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:d79f7fdb4d30aca27223445594ef9b5b7ed91d20dd10692b892f84c2fd9e6ce2
|
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:f3ff35a79c27273836277e45fc2d8bfcc697433e7acf6bec5b015852659148db
|
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:c8d0711133bf8229ff230524c63ef3888ef7baf77747ef883dd24514f43369fd
|
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 sha256:488bac7d2cdcdccdf2f3be467b16592a0e7a2964211897c99322495182ea61cc
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -6,3 +6,8 @@
|
|
6 |
{"current_steps": 50, "total_steps": 93, "loss": 0.9873, "lr": 5e-06, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:28:05", "remaining_time": "0:24:09"}
|
7 |
{"current_steps": 60, "total_steps": 93, "loss": 0.9711, "lr": 5e-06, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:33:21", "remaining_time": "0:18:20"}
|
8 |
{"current_steps": 62, "total_steps": 93, "eval_loss": 0.9961642026901245, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "0:35:00", "remaining_time": "0:17:30"}
|
|
|
|
|
|
|
|
|
|
|
|
6 |
{"current_steps": 50, "total_steps": 93, "loss": 0.9873, "lr": 5e-06, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:28:05", "remaining_time": "0:24:09"}
|
7 |
{"current_steps": 60, "total_steps": 93, "loss": 0.9711, "lr": 5e-06, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:33:21", "remaining_time": "0:18:20"}
|
8 |
{"current_steps": 62, "total_steps": 93, "eval_loss": 0.9961642026901245, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "0:35:00", "remaining_time": "0:17:30"}
|
9 |
+
{"current_steps": 70, "total_steps": 93, "loss": 1.008, "lr": 5e-06, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "0:40:15", "remaining_time": "0:13:13"}
|
10 |
+
{"current_steps": 80, "total_steps": 93, "loss": 0.9094, "lr": 5e-06, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "0:45:31", "remaining_time": "0:07:23"}
|
11 |
+
{"current_steps": 90, "total_steps": 93, "loss": 0.9089, "lr": 5e-06, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "0:50:48", "remaining_time": "0:01:41"}
|
12 |
+
{"current_steps": 93, "total_steps": 93, "eval_loss": 0.9772511720657349, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:54:03", "remaining_time": "0:00:00"}
|
13 |
+
{"current_steps": 93, "total_steps": 93, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:55:16", "remaining_time": "0:00:00"}
|