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 sha256:8a5e6668492a507e31a64326c75dcdb25227e2fd72b49176fd78e745e0050f4f
|
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:de955dc4a87f3dff148775887fbf91e7a0a4b302076ab48b734eecdf3a3cccb7
|
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:a33d7b559882b97c227557525cb76c40a4443396fbfe971565acb55a17c849a8
|
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:d50615fb7aaabfb90553ca3cd704a19d8d11192f59c381c93ffd000268e82953
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -3,3 +3,8 @@
|
|
3 |
{"current_steps": 30, "total_steps": 126, "loss": 0.8882, "lr": 5e-06, "epoch": 0.7069219440353461, "percentage": 23.81, "elapsed_time": "1:17:41", "remaining_time": "4:08:35"}
|
4 |
{"current_steps": 40, "total_steps": 126, "loss": 0.8584, "lr": 5e-06, "epoch": 0.9425625920471281, "percentage": 31.75, "elapsed_time": "1:43:31", "remaining_time": "3:42:34"}
|
5 |
{"current_steps": 42, "total_steps": 126, "eval_loss": 0.8444611430168152, "epoch": 0.9896907216494846, "percentage": 33.33, "elapsed_time": "1:52:00", "remaining_time": "3:44:00"}
|
|
|
|
|
|
|
|
|
|
|
|
3 |
{"current_steps": 30, "total_steps": 126, "loss": 0.8882, "lr": 5e-06, "epoch": 0.7069219440353461, "percentage": 23.81, "elapsed_time": "1:17:41", "remaining_time": "4:08:35"}
|
4 |
{"current_steps": 40, "total_steps": 126, "loss": 0.8584, "lr": 5e-06, "epoch": 0.9425625920471281, "percentage": 31.75, "elapsed_time": "1:43:31", "remaining_time": "3:42:34"}
|
5 |
{"current_steps": 42, "total_steps": 126, "eval_loss": 0.8444611430168152, "epoch": 0.9896907216494846, "percentage": 33.33, "elapsed_time": "1:52:00", "remaining_time": "3:44:00"}
|
6 |
+
{"current_steps": 50, "total_steps": 126, "loss": 0.818, "lr": 5e-06, "epoch": 1.1782032400589102, "percentage": 39.68, "elapsed_time": "2:12:56", "remaining_time": "3:22:04"}
|
7 |
+
{"current_steps": 60, "total_steps": 126, "loss": 0.8015, "lr": 5e-06, "epoch": 1.413843888070692, "percentage": 47.62, "elapsed_time": "2:38:45", "remaining_time": "2:54:37"}
|
8 |
+
{"current_steps": 70, "total_steps": 126, "loss": 0.7916, "lr": 5e-06, "epoch": 1.6494845360824741, "percentage": 55.56, "elapsed_time": "3:04:35", "remaining_time": "2:27:40"}
|
9 |
+
{"current_steps": 80, "total_steps": 126, "loss": 0.785, "lr": 5e-06, "epoch": 1.8851251840942562, "percentage": 63.49, "elapsed_time": "3:30:24", "remaining_time": "2:00:58"}
|
10 |
+
{"current_steps": 84, "total_steps": 126, "eval_loss": 0.8053210973739624, "epoch": 1.9793814432989691, "percentage": 66.67, "elapsed_time": "3:45:09", "remaining_time": "1:52:34"}
|