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:
# pip install -U transformers accelerate # 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 17400, 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:c48619bc4ba36be95d56895be5765d505b1e04ffa269c5d96f7c549a2cc243be
|
| 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:ba86f51fa8e2d34b8e845068ac7141a896f1d94e558c622ad1ae9a23bd238d28
|
| 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 sha256:6153d95bde30a5f000c606f975a177c649ec1c879dfdc53912062e6d1909b090
|
| 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": 19.
|
| 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,
|
|
@@ -119708,6 +119708,2106 @@
|
|
| 119708 |
"learning_rate": 9.221124291897976e-08,
|
| 119709 |
"loss": 0.3647,
|
| 119710 |
"step": 17100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119711 |
}
|
| 119712 |
],
|
| 119713 |
"logging_steps": 1,
|
|
@@ -119727,7 +121827,7 @@
|
|
| 119727 |
"attributes": {}
|
| 119728 |
}
|
| 119729 |
},
|
| 119730 |
-
"total_flos": 9.
|
| 119731 |
"train_batch_size": 8,
|
| 119732 |
"trial_name": null,
|
| 119733 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.81823361823362,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 17400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 119708 |
"learning_rate": 9.221124291897976e-08,
|
| 119709 |
"loss": 0.3647,
|
| 119710 |
"step": 17100
|
| 119711 |
+
},
|
| 119712 |
+
{
|
| 119713 |
+
"epoch": 19.477492877492878,
|
| 119714 |
+
"grad_norm": 0.22222790122032166,
|
| 119715 |
+
"learning_rate": 9.181187281131487e-08,
|
| 119716 |
+
"loss": 0.6411,
|
| 119717 |
+
"step": 17101
|
| 119718 |
+
},
|
| 119719 |
+
{
|
| 119720 |
+
"epoch": 19.478632478632477,
|
| 119721 |
+
"grad_norm": 0.2127547413110733,
|
| 119722 |
+
"learning_rate": 9.14133678335205e-08,
|
| 119723 |
+
"loss": 0.6041,
|
| 119724 |
+
"step": 17102
|
| 119725 |
+
},
|
| 119726 |
+
{
|
| 119727 |
+
"epoch": 19.47977207977208,
|
| 119728 |
+
"grad_norm": 0.22702544927597046,
|
| 119729 |
+
"learning_rate": 9.101572799943836e-08,
|
| 119730 |
+
"loss": 0.5715,
|
| 119731 |
+
"step": 17103
|
| 119732 |
+
},
|
| 119733 |
+
{
|
| 119734 |
+
"epoch": 19.48091168091168,
|
| 119735 |
+
"grad_norm": 0.18768079578876495,
|
| 119736 |
+
"learning_rate": 9.06189533228824e-08,
|
| 119737 |
+
"loss": 0.7962,
|
| 119738 |
+
"step": 17104
|
| 119739 |
+
},
|
| 119740 |
+
{
|
| 119741 |
+
"epoch": 19.48205128205128,
|
| 119742 |
+
"grad_norm": 0.17594477534294128,
|
| 119743 |
+
"learning_rate": 9.022304381763047e-08,
|
| 119744 |
+
"loss": 0.5345,
|
| 119745 |
+
"step": 17105
|
| 119746 |
+
},
|
| 119747 |
+
{
|
| 119748 |
+
"epoch": 19.483190883190883,
|
| 119749 |
+
"grad_norm": 0.18248769640922546,
|
| 119750 |
+
"learning_rate": 8.98279994974327e-08,
|
| 119751 |
+
"loss": 0.693,
|
| 119752 |
+
"step": 17106
|
| 119753 |
+
},
|
| 119754 |
+
{
|
| 119755 |
+
"epoch": 19.484330484330485,
|
| 119756 |
+
"grad_norm": 0.20692914724349976,
|
| 119757 |
+
"learning_rate": 8.943382037601422e-08,
|
| 119758 |
+
"loss": 0.7601,
|
| 119759 |
+
"step": 17107
|
| 119760 |
+
},
|
| 119761 |
+
{
|
| 119762 |
+
"epoch": 19.485470085470084,
|
| 119763 |
+
"grad_norm": 0.16740009188652039,
|
| 119764 |
+
"learning_rate": 8.90405064670613e-08,
|
| 119765 |
+
"loss": 0.7128,
|
| 119766 |
+
"step": 17108
|
| 119767 |
+
},
|
| 119768 |
+
{
|
| 119769 |
+
"epoch": 19.486609686609686,
|
| 119770 |
+
"grad_norm": 0.24666811525821686,
|
| 119771 |
+
"learning_rate": 8.864805778423801e-08,
|
| 119772 |
+
"loss": 0.4575,
|
| 119773 |
+
"step": 17109
|
| 119774 |
+
},
|
| 119775 |
+
{
|
| 119776 |
+
"epoch": 19.48774928774929,
|
| 119777 |
+
"grad_norm": 0.17780767381191254,
|
| 119778 |
+
"learning_rate": 8.825647434117512e-08,
|
| 119779 |
+
"loss": 0.7061,
|
| 119780 |
+
"step": 17110
|
| 119781 |
+
},
|
| 119782 |
+
{
|
| 119783 |
+
"epoch": 19.488888888888887,
|
| 119784 |
+
"grad_norm": 0.23126186430454254,
|
| 119785 |
+
"learning_rate": 8.786575615147007e-08,
|
| 119786 |
+
"loss": 0.6311,
|
| 119787 |
+
"step": 17111
|
| 119788 |
+
},
|
| 119789 |
+
{
|
| 119790 |
+
"epoch": 19.49002849002849,
|
| 119791 |
+
"grad_norm": 0.1918278932571411,
|
| 119792 |
+
"learning_rate": 8.747590322869814e-08,
|
| 119793 |
+
"loss": 0.7168,
|
| 119794 |
+
"step": 17112
|
| 119795 |
+
},
|
| 119796 |
+
{
|
| 119797 |
+
"epoch": 19.491168091168092,
|
| 119798 |
+
"grad_norm": 0.23038645088672638,
|
| 119799 |
+
"learning_rate": 8.70869155863957e-08,
|
| 119800 |
+
"loss": 0.5251,
|
| 119801 |
+
"step": 17113
|
| 119802 |
+
},
|
| 119803 |
+
{
|
| 119804 |
+
"epoch": 19.49230769230769,
|
| 119805 |
+
"grad_norm": 0.20258736610412598,
|
| 119806 |
+
"learning_rate": 8.669879323807694e-08,
|
| 119807 |
+
"loss": 0.745,
|
| 119808 |
+
"step": 17114
|
| 119809 |
+
},
|
| 119810 |
+
{
|
| 119811 |
+
"epoch": 19.493447293447293,
|
| 119812 |
+
"grad_norm": 0.20020519196987152,
|
| 119813 |
+
"learning_rate": 8.631153619721998e-08,
|
| 119814 |
+
"loss": 0.7075,
|
| 119815 |
+
"step": 17115
|
| 119816 |
+
},
|
| 119817 |
+
{
|
| 119818 |
+
"epoch": 19.494586894586895,
|
| 119819 |
+
"grad_norm": 0.17957910895347595,
|
| 119820 |
+
"learning_rate": 8.592514447727795e-08,
|
| 119821 |
+
"loss": 0.7416,
|
| 119822 |
+
"step": 17116
|
| 119823 |
+
},
|
| 119824 |
+
{
|
| 119825 |
+
"epoch": 19.495726495726494,
|
| 119826 |
+
"grad_norm": 0.21466033160686493,
|
| 119827 |
+
"learning_rate": 8.553961809166788e-08,
|
| 119828 |
+
"loss": 0.5896,
|
| 119829 |
+
"step": 17117
|
| 119830 |
+
},
|
| 119831 |
+
{
|
| 119832 |
+
"epoch": 19.496866096866096,
|
| 119833 |
+
"grad_norm": 0.1736799031496048,
|
| 119834 |
+
"learning_rate": 8.515495705378185e-08,
|
| 119835 |
+
"loss": 0.6359,
|
| 119836 |
+
"step": 17118
|
| 119837 |
+
},
|
| 119838 |
+
{
|
| 119839 |
+
"epoch": 19.4980056980057,
|
| 119840 |
+
"grad_norm": 0.16858024895191193,
|
| 119841 |
+
"learning_rate": 8.477116137698138e-08,
|
| 119842 |
+
"loss": 0.518,
|
| 119843 |
+
"step": 17119
|
| 119844 |
+
},
|
| 119845 |
+
{
|
| 119846 |
+
"epoch": 19.499145299145297,
|
| 119847 |
+
"grad_norm": 0.17975902557373047,
|
| 119848 |
+
"learning_rate": 8.43882310745947e-08,
|
| 119849 |
+
"loss": 0.7806,
|
| 119850 |
+
"step": 17120
|
| 119851 |
+
},
|
| 119852 |
+
{
|
| 119853 |
+
"epoch": 19.5002849002849,
|
| 119854 |
+
"grad_norm": 0.20028391480445862,
|
| 119855 |
+
"learning_rate": 8.400616615992507e-08,
|
| 119856 |
+
"loss": 0.5858,
|
| 119857 |
+
"step": 17121
|
| 119858 |
+
},
|
| 119859 |
+
{
|
| 119860 |
+
"epoch": 19.501424501424502,
|
| 119861 |
+
"grad_norm": 0.19237558543682098,
|
| 119862 |
+
"learning_rate": 8.362496664623687e-08,
|
| 119863 |
+
"loss": 0.6286,
|
| 119864 |
+
"step": 17122
|
| 119865 |
+
},
|
| 119866 |
+
{
|
| 119867 |
+
"epoch": 19.5025641025641,
|
| 119868 |
+
"grad_norm": 0.17876315116882324,
|
| 119869 |
+
"learning_rate": 8.324463254677784e-08,
|
| 119870 |
+
"loss": 0.5383,
|
| 119871 |
+
"step": 17123
|
| 119872 |
+
},
|
| 119873 |
+
{
|
| 119874 |
+
"epoch": 19.503703703703703,
|
| 119875 |
+
"grad_norm": 0.17792995274066925,
|
| 119876 |
+
"learning_rate": 8.28651638747513e-08,
|
| 119877 |
+
"loss": 0.753,
|
| 119878 |
+
"step": 17124
|
| 119879 |
+
},
|
| 119880 |
+
{
|
| 119881 |
+
"epoch": 19.504843304843305,
|
| 119882 |
+
"grad_norm": 0.20652182400226593,
|
| 119883 |
+
"learning_rate": 8.248656064334115e-08,
|
| 119884 |
+
"loss": 0.5331,
|
| 119885 |
+
"step": 17125
|
| 119886 |
+
},
|
| 119887 |
+
{
|
| 119888 |
+
"epoch": 19.505982905982904,
|
| 119889 |
+
"grad_norm": 0.18937747180461884,
|
| 119890 |
+
"learning_rate": 8.210882286569521e-08,
|
| 119891 |
+
"loss": 0.7188,
|
| 119892 |
+
"step": 17126
|
| 119893 |
+
},
|
| 119894 |
+
{
|
| 119895 |
+
"epoch": 19.507122507122507,
|
| 119896 |
+
"grad_norm": 0.1956784576177597,
|
| 119897 |
+
"learning_rate": 8.173195055493632e-08,
|
| 119898 |
+
"loss": 0.7413,
|
| 119899 |
+
"step": 17127
|
| 119900 |
+
},
|
| 119901 |
+
{
|
| 119902 |
+
"epoch": 19.50826210826211,
|
| 119903 |
+
"grad_norm": 0.19371221959590912,
|
| 119904 |
+
"learning_rate": 8.135594372415123e-08,
|
| 119905 |
+
"loss": 0.4869,
|
| 119906 |
+
"step": 17128
|
| 119907 |
+
},
|
| 119908 |
+
{
|
| 119909 |
+
"epoch": 19.509401709401708,
|
| 119910 |
+
"grad_norm": 0.2019006609916687,
|
| 119911 |
+
"learning_rate": 8.098080238639893e-08,
|
| 119912 |
+
"loss": 0.5579,
|
| 119913 |
+
"step": 17129
|
| 119914 |
+
},
|
| 119915 |
+
{
|
| 119916 |
+
"epoch": 19.51054131054131,
|
| 119917 |
+
"grad_norm": 0.24422931671142578,
|
| 119918 |
+
"learning_rate": 8.060652655471346e-08,
|
| 119919 |
+
"loss": 0.4343,
|
| 119920 |
+
"step": 17130
|
| 119921 |
+
},
|
| 119922 |
+
{
|
| 119923 |
+
"epoch": 19.511680911680912,
|
| 119924 |
+
"grad_norm": 0.24223747849464417,
|
| 119925 |
+
"learning_rate": 8.023311624208996e-08,
|
| 119926 |
+
"loss": 0.5611,
|
| 119927 |
+
"step": 17131
|
| 119928 |
+
},
|
| 119929 |
+
{
|
| 119930 |
+
"epoch": 19.51282051282051,
|
| 119931 |
+
"grad_norm": 0.18167677521705627,
|
| 119932 |
+
"learning_rate": 7.986057146150138e-08,
|
| 119933 |
+
"loss": 0.634,
|
| 119934 |
+
"step": 17132
|
| 119935 |
+
},
|
| 119936 |
+
{
|
| 119937 |
+
"epoch": 19.513960113960113,
|
| 119938 |
+
"grad_norm": 0.173972949385643,
|
| 119939 |
+
"learning_rate": 7.948889222588463e-08,
|
| 119940 |
+
"loss": 0.6816,
|
| 119941 |
+
"step": 17133
|
| 119942 |
+
},
|
| 119943 |
+
{
|
| 119944 |
+
"epoch": 19.515099715099716,
|
| 119945 |
+
"grad_norm": 0.16874933242797852,
|
| 119946 |
+
"learning_rate": 7.911807854815156e-08,
|
| 119947 |
+
"loss": 0.6713,
|
| 119948 |
+
"step": 17134
|
| 119949 |
+
},
|
| 119950 |
+
{
|
| 119951 |
+
"epoch": 19.516239316239318,
|
| 119952 |
+
"grad_norm": 0.22373968362808228,
|
| 119953 |
+
"learning_rate": 7.874813044117802e-08,
|
| 119954 |
+
"loss": 0.5097,
|
| 119955 |
+
"step": 17135
|
| 119956 |
+
},
|
| 119957 |
+
{
|
| 119958 |
+
"epoch": 19.517378917378917,
|
| 119959 |
+
"grad_norm": 0.17092277109622955,
|
| 119960 |
+
"learning_rate": 7.837904791781759e-08,
|
| 119961 |
+
"loss": 0.695,
|
| 119962 |
+
"step": 17136
|
| 119963 |
+
},
|
| 119964 |
+
{
|
| 119965 |
+
"epoch": 19.51851851851852,
|
| 119966 |
+
"grad_norm": 0.2304261028766632,
|
| 119967 |
+
"learning_rate": 7.80108309908878e-08,
|
| 119968 |
+
"loss": 0.7551,
|
| 119969 |
+
"step": 17137
|
| 119970 |
+
},
|
| 119971 |
+
{
|
| 119972 |
+
"epoch": 19.51965811965812,
|
| 119973 |
+
"grad_norm": 0.19783733785152435,
|
| 119974 |
+
"learning_rate": 7.764347967317842e-08,
|
| 119975 |
+
"loss": 0.6007,
|
| 119976 |
+
"step": 17138
|
| 119977 |
+
},
|
| 119978 |
+
{
|
| 119979 |
+
"epoch": 19.52079772079772,
|
| 119980 |
+
"grad_norm": 0.1704883575439453,
|
| 119981 |
+
"learning_rate": 7.727699397744592e-08,
|
| 119982 |
+
"loss": 0.7003,
|
| 119983 |
+
"step": 17139
|
| 119984 |
+
},
|
| 119985 |
+
{
|
| 119986 |
+
"epoch": 19.521937321937322,
|
| 119987 |
+
"grad_norm": 0.24890558421611786,
|
| 119988 |
+
"learning_rate": 7.691137391642178e-08,
|
| 119989 |
+
"loss": 0.449,
|
| 119990 |
+
"step": 17140
|
| 119991 |
+
},
|
| 119992 |
+
{
|
| 119993 |
+
"epoch": 19.523076923076925,
|
| 119994 |
+
"grad_norm": 0.21356940269470215,
|
| 119995 |
+
"learning_rate": 7.654661950280417e-08,
|
| 119996 |
+
"loss": 0.5135,
|
| 119997 |
+
"step": 17141
|
| 119998 |
+
},
|
| 119999 |
+
{
|
| 120000 |
+
"epoch": 19.524216524216524,
|
| 120001 |
+
"grad_norm": 0.2279697060585022,
|
| 120002 |
+
"learning_rate": 7.618273074926074e-08,
|
| 120003 |
+
"loss": 0.6671,
|
| 120004 |
+
"step": 17142
|
| 120005 |
+
},
|
| 120006 |
+
{
|
| 120007 |
+
"epoch": 19.525356125356126,
|
| 120008 |
+
"grad_norm": 0.20446214079856873,
|
| 120009 |
+
"learning_rate": 7.581970766843415e-08,
|
| 120010 |
+
"loss": 0.6255,
|
| 120011 |
+
"step": 17143
|
| 120012 |
+
},
|
| 120013 |
+
{
|
| 120014 |
+
"epoch": 19.526495726495728,
|
| 120015 |
+
"grad_norm": 0.15221214294433594,
|
| 120016 |
+
"learning_rate": 7.5457550272931e-08,
|
| 120017 |
+
"loss": 0.5565,
|
| 120018 |
+
"step": 17144
|
| 120019 |
+
},
|
| 120020 |
+
{
|
| 120021 |
+
"epoch": 19.527635327635327,
|
| 120022 |
+
"grad_norm": 0.18313929438591003,
|
| 120023 |
+
"learning_rate": 7.509625857533009e-08,
|
| 120024 |
+
"loss": 0.8275,
|
| 120025 |
+
"step": 17145
|
| 120026 |
+
},
|
| 120027 |
+
{
|
| 120028 |
+
"epoch": 19.52877492877493,
|
| 120029 |
+
"grad_norm": 0.19369709491729736,
|
| 120030 |
+
"learning_rate": 7.473583258817695e-08,
|
| 120031 |
+
"loss": 0.6028,
|
| 120032 |
+
"step": 17146
|
| 120033 |
+
},
|
| 120034 |
+
{
|
| 120035 |
+
"epoch": 19.52991452991453,
|
| 120036 |
+
"grad_norm": 0.22477491199970245,
|
| 120037 |
+
"learning_rate": 7.437627232399492e-08,
|
| 120038 |
+
"loss": 0.6689,
|
| 120039 |
+
"step": 17147
|
| 120040 |
+
},
|
| 120041 |
+
{
|
| 120042 |
+
"epoch": 19.53105413105413,
|
| 120043 |
+
"grad_norm": 0.177805557847023,
|
| 120044 |
+
"learning_rate": 7.401757779527118e-08,
|
| 120045 |
+
"loss": 0.6733,
|
| 120046 |
+
"step": 17148
|
| 120047 |
+
},
|
| 120048 |
+
{
|
| 120049 |
+
"epoch": 19.532193732193733,
|
| 120050 |
+
"grad_norm": 0.1790897399187088,
|
| 120051 |
+
"learning_rate": 7.365974901446248e-08,
|
| 120052 |
+
"loss": 0.5415,
|
| 120053 |
+
"step": 17149
|
| 120054 |
+
},
|
| 120055 |
+
{
|
| 120056 |
+
"epoch": 19.533333333333335,
|
| 120057 |
+
"grad_norm": 0.22771689295768738,
|
| 120058 |
+
"learning_rate": 7.330278599400053e-08,
|
| 120059 |
+
"loss": 0.5673,
|
| 120060 |
+
"step": 17150
|
| 120061 |
+
},
|
| 120062 |
+
{
|
| 120063 |
+
"epoch": 19.534472934472934,
|
| 120064 |
+
"grad_norm": 0.21820858120918274,
|
| 120065 |
+
"learning_rate": 7.294668874628096e-08,
|
| 120066 |
+
"loss": 0.4605,
|
| 120067 |
+
"step": 17151
|
| 120068 |
+
},
|
| 120069 |
+
{
|
| 120070 |
+
"epoch": 19.535612535612536,
|
| 120071 |
+
"grad_norm": 0.16659726202487946,
|
| 120072 |
+
"learning_rate": 7.259145728367167e-08,
|
| 120073 |
+
"loss": 0.6647,
|
| 120074 |
+
"step": 17152
|
| 120075 |
+
},
|
| 120076 |
+
{
|
| 120077 |
+
"epoch": 19.53675213675214,
|
| 120078 |
+
"grad_norm": 0.1653488725423813,
|
| 120079 |
+
"learning_rate": 7.223709161851e-08,
|
| 120080 |
+
"loss": 0.6669,
|
| 120081 |
+
"step": 17153
|
| 120082 |
+
},
|
| 120083 |
+
{
|
| 120084 |
+
"epoch": 19.537891737891737,
|
| 120085 |
+
"grad_norm": 0.19739170372486115,
|
| 120086 |
+
"learning_rate": 7.188359176310832e-08,
|
| 120087 |
+
"loss": 0.6552,
|
| 120088 |
+
"step": 17154
|
| 120089 |
+
},
|
| 120090 |
+
{
|
| 120091 |
+
"epoch": 19.53903133903134,
|
| 120092 |
+
"grad_norm": 0.23167668282985687,
|
| 120093 |
+
"learning_rate": 7.153095772974016e-08,
|
| 120094 |
+
"loss": 0.6213,
|
| 120095 |
+
"step": 17155
|
| 120096 |
+
},
|
| 120097 |
+
{
|
| 120098 |
+
"epoch": 19.540170940170942,
|
| 120099 |
+
"grad_norm": 0.15837553143501282,
|
| 120100 |
+
"learning_rate": 7.117918953065683e-08,
|
| 120101 |
+
"loss": 0.8195,
|
| 120102 |
+
"step": 17156
|
| 120103 |
+
},
|
| 120104 |
+
{
|
| 120105 |
+
"epoch": 19.54131054131054,
|
| 120106 |
+
"grad_norm": 0.2038544863462448,
|
| 120107 |
+
"learning_rate": 7.082828717807633e-08,
|
| 120108 |
+
"loss": 0.7856,
|
| 120109 |
+
"step": 17157
|
| 120110 |
+
},
|
| 120111 |
+
{
|
| 120112 |
+
"epoch": 19.542450142450143,
|
| 120113 |
+
"grad_norm": 0.21026979386806488,
|
| 120114 |
+
"learning_rate": 7.047825068418056e-08,
|
| 120115 |
+
"loss": 0.495,
|
| 120116 |
+
"step": 17158
|
| 120117 |
+
},
|
| 120118 |
+
{
|
| 120119 |
+
"epoch": 19.543589743589745,
|
| 120120 |
+
"grad_norm": 0.19288213551044464,
|
| 120121 |
+
"learning_rate": 7.012908006113483e-08,
|
| 120122 |
+
"loss": 0.427,
|
| 120123 |
+
"step": 17159
|
| 120124 |
+
},
|
| 120125 |
+
{
|
| 120126 |
+
"epoch": 19.544729344729344,
|
| 120127 |
+
"grad_norm": 0.15973199903964996,
|
| 120128 |
+
"learning_rate": 6.978077532106276e-08,
|
| 120129 |
+
"loss": 0.6121,
|
| 120130 |
+
"step": 17160
|
| 120131 |
+
},
|
| 120132 |
+
{
|
| 120133 |
+
"epoch": 19.545868945868946,
|
| 120134 |
+
"grad_norm": 0.19514554738998413,
|
| 120135 |
+
"learning_rate": 6.943333647606298e-08,
|
| 120136 |
+
"loss": 0.5693,
|
| 120137 |
+
"step": 17161
|
| 120138 |
+
},
|
| 120139 |
+
{
|
| 120140 |
+
"epoch": 19.54700854700855,
|
| 120141 |
+
"grad_norm": 0.16935944557189941,
|
| 120142 |
+
"learning_rate": 6.908676353820365e-08,
|
| 120143 |
+
"loss": 0.6195,
|
| 120144 |
+
"step": 17162
|
| 120145 |
+
},
|
| 120146 |
+
{
|
| 120147 |
+
"epoch": 19.548148148148147,
|
| 120148 |
+
"grad_norm": 0.1701992154121399,
|
| 120149 |
+
"learning_rate": 6.874105651951957e-08,
|
| 120150 |
+
"loss": 0.574,
|
| 120151 |
+
"step": 17163
|
| 120152 |
+
},
|
| 120153 |
+
{
|
| 120154 |
+
"epoch": 19.54928774928775,
|
| 120155 |
+
"grad_norm": 0.18068106472492218,
|
| 120156 |
+
"learning_rate": 6.839621543202058e-08,
|
| 120157 |
+
"loss": 0.686,
|
| 120158 |
+
"step": 17164
|
| 120159 |
+
},
|
| 120160 |
+
{
|
| 120161 |
+
"epoch": 19.550427350427352,
|
| 120162 |
+
"grad_norm": 0.17694298923015594,
|
| 120163 |
+
"learning_rate": 6.80522402876832e-08,
|
| 120164 |
+
"loss": 0.4524,
|
| 120165 |
+
"step": 17165
|
| 120166 |
+
},
|
| 120167 |
+
{
|
| 120168 |
+
"epoch": 19.55156695156695,
|
| 120169 |
+
"grad_norm": 0.2574649751186371,
|
| 120170 |
+
"learning_rate": 6.770913109845345e-08,
|
| 120171 |
+
"loss": 0.4532,
|
| 120172 |
+
"step": 17166
|
| 120173 |
+
},
|
| 120174 |
+
{
|
| 120175 |
+
"epoch": 19.552706552706553,
|
| 120176 |
+
"grad_norm": 0.1775989681482315,
|
| 120177 |
+
"learning_rate": 6.736688787625234e-08,
|
| 120178 |
+
"loss": 0.7867,
|
| 120179 |
+
"step": 17167
|
| 120180 |
+
},
|
| 120181 |
+
{
|
| 120182 |
+
"epoch": 19.553846153846155,
|
| 120183 |
+
"grad_norm": 0.17278486490249634,
|
| 120184 |
+
"learning_rate": 6.702551063296204e-08,
|
| 120185 |
+
"loss": 0.6284,
|
| 120186 |
+
"step": 17168
|
| 120187 |
+
},
|
| 120188 |
+
{
|
| 120189 |
+
"epoch": 19.554985754985754,
|
| 120190 |
+
"grad_norm": 0.1985652595758438,
|
| 120191 |
+
"learning_rate": 6.668499938044248e-08,
|
| 120192 |
+
"loss": 0.7282,
|
| 120193 |
+
"step": 17169
|
| 120194 |
+
},
|
| 120195 |
+
{
|
| 120196 |
+
"epoch": 19.556125356125357,
|
| 120197 |
+
"grad_norm": 0.22517012059688568,
|
| 120198 |
+
"learning_rate": 6.634535413051756e-08,
|
| 120199 |
+
"loss": 0.5876,
|
| 120200 |
+
"step": 17170
|
| 120201 |
+
},
|
| 120202 |
+
{
|
| 120203 |
+
"epoch": 19.55726495726496,
|
| 120204 |
+
"grad_norm": 0.22253260016441345,
|
| 120205 |
+
"learning_rate": 6.600657489498895e-08,
|
| 120206 |
+
"loss": 0.4699,
|
| 120207 |
+
"step": 17171
|
| 120208 |
+
},
|
| 120209 |
+
{
|
| 120210 |
+
"epoch": 19.558404558404558,
|
| 120211 |
+
"grad_norm": 0.17032331228256226,
|
| 120212 |
+
"learning_rate": 6.566866168561947e-08,
|
| 120213 |
+
"loss": 0.939,
|
| 120214 |
+
"step": 17172
|
| 120215 |
+
},
|
| 120216 |
+
{
|
| 120217 |
+
"epoch": 19.55954415954416,
|
| 120218 |
+
"grad_norm": 0.2109702080488205,
|
| 120219 |
+
"learning_rate": 6.533161451414693e-08,
|
| 120220 |
+
"loss": 0.8453,
|
| 120221 |
+
"step": 17173
|
| 120222 |
+
},
|
| 120223 |
+
{
|
| 120224 |
+
"epoch": 19.560683760683762,
|
| 120225 |
+
"grad_norm": 0.16890640556812286,
|
| 120226 |
+
"learning_rate": 6.499543339227864e-08,
|
| 120227 |
+
"loss": 0.7582,
|
| 120228 |
+
"step": 17174
|
| 120229 |
+
},
|
| 120230 |
+
{
|
| 120231 |
+
"epoch": 19.56182336182336,
|
| 120232 |
+
"grad_norm": 0.2271934449672699,
|
| 120233 |
+
"learning_rate": 6.46601183316914e-08,
|
| 120234 |
+
"loss": 0.5252,
|
| 120235 |
+
"step": 17175
|
| 120236 |
+
},
|
| 120237 |
+
{
|
| 120238 |
+
"epoch": 19.562962962962963,
|
| 120239 |
+
"grad_norm": 0.222871795296669,
|
| 120240 |
+
"learning_rate": 6.432566934402862e-08,
|
| 120241 |
+
"loss": 0.7076,
|
| 120242 |
+
"step": 17176
|
| 120243 |
+
},
|
| 120244 |
+
{
|
| 120245 |
+
"epoch": 19.564102564102566,
|
| 120246 |
+
"grad_norm": 0.19857577979564667,
|
| 120247 |
+
"learning_rate": 6.39920864409116e-08,
|
| 120248 |
+
"loss": 0.5309,
|
| 120249 |
+
"step": 17177
|
| 120250 |
+
},
|
| 120251 |
+
{
|
| 120252 |
+
"epoch": 19.565242165242164,
|
| 120253 |
+
"grad_norm": 0.1586875021457672,
|
| 120254 |
+
"learning_rate": 6.365936963392272e-08,
|
| 120255 |
+
"loss": 0.7746,
|
| 120256 |
+
"step": 17178
|
| 120257 |
+
},
|
| 120258 |
+
{
|
| 120259 |
+
"epoch": 19.566381766381767,
|
| 120260 |
+
"grad_norm": 0.1662566214799881,
|
| 120261 |
+
"learning_rate": 6.332751893461664e-08,
|
| 120262 |
+
"loss": 0.7652,
|
| 120263 |
+
"step": 17179
|
| 120264 |
+
},
|
| 120265 |
+
{
|
| 120266 |
+
"epoch": 19.56752136752137,
|
| 120267 |
+
"grad_norm": 0.2910987436771393,
|
| 120268 |
+
"learning_rate": 6.29965343545258e-08,
|
| 120269 |
+
"loss": 0.7277,
|
| 120270 |
+
"step": 17180
|
| 120271 |
+
},
|
| 120272 |
+
{
|
| 120273 |
+
"epoch": 19.568660968660968,
|
| 120274 |
+
"grad_norm": 0.18514537811279297,
|
| 120275 |
+
"learning_rate": 6.266641590513823e-08,
|
| 120276 |
+
"loss": 0.5475,
|
| 120277 |
+
"step": 17181
|
| 120278 |
+
},
|
| 120279 |
+
{
|
| 120280 |
+
"epoch": 19.56980056980057,
|
| 120281 |
+
"grad_norm": 0.25863945484161377,
|
| 120282 |
+
"learning_rate": 6.233716359792807e-08,
|
| 120283 |
+
"loss": 0.4553,
|
| 120284 |
+
"step": 17182
|
| 120285 |
+
},
|
| 120286 |
+
{
|
| 120287 |
+
"epoch": 19.570940170940172,
|
| 120288 |
+
"grad_norm": 0.20041605830192566,
|
| 120289 |
+
"learning_rate": 6.200877744432232e-08,
|
| 120290 |
+
"loss": 0.6071,
|
| 120291 |
+
"step": 17183
|
| 120292 |
+
},
|
| 120293 |
+
{
|
| 120294 |
+
"epoch": 19.57207977207977,
|
| 120295 |
+
"grad_norm": 0.1779608428478241,
|
| 120296 |
+
"learning_rate": 6.168125745573683e-08,
|
| 120297 |
+
"loss": 0.4706,
|
| 120298 |
+
"step": 17184
|
| 120299 |
+
},
|
| 120300 |
+
{
|
| 120301 |
+
"epoch": 19.573219373219374,
|
| 120302 |
+
"grad_norm": 0.21291576325893402,
|
| 120303 |
+
"learning_rate": 6.135460364353752e-08,
|
| 120304 |
+
"loss": 0.4194,
|
| 120305 |
+
"step": 17185
|
| 120306 |
+
},
|
| 120307 |
+
{
|
| 120308 |
+
"epoch": 19.574358974358976,
|
| 120309 |
+
"grad_norm": 0.15239788591861725,
|
| 120310 |
+
"learning_rate": 6.102881601907639e-08,
|
| 120311 |
+
"loss": 0.6367,
|
| 120312 |
+
"step": 17186
|
| 120313 |
+
},
|
| 120314 |
+
{
|
| 120315 |
+
"epoch": 19.575498575498575,
|
| 120316 |
+
"grad_norm": 0.1992502212524414,
|
| 120317 |
+
"learning_rate": 6.070389459366665e-08,
|
| 120318 |
+
"loss": 0.7274,
|
| 120319 |
+
"step": 17187
|
| 120320 |
+
},
|
| 120321 |
+
{
|
| 120322 |
+
"epoch": 19.576638176638177,
|
| 120323 |
+
"grad_norm": 0.21773108839988708,
|
| 120324 |
+
"learning_rate": 6.037983937859371e-08,
|
| 120325 |
+
"loss": 0.4291,
|
| 120326 |
+
"step": 17188
|
| 120327 |
+
},
|
| 120328 |
+
{
|
| 120329 |
+
"epoch": 19.57777777777778,
|
| 120330 |
+
"grad_norm": 0.18458621203899384,
|
| 120331 |
+
"learning_rate": 6.005665038511521e-08,
|
| 120332 |
+
"loss": 0.7298,
|
| 120333 |
+
"step": 17189
|
| 120334 |
+
},
|
| 120335 |
+
{
|
| 120336 |
+
"epoch": 19.578917378917378,
|
| 120337 |
+
"grad_norm": 0.17930319905281067,
|
| 120338 |
+
"learning_rate": 5.973432762445275e-08,
|
| 120339 |
+
"loss": 0.7223,
|
| 120340 |
+
"step": 17190
|
| 120341 |
+
},
|
| 120342 |
+
{
|
| 120343 |
+
"epoch": 19.58005698005698,
|
| 120344 |
+
"grad_norm": 0.21082007884979248,
|
| 120345 |
+
"learning_rate": 5.9412871107800135e-08,
|
| 120346 |
+
"loss": 0.8155,
|
| 120347 |
+
"step": 17191
|
| 120348 |
+
},
|
| 120349 |
+
{
|
| 120350 |
+
"epoch": 19.581196581196583,
|
| 120351 |
+
"grad_norm": 0.1849924772977829,
|
| 120352 |
+
"learning_rate": 5.9092280846329004e-08,
|
| 120353 |
+
"loss": 0.696,
|
| 120354 |
+
"step": 17192
|
| 120355 |
+
},
|
| 120356 |
+
{
|
| 120357 |
+
"epoch": 19.58233618233618,
|
| 120358 |
+
"grad_norm": 0.19565510749816895,
|
| 120359 |
+
"learning_rate": 5.877255685116934e-08,
|
| 120360 |
+
"loss": 0.7884,
|
| 120361 |
+
"step": 17193
|
| 120362 |
+
},
|
| 120363 |
+
{
|
| 120364 |
+
"epoch": 19.583475783475784,
|
| 120365 |
+
"grad_norm": 0.2000020444393158,
|
| 120366 |
+
"learning_rate": 5.8453699133428907e-08,
|
| 120367 |
+
"loss": 0.7215,
|
| 120368 |
+
"step": 17194
|
| 120369 |
+
},
|
| 120370 |
+
{
|
| 120371 |
+
"epoch": 19.584615384615386,
|
| 120372 |
+
"grad_norm": 0.1640736609697342,
|
| 120373 |
+
"learning_rate": 5.813570770417942e-08,
|
| 120374 |
+
"loss": 0.5945,
|
| 120375 |
+
"step": 17195
|
| 120376 |
+
},
|
| 120377 |
+
{
|
| 120378 |
+
"epoch": 19.585754985754985,
|
| 120379 |
+
"grad_norm": 0.18161728978157043,
|
| 120380 |
+
"learning_rate": 5.7818582574467594e-08,
|
| 120381 |
+
"loss": 0.5542,
|
| 120382 |
+
"step": 17196
|
| 120383 |
+
},
|
| 120384 |
+
{
|
| 120385 |
+
"epoch": 19.586894586894587,
|
| 120386 |
+
"grad_norm": 0.17179909348487854,
|
| 120387 |
+
"learning_rate": 5.750232375530962e-08,
|
| 120388 |
+
"loss": 0.8178,
|
| 120389 |
+
"step": 17197
|
| 120390 |
+
},
|
| 120391 |
+
{
|
| 120392 |
+
"epoch": 19.58803418803419,
|
| 120393 |
+
"grad_norm": 0.2215074598789215,
|
| 120394 |
+
"learning_rate": 5.7186931257685596e-08,
|
| 120395 |
+
"loss": 0.6192,
|
| 120396 |
+
"step": 17198
|
| 120397 |
+
},
|
| 120398 |
+
{
|
| 120399 |
+
"epoch": 19.58917378917379,
|
| 120400 |
+
"grad_norm": 0.20067641139030457,
|
| 120401 |
+
"learning_rate": 5.6872405092553425e-08,
|
| 120402 |
+
"loss": 0.6097,
|
| 120403 |
+
"step": 17199
|
| 120404 |
+
},
|
| 120405 |
+
{
|
| 120406 |
+
"epoch": 19.59031339031339,
|
| 120407 |
+
"grad_norm": 0.20531664788722992,
|
| 120408 |
+
"learning_rate": 5.655874527083493e-08,
|
| 120409 |
+
"loss": 0.8093,
|
| 120410 |
+
"step": 17200
|
| 120411 |
+
},
|
| 120412 |
+
{
|
| 120413 |
+
"epoch": 19.591452991452993,
|
| 120414 |
+
"grad_norm": 0.18867632746696472,
|
| 120415 |
+
"learning_rate": 5.624595180342696e-08,
|
| 120416 |
+
"loss": 0.7636,
|
| 120417 |
+
"step": 17201
|
| 120418 |
+
},
|
| 120419 |
+
{
|
| 120420 |
+
"epoch": 19.59259259259259,
|
| 120421 |
+
"grad_norm": 0.2290651500225067,
|
| 120422 |
+
"learning_rate": 5.593402470119302e-08,
|
| 120423 |
+
"loss": 0.6684,
|
| 120424 |
+
"step": 17202
|
| 120425 |
+
},
|
| 120426 |
+
{
|
| 120427 |
+
"epoch": 19.593732193732194,
|
| 120428 |
+
"grad_norm": 0.22096139192581177,
|
| 120429 |
+
"learning_rate": 5.562296397496891e-08,
|
| 120430 |
+
"loss": 0.4033,
|
| 120431 |
+
"step": 17203
|
| 120432 |
+
},
|
| 120433 |
+
{
|
| 120434 |
+
"epoch": 19.594871794871796,
|
| 120435 |
+
"grad_norm": 0.172435462474823,
|
| 120436 |
+
"learning_rate": 5.531276963555432e-08,
|
| 120437 |
+
"loss": 0.7666,
|
| 120438 |
+
"step": 17204
|
| 120439 |
+
},
|
| 120440 |
+
{
|
| 120441 |
+
"epoch": 19.596011396011395,
|
| 120442 |
+
"grad_norm": 0.16623039543628693,
|
| 120443 |
+
"learning_rate": 5.500344169372396e-08,
|
| 120444 |
+
"loss": 0.8804,
|
| 120445 |
+
"step": 17205
|
| 120446 |
+
},
|
| 120447 |
+
{
|
| 120448 |
+
"epoch": 19.597150997150997,
|
| 120449 |
+
"grad_norm": 0.20657214522361755,
|
| 120450 |
+
"learning_rate": 5.469498016022479e-08,
|
| 120451 |
+
"loss": 0.8464,
|
| 120452 |
+
"step": 17206
|
| 120453 |
+
},
|
| 120454 |
+
{
|
| 120455 |
+
"epoch": 19.5982905982906,
|
| 120456 |
+
"grad_norm": 0.17143048346042633,
|
| 120457 |
+
"learning_rate": 5.4387385045770454e-08,
|
| 120458 |
+
"loss": 0.6488,
|
| 120459 |
+
"step": 17207
|
| 120460 |
+
},
|
| 120461 |
+
{
|
| 120462 |
+
"epoch": 19.5994301994302,
|
| 120463 |
+
"grad_norm": 0.18172615766525269,
|
| 120464 |
+
"learning_rate": 5.408065636104132e-08,
|
| 120465 |
+
"loss": 0.6355,
|
| 120466 |
+
"step": 17208
|
| 120467 |
+
},
|
| 120468 |
+
{
|
| 120469 |
+
"epoch": 19.6005698005698,
|
| 120470 |
+
"grad_norm": 0.24612468481063843,
|
| 120471 |
+
"learning_rate": 5.377479411668995e-08,
|
| 120472 |
+
"loss": 0.7174,
|
| 120473 |
+
"step": 17209
|
| 120474 |
+
},
|
| 120475 |
+
{
|
| 120476 |
+
"epoch": 19.601709401709403,
|
| 120477 |
+
"grad_norm": 0.18231748044490814,
|
| 120478 |
+
"learning_rate": 5.346979832334675e-08,
|
| 120479 |
+
"loss": 0.5194,
|
| 120480 |
+
"step": 17210
|
| 120481 |
+
},
|
| 120482 |
+
{
|
| 120483 |
+
"epoch": 19.602849002849002,
|
| 120484 |
+
"grad_norm": 0.17460936307907104,
|
| 120485 |
+
"learning_rate": 5.3165668991597696e-08,
|
| 120486 |
+
"loss": 0.7452,
|
| 120487 |
+
"step": 17211
|
| 120488 |
+
},
|
| 120489 |
+
{
|
| 120490 |
+
"epoch": 19.603988603988604,
|
| 120491 |
+
"grad_norm": 0.16702604293823242,
|
| 120492 |
+
"learning_rate": 5.286240613200932e-08,
|
| 120493 |
+
"loss": 0.4361,
|
| 120494 |
+
"step": 17212
|
| 120495 |
+
},
|
| 120496 |
+
{
|
| 120497 |
+
"epoch": 19.605128205128207,
|
| 120498 |
+
"grad_norm": 0.16236288845539093,
|
| 120499 |
+
"learning_rate": 5.256000975511488e-08,
|
| 120500 |
+
"loss": 0.748,
|
| 120501 |
+
"step": 17213
|
| 120502 |
+
},
|
| 120503 |
+
{
|
| 120504 |
+
"epoch": 19.606267806267805,
|
| 120505 |
+
"grad_norm": 0.18586201965808868,
|
| 120506 |
+
"learning_rate": 5.2258479871417075e-08,
|
| 120507 |
+
"loss": 0.673,
|
| 120508 |
+
"step": 17214
|
| 120509 |
+
},
|
| 120510 |
+
{
|
| 120511 |
+
"epoch": 19.607407407407408,
|
| 120512 |
+
"grad_norm": 0.22434577345848083,
|
| 120513 |
+
"learning_rate": 5.195781649139087e-08,
|
| 120514 |
+
"loss": 0.6881,
|
| 120515 |
+
"step": 17215
|
| 120516 |
+
},
|
| 120517 |
+
{
|
| 120518 |
+
"epoch": 19.60854700854701,
|
| 120519 |
+
"grad_norm": 0.1948535442352295,
|
| 120520 |
+
"learning_rate": 5.1658019625475116e-08,
|
| 120521 |
+
"loss": 0.6597,
|
| 120522 |
+
"step": 17216
|
| 120523 |
+
},
|
| 120524 |
+
{
|
| 120525 |
+
"epoch": 19.60968660968661,
|
| 120526 |
+
"grad_norm": 0.1969522088766098,
|
| 120527 |
+
"learning_rate": 5.135908928408373e-08,
|
| 120528 |
+
"loss": 0.6556,
|
| 120529 |
+
"step": 17217
|
| 120530 |
+
},
|
| 120531 |
+
{
|
| 120532 |
+
"epoch": 19.61082621082621,
|
| 120533 |
+
"grad_norm": 0.21910102665424347,
|
| 120534 |
+
"learning_rate": 5.106102547760283e-08,
|
| 120535 |
+
"loss": 0.5069,
|
| 120536 |
+
"step": 17218
|
| 120537 |
+
},
|
| 120538 |
+
{
|
| 120539 |
+
"epoch": 19.611965811965813,
|
| 120540 |
+
"grad_norm": 0.17936351895332336,
|
| 120541 |
+
"learning_rate": 5.0763828216379703e-08,
|
| 120542 |
+
"loss": 0.7133,
|
| 120543 |
+
"step": 17219
|
| 120544 |
+
},
|
| 120545 |
+
{
|
| 120546 |
+
"epoch": 19.613105413105412,
|
| 120547 |
+
"grad_norm": 0.19450253248214722,
|
| 120548 |
+
"learning_rate": 5.046749751073943e-08,
|
| 120549 |
+
"loss": 0.611,
|
| 120550 |
+
"step": 17220
|
| 120551 |
+
},
|
| 120552 |
+
{
|
| 120553 |
+
"epoch": 19.614245014245014,
|
| 120554 |
+
"grad_norm": 0.19936460256576538,
|
| 120555 |
+
"learning_rate": 5.017203337097654e-08,
|
| 120556 |
+
"loss": 0.5414,
|
| 120557 |
+
"step": 17221
|
| 120558 |
+
},
|
| 120559 |
+
{
|
| 120560 |
+
"epoch": 19.615384615384617,
|
| 120561 |
+
"grad_norm": 0.17847365140914917,
|
| 120562 |
+
"learning_rate": 4.9877435807349494e-08,
|
| 120563 |
+
"loss": 0.6396,
|
| 120564 |
+
"step": 17222
|
| 120565 |
+
},
|
| 120566 |
+
{
|
| 120567 |
+
"epoch": 19.616524216524216,
|
| 120568 |
+
"grad_norm": 0.18983618915081024,
|
| 120569 |
+
"learning_rate": 4.958370483009456e-08,
|
| 120570 |
+
"loss": 0.814,
|
| 120571 |
+
"step": 17223
|
| 120572 |
+
},
|
| 120573 |
+
{
|
| 120574 |
+
"epoch": 19.617663817663818,
|
| 120575 |
+
"grad_norm": 0.20069336891174316,
|
| 120576 |
+
"learning_rate": 4.929084044940913e-08,
|
| 120577 |
+
"loss": 0.5583,
|
| 120578 |
+
"step": 17224
|
| 120579 |
+
},
|
| 120580 |
+
{
|
| 120581 |
+
"epoch": 19.61880341880342,
|
| 120582 |
+
"grad_norm": 0.2257624864578247,
|
| 120583 |
+
"learning_rate": 4.899884267546839e-08,
|
| 120584 |
+
"loss": 0.7554,
|
| 120585 |
+
"step": 17225
|
| 120586 |
+
},
|
| 120587 |
+
{
|
| 120588 |
+
"epoch": 19.61994301994302,
|
| 120589 |
+
"grad_norm": 0.20969153940677643,
|
| 120590 |
+
"learning_rate": 4.870771151841147e-08,
|
| 120591 |
+
"loss": 0.6199,
|
| 120592 |
+
"step": 17226
|
| 120593 |
+
},
|
| 120594 |
+
{
|
| 120595 |
+
"epoch": 19.62108262108262,
|
| 120596 |
+
"grad_norm": 0.21343040466308594,
|
| 120597 |
+
"learning_rate": 4.8417446988355265e-08,
|
| 120598 |
+
"loss": 0.8209,
|
| 120599 |
+
"step": 17227
|
| 120600 |
+
},
|
| 120601 |
+
{
|
| 120602 |
+
"epoch": 19.622222222222224,
|
| 120603 |
+
"grad_norm": 0.18037155270576477,
|
| 120604 |
+
"learning_rate": 4.812804909537505e-08,
|
| 120605 |
+
"loss": 0.6658,
|
| 120606 |
+
"step": 17228
|
| 120607 |
+
},
|
| 120608 |
+
{
|
| 120609 |
+
"epoch": 19.623361823361822,
|
| 120610 |
+
"grad_norm": 0.17783091962337494,
|
| 120611 |
+
"learning_rate": 4.783951784952945e-08,
|
| 120612 |
+
"loss": 0.7338,
|
| 120613 |
+
"step": 17229
|
| 120614 |
+
},
|
| 120615 |
+
{
|
| 120616 |
+
"epoch": 19.624501424501425,
|
| 120617 |
+
"grad_norm": 0.21028144657611847,
|
| 120618 |
+
"learning_rate": 4.755185326083267e-08,
|
| 120619 |
+
"loss": 0.8786,
|
| 120620 |
+
"step": 17230
|
| 120621 |
+
},
|
| 120622 |
+
{
|
| 120623 |
+
"epoch": 19.625641025641027,
|
| 120624 |
+
"grad_norm": 0.20974908769130707,
|
| 120625 |
+
"learning_rate": 4.726505533928227e-08,
|
| 120626 |
+
"loss": 0.6961,
|
| 120627 |
+
"step": 17231
|
| 120628 |
+
},
|
| 120629 |
+
{
|
| 120630 |
+
"epoch": 19.626780626780626,
|
| 120631 |
+
"grad_norm": 0.1904968023300171,
|
| 120632 |
+
"learning_rate": 4.697912409483418e-08,
|
| 120633 |
+
"loss": 0.7653,
|
| 120634 |
+
"step": 17232
|
| 120635 |
+
},
|
| 120636 |
+
{
|
| 120637 |
+
"epoch": 19.627920227920228,
|
| 120638 |
+
"grad_norm": 0.2758485972881317,
|
| 120639 |
+
"learning_rate": 4.669405953742489e-08,
|
| 120640 |
+
"loss": 0.5149,
|
| 120641 |
+
"step": 17233
|
| 120642 |
+
},
|
| 120643 |
+
{
|
| 120644 |
+
"epoch": 19.62905982905983,
|
| 120645 |
+
"grad_norm": 0.18627852201461792,
|
| 120646 |
+
"learning_rate": 4.6409861676949276e-08,
|
| 120647 |
+
"loss": 0.7498,
|
| 120648 |
+
"step": 17234
|
| 120649 |
+
},
|
| 120650 |
+
{
|
| 120651 |
+
"epoch": 19.63019943019943,
|
| 120652 |
+
"grad_norm": 0.20226365327835083,
|
| 120653 |
+
"learning_rate": 4.612653052328553e-08,
|
| 120654 |
+
"loss": 0.7716,
|
| 120655 |
+
"step": 17235
|
| 120656 |
+
},
|
| 120657 |
+
{
|
| 120658 |
+
"epoch": 19.63133903133903,
|
| 120659 |
+
"grad_norm": 0.2074815034866333,
|
| 120660 |
+
"learning_rate": 4.584406608626746e-08,
|
| 120661 |
+
"loss": 0.6938,
|
| 120662 |
+
"step": 17236
|
| 120663 |
+
},
|
| 120664 |
+
{
|
| 120665 |
+
"epoch": 19.632478632478634,
|
| 120666 |
+
"grad_norm": 0.1934041976928711,
|
| 120667 |
+
"learning_rate": 4.556246837571221e-08,
|
| 120668 |
+
"loss": 0.8236,
|
| 120669 |
+
"step": 17237
|
| 120670 |
+
},
|
| 120671 |
+
{
|
| 120672 |
+
"epoch": 19.633618233618233,
|
| 120673 |
+
"grad_norm": 0.19022026658058167,
|
| 120674 |
+
"learning_rate": 4.5281737401395295e-08,
|
| 120675 |
+
"loss": 0.4179,
|
| 120676 |
+
"step": 17238
|
| 120677 |
+
},
|
| 120678 |
+
{
|
| 120679 |
+
"epoch": 19.634757834757835,
|
| 120680 |
+
"grad_norm": 0.18007512390613556,
|
| 120681 |
+
"learning_rate": 4.500187317307003e-08,
|
| 120682 |
+
"loss": 0.5701,
|
| 120683 |
+
"step": 17239
|
| 120684 |
+
},
|
| 120685 |
+
{
|
| 120686 |
+
"epoch": 19.635897435897437,
|
| 120687 |
+
"grad_norm": 0.20612673461437225,
|
| 120688 |
+
"learning_rate": 4.472287570045641e-08,
|
| 120689 |
+
"loss": 0.6698,
|
| 120690 |
+
"step": 17240
|
| 120691 |
+
},
|
| 120692 |
+
{
|
| 120693 |
+
"epoch": 19.637037037037036,
|
| 120694 |
+
"grad_norm": 0.20322008430957794,
|
| 120695 |
+
"learning_rate": 4.444474499324391e-08,
|
| 120696 |
+
"loss": 0.3804,
|
| 120697 |
+
"step": 17241
|
| 120698 |
+
},
|
| 120699 |
+
{
|
| 120700 |
+
"epoch": 19.63817663817664,
|
| 120701 |
+
"grad_norm": 0.17203862965106964,
|
| 120702 |
+
"learning_rate": 4.416748106109425e-08,
|
| 120703 |
+
"loss": 0.6458,
|
| 120704 |
+
"step": 17242
|
| 120705 |
+
},
|
| 120706 |
+
{
|
| 120707 |
+
"epoch": 19.63931623931624,
|
| 120708 |
+
"grad_norm": 0.23662760853767395,
|
| 120709 |
+
"learning_rate": 4.389108391363583e-08,
|
| 120710 |
+
"loss": 0.6583,
|
| 120711 |
+
"step": 17243
|
| 120712 |
+
},
|
| 120713 |
+
{
|
| 120714 |
+
"epoch": 19.64045584045584,
|
| 120715 |
+
"grad_norm": 0.19999438524246216,
|
| 120716 |
+
"learning_rate": 4.361555356046931e-08,
|
| 120717 |
+
"loss": 0.5216,
|
| 120718 |
+
"step": 17244
|
| 120719 |
+
},
|
| 120720 |
+
{
|
| 120721 |
+
"epoch": 19.64159544159544,
|
| 120722 |
+
"grad_norm": 0.23440754413604736,
|
| 120723 |
+
"learning_rate": 4.334089001116759e-08,
|
| 120724 |
+
"loss": 0.55,
|
| 120725 |
+
"step": 17245
|
| 120726 |
+
},
|
| 120727 |
+
{
|
| 120728 |
+
"epoch": 19.642735042735044,
|
| 120729 |
+
"grad_norm": 0.1712341159582138,
|
| 120730 |
+
"learning_rate": 4.30670932752647e-08,
|
| 120731 |
+
"loss": 0.7136,
|
| 120732 |
+
"step": 17246
|
| 120733 |
+
},
|
| 120734 |
+
{
|
| 120735 |
+
"epoch": 19.643874643874643,
|
| 120736 |
+
"grad_norm": 0.18940702080726624,
|
| 120737 |
+
"learning_rate": 4.2794163362275265e-08,
|
| 120738 |
+
"loss": 0.6789,
|
| 120739 |
+
"step": 17247
|
| 120740 |
+
},
|
| 120741 |
+
{
|
| 120742 |
+
"epoch": 19.645014245014245,
|
| 120743 |
+
"grad_norm": 0.17617487907409668,
|
| 120744 |
+
"learning_rate": 4.25221002816778e-08,
|
| 120745 |
+
"loss": 0.4361,
|
| 120746 |
+
"step": 17248
|
| 120747 |
+
},
|
| 120748 |
+
{
|
| 120749 |
+
"epoch": 19.646153846153847,
|
| 120750 |
+
"grad_norm": 0.19227629899978638,
|
| 120751 |
+
"learning_rate": 4.225090404291754e-08,
|
| 120752 |
+
"loss": 0.7244,
|
| 120753 |
+
"step": 17249
|
| 120754 |
+
},
|
| 120755 |
+
{
|
| 120756 |
+
"epoch": 19.647293447293446,
|
| 120757 |
+
"grad_norm": 0.2293432205915451,
|
| 120758 |
+
"learning_rate": 4.198057465542027e-08,
|
| 120759 |
+
"loss": 0.7112,
|
| 120760 |
+
"step": 17250
|
| 120761 |
+
},
|
| 120762 |
+
{
|
| 120763 |
+
"epoch": 19.64843304843305,
|
| 120764 |
+
"grad_norm": 0.1894661784172058,
|
| 120765 |
+
"learning_rate": 4.171111212857293e-08,
|
| 120766 |
+
"loss": 0.6733,
|
| 120767 |
+
"step": 17251
|
| 120768 |
+
},
|
| 120769 |
+
{
|
| 120770 |
+
"epoch": 19.64957264957265,
|
| 120771 |
+
"grad_norm": 0.20832861959934235,
|
| 120772 |
+
"learning_rate": 4.144251647173469e-08,
|
| 120773 |
+
"loss": 0.6157,
|
| 120774 |
+
"step": 17252
|
| 120775 |
+
},
|
| 120776 |
+
{
|
| 120777 |
+
"epoch": 19.65071225071225,
|
| 120778 |
+
"grad_norm": 0.1731022298336029,
|
| 120779 |
+
"learning_rate": 4.1174787694231444e-08,
|
| 120780 |
+
"loss": 0.6309,
|
| 120781 |
+
"step": 17253
|
| 120782 |
+
},
|
| 120783 |
+
{
|
| 120784 |
+
"epoch": 19.651851851851852,
|
| 120785 |
+
"grad_norm": 0.20629489421844482,
|
| 120786 |
+
"learning_rate": 4.0907925805366845e-08,
|
| 120787 |
+
"loss": 0.7796,
|
| 120788 |
+
"step": 17254
|
| 120789 |
+
},
|
| 120790 |
+
{
|
| 120791 |
+
"epoch": 19.652991452991454,
|
| 120792 |
+
"grad_norm": 0.1739402562379837,
|
| 120793 |
+
"learning_rate": 4.064193081440848e-08,
|
| 120794 |
+
"loss": 0.8284,
|
| 120795 |
+
"step": 17255
|
| 120796 |
+
},
|
| 120797 |
+
{
|
| 120798 |
+
"epoch": 19.654131054131053,
|
| 120799 |
+
"grad_norm": 0.20788271725177765,
|
| 120800 |
+
"learning_rate": 4.0376802730593414e-08,
|
| 120801 |
+
"loss": 0.3069,
|
| 120802 |
+
"step": 17256
|
| 120803 |
+
},
|
| 120804 |
+
{
|
| 120805 |
+
"epoch": 19.655270655270655,
|
| 120806 |
+
"grad_norm": 0.1854596734046936,
|
| 120807 |
+
"learning_rate": 4.0112541563130935e-08,
|
| 120808 |
+
"loss": 0.7617,
|
| 120809 |
+
"step": 17257
|
| 120810 |
+
},
|
| 120811 |
+
{
|
| 120812 |
+
"epoch": 19.656410256410258,
|
| 120813 |
+
"grad_norm": 0.2370794266462326,
|
| 120814 |
+
"learning_rate": 3.984914732119704e-08,
|
| 120815 |
+
"loss": 0.47,
|
| 120816 |
+
"step": 17258
|
| 120817 |
+
},
|
| 120818 |
+
{
|
| 120819 |
+
"epoch": 19.657549857549856,
|
| 120820 |
+
"grad_norm": 0.20367947220802307,
|
| 120821 |
+
"learning_rate": 3.9586620013948304e-08,
|
| 120822 |
+
"loss": 0.5533,
|
| 120823 |
+
"step": 17259
|
| 120824 |
+
},
|
| 120825 |
+
{
|
| 120826 |
+
"epoch": 19.65868945868946,
|
| 120827 |
+
"grad_norm": 0.192902609705925,
|
| 120828 |
+
"learning_rate": 3.93249596504941e-08,
|
| 120829 |
+
"loss": 0.7089,
|
| 120830 |
+
"step": 17260
|
| 120831 |
+
},
|
| 120832 |
+
{
|
| 120833 |
+
"epoch": 19.65982905982906,
|
| 120834 |
+
"grad_norm": 0.20828105509281158,
|
| 120835 |
+
"learning_rate": 3.906416623992715e-08,
|
| 120836 |
+
"loss": 0.5944,
|
| 120837 |
+
"step": 17261
|
| 120838 |
+
},
|
| 120839 |
+
{
|
| 120840 |
+
"epoch": 19.66096866096866,
|
| 120841 |
+
"grad_norm": 0.20111463963985443,
|
| 120842 |
+
"learning_rate": 3.8804239791304097e-08,
|
| 120843 |
+
"loss": 0.4979,
|
| 120844 |
+
"step": 17262
|
| 120845 |
+
},
|
| 120846 |
+
{
|
| 120847 |
+
"epoch": 19.662108262108262,
|
| 120848 |
+
"grad_norm": 0.18175876140594482,
|
| 120849 |
+
"learning_rate": 3.854518031365384e-08,
|
| 120850 |
+
"loss": 0.6765,
|
| 120851 |
+
"step": 17263
|
| 120852 |
+
},
|
| 120853 |
+
{
|
| 120854 |
+
"epoch": 19.663247863247864,
|
| 120855 |
+
"grad_norm": 0.19266632199287415,
|
| 120856 |
+
"learning_rate": 3.828698781597473e-08,
|
| 120857 |
+
"loss": 0.4712,
|
| 120858 |
+
"step": 17264
|
| 120859 |
+
},
|
| 120860 |
+
{
|
| 120861 |
+
"epoch": 19.664387464387463,
|
| 120862 |
+
"grad_norm": 0.1943490207195282,
|
| 120863 |
+
"learning_rate": 3.8029662307231815e-08,
|
| 120864 |
+
"loss": 0.6413,
|
| 120865 |
+
"step": 17265
|
| 120866 |
+
},
|
| 120867 |
+
{
|
| 120868 |
+
"epoch": 19.665527065527066,
|
| 120869 |
+
"grad_norm": 0.18787044286727905,
|
| 120870 |
+
"learning_rate": 3.7773203796365175e-08,
|
| 120871 |
+
"loss": 0.6085,
|
| 120872 |
+
"step": 17266
|
| 120873 |
+
},
|
| 120874 |
+
{
|
| 120875 |
+
"epoch": 19.666666666666668,
|
| 120876 |
+
"grad_norm": 0.1959238350391388,
|
| 120877 |
+
"learning_rate": 3.751761229228157e-08,
|
| 120878 |
+
"loss": 0.3295,
|
| 120879 |
+
"step": 17267
|
| 120880 |
+
},
|
| 120881 |
+
{
|
| 120882 |
+
"epoch": 19.667806267806267,
|
| 120883 |
+
"grad_norm": 0.1961667388677597,
|
| 120884 |
+
"learning_rate": 3.7262887803857224e-08,
|
| 120885 |
+
"loss": 0.824,
|
| 120886 |
+
"step": 17268
|
| 120887 |
+
},
|
| 120888 |
+
{
|
| 120889 |
+
"epoch": 19.66894586894587,
|
| 120890 |
+
"grad_norm": 0.1957489252090454,
|
| 120891 |
+
"learning_rate": 3.700903033994063e-08,
|
| 120892 |
+
"loss": 0.8551,
|
| 120893 |
+
"step": 17269
|
| 120894 |
+
},
|
| 120895 |
+
{
|
| 120896 |
+
"epoch": 19.67008547008547,
|
| 120897 |
+
"grad_norm": 0.20766261219978333,
|
| 120898 |
+
"learning_rate": 3.67560399093525e-08,
|
| 120899 |
+
"loss": 0.8463,
|
| 120900 |
+
"step": 17270
|
| 120901 |
+
},
|
| 120902 |
+
{
|
| 120903 |
+
"epoch": 19.67122507122507,
|
| 120904 |
+
"grad_norm": 0.20428958535194397,
|
| 120905 |
+
"learning_rate": 3.6503916520871926e-08,
|
| 120906 |
+
"loss": 0.5918,
|
| 120907 |
+
"step": 17271
|
| 120908 |
+
},
|
| 120909 |
+
{
|
| 120910 |
+
"epoch": 19.672364672364672,
|
| 120911 |
+
"grad_norm": 0.21748413145542145,
|
| 120912 |
+
"learning_rate": 3.6252660183261346e-08,
|
| 120913 |
+
"loss": 0.5408,
|
| 120914 |
+
"step": 17272
|
| 120915 |
+
},
|
| 120916 |
+
{
|
| 120917 |
+
"epoch": 19.673504273504275,
|
| 120918 |
+
"grad_norm": 0.1851986199617386,
|
| 120919 |
+
"learning_rate": 3.600227090524711e-08,
|
| 120920 |
+
"loss": 0.6178,
|
| 120921 |
+
"step": 17273
|
| 120922 |
+
},
|
| 120923 |
+
{
|
| 120924 |
+
"epoch": 19.674643874643873,
|
| 120925 |
+
"grad_norm": 0.19075873494148254,
|
| 120926 |
+
"learning_rate": 3.5752748695527805e-08,
|
| 120927 |
+
"loss": 0.8041,
|
| 120928 |
+
"step": 17274
|
| 120929 |
+
},
|
| 120930 |
+
{
|
| 120931 |
+
"epoch": 19.675783475783476,
|
| 120932 |
+
"grad_norm": 0.2254505455493927,
|
| 120933 |
+
"learning_rate": 3.550409356276318e-08,
|
| 120934 |
+
"loss": 0.7691,
|
| 120935 |
+
"step": 17275
|
| 120936 |
+
},
|
| 120937 |
+
{
|
| 120938 |
+
"epoch": 19.676923076923078,
|
| 120939 |
+
"grad_norm": 0.22736750543117523,
|
| 120940 |
+
"learning_rate": 3.525630551559633e-08,
|
| 120941 |
+
"loss": 0.4992,
|
| 120942 |
+
"step": 17276
|
| 120943 |
+
},
|
| 120944 |
+
{
|
| 120945 |
+
"epoch": 19.678062678062677,
|
| 120946 |
+
"grad_norm": 0.22003592550754547,
|
| 120947 |
+
"learning_rate": 3.5009384562631473e-08,
|
| 120948 |
+
"loss": 0.7605,
|
| 120949 |
+
"step": 17277
|
| 120950 |
+
},
|
| 120951 |
+
{
|
| 120952 |
+
"epoch": 19.67920227920228,
|
| 120953 |
+
"grad_norm": 0.21777081489562988,
|
| 120954 |
+
"learning_rate": 3.476333071244231e-08,
|
| 120955 |
+
"loss": 0.6189,
|
| 120956 |
+
"step": 17278
|
| 120957 |
+
},
|
| 120958 |
+
{
|
| 120959 |
+
"epoch": 19.68034188034188,
|
| 120960 |
+
"grad_norm": 0.1750691831111908,
|
| 120961 |
+
"learning_rate": 3.451814397358033e-08,
|
| 120962 |
+
"loss": 0.7692,
|
| 120963 |
+
"step": 17279
|
| 120964 |
+
},
|
| 120965 |
+
{
|
| 120966 |
+
"epoch": 19.68148148148148,
|
| 120967 |
+
"grad_norm": 0.24190931022167206,
|
| 120968 |
+
"learning_rate": 3.4273824354555395e-08,
|
| 120969 |
+
"loss": 0.423,
|
| 120970 |
+
"step": 17280
|
| 120971 |
+
},
|
| 120972 |
+
{
|
| 120973 |
+
"epoch": 19.682621082621083,
|
| 120974 |
+
"grad_norm": 0.20943762362003326,
|
| 120975 |
+
"learning_rate": 3.403037186386071e-08,
|
| 120976 |
+
"loss": 0.6394,
|
| 120977 |
+
"step": 17281
|
| 120978 |
+
},
|
| 120979 |
+
{
|
| 120980 |
+
"epoch": 19.683760683760685,
|
| 120981 |
+
"grad_norm": 0.22648000717163086,
|
| 120982 |
+
"learning_rate": 3.378778650994507e-08,
|
| 120983 |
+
"loss": 0.5333,
|
| 120984 |
+
"step": 17282
|
| 120985 |
+
},
|
| 120986 |
+
{
|
| 120987 |
+
"epoch": 19.684900284900284,
|
| 120988 |
+
"grad_norm": 0.16168929636478424,
|
| 120989 |
+
"learning_rate": 3.354606830123508e-08,
|
| 120990 |
+
"loss": 0.788,
|
| 120991 |
+
"step": 17283
|
| 120992 |
+
},
|
| 120993 |
+
{
|
| 120994 |
+
"epoch": 19.686039886039886,
|
| 120995 |
+
"grad_norm": 0.1891418695449829,
|
| 120996 |
+
"learning_rate": 3.3305217246132335e-08,
|
| 120997 |
+
"loss": 0.6606,
|
| 120998 |
+
"step": 17284
|
| 120999 |
+
},
|
| 121000 |
+
{
|
| 121001 |
+
"epoch": 19.68717948717949,
|
| 121002 |
+
"grad_norm": 0.17276088893413544,
|
| 121003 |
+
"learning_rate": 3.306523335299683e-08,
|
| 121004 |
+
"loss": 0.7186,
|
| 121005 |
+
"step": 17285
|
| 121006 |
+
},
|
| 121007 |
+
{
|
| 121008 |
+
"epoch": 19.688319088319087,
|
| 121009 |
+
"grad_norm": 0.23356008529663086,
|
| 121010 |
+
"learning_rate": 3.282611663016355e-08,
|
| 121011 |
+
"loss": 0.5289,
|
| 121012 |
+
"step": 17286
|
| 121013 |
+
},
|
| 121014 |
+
{
|
| 121015 |
+
"epoch": 19.68945868945869,
|
| 121016 |
+
"grad_norm": 0.20581302046775818,
|
| 121017 |
+
"learning_rate": 3.258786708593975e-08,
|
| 121018 |
+
"loss": 0.4179,
|
| 121019 |
+
"step": 17287
|
| 121020 |
+
},
|
| 121021 |
+
{
|
| 121022 |
+
"epoch": 19.69059829059829,
|
| 121023 |
+
"grad_norm": 0.1834385246038437,
|
| 121024 |
+
"learning_rate": 3.235048472859936e-08,
|
| 121025 |
+
"loss": 0.6018,
|
| 121026 |
+
"step": 17288
|
| 121027 |
+
},
|
| 121028 |
+
{
|
| 121029 |
+
"epoch": 19.69173789173789,
|
| 121030 |
+
"grad_norm": 0.1842707395553589,
|
| 121031 |
+
"learning_rate": 3.211396956639134e-08,
|
| 121032 |
+
"loss": 0.701,
|
| 121033 |
+
"step": 17289
|
| 121034 |
+
},
|
| 121035 |
+
{
|
| 121036 |
+
"epoch": 19.692877492877493,
|
| 121037 |
+
"grad_norm": 0.21426624059677124,
|
| 121038 |
+
"learning_rate": 3.187832160752302e-08,
|
| 121039 |
+
"loss": 0.3809,
|
| 121040 |
+
"step": 17290
|
| 121041 |
+
},
|
| 121042 |
+
{
|
| 121043 |
+
"epoch": 19.694017094017095,
|
| 121044 |
+
"grad_norm": 0.17906080186367035,
|
| 121045 |
+
"learning_rate": 3.164354086018506e-08,
|
| 121046 |
+
"loss": 0.8176,
|
| 121047 |
+
"step": 17291
|
| 121048 |
+
},
|
| 121049 |
+
{
|
| 121050 |
+
"epoch": 19.695156695156694,
|
| 121051 |
+
"grad_norm": 0.26043346524238586,
|
| 121052 |
+
"learning_rate": 3.140962733252928e-08,
|
| 121053 |
+
"loss": 0.607,
|
| 121054 |
+
"step": 17292
|
| 121055 |
+
},
|
| 121056 |
+
{
|
| 121057 |
+
"epoch": 19.696296296296296,
|
| 121058 |
+
"grad_norm": 0.22749273478984833,
|
| 121059 |
+
"learning_rate": 3.1176581032682506e-08,
|
| 121060 |
+
"loss": 0.7603,
|
| 121061 |
+
"step": 17293
|
| 121062 |
+
},
|
| 121063 |
+
{
|
| 121064 |
+
"epoch": 19.6974358974359,
|
| 121065 |
+
"grad_norm": 0.19497859477996826,
|
| 121066 |
+
"learning_rate": 3.094440196873827e-08,
|
| 121067 |
+
"loss": 0.7188,
|
| 121068 |
+
"step": 17294
|
| 121069 |
+
},
|
| 121070 |
+
{
|
| 121071 |
+
"epoch": 19.698575498575497,
|
| 121072 |
+
"grad_norm": 0.1934613287448883,
|
| 121073 |
+
"learning_rate": 3.071309014875679e-08,
|
| 121074 |
+
"loss": 0.7491,
|
| 121075 |
+
"step": 17295
|
| 121076 |
+
},
|
| 121077 |
+
{
|
| 121078 |
+
"epoch": 19.6997150997151,
|
| 121079 |
+
"grad_norm": 0.1895592212677002,
|
| 121080 |
+
"learning_rate": 3.0482645580778846e-08,
|
| 121081 |
+
"loss": 0.699,
|
| 121082 |
+
"step": 17296
|
| 121083 |
+
},
|
| 121084 |
+
{
|
| 121085 |
+
"epoch": 19.700854700854702,
|
| 121086 |
+
"grad_norm": 0.18725530803203583,
|
| 121087 |
+
"learning_rate": 3.025306827280361e-08,
|
| 121088 |
+
"loss": 0.7173,
|
| 121089 |
+
"step": 17297
|
| 121090 |
+
},
|
| 121091 |
+
{
|
| 121092 |
+
"epoch": 19.7019943019943,
|
| 121093 |
+
"grad_norm": 0.19018876552581787,
|
| 121094 |
+
"learning_rate": 3.002435823280525e-08,
|
| 121095 |
+
"loss": 0.7807,
|
| 121096 |
+
"step": 17298
|
| 121097 |
+
},
|
| 121098 |
+
{
|
| 121099 |
+
"epoch": 19.703133903133903,
|
| 121100 |
+
"grad_norm": 0.18515364825725555,
|
| 121101 |
+
"learning_rate": 2.9796515468730192e-08,
|
| 121102 |
+
"loss": 0.8516,
|
| 121103 |
+
"step": 17299
|
| 121104 |
+
},
|
| 121105 |
+
{
|
| 121106 |
+
"epoch": 19.704273504273505,
|
| 121107 |
+
"grad_norm": 0.2370092123746872,
|
| 121108 |
+
"learning_rate": 2.956953998848877e-08,
|
| 121109 |
+
"loss": 0.5101,
|
| 121110 |
+
"step": 17300
|
| 121111 |
+
},
|
| 121112 |
+
{
|
| 121113 |
+
"epoch": 19.705413105413104,
|
| 121114 |
+
"grad_norm": 0.21618060767650604,
|
| 121115 |
+
"learning_rate": 2.9343431799969122e-08,
|
| 121116 |
+
"loss": 0.5587,
|
| 121117 |
+
"step": 17301
|
| 121118 |
+
},
|
| 121119 |
+
{
|
| 121120 |
+
"epoch": 19.706552706552706,
|
| 121121 |
+
"grad_norm": 0.15011045336723328,
|
| 121122 |
+
"learning_rate": 2.9118190911020527e-08,
|
| 121123 |
+
"loss": 0.6464,
|
| 121124 |
+
"step": 17302
|
| 121125 |
+
},
|
| 121126 |
+
{
|
| 121127 |
+
"epoch": 19.70769230769231,
|
| 121128 |
+
"grad_norm": 0.2167392075061798,
|
| 121129 |
+
"learning_rate": 2.88938173294645e-08,
|
| 121130 |
+
"loss": 0.6599,
|
| 121131 |
+
"step": 17303
|
| 121132 |
+
},
|
| 121133 |
+
{
|
| 121134 |
+
"epoch": 19.708831908831907,
|
| 121135 |
+
"grad_norm": 0.2287842035293579,
|
| 121136 |
+
"learning_rate": 2.8670311063100362e-08,
|
| 121137 |
+
"loss": 0.543,
|
| 121138 |
+
"step": 17304
|
| 121139 |
+
},
|
| 121140 |
+
{
|
| 121141 |
+
"epoch": 19.70997150997151,
|
| 121142 |
+
"grad_norm": 0.17364954948425293,
|
| 121143 |
+
"learning_rate": 2.8447672119685797e-08,
|
| 121144 |
+
"loss": 0.6019,
|
| 121145 |
+
"step": 17305
|
| 121146 |
+
},
|
| 121147 |
+
{
|
| 121148 |
+
"epoch": 19.711111111111112,
|
| 121149 |
+
"grad_norm": 0.19438974559307098,
|
| 121150 |
+
"learning_rate": 2.8225900506956282e-08,
|
| 121151 |
+
"loss": 0.6255,
|
| 121152 |
+
"step": 17306
|
| 121153 |
+
},
|
| 121154 |
+
{
|
| 121155 |
+
"epoch": 19.71225071225071,
|
| 121156 |
+
"grad_norm": 0.22095739841461182,
|
| 121157 |
+
"learning_rate": 2.8004996232613988e-08,
|
| 121158 |
+
"loss": 0.6274,
|
| 121159 |
+
"step": 17307
|
| 121160 |
+
},
|
| 121161 |
+
{
|
| 121162 |
+
"epoch": 19.713390313390313,
|
| 121163 |
+
"grad_norm": 0.18750642240047455,
|
| 121164 |
+
"learning_rate": 2.7784959304333337e-08,
|
| 121165 |
+
"loss": 0.8426,
|
| 121166 |
+
"step": 17308
|
| 121167 |
+
},
|
| 121168 |
+
{
|
| 121169 |
+
"epoch": 19.714529914529916,
|
| 121170 |
+
"grad_norm": 0.21393738687038422,
|
| 121171 |
+
"learning_rate": 2.7565789729752655e-08,
|
| 121172 |
+
"loss": 0.7651,
|
| 121173 |
+
"step": 17309
|
| 121174 |
+
},
|
| 121175 |
+
{
|
| 121176 |
+
"epoch": 19.715669515669514,
|
| 121177 |
+
"grad_norm": 0.17756567895412445,
|
| 121178 |
+
"learning_rate": 2.734748751648808e-08,
|
| 121179 |
+
"loss": 0.6271,
|
| 121180 |
+
"step": 17310
|
| 121181 |
+
},
|
| 121182 |
+
{
|
| 121183 |
+
"epoch": 19.716809116809117,
|
| 121184 |
+
"grad_norm": 0.20901112258434296,
|
| 121185 |
+
"learning_rate": 2.7130052672119653e-08,
|
| 121186 |
+
"loss": 0.4133,
|
| 121187 |
+
"step": 17311
|
| 121188 |
+
},
|
| 121189 |
+
{
|
| 121190 |
+
"epoch": 19.71794871794872,
|
| 121191 |
+
"grad_norm": 0.18372060358524323,
|
| 121192 |
+
"learning_rate": 2.6913485204199672e-08,
|
| 121193 |
+
"loss": 0.7573,
|
| 121194 |
+
"step": 17312
|
| 121195 |
+
},
|
| 121196 |
+
{
|
| 121197 |
+
"epoch": 19.719088319088318,
|
| 121198 |
+
"grad_norm": 0.22114580869674683,
|
| 121199 |
+
"learning_rate": 2.6697785120249895e-08,
|
| 121200 |
+
"loss": 0.529,
|
| 121201 |
+
"step": 17313
|
| 121202 |
+
},
|
| 121203 |
+
{
|
| 121204 |
+
"epoch": 19.72022792022792,
|
| 121205 |
+
"grad_norm": 0.17835091054439545,
|
| 121206 |
+
"learning_rate": 2.6482952427764328e-08,
|
| 121207 |
+
"loss": 0.6569,
|
| 121208 |
+
"step": 17314
|
| 121209 |
+
},
|
| 121210 |
+
{
|
| 121211 |
+
"epoch": 19.721367521367522,
|
| 121212 |
+
"grad_norm": 0.20545682311058044,
|
| 121213 |
+
"learning_rate": 2.6268987134200897e-08,
|
| 121214 |
+
"loss": 0.5758,
|
| 121215 |
+
"step": 17315
|
| 121216 |
+
},
|
| 121217 |
+
{
|
| 121218 |
+
"epoch": 19.72250712250712,
|
| 121219 |
+
"grad_norm": 0.2764587104320526,
|
| 121220 |
+
"learning_rate": 2.6055889246995313e-08,
|
| 121221 |
+
"loss": 0.5116,
|
| 121222 |
+
"step": 17316
|
| 121223 |
+
},
|
| 121224 |
+
{
|
| 121225 |
+
"epoch": 19.723646723646723,
|
| 121226 |
+
"grad_norm": 0.1845266968011856,
|
| 121227 |
+
"learning_rate": 2.584365877354722e-08,
|
| 121228 |
+
"loss": 0.4803,
|
| 121229 |
+
"step": 17317
|
| 121230 |
+
},
|
| 121231 |
+
{
|
| 121232 |
+
"epoch": 19.724786324786326,
|
| 121233 |
+
"grad_norm": 0.20697034895420074,
|
| 121234 |
+
"learning_rate": 2.5632295721228493e-08,
|
| 121235 |
+
"loss": 0.7492,
|
| 121236 |
+
"step": 17318
|
| 121237 |
+
},
|
| 121238 |
+
{
|
| 121239 |
+
"epoch": 19.725925925925925,
|
| 121240 |
+
"grad_norm": 0.2017263025045395,
|
| 121241 |
+
"learning_rate": 2.542180009738049e-08,
|
| 121242 |
+
"loss": 0.7248,
|
| 121243 |
+
"step": 17319
|
| 121244 |
+
},
|
| 121245 |
+
{
|
| 121246 |
+
"epoch": 19.727065527065527,
|
| 121247 |
+
"grad_norm": 0.1986721009016037,
|
| 121248 |
+
"learning_rate": 2.5212171909311243e-08,
|
| 121249 |
+
"loss": 0.7983,
|
| 121250 |
+
"step": 17320
|
| 121251 |
+
},
|
| 121252 |
+
{
|
| 121253 |
+
"epoch": 19.72820512820513,
|
| 121254 |
+
"grad_norm": 0.23680278658866882,
|
| 121255 |
+
"learning_rate": 2.5003411164306602e-08,
|
| 121256 |
+
"loss": 0.6465,
|
| 121257 |
+
"step": 17321
|
| 121258 |
+
},
|
| 121259 |
+
{
|
| 121260 |
+
"epoch": 19.729344729344728,
|
| 121261 |
+
"grad_norm": 0.1814713180065155,
|
| 121262 |
+
"learning_rate": 2.479551786961354e-08,
|
| 121263 |
+
"loss": 0.7606,
|
| 121264 |
+
"step": 17322
|
| 121265 |
+
},
|
| 121266 |
+
{
|
| 121267 |
+
"epoch": 19.73048433048433,
|
| 121268 |
+
"grad_norm": 0.20839419960975647,
|
| 121269 |
+
"learning_rate": 2.4588492032456833e-08,
|
| 121270 |
+
"loss": 0.6567,
|
| 121271 |
+
"step": 17323
|
| 121272 |
+
},
|
| 121273 |
+
{
|
| 121274 |
+
"epoch": 19.731623931623933,
|
| 121275 |
+
"grad_norm": 0.21391022205352783,
|
| 121276 |
+
"learning_rate": 2.438233366001963e-08,
|
| 121277 |
+
"loss": 0.6914,
|
| 121278 |
+
"step": 17324
|
| 121279 |
+
},
|
| 121280 |
+
{
|
| 121281 |
+
"epoch": 19.73276353276353,
|
| 121282 |
+
"grad_norm": 0.22437989711761475,
|
| 121283 |
+
"learning_rate": 2.417704275947119e-08,
|
| 121284 |
+
"loss": 0.5848,
|
| 121285 |
+
"step": 17325
|
| 121286 |
+
},
|
| 121287 |
+
{
|
| 121288 |
+
"epoch": 19.733903133903134,
|
| 121289 |
+
"grad_norm": 0.15253695845603943,
|
| 121290 |
+
"learning_rate": 2.3972619337936374e-08,
|
| 121291 |
+
"loss": 0.727,
|
| 121292 |
+
"step": 17326
|
| 121293 |
+
},
|
| 121294 |
+
{
|
| 121295 |
+
"epoch": 19.735042735042736,
|
| 121296 |
+
"grad_norm": 0.16123710572719574,
|
| 121297 |
+
"learning_rate": 2.376906340251783e-08,
|
| 121298 |
+
"loss": 0.6649,
|
| 121299 |
+
"step": 17327
|
| 121300 |
+
},
|
| 121301 |
+
{
|
| 121302 |
+
"epoch": 19.736182336182335,
|
| 121303 |
+
"grad_norm": 0.20879414677619934,
|
| 121304 |
+
"learning_rate": 2.356637496028491e-08,
|
| 121305 |
+
"loss": 0.6138,
|
| 121306 |
+
"step": 17328
|
| 121307 |
+
},
|
| 121308 |
+
{
|
| 121309 |
+
"epoch": 19.737321937321937,
|
| 121310 |
+
"grad_norm": 0.16920596361160278,
|
| 121311 |
+
"learning_rate": 2.3364554018273642e-08,
|
| 121312 |
+
"loss": 0.7812,
|
| 121313 |
+
"step": 17329
|
| 121314 |
+
},
|
| 121315 |
+
{
|
| 121316 |
+
"epoch": 19.73846153846154,
|
| 121317 |
+
"grad_norm": 0.19896115362644196,
|
| 121318 |
+
"learning_rate": 2.3163600583500645e-08,
|
| 121319 |
+
"loss": 0.6453,
|
| 121320 |
+
"step": 17330
|
| 121321 |
+
},
|
| 121322 |
+
{
|
| 121323 |
+
"epoch": 19.739601139601138,
|
| 121324 |
+
"grad_norm": 0.1775745004415512,
|
| 121325 |
+
"learning_rate": 2.2963514662943664e-08,
|
| 121326 |
+
"loss": 0.814,
|
| 121327 |
+
"step": 17331
|
| 121328 |
+
},
|
| 121329 |
+
{
|
| 121330 |
+
"epoch": 19.74074074074074,
|
| 121331 |
+
"grad_norm": 0.20894837379455566,
|
| 121332 |
+
"learning_rate": 2.2764296263547148e-08,
|
| 121333 |
+
"loss": 0.5946,
|
| 121334 |
+
"step": 17332
|
| 121335 |
+
},
|
| 121336 |
+
{
|
| 121337 |
+
"epoch": 19.741880341880343,
|
| 121338 |
+
"grad_norm": 0.2276475578546524,
|
| 121339 |
+
"learning_rate": 2.256594539223611e-08,
|
| 121340 |
+
"loss": 0.7004,
|
| 121341 |
+
"step": 17333
|
| 121342 |
+
},
|
| 121343 |
+
{
|
| 121344 |
+
"epoch": 19.74301994301994,
|
| 121345 |
+
"grad_norm": 0.17170199751853943,
|
| 121346 |
+
"learning_rate": 2.2368462055899487e-08,
|
| 121347 |
+
"loss": 0.687,
|
| 121348 |
+
"step": 17334
|
| 121349 |
+
},
|
| 121350 |
+
{
|
| 121351 |
+
"epoch": 19.744159544159544,
|
| 121352 |
+
"grad_norm": 0.18173982203006744,
|
| 121353 |
+
"learning_rate": 2.2171846261392904e-08,
|
| 121354 |
+
"loss": 0.8004,
|
| 121355 |
+
"step": 17335
|
| 121356 |
+
},
|
| 121357 |
+
{
|
| 121358 |
+
"epoch": 19.745299145299146,
|
| 121359 |
+
"grad_norm": 0.19223652780056,
|
| 121360 |
+
"learning_rate": 2.1976098015547008e-08,
|
| 121361 |
+
"loss": 0.7668,
|
| 121362 |
+
"step": 17336
|
| 121363 |
+
},
|
| 121364 |
+
{
|
| 121365 |
+
"epoch": 19.746438746438745,
|
| 121366 |
+
"grad_norm": 0.2115246057510376,
|
| 121367 |
+
"learning_rate": 2.1781217325161917e-08,
|
| 121368 |
+
"loss": 0.6602,
|
| 121369 |
+
"step": 17337
|
| 121370 |
+
},
|
| 121371 |
+
{
|
| 121372 |
+
"epoch": 19.747578347578347,
|
| 121373 |
+
"grad_norm": 0.1955891102552414,
|
| 121374 |
+
"learning_rate": 2.1587204197007216e-08,
|
| 121375 |
+
"loss": 0.8293,
|
| 121376 |
+
"step": 17338
|
| 121377 |
+
},
|
| 121378 |
+
{
|
| 121379 |
+
"epoch": 19.74871794871795,
|
| 121380 |
+
"grad_norm": 0.15871645510196686,
|
| 121381 |
+
"learning_rate": 2.1394058637816406e-08,
|
| 121382 |
+
"loss": 1.0231,
|
| 121383 |
+
"step": 17339
|
| 121384 |
+
},
|
| 121385 |
+
{
|
| 121386 |
+
"epoch": 19.74985754985755,
|
| 121387 |
+
"grad_norm": 0.18715499341487885,
|
| 121388 |
+
"learning_rate": 2.120178065430356e-08,
|
| 121389 |
+
"loss": 0.7425,
|
| 121390 |
+
"step": 17340
|
| 121391 |
+
},
|
| 121392 |
+
{
|
| 121393 |
+
"epoch": 19.75099715099715,
|
| 121394 |
+
"grad_norm": 0.15829820930957794,
|
| 121395 |
+
"learning_rate": 2.1010370253143896e-08,
|
| 121396 |
+
"loss": 0.6157,
|
| 121397 |
+
"step": 17341
|
| 121398 |
+
},
|
| 121399 |
+
{
|
| 121400 |
+
"epoch": 19.752136752136753,
|
| 121401 |
+
"grad_norm": 0.20122310519218445,
|
| 121402 |
+
"learning_rate": 2.0819827440987648e-08,
|
| 121403 |
+
"loss": 0.5028,
|
| 121404 |
+
"step": 17342
|
| 121405 |
+
},
|
| 121406 |
+
{
|
| 121407 |
+
"epoch": 19.753276353276352,
|
| 121408 |
+
"grad_norm": 0.1904160976409912,
|
| 121409 |
+
"learning_rate": 2.063015222445175e-08,
|
| 121410 |
+
"loss": 0.5394,
|
| 121411 |
+
"step": 17343
|
| 121412 |
+
},
|
| 121413 |
+
{
|
| 121414 |
+
"epoch": 19.754415954415954,
|
| 121415 |
+
"grad_norm": 0.17193228006362915,
|
| 121416 |
+
"learning_rate": 2.044134461012259e-08,
|
| 121417 |
+
"loss": 0.6024,
|
| 121418 |
+
"step": 17344
|
| 121419 |
+
},
|
| 121420 |
+
{
|
| 121421 |
+
"epoch": 19.755555555555556,
|
| 121422 |
+
"grad_norm": 0.14988501369953156,
|
| 121423 |
+
"learning_rate": 2.02534046045616e-08,
|
| 121424 |
+
"loss": 0.7363,
|
| 121425 |
+
"step": 17345
|
| 121426 |
+
},
|
| 121427 |
+
{
|
| 121428 |
+
"epoch": 19.756695156695155,
|
| 121429 |
+
"grad_norm": 0.21250396966934204,
|
| 121430 |
+
"learning_rate": 2.0066332214294104e-08,
|
| 121431 |
+
"loss": 0.5097,
|
| 121432 |
+
"step": 17346
|
| 121433 |
+
},
|
| 121434 |
+
{
|
| 121435 |
+
"epoch": 19.757834757834758,
|
| 121436 |
+
"grad_norm": 0.17534324526786804,
|
| 121437 |
+
"learning_rate": 1.9880127445817687e-08,
|
| 121438 |
+
"loss": 0.4889,
|
| 121439 |
+
"step": 17347
|
| 121440 |
+
},
|
| 121441 |
+
{
|
| 121442 |
+
"epoch": 19.75897435897436,
|
| 121443 |
+
"grad_norm": 0.18992437422275543,
|
| 121444 |
+
"learning_rate": 1.9694790305599397e-08,
|
| 121445 |
+
"loss": 0.759,
|
| 121446 |
+
"step": 17348
|
| 121447 |
+
},
|
| 121448 |
+
{
|
| 121449 |
+
"epoch": 19.76011396011396,
|
| 121450 |
+
"grad_norm": 0.16042746603488922,
|
| 121451 |
+
"learning_rate": 1.9510320800075754e-08,
|
| 121452 |
+
"loss": 0.7753,
|
| 121453 |
+
"step": 17349
|
| 121454 |
+
},
|
| 121455 |
+
{
|
| 121456 |
+
"epoch": 19.76125356125356,
|
| 121457 |
+
"grad_norm": 0.16928979754447937,
|
| 121458 |
+
"learning_rate": 1.9326718935658293e-08,
|
| 121459 |
+
"loss": 0.63,
|
| 121460 |
+
"step": 17350
|
| 121461 |
+
},
|
| 121462 |
+
{
|
| 121463 |
+
"epoch": 19.762393162393163,
|
| 121464 |
+
"grad_norm": 0.1815546452999115,
|
| 121465 |
+
"learning_rate": 1.91439847187197e-08,
|
| 121466 |
+
"loss": 0.655,
|
| 121467 |
+
"step": 17351
|
| 121468 |
+
},
|
| 121469 |
+
{
|
| 121470 |
+
"epoch": 19.763532763532762,
|
| 121471 |
+
"grad_norm": 0.17108528316020966,
|
| 121472 |
+
"learning_rate": 1.8962118155607668e-08,
|
| 121473 |
+
"loss": 0.7128,
|
| 121474 |
+
"step": 17352
|
| 121475 |
+
},
|
| 121476 |
+
{
|
| 121477 |
+
"epoch": 19.764672364672364,
|
| 121478 |
+
"grad_norm": 0.15614262223243713,
|
| 121479 |
+
"learning_rate": 1.8781119252639368e-08,
|
| 121480 |
+
"loss": 1.002,
|
| 121481 |
+
"step": 17353
|
| 121482 |
+
},
|
| 121483 |
+
{
|
| 121484 |
+
"epoch": 19.765811965811967,
|
| 121485 |
+
"grad_norm": 0.20092107355594635,
|
| 121486 |
+
"learning_rate": 1.860098801610144e-08,
|
| 121487 |
+
"loss": 0.6723,
|
| 121488 |
+
"step": 17354
|
| 121489 |
+
},
|
| 121490 |
+
{
|
| 121491 |
+
"epoch": 19.766951566951565,
|
| 121492 |
+
"grad_norm": 0.2087731659412384,
|
| 121493 |
+
"learning_rate": 1.8421724452252764e-08,
|
| 121494 |
+
"loss": 0.5298,
|
| 121495 |
+
"step": 17355
|
| 121496 |
+
},
|
| 121497 |
+
{
|
| 121498 |
+
"epoch": 19.768091168091168,
|
| 121499 |
+
"grad_norm": 0.18618348240852356,
|
| 121500 |
+
"learning_rate": 1.8243328567313368e-08,
|
| 121501 |
+
"loss": 0.7854,
|
| 121502 |
+
"step": 17356
|
| 121503 |
+
},
|
| 121504 |
+
{
|
| 121505 |
+
"epoch": 19.76923076923077,
|
| 121506 |
+
"grad_norm": 0.1749459058046341,
|
| 121507 |
+
"learning_rate": 1.8065800367486617e-08,
|
| 121508 |
+
"loss": 0.8249,
|
| 121509 |
+
"step": 17357
|
| 121510 |
+
},
|
| 121511 |
+
{
|
| 121512 |
+
"epoch": 19.77037037037037,
|
| 121513 |
+
"grad_norm": 0.20197616517543793,
|
| 121514 |
+
"learning_rate": 1.7889139858934257e-08,
|
| 121515 |
+
"loss": 0.6954,
|
| 121516 |
+
"step": 17358
|
| 121517 |
+
},
|
| 121518 |
+
{
|
| 121519 |
+
"epoch": 19.77150997150997,
|
| 121520 |
+
"grad_norm": 0.18469204008579254,
|
| 121521 |
+
"learning_rate": 1.7713347047790263e-08,
|
| 121522 |
+
"loss": 0.8121,
|
| 121523 |
+
"step": 17359
|
| 121524 |
+
},
|
| 121525 |
+
{
|
| 121526 |
+
"epoch": 19.772649572649573,
|
| 121527 |
+
"grad_norm": 0.15979142487049103,
|
| 121528 |
+
"learning_rate": 1.7538421940166417e-08,
|
| 121529 |
+
"loss": 0.6758,
|
| 121530 |
+
"step": 17360
|
| 121531 |
+
},
|
| 121532 |
+
{
|
| 121533 |
+
"epoch": 19.773789173789172,
|
| 121534 |
+
"grad_norm": 0.19149626791477203,
|
| 121535 |
+
"learning_rate": 1.7364364542135635e-08,
|
| 121536 |
+
"loss": 0.6704,
|
| 121537 |
+
"step": 17361
|
| 121538 |
+
},
|
| 121539 |
+
{
|
| 121540 |
+
"epoch": 19.774928774928775,
|
| 121541 |
+
"grad_norm": 0.17909017205238342,
|
| 121542 |
+
"learning_rate": 1.719117485974031e-08,
|
| 121543 |
+
"loss": 0.6038,
|
| 121544 |
+
"step": 17362
|
| 121545 |
+
},
|
| 121546 |
+
{
|
| 121547 |
+
"epoch": 19.776068376068377,
|
| 121548 |
+
"grad_norm": 0.18704593181610107,
|
| 121549 |
+
"learning_rate": 1.7018852899000626e-08,
|
| 121550 |
+
"loss": 0.744,
|
| 121551 |
+
"step": 17363
|
| 121552 |
+
},
|
| 121553 |
+
{
|
| 121554 |
+
"epoch": 19.777207977207976,
|
| 121555 |
+
"grad_norm": 0.18533900380134583,
|
| 121556 |
+
"learning_rate": 1.6847398665897906e-08,
|
| 121557 |
+
"loss": 0.6598,
|
| 121558 |
+
"step": 17364
|
| 121559 |
+
},
|
| 121560 |
+
{
|
| 121561 |
+
"epoch": 19.778347578347578,
|
| 121562 |
+
"grad_norm": 0.1875920295715332,
|
| 121563 |
+
"learning_rate": 1.6676812166391275e-08,
|
| 121564 |
+
"loss": 0.6565,
|
| 121565 |
+
"step": 17365
|
| 121566 |
+
},
|
| 121567 |
+
{
|
| 121568 |
+
"epoch": 19.77948717948718,
|
| 121569 |
+
"grad_norm": 0.172038272023201,
|
| 121570 |
+
"learning_rate": 1.6507093406401e-08,
|
| 121571 |
+
"loss": 0.651,
|
| 121572 |
+
"step": 17366
|
| 121573 |
+
},
|
| 121574 |
+
{
|
| 121575 |
+
"epoch": 19.78062678062678,
|
| 121576 |
+
"grad_norm": 0.23636727035045624,
|
| 121577 |
+
"learning_rate": 1.633824239182513e-08,
|
| 121578 |
+
"loss": 0.6692,
|
| 121579 |
+
"step": 17367
|
| 121580 |
+
},
|
| 121581 |
+
{
|
| 121582 |
+
"epoch": 19.78176638176638,
|
| 121583 |
+
"grad_norm": 0.1715584248304367,
|
| 121584 |
+
"learning_rate": 1.617025912852843e-08,
|
| 121585 |
+
"loss": 0.6428,
|
| 121586 |
+
"step": 17368
|
| 121587 |
+
},
|
| 121588 |
+
{
|
| 121589 |
+
"epoch": 19.782905982905984,
|
| 121590 |
+
"grad_norm": 0.16638945043087006,
|
| 121591 |
+
"learning_rate": 1.6003143622345117e-08,
|
| 121592 |
+
"loss": 0.6822,
|
| 121593 |
+
"step": 17369
|
| 121594 |
+
},
|
| 121595 |
+
{
|
| 121596 |
+
"epoch": 19.784045584045582,
|
| 121597 |
+
"grad_norm": 0.19432315230369568,
|
| 121598 |
+
"learning_rate": 1.583689587907611e-08,
|
| 121599 |
+
"loss": 0.8053,
|
| 121600 |
+
"step": 17370
|
| 121601 |
+
},
|
| 121602 |
+
{
|
| 121603 |
+
"epoch": 19.785185185185185,
|
| 121604 |
+
"grad_norm": 0.17379184067249298,
|
| 121605 |
+
"learning_rate": 1.567151590450011e-08,
|
| 121606 |
+
"loss": 0.7163,
|
| 121607 |
+
"step": 17371
|
| 121608 |
+
},
|
| 121609 |
+
{
|
| 121610 |
+
"epoch": 19.786324786324787,
|
| 121611 |
+
"grad_norm": 0.21618704497814178,
|
| 121612 |
+
"learning_rate": 1.550700370435976e-08,
|
| 121613 |
+
"loss": 0.7115,
|
| 121614 |
+
"step": 17372
|
| 121615 |
+
},
|
| 121616 |
+
{
|
| 121617 |
+
"epoch": 19.787464387464386,
|
| 121618 |
+
"grad_norm": 0.20042377710342407,
|
| 121619 |
+
"learning_rate": 1.534335928436714e-08,
|
| 121620 |
+
"loss": 0.6158,
|
| 121621 |
+
"step": 17373
|
| 121622 |
+
},
|
| 121623 |
+
{
|
| 121624 |
+
"epoch": 19.788603988603988,
|
| 121625 |
+
"grad_norm": 0.19638532400131226,
|
| 121626 |
+
"learning_rate": 1.5180582650209385e-08,
|
| 121627 |
+
"loss": 0.835,
|
| 121628 |
+
"step": 17374
|
| 121629 |
+
},
|
| 121630 |
+
{
|
| 121631 |
+
"epoch": 19.78974358974359,
|
| 121632 |
+
"grad_norm": 0.16307075321674347,
|
| 121633 |
+
"learning_rate": 1.501867380753752e-08,
|
| 121634 |
+
"loss": 0.776,
|
| 121635 |
+
"step": 17375
|
| 121636 |
+
},
|
| 121637 |
+
{
|
| 121638 |
+
"epoch": 19.79088319088319,
|
| 121639 |
+
"grad_norm": 0.21321846544742584,
|
| 121640 |
+
"learning_rate": 1.4857632761977603e-08,
|
| 121641 |
+
"loss": 0.6376,
|
| 121642 |
+
"step": 17376
|
| 121643 |
+
},
|
| 121644 |
+
{
|
| 121645 |
+
"epoch": 19.79202279202279,
|
| 121646 |
+
"grad_norm": 0.16780985891819,
|
| 121647 |
+
"learning_rate": 1.4697459519119605e-08,
|
| 121648 |
+
"loss": 0.7827,
|
| 121649 |
+
"step": 17377
|
| 121650 |
+
},
|
| 121651 |
+
{
|
| 121652 |
+
"epoch": 19.793162393162394,
|
| 121653 |
+
"grad_norm": 0.16664044559001923,
|
| 121654 |
+
"learning_rate": 1.4538154084528522e-08,
|
| 121655 |
+
"loss": 0.7853,
|
| 121656 |
+
"step": 17378
|
| 121657 |
+
},
|
| 121658 |
+
{
|
| 121659 |
+
"epoch": 19.794301994301993,
|
| 121660 |
+
"grad_norm": 0.1965169906616211,
|
| 121661 |
+
"learning_rate": 1.4379716463738813e-08,
|
| 121662 |
+
"loss": 0.5155,
|
| 121663 |
+
"step": 17379
|
| 121664 |
+
},
|
| 121665 |
+
{
|
| 121666 |
+
"epoch": 19.795441595441595,
|
| 121667 |
+
"grad_norm": 0.17581987380981445,
|
| 121668 |
+
"learning_rate": 1.4222146662251635e-08,
|
| 121669 |
+
"loss": 0.7154,
|
| 121670 |
+
"step": 17380
|
| 121671 |
+
},
|
| 121672 |
+
{
|
| 121673 |
+
"epoch": 19.796581196581197,
|
| 121674 |
+
"grad_norm": 0.1875821352005005,
|
| 121675 |
+
"learning_rate": 1.4065444685540385e-08,
|
| 121676 |
+
"loss": 0.9377,
|
| 121677 |
+
"step": 17381
|
| 121678 |
+
},
|
| 121679 |
+
{
|
| 121680 |
+
"epoch": 19.797720797720796,
|
| 121681 |
+
"grad_norm": 0.23596879839897156,
|
| 121682 |
+
"learning_rate": 1.3909610539047934e-08,
|
| 121683 |
+
"loss": 0.519,
|
| 121684 |
+
"step": 17382
|
| 121685 |
+
},
|
| 121686 |
+
{
|
| 121687 |
+
"epoch": 19.7988603988604,
|
| 121688 |
+
"grad_norm": 0.1874542236328125,
|
| 121689 |
+
"learning_rate": 1.3754644228189394e-08,
|
| 121690 |
+
"loss": 0.5031,
|
| 121691 |
+
"step": 17383
|
| 121692 |
+
},
|
| 121693 |
+
{
|
| 121694 |
+
"epoch": 19.8,
|
| 121695 |
+
"grad_norm": 0.186298206448555,
|
| 121696 |
+
"learning_rate": 1.3600545758341022e-08,
|
| 121697 |
+
"loss": 0.7241,
|
| 121698 |
+
"step": 17384
|
| 121699 |
+
},
|
| 121700 |
+
{
|
| 121701 |
+
"epoch": 19.8011396011396,
|
| 121702 |
+
"grad_norm": 0.222769096493721,
|
| 121703 |
+
"learning_rate": 1.344731513485964e-08,
|
| 121704 |
+
"loss": 0.4098,
|
| 121705 |
+
"step": 17385
|
| 121706 |
+
},
|
| 121707 |
+
{
|
| 121708 |
+
"epoch": 19.802279202279202,
|
| 121709 |
+
"grad_norm": 0.18376067280769348,
|
| 121710 |
+
"learning_rate": 1.3294952363065993e-08,
|
| 121711 |
+
"loss": 0.6354,
|
| 121712 |
+
"step": 17386
|
| 121713 |
+
},
|
| 121714 |
+
{
|
| 121715 |
+
"epoch": 19.803418803418804,
|
| 121716 |
+
"grad_norm": 0.1565205603837967,
|
| 121717 |
+
"learning_rate": 1.314345744825307e-08,
|
| 121718 |
+
"loss": 0.7067,
|
| 121719 |
+
"step": 17387
|
| 121720 |
+
},
|
| 121721 |
+
{
|
| 121722 |
+
"epoch": 19.804558404558403,
|
| 121723 |
+
"grad_norm": 0.2034037858247757,
|
| 121724 |
+
"learning_rate": 1.2992830395680555e-08,
|
| 121725 |
+
"loss": 0.4996,
|
| 121726 |
+
"step": 17388
|
| 121727 |
+
},
|
| 121728 |
+
{
|
| 121729 |
+
"epoch": 19.805698005698005,
|
| 121730 |
+
"grad_norm": 0.2041102647781372,
|
| 121731 |
+
"learning_rate": 1.2843071210583146e-08,
|
| 121732 |
+
"loss": 0.5664,
|
| 121733 |
+
"step": 17389
|
| 121734 |
+
},
|
| 121735 |
+
{
|
| 121736 |
+
"epoch": 19.806837606837608,
|
| 121737 |
+
"grad_norm": 0.19491428136825562,
|
| 121738 |
+
"learning_rate": 1.2694179898159464e-08,
|
| 121739 |
+
"loss": 0.7311,
|
| 121740 |
+
"step": 17390
|
| 121741 |
+
},
|
| 121742 |
+
{
|
| 121743 |
+
"epoch": 19.807977207977206,
|
| 121744 |
+
"grad_norm": 0.21402095258235931,
|
| 121745 |
+
"learning_rate": 1.2546156463583147e-08,
|
| 121746 |
+
"loss": 0.7012,
|
| 121747 |
+
"step": 17391
|
| 121748 |
+
},
|
| 121749 |
+
{
|
| 121750 |
+
"epoch": 19.80911680911681,
|
| 121751 |
+
"grad_norm": 0.17485588788986206,
|
| 121752 |
+
"learning_rate": 1.239900091199453e-08,
|
| 121753 |
+
"loss": 0.7125,
|
| 121754 |
+
"step": 17392
|
| 121755 |
+
},
|
| 121756 |
+
{
|
| 121757 |
+
"epoch": 19.81025641025641,
|
| 121758 |
+
"grad_norm": 0.23262129724025726,
|
| 121759 |
+
"learning_rate": 1.2252713248506187e-08,
|
| 121760 |
+
"loss": 0.6616,
|
| 121761 |
+
"step": 17393
|
| 121762 |
+
},
|
| 121763 |
+
{
|
| 121764 |
+
"epoch": 19.81139601139601,
|
| 121765 |
+
"grad_norm": 0.19495739042758942,
|
| 121766 |
+
"learning_rate": 1.210729347819739e-08,
|
| 121767 |
+
"loss": 0.6964,
|
| 121768 |
+
"step": 17394
|
| 121769 |
+
},
|
| 121770 |
+
{
|
| 121771 |
+
"epoch": 19.812535612535612,
|
| 121772 |
+
"grad_norm": 0.17964985966682434,
|
| 121773 |
+
"learning_rate": 1.1962741606116878e-08,
|
| 121774 |
+
"loss": 0.6539,
|
| 121775 |
+
"step": 17395
|
| 121776 |
+
},
|
| 121777 |
+
{
|
| 121778 |
+
"epoch": 19.813675213675214,
|
| 121779 |
+
"grad_norm": 0.18871615827083588,
|
| 121780 |
+
"learning_rate": 1.181905763728841e-08,
|
| 121781 |
+
"loss": 0.5455,
|
| 121782 |
+
"step": 17396
|
| 121783 |
+
},
|
| 121784 |
+
{
|
| 121785 |
+
"epoch": 19.814814814814813,
|
| 121786 |
+
"grad_norm": 0.21508648991584778,
|
| 121787 |
+
"learning_rate": 1.167624157670244e-08,
|
| 121788 |
+
"loss": 0.75,
|
| 121789 |
+
"step": 17397
|
| 121790 |
+
},
|
| 121791 |
+
{
|
| 121792 |
+
"epoch": 19.815954415954415,
|
| 121793 |
+
"grad_norm": 0.21118800342082977,
|
| 121794 |
+
"learning_rate": 1.1534293429318888e-08,
|
| 121795 |
+
"loss": 0.6959,
|
| 121796 |
+
"step": 17398
|
| 121797 |
+
},
|
| 121798 |
+
{
|
| 121799 |
+
"epoch": 19.817094017094018,
|
| 121800 |
+
"grad_norm": 0.18347077071666718,
|
| 121801 |
+
"learning_rate": 1.1393213200067144e-08,
|
| 121802 |
+
"loss": 0.8279,
|
| 121803 |
+
"step": 17399
|
| 121804 |
+
},
|
| 121805 |
+
{
|
| 121806 |
+
"epoch": 19.81823361823362,
|
| 121807 |
+
"grad_norm": 0.2921779751777649,
|
| 121808 |
+
"learning_rate": 1.1253000893848842e-08,
|
| 121809 |
+
"loss": 0.5825,
|
| 121810 |
+
"step": 17400
|
| 121811 |
}
|
| 121812 |
],
|
| 121813 |
"logging_steps": 1,
|
|
|
|
| 121827 |
"attributes": {}
|
| 121828 |
}
|
| 121829 |
},
|
| 121830 |
+
"total_flos": 9.728790249449742e+19,
|
| 121831 |
"train_batch_size": 8,
|
| 121832 |
"trial_name": null,
|
| 121833 |
"trial_params": null
|