Training in progress, epoch 7
Browse files
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44dd32d30fb9e242c7b07e4973eb9cf892a17600a480f91eddc0181514b21452
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fbe94f55281b2dab016c50ef00074ea347dab9c9c5096a9479cae17248a50a6
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0381b08037433b83a034e37e9131e6d99c1d551e098293d3ae58f26fda91d79
|
3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d23010a76788c731be09097eb089ba243399bfbb4875c9c095c1168e3c36452
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -489,3 +489,80 @@
|
|
489 |
{"current_steps": 489, "total_steps": 567, "loss": 0.0016, "lr": 1.132263140799381e-06, "epoch": 6.037037037037037, "percentage": 86.24, "elapsed_time": "3:45:35", "remaining_time": "0:35:59"}
|
490 |
{"current_steps": 490, "total_steps": 567, "loss": 0.0019, "lr": 1.1039598726929046e-06, "epoch": 6.049382716049383, "percentage": 86.42, "elapsed_time": "3:45:59", "remaining_time": "0:35:30"}
|
491 |
{"current_steps": 491, "total_steps": 567, "loss": 0.0019, "lr": 1.0759941675205221e-06, "epoch": 6.061728395061729, "percentage": 86.6, "elapsed_time": "3:46:24", "remaining_time": "0:35:02"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
489 |
{"current_steps": 489, "total_steps": 567, "loss": 0.0016, "lr": 1.132263140799381e-06, "epoch": 6.037037037037037, "percentage": 86.24, "elapsed_time": "3:45:35", "remaining_time": "0:35:59"}
|
490 |
{"current_steps": 490, "total_steps": 567, "loss": 0.0019, "lr": 1.1039598726929046e-06, "epoch": 6.049382716049383, "percentage": 86.42, "elapsed_time": "3:45:59", "remaining_time": "0:35:30"}
|
491 |
{"current_steps": 491, "total_steps": 567, "loss": 0.0019, "lr": 1.0759941675205221e-06, "epoch": 6.061728395061729, "percentage": 86.6, "elapsed_time": "3:46:24", "remaining_time": "0:35:02"}
|
492 |
+
{"current_steps": 492, "total_steps": 567, "loss": 0.0041, "lr": 1.0483670864493777e-06, "epoch": 6.074074074074074, "percentage": 86.77, "elapsed_time": "3:46:55", "remaining_time": "0:34:35"}
|
493 |
+
{"current_steps": 493, "total_steps": 567, "loss": 0.0016, "lr": 1.0210796777974196e-06, "epoch": 6.08641975308642, "percentage": 86.95, "elapsed_time": "3:47:15", "remaining_time": "0:34:06"}
|
494 |
+
{"current_steps": 494, "total_steps": 567, "loss": 0.0015, "lr": 9.94132976993627e-07, "epoch": 6.098765432098766, "percentage": 87.13, "elapsed_time": "3:47:45", "remaining_time": "0:33:39"}
|
495 |
+
{"current_steps": 495, "total_steps": 567, "loss": 0.0026, "lr": 9.675280065387117e-07, "epoch": 6.111111111111111, "percentage": 87.3, "elapsed_time": "3:48:16", "remaining_time": "0:33:12"}
|
496 |
+
{"current_steps": 496, "total_steps": 567, "loss": 0.002, "lr": 9.412657759663279e-07, "epoch": 6.1234567901234565, "percentage": 87.48, "elapsed_time": "3:48:44", "remaining_time": "0:32:44"}
|
497 |
+
{"current_steps": 497, "total_steps": 567, "loss": 0.001, "lr": 9.153472818047627e-07, "epoch": 6.135802469135802, "percentage": 87.65, "elapsed_time": "3:49:07", "remaining_time": "0:32:16"}
|
498 |
+
{"current_steps": 498, "total_steps": 567, "loss": 0.0019, "lr": 8.897735075391156e-07, "epoch": 6.148148148148148, "percentage": 87.83, "elapsed_time": "3:49:36", "remaining_time": "0:31:48"}
|
499 |
+
{"current_steps": 499, "total_steps": 567, "loss": 0.001, "lr": 8.645454235739903e-07, "epoch": 6.160493827160494, "percentage": 88.01, "elapsed_time": "3:50:06", "remaining_time": "0:31:21"}
|
500 |
+
{"current_steps": 500, "total_steps": 567, "loss": 0.0036, "lr": 8.39663987196665e-07, "epoch": 6.172839506172839, "percentage": 88.18, "elapsed_time": "3:50:33", "remaining_time": "0:30:53"}
|
501 |
+
{"current_steps": 501, "total_steps": 567, "loss": 0.0052, "lr": 8.151301425407699e-07, "epoch": 6.185185185185185, "percentage": 88.36, "elapsed_time": "3:50:59", "remaining_time": "0:30:25"}
|
502 |
+
{"current_steps": 502, "total_steps": 567, "loss": 0.0017, "lr": 7.909448205504633e-07, "epoch": 6.197530864197531, "percentage": 88.54, "elapsed_time": "3:51:25", "remaining_time": "0:29:57"}
|
503 |
+
{"current_steps": 503, "total_steps": 567, "loss": 0.0014, "lr": 7.671089389451059e-07, "epoch": 6.209876543209877, "percentage": 88.71, "elapsed_time": "3:51:49", "remaining_time": "0:29:29"}
|
504 |
+
{"current_steps": 504, "total_steps": 567, "loss": 0.0046, "lr": 7.43623402184438e-07, "epoch": 6.222222222222222, "percentage": 88.89, "elapsed_time": "3:52:13", "remaining_time": "0:29:01"}
|
505 |
+
{"current_steps": 505, "total_steps": 567, "loss": 0.0015, "lr": 7.204891014342552e-07, "epoch": 6.234567901234568, "percentage": 89.07, "elapsed_time": "3:52:40", "remaining_time": "0:28:34"}
|
506 |
+
{"current_steps": 506, "total_steps": 567, "loss": 0.0019, "lr": 6.977069145325987e-07, "epoch": 6.246913580246914, "percentage": 89.24, "elapsed_time": "3:53:07", "remaining_time": "0:28:06"}
|
507 |
+
{"current_steps": 507, "total_steps": 567, "loss": 0.0012, "lr": 6.752777059564431e-07, "epoch": 6.2592592592592595, "percentage": 89.42, "elapsed_time": "3:53:30", "remaining_time": "0:27:38"}
|
508 |
+
{"current_steps": 508, "total_steps": 567, "loss": 0.0009, "lr": 6.532023267888954e-07, "epoch": 6.271604938271605, "percentage": 89.59, "elapsed_time": "3:53:52", "remaining_time": "0:27:09"}
|
509 |
+
{"current_steps": 509, "total_steps": 567, "loss": 0.0017, "lr": 6.314816146868951e-07, "epoch": 6.283950617283951, "percentage": 89.77, "elapsed_time": "3:54:23", "remaining_time": "0:26:42"}
|
510 |
+
{"current_steps": 510, "total_steps": 567, "loss": 0.0035, "lr": 6.101163938494359e-07, "epoch": 6.296296296296296, "percentage": 89.95, "elapsed_time": "3:54:49", "remaining_time": "0:26:14"}
|
511 |
+
{"current_steps": 511, "total_steps": 567, "loss": 0.0012, "lr": 5.891074749862857e-07, "epoch": 6.308641975308642, "percentage": 90.12, "elapsed_time": "3:55:15", "remaining_time": "0:25:46"}
|
512 |
+
{"current_steps": 512, "total_steps": 567, "loss": 0.0033, "lr": 5.684556552872256e-07, "epoch": 6.320987654320987, "percentage": 90.3, "elapsed_time": "3:55:41", "remaining_time": "0:25:19"}
|
513 |
+
{"current_steps": 513, "total_steps": 567, "loss": 0.0014, "lr": 5.481617183918053e-07, "epoch": 6.333333333333333, "percentage": 90.48, "elapsed_time": "3:56:08", "remaining_time": "0:24:51"}
|
514 |
+
{"current_steps": 514, "total_steps": 567, "loss": 0.0013, "lr": 5.282264343595977e-07, "epoch": 6.345679012345679, "percentage": 90.65, "elapsed_time": "3:56:34", "remaining_time": "0:24:23"}
|
515 |
+
{"current_steps": 515, "total_steps": 567, "loss": 0.0012, "lr": 5.086505596409885e-07, "epoch": 6.3580246913580245, "percentage": 90.83, "elapsed_time": "3:57:01", "remaining_time": "0:23:55"}
|
516 |
+
{"current_steps": 516, "total_steps": 567, "loss": 0.0019, "lr": 4.894348370484648e-07, "epoch": 6.37037037037037, "percentage": 91.01, "elapsed_time": "3:57:30", "remaining_time": "0:23:28"}
|
517 |
+
{"current_steps": 517, "total_steps": 567, "loss": 0.0015, "lr": 4.7057999572843516e-07, "epoch": 6.382716049382716, "percentage": 91.18, "elapsed_time": "3:57:59", "remaining_time": "0:23:01"}
|
518 |
+
{"current_steps": 518, "total_steps": 567, "loss": 0.0053, "lr": 4.520867511335569e-07, "epoch": 6.395061728395062, "percentage": 91.36, "elapsed_time": "3:58:25", "remaining_time": "0:22:33"}
|
519 |
+
{"current_steps": 519, "total_steps": 567, "loss": 0.0016, "lr": 4.3395580499559276e-07, "epoch": 6.407407407407407, "percentage": 91.53, "elapsed_time": "3:58:50", "remaining_time": "0:22:05"}
|
520 |
+
{"current_steps": 520, "total_steps": 567, "loss": 0.0014, "lr": 4.161878452987778e-07, "epoch": 6.419753086419753, "percentage": 91.71, "elapsed_time": "3:59:15", "remaining_time": "0:21:37"}
|
521 |
+
{"current_steps": 521, "total_steps": 567, "loss": 0.001, "lr": 3.9878354625371927e-07, "epoch": 6.432098765432099, "percentage": 91.89, "elapsed_time": "3:59:45", "remaining_time": "0:21:10"}
|
522 |
+
{"current_steps": 522, "total_steps": 567, "loss": 0.0016, "lr": 3.817435682718096e-07, "epoch": 6.444444444444445, "percentage": 92.06, "elapsed_time": "4:00:10", "remaining_time": "0:20:42"}
|
523 |
+
{"current_steps": 523, "total_steps": 567, "loss": 0.0014, "lr": 3.650685579401692e-07, "epoch": 6.45679012345679, "percentage": 92.24, "elapsed_time": "4:00:39", "remaining_time": "0:20:14"}
|
524 |
+
{"current_steps": 524, "total_steps": 567, "loss": 0.0037, "lr": 3.4875914799710975e-07, "epoch": 6.469135802469136, "percentage": 92.42, "elapsed_time": "4:01:08", "remaining_time": "0:19:47"}
|
525 |
+
{"current_steps": 525, "total_steps": 567, "loss": 0.0025, "lr": 3.328159573081258e-07, "epoch": 6.481481481481482, "percentage": 92.59, "elapsed_time": "4:01:34", "remaining_time": "0:19:19"}
|
526 |
+
{"current_steps": 526, "total_steps": 567, "loss": 0.0013, "lr": 3.1723959084241195e-07, "epoch": 6.493827160493828, "percentage": 92.77, "elapsed_time": "4:02:02", "remaining_time": "0:18:52"}
|
527 |
+
{"current_steps": 527, "total_steps": 567, "loss": 0.0018, "lr": 3.020306396499062e-07, "epoch": 6.506172839506172, "percentage": 92.95, "elapsed_time": "4:02:33", "remaining_time": "0:18:24"}
|
528 |
+
{"current_steps": 528, "total_steps": 567, "loss": 0.0015, "lr": 2.871896808388608e-07, "epoch": 6.518518518518518, "percentage": 93.12, "elapsed_time": "4:02:56", "remaining_time": "0:17:56"}
|
529 |
+
{"current_steps": 529, "total_steps": 567, "loss": 0.0015, "lr": 2.727172775539522e-07, "epoch": 6.530864197530864, "percentage": 93.3, "elapsed_time": "4:03:20", "remaining_time": "0:17:28"}
|
530 |
+
{"current_steps": 530, "total_steps": 567, "loss": 0.0054, "lr": 2.5861397895489914e-07, "epoch": 6.54320987654321, "percentage": 93.47, "elapsed_time": "4:03:42", "remaining_time": "0:17:00"}
|
531 |
+
{"current_steps": 531, "total_steps": 567, "loss": 0.0014, "lr": 2.44880320195634e-07, "epoch": 6.555555555555555, "percentage": 93.65, "elapsed_time": "4:04:09", "remaining_time": "0:16:33"}
|
532 |
+
{"current_steps": 532, "total_steps": 567, "loss": 0.0011, "lr": 2.315168224039932e-07, "epoch": 6.567901234567901, "percentage": 93.83, "elapsed_time": "4:04:39", "remaining_time": "0:16:05"}
|
533 |
+
{"current_steps": 533, "total_steps": 567, "loss": 0.002, "lr": 2.1852399266194312e-07, "epoch": 6.580246913580247, "percentage": 94.0, "elapsed_time": "4:05:07", "remaining_time": "0:15:38"}
|
534 |
+
{"current_steps": 534, "total_steps": 567, "loss": 0.0035, "lr": 2.0590232398634114e-07, "epoch": 6.592592592592593, "percentage": 94.18, "elapsed_time": "4:05:32", "remaining_time": "0:15:10"}
|
535 |
+
{"current_steps": 535, "total_steps": 567, "loss": 0.0009, "lr": 1.9365229531022267e-07, "epoch": 6.604938271604938, "percentage": 94.36, "elapsed_time": "4:05:59", "remaining_time": "0:14:42"}
|
536 |
+
{"current_steps": 536, "total_steps": 567, "loss": 0.0012, "lr": 1.817743714646314e-07, "epoch": 6.617283950617284, "percentage": 94.53, "elapsed_time": "4:06:21", "remaining_time": "0:14:14"}
|
537 |
+
{"current_steps": 537, "total_steps": 567, "loss": 0.0012, "lr": 1.7026900316098217e-07, "epoch": 6.62962962962963, "percentage": 94.71, "elapsed_time": "4:06:50", "remaining_time": "0:13:47"}
|
538 |
+
{"current_steps": 538, "total_steps": 567, "loss": 0.0011, "lr": 1.5913662697395583e-07, "epoch": 6.6419753086419755, "percentage": 94.89, "elapsed_time": "4:07:20", "remaining_time": "0:13:19"}
|
539 |
+
{"current_steps": 539, "total_steps": 567, "loss": 0.0015, "lr": 1.4837766532493469e-07, "epoch": 6.654320987654321, "percentage": 95.06, "elapsed_time": "4:07:42", "remaining_time": "0:12:52"}
|
540 |
+
{"current_steps": 540, "total_steps": 567, "loss": 0.0013, "lr": 1.3799252646597428e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "4:08:11", "remaining_time": "0:12:24"}
|
541 |
+
{"current_steps": 541, "total_steps": 567, "loss": 0.001, "lr": 1.2798160446431006e-07, "epoch": 6.679012345679013, "percentage": 95.41, "elapsed_time": "4:08:35", "remaining_time": "0:11:56"}
|
542 |
+
{"current_steps": 542, "total_steps": 567, "loss": 0.0024, "lr": 1.1834527918740624e-07, "epoch": 6.6913580246913575, "percentage": 95.59, "elapsed_time": "4:08:58", "remaining_time": "0:11:29"}
|
543 |
+
{"current_steps": 543, "total_steps": 567, "loss": 0.002, "lr": 1.0908391628854042e-07, "epoch": 6.703703703703704, "percentage": 95.77, "elapsed_time": "4:09:21", "remaining_time": "0:11:01"}
|
544 |
+
{"current_steps": 544, "total_steps": 567, "loss": 0.0012, "lr": 1.0019786719293046e-07, "epoch": 6.716049382716049, "percentage": 95.94, "elapsed_time": "4:09:48", "remaining_time": "0:10:33"}
|
545 |
+
{"current_steps": 545, "total_steps": 567, "loss": 0.0013, "lr": 9.168746908439718e-08, "epoch": 6.728395061728395, "percentage": 96.12, "elapsed_time": "4:10:15", "remaining_time": "0:10:06"}
|
546 |
+
{"current_steps": 546, "total_steps": 567, "loss": 0.0011, "lr": 8.355304489257254e-08, "epoch": 6.7407407407407405, "percentage": 96.3, "elapsed_time": "4:10:36", "remaining_time": "0:09:38"}
|
547 |
+
{"current_steps": 547, "total_steps": 567, "loss": 0.0013, "lr": 7.579490328064265e-08, "epoch": 6.753086419753086, "percentage": 96.47, "elapsed_time": "4:11:02", "remaining_time": "0:09:10"}
|
548 |
+
{"current_steps": 548, "total_steps": 567, "loss": 0.0013, "lr": 6.841333863363831e-08, "epoch": 6.765432098765432, "percentage": 96.65, "elapsed_time": "4:11:27", "remaining_time": "0:08:43"}
|
549 |
+
{"current_steps": 549, "total_steps": 567, "loss": 0.0008, "lr": 6.140863104726391e-08, "epoch": 6.777777777777778, "percentage": 96.83, "elapsed_time": "4:11:58", "remaining_time": "0:08:15"}
|
550 |
+
{"current_steps": 550, "total_steps": 567, "loss": 0.0074, "lr": 5.4781046317267103e-08, "epoch": 6.790123456790123, "percentage": 97.0, "elapsed_time": "4:12:24", "remaining_time": "0:07:48"}
|
551 |
+
{"current_steps": 551, "total_steps": 567, "loss": 0.0034, "lr": 4.85308359293557e-08, "epoch": 6.802469135802469, "percentage": 97.18, "elapsed_time": "4:12:50", "remaining_time": "0:07:20"}
|
552 |
+
{"current_steps": 552, "total_steps": 567, "loss": 0.0011, "lr": 4.2658237049655325e-08, "epoch": 6.814814814814815, "percentage": 97.35, "elapsed_time": "4:13:18", "remaining_time": "0:06:53"}
|
553 |
+
{"current_steps": 553, "total_steps": 567, "loss": 0.0011, "lr": 3.716347251570551e-08, "epoch": 6.827160493827161, "percentage": 97.53, "elapsed_time": "4:13:43", "remaining_time": "0:06:25"}
|
554 |
+
{"current_steps": 554, "total_steps": 567, "loss": 0.0014, "lr": 3.204675082800979e-08, "epoch": 6.839506172839506, "percentage": 97.71, "elapsed_time": "4:14:11", "remaining_time": "0:05:57"}
|
555 |
+
{"current_steps": 555, "total_steps": 567, "loss": 0.0012, "lr": 2.7308266142119788e-08, "epoch": 6.851851851851852, "percentage": 97.88, "elapsed_time": "4:14:38", "remaining_time": "0:05:30"}
|
556 |
+
{"current_steps": 556, "total_steps": 567, "loss": 0.002, "lr": 2.294819826127115e-08, "epoch": 6.864197530864198, "percentage": 98.06, "elapsed_time": "4:15:05", "remaining_time": "0:05:02"}
|
557 |
+
{"current_steps": 557, "total_steps": 567, "loss": 0.002, "lr": 1.896671262955896e-08, "epoch": 6.8765432098765435, "percentage": 98.24, "elapsed_time": "4:15:32", "remaining_time": "0:04:35"}
|
558 |
+
{"current_steps": 558, "total_steps": 567, "loss": 0.0023, "lr": 1.5363960325660565e-08, "epoch": 6.888888888888889, "percentage": 98.41, "elapsed_time": "4:16:03", "remaining_time": "0:04:07"}
|
559 |
+
{"current_steps": 559, "total_steps": 567, "loss": 0.0016, "lr": 1.2140078057101269e-08, "epoch": 6.901234567901234, "percentage": 98.59, "elapsed_time": "4:16:29", "remaining_time": "0:03:40"}
|
560 |
+
{"current_steps": 560, "total_steps": 567, "loss": 0.0021, "lr": 9.29518815506847e-09, "epoch": 6.91358024691358, "percentage": 98.77, "elapsed_time": "4:16:54", "remaining_time": "0:03:12"}
|
561 |
+
{"current_steps": 561, "total_steps": 567, "loss": 0.0021, "lr": 6.82939856977094e-09, "epoch": 6.925925925925926, "percentage": 98.94, "elapsed_time": "4:17:27", "remaining_time": "0:02:45"}
|
562 |
+
{"current_steps": 562, "total_steps": 567, "loss": 0.0014, "lr": 4.74280286634099e-09, "epoch": 6.938271604938271, "percentage": 99.12, "elapsed_time": "4:17:58", "remaining_time": "0:02:17"}
|
563 |
+
{"current_steps": 563, "total_steps": 567, "loss": 0.0044, "lr": 3.0354802212839705e-09, "epoch": 6.950617283950617, "percentage": 99.29, "elapsed_time": "4:18:21", "remaining_time": "0:01:50"}
|
564 |
+
{"current_steps": 564, "total_steps": 567, "loss": 0.0012, "lr": 1.7074954194729044e-09, "epoch": 6.962962962962963, "percentage": 99.47, "elapsed_time": "4:18:47", "remaining_time": "0:01:22"}
|
565 |
+
{"current_steps": 565, "total_steps": 567, "loss": 0.0021, "lr": 7.588988516937789e-10, "epoch": 6.9753086419753085, "percentage": 99.65, "elapsed_time": "4:19:15", "remaining_time": "0:00:55"}
|
566 |
+
{"current_steps": 566, "total_steps": 567, "loss": 0.0029, "lr": 1.897265127315251e-10, "epoch": 6.987654320987654, "percentage": 99.82, "elapsed_time": "4:19:44", "remaining_time": "0:00:27"}
|
567 |
+
{"current_steps": 567, "total_steps": 567, "loss": 0.0019, "lr": 0.0, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "4:20:15", "remaining_time": "0:00:00"}
|
568 |
+
{"current_steps": 567, "total_steps": 567, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "4:21:49", "remaining_time": "0:00:00"}
|