Upload folder using huggingface_hub
Browse files- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +1507 -7
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 738232680
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b1ef4f235714f8c3a5d95ec86fa6fa47c88ed5427ed6c71c86591e9edd44e12
|
| 3 |
size 738232680
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1476611275
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:057005316a733a2eca1390137d08c25f58fb7b120d45f27d2286547d3da06370
|
| 3 |
size 1476611275
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9f086fad67247c070127f3d5f3c07ca470a78f03c26cde9ec189b8223e059e7
|
| 3 |
size 14645
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5a7217cbf6a48b6118e1945e7a873ce9e9505368a7aa0f316b1becdcb2a8301
|
| 3 |
size 1465
|
trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "/content/drive/MyDrive/lora_model/outputs/task15_microsoft/Phi-4-mini-instruct/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 1,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2258,6 +2258,1506 @@
|
|
| 2258 |
"eval_samples_per_second": 8.883,
|
| 2259 |
"eval_steps_per_second": 1.184,
|
| 2260 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2261 |
}
|
| 2262 |
],
|
| 2263 |
"logging_steps": 1,
|
|
@@ -2272,12 +3772,12 @@
|
|
| 2272 |
"should_evaluate": false,
|
| 2273 |
"should_log": false,
|
| 2274 |
"should_save": true,
|
| 2275 |
-
"should_training_stop":
|
| 2276 |
},
|
| 2277 |
"attributes": {}
|
| 2278 |
}
|
| 2279 |
},
|
| 2280 |
-
"total_flos":
|
| 2281 |
"train_batch_size": 1,
|
| 2282 |
"trial_name": null,
|
| 2283 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 242,
|
| 3 |
+
"best_metric": 0.0005153545062057674,
|
| 4 |
+
"best_model_checkpoint": "/content/drive/MyDrive/lora_model/outputs/task15_microsoft/Phi-4-mini-instruct/checkpoint-240",
|
| 5 |
+
"epoch": 13.157894736842104,
|
| 6 |
"eval_steps": 1,
|
| 7 |
+
"global_step": 250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2258 |
"eval_samples_per_second": 8.883,
|
| 2259 |
"eval_steps_per_second": 1.184,
|
| 2260 |
"step": 150
|
| 2261 |
+
},
|
| 2262 |
+
{
|
| 2263 |
+
"epoch": 7.947368421052632,
|
| 2264 |
+
"grad_norm": 0.5821244120597839,
|
| 2265 |
+
"learning_rate": 0.00019204496243311792,
|
| 2266 |
+
"loss": 0.0634,
|
| 2267 |
+
"step": 151
|
| 2268 |
+
},
|
| 2269 |
+
{
|
| 2270 |
+
"epoch": 7.947368421052632,
|
| 2271 |
+
"eval_loss": 0.016822049394249916,
|
| 2272 |
+
"eval_runtime": 3.3726,
|
| 2273 |
+
"eval_samples_per_second": 8.895,
|
| 2274 |
+
"eval_steps_per_second": 1.186,
|
| 2275 |
+
"step": 151
|
| 2276 |
+
},
|
| 2277 |
+
{
|
| 2278 |
+
"epoch": 8.0,
|
| 2279 |
+
"grad_norm": 0.38316017389297485,
|
| 2280 |
+
"learning_rate": 0.00018879916191120349,
|
| 2281 |
+
"loss": 0.0422,
|
| 2282 |
+
"step": 152
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 8.0,
|
| 2286 |
+
"eval_loss": 0.013590247370302677,
|
| 2287 |
+
"eval_runtime": 3.3896,
|
| 2288 |
+
"eval_samples_per_second": 8.851,
|
| 2289 |
+
"eval_steps_per_second": 1.18,
|
| 2290 |
+
"step": 152
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 8.052631578947368,
|
| 2294 |
+
"grad_norm": 0.10196978598833084,
|
| 2295 |
+
"learning_rate": 0.00018556429881011656,
|
| 2296 |
+
"loss": 0.0059,
|
| 2297 |
+
"step": 153
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 8.052631578947368,
|
| 2301 |
+
"eval_loss": 0.013392569497227669,
|
| 2302 |
+
"eval_runtime": 3.3989,
|
| 2303 |
+
"eval_samples_per_second": 8.826,
|
| 2304 |
+
"eval_steps_per_second": 1.177,
|
| 2305 |
+
"step": 153
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 8.105263157894736,
|
| 2309 |
+
"grad_norm": 0.13090473413467407,
|
| 2310 |
+
"learning_rate": 0.0001823409512438203,
|
| 2311 |
+
"loss": 0.0097,
|
| 2312 |
+
"step": 154
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 8.105263157894736,
|
| 2316 |
+
"eval_loss": 0.013524877838790417,
|
| 2317 |
+
"eval_runtime": 3.4041,
|
| 2318 |
+
"eval_samples_per_second": 8.813,
|
| 2319 |
+
"eval_steps_per_second": 1.175,
|
| 2320 |
+
"step": 154
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 8.157894736842104,
|
| 2324 |
+
"grad_norm": 0.08641204982995987,
|
| 2325 |
+
"learning_rate": 0.00017912969526829559,
|
| 2326 |
+
"loss": 0.0046,
|
| 2327 |
+
"step": 155
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 8.157894736842104,
|
| 2331 |
+
"eval_loss": 0.014381513930857182,
|
| 2332 |
+
"eval_runtime": 3.4025,
|
| 2333 |
+
"eval_samples_per_second": 8.817,
|
| 2334 |
+
"eval_steps_per_second": 1.176,
|
| 2335 |
+
"step": 155
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 8.210526315789474,
|
| 2339 |
+
"grad_norm": 0.2780037522315979,
|
| 2340 |
+
"learning_rate": 0.00017593110477859153,
|
| 2341 |
+
"loss": 0.0212,
|
| 2342 |
+
"step": 156
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 8.210526315789474,
|
| 2346 |
+
"eval_loss": 0.01327499095350504,
|
| 2347 |
+
"eval_runtime": 3.3964,
|
| 2348 |
+
"eval_samples_per_second": 8.833,
|
| 2349 |
+
"eval_steps_per_second": 1.178,
|
| 2350 |
+
"step": 156
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 8.263157894736842,
|
| 2354 |
+
"grad_norm": 0.31865352392196655,
|
| 2355 |
+
"learning_rate": 0.00017274575140626317,
|
| 2356 |
+
"loss": 0.0212,
|
| 2357 |
+
"step": 157
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 8.263157894736842,
|
| 2361 |
+
"eval_loss": 0.012452797032892704,
|
| 2362 |
+
"eval_runtime": 3.3903,
|
| 2363 |
+
"eval_samples_per_second": 8.849,
|
| 2364 |
+
"eval_steps_per_second": 1.18,
|
| 2365 |
+
"step": 157
|
| 2366 |
+
},
|
| 2367 |
+
{
|
| 2368 |
+
"epoch": 8.31578947368421,
|
| 2369 |
+
"grad_norm": 0.35457736253738403,
|
| 2370 |
+
"learning_rate": 0.00016957420441721284,
|
| 2371 |
+
"loss": 0.0098,
|
| 2372 |
+
"step": 158
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 8.31578947368421,
|
| 2376 |
+
"eval_loss": 0.011020404286682606,
|
| 2377 |
+
"eval_runtime": 3.3806,
|
| 2378 |
+
"eval_samples_per_second": 8.874,
|
| 2379 |
+
"eval_steps_per_second": 1.183,
|
| 2380 |
+
"step": 158
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 8.368421052631579,
|
| 2384 |
+
"grad_norm": 0.3316934108734131,
|
| 2385 |
+
"learning_rate": 0.00016641703060995457,
|
| 2386 |
+
"loss": 0.022,
|
| 2387 |
+
"step": 159
|
| 2388 |
+
},
|
| 2389 |
+
{
|
| 2390 |
+
"epoch": 8.368421052631579,
|
| 2391 |
+
"eval_loss": 0.010090429335832596,
|
| 2392 |
+
"eval_runtime": 3.3847,
|
| 2393 |
+
"eval_samples_per_second": 8.863,
|
| 2394 |
+
"eval_steps_per_second": 1.182,
|
| 2395 |
+
"step": 159
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 8.421052631578947,
|
| 2399 |
+
"grad_norm": 0.2943498492240906,
|
| 2400 |
+
"learning_rate": 0.00016327479421431983,
|
| 2401 |
+
"loss": 0.0208,
|
| 2402 |
+
"step": 160
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 8.421052631578947,
|
| 2406 |
+
"eval_loss": 0.008338144980370998,
|
| 2407 |
+
"eval_runtime": 3.3812,
|
| 2408 |
+
"eval_samples_per_second": 8.872,
|
| 2409 |
+
"eval_steps_per_second": 1.183,
|
| 2410 |
+
"step": 160
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 8.473684210526315,
|
| 2414 |
+
"grad_norm": 0.2523714303970337,
|
| 2415 |
+
"learning_rate": 0.00016014805679062183,
|
| 2416 |
+
"loss": 0.017,
|
| 2417 |
+
"step": 161
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 8.473684210526315,
|
| 2421 |
+
"eval_loss": 0.007794048171490431,
|
| 2422 |
+
"eval_runtime": 3.379,
|
| 2423 |
+
"eval_samples_per_second": 8.878,
|
| 2424 |
+
"eval_steps_per_second": 1.184,
|
| 2425 |
+
"step": 161
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 8.526315789473685,
|
| 2429 |
+
"grad_norm": 0.45208269357681274,
|
| 2430 |
+
"learning_rate": 0.0001570373771292967,
|
| 2431 |
+
"loss": 0.0161,
|
| 2432 |
+
"step": 162
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 8.526315789473685,
|
| 2436 |
+
"eval_loss": 0.00768243195489049,
|
| 2437 |
+
"eval_runtime": 3.4065,
|
| 2438 |
+
"eval_samples_per_second": 8.807,
|
| 2439 |
+
"eval_steps_per_second": 1.174,
|
| 2440 |
+
"step": 162
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 8.578947368421053,
|
| 2444 |
+
"grad_norm": 0.20215876400470734,
|
| 2445 |
+
"learning_rate": 0.00015394331115104075,
|
| 2446 |
+
"loss": 0.0143,
|
| 2447 |
+
"step": 163
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 8.578947368421053,
|
| 2451 |
+
"eval_loss": 0.007556635420769453,
|
| 2452 |
+
"eval_runtime": 3.4167,
|
| 2453 |
+
"eval_samples_per_second": 8.78,
|
| 2454 |
+
"eval_steps_per_second": 1.171,
|
| 2455 |
+
"step": 163
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 8.631578947368421,
|
| 2459 |
+
"grad_norm": 0.4235493540763855,
|
| 2460 |
+
"learning_rate": 0.00015086641180745932,
|
| 2461 |
+
"loss": 0.02,
|
| 2462 |
+
"step": 164
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 8.631578947368421,
|
| 2466 |
+
"eval_loss": 0.008587359450757504,
|
| 2467 |
+
"eval_runtime": 3.4278,
|
| 2468 |
+
"eval_samples_per_second": 8.752,
|
| 2469 |
+
"eval_steps_per_second": 1.167,
|
| 2470 |
+
"step": 164
|
| 2471 |
+
},
|
| 2472 |
+
{
|
| 2473 |
+
"epoch": 8.68421052631579,
|
| 2474 |
+
"grad_norm": 0.3459453582763672,
|
| 2475 |
+
"learning_rate": 0.00014780722898224708,
|
| 2476 |
+
"loss": 0.0156,
|
| 2477 |
+
"step": 165
|
| 2478 |
+
},
|
| 2479 |
+
{
|
| 2480 |
+
"epoch": 8.68421052631579,
|
| 2481 |
+
"eval_loss": 0.009687132202088833,
|
| 2482 |
+
"eval_runtime": 3.4089,
|
| 2483 |
+
"eval_samples_per_second": 8.801,
|
| 2484 |
+
"eval_steps_per_second": 1.173,
|
| 2485 |
+
"step": 165
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"epoch": 8.736842105263158,
|
| 2489 |
+
"grad_norm": 0.46791887283325195,
|
| 2490 |
+
"learning_rate": 0.0001447663093929163,
|
| 2491 |
+
"loss": 0.0254,
|
| 2492 |
+
"step": 166
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 8.736842105263158,
|
| 2496 |
+
"eval_loss": 0.005360104609280825,
|
| 2497 |
+
"eval_runtime": 3.4012,
|
| 2498 |
+
"eval_samples_per_second": 8.82,
|
| 2499 |
+
"eval_steps_per_second": 1.176,
|
| 2500 |
+
"step": 166
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 8.789473684210526,
|
| 2504 |
+
"grad_norm": 0.32888978719711304,
|
| 2505 |
+
"learning_rate": 0.00014174419649309089,
|
| 2506 |
+
"loss": 0.0193,
|
| 2507 |
+
"step": 167
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 8.789473684210526,
|
| 2511 |
+
"eval_loss": 0.005120207089930773,
|
| 2512 |
+
"eval_runtime": 3.393,
|
| 2513 |
+
"eval_samples_per_second": 8.842,
|
| 2514 |
+
"eval_steps_per_second": 1.179,
|
| 2515 |
+
"step": 167
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 8.842105263157894,
|
| 2519 |
+
"grad_norm": 0.36381661891937256,
|
| 2520 |
+
"learning_rate": 0.00013874143037538418,
|
| 2521 |
+
"loss": 0.0115,
|
| 2522 |
+
"step": 168
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 8.842105263157894,
|
| 2526 |
+
"eval_loss": 0.005558122880756855,
|
| 2527 |
+
"eval_runtime": 3.397,
|
| 2528 |
+
"eval_samples_per_second": 8.831,
|
| 2529 |
+
"eval_steps_per_second": 1.178,
|
| 2530 |
+
"step": 168
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 8.894736842105264,
|
| 2534 |
+
"grad_norm": 0.15391984581947327,
|
| 2535 |
+
"learning_rate": 0.0001357585476748766,
|
| 2536 |
+
"loss": 0.0077,
|
| 2537 |
+
"step": 169
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 8.894736842105264,
|
| 2541 |
+
"eval_loss": 0.006869714241474867,
|
| 2542 |
+
"eval_runtime": 3.392,
|
| 2543 |
+
"eval_samples_per_second": 8.844,
|
| 2544 |
+
"eval_steps_per_second": 1.179,
|
| 2545 |
+
"step": 169
|
| 2546 |
+
},
|
| 2547 |
+
{
|
| 2548 |
+
"epoch": 8.947368421052632,
|
| 2549 |
+
"grad_norm": 0.3248370289802551,
|
| 2550 |
+
"learning_rate": 0.00013279608147321223,
|
| 2551 |
+
"loss": 0.0066,
|
| 2552 |
+
"step": 170
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 8.947368421052632,
|
| 2556 |
+
"eval_loss": 0.00868891179561615,
|
| 2557 |
+
"eval_runtime": 3.391,
|
| 2558 |
+
"eval_samples_per_second": 8.847,
|
| 2559 |
+
"eval_steps_per_second": 1.18,
|
| 2560 |
+
"step": 170
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 9.0,
|
| 2564 |
+
"grad_norm": 0.22031106054782867,
|
| 2565 |
+
"learning_rate": 0.00012985456120332905,
|
| 2566 |
+
"loss": 0.0103,
|
| 2567 |
+
"step": 171
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 9.0,
|
| 2571 |
+
"eval_loss": 0.009011917747557163,
|
| 2572 |
+
"eval_runtime": 3.3794,
|
| 2573 |
+
"eval_samples_per_second": 8.877,
|
| 2574 |
+
"eval_steps_per_second": 1.184,
|
| 2575 |
+
"step": 171
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"epoch": 9.052631578947368,
|
| 2579 |
+
"grad_norm": 0.19521355628967285,
|
| 2580 |
+
"learning_rate": 0.00012693451255484312,
|
| 2581 |
+
"loss": 0.0035,
|
| 2582 |
+
"step": 172
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 9.052631578947368,
|
| 2586 |
+
"eval_loss": 0.0076974560506641865,
|
| 2587 |
+
"eval_runtime": 3.3987,
|
| 2588 |
+
"eval_samples_per_second": 8.827,
|
| 2589 |
+
"eval_steps_per_second": 1.177,
|
| 2590 |
+
"step": 172
|
| 2591 |
+
},
|
| 2592 |
+
{
|
| 2593 |
+
"epoch": 9.105263157894736,
|
| 2594 |
+
"grad_norm": 0.22541294991970062,
|
| 2595 |
+
"learning_rate": 0.00012403645738009997,
|
| 2596 |
+
"loss": 0.0089,
|
| 2597 |
+
"step": 173
|
| 2598 |
+
},
|
| 2599 |
+
{
|
| 2600 |
+
"epoch": 9.105263157894736,
|
| 2601 |
+
"eval_loss": 0.004544786177575588,
|
| 2602 |
+
"eval_runtime": 3.41,
|
| 2603 |
+
"eval_samples_per_second": 8.798,
|
| 2604 |
+
"eval_steps_per_second": 1.173,
|
| 2605 |
+
"step": 173
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 9.157894736842104,
|
| 2609 |
+
"grad_norm": 0.1337708979845047,
|
| 2610 |
+
"learning_rate": 0.00012116091360091261,
|
| 2611 |
+
"loss": 0.005,
|
| 2612 |
+
"step": 174
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 9.157894736842104,
|
| 2616 |
+
"eval_loss": 0.0032975501380860806,
|
| 2617 |
+
"eval_runtime": 3.4164,
|
| 2618 |
+
"eval_samples_per_second": 8.781,
|
| 2619 |
+
"eval_steps_per_second": 1.171,
|
| 2620 |
+
"step": 174
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 9.210526315789474,
|
| 2624 |
+
"grad_norm": 0.08104129135608673,
|
| 2625 |
+
"learning_rate": 0.00011830839511600211,
|
| 2626 |
+
"loss": 0.0028,
|
| 2627 |
+
"step": 175
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 9.210526315789474,
|
| 2631 |
+
"eval_loss": 0.002934858202934265,
|
| 2632 |
+
"eval_runtime": 3.4116,
|
| 2633 |
+
"eval_samples_per_second": 8.793,
|
| 2634 |
+
"eval_steps_per_second": 1.172,
|
| 2635 |
+
"step": 175
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 9.263157894736842,
|
| 2639 |
+
"grad_norm": 0.03561758995056152,
|
| 2640 |
+
"learning_rate": 0.00011547941170915685,
|
| 2641 |
+
"loss": 0.0017,
|
| 2642 |
+
"step": 176
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 9.263157894736842,
|
| 2646 |
+
"eval_loss": 0.0032255654223263264,
|
| 2647 |
+
"eval_runtime": 3.4066,
|
| 2648 |
+
"eval_samples_per_second": 8.806,
|
| 2649 |
+
"eval_steps_per_second": 1.174,
|
| 2650 |
+
"step": 176
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 9.31578947368421,
|
| 2654 |
+
"grad_norm": 0.11387041211128235,
|
| 2655 |
+
"learning_rate": 0.00011267446895812702,
|
| 2656 |
+
"loss": 0.0044,
|
| 2657 |
+
"step": 177
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 9.31578947368421,
|
| 2661 |
+
"eval_loss": 0.003973633516579866,
|
| 2662 |
+
"eval_runtime": 3.4044,
|
| 2663 |
+
"eval_samples_per_second": 8.812,
|
| 2664 |
+
"eval_steps_per_second": 1.175,
|
| 2665 |
+
"step": 177
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 9.368421052631579,
|
| 2669 |
+
"grad_norm": 0.19635799527168274,
|
| 2670 |
+
"learning_rate": 0.0001098940681442713,
|
| 2671 |
+
"loss": 0.0085,
|
| 2672 |
+
"step": 178
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 9.368421052631579,
|
| 2676 |
+
"eval_loss": 0.004082486033439636,
|
| 2677 |
+
"eval_runtime": 3.3977,
|
| 2678 |
+
"eval_samples_per_second": 8.83,
|
| 2679 |
+
"eval_steps_per_second": 1.177,
|
| 2680 |
+
"step": 178
|
| 2681 |
+
},
|
| 2682 |
+
{
|
| 2683 |
+
"epoch": 9.421052631578947,
|
| 2684 |
+
"grad_norm": 0.16695837676525116,
|
| 2685 |
+
"learning_rate": 0.00010713870616297092,
|
| 2686 |
+
"loss": 0.0041,
|
| 2687 |
+
"step": 179
|
| 2688 |
+
},
|
| 2689 |
+
{
|
| 2690 |
+
"epoch": 9.421052631578947,
|
| 2691 |
+
"eval_loss": 0.004096930380910635,
|
| 2692 |
+
"eval_runtime": 3.3946,
|
| 2693 |
+
"eval_samples_per_second": 8.838,
|
| 2694 |
+
"eval_steps_per_second": 1.178,
|
| 2695 |
+
"step": 179
|
| 2696 |
+
},
|
| 2697 |
+
{
|
| 2698 |
+
"epoch": 9.473684210526315,
|
| 2699 |
+
"grad_norm": 0.10704478621482849,
|
| 2700 |
+
"learning_rate": 0.00010440887543482746,
|
| 2701 |
+
"loss": 0.0061,
|
| 2702 |
+
"step": 180
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 9.473684210526315,
|
| 2706 |
+
"eval_loss": 0.003820668673142791,
|
| 2707 |
+
"eval_runtime": 3.3815,
|
| 2708 |
+
"eval_samples_per_second": 8.872,
|
| 2709 |
+
"eval_steps_per_second": 1.183,
|
| 2710 |
+
"step": 180
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 9.526315789473685,
|
| 2714 |
+
"grad_norm": 0.15356966853141785,
|
| 2715 |
+
"learning_rate": 0.0001017050638176612,
|
| 2716 |
+
"loss": 0.0042,
|
| 2717 |
+
"step": 181
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 9.526315789473685,
|
| 2721 |
+
"eval_loss": 0.002816816559061408,
|
| 2722 |
+
"eval_runtime": 3.3759,
|
| 2723 |
+
"eval_samples_per_second": 8.887,
|
| 2724 |
+
"eval_steps_per_second": 1.185,
|
| 2725 |
+
"step": 181
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 9.578947368421053,
|
| 2729 |
+
"grad_norm": 0.14018815755844116,
|
| 2730 |
+
"learning_rate": 9.902775451932386e-05,
|
| 2731 |
+
"loss": 0.0035,
|
| 2732 |
+
"step": 182
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 9.578947368421053,
|
| 2736 |
+
"eval_loss": 0.0024158721789717674,
|
| 2737 |
+
"eval_runtime": 3.385,
|
| 2738 |
+
"eval_samples_per_second": 8.863,
|
| 2739 |
+
"eval_steps_per_second": 1.182,
|
| 2740 |
+
"step": 182
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 9.631578947368421,
|
| 2744 |
+
"grad_norm": 0.131745383143425,
|
| 2745 |
+
"learning_rate": 9.637742601134286e-05,
|
| 2746 |
+
"loss": 0.0072,
|
| 2747 |
+
"step": 183
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 9.631578947368421,
|
| 2751 |
+
"eval_loss": 0.002450426109135151,
|
| 2752 |
+
"eval_runtime": 3.42,
|
| 2753 |
+
"eval_samples_per_second": 8.772,
|
| 2754 |
+
"eval_steps_per_second": 1.17,
|
| 2755 |
+
"step": 183
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 9.68421052631579,
|
| 2759 |
+
"grad_norm": 0.1151895672082901,
|
| 2760 |
+
"learning_rate": 9.375455194341214e-05,
|
| 2761 |
+
"loss": 0.0036,
|
| 2762 |
+
"step": 184
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 9.68421052631579,
|
| 2766 |
+
"eval_loss": 0.0024695699103176594,
|
| 2767 |
+
"eval_runtime": 3.4266,
|
| 2768 |
+
"eval_samples_per_second": 8.755,
|
| 2769 |
+
"eval_steps_per_second": 1.167,
|
| 2770 |
+
"step": 184
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 9.736842105263158,
|
| 2774 |
+
"grad_norm": 0.10937950760126114,
|
| 2775 |
+
"learning_rate": 9.11596010587441e-05,
|
| 2776 |
+
"loss": 0.0069,
|
| 2777 |
+
"step": 185
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 9.736842105263158,
|
| 2781 |
+
"eval_loss": 0.002432518871501088,
|
| 2782 |
+
"eval_runtime": 3.412,
|
| 2783 |
+
"eval_samples_per_second": 8.792,
|
| 2784 |
+
"eval_steps_per_second": 1.172,
|
| 2785 |
+
"step": 185
|
| 2786 |
+
},
|
| 2787 |
+
{
|
| 2788 |
+
"epoch": 9.789473684210526,
|
| 2789 |
+
"grad_norm": 0.11447066813707352,
|
| 2790 |
+
"learning_rate": 8.85930371102994e-05,
|
| 2791 |
+
"loss": 0.009,
|
| 2792 |
+
"step": 186
|
| 2793 |
+
},
|
| 2794 |
+
{
|
| 2795 |
+
"epoch": 9.789473684210526,
|
| 2796 |
+
"eval_loss": 0.0024716572370380163,
|
| 2797 |
+
"eval_runtime": 3.4131,
|
| 2798 |
+
"eval_samples_per_second": 8.79,
|
| 2799 |
+
"eval_steps_per_second": 1.172,
|
| 2800 |
+
"step": 186
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"epoch": 9.842105263157894,
|
| 2804 |
+
"grad_norm": 0.17368115484714508,
|
| 2805 |
+
"learning_rate": 8.605531877790762e-05,
|
| 2806 |
+
"loss": 0.0049,
|
| 2807 |
+
"step": 187
|
| 2808 |
+
},
|
| 2809 |
+
{
|
| 2810 |
+
"epoch": 9.842105263157894,
|
| 2811 |
+
"eval_loss": 0.002253969432786107,
|
| 2812 |
+
"eval_runtime": 3.4001,
|
| 2813 |
+
"eval_samples_per_second": 8.823,
|
| 2814 |
+
"eval_steps_per_second": 1.176,
|
| 2815 |
+
"step": 187
|
| 2816 |
+
},
|
| 2817 |
+
{
|
| 2818 |
+
"epoch": 9.894736842105264,
|
| 2819 |
+
"grad_norm": 0.11908090114593506,
|
| 2820 |
+
"learning_rate": 8.354689958629513e-05,
|
| 2821 |
+
"loss": 0.0041,
|
| 2822 |
+
"step": 188
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 9.894736842105264,
|
| 2826 |
+
"eval_loss": 0.0017488420708104968,
|
| 2827 |
+
"eval_runtime": 3.3957,
|
| 2828 |
+
"eval_samples_per_second": 8.835,
|
| 2829 |
+
"eval_steps_per_second": 1.178,
|
| 2830 |
+
"step": 188
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 9.947368421052632,
|
| 2834 |
+
"grad_norm": 0.022854585200548172,
|
| 2835 |
+
"learning_rate": 8.106822782403376e-05,
|
| 2836 |
+
"loss": 0.0009,
|
| 2837 |
+
"step": 189
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 9.947368421052632,
|
| 2841 |
+
"eval_loss": 0.0015173099236562848,
|
| 2842 |
+
"eval_runtime": 3.3937,
|
| 2843 |
+
"eval_samples_per_second": 8.84,
|
| 2844 |
+
"eval_steps_per_second": 1.179,
|
| 2845 |
+
"step": 189
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 10.0,
|
| 2849 |
+
"grad_norm": 0.11229632049798965,
|
| 2850 |
+
"learning_rate": 7.861974646342596e-05,
|
| 2851 |
+
"loss": 0.0041,
|
| 2852 |
+
"step": 190
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 10.0,
|
| 2856 |
+
"eval_loss": 0.001307736849412322,
|
| 2857 |
+
"eval_runtime": 3.3916,
|
| 2858 |
+
"eval_samples_per_second": 8.845,
|
| 2859 |
+
"eval_steps_per_second": 1.179,
|
| 2860 |
+
"step": 190
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 10.052631578947368,
|
| 2864 |
+
"grad_norm": 0.015706708654761314,
|
| 2865 |
+
"learning_rate": 7.620189308133943e-05,
|
| 2866 |
+
"loss": 0.0009,
|
| 2867 |
+
"step": 191
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 10.052631578947368,
|
| 2871 |
+
"eval_loss": 0.0011787700932472944,
|
| 2872 |
+
"eval_runtime": 3.3762,
|
| 2873 |
+
"eval_samples_per_second": 8.886,
|
| 2874 |
+
"eval_steps_per_second": 1.185,
|
| 2875 |
+
"step": 191
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 10.105263157894736,
|
| 2879 |
+
"grad_norm": 0.019422335550189018,
|
| 2880 |
+
"learning_rate": 7.381509978100626e-05,
|
| 2881 |
+
"loss": 0.001,
|
| 2882 |
+
"step": 192
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 10.105263157894736,
|
| 2886 |
+
"eval_loss": 0.0011202039895579219,
|
| 2887 |
+
"eval_runtime": 3.394,
|
| 2888 |
+
"eval_samples_per_second": 8.839,
|
| 2889 |
+
"eval_steps_per_second": 1.179,
|
| 2890 |
+
"step": 192
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 10.157894736842104,
|
| 2894 |
+
"grad_norm": 0.04005387797951698,
|
| 2895 |
+
"learning_rate": 7.145979311479986e-05,
|
| 2896 |
+
"loss": 0.0019,
|
| 2897 |
+
"step": 193
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 10.157894736842104,
|
| 2901 |
+
"eval_loss": 0.001045590965077281,
|
| 2902 |
+
"eval_runtime": 3.4086,
|
| 2903 |
+
"eval_samples_per_second": 8.801,
|
| 2904 |
+
"eval_steps_per_second": 1.173,
|
| 2905 |
+
"step": 193
|
| 2906 |
+
},
|
| 2907 |
+
{
|
| 2908 |
+
"epoch": 10.210526315789474,
|
| 2909 |
+
"grad_norm": 0.04162440448999405,
|
| 2910 |
+
"learning_rate": 6.913639400800489e-05,
|
| 2911 |
+
"loss": 0.0014,
|
| 2912 |
+
"step": 194
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"epoch": 10.210526315789474,
|
| 2916 |
+
"eval_loss": 0.0009902982274070382,
|
| 2917 |
+
"eval_runtime": 3.4252,
|
| 2918 |
+
"eval_samples_per_second": 8.759,
|
| 2919 |
+
"eval_steps_per_second": 1.168,
|
| 2920 |
+
"step": 194
|
| 2921 |
+
},
|
| 2922 |
+
{
|
| 2923 |
+
"epoch": 10.263157894736842,
|
| 2924 |
+
"grad_norm": 0.013023920357227325,
|
| 2925 |
+
"learning_rate": 6.684531768359173e-05,
|
| 2926 |
+
"loss": 0.0007,
|
| 2927 |
+
"step": 195
|
| 2928 |
+
},
|
| 2929 |
+
{
|
| 2930 |
+
"epoch": 10.263157894736842,
|
| 2931 |
+
"eval_loss": 0.0009328785818070173,
|
| 2932 |
+
"eval_runtime": 3.4148,
|
| 2933 |
+
"eval_samples_per_second": 8.785,
|
| 2934 |
+
"eval_steps_per_second": 1.171,
|
| 2935 |
+
"step": 195
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 10.31578947368421,
|
| 2939 |
+
"grad_norm": 0.028714731335639954,
|
| 2940 |
+
"learning_rate": 6.458697358801061e-05,
|
| 2941 |
+
"loss": 0.0008,
|
| 2942 |
+
"step": 196
|
| 2943 |
+
},
|
| 2944 |
+
{
|
| 2945 |
+
"epoch": 10.31578947368421,
|
| 2946 |
+
"eval_loss": 0.0008854508632794023,
|
| 2947 |
+
"eval_runtime": 3.4076,
|
| 2948 |
+
"eval_samples_per_second": 8.804,
|
| 2949 |
+
"eval_steps_per_second": 1.174,
|
| 2950 |
+
"step": 196
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 10.368421052631579,
|
| 2954 |
+
"grad_norm": 0.010757100768387318,
|
| 2955 |
+
"learning_rate": 6.236176531801813e-05,
|
| 2956 |
+
"loss": 0.0006,
|
| 2957 |
+
"step": 197
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 10.368421052631579,
|
| 2961 |
+
"eval_loss": 0.0008607438649050891,
|
| 2962 |
+
"eval_runtime": 3.4022,
|
| 2963 |
+
"eval_samples_per_second": 8.818,
|
| 2964 |
+
"eval_steps_per_second": 1.176,
|
| 2965 |
+
"step": 197
|
| 2966 |
+
},
|
| 2967 |
+
{
|
| 2968 |
+
"epoch": 10.421052631578947,
|
| 2969 |
+
"grad_norm": 0.01270526647567749,
|
| 2970 |
+
"learning_rate": 6.017009054854858e-05,
|
| 2971 |
+
"loss": 0.0006,
|
| 2972 |
+
"step": 198
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 10.421052631578947,
|
| 2976 |
+
"eval_loss": 0.000837828207295388,
|
| 2977 |
+
"eval_runtime": 3.3979,
|
| 2978 |
+
"eval_samples_per_second": 8.829,
|
| 2979 |
+
"eval_steps_per_second": 1.177,
|
| 2980 |
+
"step": 198
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 10.473684210526315,
|
| 2984 |
+
"grad_norm": 0.023228133097290993,
|
| 2985 |
+
"learning_rate": 5.801234096164468e-05,
|
| 2986 |
+
"loss": 0.0015,
|
| 2987 |
+
"step": 199
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 10.473684210526315,
|
| 2991 |
+
"eval_loss": 0.0008206319180317223,
|
| 2992 |
+
"eval_runtime": 3.3763,
|
| 2993 |
+
"eval_samples_per_second": 8.885,
|
| 2994 |
+
"eval_steps_per_second": 1.185,
|
| 2995 |
+
"step": 199
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 10.526315789473685,
|
| 2999 |
+
"grad_norm": 0.05448168143630028,
|
| 3000 |
+
"learning_rate": 5.58889021764582e-05,
|
| 3001 |
+
"loss": 0.0016,
|
| 3002 |
+
"step": 200
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 10.526315789473685,
|
| 3006 |
+
"eval_loss": 0.0007741096196696162,
|
| 3007 |
+
"eval_runtime": 3.3873,
|
| 3008 |
+
"eval_samples_per_second": 8.857,
|
| 3009 |
+
"eval_steps_per_second": 1.181,
|
| 3010 |
+
"step": 200
|
| 3011 |
+
},
|
| 3012 |
+
{
|
| 3013 |
+
"epoch": 10.578947368421053,
|
| 3014 |
+
"grad_norm": 0.016489550471305847,
|
| 3015 |
+
"learning_rate": 5.3800153680334754e-05,
|
| 3016 |
+
"loss": 0.0007,
|
| 3017 |
+
"step": 201
|
| 3018 |
+
},
|
| 3019 |
+
{
|
| 3020 |
+
"epoch": 10.578947368421053,
|
| 3021 |
+
"eval_loss": 0.0007717728731222451,
|
| 3022 |
+
"eval_runtime": 3.3789,
|
| 3023 |
+
"eval_samples_per_second": 8.879,
|
| 3024 |
+
"eval_steps_per_second": 1.184,
|
| 3025 |
+
"step": 201
|
| 3026 |
+
},
|
| 3027 |
+
{
|
| 3028 |
+
"epoch": 10.631578947368421,
|
| 3029 |
+
"grad_norm": 0.012773360125720501,
|
| 3030 |
+
"learning_rate": 5.17464687609942e-05,
|
| 3031 |
+
"loss": 0.0009,
|
| 3032 |
+
"step": 202
|
| 3033 |
+
},
|
| 3034 |
+
{
|
| 3035 |
+
"epoch": 10.631578947368421,
|
| 3036 |
+
"eval_loss": 0.0007335889968089759,
|
| 3037 |
+
"eval_runtime": 3.3991,
|
| 3038 |
+
"eval_samples_per_second": 8.826,
|
| 3039 |
+
"eval_steps_per_second": 1.177,
|
| 3040 |
+
"step": 202
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 10.68421052631579,
|
| 3044 |
+
"grad_norm": 0.055602073669433594,
|
| 3045 |
+
"learning_rate": 4.97282144398192e-05,
|
| 3046 |
+
"loss": 0.0024,
|
| 3047 |
+
"step": 203
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 10.68421052631579,
|
| 3051 |
+
"eval_loss": 0.0007247411995194852,
|
| 3052 |
+
"eval_runtime": 3.4158,
|
| 3053 |
+
"eval_samples_per_second": 8.783,
|
| 3054 |
+
"eval_steps_per_second": 1.171,
|
| 3055 |
+
"step": 203
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 10.736842105263158,
|
| 3059 |
+
"grad_norm": 0.11499447375535965,
|
| 3060 |
+
"learning_rate": 4.7745751406263163e-05,
|
| 3061 |
+
"loss": 0.0079,
|
| 3062 |
+
"step": 204
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 10.736842105263158,
|
| 3066 |
+
"eval_loss": 0.0006966831278987229,
|
| 3067 |
+
"eval_runtime": 3.4204,
|
| 3068 |
+
"eval_samples_per_second": 8.771,
|
| 3069 |
+
"eval_steps_per_second": 1.169,
|
| 3070 |
+
"step": 204
|
| 3071 |
+
},
|
| 3072 |
+
{
|
| 3073 |
+
"epoch": 10.789473684210526,
|
| 3074 |
+
"grad_norm": 0.018082423135638237,
|
| 3075 |
+
"learning_rate": 4.5799433953390616e-05,
|
| 3076 |
+
"loss": 0.0008,
|
| 3077 |
+
"step": 205
|
| 3078 |
+
},
|
| 3079 |
+
{
|
| 3080 |
+
"epoch": 10.789473684210526,
|
| 3081 |
+
"eval_loss": 0.0006818302790634334,
|
| 3082 |
+
"eval_runtime": 3.4138,
|
| 3083 |
+
"eval_samples_per_second": 8.788,
|
| 3084 |
+
"eval_steps_per_second": 1.172,
|
| 3085 |
+
"step": 205
|
| 3086 |
+
},
|
| 3087 |
+
{
|
| 3088 |
+
"epoch": 10.842105263157894,
|
| 3089 |
+
"grad_norm": 0.00948310550302267,
|
| 3090 |
+
"learning_rate": 4.388960991455998e-05,
|
| 3091 |
+
"loss": 0.0005,
|
| 3092 |
+
"step": 206
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 10.842105263157894,
|
| 3096 |
+
"eval_loss": 0.0006638814229518175,
|
| 3097 |
+
"eval_runtime": 3.4095,
|
| 3098 |
+
"eval_samples_per_second": 8.799,
|
| 3099 |
+
"eval_steps_per_second": 1.173,
|
| 3100 |
+
"step": 206
|
| 3101 |
+
},
|
| 3102 |
+
{
|
| 3103 |
+
"epoch": 10.894736842105264,
|
| 3104 |
+
"grad_norm": 0.029851695522665977,
|
| 3105 |
+
"learning_rate": 4.2016620601260796e-05,
|
| 3106 |
+
"loss": 0.0012,
|
| 3107 |
+
"step": 207
|
| 3108 |
+
},
|
| 3109 |
+
{
|
| 3110 |
+
"epoch": 10.894736842105264,
|
| 3111 |
+
"eval_loss": 0.0006514237029477954,
|
| 3112 |
+
"eval_runtime": 3.4064,
|
| 3113 |
+
"eval_samples_per_second": 8.807,
|
| 3114 |
+
"eval_steps_per_second": 1.174,
|
| 3115 |
+
"step": 207
|
| 3116 |
+
},
|
| 3117 |
+
{
|
| 3118 |
+
"epoch": 10.947368421052632,
|
| 3119 |
+
"grad_norm": 0.00712271174415946,
|
| 3120 |
+
"learning_rate": 4.0180800742117244e-05,
|
| 3121 |
+
"loss": 0.0004,
|
| 3122 |
+
"step": 208
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"epoch": 10.947368421052632,
|
| 3126 |
+
"eval_loss": 0.0006477877032011747,
|
| 3127 |
+
"eval_runtime": 3.3956,
|
| 3128 |
+
"eval_samples_per_second": 8.835,
|
| 3129 |
+
"eval_steps_per_second": 1.178,
|
| 3130 |
+
"step": 208
|
| 3131 |
+
},
|
| 3132 |
+
{
|
| 3133 |
+
"epoch": 11.0,
|
| 3134 |
+
"grad_norm": 0.028429174795746803,
|
| 3135 |
+
"learning_rate": 3.838247842306716e-05,
|
| 3136 |
+
"loss": 0.0019,
|
| 3137 |
+
"step": 209
|
| 3138 |
+
},
|
| 3139 |
+
{
|
| 3140 |
+
"epoch": 11.0,
|
| 3141 |
+
"eval_loss": 0.0006293568876571953,
|
| 3142 |
+
"eval_runtime": 3.3933,
|
| 3143 |
+
"eval_samples_per_second": 8.841,
|
| 3144 |
+
"eval_steps_per_second": 1.179,
|
| 3145 |
+
"step": 209
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 11.052631578947368,
|
| 3149 |
+
"grad_norm": 0.006855803541839123,
|
| 3150 |
+
"learning_rate": 3.662197502872885e-05,
|
| 3151 |
+
"loss": 0.0004,
|
| 3152 |
+
"step": 210
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 11.052631578947368,
|
| 3156 |
+
"eval_loss": 0.0006222613155841827,
|
| 3157 |
+
"eval_runtime": 3.3927,
|
| 3158 |
+
"eval_samples_per_second": 8.843,
|
| 3159 |
+
"eval_steps_per_second": 1.179,
|
| 3160 |
+
"step": 210
|
| 3161 |
+
},
|
| 3162 |
+
{
|
| 3163 |
+
"epoch": 11.105263157894736,
|
| 3164 |
+
"grad_norm": 0.009028893895447254,
|
| 3165 |
+
"learning_rate": 3.489960518496521e-05,
|
| 3166 |
+
"loss": 0.0005,
|
| 3167 |
+
"step": 211
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 11.105263157894736,
|
| 3171 |
+
"eval_loss": 0.0006085150525905192,
|
| 3172 |
+
"eval_runtime": 3.3748,
|
| 3173 |
+
"eval_samples_per_second": 8.89,
|
| 3174 |
+
"eval_steps_per_second": 1.185,
|
| 3175 |
+
"step": 211
|
| 3176 |
+
},
|
| 3177 |
+
{
|
| 3178 |
+
"epoch": 11.157894736842104,
|
| 3179 |
+
"grad_norm": 0.02355123870074749,
|
| 3180 |
+
"learning_rate": 3.321567670265568e-05,
|
| 3181 |
+
"loss": 0.0015,
|
| 3182 |
+
"step": 212
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 11.157894736842104,
|
| 3186 |
+
"eval_loss": 0.000603480904828757,
|
| 3187 |
+
"eval_runtime": 3.3947,
|
| 3188 |
+
"eval_samples_per_second": 8.837,
|
| 3189 |
+
"eval_steps_per_second": 1.178,
|
| 3190 |
+
"step": 212
|
| 3191 |
+
},
|
| 3192 |
+
{
|
| 3193 |
+
"epoch": 11.210526315789474,
|
| 3194 |
+
"grad_norm": 0.011118754744529724,
|
| 3195 |
+
"learning_rate": 3.157049052268662e-05,
|
| 3196 |
+
"loss": 0.0005,
|
| 3197 |
+
"step": 213
|
| 3198 |
+
},
|
| 3199 |
+
{
|
| 3200 |
+
"epoch": 11.210526315789474,
|
| 3201 |
+
"eval_loss": 0.0005958045367151499,
|
| 3202 |
+
"eval_runtime": 3.4059,
|
| 3203 |
+
"eval_samples_per_second": 8.808,
|
| 3204 |
+
"eval_steps_per_second": 1.174,
|
| 3205 |
+
"step": 213
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 11.263157894736842,
|
| 3209 |
+
"grad_norm": 0.009967654012143612,
|
| 3210 |
+
"learning_rate": 2.9964340662168772e-05,
|
| 3211 |
+
"loss": 0.0005,
|
| 3212 |
+
"step": 214
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 11.263157894736842,
|
| 3216 |
+
"eval_loss": 0.0005862968391738832,
|
| 3217 |
+
"eval_runtime": 3.4249,
|
| 3218 |
+
"eval_samples_per_second": 8.759,
|
| 3219 |
+
"eval_steps_per_second": 1.168,
|
| 3220 |
+
"step": 214
|
| 3221 |
+
},
|
| 3222 |
+
{
|
| 3223 |
+
"epoch": 11.31578947368421,
|
| 3224 |
+
"grad_norm": 0.010085620917379856,
|
| 3225 |
+
"learning_rate": 2.8397514161892484e-05,
|
| 3226 |
+
"loss": 0.0006,
|
| 3227 |
+
"step": 215
|
| 3228 |
+
},
|
| 3229 |
+
{
|
| 3230 |
+
"epoch": 11.31578947368421,
|
| 3231 |
+
"eval_loss": 0.0005840694066137075,
|
| 3232 |
+
"eval_runtime": 3.4125,
|
| 3233 |
+
"eval_samples_per_second": 8.791,
|
| 3234 |
+
"eval_steps_per_second": 1.172,
|
| 3235 |
+
"step": 215
|
| 3236 |
+
},
|
| 3237 |
+
{
|
| 3238 |
+
"epoch": 11.368421052631579,
|
| 3239 |
+
"grad_norm": 0.010143388994038105,
|
| 3240 |
+
"learning_rate": 2.687029103502972e-05,
|
| 3241 |
+
"loss": 0.0006,
|
| 3242 |
+
"step": 216
|
| 3243 |
+
},
|
| 3244 |
+
{
|
| 3245 |
+
"epoch": 11.368421052631579,
|
| 3246 |
+
"eval_loss": 0.0005839812220074236,
|
| 3247 |
+
"eval_runtime": 3.4075,
|
| 3248 |
+
"eval_samples_per_second": 8.804,
|
| 3249 |
+
"eval_steps_per_second": 1.174,
|
| 3250 |
+
"step": 216
|
| 3251 |
+
},
|
| 3252 |
+
{
|
| 3253 |
+
"epoch": 11.421052631578947,
|
| 3254 |
+
"grad_norm": 0.019067654386162758,
|
| 3255 |
+
"learning_rate": 2.5382944217091723e-05,
|
| 3256 |
+
"loss": 0.0008,
|
| 3257 |
+
"step": 217
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 11.421052631578947,
|
| 3261 |
+
"eval_loss": 0.0005800244980491698,
|
| 3262 |
+
"eval_runtime": 3.4001,
|
| 3263 |
+
"eval_samples_per_second": 8.823,
|
| 3264 |
+
"eval_steps_per_second": 1.176,
|
| 3265 |
+
"step": 217
|
| 3266 |
+
},
|
| 3267 |
+
{
|
| 3268 |
+
"epoch": 11.473684210526315,
|
| 3269 |
+
"grad_norm": 0.007881615310907364,
|
| 3270 |
+
"learning_rate": 2.3935739517151916e-05,
|
| 3271 |
+
"loss": 0.0004,
|
| 3272 |
+
"step": 218
|
| 3273 |
+
},
|
| 3274 |
+
{
|
| 3275 |
+
"epoch": 11.473684210526315,
|
| 3276 |
+
"eval_loss": 0.0005629901424981654,
|
| 3277 |
+
"eval_runtime": 3.3819,
|
| 3278 |
+
"eval_samples_per_second": 8.871,
|
| 3279 |
+
"eval_steps_per_second": 1.183,
|
| 3280 |
+
"step": 218
|
| 3281 |
+
},
|
| 3282 |
+
{
|
| 3283 |
+
"epoch": 11.526315789473685,
|
| 3284 |
+
"grad_norm": 0.009564298205077648,
|
| 3285 |
+
"learning_rate": 2.2528935570342164e-05,
|
| 3286 |
+
"loss": 0.0006,
|
| 3287 |
+
"step": 219
|
| 3288 |
+
},
|
| 3289 |
+
{
|
| 3290 |
+
"epoch": 11.526315789473685,
|
| 3291 |
+
"eval_loss": 0.0005525622400455177,
|
| 3292 |
+
"eval_runtime": 3.3902,
|
| 3293 |
+
"eval_samples_per_second": 8.849,
|
| 3294 |
+
"eval_steps_per_second": 1.18,
|
| 3295 |
+
"step": 219
|
| 3296 |
+
},
|
| 3297 |
+
{
|
| 3298 |
+
"epoch": 11.578947368421053,
|
| 3299 |
+
"grad_norm": 0.0062964498065412045,
|
| 3300 |
+
"learning_rate": 2.1162783791631057e-05,
|
| 3301 |
+
"loss": 0.0004,
|
| 3302 |
+
"step": 220
|
| 3303 |
+
},
|
| 3304 |
+
{
|
| 3305 |
+
"epoch": 11.578947368421053,
|
| 3306 |
+
"eval_loss": 0.0005619211588054895,
|
| 3307 |
+
"eval_runtime": 3.3945,
|
| 3308 |
+
"eval_samples_per_second": 8.838,
|
| 3309 |
+
"eval_steps_per_second": 1.178,
|
| 3310 |
+
"step": 220
|
| 3311 |
+
},
|
| 3312 |
+
{
|
| 3313 |
+
"epoch": 11.631578947368421,
|
| 3314 |
+
"grad_norm": 0.008192476816475391,
|
| 3315 |
+
"learning_rate": 1.9837528330892778e-05,
|
| 3316 |
+
"loss": 0.0006,
|
| 3317 |
+
"step": 221
|
| 3318 |
+
},
|
| 3319 |
+
{
|
| 3320 |
+
"epoch": 11.631578947368421,
|
| 3321 |
+
"eval_loss": 0.0005546014290302992,
|
| 3322 |
+
"eval_runtime": 3.3765,
|
| 3323 |
+
"eval_samples_per_second": 8.885,
|
| 3324 |
+
"eval_steps_per_second": 1.185,
|
| 3325 |
+
"step": 221
|
| 3326 |
+
},
|
| 3327 |
+
{
|
| 3328 |
+
"epoch": 11.68421052631579,
|
| 3329 |
+
"grad_norm": 0.04483268782496452,
|
| 3330 |
+
"learning_rate": 1.8553406029274188e-05,
|
| 3331 |
+
"loss": 0.0018,
|
| 3332 |
+
"step": 222
|
| 3333 |
+
},
|
| 3334 |
+
{
|
| 3335 |
+
"epoch": 11.68421052631579,
|
| 3336 |
+
"eval_loss": 0.0005540356505662203,
|
| 3337 |
+
"eval_runtime": 3.396,
|
| 3338 |
+
"eval_samples_per_second": 8.834,
|
| 3339 |
+
"eval_steps_per_second": 1.178,
|
| 3340 |
+
"step": 222
|
| 3341 |
+
},
|
| 3342 |
+
{
|
| 3343 |
+
"epoch": 11.736842105263158,
|
| 3344 |
+
"grad_norm": 0.03096887841820717,
|
| 3345 |
+
"learning_rate": 1.7310646376867885e-05,
|
| 3346 |
+
"loss": 0.0014,
|
| 3347 |
+
"step": 223
|
| 3348 |
+
},
|
| 3349 |
+
{
|
| 3350 |
+
"epoch": 11.736842105263158,
|
| 3351 |
+
"eval_loss": 0.0005506525631062686,
|
| 3352 |
+
"eval_runtime": 3.4241,
|
| 3353 |
+
"eval_samples_per_second": 8.761,
|
| 3354 |
+
"eval_steps_per_second": 1.168,
|
| 3355 |
+
"step": 223
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 11.789473684210526,
|
| 3359 |
+
"grad_norm": 0.03000456467270851,
|
| 3360 |
+
"learning_rate": 1.6109471471699556e-05,
|
| 3361 |
+
"loss": 0.0012,
|
| 3362 |
+
"step": 224
|
| 3363 |
+
},
|
| 3364 |
+
{
|
| 3365 |
+
"epoch": 11.789473684210526,
|
| 3366 |
+
"eval_loss": 0.0005523088038899004,
|
| 3367 |
+
"eval_runtime": 3.4328,
|
| 3368 |
+
"eval_samples_per_second": 8.739,
|
| 3369 |
+
"eval_steps_per_second": 1.165,
|
| 3370 |
+
"step": 224
|
| 3371 |
+
},
|
| 3372 |
+
{
|
| 3373 |
+
"epoch": 11.842105263157894,
|
| 3374 |
+
"grad_norm": 0.053873490542173386,
|
| 3375 |
+
"learning_rate": 1.4950095980035772e-05,
|
| 3376 |
+
"loss": 0.0025,
|
| 3377 |
+
"step": 225
|
| 3378 |
+
},
|
| 3379 |
+
{
|
| 3380 |
+
"epoch": 11.842105263157894,
|
| 3381 |
+
"eval_loss": 0.0005435250350274146,
|
| 3382 |
+
"eval_runtime": 3.4151,
|
| 3383 |
+
"eval_samples_per_second": 8.784,
|
| 3384 |
+
"eval_steps_per_second": 1.171,
|
| 3385 |
+
"step": 225
|
| 3386 |
+
},
|
| 3387 |
+
{
|
| 3388 |
+
"epoch": 11.894736842105264,
|
| 3389 |
+
"grad_norm": 0.03556260094046593,
|
| 3390 |
+
"learning_rate": 1.3832727098020331e-05,
|
| 3391 |
+
"loss": 0.0013,
|
| 3392 |
+
"step": 226
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 11.894736842105264,
|
| 3396 |
+
"eval_loss": 0.0005410811281763017,
|
| 3397 |
+
"eval_runtime": 3.4083,
|
| 3398 |
+
"eval_samples_per_second": 8.802,
|
| 3399 |
+
"eval_steps_per_second": 1.174,
|
| 3400 |
+
"step": 226
|
| 3401 |
+
},
|
| 3402 |
+
{
|
| 3403 |
+
"epoch": 11.947368421052632,
|
| 3404 |
+
"grad_norm": 0.006391770672053099,
|
| 3405 |
+
"learning_rate": 1.2757564514645492e-05,
|
| 3406 |
+
"loss": 0.0004,
|
| 3407 |
+
"step": 227
|
| 3408 |
+
},
|
| 3409 |
+
{
|
| 3410 |
+
"epoch": 11.947368421052632,
|
| 3411 |
+
"eval_loss": 0.0005350796855054796,
|
| 3412 |
+
"eval_runtime": 3.3999,
|
| 3413 |
+
"eval_samples_per_second": 8.824,
|
| 3414 |
+
"eval_steps_per_second": 1.176,
|
| 3415 |
+
"step": 227
|
| 3416 |
+
},
|
| 3417 |
+
{
|
| 3418 |
+
"epoch": 12.0,
|
| 3419 |
+
"grad_norm": 0.007496091071516275,
|
| 3420 |
+
"learning_rate": 1.1724800376064798e-05,
|
| 3421 |
+
"loss": 0.0005,
|
| 3422 |
+
"step": 228
|
| 3423 |
+
},
|
| 3424 |
+
{
|
| 3425 |
+
"epoch": 12.0,
|
| 3426 |
+
"eval_loss": 0.0005355457542464137,
|
| 3427 |
+
"eval_runtime": 3.394,
|
| 3428 |
+
"eval_samples_per_second": 8.839,
|
| 3429 |
+
"eval_steps_per_second": 1.179,
|
| 3430 |
+
"step": 228
|
| 3431 |
+
},
|
| 3432 |
+
{
|
| 3433 |
+
"epoch": 12.052631578947368,
|
| 3434 |
+
"grad_norm": 0.006685596890747547,
|
| 3435 |
+
"learning_rate": 1.0734619251253963e-05,
|
| 3436 |
+
"loss": 0.0004,
|
| 3437 |
+
"step": 229
|
| 3438 |
+
},
|
| 3439 |
+
{
|
| 3440 |
+
"epoch": 12.052631578947368,
|
| 3441 |
+
"eval_loss": 0.0005336673348210752,
|
| 3442 |
+
"eval_runtime": 3.3873,
|
| 3443 |
+
"eval_samples_per_second": 8.857,
|
| 3444 |
+
"eval_steps_per_second": 1.181,
|
| 3445 |
+
"step": 229
|
| 3446 |
+
},
|
| 3447 |
+
{
|
| 3448 |
+
"epoch": 12.105263157894736,
|
| 3449 |
+
"grad_norm": 0.006534907501190901,
|
| 3450 |
+
"learning_rate": 9.78719809902598e-06,
|
| 3451 |
+
"loss": 0.0004,
|
| 3452 |
+
"step": 230
|
| 3453 |
+
},
|
| 3454 |
+
{
|
| 3455 |
+
"epoch": 12.105263157894736,
|
| 3456 |
+
"eval_loss": 0.0005313738365657628,
|
| 3457 |
+
"eval_runtime": 3.3913,
|
| 3458 |
+
"eval_samples_per_second": 8.846,
|
| 3459 |
+
"eval_steps_per_second": 1.179,
|
| 3460 |
+
"step": 230
|
| 3461 |
+
},
|
| 3462 |
+
{
|
| 3463 |
+
"epoch": 12.157894736842104,
|
| 3464 |
+
"grad_norm": 0.009226418100297451,
|
| 3465 |
+
"learning_rate": 8.882706236405884e-06,
|
| 3466 |
+
"loss": 0.0006,
|
| 3467 |
+
"step": 231
|
| 3468 |
+
},
|
| 3469 |
+
{
|
| 3470 |
+
"epoch": 12.157894736842104,
|
| 3471 |
+
"eval_loss": 0.0005278772441670299,
|
| 3472 |
+
"eval_runtime": 3.3771,
|
| 3473 |
+
"eval_samples_per_second": 8.883,
|
| 3474 |
+
"eval_steps_per_second": 1.184,
|
| 3475 |
+
"step": 231
|
| 3476 |
+
},
|
| 3477 |
+
{
|
| 3478 |
+
"epoch": 12.210526315789474,
|
| 3479 |
+
"grad_norm": 0.06117768958210945,
|
| 3480 |
+
"learning_rate": 8.02130530837189e-06,
|
| 3481 |
+
"loss": 0.0028,
|
| 3482 |
+
"step": 232
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 12.210526315789474,
|
| 3486 |
+
"eval_loss": 0.0005292578716762364,
|
| 3487 |
+
"eval_runtime": 3.3878,
|
| 3488 |
+
"eval_samples_per_second": 8.855,
|
| 3489 |
+
"eval_steps_per_second": 1.181,
|
| 3490 |
+
"step": 232
|
| 3491 |
+
},
|
| 3492 |
+
{
|
| 3493 |
+
"epoch": 12.263157894736842,
|
| 3494 |
+
"grad_norm": 0.007965135388076305,
|
| 3495 |
+
"learning_rate": 7.203149258967034e-06,
|
| 3496 |
+
"loss": 0.0005,
|
| 3497 |
+
"step": 233
|
| 3498 |
+
},
|
| 3499 |
+
{
|
| 3500 |
+
"epoch": 12.263157894736842,
|
| 3501 |
+
"eval_loss": 0.0005250571412034333,
|
| 3502 |
+
"eval_runtime": 3.4063,
|
| 3503 |
+
"eval_samples_per_second": 8.807,
|
| 3504 |
+
"eval_steps_per_second": 1.174,
|
| 3505 |
+
"step": 233
|
| 3506 |
+
},
|
| 3507 |
+
{
|
| 3508 |
+
"epoch": 12.31578947368421,
|
| 3509 |
+
"grad_norm": 0.03267819434404373,
|
| 3510 |
+
"learning_rate": 6.428384303787282e-06,
|
| 3511 |
+
"loss": 0.0012,
|
| 3512 |
+
"step": 234
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 12.31578947368421,
|
| 3516 |
+
"eval_loss": 0.0005264608189463615,
|
| 3517 |
+
"eval_runtime": 3.4112,
|
| 3518 |
+
"eval_samples_per_second": 8.795,
|
| 3519 |
+
"eval_steps_per_second": 1.173,
|
| 3520 |
+
"step": 234
|
| 3521 |
+
},
|
| 3522 |
+
{
|
| 3523 |
+
"epoch": 12.368421052631579,
|
| 3524 |
+
"grad_norm": 0.008882233873009682,
|
| 3525 |
+
"learning_rate": 5.697148903850868e-06,
|
| 3526 |
+
"loss": 0.0006,
|
| 3527 |
+
"step": 235
|
| 3528 |
+
},
|
| 3529 |
+
{
|
| 3530 |
+
"epoch": 12.368421052631579,
|
| 3531 |
+
"eval_loss": 0.0005261496989987791,
|
| 3532 |
+
"eval_runtime": 3.4163,
|
| 3533 |
+
"eval_samples_per_second": 8.781,
|
| 3534 |
+
"eval_steps_per_second": 1.171,
|
| 3535 |
+
"step": 235
|
| 3536 |
+
},
|
| 3537 |
+
{
|
| 3538 |
+
"epoch": 12.421052631578947,
|
| 3539 |
+
"grad_norm": 0.009687397629022598,
|
| 3540 |
+
"learning_rate": 5.009573740853312e-06,
|
| 3541 |
+
"loss": 0.0007,
|
| 3542 |
+
"step": 236
|
| 3543 |
+
},
|
| 3544 |
+
{
|
| 3545 |
+
"epoch": 12.421052631578947,
|
| 3546 |
+
"eval_loss": 0.0005241932813078165,
|
| 3547 |
+
"eval_runtime": 3.4093,
|
| 3548 |
+
"eval_samples_per_second": 8.8,
|
| 3549 |
+
"eval_steps_per_second": 1.173,
|
| 3550 |
+
"step": 236
|
| 3551 |
+
},
|
| 3552 |
+
{
|
| 3553 |
+
"epoch": 12.473684210526315,
|
| 3554 |
+
"grad_norm": 0.008641810156404972,
|
| 3555 |
+
"learning_rate": 4.365781693813048e-06,
|
| 3556 |
+
"loss": 0.0006,
|
| 3557 |
+
"step": 237
|
| 3558 |
+
},
|
| 3559 |
+
{
|
| 3560 |
+
"epoch": 12.473684210526315,
|
| 3561 |
+
"eval_loss": 0.0005225687636993825,
|
| 3562 |
+
"eval_runtime": 3.4036,
|
| 3563 |
+
"eval_samples_per_second": 8.814,
|
| 3564 |
+
"eval_steps_per_second": 1.175,
|
| 3565 |
+
"step": 237
|
| 3566 |
+
},
|
| 3567 |
+
{
|
| 3568 |
+
"epoch": 12.526315789473685,
|
| 3569 |
+
"grad_norm": 0.012136328965425491,
|
| 3570 |
+
"learning_rate": 3.765887817111069e-06,
|
| 3571 |
+
"loss": 0.0006,
|
| 3572 |
+
"step": 238
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 12.526315789473685,
|
| 3576 |
+
"eval_loss": 0.0005242796614766121,
|
| 3577 |
+
"eval_runtime": 3.3861,
|
| 3578 |
+
"eval_samples_per_second": 8.86,
|
| 3579 |
+
"eval_steps_per_second": 1.181,
|
| 3580 |
+
"step": 238
|
| 3581 |
+
},
|
| 3582 |
+
{
|
| 3583 |
+
"epoch": 12.578947368421053,
|
| 3584 |
+
"grad_norm": 0.005833880975842476,
|
| 3585 |
+
"learning_rate": 3.2099993199292688e-06,
|
| 3586 |
+
"loss": 0.0004,
|
| 3587 |
+
"step": 239
|
| 3588 |
+
},
|
| 3589 |
+
{
|
| 3590 |
+
"epoch": 12.578947368421053,
|
| 3591 |
+
"eval_loss": 0.0005251504480838776,
|
| 3592 |
+
"eval_runtime": 3.3792,
|
| 3593 |
+
"eval_samples_per_second": 8.878,
|
| 3594 |
+
"eval_steps_per_second": 1.184,
|
| 3595 |
+
"step": 239
|
| 3596 |
+
},
|
| 3597 |
+
{
|
| 3598 |
+
"epoch": 12.631578947368421,
|
| 3599 |
+
"grad_norm": 0.01102867815643549,
|
| 3600 |
+
"learning_rate": 2.698215547090599e-06,
|
| 3601 |
+
"loss": 0.0006,
|
| 3602 |
+
"step": 240
|
| 3603 |
+
},
|
| 3604 |
+
{
|
| 3605 |
+
"epoch": 12.631578947368421,
|
| 3606 |
+
"eval_loss": 0.0005198249127715826,
|
| 3607 |
+
"eval_runtime": 3.38,
|
| 3608 |
+
"eval_samples_per_second": 8.876,
|
| 3609 |
+
"eval_steps_per_second": 1.183,
|
| 3610 |
+
"step": 240
|
| 3611 |
+
},
|
| 3612 |
+
{
|
| 3613 |
+
"epoch": 12.68421052631579,
|
| 3614 |
+
"grad_norm": 0.02008400671184063,
|
| 3615 |
+
"learning_rate": 2.230627961304993e-06,
|
| 3616 |
+
"loss": 0.0011,
|
| 3617 |
+
"step": 241
|
| 3618 |
+
},
|
| 3619 |
+
{
|
| 3620 |
+
"epoch": 12.68421052631579,
|
| 3621 |
+
"eval_loss": 0.0005216759163886309,
|
| 3622 |
+
"eval_runtime": 3.3907,
|
| 3623 |
+
"eval_samples_per_second": 8.848,
|
| 3624 |
+
"eval_steps_per_second": 1.18,
|
| 3625 |
+
"step": 241
|
| 3626 |
+
},
|
| 3627 |
+
{
|
| 3628 |
+
"epoch": 12.736842105263158,
|
| 3629 |
+
"grad_norm": 0.033516351133584976,
|
| 3630 |
+
"learning_rate": 1.807320126823414e-06,
|
| 3631 |
+
"loss": 0.0014,
|
| 3632 |
+
"step": 242
|
| 3633 |
+
},
|
| 3634 |
+
{
|
| 3635 |
+
"epoch": 12.736842105263158,
|
| 3636 |
+
"eval_loss": 0.0005153545062057674,
|
| 3637 |
+
"eval_runtime": 3.4033,
|
| 3638 |
+
"eval_samples_per_second": 8.815,
|
| 3639 |
+
"eval_steps_per_second": 1.175,
|
| 3640 |
+
"step": 242
|
| 3641 |
+
},
|
| 3642 |
+
{
|
| 3643 |
+
"epoch": 12.789473684210526,
|
| 3644 |
+
"grad_norm": 0.0054031675681471825,
|
| 3645 |
+
"learning_rate": 1.4283676945041346e-06,
|
| 3646 |
+
"loss": 0.0003,
|
| 3647 |
+
"step": 243
|
| 3648 |
+
},
|
| 3649 |
+
{
|
| 3650 |
+
"epoch": 12.789473684210526,
|
| 3651 |
+
"eval_loss": 0.000516153231728822,
|
| 3652 |
+
"eval_runtime": 3.4157,
|
| 3653 |
+
"eval_samples_per_second": 8.783,
|
| 3654 |
+
"eval_steps_per_second": 1.171,
|
| 3655 |
+
"step": 243
|
| 3656 |
+
},
|
| 3657 |
+
{
|
| 3658 |
+
"epoch": 12.842105263157894,
|
| 3659 |
+
"grad_norm": 0.026906250044703484,
|
| 3660 |
+
"learning_rate": 1.0938383882926617e-06,
|
| 3661 |
+
"loss": 0.0009,
|
| 3662 |
+
"step": 244
|
| 3663 |
+
},
|
| 3664 |
+
{
|
| 3665 |
+
"epoch": 12.842105263157894,
|
| 3666 |
+
"eval_loss": 0.0005240263999439776,
|
| 3667 |
+
"eval_runtime": 3.4082,
|
| 3668 |
+
"eval_samples_per_second": 8.802,
|
| 3669 |
+
"eval_steps_per_second": 1.174,
|
| 3670 |
+
"step": 244
|
| 3671 |
+
},
|
| 3672 |
+
{
|
| 3673 |
+
"epoch": 12.894736842105264,
|
| 3674 |
+
"grad_norm": 0.006174022331833839,
|
| 3675 |
+
"learning_rate": 8.037919931187243e-07,
|
| 3676 |
+
"loss": 0.0003,
|
| 3677 |
+
"step": 245
|
| 3678 |
+
},
|
| 3679 |
+
{
|
| 3680 |
+
"epoch": 12.894736842105264,
|
| 3681 |
+
"eval_loss": 0.0005176598788239062,
|
| 3682 |
+
"eval_runtime": 3.409,
|
| 3683 |
+
"eval_samples_per_second": 8.8,
|
| 3684 |
+
"eval_steps_per_second": 1.173,
|
| 3685 |
+
"step": 245
|
| 3686 |
+
},
|
| 3687 |
+
{
|
| 3688 |
+
"epoch": 12.947368421052632,
|
| 3689 |
+
"grad_norm": 0.032558590173721313,
|
| 3690 |
+
"learning_rate": 5.582803442117091e-07,
|
| 3691 |
+
"loss": 0.0011,
|
| 3692 |
+
"step": 246
|
| 3693 |
+
},
|
| 3694 |
+
{
|
| 3695 |
+
"epoch": 12.947368421052632,
|
| 3696 |
+
"eval_loss": 0.0005180027801543474,
|
| 3697 |
+
"eval_runtime": 3.4063,
|
| 3698 |
+
"eval_samples_per_second": 8.807,
|
| 3699 |
+
"eval_steps_per_second": 1.174,
|
| 3700 |
+
"step": 246
|
| 3701 |
+
},
|
| 3702 |
+
{
|
| 3703 |
+
"epoch": 13.0,
|
| 3704 |
+
"grad_norm": 0.009496565908193588,
|
| 3705 |
+
"learning_rate": 3.5734731783715333e-07,
|
| 3706 |
+
"loss": 0.0007,
|
| 3707 |
+
"step": 247
|
| 3708 |
+
},
|
| 3709 |
+
{
|
| 3710 |
+
"epoch": 13.0,
|
| 3711 |
+
"eval_loss": 0.0005225887871347368,
|
| 3712 |
+
"eval_runtime": 3.3988,
|
| 3713 |
+
"eval_samples_per_second": 8.827,
|
| 3714 |
+
"eval_steps_per_second": 1.177,
|
| 3715 |
+
"step": 247
|
| 3716 |
+
},
|
| 3717 |
+
{
|
| 3718 |
+
"epoch": 13.052631578947368,
|
| 3719 |
+
"grad_norm": 0.03507193550467491,
|
| 3720 |
+
"learning_rate": 2.0102882345540696e-07,
|
| 3721 |
+
"loss": 0.0014,
|
| 3722 |
+
"step": 248
|
| 3723 |
+
},
|
| 3724 |
+
{
|
| 3725 |
+
"epoch": 13.052631578947368,
|
| 3726 |
+
"eval_loss": 0.0005245525971986353,
|
| 3727 |
+
"eval_runtime": 3.398,
|
| 3728 |
+
"eval_samples_per_second": 8.829,
|
| 3729 |
+
"eval_steps_per_second": 1.177,
|
| 3730 |
+
"step": 248
|
| 3731 |
+
},
|
| 3732 |
+
{
|
| 3733 |
+
"epoch": 13.105263157894736,
|
| 3734 |
+
"grad_norm": 0.007154720835387707,
|
| 3735 |
+
"learning_rate": 8.935279730407086e-08,
|
| 3736 |
+
"loss": 0.0004,
|
| 3737 |
+
"step": 249
|
| 3738 |
+
},
|
| 3739 |
+
{
|
| 3740 |
+
"epoch": 13.105263157894736,
|
| 3741 |
+
"eval_loss": 0.0005229982198216021,
|
| 3742 |
+
"eval_runtime": 3.3921,
|
| 3743 |
+
"eval_samples_per_second": 8.844,
|
| 3744 |
+
"eval_steps_per_second": 1.179,
|
| 3745 |
+
"step": 249
|
| 3746 |
+
},
|
| 3747 |
+
{
|
| 3748 |
+
"epoch": 13.157894736842104,
|
| 3749 |
+
"grad_norm": 0.007874587550759315,
|
| 3750 |
+
"learning_rate": 2.2339197405490953e-08,
|
| 3751 |
+
"loss": 0.0005,
|
| 3752 |
+
"step": 250
|
| 3753 |
+
},
|
| 3754 |
+
{
|
| 3755 |
+
"epoch": 13.157894736842104,
|
| 3756 |
+
"eval_loss": 0.0005229749367572367,
|
| 3757 |
+
"eval_runtime": 3.3804,
|
| 3758 |
+
"eval_samples_per_second": 8.875,
|
| 3759 |
+
"eval_steps_per_second": 1.183,
|
| 3760 |
+
"step": 250
|
| 3761 |
}
|
| 3762 |
],
|
| 3763 |
"logging_steps": 1,
|
|
|
|
| 3772 |
"should_evaluate": false,
|
| 3773 |
"should_log": false,
|
| 3774 |
"should_save": true,
|
| 3775 |
+
"should_training_stop": true
|
| 3776 |
},
|
| 3777 |
"attributes": {}
|
| 3778 |
}
|
| 3779 |
},
|
| 3780 |
+
"total_flos": 1.0652124028778496e+16,
|
| 3781 |
"train_batch_size": 1,
|
| 3782 |
"trial_name": null,
|
| 3783 |
"trial_params": null
|