
{"current_steps": 175, "total_steps": 570, "loss": 0.1831, "lr": 4.385266524442241e-05, "epoch": 3.0701754385964914, "percentage": 30.7, "elapsed_time": "0:00:34", "remaining_time": "0:01:18", "throughput": 3233.28, "total_tokens": 112472}
{"current_steps": 180, "total_steps": 570, "loss": 0.0704, "lr": 4.334116603853007e-05, "epoch": 3.1578947368421053, "percentage": 31.58, "elapsed_time": "0:00:35", "remaining_time": "0:01:16", "throughput": 3262.85, "total_tokens": 115576}
{"current_steps": 185, "total_steps": 570, "loss": 0.0847, "lr": 4.2812471996790206e-05, "epoch": 3.245614035087719, "percentage": 32.46, "elapsed_time": "0:00:36", "remaining_time": "0:01:15", "throughput": 3297.69, "total_tokens": 119000}
{"current_steps": 190, "total_steps": 570, "loss": 0.0842, "lr": 4.226707876965611e-05, "epoch": 3.3333333333333335, "percentage": 33.33, "elapsed_time": "0:00:36", "remaining_time": "0:01:13", "throughput": 3331.27, "total_tokens": 122360}
{"current_steps": 195, "total_steps": 570, "loss": 0.2927, "lr": 4.1705497663060767e-05, "epoch": 3.4210526315789473, "percentage": 34.21, "elapsed_time": "0:00:37", "remaining_time": "0:01:11", "throughput": 3360.68, "total_tokens": 125496}
{"current_steps": 200, "total_steps": 570, "loss": 0.3084, "lr": 4.1128255159067665e-05, "epoch": 3.5087719298245617, "percentage": 35.09, "elapsed_time": "0:00:37", "remaining_time": "0:01:10", "throughput": 3390.41, "total_tokens": 128760}
{"current_steps": 203, "total_steps": 570, "eval_loss": 0.1591552346944809, "epoch": 3.56140350877193, "percentage": 35.61, "elapsed_time": "0:00:38", "remaining_time": "0:01:10", "throughput": 3364.6, "total_tokens": 131160}
{"current_steps": 205, "total_steps": 570, "loss": 0.117, "lr": 4.053589242229412e-05, "epoch": 3.5964912280701755, "percentage": 35.96, "elapsed_time": "0:00:40", "remaining_time": "0:01:11", "throughput": 3290.21, "total_tokens": 132248}
{"current_steps": 210, "total_steps": 570, "loss": 0.0982, "lr": 3.9928964792569655e-05, "epoch": 3.6842105263157894, "percentage": 36.84, "elapsed_time": "0:00:40", "remaining_time": "0:01:09", "throughput": 3310.65, "total_tokens": 135160}
{"current_steps": 215, "total_steps": 570, "loss": 0.3142, "lr": 3.930804126430513e-05, "epoch": 3.7719298245614032, "percentage": 37.72, "elapsed_time": "0:00:41", "remaining_time": "0:01:08", "throughput": 3334.34, "total_tokens": 138200}
{"current_steps": 220, "total_steps": 570, "loss": 0.0683, "lr": 3.867370395306068e-05, "epoch": 3.8596491228070176, "percentage": 38.6, "elapsed_time": "0:00:42", "remaining_time": "0:01:07", "throughput": 3365.07, "total_tokens": 141752}
{"current_steps": 225, "total_steps": 570, "loss": 0.1347, "lr": 3.8026547549812665e-05, "epoch": 3.9473684210526314, "percentage": 39.47, "elapsed_time": "0:00:42", "remaining_time": "0:01:05", "throughput": 3404.18, "total_tokens": 146008}
{"current_steps": 230, "total_steps": 570, "loss": 0.1682, "lr": 3.736717876343106e-05, "epoch": 4.035087719298246, "percentage": 40.35, "elapsed_time": "0:00:43", "remaining_time": "0:01:04", "throughput": 3385.29, "total_tokens": 148648}
{"current_steps": 232, "total_steps": 570, "eval_loss": 0.16104494035243988, "epoch": 4.0701754385964914, "percentage": 40.7, "elapsed_time": "0:00:44", "remaining_time": "0:01:05", "throughput": 3355.52, "total_tokens": 150056}
{"current_steps": 235, "total_steps": 570, "loss": 0.1885, "lr": 3.66962157518902e-05, "epoch": 4.12280701754386, "percentage": 41.23, "elapsed_time": "0:00:46", "remaining_time": "0:01:05", "throughput": 3295.22, "total_tokens": 151656}
{"current_steps": 240, "total_steps": 570, "loss": 0.3189, "lr": 3.601428754274584e-05, "epoch": 4.2105263157894735, "percentage": 42.11, "elapsed_time": "0:00:46", "remaining_time": "0:01:04", "throughput": 3307.34, "total_tokens": 154280}
{"current_steps": 245, "total_steps": 570, "loss": 0.2102, "lr": 3.532203344342212e-05, "epoch": 4.298245614035087, "percentage": 42.98, "elapsed_time": "0:00:47", "remaining_time": "0:01:02", "throughput": 3326.05, "total_tokens": 157160}
{"current_steps": 250, "total_steps": 570, "loss": 0.1598, "lr": 3.4620102441861143e-05, "epoch": 4.385964912280702, "percentage": 43.86, "elapsed_time": "0:00:47", "remaining_time": "0:01:01", "throughput": 3342.47, "total_tokens": 160072}
{"current_steps": 255, "total_steps": 570, "loss": 0.0827, "lr": 3.390915259809696e-05, "epoch": 4.473684210526316, "percentage": 44.74, "elapsed_time": "0:00:48", "remaining_time": "0:01:00", "throughput": 3370.63, "total_tokens": 163752}
{"current_steps": 260, "total_steps": 570, "loss": 0.0562, "lr": 3.318985042732461e-05, "epoch": 4.56140350877193, "percentage": 45.61, "elapsed_time": "0:00:49", "remaining_time": "0:00:58", "throughput": 3387.53, "total_tokens": 166600}
{"current_steps": 261, "total_steps": 570, "eval_loss": 0.16242551803588867, "epoch": 4.578947368421053, "percentage": 45.79, "elapsed_time": "0:00:49", "remaining_time": "0:00:59", "throughput": 3352.77, "total_tokens": 167208}
{"current_steps": 265, "total_steps": 570, "loss": 0.1684, "lr": 3.246287027504237e-05, "epoch": 4.649122807017544, "percentage": 46.49, "elapsed_time": "0:00:51", "remaining_time": "0:00:59", "throughput": 3306.52, "total_tokens": 169704}
{"current_steps": 270, "total_steps": 570, "loss": 0.1376, "lr": 3.172889368485311e-05, "epoch": 4.7368421052631575, "percentage": 47.37, "elapsed_time": "0:00:51", "remaining_time": "0:00:57", "throughput": 3327.24, "total_tokens": 173000}
{"current_steps": 275, "total_steps": 570, "loss": 0.1687, "lr": 3.0988608759517475e-05, "epoch": 4.824561403508772, "percentage": 48.25, "elapsed_time": "0:00:52", "remaining_time": "0:00:56", "throughput": 3356.39, "total_tokens": 177128}
{"current_steps": 280, "total_steps": 570, "loss": 0.0827, "lr": 3.0242709515857758e-05, "epoch": 4.912280701754386, "percentage": 49.12, "elapsed_time": "0:00:53", "remaining_time": "0:00:55", "throughput": 3381.02, "total_tokens": 180680}
{"current_steps": 285, "total_steps": 570, "loss": 0.0615, "lr": 2.949189523411747e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:00:54", "remaining_time": "0:00:54", "throughput": 3383.94, "total_tokens": 183280}
{"current_steps": 290, "total_steps": 570, "loss": 0.096, "lr": 2.8736869802386364e-05, "epoch": 5.087719298245614, "percentage": 50.88, "elapsed_time": "0:00:54", "remaining_time": "0:00:53", "throughput": 3384.99, "total_tokens": 186160}
{"current_steps": 290, "total_steps": 570, "eval_loss": 0.15590623021125793, "epoch": 5.087719298245614, "percentage": 50.88, "elapsed_time": "0:00:55", "remaining_time": "0:00:53", "throughput": 3349.17, "total_tokens": 186160}
{"current_steps": 295, "total_steps": 570, "loss": 0.1093, "lr": 2.797834105670559e-05, "epoch": 5.175438596491228, "percentage": 51.75, "elapsed_time": "0:00:57", "remaining_time": "0:00:53", "throughput": 3314.52, "total_tokens": 189584}
{"current_steps": 300, "total_steps": 570, "loss": 0.157, "lr": 2.7217020117471793e-05, "epoch": 5.2631578947368425, "percentage": 52.63, "elapsed_time": "0:00:57", "remaining_time": "0:00:52", "throughput": 3338.14, "total_tokens": 193296}
{"current_steps": 305, "total_steps": 570, "loss": 0.16, "lr": 2.6453620722761896e-05, "epoch": 5.350877192982456, "percentage": 53.51, "elapsed_time": "0:00:58", "remaining_time": "0:00:50", "throughput": 3364.6, "total_tokens": 197328}
{"current_steps": 310, "total_steps": 570, "loss": 0.0681, "lr": 2.5688858559204053e-05, "epoch": 5.43859649122807, "percentage": 54.39, "elapsed_time": "0:00:59", "remaining_time": "0:00:49", "throughput": 3381.65, "total_tokens": 200560}
{"current_steps": 315, "total_steps": 570, "loss": 0.0737, "lr": 2.492345059102164e-05, "epoch": 5.526315789473684, "percentage": 55.26, "elapsed_time": "0:00:59", "remaining_time": "0:00:48", "throughput": 3395.87, "total_tokens": 203632}
{"current_steps": 319, "total_steps": 570, "eval_loss": 0.15260252356529236, "epoch": 5.5964912280701755, "percentage": 55.96, "elapsed_time": "0:01:01", "remaining_time": "0:00:48", "throughput": 3373.27, "total_tokens": 206000}
{"current_steps": 320, "total_steps": 570, "loss": 0.2497, "lr": 2.4158114387879616e-05, "epoch": 5.614035087719298, "percentage": 56.14, "elapsed_time": "0:01:02", "remaining_time": "0:00:48", "throughput": 3321.84, "total_tokens": 206480}
{"current_steps": 325, "total_steps": 570, "loss": 0.2984, "lr": 2.3393567452163252e-05, "epoch": 5.701754385964913, "percentage": 57.02, "elapsed_time": "0:01:02", "remaining_time": "0:00:47", "throughput": 3332.85, "total_tokens": 209232}
{"current_steps": 330, "total_steps": 570, "loss": 0.1651, "lr": 2.2630526546319914e-05, "epoch": 5.7894736842105265, "percentage": 57.89, "elapsed_time": "0:01:03", "remaining_time": "0:00:46", "throughput": 3357.24, "total_tokens": 213168}
{"current_steps": 335, "total_steps": 570, "loss": 0.1575, "lr": 2.186970702089457e-05, "epoch": 5.87719298245614, "percentage": 58.77, "elapsed_time": "0:01:04", "remaining_time": "0:00:45", "throughput": 3377.33, "total_tokens": 216752}
{"current_steps": 340, "total_steps": 570, "loss": 0.0937, "lr": 2.111182214388893e-05, "epoch": 5.964912280701754, "percentage": 59.65, "elapsed_time": "0:01:04", "remaining_time": "0:00:43", "throughput": 3390.29, "total_tokens": 219536}
{"current_steps": 345, "total_steps": 570, "loss": 0.1728, "lr": 2.0357582432072957e-05, "epoch": 6.052631578947368, "percentage": 60.53, "elapsed_time": "0:01:05", "remaining_time": "0:00:42", "throughput": 3382.34, "total_tokens": 222272}
{"current_steps": 348, "total_steps": 570, "eval_loss": 0.15527071058750153, "epoch": 6.105263157894737, "percentage": 61.05, "elapsed_time": "0:01:06", "remaining_time": "0:00:42", "throughput": 3362.6, "total_tokens": 224064}
{"current_steps": 350, "total_steps": 570, "loss": 0.1903, "lr": 1.9607694984875754e-05, "epoch": 6.140350877192983, "percentage": 61.4, "elapsed_time": "0:01:07", "remaining_time": "0:00:42", "throughput": 3325.37, "total_tokens": 225664}
{"current_steps": 355, "total_steps": 570, "loss": 0.1822, "lr": 1.8862862821480025e-05, "epoch": 6.228070175438597, "percentage": 62.28, "elapsed_time": "0:01:08", "remaining_time": "0:00:41", "throughput": 3345.65, "total_tokens": 229408}
{"current_steps": 360, "total_steps": 570, "loss": 0.2763, "lr": 1.8123784221741964e-05, "epoch": 6.315789473684211, "percentage": 63.16, "elapsed_time": "0:01:09", "remaining_time": "0:00:40", "throughput": 3360.71, "total_tokens": 232832}
{"current_steps": 365, "total_steps": 570, "loss": 0.1021, "lr": 1.73911520715541e-05, "epoch": 6.4035087719298245, "percentage": 64.04, "elapsed_time": "0:01:09", "remaining_time": "0:00:39", "throughput": 3378.37, "total_tokens": 236288}
{"current_steps": 370, "total_steps": 570, "loss": 0.0561, "lr": 1.666565321326512e-05, "epoch": 6.491228070175438, "percentage": 64.91, "elapsed_time": "0:01:10", "remaining_time": "0:00:38", "throughput": 3390.58, "total_tokens": 239296}
{"current_steps": 375, "total_steps": 570, "loss": 0.1545, "lr": 1.5947967801765345e-05, "epoch": 6.578947368421053, "percentage": 65.79, "elapsed_time": "0:01:11", "remaining_time": "0:00:37", "throughput": 3408.54, "total_tokens": 242848}
{"current_steps": 377, "total_steps": 570, "eval_loss": 0.15140964090824127, "epoch": 6.614035087719298, "percentage": 66.14, "elapsed_time": "0:01:11", "remaining_time": "0:00:36", "throughput": 3387.18, "total_tokens": 243840}
{"current_steps": 380, "total_steps": 570, "loss": 0.1936, "lr": 1.5238768666841907e-05, "epoch": 6.666666666666667, "percentage": 66.67, "elapsed_time": "0:01:13", "remaining_time": "0:00:36", "throughput": 3345.83, "total_tokens": 245344}
{"current_steps": 385, "total_steps": 570, "loss": 0.0681, "lr": 1.4538720682400969e-05, "epoch": 6.754385964912281, "percentage": 67.54, "elapsed_time": "0:01:13", "remaining_time": "0:00:35", "throughput": 3356.5, "total_tokens": 248256}
{"current_steps": 390, "total_steps": 570, "loss": 0.0965, "lr": 1.3848480143148839e-05, "epoch": 6.842105263157895, "percentage": 68.42, "elapsed_time": "0:01:14", "remaining_time": "0:00:34", "throughput": 3365.79, "total_tokens": 250976}
{"current_steps": 395, "total_steps": 570, "loss": 0.0593, "lr": 1.3168694149315796e-05, "epoch": 6.9298245614035086, "percentage": 69.3, "elapsed_time": "0:01:15", "remaining_time": "0:00:33", "throughput": 3386.32, "total_tokens": 254944}
{"current_steps": 400, "total_steps": 570, "loss": 0.0929, "lr": 1.2500000000000006e-05, "epoch": 7.017543859649122, "percentage": 70.18, "elapsed_time": "0:01:16", "remaining_time": "0:00:32", "throughput": 3381.11, "total_tokens": 257888}
{"current_steps": 405, "total_steps": 570, "loss": 0.0507, "lr": 1.1843024595699805e-05, "epoch": 7.105263157894737, "percentage": 71.05, "elapsed_time": "0:01:16", "remaining_time": "0:00:31", "throughput": 3394.51, "total_tokens": 261088}
{"current_steps": 406, "total_steps": 570, "eval_loss": 0.1483900249004364, "epoch": 7.12280701754386, "percentage": 71.23, "elapsed_time": "0:01:17", "remaining_time": "0:00:31", "throughput": 3371.37, "total_tokens": 261504}
{"current_steps": 410, "total_steps": 570, "loss": 0.0565, "lr": 1.1198383850594758e-05, "epoch": 7.192982456140351, "percentage": 71.93, "elapsed_time": "0:01:19", "remaining_time": "0:00:30", "throughput": 3339.72, "total_tokens": 263840}
{"current_steps": 415, "total_steps": 570, "loss": 0.2486, "lr": 1.0566682115126344e-05, "epoch": 7.280701754385965, "percentage": 72.81, "elapsed_time": "0:01:19", "remaining_time": "0:00:29", "throughput": 3355.98, "total_tokens": 267424}
{"current_steps": 420, "total_steps": 570, "loss": 0.2373, "lr": 9.948511609419675e-06, "epoch": 7.368421052631579, "percentage": 73.68, "elapsed_time": "0:01:20", "remaining_time": "0:00:28", "throughput": 3368.5, "total_tokens": 270720}
{"current_steps": 425, "total_steps": 570, "loss": 0.2271, "lr": 9.344451868077353e-06, "epoch": 7.456140350877193, "percentage": 74.56, "elapsed_time": "0:01:20", "remaining_time": "0:00:27", "throughput": 3376.8, "total_tokens": 273504}
{"current_steps": 430, "total_steps": 570, "loss": 0.1129, "lr": 8.755069196866014e-06, "epoch": 7.543859649122807, "percentage": 75.44, "elapsed_time": "0:01:21", "remaining_time": "0:00:26", "throughput": 3389.2, "total_tokens": 276608}
{"current_steps": 435, "total_steps": 570, "loss": 0.166, "lr": 8.180916141804906e-06, "epoch": 7.631578947368421, "percentage": 76.32, "elapsed_time": "0:01:22", "remaining_time": "0:00:25", "throughput": 3406.2, "total_tokens": 280352}
{"current_steps": 435, "total_steps": 570, "eval_loss": 0.1568061262369156, "epoch": 7.631578947368421, "percentage": 76.32, "elapsed_time": "0:01:22", "remaining_time": "0:00:25", "throughput": 3382.7, "total_tokens": 280352}
{"current_steps": 440, "total_steps": 570, "loss": 0.0905, "lr": 7.622530971154199e-06, "epoch": 7.719298245614035, "percentage": 77.19, "elapsed_time": "0:01:24", "remaining_time": "0:00:24", "throughput": 3360.55, "total_tokens": 283808}
{"current_steps": 445, "total_steps": 570, "loss": 0.1109, "lr": 7.080437170788723e-06, "epoch": 7.807017543859649, "percentage": 78.07, "elapsed_time": "0:01:25", "remaining_time": "0:00:23", "throughput": 3369.69, "total_tokens": 286688}
{"current_steps": 450, "total_steps": 570, "loss": 0.164, "lr": 6.555142953430158e-06, "epoch": 7.894736842105263, "percentage": 78.95, "elapsed_time": "0:01:25", "remaining_time": "0:00:22", "throughput": 3384.31, "total_tokens": 290240}
{"current_steps": 455, "total_steps": 570, "loss": 0.1285, "lr": 6.0471407821978135e-06, "epoch": 7.982456140350877, "percentage": 79.82, "elapsed_time": "0:01:26", "remaining_time": "0:00:21", "throughput": 3396.66, "total_tokens": 293568}
{"current_steps": 460, "total_steps": 570, "loss": 0.0494, "lr": 5.556906908924655e-06, "epoch": 8.070175438596491, "percentage": 80.7, "elapsed_time": "0:01:27", "remaining_time": "0:00:20", "throughput": 3392.06, "total_tokens": 296720}
{"current_steps": 464, "total_steps": 570, "eval_loss": 0.14825789630413055, "epoch": 8.140350877192983, "percentage": 81.4, "elapsed_time": "0:01:28", "remaining_time": "0:00:20", "throughput": 3380.9, "total_tokens": 299344}
{"current_steps": 465, "total_steps": 570, "loss": 0.1731, "lr": 5.084900927671393e-06, "epoch": 8.157894736842104, "percentage": 81.58, "elapsed_time": "0:01:29", "remaining_time": "0:00:20", "throughput": 3347.76, "total_tokens": 300112}
{"current_steps": 470, "total_steps": 570, "loss": 0.1065, "lr": 4.631565343857239e-06, "epoch": 8.24561403508772, "percentage": 82.46, "elapsed_time": "0:01:30", "remaining_time": "0:00:19", "throughput": 3361.38, "total_tokens": 303664}
{"current_steps": 475, "total_steps": 570, "loss": 0.1003, "lr": 4.19732515941125e-06, "epoch": 8.333333333333334, "percentage": 83.33, "elapsed_time": "0:01:30", "remaining_time": "0:00:18", "throughput": 3369.88, "total_tokens": 306480}
{"current_steps": 480, "total_steps": 570, "loss": 0.1752, "lr": 3.7825874743331907e-06, "epoch": 8.421052631578947, "percentage": 84.21, "elapsed_time": "0:01:31", "remaining_time": "0:00:17", "throughput": 3381.3, "total_tokens": 309744}
{"current_steps": 485, "total_steps": 570, "loss": 0.1333, "lr": 3.3877411050374424e-06, "epoch": 8.508771929824562, "percentage": 85.09, "elapsed_time": "0:01:32", "remaining_time": "0:00:16", "throughput": 3395.14, "total_tokens": 313360}
{"current_steps": 490, "total_steps": 570, "loss": 0.3338, "lr": 3.013156219837776e-06, "epoch": 8.596491228070175, "percentage": 85.96, "elapsed_time": "0:01:32", "remaining_time": "0:00:15", "throughput": 3407.88, "total_tokens": 316784}
{"current_steps": 493, "total_steps": 570, "eval_loss": 0.1508120447397232, "epoch": 8.649122807017545, "percentage": 86.49, "elapsed_time": "0:01:33", "remaining_time": "0:00:14", "throughput": 3393.45, "total_tokens": 318672}
{"current_steps": 495, "total_steps": 570, "loss": 0.0512, "lr": 2.659183991914696e-06, "epoch": 8.68421052631579, "percentage": 86.84, "elapsed_time": "0:01:35", "remaining_time": "0:00:14", "throughput": 3356.26, "total_tokens": 319760}
{"current_steps": 500, "total_steps": 570, "loss": 0.0747, "lr": 2.326156270090735e-06, "epoch": 8.771929824561404, "percentage": 87.72, "elapsed_time": "0:01:35", "remaining_time": "0:00:13", "throughput": 3364.03, "total_tokens": 322512}
{"current_steps": 505, "total_steps": 570, "loss": 0.098, "lr": 2.0143852677223075e-06, "epoch": 8.859649122807017, "percentage": 88.6, "elapsed_time": "0:01:36", "remaining_time": "0:00:12", "throughput": 3375.92, "total_tokens": 325936}
{"current_steps": 510, "total_steps": 570, "loss": 0.1179, "lr": 1.7241632699998123e-06, "epoch": 8.947368421052632, "percentage": 89.47, "elapsed_time": "0:01:37", "remaining_time": "0:00:11", "throughput": 3388.79, "total_tokens": 329360}
{"current_steps": 515, "total_steps": 570, "loss": 0.187, "lr": 1.4557623599303903e-06, "epoch": 9.035087719298245, "percentage": 90.35, "elapsed_time": "0:01:38", "remaining_time": "0:00:10", "throughput": 3383.18, "total_tokens": 332168}
{"current_steps": 520, "total_steps": 570, "loss": 0.0833, "lr": 1.2094341632602064e-06, "epoch": 9.12280701754386, "percentage": 91.23, "elapsed_time": "0:01:38", "remaining_time": "0:00:09", "throughput": 3399.09, "total_tokens": 336296}
{"current_steps": 522, "total_steps": 570, "eval_loss": 0.1507260799407959, "epoch": 9.157894736842104, "percentage": 91.58, "elapsed_time": "0:01:39", "remaining_time": "0:00:09", "throughput": 3381.89, "total_tokens": 337480}
{"current_steps": 525, "total_steps": 570, "loss": 0.2548, "lr": 9.85409612575411e-07, "epoch": 9.210526315789474, "percentage": 92.11, "elapsed_time": "0:01:41", "remaining_time": "0:00:08", "throughput": 3353.47, "total_tokens": 339080}
{"current_steps": 530, "total_steps": 570, "loss": 0.0774, "lr": 7.838987308029427e-07, "epoch": 9.298245614035087, "percentage": 92.98, "elapsed_time": "0:01:41", "remaining_time": "0:00:07", "throughput": 3365.65, "total_tokens": 342568}
{"current_steps": 535, "total_steps": 570, "loss": 0.1128, "lr": 6.050904343141095e-07, "epoch": 9.385964912280702, "percentage": 93.86, "elapsed_time": "0:01:42", "remaining_time": "0:00:06", "throughput": 3374.93, "total_tokens": 345576}
{"current_steps": 540, "total_steps": 570, "loss": 0.0578, "lr": 4.491523558155714e-07, "epoch": 9.473684210526315, "percentage": 94.74, "elapsed_time": "0:01:43", "remaining_time": "0:00:05", "throughput": 3381.54, "total_tokens": 348392}
{"current_steps": 545, "total_steps": 570, "loss": 0.0793, "lr": 3.162306871937387e-07, "epoch": 9.56140350877193, "percentage": 95.61, "elapsed_time": "0:01:43", "remaining_time": "0:00:04", "throughput": 3393.0, "total_tokens": 351912}
{"current_steps": 550, "total_steps": 570, "loss": 0.1172, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:01:44", "remaining_time": "0:00:03", "throughput": 3405.01, "total_tokens": 355432}
{"current_steps": 551, "total_steps": 570, "eval_loss": 0.14835186302661896, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:01:45", "remaining_time": "0:00:03", "throughput": 3391.81, "total_tokens": 356456}
{"current_steps": 555, "total_steps": 570, "loss": 0.1617, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:01:46", "remaining_time": "0:00:02", "throughput": 3361.86, "total_tokens": 358760}
{"current_steps": 560, "total_steps": 570, "loss": 0.23, "lr": 5.6701710711626334e-08, "epoch": 9.824561403508772, "percentage": 98.25, "elapsed_time": "0:01:47", "remaining_time": "0:00:01", "throughput": 3372.52, "total_tokens": 362088}
{"current_steps": 565, "total_steps": 570, "loss": 0.2394, "lr": 1.6874412698408836e-08, "epoch": 9.912280701754385, "percentage": 99.12, "elapsed_time": "0:01:48", "remaining_time": "0:00:00", "throughput": 3384.05, "total_tokens": 365544}
{"current_steps": 570, "total_steps": 570, "loss": 0.1568, "lr": 4.687849611939576e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:01:48", "remaining_time": "0:00:00", "throughput": 3383.12, "total_tokens": 367864}
{"current_steps": 570, "total_steps": 570, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:01:49", "remaining_time": "0:00:00", "throughput": 3350.97, "total_tokens": 367864}