Training in progress, epoch 1
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 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbd6f5d4fd89a11bf5edbd7ae4ea2220f0e73b67fad5f07166b23a3ef1132b4b
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68c191814a2ff0fc415b98df100ed95cb1cb37eacedf0616d6867747a138c22f
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9134586b467e212c5e74fc89286eeceac053527afeca6ef665525a6e185893a
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92a7f86b8357cd5059b9e93cd562b395cea20faf9dbf385365d9bb24255cbe79
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -4,3 +4,9 @@
|
|
4 |
{"current_steps": 40, "total_steps": 150, "loss": 0.6274, "lr": 5e-06, "epoch": 0.7980049875311721, "percentage": 26.67, "elapsed_time": "0:37:50", "remaining_time": "1:44:02"}
|
5 |
{"current_steps": 50, "total_steps": 150, "loss": 0.6123, "lr": 5e-06, "epoch": 0.9975062344139651, "percentage": 33.33, "elapsed_time": "0:47:15", "remaining_time": "1:34:31"}
|
6 |
{"current_steps": 50, "total_steps": 150, "eval_loss": 0.6066042184829712, "epoch": 0.9975062344139651, "percentage": 33.33, "elapsed_time": "0:48:16", "remaining_time": "1:36:32"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
{"current_steps": 40, "total_steps": 150, "loss": 0.6274, "lr": 5e-06, "epoch": 0.7980049875311721, "percentage": 26.67, "elapsed_time": "0:37:50", "remaining_time": "1:44:02"}
|
5 |
{"current_steps": 50, "total_steps": 150, "loss": 0.6123, "lr": 5e-06, "epoch": 0.9975062344139651, "percentage": 33.33, "elapsed_time": "0:47:15", "remaining_time": "1:34:31"}
|
6 |
{"current_steps": 50, "total_steps": 150, "eval_loss": 0.6066042184829712, "epoch": 0.9975062344139651, "percentage": 33.33, "elapsed_time": "0:48:16", "remaining_time": "1:36:32"}
|
7 |
+
{"current_steps": 60, "total_steps": 150, "loss": 0.6278, "lr": 5e-06, "epoch": 1.1970074812967582, "percentage": 40.0, "elapsed_time": "0:58:41", "remaining_time": "1:28:02"}
|
8 |
+
{"current_steps": 70, "total_steps": 150, "loss": 0.5677, "lr": 5e-06, "epoch": 1.3965087281795512, "percentage": 46.67, "elapsed_time": "1:08:07", "remaining_time": "1:17:51"}
|
9 |
+
{"current_steps": 80, "total_steps": 150, "loss": 0.5516, "lr": 5e-06, "epoch": 1.5960099750623442, "percentage": 53.33, "elapsed_time": "1:17:32", "remaining_time": "1:07:51"}
|
10 |
+
{"current_steps": 90, "total_steps": 150, "loss": 0.5397, "lr": 5e-06, "epoch": 1.7955112219451372, "percentage": 60.0, "elapsed_time": "1:26:57", "remaining_time": "0:57:58"}
|
11 |
+
{"current_steps": 100, "total_steps": 150, "loss": 0.5438, "lr": 5e-06, "epoch": 1.9950124688279303, "percentage": 66.67, "elapsed_time": "1:36:23", "remaining_time": "0:48:11"}
|
12 |
+
{"current_steps": 100, "total_steps": 150, "eval_loss": 0.5740869641304016, "epoch": 1.9950124688279303, "percentage": 66.67, "elapsed_time": "1:37:29", "remaining_time": "0:48:44"}
|