Training in progress, step 4340
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 sha256:6f78f6e9825e610b02eaa0653dc278f51ec831a43ff9103af97cd4b5677ce53f
|
| 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:f57b48a01b0af7435a9b7232375b2e9e12f469a64f06d84136810df8fc5aaf19
|
| 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:aebe5b1c557da4bb949981f01af3653999b95718cb2e9887f1636eb3cd0d418d
|
| 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 sha256:540df25d24e8436164126d34f7227dfd859cf83dd060cdc5058cace4bf241742
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -838,3 +838,32 @@
|
|
| 838 |
{"current_steps": 4190, "total_steps": 4340, "loss": 0.4022, "lr": 1.473178186723545e-07, "epoch": 6.758064516129032, "percentage": 96.54, "elapsed_time": "20:39:28", "remaining_time": "0:44:22"}
|
| 839 |
{"current_steps": 4195, "total_steps": 4340, "loss": 0.4031, "lr": 1.3773422564417939e-07, "epoch": 6.766129032258064, "percentage": 96.66, "elapsed_time": "20:40:52", "remaining_time": "0:42:53"}
|
| 840 |
{"current_steps": 4200, "total_steps": 4340, "loss": 0.3839, "lr": 1.2847185328310087e-07, "epoch": 6.774193548387097, "percentage": 96.77, "elapsed_time": "20:42:10", "remaining_time": "0:41:24"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 838 |
{"current_steps": 4190, "total_steps": 4340, "loss": 0.4022, "lr": 1.473178186723545e-07, "epoch": 6.758064516129032, "percentage": 96.54, "elapsed_time": "20:39:28", "remaining_time": "0:44:22"}
|
| 839 |
{"current_steps": 4195, "total_steps": 4340, "loss": 0.4031, "lr": 1.3773422564417939e-07, "epoch": 6.766129032258064, "percentage": 96.66, "elapsed_time": "20:40:52", "remaining_time": "0:42:53"}
|
| 840 |
{"current_steps": 4200, "total_steps": 4340, "loss": 0.3839, "lr": 1.2847185328310087e-07, "epoch": 6.774193548387097, "percentage": 96.77, "elapsed_time": "20:42:10", "remaining_time": "0:41:24"}
|
| 841 |
+
{"current_steps": 4205, "total_steps": 4340, "loss": 0.4107, "lr": 1.1953085138398656e-07, "epoch": 6.782258064516129, "percentage": 96.89, "elapsed_time": "20:45:22", "remaining_time": "0:39:58"}
|
| 842 |
+
{"current_steps": 4210, "total_steps": 4340, "loss": 0.4113, "lr": 1.1091136454436602e-07, "epoch": 6.790322580645161, "percentage": 97.0, "elapsed_time": "20:46:38", "remaining_time": "0:38:29"}
|
| 843 |
+
{"current_steps": 4215, "total_steps": 4340, "loss": 0.4002, "lr": 1.0261353216209691e-07, "epoch": 6.798387096774194, "percentage": 97.12, "elapsed_time": "20:47:57", "remaining_time": "0:37:00"}
|
| 844 |
+
{"current_steps": 4220, "total_steps": 4340, "loss": 0.4258, "lr": 9.463748843311138e-08, "epoch": 6.806451612903226, "percentage": 97.24, "elapsed_time": "20:49:37", "remaining_time": "0:35:32"}
|
| 845 |
+
{"current_steps": 4225, "total_steps": 4340, "loss": 0.407, "lr": 8.698336234924442e-08, "epoch": 6.814516129032258, "percentage": 97.35, "elapsed_time": "20:50:58", "remaining_time": "0:34:03"}
|
| 846 |
+
{"current_steps": 4230, "total_steps": 4340, "loss": 0.4273, "lr": 7.965127769614667e-08, "epoch": 6.82258064516129, "percentage": 97.47, "elapsed_time": "20:52:36", "remaining_time": "0:32:34"}
|
| 847 |
+
{"current_steps": 4235, "total_steps": 4340, "loss": 0.4127, "lr": 7.264135305127929e-08, "epoch": 6.830645161290323, "percentage": 97.58, "elapsed_time": "20:53:58", "remaining_time": "0:31:05"}
|
| 848 |
+
{"current_steps": 4240, "total_steps": 4340, "loss": 0.4004, "lr": 6.595370178200666e-08, "epoch": 6.838709677419355, "percentage": 97.7, "elapsed_time": "20:55:21", "remaining_time": "0:29:36"}
|
| 849 |
+
{"current_steps": 4245, "total_steps": 4340, "loss": 0.4128, "lr": 5.958843204375564e-08, "epoch": 6.846774193548387, "percentage": 97.81, "elapsed_time": "20:56:57", "remaining_time": "0:28:07"}
|
| 850 |
+
{"current_steps": 4250, "total_steps": 4340, "loss": 0.3928, "lr": 5.3545646778263575e-08, "epoch": 6.854838709677419, "percentage": 97.93, "elapsed_time": "20:58:15", "remaining_time": "0:26:38"}
|
| 851 |
+
{"current_steps": 4255, "total_steps": 4340, "loss": 0.3959, "lr": 4.782544371191966e-08, "epoch": 6.862903225806452, "percentage": 98.04, "elapsed_time": "20:59:50", "remaining_time": "0:25:10"}
|
| 852 |
+
{"current_steps": 4260, "total_steps": 4340, "loss": 0.3944, "lr": 4.242791535418178e-08, "epoch": 6.870967741935484, "percentage": 98.16, "elapsed_time": "21:01:09", "remaining_time": "0:23:41"}
|
| 853 |
+
{"current_steps": 4265, "total_steps": 4340, "loss": 0.3971, "lr": 3.7353148996084334e-08, "epoch": 6.879032258064516, "percentage": 98.27, "elapsed_time": "21:02:42", "remaining_time": "0:22:12"}
|
| 854 |
+
{"current_steps": 4270, "total_steps": 4340, "loss": 0.421, "lr": 3.260122670881494e-08, "epoch": 6.887096774193548, "percentage": 98.39, "elapsed_time": "21:04:02", "remaining_time": "0:20:43"}
|
| 855 |
+
{"current_steps": 4275, "total_steps": 4340, "loss": 0.4021, "lr": 2.817222534240438e-08, "epoch": 6.895161290322581, "percentage": 98.5, "elapsed_time": "21:05:34", "remaining_time": "0:19:14"}
|
| 856 |
+
{"current_steps": 4280, "total_steps": 4340, "loss": 0.3846, "lr": 2.4066216524465392e-08, "epoch": 6.903225806451613, "percentage": 98.62, "elapsed_time": "21:06:47", "remaining_time": "0:17:45"}
|
| 857 |
+
{"current_steps": 4285, "total_steps": 4340, "loss": 0.4039, "lr": 2.0283266659051338e-08, "epoch": 6.911290322580645, "percentage": 98.73, "elapsed_time": "21:08:11", "remaining_time": "0:16:16"}
|
| 858 |
+
{"current_steps": 4290, "total_steps": 4340, "loss": 0.3928, "lr": 1.6823436925572646e-08, "epoch": 6.919354838709677, "percentage": 98.85, "elapsed_time": "21:09:35", "remaining_time": "0:14:47"}
|
| 859 |
+
{"current_steps": 4295, "total_steps": 4340, "loss": 0.394, "lr": 1.368678327780204e-08, "epoch": 6.92741935483871, "percentage": 98.96, "elapsed_time": "21:10:58", "remaining_time": "0:13:18"}
|
| 860 |
+
{"current_steps": 4300, "total_steps": 4340, "loss": 0.4115, "lr": 1.0873356442986371e-08, "epoch": 6.935483870967742, "percentage": 99.08, "elapsed_time": "21:12:26", "remaining_time": "0:11:50"}
|
| 861 |
+
{"current_steps": 4305, "total_steps": 4340, "loss": 0.4021, "lr": 8.383201921011719e-09, "epoch": 6.943548387096774, "percentage": 99.19, "elapsed_time": "21:13:46", "remaining_time": "0:10:21"}
|
| 862 |
+
{"current_steps": 4310, "total_steps": 4340, "loss": 0.4092, "lr": 6.216359983675091e-09, "epoch": 6.951612903225806, "percentage": 99.31, "elapsed_time": "21:15:31", "remaining_time": "0:08:52"}
|
| 863 |
+
{"current_steps": 4315, "total_steps": 4340, "loss": 0.3977, "lr": 4.372865674024951e-09, "epoch": 6.959677419354839, "percentage": 99.42, "elapsed_time": "21:16:49", "remaining_time": "0:07:23"}
|
| 864 |
+
{"current_steps": 4320, "total_steps": 4340, "loss": 0.4098, "lr": 2.8527488058038844e-09, "epoch": 6.967741935483871, "percentage": 99.54, "elapsed_time": "21:18:06", "remaining_time": "0:05:55"}
|
| 865 |
+
{"current_steps": 4325, "total_steps": 4340, "loss": 0.4092, "lr": 1.6560339629645427e-09, "epoch": 6.975806451612903, "percentage": 99.65, "elapsed_time": "21:19:20", "remaining_time": "0:04:26"}
|
| 866 |
+
{"current_steps": 4330, "total_steps": 4340, "loss": 0.4078, "lr": 7.827404992655219e-10, "epoch": 6.983870967741936, "percentage": 99.77, "elapsed_time": "21:20:59", "remaining_time": "0:02:57"}
|
| 867 |
+
{"current_steps": 4335, "total_steps": 4340, "loss": 0.4116, "lr": 2.328825379649402e-10, "epoch": 6.991935483870968, "percentage": 99.88, "elapsed_time": "21:22:36", "remaining_time": "0:01:28"}
|
| 868 |
+
{"current_steps": 4340, "total_steps": 4340, "loss": 0.3971, "lr": 6.4689715939536544e-12, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "21:23:58", "remaining_time": "0:00:00"}
|
| 869 |
+
{"current_steps": 4340, "total_steps": 4340, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "21:25:16", "remaining_time": "0:00:00"}
|