halencarjunior's picture
Upload folder using huggingface_hub
ef79a77 verified
{"current_steps": 5, "total_steps": 303, "loss": 1.3604, "lr": 4.997850278334526e-05, "epoch": 0.049689440993788817, "percentage": 1.65, "elapsed_time": "0:00:22", "remaining_time": "0:21:57", "throughput": 1329.14, "total_tokens": 29376}
{"current_steps": 10, "total_steps": 303, "loss": 1.5041, "lr": 4.989123369922547e-05, "epoch": 0.09937888198757763, "percentage": 3.3, "elapsed_time": "0:00:41", "remaining_time": "0:20:08", "throughput": 1313.99, "total_tokens": 54192}
{"current_steps": 15, "total_steps": 303, "loss": 1.4015, "lr": 4.9737083477433165e-05, "epoch": 0.14906832298136646, "percentage": 4.95, "elapsed_time": "0:01:01", "remaining_time": "0:19:38", "throughput": 1321.63, "total_tokens": 81120}
{"current_steps": 20, "total_steps": 303, "loss": 1.3126, "lr": 4.951646630966053e-05, "epoch": 0.19875776397515527, "percentage": 6.6, "elapsed_time": "0:01:22", "remaining_time": "0:19:23", "throughput": 1322.48, "total_tokens": 108736}
{"current_steps": 25, "total_steps": 303, "loss": 1.2784, "lr": 4.922997497999166e-05, "epoch": 0.2484472049689441, "percentage": 8.25, "elapsed_time": "0:01:44", "remaining_time": "0:19:24", "throughput": 1321.12, "total_tokens": 138368}
{"current_steps": 30, "total_steps": 303, "loss": 1.1681, "lr": 4.887837927213005e-05, "epoch": 0.2981366459627329, "percentage": 9.9, "elapsed_time": "0:02:07", "remaining_time": "0:19:17", "throughput": 1326.71, "total_tokens": 168688}
{"current_steps": 35, "total_steps": 303, "loss": 1.1416, "lr": 4.8462623901039485e-05, "epoch": 0.34782608695652173, "percentage": 11.55, "elapsed_time": "0:02:31", "remaining_time": "0:19:17", "throughput": 1332.84, "total_tokens": 201424}
{"current_steps": 40, "total_steps": 303, "loss": 1.2108, "lr": 4.798382597455591e-05, "epoch": 0.39751552795031053, "percentage": 13.2, "elapsed_time": "0:02:51", "remaining_time": "0:18:47", "throughput": 1331.09, "total_tokens": 228336}
{"current_steps": 45, "total_steps": 303, "loss": 1.1843, "lr": 4.744327199179085e-05, "epoch": 0.4472049689440994, "percentage": 14.85, "elapsed_time": "0:03:11", "remaining_time": "0:18:20", "throughput": 1326.38, "total_tokens": 254560}
{"current_steps": 50, "total_steps": 303, "loss": 1.1388, "lr": 4.684241438639132e-05, "epoch": 0.4968944099378882, "percentage": 16.5, "elapsed_time": "0:03:33", "remaining_time": "0:18:01", "throughput": 1327.96, "total_tokens": 283952}
{"current_steps": 55, "total_steps": 303, "loss": 1.1634, "lr": 4.6182867623944436e-05, "epoch": 0.546583850931677, "percentage": 18.15, "elapsed_time": "0:03:57", "remaining_time": "0:17:51", "throughput": 1327.5, "total_tokens": 315600}
{"current_steps": 60, "total_steps": 303, "loss": 1.1558, "lr": 4.5466403864012635e-05, "epoch": 0.5962732919254659, "percentage": 19.8, "elapsed_time": "0:04:18", "remaining_time": "0:17:27", "throughput": 1328.28, "total_tokens": 343568}
{"current_steps": 65, "total_steps": 303, "loss": 1.1439, "lr": 4.4694948198455336e-05, "epoch": 0.6459627329192547, "percentage": 21.45, "elapsed_time": "0:04:40", "remaining_time": "0:17:05", "throughput": 1328.72, "total_tokens": 372272}
{"current_steps": 70, "total_steps": 303, "loss": 1.0852, "lr": 4.387057347883143e-05, "epoch": 0.6956521739130435, "percentage": 23.1, "elapsed_time": "0:05:01", "remaining_time": "0:16:45", "throughput": 1328.51, "total_tokens": 401184}
{"current_steps": 75, "total_steps": 303, "loss": 1.1663, "lr": 4.299549474678101e-05, "epoch": 0.7453416149068323, "percentage": 24.75, "elapsed_time": "0:05:22", "remaining_time": "0:16:21", "throughput": 1328.29, "total_tokens": 428928}
{"current_steps": 80, "total_steps": 303, "loss": 1.1636, "lr": 4.207206328235148e-05, "epoch": 0.7950310559006211, "percentage": 26.4, "elapsed_time": "0:05:43", "remaining_time": "0:15:56", "throughput": 1327.98, "total_tokens": 455776}
{"current_steps": 85, "total_steps": 303, "loss": 1.112, "lr": 4.110276028625995e-05, "epoch": 0.84472049689441, "percentage": 28.05, "elapsed_time": "0:06:03", "remaining_time": "0:15:32", "throughput": 1327.67, "total_tokens": 482736}
{"current_steps": 90, "total_steps": 303, "loss": 1.0987, "lr": 4.0090190213067035e-05, "epoch": 0.8944099378881988, "percentage": 29.7, "elapsed_time": "0:06:25", "remaining_time": "0:15:12", "throughput": 1328.27, "total_tokens": 512192}
{"current_steps": 95, "total_steps": 303, "loss": 1.0928, "lr": 3.9037073773175725e-05, "epoch": 0.9440993788819876, "percentage": 31.35, "elapsed_time": "0:06:47", "remaining_time": "0:14:52", "throughput": 1329.98, "total_tokens": 542384}
{"current_steps": 100, "total_steps": 303, "loss": 1.1012, "lr": 3.7946240622458135e-05, "epoch": 0.9937888198757764, "percentage": 33.0, "elapsed_time": "0:07:09", "remaining_time": "0:14:31", "throughput": 1330.76, "total_tokens": 571008}
{"current_steps": 105, "total_steps": 303, "loss": 1.008, "lr": 3.6820621759152956e-05, "epoch": 1.039751552795031, "percentage": 34.65, "elapsed_time": "0:07:30", "remaining_time": "0:14:10", "throughput": 1329.82, "total_tokens": 599472}
{"current_steps": 110, "total_steps": 303, "loss": 1.0518, "lr": 3.566324164846239e-05, "epoch": 1.0894409937888199, "percentage": 36.3, "elapsed_time": "0:07:48", "remaining_time": "0:13:41", "throughput": 1329.57, "total_tokens": 622832}
{"current_steps": 115, "total_steps": 303, "loss": 1.0862, "lr": 3.447721009600949e-05, "epoch": 1.1391304347826088, "percentage": 37.95, "elapsed_time": "0:08:09", "remaining_time": "0:13:19", "throughput": 1330.55, "total_tokens": 650704}
{"current_steps": 120, "total_steps": 303, "loss": 1.0748, "lr": 3.326571389199124e-05, "epoch": 1.1888198757763975, "percentage": 39.6, "elapsed_time": "0:08:30", "remaining_time": "0:12:58", "throughput": 1331.35, "total_tokens": 679392}
{"current_steps": 125, "total_steps": 303, "loss": 0.9997, "lr": 3.203200824847907e-05, "epoch": 1.2385093167701864, "percentage": 41.25, "elapsed_time": "0:08:52", "remaining_time": "0:12:37", "throughput": 1333.14, "total_tokens": 709424}
{"current_steps": 130, "total_steps": 303, "loss": 1.1077, "lr": 3.077940805287425e-05, "epoch": 1.288198757763975, "percentage": 42.9, "elapsed_time": "0:09:10", "remaining_time": "0:12:11", "throughput": 1332.97, "total_tokens": 733184}
{"current_steps": 135, "total_steps": 303, "loss": 1.0302, "lr": 2.9511278961019407e-05, "epoch": 1.337888198757764, "percentage": 44.55, "elapsed_time": "0:09:31", "remaining_time": "0:11:51", "throughput": 1334.18, "total_tokens": 762624}
{"current_steps": 140, "total_steps": 303, "loss": 0.9886, "lr": 2.8231028353898725e-05, "epoch": 1.387577639751553, "percentage": 46.2, "elapsed_time": "0:09:57", "remaining_time": "0:11:35", "throughput": 1336.8, "total_tokens": 798384}
{"current_steps": 145, "total_steps": 303, "loss": 0.9857, "lr": 2.6942096182225162e-05, "epoch": 1.4372670807453416, "percentage": 47.85, "elapsed_time": "0:10:19", "remaining_time": "0:11:14", "throughput": 1336.96, "total_tokens": 828016}
{"current_steps": 150, "total_steps": 303, "loss": 1.0245, "lr": 2.5647945723515027e-05, "epoch": 1.4869565217391305, "percentage": 49.5, "elapsed_time": "0:10:41", "remaining_time": "0:10:54", "throughput": 1336.6, "total_tokens": 857024}
{"current_steps": 155, "total_steps": 303, "loss": 1.0184, "lr": 2.4352054276484972e-05, "epoch": 1.5366459627329192, "percentage": 51.16, "elapsed_time": "0:11:02", "remaining_time": "0:10:32", "throughput": 1335.18, "total_tokens": 884080}
{"current_steps": 160, "total_steps": 303, "loss": 1.0244, "lr": 2.3057903817774843e-05, "epoch": 1.5863354037267081, "percentage": 52.81, "elapsed_time": "0:11:24", "remaining_time": "0:10:12", "throughput": 1334.26, "total_tokens": 913760}
{"current_steps": 165, "total_steps": 303, "loss": 1.0159, "lr": 2.1768971646101277e-05, "epoch": 1.636024844720497, "percentage": 54.46, "elapsed_time": "0:11:47", "remaining_time": "0:09:51", "throughput": 1333.98, "total_tokens": 943504}
{"current_steps": 170, "total_steps": 303, "loss": 0.9749, "lr": 2.0488721038980595e-05, "epoch": 1.6857142857142857, "percentage": 56.11, "elapsed_time": "0:12:10", "remaining_time": "0:09:31", "throughput": 1334.1, "total_tokens": 974880}
{"current_steps": 175, "total_steps": 303, "loss": 1.0911, "lr": 1.9220591947125766e-05, "epoch": 1.7354037267080744, "percentage": 57.76, "elapsed_time": "0:12:31", "remaining_time": "0:09:09", "throughput": 1334.01, "total_tokens": 1001984}
{"current_steps": 180, "total_steps": 303, "loss": 1.0446, "lr": 1.7967991751520933e-05, "epoch": 1.7850931677018633, "percentage": 59.41, "elapsed_time": "0:12:50", "remaining_time": "0:08:46", "throughput": 1333.73, "total_tokens": 1026992}
{"current_steps": 185, "total_steps": 303, "loss": 1.0175, "lr": 1.6734286108008768e-05, "epoch": 1.8347826086956522, "percentage": 61.06, "elapsed_time": "0:13:10", "remaining_time": "0:08:24", "throughput": 1334.13, "total_tokens": 1054560}
{"current_steps": 190, "total_steps": 303, "loss": 1.044, "lr": 1.552278990399052e-05, "epoch": 1.8844720496894412, "percentage": 62.71, "elapsed_time": "0:13:30", "remaining_time": "0:08:01", "throughput": 1334.31, "total_tokens": 1081312}
{"current_steps": 195, "total_steps": 303, "loss": 1.0445, "lr": 1.4336758351537624e-05, "epoch": 1.9341614906832298, "percentage": 64.36, "elapsed_time": "0:13:50", "remaining_time": "0:07:39", "throughput": 1333.71, "total_tokens": 1107584}
{"current_steps": 200, "total_steps": 303, "loss": 1.0273, "lr": 1.3179378240847057e-05, "epoch": 1.9838509316770185, "percentage": 66.01, "elapsed_time": "0:14:12", "remaining_time": "0:07:18", "throughput": 1334.22, "total_tokens": 1137120}
{"current_steps": 205, "total_steps": 303, "loss": 1.0007, "lr": 1.2053759377541866e-05, "epoch": 2.0298136645962734, "percentage": 67.66, "elapsed_time": "0:14:31", "remaining_time": "0:06:56", "throughput": 1333.05, "total_tokens": 1161824}
{"current_steps": 210, "total_steps": 303, "loss": 1.0029, "lr": 1.096292622682428e-05, "epoch": 2.079503105590062, "percentage": 69.31, "elapsed_time": "0:14:52", "remaining_time": "0:06:35", "throughput": 1333.87, "total_tokens": 1190784}
{"current_steps": 215, "total_steps": 303, "loss": 1.0029, "lr": 9.909809786932967e-06, "epoch": 2.129192546583851, "percentage": 70.96, "elapsed_time": "0:15:12", "remaining_time": "0:06:13", "throughput": 1333.47, "total_tokens": 1216896}
{"current_steps": 220, "total_steps": 303, "loss": 0.9305, "lr": 8.897239713740058e-06, "epoch": 2.1788819875776397, "percentage": 72.61, "elapsed_time": "0:15:35", "remaining_time": "0:05:52", "throughput": 1334.45, "total_tokens": 1248000}
{"current_steps": 225, "total_steps": 303, "loss": 0.9636, "lr": 7.927936717648521e-06, "epoch": 2.2285714285714286, "percentage": 74.26, "elapsed_time": "0:15:56", "remaining_time": "0:05:31", "throughput": 1335.37, "total_tokens": 1276800}
{"current_steps": 230, "total_steps": 303, "loss": 0.9772, "lr": 7.004505253218999e-06, "epoch": 2.2782608695652176, "percentage": 75.91, "elapsed_time": "0:16:16", "remaining_time": "0:05:10", "throughput": 1335.89, "total_tokens": 1304928}
{"current_steps": 235, "total_steps": 303, "loss": 0.8787, "lr": 6.12942652116858e-06, "epoch": 2.327950310559006, "percentage": 77.56, "elapsed_time": "0:16:39", "remaining_time": "0:04:49", "throughput": 1336.63, "total_tokens": 1335984}
{"current_steps": 240, "total_steps": 303, "loss": 0.9571, "lr": 5.305051801544672e-06, "epoch": 2.377639751552795, "percentage": 79.21, "elapsed_time": "0:17:00", "remaining_time": "0:04:27", "throughput": 1337.11, "total_tokens": 1364128}
{"current_steps": 245, "total_steps": 303, "loss": 0.9502, "lr": 4.5335961359873695e-06, "epoch": 2.427329192546584, "percentage": 80.86, "elapsed_time": "0:17:22", "remaining_time": "0:04:06", "throughput": 1338.18, "total_tokens": 1394752}
{"current_steps": 250, "total_steps": 303, "loss": 0.9769, "lr": 3.817132376055565e-06, "epoch": 2.4770186335403728, "percentage": 82.51, "elapsed_time": "0:17:41", "remaining_time": "0:03:44", "throughput": 1338.1, "total_tokens": 1420128}
{"current_steps": 255, "total_steps": 303, "loss": 0.9383, "lr": 3.1575856136086824e-06, "epoch": 2.5267080745341612, "percentage": 84.16, "elapsed_time": "0:18:03", "remaining_time": "0:03:23", "throughput": 1338.81, "total_tokens": 1450496}
{"current_steps": 260, "total_steps": 303, "loss": 1.0071, "lr": 2.5567280082091527e-06, "epoch": 2.57639751552795, "percentage": 85.81, "elapsed_time": "0:18:26", "remaining_time": "0:03:03", "throughput": 1339.69, "total_tokens": 1482384}
{"current_steps": 265, "total_steps": 303, "loss": 0.9361, "lr": 2.0161740254440896e-06, "epoch": 2.626086956521739, "percentage": 87.46, "elapsed_time": "0:18:46", "remaining_time": "0:02:41", "throughput": 1339.74, "total_tokens": 1508944}
{"current_steps": 270, "total_steps": 303, "loss": 1.0098, "lr": 1.5373760989605218e-06, "epoch": 2.675776397515528, "percentage": 89.11, "elapsed_time": "0:19:06", "remaining_time": "0:02:20", "throughput": 1339.75, "total_tokens": 1535488}
{"current_steps": 275, "total_steps": 303, "loss": 1.023, "lr": 1.1216207278699597e-06, "epoch": 2.725465838509317, "percentage": 90.76, "elapsed_time": "0:19:26", "remaining_time": "0:01:58", "throughput": 1340.15, "total_tokens": 1563792}
{"current_steps": 280, "total_steps": 303, "loss": 0.9453, "lr": 7.700250200083469e-07, "epoch": 2.775155279503106, "percentage": 92.41, "elapsed_time": "0:19:47", "remaining_time": "0:01:37", "throughput": 1340.39, "total_tokens": 1591744}
{"current_steps": 285, "total_steps": 303, "loss": 1.0174, "lr": 4.835336903394772e-07, "epoch": 2.8248447204968943, "percentage": 94.06, "elapsed_time": "0:20:08", "remaining_time": "0:01:16", "throughput": 1340.86, "total_tokens": 1620656}
{"current_steps": 290, "total_steps": 303, "loss": 0.9666, "lr": 2.629165225668362e-07, "epoch": 2.874534161490683, "percentage": 95.71, "elapsed_time": "0:20:28", "remaining_time": "0:00:55", "throughput": 1341.01, "total_tokens": 1647808}
{"current_steps": 295, "total_steps": 303, "loss": 0.9679, "lr": 1.0876630077453487e-07, "epoch": 2.924223602484472, "percentage": 97.36, "elapsed_time": "0:20:48", "remaining_time": "0:00:33", "throughput": 1341.15, "total_tokens": 1674512}
{"current_steps": 300, "total_steps": 303, "loss": 0.9439, "lr": 2.149721665473947e-08, "epoch": 2.973913043478261, "percentage": 99.01, "elapsed_time": "0:21:09", "remaining_time": "0:00:12", "throughput": 1341.32, "total_tokens": 1702448}
{"current_steps": 303, "total_steps": 303, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:21:23", "remaining_time": "0:00:00", "throughput": 1340.18, "total_tokens": 1719488}