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 sha256:18f97bbcfa94d2cc6e795b45d3a0991339e6a082d965f61997152912cae4de29
|
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 sha256:3adee6140ceca6c61540ad4452d789f4be8b0304cacb7109bfb9a0f7737fc2a4
|
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 sha256:919adedf7782cbc4faa2693498eb26839205f477dc00c1ec4063a64c3e93f105
|
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 sha256:07c423b92ed2336f48eaf1c91ee04662a33e8e2671b5a4ce69a8006dbe241c95
|
3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
@@ -2,3 +2,8 @@
|
|
2 |
{"current_steps": 20, "total_steps": 105, "loss": 1.0832, "lr": 5e-06, "epoch": 0.5653710247349824, "percentage": 19.05, "elapsed_time": "0:10:48", "remaining_time": "0:45:56"}
|
3 |
{"current_steps": 30, "total_steps": 105, "loss": 1.0481, "lr": 5e-06, "epoch": 0.8480565371024735, "percentage": 28.57, "elapsed_time": "0:16:10", "remaining_time": "0:40:25"}
|
4 |
{"current_steps": 35, "total_steps": 105, "eval_loss": 1.0256564617156982, "epoch": 0.9893992932862191, "percentage": 33.33, "elapsed_time": "0:19:24", "remaining_time": "0:38:48"}
|
|
|
|
|
|
|
|
|
|
|
|
2 |
{"current_steps": 20, "total_steps": 105, "loss": 1.0832, "lr": 5e-06, "epoch": 0.5653710247349824, "percentage": 19.05, "elapsed_time": "0:10:48", "remaining_time": "0:45:56"}
|
3 |
{"current_steps": 30, "total_steps": 105, "loss": 1.0481, "lr": 5e-06, "epoch": 0.8480565371024735, "percentage": 28.57, "elapsed_time": "0:16:10", "remaining_time": "0:40:25"}
|
4 |
{"current_steps": 35, "total_steps": 105, "eval_loss": 1.0256564617156982, "epoch": 0.9893992932862191, "percentage": 33.33, "elapsed_time": "0:19:24", "remaining_time": "0:38:48"}
|
5 |
+
{"current_steps": 40, "total_steps": 105, "loss": 1.092, "lr": 5e-06, "epoch": 1.1342756183745584, "percentage": 38.1, "elapsed_time": "0:23:05", "remaining_time": "0:37:32"}
|
6 |
+
{"current_steps": 50, "total_steps": 105, "loss": 0.9837, "lr": 5e-06, "epoch": 1.4169611307420495, "percentage": 47.62, "elapsed_time": "0:28:26", "remaining_time": "0:31:17"}
|
7 |
+
{"current_steps": 60, "total_steps": 105, "loss": 0.9671, "lr": 5e-06, "epoch": 1.6996466431095407, "percentage": 57.14, "elapsed_time": "0:33:45", "remaining_time": "0:25:19"}
|
8 |
+
{"current_steps": 70, "total_steps": 105, "loss": 0.9613, "lr": 5e-06, "epoch": 1.9823321554770317, "percentage": 66.67, "elapsed_time": "0:39:05", "remaining_time": "0:19:32"}
|
9 |
+
{"current_steps": 70, "total_steps": 105, "eval_loss": 0.9848190546035767, "epoch": 1.9823321554770317, "percentage": 66.67, "elapsed_time": "0:39:43", "remaining_time": "0:19:51"}
|