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:d87a7a4cee62628d96e1920a34e3347c96ec250da2fe8b723901339950401199
|
| 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:a4e5b62841210439d615f38d96fc5bdaa5318a67fe6f5a93c3fb0d81c017fb91
|
| 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:b6e4efe7126d7c45a26b1a2faae6a692d9840c9cb7b78c63668c3ee3d83298af
|
| 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 sha256:87e158475ac233b3ee6b74734fbc77f3306fd93d226b59d3ea31e47c8b55630b
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -880,3 +880,43 @@
|
|
| 880 |
{"current_steps": 4390, "total_steps": 6188, "loss": 0.0696, "lr": 9.445130936146098e-06, "epoch": 4.967741935483871, "percentage": 70.94, "elapsed_time": "9:46:08", "remaining_time": "4:00:03"}
|
| 881 |
{"current_steps": 4395, "total_steps": 6188, "loss": 0.0767, "lr": 9.397256290058869e-06, "epoch": 4.973401245048104, "percentage": 71.02, "elapsed_time": "9:47:52", "remaining_time": "3:59:49"}
|
| 882 |
{"current_steps": 4400, "total_steps": 6188, "loss": 0.0971, "lr": 9.349465997507974e-06, "epoch": 4.979060554612337, "percentage": 71.11, "elapsed_time": "9:50:18", "remaining_time": "3:59:52"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 880 |
{"current_steps": 4390, "total_steps": 6188, "loss": 0.0696, "lr": 9.445130936146098e-06, "epoch": 4.967741935483871, "percentage": 70.94, "elapsed_time": "9:46:08", "remaining_time": "4:00:03"}
|
| 881 |
{"current_steps": 4395, "total_steps": 6188, "loss": 0.0767, "lr": 9.397256290058869e-06, "epoch": 4.973401245048104, "percentage": 71.02, "elapsed_time": "9:47:52", "remaining_time": "3:59:49"}
|
| 882 |
{"current_steps": 4400, "total_steps": 6188, "loss": 0.0971, "lr": 9.349465997507974e-06, "epoch": 4.979060554612337, "percentage": 71.11, "elapsed_time": "9:50:18", "remaining_time": "3:59:52"}
|
| 883 |
+
{"current_steps": 4405, "total_steps": 6188, "loss": 0.1424, "lr": 9.301760438704442e-06, "epoch": 4.98471986417657, "percentage": 71.19, "elapsed_time": "9:53:54", "remaining_time": "4:00:23"}
|
| 884 |
+
{"current_steps": 4410, "total_steps": 6188, "loss": 0.0778, "lr": 9.254139993185176e-06, "epoch": 4.990379173740804, "percentage": 71.27, "elapsed_time": "9:55:39", "remaining_time": "4:00:09"}
|
| 885 |
+
{"current_steps": 4415, "total_steps": 6188, "loss": 0.073, "lr": 9.206605039809955e-06, "epoch": 4.996038483305036, "percentage": 71.35, "elapsed_time": "9:57:15", "remaining_time": "3:59:50"}
|
| 886 |
+
{"current_steps": 4420, "total_steps": 6188, "loss": 0.1219, "lr": 9.159155956758375e-06, "epoch": 5.001131861912847, "percentage": 71.43, "elapsed_time": "9:59:19", "remaining_time": "3:59:43"}
|
| 887 |
+
{"current_steps": 4425, "total_steps": 6188, "loss": 0.1623, "lr": 9.111793121526862e-06, "epoch": 5.006791171477079, "percentage": 71.51, "elapsed_time": "10:02:16", "remaining_time": "3:59:57"}
|
| 888 |
+
{"current_steps": 4430, "total_steps": 6188, "loss": 0.1565, "lr": 9.064516910925698e-06, "epoch": 5.012450481041313, "percentage": 71.59, "elapsed_time": "10:05:10", "remaining_time": "4:00:09"}
|
| 889 |
+
{"current_steps": 4435, "total_steps": 6188, "loss": 0.1494, "lr": 9.017327701075965e-06, "epoch": 5.018109790605546, "percentage": 71.67, "elapsed_time": "10:08:03", "remaining_time": "4:00:20"}
|
| 890 |
+
{"current_steps": 4440, "total_steps": 6188, "loss": 0.1481, "lr": 8.970225867406593e-06, "epoch": 5.023769100169779, "percentage": 71.75, "elapsed_time": "10:10:54", "remaining_time": "4:00:30"}
|
| 891 |
+
{"current_steps": 4445, "total_steps": 6188, "loss": 0.1642, "lr": 8.923211784651356e-06, "epoch": 5.029428409734012, "percentage": 71.83, "elapsed_time": "10:13:46", "remaining_time": "4:00:40"}
|
| 892 |
+
{"current_steps": 4450, "total_steps": 6188, "loss": 0.1581, "lr": 8.876285826845918e-06, "epoch": 5.035087719298246, "percentage": 71.91, "elapsed_time": "10:16:48", "remaining_time": "4:00:53"}
|
| 893 |
+
{"current_steps": 4455, "total_steps": 6188, "loss": 0.1467, "lr": 8.82944836732482e-06, "epoch": 5.040747028862479, "percentage": 71.99, "elapsed_time": "10:19:45", "remaining_time": "4:01:05"}
|
| 894 |
+
{"current_steps": 4460, "total_steps": 6188, "loss": 0.1738, "lr": 8.782699778718516e-06, "epoch": 5.046406338426712, "percentage": 72.07, "elapsed_time": "10:22:22", "remaining_time": "4:01:08"}
|
| 895 |
+
{"current_steps": 4465, "total_steps": 6188, "loss": 0.1482, "lr": 8.736040432950447e-06, "epoch": 5.052065647990945, "percentage": 72.16, "elapsed_time": "10:25:19", "remaining_time": "4:01:18"}
|
| 896 |
+
{"current_steps": 4470, "total_steps": 6188, "loss": 0.1578, "lr": 8.689470701234037e-06, "epoch": 5.057724957555179, "percentage": 72.24, "elapsed_time": "10:28:24", "remaining_time": "4:01:31"}
|
| 897 |
+
{"current_steps": 4475, "total_steps": 6188, "loss": 0.145, "lr": 8.642990954069747e-06, "epoch": 5.063384267119411, "percentage": 72.32, "elapsed_time": "10:31:08", "remaining_time": "4:01:35"}
|
| 898 |
+
{"current_steps": 4480, "total_steps": 6188, "loss": 0.1554, "lr": 8.596601561242167e-06, "epoch": 5.069043576683645, "percentage": 72.4, "elapsed_time": "10:34:04", "remaining_time": "4:01:44"}
|
| 899 |
+
{"current_steps": 4485, "total_steps": 6188, "loss": 0.1406, "lr": 8.550302891817015e-06, "epoch": 5.074702886247878, "percentage": 72.48, "elapsed_time": "10:37:05", "remaining_time": "4:01:54"}
|
| 900 |
+
{"current_steps": 4490, "total_steps": 6188, "loss": 0.1417, "lr": 8.50409531413824e-06, "epoch": 5.080362195812111, "percentage": 72.56, "elapsed_time": "10:39:54", "remaining_time": "4:01:59"}
|
| 901 |
+
{"current_steps": 4495, "total_steps": 6188, "loss": 0.1387, "lr": 8.457979195825076e-06, "epoch": 5.086021505376344, "percentage": 72.64, "elapsed_time": "10:42:43", "remaining_time": "4:02:04"}
|
| 902 |
+
{"current_steps": 4500, "total_steps": 6188, "loss": 0.1516, "lr": 8.411954903769145e-06, "epoch": 5.0916808149405774, "percentage": 72.72, "elapsed_time": "10:45:38", "remaining_time": "4:02:11"}
|
| 903 |
+
{"current_steps": 4505, "total_steps": 6188, "loss": 0.1456, "lr": 8.366022804131487e-06, "epoch": 5.09734012450481, "percentage": 72.8, "elapsed_time": "10:48:26", "remaining_time": "4:02:14"}
|
| 904 |
+
{"current_steps": 4510, "total_steps": 6188, "loss": 0.1314, "lr": 8.320183262339686e-06, "epoch": 5.102999434069043, "percentage": 72.88, "elapsed_time": "10:51:30", "remaining_time": "4:02:24"}
|
| 905 |
+
{"current_steps": 4515, "total_steps": 6188, "loss": 0.1382, "lr": 8.274436643084962e-06, "epoch": 5.108658743633277, "percentage": 72.96, "elapsed_time": "10:54:28", "remaining_time": "4:02:30"}
|
| 906 |
+
{"current_steps": 4520, "total_steps": 6188, "loss": 0.1577, "lr": 8.228783310319248e-06, "epoch": 5.11431805319751, "percentage": 73.04, "elapsed_time": "10:57:28", "remaining_time": "4:02:37"}
|
| 907 |
+
{"current_steps": 4525, "total_steps": 6188, "loss": 0.1596, "lr": 8.183223627252305e-06, "epoch": 5.119977362761743, "percentage": 73.13, "elapsed_time": "11:00:25", "remaining_time": "4:02:43"}
|
| 908 |
+
{"current_steps": 4530, "total_steps": 6188, "loss": 0.1413, "lr": 8.137757956348854e-06, "epoch": 5.125636672325976, "percentage": 73.21, "elapsed_time": "11:03:18", "remaining_time": "4:02:46"}
|
| 909 |
+
{"current_steps": 4535, "total_steps": 6188, "loss": 0.1499, "lr": 8.092386659325644e-06, "epoch": 5.13129598189021, "percentage": 73.29, "elapsed_time": "11:06:18", "remaining_time": "4:02:52"}
|
| 910 |
+
{"current_steps": 4540, "total_steps": 6188, "loss": 0.1624, "lr": 8.047110097148618e-06, "epoch": 5.136955291454442, "percentage": 73.37, "elapsed_time": "11:09:11", "remaining_time": "4:02:54"}
|
| 911 |
+
{"current_steps": 4545, "total_steps": 6188, "loss": 0.1799, "lr": 8.001928630030017e-06, "epoch": 5.142614601018676, "percentage": 73.45, "elapsed_time": "11:12:12", "remaining_time": "4:02:59"}
|
| 912 |
+
{"current_steps": 4550, "total_steps": 6188, "loss": 0.1687, "lr": 7.95684261742554e-06, "epoch": 5.148273910582909, "percentage": 73.53, "elapsed_time": "11:15:14", "remaining_time": "4:03:05"}
|
| 913 |
+
{"current_steps": 4555, "total_steps": 6188, "loss": 0.1495, "lr": 7.911852418031449e-06, "epoch": 5.153933220147142, "percentage": 73.61, "elapsed_time": "11:18:21", "remaining_time": "4:03:11"}
|
| 914 |
+
{"current_steps": 4560, "total_steps": 6188, "loss": 0.1517, "lr": 7.866958389781736e-06, "epoch": 5.159592529711375, "percentage": 73.69, "elapsed_time": "11:21:24", "remaining_time": "4:03:16"}
|
| 915 |
+
{"current_steps": 4565, "total_steps": 6188, "loss": 0.1574, "lr": 7.822160889845286e-06, "epoch": 5.165251839275609, "percentage": 73.77, "elapsed_time": "11:24:22", "remaining_time": "4:03:19"}
|
| 916 |
+
{"current_steps": 4570, "total_steps": 6188, "loss": 0.1526, "lr": 7.777460274623005e-06, "epoch": 5.170911148839841, "percentage": 73.85, "elapsed_time": "11:27:18", "remaining_time": "4:03:20"}
|
| 917 |
+
{"current_steps": 4575, "total_steps": 6188, "loss": 0.1529, "lr": 7.732856899745003e-06, "epoch": 5.176570458404075, "percentage": 73.93, "elapsed_time": "11:30:26", "remaining_time": "4:03:25"}
|
| 918 |
+
{"current_steps": 4580, "total_steps": 6188, "loss": 0.1606, "lr": 7.688351120067781e-06, "epoch": 5.182229767968308, "percentage": 74.01, "elapsed_time": "11:33:32", "remaining_time": "4:03:29"}
|
| 919 |
+
{"current_steps": 4585, "total_steps": 6188, "loss": 0.1553, "lr": 7.643943289671374e-06, "epoch": 5.187889077532541, "percentage": 74.1, "elapsed_time": "11:36:29", "remaining_time": "4:03:30"}
|
| 920 |
+
{"current_steps": 4590, "total_steps": 6188, "loss": 0.1399, "lr": 7.599633761856542e-06, "epoch": 5.193548387096774, "percentage": 74.18, "elapsed_time": "11:39:25", "remaining_time": "4:03:30"}
|
| 921 |
+
{"current_steps": 4595, "total_steps": 6188, "loss": 0.134, "lr": 7.555422889141997e-06, "epoch": 5.1992076966610075, "percentage": 74.26, "elapsed_time": "11:42:32", "remaining_time": "4:03:33"}
|
| 922 |
+
{"current_steps": 4600, "total_steps": 6188, "loss": 0.1596, "lr": 7.51131102326154e-06, "epoch": 5.204867006225241, "percentage": 74.34, "elapsed_time": "11:45:34", "remaining_time": "4:03:34"}
|