Training in progress, step 4000
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:bab24cbb9d9eae73b2043d933f52fdf69e9526f9d1c9fdfcaa92bb3dbe1eeb5c
|
| 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:eece067c9959f6276ac74033b3f84d652ff32cfc63aa3f02808846d3de862065
|
| 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:d04b81701e6825dc891ac4786b5da8fb4277a96b8d524a66024edb7973bbcebe
|
| 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 sha256:6578e9d4320da95fcc152a9bd9b052a769558d9c2b86c072ecf659f01a28281c
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -781,3 +781,43 @@
|
|
| 781 |
{"current_steps": 3790, "total_steps": 6713, "loss": 0.2411, "lr": 1.8996734131187867e-05, "epoch": 3.952529994783516, "percentage": 56.46, "elapsed_time": "5:44:25", "remaining_time": "4:25:38"}
|
| 782 |
{"current_steps": 3795, "total_steps": 6713, "loss": 0.2184, "lr": 1.894479854010499e-05, "epoch": 3.9577464788732395, "percentage": 56.53, "elapsed_time": "5:46:04", "remaining_time": "4:26:05"}
|
| 783 |
{"current_steps": 3800, "total_steps": 6713, "loss": 0.2195, "lr": 1.8892870083418272e-05, "epoch": 3.962962962962963, "percentage": 56.61, "elapsed_time": "5:47:44", "remaining_time": "4:26:34"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 781 |
{"current_steps": 3790, "total_steps": 6713, "loss": 0.2411, "lr": 1.8996734131187867e-05, "epoch": 3.952529994783516, "percentage": 56.46, "elapsed_time": "5:44:25", "remaining_time": "4:25:38"}
|
| 782 |
{"current_steps": 3795, "total_steps": 6713, "loss": 0.2184, "lr": 1.894479854010499e-05, "epoch": 3.9577464788732395, "percentage": 56.53, "elapsed_time": "5:46:04", "remaining_time": "4:26:05"}
|
| 783 |
{"current_steps": 3800, "total_steps": 6713, "loss": 0.2195, "lr": 1.8892870083418272e-05, "epoch": 3.962962962962963, "percentage": 56.61, "elapsed_time": "5:47:44", "remaining_time": "4:26:34"}
|
| 784 |
+
{"current_steps": 3805, "total_steps": 6713, "loss": 0.2184, "lr": 1.8840949112224823e-05, "epoch": 3.9681794470526865, "percentage": 56.68, "elapsed_time": "5:50:38", "remaining_time": "4:27:58"}
|
| 785 |
+
{"current_steps": 3810, "total_steps": 6713, "loss": 0.224, "lr": 1.8789035977571145e-05, "epoch": 3.97339593114241, "percentage": 56.76, "elapsed_time": "5:52:18", "remaining_time": "4:28:26"}
|
| 786 |
+
{"current_steps": 3815, "total_steps": 6713, "loss": 0.2349, "lr": 1.873713103045076e-05, "epoch": 3.9786124152321336, "percentage": 56.83, "elapsed_time": "5:53:55", "remaining_time": "4:28:51"}
|
| 787 |
+
{"current_steps": 3820, "total_steps": 6713, "loss": 0.2237, "lr": 1.8685234621801803e-05, "epoch": 3.983828899321857, "percentage": 56.9, "elapsed_time": "5:55:37", "remaining_time": "4:29:19"}
|
| 788 |
+
{"current_steps": 3825, "total_steps": 6713, "loss": 0.2291, "lr": 1.863334710250471e-05, "epoch": 3.9890453834115807, "percentage": 56.98, "elapsed_time": "5:57:16", "remaining_time": "4:29:45"}
|
| 789 |
+
{"current_steps": 3830, "total_steps": 6713, "loss": 0.2274, "lr": 1.858146882337981e-05, "epoch": 3.994261867501304, "percentage": 57.05, "elapsed_time": "5:58:57", "remaining_time": "4:30:11"}
|
| 790 |
+
{"current_steps": 3835, "total_steps": 6713, "loss": 0.2292, "lr": 1.852960013518495e-05, "epoch": 3.9994783515910277, "percentage": 57.13, "elapsed_time": "6:00:43", "remaining_time": "4:30:42"}
|
| 791 |
+
{"current_steps": 3840, "total_steps": 6713, "loss": 0.2012, "lr": 1.8477741388613132e-05, "epoch": 4.005216484089724, "percentage": 57.2, "elapsed_time": "6:03:59", "remaining_time": "4:32:19"}
|
| 792 |
+
{"current_steps": 3845, "total_steps": 6713, "loss": 0.1639, "lr": 1.8425892934290152e-05, "epoch": 4.010432968179447, "percentage": 57.28, "elapsed_time": "6:06:49", "remaining_time": "4:33:37"}
|
| 793 |
+
{"current_steps": 3850, "total_steps": 6713, "loss": 0.1589, "lr": 1.8374055122772195e-05, "epoch": 4.01564945226917, "percentage": 57.35, "elapsed_time": "6:09:45", "remaining_time": "4:34:57"}
|
| 794 |
+
{"current_steps": 3855, "total_steps": 6713, "loss": 0.1563, "lr": 1.8322228304543515e-05, "epoch": 4.020865936358894, "percentage": 57.43, "elapsed_time": "6:12:35", "remaining_time": "4:36:13"}
|
| 795 |
+
{"current_steps": 3860, "total_steps": 6713, "loss": 0.1728, "lr": 1.827041283001403e-05, "epoch": 4.026082420448618, "percentage": 57.5, "elapsed_time": "6:15:31", "remaining_time": "4:37:33"}
|
| 796 |
+
{"current_steps": 3865, "total_steps": 6713, "loss": 0.1673, "lr": 1.8218609049516943e-05, "epoch": 4.031298904538341, "percentage": 57.57, "elapsed_time": "6:18:32", "remaining_time": "4:38:55"}
|
| 797 |
+
{"current_steps": 3870, "total_steps": 6713, "loss": 0.1612, "lr": 1.816681731330641e-05, "epoch": 4.0365153886280645, "percentage": 57.65, "elapsed_time": "6:21:28", "remaining_time": "4:40:14"}
|
| 798 |
+
{"current_steps": 3875, "total_steps": 6713, "loss": 0.1766, "lr": 1.811503797155516e-05, "epoch": 4.041731872717788, "percentage": 57.72, "elapsed_time": "6:24:17", "remaining_time": "4:41:27"}
|
| 799 |
+
{"current_steps": 3880, "total_steps": 6713, "loss": 0.1667, "lr": 1.8063271374352097e-05, "epoch": 4.046948356807512, "percentage": 57.8, "elapsed_time": "6:27:05", "remaining_time": "4:42:38"}
|
| 800 |
+
{"current_steps": 3885, "total_steps": 6713, "loss": 0.16, "lr": 1.8011517871699978e-05, "epoch": 4.052164840897235, "percentage": 57.87, "elapsed_time": "6:30:08", "remaining_time": "4:43:59"}
|
| 801 |
+
{"current_steps": 3890, "total_steps": 6713, "loss": 0.1719, "lr": 1.7959777813513015e-05, "epoch": 4.057381324986959, "percentage": 57.95, "elapsed_time": "6:32:58", "remaining_time": "4:45:10"}
|
| 802 |
+
{"current_steps": 3895, "total_steps": 6713, "loss": 0.1602, "lr": 1.7908051549614527e-05, "epoch": 4.062597809076682, "percentage": 58.02, "elapsed_time": "6:35:48", "remaining_time": "4:46:21"}
|
| 803 |
+
{"current_steps": 3900, "total_steps": 6713, "loss": 0.157, "lr": 1.7856339429734557e-05, "epoch": 4.067814293166406, "percentage": 58.1, "elapsed_time": "6:38:53", "remaining_time": "4:47:42"}
|
| 804 |
+
{"current_steps": 3905, "total_steps": 6713, "loss": 0.1494, "lr": 1.780464180350753e-05, "epoch": 4.073030777256129, "percentage": 58.17, "elapsed_time": "6:41:52", "remaining_time": "4:48:58"}
|
| 805 |
+
{"current_steps": 3910, "total_steps": 6713, "loss": 0.1501, "lr": 1.7752959020469868e-05, "epoch": 4.078247261345853, "percentage": 58.25, "elapsed_time": "6:44:30", "remaining_time": "4:49:58"}
|
| 806 |
+
{"current_steps": 3915, "total_steps": 6713, "loss": 0.1651, "lr": 1.7701291430057653e-05, "epoch": 4.083463745435576, "percentage": 58.32, "elapsed_time": "6:47:27", "remaining_time": "4:51:12"}
|
| 807 |
+
{"current_steps": 3920, "total_steps": 6713, "loss": 0.1586, "lr": 1.7649639381604207e-05, "epoch": 4.0886802295253, "percentage": 58.39, "elapsed_time": "6:50:17", "remaining_time": "4:52:19"}
|
| 808 |
+
{"current_steps": 3925, "total_steps": 6713, "loss": 0.1449, "lr": 1.759800322433781e-05, "epoch": 4.093896713615023, "percentage": 58.47, "elapsed_time": "6:53:20", "remaining_time": "4:53:36"}
|
| 809 |
+
{"current_steps": 3930, "total_steps": 6713, "loss": 0.1477, "lr": 1.7546383307379284e-05, "epoch": 4.099113197704747, "percentage": 58.54, "elapsed_time": "6:56:20", "remaining_time": "4:54:49"}
|
| 810 |
+
{"current_steps": 3935, "total_steps": 6713, "loss": 0.1614, "lr": 1.7494779979739645e-05, "epoch": 4.1043296817944706, "percentage": 58.62, "elapsed_time": "6:59:25", "remaining_time": "4:56:06"}
|
| 811 |
+
{"current_steps": 3940, "total_steps": 6713, "loss": 0.1808, "lr": 1.7443193590317756e-05, "epoch": 4.109546165884194, "percentage": 58.69, "elapsed_time": "7:02:22", "remaining_time": "4:57:15"}
|
| 812 |
+
{"current_steps": 3945, "total_steps": 6713, "loss": 0.1496, "lr": 1.7391624487897947e-05, "epoch": 4.114762649973917, "percentage": 58.77, "elapsed_time": "7:05:14", "remaining_time": "4:58:22"}
|
| 813 |
+
{"current_steps": 3950, "total_steps": 6713, "loss": 0.1585, "lr": 1.734007302114768e-05, "epoch": 4.119979134063641, "percentage": 58.84, "elapsed_time": "7:08:18", "remaining_time": "4:59:35"}
|
| 814 |
+
{"current_steps": 3955, "total_steps": 6713, "loss": 0.1739, "lr": 1.728853953861516e-05, "epoch": 4.125195618153365, "percentage": 58.92, "elapsed_time": "7:11:09", "remaining_time": "5:00:40"}
|
| 815 |
+
{"current_steps": 3960, "total_steps": 6713, "loss": 0.192, "lr": 1.723702438872701e-05, "epoch": 4.130412102243088, "percentage": 58.99, "elapsed_time": "7:14:07", "remaining_time": "5:01:48"}
|
| 816 |
+
{"current_steps": 3965, "total_steps": 6713, "loss": 0.1849, "lr": 1.718552791978591e-05, "epoch": 4.135628586332811, "percentage": 59.06, "elapsed_time": "7:17:08", "remaining_time": "5:02:58"}
|
| 817 |
+
{"current_steps": 3970, "total_steps": 6713, "loss": 0.1619, "lr": 1.713405047996822e-05, "epoch": 4.140845070422535, "percentage": 59.14, "elapsed_time": "7:20:15", "remaining_time": "5:04:11"}
|
| 818 |
+
{"current_steps": 3975, "total_steps": 6713, "loss": 0.1634, "lr": 1.7082592417321647e-05, "epoch": 4.146061554512259, "percentage": 59.21, "elapsed_time": "7:23:19", "remaining_time": "5:05:21"}
|
| 819 |
+
{"current_steps": 3980, "total_steps": 6713, "loss": 0.1647, "lr": 1.7031154079762885e-05, "epoch": 4.1512780386019825, "percentage": 59.29, "elapsed_time": "7:26:19", "remaining_time": "5:06:29"}
|
| 820 |
+
{"current_steps": 3985, "total_steps": 6713, "loss": 0.1675, "lr": 1.6979735815075263e-05, "epoch": 4.156494522691705, "percentage": 59.36, "elapsed_time": "7:29:13", "remaining_time": "5:07:31"}
|
| 821 |
+
{"current_steps": 3990, "total_steps": 6713, "loss": 0.1621, "lr": 1.6928337970906406e-05, "epoch": 4.161711006781429, "percentage": 59.44, "elapsed_time": "7:32:20", "remaining_time": "5:08:42"}
|
| 822 |
+
{"current_steps": 3995, "total_steps": 6713, "loss": 0.1723, "lr": 1.687696089476585e-05, "epoch": 4.166927490871153, "percentage": 59.51, "elapsed_time": "7:35:25", "remaining_time": "5:09:51"}
|
| 823 |
+
{"current_steps": 4000, "total_steps": 6713, "loss": 0.1664, "lr": 1.6825604934022734e-05, "epoch": 4.172143974960877, "percentage": 59.59, "elapsed_time": "7:38:27", "remaining_time": "5:10:56"}
|