Training in progress, step 3600
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 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e53324ff4b9cee02f8f7fcbf303cf9ca8c2a3bdc0b6a8094b0bbdee9f07531c
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e38c6788cbf2857402dbfb3fb162f477175fcef516aac728cc72fd0905c64b90
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e0d3967dad5caddb3b52db88f2576d86d9766497b1dad101591eed11327989b
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2498065ad7f8ec19796750c43c85b26ff3154a6fcdbeec1edb5f08a128acf37
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -679,3 +679,43 @@
|
|
| 679 |
{"current_steps": 3395, "total_steps": 3850, "loss": 0.1896, "lr": 1.6851085711866598e-06, "epoch": 6.172884440400364, "percentage": 88.18, "elapsed_time": "22:43:16", "remaining_time": "3:02:42"}
|
| 680 |
{"current_steps": 3400, "total_steps": 3850, "loss": 0.179, "lr": 1.648870647345322e-06, "epoch": 6.1819836214740675, "percentage": 88.31, "elapsed_time": "22:45:07", "remaining_time": "3:00:40"}
|
| 681 |
{"current_steps": 3405, "total_steps": 3850, "loss": 0.1759, "lr": 1.6130098571926468e-06, "epoch": 6.191082802547771, "percentage": 88.44, "elapsed_time": "22:48:08", "remaining_time": "2:58:48"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 679 |
{"current_steps": 3395, "total_steps": 3850, "loss": 0.1896, "lr": 1.6851085711866598e-06, "epoch": 6.172884440400364, "percentage": 88.18, "elapsed_time": "22:43:16", "remaining_time": "3:02:42"}
|
| 680 |
{"current_steps": 3400, "total_steps": 3850, "loss": 0.179, "lr": 1.648870647345322e-06, "epoch": 6.1819836214740675, "percentage": 88.31, "elapsed_time": "22:45:07", "remaining_time": "3:00:40"}
|
| 681 |
{"current_steps": 3405, "total_steps": 3850, "loss": 0.1759, "lr": 1.6130098571926468e-06, "epoch": 6.191082802547771, "percentage": 88.44, "elapsed_time": "22:48:08", "remaining_time": "2:58:48"}
|
| 682 |
+
{"current_steps": 3410, "total_steps": 3850, "loss": 0.1728, "lr": 1.577526937703e-06, "epoch": 6.200181983621474, "percentage": 88.57, "elapsed_time": "22:50:17", "remaining_time": "2:56:48"}
|
| 683 |
+
{"current_steps": 3415, "total_steps": 3850, "loss": 0.1849, "lr": 1.5424226180851443e-06, "epoch": 6.209281164695177, "percentage": 88.7, "elapsed_time": "22:52:14", "remaining_time": "2:54:47"}
|
| 684 |
+
{"current_steps": 3420, "total_steps": 3850, "loss": 0.1857, "lr": 1.5076976197672432e-06, "epoch": 6.218380345768881, "percentage": 88.83, "elapsed_time": "22:54:06", "remaining_time": "2:52:46"}
|
| 685 |
+
{"current_steps": 3425, "total_steps": 3850, "loss": 0.1796, "lr": 1.473352656382039e-06, "epoch": 6.227479526842584, "percentage": 88.96, "elapsed_time": "22:56:17", "remaining_time": "2:50:46"}
|
| 686 |
+
{"current_steps": 3430, "total_steps": 3850, "loss": 0.1831, "lr": 1.439388433752178e-06, "epoch": 6.236578707916287, "percentage": 89.09, "elapsed_time": "22:58:12", "remaining_time": "2:48:45"}
|
| 687 |
+
{"current_steps": 3435, "total_steps": 3850, "loss": 0.1891, "lr": 1.4058056498757112e-06, "epoch": 6.245677888989991, "percentage": 89.22, "elapsed_time": "23:00:01", "remaining_time": "2:46:43"}
|
| 688 |
+
{"current_steps": 3440, "total_steps": 3850, "loss": 0.1905, "lr": 1.372604994911757e-06, "epoch": 6.254777070063694, "percentage": 89.35, "elapsed_time": "23:02:14", "remaining_time": "2:44:44"}
|
| 689 |
+
{"current_steps": 3445, "total_steps": 3850, "loss": 0.1815, "lr": 1.3397871511662986e-06, "epoch": 6.263876251137398, "percentage": 89.48, "elapsed_time": "23:04:11", "remaining_time": "2:42:43"}
|
| 690 |
+
{"current_steps": 3450, "total_steps": 3850, "loss": 0.1896, "lr": 1.307352793078187e-06, "epoch": 6.272975432211101, "percentage": 89.61, "elapsed_time": "23:06:12", "remaining_time": "2:40:43"}
|
| 691 |
+
{"current_steps": 3455, "total_steps": 3850, "loss": 0.1945, "lr": 1.275302587205256e-06, "epoch": 6.282074613284804, "percentage": 89.74, "elapsed_time": "23:07:53", "remaining_time": "2:38:40"}
|
| 692 |
+
{"current_steps": 3460, "total_steps": 3850, "loss": 0.1843, "lr": 1.2436371922106404e-06, "epoch": 6.2911737943585075, "percentage": 89.87, "elapsed_time": "23:09:57", "remaining_time": "2:36:40"}
|
| 693 |
+
{"current_steps": 3465, "total_steps": 3850, "loss": 0.1759, "lr": 1.2123572588492306e-06, "epoch": 6.300272975432211, "percentage": 90.0, "elapsed_time": "23:11:58", "remaining_time": "2:34:39"}
|
| 694 |
+
{"current_steps": 3470, "total_steps": 3850, "loss": 0.1835, "lr": 1.1814634299543103e-06, "epoch": 6.309372156505915, "percentage": 90.13, "elapsed_time": "23:14:00", "remaining_time": "2:32:39"}
|
| 695 |
+
{"current_steps": 3475, "total_steps": 3850, "loss": 0.1871, "lr": 1.1509563404243274e-06, "epoch": 6.318471337579618, "percentage": 90.26, "elapsed_time": "23:15:53", "remaining_time": "2:30:38"}
|
| 696 |
+
{"current_steps": 3480, "total_steps": 3850, "loss": 0.1752, "lr": 1.1208366172098684e-06, "epoch": 6.327570518653321, "percentage": 90.39, "elapsed_time": "23:17:57", "remaining_time": "2:28:37"}
|
| 697 |
+
{"current_steps": 3485, "total_steps": 3850, "loss": 0.1813, "lr": 1.0911048793007484e-06, "epoch": 6.336669699727024, "percentage": 90.52, "elapsed_time": "23:20:00", "remaining_time": "2:26:37"}
|
| 698 |
+
{"current_steps": 3490, "total_steps": 3850, "loss": 0.1868, "lr": 1.0617617377133205e-06, "epoch": 6.345768880800728, "percentage": 90.65, "elapsed_time": "23:22:05", "remaining_time": "2:24:37"}
|
| 699 |
+
{"current_steps": 3495, "total_steps": 3850, "loss": 0.182, "lr": 1.0328077954778904e-06, "epoch": 6.3548680618744315, "percentage": 90.78, "elapsed_time": "23:24:01", "remaining_time": "2:22:36"}
|
| 700 |
+
{"current_steps": 3500, "total_steps": 3850, "loss": 0.1784, "lr": 1.004243647626344e-06, "epoch": 6.363967242948135, "percentage": 90.91, "elapsed_time": "23:25:59", "remaining_time": "2:20:35"}
|
| 701 |
+
{"current_steps": 3505, "total_steps": 3850, "loss": 0.1872, "lr": 9.760698811799064e-07, "epoch": 6.373066424021838, "percentage": 91.04, "elapsed_time": "23:28:02", "remaining_time": "2:18:35"}
|
| 702 |
+
{"current_steps": 3510, "total_steps": 3850, "loss": 0.1805, "lr": 9.482870751370755e-07, "epoch": 6.382165605095541, "percentage": 91.17, "elapsed_time": "23:30:02", "remaining_time": "2:16:35"}
|
| 703 |
+
{"current_steps": 3515, "total_steps": 3850, "loss": 0.1942, "lr": 9.208958004617475e-07, "epoch": 6.391264786169245, "percentage": 91.3, "elapsed_time": "23:31:45", "remaining_time": "2:14:32"}
|
| 704 |
+
{"current_steps": 3520, "total_steps": 3850, "loss": 0.1768, "lr": 8.938966200714482e-07, "epoch": 6.400363967242948, "percentage": 91.43, "elapsed_time": "23:33:49", "remaining_time": "2:12:32"}
|
| 705 |
+
{"current_steps": 3525, "total_steps": 3850, "loss": 0.1808, "lr": 8.672900888257918e-07, "epoch": 6.409463148316651, "percentage": 91.56, "elapsed_time": "23:35:41", "remaining_time": "2:10:31"}
|
| 706 |
+
{"current_steps": 3530, "total_steps": 3850, "loss": 0.1723, "lr": 8.410767535150599e-07, "epoch": 6.418562329390355, "percentage": 91.69, "elapsed_time": "23:37:52", "remaining_time": "2:08:31"}
|
| 707 |
+
{"current_steps": 3535, "total_steps": 3850, "loss": 0.1863, "lr": 8.152571528489828e-07, "epoch": 6.427661510464058, "percentage": 91.82, "elapsed_time": "23:39:48", "remaining_time": "2:06:31"}
|
| 708 |
+
{"current_steps": 3540, "total_steps": 3850, "loss": 0.1864, "lr": 7.898318174456498e-07, "epoch": 6.436760691537762, "percentage": 91.95, "elapsed_time": "23:41:42", "remaining_time": "2:04:30"}
|
| 709 |
+
{"current_steps": 3545, "total_steps": 3850, "loss": 0.1898, "lr": 7.64801269820612e-07, "epoch": 6.445859872611465, "percentage": 92.08, "elapsed_time": "23:43:31", "remaining_time": "2:02:28"}
|
| 710 |
+
{"current_steps": 3550, "total_steps": 3850, "loss": 0.1771, "lr": 7.401660243761543e-07, "epoch": 6.454959053685168, "percentage": 92.21, "elapsed_time": "23:45:51", "remaining_time": "2:00:29"}
|
| 711 |
+
{"current_steps": 3555, "total_steps": 3850, "loss": 0.193, "lr": 7.159265873907006e-07, "epoch": 6.4640582347588715, "percentage": 92.34, "elapsed_time": "23:47:52", "remaining_time": "1:58:29"}
|
| 712 |
+
{"current_steps": 3560, "total_steps": 3850, "loss": 0.1904, "lr": 6.920834570084389e-07, "epoch": 6.473157415832575, "percentage": 92.47, "elapsed_time": "23:50:06", "remaining_time": "1:56:29"}
|
| 713 |
+
{"current_steps": 3565, "total_steps": 3850, "loss": 0.1982, "lr": 6.686371232290567e-07, "epoch": 6.482256596906279, "percentage": 92.6, "elapsed_time": "23:52:09", "remaining_time": "1:54:29"}
|
| 714 |
+
{"current_steps": 3570, "total_steps": 3850, "loss": 0.1829, "lr": 6.455880678976845e-07, "epoch": 6.491355777979982, "percentage": 92.73, "elapsed_time": "23:53:51", "remaining_time": "1:52:27"}
|
| 715 |
+
{"current_steps": 3575, "total_steps": 3850, "loss": 0.1711, "lr": 6.229367646949924e-07, "epoch": 6.500454959053685, "percentage": 92.86, "elapsed_time": "23:56:01", "remaining_time": "1:50:27"}
|
| 716 |
+
{"current_steps": 3580, "total_steps": 3850, "loss": 0.1795, "lr": 6.006836791274606e-07, "epoch": 6.509554140127388, "percentage": 92.99, "elapsed_time": "23:57:58", "remaining_time": "1:48:27"}
|
| 717 |
+
{"current_steps": 3585, "total_steps": 3850, "loss": 0.1904, "lr": 5.788292685177954e-07, "epoch": 6.518653321201092, "percentage": 93.12, "elapsed_time": "23:59:50", "remaining_time": "1:46:25"}
|
| 718 |
+
{"current_steps": 3590, "total_steps": 3850, "loss": 0.1727, "lr": 5.573739819955459e-07, "epoch": 6.5277525022747955, "percentage": 93.25, "elapsed_time": "1 day, 0:01:45", "remaining_time": "1:44:25"}
|
| 719 |
+
{"current_steps": 3595, "total_steps": 3850, "loss": 0.1855, "lr": 5.363182604878803e-07, "epoch": 6.536851683348498, "percentage": 93.38, "elapsed_time": "1 day, 0:03:45", "remaining_time": "1:42:24"}
|
| 720 |
+
{"current_steps": 3600, "total_steps": 3850, "loss": 0.1914, "lr": 5.156625367104973e-07, "epoch": 6.545950864422202, "percentage": 93.51, "elapsed_time": "1 day, 0:05:51", "remaining_time": "1:40:24"}
|
| 721 |
+
{"current_steps": 3605, "total_steps": 3850, "loss": 0.1788, "lr": 4.954072351587646e-07, "epoch": 6.555050045495905, "percentage": 93.64, "elapsed_time": "1 day, 0:09:10", "remaining_time": "1:38:29"}
|