|
{"current_steps": 5, "total_steps": 765, "loss": 0.8739, "lr": 1.9997891995035914e-05, "epoch": 0.097799511002445, "percentage": 0.65, "elapsed_time": "0:00:20", "remaining_time": "0:51:43", "throughput": 8024.43, "total_tokens": 163840} |
|
{"current_steps": 10, "total_steps": 765, "loss": 0.7957, "lr": 1.999156886888064e-05, "epoch": 0.19559902200489, "percentage": 1.31, "elapsed_time": "0:00:40", "remaining_time": "0:50:51", "throughput": 8106.29, "total_tokens": 327680} |
|
{"current_steps": 15, "total_steps": 765, "loss": 0.7822, "lr": 1.9981033287370443e-05, "epoch": 0.293398533007335, "percentage": 1.96, "elapsed_time": "0:00:59", "remaining_time": "0:49:49", "throughput": 8219.61, "total_tokens": 491520} |
|
{"current_steps": 20, "total_steps": 765, "loss": 0.7815, "lr": 1.9966289692316944e-05, "epoch": 0.39119804400978, "percentage": 2.61, "elapsed_time": "0:01:19", "remaining_time": "0:49:15", "throughput": 8260.2, "total_tokens": 655360} |
|
{"current_steps": 25, "total_steps": 765, "loss": 0.7432, "lr": 1.9947344299634464e-05, "epoch": 0.4889975550122249, "percentage": 3.27, "elapsed_time": "0:01:39", "remaining_time": "0:48:52", "throughput": 8269.83, "total_tokens": 819200} |
|
{"current_steps": 30, "total_steps": 765, "loss": 0.7389, "lr": 1.992420509671936e-05, "epoch": 0.58679706601467, "percentage": 3.92, "elapsed_time": "0:01:58", "remaining_time": "0:48:26", "throughput": 8282.1, "total_tokens": 982368} |
|
{"current_steps": 35, "total_steps": 765, "loss": 0.7654, "lr": 1.9896881839082554e-05, "epoch": 0.684596577017115, "percentage": 4.58, "elapsed_time": "0:02:17", "remaining_time": "0:47:58", "throughput": 8305.86, "total_tokens": 1146208} |
|
{"current_steps": 40, "total_steps": 765, "loss": 0.7753, "lr": 1.9865386046236597e-05, "epoch": 0.78239608801956, "percentage": 5.23, "elapsed_time": "0:02:37", "remaining_time": "0:47:34", "throughput": 8319.21, "total_tokens": 1310048} |
|
{"current_steps": 45, "total_steps": 765, "loss": 0.7256, "lr": 1.982973099683902e-05, "epoch": 0.8801955990220048, "percentage": 5.88, "elapsed_time": "0:02:57", "remaining_time": "0:47:13", "throughput": 8321.93, "total_tokens": 1473888} |
|
{"current_steps": 50, "total_steps": 765, "loss": 0.727, "lr": 1.9789931723094046e-05, "epoch": 0.9779951100244498, "percentage": 6.54, "elapsed_time": "0:03:16", "remaining_time": "0:46:54", "throughput": 8320.84, "total_tokens": 1637728} |
|
{"current_steps": 55, "total_steps": 765, "loss": 0.582, "lr": 1.9746005004415004e-05, "epoch": 1.058679706601467, "percentage": 7.19, "elapsed_time": "0:03:32", "remaining_time": "0:45:47", "throughput": 8319.31, "total_tokens": 1770848} |
|
{"current_steps": 60, "total_steps": 765, "loss": 0.5628, "lr": 1.9697969360350098e-05, "epoch": 1.156479217603912, "percentage": 7.84, "elapsed_time": "0:03:52", "remaining_time": "0:45:31", "throughput": 8321.68, "total_tokens": 1934688} |
|
{"current_steps": 65, "total_steps": 765, "loss": 0.5561, "lr": 1.9645845042774555e-05, "epoch": 1.254278728606357, "percentage": 8.5, "elapsed_time": "0:04:12", "remaining_time": "0:45:14", "throughput": 8326.47, "total_tokens": 2098528} |
|
{"current_steps": 70, "total_steps": 765, "loss": 0.5778, "lr": 1.9589654027352412e-05, "epoch": 1.352078239608802, "percentage": 9.15, "elapsed_time": "0:04:31", "remaining_time": "0:44:57", "throughput": 8327.91, "total_tokens": 2262368} |
|
{"current_steps": 75, "total_steps": 765, "loss": 0.5207, "lr": 1.9529420004271568e-05, "epoch": 1.449877750611247, "percentage": 9.8, "elapsed_time": "0:04:51", "remaining_time": "0:44:39", "throughput": 8328.77, "total_tokens": 2426128} |
|
{"current_steps": 80, "total_steps": 765, "loss": 0.5452, "lr": 1.9465168368255946e-05, "epoch": 1.5476772616136918, "percentage": 10.46, "elapsed_time": "0:05:10", "remaining_time": "0:44:20", "throughput": 8334.34, "total_tokens": 2589968} |
|
{"current_steps": 85, "total_steps": 765, "loss": 0.5379, "lr": 1.9396926207859085e-05, "epoch": 1.6454767726161368, "percentage": 11.11, "elapsed_time": "0:05:30", "remaining_time": "0:44:01", "throughput": 8341.18, "total_tokens": 2753808} |
|
{"current_steps": 90, "total_steps": 765, "loss": 0.5116, "lr": 1.932472229404356e-05, "epoch": 1.7432762836185818, "percentage": 11.76, "elapsed_time": "0:05:49", "remaining_time": "0:43:44", "throughput": 8337.37, "total_tokens": 2917648} |
|
{"current_steps": 95, "total_steps": 765, "loss": 0.5532, "lr": 1.924858706805112e-05, "epoch": 1.8410757946210268, "percentage": 12.42, "elapsed_time": "0:06:09", "remaining_time": "0:43:26", "throughput": 8339.42, "total_tokens": 3081488} |
|
{"current_steps": 100, "total_steps": 765, "loss": 0.5659, "lr": 1.9168552628568632e-05, "epoch": 1.9388753056234718, "percentage": 13.07, "elapsed_time": "0:06:28", "remaining_time": "0:43:06", "throughput": 8344.96, "total_tokens": 3245328} |
|
{"current_steps": 105, "total_steps": 765, "loss": 0.6028, "lr": 1.9084652718195237e-05, "epoch": 2.019559902200489, "percentage": 13.73, "elapsed_time": "0:07:38", "remaining_time": "0:47:59", "throughput": 7373.76, "total_tokens": 3378448} |
|
{"current_steps": 110, "total_steps": 765, "loss": 0.4228, "lr": 1.8996922709216456e-05, "epoch": 2.117359413202934, "percentage": 14.38, "elapsed_time": "0:07:57", "remaining_time": "0:47:25", "throughput": 7412.32, "total_tokens": 3542288} |
|
{"current_steps": 115, "total_steps": 765, "loss": 0.3648, "lr": 1.8905399588691165e-05, "epoch": 2.215158924205379, "percentage": 15.03, "elapsed_time": "0:08:17", "remaining_time": "0:46:52", "throughput": 7448.87, "total_tokens": 3706128} |
|
{"current_steps": 120, "total_steps": 765, "loss": 0.3822, "lr": 1.8810121942857848e-05, "epoch": 2.312958435207824, "percentage": 15.69, "elapsed_time": "0:08:36", "remaining_time": "0:46:18", "throughput": 7486.42, "total_tokens": 3869968} |
|
{"current_steps": 125, "total_steps": 765, "loss": 0.3907, "lr": 1.8711129940866577e-05, "epoch": 2.410757946210269, "percentage": 16.34, "elapsed_time": "0:08:56", "remaining_time": "0:45:46", "throughput": 7521.14, "total_tokens": 4033808} |
|
{"current_steps": 130, "total_steps": 765, "loss": 0.3936, "lr": 1.860846531784368e-05, "epoch": 2.508557457212714, "percentage": 16.99, "elapsed_time": "0:09:15", "remaining_time": "0:45:15", "throughput": 7551.36, "total_tokens": 4197648} |
|
{"current_steps": 135, "total_steps": 765, "loss": 0.376, "lr": 1.8502171357296144e-05, "epoch": 2.606356968215159, "percentage": 17.65, "elapsed_time": "0:09:35", "remaining_time": "0:44:46", "throughput": 7577.31, "total_tokens": 4361488} |
|
{"current_steps": 140, "total_steps": 765, "loss": 0.3735, "lr": 1.839229287286327e-05, "epoch": 2.704156479217604, "percentage": 18.3, "elapsed_time": "0:09:55", "remaining_time": "0:44:17", "throughput": 7602.53, "total_tokens": 4525328} |
|
{"current_steps": 145, "total_steps": 765, "loss": 0.4114, "lr": 1.827887618942318e-05, "epoch": 2.801955990220049, "percentage": 18.95, "elapsed_time": "0:10:14", "remaining_time": "0:43:48", "throughput": 7628.26, "total_tokens": 4689168} |
|
{"current_steps": 150, "total_steps": 765, "loss": 0.3696, "lr": 1.816196912356222e-05, "epoch": 2.899755501222494, "percentage": 19.61, "elapsed_time": "0:10:34", "remaining_time": "0:43:20", "throughput": 7652.37, "total_tokens": 4853008} |
|
{"current_steps": 155, "total_steps": 765, "loss": 0.3888, "lr": 1.8041620963415418e-05, "epoch": 2.997555012224939, "percentage": 20.26, "elapsed_time": "0:10:53", "remaining_time": "0:42:53", "throughput": 7671.13, "total_tokens": 5016848} |
|
{"current_steps": 160, "total_steps": 765, "loss": 0.2605, "lr": 1.7917882447886585e-05, "epoch": 3.078239608801956, "percentage": 20.92, "elapsed_time": "0:11:09", "remaining_time": "0:42:12", "throughput": 7688.94, "total_tokens": 5149968} |
|
{"current_steps": 165, "total_steps": 765, "loss": 0.2475, "lr": 1.7790805745256703e-05, "epoch": 3.176039119804401, "percentage": 21.57, "elapsed_time": "0:11:29", "remaining_time": "0:41:46", "throughput": 7710.27, "total_tokens": 5313808} |
|
{"current_steps": 170, "total_steps": 765, "loss": 0.2344, "lr": 1.766044443118978e-05, "epoch": 3.273838630806846, "percentage": 22.22, "elapsed_time": "0:11:48", "remaining_time": "0:41:21", "throughput": 7726.87, "total_tokens": 5477648} |
|
{"current_steps": 175, "total_steps": 765, "loss": 0.2665, "lr": 1.7526853466145248e-05, "epoch": 3.371638141809291, "percentage": 22.88, "elapsed_time": "0:12:08", "remaining_time": "0:40:56", "throughput": 7743.4, "total_tokens": 5641488} |
|
{"current_steps": 180, "total_steps": 765, "loss": 0.2477, "lr": 1.7390089172206594e-05, "epoch": 3.469437652811736, "percentage": 23.53, "elapsed_time": "0:12:28", "remaining_time": "0:40:31", "throughput": 7760.52, "total_tokens": 5805328} |
|
{"current_steps": 185, "total_steps": 765, "loss": 0.2679, "lr": 1.725020920933593e-05, "epoch": 3.567237163814181, "percentage": 24.18, "elapsed_time": "0:12:47", "remaining_time": "0:40:06", "throughput": 7776.01, "total_tokens": 5969168} |
|
{"current_steps": 190, "total_steps": 765, "loss": 0.234, "lr": 1.710727255106447e-05, "epoch": 3.665036674816626, "percentage": 24.84, "elapsed_time": "0:13:07", "remaining_time": "0:39:42", "throughput": 7790.11, "total_tokens": 6133008} |
|
{"current_steps": 195, "total_steps": 765, "loss": 0.2587, "lr": 1.696133945962927e-05, "epoch": 3.762836185819071, "percentage": 25.49, "elapsed_time": "0:13:27", "remaining_time": "0:39:19", "throughput": 7801.88, "total_tokens": 6296848} |
|
{"current_steps": 200, "total_steps": 765, "loss": 0.2606, "lr": 1.681247146056654e-05, "epoch": 3.860635696821516, "percentage": 26.14, "elapsed_time": "0:13:46", "remaining_time": "0:38:55", "throughput": 7815.59, "total_tokens": 6460688} |
|
{"current_steps": 205, "total_steps": 765, "loss": 0.2543, "lr": 1.6660731316772503e-05, "epoch": 3.958435207823961, "percentage": 26.8, "elapsed_time": "0:15:01", "remaining_time": "0:41:02", "throughput": 7347.53, "total_tokens": 6624528} |
|
{"current_steps": 210, "total_steps": 765, "loss": 0.1856, "lr": 1.650618300204242e-05, "epoch": 4.039119804400978, "percentage": 27.45, "elapsed_time": "0:15:17", "remaining_time": "0:40:24", "throughput": 7365.09, "total_tokens": 6757128} |
|
{"current_steps": 215, "total_steps": 765, "loss": 0.1462, "lr": 1.634889167409923e-05, "epoch": 4.136919315403423, "percentage": 28.1, "elapsed_time": "0:15:36", "remaining_time": "0:39:56", "throughput": 7387.6, "total_tokens": 6920968} |
|
{"current_steps": 220, "total_steps": 765, "loss": 0.17, "lr": 1.6188923647122946e-05, "epoch": 4.234718826405868, "percentage": 28.76, "elapsed_time": "0:15:56", "remaining_time": "0:39:29", "throughput": 7407.89, "total_tokens": 7084808} |
|
{"current_steps": 225, "total_steps": 765, "loss": 0.1427, "lr": 1.6026346363792565e-05, "epoch": 4.332518337408313, "percentage": 29.41, "elapsed_time": "0:16:16", "remaining_time": "0:39:02", "throughput": 7426.73, "total_tokens": 7248648} |
|
{"current_steps": 230, "total_steps": 765, "loss": 0.15, "lr": 1.5861228366852148e-05, "epoch": 4.430317848410758, "percentage": 30.07, "elapsed_time": "0:16:35", "remaining_time": "0:38:35", "throughput": 7444.87, "total_tokens": 7412488} |
|
{"current_steps": 235, "total_steps": 765, "loss": 0.1603, "lr": 1.5693639270213138e-05, "epoch": 4.528117359413203, "percentage": 30.72, "elapsed_time": "0:16:55", "remaining_time": "0:38:09", "throughput": 7464.06, "total_tokens": 7576264} |
|
{"current_steps": 240, "total_steps": 765, "loss": 0.1536, "lr": 1.552364972960506e-05, "epoch": 4.625916870415648, "percentage": 31.37, "elapsed_time": "0:17:14", "remaining_time": "0:37:43", "throughput": 7479.59, "total_tokens": 7740104} |
|
{"current_steps": 245, "total_steps": 765, "loss": 0.1415, "lr": 1.5351331412787004e-05, "epoch": 4.723716381418093, "percentage": 32.03, "elapsed_time": "0:17:34", "remaining_time": "0:37:18", "throughput": 7495.78, "total_tokens": 7903944} |
|
{"current_steps": 250, "total_steps": 765, "loss": 0.159, "lr": 1.5176756969332428e-05, "epoch": 4.821515892420538, "percentage": 32.68, "elapsed_time": "0:17:53", "remaining_time": "0:36:52", "throughput": 7511.92, "total_tokens": 8067784} |
|
{"current_steps": 255, "total_steps": 765, "loss": 0.1699, "lr": 1.5000000000000002e-05, "epoch": 4.919315403422983, "percentage": 33.33, "elapsed_time": "0:18:13", "remaining_time": "0:36:27", "throughput": 7526.38, "total_tokens": 8231624} |
|
{"current_steps": 260, "total_steps": 765, "loss": 0.1295, "lr": 1.4821135025703491e-05, "epoch": 5.0, "percentage": 33.99, "elapsed_time": "0:18:29", "remaining_time": "0:35:55", "throughput": 7538.13, "total_tokens": 8364744} |
|
{"current_steps": 265, "total_steps": 765, "loss": 0.1019, "lr": 1.4640237456093636e-05, "epoch": 5.097799511002445, "percentage": 34.64, "elapsed_time": "0:18:49", "remaining_time": "0:35:30", "throughput": 7553.8, "total_tokens": 8528584} |
|
{"current_steps": 270, "total_steps": 765, "loss": 0.0916, "lr": 1.4457383557765385e-05, "epoch": 5.19559902200489, "percentage": 35.29, "elapsed_time": "0:19:08", "remaining_time": "0:35:05", "throughput": 7567.93, "total_tokens": 8692424} |
|
{"current_steps": 275, "total_steps": 765, "loss": 0.0935, "lr": 1.427265042210381e-05, "epoch": 5.293398533007335, "percentage": 35.95, "elapsed_time": "0:19:27", "remaining_time": "0:34:40", "throughput": 7583.13, "total_tokens": 8856264} |
|
{"current_steps": 280, "total_steps": 765, "loss": 0.0679, "lr": 1.4086115932782316e-05, "epoch": 5.39119804400978, "percentage": 36.6, "elapsed_time": "0:19:47", "remaining_time": "0:34:16", "throughput": 7596.23, "total_tokens": 9020104} |
|
{"current_steps": 285, "total_steps": 765, "loss": 0.101, "lr": 1.3897858732926794e-05, "epoch": 5.488997555012225, "percentage": 37.25, "elapsed_time": "0:20:07", "remaining_time": "0:33:53", "throughput": 7607.87, "total_tokens": 9183944} |
|
{"current_steps": 290, "total_steps": 765, "loss": 0.0802, "lr": 1.3707958191959609e-05, "epoch": 5.58679706601467, "percentage": 37.91, "elapsed_time": "0:20:26", "remaining_time": "0:33:29", "throughput": 7621.15, "total_tokens": 9347784} |
|
{"current_steps": 295, "total_steps": 765, "loss": 0.0812, "lr": 1.3516494372137368e-05, "epoch": 5.684596577017115, "percentage": 38.56, "elapsed_time": "0:20:46", "remaining_time": "0:33:05", "throughput": 7631.54, "total_tokens": 9511624} |
|
{"current_steps": 300, "total_steps": 765, "loss": 0.0812, "lr": 1.3323547994796597e-05, "epoch": 5.78239608801956, "percentage": 39.22, "elapsed_time": "0:21:05", "remaining_time": "0:32:42", "throughput": 7643.59, "total_tokens": 9675464} |
|
{"current_steps": 305, "total_steps": 765, "loss": 0.0884, "lr": 1.3129200406321545e-05, "epoch": 5.880195599022005, "percentage": 39.87, "elapsed_time": "0:22:24", "remaining_time": "0:33:47", "throughput": 7317.78, "total_tokens": 9839304} |
|
{"current_steps": 310, "total_steps": 765, "loss": 0.0906, "lr": 1.2933533543848462e-05, "epoch": 5.97799511002445, "percentage": 40.52, "elapsed_time": "0:22:44", "remaining_time": "0:33:22", "throughput": 7332.2, "total_tokens": 10003144} |
|
{"current_steps": 315, "total_steps": 765, "loss": 0.0616, "lr": 1.2736629900720832e-05, "epoch": 6.058679706601467, "percentage": 41.18, "elapsed_time": "0:23:00", "remaining_time": "0:32:51", "throughput": 7343.0, "total_tokens": 10136264} |
|
{"current_steps": 320, "total_steps": 765, "loss": 0.0447, "lr": 1.2538572491710079e-05, "epoch": 6.156479217603912, "percentage": 41.83, "elapsed_time": "0:23:19", "remaining_time": "0:32:26", "throughput": 7357.5, "total_tokens": 10300104} |
|
{"current_steps": 325, "total_steps": 765, "loss": 0.0528, "lr": 1.2339444818016488e-05, "epoch": 6.254278728606357, "percentage": 42.48, "elapsed_time": "0:23:39", "remaining_time": "0:32:01", "throughput": 7372.88, "total_tokens": 10463944} |
|
{"current_steps": 330, "total_steps": 765, "loss": 0.0429, "lr": 1.2139330832064975e-05, "epoch": 6.352078239608802, "percentage": 43.14, "elapsed_time": "0:23:58", "remaining_time": "0:31:36", "throughput": 7387.4, "total_tokens": 10627784} |
|
{"current_steps": 335, "total_steps": 765, "loss": 0.0442, "lr": 1.1938314902110701e-05, "epoch": 6.449877750611247, "percentage": 43.79, "elapsed_time": "0:24:18", "remaining_time": "0:31:12", "throughput": 7398.63, "total_tokens": 10791624} |
|
{"current_steps": 340, "total_steps": 765, "loss": 0.047, "lr": 1.1736481776669307e-05, "epoch": 6.547677261613692, "percentage": 44.44, "elapsed_time": "0:24:38", "remaining_time": "0:30:47", "throughput": 7411.53, "total_tokens": 10955464} |
|
{"current_steps": 345, "total_steps": 765, "loss": 0.0437, "lr": 1.1533916548786856e-05, "epoch": 6.645476772616137, "percentage": 45.1, "elapsed_time": "0:24:57", "remaining_time": "0:30:23", "throughput": 7424.59, "total_tokens": 11119304} |
|
{"current_steps": 350, "total_steps": 765, "loss": 0.0466, "lr": 1.133070462016454e-05, "epoch": 6.743276283618582, "percentage": 45.75, "elapsed_time": "0:25:17", "remaining_time": "0:29:58", "throughput": 7436.34, "total_tokens": 11282568} |
|
{"current_steps": 355, "total_steps": 765, "loss": 0.0498, "lr": 1.1126931665153213e-05, "epoch": 6.841075794621027, "percentage": 46.41, "elapsed_time": "0:25:37", "remaining_time": "0:29:35", "throughput": 7447.16, "total_tokens": 11446408} |
|
{"current_steps": 360, "total_steps": 765, "loss": 0.0409, "lr": 1.092268359463302e-05, "epoch": 6.938875305623472, "percentage": 47.06, "elapsed_time": "0:25:56", "remaining_time": "0:29:11", "throughput": 7459.25, "total_tokens": 11610248} |
|
{"current_steps": 365, "total_steps": 765, "loss": 0.0444, "lr": 1.0718046519793276e-05, "epoch": 7.019559902200489, "percentage": 47.71, "elapsed_time": "0:26:12", "remaining_time": "0:28:43", "throughput": 7468.55, "total_tokens": 11743368} |
|
{"current_steps": 370, "total_steps": 765, "loss": 0.0212, "lr": 1.0513106715827897e-05, "epoch": 7.117359413202934, "percentage": 48.37, "elapsed_time": "0:26:31", "remaining_time": "0:28:19", "throughput": 7479.66, "total_tokens": 11906632} |
|
{"current_steps": 375, "total_steps": 765, "loss": 0.0275, "lr": 1.0307950585561705e-05, "epoch": 7.215158924205379, "percentage": 49.02, "elapsed_time": "0:26:51", "remaining_time": "0:27:56", "throughput": 7489.44, "total_tokens": 12070472} |
|
{"current_steps": 380, "total_steps": 765, "loss": 0.0234, "lr": 1.01026646230229e-05, "epoch": 7.312958435207824, "percentage": 49.67, "elapsed_time": "0:27:11", "remaining_time": "0:27:32", "throughput": 7500.49, "total_tokens": 12234312} |
|
{"current_steps": 385, "total_steps": 765, "loss": 0.0227, "lr": 9.897335376977104e-06, "epoch": 7.410757946210269, "percentage": 50.33, "elapsed_time": "0:27:30", "remaining_time": "0:27:09", "throughput": 7510.51, "total_tokens": 12398152} |
|
{"current_steps": 390, "total_steps": 765, "loss": 0.0264, "lr": 9.692049414438298e-06, "epoch": 7.508557457212714, "percentage": 50.98, "elapsed_time": "0:27:50", "remaining_time": "0:26:46", "throughput": 7520.71, "total_tokens": 12561992} |
|
{"current_steps": 395, "total_steps": 765, "loss": 0.0251, "lr": 9.486893284172103e-06, "epoch": 7.606356968215159, "percentage": 51.63, "elapsed_time": "0:28:09", "remaining_time": "0:26:22", "throughput": 7530.64, "total_tokens": 12725832} |
|
{"current_steps": 400, "total_steps": 765, "loss": 0.0237, "lr": 9.281953480206725e-06, "epoch": 7.704156479217604, "percentage": 52.29, "elapsed_time": "0:28:29", "remaining_time": "0:25:59", "throughput": 7541.1, "total_tokens": 12889672} |
|
{"current_steps": 405, "total_steps": 765, "loss": 0.0228, "lr": 9.07731640536698e-06, "epoch": 7.801955990220049, "percentage": 52.94, "elapsed_time": "0:29:47", "remaining_time": "0:26:28", "throughput": 7303.95, "total_tokens": 13053512} |
|
{"current_steps": 410, "total_steps": 765, "loss": 0.0238, "lr": 8.87306833484679e-06, "epoch": 7.899755501222494, "percentage": 53.59, "elapsed_time": "0:30:06", "remaining_time": "0:26:04", "throughput": 7315.29, "total_tokens": 13217352} |
|
{"current_steps": 415, "total_steps": 765, "loss": 0.0222, "lr": 8.669295379835467e-06, "epoch": 7.997555012224939, "percentage": 54.25, "elapsed_time": "0:30:26", "remaining_time": "0:25:40", "throughput": 7326.04, "total_tokens": 13381192} |
|
{"current_steps": 420, "total_steps": 765, "loss": 0.0109, "lr": 8.466083451213145e-06, "epoch": 8.078239608801956, "percentage": 54.9, "elapsed_time": "0:30:42", "remaining_time": "0:25:13", "throughput": 7334.51, "total_tokens": 13514312} |
|
{"current_steps": 425, "total_steps": 765, "loss": 0.0118, "lr": 8.263518223330698e-06, "epoch": 8.1760391198044, "percentage": 55.56, "elapsed_time": "0:31:01", "remaining_time": "0:24:49", "throughput": 7345.75, "total_tokens": 13677448} |
|
{"current_steps": 430, "total_steps": 765, "loss": 0.01, "lr": 8.0616850978893e-06, "epoch": 8.273838630806846, "percentage": 56.21, "elapsed_time": "0:31:21", "remaining_time": "0:24:25", "throughput": 7356.49, "total_tokens": 13841288} |
|
{"current_steps": 435, "total_steps": 765, "loss": 0.0112, "lr": 7.860669167935028e-06, "epoch": 8.37163814180929, "percentage": 56.86, "elapsed_time": "0:31:40", "remaining_time": "0:24:02", "throughput": 7367.37, "total_tokens": 14005128} |
|
{"current_steps": 440, "total_steps": 765, "loss": 0.0133, "lr": 7.660555181983517e-06, "epoch": 8.469437652811736, "percentage": 57.52, "elapsed_time": "0:32:00", "remaining_time": "0:23:38", "throughput": 7377.67, "total_tokens": 14168968} |
|
{"current_steps": 445, "total_steps": 765, "loss": 0.0113, "lr": 7.461427508289922e-06, "epoch": 8.56723716381418, "percentage": 58.17, "elapsed_time": "0:32:19", "remaining_time": "0:23:14", "throughput": 7388.41, "total_tokens": 14332808} |
|
{"current_steps": 450, "total_steps": 765, "loss": 0.0102, "lr": 7.263370099279173e-06, "epoch": 8.665036674816626, "percentage": 58.82, "elapsed_time": "0:32:39", "remaining_time": "0:22:51", "throughput": 7397.72, "total_tokens": 14496648} |
|
{"current_steps": 455, "total_steps": 765, "loss": 0.01, "lr": 7.066466456151541e-06, "epoch": 8.76283618581907, "percentage": 59.48, "elapsed_time": "0:32:58", "remaining_time": "0:22:28", "throughput": 7408.35, "total_tokens": 14660488} |
|
{"current_steps": 460, "total_steps": 765, "loss": 0.0116, "lr": 6.870799593678459e-06, "epoch": 8.860635696821516, "percentage": 60.13, "elapsed_time": "0:33:18", "remaining_time": "0:22:05", "throughput": 7417.24, "total_tokens": 14824328} |
|
{"current_steps": 465, "total_steps": 765, "loss": 0.0111, "lr": 6.6764520052034054e-06, "epoch": 8.95843520782396, "percentage": 60.78, "elapsed_time": "0:33:38", "remaining_time": "0:21:42", "throughput": 7425.37, "total_tokens": 14988168} |
|
{"current_steps": 470, "total_steps": 765, "loss": 0.0071, "lr": 6.483505627862632e-06, "epoch": 9.039119804400977, "percentage": 61.44, "elapsed_time": "0:33:54", "remaining_time": "0:21:17", "throughput": 7432.24, "total_tokens": 15121288} |
|
{"current_steps": 475, "total_steps": 765, "loss": 0.0054, "lr": 6.292041808040393e-06, "epoch": 9.136919315403423, "percentage": 62.09, "elapsed_time": "0:34:14", "remaining_time": "0:20:54", "throughput": 7440.97, "total_tokens": 15285128} |
|
{"current_steps": 480, "total_steps": 765, "loss": 0.0059, "lr": 6.102141267073207e-06, "epoch": 9.234718826405867, "percentage": 62.75, "elapsed_time": "0:34:33", "remaining_time": "0:20:31", "throughput": 7450.14, "total_tokens": 15448968} |
|
{"current_steps": 485, "total_steps": 765, "loss": 0.0045, "lr": 5.913884067217686e-06, "epoch": 9.332518337408313, "percentage": 63.4, "elapsed_time": "0:34:53", "remaining_time": "0:20:08", "throughput": 7458.5, "total_tokens": 15612552} |
|
{"current_steps": 490, "total_steps": 765, "loss": 0.004, "lr": 5.727349577896194e-06, "epoch": 9.430317848410757, "percentage": 64.05, "elapsed_time": "0:35:12", "remaining_time": "0:19:45", "throughput": 7466.39, "total_tokens": 15776392} |
|
{"current_steps": 495, "total_steps": 765, "loss": 0.0042, "lr": 5.542616442234618e-06, "epoch": 9.528117359413203, "percentage": 64.71, "elapsed_time": "0:35:32", "remaining_time": "0:19:23", "throughput": 7474.49, "total_tokens": 15940232} |
|
{"current_steps": 500, "total_steps": 765, "loss": 0.0049, "lr": 5.3597625439063685e-06, "epoch": 9.625916870415647, "percentage": 65.36, "elapsed_time": "0:35:52", "remaining_time": "0:19:00", "throughput": 7483.27, "total_tokens": 16104072} |
|
{"current_steps": 505, "total_steps": 765, "loss": 0.0045, "lr": 5.178864974296511e-06, "epoch": 9.723716381418093, "percentage": 66.01, "elapsed_time": "0:37:10", "remaining_time": "0:19:08", "throughput": 7292.37, "total_tokens": 16267912} |
|
{"current_steps": 510, "total_steps": 765, "loss": 0.004, "lr": 5.000000000000003e-06, "epoch": 9.821515892420537, "percentage": 66.67, "elapsed_time": "0:37:30", "remaining_time": "0:18:45", "throughput": 7300.78, "total_tokens": 16431752} |
|
{"current_steps": 515, "total_steps": 765, "loss": 0.0042, "lr": 4.823243030667576e-06, "epoch": 9.919315403422983, "percentage": 67.32, "elapsed_time": "0:37:50", "remaining_time": "0:18:21", "throughput": 7310.63, "total_tokens": 16595592} |
|
{"current_steps": 520, "total_steps": 765, "loss": 0.0037, "lr": 4.648668587212998e-06, "epoch": 10.0, "percentage": 67.97, "elapsed_time": "0:38:06", "remaining_time": "0:17:57", "throughput": 7317.82, "total_tokens": 16728712} |
|
{"current_steps": 525, "total_steps": 765, "loss": 0.0021, "lr": 4.476350270394942e-06, "epoch": 10.097799511002446, "percentage": 68.63, "elapsed_time": "0:38:25", "remaining_time": "0:17:33", "throughput": 7327.07, "total_tokens": 16892552} |
|
{"current_steps": 530, "total_steps": 765, "loss": 0.002, "lr": 4.306360729786867e-06, "epoch": 10.19559902200489, "percentage": 69.28, "elapsed_time": "0:38:45", "remaining_time": "0:17:10", "throughput": 7335.94, "total_tokens": 17056392} |
|
{"current_steps": 535, "total_steps": 765, "loss": 0.0023, "lr": 4.138771633147856e-06, "epoch": 10.293398533007334, "percentage": 69.93, "elapsed_time": "0:39:04", "remaining_time": "0:16:47", "throughput": 7344.64, "total_tokens": 17220232} |
|
{"current_steps": 540, "total_steps": 765, "loss": 0.002, "lr": 3.973653636207437e-06, "epoch": 10.39119804400978, "percentage": 70.59, "elapsed_time": "0:39:24", "remaining_time": "0:16:25", "throughput": 7352.7, "total_tokens": 17384072} |
|
{"current_steps": 545, "total_steps": 765, "loss": 0.0021, "lr": 3.8110763528770543e-06, "epoch": 10.488997555012224, "percentage": 71.24, "elapsed_time": "0:39:44", "remaining_time": "0:16:02", "throughput": 7360.36, "total_tokens": 17547912} |
|
{"current_steps": 550, "total_steps": 765, "loss": 0.0025, "lr": 3.651108325900773e-06, "epoch": 10.58679706601467, "percentage": 71.9, "elapsed_time": "0:40:03", "remaining_time": "0:15:39", "throughput": 7369.18, "total_tokens": 17711752} |
|
{"current_steps": 555, "total_steps": 765, "loss": 0.0021, "lr": 3.493816997957582e-06, "epoch": 10.684596577017114, "percentage": 72.55, "elapsed_time": "0:40:23", "remaining_time": "0:15:16", "throughput": 7377.11, "total_tokens": 17875592} |
|
{"current_steps": 560, "total_steps": 765, "loss": 0.0017, "lr": 3.339268683227499e-06, "epoch": 10.78239608801956, "percentage": 73.2, "elapsed_time": "0:40:42", "remaining_time": "0:14:54", "throughput": 7384.9, "total_tokens": 18039432} |
|
{"current_steps": 565, "total_steps": 765, "loss": 0.0018, "lr": 3.1875285394334575e-06, "epoch": 10.880195599022004, "percentage": 73.86, "elapsed_time": "0:41:02", "remaining_time": "0:14:31", "throughput": 7392.59, "total_tokens": 18203272} |
|
{"current_steps": 570, "total_steps": 765, "loss": 0.0018, "lr": 3.0386605403707347e-06, "epoch": 10.97799511002445, "percentage": 74.51, "elapsed_time": "0:41:21", "remaining_time": "0:14:09", "throughput": 7400.64, "total_tokens": 18367112} |
|
{"current_steps": 575, "total_steps": 765, "loss": 0.0014, "lr": 2.8927274489355296e-06, "epoch": 11.058679706601467, "percentage": 75.16, "elapsed_time": "0:41:37", "remaining_time": "0:13:45", "throughput": 7406.36, "total_tokens": 18500232} |
|
{"current_steps": 580, "total_steps": 765, "loss": 0.0013, "lr": 2.749790790664074e-06, "epoch": 11.156479217603913, "percentage": 75.82, "elapsed_time": "0:41:57", "remaining_time": "0:13:22", "throughput": 7413.44, "total_tokens": 18662984} |
|
{"current_steps": 585, "total_steps": 765, "loss": 0.0014, "lr": 2.6099108277934105e-06, "epoch": 11.254278728606357, "percentage": 76.47, "elapsed_time": "0:42:16", "remaining_time": "0:13:00", "throughput": 7420.91, "total_tokens": 18826824} |
|
{"current_steps": 590, "total_steps": 765, "loss": 0.0013, "lr": 2.4731465338547556e-06, "epoch": 11.352078239608803, "percentage": 77.12, "elapsed_time": "0:42:36", "remaining_time": "0:12:38", "throughput": 7427.77, "total_tokens": 18990664} |
|
{"current_steps": 595, "total_steps": 765, "loss": 0.0013, "lr": 2.339555568810221e-06, "epoch": 11.449877750611247, "percentage": 77.78, "elapsed_time": "0:42:56", "remaining_time": "0:12:16", "throughput": 7434.56, "total_tokens": 19154504} |
|
{"current_steps": 600, "total_steps": 765, "loss": 0.0012, "lr": 2.209194254743295e-06, "epoch": 11.547677261613693, "percentage": 78.43, "elapsed_time": "0:43:15", "remaining_time": "0:11:53", "throughput": 7441.93, "total_tokens": 19318344} |
|
{"current_steps": 605, "total_steps": 765, "loss": 0.0013, "lr": 2.0821175521134208e-06, "epoch": 11.645476772616137, "percentage": 79.08, "elapsed_time": "0:44:39", "remaining_time": "0:11:48", "throughput": 7271.4, "total_tokens": 19482184} |
|
{"current_steps": 610, "total_steps": 765, "loss": 0.0013, "lr": 1.9583790365845823e-06, "epoch": 11.743276283618583, "percentage": 79.74, "elapsed_time": "0:44:58", "remaining_time": "0:11:25", "throughput": 7279.67, "total_tokens": 19646024} |
|
{"current_steps": 615, "total_steps": 765, "loss": 0.0014, "lr": 1.8380308764377841e-06, "epoch": 11.841075794621027, "percentage": 80.39, "elapsed_time": "0:45:18", "remaining_time": "0:11:02", "throughput": 7287.84, "total_tokens": 19809864} |
|
{"current_steps": 620, "total_steps": 765, "loss": 0.0012, "lr": 1.7211238105768213e-06, "epoch": 11.938875305623473, "percentage": 81.05, "elapsed_time": "0:45:37", "remaining_time": "0:10:40", "throughput": 7295.63, "total_tokens": 19973704} |
|
{"current_steps": 625, "total_steps": 765, "loss": 0.0014, "lr": 1.607707127136734e-06, "epoch": 12.01955990220049, "percentage": 81.7, "elapsed_time": "0:45:53", "remaining_time": "0:10:16", "throughput": 7301.92, "total_tokens": 20106824} |
|
{"current_steps": 630, "total_steps": 765, "loss": 0.0011, "lr": 1.4978286427038602e-06, "epoch": 12.117359413202934, "percentage": 82.35, "elapsed_time": "0:46:13", "remaining_time": "0:09:54", "throughput": 7308.89, "total_tokens": 20270664} |
|
{"current_steps": 635, "total_steps": 765, "loss": 0.0012, "lr": 1.3915346821563235e-06, "epoch": 12.21515892420538, "percentage": 83.01, "elapsed_time": "0:46:32", "remaining_time": "0:09:31", "throughput": 7316.86, "total_tokens": 20434504} |
|
{"current_steps": 640, "total_steps": 765, "loss": 0.0011, "lr": 1.2888700591334225e-06, "epoch": 12.312958435207824, "percentage": 83.66, "elapsed_time": "0:46:52", "remaining_time": "0:09:09", "throughput": 7324.06, "total_tokens": 20598280} |
|
{"current_steps": 645, "total_steps": 765, "loss": 0.0011, "lr": 1.1898780571421554e-06, "epoch": 12.41075794621027, "percentage": 84.31, "elapsed_time": "0:47:12", "remaining_time": "0:08:46", "throughput": 7331.13, "total_tokens": 20762120} |
|
{"current_steps": 650, "total_steps": 765, "loss": 0.0012, "lr": 1.0946004113088381e-06, "epoch": 12.508557457212714, "percentage": 84.97, "elapsed_time": "0:47:31", "remaining_time": "0:08:24", "throughput": 7338.53, "total_tokens": 20925960} |
|
{"current_steps": 655, "total_steps": 765, "loss": 0.001, "lr": 1.0030772907835484e-06, "epoch": 12.60635696821516, "percentage": 85.62, "elapsed_time": "0:47:51", "remaining_time": "0:08:02", "throughput": 7345.34, "total_tokens": 21089800} |
|
{"current_steps": 660, "total_steps": 765, "loss": 0.001, "lr": 9.153472818047627e-07, "epoch": 12.704156479217604, "percentage": 86.27, "elapsed_time": "0:48:10", "remaining_time": "0:07:39", "throughput": 7352.25, "total_tokens": 21253640} |
|
{"current_steps": 665, "total_steps": 765, "loss": 0.0011, "lr": 8.31447371431372e-07, "epoch": 12.80195599022005, "percentage": 86.93, "elapsed_time": "0:48:30", "remaining_time": "0:07:17", "throughput": 7359.27, "total_tokens": 21417480} |
|
{"current_steps": 670, "total_steps": 765, "loss": 0.0011, "lr": 7.514129319488839e-07, "epoch": 12.899755501222494, "percentage": 87.58, "elapsed_time": "0:48:49", "remaining_time": "0:06:55", "throughput": 7365.77, "total_tokens": 21581320} |
|
{"current_steps": 675, "total_steps": 765, "loss": 0.0011, "lr": 6.752777059564431e-07, "epoch": 12.99755501222494, "percentage": 88.24, "elapsed_time": "0:49:09", "remaining_time": "0:06:33", "throughput": 7372.62, "total_tokens": 21745160} |
|
{"current_steps": 680, "total_steps": 765, "loss": 0.0011, "lr": 6.030737921409169e-07, "epoch": 13.078239608801956, "percentage": 88.89, "elapsed_time": "0:49:25", "remaining_time": "0:06:10", "throughput": 7377.3, "total_tokens": 21877864} |
|
{"current_steps": 685, "total_steps": 765, "loss": 0.001, "lr": 5.348316317440549e-07, "epoch": 13.1760391198044, "percentage": 89.54, "elapsed_time": "0:49:45", "remaining_time": "0:05:48", "throughput": 7383.8, "total_tokens": 22041704} |
|
{"current_steps": 690, "total_steps": 765, "loss": 0.001, "lr": 4.7057999572843516e-07, "epoch": 13.273838630806846, "percentage": 90.2, "elapsed_time": "0:50:04", "remaining_time": "0:05:26", "throughput": 7390.6, "total_tokens": 22205544} |
|
{"current_steps": 695, "total_steps": 765, "loss": 0.0011, "lr": 4.103459726475889e-07, "epoch": 13.37163814180929, "percentage": 90.85, "elapsed_time": "0:50:24", "remaining_time": "0:05:04", "throughput": 7396.91, "total_tokens": 22369384} |
|
{"current_steps": 700, "total_steps": 765, "loss": 0.0011, "lr": 3.541549572254488e-07, "epoch": 13.469437652811736, "percentage": 91.5, "elapsed_time": "0:50:43", "remaining_time": "0:04:42", "throughput": 7402.92, "total_tokens": 22533224} |
|
{"current_steps": 705, "total_steps": 765, "loss": 0.0009, "lr": 3.020306396499062e-07, "epoch": 13.56723716381418, "percentage": 92.16, "elapsed_time": "0:52:06", "remaining_time": "0:04:26", "throughput": 7259.08, "total_tokens": 22697064} |
|
{"current_steps": 710, "total_steps": 765, "loss": 0.0011, "lr": 2.539949955849985e-07, "epoch": 13.665036674816626, "percentage": 92.81, "elapsed_time": "0:52:26", "remaining_time": "0:04:03", "throughput": 7266.36, "total_tokens": 22860904} |
|
{"current_steps": 715, "total_steps": 765, "loss": 0.001, "lr": 2.1006827690595478e-07, "epoch": 13.76283618581907, "percentage": 93.46, "elapsed_time": "0:52:45", "remaining_time": "0:03:41", "throughput": 7273.17, "total_tokens": 23024744} |
|
{"current_steps": 720, "total_steps": 765, "loss": 0.001, "lr": 1.7026900316098217e-07, "epoch": 13.860635696821516, "percentage": 94.12, "elapsed_time": "0:53:05", "remaining_time": "0:03:19", "throughput": 7280.07, "total_tokens": 23188584} |
|
{"current_steps": 725, "total_steps": 765, "loss": 0.001, "lr": 1.3461395376340502e-07, "epoch": 13.95843520782396, "percentage": 94.77, "elapsed_time": "0:53:24", "remaining_time": "0:02:56", "throughput": 7286.52, "total_tokens": 23352424} |
|
{"current_steps": 730, "total_steps": 765, "loss": 0.001, "lr": 1.0311816091744698e-07, "epoch": 14.039119804400977, "percentage": 95.42, "elapsed_time": "0:53:41", "remaining_time": "0:02:34", "throughput": 7291.0, "total_tokens": 23485296} |
|
{"current_steps": 735, "total_steps": 765, "loss": 0.001, "lr": 7.579490328064265e-08, "epoch": 14.136919315403423, "percentage": 96.08, "elapsed_time": "0:54:00", "remaining_time": "0:02:12", "throughput": 7297.68, "total_tokens": 23649136} |
|
{"current_steps": 740, "total_steps": 765, "loss": 0.001, "lr": 5.265570036553813e-08, "epoch": 14.234718826405867, "percentage": 96.73, "elapsed_time": "0:54:19", "remaining_time": "0:01:50", "throughput": 7304.61, "total_tokens": 23812976} |
|
{"current_steps": 745, "total_steps": 765, "loss": 0.0009, "lr": 3.371030768305583e-08, "epoch": 14.332518337408313, "percentage": 97.39, "elapsed_time": "0:54:39", "remaining_time": "0:01:28", "throughput": 7311.13, "total_tokens": 23976816} |
|
{"current_steps": 750, "total_steps": 765, "loss": 0.001, "lr": 1.896671262955896e-08, "epoch": 14.430317848410757, "percentage": 98.04, "elapsed_time": "0:54:58", "remaining_time": "0:01:05", "throughput": 7317.57, "total_tokens": 24140656} |
|
{"current_steps": 755, "total_steps": 765, "loss": 0.001, "lr": 8.431131119361891e-09, "epoch": 14.528117359413203, "percentage": 98.69, "elapsed_time": "0:55:18", "remaining_time": "0:00:43", "throughput": 7322.85, "total_tokens": 24304496} |
|
{"current_steps": 760, "total_steps": 765, "loss": 0.001, "lr": 2.108004964086474e-09, "epoch": 14.625916870415647, "percentage": 99.35, "elapsed_time": "0:55:38", "remaining_time": "0:00:21", "throughput": 7328.91, "total_tokens": 24467760} |
|
{"current_steps": 765, "total_steps": 765, "loss": 0.001, "lr": 0.0, "epoch": 14.723716381418093, "percentage": 100.0, "elapsed_time": "0:55:57", "remaining_time": "0:00:00", "throughput": 7335.46, "total_tokens": 24631600} |
|
{"current_steps": 765, "total_steps": 765, "epoch": 14.723716381418093, "percentage": 100.0, "elapsed_time": "0:56:51", "remaining_time": "0:00:00", "throughput": 7220.86, "total_tokens": 24631600} |
|
|