Upload folder using huggingface_hub
Browse files- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- trainer_state.json +1263 -3
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4991459544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a239bd0e58246448c79b136afab824a8a9a6153ce17d8d6d113a2e318b3de72
|
| 3 |
size 4991459544
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4991757456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e1c690f2f36f7d22d9985346afe5114ce093d3af04d6ba6b3fb22d697c78864
|
| 3 |
size 4991757456
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4947691960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2759dd1a7d4b026c79bb5df907c7fe108df5d36ceb75f2082f8aa3202ce44bcf
|
| 3 |
size 4947691960
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1863387424
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ab61af589c217a86e226ecc839b1b369bd32759a3234e18b7cf254d273dabb3
|
| 3 |
size 1863387424
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 100000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -556,6 +556,1266 @@
|
|
| 556 |
"memory(GiB)": 75.3,
|
| 557 |
"step": 300,
|
| 558 |
"train_speed(iter/s)": 0.003347
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 559 |
}
|
| 560 |
],
|
| 561 |
"logging_steps": 5,
|
|
@@ -575,7 +1835,7 @@
|
|
| 575 |
"attributes": {}
|
| 576 |
}
|
| 577 |
},
|
| 578 |
-
"total_flos":
|
| 579 |
"train_batch_size": 2,
|
| 580 |
"trial_name": null,
|
| 581 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.942375227311212,
|
| 5 |
"eval_steps": 100000,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 556 |
"memory(GiB)": 75.3,
|
| 557 |
"step": 300,
|
| 558 |
"train_speed(iter/s)": 0.003347
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.2874244443299197,
|
| 562 |
+
"grad_norm": 0.91015625,
|
| 563 |
+
"learning_rate": 8.104190202580811e-06,
|
| 564 |
+
"loss": 0.05302551,
|
| 565 |
+
"memory(GiB)": 75.3,
|
| 566 |
+
"step": 305,
|
| 567 |
+
"train_speed(iter/s)": 0.003346
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.29213632046647575,
|
| 571 |
+
"grad_norm": 0.91796875,
|
| 572 |
+
"learning_rate": 8.045766202102358e-06,
|
| 573 |
+
"loss": 0.05804279,
|
| 574 |
+
"memory(GiB)": 75.3,
|
| 575 |
+
"step": 310,
|
| 576 |
+
"train_speed(iter/s)": 0.003346
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.2968481966030318,
|
| 580 |
+
"grad_norm": 0.9375,
|
| 581 |
+
"learning_rate": 7.986673370246743e-06,
|
| 582 |
+
"loss": 0.05822692,
|
| 583 |
+
"memory(GiB)": 75.3,
|
| 584 |
+
"step": 315,
|
| 585 |
+
"train_speed(iter/s)": 0.003346
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.30156007273958785,
|
| 589 |
+
"grad_norm": 1.0078125,
|
| 590 |
+
"learning_rate": 7.926924683433523e-06,
|
| 591 |
+
"loss": 0.06007032,
|
| 592 |
+
"memory(GiB)": 75.3,
|
| 593 |
+
"step": 320,
|
| 594 |
+
"train_speed(iter/s)": 0.003346
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.3062719488761439,
|
| 598 |
+
"grad_norm": 0.921875,
|
| 599 |
+
"learning_rate": 7.866533262103937e-06,
|
| 600 |
+
"loss": 0.06018423,
|
| 601 |
+
"memory(GiB)": 75.3,
|
| 602 |
+
"step": 325,
|
| 603 |
+
"train_speed(iter/s)": 0.003346
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.3109838250127,
|
| 607 |
+
"grad_norm": 0.9375,
|
| 608 |
+
"learning_rate": 7.805512367839742e-06,
|
| 609 |
+
"loss": 0.05931915,
|
| 610 |
+
"memory(GiB)": 75.3,
|
| 611 |
+
"step": 330,
|
| 612 |
+
"train_speed(iter/s)": 0.003346
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.31569570114925605,
|
| 616 |
+
"grad_norm": 1.015625,
|
| 617 |
+
"learning_rate": 7.743875400451047e-06,
|
| 618 |
+
"loss": 0.0566447,
|
| 619 |
+
"memory(GiB)": 75.3,
|
| 620 |
+
"step": 335,
|
| 621 |
+
"train_speed(iter/s)": 0.003346
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.3204075772858121,
|
| 625 |
+
"grad_norm": 0.8203125,
|
| 626 |
+
"learning_rate": 7.681635895033798e-06,
|
| 627 |
+
"loss": 0.05161901,
|
| 628 |
+
"memory(GiB)": 75.3,
|
| 629 |
+
"step": 340,
|
| 630 |
+
"train_speed(iter/s)": 0.003346
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.32511945342236814,
|
| 634 |
+
"grad_norm": 1.0,
|
| 635 |
+
"learning_rate": 7.6188075189975644e-06,
|
| 636 |
+
"loss": 0.05694907,
|
| 637 |
+
"memory(GiB)": 75.3,
|
| 638 |
+
"step": 345,
|
| 639 |
+
"train_speed(iter/s)": 0.003346
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.32983132955892425,
|
| 643 |
+
"grad_norm": 1.0390625,
|
| 644 |
+
"learning_rate": 7.555404069064245e-06,
|
| 645 |
+
"loss": 0.05555046,
|
| 646 |
+
"memory(GiB)": 75.3,
|
| 647 |
+
"step": 350,
|
| 648 |
+
"train_speed(iter/s)": 0.003347
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.3345432056954803,
|
| 652 |
+
"grad_norm": 0.97265625,
|
| 653 |
+
"learning_rate": 7.491439468238404e-06,
|
| 654 |
+
"loss": 0.05587023,
|
| 655 |
+
"memory(GiB)": 75.3,
|
| 656 |
+
"step": 355,
|
| 657 |
+
"train_speed(iter/s)": 0.003347
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.33925508183203634,
|
| 661 |
+
"grad_norm": 0.96875,
|
| 662 |
+
"learning_rate": 7.426927762749867e-06,
|
| 663 |
+
"loss": 0.05913154,
|
| 664 |
+
"memory(GiB)": 75.3,
|
| 665 |
+
"step": 360,
|
| 666 |
+
"train_speed(iter/s)": 0.003347
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.3439669579685924,
|
| 670 |
+
"grad_norm": 0.89453125,
|
| 671 |
+
"learning_rate": 7.361883118969248e-06,
|
| 672 |
+
"loss": 0.05830712,
|
| 673 |
+
"memory(GiB)": 75.3,
|
| 674 |
+
"step": 365,
|
| 675 |
+
"train_speed(iter/s)": 0.003348
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.34867883410514844,
|
| 679 |
+
"grad_norm": 0.89453125,
|
| 680 |
+
"learning_rate": 7.2963198202971055e-06,
|
| 681 |
+
"loss": 0.05937972,
|
| 682 |
+
"memory(GiB)": 75.3,
|
| 683 |
+
"step": 370,
|
| 684 |
+
"train_speed(iter/s)": 0.003348
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.35339071024170454,
|
| 688 |
+
"grad_norm": 0.9375,
|
| 689 |
+
"learning_rate": 7.230252264027398e-06,
|
| 690 |
+
"loss": 0.0565136,
|
| 691 |
+
"memory(GiB)": 75.3,
|
| 692 |
+
"step": 375,
|
| 693 |
+
"train_speed(iter/s)": 0.003348
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.3581025863782606,
|
| 697 |
+
"grad_norm": 0.96875,
|
| 698 |
+
"learning_rate": 7.163694958185928e-06,
|
| 699 |
+
"loss": 0.05636386,
|
| 700 |
+
"memory(GiB)": 75.3,
|
| 701 |
+
"step": 380,
|
| 702 |
+
"train_speed(iter/s)": 0.003348
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.36281446251481664,
|
| 706 |
+
"grad_norm": 0.96875,
|
| 707 |
+
"learning_rate": 7.09666251834447e-06,
|
| 708 |
+
"loss": 0.06038175,
|
| 709 |
+
"memory(GiB)": 75.3,
|
| 710 |
+
"step": 385,
|
| 711 |
+
"train_speed(iter/s)": 0.003348
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.3675263386513727,
|
| 715 |
+
"grad_norm": 0.92578125,
|
| 716 |
+
"learning_rate": 7.0291696644112705e-06,
|
| 717 |
+
"loss": 0.05833557,
|
| 718 |
+
"memory(GiB)": 75.3,
|
| 719 |
+
"step": 390,
|
| 720 |
+
"train_speed(iter/s)": 0.003349
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.3722382147879288,
|
| 724 |
+
"grad_norm": 0.8359375,
|
| 725 |
+
"learning_rate": 6.9612312173986675e-06,
|
| 726 |
+
"loss": 0.05632974,
|
| 727 |
+
"memory(GiB)": 75.3,
|
| 728 |
+
"step": 395,
|
| 729 |
+
"train_speed(iter/s)": 0.003348
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.37695009092448484,
|
| 733 |
+
"grad_norm": 0.921875,
|
| 734 |
+
"learning_rate": 6.892862096168469e-06,
|
| 735 |
+
"loss": 0.05656151,
|
| 736 |
+
"memory(GiB)": 75.3,
|
| 737 |
+
"step": 400,
|
| 738 |
+
"train_speed(iter/s)": 0.003348
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.3816619670610409,
|
| 742 |
+
"grad_norm": 0.98828125,
|
| 743 |
+
"learning_rate": 6.824077314155877e-06,
|
| 744 |
+
"loss": 0.05432441,
|
| 745 |
+
"memory(GiB)": 75.3,
|
| 746 |
+
"step": 405,
|
| 747 |
+
"train_speed(iter/s)": 0.003347
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.38637384319759693,
|
| 751 |
+
"grad_norm": 0.9453125,
|
| 752 |
+
"learning_rate": 6.75489197607262e-06,
|
| 753 |
+
"loss": 0.05709869,
|
| 754 |
+
"memory(GiB)": 75.3,
|
| 755 |
+
"step": 410,
|
| 756 |
+
"train_speed(iter/s)": 0.003347
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.391085719334153,
|
| 760 |
+
"grad_norm": 1.0546875,
|
| 761 |
+
"learning_rate": 6.6853212745900585e-06,
|
| 762 |
+
"loss": 0.05979726,
|
| 763 |
+
"memory(GiB)": 75.3,
|
| 764 |
+
"step": 415,
|
| 765 |
+
"train_speed(iter/s)": 0.003348
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.3957975954707091,
|
| 769 |
+
"grad_norm": 0.9140625,
|
| 770 |
+
"learning_rate": 6.615380487002969e-06,
|
| 771 |
+
"loss": 0.0600209,
|
| 772 |
+
"memory(GiB)": 75.3,
|
| 773 |
+
"step": 420,
|
| 774 |
+
"train_speed(iter/s)": 0.003348
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.40050947160726513,
|
| 778 |
+
"grad_norm": 0.94140625,
|
| 779 |
+
"learning_rate": 6.545084971874738e-06,
|
| 780 |
+
"loss": 0.0563777,
|
| 781 |
+
"memory(GiB)": 75.3,
|
| 782 |
+
"step": 425,
|
| 783 |
+
"train_speed(iter/s)": 0.003348
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.4052213477438212,
|
| 787 |
+
"grad_norm": 0.91796875,
|
| 788 |
+
"learning_rate": 6.474450165664722e-06,
|
| 789 |
+
"loss": 0.05698464,
|
| 790 |
+
"memory(GiB)": 75.3,
|
| 791 |
+
"step": 430,
|
| 792 |
+
"train_speed(iter/s)": 0.003348
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.40993322388037723,
|
| 796 |
+
"grad_norm": 0.890625,
|
| 797 |
+
"learning_rate": 6.4034915793385e-06,
|
| 798 |
+
"loss": 0.05311573,
|
| 799 |
+
"memory(GiB)": 75.3,
|
| 800 |
+
"step": 435,
|
| 801 |
+
"train_speed(iter/s)": 0.003348
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.41464510001693333,
|
| 805 |
+
"grad_norm": 0.97265625,
|
| 806 |
+
"learning_rate": 6.332224794961752e-06,
|
| 807 |
+
"loss": 0.05458606,
|
| 808 |
+
"memory(GiB)": 75.3,
|
| 809 |
+
"step": 440,
|
| 810 |
+
"train_speed(iter/s)": 0.003348
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.4193569761534894,
|
| 814 |
+
"grad_norm": 0.95703125,
|
| 815 |
+
"learning_rate": 6.260665462278544e-06,
|
| 816 |
+
"loss": 0.05579169,
|
| 817 |
+
"memory(GiB)": 75.3,
|
| 818 |
+
"step": 445,
|
| 819 |
+
"train_speed(iter/s)": 0.003348
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.42406885229004543,
|
| 823 |
+
"grad_norm": 0.99609375,
|
| 824 |
+
"learning_rate": 6.18882929527473e-06,
|
| 825 |
+
"loss": 0.06002288,
|
| 826 |
+
"memory(GiB)": 75.3,
|
| 827 |
+
"step": 450,
|
| 828 |
+
"train_speed(iter/s)": 0.003348
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.4287807284266015,
|
| 832 |
+
"grad_norm": 0.94140625,
|
| 833 |
+
"learning_rate": 6.116732068727271e-06,
|
| 834 |
+
"loss": 0.05494517,
|
| 835 |
+
"memory(GiB)": 75.3,
|
| 836 |
+
"step": 455,
|
| 837 |
+
"train_speed(iter/s)": 0.003349
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.4334926045631575,
|
| 841 |
+
"grad_norm": 0.953125,
|
| 842 |
+
"learning_rate": 6.0443896147401856e-06,
|
| 843 |
+
"loss": 0.0547879,
|
| 844 |
+
"memory(GiB)": 75.3,
|
| 845 |
+
"step": 460,
|
| 846 |
+
"train_speed(iter/s)": 0.003349
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.4382044806997136,
|
| 850 |
+
"grad_norm": 0.82421875,
|
| 851 |
+
"learning_rate": 5.971817819267914e-06,
|
| 852 |
+
"loss": 0.05363967,
|
| 853 |
+
"memory(GiB)": 75.3,
|
| 854 |
+
"step": 465,
|
| 855 |
+
"train_speed(iter/s)": 0.003348
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.4429163568362697,
|
| 859 |
+
"grad_norm": 0.91796875,
|
| 860 |
+
"learning_rate": 5.8990326186268655e-06,
|
| 861 |
+
"loss": 0.056594,
|
| 862 |
+
"memory(GiB)": 75.3,
|
| 863 |
+
"step": 470,
|
| 864 |
+
"train_speed(iter/s)": 0.003349
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.4476282329728257,
|
| 868 |
+
"grad_norm": 0.9765625,
|
| 869 |
+
"learning_rate": 5.826049995995905e-06,
|
| 870 |
+
"loss": 0.05898719,
|
| 871 |
+
"memory(GiB)": 75.3,
|
| 872 |
+
"step": 475,
|
| 873 |
+
"train_speed(iter/s)": 0.003349
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.45234010910938177,
|
| 877 |
+
"grad_norm": 1.3671875,
|
| 878 |
+
"learning_rate": 5.752885977906539e-06,
|
| 879 |
+
"loss": 0.05439388,
|
| 880 |
+
"memory(GiB)": 75.3,
|
| 881 |
+
"step": 480,
|
| 882 |
+
"train_speed(iter/s)": 0.003349
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.4570519852459379,
|
| 886 |
+
"grad_norm": 1.0390625,
|
| 887 |
+
"learning_rate": 5.679556630723592e-06,
|
| 888 |
+
"loss": 0.05334362,
|
| 889 |
+
"memory(GiB)": 75.3,
|
| 890 |
+
"step": 485,
|
| 891 |
+
"train_speed(iter/s)": 0.003349
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.4617638613824939,
|
| 895 |
+
"grad_norm": 0.9765625,
|
| 896 |
+
"learning_rate": 5.606078057117136e-06,
|
| 897 |
+
"loss": 0.06019425,
|
| 898 |
+
"memory(GiB)": 75.3,
|
| 899 |
+
"step": 490,
|
| 900 |
+
"train_speed(iter/s)": 0.003349
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.46647573751904997,
|
| 904 |
+
"grad_norm": 0.95703125,
|
| 905 |
+
"learning_rate": 5.532466392526439e-06,
|
| 906 |
+
"loss": 0.05597678,
|
| 907 |
+
"memory(GiB)": 75.3,
|
| 908 |
+
"step": 495,
|
| 909 |
+
"train_speed(iter/s)": 0.00335
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.471187613655606,
|
| 913 |
+
"grad_norm": 0.86328125,
|
| 914 |
+
"learning_rate": 5.458737801616721e-06,
|
| 915 |
+
"loss": 0.05094014,
|
| 916 |
+
"memory(GiB)": 75.3,
|
| 917 |
+
"step": 500,
|
| 918 |
+
"train_speed(iter/s)": 0.003349
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.47589948979216207,
|
| 922 |
+
"grad_norm": 0.875,
|
| 923 |
+
"learning_rate": 5.384908474729501e-06,
|
| 924 |
+
"loss": 0.0548723,
|
| 925 |
+
"memory(GiB)": 75.3,
|
| 926 |
+
"step": 505,
|
| 927 |
+
"train_speed(iter/s)": 0.003348
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.48061136592871817,
|
| 931 |
+
"grad_norm": 0.8984375,
|
| 932 |
+
"learning_rate": 5.310994624327292e-06,
|
| 933 |
+
"loss": 0.05574841,
|
| 934 |
+
"memory(GiB)": 75.3,
|
| 935 |
+
"step": 510,
|
| 936 |
+
"train_speed(iter/s)": 0.003348
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.4853232420652742,
|
| 940 |
+
"grad_norm": 0.8671875,
|
| 941 |
+
"learning_rate": 5.23701248143345e-06,
|
| 942 |
+
"loss": 0.05651059,
|
| 943 |
+
"memory(GiB)": 75.3,
|
| 944 |
+
"step": 515,
|
| 945 |
+
"train_speed(iter/s)": 0.003348
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.49003511820183027,
|
| 949 |
+
"grad_norm": 0.921875,
|
| 950 |
+
"learning_rate": 5.162978292067933e-06,
|
| 951 |
+
"loss": 0.05878415,
|
| 952 |
+
"memory(GiB)": 75.3,
|
| 953 |
+
"step": 520,
|
| 954 |
+
"train_speed(iter/s)": 0.003348
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.4947469943383863,
|
| 958 |
+
"grad_norm": 1.0234375,
|
| 959 |
+
"learning_rate": 5.088908313679788e-06,
|
| 960 |
+
"loss": 0.05620171,
|
| 961 |
+
"memory(GiB)": 75.3,
|
| 962 |
+
"step": 525,
|
| 963 |
+
"train_speed(iter/s)": 0.003348
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.49945887047494236,
|
| 967 |
+
"grad_norm": 0.86328125,
|
| 968 |
+
"learning_rate": 5.014818811577104e-06,
|
| 969 |
+
"loss": 0.05407885,
|
| 970 |
+
"memory(GiB)": 75.3,
|
| 971 |
+
"step": 530,
|
| 972 |
+
"train_speed(iter/s)": 0.003348
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 0.5041707466114984,
|
| 976 |
+
"grad_norm": 0.84375,
|
| 977 |
+
"learning_rate": 4.940726055355259e-06,
|
| 978 |
+
"loss": 0.05323058,
|
| 979 |
+
"memory(GiB)": 75.3,
|
| 980 |
+
"step": 535,
|
| 981 |
+
"train_speed(iter/s)": 0.003349
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.5088826227480545,
|
| 985 |
+
"grad_norm": 0.83984375,
|
| 986 |
+
"learning_rate": 4.866646315324217e-06,
|
| 987 |
+
"loss": 0.05346375,
|
| 988 |
+
"memory(GiB)": 75.3,
|
| 989 |
+
"step": 540,
|
| 990 |
+
"train_speed(iter/s)": 0.003349
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5135944988846106,
|
| 994 |
+
"grad_norm": 0.828125,
|
| 995 |
+
"learning_rate": 4.792595858935668e-06,
|
| 996 |
+
"loss": 0.05774211,
|
| 997 |
+
"memory(GiB)": 75.3,
|
| 998 |
+
"step": 545,
|
| 999 |
+
"train_speed(iter/s)": 0.003349
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.5183063750211666,
|
| 1003 |
+
"grad_norm": 0.9921875,
|
| 1004 |
+
"learning_rate": 4.718590947210788e-06,
|
| 1005 |
+
"loss": 0.05547717,
|
| 1006 |
+
"memory(GiB)": 75.3,
|
| 1007 |
+
"step": 550,
|
| 1008 |
+
"train_speed(iter/s)": 0.003349
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 0.5230182511577227,
|
| 1012 |
+
"grad_norm": 0.8046875,
|
| 1013 |
+
"learning_rate": 4.644647831169435e-06,
|
| 1014 |
+
"loss": 0.05536319,
|
| 1015 |
+
"memory(GiB)": 75.3,
|
| 1016 |
+
"step": 555,
|
| 1017 |
+
"train_speed(iter/s)": 0.003349
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.5277301272942787,
|
| 1021 |
+
"grad_norm": 1.015625,
|
| 1022 |
+
"learning_rate": 4.570782748261516e-06,
|
| 1023 |
+
"loss": 0.05369086,
|
| 1024 |
+
"memory(GiB)": 75.3,
|
| 1025 |
+
"step": 560,
|
| 1026 |
+
"train_speed(iter/s)": 0.003349
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.5324420034308348,
|
| 1030 |
+
"grad_norm": 0.94140625,
|
| 1031 |
+
"learning_rate": 4.497011918801347e-06,
|
| 1032 |
+
"loss": 0.05471834,
|
| 1033 |
+
"memory(GiB)": 75.3,
|
| 1034 |
+
"step": 565,
|
| 1035 |
+
"train_speed(iter/s)": 0.00335
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.5371538795673909,
|
| 1039 |
+
"grad_norm": 0.9140625,
|
| 1040 |
+
"learning_rate": 4.423351542405764e-06,
|
| 1041 |
+
"loss": 0.05114409,
|
| 1042 |
+
"memory(GiB)": 75.3,
|
| 1043 |
+
"step": 570,
|
| 1044 |
+
"train_speed(iter/s)": 0.00335
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.5418657557039469,
|
| 1048 |
+
"grad_norm": 0.9765625,
|
| 1049 |
+
"learning_rate": 4.349817794436805e-06,
|
| 1050 |
+
"loss": 0.05673685,
|
| 1051 |
+
"memory(GiB)": 75.3,
|
| 1052 |
+
"step": 575,
|
| 1053 |
+
"train_speed(iter/s)": 0.00335
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.546577631840503,
|
| 1057 |
+
"grad_norm": 0.88671875,
|
| 1058 |
+
"learning_rate": 4.276426822449682e-06,
|
| 1059 |
+
"loss": 0.05527523,
|
| 1060 |
+
"memory(GiB)": 75.3,
|
| 1061 |
+
"step": 580,
|
| 1062 |
+
"train_speed(iter/s)": 0.00335
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.551289507977059,
|
| 1066 |
+
"grad_norm": 0.90625,
|
| 1067 |
+
"learning_rate": 4.203194742646893e-06,
|
| 1068 |
+
"loss": 0.05317973,
|
| 1069 |
+
"memory(GiB)": 75.3,
|
| 1070 |
+
"step": 585,
|
| 1071 |
+
"train_speed(iter/s)": 0.00335
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.5560013841136151,
|
| 1075 |
+
"grad_norm": 1.0078125,
|
| 1076 |
+
"learning_rate": 4.130137636339191e-06,
|
| 1077 |
+
"loss": 0.05449303,
|
| 1078 |
+
"memory(GiB)": 75.3,
|
| 1079 |
+
"step": 590,
|
| 1080 |
+
"train_speed(iter/s)": 0.00335
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.5607132602501712,
|
| 1084 |
+
"grad_norm": 0.89453125,
|
| 1085 |
+
"learning_rate": 4.057271546414242e-06,
|
| 1086 |
+
"loss": 0.05341119,
|
| 1087 |
+
"memory(GiB)": 75.3,
|
| 1088 |
+
"step": 595,
|
| 1089 |
+
"train_speed(iter/s)": 0.00335
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.5654251363867272,
|
| 1093 |
+
"grad_norm": 0.8515625,
|
| 1094 |
+
"learning_rate": 3.984612473813689e-06,
|
| 1095 |
+
"loss": 0.05254069,
|
| 1096 |
+
"memory(GiB)": 75.3,
|
| 1097 |
+
"step": 600,
|
| 1098 |
+
"train_speed(iter/s)": 0.00335
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.5701370125232833,
|
| 1102 |
+
"grad_norm": 0.8984375,
|
| 1103 |
+
"learning_rate": 3.912176374019462e-06,
|
| 1104 |
+
"loss": 0.05324795,
|
| 1105 |
+
"memory(GiB)": 75.3,
|
| 1106 |
+
"step": 605,
|
| 1107 |
+
"train_speed(iter/s)": 0.00335
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.5748488886598394,
|
| 1111 |
+
"grad_norm": 0.8671875,
|
| 1112 |
+
"learning_rate": 3.839979153550039e-06,
|
| 1113 |
+
"loss": 0.05177047,
|
| 1114 |
+
"memory(GiB)": 75.3,
|
| 1115 |
+
"step": 610,
|
| 1116 |
+
"train_speed(iter/s)": 0.00335
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.5795607647963954,
|
| 1120 |
+
"grad_norm": 0.82421875,
|
| 1121 |
+
"learning_rate": 3.768036666467486e-06,
|
| 1122 |
+
"loss": 0.05265539,
|
| 1123 |
+
"memory(GiB)": 75.3,
|
| 1124 |
+
"step": 615,
|
| 1125 |
+
"train_speed(iter/s)": 0.00335
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.5842726409329515,
|
| 1129 |
+
"grad_norm": 0.88671875,
|
| 1130 |
+
"learning_rate": 3.6963647108959868e-06,
|
| 1131 |
+
"loss": 0.05418316,
|
| 1132 |
+
"memory(GiB)": 75.3,
|
| 1133 |
+
"step": 620,
|
| 1134 |
+
"train_speed(iter/s)": 0.00335
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.5889845170695075,
|
| 1138 |
+
"grad_norm": 0.93359375,
|
| 1139 |
+
"learning_rate": 3.6249790255526916e-06,
|
| 1140 |
+
"loss": 0.05562772,
|
| 1141 |
+
"memory(GiB)": 75.3,
|
| 1142 |
+
"step": 625,
|
| 1143 |
+
"train_speed(iter/s)": 0.00335
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.5936963932060636,
|
| 1147 |
+
"grad_norm": 0.90234375,
|
| 1148 |
+
"learning_rate": 3.553895286291577e-06,
|
| 1149 |
+
"loss": 0.05445199,
|
| 1150 |
+
"memory(GiB)": 75.3,
|
| 1151 |
+
"step": 630,
|
| 1152 |
+
"train_speed(iter/s)": 0.00335
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 0.5984082693426197,
|
| 1156 |
+
"grad_norm": 0.90234375,
|
| 1157 |
+
"learning_rate": 3.483129102661137e-06,
|
| 1158 |
+
"loss": 0.05333483,
|
| 1159 |
+
"memory(GiB)": 75.3,
|
| 1160 |
+
"step": 635,
|
| 1161 |
+
"train_speed(iter/s)": 0.00335
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.6031201454791757,
|
| 1165 |
+
"grad_norm": 0.8515625,
|
| 1166 |
+
"learning_rate": 3.4126960144766107e-06,
|
| 1167 |
+
"loss": 0.05417204,
|
| 1168 |
+
"memory(GiB)": 75.3,
|
| 1169 |
+
"step": 640,
|
| 1170 |
+
"train_speed(iter/s)": 0.00335
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.6078320216157318,
|
| 1174 |
+
"grad_norm": 0.91015625,
|
| 1175 |
+
"learning_rate": 3.3426114884075488e-06,
|
| 1176 |
+
"loss": 0.05412987,
|
| 1177 |
+
"memory(GiB)": 75.3,
|
| 1178 |
+
"step": 645,
|
| 1179 |
+
"train_speed(iter/s)": 0.00335
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6125438977522878,
|
| 1183 |
+
"grad_norm": 0.87109375,
|
| 1184 |
+
"learning_rate": 3.272890914581417e-06,
|
| 1185 |
+
"loss": 0.05388454,
|
| 1186 |
+
"memory(GiB)": 75.3,
|
| 1187 |
+
"step": 650,
|
| 1188 |
+
"train_speed(iter/s)": 0.003349
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.6172557738888439,
|
| 1192 |
+
"grad_norm": 0.85546875,
|
| 1193 |
+
"learning_rate": 3.2035496032040303e-06,
|
| 1194 |
+
"loss": 0.05097753,
|
| 1195 |
+
"memory(GiB)": 75.3,
|
| 1196 |
+
"step": 655,
|
| 1197 |
+
"train_speed(iter/s)": 0.003349
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.6219676500254,
|
| 1201 |
+
"grad_norm": 0.875,
|
| 1202 |
+
"learning_rate": 3.134602781197515e-06,
|
| 1203 |
+
"loss": 0.05341196,
|
| 1204 |
+
"memory(GiB)": 75.3,
|
| 1205 |
+
"step": 660,
|
| 1206 |
+
"train_speed(iter/s)": 0.00335
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.626679526161956,
|
| 1210 |
+
"grad_norm": 0.90625,
|
| 1211 |
+
"learning_rate": 3.0660655888565827e-06,
|
| 1212 |
+
"loss": 0.05016219,
|
| 1213 |
+
"memory(GiB)": 75.3,
|
| 1214 |
+
"step": 665,
|
| 1215 |
+
"train_speed(iter/s)": 0.00335
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.6313914022985121,
|
| 1219 |
+
"grad_norm": 0.95703125,
|
| 1220 |
+
"learning_rate": 2.997953076523803e-06,
|
| 1221 |
+
"loss": 0.05216441,
|
| 1222 |
+
"memory(GiB)": 75.3,
|
| 1223 |
+
"step": 670,
|
| 1224 |
+
"train_speed(iter/s)": 0.00335
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.6361032784350681,
|
| 1228 |
+
"grad_norm": 1.015625,
|
| 1229 |
+
"learning_rate": 2.930280201284654e-06,
|
| 1230 |
+
"loss": 0.05449665,
|
| 1231 |
+
"memory(GiB)": 75.3,
|
| 1232 |
+
"step": 675,
|
| 1233 |
+
"train_speed(iter/s)": 0.00335
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.6408151545716242,
|
| 1237 |
+
"grad_norm": 0.921875,
|
| 1238 |
+
"learning_rate": 2.863061823683032e-06,
|
| 1239 |
+
"loss": 0.05129569,
|
| 1240 |
+
"memory(GiB)": 75.3,
|
| 1241 |
+
"step": 680,
|
| 1242 |
+
"train_speed(iter/s)": 0.00335
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6455270307081803,
|
| 1246 |
+
"grad_norm": 0.87890625,
|
| 1247 |
+
"learning_rate": 2.7963127044579697e-06,
|
| 1248 |
+
"loss": 0.05290835,
|
| 1249 |
+
"memory(GiB)": 75.3,
|
| 1250 |
+
"step": 685,
|
| 1251 |
+
"train_speed(iter/s)": 0.00335
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.6502389068447363,
|
| 1255 |
+
"grad_norm": 0.87109375,
|
| 1256 |
+
"learning_rate": 2.7300475013022666e-06,
|
| 1257 |
+
"loss": 0.0528672,
|
| 1258 |
+
"memory(GiB)": 75.3,
|
| 1259 |
+
"step": 690,
|
| 1260 |
+
"train_speed(iter/s)": 0.00335
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 0.6549507829812924,
|
| 1264 |
+
"grad_norm": 0.984375,
|
| 1265 |
+
"learning_rate": 2.6642807656437565e-06,
|
| 1266 |
+
"loss": 0.05229232,
|
| 1267 |
+
"memory(GiB)": 75.3,
|
| 1268 |
+
"step": 695,
|
| 1269 |
+
"train_speed(iter/s)": 0.00335
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.6596626591178485,
|
| 1273 |
+
"grad_norm": 0.9609375,
|
| 1274 |
+
"learning_rate": 2.599026939449899e-06,
|
| 1275 |
+
"loss": 0.05371115,
|
| 1276 |
+
"memory(GiB)": 75.3,
|
| 1277 |
+
"step": 700,
|
| 1278 |
+
"train_speed(iter/s)": 0.00335
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 0.6643745352544045,
|
| 1282 |
+
"grad_norm": 1.0703125,
|
| 1283 |
+
"learning_rate": 2.534300352056416e-06,
|
| 1284 |
+
"loss": 0.05234203,
|
| 1285 |
+
"memory(GiB)": 75.3,
|
| 1286 |
+
"step": 705,
|
| 1287 |
+
"train_speed(iter/s)": 0.00335
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.6690864113909606,
|
| 1291 |
+
"grad_norm": 0.98828125,
|
| 1292 |
+
"learning_rate": 2.470115217020654e-06,
|
| 1293 |
+
"loss": 0.05360326,
|
| 1294 |
+
"memory(GiB)": 75.3,
|
| 1295 |
+
"step": 710,
|
| 1296 |
+
"train_speed(iter/s)": 0.00335
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 0.6737982875275166,
|
| 1300 |
+
"grad_norm": 0.92578125,
|
| 1301 |
+
"learning_rate": 2.4064856290003863e-06,
|
| 1302 |
+
"loss": 0.05475932,
|
| 1303 |
+
"memory(GiB)": 75.3,
|
| 1304 |
+
"step": 715,
|
| 1305 |
+
"train_speed(iter/s)": 0.00335
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.6785101636640727,
|
| 1309 |
+
"grad_norm": 1.0703125,
|
| 1310 |
+
"learning_rate": 2.3434255606586925e-06,
|
| 1311 |
+
"loss": 0.05548735,
|
| 1312 |
+
"memory(GiB)": 75.3,
|
| 1313 |
+
"step": 720,
|
| 1314 |
+
"train_speed(iter/s)": 0.00335
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.6832220398006288,
|
| 1318 |
+
"grad_norm": 0.89453125,
|
| 1319 |
+
"learning_rate": 2.2809488595956746e-06,
|
| 1320 |
+
"loss": 0.05201564,
|
| 1321 |
+
"memory(GiB)": 75.3,
|
| 1322 |
+
"step": 725,
|
| 1323 |
+
"train_speed(iter/s)": 0.00335
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.6879339159371848,
|
| 1327 |
+
"grad_norm": 0.9140625,
|
| 1328 |
+
"learning_rate": 2.219069245307589e-06,
|
| 1329 |
+
"loss": 0.05408272,
|
| 1330 |
+
"memory(GiB)": 75.3,
|
| 1331 |
+
"step": 730,
|
| 1332 |
+
"train_speed(iter/s)": 0.003351
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.6926457920737409,
|
| 1336 |
+
"grad_norm": 1.1640625,
|
| 1337 |
+
"learning_rate": 2.157800306174139e-06,
|
| 1338 |
+
"loss": 0.05537663,
|
| 1339 |
+
"memory(GiB)": 75.3,
|
| 1340 |
+
"step": 735,
|
| 1341 |
+
"train_speed(iter/s)": 0.003351
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.6973576682102969,
|
| 1345 |
+
"grad_norm": 1.125,
|
| 1346 |
+
"learning_rate": 2.0971554964745476e-06,
|
| 1347 |
+
"loss": 0.05455139,
|
| 1348 |
+
"memory(GiB)": 75.3,
|
| 1349 |
+
"step": 740,
|
| 1350 |
+
"train_speed(iter/s)": 0.003351
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.702069544346853,
|
| 1354 |
+
"grad_norm": 0.87890625,
|
| 1355 |
+
"learning_rate": 2.0371481334330913e-06,
|
| 1356 |
+
"loss": 0.05394316,
|
| 1357 |
+
"memory(GiB)": 75.3,
|
| 1358 |
+
"step": 745,
|
| 1359 |
+
"train_speed(iter/s)": 0.003351
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.7067814204834091,
|
| 1363 |
+
"grad_norm": 0.828125,
|
| 1364 |
+
"learning_rate": 1.9777913942946987e-06,
|
| 1365 |
+
"loss": 0.05269849,
|
| 1366 |
+
"memory(GiB)": 75.3,
|
| 1367 |
+
"step": 750,
|
| 1368 |
+
"train_speed(iter/s)": 0.003351
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7114932966199651,
|
| 1372 |
+
"grad_norm": 0.81640625,
|
| 1373 |
+
"learning_rate": 1.919098313431335e-06,
|
| 1374 |
+
"loss": 0.05057405,
|
| 1375 |
+
"memory(GiB)": 75.3,
|
| 1376 |
+
"step": 755,
|
| 1377 |
+
"train_speed(iter/s)": 0.003351
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.7162051727565212,
|
| 1381 |
+
"grad_norm": 0.9375,
|
| 1382 |
+
"learning_rate": 1.8610817794797164e-06,
|
| 1383 |
+
"loss": 0.05438253,
|
| 1384 |
+
"memory(GiB)": 75.3,
|
| 1385 |
+
"step": 760,
|
| 1386 |
+
"train_speed(iter/s)": 0.003351
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 0.7209170488930772,
|
| 1390 |
+
"grad_norm": 0.84375,
|
| 1391 |
+
"learning_rate": 1.8037545325110506e-06,
|
| 1392 |
+
"loss": 0.05222658,
|
| 1393 |
+
"memory(GiB)": 75.3,
|
| 1394 |
+
"step": 765,
|
| 1395 |
+
"train_speed(iter/s)": 0.003351
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.7256289250296333,
|
| 1399 |
+
"grad_norm": 0.88671875,
|
| 1400 |
+
"learning_rate": 1.7471291612333997e-06,
|
| 1401 |
+
"loss": 0.05131737,
|
| 1402 |
+
"memory(GiB)": 75.3,
|
| 1403 |
+
"step": 770,
|
| 1404 |
+
"train_speed(iter/s)": 0.003351
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 0.7303408011661894,
|
| 1408 |
+
"grad_norm": 0.93359375,
|
| 1409 |
+
"learning_rate": 1.6912181002272714e-06,
|
| 1410 |
+
"loss": 0.05391481,
|
| 1411 |
+
"memory(GiB)": 75.3,
|
| 1412 |
+
"step": 775,
|
| 1413 |
+
"train_speed(iter/s)": 0.003351
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.7350526773027454,
|
| 1417 |
+
"grad_norm": 0.8984375,
|
| 1418 |
+
"learning_rate": 1.6360336272150684e-06,
|
| 1419 |
+
"loss": 0.05078862,
|
| 1420 |
+
"memory(GiB)": 75.3,
|
| 1421 |
+
"step": 780,
|
| 1422 |
+
"train_speed(iter/s)": 0.003351
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 0.7397645534393015,
|
| 1426 |
+
"grad_norm": 0.953125,
|
| 1427 |
+
"learning_rate": 1.581587860364977e-06,
|
| 1428 |
+
"loss": 0.05192038,
|
| 1429 |
+
"memory(GiB)": 75.3,
|
| 1430 |
+
"step": 785,
|
| 1431 |
+
"train_speed(iter/s)": 0.003351
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7444764295758576,
|
| 1435 |
+
"grad_norm": 0.96875,
|
| 1436 |
+
"learning_rate": 1.52789275562988e-06,
|
| 1437 |
+
"loss": 0.05364103,
|
| 1438 |
+
"memory(GiB)": 75.3,
|
| 1439 |
+
"step": 790,
|
| 1440 |
+
"train_speed(iter/s)": 0.003351
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 0.7491883057124136,
|
| 1444 |
+
"grad_norm": 1.0625,
|
| 1445 |
+
"learning_rate": 1.4749601041219246e-06,
|
| 1446 |
+
"loss": 0.0536845,
|
| 1447 |
+
"memory(GiB)": 75.3,
|
| 1448 |
+
"step": 795,
|
| 1449 |
+
"train_speed(iter/s)": 0.003351
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.7539001818489697,
|
| 1453 |
+
"grad_norm": 0.90234375,
|
| 1454 |
+
"learning_rate": 1.4228015295232484e-06,
|
| 1455 |
+
"loss": 0.05084696,
|
| 1456 |
+
"memory(GiB)": 75.3,
|
| 1457 |
+
"step": 800,
|
| 1458 |
+
"train_speed(iter/s)": 0.003351
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.7586120579855257,
|
| 1462 |
+
"grad_norm": 0.875,
|
| 1463 |
+
"learning_rate": 1.371428485533498e-06,
|
| 1464 |
+
"loss": 0.05773014,
|
| 1465 |
+
"memory(GiB)": 75.3,
|
| 1466 |
+
"step": 805,
|
| 1467 |
+
"train_speed(iter/s)": 0.00335
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.7633239341220818,
|
| 1471 |
+
"grad_norm": 0.91796875,
|
| 1472 |
+
"learning_rate": 1.3208522533546748e-06,
|
| 1473 |
+
"loss": 0.05219783,
|
| 1474 |
+
"memory(GiB)": 75.3,
|
| 1475 |
+
"step": 810,
|
| 1476 |
+
"train_speed(iter/s)": 0.00335
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 0.7680358102586379,
|
| 1480 |
+
"grad_norm": 0.96875,
|
| 1481 |
+
"learning_rate": 1.2710839392138386e-06,
|
| 1482 |
+
"loss": 0.05375321,
|
| 1483 |
+
"memory(GiB)": 75.3,
|
| 1484 |
+
"step": 815,
|
| 1485 |
+
"train_speed(iter/s)": 0.00335
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.7727476863951939,
|
| 1489 |
+
"grad_norm": 0.87890625,
|
| 1490 |
+
"learning_rate": 1.222134471924259e-06,
|
| 1491 |
+
"loss": 0.05204231,
|
| 1492 |
+
"memory(GiB)": 75.3,
|
| 1493 |
+
"step": 820,
|
| 1494 |
+
"train_speed(iter/s)": 0.00335
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.77745956253175,
|
| 1498 |
+
"grad_norm": 0.91796875,
|
| 1499 |
+
"learning_rate": 1.1740146004855141e-06,
|
| 1500 |
+
"loss": 0.0559127,
|
| 1501 |
+
"memory(GiB)": 75.3,
|
| 1502 |
+
"step": 825,
|
| 1503 |
+
"train_speed(iter/s)": 0.003351
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.782171438668306,
|
| 1507 |
+
"grad_norm": 0.89453125,
|
| 1508 |
+
"learning_rate": 1.1267348917230737e-06,
|
| 1509 |
+
"loss": 0.05298336,
|
| 1510 |
+
"memory(GiB)": 75.3,
|
| 1511 |
+
"step": 830,
|
| 1512 |
+
"train_speed(iter/s)": 0.00335
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.7868833148048621,
|
| 1516 |
+
"grad_norm": 0.90625,
|
| 1517 |
+
"learning_rate": 1.080305727967893e-06,
|
| 1518 |
+
"loss": 0.05347639,
|
| 1519 |
+
"memory(GiB)": 75.3,
|
| 1520 |
+
"step": 835,
|
| 1521 |
+
"train_speed(iter/s)": 0.00335
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.7915951909414182,
|
| 1525 |
+
"grad_norm": 0.84765625,
|
| 1526 |
+
"learning_rate": 1.0347373047765202e-06,
|
| 1527 |
+
"loss": 0.05329442,
|
| 1528 |
+
"memory(GiB)": 75.3,
|
| 1529 |
+
"step": 840,
|
| 1530 |
+
"train_speed(iter/s)": 0.00335
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 0.7963070670779742,
|
| 1534 |
+
"grad_norm": 0.8359375,
|
| 1535 |
+
"learning_rate": 9.900396286922025e-07,
|
| 1536 |
+
"loss": 0.0537856,
|
| 1537 |
+
"memory(GiB)": 75.3,
|
| 1538 |
+
"step": 845,
|
| 1539 |
+
"train_speed(iter/s)": 0.00335
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.8010189432145303,
|
| 1543 |
+
"grad_norm": 0.8125,
|
| 1544 |
+
"learning_rate": 9.462225150475296e-07,
|
| 1545 |
+
"loss": 0.05233877,
|
| 1546 |
+
"memory(GiB)": 75.3,
|
| 1547 |
+
"step": 850,
|
| 1548 |
+
"train_speed(iter/s)": 0.00335
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 0.8057308193510863,
|
| 1552 |
+
"grad_norm": 0.88671875,
|
| 1553 |
+
"learning_rate": 9.032955858090319e-07,
|
| 1554 |
+
"loss": 0.0549244,
|
| 1555 |
+
"memory(GiB)": 75.3,
|
| 1556 |
+
"step": 855,
|
| 1557 |
+
"train_speed(iter/s)": 0.003351
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.8104426954876424,
|
| 1561 |
+
"grad_norm": 0.9140625,
|
| 1562 |
+
"learning_rate": 8.612682674642647e-07,
|
| 1563 |
+
"loss": 0.04935811,
|
| 1564 |
+
"memory(GiB)": 75.3,
|
| 1565 |
+
"step": 860,
|
| 1566 |
+
"train_speed(iter/s)": 0.003351
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 0.8151545716241985,
|
| 1570 |
+
"grad_norm": 0.921875,
|
| 1571 |
+
"learning_rate": 8.201497889518073e-07,
|
| 1572 |
+
"loss": 0.05281691,
|
| 1573 |
+
"memory(GiB)": 75.3,
|
| 1574 |
+
"step": 865,
|
| 1575 |
+
"train_speed(iter/s)": 0.003351
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.8198664477607545,
|
| 1579 |
+
"grad_norm": 0.90625,
|
| 1580 |
+
"learning_rate": 7.799491796346487e-07,
|
| 1581 |
+
"loss": 0.05795277,
|
| 1582 |
+
"memory(GiB)": 75.3,
|
| 1583 |
+
"step": 870,
|
| 1584 |
+
"train_speed(iter/s)": 0.003351
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.8245783238973106,
|
| 1588 |
+
"grad_norm": 0.8046875,
|
| 1589 |
+
"learning_rate": 7.406752673173851e-07,
|
| 1590 |
+
"loss": 0.05225162,
|
| 1591 |
+
"memory(GiB)": 75.3,
|
| 1592 |
+
"step": 875,
|
| 1593 |
+
"train_speed(iter/s)": 0.003351
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.8292902000338667,
|
| 1597 |
+
"grad_norm": 0.87890625,
|
| 1598 |
+
"learning_rate": 7.023366763077044e-07,
|
| 1599 |
+
"loss": 0.0509973,
|
| 1600 |
+
"memory(GiB)": 75.3,
|
| 1601 |
+
"step": 880,
|
| 1602 |
+
"train_speed(iter/s)": 0.003351
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 0.8340020761704227,
|
| 1606 |
+
"grad_norm": 0.87109375,
|
| 1607 |
+
"learning_rate": 6.649418255225298e-07,
|
| 1608 |
+
"loss": 0.05142277,
|
| 1609 |
+
"memory(GiB)": 75.3,
|
| 1610 |
+
"step": 885,
|
| 1611 |
+
"train_speed(iter/s)": 0.003351
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.8387139523069788,
|
| 1615 |
+
"grad_norm": 0.95703125,
|
| 1616 |
+
"learning_rate": 6.284989266392805e-07,
|
| 1617 |
+
"loss": 0.05023923,
|
| 1618 |
+
"memory(GiB)": 75.3,
|
| 1619 |
+
"step": 890,
|
| 1620 |
+
"train_speed(iter/s)": 0.003351
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.8434258284435348,
|
| 1624 |
+
"grad_norm": 0.8828125,
|
| 1625 |
+
"learning_rate": 5.930159822926407e-07,
|
| 1626 |
+
"loss": 0.0534648,
|
| 1627 |
+
"memory(GiB)": 75.3,
|
| 1628 |
+
"step": 895,
|
| 1629 |
+
"train_speed(iter/s)": 0.003351
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.8481377045800909,
|
| 1633 |
+
"grad_norm": 0.84375,
|
| 1634 |
+
"learning_rate": 5.585007843172286e-07,
|
| 1635 |
+
"loss": 0.05155768,
|
| 1636 |
+
"memory(GiB)": 75.3,
|
| 1637 |
+
"step": 900,
|
| 1638 |
+
"train_speed(iter/s)": 0.003351
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.852849580716647,
|
| 1642 |
+
"grad_norm": 0.9453125,
|
| 1643 |
+
"learning_rate": 5.249609120365579e-07,
|
| 1644 |
+
"loss": 0.05368913,
|
| 1645 |
+
"memory(GiB)": 75.3,
|
| 1646 |
+
"step": 905,
|
| 1647 |
+
"train_speed(iter/s)": 0.003351
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.857561456853203,
|
| 1651 |
+
"grad_norm": 0.859375,
|
| 1652 |
+
"learning_rate": 4.924037305986696e-07,
|
| 1653 |
+
"loss": 0.05452033,
|
| 1654 |
+
"memory(GiB)": 75.3,
|
| 1655 |
+
"step": 910,
|
| 1656 |
+
"train_speed(iter/s)": 0.003351
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 0.8622733329897591,
|
| 1660 |
+
"grad_norm": 0.8515625,
|
| 1661 |
+
"learning_rate": 4.6083638935878025e-07,
|
| 1662 |
+
"loss": 0.05384221,
|
| 1663 |
+
"memory(GiB)": 75.3,
|
| 1664 |
+
"step": 915,
|
| 1665 |
+
"train_speed(iter/s)": 0.003351
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.866985209126315,
|
| 1669 |
+
"grad_norm": 0.828125,
|
| 1670 |
+
"learning_rate": 4.302658203093418e-07,
|
| 1671 |
+
"loss": 0.05272598,
|
| 1672 |
+
"memory(GiB)": 75.3,
|
| 1673 |
+
"step": 920,
|
| 1674 |
+
"train_speed(iter/s)": 0.003351
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 0.8716970852628712,
|
| 1678 |
+
"grad_norm": 0.8671875,
|
| 1679 |
+
"learning_rate": 4.00698736557808e-07,
|
| 1680 |
+
"loss": 0.05447989,
|
| 1681 |
+
"memory(GiB)": 75.3,
|
| 1682 |
+
"step": 925,
|
| 1683 |
+
"train_speed(iter/s)": 0.003351
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.8764089613994273,
|
| 1687 |
+
"grad_norm": 0.9453125,
|
| 1688 |
+
"learning_rate": 3.721416308524839e-07,
|
| 1689 |
+
"loss": 0.05123619,
|
| 1690 |
+
"memory(GiB)": 75.3,
|
| 1691 |
+
"step": 930,
|
| 1692 |
+
"train_speed(iter/s)": 0.003351
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 0.8811208375359832,
|
| 1696 |
+
"grad_norm": 0.8515625,
|
| 1697 |
+
"learning_rate": 3.4460077415675473e-07,
|
| 1698 |
+
"loss": 0.05347574,
|
| 1699 |
+
"memory(GiB)": 75.3,
|
| 1700 |
+
"step": 935,
|
| 1701 |
+
"train_speed(iter/s)": 0.003351
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.8858327136725394,
|
| 1705 |
+
"grad_norm": 0.7890625,
|
| 1706 |
+
"learning_rate": 3.1808221427202636e-07,
|
| 1707 |
+
"loss": 0.05334803,
|
| 1708 |
+
"memory(GiB)": 75.3,
|
| 1709 |
+
"step": 940,
|
| 1710 |
+
"train_speed(iter/s)": 0.003351
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.8905445898090953,
|
| 1714 |
+
"grad_norm": 0.94921875,
|
| 1715 |
+
"learning_rate": 2.925917745096568e-07,
|
| 1716 |
+
"loss": 0.05249671,
|
| 1717 |
+
"memory(GiB)": 75.3,
|
| 1718 |
+
"step": 945,
|
| 1719 |
+
"train_speed(iter/s)": 0.003351
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.8952564659456514,
|
| 1723 |
+
"grad_norm": 0.91015625,
|
| 1724 |
+
"learning_rate": 2.681350524122045e-07,
|
| 1725 |
+
"loss": 0.05494893,
|
| 1726 |
+
"memory(GiB)": 75.3,
|
| 1727 |
+
"step": 950,
|
| 1728 |
+
"train_speed(iter/s)": 0.003351
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 0.8999683420822076,
|
| 1732 |
+
"grad_norm": 0.828125,
|
| 1733 |
+
"learning_rate": 2.447174185242324e-07,
|
| 1734 |
+
"loss": 0.05149726,
|
| 1735 |
+
"memory(GiB)": 75.3,
|
| 1736 |
+
"step": 955,
|
| 1737 |
+
"train_speed(iter/s)": 0.003351
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.9046802182187635,
|
| 1741 |
+
"grad_norm": 1.0859375,
|
| 1742 |
+
"learning_rate": 2.2234401521297576e-07,
|
| 1743 |
+
"loss": 0.05425293,
|
| 1744 |
+
"memory(GiB)": 75.3,
|
| 1745 |
+
"step": 960,
|
| 1746 |
+
"train_speed(iter/s)": 0.003351
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.9093920943553196,
|
| 1750 |
+
"grad_norm": 0.87109375,
|
| 1751 |
+
"learning_rate": 2.01019755539108e-07,
|
| 1752 |
+
"loss": 0.0552171,
|
| 1753 |
+
"memory(GiB)": 75.3,
|
| 1754 |
+
"step": 965,
|
| 1755 |
+
"train_speed(iter/s)": 0.003351
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 0.9141039704918758,
|
| 1759 |
+
"grad_norm": 0.84375,
|
| 1760 |
+
"learning_rate": 1.8074932217786445e-07,
|
| 1761 |
+
"loss": 0.05237709,
|
| 1762 |
+
"memory(GiB)": 75.3,
|
| 1763 |
+
"step": 970,
|
| 1764 |
+
"train_speed(iter/s)": 0.003351
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 0.9188158466284317,
|
| 1768 |
+
"grad_norm": 0.86328125,
|
| 1769 |
+
"learning_rate": 1.6153716639075223e-07,
|
| 1770 |
+
"loss": 0.05221198,
|
| 1771 |
+
"memory(GiB)": 75.3,
|
| 1772 |
+
"step": 975,
|
| 1773 |
+
"train_speed(iter/s)": 0.003351
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.9235277227649878,
|
| 1777 |
+
"grad_norm": 0.8125,
|
| 1778 |
+
"learning_rate": 1.433875070480878e-07,
|
| 1779 |
+
"loss": 0.05134506,
|
| 1780 |
+
"memory(GiB)": 75.3,
|
| 1781 |
+
"step": 980,
|
| 1782 |
+
"train_speed(iter/s)": 0.003352
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.9282395989015438,
|
| 1786 |
+
"grad_norm": 0.890625,
|
| 1787 |
+
"learning_rate": 1.2630432970255014e-07,
|
| 1788 |
+
"loss": 0.05436495,
|
| 1789 |
+
"memory(GiB)": 75.3,
|
| 1790 |
+
"step": 985,
|
| 1791 |
+
"train_speed(iter/s)": 0.003352
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.9329514750380999,
|
| 1795 |
+
"grad_norm": 0.921875,
|
| 1796 |
+
"learning_rate": 1.1029138571398645e-07,
|
| 1797 |
+
"loss": 0.05440986,
|
| 1798 |
+
"memory(GiB)": 75.3,
|
| 1799 |
+
"step": 990,
|
| 1800 |
+
"train_speed(iter/s)": 0.003352
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 0.937663351174656,
|
| 1804 |
+
"grad_norm": 0.91796875,
|
| 1805 |
+
"learning_rate": 9.535219142563168e-08,
|
| 1806 |
+
"loss": 0.05418127,
|
| 1807 |
+
"memory(GiB)": 75.3,
|
| 1808 |
+
"step": 995,
|
| 1809 |
+
"train_speed(iter/s)": 0.003352
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.942375227311212,
|
| 1813 |
+
"grad_norm": 0.8984375,
|
| 1814 |
+
"learning_rate": 8.149002739194222e-08,
|
| 1815 |
+
"loss": 0.05519557,
|
| 1816 |
+
"memory(GiB)": 75.3,
|
| 1817 |
+
"step": 1000,
|
| 1818 |
+
"train_speed(iter/s)": 0.003352
|
| 1819 |
}
|
| 1820 |
],
|
| 1821 |
"logging_steps": 5,
|
|
|
|
| 1835 |
"attributes": {}
|
| 1836 |
}
|
| 1837 |
},
|
| 1838 |
+
"total_flos": 5.440049406181114e+18,
|
| 1839 |
"train_batch_size": 2,
|
| 1840 |
"trial_name": null,
|
| 1841 |
"trial_params": null
|