Training in progress, step 4600
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:fd35ed7a08c4ac5684fe35fa888fef480ed5a304be0aa449ff5243d7cf1e552a
|
| 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:ff26eb49980efe71ba0fa836bbf7d65212f5da40760c07ebcd44efe30b4290d2
|
| 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:ab3518a489ed1c8c9a661fa548187c488724dd12c8026040f41f8f3e0a2e6021
|
| 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 sha256:162a307cb2095e3e71fc8e111036033fefcaa8b78104c311412d5a37f81317f2
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -883,3 +883,43 @@
|
|
| 883 |
{"current_steps": 4390, "total_steps": 6188, "loss": 0.1447, "lr": 9.445130936146098e-06, "epoch": 4.967741935483871, "percentage": 70.94, "elapsed_time": "9:51:13", "remaining_time": "4:02:08"}
|
| 884 |
{"current_steps": 4395, "total_steps": 6188, "loss": 0.1471, "lr": 9.397256290058869e-06, "epoch": 4.973401245048104, "percentage": 71.02, "elapsed_time": "9:54:16", "remaining_time": "4:02:26"}
|
| 885 |
{"current_steps": 4400, "total_steps": 6188, "loss": 0.1572, "lr": 9.349465997507974e-06, "epoch": 4.979060554612337, "percentage": 71.11, "elapsed_time": "9:57:18", "remaining_time": "4:02:43"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 883 |
{"current_steps": 4390, "total_steps": 6188, "loss": 0.1447, "lr": 9.445130936146098e-06, "epoch": 4.967741935483871, "percentage": 70.94, "elapsed_time": "9:51:13", "remaining_time": "4:02:08"}
|
| 884 |
{"current_steps": 4395, "total_steps": 6188, "loss": 0.1471, "lr": 9.397256290058869e-06, "epoch": 4.973401245048104, "percentage": 71.02, "elapsed_time": "9:54:16", "remaining_time": "4:02:26"}
|
| 885 |
{"current_steps": 4400, "total_steps": 6188, "loss": 0.1572, "lr": 9.349465997507974e-06, "epoch": 4.979060554612337, "percentage": 71.11, "elapsed_time": "9:57:18", "remaining_time": "4:02:43"}
|
| 886 |
+
{"current_steps": 4405, "total_steps": 6188, "loss": 0.1335, "lr": 9.301760438704442e-06, "epoch": 4.98471986417657, "percentage": 71.19, "elapsed_time": "10:01:37", "remaining_time": "4:03:31"}
|
| 887 |
+
{"current_steps": 4410, "total_steps": 6188, "loss": 0.1606, "lr": 9.254139993185176e-06, "epoch": 4.990379173740804, "percentage": 71.27, "elapsed_time": "10:04:44", "remaining_time": "4:03:49"}
|
| 888 |
+
{"current_steps": 4415, "total_steps": 6188, "loss": 0.16, "lr": 9.206605039809955e-06, "epoch": 4.996038483305036, "percentage": 71.35, "elapsed_time": "10:07:48", "remaining_time": "4:04:05"}
|
| 889 |
+
{"current_steps": 4420, "total_steps": 6188, "loss": 0.1498, "lr": 9.159155956758375e-06, "epoch": 5.001131861912847, "percentage": 71.43, "elapsed_time": "10:10:20", "remaining_time": "4:04:08"}
|
| 890 |
+
{"current_steps": 4425, "total_steps": 6188, "loss": 0.1006, "lr": 9.111793121526862e-06, "epoch": 5.006791171477079, "percentage": 71.51, "elapsed_time": "10:12:01", "remaining_time": "4:03:50"}
|
| 891 |
+
{"current_steps": 4430, "total_steps": 6188, "loss": 0.0817, "lr": 9.064516910925698e-06, "epoch": 5.012450481041313, "percentage": 71.59, "elapsed_time": "10:13:43", "remaining_time": "4:03:32"}
|
| 892 |
+
{"current_steps": 4435, "total_steps": 6188, "loss": 0.0755, "lr": 9.017327701075965e-06, "epoch": 5.018109790605546, "percentage": 71.67, "elapsed_time": "10:15:19", "remaining_time": "4:03:12"}
|
| 893 |
+
{"current_steps": 4440, "total_steps": 6188, "loss": 0.0951, "lr": 8.970225867406593e-06, "epoch": 5.023769100169779, "percentage": 71.75, "elapsed_time": "10:16:55", "remaining_time": "4:02:52"}
|
| 894 |
+
{"current_steps": 4445, "total_steps": 6188, "loss": 0.0739, "lr": 8.923211784651356e-06, "epoch": 5.029428409734012, "percentage": 71.83, "elapsed_time": "10:18:37", "remaining_time": "4:02:34"}
|
| 895 |
+
{"current_steps": 4450, "total_steps": 6188, "loss": 0.1014, "lr": 8.876285826845918e-06, "epoch": 5.035087719298246, "percentage": 71.91, "elapsed_time": "10:20:14", "remaining_time": "4:02:14"}
|
| 896 |
+
{"current_steps": 4455, "total_steps": 6188, "loss": 0.1122, "lr": 8.82944836732482e-06, "epoch": 5.040747028862479, "percentage": 71.99, "elapsed_time": "10:22:01", "remaining_time": "4:01:58"}
|
| 897 |
+
{"current_steps": 4460, "total_steps": 6188, "loss": 0.0852, "lr": 8.782699778718516e-06, "epoch": 5.046406338426712, "percentage": 72.07, "elapsed_time": "10:23:36", "remaining_time": "4:01:36"}
|
| 898 |
+
{"current_steps": 4465, "total_steps": 6188, "loss": 0.1107, "lr": 8.736040432950447e-06, "epoch": 5.052065647990945, "percentage": 72.16, "elapsed_time": "10:25:37", "remaining_time": "4:01:25"}
|
| 899 |
+
{"current_steps": 4470, "total_steps": 6188, "loss": 0.0768, "lr": 8.689470701234037e-06, "epoch": 5.057724957555179, "percentage": 72.24, "elapsed_time": "10:27:44", "remaining_time": "4:01:15"}
|
| 900 |
+
{"current_steps": 4475, "total_steps": 6188, "loss": 0.0766, "lr": 8.642990954069747e-06, "epoch": 5.063384267119411, "percentage": 72.32, "elapsed_time": "10:29:44", "remaining_time": "4:01:03"}
|
| 901 |
+
{"current_steps": 4480, "total_steps": 6188, "loss": 0.0755, "lr": 8.596601561242167e-06, "epoch": 5.069043576683645, "percentage": 72.4, "elapsed_time": "10:31:29", "remaining_time": "4:00:45"}
|
| 902 |
+
{"current_steps": 4485, "total_steps": 6188, "loss": 0.0938, "lr": 8.550302891817015e-06, "epoch": 5.074702886247878, "percentage": 72.48, "elapsed_time": "10:33:22", "remaining_time": "4:00:29"}
|
| 903 |
+
{"current_steps": 4490, "total_steps": 6188, "loss": 0.096, "lr": 8.50409531413824e-06, "epoch": 5.080362195812111, "percentage": 72.56, "elapsed_time": "10:35:03", "remaining_time": "4:00:09"}
|
| 904 |
+
{"current_steps": 4495, "total_steps": 6188, "loss": 0.0775, "lr": 8.457979195825076e-06, "epoch": 5.086021505376344, "percentage": 72.64, "elapsed_time": "10:36:44", "remaining_time": "3:59:49"}
|
| 905 |
+
{"current_steps": 4500, "total_steps": 6188, "loss": 0.0712, "lr": 8.411954903769145e-06, "epoch": 5.0916808149405774, "percentage": 72.72, "elapsed_time": "10:38:20", "remaining_time": "3:59:27"}
|
| 906 |
+
{"current_steps": 4505, "total_steps": 6188, "loss": 0.0764, "lr": 8.366022804131487e-06, "epoch": 5.09734012450481, "percentage": 72.8, "elapsed_time": "10:39:54", "remaining_time": "3:59:03"}
|
| 907 |
+
{"current_steps": 4510, "total_steps": 6188, "loss": 0.0875, "lr": 8.320183262339686e-06, "epoch": 5.102999434069043, "percentage": 72.88, "elapsed_time": "10:41:24", "remaining_time": "3:58:38"}
|
| 908 |
+
{"current_steps": 4515, "total_steps": 6188, "loss": 0.086, "lr": 8.274436643084962e-06, "epoch": 5.108658743633277, "percentage": 72.96, "elapsed_time": "10:43:14", "remaining_time": "3:58:21"}
|
| 909 |
+
{"current_steps": 4520, "total_steps": 6188, "loss": 0.0865, "lr": 8.228783310319248e-06, "epoch": 5.11431805319751, "percentage": 73.04, "elapsed_time": "10:44:51", "remaining_time": "3:57:58"}
|
| 910 |
+
{"current_steps": 4525, "total_steps": 6188, "loss": 0.0951, "lr": 8.183223627252305e-06, "epoch": 5.119977362761743, "percentage": 73.13, "elapsed_time": "10:46:46", "remaining_time": "3:57:41"}
|
| 911 |
+
{"current_steps": 4530, "total_steps": 6188, "loss": 0.113, "lr": 8.137757956348854e-06, "epoch": 5.125636672325976, "percentage": 73.21, "elapsed_time": "10:48:25", "remaining_time": "3:57:19"}
|
| 912 |
+
{"current_steps": 4535, "total_steps": 6188, "loss": 0.0732, "lr": 8.092386659325644e-06, "epoch": 5.13129598189021, "percentage": 73.29, "elapsed_time": "10:49:56", "remaining_time": "3:56:54"}
|
| 913 |
+
{"current_steps": 4540, "total_steps": 6188, "loss": 0.1092, "lr": 8.047110097148618e-06, "epoch": 5.136955291454442, "percentage": 73.37, "elapsed_time": "10:51:31", "remaining_time": "3:56:30"}
|
| 914 |
+
{"current_steps": 4545, "total_steps": 6188, "loss": 0.0912, "lr": 8.001928630030017e-06, "epoch": 5.142614601018676, "percentage": 73.45, "elapsed_time": "10:53:19", "remaining_time": "3:56:10"}
|
| 915 |
+
{"current_steps": 4550, "total_steps": 6188, "loss": 0.082, "lr": 7.95684261742554e-06, "epoch": 5.148273910582909, "percentage": 73.53, "elapsed_time": "10:55:02", "remaining_time": "3:55:49"}
|
| 916 |
+
{"current_steps": 4555, "total_steps": 6188, "loss": 0.2466, "lr": 7.911852418031449e-06, "epoch": 5.153933220147142, "percentage": 73.61, "elapsed_time": "10:57:11", "remaining_time": "3:55:36"}
|
| 917 |
+
{"current_steps": 4560, "total_steps": 6188, "loss": 0.1153, "lr": 7.866958389781736e-06, "epoch": 5.159592529711375, "percentage": 73.69, "elapsed_time": "10:58:58", "remaining_time": "3:55:15"}
|
| 918 |
+
{"current_steps": 4565, "total_steps": 6188, "loss": 0.0945, "lr": 7.822160889845286e-06, "epoch": 5.165251839275609, "percentage": 73.77, "elapsed_time": "11:00:55", "remaining_time": "3:54:58"}
|
| 919 |
+
{"current_steps": 4570, "total_steps": 6188, "loss": 0.1741, "lr": 7.777460274623005e-06, "epoch": 5.170911148839841, "percentage": 73.85, "elapsed_time": "11:03:09", "remaining_time": "3:54:47"}
|
| 920 |
+
{"current_steps": 4575, "total_steps": 6188, "loss": 0.0815, "lr": 7.732856899745003e-06, "epoch": 5.176570458404075, "percentage": 73.93, "elapsed_time": "11:04:51", "remaining_time": "3:54:24"}
|
| 921 |
+
{"current_steps": 4580, "total_steps": 6188, "loss": 0.0806, "lr": 7.688351120067781e-06, "epoch": 5.182229767968308, "percentage": 74.01, "elapsed_time": "11:06:44", "remaining_time": "3:54:05"}
|
| 922 |
+
{"current_steps": 4585, "total_steps": 6188, "loss": 0.0844, "lr": 7.643943289671374e-06, "epoch": 5.187889077532541, "percentage": 74.1, "elapsed_time": "11:08:26", "remaining_time": "3:53:41"}
|
| 923 |
+
{"current_steps": 4590, "total_steps": 6188, "loss": 0.076, "lr": 7.599633761856542e-06, "epoch": 5.193548387096774, "percentage": 74.18, "elapsed_time": "11:10:03", "remaining_time": "3:53:16"}
|
| 924 |
+
{"current_steps": 4595, "total_steps": 6188, "loss": 0.0763, "lr": 7.555422889141997e-06, "epoch": 5.1992076966610075, "percentage": 74.26, "elapsed_time": "11:11:49", "remaining_time": "3:52:54"}
|
| 925 |
+
{"current_steps": 4600, "total_steps": 6188, "loss": 0.0702, "lr": 7.51131102326154e-06, "epoch": 5.204867006225241, "percentage": 74.34, "elapsed_time": "11:13:21", "remaining_time": "3:52:27"}
|