|
{"current_steps": 1, "total_steps": 101, "loss": 1.0213, "lr": 4.998790705729971e-05, "epoch": 0.009864364981504316, "percentage": 0.99, "elapsed_time": "0:02:42", "remaining_time": "4:30:47", "throughput": 12907.24, "total_tokens": 2097152} |
|
{"current_steps": 2, "total_steps": 101, "loss": 1.0136, "lr": 4.995163992833986e-05, "epoch": 0.01972872996300863, "percentage": 1.98, "elapsed_time": "0:05:16", "remaining_time": "4:21:11", "throughput": 13247.81, "total_tokens": 4194304} |
|
{"current_steps": 3, "total_steps": 101, "loss": 0.9404, "lr": 4.989123369922547e-05, "epoch": 0.029593094944512947, "percentage": 2.97, "elapsed_time": "0:07:50", "remaining_time": "4:16:12", "throughput": 13369.6, "total_tokens": 6291456} |
|
{"current_steps": 4, "total_steps": 101, "loss": 0.953, "lr": 4.980674680908192e-05, "epoch": 0.03945745992601726, "percentage": 3.96, "elapsed_time": "0:10:24", "remaining_time": "4:12:30", "throughput": 13426.82, "total_tokens": 8388608} |
|
{"current_steps": 5, "total_steps": 101, "loss": 0.9453, "lr": 4.969826099351892e-05, "epoch": 0.04932182490752158, "percentage": 4.95, "elapsed_time": "0:12:58", "remaining_time": "4:09:13", "throughput": 13463.63, "total_tokens": 10485760} |
|
{"current_steps": 6, "total_steps": 101, "loss": 0.9111, "lr": 4.9565881205556594e-05, "epoch": 0.059186189889025895, "percentage": 5.94, "elapsed_time": "0:15:33", "remaining_time": "4:06:13", "throughput": 13485.87, "total_tokens": 12582912} |
|
{"current_steps": 7, "total_steps": 101, "loss": 0.878, "lr": 4.940973551409018e-05, "epoch": 0.0690505548705302, "percentage": 6.93, "elapsed_time": "0:18:07", "remaining_time": "4:03:18", "throughput": 13503.29, "total_tokens": 14680064} |
|
{"current_steps": 8, "total_steps": 101, "loss": 0.914, "lr": 4.922997497999166e-05, "epoch": 0.07891491985203453, "percentage": 7.92, "elapsed_time": "0:20:41", "remaining_time": "4:00:30", "throughput": 13515.4, "total_tokens": 16777216} |
|
{"current_steps": 9, "total_steps": 101, "loss": 0.8649, "lr": 4.9026773509968115e-05, "epoch": 0.08877928483353884, "percentage": 8.91, "elapsed_time": "0:23:15", "remaining_time": "3:57:46", "throughput": 13523.38, "total_tokens": 18874368} |
|
{"current_steps": 10, "total_steps": 101, "loss": 0.9029, "lr": 4.8800327688318246e-05, "epoch": 0.09864364981504316, "percentage": 9.9, "elapsed_time": "0:25:49", "remaining_time": "3:55:04", "throughput": 13530.26, "total_tokens": 20971520} |
|
{"current_steps": 11, "total_steps": 101, "loss": 0.882, "lr": 4.855085658674973e-05, "epoch": 0.10850801479654747, "percentage": 10.89, "elapsed_time": "0:28:24", "remaining_time": "3:52:24", "throughput": 13535.32, "total_tokens": 23068672} |
|
{"current_steps": 12, "total_steps": 101, "loss": 0.8438, "lr": 4.827860155244149e-05, "epoch": 0.11837237977805179, "percentage": 11.88, "elapsed_time": "0:30:59", "remaining_time": "3:49:47", "throughput": 13536.9, "total_tokens": 25165824} |
|
{"current_steps": 13, "total_steps": 101, "loss": 0.8743, "lr": 4.798382597455591e-05, "epoch": 0.1282367447595561, "percentage": 12.87, "elapsed_time": "0:33:34", "remaining_time": "3:47:14", "throughput": 13535.86, "total_tokens": 27262976} |
|
{"current_steps": 14, "total_steps": 101, "loss": 0.8736, "lr": 4.7666815029426816e-05, "epoch": 0.1381011097410604, "percentage": 13.86, "elapsed_time": "0:36:08", "remaining_time": "3:44:35", "throughput": 13539.44, "total_tokens": 29360128} |
|
{"current_steps": 15, "total_steps": 101, "loss": 0.8687, "lr": 4.732787540466979e-05, "epoch": 0.14796547472256474, "percentage": 14.85, "elapsed_time": "0:38:42", "remaining_time": "3:41:57", "throughput": 13542.72, "total_tokens": 31457280} |
|
{"current_steps": 16, "total_steps": 101, "loss": 0.864, "lr": 4.696733500248172e-05, "epoch": 0.15782983970406905, "percentage": 15.84, "elapsed_time": "0:41:17", "remaining_time": "3:39:19", "throughput": 13545.64, "total_tokens": 33554432} |
|
{"current_steps": 17, "total_steps": 101, "loss": 0.8877, "lr": 4.658554262241659e-05, "epoch": 0.16769420468557336, "percentage": 16.83, "elapsed_time": "0:43:51", "remaining_time": "3:36:42", "throughput": 13548.59, "total_tokens": 35651584} |
|
{"current_steps": 18, "total_steps": 101, "loss": 0.8749, "lr": 4.6182867623944436e-05, "epoch": 0.17755856966707767, "percentage": 17.82, "elapsed_time": "0:46:25", "remaining_time": "3:34:04", "throughput": 13551.29, "total_tokens": 37748736} |
|
{"current_steps": 19, "total_steps": 101, "loss": 0.8338, "lr": 4.575969956911994e-05, "epoch": 0.187422934648582, "percentage": 18.81, "elapsed_time": "0:49:00", "remaining_time": "3:31:29", "throughput": 13551.85, "total_tokens": 39845888} |
|
{"current_steps": 20, "total_steps": 101, "loss": 0.8294, "lr": 4.531644784570626e-05, "epoch": 0.19728729963008632, "percentage": 19.8, "elapsed_time": "0:51:34", "remaining_time": "3:28:54", "throughput": 13552.35, "total_tokens": 41943040} |
|
{"current_steps": 21, "total_steps": 101, "loss": 0.8666, "lr": 4.485354127111884e-05, "epoch": 0.20715166461159062, "percentage": 20.79, "elapsed_time": "0:54:09", "remaining_time": "3:26:18", "throughput": 13553.49, "total_tokens": 44040192} |
|
{"current_steps": 22, "total_steps": 101, "loss": 0.8038, "lr": 4.437142767757225e-05, "epoch": 0.21701602959309493, "percentage": 21.78, "elapsed_time": "0:56:43", "remaining_time": "3:23:43", "throughput": 13554.09, "total_tokens": 46137344} |
|
{"current_steps": 23, "total_steps": 101, "loss": 0.8492, "lr": 4.387057347883143e-05, "epoch": 0.22688039457459927, "percentage": 22.77, "elapsed_time": "0:59:18", "remaining_time": "3:21:07", "throughput": 13554.87, "total_tokens": 48234496} |
|
{"current_steps": 24, "total_steps": 101, "loss": 0.8047, "lr": 4.335146321898651e-05, "epoch": 0.23674475955610358, "percentage": 23.76, "elapsed_time": "1:01:52", "remaining_time": "3:18:32", "throughput": 13555.65, "total_tokens": 50331648} |
|
{"current_steps": 25, "total_steps": 101, "loss": 0.8521, "lr": 4.281459910368768e-05, "epoch": 0.2466091245376079, "percentage": 24.75, "elapsed_time": "1:04:27", "remaining_time": "3:15:57", "throughput": 13556.2, "total_tokens": 52428800} |
|
{"current_steps": 26, "total_steps": 101, "loss": 0.8133, "lr": 4.226050051429367e-05, "epoch": 0.2564734895191122, "percentage": 25.74, "elapsed_time": "1:07:02", "remaining_time": "3:13:22", "throughput": 13556.46, "total_tokens": 54525952} |
|
{"current_steps": 27, "total_steps": 101, "loss": 0.8365, "lr": 4.168970350540384e-05, "epoch": 0.26633785450061653, "percentage": 26.73, "elapsed_time": "1:09:35", "remaining_time": "3:10:45", "throughput": 13559.29, "total_tokens": 56623104} |
|
{"current_steps": 28, "total_steps": 101, "loss": 0.8094, "lr": 4.110276028625995e-05, "epoch": 0.2762022194821208, "percentage": 27.72, "elapsed_time": "1:12:09", "remaining_time": "3:08:07", "throughput": 13563.03, "total_tokens": 58720256} |
|
{"current_steps": 29, "total_steps": 101, "loss": 0.8174, "lr": 4.050023868651938e-05, "epoch": 0.28606658446362515, "percentage": 28.71, "elapsed_time": "1:14:43", "remaining_time": "3:05:30", "throughput": 13565.42, "total_tokens": 60817408} |
|
{"current_steps": 30, "total_steps": 101, "loss": 0.8278, "lr": 3.988272160691665e-05, "epoch": 0.2959309494451295, "percentage": 29.7, "elapsed_time": "1:17:17", "remaining_time": "3:02:55", "throughput": 13566.62, "total_tokens": 62914560} |
|
{"current_steps": 31, "total_steps": 101, "loss": 0.8425, "lr": 3.925080645534457e-05, "epoch": 0.30579531442663377, "percentage": 30.69, "elapsed_time": "1:19:51", "remaining_time": "3:00:18", "throughput": 13569.29, "total_tokens": 65011712} |
|
{"current_steps": 32, "total_steps": 101, "loss": 0.8145, "lr": 3.8605104568900685e-05, "epoch": 0.3156596794081381, "percentage": 31.68, "elapsed_time": "1:22:25", "remaining_time": "2:57:42", "throughput": 13570.89, "total_tokens": 67108864} |
|
{"current_steps": 33, "total_steps": 101, "loss": 0.8322, "lr": 3.7946240622458135e-05, "epoch": 0.32552404438964244, "percentage": 32.67, "elapsed_time": "1:24:58", "remaining_time": "2:55:06", "throughput": 13573.07, "total_tokens": 69206016} |
|
{"current_steps": 34, "total_steps": 101, "loss": 0.8114, "lr": 3.7274852024333054e-05, "epoch": 0.3353884093711467, "percentage": 33.66, "elapsed_time": "1:27:33", "remaining_time": "2:52:32", "throughput": 13572.53, "total_tokens": 71303168} |
|
{"current_steps": 35, "total_steps": 101, "loss": 0.8091, "lr": 3.6591588299633186e-05, "epoch": 0.34525277435265106, "percentage": 34.65, "elapsed_time": "1:30:08", "remaining_time": "2:49:58", "throughput": 13572.13, "total_tokens": 73400320} |
|
{"current_steps": 36, "total_steps": 101, "loss": 0.7743, "lr": 3.589711046188428e-05, "epoch": 0.35511713933415534, "percentage": 35.64, "elapsed_time": "1:32:42", "remaining_time": "2:47:22", "throughput": 13573.61, "total_tokens": 75497472} |
|
{"current_steps": 37, "total_steps": 101, "loss": 0.8368, "lr": 3.519209037354222e-05, "epoch": 0.3649815043156597, "percentage": 36.63, "elapsed_time": "1:35:15", "remaining_time": "2:44:46", "throughput": 13575.22, "total_tokens": 77594624} |
|
{"current_steps": 38, "total_steps": 101, "loss": 0.8177, "lr": 3.447721009600949e-05, "epoch": 0.374845869297164, "percentage": 37.62, "elapsed_time": "1:37:49", "remaining_time": "2:42:11", "throughput": 13576.95, "total_tokens": 79691776} |
|
{"current_steps": 39, "total_steps": 101, "loss": 0.8109, "lr": 3.3753161229784766e-05, "epoch": 0.3847102342786683, "percentage": 38.61, "elapsed_time": "1:40:24", "remaining_time": "2:39:36", "throughput": 13577.04, "total_tokens": 81788928} |
|
{"current_steps": 40, "total_steps": 101, "loss": 0.827, "lr": 3.302064424538419e-05, "epoch": 0.39457459926017263, "percentage": 39.6, "elapsed_time": "1:42:58", "remaining_time": "2:37:01", "throughput": 13578.09, "total_tokens": 83886080} |
|
{"current_steps": 41, "total_steps": 101, "loss": 0.8167, "lr": 3.228036780568131e-05, "epoch": 0.40443896424167697, "percentage": 40.59, "elapsed_time": "1:45:31", "remaining_time": "2:34:25", "throughput": 13579.75, "total_tokens": 85983232} |
|
{"current_steps": 42, "total_steps": 101, "loss": 0.8073, "lr": 3.153304808032152e-05, "epoch": 0.41430332922318125, "percentage": 41.58, "elapsed_time": "1:48:05", "remaining_time": "2:31:50", "throughput": 13581.88, "total_tokens": 88080384} |
|
{"current_steps": 43, "total_steps": 101, "loss": 0.7793, "lr": 3.077940805287425e-05, "epoch": 0.4241676942046856, "percentage": 42.57, "elapsed_time": "1:50:38", "remaining_time": "2:29:14", "throughput": 13583.46, "total_tokens": 90177536} |
|
{"current_steps": 44, "total_steps": 101, "loss": 0.8096, "lr": 3.0020176821392964e-05, "epoch": 0.43403205918618987, "percentage": 43.56, "elapsed_time": "1:53:12", "remaining_time": "2:26:39", "throughput": 13585.16, "total_tokens": 92274688} |
|
{"current_steps": 45, "total_steps": 101, "loss": 0.8212, "lr": 2.925608889305997e-05, "epoch": 0.4438964241676942, "percentage": 44.55, "elapsed_time": "1:55:45", "remaining_time": "2:24:03", "throughput": 13586.73, "total_tokens": 94371840} |
|
{"current_steps": 46, "total_steps": 101, "loss": 0.8151, "lr": 2.848788347359808e-05, "epoch": 0.45376078914919854, "percentage": 45.54, "elapsed_time": "1:58:20", "remaining_time": "2:21:29", "throughput": 13586.13, "total_tokens": 96468992} |
|
{"current_steps": 47, "total_steps": 101, "loss": 0.8331, "lr": 2.7716303752136864e-05, "epoch": 0.4636251541307028, "percentage": 46.53, "elapsed_time": "2:00:54", "remaining_time": "2:18:54", "throughput": 13587.29, "total_tokens": 98566144} |
|
{"current_steps": 48, "total_steps": 101, "loss": 0.8003, "lr": 2.6942096182225162e-05, "epoch": 0.47348951911220716, "percentage": 47.52, "elapsed_time": "2:03:28", "remaining_time": "2:16:20", "throughput": 13587.74, "total_tokens": 100663296} |
|
{"current_steps": 49, "total_steps": 101, "loss": 0.8214, "lr": 2.616600975968544e-05, "epoch": 0.4833538840937115, "percentage": 48.51, "elapsed_time": "2:06:02", "remaining_time": "2:13:45", "throughput": 13588.82, "total_tokens": 102760448} |
|
{"current_steps": 50, "total_steps": 101, "loss": 0.8118, "lr": 2.5388795298008776e-05, "epoch": 0.4932182490752158, "percentage": 49.5, "elapsed_time": "2:08:36", "remaining_time": "2:11:10", "throughput": 13589.6, "total_tokens": 104857600} |
|
{"current_steps": 51, "total_steps": 101, "loss": 0.8382, "lr": 2.4611204701991227e-05, "epoch": 0.5030826140567201, "percentage": 50.5, "elapsed_time": "2:11:09", "remaining_time": "2:08:35", "throughput": 13590.81, "total_tokens": 106954752} |
|
{"current_steps": 52, "total_steps": 101, "loss": 0.8099, "lr": 2.3833990240314562e-05, "epoch": 0.5129469790382244, "percentage": 51.49, "elapsed_time": "2:13:43", "remaining_time": "2:06:01", "throughput": 13590.72, "total_tokens": 109051904} |
|
{"current_steps": 53, "total_steps": 101, "loss": 0.7914, "lr": 2.3057903817774843e-05, "epoch": 0.5228113440197287, "percentage": 52.48, "elapsed_time": "2:16:17", "remaining_time": "2:03:26", "throughput": 13591.47, "total_tokens": 111149056} |
|
{"current_steps": 54, "total_steps": 101, "loss": 0.8104, "lr": 2.2283696247863135e-05, "epoch": 0.5326757090012331, "percentage": 53.47, "elapsed_time": "2:18:51", "remaining_time": "2:00:51", "throughput": 13592.65, "total_tokens": 113246208} |
|
{"current_steps": 55, "total_steps": 101, "loss": 0.8125, "lr": 2.1512116526401928e-05, "epoch": 0.5425400739827374, "percentage": 54.46, "elapsed_time": "2:21:25", "remaining_time": "1:58:16", "throughput": 13593.72, "total_tokens": 115343360} |
|
{"current_steps": 56, "total_steps": 101, "loss": 0.8198, "lr": 2.0743911106940034e-05, "epoch": 0.5524044389642416, "percentage": 55.45, "elapsed_time": "2:23:58", "remaining_time": "1:55:41", "throughput": 13594.46, "total_tokens": 117440512} |
|
{"current_steps": 57, "total_steps": 101, "loss": 0.8019, "lr": 1.9979823178607042e-05, "epoch": 0.562268803945746, "percentage": 56.44, "elapsed_time": "2:26:33", "remaining_time": "1:53:07", "throughput": 13594.62, "total_tokens": 119537664} |
|
{"current_steps": 58, "total_steps": 101, "loss": 0.8141, "lr": 1.9220591947125766e-05, "epoch": 0.5721331689272503, "percentage": 57.43, "elapsed_time": "2:29:06", "remaining_time": "1:50:32", "throughput": 13595.48, "total_tokens": 121634816} |
|
{"current_steps": 59, "total_steps": 101, "loss": 0.7985, "lr": 1.846695191967849e-05, "epoch": 0.5819975339087546, "percentage": 58.42, "elapsed_time": "2:31:40", "remaining_time": "1:47:58", "throughput": 13596.37, "total_tokens": 123731968} |
|
{"current_steps": 60, "total_steps": 101, "loss": 0.7998, "lr": 1.7719632194318702e-05, "epoch": 0.591861898890259, "percentage": 59.41, "elapsed_time": "2:34:13", "remaining_time": "1:45:23", "throughput": 13597.32, "total_tokens": 125829120} |
|
{"current_steps": 61, "total_steps": 101, "loss": 0.7988, "lr": 1.6979355754615814e-05, "epoch": 0.6017262638717632, "percentage": 60.4, "elapsed_time": "2:36:47", "remaining_time": "1:42:49", "throughput": 13597.98, "total_tokens": 127926272} |
|
{"current_steps": 62, "total_steps": 101, "loss": 0.8016, "lr": 1.6246838770215233e-05, "epoch": 0.6115906288532675, "percentage": 61.39, "elapsed_time": "2:39:21", "remaining_time": "1:40:14", "throughput": 13598.66, "total_tokens": 130023424} |
|
{"current_steps": 63, "total_steps": 101, "loss": 0.8162, "lr": 1.552278990399052e-05, "epoch": 0.6214549938347719, "percentage": 62.38, "elapsed_time": "2:41:54", "remaining_time": "1:37:39", "throughput": 13599.73, "total_tokens": 132120576} |
|
{"current_steps": 64, "total_steps": 101, "loss": 0.8258, "lr": 1.4807909626457782e-05, "epoch": 0.6313193588162762, "percentage": 63.37, "elapsed_time": "2:44:28", "remaining_time": "1:35:05", "throughput": 13600.66, "total_tokens": 134217728} |
|
{"current_steps": 65, "total_steps": 101, "loss": 0.8063, "lr": 1.4102889538115723e-05, "epoch": 0.6411837237977805, "percentage": 64.36, "elapsed_time": "2:47:02", "remaining_time": "1:32:30", "throughput": 13601.35, "total_tokens": 136314880} |
|
{"current_steps": 66, "total_steps": 101, "loss": 0.8116, "lr": 1.3408411700366813e-05, "epoch": 0.6510480887792849, "percentage": 65.35, "elapsed_time": "2:49:36", "remaining_time": "1:29:56", "throughput": 13601.79, "total_tokens": 138412032} |
|
{"current_steps": 67, "total_steps": 101, "loss": 0.785, "lr": 1.2725147975666948e-05, "epoch": 0.6609124537607891, "percentage": 66.34, "elapsed_time": "2:52:09", "remaining_time": "1:27:21", "throughput": 13602.47, "total_tokens": 140509184} |
|
{"current_steps": 68, "total_steps": 101, "loss": 0.8049, "lr": 1.2053759377541866e-05, "epoch": 0.6707768187422934, "percentage": 67.33, "elapsed_time": "2:54:43", "remaining_time": "1:24:47", "throughput": 13602.6, "total_tokens": 142606336} |
|
{"current_steps": 69, "total_steps": 101, "loss": 0.8034, "lr": 1.1394895431099314e-05, "epoch": 0.6806411837237978, "percentage": 68.32, "elapsed_time": "2:57:17", "remaining_time": "1:22:13", "throughput": 13603.14, "total_tokens": 144703488} |
|
{"current_steps": 70, "total_steps": 101, "loss": 0.7949, "lr": 1.0749193544655434e-05, "epoch": 0.6905055487053021, "percentage": 69.31, "elapsed_time": "2:59:51", "remaining_time": "1:19:38", "throughput": 13603.86, "total_tokens": 146800640} |
|
{"current_steps": 71, "total_steps": 101, "loss": 0.8024, "lr": 1.0117278393083358e-05, "epoch": 0.7003699136868065, "percentage": 70.3, "elapsed_time": "3:02:25", "remaining_time": "1:17:04", "throughput": 13603.82, "total_tokens": 148897792} |
|
{"current_steps": 72, "total_steps": 101, "loss": 0.7608, "lr": 9.499761313480626e-06, "epoch": 0.7102342786683107, "percentage": 71.29, "elapsed_time": "3:04:59", "remaining_time": "1:14:30", "throughput": 13603.58, "total_tokens": 150994944} |
|
{"current_steps": 73, "total_steps": 101, "loss": 0.8012, "lr": 8.897239713740058e-06, "epoch": 0.720098643649815, "percentage": 72.28, "elapsed_time": "3:07:33", "remaining_time": "1:11:56", "throughput": 13603.8, "total_tokens": 153092096} |
|
{"current_steps": 74, "total_steps": 101, "loss": 0.7688, "lr": 8.31029649459616e-06, "epoch": 0.7299630086313194, "percentage": 73.27, "elapsed_time": "3:10:07", "remaining_time": "1:09:22", "throughput": 13604.36, "total_tokens": 155189248} |
|
{"current_steps": 75, "total_steps": 101, "loss": 0.8023, "lr": 7.739499485706334e-06, "epoch": 0.7398273736128237, "percentage": 74.26, "elapsed_time": "3:12:41", "remaining_time": "1:06:47", "throughput": 13604.88, "total_tokens": 157286400} |
|
{"current_steps": 76, "total_steps": 101, "loss": 0.7809, "lr": 7.185400896312328e-06, "epoch": 0.749691738594328, "percentage": 75.25, "elapsed_time": "3:15:14", "remaining_time": "1:04:13", "throughput": 13605.47, "total_tokens": 159383552} |
|
{"current_steps": 77, "total_steps": 101, "loss": 0.8083, "lr": 6.648536781013495e-06, "epoch": 0.7595561035758323, "percentage": 76.24, "elapsed_time": "3:17:48", "remaining_time": "1:01:39", "throughput": 13606.21, "total_tokens": 161480704} |
|
{"current_steps": 78, "total_steps": 101, "loss": 0.7903, "lr": 6.12942652116858e-06, "epoch": 0.7694204685573366, "percentage": 77.23, "elapsed_time": "3:20:21", "remaining_time": "0:59:04", "throughput": 13606.72, "total_tokens": 163577856} |
|
{"current_steps": 79, "total_steps": 101, "loss": 0.7904, "lr": 5.628572322427755e-06, "epoch": 0.7792848335388409, "percentage": 78.22, "elapsed_time": "3:22:55", "remaining_time": "0:56:30", "throughput": 13607.18, "total_tokens": 165675008} |
|
{"current_steps": 80, "total_steps": 101, "loss": 0.797, "lr": 5.1464587288811624e-06, "epoch": 0.7891491985203453, "percentage": 79.21, "elapsed_time": "3:25:29", "remaining_time": "0:53:56", "throughput": 13607.74, "total_tokens": 167772160} |
|
{"current_steps": 81, "total_steps": 101, "loss": 0.7636, "lr": 4.683552154293747e-06, "epoch": 0.7990135635018496, "percentage": 80.2, "elapsed_time": "3:28:02", "remaining_time": "0:51:22", "throughput": 13608.08, "total_tokens": 169869312} |
|
{"current_steps": 82, "total_steps": 101, "loss": 0.7818, "lr": 4.240300430880062e-06, "epoch": 0.8088779284833539, "percentage": 81.19, "elapsed_time": "3:30:38", "remaining_time": "0:48:48", "throughput": 13607.0, "total_tokens": 171966464} |
|
{"current_steps": 83, "total_steps": 101, "loss": 0.7914, "lr": 3.817132376055565e-06, "epoch": 0.8187422934648582, "percentage": 82.18, "elapsed_time": "3:33:11", "remaining_time": "0:46:14", "throughput": 13607.35, "total_tokens": 174063616} |
|
{"current_steps": 84, "total_steps": 101, "loss": 0.7985, "lr": 3.4144573775834134e-06, "epoch": 0.8286066584463625, "percentage": 83.17, "elapsed_time": "3:35:45", "remaining_time": "0:43:39", "throughput": 13607.72, "total_tokens": 176160768} |
|
{"current_steps": 85, "total_steps": 101, "loss": 0.7868, "lr": 3.0326649975182865e-06, "epoch": 0.8384710234278668, "percentage": 84.16, "elapsed_time": "3:38:19", "remaining_time": "0:41:05", "throughput": 13608.19, "total_tokens": 178257920} |
|
{"current_steps": 86, "total_steps": 101, "loss": 0.7972, "lr": 2.672124595330214e-06, "epoch": 0.8483353884093712, "percentage": 85.15, "elapsed_time": "3:40:53", "remaining_time": "0:38:31", "throughput": 13608.54, "total_tokens": 180355072} |
|
{"current_steps": 87, "total_steps": 101, "loss": 0.7933, "lr": 2.333184970573188e-06, "epoch": 0.8581997533908755, "percentage": 86.14, "elapsed_time": "3:43:26", "remaining_time": "0:35:57", "throughput": 13609.13, "total_tokens": 182452224} |
|
{"current_steps": 88, "total_steps": 101, "loss": 0.7695, "lr": 2.0161740254440896e-06, "epoch": 0.8680641183723797, "percentage": 87.13, "elapsed_time": "3:45:59", "remaining_time": "0:33:23", "throughput": 13609.89, "total_tokens": 184549376} |
|
{"current_steps": 89, "total_steps": 101, "loss": 0.7929, "lr": 1.7213984475585144e-06, "epoch": 0.8779284833538841, "percentage": 88.12, "elapsed_time": "3:48:34", "remaining_time": "0:30:49", "throughput": 13609.74, "total_tokens": 186646528} |
|
{"current_steps": 90, "total_steps": 101, "loss": 0.7995, "lr": 1.4491434132502729e-06, "epoch": 0.8877928483353884, "percentage": 89.11, "elapsed_time": "3:51:07", "remaining_time": "0:28:14", "throughput": 13610.21, "total_tokens": 188743680} |
|
{"current_steps": 91, "total_steps": 101, "loss": 0.7857, "lr": 1.1996723116817516e-06, "epoch": 0.8976572133168927, "percentage": 90.1, "elapsed_time": "3:53:41", "remaining_time": "0:25:40", "throughput": 13610.41, "total_tokens": 190840832} |
|
{"current_steps": 92, "total_steps": 101, "loss": 0.8215, "lr": 9.732264900318866e-07, "epoch": 0.9075215782983971, "percentage": 91.09, "elapsed_time": "3:56:15", "remaining_time": "0:23:06", "throughput": 13610.73, "total_tokens": 192937984} |
|
{"current_steps": 93, "total_steps": 101, "loss": 0.7931, "lr": 7.700250200083469e-07, "epoch": 0.9173859432799013, "percentage": 92.08, "elapsed_time": "3:58:49", "remaining_time": "0:20:32", "throughput": 13611.14, "total_tokens": 195035136} |
|
{"current_steps": 94, "total_steps": 101, "loss": 0.7927, "lr": 5.90264485909825e-07, "epoch": 0.9272503082614056, "percentage": 93.07, "elapsed_time": "4:01:22", "remaining_time": "0:17:58", "throughput": 13611.37, "total_tokens": 197132288} |
|
{"current_steps": 95, "total_steps": 101, "loss": 0.7787, "lr": 4.341187944434083e-07, "epoch": 0.93711467324291, "percentage": 94.06, "elapsed_time": "4:03:56", "remaining_time": "0:15:24", "throughput": 13611.55, "total_tokens": 199229440} |
|
{"current_steps": 96, "total_steps": 101, "loss": 0.7771, "lr": 3.017390064810832e-07, "epoch": 0.9469790382244143, "percentage": 95.05, "elapsed_time": "4:06:32", "remaining_time": "0:12:50", "throughput": 13610.5, "total_tokens": 201326592} |
|
{"current_steps": 97, "total_steps": 101, "loss": 0.7931, "lr": 1.9325319091808847e-07, "epoch": 0.9568434032059187, "percentage": 96.04, "elapsed_time": "4:09:06", "remaining_time": "0:10:16", "throughput": 13610.2, "total_tokens": 203423744} |
|
{"current_steps": 98, "total_steps": 101, "loss": 0.7902, "lr": 1.0876630077453487e-07, "epoch": 0.966707768187423, "percentage": 97.03, "elapsed_time": "4:11:40", "remaining_time": "0:07:42", "throughput": 13609.88, "total_tokens": 205520896} |
|
{"current_steps": 99, "total_steps": 101, "loss": 0.7906, "lr": 4.836007166014178e-08, "epoch": 0.9765721331689272, "percentage": 98.02, "elapsed_time": "4:14:14", "remaining_time": "0:05:08", "throughput": 13610.3, "total_tokens": 207618048} |
|
{"current_steps": 100, "total_steps": 101, "loss": 0.8083, "lr": 1.2092942700298038e-08, "epoch": 0.9864364981504316, "percentage": 99.01, "elapsed_time": "4:16:47", "remaining_time": "0:02:34", "throughput": 13610.82, "total_tokens": 209715200} |
|
{"current_steps": 101, "total_steps": 101, "loss": 0.7963, "lr": 0.0, "epoch": 0.9963008631319359, "percentage": 100.0, "elapsed_time": "4:19:21", "remaining_time": "0:00:00", "throughput": 13611.38, "total_tokens": 211812352} |
|
{"current_steps": 101, "total_steps": 101, "epoch": 0.9963008631319359, "percentage": 100.0, "elapsed_time": "4:19:45", "remaining_time": "0:00:00", "throughput": 13590.34, "total_tokens": 211812352} |
|
|