Instructions to use shareit/chatbot-supervisor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shareit/chatbot-supervisor with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shareit/chatbot-supervisor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Training in progress, step 11100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 340808816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c10fb4ee97b92a9019ccccbd10a1d8a49b0e3bbc387c352bd420b9f4d1fff057
|
| 3 |
size 340808816
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 173247691
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb50355aa39f8467d11aa9e7f2b0dba1d9b2b1414f4beae5f33025e2590d855a
|
| 3 |
size 173247691
|
last-checkpoint/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:b6cba449e4654bd5daf58a23e9e4face033094966520841bfbcab0ff728af0ff
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 12.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -75608,6 +75608,2106 @@
|
|
| 75608 |
"learning_rate": 1.7355266257257438e-05,
|
| 75609 |
"loss": 0.5878,
|
| 75610 |
"step": 10800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75611 |
}
|
| 75612 |
],
|
| 75613 |
"logging_steps": 1,
|
|
@@ -75627,7 +77727,7 @@
|
|
| 75627 |
"attributes": {}
|
| 75628 |
}
|
| 75629 |
},
|
| 75630 |
-
"total_flos": 6.
|
| 75631 |
"train_batch_size": 8,
|
| 75632 |
"trial_name": null,
|
| 75633 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.642735042735042,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 11100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 75608 |
"learning_rate": 1.7355266257257438e-05,
|
| 75609 |
"loss": 0.5878,
|
| 75610 |
"step": 10800
|
| 75611 |
+
},
|
| 75612 |
+
{
|
| 75613 |
+
"epoch": 12.301994301994302,
|
| 75614 |
+
"grad_norm": 0.25265562534332275,
|
| 75615 |
+
"learning_rate": 1.735083038744803e-05,
|
| 75616 |
+
"loss": 0.5441,
|
| 75617 |
+
"step": 10801
|
| 75618 |
+
},
|
| 75619 |
+
{
|
| 75620 |
+
"epoch": 12.303133903133903,
|
| 75621 |
+
"grad_norm": 0.20412509143352509,
|
| 75622 |
+
"learning_rate": 1.734639478331532e-05,
|
| 75623 |
+
"loss": 0.7165,
|
| 75624 |
+
"step": 10802
|
| 75625 |
+
},
|
| 75626 |
+
{
|
| 75627 |
+
"epoch": 12.304273504273505,
|
| 75628 |
+
"grad_norm": 0.2196875661611557,
|
| 75629 |
+
"learning_rate": 1.7341959445013362e-05,
|
| 75630 |
+
"loss": 0.8689,
|
| 75631 |
+
"step": 10803
|
| 75632 |
+
},
|
| 75633 |
+
{
|
| 75634 |
+
"epoch": 12.305413105413106,
|
| 75635 |
+
"grad_norm": 0.206462100148201,
|
| 75636 |
+
"learning_rate": 1.7337524372696218e-05,
|
| 75637 |
+
"loss": 0.6361,
|
| 75638 |
+
"step": 10804
|
| 75639 |
+
},
|
| 75640 |
+
{
|
| 75641 |
+
"epoch": 12.306552706552706,
|
| 75642 |
+
"grad_norm": 0.1997363120317459,
|
| 75643 |
+
"learning_rate": 1.7333089566517917e-05,
|
| 75644 |
+
"loss": 0.7908,
|
| 75645 |
+
"step": 10805
|
| 75646 |
+
},
|
| 75647 |
+
{
|
| 75648 |
+
"epoch": 12.307692307692308,
|
| 75649 |
+
"grad_norm": 0.20651085674762726,
|
| 75650 |
+
"learning_rate": 1.732865502663251e-05,
|
| 75651 |
+
"loss": 0.641,
|
| 75652 |
+
"step": 10806
|
| 75653 |
+
},
|
| 75654 |
+
{
|
| 75655 |
+
"epoch": 12.308831908831909,
|
| 75656 |
+
"grad_norm": 0.23688238859176636,
|
| 75657 |
+
"learning_rate": 1.7324220753194e-05,
|
| 75658 |
+
"loss": 0.5492,
|
| 75659 |
+
"step": 10807
|
| 75660 |
+
},
|
| 75661 |
+
{
|
| 75662 |
+
"epoch": 12.30997150997151,
|
| 75663 |
+
"grad_norm": 0.23155272006988525,
|
| 75664 |
+
"learning_rate": 1.731978674635641e-05,
|
| 75665 |
+
"loss": 0.6126,
|
| 75666 |
+
"step": 10808
|
| 75667 |
+
},
|
| 75668 |
+
{
|
| 75669 |
+
"epoch": 12.311111111111112,
|
| 75670 |
+
"grad_norm": 0.188265860080719,
|
| 75671 |
+
"learning_rate": 1.7315353006273755e-05,
|
| 75672 |
+
"loss": 0.7488,
|
| 75673 |
+
"step": 10809
|
| 75674 |
+
},
|
| 75675 |
+
{
|
| 75676 |
+
"epoch": 12.312250712250712,
|
| 75677 |
+
"grad_norm": 0.2498866468667984,
|
| 75678 |
+
"learning_rate": 1.731091953310002e-05,
|
| 75679 |
+
"loss": 0.6749,
|
| 75680 |
+
"step": 10810
|
| 75681 |
+
},
|
| 75682 |
+
{
|
| 75683 |
+
"epoch": 12.313390313390313,
|
| 75684 |
+
"grad_norm": 0.20068980753421783,
|
| 75685 |
+
"learning_rate": 1.7306486326989195e-05,
|
| 75686 |
+
"loss": 0.7336,
|
| 75687 |
+
"step": 10811
|
| 75688 |
+
},
|
| 75689 |
+
{
|
| 75690 |
+
"epoch": 12.314529914529915,
|
| 75691 |
+
"grad_norm": 0.2250603288412094,
|
| 75692 |
+
"learning_rate": 1.7302053388095256e-05,
|
| 75693 |
+
"loss": 0.6995,
|
| 75694 |
+
"step": 10812
|
| 75695 |
+
},
|
| 75696 |
+
{
|
| 75697 |
+
"epoch": 12.315669515669516,
|
| 75698 |
+
"grad_norm": 0.21724343299865723,
|
| 75699 |
+
"learning_rate": 1.7297620716572177e-05,
|
| 75700 |
+
"loss": 0.7542,
|
| 75701 |
+
"step": 10813
|
| 75702 |
+
},
|
| 75703 |
+
{
|
| 75704 |
+
"epoch": 12.316809116809116,
|
| 75705 |
+
"grad_norm": 0.3206590414047241,
|
| 75706 |
+
"learning_rate": 1.729318831257391e-05,
|
| 75707 |
+
"loss": 0.4611,
|
| 75708 |
+
"step": 10814
|
| 75709 |
+
},
|
| 75710 |
+
{
|
| 75711 |
+
"epoch": 12.317948717948719,
|
| 75712 |
+
"grad_norm": 0.20177413523197174,
|
| 75713 |
+
"learning_rate": 1.7288756176254406e-05,
|
| 75714 |
+
"loss": 0.6522,
|
| 75715 |
+
"step": 10815
|
| 75716 |
+
},
|
| 75717 |
+
{
|
| 75718 |
+
"epoch": 12.31908831908832,
|
| 75719 |
+
"grad_norm": 0.2285015881061554,
|
| 75720 |
+
"learning_rate": 1.7284324307767604e-05,
|
| 75721 |
+
"loss": 0.5431,
|
| 75722 |
+
"step": 10816
|
| 75723 |
+
},
|
| 75724 |
+
{
|
| 75725 |
+
"epoch": 12.32022792022792,
|
| 75726 |
+
"grad_norm": 0.17258432507514954,
|
| 75727 |
+
"learning_rate": 1.727989270726744e-05,
|
| 75728 |
+
"loss": 0.7312,
|
| 75729 |
+
"step": 10817
|
| 75730 |
+
},
|
| 75731 |
+
{
|
| 75732 |
+
"epoch": 12.321367521367522,
|
| 75733 |
+
"grad_norm": 0.21014466881752014,
|
| 75734 |
+
"learning_rate": 1.7275461374907825e-05,
|
| 75735 |
+
"loss": 0.7903,
|
| 75736 |
+
"step": 10818
|
| 75737 |
+
},
|
| 75738 |
+
{
|
| 75739 |
+
"epoch": 12.322507122507123,
|
| 75740 |
+
"grad_norm": 0.1585046947002411,
|
| 75741 |
+
"learning_rate": 1.7271030310842684e-05,
|
| 75742 |
+
"loss": 0.7555,
|
| 75743 |
+
"step": 10819
|
| 75744 |
+
},
|
| 75745 |
+
{
|
| 75746 |
+
"epoch": 12.323646723646723,
|
| 75747 |
+
"grad_norm": 0.19881057739257812,
|
| 75748 |
+
"learning_rate": 1.726659951522592e-05,
|
| 75749 |
+
"loss": 0.8694,
|
| 75750 |
+
"step": 10820
|
| 75751 |
+
},
|
| 75752 |
+
{
|
| 75753 |
+
"epoch": 12.324786324786325,
|
| 75754 |
+
"grad_norm": 0.2570485472679138,
|
| 75755 |
+
"learning_rate": 1.7262168988211413e-05,
|
| 75756 |
+
"loss": 0.5388,
|
| 75757 |
+
"step": 10821
|
| 75758 |
+
},
|
| 75759 |
+
{
|
| 75760 |
+
"epoch": 12.325925925925926,
|
| 75761 |
+
"grad_norm": 0.20987975597381592,
|
| 75762 |
+
"learning_rate": 1.7257738729953065e-05,
|
| 75763 |
+
"loss": 0.5459,
|
| 75764 |
+
"step": 10822
|
| 75765 |
+
},
|
| 75766 |
+
{
|
| 75767 |
+
"epoch": 12.327065527065526,
|
| 75768 |
+
"grad_norm": 0.24118657410144806,
|
| 75769 |
+
"learning_rate": 1.7253308740604736e-05,
|
| 75770 |
+
"loss": 0.4905,
|
| 75771 |
+
"step": 10823
|
| 75772 |
+
},
|
| 75773 |
+
{
|
| 75774 |
+
"epoch": 12.328205128205129,
|
| 75775 |
+
"grad_norm": 0.20755544304847717,
|
| 75776 |
+
"learning_rate": 1.7248879020320306e-05,
|
| 75777 |
+
"loss": 0.6382,
|
| 75778 |
+
"step": 10824
|
| 75779 |
+
},
|
| 75780 |
+
{
|
| 75781 |
+
"epoch": 12.32934472934473,
|
| 75782 |
+
"grad_norm": 0.19893032312393188,
|
| 75783 |
+
"learning_rate": 1.7244449569253616e-05,
|
| 75784 |
+
"loss": 0.8554,
|
| 75785 |
+
"step": 10825
|
| 75786 |
+
},
|
| 75787 |
+
{
|
| 75788 |
+
"epoch": 12.33048433048433,
|
| 75789 |
+
"grad_norm": 0.2536832094192505,
|
| 75790 |
+
"learning_rate": 1.7240020387558525e-05,
|
| 75791 |
+
"loss": 0.3889,
|
| 75792 |
+
"step": 10826
|
| 75793 |
+
},
|
| 75794 |
+
{
|
| 75795 |
+
"epoch": 12.331623931623932,
|
| 75796 |
+
"grad_norm": 0.20230743288993835,
|
| 75797 |
+
"learning_rate": 1.723559147538886e-05,
|
| 75798 |
+
"loss": 0.6262,
|
| 75799 |
+
"step": 10827
|
| 75800 |
+
},
|
| 75801 |
+
{
|
| 75802 |
+
"epoch": 12.332763532763533,
|
| 75803 |
+
"grad_norm": 0.19835615158081055,
|
| 75804 |
+
"learning_rate": 1.7231162832898462e-05,
|
| 75805 |
+
"loss": 0.7368,
|
| 75806 |
+
"step": 10828
|
| 75807 |
+
},
|
| 75808 |
+
{
|
| 75809 |
+
"epoch": 12.333903133903133,
|
| 75810 |
+
"grad_norm": 0.19229477643966675,
|
| 75811 |
+
"learning_rate": 1.7226734460241127e-05,
|
| 75812 |
+
"loss": 0.6124,
|
| 75813 |
+
"step": 10829
|
| 75814 |
+
},
|
| 75815 |
+
{
|
| 75816 |
+
"epoch": 12.335042735042736,
|
| 75817 |
+
"grad_norm": 0.20986317098140717,
|
| 75818 |
+
"learning_rate": 1.7222306357570696e-05,
|
| 75819 |
+
"loss": 0.8819,
|
| 75820 |
+
"step": 10830
|
| 75821 |
+
},
|
| 75822 |
+
{
|
| 75823 |
+
"epoch": 12.336182336182336,
|
| 75824 |
+
"grad_norm": 0.2248592972755432,
|
| 75825 |
+
"learning_rate": 1.7217878525040955e-05,
|
| 75826 |
+
"loss": 0.6465,
|
| 75827 |
+
"step": 10831
|
| 75828 |
+
},
|
| 75829 |
+
{
|
| 75830 |
+
"epoch": 12.337321937321937,
|
| 75831 |
+
"grad_norm": 0.21292966604232788,
|
| 75832 |
+
"learning_rate": 1.7213450962805685e-05,
|
| 75833 |
+
"loss": 0.7351,
|
| 75834 |
+
"step": 10832
|
| 75835 |
+
},
|
| 75836 |
+
{
|
| 75837 |
+
"epoch": 12.338461538461539,
|
| 75838 |
+
"grad_norm": 0.17942236363887787,
|
| 75839 |
+
"learning_rate": 1.7209023671018685e-05,
|
| 75840 |
+
"loss": 0.8832,
|
| 75841 |
+
"step": 10833
|
| 75842 |
+
},
|
| 75843 |
+
{
|
| 75844 |
+
"epoch": 12.33960113960114,
|
| 75845 |
+
"grad_norm": 0.1823773980140686,
|
| 75846 |
+
"learning_rate": 1.720459664983371e-05,
|
| 75847 |
+
"loss": 0.5213,
|
| 75848 |
+
"step": 10834
|
| 75849 |
+
},
|
| 75850 |
+
{
|
| 75851 |
+
"epoch": 12.34074074074074,
|
| 75852 |
+
"grad_norm": 0.2529001533985138,
|
| 75853 |
+
"learning_rate": 1.7200169899404534e-05,
|
| 75854 |
+
"loss": 0.6295,
|
| 75855 |
+
"step": 10835
|
| 75856 |
+
},
|
| 75857 |
+
{
|
| 75858 |
+
"epoch": 12.341880341880342,
|
| 75859 |
+
"grad_norm": 0.17539896070957184,
|
| 75860 |
+
"learning_rate": 1.719574341988491e-05,
|
| 75861 |
+
"loss": 0.7827,
|
| 75862 |
+
"step": 10836
|
| 75863 |
+
},
|
| 75864 |
+
{
|
| 75865 |
+
"epoch": 12.343019943019943,
|
| 75866 |
+
"grad_norm": 0.1981101632118225,
|
| 75867 |
+
"learning_rate": 1.7191317211428577e-05,
|
| 75868 |
+
"loss": 0.669,
|
| 75869 |
+
"step": 10837
|
| 75870 |
+
},
|
| 75871 |
+
{
|
| 75872 |
+
"epoch": 12.344159544159544,
|
| 75873 |
+
"grad_norm": 0.22740918397903442,
|
| 75874 |
+
"learning_rate": 1.718689127418927e-05,
|
| 75875 |
+
"loss": 0.6029,
|
| 75876 |
+
"step": 10838
|
| 75877 |
+
},
|
| 75878 |
+
{
|
| 75879 |
+
"epoch": 12.345299145299146,
|
| 75880 |
+
"grad_norm": 0.18608032166957855,
|
| 75881 |
+
"learning_rate": 1.7182465608320717e-05,
|
| 75882 |
+
"loss": 0.8558,
|
| 75883 |
+
"step": 10839
|
| 75884 |
+
},
|
| 75885 |
+
{
|
| 75886 |
+
"epoch": 12.346438746438746,
|
| 75887 |
+
"grad_norm": 0.22309254109859467,
|
| 75888 |
+
"learning_rate": 1.7178040213976623e-05,
|
| 75889 |
+
"loss": 0.6231,
|
| 75890 |
+
"step": 10840
|
| 75891 |
+
},
|
| 75892 |
+
{
|
| 75893 |
+
"epoch": 12.347578347578347,
|
| 75894 |
+
"grad_norm": 0.21621108055114746,
|
| 75895 |
+
"learning_rate": 1.7173615091310713e-05,
|
| 75896 |
+
"loss": 0.7582,
|
| 75897 |
+
"step": 10841
|
| 75898 |
+
},
|
| 75899 |
+
{
|
| 75900 |
+
"epoch": 12.34871794871795,
|
| 75901 |
+
"grad_norm": 0.18133021891117096,
|
| 75902 |
+
"learning_rate": 1.716919024047667e-05,
|
| 75903 |
+
"loss": 0.7135,
|
| 75904 |
+
"step": 10842
|
| 75905 |
+
},
|
| 75906 |
+
{
|
| 75907 |
+
"epoch": 12.34985754985755,
|
| 75908 |
+
"grad_norm": 0.22286663949489594,
|
| 75909 |
+
"learning_rate": 1.7164765661628192e-05,
|
| 75910 |
+
"loss": 0.6465,
|
| 75911 |
+
"step": 10843
|
| 75912 |
+
},
|
| 75913 |
+
{
|
| 75914 |
+
"epoch": 12.35099715099715,
|
| 75915 |
+
"grad_norm": 0.20079916715621948,
|
| 75916 |
+
"learning_rate": 1.716034135491894e-05,
|
| 75917 |
+
"loss": 0.6421,
|
| 75918 |
+
"step": 10844
|
| 75919 |
+
},
|
| 75920 |
+
{
|
| 75921 |
+
"epoch": 12.352136752136753,
|
| 75922 |
+
"grad_norm": 0.21749894320964813,
|
| 75923 |
+
"learning_rate": 1.7155917320502596e-05,
|
| 75924 |
+
"loss": 0.7368,
|
| 75925 |
+
"step": 10845
|
| 75926 |
+
},
|
| 75927 |
+
{
|
| 75928 |
+
"epoch": 12.353276353276353,
|
| 75929 |
+
"grad_norm": 0.21311548352241516,
|
| 75930 |
+
"learning_rate": 1.715149355853281e-05,
|
| 75931 |
+
"loss": 0.6545,
|
| 75932 |
+
"step": 10846
|
| 75933 |
+
},
|
| 75934 |
+
{
|
| 75935 |
+
"epoch": 12.354415954415954,
|
| 75936 |
+
"grad_norm": 0.1735820770263672,
|
| 75937 |
+
"learning_rate": 1.7147070069163247e-05,
|
| 75938 |
+
"loss": 0.9553,
|
| 75939 |
+
"step": 10847
|
| 75940 |
+
},
|
| 75941 |
+
{
|
| 75942 |
+
"epoch": 12.355555555555556,
|
| 75943 |
+
"grad_norm": 0.18377651274204254,
|
| 75944 |
+
"learning_rate": 1.7142646852547528e-05,
|
| 75945 |
+
"loss": 0.7713,
|
| 75946 |
+
"step": 10848
|
| 75947 |
+
},
|
| 75948 |
+
{
|
| 75949 |
+
"epoch": 12.356695156695157,
|
| 75950 |
+
"grad_norm": 0.2323378026485443,
|
| 75951 |
+
"learning_rate": 1.7138223908839296e-05,
|
| 75952 |
+
"loss": 0.851,
|
| 75953 |
+
"step": 10849
|
| 75954 |
+
},
|
| 75955 |
+
{
|
| 75956 |
+
"epoch": 12.357834757834757,
|
| 75957 |
+
"grad_norm": 0.21971707046031952,
|
| 75958 |
+
"learning_rate": 1.713380123819216e-05,
|
| 75959 |
+
"loss": 0.6503,
|
| 75960 |
+
"step": 10850
|
| 75961 |
+
},
|
| 75962 |
+
{
|
| 75963 |
+
"epoch": 12.35897435897436,
|
| 75964 |
+
"grad_norm": 0.22638419270515442,
|
| 75965 |
+
"learning_rate": 1.7129378840759735e-05,
|
| 75966 |
+
"loss": 0.6714,
|
| 75967 |
+
"step": 10851
|
| 75968 |
+
},
|
| 75969 |
+
{
|
| 75970 |
+
"epoch": 12.36011396011396,
|
| 75971 |
+
"grad_norm": 0.202363520860672,
|
| 75972 |
+
"learning_rate": 1.7124956716695643e-05,
|
| 75973 |
+
"loss": 0.7194,
|
| 75974 |
+
"step": 10852
|
| 75975 |
+
},
|
| 75976 |
+
{
|
| 75977 |
+
"epoch": 12.36125356125356,
|
| 75978 |
+
"grad_norm": 0.19767224788665771,
|
| 75979 |
+
"learning_rate": 1.712053486615345e-05,
|
| 75980 |
+
"loss": 0.6844,
|
| 75981 |
+
"step": 10853
|
| 75982 |
+
},
|
| 75983 |
+
{
|
| 75984 |
+
"epoch": 12.362393162393163,
|
| 75985 |
+
"grad_norm": 0.19901210069656372,
|
| 75986 |
+
"learning_rate": 1.7116113289286755e-05,
|
| 75987 |
+
"loss": 0.7594,
|
| 75988 |
+
"step": 10854
|
| 75989 |
+
},
|
| 75990 |
+
{
|
| 75991 |
+
"epoch": 12.363532763532763,
|
| 75992 |
+
"grad_norm": 0.22945459187030792,
|
| 75993 |
+
"learning_rate": 1.7111691986249124e-05,
|
| 75994 |
+
"loss": 0.7578,
|
| 75995 |
+
"step": 10855
|
| 75996 |
+
},
|
| 75997 |
+
{
|
| 75998 |
+
"epoch": 12.364672364672364,
|
| 75999 |
+
"grad_norm": 0.20821332931518555,
|
| 76000 |
+
"learning_rate": 1.7107270957194128e-05,
|
| 76001 |
+
"loss": 0.6723,
|
| 76002 |
+
"step": 10856
|
| 76003 |
+
},
|
| 76004 |
+
{
|
| 76005 |
+
"epoch": 12.365811965811966,
|
| 76006 |
+
"grad_norm": 0.18176351487636566,
|
| 76007 |
+
"learning_rate": 1.7102850202275312e-05,
|
| 76008 |
+
"loss": 0.7668,
|
| 76009 |
+
"step": 10857
|
| 76010 |
+
},
|
| 76011 |
+
{
|
| 76012 |
+
"epoch": 12.366951566951567,
|
| 76013 |
+
"grad_norm": 0.1840147227048874,
|
| 76014 |
+
"learning_rate": 1.7098429721646224e-05,
|
| 76015 |
+
"loss": 0.9512,
|
| 76016 |
+
"step": 10858
|
| 76017 |
+
},
|
| 76018 |
+
{
|
| 76019 |
+
"epoch": 12.368091168091167,
|
| 76020 |
+
"grad_norm": 0.20341096818447113,
|
| 76021 |
+
"learning_rate": 1.7094009515460403e-05,
|
| 76022 |
+
"loss": 0.7151,
|
| 76023 |
+
"step": 10859
|
| 76024 |
+
},
|
| 76025 |
+
{
|
| 76026 |
+
"epoch": 12.36923076923077,
|
| 76027 |
+
"grad_norm": 0.21524856984615326,
|
| 76028 |
+
"learning_rate": 1.708958958387138e-05,
|
| 76029 |
+
"loss": 0.6924,
|
| 76030 |
+
"step": 10860
|
| 76031 |
+
},
|
| 76032 |
+
{
|
| 76033 |
+
"epoch": 12.37037037037037,
|
| 76034 |
+
"grad_norm": 0.26379674673080444,
|
| 76035 |
+
"learning_rate": 1.7085169927032653e-05,
|
| 76036 |
+
"loss": 0.6872,
|
| 76037 |
+
"step": 10861
|
| 76038 |
+
},
|
| 76039 |
+
{
|
| 76040 |
+
"epoch": 12.37150997150997,
|
| 76041 |
+
"grad_norm": 0.1969965249300003,
|
| 76042 |
+
"learning_rate": 1.708075054509774e-05,
|
| 76043 |
+
"loss": 0.6073,
|
| 76044 |
+
"step": 10862
|
| 76045 |
+
},
|
| 76046 |
+
{
|
| 76047 |
+
"epoch": 12.372649572649573,
|
| 76048 |
+
"grad_norm": 0.18986299633979797,
|
| 76049 |
+
"learning_rate": 1.7076331438220145e-05,
|
| 76050 |
+
"loss": 0.6506,
|
| 76051 |
+
"step": 10863
|
| 76052 |
+
},
|
| 76053 |
+
{
|
| 76054 |
+
"epoch": 12.373789173789174,
|
| 76055 |
+
"grad_norm": 0.2116694152355194,
|
| 76056 |
+
"learning_rate": 1.707191260655335e-05,
|
| 76057 |
+
"loss": 0.5803,
|
| 76058 |
+
"step": 10864
|
| 76059 |
+
},
|
| 76060 |
+
{
|
| 76061 |
+
"epoch": 12.374928774928774,
|
| 76062 |
+
"grad_norm": 0.1978309452533722,
|
| 76063 |
+
"learning_rate": 1.7067494050250832e-05,
|
| 76064 |
+
"loss": 0.5744,
|
| 76065 |
+
"step": 10865
|
| 76066 |
+
},
|
| 76067 |
+
{
|
| 76068 |
+
"epoch": 12.376068376068377,
|
| 76069 |
+
"grad_norm": 0.22155092656612396,
|
| 76070 |
+
"learning_rate": 1.7063075769466055e-05,
|
| 76071 |
+
"loss": 0.568,
|
| 76072 |
+
"step": 10866
|
| 76073 |
+
},
|
| 76074 |
+
{
|
| 76075 |
+
"epoch": 12.377207977207977,
|
| 76076 |
+
"grad_norm": 0.21958346664905548,
|
| 76077 |
+
"learning_rate": 1.705865776435249e-05,
|
| 76078 |
+
"loss": 0.6179,
|
| 76079 |
+
"step": 10867
|
| 76080 |
+
},
|
| 76081 |
+
{
|
| 76082 |
+
"epoch": 12.378347578347578,
|
| 76083 |
+
"grad_norm": 0.24003711342811584,
|
| 76084 |
+
"learning_rate": 1.7054240035063572e-05,
|
| 76085 |
+
"loss": 0.6299,
|
| 76086 |
+
"step": 10868
|
| 76087 |
+
},
|
| 76088 |
+
{
|
| 76089 |
+
"epoch": 12.37948717948718,
|
| 76090 |
+
"grad_norm": 0.23949706554412842,
|
| 76091 |
+
"learning_rate": 1.7049822581752763e-05,
|
| 76092 |
+
"loss": 0.6282,
|
| 76093 |
+
"step": 10869
|
| 76094 |
+
},
|
| 76095 |
+
{
|
| 76096 |
+
"epoch": 12.38062678062678,
|
| 76097 |
+
"grad_norm": 0.20721937716007233,
|
| 76098 |
+
"learning_rate": 1.7045405404573464e-05,
|
| 76099 |
+
"loss": 0.7627,
|
| 76100 |
+
"step": 10870
|
| 76101 |
+
},
|
| 76102 |
+
{
|
| 76103 |
+
"epoch": 12.381766381766381,
|
| 76104 |
+
"grad_norm": 0.2312813550233841,
|
| 76105 |
+
"learning_rate": 1.7040988503679118e-05,
|
| 76106 |
+
"loss": 0.7129,
|
| 76107 |
+
"step": 10871
|
| 76108 |
+
},
|
| 76109 |
+
{
|
| 76110 |
+
"epoch": 12.382905982905983,
|
| 76111 |
+
"grad_norm": 0.22972968220710754,
|
| 76112 |
+
"learning_rate": 1.7036571879223123e-05,
|
| 76113 |
+
"loss": 0.5168,
|
| 76114 |
+
"step": 10872
|
| 76115 |
+
},
|
| 76116 |
+
{
|
| 76117 |
+
"epoch": 12.384045584045584,
|
| 76118 |
+
"grad_norm": 0.2056453377008438,
|
| 76119 |
+
"learning_rate": 1.7032155531358885e-05,
|
| 76120 |
+
"loss": 0.5596,
|
| 76121 |
+
"step": 10873
|
| 76122 |
+
},
|
| 76123 |
+
{
|
| 76124 |
+
"epoch": 12.385185185185184,
|
| 76125 |
+
"grad_norm": 0.23936963081359863,
|
| 76126 |
+
"learning_rate": 1.7027739460239797e-05,
|
| 76127 |
+
"loss": 0.6441,
|
| 76128 |
+
"step": 10874
|
| 76129 |
+
},
|
| 76130 |
+
{
|
| 76131 |
+
"epoch": 12.386324786324787,
|
| 76132 |
+
"grad_norm": 0.22788862884044647,
|
| 76133 |
+
"learning_rate": 1.7023323666019248e-05,
|
| 76134 |
+
"loss": 0.6808,
|
| 76135 |
+
"step": 10875
|
| 76136 |
+
},
|
| 76137 |
+
{
|
| 76138 |
+
"epoch": 12.387464387464387,
|
| 76139 |
+
"grad_norm": 0.17753151059150696,
|
| 76140 |
+
"learning_rate": 1.70189081488506e-05,
|
| 76141 |
+
"loss": 0.8624,
|
| 76142 |
+
"step": 10876
|
| 76143 |
+
},
|
| 76144 |
+
{
|
| 76145 |
+
"epoch": 12.388603988603988,
|
| 76146 |
+
"grad_norm": 0.2086041420698166,
|
| 76147 |
+
"learning_rate": 1.7014492908887226e-05,
|
| 76148 |
+
"loss": 0.496,
|
| 76149 |
+
"step": 10877
|
| 76150 |
+
},
|
| 76151 |
+
{
|
| 76152 |
+
"epoch": 12.38974358974359,
|
| 76153 |
+
"grad_norm": 0.29431894421577454,
|
| 76154 |
+
"learning_rate": 1.7010077946282466e-05,
|
| 76155 |
+
"loss": 0.4777,
|
| 76156 |
+
"step": 10878
|
| 76157 |
+
},
|
| 76158 |
+
{
|
| 76159 |
+
"epoch": 12.39088319088319,
|
| 76160 |
+
"grad_norm": 0.22070807218551636,
|
| 76161 |
+
"learning_rate": 1.7005663261189678e-05,
|
| 76162 |
+
"loss": 0.8056,
|
| 76163 |
+
"step": 10879
|
| 76164 |
+
},
|
| 76165 |
+
{
|
| 76166 |
+
"epoch": 12.392022792022791,
|
| 76167 |
+
"grad_norm": 0.1758912056684494,
|
| 76168 |
+
"learning_rate": 1.7001248853762184e-05,
|
| 76169 |
+
"loss": 0.7873,
|
| 76170 |
+
"step": 10880
|
| 76171 |
+
},
|
| 76172 |
+
{
|
| 76173 |
+
"epoch": 12.393162393162394,
|
| 76174 |
+
"grad_norm": 0.18746311962604523,
|
| 76175 |
+
"learning_rate": 1.6996834724153318e-05,
|
| 76176 |
+
"loss": 0.5918,
|
| 76177 |
+
"step": 10881
|
| 76178 |
+
},
|
| 76179 |
+
{
|
| 76180 |
+
"epoch": 12.394301994301994,
|
| 76181 |
+
"grad_norm": 0.2081279754638672,
|
| 76182 |
+
"learning_rate": 1.699242087251639e-05,
|
| 76183 |
+
"loss": 0.6617,
|
| 76184 |
+
"step": 10882
|
| 76185 |
+
},
|
| 76186 |
+
{
|
| 76187 |
+
"epoch": 12.395441595441595,
|
| 76188 |
+
"grad_norm": 0.17694391310214996,
|
| 76189 |
+
"learning_rate": 1.6988007299004704e-05,
|
| 76190 |
+
"loss": 0.8219,
|
| 76191 |
+
"step": 10883
|
| 76192 |
+
},
|
| 76193 |
+
{
|
| 76194 |
+
"epoch": 12.396581196581197,
|
| 76195 |
+
"grad_norm": 0.21463613212108612,
|
| 76196 |
+
"learning_rate": 1.698359400377155e-05,
|
| 76197 |
+
"loss": 0.6713,
|
| 76198 |
+
"step": 10884
|
| 76199 |
+
},
|
| 76200 |
+
{
|
| 76201 |
+
"epoch": 12.397720797720797,
|
| 76202 |
+
"grad_norm": 0.2681838274002075,
|
| 76203 |
+
"learning_rate": 1.697918098697023e-05,
|
| 76204 |
+
"loss": 0.4294,
|
| 76205 |
+
"step": 10885
|
| 76206 |
+
},
|
| 76207 |
+
{
|
| 76208 |
+
"epoch": 12.398860398860398,
|
| 76209 |
+
"grad_norm": 0.24642108380794525,
|
| 76210 |
+
"learning_rate": 1.6974768248754015e-05,
|
| 76211 |
+
"loss": 0.801,
|
| 76212 |
+
"step": 10886
|
| 76213 |
+
},
|
| 76214 |
+
{
|
| 76215 |
+
"epoch": 12.4,
|
| 76216 |
+
"grad_norm": 0.23168188333511353,
|
| 76217 |
+
"learning_rate": 1.6970355789276162e-05,
|
| 76218 |
+
"loss": 0.6824,
|
| 76219 |
+
"step": 10887
|
| 76220 |
+
},
|
| 76221 |
+
{
|
| 76222 |
+
"epoch": 12.401139601139601,
|
| 76223 |
+
"grad_norm": 0.19611448049545288,
|
| 76224 |
+
"learning_rate": 1.6965943608689938e-05,
|
| 76225 |
+
"loss": 0.7616,
|
| 76226 |
+
"step": 10888
|
| 76227 |
+
},
|
| 76228 |
+
{
|
| 76229 |
+
"epoch": 12.402279202279201,
|
| 76230 |
+
"grad_norm": 0.2129056453704834,
|
| 76231 |
+
"learning_rate": 1.6961531707148588e-05,
|
| 76232 |
+
"loss": 0.5648,
|
| 76233 |
+
"step": 10889
|
| 76234 |
+
},
|
| 76235 |
+
{
|
| 76236 |
+
"epoch": 12.403418803418804,
|
| 76237 |
+
"grad_norm": 0.2036651223897934,
|
| 76238 |
+
"learning_rate": 1.6957120084805344e-05,
|
| 76239 |
+
"loss": 0.6716,
|
| 76240 |
+
"step": 10890
|
| 76241 |
+
},
|
| 76242 |
+
{
|
| 76243 |
+
"epoch": 12.404558404558404,
|
| 76244 |
+
"grad_norm": 0.22893372178077698,
|
| 76245 |
+
"learning_rate": 1.6952708741813437e-05,
|
| 76246 |
+
"loss": 0.6018,
|
| 76247 |
+
"step": 10891
|
| 76248 |
+
},
|
| 76249 |
+
{
|
| 76250 |
+
"epoch": 12.405698005698005,
|
| 76251 |
+
"grad_norm": 0.1946319192647934,
|
| 76252 |
+
"learning_rate": 1.694829767832609e-05,
|
| 76253 |
+
"loss": 0.8137,
|
| 76254 |
+
"step": 10892
|
| 76255 |
+
},
|
| 76256 |
+
{
|
| 76257 |
+
"epoch": 12.406837606837607,
|
| 76258 |
+
"grad_norm": 0.2172234207391739,
|
| 76259 |
+
"learning_rate": 1.6943886894496503e-05,
|
| 76260 |
+
"loss": 0.7576,
|
| 76261 |
+
"step": 10893
|
| 76262 |
+
},
|
| 76263 |
+
{
|
| 76264 |
+
"epoch": 12.407977207977208,
|
| 76265 |
+
"grad_norm": 0.23911713063716888,
|
| 76266 |
+
"learning_rate": 1.6939476390477883e-05,
|
| 76267 |
+
"loss": 0.74,
|
| 76268 |
+
"step": 10894
|
| 76269 |
+
},
|
| 76270 |
+
{
|
| 76271 |
+
"epoch": 12.40911680911681,
|
| 76272 |
+
"grad_norm": 0.2226768434047699,
|
| 76273 |
+
"learning_rate": 1.69350661664234e-05,
|
| 76274 |
+
"loss": 0.6618,
|
| 76275 |
+
"step": 10895
|
| 76276 |
+
},
|
| 76277 |
+
{
|
| 76278 |
+
"epoch": 12.41025641025641,
|
| 76279 |
+
"grad_norm": 0.21871010959148407,
|
| 76280 |
+
"learning_rate": 1.6930656222486258e-05,
|
| 76281 |
+
"loss": 0.7467,
|
| 76282 |
+
"step": 10896
|
| 76283 |
+
},
|
| 76284 |
+
{
|
| 76285 |
+
"epoch": 12.411396011396011,
|
| 76286 |
+
"grad_norm": 0.16431699693202972,
|
| 76287 |
+
"learning_rate": 1.692624655881962e-05,
|
| 76288 |
+
"loss": 0.7324,
|
| 76289 |
+
"step": 10897
|
| 76290 |
+
},
|
| 76291 |
+
{
|
| 76292 |
+
"epoch": 12.412535612535613,
|
| 76293 |
+
"grad_norm": 0.20297163724899292,
|
| 76294 |
+
"learning_rate": 1.6921837175576634e-05,
|
| 76295 |
+
"loss": 0.6638,
|
| 76296 |
+
"step": 10898
|
| 76297 |
+
},
|
| 76298 |
+
{
|
| 76299 |
+
"epoch": 12.413675213675214,
|
| 76300 |
+
"grad_norm": 0.2928679287433624,
|
| 76301 |
+
"learning_rate": 1.6917428072910467e-05,
|
| 76302 |
+
"loss": 0.7598,
|
| 76303 |
+
"step": 10899
|
| 76304 |
+
},
|
| 76305 |
+
{
|
| 76306 |
+
"epoch": 12.414814814814815,
|
| 76307 |
+
"grad_norm": 0.18867497146129608,
|
| 76308 |
+
"learning_rate": 1.6913019250974244e-05,
|
| 76309 |
+
"loss": 0.7946,
|
| 76310 |
+
"step": 10900
|
| 76311 |
+
},
|
| 76312 |
+
{
|
| 76313 |
+
"epoch": 12.415954415954417,
|
| 76314 |
+
"grad_norm": 0.2605903446674347,
|
| 76315 |
+
"learning_rate": 1.6908610709921102e-05,
|
| 76316 |
+
"loss": 0.3366,
|
| 76317 |
+
"step": 10901
|
| 76318 |
+
},
|
| 76319 |
+
{
|
| 76320 |
+
"epoch": 12.417094017094017,
|
| 76321 |
+
"grad_norm": 0.18068283796310425,
|
| 76322 |
+
"learning_rate": 1.690420244990416e-05,
|
| 76323 |
+
"loss": 0.741,
|
| 76324 |
+
"step": 10902
|
| 76325 |
+
},
|
| 76326 |
+
{
|
| 76327 |
+
"epoch": 12.418233618233618,
|
| 76328 |
+
"grad_norm": 0.26920533180236816,
|
| 76329 |
+
"learning_rate": 1.6899794471076537e-05,
|
| 76330 |
+
"loss": 0.4441,
|
| 76331 |
+
"step": 10903
|
| 76332 |
+
},
|
| 76333 |
+
{
|
| 76334 |
+
"epoch": 12.41937321937322,
|
| 76335 |
+
"grad_norm": 0.26625603437423706,
|
| 76336 |
+
"learning_rate": 1.6895386773591324e-05,
|
| 76337 |
+
"loss": 0.7136,
|
| 76338 |
+
"step": 10904
|
| 76339 |
+
},
|
| 76340 |
+
{
|
| 76341 |
+
"epoch": 12.42051282051282,
|
| 76342 |
+
"grad_norm": 0.2134181559085846,
|
| 76343 |
+
"learning_rate": 1.6890979357601617e-05,
|
| 76344 |
+
"loss": 0.8128,
|
| 76345 |
+
"step": 10905
|
| 76346 |
+
},
|
| 76347 |
+
{
|
| 76348 |
+
"epoch": 12.421652421652421,
|
| 76349 |
+
"grad_norm": 0.18584464490413666,
|
| 76350 |
+
"learning_rate": 1.688657222326049e-05,
|
| 76351 |
+
"loss": 0.7526,
|
| 76352 |
+
"step": 10906
|
| 76353 |
+
},
|
| 76354 |
+
{
|
| 76355 |
+
"epoch": 12.422792022792024,
|
| 76356 |
+
"grad_norm": 0.19565482437610626,
|
| 76357 |
+
"learning_rate": 1.6882165370721025e-05,
|
| 76358 |
+
"loss": 0.8005,
|
| 76359 |
+
"step": 10907
|
| 76360 |
+
},
|
| 76361 |
+
{
|
| 76362 |
+
"epoch": 12.423931623931624,
|
| 76363 |
+
"grad_norm": 0.22352029383182526,
|
| 76364 |
+
"learning_rate": 1.6877758800136285e-05,
|
| 76365 |
+
"loss": 0.5997,
|
| 76366 |
+
"step": 10908
|
| 76367 |
+
},
|
| 76368 |
+
{
|
| 76369 |
+
"epoch": 12.425071225071225,
|
| 76370 |
+
"grad_norm": 0.18467660248279572,
|
| 76371 |
+
"learning_rate": 1.6873352511659317e-05,
|
| 76372 |
+
"loss": 0.7041,
|
| 76373 |
+
"step": 10909
|
| 76374 |
+
},
|
| 76375 |
+
{
|
| 76376 |
+
"epoch": 12.426210826210827,
|
| 76377 |
+
"grad_norm": 0.21925725042819977,
|
| 76378 |
+
"learning_rate": 1.6868946505443163e-05,
|
| 76379 |
+
"loss": 0.6993,
|
| 76380 |
+
"step": 10910
|
| 76381 |
+
},
|
| 76382 |
+
{
|
| 76383 |
+
"epoch": 12.427350427350428,
|
| 76384 |
+
"grad_norm": 0.18253867328166962,
|
| 76385 |
+
"learning_rate": 1.686454078164086e-05,
|
| 76386 |
+
"loss": 0.8133,
|
| 76387 |
+
"step": 10911
|
| 76388 |
+
},
|
| 76389 |
+
{
|
| 76390 |
+
"epoch": 12.428490028490028,
|
| 76391 |
+
"grad_norm": 0.2522498071193695,
|
| 76392 |
+
"learning_rate": 1.686013534040543e-05,
|
| 76393 |
+
"loss": 0.5022,
|
| 76394 |
+
"step": 10912
|
| 76395 |
+
},
|
| 76396 |
+
{
|
| 76397 |
+
"epoch": 12.42962962962963,
|
| 76398 |
+
"grad_norm": 0.20844027400016785,
|
| 76399 |
+
"learning_rate": 1.6855730181889877e-05,
|
| 76400 |
+
"loss": 0.7698,
|
| 76401 |
+
"step": 10913
|
| 76402 |
+
},
|
| 76403 |
+
{
|
| 76404 |
+
"epoch": 12.430769230769231,
|
| 76405 |
+
"grad_norm": 0.24319635331630707,
|
| 76406 |
+
"learning_rate": 1.6851325306247213e-05,
|
| 76407 |
+
"loss": 0.4736,
|
| 76408 |
+
"step": 10914
|
| 76409 |
+
},
|
| 76410 |
+
{
|
| 76411 |
+
"epoch": 12.431908831908832,
|
| 76412 |
+
"grad_norm": 0.20779003202915192,
|
| 76413 |
+
"learning_rate": 1.6846920713630436e-05,
|
| 76414 |
+
"loss": 0.608,
|
| 76415 |
+
"step": 10915
|
| 76416 |
+
},
|
| 76417 |
+
{
|
| 76418 |
+
"epoch": 12.433048433048434,
|
| 76419 |
+
"grad_norm": 0.273119181394577,
|
| 76420 |
+
"learning_rate": 1.6842516404192515e-05,
|
| 76421 |
+
"loss": 0.5014,
|
| 76422 |
+
"step": 10916
|
| 76423 |
+
},
|
| 76424 |
+
{
|
| 76425 |
+
"epoch": 12.434188034188034,
|
| 76426 |
+
"grad_norm": 0.20731210708618164,
|
| 76427 |
+
"learning_rate": 1.683811237808643e-05,
|
| 76428 |
+
"loss": 0.4557,
|
| 76429 |
+
"step": 10917
|
| 76430 |
+
},
|
| 76431 |
+
{
|
| 76432 |
+
"epoch": 12.435327635327635,
|
| 76433 |
+
"grad_norm": 0.1937895119190216,
|
| 76434 |
+
"learning_rate": 1.683370863546516e-05,
|
| 76435 |
+
"loss": 0.7014,
|
| 76436 |
+
"step": 10918
|
| 76437 |
+
},
|
| 76438 |
+
{
|
| 76439 |
+
"epoch": 12.436467236467237,
|
| 76440 |
+
"grad_norm": 0.2328297644853592,
|
| 76441 |
+
"learning_rate": 1.682930517648164e-05,
|
| 76442 |
+
"loss": 0.6301,
|
| 76443 |
+
"step": 10919
|
| 76444 |
+
},
|
| 76445 |
+
{
|
| 76446 |
+
"epoch": 12.437606837606838,
|
| 76447 |
+
"grad_norm": 0.21277906000614166,
|
| 76448 |
+
"learning_rate": 1.6824902001288826e-05,
|
| 76449 |
+
"loss": 0.585,
|
| 76450 |
+
"step": 10920
|
| 76451 |
+
},
|
| 76452 |
+
{
|
| 76453 |
+
"epoch": 12.438746438746438,
|
| 76454 |
+
"grad_norm": 0.22262638807296753,
|
| 76455 |
+
"learning_rate": 1.682049911003964e-05,
|
| 76456 |
+
"loss": 0.6298,
|
| 76457 |
+
"step": 10921
|
| 76458 |
+
},
|
| 76459 |
+
{
|
| 76460 |
+
"epoch": 12.43988603988604,
|
| 76461 |
+
"grad_norm": 0.21188397705554962,
|
| 76462 |
+
"learning_rate": 1.6816096502887017e-05,
|
| 76463 |
+
"loss": 0.6325,
|
| 76464 |
+
"step": 10922
|
| 76465 |
+
},
|
| 76466 |
+
{
|
| 76467 |
+
"epoch": 12.441025641025641,
|
| 76468 |
+
"grad_norm": 0.22162698209285736,
|
| 76469 |
+
"learning_rate": 1.681169417998387e-05,
|
| 76470 |
+
"loss": 0.6926,
|
| 76471 |
+
"step": 10923
|
| 76472 |
+
},
|
| 76473 |
+
{
|
| 76474 |
+
"epoch": 12.442165242165242,
|
| 76475 |
+
"grad_norm": 0.20816735923290253,
|
| 76476 |
+
"learning_rate": 1.6807292141483104e-05,
|
| 76477 |
+
"loss": 0.7027,
|
| 76478 |
+
"step": 10924
|
| 76479 |
+
},
|
| 76480 |
+
{
|
| 76481 |
+
"epoch": 12.443304843304844,
|
| 76482 |
+
"grad_norm": 0.24191802740097046,
|
| 76483 |
+
"learning_rate": 1.6802890387537608e-05,
|
| 76484 |
+
"loss": 0.6088,
|
| 76485 |
+
"step": 10925
|
| 76486 |
+
},
|
| 76487 |
+
{
|
| 76488 |
+
"epoch": 12.444444444444445,
|
| 76489 |
+
"grad_norm": 0.2472567856311798,
|
| 76490 |
+
"learning_rate": 1.679848891830027e-05,
|
| 76491 |
+
"loss": 0.5705,
|
| 76492 |
+
"step": 10926
|
| 76493 |
+
},
|
| 76494 |
+
{
|
| 76495 |
+
"epoch": 12.445584045584045,
|
| 76496 |
+
"grad_norm": 0.19793660938739777,
|
| 76497 |
+
"learning_rate": 1.6794087733923966e-05,
|
| 76498 |
+
"loss": 0.7335,
|
| 76499 |
+
"step": 10927
|
| 76500 |
+
},
|
| 76501 |
+
{
|
| 76502 |
+
"epoch": 12.446723646723648,
|
| 76503 |
+
"grad_norm": 0.2164766937494278,
|
| 76504 |
+
"learning_rate": 1.6789686834561557e-05,
|
| 76505 |
+
"loss": 0.8562,
|
| 76506 |
+
"step": 10928
|
| 76507 |
+
},
|
| 76508 |
+
{
|
| 76509 |
+
"epoch": 12.447863247863248,
|
| 76510 |
+
"grad_norm": 0.2467564195394516,
|
| 76511 |
+
"learning_rate": 1.678528622036591e-05,
|
| 76512 |
+
"loss": 0.5478,
|
| 76513 |
+
"step": 10929
|
| 76514 |
+
},
|
| 76515 |
+
{
|
| 76516 |
+
"epoch": 12.449002849002849,
|
| 76517 |
+
"grad_norm": 0.19778405129909515,
|
| 76518 |
+
"learning_rate": 1.678088589148986e-05,
|
| 76519 |
+
"loss": 0.7746,
|
| 76520 |
+
"step": 10930
|
| 76521 |
+
},
|
| 76522 |
+
{
|
| 76523 |
+
"epoch": 12.450142450142451,
|
| 76524 |
+
"grad_norm": 0.24205471575260162,
|
| 76525 |
+
"learning_rate": 1.677648584808625e-05,
|
| 76526 |
+
"loss": 0.4983,
|
| 76527 |
+
"step": 10931
|
| 76528 |
+
},
|
| 76529 |
+
{
|
| 76530 |
+
"epoch": 12.451282051282051,
|
| 76531 |
+
"grad_norm": 0.23273898661136627,
|
| 76532 |
+
"learning_rate": 1.6772086090307898e-05,
|
| 76533 |
+
"loss": 0.5497,
|
| 76534 |
+
"step": 10932
|
| 76535 |
+
},
|
| 76536 |
+
{
|
| 76537 |
+
"epoch": 12.452421652421652,
|
| 76538 |
+
"grad_norm": 0.24793747067451477,
|
| 76539 |
+
"learning_rate": 1.6767686618307628e-05,
|
| 76540 |
+
"loss": 0.5743,
|
| 76541 |
+
"step": 10933
|
| 76542 |
+
},
|
| 76543 |
+
{
|
| 76544 |
+
"epoch": 12.453561253561254,
|
| 76545 |
+
"grad_norm": 0.19684715569019318,
|
| 76546 |
+
"learning_rate": 1.676328743223823e-05,
|
| 76547 |
+
"loss": 0.8132,
|
| 76548 |
+
"step": 10934
|
| 76549 |
+
},
|
| 76550 |
+
{
|
| 76551 |
+
"epoch": 12.454700854700855,
|
| 76552 |
+
"grad_norm": 0.22554780542850494,
|
| 76553 |
+
"learning_rate": 1.675888853225252e-05,
|
| 76554 |
+
"loss": 0.623,
|
| 76555 |
+
"step": 10935
|
| 76556 |
+
},
|
| 76557 |
+
{
|
| 76558 |
+
"epoch": 12.455840455840455,
|
| 76559 |
+
"grad_norm": 0.2464742809534073,
|
| 76560 |
+
"learning_rate": 1.675448991850327e-05,
|
| 76561 |
+
"loss": 0.6751,
|
| 76562 |
+
"step": 10936
|
| 76563 |
+
},
|
| 76564 |
+
{
|
| 76565 |
+
"epoch": 12.456980056980058,
|
| 76566 |
+
"grad_norm": 0.19820618629455566,
|
| 76567 |
+
"learning_rate": 1.6750091591143263e-05,
|
| 76568 |
+
"loss": 0.6132,
|
| 76569 |
+
"step": 10937
|
| 76570 |
+
},
|
| 76571 |
+
{
|
| 76572 |
+
"epoch": 12.458119658119658,
|
| 76573 |
+
"grad_norm": 0.2199823409318924,
|
| 76574 |
+
"learning_rate": 1.674569355032526e-05,
|
| 76575 |
+
"loss": 0.7071,
|
| 76576 |
+
"step": 10938
|
| 76577 |
+
},
|
| 76578 |
+
{
|
| 76579 |
+
"epoch": 12.459259259259259,
|
| 76580 |
+
"grad_norm": 0.19806915521621704,
|
| 76581 |
+
"learning_rate": 1.674129579620201e-05,
|
| 76582 |
+
"loss": 0.6505,
|
| 76583 |
+
"step": 10939
|
| 76584 |
+
},
|
| 76585 |
+
{
|
| 76586 |
+
"epoch": 12.460398860398861,
|
| 76587 |
+
"grad_norm": 0.19808705151081085,
|
| 76588 |
+
"learning_rate": 1.6736898328926282e-05,
|
| 76589 |
+
"loss": 0.8088,
|
| 76590 |
+
"step": 10940
|
| 76591 |
+
},
|
| 76592 |
+
{
|
| 76593 |
+
"epoch": 12.461538461538462,
|
| 76594 |
+
"grad_norm": 0.21985428035259247,
|
| 76595 |
+
"learning_rate": 1.6732501148650795e-05,
|
| 76596 |
+
"loss": 0.6154,
|
| 76597 |
+
"step": 10941
|
| 76598 |
+
},
|
| 76599 |
+
{
|
| 76600 |
+
"epoch": 12.462678062678062,
|
| 76601 |
+
"grad_norm": 0.2526129484176636,
|
| 76602 |
+
"learning_rate": 1.6728104255528282e-05,
|
| 76603 |
+
"loss": 0.6772,
|
| 76604 |
+
"step": 10942
|
| 76605 |
+
},
|
| 76606 |
+
{
|
| 76607 |
+
"epoch": 12.463817663817665,
|
| 76608 |
+
"grad_norm": 0.28405681252479553,
|
| 76609 |
+
"learning_rate": 1.672370764971145e-05,
|
| 76610 |
+
"loss": 0.5673,
|
| 76611 |
+
"step": 10943
|
| 76612 |
+
},
|
| 76613 |
+
{
|
| 76614 |
+
"epoch": 12.464957264957265,
|
| 76615 |
+
"grad_norm": 0.1978614330291748,
|
| 76616 |
+
"learning_rate": 1.671931133135302e-05,
|
| 76617 |
+
"loss": 0.8093,
|
| 76618 |
+
"step": 10944
|
| 76619 |
+
},
|
| 76620 |
+
{
|
| 76621 |
+
"epoch": 12.466096866096866,
|
| 76622 |
+
"grad_norm": 0.20405744016170502,
|
| 76623 |
+
"learning_rate": 1.671491530060567e-05,
|
| 76624 |
+
"loss": 0.6331,
|
| 76625 |
+
"step": 10945
|
| 76626 |
+
},
|
| 76627 |
+
{
|
| 76628 |
+
"epoch": 12.467236467236468,
|
| 76629 |
+
"grad_norm": 0.17509637773036957,
|
| 76630 |
+
"learning_rate": 1.67105195576221e-05,
|
| 76631 |
+
"loss": 0.8965,
|
| 76632 |
+
"step": 10946
|
| 76633 |
+
},
|
| 76634 |
+
{
|
| 76635 |
+
"epoch": 12.468376068376068,
|
| 76636 |
+
"grad_norm": 0.2595173418521881,
|
| 76637 |
+
"learning_rate": 1.6706124102554983e-05,
|
| 76638 |
+
"loss": 0.5936,
|
| 76639 |
+
"step": 10947
|
| 76640 |
+
},
|
| 76641 |
+
{
|
| 76642 |
+
"epoch": 12.469515669515669,
|
| 76643 |
+
"grad_norm": 0.1783231645822525,
|
| 76644 |
+
"learning_rate": 1.6701728935556984e-05,
|
| 76645 |
+
"loss": 0.6488,
|
| 76646 |
+
"step": 10948
|
| 76647 |
+
},
|
| 76648 |
+
{
|
| 76649 |
+
"epoch": 12.470655270655271,
|
| 76650 |
+
"grad_norm": 0.18801869451999664,
|
| 76651 |
+
"learning_rate": 1.6697334056780755e-05,
|
| 76652 |
+
"loss": 0.6566,
|
| 76653 |
+
"step": 10949
|
| 76654 |
+
},
|
| 76655 |
+
{
|
| 76656 |
+
"epoch": 12.471794871794872,
|
| 76657 |
+
"grad_norm": 0.20684203505516052,
|
| 76658 |
+
"learning_rate": 1.6692939466378944e-05,
|
| 76659 |
+
"loss": 0.7693,
|
| 76660 |
+
"step": 10950
|
| 76661 |
+
},
|
| 76662 |
+
{
|
| 76663 |
+
"epoch": 12.472934472934472,
|
| 76664 |
+
"grad_norm": 0.2421393096446991,
|
| 76665 |
+
"learning_rate": 1.6688545164504194e-05,
|
| 76666 |
+
"loss": 0.5507,
|
| 76667 |
+
"step": 10951
|
| 76668 |
+
},
|
| 76669 |
+
{
|
| 76670 |
+
"epoch": 12.474074074074075,
|
| 76671 |
+
"grad_norm": 0.2938486337661743,
|
| 76672 |
+
"learning_rate": 1.668415115130913e-05,
|
| 76673 |
+
"loss": 0.4418,
|
| 76674 |
+
"step": 10952
|
| 76675 |
+
},
|
| 76676 |
+
{
|
| 76677 |
+
"epoch": 12.475213675213675,
|
| 76678 |
+
"grad_norm": 0.20215126872062683,
|
| 76679 |
+
"learning_rate": 1.6679757426946362e-05,
|
| 76680 |
+
"loss": 0.7922,
|
| 76681 |
+
"step": 10953
|
| 76682 |
+
},
|
| 76683 |
+
{
|
| 76684 |
+
"epoch": 12.476353276353276,
|
| 76685 |
+
"grad_norm": 0.19147877395153046,
|
| 76686 |
+
"learning_rate": 1.6675363991568503e-05,
|
| 76687 |
+
"loss": 0.5436,
|
| 76688 |
+
"step": 10954
|
| 76689 |
+
},
|
| 76690 |
+
{
|
| 76691 |
+
"epoch": 12.477492877492878,
|
| 76692 |
+
"grad_norm": 0.22713878750801086,
|
| 76693 |
+
"learning_rate": 1.6670970845328142e-05,
|
| 76694 |
+
"loss": 0.7034,
|
| 76695 |
+
"step": 10955
|
| 76696 |
+
},
|
| 76697 |
+
{
|
| 76698 |
+
"epoch": 12.478632478632479,
|
| 76699 |
+
"grad_norm": 0.2423946112394333,
|
| 76700 |
+
"learning_rate": 1.6666577988377875e-05,
|
| 76701 |
+
"loss": 0.525,
|
| 76702 |
+
"step": 10956
|
| 76703 |
+
},
|
| 76704 |
+
{
|
| 76705 |
+
"epoch": 12.47977207977208,
|
| 76706 |
+
"grad_norm": 0.2133038491010666,
|
| 76707 |
+
"learning_rate": 1.6662185420870265e-05,
|
| 76708 |
+
"loss": 0.5818,
|
| 76709 |
+
"step": 10957
|
| 76710 |
+
},
|
| 76711 |
+
{
|
| 76712 |
+
"epoch": 12.480911680911682,
|
| 76713 |
+
"grad_norm": 0.23854395747184753,
|
| 76714 |
+
"learning_rate": 1.6657793142957883e-05,
|
| 76715 |
+
"loss": 0.4953,
|
| 76716 |
+
"step": 10958
|
| 76717 |
+
},
|
| 76718 |
+
{
|
| 76719 |
+
"epoch": 12.482051282051282,
|
| 76720 |
+
"grad_norm": 0.24194027483463287,
|
| 76721 |
+
"learning_rate": 1.665340115479329e-05,
|
| 76722 |
+
"loss": 0.8131,
|
| 76723 |
+
"step": 10959
|
| 76724 |
+
},
|
| 76725 |
+
{
|
| 76726 |
+
"epoch": 12.483190883190883,
|
| 76727 |
+
"grad_norm": 0.190907284617424,
|
| 76728 |
+
"learning_rate": 1.664900945652903e-05,
|
| 76729 |
+
"loss": 0.9208,
|
| 76730 |
+
"step": 10960
|
| 76731 |
+
},
|
| 76732 |
+
{
|
| 76733 |
+
"epoch": 12.484330484330485,
|
| 76734 |
+
"grad_norm": 0.22213807702064514,
|
| 76735 |
+
"learning_rate": 1.6644618048317625e-05,
|
| 76736 |
+
"loss": 0.8089,
|
| 76737 |
+
"step": 10961
|
| 76738 |
+
},
|
| 76739 |
+
{
|
| 76740 |
+
"epoch": 12.485470085470086,
|
| 76741 |
+
"grad_norm": 0.20240817964076996,
|
| 76742 |
+
"learning_rate": 1.664022693031162e-05,
|
| 76743 |
+
"loss": 0.9218,
|
| 76744 |
+
"step": 10962
|
| 76745 |
+
},
|
| 76746 |
+
{
|
| 76747 |
+
"epoch": 12.486609686609686,
|
| 76748 |
+
"grad_norm": 0.22596926987171173,
|
| 76749 |
+
"learning_rate": 1.6635836102663527e-05,
|
| 76750 |
+
"loss": 0.6796,
|
| 76751 |
+
"step": 10963
|
| 76752 |
+
},
|
| 76753 |
+
{
|
| 76754 |
+
"epoch": 12.487749287749288,
|
| 76755 |
+
"grad_norm": 0.21198280155658722,
|
| 76756 |
+
"learning_rate": 1.6631445565525845e-05,
|
| 76757 |
+
"loss": 0.5697,
|
| 76758 |
+
"step": 10964
|
| 76759 |
+
},
|
| 76760 |
+
{
|
| 76761 |
+
"epoch": 12.488888888888889,
|
| 76762 |
+
"grad_norm": 0.19748011231422424,
|
| 76763 |
+
"learning_rate": 1.6627055319051076e-05,
|
| 76764 |
+
"loss": 0.5982,
|
| 76765 |
+
"step": 10965
|
| 76766 |
+
},
|
| 76767 |
+
{
|
| 76768 |
+
"epoch": 12.49002849002849,
|
| 76769 |
+
"grad_norm": 0.3053680956363678,
|
| 76770 |
+
"learning_rate": 1.6622665363391697e-05,
|
| 76771 |
+
"loss": 0.5573,
|
| 76772 |
+
"step": 10966
|
| 76773 |
+
},
|
| 76774 |
+
{
|
| 76775 |
+
"epoch": 12.491168091168092,
|
| 76776 |
+
"grad_norm": 0.22078709304332733,
|
| 76777 |
+
"learning_rate": 1.6618275698700193e-05,
|
| 76778 |
+
"loss": 0.9135,
|
| 76779 |
+
"step": 10967
|
| 76780 |
+
},
|
| 76781 |
+
{
|
| 76782 |
+
"epoch": 12.492307692307692,
|
| 76783 |
+
"grad_norm": 0.18783444166183472,
|
| 76784 |
+
"learning_rate": 1.6613886325129015e-05,
|
| 76785 |
+
"loss": 0.7731,
|
| 76786 |
+
"step": 10968
|
| 76787 |
+
},
|
| 76788 |
+
{
|
| 76789 |
+
"epoch": 12.493447293447293,
|
| 76790 |
+
"grad_norm": 0.2591036260128021,
|
| 76791 |
+
"learning_rate": 1.6609497242830633e-05,
|
| 76792 |
+
"loss": 0.5407,
|
| 76793 |
+
"step": 10969
|
| 76794 |
+
},
|
| 76795 |
+
{
|
| 76796 |
+
"epoch": 12.494586894586895,
|
| 76797 |
+
"grad_norm": 0.2199113816022873,
|
| 76798 |
+
"learning_rate": 1.6605108451957485e-05,
|
| 76799 |
+
"loss": 0.7096,
|
| 76800 |
+
"step": 10970
|
| 76801 |
+
},
|
| 76802 |
+
{
|
| 76803 |
+
"epoch": 12.495726495726496,
|
| 76804 |
+
"grad_norm": 0.2580206096172333,
|
| 76805 |
+
"learning_rate": 1.660071995266201e-05,
|
| 76806 |
+
"loss": 0.7711,
|
| 76807 |
+
"step": 10971
|
| 76808 |
+
},
|
| 76809 |
+
{
|
| 76810 |
+
"epoch": 12.496866096866096,
|
| 76811 |
+
"grad_norm": 0.2157939374446869,
|
| 76812 |
+
"learning_rate": 1.6596331745096615e-05,
|
| 76813 |
+
"loss": 0.7494,
|
| 76814 |
+
"step": 10972
|
| 76815 |
+
},
|
| 76816 |
+
{
|
| 76817 |
+
"epoch": 12.498005698005699,
|
| 76818 |
+
"grad_norm": 0.18810850381851196,
|
| 76819 |
+
"learning_rate": 1.6591943829413737e-05,
|
| 76820 |
+
"loss": 0.5819,
|
| 76821 |
+
"step": 10973
|
| 76822 |
+
},
|
| 76823 |
+
{
|
| 76824 |
+
"epoch": 12.4991452991453,
|
| 76825 |
+
"grad_norm": 0.23743487894535065,
|
| 76826 |
+
"learning_rate": 1.6587556205765777e-05,
|
| 76827 |
+
"loss": 0.5564,
|
| 76828 |
+
"step": 10974
|
| 76829 |
+
},
|
| 76830 |
+
{
|
| 76831 |
+
"epoch": 12.5002849002849,
|
| 76832 |
+
"grad_norm": 0.22389283776283264,
|
| 76833 |
+
"learning_rate": 1.6583168874305118e-05,
|
| 76834 |
+
"loss": 0.6437,
|
| 76835 |
+
"step": 10975
|
| 76836 |
+
},
|
| 76837 |
+
{
|
| 76838 |
+
"epoch": 12.501424501424502,
|
| 76839 |
+
"grad_norm": 0.19681458175182343,
|
| 76840 |
+
"learning_rate": 1.6578781835184155e-05,
|
| 76841 |
+
"loss": 0.7081,
|
| 76842 |
+
"step": 10976
|
| 76843 |
+
},
|
| 76844 |
+
{
|
| 76845 |
+
"epoch": 12.502564102564103,
|
| 76846 |
+
"grad_norm": 0.1927095651626587,
|
| 76847 |
+
"learning_rate": 1.6574395088555253e-05,
|
| 76848 |
+
"loss": 0.6656,
|
| 76849 |
+
"step": 10977
|
| 76850 |
+
},
|
| 76851 |
+
{
|
| 76852 |
+
"epoch": 12.503703703703703,
|
| 76853 |
+
"grad_norm": 0.17713747918605804,
|
| 76854 |
+
"learning_rate": 1.6570008634570786e-05,
|
| 76855 |
+
"loss": 0.7476,
|
| 76856 |
+
"step": 10978
|
| 76857 |
+
},
|
| 76858 |
+
{
|
| 76859 |
+
"epoch": 12.504843304843305,
|
| 76860 |
+
"grad_norm": 0.24266201257705688,
|
| 76861 |
+
"learning_rate": 1.6565622473383095e-05,
|
| 76862 |
+
"loss": 0.6614,
|
| 76863 |
+
"step": 10979
|
| 76864 |
+
},
|
| 76865 |
+
{
|
| 76866 |
+
"epoch": 12.505982905982906,
|
| 76867 |
+
"grad_norm": 0.1891140341758728,
|
| 76868 |
+
"learning_rate": 1.6561236605144537e-05,
|
| 76869 |
+
"loss": 0.8354,
|
| 76870 |
+
"step": 10980
|
| 76871 |
+
},
|
| 76872 |
+
{
|
| 76873 |
+
"epoch": 12.507122507122507,
|
| 76874 |
+
"grad_norm": 0.17886357009410858,
|
| 76875 |
+
"learning_rate": 1.655685103000743e-05,
|
| 76876 |
+
"loss": 0.5899,
|
| 76877 |
+
"step": 10981
|
| 76878 |
+
},
|
| 76879 |
+
{
|
| 76880 |
+
"epoch": 12.508262108262109,
|
| 76881 |
+
"grad_norm": 0.1950901299715042,
|
| 76882 |
+
"learning_rate": 1.6552465748124116e-05,
|
| 76883 |
+
"loss": 0.8008,
|
| 76884 |
+
"step": 10982
|
| 76885 |
+
},
|
| 76886 |
+
{
|
| 76887 |
+
"epoch": 12.50940170940171,
|
| 76888 |
+
"grad_norm": 0.22581149637699127,
|
| 76889 |
+
"learning_rate": 1.6548080759646883e-05,
|
| 76890 |
+
"loss": 0.5845,
|
| 76891 |
+
"step": 10983
|
| 76892 |
+
},
|
| 76893 |
+
{
|
| 76894 |
+
"epoch": 12.51054131054131,
|
| 76895 |
+
"grad_norm": 0.16622164845466614,
|
| 76896 |
+
"learning_rate": 1.6543696064728053e-05,
|
| 76897 |
+
"loss": 0.7195,
|
| 76898 |
+
"step": 10984
|
| 76899 |
+
},
|
| 76900 |
+
{
|
| 76901 |
+
"epoch": 12.511680911680912,
|
| 76902 |
+
"grad_norm": 0.1869547814130783,
|
| 76903 |
+
"learning_rate": 1.6539311663519925e-05,
|
| 76904 |
+
"loss": 0.8042,
|
| 76905 |
+
"step": 10985
|
| 76906 |
+
},
|
| 76907 |
+
{
|
| 76908 |
+
"epoch": 12.512820512820513,
|
| 76909 |
+
"grad_norm": 0.2045227736234665,
|
| 76910 |
+
"learning_rate": 1.6534927556174756e-05,
|
| 76911 |
+
"loss": 0.6094,
|
| 76912 |
+
"step": 10986
|
| 76913 |
+
},
|
| 76914 |
+
{
|
| 76915 |
+
"epoch": 12.513960113960113,
|
| 76916 |
+
"grad_norm": 0.2639092803001404,
|
| 76917 |
+
"learning_rate": 1.6530543742844843e-05,
|
| 76918 |
+
"loss": 0.4522,
|
| 76919 |
+
"step": 10987
|
| 76920 |
+
},
|
| 76921 |
+
{
|
| 76922 |
+
"epoch": 12.515099715099716,
|
| 76923 |
+
"grad_norm": 0.20233054459095,
|
| 76924 |
+
"learning_rate": 1.652616022368243e-05,
|
| 76925 |
+
"loss": 0.8569,
|
| 76926 |
+
"step": 10988
|
| 76927 |
+
},
|
| 76928 |
+
{
|
| 76929 |
+
"epoch": 12.516239316239316,
|
| 76930 |
+
"grad_norm": 0.19802075624465942,
|
| 76931 |
+
"learning_rate": 1.652177699883978e-05,
|
| 76932 |
+
"loss": 0.6387,
|
| 76933 |
+
"step": 10989
|
| 76934 |
+
},
|
| 76935 |
+
{
|
| 76936 |
+
"epoch": 12.517378917378917,
|
| 76937 |
+
"grad_norm": 0.20674096047878265,
|
| 76938 |
+
"learning_rate": 1.6517394068469128e-05,
|
| 76939 |
+
"loss": 0.8587,
|
| 76940 |
+
"step": 10990
|
| 76941 |
+
},
|
| 76942 |
+
{
|
| 76943 |
+
"epoch": 12.518518518518519,
|
| 76944 |
+
"grad_norm": 0.20811493694782257,
|
| 76945 |
+
"learning_rate": 1.6513011432722708e-05,
|
| 76946 |
+
"loss": 0.7051,
|
| 76947 |
+
"step": 10991
|
| 76948 |
+
},
|
| 76949 |
+
{
|
| 76950 |
+
"epoch": 12.51965811965812,
|
| 76951 |
+
"grad_norm": 0.18526801466941833,
|
| 76952 |
+
"learning_rate": 1.6508629091752736e-05,
|
| 76953 |
+
"loss": 0.6825,
|
| 76954 |
+
"step": 10992
|
| 76955 |
+
},
|
| 76956 |
+
{
|
| 76957 |
+
"epoch": 12.52079772079772,
|
| 76958 |
+
"grad_norm": 0.2324620634317398,
|
| 76959 |
+
"learning_rate": 1.650424704571143e-05,
|
| 76960 |
+
"loss": 0.6098,
|
| 76961 |
+
"step": 10993
|
| 76962 |
+
},
|
| 76963 |
+
{
|
| 76964 |
+
"epoch": 12.521937321937322,
|
| 76965 |
+
"grad_norm": 0.22030244767665863,
|
| 76966 |
+
"learning_rate": 1.649986529475098e-05,
|
| 76967 |
+
"loss": 0.5876,
|
| 76968 |
+
"step": 10994
|
| 76969 |
+
},
|
| 76970 |
+
{
|
| 76971 |
+
"epoch": 12.523076923076923,
|
| 76972 |
+
"grad_norm": 0.20725619792938232,
|
| 76973 |
+
"learning_rate": 1.6495483839023595e-05,
|
| 76974 |
+
"loss": 0.6561,
|
| 76975 |
+
"step": 10995
|
| 76976 |
+
},
|
| 76977 |
+
{
|
| 76978 |
+
"epoch": 12.524216524216524,
|
| 76979 |
+
"grad_norm": 0.19436527788639069,
|
| 76980 |
+
"learning_rate": 1.6491102678681436e-05,
|
| 76981 |
+
"loss": 0.6815,
|
| 76982 |
+
"step": 10996
|
| 76983 |
+
},
|
| 76984 |
+
{
|
| 76985 |
+
"epoch": 12.525356125356126,
|
| 76986 |
+
"grad_norm": 0.2555645704269409,
|
| 76987 |
+
"learning_rate": 1.6486721813876686e-05,
|
| 76988 |
+
"loss": 0.4067,
|
| 76989 |
+
"step": 10997
|
| 76990 |
+
},
|
| 76991 |
+
{
|
| 76992 |
+
"epoch": 12.526495726495726,
|
| 76993 |
+
"grad_norm": 0.2308678776025772,
|
| 76994 |
+
"learning_rate": 1.6482341244761502e-05,
|
| 76995 |
+
"loss": 0.7071,
|
| 76996 |
+
"step": 10998
|
| 76997 |
+
},
|
| 76998 |
+
{
|
| 76999 |
+
"epoch": 12.527635327635327,
|
| 77000 |
+
"grad_norm": 0.2093668431043625,
|
| 77001 |
+
"learning_rate": 1.6477960971488028e-05,
|
| 77002 |
+
"loss": 0.6203,
|
| 77003 |
+
"step": 10999
|
| 77004 |
+
},
|
| 77005 |
+
{
|
| 77006 |
+
"epoch": 12.52877492877493,
|
| 77007 |
+
"grad_norm": 0.26428475975990295,
|
| 77008 |
+
"learning_rate": 1.6473580994208398e-05,
|
| 77009 |
+
"loss": 0.3758,
|
| 77010 |
+
"step": 11000
|
| 77011 |
+
},
|
| 77012 |
+
{
|
| 77013 |
+
"epoch": 12.52991452991453,
|
| 77014 |
+
"grad_norm": 0.22192619740962982,
|
| 77015 |
+
"learning_rate": 1.6469201313074756e-05,
|
| 77016 |
+
"loss": 0.5943,
|
| 77017 |
+
"step": 11001
|
| 77018 |
+
},
|
| 77019 |
+
{
|
| 77020 |
+
"epoch": 12.53105413105413,
|
| 77021 |
+
"grad_norm": 0.2347877025604248,
|
| 77022 |
+
"learning_rate": 1.646482192823921e-05,
|
| 77023 |
+
"loss": 0.7203,
|
| 77024 |
+
"step": 11002
|
| 77025 |
+
},
|
| 77026 |
+
{
|
| 77027 |
+
"epoch": 12.532193732193733,
|
| 77028 |
+
"grad_norm": 0.20047219097614288,
|
| 77029 |
+
"learning_rate": 1.646044283985387e-05,
|
| 77030 |
+
"loss": 0.6711,
|
| 77031 |
+
"step": 11003
|
| 77032 |
+
},
|
| 77033 |
+
{
|
| 77034 |
+
"epoch": 12.533333333333333,
|
| 77035 |
+
"grad_norm": 0.2244284749031067,
|
| 77036 |
+
"learning_rate": 1.6456064048070832e-05,
|
| 77037 |
+
"loss": 0.4248,
|
| 77038 |
+
"step": 11004
|
| 77039 |
+
},
|
| 77040 |
+
{
|
| 77041 |
+
"epoch": 12.534472934472934,
|
| 77042 |
+
"grad_norm": 0.1928756833076477,
|
| 77043 |
+
"learning_rate": 1.645168555304218e-05,
|
| 77044 |
+
"loss": 0.8309,
|
| 77045 |
+
"step": 11005
|
| 77046 |
+
},
|
| 77047 |
+
{
|
| 77048 |
+
"epoch": 12.535612535612536,
|
| 77049 |
+
"grad_norm": 0.24166139960289001,
|
| 77050 |
+
"learning_rate": 1.6447307354920005e-05,
|
| 77051 |
+
"loss": 0.49,
|
| 77052 |
+
"step": 11006
|
| 77053 |
+
},
|
| 77054 |
+
{
|
| 77055 |
+
"epoch": 12.536752136752137,
|
| 77056 |
+
"grad_norm": 0.19183756411075592,
|
| 77057 |
+
"learning_rate": 1.6442929453856364e-05,
|
| 77058 |
+
"loss": 0.7716,
|
| 77059 |
+
"step": 11007
|
| 77060 |
+
},
|
| 77061 |
+
{
|
| 77062 |
+
"epoch": 12.537891737891737,
|
| 77063 |
+
"grad_norm": 0.21705985069274902,
|
| 77064 |
+
"learning_rate": 1.643855185000332e-05,
|
| 77065 |
+
"loss": 0.7428,
|
| 77066 |
+
"step": 11008
|
| 77067 |
+
},
|
| 77068 |
+
{
|
| 77069 |
+
"epoch": 12.53903133903134,
|
| 77070 |
+
"grad_norm": 0.1837446242570877,
|
| 77071 |
+
"learning_rate": 1.6434174543512905e-05,
|
| 77072 |
+
"loss": 0.6945,
|
| 77073 |
+
"step": 11009
|
| 77074 |
+
},
|
| 77075 |
+
{
|
| 77076 |
+
"epoch": 12.54017094017094,
|
| 77077 |
+
"grad_norm": 0.17365996539592743,
|
| 77078 |
+
"learning_rate": 1.6429797534537172e-05,
|
| 77079 |
+
"loss": 0.8055,
|
| 77080 |
+
"step": 11010
|
| 77081 |
+
},
|
| 77082 |
+
{
|
| 77083 |
+
"epoch": 12.54131054131054,
|
| 77084 |
+
"grad_norm": 0.24148063361644745,
|
| 77085 |
+
"learning_rate": 1.642542082322813e-05,
|
| 77086 |
+
"loss": 0.83,
|
| 77087 |
+
"step": 11011
|
| 77088 |
+
},
|
| 77089 |
+
{
|
| 77090 |
+
"epoch": 12.542450142450143,
|
| 77091 |
+
"grad_norm": 0.24556422233581543,
|
| 77092 |
+
"learning_rate": 1.6421044409737817e-05,
|
| 77093 |
+
"loss": 0.5919,
|
| 77094 |
+
"step": 11012
|
| 77095 |
+
},
|
| 77096 |
+
{
|
| 77097 |
+
"epoch": 12.543589743589743,
|
| 77098 |
+
"grad_norm": 0.2238049954175949,
|
| 77099 |
+
"learning_rate": 1.6416668294218213e-05,
|
| 77100 |
+
"loss": 0.6238,
|
| 77101 |
+
"step": 11013
|
| 77102 |
+
},
|
| 77103 |
+
{
|
| 77104 |
+
"epoch": 12.544729344729344,
|
| 77105 |
+
"grad_norm": 0.2636539340019226,
|
| 77106 |
+
"learning_rate": 1.6412292476821328e-05,
|
| 77107 |
+
"loss": 0.4099,
|
| 77108 |
+
"step": 11014
|
| 77109 |
+
},
|
| 77110 |
+
{
|
| 77111 |
+
"epoch": 12.545868945868946,
|
| 77112 |
+
"grad_norm": 0.17827825248241425,
|
| 77113 |
+
"learning_rate": 1.6407916957699136e-05,
|
| 77114 |
+
"loss": 0.8987,
|
| 77115 |
+
"step": 11015
|
| 77116 |
+
},
|
| 77117 |
+
{
|
| 77118 |
+
"epoch": 12.547008547008547,
|
| 77119 |
+
"grad_norm": 0.2063855081796646,
|
| 77120 |
+
"learning_rate": 1.6403541737003613e-05,
|
| 77121 |
+
"loss": 0.6717,
|
| 77122 |
+
"step": 11016
|
| 77123 |
+
},
|
| 77124 |
+
{
|
| 77125 |
+
"epoch": 12.548148148148147,
|
| 77126 |
+
"grad_norm": 0.2015405148267746,
|
| 77127 |
+
"learning_rate": 1.6399166814886736e-05,
|
| 77128 |
+
"loss": 0.6795,
|
| 77129 |
+
"step": 11017
|
| 77130 |
+
},
|
| 77131 |
+
{
|
| 77132 |
+
"epoch": 12.54928774928775,
|
| 77133 |
+
"grad_norm": 0.1882464587688446,
|
| 77134 |
+
"learning_rate": 1.6394792191500443e-05,
|
| 77135 |
+
"loss": 0.6898,
|
| 77136 |
+
"step": 11018
|
| 77137 |
+
},
|
| 77138 |
+
{
|
| 77139 |
+
"epoch": 12.55042735042735,
|
| 77140 |
+
"grad_norm": 0.2405157834291458,
|
| 77141 |
+
"learning_rate": 1.639041786699669e-05,
|
| 77142 |
+
"loss": 0.738,
|
| 77143 |
+
"step": 11019
|
| 77144 |
+
},
|
| 77145 |
+
{
|
| 77146 |
+
"epoch": 12.55156695156695,
|
| 77147 |
+
"grad_norm": 0.2269430160522461,
|
| 77148 |
+
"learning_rate": 1.638604384152739e-05,
|
| 77149 |
+
"loss": 0.66,
|
| 77150 |
+
"step": 11020
|
| 77151 |
+
},
|
| 77152 |
+
{
|
| 77153 |
+
"epoch": 12.552706552706553,
|
| 77154 |
+
"grad_norm": 0.24743977189064026,
|
| 77155 |
+
"learning_rate": 1.638167011524448e-05,
|
| 77156 |
+
"loss": 0.3647,
|
| 77157 |
+
"step": 11021
|
| 77158 |
+
},
|
| 77159 |
+
{
|
| 77160 |
+
"epoch": 12.553846153846154,
|
| 77161 |
+
"grad_norm": 0.2229391634464264,
|
| 77162 |
+
"learning_rate": 1.6377296688299866e-05,
|
| 77163 |
+
"loss": 0.8568,
|
| 77164 |
+
"step": 11022
|
| 77165 |
+
},
|
| 77166 |
+
{
|
| 77167 |
+
"epoch": 12.554985754985754,
|
| 77168 |
+
"grad_norm": 0.2505655884742737,
|
| 77169 |
+
"learning_rate": 1.6372923560845454e-05,
|
| 77170 |
+
"loss": 0.5591,
|
| 77171 |
+
"step": 11023
|
| 77172 |
+
},
|
| 77173 |
+
{
|
| 77174 |
+
"epoch": 12.556125356125357,
|
| 77175 |
+
"grad_norm": 0.23933634161949158,
|
| 77176 |
+
"learning_rate": 1.636855073303313e-05,
|
| 77177 |
+
"loss": 0.7009,
|
| 77178 |
+
"step": 11024
|
| 77179 |
+
},
|
| 77180 |
+
{
|
| 77181 |
+
"epoch": 12.557264957264957,
|
| 77182 |
+
"grad_norm": 0.2654150128364563,
|
| 77183 |
+
"learning_rate": 1.636417820501478e-05,
|
| 77184 |
+
"loss": 0.5882,
|
| 77185 |
+
"step": 11025
|
| 77186 |
+
},
|
| 77187 |
+
{
|
| 77188 |
+
"epoch": 12.558404558404558,
|
| 77189 |
+
"grad_norm": 0.1851956993341446,
|
| 77190 |
+
"learning_rate": 1.635980597694226e-05,
|
| 77191 |
+
"loss": 0.8961,
|
| 77192 |
+
"step": 11026
|
| 77193 |
+
},
|
| 77194 |
+
{
|
| 77195 |
+
"epoch": 12.55954415954416,
|
| 77196 |
+
"grad_norm": 0.2490128129720688,
|
| 77197 |
+
"learning_rate": 1.6355434048967434e-05,
|
| 77198 |
+
"loss": 0.6622,
|
| 77199 |
+
"step": 11027
|
| 77200 |
+
},
|
| 77201 |
+
{
|
| 77202 |
+
"epoch": 12.56068376068376,
|
| 77203 |
+
"grad_norm": 0.19830764830112457,
|
| 77204 |
+
"learning_rate": 1.6351062421242162e-05,
|
| 77205 |
+
"loss": 0.631,
|
| 77206 |
+
"step": 11028
|
| 77207 |
+
},
|
| 77208 |
+
{
|
| 77209 |
+
"epoch": 12.561823361823361,
|
| 77210 |
+
"grad_norm": 0.17523930966854095,
|
| 77211 |
+
"learning_rate": 1.6346691093918287e-05,
|
| 77212 |
+
"loss": 0.8467,
|
| 77213 |
+
"step": 11029
|
| 77214 |
+
},
|
| 77215 |
+
{
|
| 77216 |
+
"epoch": 12.562962962962963,
|
| 77217 |
+
"grad_norm": 0.19710446894168854,
|
| 77218 |
+
"learning_rate": 1.6342320067147618e-05,
|
| 77219 |
+
"loss": 0.7908,
|
| 77220 |
+
"step": 11030
|
| 77221 |
+
},
|
| 77222 |
+
{
|
| 77223 |
+
"epoch": 12.564102564102564,
|
| 77224 |
+
"grad_norm": 0.17316338419914246,
|
| 77225 |
+
"learning_rate": 1.6337949341081986e-05,
|
| 77226 |
+
"loss": 0.7468,
|
| 77227 |
+
"step": 11031
|
| 77228 |
+
},
|
| 77229 |
+
{
|
| 77230 |
+
"epoch": 12.565242165242164,
|
| 77231 |
+
"grad_norm": 0.21457502245903015,
|
| 77232 |
+
"learning_rate": 1.633357891587319e-05,
|
| 77233 |
+
"loss": 0.9224,
|
| 77234 |
+
"step": 11032
|
| 77235 |
+
},
|
| 77236 |
+
{
|
| 77237 |
+
"epoch": 12.566381766381767,
|
| 77238 |
+
"grad_norm": 0.24812400341033936,
|
| 77239 |
+
"learning_rate": 1.6329208791673037e-05,
|
| 77240 |
+
"loss": 0.519,
|
| 77241 |
+
"step": 11033
|
| 77242 |
+
},
|
| 77243 |
+
{
|
| 77244 |
+
"epoch": 12.567521367521367,
|
| 77245 |
+
"grad_norm": 0.22866606712341309,
|
| 77246 |
+
"learning_rate": 1.6324838968633303e-05,
|
| 77247 |
+
"loss": 0.5053,
|
| 77248 |
+
"step": 11034
|
| 77249 |
+
},
|
| 77250 |
+
{
|
| 77251 |
+
"epoch": 12.568660968660968,
|
| 77252 |
+
"grad_norm": 0.18968430161476135,
|
| 77253 |
+
"learning_rate": 1.6320469446905773e-05,
|
| 77254 |
+
"loss": 0.9831,
|
| 77255 |
+
"step": 11035
|
| 77256 |
+
},
|
| 77257 |
+
{
|
| 77258 |
+
"epoch": 12.56980056980057,
|
| 77259 |
+
"grad_norm": 0.20741485059261322,
|
| 77260 |
+
"learning_rate": 1.63161002266422e-05,
|
| 77261 |
+
"loss": 0.8396,
|
| 77262 |
+
"step": 11036
|
| 77263 |
+
},
|
| 77264 |
+
{
|
| 77265 |
+
"epoch": 12.57094017094017,
|
| 77266 |
+
"grad_norm": 0.16728100180625916,
|
| 77267 |
+
"learning_rate": 1.6311731307994356e-05,
|
| 77268 |
+
"loss": 0.8375,
|
| 77269 |
+
"step": 11037
|
| 77270 |
+
},
|
| 77271 |
+
{
|
| 77272 |
+
"epoch": 12.572079772079771,
|
| 77273 |
+
"grad_norm": 0.21869726479053497,
|
| 77274 |
+
"learning_rate": 1.6307362691113967e-05,
|
| 77275 |
+
"loss": 0.7689,
|
| 77276 |
+
"step": 11038
|
| 77277 |
+
},
|
| 77278 |
+
{
|
| 77279 |
+
"epoch": 12.573219373219374,
|
| 77280 |
+
"grad_norm": 0.2434314489364624,
|
| 77281 |
+
"learning_rate": 1.6302994376152776e-05,
|
| 77282 |
+
"loss": 0.7189,
|
| 77283 |
+
"step": 11039
|
| 77284 |
+
},
|
| 77285 |
+
{
|
| 77286 |
+
"epoch": 12.574358974358974,
|
| 77287 |
+
"grad_norm": 0.18562611937522888,
|
| 77288 |
+
"learning_rate": 1.6298626363262515e-05,
|
| 77289 |
+
"loss": 0.6075,
|
| 77290 |
+
"step": 11040
|
| 77291 |
+
},
|
| 77292 |
+
{
|
| 77293 |
+
"epoch": 12.575498575498575,
|
| 77294 |
+
"grad_norm": 0.2555478811264038,
|
| 77295 |
+
"learning_rate": 1.6294258652594883e-05,
|
| 77296 |
+
"loss": 0.5631,
|
| 77297 |
+
"step": 11041
|
| 77298 |
+
},
|
| 77299 |
+
{
|
| 77300 |
+
"epoch": 12.576638176638177,
|
| 77301 |
+
"grad_norm": 0.2179694026708603,
|
| 77302 |
+
"learning_rate": 1.6289891244301595e-05,
|
| 77303 |
+
"loss": 0.7161,
|
| 77304 |
+
"step": 11042
|
| 77305 |
+
},
|
| 77306 |
+
{
|
| 77307 |
+
"epoch": 12.577777777777778,
|
| 77308 |
+
"grad_norm": 0.250118613243103,
|
| 77309 |
+
"learning_rate": 1.628552413853433e-05,
|
| 77310 |
+
"loss": 0.7754,
|
| 77311 |
+
"step": 11043
|
| 77312 |
+
},
|
| 77313 |
+
{
|
| 77314 |
+
"epoch": 12.578917378917378,
|
| 77315 |
+
"grad_norm": 0.20918738842010498,
|
| 77316 |
+
"learning_rate": 1.6281157335444785e-05,
|
| 77317 |
+
"loss": 0.6769,
|
| 77318 |
+
"step": 11044
|
| 77319 |
+
},
|
| 77320 |
+
{
|
| 77321 |
+
"epoch": 12.58005698005698,
|
| 77322 |
+
"grad_norm": 0.2173689305782318,
|
| 77323 |
+
"learning_rate": 1.627679083518462e-05,
|
| 77324 |
+
"loss": 0.8834,
|
| 77325 |
+
"step": 11045
|
| 77326 |
+
},
|
| 77327 |
+
{
|
| 77328 |
+
"epoch": 12.581196581196581,
|
| 77329 |
+
"grad_norm": 0.252636581659317,
|
| 77330 |
+
"learning_rate": 1.62724246379055e-05,
|
| 77331 |
+
"loss": 0.6731,
|
| 77332 |
+
"step": 11046
|
| 77333 |
+
},
|
| 77334 |
+
{
|
| 77335 |
+
"epoch": 12.582336182336181,
|
| 77336 |
+
"grad_norm": 0.2242475003004074,
|
| 77337 |
+
"learning_rate": 1.6268058743759064e-05,
|
| 77338 |
+
"loss": 0.6637,
|
| 77339 |
+
"step": 11047
|
| 77340 |
+
},
|
| 77341 |
+
{
|
| 77342 |
+
"epoch": 12.583475783475784,
|
| 77343 |
+
"grad_norm": 0.21343784034252167,
|
| 77344 |
+
"learning_rate": 1.626369315289697e-05,
|
| 77345 |
+
"loss": 0.6821,
|
| 77346 |
+
"step": 11048
|
| 77347 |
+
},
|
| 77348 |
+
{
|
| 77349 |
+
"epoch": 12.584615384615384,
|
| 77350 |
+
"grad_norm": 0.20597362518310547,
|
| 77351 |
+
"learning_rate": 1.6259327865470834e-05,
|
| 77352 |
+
"loss": 0.7599,
|
| 77353 |
+
"step": 11049
|
| 77354 |
+
},
|
| 77355 |
+
{
|
| 77356 |
+
"epoch": 12.585754985754985,
|
| 77357 |
+
"grad_norm": 0.19783805310726166,
|
| 77358 |
+
"learning_rate": 1.625496288163227e-05,
|
| 77359 |
+
"loss": 0.8005,
|
| 77360 |
+
"step": 11050
|
| 77361 |
+
},
|
| 77362 |
+
{
|
| 77363 |
+
"epoch": 12.586894586894587,
|
| 77364 |
+
"grad_norm": 0.20493733882904053,
|
| 77365 |
+
"learning_rate": 1.6250598201532907e-05,
|
| 77366 |
+
"loss": 0.8026,
|
| 77367 |
+
"step": 11051
|
| 77368 |
+
},
|
| 77369 |
+
{
|
| 77370 |
+
"epoch": 12.588034188034188,
|
| 77371 |
+
"grad_norm": 0.20619259774684906,
|
| 77372 |
+
"learning_rate": 1.6246233825324324e-05,
|
| 77373 |
+
"loss": 0.6866,
|
| 77374 |
+
"step": 11052
|
| 77375 |
+
},
|
| 77376 |
+
{
|
| 77377 |
+
"epoch": 12.589173789173788,
|
| 77378 |
+
"grad_norm": 0.16386501491069794,
|
| 77379 |
+
"learning_rate": 1.624186975315812e-05,
|
| 77380 |
+
"loss": 0.6641,
|
| 77381 |
+
"step": 11053
|
| 77382 |
+
},
|
| 77383 |
+
{
|
| 77384 |
+
"epoch": 12.59031339031339,
|
| 77385 |
+
"grad_norm": 0.1730891913175583,
|
| 77386 |
+
"learning_rate": 1.6237505985185853e-05,
|
| 77387 |
+
"loss": 0.7881,
|
| 77388 |
+
"step": 11054
|
| 77389 |
+
},
|
| 77390 |
+
{
|
| 77391 |
+
"epoch": 12.591452991452991,
|
| 77392 |
+
"grad_norm": 0.19879373908042908,
|
| 77393 |
+
"learning_rate": 1.6233142521559108e-05,
|
| 77394 |
+
"loss": 0.7469,
|
| 77395 |
+
"step": 11055
|
| 77396 |
+
},
|
| 77397 |
+
{
|
| 77398 |
+
"epoch": 12.592592592592592,
|
| 77399 |
+
"grad_norm": 0.27814745903015137,
|
| 77400 |
+
"learning_rate": 1.622877936242943e-05,
|
| 77401 |
+
"loss": 0.6045,
|
| 77402 |
+
"step": 11056
|
| 77403 |
+
},
|
| 77404 |
+
{
|
| 77405 |
+
"epoch": 12.593732193732194,
|
| 77406 |
+
"grad_norm": 0.16927435994148254,
|
| 77407 |
+
"learning_rate": 1.6224416507948366e-05,
|
| 77408 |
+
"loss": 0.8278,
|
| 77409 |
+
"step": 11057
|
| 77410 |
+
},
|
| 77411 |
+
{
|
| 77412 |
+
"epoch": 12.594871794871795,
|
| 77413 |
+
"grad_norm": 0.16074690222740173,
|
| 77414 |
+
"learning_rate": 1.6220053958267447e-05,
|
| 77415 |
+
"loss": 0.8925,
|
| 77416 |
+
"step": 11058
|
| 77417 |
+
},
|
| 77418 |
+
{
|
| 77419 |
+
"epoch": 12.596011396011395,
|
| 77420 |
+
"grad_norm": 0.23557724058628082,
|
| 77421 |
+
"learning_rate": 1.6215691713538207e-05,
|
| 77422 |
+
"loss": 0.5533,
|
| 77423 |
+
"step": 11059
|
| 77424 |
+
},
|
| 77425 |
+
{
|
| 77426 |
+
"epoch": 12.597150997150997,
|
| 77427 |
+
"grad_norm": 0.18923786282539368,
|
| 77428 |
+
"learning_rate": 1.621132977391214e-05,
|
| 77429 |
+
"loss": 0.7038,
|
| 77430 |
+
"step": 11060
|
| 77431 |
+
},
|
| 77432 |
+
{
|
| 77433 |
+
"epoch": 12.598290598290598,
|
| 77434 |
+
"grad_norm": 0.2361970990896225,
|
| 77435 |
+
"learning_rate": 1.6206968139540758e-05,
|
| 77436 |
+
"loss": 0.6842,
|
| 77437 |
+
"step": 11061
|
| 77438 |
+
},
|
| 77439 |
+
{
|
| 77440 |
+
"epoch": 12.5994301994302,
|
| 77441 |
+
"grad_norm": 0.23810768127441406,
|
| 77442 |
+
"learning_rate": 1.6202606810575564e-05,
|
| 77443 |
+
"loss": 0.5675,
|
| 77444 |
+
"step": 11062
|
| 77445 |
+
},
|
| 77446 |
+
{
|
| 77447 |
+
"epoch": 12.6005698005698,
|
| 77448 |
+
"grad_norm": 0.1956935077905655,
|
| 77449 |
+
"learning_rate": 1.619824578716802e-05,
|
| 77450 |
+
"loss": 0.885,
|
| 77451 |
+
"step": 11063
|
| 77452 |
+
},
|
| 77453 |
+
{
|
| 77454 |
+
"epoch": 12.601709401709401,
|
| 77455 |
+
"grad_norm": 0.2303309291601181,
|
| 77456 |
+
"learning_rate": 1.619388506946961e-05,
|
| 77457 |
+
"loss": 0.6753,
|
| 77458 |
+
"step": 11064
|
| 77459 |
+
},
|
| 77460 |
+
{
|
| 77461 |
+
"epoch": 12.602849002849004,
|
| 77462 |
+
"grad_norm": 0.2104651927947998,
|
| 77463 |
+
"learning_rate": 1.618952465763179e-05,
|
| 77464 |
+
"loss": 0.622,
|
| 77465 |
+
"step": 11065
|
| 77466 |
+
},
|
| 77467 |
+
{
|
| 77468 |
+
"epoch": 12.603988603988604,
|
| 77469 |
+
"grad_norm": 0.20536163449287415,
|
| 77470 |
+
"learning_rate": 1.6185164551806004e-05,
|
| 77471 |
+
"loss": 0.6924,
|
| 77472 |
+
"step": 11066
|
| 77473 |
+
},
|
| 77474 |
+
{
|
| 77475 |
+
"epoch": 12.605128205128205,
|
| 77476 |
+
"grad_norm": 0.2689109146595001,
|
| 77477 |
+
"learning_rate": 1.6180804752143692e-05,
|
| 77478 |
+
"loss": 0.4751,
|
| 77479 |
+
"step": 11067
|
| 77480 |
+
},
|
| 77481 |
+
{
|
| 77482 |
+
"epoch": 12.606267806267807,
|
| 77483 |
+
"grad_norm": 0.17425256967544556,
|
| 77484 |
+
"learning_rate": 1.617644525879629e-05,
|
| 77485 |
+
"loss": 0.7078,
|
| 77486 |
+
"step": 11068
|
| 77487 |
+
},
|
| 77488 |
+
{
|
| 77489 |
+
"epoch": 12.607407407407408,
|
| 77490 |
+
"grad_norm": 0.22629356384277344,
|
| 77491 |
+
"learning_rate": 1.6172086071915204e-05,
|
| 77492 |
+
"loss": 0.7829,
|
| 77493 |
+
"step": 11069
|
| 77494 |
+
},
|
| 77495 |
+
{
|
| 77496 |
+
"epoch": 12.608547008547008,
|
| 77497 |
+
"grad_norm": 0.2518870234489441,
|
| 77498 |
+
"learning_rate": 1.6167727191651848e-05,
|
| 77499 |
+
"loss": 0.577,
|
| 77500 |
+
"step": 11070
|
| 77501 |
+
},
|
| 77502 |
+
{
|
| 77503 |
+
"epoch": 12.60968660968661,
|
| 77504 |
+
"grad_norm": 0.17481626570224762,
|
| 77505 |
+
"learning_rate": 1.6163368618157615e-05,
|
| 77506 |
+
"loss": 0.6537,
|
| 77507 |
+
"step": 11071
|
| 77508 |
+
},
|
| 77509 |
+
{
|
| 77510 |
+
"epoch": 12.610826210826211,
|
| 77511 |
+
"grad_norm": 0.2701930105686188,
|
| 77512 |
+
"learning_rate": 1.615901035158388e-05,
|
| 77513 |
+
"loss": 0.5066,
|
| 77514 |
+
"step": 11072
|
| 77515 |
+
},
|
| 77516 |
+
{
|
| 77517 |
+
"epoch": 12.611965811965812,
|
| 77518 |
+
"grad_norm": 0.17483319342136383,
|
| 77519 |
+
"learning_rate": 1.6154652392082036e-05,
|
| 77520 |
+
"loss": 0.7244,
|
| 77521 |
+
"step": 11073
|
| 77522 |
+
},
|
| 77523 |
+
{
|
| 77524 |
+
"epoch": 12.613105413105414,
|
| 77525 |
+
"grad_norm": 0.21778984367847443,
|
| 77526 |
+
"learning_rate": 1.6150294739803445e-05,
|
| 77527 |
+
"loss": 0.6299,
|
| 77528 |
+
"step": 11074
|
| 77529 |
+
},
|
| 77530 |
+
{
|
| 77531 |
+
"epoch": 12.614245014245014,
|
| 77532 |
+
"grad_norm": 0.22433669865131378,
|
| 77533 |
+
"learning_rate": 1.614593739489945e-05,
|
| 77534 |
+
"loss": 0.7286,
|
| 77535 |
+
"step": 11075
|
| 77536 |
+
},
|
| 77537 |
+
{
|
| 77538 |
+
"epoch": 12.615384615384615,
|
| 77539 |
+
"grad_norm": 0.22760696709156036,
|
| 77540 |
+
"learning_rate": 1.6141580357521403e-05,
|
| 77541 |
+
"loss": 0.7473,
|
| 77542 |
+
"step": 11076
|
| 77543 |
+
},
|
| 77544 |
+
{
|
| 77545 |
+
"epoch": 12.616524216524217,
|
| 77546 |
+
"grad_norm": 0.1692415028810501,
|
| 77547 |
+
"learning_rate": 1.6137223627820626e-05,
|
| 77548 |
+
"loss": 0.8738,
|
| 77549 |
+
"step": 11077
|
| 77550 |
+
},
|
| 77551 |
+
{
|
| 77552 |
+
"epoch": 12.617663817663818,
|
| 77553 |
+
"grad_norm": 0.48261013627052307,
|
| 77554 |
+
"learning_rate": 1.6132867205948447e-05,
|
| 77555 |
+
"loss": 0.5273,
|
| 77556 |
+
"step": 11078
|
| 77557 |
+
},
|
| 77558 |
+
{
|
| 77559 |
+
"epoch": 12.618803418803418,
|
| 77560 |
+
"grad_norm": 0.21189595758914948,
|
| 77561 |
+
"learning_rate": 1.6128511092056174e-05,
|
| 77562 |
+
"loss": 0.779,
|
| 77563 |
+
"step": 11079
|
| 77564 |
+
},
|
| 77565 |
+
{
|
| 77566 |
+
"epoch": 12.61994301994302,
|
| 77567 |
+
"grad_norm": 0.24352779984474182,
|
| 77568 |
+
"learning_rate": 1.6124155286295107e-05,
|
| 77569 |
+
"loss": 0.6357,
|
| 77570 |
+
"step": 11080
|
| 77571 |
+
},
|
| 77572 |
+
{
|
| 77573 |
+
"epoch": 12.621082621082621,
|
| 77574 |
+
"grad_norm": 0.1993314027786255,
|
| 77575 |
+
"learning_rate": 1.6119799788816537e-05,
|
| 77576 |
+
"loss": 0.6663,
|
| 77577 |
+
"step": 11081
|
| 77578 |
+
},
|
| 77579 |
+
{
|
| 77580 |
+
"epoch": 12.622222222222222,
|
| 77581 |
+
"grad_norm": 0.23018746078014374,
|
| 77582 |
+
"learning_rate": 1.6115444599771743e-05,
|
| 77583 |
+
"loss": 0.5983,
|
| 77584 |
+
"step": 11082
|
| 77585 |
+
},
|
| 77586 |
+
{
|
| 77587 |
+
"epoch": 12.623361823361824,
|
| 77588 |
+
"grad_norm": 0.17441576719284058,
|
| 77589 |
+
"learning_rate": 1.611108971931198e-05,
|
| 77590 |
+
"loss": 0.7592,
|
| 77591 |
+
"step": 11083
|
| 77592 |
+
},
|
| 77593 |
+
{
|
| 77594 |
+
"epoch": 12.624501424501425,
|
| 77595 |
+
"grad_norm": 0.23152019083499908,
|
| 77596 |
+
"learning_rate": 1.610673514758852e-05,
|
| 77597 |
+
"loss": 0.8389,
|
| 77598 |
+
"step": 11084
|
| 77599 |
+
},
|
| 77600 |
+
{
|
| 77601 |
+
"epoch": 12.625641025641025,
|
| 77602 |
+
"grad_norm": 0.28077030181884766,
|
| 77603 |
+
"learning_rate": 1.610238088475261e-05,
|
| 77604 |
+
"loss": 0.5543,
|
| 77605 |
+
"step": 11085
|
| 77606 |
+
},
|
| 77607 |
+
{
|
| 77608 |
+
"epoch": 12.626780626780628,
|
| 77609 |
+
"grad_norm": 0.22574378550052643,
|
| 77610 |
+
"learning_rate": 1.609802693095548e-05,
|
| 77611 |
+
"loss": 0.7816,
|
| 77612 |
+
"step": 11086
|
| 77613 |
+
},
|
| 77614 |
+
{
|
| 77615 |
+
"epoch": 12.627920227920228,
|
| 77616 |
+
"grad_norm": 0.23004484176635742,
|
| 77617 |
+
"learning_rate": 1.6093673286348355e-05,
|
| 77618 |
+
"loss": 0.5654,
|
| 77619 |
+
"step": 11087
|
| 77620 |
+
},
|
| 77621 |
+
{
|
| 77622 |
+
"epoch": 12.629059829059829,
|
| 77623 |
+
"grad_norm": 0.2010558694601059,
|
| 77624 |
+
"learning_rate": 1.6089319951082445e-05,
|
| 77625 |
+
"loss": 0.6681,
|
| 77626 |
+
"step": 11088
|
| 77627 |
+
},
|
| 77628 |
+
{
|
| 77629 |
+
"epoch": 12.630199430199431,
|
| 77630 |
+
"grad_norm": 0.15654054284095764,
|
| 77631 |
+
"learning_rate": 1.6084966925308966e-05,
|
| 77632 |
+
"loss": 0.9109,
|
| 77633 |
+
"step": 11089
|
| 77634 |
+
},
|
| 77635 |
+
{
|
| 77636 |
+
"epoch": 12.631339031339031,
|
| 77637 |
+
"grad_norm": 0.2031426727771759,
|
| 77638 |
+
"learning_rate": 1.6080614209179094e-05,
|
| 77639 |
+
"loss": 0.8188,
|
| 77640 |
+
"step": 11090
|
| 77641 |
+
},
|
| 77642 |
+
{
|
| 77643 |
+
"epoch": 12.632478632478632,
|
| 77644 |
+
"grad_norm": 0.17334313690662384,
|
| 77645 |
+
"learning_rate": 1.607626180284402e-05,
|
| 77646 |
+
"loss": 0.8053,
|
| 77647 |
+
"step": 11091
|
| 77648 |
+
},
|
| 77649 |
+
{
|
| 77650 |
+
"epoch": 12.633618233618234,
|
| 77651 |
+
"grad_norm": 0.18525288999080658,
|
| 77652 |
+
"learning_rate": 1.607190970645492e-05,
|
| 77653 |
+
"loss": 0.784,
|
| 77654 |
+
"step": 11092
|
| 77655 |
+
},
|
| 77656 |
+
{
|
| 77657 |
+
"epoch": 12.634757834757835,
|
| 77658 |
+
"grad_norm": 0.21956297755241394,
|
| 77659 |
+
"learning_rate": 1.6067557920162947e-05,
|
| 77660 |
+
"loss": 0.6042,
|
| 77661 |
+
"step": 11093
|
| 77662 |
+
},
|
| 77663 |
+
{
|
| 77664 |
+
"epoch": 12.635897435897435,
|
| 77665 |
+
"grad_norm": 0.26183709502220154,
|
| 77666 |
+
"learning_rate": 1.6063206444119238e-05,
|
| 77667 |
+
"loss": 0.535,
|
| 77668 |
+
"step": 11094
|
| 77669 |
+
},
|
| 77670 |
+
{
|
| 77671 |
+
"epoch": 12.637037037037038,
|
| 77672 |
+
"grad_norm": 0.23704814910888672,
|
| 77673 |
+
"learning_rate": 1.6058855278474956e-05,
|
| 77674 |
+
"loss": 0.655,
|
| 77675 |
+
"step": 11095
|
| 77676 |
+
},
|
| 77677 |
+
{
|
| 77678 |
+
"epoch": 12.638176638176638,
|
| 77679 |
+
"grad_norm": 0.27600836753845215,
|
| 77680 |
+
"learning_rate": 1.605450442338122e-05,
|
| 77681 |
+
"loss": 0.5203,
|
| 77682 |
+
"step": 11096
|
| 77683 |
+
},
|
| 77684 |
+
{
|
| 77685 |
+
"epoch": 12.639316239316239,
|
| 77686 |
+
"grad_norm": 0.22738400101661682,
|
| 77687 |
+
"learning_rate": 1.605015387898914e-05,
|
| 77688 |
+
"loss": 0.5225,
|
| 77689 |
+
"step": 11097
|
| 77690 |
+
},
|
| 77691 |
+
{
|
| 77692 |
+
"epoch": 12.640455840455841,
|
| 77693 |
+
"grad_norm": 0.2282770872116089,
|
| 77694 |
+
"learning_rate": 1.6045803645449836e-05,
|
| 77695 |
+
"loss": 0.5768,
|
| 77696 |
+
"step": 11098
|
| 77697 |
+
},
|
| 77698 |
+
{
|
| 77699 |
+
"epoch": 12.641595441595442,
|
| 77700 |
+
"grad_norm": 0.23350057005882263,
|
| 77701 |
+
"learning_rate": 1.604145372291439e-05,
|
| 77702 |
+
"loss": 0.6944,
|
| 77703 |
+
"step": 11099
|
| 77704 |
+
},
|
| 77705 |
+
{
|
| 77706 |
+
"epoch": 12.642735042735042,
|
| 77707 |
+
"grad_norm": 0.22004786133766174,
|
| 77708 |
+
"learning_rate": 1.6037104111533897e-05,
|
| 77709 |
+
"loss": 0.7505,
|
| 77710 |
+
"step": 11100
|
| 77711 |
}
|
| 77712 |
],
|
| 77713 |
"logging_steps": 1,
|
|
|
|
| 77727 |
"attributes": {}
|
| 77728 |
}
|
| 77729 |
},
|
| 77730 |
+
"total_flos": 6.206379008476889e+19,
|
| 77731 |
"train_batch_size": 8,
|
| 77732 |
"trial_name": null,
|
| 77733 |
"trial_params": null
|