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:a0eb0ac17186104b9dbbfab1ad791036818bd9755389e2597d57abd674b80094
|
| 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:bb07289f5b023f7b076079d437ea388f109a13be03e1fd53dd23744348648311
|
| 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:dd62bdfe80fa5ab65593823a85c87b0b3a259665427eef1603a8e502b4dbe199
|
| 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 sha256:8778c36724c2f898298e1e3b23c3a7e8002762af9b657b84460a4f42474c7938
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -2,3 +2,7 @@
|
|
| 2 |
{"current_steps": 20, "total_steps": 87, "loss": 0.5008, "lr": 5e-06, "epoch": 0.6751054852320675, "percentage": 22.99, "elapsed_time": "0:19:16", "remaining_time": "1:04:32"}
|
| 3 |
{"current_steps": 29, "total_steps": 87, "eval_loss": 0.47183147072792053, "epoch": 0.9789029535864979, "percentage": 33.33, "elapsed_time": "0:28:54", "remaining_time": "0:57:49"}
|
| 4 |
{"current_steps": 30, "total_steps": 87, "loss": 0.4944, "lr": 5e-06, "epoch": 1.0168776371308017, "percentage": 34.48, "elapsed_time": "0:30:34", "remaining_time": "0:58:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
{"current_steps": 20, "total_steps": 87, "loss": 0.5008, "lr": 5e-06, "epoch": 0.6751054852320675, "percentage": 22.99, "elapsed_time": "0:19:16", "remaining_time": "1:04:32"}
|
| 3 |
{"current_steps": 29, "total_steps": 87, "eval_loss": 0.47183147072792053, "epoch": 0.9789029535864979, "percentage": 33.33, "elapsed_time": "0:28:54", "remaining_time": "0:57:49"}
|
| 4 |
{"current_steps": 30, "total_steps": 87, "loss": 0.4944, "lr": 5e-06, "epoch": 1.0168776371308017, "percentage": 34.48, "elapsed_time": "0:30:34", "remaining_time": "0:58:05"}
|
| 5 |
+
{"current_steps": 40, "total_steps": 87, "loss": 0.4423, "lr": 5e-06, "epoch": 1.3544303797468356, "percentage": 45.98, "elapsed_time": "0:40:09", "remaining_time": "0:47:11"}
|
| 6 |
+
{"current_steps": 50, "total_steps": 87, "loss": 0.4328, "lr": 5e-06, "epoch": 1.6919831223628692, "percentage": 57.47, "elapsed_time": "0:49:43", "remaining_time": "0:36:47"}
|
| 7 |
+
{"current_steps": 59, "total_steps": 87, "eval_loss": 0.44264522194862366, "epoch": 1.9957805907172996, "percentage": 67.82, "elapsed_time": "0:58:49", "remaining_time": "0:27:55"}
|
| 8 |
+
{"current_steps": 60, "total_steps": 87, "loss": 0.4452, "lr": 5e-06, "epoch": 2.0337552742616034, "percentage": 68.97, "elapsed_time": "1:00:59", "remaining_time": "0:27:26"}
|