Training in progress, step 4400
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 sha256:1753924b9521a099700a5914e000858c690bb890b4ace47d2d1bb8fe9744d639
|
| 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:e7be15cb0a7dc177c18f9095838494966527d77f9446841b2cb5d4007bf05868
|
| 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 sha256:07e48546613c869fcbf3bbdf339c1aec1d281f466d15ff9fd31743a2ba5af19f
|
| 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 sha256:626b5adb5eef04f60b8049f32782a05ec3a9accd67517231f6594f4cad0f5501
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -843,3 +843,43 @@
|
|
| 843 |
{"current_steps": 4190, "total_steps": 6188, "loss": 0.1568, "lr": 1.142484198457475e-05, "epoch": 4.741369552914544, "percentage": 67.71, "elapsed_time": "7:50:17", "remaining_time": "3:44:15"}
|
| 844 |
{"current_steps": 4195, "total_steps": 6188, "loss": 0.1618, "lr": 1.1373912330764671e-05, "epoch": 4.7470288624787775, "percentage": 67.79, "elapsed_time": "7:53:12", "remaining_time": "3:44:48"}
|
| 845 |
{"current_steps": 4200, "total_steps": 6188, "loss": 0.1482, "lr": 1.1323051304568292e-05, "epoch": 4.752688172043011, "percentage": 67.87, "elapsed_time": "7:56:15", "remaining_time": "3:45:25"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 843 |
{"current_steps": 4190, "total_steps": 6188, "loss": 0.1568, "lr": 1.142484198457475e-05, "epoch": 4.741369552914544, "percentage": 67.71, "elapsed_time": "7:50:17", "remaining_time": "3:44:15"}
|
| 844 |
{"current_steps": 4195, "total_steps": 6188, "loss": 0.1618, "lr": 1.1373912330764671e-05, "epoch": 4.7470288624787775, "percentage": 67.79, "elapsed_time": "7:53:12", "remaining_time": "3:44:48"}
|
| 845 |
{"current_steps": 4200, "total_steps": 6188, "loss": 0.1482, "lr": 1.1323051304568292e-05, "epoch": 4.752688172043011, "percentage": 67.87, "elapsed_time": "7:56:15", "remaining_time": "3:45:25"}
|
| 846 |
+
{"current_steps": 4205, "total_steps": 6188, "loss": 0.1647, "lr": 1.1272259310626872e-05, "epoch": 4.7583474816072435, "percentage": 67.95, "elapsed_time": "8:00:37", "remaining_time": "3:46:39"}
|
| 847 |
+
{"current_steps": 4210, "total_steps": 6188, "loss": 0.1597, "lr": 1.122153675303244e-05, "epoch": 4.764006791171477, "percentage": 68.03, "elapsed_time": "8:03:42", "remaining_time": "3:47:15"}
|
| 848 |
+
{"current_steps": 4215, "total_steps": 6188, "loss": 0.1472, "lr": 1.1170884035324607e-05, "epoch": 4.76966610073571, "percentage": 68.12, "elapsed_time": "8:06:31", "remaining_time": "3:47:44"}
|
| 849 |
+
{"current_steps": 4220, "total_steps": 6188, "loss": 0.1373, "lr": 1.1120301560487365e-05, "epoch": 4.775325410299944, "percentage": 68.2, "elapsed_time": "8:09:36", "remaining_time": "3:48:19"}
|
| 850 |
+
{"current_steps": 4225, "total_steps": 6188, "loss": 0.1535, "lr": 1.1069789730945849e-05, "epoch": 4.780984719864176, "percentage": 68.28, "elapsed_time": "8:12:37", "remaining_time": "3:48:53"}
|
| 851 |
+
{"current_steps": 4230, "total_steps": 6188, "loss": 0.1667, "lr": 1.1019348948563154e-05, "epoch": 4.78664402942841, "percentage": 68.36, "elapsed_time": "8:15:41", "remaining_time": "3:49:26"}
|
| 852 |
+
{"current_steps": 4235, "total_steps": 6188, "loss": 0.1605, "lr": 1.096897961463714e-05, "epoch": 4.792303338992643, "percentage": 68.44, "elapsed_time": "8:18:44", "remaining_time": "3:50:00"}
|
| 853 |
+
{"current_steps": 4240, "total_steps": 6188, "loss": 0.1453, "lr": 1.0918682129897244e-05, "epoch": 4.797962648556876, "percentage": 68.52, "elapsed_time": "8:21:25", "remaining_time": "3:50:22"}
|
| 854 |
+
{"current_steps": 4245, "total_steps": 6188, "loss": 0.1468, "lr": 1.0868456894501276e-05, "epoch": 4.803621958121109, "percentage": 68.6, "elapsed_time": "8:24:18", "remaining_time": "3:50:49"}
|
| 855 |
+
{"current_steps": 4250, "total_steps": 6188, "loss": 0.1541, "lr": 1.0818304308032232e-05, "epoch": 4.809281267685343, "percentage": 68.68, "elapsed_time": "8:27:16", "remaining_time": "3:51:19"}
|
| 856 |
+
{"current_steps": 4255, "total_steps": 6188, "loss": 0.1597, "lr": 1.0768224769495155e-05, "epoch": 4.814940577249575, "percentage": 68.76, "elapsed_time": "8:30:11", "remaining_time": "3:51:46"}
|
| 857 |
+
{"current_steps": 4260, "total_steps": 6188, "loss": 0.1471, "lr": 1.0718218677313904e-05, "epoch": 4.820599886813809, "percentage": 68.84, "elapsed_time": "8:33:00", "remaining_time": "3:52:10"}
|
| 858 |
+
{"current_steps": 4265, "total_steps": 6188, "loss": 0.152, "lr": 1.0668286429328015e-05, "epoch": 4.826259196378042, "percentage": 68.92, "elapsed_time": "8:35:55", "remaining_time": "3:52:37"}
|
| 859 |
+
{"current_steps": 4270, "total_steps": 6188, "loss": 0.1593, "lr": 1.0618428422789555e-05, "epoch": 4.831918505942275, "percentage": 69.0, "elapsed_time": "8:38:42", "remaining_time": "3:52:59"}
|
| 860 |
+
{"current_steps": 4275, "total_steps": 6188, "loss": 0.1324, "lr": 1.0568645054359919e-05, "epoch": 4.837577815506508, "percentage": 69.09, "elapsed_time": "8:41:40", "remaining_time": "3:53:26"}
|
| 861 |
+
{"current_steps": 4280, "total_steps": 6188, "loss": 0.1295, "lr": 1.051893672010669e-05, "epoch": 4.8432371250707416, "percentage": 69.17, "elapsed_time": "8:44:39", "remaining_time": "3:53:53"}
|
| 862 |
+
{"current_steps": 4285, "total_steps": 6188, "loss": 0.1404, "lr": 1.0469303815500518e-05, "epoch": 4.848896434634975, "percentage": 69.25, "elapsed_time": "8:47:43", "remaining_time": "3:54:22"}
|
| 863 |
+
{"current_steps": 4290, "total_steps": 6188, "loss": 0.1461, "lr": 1.0419746735411922e-05, "epoch": 4.8545557441992075, "percentage": 69.33, "elapsed_time": "8:50:43", "remaining_time": "3:54:48"}
|
| 864 |
+
{"current_steps": 4295, "total_steps": 6188, "loss": 0.1666, "lr": 1.037026587410819e-05, "epoch": 4.860215053763441, "percentage": 69.41, "elapsed_time": "8:53:41", "remaining_time": "3:55:13"}
|
| 865 |
+
{"current_steps": 4300, "total_steps": 6188, "loss": 0.1842, "lr": 1.032086162525021e-05, "epoch": 4.8658743633276735, "percentage": 69.49, "elapsed_time": "8:56:24", "remaining_time": "3:55:31"}
|
| 866 |
+
{"current_steps": 4305, "total_steps": 6188, "loss": 0.1467, "lr": 1.0271534381889385e-05, "epoch": 4.871533672891907, "percentage": 69.57, "elapsed_time": "8:59:18", "remaining_time": "3:55:53"}
|
| 867 |
+
{"current_steps": 4310, "total_steps": 6188, "loss": 0.1533, "lr": 1.0222284536464451e-05, "epoch": 4.87719298245614, "percentage": 69.65, "elapsed_time": "9:02:22", "remaining_time": "3:56:19"}
|
| 868 |
+
{"current_steps": 4315, "total_steps": 6188, "loss": 0.1496, "lr": 1.0173112480798376e-05, "epoch": 4.882852292020374, "percentage": 69.73, "elapsed_time": "9:05:27", "remaining_time": "3:56:45"}
|
| 869 |
+
{"current_steps": 4320, "total_steps": 6188, "loss": 0.1723, "lr": 1.0124018606095278e-05, "epoch": 4.888511601584606, "percentage": 69.81, "elapsed_time": "9:08:33", "remaining_time": "3:57:12"}
|
| 870 |
+
{"current_steps": 4325, "total_steps": 6188, "loss": 0.1571, "lr": 1.0075003302937247e-05, "epoch": 4.89417091114884, "percentage": 69.89, "elapsed_time": "9:11:39", "remaining_time": "3:57:37"}
|
| 871 |
+
{"current_steps": 4330, "total_steps": 6188, "loss": 0.1558, "lr": 1.0026066961281282e-05, "epoch": 4.899830220713073, "percentage": 69.97, "elapsed_time": "9:14:44", "remaining_time": "3:58:02"}
|
| 872 |
+
{"current_steps": 4335, "total_steps": 6188, "loss": 0.1581, "lr": 9.977209970456194e-06, "epoch": 4.905489530277306, "percentage": 70.05, "elapsed_time": "9:17:48", "remaining_time": "3:58:26"}
|
| 873 |
+
{"current_steps": 4340, "total_steps": 6188, "loss": 0.1381, "lr": 9.928432719159475e-06, "epoch": 4.911148839841539, "percentage": 70.14, "elapsed_time": "9:20:53", "remaining_time": "3:58:49"}
|
| 874 |
+
{"current_steps": 4345, "total_steps": 6188, "loss": 0.1523, "lr": 9.879735595454232e-06, "epoch": 4.916808149405773, "percentage": 70.22, "elapsed_time": "9:23:58", "remaining_time": "3:59:12"}
|
| 875 |
+
{"current_steps": 4350, "total_steps": 6188, "loss": 0.1936, "lr": 9.831118986766084e-06, "epoch": 4.922467458970006, "percentage": 70.3, "elapsed_time": "9:27:02", "remaining_time": "3:59:35"}
|
| 876 |
+
{"current_steps": 4355, "total_steps": 6188, "loss": 0.1445, "lr": 9.782583279880096e-06, "epoch": 4.928126768534239, "percentage": 70.38, "elapsed_time": "9:30:04", "remaining_time": "3:59:56"}
|
| 877 |
+
{"current_steps": 4360, "total_steps": 6188, "loss": 0.1571, "lr": 9.734128860937675e-06, "epoch": 4.933786078098472, "percentage": 70.46, "elapsed_time": "9:33:07", "remaining_time": "4:00:17"}
|
| 878 |
+
{"current_steps": 4365, "total_steps": 6188, "loss": 0.1578, "lr": 9.68575611543355e-06, "epoch": 4.939445387662705, "percentage": 70.54, "elapsed_time": "9:36:08", "remaining_time": "4:00:37"}
|
| 879 |
+
{"current_steps": 4370, "total_steps": 6188, "loss": 0.1443, "lr": 9.637465428212636e-06, "epoch": 4.945104697226938, "percentage": 70.62, "elapsed_time": "9:39:11", "remaining_time": "4:00:57"}
|
| 880 |
+
{"current_steps": 4375, "total_steps": 6188, "loss": 0.1409, "lr": 9.589257183467025e-06, "epoch": 4.950764006791172, "percentage": 70.7, "elapsed_time": "9:42:18", "remaining_time": "4:01:18"}
|
| 881 |
+
{"current_steps": 4380, "total_steps": 6188, "loss": 0.1453, "lr": 9.541131764732896e-06, "epoch": 4.956423316355405, "percentage": 70.78, "elapsed_time": "9:45:15", "remaining_time": "4:01:35"}
|
| 882 |
+
{"current_steps": 4385, "total_steps": 6188, "loss": 0.1538, "lr": 9.493089554887508e-06, "epoch": 4.962082625919638, "percentage": 70.86, "elapsed_time": "9:48:14", "remaining_time": "4:01:52"}
|
| 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"}
|