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:d4570bec3b343db6c2115ce75a33dc5ac28667746d1dd513ec9dbc3a03ed369f
|
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 sha256:68ce070e4082d402ac2a5d398faf6d66a3255476448dccd8278f8b3b1042e78a
|
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:a68d504b1d72ede444d0a420f9f4752e7c4d9041488bc729df466dfd930c0d95
|
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 sha256:88802e26afbeb98ad537bbbe839fb171759a0b098f33c416b576498a72cce72e
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -4,3 +4,9 @@
|
|
4 |
{"current_steps": 40, "total_steps": 150, "loss": 0.6225, "lr": 5e-06, "epoch": 0.7980049875311721, "percentage": 26.67, "elapsed_time": "0:38:21", "remaining_time": "1:45:29"}
|
5 |
{"current_steps": 50, "total_steps": 150, "loss": 0.6165, "lr": 5e-06, "epoch": 0.9975062344139651, "percentage": 33.33, "elapsed_time": "0:47:56", "remaining_time": "1:35:52"}
|
6 |
{"current_steps": 50, "total_steps": 150, "eval_loss": 0.6011843085289001, "epoch": 0.9975062344139651, "percentage": 33.33, "elapsed_time": "0:48:57", "remaining_time": "1:37:55"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
{"current_steps": 40, "total_steps": 150, "loss": 0.6225, "lr": 5e-06, "epoch": 0.7980049875311721, "percentage": 26.67, "elapsed_time": "0:38:21", "remaining_time": "1:45:29"}
|
5 |
{"current_steps": 50, "total_steps": 150, "loss": 0.6165, "lr": 5e-06, "epoch": 0.9975062344139651, "percentage": 33.33, "elapsed_time": "0:47:56", "remaining_time": "1:35:52"}
|
6 |
{"current_steps": 50, "total_steps": 150, "eval_loss": 0.6011843085289001, "epoch": 0.9975062344139651, "percentage": 33.33, "elapsed_time": "0:48:57", "remaining_time": "1:37:55"}
|
7 |
+
{"current_steps": 60, "total_steps": 150, "loss": 0.6217, "lr": 5e-06, "epoch": 1.1970074812967582, "percentage": 40.0, "elapsed_time": "0:59:33", "remaining_time": "1:29:20"}
|
8 |
+
{"current_steps": 70, "total_steps": 150, "loss": 0.555, "lr": 5e-06, "epoch": 1.3965087281795512, "percentage": 46.67, "elapsed_time": "1:09:08", "remaining_time": "1:19:01"}
|
9 |
+
{"current_steps": 80, "total_steps": 150, "loss": 0.5496, "lr": 5e-06, "epoch": 1.5960099750623442, "percentage": 53.33, "elapsed_time": "1:18:43", "remaining_time": "1:08:52"}
|
10 |
+
{"current_steps": 90, "total_steps": 150, "loss": 0.5567, "lr": 5e-06, "epoch": 1.7955112219451372, "percentage": 60.0, "elapsed_time": "1:28:17", "remaining_time": "0:58:51"}
|
11 |
+
{"current_steps": 100, "total_steps": 150, "loss": 0.5416, "lr": 5e-06, "epoch": 1.9950124688279303, "percentage": 66.67, "elapsed_time": "1:37:52", "remaining_time": "0:48:56"}
|
12 |
+
{"current_steps": 100, "total_steps": 150, "eval_loss": 0.5647123456001282, "epoch": 1.9950124688279303, "percentage": 66.67, "elapsed_time": "1:39:00", "remaining_time": "0:49:30"}
|