Training in progress, epoch 2
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 sha256:963e698592c59d6fcf14666900a33e5ea7c692ee73674ca77c38e6b15b4ba061
|
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 sha256:11c0df444fb22c3642b7d62147f30fee37765a10a80f071501657bbca0261887
|
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 sha256:5757d9400da5fe575b082477195d8f370145f2694315fbc9e6330db126e0bc3c
|
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 sha256:6023648d2b947a8a6db2329541fd5d618118d5a5d243ef65fa507a3c991f340c
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -6,3 +6,8 @@
|
|
6 |
{"current_steps": 50, "total_steps": 96, "loss": 0.5098, "lr": 5e-06, "epoch": 1.5267175572519083, "percentage": 52.08, "elapsed_time": "0:28:31", "remaining_time": "0:26:14"}
|
7 |
{"current_steps": 60, "total_steps": 96, "loss": 0.4986, "lr": 5e-06, "epoch": 1.83206106870229, "percentage": 62.5, "elapsed_time": "0:33:52", "remaining_time": "0:20:19"}
|
8 |
{"current_steps": 65, "total_steps": 96, "eval_loss": 0.5270054340362549, "epoch": 1.984732824427481, "percentage": 67.71, "elapsed_time": "0:37:06", "remaining_time": "0:17:41"}
|
|
|
|
|
|
|
|
|
|
|
|
6 |
{"current_steps": 50, "total_steps": 96, "loss": 0.5098, "lr": 5e-06, "epoch": 1.5267175572519083, "percentage": 52.08, "elapsed_time": "0:28:31", "remaining_time": "0:26:14"}
|
7 |
{"current_steps": 60, "total_steps": 96, "loss": 0.4986, "lr": 5e-06, "epoch": 1.83206106870229, "percentage": 62.5, "elapsed_time": "0:33:52", "remaining_time": "0:20:19"}
|
8 |
{"current_steps": 65, "total_steps": 96, "eval_loss": 0.5270054340362549, "epoch": 1.984732824427481, "percentage": 67.71, "elapsed_time": "0:37:06", "remaining_time": "0:17:41"}
|
9 |
+
{"current_steps": 70, "total_steps": 96, "loss": 0.4818, "lr": 5e-06, "epoch": 2.1374045801526718, "percentage": 72.92, "elapsed_time": "0:40:50", "remaining_time": "0:15:10"}
|
10 |
+
{"current_steps": 80, "total_steps": 96, "loss": 0.4381, "lr": 5e-06, "epoch": 2.4427480916030535, "percentage": 83.33, "elapsed_time": "0:46:14", "remaining_time": "0:09:14"}
|
11 |
+
{"current_steps": 90, "total_steps": 96, "loss": 0.4286, "lr": 5e-06, "epoch": 2.7480916030534353, "percentage": 93.75, "elapsed_time": "0:51:37", "remaining_time": "0:03:26"}
|
12 |
+
{"current_steps": 96, "total_steps": 96, "eval_loss": 0.5195185542106628, "epoch": 2.931297709923664, "percentage": 100.0, "elapsed_time": "0:56:31", "remaining_time": "0:00:00"}
|
13 |
+
{"current_steps": 96, "total_steps": 96, "epoch": 2.931297709923664, "percentage": 100.0, "elapsed_time": "0:57:45", "remaining_time": "0:00:00"}
|