Modelo-Treinado-Mistral2 / trainer_log.jsonl
alexiaassis's picture
Upload folder using huggingface_hub
0d4436f verified
Raw
History Blame Contribute Delete
33.9 kB
{"current_steps": 10, "total_steps": 1395, "loss": 0.6799, "lr": 2.9996919063517692e-05, "epoch": 0.021528525296017224, "percentage": 0.72, "elapsed_time": "0:00:20", "remaining_time": "0:47:43", "throughput": 1796.76, "total_tokens": 37152}
{"current_steps": 20, "total_steps": 1395, "loss": 0.1361, "lr": 2.9986270537572827e-05, "epoch": 0.04305705059203445, "percentage": 1.43, "elapsed_time": "0:00:32", "remaining_time": "0:37:30", "throughput": 2255.76, "total_tokens": 73856}
{"current_steps": 30, "total_steps": 1395, "loss": 0.1558, "lr": 2.9968021784983436e-05, "epoch": 0.06458557588805167, "percentage": 2.15, "elapsed_time": "0:00:45", "remaining_time": "0:34:28", "throughput": 2446.49, "total_tokens": 111232}
{"current_steps": 40, "total_steps": 1395, "loss": 0.1344, "lr": 2.994218206053077e-05, "epoch": 0.0861141011840689, "percentage": 2.87, "elapsed_time": "0:00:57", "remaining_time": "0:32:32", "throughput": 2584.35, "total_tokens": 148992}
{"current_steps": 50, "total_steps": 1395, "loss": 0.1262, "lr": 2.9908764468726846e-05, "epoch": 0.10764262648008611, "percentage": 3.58, "elapsed_time": "0:01:09", "remaining_time": "0:31:14", "throughput": 2671.91, "total_tokens": 186176}
{"current_steps": 60, "total_steps": 1395, "loss": 0.1182, "lr": 2.986778595716853e-05, "epoch": 0.12917115177610333, "percentage": 4.3, "elapsed_time": "0:01:21", "remaining_time": "0:30:20", "throughput": 2735.61, "total_tokens": 223840}
{"current_steps": 70, "total_steps": 1395, "loss": 0.1333, "lr": 2.981926730794264e-05, "epoch": 0.15069967707212056, "percentage": 5.02, "elapsed_time": "0:01:33", "remaining_time": "0:29:38", "throughput": 2777.09, "total_tokens": 260960}
{"current_steps": 80, "total_steps": 1395, "loss": 0.0925, "lr": 2.9763233127086394e-05, "epoch": 0.1722282023681378, "percentage": 5.73, "elapsed_time": "0:01:46", "remaining_time": "0:29:05", "throughput": 2807.44, "total_tokens": 298048}
{"current_steps": 90, "total_steps": 1395, "loss": 0.0886, "lr": 2.9699711832108555e-05, "epoch": 0.193756727664155, "percentage": 6.45, "elapsed_time": "0:01:58", "remaining_time": "0:28:31", "throughput": 2834.45, "total_tokens": 334496}
{"current_steps": 100, "total_steps": 1395, "loss": 0.1127, "lr": 2.9628735637577612e-05, "epoch": 0.21528525296017223, "percentage": 7.17, "elapsed_time": "0:02:10", "remaining_time": "0:28:04", "throughput": 2857.99, "total_tokens": 371712}
{"current_steps": 110, "total_steps": 1395, "loss": 0.1018, "lr": 2.955034053878428e-05, "epoch": 0.23681377825618946, "percentage": 7.89, "elapsed_time": "0:02:22", "remaining_time": "0:27:38", "throughput": 2876.81, "total_tokens": 408512}
{"current_steps": 120, "total_steps": 1395, "loss": 0.1001, "lr": 2.9464566293486653e-05, "epoch": 0.25834230355220666, "percentage": 8.6, "elapsed_time": "0:02:34", "remaining_time": "0:27:17", "throughput": 2893.53, "total_tokens": 446048}
{"current_steps": 130, "total_steps": 1395, "loss": 0.0962, "lr": 2.9371456401747193e-05, "epoch": 0.2798708288482239, "percentage": 9.32, "elapsed_time": "0:02:46", "remaining_time": "0:26:58", "throughput": 2908.32, "total_tokens": 483616}
{"current_steps": 140, "total_steps": 1395, "loss": 0.1076, "lr": 2.9271058083871864e-05, "epoch": 0.3013993541442411, "percentage": 10.04, "elapsed_time": "0:02:58", "remaining_time": "0:26:38", "throughput": 2919.87, "total_tokens": 520768}
{"current_steps": 150, "total_steps": 1395, "loss": 0.0886, "lr": 2.916342225646254e-05, "epoch": 0.32292787944025836, "percentage": 10.75, "elapsed_time": "0:03:10", "remaining_time": "0:26:22", "throughput": 2928.43, "total_tokens": 558240}
{"current_steps": 160, "total_steps": 1395, "loss": 0.0861, "lr": 2.904860350659487e-05, "epoch": 0.3444564047362756, "percentage": 11.47, "elapsed_time": "0:03:22", "remaining_time": "0:26:05", "throughput": 2937.16, "total_tokens": 595648}
{"current_steps": 170, "total_steps": 1395, "loss": 0.1158, "lr": 2.8926660064134637e-05, "epoch": 0.36598493003229277, "percentage": 12.19, "elapsed_time": "0:03:34", "remaining_time": "0:25:48", "throughput": 2942.81, "total_tokens": 632352}
{"current_steps": 180, "total_steps": 1395, "loss": 0.0931, "lr": 2.8797653772206726e-05, "epoch": 0.38751345532831, "percentage": 12.9, "elapsed_time": "0:03:46", "remaining_time": "0:25:31", "throughput": 2950.21, "total_tokens": 669440}
{"current_steps": 190, "total_steps": 1395, "loss": 0.0964, "lr": 2.8661650055831645e-05, "epoch": 0.40904198062432723, "percentage": 13.62, "elapsed_time": "0:03:59", "remaining_time": "0:25:15", "throughput": 2957.11, "total_tokens": 706784}
{"current_steps": 200, "total_steps": 1395, "loss": 0.0708, "lr": 2.8518717888745486e-05, "epoch": 0.43057050592034446, "percentage": 14.34, "elapsed_time": "0:04:11", "remaining_time": "0:25:00", "throughput": 2963.94, "total_tokens": 744480}
{"current_steps": 210, "total_steps": 1395, "loss": 0.0954, "lr": 2.836892975842015e-05, "epoch": 0.4520990312163617, "percentage": 15.05, "elapsed_time": "0:04:23", "remaining_time": "0:24:45", "throughput": 2968.41, "total_tokens": 781632}
{"current_steps": 220, "total_steps": 1395, "loss": 0.0897, "lr": 2.8212361629301655e-05, "epoch": 0.4736275565123789, "percentage": 15.77, "elapsed_time": "0:04:35", "remaining_time": "0:24:31", "throughput": 2973.98, "total_tokens": 819264}
{"current_steps": 230, "total_steps": 1395, "loss": 0.0783, "lr": 2.8049092904285033e-05, "epoch": 0.4951560818083961, "percentage": 16.49, "elapsed_time": "0:04:47", "remaining_time": "0:24:16", "throughput": 2977.07, "total_tokens": 855936}
{"current_steps": 240, "total_steps": 1395, "loss": 0.092, "lr": 2.7879206384445526e-05, "epoch": 0.5166846071044133, "percentage": 17.2, "elapsed_time": "0:04:59", "remaining_time": "0:24:02", "throughput": 2981.87, "total_tokens": 893536}
{"current_steps": 250, "total_steps": 1395, "loss": 0.1014, "lr": 2.7702788227046286e-05, "epoch": 0.5382131324004306, "percentage": 17.92, "elapsed_time": "0:05:11", "remaining_time": "0:23:47", "throughput": 2984.96, "total_tokens": 930272}
{"current_steps": 260, "total_steps": 1395, "loss": 0.1032, "lr": 2.751992790184413e-05, "epoch": 0.5597416576964478, "percentage": 18.64, "elapsed_time": "0:05:24", "remaining_time": "0:23:34", "throughput": 2989.88, "total_tokens": 968768}
{"current_steps": 270, "total_steps": 1395, "loss": 0.1016, "lr": 2.733071814571527e-05, "epoch": 0.581270182992465, "percentage": 19.35, "elapsed_time": "0:05:36", "remaining_time": "0:23:20", "throughput": 2992.79, "total_tokens": 1005888}
{"current_steps": 280, "total_steps": 1395, "loss": 0.0843, "lr": 2.7135254915624213e-05, "epoch": 0.6027987082884823, "percentage": 20.07, "elapsed_time": "0:05:48", "remaining_time": "0:23:06", "throughput": 2996.74, "total_tokens": 1043744}
{"current_steps": 290, "total_steps": 1395, "loss": 0.1012, "lr": 2.693363733995954e-05, "epoch": 0.6243272335844995, "percentage": 20.79, "elapsed_time": "0:06:00", "remaining_time": "0:22:54", "throughput": 3000.16, "total_tokens": 1081920}
{"current_steps": 300, "total_steps": 1395, "loss": 0.0835, "lr": 2.672596766826138e-05, "epoch": 0.6458557588805167, "percentage": 21.51, "elapsed_time": "0:06:12", "remaining_time": "0:22:40", "throughput": 3001.47, "total_tokens": 1118784}
{"current_steps": 310, "total_steps": 1395, "loss": 0.0884, "lr": 2.6512351219365927e-05, "epoch": 0.667384284176534, "percentage": 22.22, "elapsed_time": "0:06:24", "remaining_time": "0:22:26", "throughput": 3002.24, "total_tokens": 1155392}
{"current_steps": 320, "total_steps": 1395, "loss": 0.0907, "lr": 2.6292896327993467e-05, "epoch": 0.6889128094725512, "percentage": 22.94, "elapsed_time": "0:06:37", "remaining_time": "0:22:13", "throughput": 3004.35, "total_tokens": 1192768}
{"current_steps": 330, "total_steps": 1395, "loss": 0.0786, "lr": 2.606771428980681e-05, "epoch": 0.7104413347685683, "percentage": 23.66, "elapsed_time": "0:06:49", "remaining_time": "0:22:00", "throughput": 3006.91, "total_tokens": 1230464}
{"current_steps": 340, "total_steps": 1395, "loss": 0.0863, "lr": 2.5836919304968184e-05, "epoch": 0.7319698600645855, "percentage": 24.37, "elapsed_time": "0:07:01", "remaining_time": "0:21:47", "throughput": 3008.52, "total_tokens": 1267520}
{"current_steps": 350, "total_steps": 1395, "loss": 0.0976, "lr": 2.5600628420223057e-05, "epoch": 0.7534983853606028, "percentage": 25.09, "elapsed_time": "0:07:13", "remaining_time": "0:21:35", "throughput": 3012.05, "total_tokens": 1306592}
{"current_steps": 360, "total_steps": 1395, "loss": 0.0914, "lr": 2.535896146954037e-05, "epoch": 0.77502691065662, "percentage": 25.81, "elapsed_time": "0:07:25", "remaining_time": "0:21:21", "throughput": 3013.82, "total_tokens": 1343840}
{"current_steps": 370, "total_steps": 1395, "loss": 0.0997, "lr": 2.5112041013339212e-05, "epoch": 0.7965554359526372, "percentage": 26.52, "elapsed_time": "0:07:38", "remaining_time": "0:21:09", "throughput": 3016.75, "total_tokens": 1382816}
{"current_steps": 380, "total_steps": 1395, "loss": 0.0689, "lr": 2.48599922763328e-05, "epoch": 0.8180839612486545, "percentage": 27.24, "elapsed_time": "0:07:50", "remaining_time": "0:20:56", "throughput": 3019.08, "total_tokens": 1420352}
{"current_steps": 390, "total_steps": 1395, "loss": 0.1062, "lr": 2.4602943084021286e-05, "epoch": 0.8396124865446717, "percentage": 27.96, "elapsed_time": "0:08:02", "remaining_time": "0:20:43", "throughput": 3020.05, "total_tokens": 1457280}
{"current_steps": 400, "total_steps": 1395, "loss": 0.0579, "lr": 2.434102379786553e-05, "epoch": 0.8611410118406889, "percentage": 28.67, "elapsed_time": "0:08:14", "remaining_time": "0:20:30", "throughput": 3020.61, "total_tokens": 1493984}
{"current_steps": 410, "total_steps": 1395, "loss": 0.074, "lr": 2.4074367249174864e-05, "epoch": 0.8826695371367062, "percentage": 29.39, "elapsed_time": "0:08:26", "remaining_time": "0:20:17", "throughput": 3022.13, "total_tokens": 1531392}
{"current_steps": 420, "total_steps": 1395, "loss": 0.0774, "lr": 2.380310867174219e-05, "epoch": 0.9041980624327234, "percentage": 30.11, "elapsed_time": "0:08:38", "remaining_time": "0:20:04", "throughput": 3023.51, "total_tokens": 1568992}
{"current_steps": 430, "total_steps": 1395, "loss": 0.0771, "lr": 2.3527385633260724e-05, "epoch": 0.9257265877287406, "percentage": 30.82, "elapsed_time": "0:08:50", "remaining_time": "0:19:51", "throughput": 3025.2, "total_tokens": 1606144}
{"current_steps": 440, "total_steps": 1395, "loss": 0.075, "lr": 2.3247337965557097e-05, "epoch": 0.9472551130247578, "percentage": 31.54, "elapsed_time": "0:09:02", "remaining_time": "0:19:37", "throughput": 3025.01, "total_tokens": 1641696}
{"current_steps": 450, "total_steps": 1395, "loss": 0.0785, "lr": 2.2963107693676192e-05, "epoch": 0.9687836383207751, "percentage": 32.26, "elapsed_time": "0:09:14", "remaining_time": "0:19:25", "throughput": 3025.73, "total_tokens": 1678816}
{"current_steps": 460, "total_steps": 1395, "loss": 0.074, "lr": 2.2674838963853738e-05, "epoch": 0.9903121636167922, "percentage": 32.97, "elapsed_time": "0:09:26", "remaining_time": "0:19:12", "throughput": 3026.88, "total_tokens": 1715808}
{"current_steps": 470, "total_steps": 1395, "loss": 0.0653, "lr": 2.2382677970413097e-05, "epoch": 1.0107642626480087, "percentage": 33.69, "elapsed_time": "0:09:38", "remaining_time": "0:18:58", "throughput": 3028.66, "total_tokens": 1751552}
{"current_steps": 480, "total_steps": 1395, "loss": 0.0632, "lr": 2.2086772881623455e-05, "epoch": 1.0322927879440258, "percentage": 34.41, "elapsed_time": "0:09:50", "remaining_time": "0:18:45", "throughput": 3029.41, "total_tokens": 1788544}
{"current_steps": 490, "total_steps": 1395, "loss": 0.0472, "lr": 2.1787273764556827e-05, "epoch": 1.0538213132400431, "percentage": 35.13, "elapsed_time": "0:10:02", "remaining_time": "0:18:33", "throughput": 3030.79, "total_tokens": 1826496}
{"current_steps": 500, "total_steps": 1395, "loss": 0.0534, "lr": 2.1484332508982167e-05, "epoch": 1.0753498385360603, "percentage": 35.84, "elapsed_time": "0:10:14", "remaining_time": "0:18:20", "throughput": 3032.11, "total_tokens": 1864544}
{"current_steps": 510, "total_steps": 1395, "loss": 0.0751, "lr": 2.11781027503351e-05, "epoch": 1.0968783638320776, "percentage": 36.56, "elapsed_time": "0:10:27", "remaining_time": "0:18:08", "throughput": 3032.88, "total_tokens": 1901856}
{"current_steps": 520, "total_steps": 1395, "loss": 0.0747, "lr": 2.0868739791802312e-05, "epoch": 1.1184068891280947, "percentage": 37.28, "elapsed_time": "0:10:39", "remaining_time": "0:17:55", "throughput": 3033.66, "total_tokens": 1939264}
{"current_steps": 530, "total_steps": 1395, "loss": 0.0492, "lr": 2.0556400525560168e-05, "epoch": 1.1399354144241118, "percentage": 37.99, "elapsed_time": "0:10:51", "remaining_time": "0:17:42", "throughput": 3034.22, "total_tokens": 1975872}
{"current_steps": 540, "total_steps": 1395, "loss": 0.0651, "lr": 2.0241243353207484e-05, "epoch": 1.1614639397201292, "percentage": 38.71, "elapsed_time": "0:11:03", "remaining_time": "0:17:30", "throughput": 3034.64, "total_tokens": 2012928}
{"current_steps": 550, "total_steps": 1395, "loss": 0.0565, "lr": 1.9923428105432796e-05, "epoch": 1.1829924650161463, "percentage": 39.43, "elapsed_time": "0:11:15", "remaining_time": "0:17:18", "throughput": 3035.81, "total_tokens": 2051168}
{"current_steps": 560, "total_steps": 1395, "loss": 0.0696, "lr": 1.9603115960956852e-05, "epoch": 1.2045209903121636, "percentage": 40.14, "elapsed_time": "0:11:27", "remaining_time": "0:17:05", "throughput": 3036.73, "total_tokens": 2088576}
{"current_steps": 570, "total_steps": 1395, "loss": 0.0553, "lr": 1.9280469364791505e-05, "epoch": 1.2260495156081808, "percentage": 40.86, "elapsed_time": "0:11:39", "remaining_time": "0:16:52", "throughput": 3037.22, "total_tokens": 2125216}
{"current_steps": 580, "total_steps": 1395, "loss": 0.0666, "lr": 1.8955651945856354e-05, "epoch": 1.247578040904198, "percentage": 41.58, "elapsed_time": "0:11:51", "remaining_time": "0:16:40", "throughput": 3037.97, "total_tokens": 2162816}
{"current_steps": 590, "total_steps": 1395, "loss": 0.0449, "lr": 1.8628828433995013e-05, "epoch": 1.2691065662002152, "percentage": 42.29, "elapsed_time": "0:12:04", "remaining_time": "0:16:27", "throughput": 3038.24, "total_tokens": 2199712}
{"current_steps": 600, "total_steps": 1395, "loss": 0.0522, "lr": 1.8300164576433035e-05, "epoch": 1.2906350914962326, "percentage": 43.01, "elapsed_time": "0:12:16", "remaining_time": "0:16:15", "throughput": 3038.41, "total_tokens": 2236416}
{"current_steps": 610, "total_steps": 1395, "loss": 0.0638, "lr": 1.7969827053719862e-05, "epoch": 1.3121636167922497, "percentage": 43.73, "elapsed_time": "0:12:28", "remaining_time": "0:16:02", "throughput": 3039.22, "total_tokens": 2274272}
{"current_steps": 620, "total_steps": 1395, "loss": 0.0683, "lr": 1.7637983395197465e-05, "epoch": 1.333692142088267, "percentage": 44.44, "elapsed_time": "0:12:40", "remaining_time": "0:15:50", "throughput": 3039.15, "total_tokens": 2310688}
{"current_steps": 630, "total_steps": 1395, "loss": 0.0678, "lr": 1.7304801894038522e-05, "epoch": 1.3552206673842842, "percentage": 45.16, "elapsed_time": "0:12:52", "remaining_time": "0:15:38", "throughput": 3039.88, "total_tokens": 2348608}
{"current_steps": 640, "total_steps": 1395, "loss": 0.0502, "lr": 1.6970451521897198e-05, "epoch": 1.3767491926803013, "percentage": 45.88, "elapsed_time": "0:13:04", "remaining_time": "0:15:25", "throughput": 3040.29, "total_tokens": 2386144}
{"current_steps": 650, "total_steps": 1395, "loss": 0.0728, "lr": 1.663510184321587e-05, "epoch": 1.3982777179763186, "percentage": 46.59, "elapsed_time": "0:13:16", "remaining_time": "0:15:13", "throughput": 3040.28, "total_tokens": 2422912}
{"current_steps": 660, "total_steps": 1395, "loss": 0.059, "lr": 1.6298922929231194e-05, "epoch": 1.419806243272336, "percentage": 47.31, "elapsed_time": "0:13:29", "remaining_time": "0:15:01", "throughput": 3040.16, "total_tokens": 2459744}
{"current_steps": 670, "total_steps": 1395, "loss": 0.0514, "lr": 1.5962085271723158e-05, "epoch": 1.441334768568353, "percentage": 48.03, "elapsed_time": "0:13:41", "remaining_time": "0:14:48", "throughput": 3040.77, "total_tokens": 2497184}
{"current_steps": 680, "total_steps": 1395, "loss": 0.0689, "lr": 1.5624759696550874e-05, "epoch": 1.4628632938643702, "percentage": 48.75, "elapsed_time": "0:13:53", "remaining_time": "0:14:36", "throughput": 3041.47, "total_tokens": 2535456}
{"current_steps": 690, "total_steps": 1395, "loss": 0.0338, "lr": 1.528711727701893e-05, "epoch": 1.4843918191603875, "percentage": 49.46, "elapsed_time": "0:14:05", "remaining_time": "0:14:24", "throughput": 3041.91, "total_tokens": 2572704}
{"current_steps": 700, "total_steps": 1395, "loss": 0.0621, "lr": 1.4949329247118258e-05, "epoch": 1.5059203444564049, "percentage": 50.18, "elapsed_time": "0:14:17", "remaining_time": "0:14:11", "throughput": 3042.48, "total_tokens": 2609696}
{"current_steps": 710, "total_steps": 1395, "loss": 0.057, "lr": 1.4611566914685489e-05, "epoch": 1.527448869752422, "percentage": 50.9, "elapsed_time": "0:14:29", "remaining_time": "0:13:59", "throughput": 3042.86, "total_tokens": 2646976}
{"current_steps": 720, "total_steps": 1395, "loss": 0.0632, "lr": 1.4274001574524894e-05, "epoch": 1.5489773950484391, "percentage": 51.61, "elapsed_time": "0:14:42", "remaining_time": "0:13:46", "throughput": 3043.37, "total_tokens": 2684576}
{"current_steps": 730, "total_steps": 1395, "loss": 0.0361, "lr": 1.3936804421536906e-05, "epoch": 1.5705059203444565, "percentage": 52.33, "elapsed_time": "0:14:54", "remaining_time": "0:13:34", "throughput": 3041.59, "total_tokens": 2720736}
{"current_steps": 740, "total_steps": 1395, "loss": 0.0503, "lr": 1.3600146463897327e-05, "epoch": 1.5920344456404736, "percentage": 53.05, "elapsed_time": "0:15:06", "remaining_time": "0:13:22", "throughput": 3041.96, "total_tokens": 2757728}
{"current_steps": 750, "total_steps": 1395, "loss": 0.0843, "lr": 1.3264198436331193e-05, "epoch": 1.6135629709364907, "percentage": 53.76, "elapsed_time": "0:15:18", "remaining_time": "0:13:10", "throughput": 3042.71, "total_tokens": 2795168}
{"current_steps": 760, "total_steps": 1395, "loss": 0.05, "lr": 1.2929130713525396e-05, "epoch": 1.635091496232508, "percentage": 54.48, "elapsed_time": "0:15:30", "remaining_time": "0:12:57", "throughput": 3042.97, "total_tokens": 2832000}
{"current_steps": 770, "total_steps": 1395, "loss": 0.0608, "lr": 1.2595113223723788e-05, "epoch": 1.6566200215285254, "percentage": 55.2, "elapsed_time": "0:15:42", "remaining_time": "0:12:45", "throughput": 3043.39, "total_tokens": 2869696}
{"current_steps": 780, "total_steps": 1395, "loss": 0.0422, "lr": 1.2262315362548825e-05, "epoch": 1.6781485468245425, "percentage": 55.91, "elapsed_time": "0:15:55", "remaining_time": "0:12:33", "throughput": 3044.09, "total_tokens": 2907840}
{"current_steps": 790, "total_steps": 1395, "loss": 0.0558, "lr": 1.1930905907093196e-05, "epoch": 1.6996770721205596, "percentage": 56.63, "elapsed_time": "0:16:07", "remaining_time": "0:12:20", "throughput": 3043.47, "total_tokens": 2943232}
{"current_steps": 800, "total_steps": 1395, "loss": 0.0509, "lr": 1.1601052930325236e-05, "epoch": 1.721205597416577, "percentage": 57.35, "elapsed_time": "0:16:19", "remaining_time": "0:12:08", "throughput": 3043.89, "total_tokens": 2980608}
{"current_steps": 810, "total_steps": 1395, "loss": 0.0674, "lr": 1.127292371585141e-05, "epoch": 1.7427341227125943, "percentage": 58.06, "elapsed_time": "0:16:31", "remaining_time": "0:11:55", "throughput": 3044.5, "total_tokens": 3018080}
{"current_steps": 820, "total_steps": 1395, "loss": 0.0694, "lr": 1.0946684673079074e-05, "epoch": 1.7642626480086114, "percentage": 58.78, "elapsed_time": "0:16:43", "remaining_time": "0:11:43", "throughput": 3044.95, "total_tokens": 3055520}
{"current_steps": 830, "total_steps": 1395, "loss": 0.0383, "lr": 1.0622501252822628e-05, "epoch": 1.7857911733046286, "percentage": 59.5, "elapsed_time": "0:16:55", "remaining_time": "0:11:31", "throughput": 3045.52, "total_tokens": 3092800}
{"current_steps": 840, "total_steps": 1395, "loss": 0.0547, "lr": 1.0300537863395823e-05, "epoch": 1.807319698600646, "percentage": 60.22, "elapsed_time": "0:17:07", "remaining_time": "0:11:19", "throughput": 3046.03, "total_tokens": 3130656}
{"current_steps": 850, "total_steps": 1395, "loss": 0.0516, "lr": 9.98095778723271e-06, "epoch": 1.8288482238966632, "percentage": 60.93, "elapsed_time": "0:17:19", "remaining_time": "0:11:06", "throughput": 3046.52, "total_tokens": 3167744}
{"current_steps": 860, "total_steps": 1395, "loss": 0.0628, "lr": 9.663923098079656e-06, "epoch": 1.8503767491926801, "percentage": 61.65, "elapsed_time": "0:17:31", "remaining_time": "0:10:54", "throughput": 3047.17, "total_tokens": 3205376}
{"current_steps": 870, "total_steps": 1395, "loss": 0.0733, "lr": 9.349594578800259e-06, "epoch": 1.8719052744886975, "percentage": 62.37, "elapsed_time": "0:17:44", "remaining_time": "0:10:42", "throughput": 3047.51, "total_tokens": 3242976}
{"current_steps": 880, "total_steps": 1395, "loss": 0.0727, "lr": 9.038131639834977e-06, "epoch": 1.8934337997847148, "percentage": 63.08, "elapsed_time": "0:17:56", "remaining_time": "0:10:29", "throughput": 3047.92, "total_tokens": 3280096}
{"current_steps": 890, "total_steps": 1395, "loss": 0.058, "lr": 8.7296922383568e-06, "epoch": 1.914962325080732, "percentage": 63.8, "elapsed_time": "0:18:08", "remaining_time": "0:10:17", "throughput": 3048.21, "total_tokens": 3316960}
{"current_steps": 900, "total_steps": 1395, "loss": 0.0588, "lr": 8.424432798163838e-06, "epoch": 1.936490850376749, "percentage": 64.52, "elapsed_time": "0:18:20", "remaining_time": "0:10:05", "throughput": 3048.41, "total_tokens": 3353600}
{"current_steps": 910, "total_steps": 1395, "loss": 0.0375, "lr": 8.122508130349711e-06, "epoch": 1.9580193756727664, "percentage": 65.23, "elapsed_time": "0:18:32", "remaining_time": "0:09:52", "throughput": 3048.92, "total_tokens": 3390592}
{"current_steps": 920, "total_steps": 1395, "loss": 0.0644, "lr": 7.82407135479164e-06, "epoch": 1.9795479009687837, "percentage": 65.95, "elapsed_time": "0:18:44", "remaining_time": "0:09:40", "throughput": 3049.05, "total_tokens": 3427840}
{"current_steps": 930, "total_steps": 1395, "loss": 0.0347, "lr": 7.529273822496379e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:18:55", "remaining_time": "0:09:27", "throughput": 3049.71, "total_tokens": 3464032}
{"current_steps": 940, "total_steps": 1395, "loss": 0.0491, "lr": 7.238265038843143e-06, "epoch": 2.0215285252960173, "percentage": 67.38, "elapsed_time": "0:19:07", "remaining_time": "0:09:15", "throughput": 3049.77, "total_tokens": 3501056}
{"current_steps": 950, "total_steps": 1395, "loss": 0.0263, "lr": 6.951192587762555e-06, "epoch": 2.0430570505920342, "percentage": 68.1, "elapsed_time": "0:19:20", "remaining_time": "0:09:03", "throughput": 3049.91, "total_tokens": 3538464}
{"current_steps": 960, "total_steps": 1395, "loss": 0.029, "lr": 6.668202056890052e-06, "epoch": 2.0645855758880516, "percentage": 68.82, "elapsed_time": "0:19:32", "remaining_time": "0:08:51", "throughput": 3050.03, "total_tokens": 3575552}
{"current_steps": 970, "total_steps": 1395, "loss": 0.0338, "lr": 6.389436963731707e-06, "epoch": 2.086114101184069, "percentage": 69.53, "elapsed_time": "0:19:44", "remaining_time": "0:08:38", "throughput": 3050.09, "total_tokens": 3612736}
{"current_steps": 980, "total_steps": 1395, "loss": 0.0427, "lr": 6.115038682879904e-06, "epoch": 2.1076426264800863, "percentage": 70.25, "elapsed_time": "0:19:56", "remaining_time": "0:08:26", "throughput": 3050.36, "total_tokens": 3650464}
{"current_steps": 990, "total_steps": 1395, "loss": 0.0323, "lr": 5.845146374315781e-06, "epoch": 2.129171151776103, "percentage": 70.97, "elapsed_time": "0:20:08", "remaining_time": "0:08:14", "throughput": 3050.25, "total_tokens": 3687392}
{"current_steps": 1000, "total_steps": 1395, "loss": 0.0504, "lr": 5.579896912834807e-06, "epoch": 2.1506996770721205, "percentage": 71.68, "elapsed_time": "0:20:21", "remaining_time": "0:08:02", "throughput": 3050.66, "total_tokens": 3725152}
{"current_steps": 1010, "total_steps": 1395, "loss": 0.043, "lr": 5.319424818631293e-06, "epoch": 2.172228202368138, "percentage": 72.4, "elapsed_time": "0:20:34", "remaining_time": "0:07:50", "throughput": 3048.97, "total_tokens": 3762752}
{"current_steps": 1020, "total_steps": 1395, "loss": 0.0377, "lr": 5.063862189076988e-06, "epoch": 2.193756727664155, "percentage": 73.12, "elapsed_time": "0:20:46", "remaining_time": "0:07:38", "throughput": 3049.38, "total_tokens": 3800736}
{"current_steps": 1030, "total_steps": 1395, "loss": 0.0408, "lr": 4.813338631728471e-06, "epoch": 2.215285252960172, "percentage": 73.84, "elapsed_time": "0:20:58", "remaining_time": "0:07:26", "throughput": 3049.81, "total_tokens": 3838432}
{"current_steps": 1040, "total_steps": 1395, "loss": 0.0328, "lr": 4.567981198597168e-06, "epoch": 2.2368137782561894, "percentage": 74.55, "elapsed_time": "0:21:10", "remaining_time": "0:07:13", "throughput": 3050.1, "total_tokens": 3876224}
{"current_steps": 1050, "total_steps": 1395, "loss": 0.0259, "lr": 4.327914321715459e-06, "epoch": 2.2583423035522068, "percentage": 75.27, "elapsed_time": "0:21:22", "remaining_time": "0:07:01", "throughput": 3050.4, "total_tokens": 3913216}
{"current_steps": 1060, "total_steps": 1395, "loss": 0.027, "lr": 4.09325975003146e-06, "epoch": 2.2798708288482237, "percentage": 75.99, "elapsed_time": "0:21:34", "remaining_time": "0:06:49", "throughput": 3050.52, "total_tokens": 3950208}
{"current_steps": 1070, "total_steps": 1395, "loss": 0.0347, "lr": 3.864136487664538e-06, "epoch": 2.301399354144241, "percentage": 76.7, "elapsed_time": "0:21:46", "remaining_time": "0:06:36", "throughput": 3050.36, "total_tokens": 3986752}
{"current_steps": 1080, "total_steps": 1395, "loss": 0.0189, "lr": 3.640660733552863e-06, "epoch": 2.3229278794402584, "percentage": 77.42, "elapsed_time": "0:21:58", "remaining_time": "0:06:24", "throughput": 3050.42, "total_tokens": 4023360}
{"current_steps": 1090, "total_steps": 1395, "loss": 0.0186, "lr": 3.4229458225235696e-06, "epoch": 2.3444564047362757, "percentage": 78.14, "elapsed_time": "0:22:11", "remaining_time": "0:06:12", "throughput": 3050.89, "total_tokens": 4061856}
{"current_steps": 1100, "total_steps": 1395, "loss": 0.0366, "lr": 3.211102167815469e-06, "epoch": 2.3659849300322926, "percentage": 78.85, "elapsed_time": "0:22:23", "remaining_time": "0:06:00", "throughput": 3050.95, "total_tokens": 4098464}
{"current_steps": 1110, "total_steps": 1395, "loss": 0.0333, "lr": 3.0052372050834025e-06, "epoch": 2.38751345532831, "percentage": 79.57, "elapsed_time": "0:22:35", "remaining_time": "0:05:48", "throughput": 3051.25, "total_tokens": 4136576}
{"current_steps": 1120, "total_steps": 1395, "loss": 0.0259, "lr": 2.805455337912722e-06, "epoch": 2.4090419806243273, "percentage": 80.29, "elapsed_time": "0:22:47", "remaining_time": "0:05:35", "throughput": 3051.82, "total_tokens": 4174528}
{"current_steps": 1130, "total_steps": 1395, "loss": 0.0377, "lr": 2.611857884871379e-06, "epoch": 2.4305705059203446, "percentage": 81.0, "elapsed_time": "0:23:00", "remaining_time": "0:05:23", "throughput": 3051.95, "total_tokens": 4211712}
{"current_steps": 1140, "total_steps": 1395, "loss": 0.0457, "lr": 2.424543028126661e-06, "epoch": 2.4520990312163615, "percentage": 81.72, "elapsed_time": "0:23:12", "remaining_time": "0:05:11", "throughput": 3052.0, "total_tokens": 4248800}
{"current_steps": 1150, "total_steps": 1395, "loss": 0.0341, "lr": 2.243605763652489e-06, "epoch": 2.473627556512379, "percentage": 82.44, "elapsed_time": "0:23:24", "remaining_time": "0:04:59", "throughput": 3052.3, "total_tokens": 4286496}
{"current_steps": 1160, "total_steps": 1395, "loss": 0.0311, "lr": 2.0691378530525933e-06, "epoch": 2.495156081808396, "percentage": 83.15, "elapsed_time": "0:23:36", "remaining_time": "0:04:46", "throughput": 3052.38, "total_tokens": 4323328}
{"current_steps": 1170, "total_steps": 1395, "loss": 0.0373, "lr": 1.9012277770239829e-06, "epoch": 2.5166846071044136, "percentage": 83.87, "elapsed_time": "0:23:48", "remaining_time": "0:04:34", "throughput": 3052.59, "total_tokens": 4360384}
{"current_steps": 1180, "total_steps": 1395, "loss": 0.0176, "lr": 1.7399606904843224e-06, "epoch": 2.5382131324004304, "percentage": 84.59, "elapsed_time": "0:24:00", "remaining_time": "0:04:22", "throughput": 3052.55, "total_tokens": 4397440}
{"current_steps": 1190, "total_steps": 1395, "loss": 0.0264, "lr": 1.5854183793859577e-06, "epoch": 2.559741657696448, "percentage": 85.3, "elapsed_time": "0:24:12", "remaining_time": "0:04:10", "throughput": 3052.77, "total_tokens": 4435584}
{"current_steps": 1200, "total_steps": 1395, "loss": 0.0211, "lr": 1.437679219238498e-06, "epoch": 2.581270182992465, "percentage": 86.02, "elapsed_time": "0:24:25", "remaining_time": "0:03:58", "throughput": 3053.0, "total_tokens": 4472800}
{"current_steps": 1210, "total_steps": 1395, "loss": 0.0264, "lr": 1.2968181353609854e-06, "epoch": 2.602798708288482, "percentage": 86.74, "elapsed_time": "0:24:37", "remaining_time": "0:03:45", "throughput": 3053.33, "total_tokens": 4510464}
{"current_steps": 1220, "total_steps": 1395, "loss": 0.0369, "lr": 1.1629065648838495e-06, "epoch": 2.6243272335844994, "percentage": 87.46, "elapsed_time": "0:24:49", "remaining_time": "0:03:33", "throughput": 3052.94, "total_tokens": 4546592}
{"current_steps": 1230, "total_steps": 1395, "loss": 0.0285, "lr": 1.0360124205198102e-06, "epoch": 2.6458557588805167, "percentage": 88.17, "elapsed_time": "0:25:01", "remaining_time": "0:03:21", "throughput": 3053.06, "total_tokens": 4583680}
{"current_steps": 1240, "total_steps": 1395, "loss": 0.0452, "lr": 9.162000561222672e-07, "epoch": 2.667384284176534, "percentage": 88.89, "elapsed_time": "0:25:13", "remaining_time": "0:03:09", "throughput": 3053.46, "total_tokens": 4622080}
{"current_steps": 1250, "total_steps": 1395, "loss": 0.051, "lr": 8.035302340484646e-07, "epoch": 2.6889128094725514, "percentage": 89.61, "elapsed_time": "0:25:25", "remaining_time": "0:02:56", "throughput": 3053.44, "total_tokens": 4658848}
{"current_steps": 1260, "total_steps": 1395, "loss": 0.0217, "lr": 6.980600943441273e-07, "epoch": 2.7104413347685683, "percentage": 90.32, "elapsed_time": "0:25:37", "remaining_time": "0:02:44", "throughput": 3053.64, "total_tokens": 4695968}
{"current_steps": 1270, "total_steps": 1395, "loss": 0.0414, "lr": 5.998431257651132e-07, "epoch": 2.7319698600645856, "percentage": 91.04, "elapsed_time": "0:25:50", "remaining_time": "0:02:32", "throughput": 3053.69, "total_tokens": 4733344}
{"current_steps": 1280, "total_steps": 1395, "loss": 0.0315, "lr": 5.089291386508055e-07, "epoch": 2.7534983853606025, "percentage": 91.76, "elapsed_time": "0:26:02", "remaining_time": "0:02:20", "throughput": 3053.89, "total_tokens": 4770496}
{"current_steps": 1290, "total_steps": 1395, "loss": 0.0336, "lr": 4.2536423966299256e-07, "epoch": 2.77502691065662, "percentage": 92.47, "elapsed_time": "0:26:14", "remaining_time": "0:02:08", "throughput": 3053.79, "total_tokens": 4807456}
{"current_steps": 1300, "total_steps": 1395, "loss": 0.0426, "lr": 3.491908084030776e-07, "epoch": 2.7965554359526372, "percentage": 93.19, "elapsed_time": "0:26:26", "remaining_time": "0:01:55", "throughput": 3053.9, "total_tokens": 4845440}
{"current_steps": 1310, "total_steps": 1395, "loss": 0.0434, "lr": 2.804474759194176e-07, "epoch": 2.8180839612486546, "percentage": 93.91, "elapsed_time": "0:26:38", "remaining_time": "0:01:43", "throughput": 3054.19, "total_tokens": 4883392}
{"current_steps": 1320, "total_steps": 1395, "loss": 0.0297, "lr": 2.1916910511575627e-07, "epoch": 2.839612486544672, "percentage": 94.62, "elapsed_time": "0:26:50", "remaining_time": "0:01:31", "throughput": 3054.36, "total_tokens": 4920384}
{"current_steps": 1330, "total_steps": 1395, "loss": 0.036, "lr": 1.6538677307062933e-07, "epoch": 2.861141011840689, "percentage": 95.34, "elapsed_time": "0:27:03", "remaining_time": "0:01:19", "throughput": 3054.48, "total_tokens": 4957888}
{"current_steps": 1340, "total_steps": 1395, "loss": 0.0209, "lr": 1.1912775527676278e-07, "epoch": 2.882669537136706, "percentage": 96.06, "elapsed_time": "0:27:15", "remaining_time": "0:01:07", "throughput": 3054.75, "total_tokens": 4994944}
{"current_steps": 1350, "total_steps": 1395, "loss": 0.0467, "lr": 8.04155118084099e-08, "epoch": 2.9041980624327235, "percentage": 96.77, "elapsed_time": "0:27:27", "remaining_time": "0:00:54", "throughput": 3054.83, "total_tokens": 5031584}
{"current_steps": 1360, "total_steps": 1395, "loss": 0.0414, "lr": 4.9269675423671556e-08, "epoch": 2.9257265877287404, "percentage": 97.49, "elapsed_time": "0:27:39", "remaining_time": "0:00:42", "throughput": 3054.95, "total_tokens": 5068928}
{"current_steps": 1370, "total_steps": 1395, "loss": 0.0182, "lr": 2.570604160781753e-08, "epoch": 2.9472551130247577, "percentage": 98.21, "elapsed_time": "0:27:51", "remaining_time": "0:00:30", "throughput": 3054.99, "total_tokens": 5105984}
{"current_steps": 1380, "total_steps": 1395, "loss": 0.0236, "lr": 9.736560562675912e-09, "epoch": 2.968783638320775, "percentage": 98.92, "elapsed_time": "0:28:03", "remaining_time": "0:00:18", "throughput": 3055.07, "total_tokens": 5143296}
{"current_steps": 1390, "total_steps": 1395, "loss": 0.0323, "lr": 1.3693311461326908e-09, "epoch": 2.9903121636167924, "percentage": 99.64, "elapsed_time": "0:28:15", "remaining_time": "0:00:06", "throughput": 3055.34, "total_tokens": 5181056}
{"current_steps": 1395, "total_steps": 1395, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:28:22", "remaining_time": "0:00:00", "throughput": 3053.89, "total_tokens": 5197824}