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 9300, 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:a9846e8f707f1143802295da735fac2d90e947deebdcb42697ddebf674e596b5
|
| 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 sha256:552276b86d25e088e6ebe6c0e5862baa048647b20b374d81494d7367c4729ab8
|
| 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 sha256:127730045697a7826e96de048987068133dcfb1fb976ec24e799b423857e870d
|
| 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": 10.
|
| 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,
|
|
@@ -63008,6 +63008,2106 @@
|
|
| 63008 |
"learning_rate": 2.5617278761792206e-05,
|
| 63009 |
"loss": 0.5229,
|
| 63010 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63011 |
}
|
| 63012 |
],
|
| 63013 |
"logging_steps": 1,
|
|
@@ -63027,7 +65127,7 @@
|
|
| 63027 |
"attributes": {}
|
| 63028 |
}
|
| 63029 |
},
|
| 63030 |
-
"total_flos": 5.
|
| 63031 |
"train_batch_size": 8,
|
| 63032 |
"trial_name": null,
|
| 63033 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.592592592592592,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 63008 |
"learning_rate": 2.5617278761792206e-05,
|
| 63009 |
"loss": 0.5229,
|
| 63010 |
"step": 9000
|
| 63011 |
+
},
|
| 63012 |
+
{
|
| 63013 |
+
"epoch": 10.251851851851852,
|
| 63014 |
+
"grad_norm": 0.24556277692317963,
|
| 63015 |
+
"learning_rate": 2.5612620990425624e-05,
|
| 63016 |
+
"loss": 0.6393,
|
| 63017 |
+
"step": 9001
|
| 63018 |
+
},
|
| 63019 |
+
{
|
| 63020 |
+
"epoch": 10.252991452991452,
|
| 63021 |
+
"grad_norm": 0.21111436188220978,
|
| 63022 |
+
"learning_rate": 2.5607963197781022e-05,
|
| 63023 |
+
"loss": 0.5632,
|
| 63024 |
+
"step": 9002
|
| 63025 |
+
},
|
| 63026 |
+
{
|
| 63027 |
+
"epoch": 10.254131054131054,
|
| 63028 |
+
"grad_norm": 0.21761007606983185,
|
| 63029 |
+
"learning_rate": 2.560330538402018e-05,
|
| 63030 |
+
"loss": 0.6946,
|
| 63031 |
+
"step": 9003
|
| 63032 |
+
},
|
| 63033 |
+
{
|
| 63034 |
+
"epoch": 10.255270655270655,
|
| 63035 |
+
"grad_norm": 0.19828318059444427,
|
| 63036 |
+
"learning_rate": 2.55986475493049e-05,
|
| 63037 |
+
"loss": 0.8467,
|
| 63038 |
+
"step": 9004
|
| 63039 |
+
},
|
| 63040 |
+
{
|
| 63041 |
+
"epoch": 10.256410256410255,
|
| 63042 |
+
"grad_norm": 0.25546392798423767,
|
| 63043 |
+
"learning_rate": 2.5593989693796927e-05,
|
| 63044 |
+
"loss": 0.7468,
|
| 63045 |
+
"step": 9005
|
| 63046 |
+
},
|
| 63047 |
+
{
|
| 63048 |
+
"epoch": 10.257549857549858,
|
| 63049 |
+
"grad_norm": 0.17720606923103333,
|
| 63050 |
+
"learning_rate": 2.5589331817658076e-05,
|
| 63051 |
+
"loss": 0.8694,
|
| 63052 |
+
"step": 9006
|
| 63053 |
+
},
|
| 63054 |
+
{
|
| 63055 |
+
"epoch": 10.258689458689458,
|
| 63056 |
+
"grad_norm": 0.2313048243522644,
|
| 63057 |
+
"learning_rate": 2.5584673921050097e-05,
|
| 63058 |
+
"loss": 0.7185,
|
| 63059 |
+
"step": 9007
|
| 63060 |
+
},
|
| 63061 |
+
{
|
| 63062 |
+
"epoch": 10.25982905982906,
|
| 63063 |
+
"grad_norm": 0.251424640417099,
|
| 63064 |
+
"learning_rate": 2.5580016004134787e-05,
|
| 63065 |
+
"loss": 0.6053,
|
| 63066 |
+
"step": 9008
|
| 63067 |
+
},
|
| 63068 |
+
{
|
| 63069 |
+
"epoch": 10.260968660968661,
|
| 63070 |
+
"grad_norm": 0.22431643307209015,
|
| 63071 |
+
"learning_rate": 2.5575358067073924e-05,
|
| 63072 |
+
"loss": 0.7118,
|
| 63073 |
+
"step": 9009
|
| 63074 |
+
},
|
| 63075 |
+
{
|
| 63076 |
+
"epoch": 10.262108262108262,
|
| 63077 |
+
"grad_norm": 0.19620449841022491,
|
| 63078 |
+
"learning_rate": 2.5570700110029294e-05,
|
| 63079 |
+
"loss": 0.6793,
|
| 63080 |
+
"step": 9010
|
| 63081 |
+
},
|
| 63082 |
+
{
|
| 63083 |
+
"epoch": 10.263247863247864,
|
| 63084 |
+
"grad_norm": 0.2035008817911148,
|
| 63085 |
+
"learning_rate": 2.5566042133162684e-05,
|
| 63086 |
+
"loss": 0.7385,
|
| 63087 |
+
"step": 9011
|
| 63088 |
+
},
|
| 63089 |
+
{
|
| 63090 |
+
"epoch": 10.264387464387465,
|
| 63091 |
+
"grad_norm": 0.23007768392562866,
|
| 63092 |
+
"learning_rate": 2.5561384136635873e-05,
|
| 63093 |
+
"loss": 0.6546,
|
| 63094 |
+
"step": 9012
|
| 63095 |
+
},
|
| 63096 |
+
{
|
| 63097 |
+
"epoch": 10.265527065527065,
|
| 63098 |
+
"grad_norm": 0.16230762004852295,
|
| 63099 |
+
"learning_rate": 2.5556726120610648e-05,
|
| 63100 |
+
"loss": 0.8617,
|
| 63101 |
+
"step": 9013
|
| 63102 |
+
},
|
| 63103 |
+
{
|
| 63104 |
+
"epoch": 10.266666666666667,
|
| 63105 |
+
"grad_norm": 0.1794481724500656,
|
| 63106 |
+
"learning_rate": 2.555206808524879e-05,
|
| 63107 |
+
"loss": 0.8314,
|
| 63108 |
+
"step": 9014
|
| 63109 |
+
},
|
| 63110 |
+
{
|
| 63111 |
+
"epoch": 10.267806267806268,
|
| 63112 |
+
"grad_norm": 0.20571161806583405,
|
| 63113 |
+
"learning_rate": 2.554741003071209e-05,
|
| 63114 |
+
"loss": 0.7129,
|
| 63115 |
+
"step": 9015
|
| 63116 |
+
},
|
| 63117 |
+
{
|
| 63118 |
+
"epoch": 10.268945868945869,
|
| 63119 |
+
"grad_norm": 0.31665948033332825,
|
| 63120 |
+
"learning_rate": 2.5542751957162336e-05,
|
| 63121 |
+
"loss": 0.5694,
|
| 63122 |
+
"step": 9016
|
| 63123 |
+
},
|
| 63124 |
+
{
|
| 63125 |
+
"epoch": 10.270085470085471,
|
| 63126 |
+
"grad_norm": 0.19845467805862427,
|
| 63127 |
+
"learning_rate": 2.553809386476131e-05,
|
| 63128 |
+
"loss": 0.7631,
|
| 63129 |
+
"step": 9017
|
| 63130 |
+
},
|
| 63131 |
+
{
|
| 63132 |
+
"epoch": 10.271225071225071,
|
| 63133 |
+
"grad_norm": 0.19833163917064667,
|
| 63134 |
+
"learning_rate": 2.5533435753670815e-05,
|
| 63135 |
+
"loss": 0.6717,
|
| 63136 |
+
"step": 9018
|
| 63137 |
+
},
|
| 63138 |
+
{
|
| 63139 |
+
"epoch": 10.272364672364672,
|
| 63140 |
+
"grad_norm": 0.27582642436027527,
|
| 63141 |
+
"learning_rate": 2.5528777624052617e-05,
|
| 63142 |
+
"loss": 0.4747,
|
| 63143 |
+
"step": 9019
|
| 63144 |
+
},
|
| 63145 |
+
{
|
| 63146 |
+
"epoch": 10.273504273504274,
|
| 63147 |
+
"grad_norm": 0.1753959208726883,
|
| 63148 |
+
"learning_rate": 2.552411947606852e-05,
|
| 63149 |
+
"loss": 0.7539,
|
| 63150 |
+
"step": 9020
|
| 63151 |
+
},
|
| 63152 |
+
{
|
| 63153 |
+
"epoch": 10.274643874643875,
|
| 63154 |
+
"grad_norm": 0.20944949984550476,
|
| 63155 |
+
"learning_rate": 2.551946130988032e-05,
|
| 63156 |
+
"loss": 0.5579,
|
| 63157 |
+
"step": 9021
|
| 63158 |
+
},
|
| 63159 |
+
{
|
| 63160 |
+
"epoch": 10.275783475783475,
|
| 63161 |
+
"grad_norm": 0.22696365416049957,
|
| 63162 |
+
"learning_rate": 2.5514803125649796e-05,
|
| 63163 |
+
"loss": 0.6115,
|
| 63164 |
+
"step": 9022
|
| 63165 |
+
},
|
| 63166 |
+
{
|
| 63167 |
+
"epoch": 10.276923076923078,
|
| 63168 |
+
"grad_norm": 0.2090187817811966,
|
| 63169 |
+
"learning_rate": 2.5510144923538744e-05,
|
| 63170 |
+
"loss": 0.7988,
|
| 63171 |
+
"step": 9023
|
| 63172 |
+
},
|
| 63173 |
+
{
|
| 63174 |
+
"epoch": 10.278062678062678,
|
| 63175 |
+
"grad_norm": 0.2817879915237427,
|
| 63176 |
+
"learning_rate": 2.5505486703708952e-05,
|
| 63177 |
+
"loss": 0.6709,
|
| 63178 |
+
"step": 9024
|
| 63179 |
+
},
|
| 63180 |
+
{
|
| 63181 |
+
"epoch": 10.279202279202279,
|
| 63182 |
+
"grad_norm": 0.1797921508550644,
|
| 63183 |
+
"learning_rate": 2.550082846632222e-05,
|
| 63184 |
+
"loss": 0.8487,
|
| 63185 |
+
"step": 9025
|
| 63186 |
+
},
|
| 63187 |
+
{
|
| 63188 |
+
"epoch": 10.280341880341881,
|
| 63189 |
+
"grad_norm": 0.24475227296352386,
|
| 63190 |
+
"learning_rate": 2.5496170211540332e-05,
|
| 63191 |
+
"loss": 0.6877,
|
| 63192 |
+
"step": 9026
|
| 63193 |
+
},
|
| 63194 |
+
{
|
| 63195 |
+
"epoch": 10.281481481481482,
|
| 63196 |
+
"grad_norm": 0.2791805565357208,
|
| 63197 |
+
"learning_rate": 2.5491511939525098e-05,
|
| 63198 |
+
"loss": 0.42,
|
| 63199 |
+
"step": 9027
|
| 63200 |
+
},
|
| 63201 |
+
{
|
| 63202 |
+
"epoch": 10.282621082621082,
|
| 63203 |
+
"grad_norm": 0.25618109107017517,
|
| 63204 |
+
"learning_rate": 2.5486853650438297e-05,
|
| 63205 |
+
"loss": 0.686,
|
| 63206 |
+
"step": 9028
|
| 63207 |
+
},
|
| 63208 |
+
{
|
| 63209 |
+
"epoch": 10.283760683760685,
|
| 63210 |
+
"grad_norm": 0.20590481162071228,
|
| 63211 |
+
"learning_rate": 2.5482195344441734e-05,
|
| 63212 |
+
"loss": 0.7595,
|
| 63213 |
+
"step": 9029
|
| 63214 |
+
},
|
| 63215 |
+
{
|
| 63216 |
+
"epoch": 10.284900284900285,
|
| 63217 |
+
"grad_norm": 0.20788438618183136,
|
| 63218 |
+
"learning_rate": 2.5477537021697202e-05,
|
| 63219 |
+
"loss": 0.7769,
|
| 63220 |
+
"step": 9030
|
| 63221 |
+
},
|
| 63222 |
+
{
|
| 63223 |
+
"epoch": 10.286039886039886,
|
| 63224 |
+
"grad_norm": 0.1922910213470459,
|
| 63225 |
+
"learning_rate": 2.5472878682366484e-05,
|
| 63226 |
+
"loss": 0.6286,
|
| 63227 |
+
"step": 9031
|
| 63228 |
+
},
|
| 63229 |
+
{
|
| 63230 |
+
"epoch": 10.287179487179488,
|
| 63231 |
+
"grad_norm": 0.21666008234024048,
|
| 63232 |
+
"learning_rate": 2.5468220326611404e-05,
|
| 63233 |
+
"loss": 0.7785,
|
| 63234 |
+
"step": 9032
|
| 63235 |
+
},
|
| 63236 |
+
{
|
| 63237 |
+
"epoch": 10.288319088319088,
|
| 63238 |
+
"grad_norm": 0.24231019616127014,
|
| 63239 |
+
"learning_rate": 2.5463561954593736e-05,
|
| 63240 |
+
"loss": 0.5637,
|
| 63241 |
+
"step": 9033
|
| 63242 |
+
},
|
| 63243 |
+
{
|
| 63244 |
+
"epoch": 10.289458689458689,
|
| 63245 |
+
"grad_norm": 0.20492561161518097,
|
| 63246 |
+
"learning_rate": 2.545890356647529e-05,
|
| 63247 |
+
"loss": 0.6971,
|
| 63248 |
+
"step": 9034
|
| 63249 |
+
},
|
| 63250 |
+
{
|
| 63251 |
+
"epoch": 10.290598290598291,
|
| 63252 |
+
"grad_norm": 0.20477353036403656,
|
| 63253 |
+
"learning_rate": 2.5454245162417857e-05,
|
| 63254 |
+
"loss": 0.7399,
|
| 63255 |
+
"step": 9035
|
| 63256 |
+
},
|
| 63257 |
+
{
|
| 63258 |
+
"epoch": 10.291737891737892,
|
| 63259 |
+
"grad_norm": 0.2130691260099411,
|
| 63260 |
+
"learning_rate": 2.5449586742583244e-05,
|
| 63261 |
+
"loss": 0.5531,
|
| 63262 |
+
"step": 9036
|
| 63263 |
+
},
|
| 63264 |
+
{
|
| 63265 |
+
"epoch": 10.292877492877492,
|
| 63266 |
+
"grad_norm": 0.20497938990592957,
|
| 63267 |
+
"learning_rate": 2.5444928307133243e-05,
|
| 63268 |
+
"loss": 0.8259,
|
| 63269 |
+
"step": 9037
|
| 63270 |
+
},
|
| 63271 |
+
{
|
| 63272 |
+
"epoch": 10.294017094017095,
|
| 63273 |
+
"grad_norm": 0.2435048669576645,
|
| 63274 |
+
"learning_rate": 2.5440269856229658e-05,
|
| 63275 |
+
"loss": 0.6226,
|
| 63276 |
+
"step": 9038
|
| 63277 |
+
},
|
| 63278 |
+
{
|
| 63279 |
+
"epoch": 10.295156695156695,
|
| 63280 |
+
"grad_norm": 0.18705344200134277,
|
| 63281 |
+
"learning_rate": 2.54356113900343e-05,
|
| 63282 |
+
"loss": 0.478,
|
| 63283 |
+
"step": 9039
|
| 63284 |
+
},
|
| 63285 |
+
{
|
| 63286 |
+
"epoch": 10.296296296296296,
|
| 63287 |
+
"grad_norm": 0.19532230496406555,
|
| 63288 |
+
"learning_rate": 2.543095290870895e-05,
|
| 63289 |
+
"loss": 0.8921,
|
| 63290 |
+
"step": 9040
|
| 63291 |
+
},
|
| 63292 |
+
{
|
| 63293 |
+
"epoch": 10.297435897435898,
|
| 63294 |
+
"grad_norm": 0.17932532727718353,
|
| 63295 |
+
"learning_rate": 2.5426294412415424e-05,
|
| 63296 |
+
"loss": 0.7321,
|
| 63297 |
+
"step": 9041
|
| 63298 |
+
},
|
| 63299 |
+
{
|
| 63300 |
+
"epoch": 10.298575498575499,
|
| 63301 |
+
"grad_norm": 0.2342417687177658,
|
| 63302 |
+
"learning_rate": 2.5421635901315514e-05,
|
| 63303 |
+
"loss": 0.6227,
|
| 63304 |
+
"step": 9042
|
| 63305 |
+
},
|
| 63306 |
+
{
|
| 63307 |
+
"epoch": 10.2997150997151,
|
| 63308 |
+
"grad_norm": 0.23890571296215057,
|
| 63309 |
+
"learning_rate": 2.541697737557104e-05,
|
| 63310 |
+
"loss": 0.5157,
|
| 63311 |
+
"step": 9043
|
| 63312 |
+
},
|
| 63313 |
+
{
|
| 63314 |
+
"epoch": 10.300854700854702,
|
| 63315 |
+
"grad_norm": 0.20371253788471222,
|
| 63316 |
+
"learning_rate": 2.5412318835343794e-05,
|
| 63317 |
+
"loss": 0.7216,
|
| 63318 |
+
"step": 9044
|
| 63319 |
+
},
|
| 63320 |
+
{
|
| 63321 |
+
"epoch": 10.301994301994302,
|
| 63322 |
+
"grad_norm": 0.22724924981594086,
|
| 63323 |
+
"learning_rate": 2.5407660280795577e-05,
|
| 63324 |
+
"loss": 0.7191,
|
| 63325 |
+
"step": 9045
|
| 63326 |
+
},
|
| 63327 |
+
{
|
| 63328 |
+
"epoch": 10.303133903133903,
|
| 63329 |
+
"grad_norm": 0.20855417847633362,
|
| 63330 |
+
"learning_rate": 2.5403001712088198e-05,
|
| 63331 |
+
"loss": 0.6524,
|
| 63332 |
+
"step": 9046
|
| 63333 |
+
},
|
| 63334 |
+
{
|
| 63335 |
+
"epoch": 10.304273504273505,
|
| 63336 |
+
"grad_norm": 0.2518128752708435,
|
| 63337 |
+
"learning_rate": 2.539834312938346e-05,
|
| 63338 |
+
"loss": 0.42,
|
| 63339 |
+
"step": 9047
|
| 63340 |
+
},
|
| 63341 |
+
{
|
| 63342 |
+
"epoch": 10.305413105413106,
|
| 63343 |
+
"grad_norm": 0.2135232836008072,
|
| 63344 |
+
"learning_rate": 2.5393684532843172e-05,
|
| 63345 |
+
"loss": 0.4781,
|
| 63346 |
+
"step": 9048
|
| 63347 |
+
},
|
| 63348 |
+
{
|
| 63349 |
+
"epoch": 10.306552706552706,
|
| 63350 |
+
"grad_norm": 0.19639183580875397,
|
| 63351 |
+
"learning_rate": 2.538902592262914e-05,
|
| 63352 |
+
"loss": 0.7857,
|
| 63353 |
+
"step": 9049
|
| 63354 |
+
},
|
| 63355 |
+
{
|
| 63356 |
+
"epoch": 10.307692307692308,
|
| 63357 |
+
"grad_norm": 0.2120703160762787,
|
| 63358 |
+
"learning_rate": 2.5384367298903165e-05,
|
| 63359 |
+
"loss": 0.7064,
|
| 63360 |
+
"step": 9050
|
| 63361 |
+
},
|
| 63362 |
+
{
|
| 63363 |
+
"epoch": 10.308831908831909,
|
| 63364 |
+
"grad_norm": 0.17633357644081116,
|
| 63365 |
+
"learning_rate": 2.537970866182706e-05,
|
| 63366 |
+
"loss": 0.6981,
|
| 63367 |
+
"step": 9051
|
| 63368 |
+
},
|
| 63369 |
+
{
|
| 63370 |
+
"epoch": 10.30997150997151,
|
| 63371 |
+
"grad_norm": 0.24732357263565063,
|
| 63372 |
+
"learning_rate": 2.5375050011562623e-05,
|
| 63373 |
+
"loss": 0.6496,
|
| 63374 |
+
"step": 9052
|
| 63375 |
+
},
|
| 63376 |
+
{
|
| 63377 |
+
"epoch": 10.311111111111112,
|
| 63378 |
+
"grad_norm": 0.21399758756160736,
|
| 63379 |
+
"learning_rate": 2.5370391348271666e-05,
|
| 63380 |
+
"loss": 0.6885,
|
| 63381 |
+
"step": 9053
|
| 63382 |
+
},
|
| 63383 |
+
{
|
| 63384 |
+
"epoch": 10.312250712250712,
|
| 63385 |
+
"grad_norm": 0.20664972066879272,
|
| 63386 |
+
"learning_rate": 2.5365732672116006e-05,
|
| 63387 |
+
"loss": 0.7207,
|
| 63388 |
+
"step": 9054
|
| 63389 |
+
},
|
| 63390 |
+
{
|
| 63391 |
+
"epoch": 10.313390313390313,
|
| 63392 |
+
"grad_norm": 0.2515653073787689,
|
| 63393 |
+
"learning_rate": 2.5361073983257444e-05,
|
| 63394 |
+
"loss": 0.542,
|
| 63395 |
+
"step": 9055
|
| 63396 |
+
},
|
| 63397 |
+
{
|
| 63398 |
+
"epoch": 10.314529914529915,
|
| 63399 |
+
"grad_norm": 0.21457159519195557,
|
| 63400 |
+
"learning_rate": 2.535641528185778e-05,
|
| 63401 |
+
"loss": 0.5081,
|
| 63402 |
+
"step": 9056
|
| 63403 |
+
},
|
| 63404 |
+
{
|
| 63405 |
+
"epoch": 10.315669515669516,
|
| 63406 |
+
"grad_norm": 0.23283055424690247,
|
| 63407 |
+
"learning_rate": 2.5351756568078848e-05,
|
| 63408 |
+
"loss": 0.7544,
|
| 63409 |
+
"step": 9057
|
| 63410 |
+
},
|
| 63411 |
+
{
|
| 63412 |
+
"epoch": 10.316809116809116,
|
| 63413 |
+
"grad_norm": 0.21763315796852112,
|
| 63414 |
+
"learning_rate": 2.5347097842082428e-05,
|
| 63415 |
+
"loss": 0.6422,
|
| 63416 |
+
"step": 9058
|
| 63417 |
+
},
|
| 63418 |
+
{
|
| 63419 |
+
"epoch": 10.317948717948719,
|
| 63420 |
+
"grad_norm": 0.199775829911232,
|
| 63421 |
+
"learning_rate": 2.5342439104030357e-05,
|
| 63422 |
+
"loss": 0.6528,
|
| 63423 |
+
"step": 9059
|
| 63424 |
+
},
|
| 63425 |
+
{
|
| 63426 |
+
"epoch": 10.31908831908832,
|
| 63427 |
+
"grad_norm": 0.19493013620376587,
|
| 63428 |
+
"learning_rate": 2.533778035408443e-05,
|
| 63429 |
+
"loss": 0.7672,
|
| 63430 |
+
"step": 9060
|
| 63431 |
+
},
|
| 63432 |
+
{
|
| 63433 |
+
"epoch": 10.32022792022792,
|
| 63434 |
+
"grad_norm": 0.1942964792251587,
|
| 63435 |
+
"learning_rate": 2.533312159240647e-05,
|
| 63436 |
+
"loss": 0.6985,
|
| 63437 |
+
"step": 9061
|
| 63438 |
+
},
|
| 63439 |
+
{
|
| 63440 |
+
"epoch": 10.321367521367522,
|
| 63441 |
+
"grad_norm": 0.2270016074180603,
|
| 63442 |
+
"learning_rate": 2.5328462819158268e-05,
|
| 63443 |
+
"loss": 0.6211,
|
| 63444 |
+
"step": 9062
|
| 63445 |
+
},
|
| 63446 |
+
{
|
| 63447 |
+
"epoch": 10.322507122507123,
|
| 63448 |
+
"grad_norm": 0.22101987898349762,
|
| 63449 |
+
"learning_rate": 2.532380403450166e-05,
|
| 63450 |
+
"loss": 0.7484,
|
| 63451 |
+
"step": 9063
|
| 63452 |
+
},
|
| 63453 |
+
{
|
| 63454 |
+
"epoch": 10.323646723646723,
|
| 63455 |
+
"grad_norm": 0.19234544038772583,
|
| 63456 |
+
"learning_rate": 2.5319145238598437e-05,
|
| 63457 |
+
"loss": 0.6808,
|
| 63458 |
+
"step": 9064
|
| 63459 |
+
},
|
| 63460 |
+
{
|
| 63461 |
+
"epoch": 10.324786324786325,
|
| 63462 |
+
"grad_norm": 0.23379816114902496,
|
| 63463 |
+
"learning_rate": 2.5314486431610424e-05,
|
| 63464 |
+
"loss": 0.6194,
|
| 63465 |
+
"step": 9065
|
| 63466 |
+
},
|
| 63467 |
+
{
|
| 63468 |
+
"epoch": 10.325925925925926,
|
| 63469 |
+
"grad_norm": 0.18350186944007874,
|
| 63470 |
+
"learning_rate": 2.530982761369944e-05,
|
| 63471 |
+
"loss": 0.7657,
|
| 63472 |
+
"step": 9066
|
| 63473 |
+
},
|
| 63474 |
+
{
|
| 63475 |
+
"epoch": 10.327065527065526,
|
| 63476 |
+
"grad_norm": 0.20779354870319366,
|
| 63477 |
+
"learning_rate": 2.5305168785027285e-05,
|
| 63478 |
+
"loss": 0.6434,
|
| 63479 |
+
"step": 9067
|
| 63480 |
+
},
|
| 63481 |
+
{
|
| 63482 |
+
"epoch": 10.328205128205129,
|
| 63483 |
+
"grad_norm": 0.32120004296302795,
|
| 63484 |
+
"learning_rate": 2.5300509945755783e-05,
|
| 63485 |
+
"loss": 0.7547,
|
| 63486 |
+
"step": 9068
|
| 63487 |
+
},
|
| 63488 |
+
{
|
| 63489 |
+
"epoch": 10.32934472934473,
|
| 63490 |
+
"grad_norm": 0.18596863746643066,
|
| 63491 |
+
"learning_rate": 2.5295851096046735e-05,
|
| 63492 |
+
"loss": 0.8268,
|
| 63493 |
+
"step": 9069
|
| 63494 |
+
},
|
| 63495 |
+
{
|
| 63496 |
+
"epoch": 10.33048433048433,
|
| 63497 |
+
"grad_norm": 0.21592064201831818,
|
| 63498 |
+
"learning_rate": 2.529119223606197e-05,
|
| 63499 |
+
"loss": 0.5348,
|
| 63500 |
+
"step": 9070
|
| 63501 |
+
},
|
| 63502 |
+
{
|
| 63503 |
+
"epoch": 10.331623931623932,
|
| 63504 |
+
"grad_norm": 0.23385873436927795,
|
| 63505 |
+
"learning_rate": 2.5286533365963298e-05,
|
| 63506 |
+
"loss": 0.7101,
|
| 63507 |
+
"step": 9071
|
| 63508 |
+
},
|
| 63509 |
+
{
|
| 63510 |
+
"epoch": 10.332763532763533,
|
| 63511 |
+
"grad_norm": 0.18794724345207214,
|
| 63512 |
+
"learning_rate": 2.5281874485912544e-05,
|
| 63513 |
+
"loss": 0.798,
|
| 63514 |
+
"step": 9072
|
| 63515 |
+
},
|
| 63516 |
+
{
|
| 63517 |
+
"epoch": 10.333903133903133,
|
| 63518 |
+
"grad_norm": 0.24771134555339813,
|
| 63519 |
+
"learning_rate": 2.52772155960715e-05,
|
| 63520 |
+
"loss": 0.6846,
|
| 63521 |
+
"step": 9073
|
| 63522 |
+
},
|
| 63523 |
+
{
|
| 63524 |
+
"epoch": 10.335042735042736,
|
| 63525 |
+
"grad_norm": 0.22779740393161774,
|
| 63526 |
+
"learning_rate": 2.5272556696602005e-05,
|
| 63527 |
+
"loss": 0.7489,
|
| 63528 |
+
"step": 9074
|
| 63529 |
+
},
|
| 63530 |
+
{
|
| 63531 |
+
"epoch": 10.336182336182336,
|
| 63532 |
+
"grad_norm": 0.19389639794826508,
|
| 63533 |
+
"learning_rate": 2.5267897787665856e-05,
|
| 63534 |
+
"loss": 0.9602,
|
| 63535 |
+
"step": 9075
|
| 63536 |
+
},
|
| 63537 |
+
{
|
| 63538 |
+
"epoch": 10.337321937321937,
|
| 63539 |
+
"grad_norm": 0.1903086155653,
|
| 63540 |
+
"learning_rate": 2.5263238869424893e-05,
|
| 63541 |
+
"loss": 0.7167,
|
| 63542 |
+
"step": 9076
|
| 63543 |
+
},
|
| 63544 |
+
{
|
| 63545 |
+
"epoch": 10.338461538461539,
|
| 63546 |
+
"grad_norm": 0.19804181158542633,
|
| 63547 |
+
"learning_rate": 2.525857994204091e-05,
|
| 63548 |
+
"loss": 0.8767,
|
| 63549 |
+
"step": 9077
|
| 63550 |
+
},
|
| 63551 |
+
{
|
| 63552 |
+
"epoch": 10.33960113960114,
|
| 63553 |
+
"grad_norm": 0.22120852768421173,
|
| 63554 |
+
"learning_rate": 2.5253921005675747e-05,
|
| 63555 |
+
"loss": 0.5659,
|
| 63556 |
+
"step": 9078
|
| 63557 |
+
},
|
| 63558 |
+
{
|
| 63559 |
+
"epoch": 10.34074074074074,
|
| 63560 |
+
"grad_norm": 0.24915292859077454,
|
| 63561 |
+
"learning_rate": 2.5249262060491195e-05,
|
| 63562 |
+
"loss": 0.553,
|
| 63563 |
+
"step": 9079
|
| 63564 |
+
},
|
| 63565 |
+
{
|
| 63566 |
+
"epoch": 10.341880341880342,
|
| 63567 |
+
"grad_norm": 0.20701691508293152,
|
| 63568 |
+
"learning_rate": 2.5244603106649095e-05,
|
| 63569 |
+
"loss": 0.7905,
|
| 63570 |
+
"step": 9080
|
| 63571 |
+
},
|
| 63572 |
+
{
|
| 63573 |
+
"epoch": 10.343019943019943,
|
| 63574 |
+
"grad_norm": 0.19434839487075806,
|
| 63575 |
+
"learning_rate": 2.5239944144311252e-05,
|
| 63576 |
+
"loss": 0.7948,
|
| 63577 |
+
"step": 9081
|
| 63578 |
+
},
|
| 63579 |
+
{
|
| 63580 |
+
"epoch": 10.344159544159544,
|
| 63581 |
+
"grad_norm": 0.20556633174419403,
|
| 63582 |
+
"learning_rate": 2.523528517363949e-05,
|
| 63583 |
+
"loss": 0.755,
|
| 63584 |
+
"step": 9082
|
| 63585 |
+
},
|
| 63586 |
+
{
|
| 63587 |
+
"epoch": 10.345299145299146,
|
| 63588 |
+
"grad_norm": 0.18583397567272186,
|
| 63589 |
+
"learning_rate": 2.5230626194795633e-05,
|
| 63590 |
+
"loss": 0.8336,
|
| 63591 |
+
"step": 9083
|
| 63592 |
+
},
|
| 63593 |
+
{
|
| 63594 |
+
"epoch": 10.346438746438746,
|
| 63595 |
+
"grad_norm": 0.17649589478969574,
|
| 63596 |
+
"learning_rate": 2.522596720794148e-05,
|
| 63597 |
+
"loss": 0.7059,
|
| 63598 |
+
"step": 9084
|
| 63599 |
+
},
|
| 63600 |
+
{
|
| 63601 |
+
"epoch": 10.347578347578347,
|
| 63602 |
+
"grad_norm": 0.19684922695159912,
|
| 63603 |
+
"learning_rate": 2.522130821323888e-05,
|
| 63604 |
+
"loss": 0.5711,
|
| 63605 |
+
"step": 9085
|
| 63606 |
+
},
|
| 63607 |
+
{
|
| 63608 |
+
"epoch": 10.34871794871795,
|
| 63609 |
+
"grad_norm": 0.21036779880523682,
|
| 63610 |
+
"learning_rate": 2.5216649210849624e-05,
|
| 63611 |
+
"loss": 0.7529,
|
| 63612 |
+
"step": 9086
|
| 63613 |
+
},
|
| 63614 |
+
{
|
| 63615 |
+
"epoch": 10.34985754985755,
|
| 63616 |
+
"grad_norm": 0.268655002117157,
|
| 63617 |
+
"learning_rate": 2.5211990200935552e-05,
|
| 63618 |
+
"loss": 0.6021,
|
| 63619 |
+
"step": 9087
|
| 63620 |
+
},
|
| 63621 |
+
{
|
| 63622 |
+
"epoch": 10.35099715099715,
|
| 63623 |
+
"grad_norm": 0.2607416808605194,
|
| 63624 |
+
"learning_rate": 2.5207331183658478e-05,
|
| 63625 |
+
"loss": 0.5326,
|
| 63626 |
+
"step": 9088
|
| 63627 |
+
},
|
| 63628 |
+
{
|
| 63629 |
+
"epoch": 10.352136752136753,
|
| 63630 |
+
"grad_norm": 0.23464538156986237,
|
| 63631 |
+
"learning_rate": 2.5202672159180224e-05,
|
| 63632 |
+
"loss": 0.5043,
|
| 63633 |
+
"step": 9089
|
| 63634 |
+
},
|
| 63635 |
+
{
|
| 63636 |
+
"epoch": 10.353276353276353,
|
| 63637 |
+
"grad_norm": 0.24285195767879486,
|
| 63638 |
+
"learning_rate": 2.51980131276626e-05,
|
| 63639 |
+
"loss": 0.5214,
|
| 63640 |
+
"step": 9090
|
| 63641 |
+
},
|
| 63642 |
+
{
|
| 63643 |
+
"epoch": 10.354415954415954,
|
| 63644 |
+
"grad_norm": 0.22683288156986237,
|
| 63645 |
+
"learning_rate": 2.5193354089267446e-05,
|
| 63646 |
+
"loss": 0.7075,
|
| 63647 |
+
"step": 9091
|
| 63648 |
+
},
|
| 63649 |
+
{
|
| 63650 |
+
"epoch": 10.355555555555556,
|
| 63651 |
+
"grad_norm": 0.246296688914299,
|
| 63652 |
+
"learning_rate": 2.5188695044156564e-05,
|
| 63653 |
+
"loss": 0.6478,
|
| 63654 |
+
"step": 9092
|
| 63655 |
+
},
|
| 63656 |
+
{
|
| 63657 |
+
"epoch": 10.356695156695157,
|
| 63658 |
+
"grad_norm": 0.2281445860862732,
|
| 63659 |
+
"learning_rate": 2.5184035992491785e-05,
|
| 63660 |
+
"loss": 0.5469,
|
| 63661 |
+
"step": 9093
|
| 63662 |
+
},
|
| 63663 |
+
{
|
| 63664 |
+
"epoch": 10.357834757834757,
|
| 63665 |
+
"grad_norm": 0.2476527839899063,
|
| 63666 |
+
"learning_rate": 2.517937693443493e-05,
|
| 63667 |
+
"loss": 0.5761,
|
| 63668 |
+
"step": 9094
|
| 63669 |
+
},
|
| 63670 |
+
{
|
| 63671 |
+
"epoch": 10.35897435897436,
|
| 63672 |
+
"grad_norm": 0.204382985830307,
|
| 63673 |
+
"learning_rate": 2.517471787014783e-05,
|
| 63674 |
+
"loss": 0.7355,
|
| 63675 |
+
"step": 9095
|
| 63676 |
+
},
|
| 63677 |
+
{
|
| 63678 |
+
"epoch": 10.36011396011396,
|
| 63679 |
+
"grad_norm": 0.21977843344211578,
|
| 63680 |
+
"learning_rate": 2.5170058799792283e-05,
|
| 63681 |
+
"loss": 0.5223,
|
| 63682 |
+
"step": 9096
|
| 63683 |
+
},
|
| 63684 |
+
{
|
| 63685 |
+
"epoch": 10.36125356125356,
|
| 63686 |
+
"grad_norm": 0.23635803163051605,
|
| 63687 |
+
"learning_rate": 2.5165399723530138e-05,
|
| 63688 |
+
"loss": 0.5094,
|
| 63689 |
+
"step": 9097
|
| 63690 |
+
},
|
| 63691 |
+
{
|
| 63692 |
+
"epoch": 10.362393162393163,
|
| 63693 |
+
"grad_norm": 0.25939029455184937,
|
| 63694 |
+
"learning_rate": 2.5160740641523202e-05,
|
| 63695 |
+
"loss": 0.5848,
|
| 63696 |
+
"step": 9098
|
| 63697 |
+
},
|
| 63698 |
+
{
|
| 63699 |
+
"epoch": 10.363532763532763,
|
| 63700 |
+
"grad_norm": 0.1882343739271164,
|
| 63701 |
+
"learning_rate": 2.5156081553933302e-05,
|
| 63702 |
+
"loss": 0.8578,
|
| 63703 |
+
"step": 9099
|
| 63704 |
+
},
|
| 63705 |
+
{
|
| 63706 |
+
"epoch": 10.364672364672364,
|
| 63707 |
+
"grad_norm": 0.16867879033088684,
|
| 63708 |
+
"learning_rate": 2.5151422460922263e-05,
|
| 63709 |
+
"loss": 0.8172,
|
| 63710 |
+
"step": 9100
|
| 63711 |
+
},
|
| 63712 |
+
{
|
| 63713 |
+
"epoch": 10.365811965811966,
|
| 63714 |
+
"grad_norm": 0.18571686744689941,
|
| 63715 |
+
"learning_rate": 2.5146763362651898e-05,
|
| 63716 |
+
"loss": 0.7812,
|
| 63717 |
+
"step": 9101
|
| 63718 |
+
},
|
| 63719 |
+
{
|
| 63720 |
+
"epoch": 10.366951566951567,
|
| 63721 |
+
"grad_norm": 0.2958218455314636,
|
| 63722 |
+
"learning_rate": 2.5142104259284048e-05,
|
| 63723 |
+
"loss": 0.4948,
|
| 63724 |
+
"step": 9102
|
| 63725 |
+
},
|
| 63726 |
+
{
|
| 63727 |
+
"epoch": 10.368091168091167,
|
| 63728 |
+
"grad_norm": 0.18356817960739136,
|
| 63729 |
+
"learning_rate": 2.513744515098051e-05,
|
| 63730 |
+
"loss": 0.6299,
|
| 63731 |
+
"step": 9103
|
| 63732 |
+
},
|
| 63733 |
+
{
|
| 63734 |
+
"epoch": 10.36923076923077,
|
| 63735 |
+
"grad_norm": 0.1769261211156845,
|
| 63736 |
+
"learning_rate": 2.5132786037903138e-05,
|
| 63737 |
+
"loss": 0.7487,
|
| 63738 |
+
"step": 9104
|
| 63739 |
+
},
|
| 63740 |
+
{
|
| 63741 |
+
"epoch": 10.37037037037037,
|
| 63742 |
+
"grad_norm": 0.20499293506145477,
|
| 63743 |
+
"learning_rate": 2.5128126920213736e-05,
|
| 63744 |
+
"loss": 0.6185,
|
| 63745 |
+
"step": 9105
|
| 63746 |
+
},
|
| 63747 |
+
{
|
| 63748 |
+
"epoch": 10.37150997150997,
|
| 63749 |
+
"grad_norm": 0.24470171332359314,
|
| 63750 |
+
"learning_rate": 2.5123467798074142e-05,
|
| 63751 |
+
"loss": 0.7261,
|
| 63752 |
+
"step": 9106
|
| 63753 |
+
},
|
| 63754 |
+
{
|
| 63755 |
+
"epoch": 10.372649572649573,
|
| 63756 |
+
"grad_norm": 0.1934887170791626,
|
| 63757 |
+
"learning_rate": 2.511880867164616e-05,
|
| 63758 |
+
"loss": 0.7357,
|
| 63759 |
+
"step": 9107
|
| 63760 |
+
},
|
| 63761 |
+
{
|
| 63762 |
+
"epoch": 10.373789173789174,
|
| 63763 |
+
"grad_norm": 0.2458781898021698,
|
| 63764 |
+
"learning_rate": 2.511414954109163e-05,
|
| 63765 |
+
"loss": 0.591,
|
| 63766 |
+
"step": 9108
|
| 63767 |
+
},
|
| 63768 |
+
{
|
| 63769 |
+
"epoch": 10.374928774928774,
|
| 63770 |
+
"grad_norm": 0.25309842824935913,
|
| 63771 |
+
"learning_rate": 2.510949040657238e-05,
|
| 63772 |
+
"loss": 0.7098,
|
| 63773 |
+
"step": 9109
|
| 63774 |
+
},
|
| 63775 |
+
{
|
| 63776 |
+
"epoch": 10.376068376068377,
|
| 63777 |
+
"grad_norm": 0.24694037437438965,
|
| 63778 |
+
"learning_rate": 2.5104831268250217e-05,
|
| 63779 |
+
"loss": 0.4802,
|
| 63780 |
+
"step": 9110
|
| 63781 |
+
},
|
| 63782 |
+
{
|
| 63783 |
+
"epoch": 10.377207977207977,
|
| 63784 |
+
"grad_norm": 0.3160017728805542,
|
| 63785 |
+
"learning_rate": 2.5100172126286986e-05,
|
| 63786 |
+
"loss": 0.8525,
|
| 63787 |
+
"step": 9111
|
| 63788 |
+
},
|
| 63789 |
+
{
|
| 63790 |
+
"epoch": 10.378347578347578,
|
| 63791 |
+
"grad_norm": 0.19555474817752838,
|
| 63792 |
+
"learning_rate": 2.5095512980844495e-05,
|
| 63793 |
+
"loss": 0.8472,
|
| 63794 |
+
"step": 9112
|
| 63795 |
+
},
|
| 63796 |
+
{
|
| 63797 |
+
"epoch": 10.37948717948718,
|
| 63798 |
+
"grad_norm": 0.2248135209083557,
|
| 63799 |
+
"learning_rate": 2.5090853832084576e-05,
|
| 63800 |
+
"loss": 0.5696,
|
| 63801 |
+
"step": 9113
|
| 63802 |
+
},
|
| 63803 |
+
{
|
| 63804 |
+
"epoch": 10.38062678062678,
|
| 63805 |
+
"grad_norm": 0.26771700382232666,
|
| 63806 |
+
"learning_rate": 2.508619468016905e-05,
|
| 63807 |
+
"loss": 0.5819,
|
| 63808 |
+
"step": 9114
|
| 63809 |
+
},
|
| 63810 |
+
{
|
| 63811 |
+
"epoch": 10.381766381766381,
|
| 63812 |
+
"grad_norm": 0.22154538333415985,
|
| 63813 |
+
"learning_rate": 2.5081535525259753e-05,
|
| 63814 |
+
"loss": 0.6595,
|
| 63815 |
+
"step": 9115
|
| 63816 |
+
},
|
| 63817 |
+
{
|
| 63818 |
+
"epoch": 10.382905982905983,
|
| 63819 |
+
"grad_norm": 0.1972038894891739,
|
| 63820 |
+
"learning_rate": 2.5076876367518497e-05,
|
| 63821 |
+
"loss": 0.6492,
|
| 63822 |
+
"step": 9116
|
| 63823 |
+
},
|
| 63824 |
+
{
|
| 63825 |
+
"epoch": 10.384045584045584,
|
| 63826 |
+
"grad_norm": 0.22136695683002472,
|
| 63827 |
+
"learning_rate": 2.5072217207107118e-05,
|
| 63828 |
+
"loss": 0.7124,
|
| 63829 |
+
"step": 9117
|
| 63830 |
+
},
|
| 63831 |
+
{
|
| 63832 |
+
"epoch": 10.385185185185184,
|
| 63833 |
+
"grad_norm": 0.19860419631004333,
|
| 63834 |
+
"learning_rate": 2.5067558044187434e-05,
|
| 63835 |
+
"loss": 0.5594,
|
| 63836 |
+
"step": 9118
|
| 63837 |
+
},
|
| 63838 |
+
{
|
| 63839 |
+
"epoch": 10.386324786324787,
|
| 63840 |
+
"grad_norm": 0.2616336941719055,
|
| 63841 |
+
"learning_rate": 2.506289887892127e-05,
|
| 63842 |
+
"loss": 0.533,
|
| 63843 |
+
"step": 9119
|
| 63844 |
+
},
|
| 63845 |
+
{
|
| 63846 |
+
"epoch": 10.387464387464387,
|
| 63847 |
+
"grad_norm": 0.23004023730754852,
|
| 63848 |
+
"learning_rate": 2.505823971147046e-05,
|
| 63849 |
+
"loss": 0.7366,
|
| 63850 |
+
"step": 9120
|
| 63851 |
+
},
|
| 63852 |
+
{
|
| 63853 |
+
"epoch": 10.388603988603988,
|
| 63854 |
+
"grad_norm": 0.28769731521606445,
|
| 63855 |
+
"learning_rate": 2.5053580541996825e-05,
|
| 63856 |
+
"loss": 0.7604,
|
| 63857 |
+
"step": 9121
|
| 63858 |
+
},
|
| 63859 |
+
{
|
| 63860 |
+
"epoch": 10.38974358974359,
|
| 63861 |
+
"grad_norm": 0.2059997171163559,
|
| 63862 |
+
"learning_rate": 2.5048921370662188e-05,
|
| 63863 |
+
"loss": 0.83,
|
| 63864 |
+
"step": 9122
|
| 63865 |
+
},
|
| 63866 |
+
{
|
| 63867 |
+
"epoch": 10.39088319088319,
|
| 63868 |
+
"grad_norm": 0.21634230017662048,
|
| 63869 |
+
"learning_rate": 2.504426219762838e-05,
|
| 63870 |
+
"loss": 0.781,
|
| 63871 |
+
"step": 9123
|
| 63872 |
+
},
|
| 63873 |
+
{
|
| 63874 |
+
"epoch": 10.392022792022791,
|
| 63875 |
+
"grad_norm": 0.19295218586921692,
|
| 63876 |
+
"learning_rate": 2.5039603023057224e-05,
|
| 63877 |
+
"loss": 0.804,
|
| 63878 |
+
"step": 9124
|
| 63879 |
+
},
|
| 63880 |
+
{
|
| 63881 |
+
"epoch": 10.393162393162394,
|
| 63882 |
+
"grad_norm": 0.24506190419197083,
|
| 63883 |
+
"learning_rate": 2.5034943847110543e-05,
|
| 63884 |
+
"loss": 0.6323,
|
| 63885 |
+
"step": 9125
|
| 63886 |
+
},
|
| 63887 |
+
{
|
| 63888 |
+
"epoch": 10.394301994301994,
|
| 63889 |
+
"grad_norm": 0.24567458033561707,
|
| 63890 |
+
"learning_rate": 2.5030284669950165e-05,
|
| 63891 |
+
"loss": 0.528,
|
| 63892 |
+
"step": 9126
|
| 63893 |
+
},
|
| 63894 |
+
{
|
| 63895 |
+
"epoch": 10.395441595441595,
|
| 63896 |
+
"grad_norm": 0.20807871222496033,
|
| 63897 |
+
"learning_rate": 2.5025625491737918e-05,
|
| 63898 |
+
"loss": 0.7562,
|
| 63899 |
+
"step": 9127
|
| 63900 |
+
},
|
| 63901 |
+
{
|
| 63902 |
+
"epoch": 10.396581196581197,
|
| 63903 |
+
"grad_norm": 0.18178433179855347,
|
| 63904 |
+
"learning_rate": 2.5020966312635636e-05,
|
| 63905 |
+
"loss": 0.7226,
|
| 63906 |
+
"step": 9128
|
| 63907 |
+
},
|
| 63908 |
+
{
|
| 63909 |
+
"epoch": 10.397720797720797,
|
| 63910 |
+
"grad_norm": 0.24313658475875854,
|
| 63911 |
+
"learning_rate": 2.501630713280513e-05,
|
| 63912 |
+
"loss": 0.5879,
|
| 63913 |
+
"step": 9129
|
| 63914 |
+
},
|
| 63915 |
+
{
|
| 63916 |
+
"epoch": 10.398860398860398,
|
| 63917 |
+
"grad_norm": 0.17432768642902374,
|
| 63918 |
+
"learning_rate": 2.5011647952408228e-05,
|
| 63919 |
+
"loss": 0.8408,
|
| 63920 |
+
"step": 9130
|
| 63921 |
+
},
|
| 63922 |
+
{
|
| 63923 |
+
"epoch": 10.4,
|
| 63924 |
+
"grad_norm": 0.2106270045042038,
|
| 63925 |
+
"learning_rate": 2.500698877160676e-05,
|
| 63926 |
+
"loss": 0.6269,
|
| 63927 |
+
"step": 9131
|
| 63928 |
+
},
|
| 63929 |
+
{
|
| 63930 |
+
"epoch": 10.401139601139601,
|
| 63931 |
+
"grad_norm": 0.1890728622674942,
|
| 63932 |
+
"learning_rate": 2.500232959056256e-05,
|
| 63933 |
+
"loss": 0.8182,
|
| 63934 |
+
"step": 9132
|
| 63935 |
+
},
|
| 63936 |
+
{
|
| 63937 |
+
"epoch": 10.402279202279201,
|
| 63938 |
+
"grad_norm": 0.15904033184051514,
|
| 63939 |
+
"learning_rate": 2.4997670409437442e-05,
|
| 63940 |
+
"loss": 0.7987,
|
| 63941 |
+
"step": 9133
|
| 63942 |
+
},
|
| 63943 |
+
{
|
| 63944 |
+
"epoch": 10.403418803418804,
|
| 63945 |
+
"grad_norm": 0.24167656898498535,
|
| 63946 |
+
"learning_rate": 2.4993011228393245e-05,
|
| 63947 |
+
"loss": 0.6376,
|
| 63948 |
+
"step": 9134
|
| 63949 |
+
},
|
| 63950 |
+
{
|
| 63951 |
+
"epoch": 10.404558404558404,
|
| 63952 |
+
"grad_norm": 0.26482895016670227,
|
| 63953 |
+
"learning_rate": 2.4988352047591778e-05,
|
| 63954 |
+
"loss": 0.5588,
|
| 63955 |
+
"step": 9135
|
| 63956 |
+
},
|
| 63957 |
+
{
|
| 63958 |
+
"epoch": 10.405698005698005,
|
| 63959 |
+
"grad_norm": 0.22393764555454254,
|
| 63960 |
+
"learning_rate": 2.4983692867194883e-05,
|
| 63961 |
+
"loss": 0.6064,
|
| 63962 |
+
"step": 9136
|
| 63963 |
+
},
|
| 63964 |
+
{
|
| 63965 |
+
"epoch": 10.406837606837607,
|
| 63966 |
+
"grad_norm": 0.19010251760482788,
|
| 63967 |
+
"learning_rate": 2.4979033687364377e-05,
|
| 63968 |
+
"loss": 0.8819,
|
| 63969 |
+
"step": 9137
|
| 63970 |
+
},
|
| 63971 |
+
{
|
| 63972 |
+
"epoch": 10.407977207977208,
|
| 63973 |
+
"grad_norm": 0.2721906304359436,
|
| 63974 |
+
"learning_rate": 2.4974374508262088e-05,
|
| 63975 |
+
"loss": 0.4509,
|
| 63976 |
+
"step": 9138
|
| 63977 |
+
},
|
| 63978 |
+
{
|
| 63979 |
+
"epoch": 10.40911680911681,
|
| 63980 |
+
"grad_norm": 0.17516137659549713,
|
| 63981 |
+
"learning_rate": 2.4969715330049837e-05,
|
| 63982 |
+
"loss": 0.8094,
|
| 63983 |
+
"step": 9139
|
| 63984 |
+
},
|
| 63985 |
+
{
|
| 63986 |
+
"epoch": 10.41025641025641,
|
| 63987 |
+
"grad_norm": 0.19217105209827423,
|
| 63988 |
+
"learning_rate": 2.496505615288946e-05,
|
| 63989 |
+
"loss": 0.7668,
|
| 63990 |
+
"step": 9140
|
| 63991 |
+
},
|
| 63992 |
+
{
|
| 63993 |
+
"epoch": 10.411396011396011,
|
| 63994 |
+
"grad_norm": 0.18340454995632172,
|
| 63995 |
+
"learning_rate": 2.4960396976942785e-05,
|
| 63996 |
+
"loss": 0.8836,
|
| 63997 |
+
"step": 9141
|
| 63998 |
+
},
|
| 63999 |
+
{
|
| 64000 |
+
"epoch": 10.412535612535613,
|
| 64001 |
+
"grad_norm": 0.2205548882484436,
|
| 64002 |
+
"learning_rate": 2.4955737802371624e-05,
|
| 64003 |
+
"loss": 0.73,
|
| 64004 |
+
"step": 9142
|
| 64005 |
+
},
|
| 64006 |
+
{
|
| 64007 |
+
"epoch": 10.413675213675214,
|
| 64008 |
+
"grad_norm": 0.2542133629322052,
|
| 64009 |
+
"learning_rate": 2.4951078629337818e-05,
|
| 64010 |
+
"loss": 0.5596,
|
| 64011 |
+
"step": 9143
|
| 64012 |
+
},
|
| 64013 |
+
{
|
| 64014 |
+
"epoch": 10.414814814814815,
|
| 64015 |
+
"grad_norm": 0.18789978325366974,
|
| 64016 |
+
"learning_rate": 2.494641945800318e-05,
|
| 64017 |
+
"loss": 0.7735,
|
| 64018 |
+
"step": 9144
|
| 64019 |
+
},
|
| 64020 |
+
{
|
| 64021 |
+
"epoch": 10.415954415954417,
|
| 64022 |
+
"grad_norm": 0.22405776381492615,
|
| 64023 |
+
"learning_rate": 2.494176028852955e-05,
|
| 64024 |
+
"loss": 0.7452,
|
| 64025 |
+
"step": 9145
|
| 64026 |
+
},
|
| 64027 |
+
{
|
| 64028 |
+
"epoch": 10.417094017094017,
|
| 64029 |
+
"grad_norm": 0.24683396518230438,
|
| 64030 |
+
"learning_rate": 2.4937101121078733e-05,
|
| 64031 |
+
"loss": 0.6412,
|
| 64032 |
+
"step": 9146
|
| 64033 |
+
},
|
| 64034 |
+
{
|
| 64035 |
+
"epoch": 10.418233618233618,
|
| 64036 |
+
"grad_norm": 0.22049246728420258,
|
| 64037 |
+
"learning_rate": 2.493244195581258e-05,
|
| 64038 |
+
"loss": 0.5547,
|
| 64039 |
+
"step": 9147
|
| 64040 |
+
},
|
| 64041 |
+
{
|
| 64042 |
+
"epoch": 10.41937321937322,
|
| 64043 |
+
"grad_norm": 0.224561870098114,
|
| 64044 |
+
"learning_rate": 2.492778279289289e-05,
|
| 64045 |
+
"loss": 0.6858,
|
| 64046 |
+
"step": 9148
|
| 64047 |
+
},
|
| 64048 |
+
{
|
| 64049 |
+
"epoch": 10.42051282051282,
|
| 64050 |
+
"grad_norm": 0.25088754296302795,
|
| 64051 |
+
"learning_rate": 2.4923123632481516e-05,
|
| 64052 |
+
"loss": 0.6639,
|
| 64053 |
+
"step": 9149
|
| 64054 |
+
},
|
| 64055 |
+
{
|
| 64056 |
+
"epoch": 10.421652421652421,
|
| 64057 |
+
"grad_norm": 0.22070088982582092,
|
| 64058 |
+
"learning_rate": 2.4918464474740246e-05,
|
| 64059 |
+
"loss": 0.7119,
|
| 64060 |
+
"step": 9150
|
| 64061 |
+
},
|
| 64062 |
+
{
|
| 64063 |
+
"epoch": 10.422792022792024,
|
| 64064 |
+
"grad_norm": 0.21628473699092865,
|
| 64065 |
+
"learning_rate": 2.4913805319830953e-05,
|
| 64066 |
+
"loss": 0.7809,
|
| 64067 |
+
"step": 9151
|
| 64068 |
+
},
|
| 64069 |
+
{
|
| 64070 |
+
"epoch": 10.423931623931624,
|
| 64071 |
+
"grad_norm": 0.18613789975643158,
|
| 64072 |
+
"learning_rate": 2.4909146167915426e-05,
|
| 64073 |
+
"loss": 0.7631,
|
| 64074 |
+
"step": 9152
|
| 64075 |
+
},
|
| 64076 |
+
{
|
| 64077 |
+
"epoch": 10.425071225071225,
|
| 64078 |
+
"grad_norm": 0.20988789200782776,
|
| 64079 |
+
"learning_rate": 2.490448701915551e-05,
|
| 64080 |
+
"loss": 0.7389,
|
| 64081 |
+
"step": 9153
|
| 64082 |
+
},
|
| 64083 |
+
{
|
| 64084 |
+
"epoch": 10.426210826210827,
|
| 64085 |
+
"grad_norm": 0.20752722024917603,
|
| 64086 |
+
"learning_rate": 2.489982787371302e-05,
|
| 64087 |
+
"loss": 0.8322,
|
| 64088 |
+
"step": 9154
|
| 64089 |
+
},
|
| 64090 |
+
{
|
| 64091 |
+
"epoch": 10.427350427350428,
|
| 64092 |
+
"grad_norm": 0.2517094612121582,
|
| 64093 |
+
"learning_rate": 2.4895168731749785e-05,
|
| 64094 |
+
"loss": 0.7053,
|
| 64095 |
+
"step": 9155
|
| 64096 |
+
},
|
| 64097 |
+
{
|
| 64098 |
+
"epoch": 10.428490028490028,
|
| 64099 |
+
"grad_norm": 0.26300299167633057,
|
| 64100 |
+
"learning_rate": 2.4890509593427623e-05,
|
| 64101 |
+
"loss": 0.5408,
|
| 64102 |
+
"step": 9156
|
| 64103 |
+
},
|
| 64104 |
+
{
|
| 64105 |
+
"epoch": 10.42962962962963,
|
| 64106 |
+
"grad_norm": 0.21144193410873413,
|
| 64107 |
+
"learning_rate": 2.488585045890837e-05,
|
| 64108 |
+
"loss": 0.56,
|
| 64109 |
+
"step": 9157
|
| 64110 |
+
},
|
| 64111 |
+
{
|
| 64112 |
+
"epoch": 10.430769230769231,
|
| 64113 |
+
"grad_norm": 0.3269287943840027,
|
| 64114 |
+
"learning_rate": 2.4881191328353844e-05,
|
| 64115 |
+
"loss": 0.6435,
|
| 64116 |
+
"step": 9158
|
| 64117 |
+
},
|
| 64118 |
+
{
|
| 64119 |
+
"epoch": 10.431908831908832,
|
| 64120 |
+
"grad_norm": 0.21544551849365234,
|
| 64121 |
+
"learning_rate": 2.487653220192587e-05,
|
| 64122 |
+
"loss": 0.8135,
|
| 64123 |
+
"step": 9159
|
| 64124 |
+
},
|
| 64125 |
+
{
|
| 64126 |
+
"epoch": 10.433048433048434,
|
| 64127 |
+
"grad_norm": 0.2292126566171646,
|
| 64128 |
+
"learning_rate": 2.4871873079786266e-05,
|
| 64129 |
+
"loss": 0.6312,
|
| 64130 |
+
"step": 9160
|
| 64131 |
+
},
|
| 64132 |
+
{
|
| 64133 |
+
"epoch": 10.434188034188034,
|
| 64134 |
+
"grad_norm": 0.19939513504505157,
|
| 64135 |
+
"learning_rate": 2.486721396209686e-05,
|
| 64136 |
+
"loss": 0.7441,
|
| 64137 |
+
"step": 9161
|
| 64138 |
+
},
|
| 64139 |
+
{
|
| 64140 |
+
"epoch": 10.435327635327635,
|
| 64141 |
+
"grad_norm": 0.240824356675148,
|
| 64142 |
+
"learning_rate": 2.4862554849019486e-05,
|
| 64143 |
+
"loss": 0.8579,
|
| 64144 |
+
"step": 9162
|
| 64145 |
+
},
|
| 64146 |
+
{
|
| 64147 |
+
"epoch": 10.436467236467237,
|
| 64148 |
+
"grad_norm": 0.18286165595054626,
|
| 64149 |
+
"learning_rate": 2.4857895740715958e-05,
|
| 64150 |
+
"loss": 0.6545,
|
| 64151 |
+
"step": 9163
|
| 64152 |
+
},
|
| 64153 |
+
{
|
| 64154 |
+
"epoch": 10.437606837606838,
|
| 64155 |
+
"grad_norm": 0.20635467767715454,
|
| 64156 |
+
"learning_rate": 2.4853236637348108e-05,
|
| 64157 |
+
"loss": 0.71,
|
| 64158 |
+
"step": 9164
|
| 64159 |
+
},
|
| 64160 |
+
{
|
| 64161 |
+
"epoch": 10.438746438746438,
|
| 64162 |
+
"grad_norm": 0.16474197804927826,
|
| 64163 |
+
"learning_rate": 2.4848577539077743e-05,
|
| 64164 |
+
"loss": 0.9268,
|
| 64165 |
+
"step": 9165
|
| 64166 |
+
},
|
| 64167 |
+
{
|
| 64168 |
+
"epoch": 10.43988603988604,
|
| 64169 |
+
"grad_norm": 0.29166439175605774,
|
| 64170 |
+
"learning_rate": 2.4843918446066703e-05,
|
| 64171 |
+
"loss": 0.5326,
|
| 64172 |
+
"step": 9166
|
| 64173 |
+
},
|
| 64174 |
+
{
|
| 64175 |
+
"epoch": 10.441025641025641,
|
| 64176 |
+
"grad_norm": 0.2056402862071991,
|
| 64177 |
+
"learning_rate": 2.48392593584768e-05,
|
| 64178 |
+
"loss": 0.695,
|
| 64179 |
+
"step": 9167
|
| 64180 |
+
},
|
| 64181 |
+
{
|
| 64182 |
+
"epoch": 10.442165242165242,
|
| 64183 |
+
"grad_norm": 0.25406187772750854,
|
| 64184 |
+
"learning_rate": 2.4834600276469868e-05,
|
| 64185 |
+
"loss": 0.5937,
|
| 64186 |
+
"step": 9168
|
| 64187 |
+
},
|
| 64188 |
+
{
|
| 64189 |
+
"epoch": 10.443304843304844,
|
| 64190 |
+
"grad_norm": 0.2251429706811905,
|
| 64191 |
+
"learning_rate": 2.482994120020772e-05,
|
| 64192 |
+
"loss": 0.6429,
|
| 64193 |
+
"step": 9169
|
| 64194 |
+
},
|
| 64195 |
+
{
|
| 64196 |
+
"epoch": 10.444444444444445,
|
| 64197 |
+
"grad_norm": 0.19202420115470886,
|
| 64198 |
+
"learning_rate": 2.4825282129852185e-05,
|
| 64199 |
+
"loss": 0.8191,
|
| 64200 |
+
"step": 9170
|
| 64201 |
+
},
|
| 64202 |
+
{
|
| 64203 |
+
"epoch": 10.445584045584045,
|
| 64204 |
+
"grad_norm": 0.2481834441423416,
|
| 64205 |
+
"learning_rate": 2.4820623065565074e-05,
|
| 64206 |
+
"loss": 0.6438,
|
| 64207 |
+
"step": 9171
|
| 64208 |
+
},
|
| 64209 |
+
{
|
| 64210 |
+
"epoch": 10.446723646723648,
|
| 64211 |
+
"grad_norm": 0.20098984241485596,
|
| 64212 |
+
"learning_rate": 2.4815964007508214e-05,
|
| 64213 |
+
"loss": 0.7943,
|
| 64214 |
+
"step": 9172
|
| 64215 |
+
},
|
| 64216 |
+
{
|
| 64217 |
+
"epoch": 10.447863247863248,
|
| 64218 |
+
"grad_norm": 0.2452813982963562,
|
| 64219 |
+
"learning_rate": 2.4811304955843442e-05,
|
| 64220 |
+
"loss": 0.4899,
|
| 64221 |
+
"step": 9173
|
| 64222 |
+
},
|
| 64223 |
+
{
|
| 64224 |
+
"epoch": 10.449002849002849,
|
| 64225 |
+
"grad_norm": 0.22470121085643768,
|
| 64226 |
+
"learning_rate": 2.480664591073256e-05,
|
| 64227 |
+
"loss": 0.7734,
|
| 64228 |
+
"step": 9174
|
| 64229 |
+
},
|
| 64230 |
+
{
|
| 64231 |
+
"epoch": 10.450142450142451,
|
| 64232 |
+
"grad_norm": 0.20485779643058777,
|
| 64233 |
+
"learning_rate": 2.4801986872337405e-05,
|
| 64234 |
+
"loss": 0.729,
|
| 64235 |
+
"step": 9175
|
| 64236 |
+
},
|
| 64237 |
+
{
|
| 64238 |
+
"epoch": 10.451282051282051,
|
| 64239 |
+
"grad_norm": 0.1785956621170044,
|
| 64240 |
+
"learning_rate": 2.4797327840819786e-05,
|
| 64241 |
+
"loss": 0.9572,
|
| 64242 |
+
"step": 9176
|
| 64243 |
+
},
|
| 64244 |
+
{
|
| 64245 |
+
"epoch": 10.452421652421652,
|
| 64246 |
+
"grad_norm": 0.1983714997768402,
|
| 64247 |
+
"learning_rate": 2.479266881634153e-05,
|
| 64248 |
+
"loss": 0.7518,
|
| 64249 |
+
"step": 9177
|
| 64250 |
+
},
|
| 64251 |
+
{
|
| 64252 |
+
"epoch": 10.453561253561254,
|
| 64253 |
+
"grad_norm": 0.2530549168586731,
|
| 64254 |
+
"learning_rate": 2.478800979906445e-05,
|
| 64255 |
+
"loss": 0.5448,
|
| 64256 |
+
"step": 9178
|
| 64257 |
+
},
|
| 64258 |
+
{
|
| 64259 |
+
"epoch": 10.454700854700855,
|
| 64260 |
+
"grad_norm": 0.18680530786514282,
|
| 64261 |
+
"learning_rate": 2.4783350789150382e-05,
|
| 64262 |
+
"loss": 0.7539,
|
| 64263 |
+
"step": 9179
|
| 64264 |
+
},
|
| 64265 |
+
{
|
| 64266 |
+
"epoch": 10.455840455840455,
|
| 64267 |
+
"grad_norm": 0.18843460083007812,
|
| 64268 |
+
"learning_rate": 2.477869178676113e-05,
|
| 64269 |
+
"loss": 0.8563,
|
| 64270 |
+
"step": 9180
|
| 64271 |
+
},
|
| 64272 |
+
{
|
| 64273 |
+
"epoch": 10.456980056980058,
|
| 64274 |
+
"grad_norm": 0.1869039237499237,
|
| 64275 |
+
"learning_rate": 2.4774032792058528e-05,
|
| 64276 |
+
"loss": 0.7921,
|
| 64277 |
+
"step": 9181
|
| 64278 |
+
},
|
| 64279 |
+
{
|
| 64280 |
+
"epoch": 10.458119658119658,
|
| 64281 |
+
"grad_norm": 0.19671130180358887,
|
| 64282 |
+
"learning_rate": 2.476937380520438e-05,
|
| 64283 |
+
"loss": 0.6853,
|
| 64284 |
+
"step": 9182
|
| 64285 |
+
},
|
| 64286 |
+
{
|
| 64287 |
+
"epoch": 10.459259259259259,
|
| 64288 |
+
"grad_norm": 0.16532261669635773,
|
| 64289 |
+
"learning_rate": 2.476471482636051e-05,
|
| 64290 |
+
"loss": 0.8053,
|
| 64291 |
+
"step": 9183
|
| 64292 |
+
},
|
| 64293 |
+
{
|
| 64294 |
+
"epoch": 10.460398860398861,
|
| 64295 |
+
"grad_norm": 0.20217740535736084,
|
| 64296 |
+
"learning_rate": 2.476005585568875e-05,
|
| 64297 |
+
"loss": 0.6541,
|
| 64298 |
+
"step": 9184
|
| 64299 |
+
},
|
| 64300 |
+
{
|
| 64301 |
+
"epoch": 10.461538461538462,
|
| 64302 |
+
"grad_norm": 0.2208511084318161,
|
| 64303 |
+
"learning_rate": 2.475539689335091e-05,
|
| 64304 |
+
"loss": 0.6965,
|
| 64305 |
+
"step": 9185
|
| 64306 |
+
},
|
| 64307 |
+
{
|
| 64308 |
+
"epoch": 10.462678062678062,
|
| 64309 |
+
"grad_norm": 0.2560354471206665,
|
| 64310 |
+
"learning_rate": 2.4750737939508807e-05,
|
| 64311 |
+
"loss": 0.5133,
|
| 64312 |
+
"step": 9186
|
| 64313 |
+
},
|
| 64314 |
+
{
|
| 64315 |
+
"epoch": 10.463817663817665,
|
| 64316 |
+
"grad_norm": 0.24244089424610138,
|
| 64317 |
+
"learning_rate": 2.4746078994324262e-05,
|
| 64318 |
+
"loss": 0.8707,
|
| 64319 |
+
"step": 9187
|
| 64320 |
+
},
|
| 64321 |
+
{
|
| 64322 |
+
"epoch": 10.464957264957265,
|
| 64323 |
+
"grad_norm": 0.21213071048259735,
|
| 64324 |
+
"learning_rate": 2.4741420057959095e-05,
|
| 64325 |
+
"loss": 0.6993,
|
| 64326 |
+
"step": 9188
|
| 64327 |
+
},
|
| 64328 |
+
{
|
| 64329 |
+
"epoch": 10.466096866096866,
|
| 64330 |
+
"grad_norm": 0.25305524468421936,
|
| 64331 |
+
"learning_rate": 2.4736761130575113e-05,
|
| 64332 |
+
"loss": 0.5913,
|
| 64333 |
+
"step": 9189
|
| 64334 |
+
},
|
| 64335 |
+
{
|
| 64336 |
+
"epoch": 10.467236467236468,
|
| 64337 |
+
"grad_norm": 0.2465902715921402,
|
| 64338 |
+
"learning_rate": 2.473210221233415e-05,
|
| 64339 |
+
"loss": 0.523,
|
| 64340 |
+
"step": 9190
|
| 64341 |
+
},
|
| 64342 |
+
{
|
| 64343 |
+
"epoch": 10.468376068376068,
|
| 64344 |
+
"grad_norm": 0.1970120519399643,
|
| 64345 |
+
"learning_rate": 2.4727443303398004e-05,
|
| 64346 |
+
"loss": 0.772,
|
| 64347 |
+
"step": 9191
|
| 64348 |
+
},
|
| 64349 |
+
{
|
| 64350 |
+
"epoch": 10.469515669515669,
|
| 64351 |
+
"grad_norm": 0.2229175716638565,
|
| 64352 |
+
"learning_rate": 2.4722784403928507e-05,
|
| 64353 |
+
"loss": 0.4972,
|
| 64354 |
+
"step": 9192
|
| 64355 |
+
},
|
| 64356 |
+
{
|
| 64357 |
+
"epoch": 10.470655270655271,
|
| 64358 |
+
"grad_norm": 0.1660129576921463,
|
| 64359 |
+
"learning_rate": 2.471812551408747e-05,
|
| 64360 |
+
"loss": 0.7344,
|
| 64361 |
+
"step": 9193
|
| 64362 |
+
},
|
| 64363 |
+
{
|
| 64364 |
+
"epoch": 10.471794871794872,
|
| 64365 |
+
"grad_norm": 0.24172258377075195,
|
| 64366 |
+
"learning_rate": 2.4713466634036697e-05,
|
| 64367 |
+
"loss": 0.6205,
|
| 64368 |
+
"step": 9194
|
| 64369 |
+
},
|
| 64370 |
+
{
|
| 64371 |
+
"epoch": 10.472934472934472,
|
| 64372 |
+
"grad_norm": 0.1414172202348709,
|
| 64373 |
+
"learning_rate": 2.4708807763938025e-05,
|
| 64374 |
+
"loss": 0.8975,
|
| 64375 |
+
"step": 9195
|
| 64376 |
+
},
|
| 64377 |
+
{
|
| 64378 |
+
"epoch": 10.474074074074075,
|
| 64379 |
+
"grad_norm": 0.21612918376922607,
|
| 64380 |
+
"learning_rate": 2.4704148903953267e-05,
|
| 64381 |
+
"loss": 0.7639,
|
| 64382 |
+
"step": 9196
|
| 64383 |
+
},
|
| 64384 |
+
{
|
| 64385 |
+
"epoch": 10.475213675213675,
|
| 64386 |
+
"grad_norm": 0.27035245299339294,
|
| 64387 |
+
"learning_rate": 2.4699490054244223e-05,
|
| 64388 |
+
"loss": 0.5958,
|
| 64389 |
+
"step": 9197
|
| 64390 |
+
},
|
| 64391 |
+
{
|
| 64392 |
+
"epoch": 10.476353276353276,
|
| 64393 |
+
"grad_norm": 0.25695329904556274,
|
| 64394 |
+
"learning_rate": 2.469483121497272e-05,
|
| 64395 |
+
"loss": 0.6122,
|
| 64396 |
+
"step": 9198
|
| 64397 |
+
},
|
| 64398 |
+
{
|
| 64399 |
+
"epoch": 10.477492877492878,
|
| 64400 |
+
"grad_norm": 0.2563282251358032,
|
| 64401 |
+
"learning_rate": 2.4690172386300566e-05,
|
| 64402 |
+
"loss": 0.5376,
|
| 64403 |
+
"step": 9199
|
| 64404 |
+
},
|
| 64405 |
+
{
|
| 64406 |
+
"epoch": 10.478632478632479,
|
| 64407 |
+
"grad_norm": 0.3040502071380615,
|
| 64408 |
+
"learning_rate": 2.4685513568389582e-05,
|
| 64409 |
+
"loss": 0.5579,
|
| 64410 |
+
"step": 9200
|
| 64411 |
+
},
|
| 64412 |
+
{
|
| 64413 |
+
"epoch": 10.47977207977208,
|
| 64414 |
+
"grad_norm": 0.20318159461021423,
|
| 64415 |
+
"learning_rate": 2.468085476140157e-05,
|
| 64416 |
+
"loss": 0.8939,
|
| 64417 |
+
"step": 9201
|
| 64418 |
+
},
|
| 64419 |
+
{
|
| 64420 |
+
"epoch": 10.480911680911682,
|
| 64421 |
+
"grad_norm": 0.18470041453838348,
|
| 64422 |
+
"learning_rate": 2.4676195965498354e-05,
|
| 64423 |
+
"loss": 0.7726,
|
| 64424 |
+
"step": 9202
|
| 64425 |
+
},
|
| 64426 |
+
{
|
| 64427 |
+
"epoch": 10.482051282051282,
|
| 64428 |
+
"grad_norm": 0.2489010989665985,
|
| 64429 |
+
"learning_rate": 2.4671537180841738e-05,
|
| 64430 |
+
"loss": 0.5073,
|
| 64431 |
+
"step": 9203
|
| 64432 |
+
},
|
| 64433 |
+
{
|
| 64434 |
+
"epoch": 10.483190883190883,
|
| 64435 |
+
"grad_norm": 0.18530192971229553,
|
| 64436 |
+
"learning_rate": 2.4666878407593548e-05,
|
| 64437 |
+
"loss": 0.5438,
|
| 64438 |
+
"step": 9204
|
| 64439 |
+
},
|
| 64440 |
+
{
|
| 64441 |
+
"epoch": 10.484330484330485,
|
| 64442 |
+
"grad_norm": 0.2398802638053894,
|
| 64443 |
+
"learning_rate": 2.466221964591557e-05,
|
| 64444 |
+
"loss": 0.6481,
|
| 64445 |
+
"step": 9205
|
| 64446 |
+
},
|
| 64447 |
+
{
|
| 64448 |
+
"epoch": 10.485470085470086,
|
| 64449 |
+
"grad_norm": 0.3169020414352417,
|
| 64450 |
+
"learning_rate": 2.4657560895969642e-05,
|
| 64451 |
+
"loss": 0.6789,
|
| 64452 |
+
"step": 9206
|
| 64453 |
+
},
|
| 64454 |
+
{
|
| 64455 |
+
"epoch": 10.486609686609686,
|
| 64456 |
+
"grad_norm": 0.2191244512796402,
|
| 64457 |
+
"learning_rate": 2.465290215791757e-05,
|
| 64458 |
+
"loss": 0.7045,
|
| 64459 |
+
"step": 9207
|
| 64460 |
+
},
|
| 64461 |
+
{
|
| 64462 |
+
"epoch": 10.487749287749288,
|
| 64463 |
+
"grad_norm": 0.2541128396987915,
|
| 64464 |
+
"learning_rate": 2.4648243431921155e-05,
|
| 64465 |
+
"loss": 0.6094,
|
| 64466 |
+
"step": 9208
|
| 64467 |
+
},
|
| 64468 |
+
{
|
| 64469 |
+
"epoch": 10.488888888888889,
|
| 64470 |
+
"grad_norm": 0.18173936009407043,
|
| 64471 |
+
"learning_rate": 2.4643584718142222e-05,
|
| 64472 |
+
"loss": 0.7499,
|
| 64473 |
+
"step": 9209
|
| 64474 |
+
},
|
| 64475 |
+
{
|
| 64476 |
+
"epoch": 10.49002849002849,
|
| 64477 |
+
"grad_norm": 0.22637872397899628,
|
| 64478 |
+
"learning_rate": 2.4638926016742565e-05,
|
| 64479 |
+
"loss": 0.7103,
|
| 64480 |
+
"step": 9210
|
| 64481 |
+
},
|
| 64482 |
+
{
|
| 64483 |
+
"epoch": 10.491168091168092,
|
| 64484 |
+
"grad_norm": 0.2989262640476227,
|
| 64485 |
+
"learning_rate": 2.4634267327884003e-05,
|
| 64486 |
+
"loss": 0.5129,
|
| 64487 |
+
"step": 9211
|
| 64488 |
+
},
|
| 64489 |
+
{
|
| 64490 |
+
"epoch": 10.492307692307692,
|
| 64491 |
+
"grad_norm": 0.31442877650260925,
|
| 64492 |
+
"learning_rate": 2.4629608651728336e-05,
|
| 64493 |
+
"loss": 0.7376,
|
| 64494 |
+
"step": 9212
|
| 64495 |
+
},
|
| 64496 |
+
{
|
| 64497 |
+
"epoch": 10.493447293447293,
|
| 64498 |
+
"grad_norm": 0.26555660367012024,
|
| 64499 |
+
"learning_rate": 2.4624949988437386e-05,
|
| 64500 |
+
"loss": 0.5071,
|
| 64501 |
+
"step": 9213
|
| 64502 |
+
},
|
| 64503 |
+
{
|
| 64504 |
+
"epoch": 10.494586894586895,
|
| 64505 |
+
"grad_norm": 0.22290778160095215,
|
| 64506 |
+
"learning_rate": 2.462029133817295e-05,
|
| 64507 |
+
"loss": 0.6802,
|
| 64508 |
+
"step": 9214
|
| 64509 |
+
},
|
| 64510 |
+
{
|
| 64511 |
+
"epoch": 10.495726495726496,
|
| 64512 |
+
"grad_norm": 0.1604098081588745,
|
| 64513 |
+
"learning_rate": 2.4615632701096847e-05,
|
| 64514 |
+
"loss": 0.8559,
|
| 64515 |
+
"step": 9215
|
| 64516 |
+
},
|
| 64517 |
+
{
|
| 64518 |
+
"epoch": 10.496866096866096,
|
| 64519 |
+
"grad_norm": 0.26704758405685425,
|
| 64520 |
+
"learning_rate": 2.4610974077370867e-05,
|
| 64521 |
+
"loss": 0.4808,
|
| 64522 |
+
"step": 9216
|
| 64523 |
+
},
|
| 64524 |
+
{
|
| 64525 |
+
"epoch": 10.498005698005699,
|
| 64526 |
+
"grad_norm": 0.2803448438644409,
|
| 64527 |
+
"learning_rate": 2.4606315467156827e-05,
|
| 64528 |
+
"loss": 0.398,
|
| 64529 |
+
"step": 9217
|
| 64530 |
+
},
|
| 64531 |
+
{
|
| 64532 |
+
"epoch": 10.4991452991453,
|
| 64533 |
+
"grad_norm": 0.26626428961753845,
|
| 64534 |
+
"learning_rate": 2.4601656870616545e-05,
|
| 64535 |
+
"loss": 0.656,
|
| 64536 |
+
"step": 9218
|
| 64537 |
+
},
|
| 64538 |
+
{
|
| 64539 |
+
"epoch": 10.5002849002849,
|
| 64540 |
+
"grad_norm": 0.18743109703063965,
|
| 64541 |
+
"learning_rate": 2.4596998287911804e-05,
|
| 64542 |
+
"loss": 0.9127,
|
| 64543 |
+
"step": 9219
|
| 64544 |
+
},
|
| 64545 |
+
{
|
| 64546 |
+
"epoch": 10.501424501424502,
|
| 64547 |
+
"grad_norm": 0.18646414577960968,
|
| 64548 |
+
"learning_rate": 2.459233971920443e-05,
|
| 64549 |
+
"loss": 0.7461,
|
| 64550 |
+
"step": 9220
|
| 64551 |
+
},
|
| 64552 |
+
{
|
| 64553 |
+
"epoch": 10.502564102564103,
|
| 64554 |
+
"grad_norm": 0.19627082347869873,
|
| 64555 |
+
"learning_rate": 2.458768116465621e-05,
|
| 64556 |
+
"loss": 0.7265,
|
| 64557 |
+
"step": 9221
|
| 64558 |
+
},
|
| 64559 |
+
{
|
| 64560 |
+
"epoch": 10.503703703703703,
|
| 64561 |
+
"grad_norm": 0.2861216068267822,
|
| 64562 |
+
"learning_rate": 2.4583022624428967e-05,
|
| 64563 |
+
"loss": 0.4033,
|
| 64564 |
+
"step": 9222
|
| 64565 |
+
},
|
| 64566 |
+
{
|
| 64567 |
+
"epoch": 10.504843304843305,
|
| 64568 |
+
"grad_norm": 0.2405533343553543,
|
| 64569 |
+
"learning_rate": 2.4578364098684488e-05,
|
| 64570 |
+
"loss": 0.5667,
|
| 64571 |
+
"step": 9223
|
| 64572 |
+
},
|
| 64573 |
+
{
|
| 64574 |
+
"epoch": 10.505982905982906,
|
| 64575 |
+
"grad_norm": 0.22812910377979279,
|
| 64576 |
+
"learning_rate": 2.4573705587584586e-05,
|
| 64577 |
+
"loss": 0.7377,
|
| 64578 |
+
"step": 9224
|
| 64579 |
+
},
|
| 64580 |
+
{
|
| 64581 |
+
"epoch": 10.507122507122507,
|
| 64582 |
+
"grad_norm": 0.21617454290390015,
|
| 64583 |
+
"learning_rate": 2.456904709129106e-05,
|
| 64584 |
+
"loss": 0.4541,
|
| 64585 |
+
"step": 9225
|
| 64586 |
+
},
|
| 64587 |
+
{
|
| 64588 |
+
"epoch": 10.508262108262109,
|
| 64589 |
+
"grad_norm": 0.1916038990020752,
|
| 64590 |
+
"learning_rate": 2.4564388609965717e-05,
|
| 64591 |
+
"loss": 0.7945,
|
| 64592 |
+
"step": 9226
|
| 64593 |
+
},
|
| 64594 |
+
{
|
| 64595 |
+
"epoch": 10.50940170940171,
|
| 64596 |
+
"grad_norm": 0.23479774594306946,
|
| 64597 |
+
"learning_rate": 2.4559730143770345e-05,
|
| 64598 |
+
"loss": 0.6864,
|
| 64599 |
+
"step": 9227
|
| 64600 |
+
},
|
| 64601 |
+
{
|
| 64602 |
+
"epoch": 10.51054131054131,
|
| 64603 |
+
"grad_norm": 0.2074567824602127,
|
| 64604 |
+
"learning_rate": 2.455507169286676e-05,
|
| 64605 |
+
"loss": 0.7917,
|
| 64606 |
+
"step": 9228
|
| 64607 |
+
},
|
| 64608 |
+
{
|
| 64609 |
+
"epoch": 10.511680911680912,
|
| 64610 |
+
"grad_norm": 0.23633286356925964,
|
| 64611 |
+
"learning_rate": 2.455041325741676e-05,
|
| 64612 |
+
"loss": 0.6294,
|
| 64613 |
+
"step": 9229
|
| 64614 |
+
},
|
| 64615 |
+
{
|
| 64616 |
+
"epoch": 10.512820512820513,
|
| 64617 |
+
"grad_norm": 0.19726577401161194,
|
| 64618 |
+
"learning_rate": 2.454575483758215e-05,
|
| 64619 |
+
"loss": 0.7558,
|
| 64620 |
+
"step": 9230
|
| 64621 |
+
},
|
| 64622 |
+
{
|
| 64623 |
+
"epoch": 10.513960113960113,
|
| 64624 |
+
"grad_norm": 0.18224595487117767,
|
| 64625 |
+
"learning_rate": 2.4541096433524717e-05,
|
| 64626 |
+
"loss": 0.9511,
|
| 64627 |
+
"step": 9231
|
| 64628 |
+
},
|
| 64629 |
+
{
|
| 64630 |
+
"epoch": 10.515099715099716,
|
| 64631 |
+
"grad_norm": 0.26174822449684143,
|
| 64632 |
+
"learning_rate": 2.453643804540627e-05,
|
| 64633 |
+
"loss": 0.6631,
|
| 64634 |
+
"step": 9232
|
| 64635 |
+
},
|
| 64636 |
+
{
|
| 64637 |
+
"epoch": 10.516239316239316,
|
| 64638 |
+
"grad_norm": 0.25406506657600403,
|
| 64639 |
+
"learning_rate": 2.45317796733886e-05,
|
| 64640 |
+
"loss": 0.5523,
|
| 64641 |
+
"step": 9233
|
| 64642 |
+
},
|
| 64643 |
+
{
|
| 64644 |
+
"epoch": 10.517378917378917,
|
| 64645 |
+
"grad_norm": 0.16637858748435974,
|
| 64646 |
+
"learning_rate": 2.4527121317633518e-05,
|
| 64647 |
+
"loss": 0.6464,
|
| 64648 |
+
"step": 9234
|
| 64649 |
+
},
|
| 64650 |
+
{
|
| 64651 |
+
"epoch": 10.518518518518519,
|
| 64652 |
+
"grad_norm": 0.2870800495147705,
|
| 64653 |
+
"learning_rate": 2.4522462978302807e-05,
|
| 64654 |
+
"loss": 0.6354,
|
| 64655 |
+
"step": 9235
|
| 64656 |
+
},
|
| 64657 |
+
{
|
| 64658 |
+
"epoch": 10.51965811965812,
|
| 64659 |
+
"grad_norm": 0.22352823615074158,
|
| 64660 |
+
"learning_rate": 2.4517804655558275e-05,
|
| 64661 |
+
"loss": 0.5128,
|
| 64662 |
+
"step": 9236
|
| 64663 |
+
},
|
| 64664 |
+
{
|
| 64665 |
+
"epoch": 10.52079772079772,
|
| 64666 |
+
"grad_norm": 0.2656743824481964,
|
| 64667 |
+
"learning_rate": 2.451314634956171e-05,
|
| 64668 |
+
"loss": 0.653,
|
| 64669 |
+
"step": 9237
|
| 64670 |
+
},
|
| 64671 |
+
{
|
| 64672 |
+
"epoch": 10.521937321937322,
|
| 64673 |
+
"grad_norm": 0.21166376769542694,
|
| 64674 |
+
"learning_rate": 2.4508488060474898e-05,
|
| 64675 |
+
"loss": 0.8678,
|
| 64676 |
+
"step": 9238
|
| 64677 |
+
},
|
| 64678 |
+
{
|
| 64679 |
+
"epoch": 10.523076923076923,
|
| 64680 |
+
"grad_norm": 0.21826742589473724,
|
| 64681 |
+
"learning_rate": 2.4503829788459664e-05,
|
| 64682 |
+
"loss": 0.6687,
|
| 64683 |
+
"step": 9239
|
| 64684 |
+
},
|
| 64685 |
+
{
|
| 64686 |
+
"epoch": 10.524216524216524,
|
| 64687 |
+
"grad_norm": 0.20269319415092468,
|
| 64688 |
+
"learning_rate": 2.4499171533677782e-05,
|
| 64689 |
+
"loss": 0.8563,
|
| 64690 |
+
"step": 9240
|
| 64691 |
+
},
|
| 64692 |
+
{
|
| 64693 |
+
"epoch": 10.525356125356126,
|
| 64694 |
+
"grad_norm": 0.20262055099010468,
|
| 64695 |
+
"learning_rate": 2.4494513296291054e-05,
|
| 64696 |
+
"loss": 0.625,
|
| 64697 |
+
"step": 9241
|
| 64698 |
+
},
|
| 64699 |
+
{
|
| 64700 |
+
"epoch": 10.526495726495726,
|
| 64701 |
+
"grad_norm": 0.218480184674263,
|
| 64702 |
+
"learning_rate": 2.4489855076461262e-05,
|
| 64703 |
+
"loss": 0.8716,
|
| 64704 |
+
"step": 9242
|
| 64705 |
+
},
|
| 64706 |
+
{
|
| 64707 |
+
"epoch": 10.527635327635327,
|
| 64708 |
+
"grad_norm": 0.23494336009025574,
|
| 64709 |
+
"learning_rate": 2.4485196874350213e-05,
|
| 64710 |
+
"loss": 0.6349,
|
| 64711 |
+
"step": 9243
|
| 64712 |
+
},
|
| 64713 |
+
{
|
| 64714 |
+
"epoch": 10.52877492877493,
|
| 64715 |
+
"grad_norm": 0.19913607835769653,
|
| 64716 |
+
"learning_rate": 2.4480538690119685e-05,
|
| 64717 |
+
"loss": 0.4072,
|
| 64718 |
+
"step": 9244
|
| 64719 |
+
},
|
| 64720 |
+
{
|
| 64721 |
+
"epoch": 10.52991452991453,
|
| 64722 |
+
"grad_norm": 0.25605538487434387,
|
| 64723 |
+
"learning_rate": 2.4475880523931487e-05,
|
| 64724 |
+
"loss": 0.5784,
|
| 64725 |
+
"step": 9245
|
| 64726 |
+
},
|
| 64727 |
+
{
|
| 64728 |
+
"epoch": 10.53105413105413,
|
| 64729 |
+
"grad_norm": 0.23360183835029602,
|
| 64730 |
+
"learning_rate": 2.447122237594739e-05,
|
| 64731 |
+
"loss": 0.5614,
|
| 64732 |
+
"step": 9246
|
| 64733 |
+
},
|
| 64734 |
+
{
|
| 64735 |
+
"epoch": 10.532193732193733,
|
| 64736 |
+
"grad_norm": 0.22565987706184387,
|
| 64737 |
+
"learning_rate": 2.4466564246329197e-05,
|
| 64738 |
+
"loss": 0.6422,
|
| 64739 |
+
"step": 9247
|
| 64740 |
+
},
|
| 64741 |
+
{
|
| 64742 |
+
"epoch": 10.533333333333333,
|
| 64743 |
+
"grad_norm": 0.2499256432056427,
|
| 64744 |
+
"learning_rate": 2.4461906135238693e-05,
|
| 64745 |
+
"loss": 0.664,
|
| 64746 |
+
"step": 9248
|
| 64747 |
+
},
|
| 64748 |
+
{
|
| 64749 |
+
"epoch": 10.534472934472934,
|
| 64750 |
+
"grad_norm": 0.29015761613845825,
|
| 64751 |
+
"learning_rate": 2.4457248042837663e-05,
|
| 64752 |
+
"loss": 0.4316,
|
| 64753 |
+
"step": 9249
|
| 64754 |
+
},
|
| 64755 |
+
{
|
| 64756 |
+
"epoch": 10.535612535612536,
|
| 64757 |
+
"grad_norm": 0.20617923140525818,
|
| 64758 |
+
"learning_rate": 2.4452589969287913e-05,
|
| 64759 |
+
"loss": 0.7275,
|
| 64760 |
+
"step": 9250
|
| 64761 |
+
},
|
| 64762 |
+
{
|
| 64763 |
+
"epoch": 10.536752136752137,
|
| 64764 |
+
"grad_norm": 0.291335791349411,
|
| 64765 |
+
"learning_rate": 2.4447931914751214e-05,
|
| 64766 |
+
"loss": 0.6367,
|
| 64767 |
+
"step": 9251
|
| 64768 |
+
},
|
| 64769 |
+
{
|
| 64770 |
+
"epoch": 10.537891737891737,
|
| 64771 |
+
"grad_norm": 0.18563072383403778,
|
| 64772 |
+
"learning_rate": 2.444327387938936e-05,
|
| 64773 |
+
"loss": 0.8131,
|
| 64774 |
+
"step": 9252
|
| 64775 |
+
},
|
| 64776 |
+
{
|
| 64777 |
+
"epoch": 10.53903133903134,
|
| 64778 |
+
"grad_norm": 0.17296385765075684,
|
| 64779 |
+
"learning_rate": 2.443861586336413e-05,
|
| 64780 |
+
"loss": 0.7935,
|
| 64781 |
+
"step": 9253
|
| 64782 |
+
},
|
| 64783 |
+
{
|
| 64784 |
+
"epoch": 10.54017094017094,
|
| 64785 |
+
"grad_norm": 0.1931563913822174,
|
| 64786 |
+
"learning_rate": 2.4433957866837322e-05,
|
| 64787 |
+
"loss": 0.7372,
|
| 64788 |
+
"step": 9254
|
| 64789 |
+
},
|
| 64790 |
+
{
|
| 64791 |
+
"epoch": 10.54131054131054,
|
| 64792 |
+
"grad_norm": 0.22677938640117645,
|
| 64793 |
+
"learning_rate": 2.4429299889970708e-05,
|
| 64794 |
+
"loss": 0.7651,
|
| 64795 |
+
"step": 9255
|
| 64796 |
+
},
|
| 64797 |
+
{
|
| 64798 |
+
"epoch": 10.542450142450143,
|
| 64799 |
+
"grad_norm": 0.20666667819023132,
|
| 64800 |
+
"learning_rate": 2.4424641932926085e-05,
|
| 64801 |
+
"loss": 0.6628,
|
| 64802 |
+
"step": 9256
|
| 64803 |
+
},
|
| 64804 |
+
{
|
| 64805 |
+
"epoch": 10.543589743589743,
|
| 64806 |
+
"grad_norm": 0.2504830062389374,
|
| 64807 |
+
"learning_rate": 2.4419983995865222e-05,
|
| 64808 |
+
"loss": 0.8023,
|
| 64809 |
+
"step": 9257
|
| 64810 |
+
},
|
| 64811 |
+
{
|
| 64812 |
+
"epoch": 10.544729344729344,
|
| 64813 |
+
"grad_norm": 0.18859297037124634,
|
| 64814 |
+
"learning_rate": 2.441532607894992e-05,
|
| 64815 |
+
"loss": 0.7016,
|
| 64816 |
+
"step": 9258
|
| 64817 |
+
},
|
| 64818 |
+
{
|
| 64819 |
+
"epoch": 10.545868945868946,
|
| 64820 |
+
"grad_norm": 0.19908884167671204,
|
| 64821 |
+
"learning_rate": 2.441066818234194e-05,
|
| 64822 |
+
"loss": 0.7568,
|
| 64823 |
+
"step": 9259
|
| 64824 |
+
},
|
| 64825 |
+
{
|
| 64826 |
+
"epoch": 10.547008547008547,
|
| 64827 |
+
"grad_norm": 0.23446115851402283,
|
| 64828 |
+
"learning_rate": 2.4406010306203068e-05,
|
| 64829 |
+
"loss": 0.5168,
|
| 64830 |
+
"step": 9260
|
| 64831 |
+
},
|
| 64832 |
+
{
|
| 64833 |
+
"epoch": 10.548148148148147,
|
| 64834 |
+
"grad_norm": 0.21079429984092712,
|
| 64835 |
+
"learning_rate": 2.440135245069511e-05,
|
| 64836 |
+
"loss": 0.8225,
|
| 64837 |
+
"step": 9261
|
| 64838 |
+
},
|
| 64839 |
+
{
|
| 64840 |
+
"epoch": 10.54928774928775,
|
| 64841 |
+
"grad_norm": 0.24125830829143524,
|
| 64842 |
+
"learning_rate": 2.4396694615979815e-05,
|
| 64843 |
+
"loss": 0.6538,
|
| 64844 |
+
"step": 9262
|
| 64845 |
+
},
|
| 64846 |
+
{
|
| 64847 |
+
"epoch": 10.55042735042735,
|
| 64848 |
+
"grad_norm": 0.2429075837135315,
|
| 64849 |
+
"learning_rate": 2.4392036802218983e-05,
|
| 64850 |
+
"loss": 0.5568,
|
| 64851 |
+
"step": 9263
|
| 64852 |
+
},
|
| 64853 |
+
{
|
| 64854 |
+
"epoch": 10.55156695156695,
|
| 64855 |
+
"grad_norm": 0.177407369017601,
|
| 64856 |
+
"learning_rate": 2.438737900957438e-05,
|
| 64857 |
+
"loss": 0.8232,
|
| 64858 |
+
"step": 9264
|
| 64859 |
+
},
|
| 64860 |
+
{
|
| 64861 |
+
"epoch": 10.552706552706553,
|
| 64862 |
+
"grad_norm": 0.2627646028995514,
|
| 64863 |
+
"learning_rate": 2.4382721238207796e-05,
|
| 64864 |
+
"loss": 0.5178,
|
| 64865 |
+
"step": 9265
|
| 64866 |
+
},
|
| 64867 |
+
{
|
| 64868 |
+
"epoch": 10.553846153846154,
|
| 64869 |
+
"grad_norm": 0.26185911893844604,
|
| 64870 |
+
"learning_rate": 2.4378063488280994e-05,
|
| 64871 |
+
"loss": 0.4895,
|
| 64872 |
+
"step": 9266
|
| 64873 |
+
},
|
| 64874 |
+
{
|
| 64875 |
+
"epoch": 10.554985754985754,
|
| 64876 |
+
"grad_norm": 0.20316262543201447,
|
| 64877 |
+
"learning_rate": 2.437340575995576e-05,
|
| 64878 |
+
"loss": 0.721,
|
| 64879 |
+
"step": 9267
|
| 64880 |
+
},
|
| 64881 |
+
{
|
| 64882 |
+
"epoch": 10.556125356125357,
|
| 64883 |
+
"grad_norm": 0.26230934262275696,
|
| 64884 |
+
"learning_rate": 2.4368748053393868e-05,
|
| 64885 |
+
"loss": 0.6229,
|
| 64886 |
+
"step": 9268
|
| 64887 |
+
},
|
| 64888 |
+
{
|
| 64889 |
+
"epoch": 10.557264957264957,
|
| 64890 |
+
"grad_norm": 0.19705653190612793,
|
| 64891 |
+
"learning_rate": 2.4364090368757093e-05,
|
| 64892 |
+
"loss": 0.73,
|
| 64893 |
+
"step": 9269
|
| 64894 |
+
},
|
| 64895 |
+
{
|
| 64896 |
+
"epoch": 10.558404558404558,
|
| 64897 |
+
"grad_norm": 0.24998103082180023,
|
| 64898 |
+
"learning_rate": 2.43594327062072e-05,
|
| 64899 |
+
"loss": 0.6415,
|
| 64900 |
+
"step": 9270
|
| 64901 |
+
},
|
| 64902 |
+
{
|
| 64903 |
+
"epoch": 10.55954415954416,
|
| 64904 |
+
"grad_norm": 0.19474878907203674,
|
| 64905 |
+
"learning_rate": 2.4354775065905968e-05,
|
| 64906 |
+
"loss": 0.6854,
|
| 64907 |
+
"step": 9271
|
| 64908 |
+
},
|
| 64909 |
+
{
|
| 64910 |
+
"epoch": 10.56068376068376,
|
| 64911 |
+
"grad_norm": 0.23544877767562866,
|
| 64912 |
+
"learning_rate": 2.435011744801518e-05,
|
| 64913 |
+
"loss": 0.7466,
|
| 64914 |
+
"step": 9272
|
| 64915 |
+
},
|
| 64916 |
+
{
|
| 64917 |
+
"epoch": 10.561823361823361,
|
| 64918 |
+
"grad_norm": 0.22600121796131134,
|
| 64919 |
+
"learning_rate": 2.4345459852696603e-05,
|
| 64920 |
+
"loss": 0.3899,
|
| 64921 |
+
"step": 9273
|
| 64922 |
+
},
|
| 64923 |
+
{
|
| 64924 |
+
"epoch": 10.562962962962963,
|
| 64925 |
+
"grad_norm": 0.25168585777282715,
|
| 64926 |
+
"learning_rate": 2.4340802280112e-05,
|
| 64927 |
+
"loss": 0.6318,
|
| 64928 |
+
"step": 9274
|
| 64929 |
+
},
|
| 64930 |
+
{
|
| 64931 |
+
"epoch": 10.564102564102564,
|
| 64932 |
+
"grad_norm": 0.19967123866081238,
|
| 64933 |
+
"learning_rate": 2.4336144730423154e-05,
|
| 64934 |
+
"loss": 0.5816,
|
| 64935 |
+
"step": 9275
|
| 64936 |
+
},
|
| 64937 |
+
{
|
| 64938 |
+
"epoch": 10.565242165242164,
|
| 64939 |
+
"grad_norm": 0.18906304240226746,
|
| 64940 |
+
"learning_rate": 2.433148720379182e-05,
|
| 64941 |
+
"loss": 0.7827,
|
| 64942 |
+
"step": 9276
|
| 64943 |
+
},
|
| 64944 |
+
{
|
| 64945 |
+
"epoch": 10.566381766381767,
|
| 64946 |
+
"grad_norm": 0.2090078741312027,
|
| 64947 |
+
"learning_rate": 2.432682970037978e-05,
|
| 64948 |
+
"loss": 0.679,
|
| 64949 |
+
"step": 9277
|
| 64950 |
+
},
|
| 64951 |
+
{
|
| 64952 |
+
"epoch": 10.567521367521367,
|
| 64953 |
+
"grad_norm": 0.21482527256011963,
|
| 64954 |
+
"learning_rate": 2.432217222034879e-05,
|
| 64955 |
+
"loss": 0.7569,
|
| 64956 |
+
"step": 9278
|
| 64957 |
+
},
|
| 64958 |
+
{
|
| 64959 |
+
"epoch": 10.568660968660968,
|
| 64960 |
+
"grad_norm": 0.2805091440677643,
|
| 64961 |
+
"learning_rate": 2.431751476386063e-05,
|
| 64962 |
+
"loss": 0.5128,
|
| 64963 |
+
"step": 9279
|
| 64964 |
+
},
|
| 64965 |
+
{
|
| 64966 |
+
"epoch": 10.56980056980057,
|
| 64967 |
+
"grad_norm": 0.18089546263217926,
|
| 64968 |
+
"learning_rate": 2.4312857331077052e-05,
|
| 64969 |
+
"loss": 1.0565,
|
| 64970 |
+
"step": 9280
|
| 64971 |
+
},
|
| 64972 |
+
{
|
| 64973 |
+
"epoch": 10.57094017094017,
|
| 64974 |
+
"grad_norm": 0.202863410115242,
|
| 64975 |
+
"learning_rate": 2.4308199922159833e-05,
|
| 64976 |
+
"loss": 0.6263,
|
| 64977 |
+
"step": 9281
|
| 64978 |
+
},
|
| 64979 |
+
{
|
| 64980 |
+
"epoch": 10.572079772079771,
|
| 64981 |
+
"grad_norm": 0.2146240621805191,
|
| 64982 |
+
"learning_rate": 2.4303542537270725e-05,
|
| 64983 |
+
"loss": 0.7396,
|
| 64984 |
+
"step": 9282
|
| 64985 |
+
},
|
| 64986 |
+
{
|
| 64987 |
+
"epoch": 10.573219373219374,
|
| 64988 |
+
"grad_norm": 0.23256784677505493,
|
| 64989 |
+
"learning_rate": 2.4298885176571503e-05,
|
| 64990 |
+
"loss": 0.7889,
|
| 64991 |
+
"step": 9283
|
| 64992 |
+
},
|
| 64993 |
+
{
|
| 64994 |
+
"epoch": 10.574358974358974,
|
| 64995 |
+
"grad_norm": 0.15683580935001373,
|
| 64996 |
+
"learning_rate": 2.4294227840223933e-05,
|
| 64997 |
+
"loss": 0.7822,
|
| 64998 |
+
"step": 9284
|
| 64999 |
+
},
|
| 65000 |
+
{
|
| 65001 |
+
"epoch": 10.575498575498575,
|
| 65002 |
+
"grad_norm": 0.23500467836856842,
|
| 65003 |
+
"learning_rate": 2.4289570528389764e-05,
|
| 65004 |
+
"loss": 0.4418,
|
| 65005 |
+
"step": 9285
|
| 65006 |
+
},
|
| 65007 |
+
{
|
| 65008 |
+
"epoch": 10.576638176638177,
|
| 65009 |
+
"grad_norm": 0.1923016458749771,
|
| 65010 |
+
"learning_rate": 2.4284913241230773e-05,
|
| 65011 |
+
"loss": 0.8286,
|
| 65012 |
+
"step": 9286
|
| 65013 |
+
},
|
| 65014 |
+
{
|
| 65015 |
+
"epoch": 10.577777777777778,
|
| 65016 |
+
"grad_norm": 0.20705291628837585,
|
| 65017 |
+
"learning_rate": 2.42802559789087e-05,
|
| 65018 |
+
"loss": 0.6979,
|
| 65019 |
+
"step": 9287
|
| 65020 |
+
},
|
| 65021 |
+
{
|
| 65022 |
+
"epoch": 10.578917378917378,
|
| 65023 |
+
"grad_norm": 0.2262626737356186,
|
| 65024 |
+
"learning_rate": 2.427559874158533e-05,
|
| 65025 |
+
"loss": 0.6143,
|
| 65026 |
+
"step": 9288
|
| 65027 |
+
},
|
| 65028 |
+
{
|
| 65029 |
+
"epoch": 10.58005698005698,
|
| 65030 |
+
"grad_norm": 0.16545400023460388,
|
| 65031 |
+
"learning_rate": 2.4270941529422396e-05,
|
| 65032 |
+
"loss": 0.81,
|
| 65033 |
+
"step": 9289
|
| 65034 |
+
},
|
| 65035 |
+
{
|
| 65036 |
+
"epoch": 10.581196581196581,
|
| 65037 |
+
"grad_norm": 0.22591204941272736,
|
| 65038 |
+
"learning_rate": 2.4266284342581677e-05,
|
| 65039 |
+
"loss": 0.6341,
|
| 65040 |
+
"step": 9290
|
| 65041 |
+
},
|
| 65042 |
+
{
|
| 65043 |
+
"epoch": 10.582336182336181,
|
| 65044 |
+
"grad_norm": 0.2036348134279251,
|
| 65045 |
+
"learning_rate": 2.4261627181224914e-05,
|
| 65046 |
+
"loss": 0.6356,
|
| 65047 |
+
"step": 9291
|
| 65048 |
+
},
|
| 65049 |
+
{
|
| 65050 |
+
"epoch": 10.583475783475784,
|
| 65051 |
+
"grad_norm": 0.25399860739707947,
|
| 65052 |
+
"learning_rate": 2.4256970045513875e-05,
|
| 65053 |
+
"loss": 0.619,
|
| 65054 |
+
"step": 9292
|
| 65055 |
+
},
|
| 65056 |
+
{
|
| 65057 |
+
"epoch": 10.584615384615384,
|
| 65058 |
+
"grad_norm": 0.17429670691490173,
|
| 65059 |
+
"learning_rate": 2.42523129356103e-05,
|
| 65060 |
+
"loss": 0.759,
|
| 65061 |
+
"step": 9293
|
| 65062 |
+
},
|
| 65063 |
+
{
|
| 65064 |
+
"epoch": 10.585754985754985,
|
| 65065 |
+
"grad_norm": 0.22275413572788239,
|
| 65066 |
+
"learning_rate": 2.4247655851675953e-05,
|
| 65067 |
+
"loss": 0.6622,
|
| 65068 |
+
"step": 9294
|
| 65069 |
+
},
|
| 65070 |
+
{
|
| 65071 |
+
"epoch": 10.586894586894587,
|
| 65072 |
+
"grad_norm": 0.26823070645332336,
|
| 65073 |
+
"learning_rate": 2.42429987938726e-05,
|
| 65074 |
+
"loss": 0.3567,
|
| 65075 |
+
"step": 9295
|
| 65076 |
+
},
|
| 65077 |
+
{
|
| 65078 |
+
"epoch": 10.588034188034188,
|
| 65079 |
+
"grad_norm": 0.20424869656562805,
|
| 65080 |
+
"learning_rate": 2.423834176236197e-05,
|
| 65081 |
+
"loss": 0.7477,
|
| 65082 |
+
"step": 9296
|
| 65083 |
+
},
|
| 65084 |
+
{
|
| 65085 |
+
"epoch": 10.589173789173788,
|
| 65086 |
+
"grad_norm": 0.2231968194246292,
|
| 65087 |
+
"learning_rate": 2.4233684757305833e-05,
|
| 65088 |
+
"loss": 0.8067,
|
| 65089 |
+
"step": 9297
|
| 65090 |
+
},
|
| 65091 |
+
{
|
| 65092 |
+
"epoch": 10.59031339031339,
|
| 65093 |
+
"grad_norm": 0.19134043157100677,
|
| 65094 |
+
"learning_rate": 2.4229027778865923e-05,
|
| 65095 |
+
"loss": 0.7333,
|
| 65096 |
+
"step": 9298
|
| 65097 |
+
},
|
| 65098 |
+
{
|
| 65099 |
+
"epoch": 10.591452991452991,
|
| 65100 |
+
"grad_norm": 0.22105371952056885,
|
| 65101 |
+
"learning_rate": 2.4224370827204007e-05,
|
| 65102 |
+
"loss": 0.6057,
|
| 65103 |
+
"step": 9299
|
| 65104 |
+
},
|
| 65105 |
+
{
|
| 65106 |
+
"epoch": 10.592592592592592,
|
| 65107 |
+
"grad_norm": 0.17917677760124207,
|
| 65108 |
+
"learning_rate": 2.4219713902481818e-05,
|
| 65109 |
+
"loss": 0.7783,
|
| 65110 |
+
"step": 9300
|
| 65111 |
}
|
| 65112 |
],
|
| 65113 |
"logging_steps": 1,
|
|
|
|
| 65127 |
"attributes": {}
|
| 65128 |
}
|
| 65129 |
},
|
| 65130 |
+
"total_flos": 5.199984959844704e+19,
|
| 65131 |
"train_batch_size": 8,
|
| 65132 |
"trial_name": null,
|
| 65133 |
"trial_params": null
|