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 3900, 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:bd22a30a1a189e7fe5b982ca909b3851f37bdf9939c170f720df2f2a94c049a2
|
| 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 sha256:246bd678a3d1282fce4603684aa9c453b4e1db39a2dd6f4f312c9b1c9df987f1
|
| 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:de703555543612b196a9702c942d15b1285991804866807cc148de0aaff9a049
|
| 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": 4.
|
| 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,
|
|
@@ -25208,6 +25208,2106 @@
|
|
| 25208 |
"learning_rate": 4.644632102549956e-05,
|
| 25209 |
"loss": 0.8383,
|
| 25210 |
"step": 3600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25211 |
}
|
| 25212 |
],
|
| 25213 |
"logging_steps": 1,
|
|
@@ -25227,7 +27327,7 @@
|
|
| 25227 |
"attributes": {}
|
| 25228 |
}
|
| 25229 |
},
|
| 25230 |
-
"total_flos": 2.
|
| 25231 |
"train_batch_size": 8,
|
| 25232 |
"trial_name": null,
|
| 25233 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.442165242165242,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 25208 |
"learning_rate": 4.644632102549956e-05,
|
| 25209 |
"loss": 0.8383,
|
| 25210 |
"step": 3600
|
| 25211 |
+
},
|
| 25212 |
+
{
|
| 25213 |
+
"epoch": 4.101424501424502,
|
| 25214 |
+
"grad_norm": 0.13314323127269745,
|
| 25215 |
+
"learning_rate": 4.6443926321221886e-05,
|
| 25216 |
+
"loss": 0.9247,
|
| 25217 |
+
"step": 3601
|
| 25218 |
+
},
|
| 25219 |
+
{
|
| 25220 |
+
"epoch": 4.102564102564102,
|
| 25221 |
+
"grad_norm": 0.13570788502693176,
|
| 25222 |
+
"learning_rate": 4.644153087213768e-05,
|
| 25223 |
+
"loss": 0.9356,
|
| 25224 |
+
"step": 3602
|
| 25225 |
+
},
|
| 25226 |
+
{
|
| 25227 |
+
"epoch": 4.103703703703704,
|
| 25228 |
+
"grad_norm": 0.1606551706790924,
|
| 25229 |
+
"learning_rate": 4.6439134678330134e-05,
|
| 25230 |
+
"loss": 0.78,
|
| 25231 |
+
"step": 3603
|
| 25232 |
+
},
|
| 25233 |
+
{
|
| 25234 |
+
"epoch": 4.104843304843305,
|
| 25235 |
+
"grad_norm": 0.17509931325912476,
|
| 25236 |
+
"learning_rate": 4.643673773988249e-05,
|
| 25237 |
+
"loss": 0.8968,
|
| 25238 |
+
"step": 3604
|
| 25239 |
+
},
|
| 25240 |
+
{
|
| 25241 |
+
"epoch": 4.105982905982906,
|
| 25242 |
+
"grad_norm": 0.19881106913089752,
|
| 25243 |
+
"learning_rate": 4.643434005687799e-05,
|
| 25244 |
+
"loss": 0.6532,
|
| 25245 |
+
"step": 3605
|
| 25246 |
+
},
|
| 25247 |
+
{
|
| 25248 |
+
"epoch": 4.107122507122507,
|
| 25249 |
+
"grad_norm": 0.14632968604564667,
|
| 25250 |
+
"learning_rate": 4.643194162939992e-05,
|
| 25251 |
+
"loss": 0.9583,
|
| 25252 |
+
"step": 3606
|
| 25253 |
+
},
|
| 25254 |
+
{
|
| 25255 |
+
"epoch": 4.1082621082621085,
|
| 25256 |
+
"grad_norm": 0.15079665184020996,
|
| 25257 |
+
"learning_rate": 4.642954245753157e-05,
|
| 25258 |
+
"loss": 0.8201,
|
| 25259 |
+
"step": 3607
|
| 25260 |
+
},
|
| 25261 |
+
{
|
| 25262 |
+
"epoch": 4.109401709401709,
|
| 25263 |
+
"grad_norm": 0.1575961709022522,
|
| 25264 |
+
"learning_rate": 4.642714254135628e-05,
|
| 25265 |
+
"loss": 0.6698,
|
| 25266 |
+
"step": 3608
|
| 25267 |
+
},
|
| 25268 |
+
{
|
| 25269 |
+
"epoch": 4.1105413105413104,
|
| 25270 |
+
"grad_norm": 0.18284007906913757,
|
| 25271 |
+
"learning_rate": 4.642474188095741e-05,
|
| 25272 |
+
"loss": 0.6156,
|
| 25273 |
+
"step": 3609
|
| 25274 |
+
},
|
| 25275 |
+
{
|
| 25276 |
+
"epoch": 4.111680911680912,
|
| 25277 |
+
"grad_norm": 0.16812333464622498,
|
| 25278 |
+
"learning_rate": 4.6422340476418344e-05,
|
| 25279 |
+
"loss": 0.861,
|
| 25280 |
+
"step": 3610
|
| 25281 |
+
},
|
| 25282 |
+
{
|
| 25283 |
+
"epoch": 4.112820512820512,
|
| 25284 |
+
"grad_norm": 0.1552661657333374,
|
| 25285 |
+
"learning_rate": 4.641993832782246e-05,
|
| 25286 |
+
"loss": 0.6791,
|
| 25287 |
+
"step": 3611
|
| 25288 |
+
},
|
| 25289 |
+
{
|
| 25290 |
+
"epoch": 4.113960113960114,
|
| 25291 |
+
"grad_norm": 0.16001765429973602,
|
| 25292 |
+
"learning_rate": 4.6417535435253236e-05,
|
| 25293 |
+
"loss": 0.7138,
|
| 25294 |
+
"step": 3612
|
| 25295 |
+
},
|
| 25296 |
+
{
|
| 25297 |
+
"epoch": 4.115099715099715,
|
| 25298 |
+
"grad_norm": 0.13813526928424835,
|
| 25299 |
+
"learning_rate": 4.6415131798794096e-05,
|
| 25300 |
+
"loss": 0.9783,
|
| 25301 |
+
"step": 3613
|
| 25302 |
+
},
|
| 25303 |
+
{
|
| 25304 |
+
"epoch": 4.116239316239316,
|
| 25305 |
+
"grad_norm": 0.14909638464450836,
|
| 25306 |
+
"learning_rate": 4.641272741852853e-05,
|
| 25307 |
+
"loss": 0.9292,
|
| 25308 |
+
"step": 3614
|
| 25309 |
+
},
|
| 25310 |
+
{
|
| 25311 |
+
"epoch": 4.117378917378917,
|
| 25312 |
+
"grad_norm": 0.15766140818595886,
|
| 25313 |
+
"learning_rate": 4.641032229454007e-05,
|
| 25314 |
+
"loss": 0.876,
|
| 25315 |
+
"step": 3615
|
| 25316 |
+
},
|
| 25317 |
+
{
|
| 25318 |
+
"epoch": 4.118518518518519,
|
| 25319 |
+
"grad_norm": 0.1870744526386261,
|
| 25320 |
+
"learning_rate": 4.640791642691223e-05,
|
| 25321 |
+
"loss": 0.7223,
|
| 25322 |
+
"step": 3616
|
| 25323 |
+
},
|
| 25324 |
+
{
|
| 25325 |
+
"epoch": 4.119658119658119,
|
| 25326 |
+
"grad_norm": 0.18714767694473267,
|
| 25327 |
+
"learning_rate": 4.640550981572858e-05,
|
| 25328 |
+
"loss": 0.6913,
|
| 25329 |
+
"step": 3617
|
| 25330 |
+
},
|
| 25331 |
+
{
|
| 25332 |
+
"epoch": 4.120797720797721,
|
| 25333 |
+
"grad_norm": 0.16612930595874786,
|
| 25334 |
+
"learning_rate": 4.640310246107271e-05,
|
| 25335 |
+
"loss": 0.9073,
|
| 25336 |
+
"step": 3618
|
| 25337 |
+
},
|
| 25338 |
+
{
|
| 25339 |
+
"epoch": 4.121937321937322,
|
| 25340 |
+
"grad_norm": 0.19368138909339905,
|
| 25341 |
+
"learning_rate": 4.640069436302823e-05,
|
| 25342 |
+
"loss": 0.6559,
|
| 25343 |
+
"step": 3619
|
| 25344 |
+
},
|
| 25345 |
+
{
|
| 25346 |
+
"epoch": 4.123076923076923,
|
| 25347 |
+
"grad_norm": 0.16957665979862213,
|
| 25348 |
+
"learning_rate": 4.6398285521678795e-05,
|
| 25349 |
+
"loss": 0.7556,
|
| 25350 |
+
"step": 3620
|
| 25351 |
+
},
|
| 25352 |
+
{
|
| 25353 |
+
"epoch": 4.124216524216524,
|
| 25354 |
+
"grad_norm": 0.14673933386802673,
|
| 25355 |
+
"learning_rate": 4.639587593710805e-05,
|
| 25356 |
+
"loss": 0.8789,
|
| 25357 |
+
"step": 3621
|
| 25358 |
+
},
|
| 25359 |
+
{
|
| 25360 |
+
"epoch": 4.1253561253561255,
|
| 25361 |
+
"grad_norm": 0.1646455079317093,
|
| 25362 |
+
"learning_rate": 4.639346560939969e-05,
|
| 25363 |
+
"loss": 0.7582,
|
| 25364 |
+
"step": 3622
|
| 25365 |
+
},
|
| 25366 |
+
{
|
| 25367 |
+
"epoch": 4.126495726495726,
|
| 25368 |
+
"grad_norm": 0.1604212373495102,
|
| 25369 |
+
"learning_rate": 4.6391054538637444e-05,
|
| 25370 |
+
"loss": 0.8656,
|
| 25371 |
+
"step": 3623
|
| 25372 |
+
},
|
| 25373 |
+
{
|
| 25374 |
+
"epoch": 4.1276353276353275,
|
| 25375 |
+
"grad_norm": 0.17970581352710724,
|
| 25376 |
+
"learning_rate": 4.638864272490505e-05,
|
| 25377 |
+
"loss": 0.7821,
|
| 25378 |
+
"step": 3624
|
| 25379 |
+
},
|
| 25380 |
+
{
|
| 25381 |
+
"epoch": 4.128774928774929,
|
| 25382 |
+
"grad_norm": 0.17448319494724274,
|
| 25383 |
+
"learning_rate": 4.6386230168286265e-05,
|
| 25384 |
+
"loss": 0.841,
|
| 25385 |
+
"step": 3625
|
| 25386 |
+
},
|
| 25387 |
+
{
|
| 25388 |
+
"epoch": 4.12991452991453,
|
| 25389 |
+
"grad_norm": 0.15706060826778412,
|
| 25390 |
+
"learning_rate": 4.63838168688649e-05,
|
| 25391 |
+
"loss": 0.954,
|
| 25392 |
+
"step": 3626
|
| 25393 |
+
},
|
| 25394 |
+
{
|
| 25395 |
+
"epoch": 4.131054131054131,
|
| 25396 |
+
"grad_norm": 0.12947851419448853,
|
| 25397 |
+
"learning_rate": 4.638140282672477e-05,
|
| 25398 |
+
"loss": 1.0501,
|
| 25399 |
+
"step": 3627
|
| 25400 |
+
},
|
| 25401 |
+
{
|
| 25402 |
+
"epoch": 4.132193732193732,
|
| 25403 |
+
"grad_norm": 0.14992794394493103,
|
| 25404 |
+
"learning_rate": 4.6378988041949725e-05,
|
| 25405 |
+
"loss": 0.8091,
|
| 25406 |
+
"step": 3628
|
| 25407 |
+
},
|
| 25408 |
+
{
|
| 25409 |
+
"epoch": 4.133333333333334,
|
| 25410 |
+
"grad_norm": 0.16071423888206482,
|
| 25411 |
+
"learning_rate": 4.6376572514623625e-05,
|
| 25412 |
+
"loss": 0.8783,
|
| 25413 |
+
"step": 3629
|
| 25414 |
+
},
|
| 25415 |
+
{
|
| 25416 |
+
"epoch": 4.134472934472934,
|
| 25417 |
+
"grad_norm": 0.13396671414375305,
|
| 25418 |
+
"learning_rate": 4.6374156244830374e-05,
|
| 25419 |
+
"loss": 0.8796,
|
| 25420 |
+
"step": 3630
|
| 25421 |
+
},
|
| 25422 |
+
{
|
| 25423 |
+
"epoch": 4.135612535612536,
|
| 25424 |
+
"grad_norm": 0.13779418170452118,
|
| 25425 |
+
"learning_rate": 4.6371739232653905e-05,
|
| 25426 |
+
"loss": 0.9137,
|
| 25427 |
+
"step": 3631
|
| 25428 |
+
},
|
| 25429 |
+
{
|
| 25430 |
+
"epoch": 4.136752136752137,
|
| 25431 |
+
"grad_norm": 0.17061258852481842,
|
| 25432 |
+
"learning_rate": 4.636932147817816e-05,
|
| 25433 |
+
"loss": 0.7282,
|
| 25434 |
+
"step": 3632
|
| 25435 |
+
},
|
| 25436 |
+
{
|
| 25437 |
+
"epoch": 4.137891737891738,
|
| 25438 |
+
"grad_norm": 0.14861363172531128,
|
| 25439 |
+
"learning_rate": 4.6366902981487105e-05,
|
| 25440 |
+
"loss": 0.8182,
|
| 25441 |
+
"step": 3633
|
| 25442 |
+
},
|
| 25443 |
+
{
|
| 25444 |
+
"epoch": 4.139031339031339,
|
| 25445 |
+
"grad_norm": 0.16506506502628326,
|
| 25446 |
+
"learning_rate": 4.636448374266475e-05,
|
| 25447 |
+
"loss": 0.7298,
|
| 25448 |
+
"step": 3634
|
| 25449 |
+
},
|
| 25450 |
+
{
|
| 25451 |
+
"epoch": 4.140170940170941,
|
| 25452 |
+
"grad_norm": 0.15416599810123444,
|
| 25453 |
+
"learning_rate": 4.636206376179514e-05,
|
| 25454 |
+
"loss": 0.8121,
|
| 25455 |
+
"step": 3635
|
| 25456 |
+
},
|
| 25457 |
+
{
|
| 25458 |
+
"epoch": 4.141310541310541,
|
| 25459 |
+
"grad_norm": 0.15596051514148712,
|
| 25460 |
+
"learning_rate": 4.6359643038962296e-05,
|
| 25461 |
+
"loss": 0.8538,
|
| 25462 |
+
"step": 3636
|
| 25463 |
+
},
|
| 25464 |
+
{
|
| 25465 |
+
"epoch": 4.1424501424501425,
|
| 25466 |
+
"grad_norm": 0.1777096390724182,
|
| 25467 |
+
"learning_rate": 4.635722157425031e-05,
|
| 25468 |
+
"loss": 0.7866,
|
| 25469 |
+
"step": 3637
|
| 25470 |
+
},
|
| 25471 |
+
{
|
| 25472 |
+
"epoch": 4.143589743589744,
|
| 25473 |
+
"grad_norm": 0.1438266932964325,
|
| 25474 |
+
"learning_rate": 4.635479936774329e-05,
|
| 25475 |
+
"loss": 0.8084,
|
| 25476 |
+
"step": 3638
|
| 25477 |
+
},
|
| 25478 |
+
{
|
| 25479 |
+
"epoch": 4.1447293447293445,
|
| 25480 |
+
"grad_norm": 0.14145760238170624,
|
| 25481 |
+
"learning_rate": 4.635237641952536e-05,
|
| 25482 |
+
"loss": 0.8315,
|
| 25483 |
+
"step": 3639
|
| 25484 |
+
},
|
| 25485 |
+
{
|
| 25486 |
+
"epoch": 4.145868945868946,
|
| 25487 |
+
"grad_norm": 0.16704396903514862,
|
| 25488 |
+
"learning_rate": 4.6349952729680677e-05,
|
| 25489 |
+
"loss": 0.7879,
|
| 25490 |
+
"step": 3640
|
| 25491 |
+
},
|
| 25492 |
+
{
|
| 25493 |
+
"epoch": 4.147008547008547,
|
| 25494 |
+
"grad_norm": 0.18530404567718506,
|
| 25495 |
+
"learning_rate": 4.6347528298293426e-05,
|
| 25496 |
+
"loss": 0.6051,
|
| 25497 |
+
"step": 3641
|
| 25498 |
+
},
|
| 25499 |
+
{
|
| 25500 |
+
"epoch": 4.148148148148148,
|
| 25501 |
+
"grad_norm": 0.18084098398685455,
|
| 25502 |
+
"learning_rate": 4.634510312544781e-05,
|
| 25503 |
+
"loss": 0.7673,
|
| 25504 |
+
"step": 3642
|
| 25505 |
+
},
|
| 25506 |
+
{
|
| 25507 |
+
"epoch": 4.149287749287749,
|
| 25508 |
+
"grad_norm": 0.24151214957237244,
|
| 25509 |
+
"learning_rate": 4.634267721122806e-05,
|
| 25510 |
+
"loss": 0.8762,
|
| 25511 |
+
"step": 3643
|
| 25512 |
+
},
|
| 25513 |
+
{
|
| 25514 |
+
"epoch": 4.150427350427351,
|
| 25515 |
+
"grad_norm": 0.17945998907089233,
|
| 25516 |
+
"learning_rate": 4.634025055571844e-05,
|
| 25517 |
+
"loss": 0.7239,
|
| 25518 |
+
"step": 3644
|
| 25519 |
+
},
|
| 25520 |
+
{
|
| 25521 |
+
"epoch": 4.151566951566951,
|
| 25522 |
+
"grad_norm": 0.1628548949956894,
|
| 25523 |
+
"learning_rate": 4.6337823159003234e-05,
|
| 25524 |
+
"loss": 0.8899,
|
| 25525 |
+
"step": 3645
|
| 25526 |
+
},
|
| 25527 |
+
{
|
| 25528 |
+
"epoch": 4.152706552706553,
|
| 25529 |
+
"grad_norm": 0.1715235561132431,
|
| 25530 |
+
"learning_rate": 4.633539502116675e-05,
|
| 25531 |
+
"loss": 0.7984,
|
| 25532 |
+
"step": 3646
|
| 25533 |
+
},
|
| 25534 |
+
{
|
| 25535 |
+
"epoch": 4.153846153846154,
|
| 25536 |
+
"grad_norm": 0.15338733792304993,
|
| 25537 |
+
"learning_rate": 4.633296614229332e-05,
|
| 25538 |
+
"loss": 0.7406,
|
| 25539 |
+
"step": 3647
|
| 25540 |
+
},
|
| 25541 |
+
{
|
| 25542 |
+
"epoch": 4.154985754985755,
|
| 25543 |
+
"grad_norm": 0.1404416561126709,
|
| 25544 |
+
"learning_rate": 4.6330536522467315e-05,
|
| 25545 |
+
"loss": 0.8761,
|
| 25546 |
+
"step": 3648
|
| 25547 |
+
},
|
| 25548 |
+
{
|
| 25549 |
+
"epoch": 4.156125356125356,
|
| 25550 |
+
"grad_norm": 0.17968951165676117,
|
| 25551 |
+
"learning_rate": 4.632810616177312e-05,
|
| 25552 |
+
"loss": 0.7429,
|
| 25553 |
+
"step": 3649
|
| 25554 |
+
},
|
| 25555 |
+
{
|
| 25556 |
+
"epoch": 4.157264957264958,
|
| 25557 |
+
"grad_norm": 0.16005079448223114,
|
| 25558 |
+
"learning_rate": 4.632567506029514e-05,
|
| 25559 |
+
"loss": 0.8709,
|
| 25560 |
+
"step": 3650
|
| 25561 |
+
},
|
| 25562 |
+
{
|
| 25563 |
+
"epoch": 4.158404558404558,
|
| 25564 |
+
"grad_norm": 0.18263664841651917,
|
| 25565 |
+
"learning_rate": 4.6323243218117816e-05,
|
| 25566 |
+
"loss": 0.7205,
|
| 25567 |
+
"step": 3651
|
| 25568 |
+
},
|
| 25569 |
+
{
|
| 25570 |
+
"epoch": 4.15954415954416,
|
| 25571 |
+
"grad_norm": 0.14968404173851013,
|
| 25572 |
+
"learning_rate": 4.632081063532562e-05,
|
| 25573 |
+
"loss": 0.8413,
|
| 25574 |
+
"step": 3652
|
| 25575 |
+
},
|
| 25576 |
+
{
|
| 25577 |
+
"epoch": 4.160683760683761,
|
| 25578 |
+
"grad_norm": 0.15817460417747498,
|
| 25579 |
+
"learning_rate": 4.631837731200304e-05,
|
| 25580 |
+
"loss": 0.8515,
|
| 25581 |
+
"step": 3653
|
| 25582 |
+
},
|
| 25583 |
+
{
|
| 25584 |
+
"epoch": 4.1618233618233615,
|
| 25585 |
+
"grad_norm": 0.15472495555877686,
|
| 25586 |
+
"learning_rate": 4.631594324823459e-05,
|
| 25587 |
+
"loss": 0.764,
|
| 25588 |
+
"step": 3654
|
| 25589 |
+
},
|
| 25590 |
+
{
|
| 25591 |
+
"epoch": 4.162962962962963,
|
| 25592 |
+
"grad_norm": 0.14850182831287384,
|
| 25593 |
+
"learning_rate": 4.6313508444104814e-05,
|
| 25594 |
+
"loss": 1.0525,
|
| 25595 |
+
"step": 3655
|
| 25596 |
+
},
|
| 25597 |
+
{
|
| 25598 |
+
"epoch": 4.164102564102564,
|
| 25599 |
+
"grad_norm": 0.12211723625659943,
|
| 25600 |
+
"learning_rate": 4.631107289969827e-05,
|
| 25601 |
+
"loss": 0.9301,
|
| 25602 |
+
"step": 3656
|
| 25603 |
+
},
|
| 25604 |
+
{
|
| 25605 |
+
"epoch": 4.165242165242165,
|
| 25606 |
+
"grad_norm": 0.17291347682476044,
|
| 25607 |
+
"learning_rate": 4.630863661509956e-05,
|
| 25608 |
+
"loss": 0.7622,
|
| 25609 |
+
"step": 3657
|
| 25610 |
+
},
|
| 25611 |
+
{
|
| 25612 |
+
"epoch": 4.166381766381766,
|
| 25613 |
+
"grad_norm": 0.15008722245693207,
|
| 25614 |
+
"learning_rate": 4.6306199590393306e-05,
|
| 25615 |
+
"loss": 0.737,
|
| 25616 |
+
"step": 3658
|
| 25617 |
+
},
|
| 25618 |
+
{
|
| 25619 |
+
"epoch": 4.167521367521368,
|
| 25620 |
+
"grad_norm": 0.19958460330963135,
|
| 25621 |
+
"learning_rate": 4.630376182566415e-05,
|
| 25622 |
+
"loss": 0.5149,
|
| 25623 |
+
"step": 3659
|
| 25624 |
+
},
|
| 25625 |
+
{
|
| 25626 |
+
"epoch": 4.168660968660968,
|
| 25627 |
+
"grad_norm": 0.18100185692310333,
|
| 25628 |
+
"learning_rate": 4.630132332099676e-05,
|
| 25629 |
+
"loss": 0.9104,
|
| 25630 |
+
"step": 3660
|
| 25631 |
+
},
|
| 25632 |
+
{
|
| 25633 |
+
"epoch": 4.16980056980057,
|
| 25634 |
+
"grad_norm": 0.16496123373508453,
|
| 25635 |
+
"learning_rate": 4.629888407647582e-05,
|
| 25636 |
+
"loss": 0.7213,
|
| 25637 |
+
"step": 3661
|
| 25638 |
+
},
|
| 25639 |
+
{
|
| 25640 |
+
"epoch": 4.170940170940171,
|
| 25641 |
+
"grad_norm": 0.1654644012451172,
|
| 25642 |
+
"learning_rate": 4.629644409218608e-05,
|
| 25643 |
+
"loss": 0.9031,
|
| 25644 |
+
"step": 3662
|
| 25645 |
+
},
|
| 25646 |
+
{
|
| 25647 |
+
"epoch": 4.172079772079772,
|
| 25648 |
+
"grad_norm": 0.15994341671466827,
|
| 25649 |
+
"learning_rate": 4.629400336821226e-05,
|
| 25650 |
+
"loss": 0.755,
|
| 25651 |
+
"step": 3663
|
| 25652 |
+
},
|
| 25653 |
+
{
|
| 25654 |
+
"epoch": 4.173219373219373,
|
| 25655 |
+
"grad_norm": 0.1428716480731964,
|
| 25656 |
+
"learning_rate": 4.6291561904639145e-05,
|
| 25657 |
+
"loss": 0.8363,
|
| 25658 |
+
"step": 3664
|
| 25659 |
+
},
|
| 25660 |
+
{
|
| 25661 |
+
"epoch": 4.174358974358975,
|
| 25662 |
+
"grad_norm": 0.18579061329364777,
|
| 25663 |
+
"learning_rate": 4.628911970155154e-05,
|
| 25664 |
+
"loss": 0.6596,
|
| 25665 |
+
"step": 3665
|
| 25666 |
+
},
|
| 25667 |
+
{
|
| 25668 |
+
"epoch": 4.175498575498575,
|
| 25669 |
+
"grad_norm": 0.1424458920955658,
|
| 25670 |
+
"learning_rate": 4.6286676759034253e-05,
|
| 25671 |
+
"loss": 0.9963,
|
| 25672 |
+
"step": 3666
|
| 25673 |
+
},
|
| 25674 |
+
{
|
| 25675 |
+
"epoch": 4.176638176638177,
|
| 25676 |
+
"grad_norm": 0.1387307345867157,
|
| 25677 |
+
"learning_rate": 4.628423307717215e-05,
|
| 25678 |
+
"loss": 1.0031,
|
| 25679 |
+
"step": 3667
|
| 25680 |
+
},
|
| 25681 |
+
{
|
| 25682 |
+
"epoch": 4.177777777777778,
|
| 25683 |
+
"grad_norm": 0.16689176857471466,
|
| 25684 |
+
"learning_rate": 4.62817886560501e-05,
|
| 25685 |
+
"loss": 0.7465,
|
| 25686 |
+
"step": 3668
|
| 25687 |
+
},
|
| 25688 |
+
{
|
| 25689 |
+
"epoch": 4.178917378917379,
|
| 25690 |
+
"grad_norm": 0.16913136839866638,
|
| 25691 |
+
"learning_rate": 4.6279343495753e-05,
|
| 25692 |
+
"loss": 0.6266,
|
| 25693 |
+
"step": 3669
|
| 25694 |
+
},
|
| 25695 |
+
{
|
| 25696 |
+
"epoch": 4.18005698005698,
|
| 25697 |
+
"grad_norm": 0.15506194531917572,
|
| 25698 |
+
"learning_rate": 4.6276897596365794e-05,
|
| 25699 |
+
"loss": 0.7579,
|
| 25700 |
+
"step": 3670
|
| 25701 |
+
},
|
| 25702 |
+
{
|
| 25703 |
+
"epoch": 4.181196581196581,
|
| 25704 |
+
"grad_norm": 0.152205690741539,
|
| 25705 |
+
"learning_rate": 4.6274450957973415e-05,
|
| 25706 |
+
"loss": 0.9007,
|
| 25707 |
+
"step": 3671
|
| 25708 |
+
},
|
| 25709 |
+
{
|
| 25710 |
+
"epoch": 4.182336182336182,
|
| 25711 |
+
"grad_norm": 0.1602986454963684,
|
| 25712 |
+
"learning_rate": 4.627200358066085e-05,
|
| 25713 |
+
"loss": 0.7788,
|
| 25714 |
+
"step": 3672
|
| 25715 |
+
},
|
| 25716 |
+
{
|
| 25717 |
+
"epoch": 4.183475783475783,
|
| 25718 |
+
"grad_norm": 0.17027804255485535,
|
| 25719 |
+
"learning_rate": 4.62695554645131e-05,
|
| 25720 |
+
"loss": 0.6838,
|
| 25721 |
+
"step": 3673
|
| 25722 |
+
},
|
| 25723 |
+
{
|
| 25724 |
+
"epoch": 4.184615384615385,
|
| 25725 |
+
"grad_norm": 0.14730262756347656,
|
| 25726 |
+
"learning_rate": 4.6267106609615195e-05,
|
| 25727 |
+
"loss": 0.8341,
|
| 25728 |
+
"step": 3674
|
| 25729 |
+
},
|
| 25730 |
+
{
|
| 25731 |
+
"epoch": 4.185754985754985,
|
| 25732 |
+
"grad_norm": 0.16242659091949463,
|
| 25733 |
+
"learning_rate": 4.6264657016052196e-05,
|
| 25734 |
+
"loss": 0.792,
|
| 25735 |
+
"step": 3675
|
| 25736 |
+
},
|
| 25737 |
+
{
|
| 25738 |
+
"epoch": 4.186894586894587,
|
| 25739 |
+
"grad_norm": 0.13900625705718994,
|
| 25740 |
+
"learning_rate": 4.626220668390918e-05,
|
| 25741 |
+
"loss": 0.9605,
|
| 25742 |
+
"step": 3676
|
| 25743 |
+
},
|
| 25744 |
+
{
|
| 25745 |
+
"epoch": 4.188034188034188,
|
| 25746 |
+
"grad_norm": 0.13298556208610535,
|
| 25747 |
+
"learning_rate": 4.625975561327126e-05,
|
| 25748 |
+
"loss": 0.8414,
|
| 25749 |
+
"step": 3677
|
| 25750 |
+
},
|
| 25751 |
+
{
|
| 25752 |
+
"epoch": 4.189173789173789,
|
| 25753 |
+
"grad_norm": 0.1835649162530899,
|
| 25754 |
+
"learning_rate": 4.625730380422356e-05,
|
| 25755 |
+
"loss": 0.594,
|
| 25756 |
+
"step": 3678
|
| 25757 |
+
},
|
| 25758 |
+
{
|
| 25759 |
+
"epoch": 4.19031339031339,
|
| 25760 |
+
"grad_norm": 0.19300466775894165,
|
| 25761 |
+
"learning_rate": 4.625485125685124e-05,
|
| 25762 |
+
"loss": 0.7097,
|
| 25763 |
+
"step": 3679
|
| 25764 |
+
},
|
| 25765 |
+
{
|
| 25766 |
+
"epoch": 4.191452991452992,
|
| 25767 |
+
"grad_norm": 0.17401108145713806,
|
| 25768 |
+
"learning_rate": 4.625239797123948e-05,
|
| 25769 |
+
"loss": 0.7094,
|
| 25770 |
+
"step": 3680
|
| 25771 |
+
},
|
| 25772 |
+
{
|
| 25773 |
+
"epoch": 4.192592592592592,
|
| 25774 |
+
"grad_norm": 0.15717926621437073,
|
| 25775 |
+
"learning_rate": 4.62499439474735e-05,
|
| 25776 |
+
"loss": 0.7873,
|
| 25777 |
+
"step": 3681
|
| 25778 |
+
},
|
| 25779 |
+
{
|
| 25780 |
+
"epoch": 4.193732193732194,
|
| 25781 |
+
"grad_norm": 0.17586669325828552,
|
| 25782 |
+
"learning_rate": 4.624748918563852e-05,
|
| 25783 |
+
"loss": 0.83,
|
| 25784 |
+
"step": 3682
|
| 25785 |
+
},
|
| 25786 |
+
{
|
| 25787 |
+
"epoch": 4.194871794871795,
|
| 25788 |
+
"grad_norm": 0.17962506413459778,
|
| 25789 |
+
"learning_rate": 4.624503368581983e-05,
|
| 25790 |
+
"loss": 0.7088,
|
| 25791 |
+
"step": 3683
|
| 25792 |
+
},
|
| 25793 |
+
{
|
| 25794 |
+
"epoch": 4.196011396011396,
|
| 25795 |
+
"grad_norm": 0.22976629436016083,
|
| 25796 |
+
"learning_rate": 4.624257744810268e-05,
|
| 25797 |
+
"loss": 0.5079,
|
| 25798 |
+
"step": 3684
|
| 25799 |
+
},
|
| 25800 |
+
{
|
| 25801 |
+
"epoch": 4.197150997150997,
|
| 25802 |
+
"grad_norm": 0.13983486592769623,
|
| 25803 |
+
"learning_rate": 4.62401204725724e-05,
|
| 25804 |
+
"loss": 0.7997,
|
| 25805 |
+
"step": 3685
|
| 25806 |
+
},
|
| 25807 |
+
{
|
| 25808 |
+
"epoch": 4.1982905982905985,
|
| 25809 |
+
"grad_norm": 0.1361929327249527,
|
| 25810 |
+
"learning_rate": 4.6237662759314326e-05,
|
| 25811 |
+
"loss": 0.8305,
|
| 25812 |
+
"step": 3686
|
| 25813 |
+
},
|
| 25814 |
+
{
|
| 25815 |
+
"epoch": 4.199430199430199,
|
| 25816 |
+
"grad_norm": 0.17344947159290314,
|
| 25817 |
+
"learning_rate": 4.623520430841383e-05,
|
| 25818 |
+
"loss": 0.7241,
|
| 25819 |
+
"step": 3687
|
| 25820 |
+
},
|
| 25821 |
+
{
|
| 25822 |
+
"epoch": 4.2005698005698004,
|
| 25823 |
+
"grad_norm": 0.17485690116882324,
|
| 25824 |
+
"learning_rate": 4.6232745119956276e-05,
|
| 25825 |
+
"loss": 0.7006,
|
| 25826 |
+
"step": 3688
|
| 25827 |
+
},
|
| 25828 |
+
{
|
| 25829 |
+
"epoch": 4.201709401709402,
|
| 25830 |
+
"grad_norm": 0.12447243183851242,
|
| 25831 |
+
"learning_rate": 4.62302851940271e-05,
|
| 25832 |
+
"loss": 0.9402,
|
| 25833 |
+
"step": 3689
|
| 25834 |
+
},
|
| 25835 |
+
{
|
| 25836 |
+
"epoch": 4.202849002849002,
|
| 25837 |
+
"grad_norm": 0.1367679089307785,
|
| 25838 |
+
"learning_rate": 4.6227824530711736e-05,
|
| 25839 |
+
"loss": 0.9485,
|
| 25840 |
+
"step": 3690
|
| 25841 |
+
},
|
| 25842 |
+
{
|
| 25843 |
+
"epoch": 4.203988603988604,
|
| 25844 |
+
"grad_norm": 0.18233831226825714,
|
| 25845 |
+
"learning_rate": 4.622536313009565e-05,
|
| 25846 |
+
"loss": 0.618,
|
| 25847 |
+
"step": 3691
|
| 25848 |
+
},
|
| 25849 |
+
{
|
| 25850 |
+
"epoch": 4.205128205128205,
|
| 25851 |
+
"grad_norm": 0.16943730413913727,
|
| 25852 |
+
"learning_rate": 4.6222900992264336e-05,
|
| 25853 |
+
"loss": 0.8441,
|
| 25854 |
+
"step": 3692
|
| 25855 |
+
},
|
| 25856 |
+
{
|
| 25857 |
+
"epoch": 4.206267806267807,
|
| 25858 |
+
"grad_norm": 0.17953555285930634,
|
| 25859 |
+
"learning_rate": 4.62204381173033e-05,
|
| 25860 |
+
"loss": 0.6973,
|
| 25861 |
+
"step": 3693
|
| 25862 |
+
},
|
| 25863 |
+
{
|
| 25864 |
+
"epoch": 4.207407407407407,
|
| 25865 |
+
"grad_norm": 0.15341761708259583,
|
| 25866 |
+
"learning_rate": 4.62179745052981e-05,
|
| 25867 |
+
"loss": 0.8015,
|
| 25868 |
+
"step": 3694
|
| 25869 |
+
},
|
| 25870 |
+
{
|
| 25871 |
+
"epoch": 4.208547008547009,
|
| 25872 |
+
"grad_norm": 0.15298165380954742,
|
| 25873 |
+
"learning_rate": 4.621551015633429e-05,
|
| 25874 |
+
"loss": 0.8267,
|
| 25875 |
+
"step": 3695
|
| 25876 |
+
},
|
| 25877 |
+
{
|
| 25878 |
+
"epoch": 4.20968660968661,
|
| 25879 |
+
"grad_norm": 0.1532493233680725,
|
| 25880 |
+
"learning_rate": 4.621304507049747e-05,
|
| 25881 |
+
"loss": 0.8052,
|
| 25882 |
+
"step": 3696
|
| 25883 |
+
},
|
| 25884 |
+
{
|
| 25885 |
+
"epoch": 4.210826210826211,
|
| 25886 |
+
"grad_norm": 0.13848675787448883,
|
| 25887 |
+
"learning_rate": 4.621057924787325e-05,
|
| 25888 |
+
"loss": 1.0222,
|
| 25889 |
+
"step": 3697
|
| 25890 |
+
},
|
| 25891 |
+
{
|
| 25892 |
+
"epoch": 4.211965811965812,
|
| 25893 |
+
"grad_norm": 0.1508934497833252,
|
| 25894 |
+
"learning_rate": 4.62081126885473e-05,
|
| 25895 |
+
"loss": 0.8087,
|
| 25896 |
+
"step": 3698
|
| 25897 |
+
},
|
| 25898 |
+
{
|
| 25899 |
+
"epoch": 4.2131054131054135,
|
| 25900 |
+
"grad_norm": 0.1419859081506729,
|
| 25901 |
+
"learning_rate": 4.6205645392605267e-05,
|
| 25902 |
+
"loss": 0.8482,
|
| 25903 |
+
"step": 3699
|
| 25904 |
+
},
|
| 25905 |
+
{
|
| 25906 |
+
"epoch": 4.214245014245014,
|
| 25907 |
+
"grad_norm": 0.15996615588665009,
|
| 25908 |
+
"learning_rate": 4.620317736013285e-05,
|
| 25909 |
+
"loss": 0.8327,
|
| 25910 |
+
"step": 3700
|
| 25911 |
+
},
|
| 25912 |
+
{
|
| 25913 |
+
"epoch": 4.2153846153846155,
|
| 25914 |
+
"grad_norm": 0.15426044166088104,
|
| 25915 |
+
"learning_rate": 4.620070859121578e-05,
|
| 25916 |
+
"loss": 0.7603,
|
| 25917 |
+
"step": 3701
|
| 25918 |
+
},
|
| 25919 |
+
{
|
| 25920 |
+
"epoch": 4.216524216524217,
|
| 25921 |
+
"grad_norm": 0.17264823615550995,
|
| 25922 |
+
"learning_rate": 4.61982390859398e-05,
|
| 25923 |
+
"loss": 0.8172,
|
| 25924 |
+
"step": 3702
|
| 25925 |
+
},
|
| 25926 |
+
{
|
| 25927 |
+
"epoch": 4.2176638176638175,
|
| 25928 |
+
"grad_norm": 0.19376209378242493,
|
| 25929 |
+
"learning_rate": 4.6195768844390674e-05,
|
| 25930 |
+
"loss": 0.6843,
|
| 25931 |
+
"step": 3703
|
| 25932 |
+
},
|
| 25933 |
+
{
|
| 25934 |
+
"epoch": 4.218803418803419,
|
| 25935 |
+
"grad_norm": 0.14135196805000305,
|
| 25936 |
+
"learning_rate": 4.6193297866654203e-05,
|
| 25937 |
+
"loss": 0.9739,
|
| 25938 |
+
"step": 3704
|
| 25939 |
+
},
|
| 25940 |
+
{
|
| 25941 |
+
"epoch": 4.21994301994302,
|
| 25942 |
+
"grad_norm": 0.18155446648597717,
|
| 25943 |
+
"learning_rate": 4.6190826152816225e-05,
|
| 25944 |
+
"loss": 0.7857,
|
| 25945 |
+
"step": 3705
|
| 25946 |
+
},
|
| 25947 |
+
{
|
| 25948 |
+
"epoch": 4.221082621082621,
|
| 25949 |
+
"grad_norm": 0.14685101807117462,
|
| 25950 |
+
"learning_rate": 4.618835370296258e-05,
|
| 25951 |
+
"loss": 0.8411,
|
| 25952 |
+
"step": 3706
|
| 25953 |
+
},
|
| 25954 |
+
{
|
| 25955 |
+
"epoch": 4.222222222222222,
|
| 25956 |
+
"grad_norm": 0.1883654147386551,
|
| 25957 |
+
"learning_rate": 4.618588051717914e-05,
|
| 25958 |
+
"loss": 0.7015,
|
| 25959 |
+
"step": 3707
|
| 25960 |
+
},
|
| 25961 |
+
{
|
| 25962 |
+
"epoch": 4.223361823361824,
|
| 25963 |
+
"grad_norm": 0.16308410465717316,
|
| 25964 |
+
"learning_rate": 4.618340659555181e-05,
|
| 25965 |
+
"loss": 0.8265,
|
| 25966 |
+
"step": 3708
|
| 25967 |
+
},
|
| 25968 |
+
{
|
| 25969 |
+
"epoch": 4.224501424501424,
|
| 25970 |
+
"grad_norm": 0.1645018309354782,
|
| 25971 |
+
"learning_rate": 4.618093193816652e-05,
|
| 25972 |
+
"loss": 0.6949,
|
| 25973 |
+
"step": 3709
|
| 25974 |
+
},
|
| 25975 |
+
{
|
| 25976 |
+
"epoch": 4.225641025641026,
|
| 25977 |
+
"grad_norm": 0.17556124925613403,
|
| 25978 |
+
"learning_rate": 4.61784565451092e-05,
|
| 25979 |
+
"loss": 0.6353,
|
| 25980 |
+
"step": 3710
|
| 25981 |
+
},
|
| 25982 |
+
{
|
| 25983 |
+
"epoch": 4.226780626780627,
|
| 25984 |
+
"grad_norm": 0.15007174015045166,
|
| 25985 |
+
"learning_rate": 4.617598041646585e-05,
|
| 25986 |
+
"loss": 0.7372,
|
| 25987 |
+
"step": 3711
|
| 25988 |
+
},
|
| 25989 |
+
{
|
| 25990 |
+
"epoch": 4.227920227920228,
|
| 25991 |
+
"grad_norm": 0.14627604186534882,
|
| 25992 |
+
"learning_rate": 4.617350355232247e-05,
|
| 25993 |
+
"loss": 0.9112,
|
| 25994 |
+
"step": 3712
|
| 25995 |
+
},
|
| 25996 |
+
{
|
| 25997 |
+
"epoch": 4.229059829059829,
|
| 25998 |
+
"grad_norm": 0.1603684425354004,
|
| 25999 |
+
"learning_rate": 4.617102595276508e-05,
|
| 26000 |
+
"loss": 0.84,
|
| 26001 |
+
"step": 3713
|
| 26002 |
+
},
|
| 26003 |
+
{
|
| 26004 |
+
"epoch": 4.230199430199431,
|
| 26005 |
+
"grad_norm": 0.15586189925670624,
|
| 26006 |
+
"learning_rate": 4.616854761787974e-05,
|
| 26007 |
+
"loss": 0.7862,
|
| 26008 |
+
"step": 3714
|
| 26009 |
+
},
|
| 26010 |
+
{
|
| 26011 |
+
"epoch": 4.231339031339031,
|
| 26012 |
+
"grad_norm": 0.16218826174736023,
|
| 26013 |
+
"learning_rate": 4.616606854775253e-05,
|
| 26014 |
+
"loss": 0.7294,
|
| 26015 |
+
"step": 3715
|
| 26016 |
+
},
|
| 26017 |
+
{
|
| 26018 |
+
"epoch": 4.2324786324786325,
|
| 26019 |
+
"grad_norm": 0.142206072807312,
|
| 26020 |
+
"learning_rate": 4.6163588742469556e-05,
|
| 26021 |
+
"loss": 0.8574,
|
| 26022 |
+
"step": 3716
|
| 26023 |
+
},
|
| 26024 |
+
{
|
| 26025 |
+
"epoch": 4.233618233618234,
|
| 26026 |
+
"grad_norm": 0.1761651635169983,
|
| 26027 |
+
"learning_rate": 4.616110820211693e-05,
|
| 26028 |
+
"loss": 0.7301,
|
| 26029 |
+
"step": 3717
|
| 26030 |
+
},
|
| 26031 |
+
{
|
| 26032 |
+
"epoch": 4.2347578347578345,
|
| 26033 |
+
"grad_norm": 0.14478951692581177,
|
| 26034 |
+
"learning_rate": 4.6158626926780835e-05,
|
| 26035 |
+
"loss": 0.8113,
|
| 26036 |
+
"step": 3718
|
| 26037 |
+
},
|
| 26038 |
+
{
|
| 26039 |
+
"epoch": 4.235897435897436,
|
| 26040 |
+
"grad_norm": 0.18671946227550507,
|
| 26041 |
+
"learning_rate": 4.615614491654744e-05,
|
| 26042 |
+
"loss": 0.6897,
|
| 26043 |
+
"step": 3719
|
| 26044 |
+
},
|
| 26045 |
+
{
|
| 26046 |
+
"epoch": 4.237037037037037,
|
| 26047 |
+
"grad_norm": 0.16866810619831085,
|
| 26048 |
+
"learning_rate": 4.615366217150295e-05,
|
| 26049 |
+
"loss": 0.8514,
|
| 26050 |
+
"step": 3720
|
| 26051 |
+
},
|
| 26052 |
+
{
|
| 26053 |
+
"epoch": 4.238176638176638,
|
| 26054 |
+
"grad_norm": 0.16729912161827087,
|
| 26055 |
+
"learning_rate": 4.6151178691733596e-05,
|
| 26056 |
+
"loss": 0.8627,
|
| 26057 |
+
"step": 3721
|
| 26058 |
+
},
|
| 26059 |
+
{
|
| 26060 |
+
"epoch": 4.239316239316239,
|
| 26061 |
+
"grad_norm": 0.16953368484973907,
|
| 26062 |
+
"learning_rate": 4.614869447732564e-05,
|
| 26063 |
+
"loss": 0.8992,
|
| 26064 |
+
"step": 3722
|
| 26065 |
+
},
|
| 26066 |
+
{
|
| 26067 |
+
"epoch": 4.240455840455841,
|
| 26068 |
+
"grad_norm": 0.12552765011787415,
|
| 26069 |
+
"learning_rate": 4.6146209528365376e-05,
|
| 26070 |
+
"loss": 0.9473,
|
| 26071 |
+
"step": 3723
|
| 26072 |
+
},
|
| 26073 |
+
{
|
| 26074 |
+
"epoch": 4.241595441595441,
|
| 26075 |
+
"grad_norm": 0.16287629306316376,
|
| 26076 |
+
"learning_rate": 4.614372384493909e-05,
|
| 26077 |
+
"loss": 0.7719,
|
| 26078 |
+
"step": 3724
|
| 26079 |
+
},
|
| 26080 |
+
{
|
| 26081 |
+
"epoch": 4.242735042735043,
|
| 26082 |
+
"grad_norm": 0.1784881204366684,
|
| 26083 |
+
"learning_rate": 4.614123742713314e-05,
|
| 26084 |
+
"loss": 0.7364,
|
| 26085 |
+
"step": 3725
|
| 26086 |
+
},
|
| 26087 |
+
{
|
| 26088 |
+
"epoch": 4.243874643874644,
|
| 26089 |
+
"grad_norm": 0.15355971455574036,
|
| 26090 |
+
"learning_rate": 4.613875027503387e-05,
|
| 26091 |
+
"loss": 0.8259,
|
| 26092 |
+
"step": 3726
|
| 26093 |
+
},
|
| 26094 |
+
{
|
| 26095 |
+
"epoch": 4.245014245014245,
|
| 26096 |
+
"grad_norm": 0.1835944652557373,
|
| 26097 |
+
"learning_rate": 4.613626238872767e-05,
|
| 26098 |
+
"loss": 0.7589,
|
| 26099 |
+
"step": 3727
|
| 26100 |
+
},
|
| 26101 |
+
{
|
| 26102 |
+
"epoch": 4.246153846153846,
|
| 26103 |
+
"grad_norm": 0.1890999972820282,
|
| 26104 |
+
"learning_rate": 4.613377376830096e-05,
|
| 26105 |
+
"loss": 0.5468,
|
| 26106 |
+
"step": 3728
|
| 26107 |
+
},
|
| 26108 |
+
{
|
| 26109 |
+
"epoch": 4.247293447293448,
|
| 26110 |
+
"grad_norm": 0.16878777742385864,
|
| 26111 |
+
"learning_rate": 4.613128441384016e-05,
|
| 26112 |
+
"loss": 0.7012,
|
| 26113 |
+
"step": 3729
|
| 26114 |
+
},
|
| 26115 |
+
{
|
| 26116 |
+
"epoch": 4.248433048433048,
|
| 26117 |
+
"grad_norm": 0.1307375282049179,
|
| 26118 |
+
"learning_rate": 4.612879432543175e-05,
|
| 26119 |
+
"loss": 0.9886,
|
| 26120 |
+
"step": 3730
|
| 26121 |
+
},
|
| 26122 |
+
{
|
| 26123 |
+
"epoch": 4.24957264957265,
|
| 26124 |
+
"grad_norm": 0.1786198765039444,
|
| 26125 |
+
"learning_rate": 4.6126303503162196e-05,
|
| 26126 |
+
"loss": 0.8062,
|
| 26127 |
+
"step": 3731
|
| 26128 |
+
},
|
| 26129 |
+
{
|
| 26130 |
+
"epoch": 4.250712250712251,
|
| 26131 |
+
"grad_norm": 0.192620649933815,
|
| 26132 |
+
"learning_rate": 4.612381194711803e-05,
|
| 26133 |
+
"loss": 0.6136,
|
| 26134 |
+
"step": 3732
|
| 26135 |
+
},
|
| 26136 |
+
{
|
| 26137 |
+
"epoch": 4.2518518518518515,
|
| 26138 |
+
"grad_norm": 0.15778356790542603,
|
| 26139 |
+
"learning_rate": 4.612131965738579e-05,
|
| 26140 |
+
"loss": 1.0118,
|
| 26141 |
+
"step": 3733
|
| 26142 |
+
},
|
| 26143 |
+
{
|
| 26144 |
+
"epoch": 4.252991452991453,
|
| 26145 |
+
"grad_norm": 0.17104782164096832,
|
| 26146 |
+
"learning_rate": 4.611882663405203e-05,
|
| 26147 |
+
"loss": 0.6261,
|
| 26148 |
+
"step": 3734
|
| 26149 |
+
},
|
| 26150 |
+
{
|
| 26151 |
+
"epoch": 4.254131054131054,
|
| 26152 |
+
"grad_norm": 0.17603422701358795,
|
| 26153 |
+
"learning_rate": 4.6116332877203344e-05,
|
| 26154 |
+
"loss": 0.913,
|
| 26155 |
+
"step": 3735
|
| 26156 |
+
},
|
| 26157 |
+
{
|
| 26158 |
+
"epoch": 4.255270655270655,
|
| 26159 |
+
"grad_norm": 0.15426822006702423,
|
| 26160 |
+
"learning_rate": 4.611383838692635e-05,
|
| 26161 |
+
"loss": 0.7447,
|
| 26162 |
+
"step": 3736
|
| 26163 |
+
},
|
| 26164 |
+
{
|
| 26165 |
+
"epoch": 4.256410256410256,
|
| 26166 |
+
"grad_norm": 0.19463273882865906,
|
| 26167 |
+
"learning_rate": 4.611134316330768e-05,
|
| 26168 |
+
"loss": 0.7212,
|
| 26169 |
+
"step": 3737
|
| 26170 |
+
},
|
| 26171 |
+
{
|
| 26172 |
+
"epoch": 4.257549857549858,
|
| 26173 |
+
"grad_norm": 0.16557398438453674,
|
| 26174 |
+
"learning_rate": 4.6108847206434e-05,
|
| 26175 |
+
"loss": 0.8571,
|
| 26176 |
+
"step": 3738
|
| 26177 |
+
},
|
| 26178 |
+
{
|
| 26179 |
+
"epoch": 4.258689458689458,
|
| 26180 |
+
"grad_norm": 0.17092663049697876,
|
| 26181 |
+
"learning_rate": 4.610635051639202e-05,
|
| 26182 |
+
"loss": 0.7672,
|
| 26183 |
+
"step": 3739
|
| 26184 |
+
},
|
| 26185 |
+
{
|
| 26186 |
+
"epoch": 4.25982905982906,
|
| 26187 |
+
"grad_norm": 0.1692628413438797,
|
| 26188 |
+
"learning_rate": 4.610385309326844e-05,
|
| 26189 |
+
"loss": 0.6786,
|
| 26190 |
+
"step": 3740
|
| 26191 |
+
},
|
| 26192 |
+
{
|
| 26193 |
+
"epoch": 4.260968660968661,
|
| 26194 |
+
"grad_norm": 0.18885384500026703,
|
| 26195 |
+
"learning_rate": 4.610135493715e-05,
|
| 26196 |
+
"loss": 0.8426,
|
| 26197 |
+
"step": 3741
|
| 26198 |
+
},
|
| 26199 |
+
{
|
| 26200 |
+
"epoch": 4.262108262108262,
|
| 26201 |
+
"grad_norm": 0.20354245603084564,
|
| 26202 |
+
"learning_rate": 4.6098856048123485e-05,
|
| 26203 |
+
"loss": 0.7192,
|
| 26204 |
+
"step": 3742
|
| 26205 |
+
},
|
| 26206 |
+
{
|
| 26207 |
+
"epoch": 4.263247863247863,
|
| 26208 |
+
"grad_norm": 0.14963997900485992,
|
| 26209 |
+
"learning_rate": 4.6096356426275674e-05,
|
| 26210 |
+
"loss": 0.8953,
|
| 26211 |
+
"step": 3743
|
| 26212 |
+
},
|
| 26213 |
+
{
|
| 26214 |
+
"epoch": 4.264387464387465,
|
| 26215 |
+
"grad_norm": 0.16042745113372803,
|
| 26216 |
+
"learning_rate": 4.6093856071693386e-05,
|
| 26217 |
+
"loss": 0.7398,
|
| 26218 |
+
"step": 3744
|
| 26219 |
+
},
|
| 26220 |
+
{
|
| 26221 |
+
"epoch": 4.265527065527065,
|
| 26222 |
+
"grad_norm": 0.1531853973865509,
|
| 26223 |
+
"learning_rate": 4.6091354984463465e-05,
|
| 26224 |
+
"loss": 0.8418,
|
| 26225 |
+
"step": 3745
|
| 26226 |
+
},
|
| 26227 |
+
{
|
| 26228 |
+
"epoch": 4.266666666666667,
|
| 26229 |
+
"grad_norm": 0.14608848094940186,
|
| 26230 |
+
"learning_rate": 4.608885316467279e-05,
|
| 26231 |
+
"loss": 0.8293,
|
| 26232 |
+
"step": 3746
|
| 26233 |
+
},
|
| 26234 |
+
{
|
| 26235 |
+
"epoch": 4.267806267806268,
|
| 26236 |
+
"grad_norm": 0.1838957965373993,
|
| 26237 |
+
"learning_rate": 4.6086350612408246e-05,
|
| 26238 |
+
"loss": 0.7711,
|
| 26239 |
+
"step": 3747
|
| 26240 |
+
},
|
| 26241 |
+
{
|
| 26242 |
+
"epoch": 4.268945868945869,
|
| 26243 |
+
"grad_norm": 0.16072875261306763,
|
| 26244 |
+
"learning_rate": 4.6083847327756766e-05,
|
| 26245 |
+
"loss": 0.7368,
|
| 26246 |
+
"step": 3748
|
| 26247 |
+
},
|
| 26248 |
+
{
|
| 26249 |
+
"epoch": 4.27008547008547,
|
| 26250 |
+
"grad_norm": 0.1710791140794754,
|
| 26251 |
+
"learning_rate": 4.6081343310805275e-05,
|
| 26252 |
+
"loss": 0.7877,
|
| 26253 |
+
"step": 3749
|
| 26254 |
+
},
|
| 26255 |
+
{
|
| 26256 |
+
"epoch": 4.2712250712250714,
|
| 26257 |
+
"grad_norm": 0.18032675981521606,
|
| 26258 |
+
"learning_rate": 4.607883856164076e-05,
|
| 26259 |
+
"loss": 0.7567,
|
| 26260 |
+
"step": 3750
|
| 26261 |
+
},
|
| 26262 |
+
{
|
| 26263 |
+
"epoch": 4.272364672364672,
|
| 26264 |
+
"grad_norm": 0.16010992228984833,
|
| 26265 |
+
"learning_rate": 4.607633308035022e-05,
|
| 26266 |
+
"loss": 0.8425,
|
| 26267 |
+
"step": 3751
|
| 26268 |
+
},
|
| 26269 |
+
{
|
| 26270 |
+
"epoch": 4.273504273504273,
|
| 26271 |
+
"grad_norm": 0.15786418318748474,
|
| 26272 |
+
"learning_rate": 4.607382686702067e-05,
|
| 26273 |
+
"loss": 0.8954,
|
| 26274 |
+
"step": 3752
|
| 26275 |
+
},
|
| 26276 |
+
{
|
| 26277 |
+
"epoch": 4.274643874643875,
|
| 26278 |
+
"grad_norm": 0.18093998730182648,
|
| 26279 |
+
"learning_rate": 4.607131992173916e-05,
|
| 26280 |
+
"loss": 0.8716,
|
| 26281 |
+
"step": 3753
|
| 26282 |
+
},
|
| 26283 |
+
{
|
| 26284 |
+
"epoch": 4.275783475783475,
|
| 26285 |
+
"grad_norm": 0.1507583111524582,
|
| 26286 |
+
"learning_rate": 4.6068812244592766e-05,
|
| 26287 |
+
"loss": 0.7992,
|
| 26288 |
+
"step": 3754
|
| 26289 |
+
},
|
| 26290 |
+
{
|
| 26291 |
+
"epoch": 4.276923076923077,
|
| 26292 |
+
"grad_norm": 0.15738655626773834,
|
| 26293 |
+
"learning_rate": 4.6066303835668575e-05,
|
| 26294 |
+
"loss": 0.8685,
|
| 26295 |
+
"step": 3755
|
| 26296 |
+
},
|
| 26297 |
+
{
|
| 26298 |
+
"epoch": 4.278062678062678,
|
| 26299 |
+
"grad_norm": 0.14686685800552368,
|
| 26300 |
+
"learning_rate": 4.6063794695053716e-05,
|
| 26301 |
+
"loss": 0.935,
|
| 26302 |
+
"step": 3756
|
| 26303 |
+
},
|
| 26304 |
+
{
|
| 26305 |
+
"epoch": 4.279202279202279,
|
| 26306 |
+
"grad_norm": 0.14715251326560974,
|
| 26307 |
+
"learning_rate": 4.606128482283535e-05,
|
| 26308 |
+
"loss": 0.8501,
|
| 26309 |
+
"step": 3757
|
| 26310 |
+
},
|
| 26311 |
+
{
|
| 26312 |
+
"epoch": 4.28034188034188,
|
| 26313 |
+
"grad_norm": 0.16606487333774567,
|
| 26314 |
+
"learning_rate": 4.6058774219100646e-05,
|
| 26315 |
+
"loss": 0.7991,
|
| 26316 |
+
"step": 3758
|
| 26317 |
+
},
|
| 26318 |
+
{
|
| 26319 |
+
"epoch": 4.281481481481482,
|
| 26320 |
+
"grad_norm": 0.16110959649085999,
|
| 26321 |
+
"learning_rate": 4.60562628839368e-05,
|
| 26322 |
+
"loss": 0.7071,
|
| 26323 |
+
"step": 3759
|
| 26324 |
+
},
|
| 26325 |
+
{
|
| 26326 |
+
"epoch": 4.282621082621082,
|
| 26327 |
+
"grad_norm": 0.19022086262702942,
|
| 26328 |
+
"learning_rate": 4.605375081743104e-05,
|
| 26329 |
+
"loss": 0.6373,
|
| 26330 |
+
"step": 3760
|
| 26331 |
+
},
|
| 26332 |
+
{
|
| 26333 |
+
"epoch": 4.283760683760684,
|
| 26334 |
+
"grad_norm": 0.17297887802124023,
|
| 26335 |
+
"learning_rate": 4.605123801967061e-05,
|
| 26336 |
+
"loss": 0.8084,
|
| 26337 |
+
"step": 3761
|
| 26338 |
+
},
|
| 26339 |
+
{
|
| 26340 |
+
"epoch": 4.284900284900285,
|
| 26341 |
+
"grad_norm": 0.15393395721912384,
|
| 26342 |
+
"learning_rate": 4.60487244907428e-05,
|
| 26343 |
+
"loss": 0.7803,
|
| 26344 |
+
"step": 3762
|
| 26345 |
+
},
|
| 26346 |
+
{
|
| 26347 |
+
"epoch": 4.286039886039886,
|
| 26348 |
+
"grad_norm": 0.14357399940490723,
|
| 26349 |
+
"learning_rate": 4.60462102307349e-05,
|
| 26350 |
+
"loss": 0.7516,
|
| 26351 |
+
"step": 3763
|
| 26352 |
+
},
|
| 26353 |
+
{
|
| 26354 |
+
"epoch": 4.287179487179487,
|
| 26355 |
+
"grad_norm": 0.17141439020633698,
|
| 26356 |
+
"learning_rate": 4.604369523973424e-05,
|
| 26357 |
+
"loss": 0.7055,
|
| 26358 |
+
"step": 3764
|
| 26359 |
+
},
|
| 26360 |
+
{
|
| 26361 |
+
"epoch": 4.2883190883190885,
|
| 26362 |
+
"grad_norm": 0.15102678537368774,
|
| 26363 |
+
"learning_rate": 4.604117951782817e-05,
|
| 26364 |
+
"loss": 0.8778,
|
| 26365 |
+
"step": 3765
|
| 26366 |
+
},
|
| 26367 |
+
{
|
| 26368 |
+
"epoch": 4.289458689458689,
|
| 26369 |
+
"grad_norm": 0.1764611452817917,
|
| 26370 |
+
"learning_rate": 4.603866306510408e-05,
|
| 26371 |
+
"loss": 0.8287,
|
| 26372 |
+
"step": 3766
|
| 26373 |
+
},
|
| 26374 |
+
{
|
| 26375 |
+
"epoch": 4.2905982905982905,
|
| 26376 |
+
"grad_norm": 0.1734817773103714,
|
| 26377 |
+
"learning_rate": 4.603614588164936e-05,
|
| 26378 |
+
"loss": 0.7691,
|
| 26379 |
+
"step": 3767
|
| 26380 |
+
},
|
| 26381 |
+
{
|
| 26382 |
+
"epoch": 4.291737891737892,
|
| 26383 |
+
"grad_norm": 0.1688023954629898,
|
| 26384 |
+
"learning_rate": 4.603362796755145e-05,
|
| 26385 |
+
"loss": 0.8033,
|
| 26386 |
+
"step": 3768
|
| 26387 |
+
},
|
| 26388 |
+
{
|
| 26389 |
+
"epoch": 4.292877492877492,
|
| 26390 |
+
"grad_norm": 0.19275137782096863,
|
| 26391 |
+
"learning_rate": 4.6031109322897794e-05,
|
| 26392 |
+
"loss": 0.5918,
|
| 26393 |
+
"step": 3769
|
| 26394 |
+
},
|
| 26395 |
+
{
|
| 26396 |
+
"epoch": 4.294017094017094,
|
| 26397 |
+
"grad_norm": 0.18453450500965118,
|
| 26398 |
+
"learning_rate": 4.6028589947775866e-05,
|
| 26399 |
+
"loss": 0.575,
|
| 26400 |
+
"step": 3770
|
| 26401 |
+
},
|
| 26402 |
+
{
|
| 26403 |
+
"epoch": 4.295156695156695,
|
| 26404 |
+
"grad_norm": 0.16129399836063385,
|
| 26405 |
+
"learning_rate": 4.6026069842273196e-05,
|
| 26406 |
+
"loss": 0.7724,
|
| 26407 |
+
"step": 3771
|
| 26408 |
+
},
|
| 26409 |
+
{
|
| 26410 |
+
"epoch": 4.296296296296296,
|
| 26411 |
+
"grad_norm": 0.1554025113582611,
|
| 26412 |
+
"learning_rate": 4.602354900647729e-05,
|
| 26413 |
+
"loss": 0.9147,
|
| 26414 |
+
"step": 3772
|
| 26415 |
+
},
|
| 26416 |
+
{
|
| 26417 |
+
"epoch": 4.297435897435897,
|
| 26418 |
+
"grad_norm": 0.18058346211910248,
|
| 26419 |
+
"learning_rate": 4.602102744047572e-05,
|
| 26420 |
+
"loss": 0.7304,
|
| 26421 |
+
"step": 3773
|
| 26422 |
+
},
|
| 26423 |
+
{
|
| 26424 |
+
"epoch": 4.298575498575499,
|
| 26425 |
+
"grad_norm": 0.1559993177652359,
|
| 26426 |
+
"learning_rate": 4.601850514435605e-05,
|
| 26427 |
+
"loss": 0.8581,
|
| 26428 |
+
"step": 3774
|
| 26429 |
+
},
|
| 26430 |
+
{
|
| 26431 |
+
"epoch": 4.2997150997151,
|
| 26432 |
+
"grad_norm": 0.20117342472076416,
|
| 26433 |
+
"learning_rate": 4.60159821182059e-05,
|
| 26434 |
+
"loss": 0.7591,
|
| 26435 |
+
"step": 3775
|
| 26436 |
+
},
|
| 26437 |
+
{
|
| 26438 |
+
"epoch": 4.300854700854701,
|
| 26439 |
+
"grad_norm": 0.13583272695541382,
|
| 26440 |
+
"learning_rate": 4.6013458362112895e-05,
|
| 26441 |
+
"loss": 1.0527,
|
| 26442 |
+
"step": 3776
|
| 26443 |
+
},
|
| 26444 |
+
{
|
| 26445 |
+
"epoch": 4.301994301994302,
|
| 26446 |
+
"grad_norm": 0.14380411803722382,
|
| 26447 |
+
"learning_rate": 4.6010933876164694e-05,
|
| 26448 |
+
"loss": 0.9164,
|
| 26449 |
+
"step": 3777
|
| 26450 |
+
},
|
| 26451 |
+
{
|
| 26452 |
+
"epoch": 4.3031339031339035,
|
| 26453 |
+
"grad_norm": 0.17932040989398956,
|
| 26454 |
+
"learning_rate": 4.600840866044898e-05,
|
| 26455 |
+
"loss": 0.8558,
|
| 26456 |
+
"step": 3778
|
| 26457 |
+
},
|
| 26458 |
+
{
|
| 26459 |
+
"epoch": 4.304273504273504,
|
| 26460 |
+
"grad_norm": 0.17651857435703278,
|
| 26461 |
+
"learning_rate": 4.600588271505346e-05,
|
| 26462 |
+
"loss": 0.7339,
|
| 26463 |
+
"step": 3779
|
| 26464 |
+
},
|
| 26465 |
+
{
|
| 26466 |
+
"epoch": 4.3054131054131055,
|
| 26467 |
+
"grad_norm": 0.18811674416065216,
|
| 26468 |
+
"learning_rate": 4.600335604006586e-05,
|
| 26469 |
+
"loss": 0.7801,
|
| 26470 |
+
"step": 3780
|
| 26471 |
+
},
|
| 26472 |
+
{
|
| 26473 |
+
"epoch": 4.306552706552707,
|
| 26474 |
+
"grad_norm": 0.15561941266059875,
|
| 26475 |
+
"learning_rate": 4.6000828635573955e-05,
|
| 26476 |
+
"loss": 0.9072,
|
| 26477 |
+
"step": 3781
|
| 26478 |
+
},
|
| 26479 |
+
{
|
| 26480 |
+
"epoch": 4.3076923076923075,
|
| 26481 |
+
"grad_norm": 0.1979294717311859,
|
| 26482 |
+
"learning_rate": 4.599830050166551e-05,
|
| 26483 |
+
"loss": 0.7837,
|
| 26484 |
+
"step": 3782
|
| 26485 |
+
},
|
| 26486 |
+
{
|
| 26487 |
+
"epoch": 4.308831908831909,
|
| 26488 |
+
"grad_norm": 0.15381856262683868,
|
| 26489 |
+
"learning_rate": 4.5995771638428355e-05,
|
| 26490 |
+
"loss": 0.979,
|
| 26491 |
+
"step": 3783
|
| 26492 |
+
},
|
| 26493 |
+
{
|
| 26494 |
+
"epoch": 4.30997150997151,
|
| 26495 |
+
"grad_norm": 0.1749049872159958,
|
| 26496 |
+
"learning_rate": 4.5993242045950304e-05,
|
| 26497 |
+
"loss": 0.7201,
|
| 26498 |
+
"step": 3784
|
| 26499 |
+
},
|
| 26500 |
+
{
|
| 26501 |
+
"epoch": 4.311111111111111,
|
| 26502 |
+
"grad_norm": 0.1437012404203415,
|
| 26503 |
+
"learning_rate": 4.599071172431922e-05,
|
| 26504 |
+
"loss": 0.7694,
|
| 26505 |
+
"step": 3785
|
| 26506 |
+
},
|
| 26507 |
+
{
|
| 26508 |
+
"epoch": 4.312250712250712,
|
| 26509 |
+
"grad_norm": 0.1626712679862976,
|
| 26510 |
+
"learning_rate": 4.5988180673623e-05,
|
| 26511 |
+
"loss": 0.7283,
|
| 26512 |
+
"step": 3786
|
| 26513 |
+
},
|
| 26514 |
+
{
|
| 26515 |
+
"epoch": 4.313390313390314,
|
| 26516 |
+
"grad_norm": 0.18755604326725006,
|
| 26517 |
+
"learning_rate": 4.5985648893949554e-05,
|
| 26518 |
+
"loss": 0.595,
|
| 26519 |
+
"step": 3787
|
| 26520 |
+
},
|
| 26521 |
+
{
|
| 26522 |
+
"epoch": 4.314529914529914,
|
| 26523 |
+
"grad_norm": 0.16814053058624268,
|
| 26524 |
+
"learning_rate": 4.5983116385386805e-05,
|
| 26525 |
+
"loss": 0.6691,
|
| 26526 |
+
"step": 3788
|
| 26527 |
+
},
|
| 26528 |
+
{
|
| 26529 |
+
"epoch": 4.315669515669516,
|
| 26530 |
+
"grad_norm": 0.15925413370132446,
|
| 26531 |
+
"learning_rate": 4.598058314802271e-05,
|
| 26532 |
+
"loss": 0.9136,
|
| 26533 |
+
"step": 3789
|
| 26534 |
+
},
|
| 26535 |
+
{
|
| 26536 |
+
"epoch": 4.316809116809117,
|
| 26537 |
+
"grad_norm": 0.1466931253671646,
|
| 26538 |
+
"learning_rate": 4.597804918194528e-05,
|
| 26539 |
+
"loss": 0.8129,
|
| 26540 |
+
"step": 3790
|
| 26541 |
+
},
|
| 26542 |
+
{
|
| 26543 |
+
"epoch": 4.317948717948718,
|
| 26544 |
+
"grad_norm": 0.1601477861404419,
|
| 26545 |
+
"learning_rate": 4.597551448724251e-05,
|
| 26546 |
+
"loss": 0.7165,
|
| 26547 |
+
"step": 3791
|
| 26548 |
+
},
|
| 26549 |
+
{
|
| 26550 |
+
"epoch": 4.319088319088319,
|
| 26551 |
+
"grad_norm": 0.17426732182502747,
|
| 26552 |
+
"learning_rate": 4.5972979064002444e-05,
|
| 26553 |
+
"loss": 0.7991,
|
| 26554 |
+
"step": 3792
|
| 26555 |
+
},
|
| 26556 |
+
{
|
| 26557 |
+
"epoch": 4.320227920227921,
|
| 26558 |
+
"grad_norm": 0.1685943603515625,
|
| 26559 |
+
"learning_rate": 4.597044291231313e-05,
|
| 26560 |
+
"loss": 0.9124,
|
| 26561 |
+
"step": 3793
|
| 26562 |
+
},
|
| 26563 |
+
{
|
| 26564 |
+
"epoch": 4.321367521367521,
|
| 26565 |
+
"grad_norm": 0.16514858603477478,
|
| 26566 |
+
"learning_rate": 4.5967906032262666e-05,
|
| 26567 |
+
"loss": 0.8468,
|
| 26568 |
+
"step": 3794
|
| 26569 |
+
},
|
| 26570 |
+
{
|
| 26571 |
+
"epoch": 4.3225071225071225,
|
| 26572 |
+
"grad_norm": 0.15124280750751495,
|
| 26573 |
+
"learning_rate": 4.596536842393916e-05,
|
| 26574 |
+
"loss": 0.7713,
|
| 26575 |
+
"step": 3795
|
| 26576 |
+
},
|
| 26577 |
+
{
|
| 26578 |
+
"epoch": 4.323646723646724,
|
| 26579 |
+
"grad_norm": 0.19503721594810486,
|
| 26580 |
+
"learning_rate": 4.596283008743075e-05,
|
| 26581 |
+
"loss": 0.5219,
|
| 26582 |
+
"step": 3796
|
| 26583 |
+
},
|
| 26584 |
+
{
|
| 26585 |
+
"epoch": 4.3247863247863245,
|
| 26586 |
+
"grad_norm": 0.1756066083908081,
|
| 26587 |
+
"learning_rate": 4.596029102282562e-05,
|
| 26588 |
+
"loss": 0.8621,
|
| 26589 |
+
"step": 3797
|
| 26590 |
+
},
|
| 26591 |
+
{
|
| 26592 |
+
"epoch": 4.325925925925926,
|
| 26593 |
+
"grad_norm": 0.1294962763786316,
|
| 26594 |
+
"learning_rate": 4.595775123021193e-05,
|
| 26595 |
+
"loss": 0.9163,
|
| 26596 |
+
"step": 3798
|
| 26597 |
+
},
|
| 26598 |
+
{
|
| 26599 |
+
"epoch": 4.327065527065527,
|
| 26600 |
+
"grad_norm": 0.14610126614570618,
|
| 26601 |
+
"learning_rate": 4.595521070967791e-05,
|
| 26602 |
+
"loss": 0.8526,
|
| 26603 |
+
"step": 3799
|
| 26604 |
+
},
|
| 26605 |
+
{
|
| 26606 |
+
"epoch": 4.328205128205128,
|
| 26607 |
+
"grad_norm": 0.15656009316444397,
|
| 26608 |
+
"learning_rate": 4.5952669461311795e-05,
|
| 26609 |
+
"loss": 0.7453,
|
| 26610 |
+
"step": 3800
|
| 26611 |
+
},
|
| 26612 |
+
{
|
| 26613 |
+
"epoch": 4.329344729344729,
|
| 26614 |
+
"grad_norm": 0.141379714012146,
|
| 26615 |
+
"learning_rate": 4.5950127485201844e-05,
|
| 26616 |
+
"loss": 0.8304,
|
| 26617 |
+
"step": 3801
|
| 26618 |
+
},
|
| 26619 |
+
{
|
| 26620 |
+
"epoch": 4.330484330484331,
|
| 26621 |
+
"grad_norm": 0.15407662093639374,
|
| 26622 |
+
"learning_rate": 4.5947584781436354e-05,
|
| 26623 |
+
"loss": 0.6151,
|
| 26624 |
+
"step": 3802
|
| 26625 |
+
},
|
| 26626 |
+
{
|
| 26627 |
+
"epoch": 4.331623931623931,
|
| 26628 |
+
"grad_norm": 0.18312354385852814,
|
| 26629 |
+
"learning_rate": 4.594504135010364e-05,
|
| 26630 |
+
"loss": 0.6962,
|
| 26631 |
+
"step": 3803
|
| 26632 |
+
},
|
| 26633 |
+
{
|
| 26634 |
+
"epoch": 4.332763532763533,
|
| 26635 |
+
"grad_norm": 0.162358358502388,
|
| 26636 |
+
"learning_rate": 4.5942497191292045e-05,
|
| 26637 |
+
"loss": 0.741,
|
| 26638 |
+
"step": 3804
|
| 26639 |
+
},
|
| 26640 |
+
{
|
| 26641 |
+
"epoch": 4.333903133903134,
|
| 26642 |
+
"grad_norm": 0.13303545117378235,
|
| 26643 |
+
"learning_rate": 4.5939952305089923e-05,
|
| 26644 |
+
"loss": 0.9005,
|
| 26645 |
+
"step": 3805
|
| 26646 |
+
},
|
| 26647 |
+
{
|
| 26648 |
+
"epoch": 4.335042735042735,
|
| 26649 |
+
"grad_norm": 0.16208922863006592,
|
| 26650 |
+
"learning_rate": 4.593740669158568e-05,
|
| 26651 |
+
"loss": 0.7788,
|
| 26652 |
+
"step": 3806
|
| 26653 |
+
},
|
| 26654 |
+
{
|
| 26655 |
+
"epoch": 4.336182336182336,
|
| 26656 |
+
"grad_norm": 0.21589314937591553,
|
| 26657 |
+
"learning_rate": 4.5934860350867715e-05,
|
| 26658 |
+
"loss": 0.5786,
|
| 26659 |
+
"step": 3807
|
| 26660 |
+
},
|
| 26661 |
+
{
|
| 26662 |
+
"epoch": 4.337321937321938,
|
| 26663 |
+
"grad_norm": 0.17553921043872833,
|
| 26664 |
+
"learning_rate": 4.593231328302449e-05,
|
| 26665 |
+
"loss": 0.8094,
|
| 26666 |
+
"step": 3808
|
| 26667 |
+
},
|
| 26668 |
+
{
|
| 26669 |
+
"epoch": 4.338461538461538,
|
| 26670 |
+
"grad_norm": 0.15923000872135162,
|
| 26671 |
+
"learning_rate": 4.592976548814445e-05,
|
| 26672 |
+
"loss": 0.8614,
|
| 26673 |
+
"step": 3809
|
| 26674 |
+
},
|
| 26675 |
+
{
|
| 26676 |
+
"epoch": 4.33960113960114,
|
| 26677 |
+
"grad_norm": 0.16006356477737427,
|
| 26678 |
+
"learning_rate": 4.59272169663161e-05,
|
| 26679 |
+
"loss": 0.8729,
|
| 26680 |
+
"step": 3810
|
| 26681 |
+
},
|
| 26682 |
+
{
|
| 26683 |
+
"epoch": 4.340740740740741,
|
| 26684 |
+
"grad_norm": 0.17715489864349365,
|
| 26685 |
+
"learning_rate": 4.5924667717627964e-05,
|
| 26686 |
+
"loss": 0.733,
|
| 26687 |
+
"step": 3811
|
| 26688 |
+
},
|
| 26689 |
+
{
|
| 26690 |
+
"epoch": 4.3418803418803416,
|
| 26691 |
+
"grad_norm": 0.13069522380828857,
|
| 26692 |
+
"learning_rate": 4.5922117742168566e-05,
|
| 26693 |
+
"loss": 1.0037,
|
| 26694 |
+
"step": 3812
|
| 26695 |
+
},
|
| 26696 |
+
{
|
| 26697 |
+
"epoch": 4.343019943019943,
|
| 26698 |
+
"grad_norm": 0.20016714930534363,
|
| 26699 |
+
"learning_rate": 4.5919567040026484e-05,
|
| 26700 |
+
"loss": 0.5621,
|
| 26701 |
+
"step": 3813
|
| 26702 |
+
},
|
| 26703 |
+
{
|
| 26704 |
+
"epoch": 4.344159544159544,
|
| 26705 |
+
"grad_norm": 0.16844871640205383,
|
| 26706 |
+
"learning_rate": 4.591701561129031e-05,
|
| 26707 |
+
"loss": 0.6644,
|
| 26708 |
+
"step": 3814
|
| 26709 |
+
},
|
| 26710 |
+
{
|
| 26711 |
+
"epoch": 4.345299145299145,
|
| 26712 |
+
"grad_norm": 0.16659404337406158,
|
| 26713 |
+
"learning_rate": 4.591446345604866e-05,
|
| 26714 |
+
"loss": 0.885,
|
| 26715 |
+
"step": 3815
|
| 26716 |
+
},
|
| 26717 |
+
{
|
| 26718 |
+
"epoch": 4.346438746438746,
|
| 26719 |
+
"grad_norm": 0.13851837813854218,
|
| 26720 |
+
"learning_rate": 4.591191057439018e-05,
|
| 26721 |
+
"loss": 0.8889,
|
| 26722 |
+
"step": 3816
|
| 26723 |
+
},
|
| 26724 |
+
{
|
| 26725 |
+
"epoch": 4.347578347578348,
|
| 26726 |
+
"grad_norm": 0.14378002285957336,
|
| 26727 |
+
"learning_rate": 4.590935696640354e-05,
|
| 26728 |
+
"loss": 0.8223,
|
| 26729 |
+
"step": 3817
|
| 26730 |
+
},
|
| 26731 |
+
{
|
| 26732 |
+
"epoch": 4.348717948717948,
|
| 26733 |
+
"grad_norm": 0.1335776001214981,
|
| 26734 |
+
"learning_rate": 4.5906802632177434e-05,
|
| 26735 |
+
"loss": 0.8589,
|
| 26736 |
+
"step": 3818
|
| 26737 |
+
},
|
| 26738 |
+
{
|
| 26739 |
+
"epoch": 4.34985754985755,
|
| 26740 |
+
"grad_norm": 0.15075504779815674,
|
| 26741 |
+
"learning_rate": 4.590424757180057e-05,
|
| 26742 |
+
"loss": 0.8288,
|
| 26743 |
+
"step": 3819
|
| 26744 |
+
},
|
| 26745 |
+
{
|
| 26746 |
+
"epoch": 4.350997150997151,
|
| 26747 |
+
"grad_norm": 0.17949166893959045,
|
| 26748 |
+
"learning_rate": 4.590169178536171e-05,
|
| 26749 |
+
"loss": 0.7027,
|
| 26750 |
+
"step": 3820
|
| 26751 |
+
},
|
| 26752 |
+
{
|
| 26753 |
+
"epoch": 4.352136752136752,
|
| 26754 |
+
"grad_norm": 0.1760595142841339,
|
| 26755 |
+
"learning_rate": 4.589913527294961e-05,
|
| 26756 |
+
"loss": 0.8434,
|
| 26757 |
+
"step": 3821
|
| 26758 |
+
},
|
| 26759 |
+
{
|
| 26760 |
+
"epoch": 4.353276353276353,
|
| 26761 |
+
"grad_norm": 0.1611568033695221,
|
| 26762 |
+
"learning_rate": 4.589657803465308e-05,
|
| 26763 |
+
"loss": 0.8463,
|
| 26764 |
+
"step": 3822
|
| 26765 |
+
},
|
| 26766 |
+
{
|
| 26767 |
+
"epoch": 4.354415954415955,
|
| 26768 |
+
"grad_norm": 0.1709708869457245,
|
| 26769 |
+
"learning_rate": 4.5894020070560914e-05,
|
| 26770 |
+
"loss": 0.7497,
|
| 26771 |
+
"step": 3823
|
| 26772 |
+
},
|
| 26773 |
+
{
|
| 26774 |
+
"epoch": 4.355555555555555,
|
| 26775 |
+
"grad_norm": 0.19568359851837158,
|
| 26776 |
+
"learning_rate": 4.589146138076198e-05,
|
| 26777 |
+
"loss": 0.7625,
|
| 26778 |
+
"step": 3824
|
| 26779 |
+
},
|
| 26780 |
+
{
|
| 26781 |
+
"epoch": 4.356695156695157,
|
| 26782 |
+
"grad_norm": 0.1605634093284607,
|
| 26783 |
+
"learning_rate": 4.588890196534513e-05,
|
| 26784 |
+
"loss": 0.851,
|
| 26785 |
+
"step": 3825
|
| 26786 |
+
},
|
| 26787 |
+
{
|
| 26788 |
+
"epoch": 4.357834757834758,
|
| 26789 |
+
"grad_norm": 0.1573217362165451,
|
| 26790 |
+
"learning_rate": 4.588634182439928e-05,
|
| 26791 |
+
"loss": 0.8307,
|
| 26792 |
+
"step": 3826
|
| 26793 |
+
},
|
| 26794 |
+
{
|
| 26795 |
+
"epoch": 4.358974358974359,
|
| 26796 |
+
"grad_norm": 0.15628954768180847,
|
| 26797 |
+
"learning_rate": 4.588378095801335e-05,
|
| 26798 |
+
"loss": 0.8441,
|
| 26799 |
+
"step": 3827
|
| 26800 |
+
},
|
| 26801 |
+
{
|
| 26802 |
+
"epoch": 4.36011396011396,
|
| 26803 |
+
"grad_norm": 0.14356233179569244,
|
| 26804 |
+
"learning_rate": 4.588121936627626e-05,
|
| 26805 |
+
"loss": 0.9888,
|
| 26806 |
+
"step": 3828
|
| 26807 |
+
},
|
| 26808 |
+
{
|
| 26809 |
+
"epoch": 4.3612535612535615,
|
| 26810 |
+
"grad_norm": 0.1678401380777359,
|
| 26811 |
+
"learning_rate": 4.5878657049276996e-05,
|
| 26812 |
+
"loss": 0.6547,
|
| 26813 |
+
"step": 3829
|
| 26814 |
+
},
|
| 26815 |
+
{
|
| 26816 |
+
"epoch": 4.362393162393162,
|
| 26817 |
+
"grad_norm": 0.17374159395694733,
|
| 26818 |
+
"learning_rate": 4.587609400710456e-05,
|
| 26819 |
+
"loss": 0.7695,
|
| 26820 |
+
"step": 3830
|
| 26821 |
+
},
|
| 26822 |
+
{
|
| 26823 |
+
"epoch": 4.363532763532763,
|
| 26824 |
+
"grad_norm": 0.1446637511253357,
|
| 26825 |
+
"learning_rate": 4.5873530239847986e-05,
|
| 26826 |
+
"loss": 0.8876,
|
| 26827 |
+
"step": 3831
|
| 26828 |
+
},
|
| 26829 |
+
{
|
| 26830 |
+
"epoch": 4.364672364672365,
|
| 26831 |
+
"grad_norm": 0.14191895723342896,
|
| 26832 |
+
"learning_rate": 4.5870965747596286e-05,
|
| 26833 |
+
"loss": 0.8637,
|
| 26834 |
+
"step": 3832
|
| 26835 |
+
},
|
| 26836 |
+
{
|
| 26837 |
+
"epoch": 4.365811965811965,
|
| 26838 |
+
"grad_norm": 0.18284063041210175,
|
| 26839 |
+
"learning_rate": 4.586840053043856e-05,
|
| 26840 |
+
"loss": 0.7768,
|
| 26841 |
+
"step": 3833
|
| 26842 |
+
},
|
| 26843 |
+
{
|
| 26844 |
+
"epoch": 4.366951566951567,
|
| 26845 |
+
"grad_norm": 0.13698497414588928,
|
| 26846 |
+
"learning_rate": 4.5865834588463885e-05,
|
| 26847 |
+
"loss": 0.8514,
|
| 26848 |
+
"step": 3834
|
| 26849 |
+
},
|
| 26850 |
+
{
|
| 26851 |
+
"epoch": 4.368091168091168,
|
| 26852 |
+
"grad_norm": 0.21228642761707306,
|
| 26853 |
+
"learning_rate": 4.58632679217614e-05,
|
| 26854 |
+
"loss": 0.5781,
|
| 26855 |
+
"step": 3835
|
| 26856 |
+
},
|
| 26857 |
+
{
|
| 26858 |
+
"epoch": 4.36923076923077,
|
| 26859 |
+
"grad_norm": 0.15032905340194702,
|
| 26860 |
+
"learning_rate": 4.5860700530420244e-05,
|
| 26861 |
+
"loss": 0.8327,
|
| 26862 |
+
"step": 3836
|
| 26863 |
+
},
|
| 26864 |
+
{
|
| 26865 |
+
"epoch": 4.37037037037037,
|
| 26866 |
+
"grad_norm": 0.15202458202838898,
|
| 26867 |
+
"learning_rate": 4.58581324145296e-05,
|
| 26868 |
+
"loss": 0.8469,
|
| 26869 |
+
"step": 3837
|
| 26870 |
+
},
|
| 26871 |
+
{
|
| 26872 |
+
"epoch": 4.371509971509972,
|
| 26873 |
+
"grad_norm": 0.16406792402267456,
|
| 26874 |
+
"learning_rate": 4.5855563574178645e-05,
|
| 26875 |
+
"loss": 0.6976,
|
| 26876 |
+
"step": 3838
|
| 26877 |
+
},
|
| 26878 |
+
{
|
| 26879 |
+
"epoch": 4.372649572649573,
|
| 26880 |
+
"grad_norm": 0.1301998645067215,
|
| 26881 |
+
"learning_rate": 4.585299400945662e-05,
|
| 26882 |
+
"loss": 0.9388,
|
| 26883 |
+
"step": 3839
|
| 26884 |
+
},
|
| 26885 |
+
{
|
| 26886 |
+
"epoch": 4.373789173789174,
|
| 26887 |
+
"grad_norm": 0.1878965049982071,
|
| 26888 |
+
"learning_rate": 4.5850423720452764e-05,
|
| 26889 |
+
"loss": 0.7147,
|
| 26890 |
+
"step": 3840
|
| 26891 |
+
},
|
| 26892 |
+
{
|
| 26893 |
+
"epoch": 4.374928774928775,
|
| 26894 |
+
"grad_norm": 0.14204874634742737,
|
| 26895 |
+
"learning_rate": 4.584785270725636e-05,
|
| 26896 |
+
"loss": 0.8793,
|
| 26897 |
+
"step": 3841
|
| 26898 |
+
},
|
| 26899 |
+
{
|
| 26900 |
+
"epoch": 4.3760683760683765,
|
| 26901 |
+
"grad_norm": 0.16943851113319397,
|
| 26902 |
+
"learning_rate": 4.584528096995669e-05,
|
| 26903 |
+
"loss": 0.6463,
|
| 26904 |
+
"step": 3842
|
| 26905 |
+
},
|
| 26906 |
+
{
|
| 26907 |
+
"epoch": 4.377207977207977,
|
| 26908 |
+
"grad_norm": 0.17809520661830902,
|
| 26909 |
+
"learning_rate": 4.58427085086431e-05,
|
| 26910 |
+
"loss": 0.7687,
|
| 26911 |
+
"step": 3843
|
| 26912 |
+
},
|
| 26913 |
+
{
|
| 26914 |
+
"epoch": 4.3783475783475785,
|
| 26915 |
+
"grad_norm": 0.16223205626010895,
|
| 26916 |
+
"learning_rate": 4.584013532340491e-05,
|
| 26917 |
+
"loss": 0.892,
|
| 26918 |
+
"step": 3844
|
| 26919 |
+
},
|
| 26920 |
+
{
|
| 26921 |
+
"epoch": 4.37948717948718,
|
| 26922 |
+
"grad_norm": 0.19467252492904663,
|
| 26923 |
+
"learning_rate": 4.583756141433152e-05,
|
| 26924 |
+
"loss": 0.7755,
|
| 26925 |
+
"step": 3845
|
| 26926 |
+
},
|
| 26927 |
+
{
|
| 26928 |
+
"epoch": 4.3806267806267805,
|
| 26929 |
+
"grad_norm": 0.18585580587387085,
|
| 26930 |
+
"learning_rate": 4.583498678151231e-05,
|
| 26931 |
+
"loss": 0.6314,
|
| 26932 |
+
"step": 3846
|
| 26933 |
+
},
|
| 26934 |
+
{
|
| 26935 |
+
"epoch": 4.381766381766382,
|
| 26936 |
+
"grad_norm": 0.1589478999376297,
|
| 26937 |
+
"learning_rate": 4.5832411425036724e-05,
|
| 26938 |
+
"loss": 0.7406,
|
| 26939 |
+
"step": 3847
|
| 26940 |
+
},
|
| 26941 |
+
{
|
| 26942 |
+
"epoch": 4.382905982905983,
|
| 26943 |
+
"grad_norm": 0.17925570905208588,
|
| 26944 |
+
"learning_rate": 4.582983534499419e-05,
|
| 26945 |
+
"loss": 0.6538,
|
| 26946 |
+
"step": 3848
|
| 26947 |
+
},
|
| 26948 |
+
{
|
| 26949 |
+
"epoch": 4.384045584045584,
|
| 26950 |
+
"grad_norm": 0.16629046201705933,
|
| 26951 |
+
"learning_rate": 4.58272585414742e-05,
|
| 26952 |
+
"loss": 0.7406,
|
| 26953 |
+
"step": 3849
|
| 26954 |
+
},
|
| 26955 |
+
{
|
| 26956 |
+
"epoch": 4.385185185185185,
|
| 26957 |
+
"grad_norm": 0.16629096865653992,
|
| 26958 |
+
"learning_rate": 4.582468101456624e-05,
|
| 26959 |
+
"loss": 0.8754,
|
| 26960 |
+
"step": 3850
|
| 26961 |
+
},
|
| 26962 |
+
{
|
| 26963 |
+
"epoch": 4.386324786324787,
|
| 26964 |
+
"grad_norm": 0.1374756097793579,
|
| 26965 |
+
"learning_rate": 4.582210276435984e-05,
|
| 26966 |
+
"loss": 0.8782,
|
| 26967 |
+
"step": 3851
|
| 26968 |
+
},
|
| 26969 |
+
{
|
| 26970 |
+
"epoch": 4.387464387464387,
|
| 26971 |
+
"grad_norm": 0.2001880705356598,
|
| 26972 |
+
"learning_rate": 4.581952379094456e-05,
|
| 26973 |
+
"loss": 0.676,
|
| 26974 |
+
"step": 3852
|
| 26975 |
+
},
|
| 26976 |
+
{
|
| 26977 |
+
"epoch": 4.388603988603989,
|
| 26978 |
+
"grad_norm": 0.16196000576019287,
|
| 26979 |
+
"learning_rate": 4.581694409440995e-05,
|
| 26980 |
+
"loss": 0.7972,
|
| 26981 |
+
"step": 3853
|
| 26982 |
+
},
|
| 26983 |
+
{
|
| 26984 |
+
"epoch": 4.38974358974359,
|
| 26985 |
+
"grad_norm": 0.1636325716972351,
|
| 26986 |
+
"learning_rate": 4.581436367484564e-05,
|
| 26987 |
+
"loss": 0.7659,
|
| 26988 |
+
"step": 3854
|
| 26989 |
+
},
|
| 26990 |
+
{
|
| 26991 |
+
"epoch": 4.390883190883191,
|
| 26992 |
+
"grad_norm": 0.14268454909324646,
|
| 26993 |
+
"learning_rate": 4.581178253234123e-05,
|
| 26994 |
+
"loss": 0.7647,
|
| 26995 |
+
"step": 3855
|
| 26996 |
+
},
|
| 26997 |
+
{
|
| 26998 |
+
"epoch": 4.392022792022792,
|
| 26999 |
+
"grad_norm": 0.17906972765922546,
|
| 27000 |
+
"learning_rate": 4.5809200666986386e-05,
|
| 27001 |
+
"loss": 0.7858,
|
| 27002 |
+
"step": 3856
|
| 27003 |
+
},
|
| 27004 |
+
{
|
| 27005 |
+
"epoch": 4.3931623931623935,
|
| 27006 |
+
"grad_norm": 0.15701225399971008,
|
| 27007 |
+
"learning_rate": 4.580661807887077e-05,
|
| 27008 |
+
"loss": 0.6254,
|
| 27009 |
+
"step": 3857
|
| 27010 |
+
},
|
| 27011 |
+
{
|
| 27012 |
+
"epoch": 4.394301994301994,
|
| 27013 |
+
"grad_norm": 0.18031233549118042,
|
| 27014 |
+
"learning_rate": 4.580403476808409e-05,
|
| 27015 |
+
"loss": 0.8396,
|
| 27016 |
+
"step": 3858
|
| 27017 |
+
},
|
| 27018 |
+
{
|
| 27019 |
+
"epoch": 4.3954415954415955,
|
| 27020 |
+
"grad_norm": 0.17270846664905548,
|
| 27021 |
+
"learning_rate": 4.5801450734716075e-05,
|
| 27022 |
+
"loss": 0.7001,
|
| 27023 |
+
"step": 3859
|
| 27024 |
+
},
|
| 27025 |
+
{
|
| 27026 |
+
"epoch": 4.396581196581197,
|
| 27027 |
+
"grad_norm": 0.15081731975078583,
|
| 27028 |
+
"learning_rate": 4.579886597885648e-05,
|
| 27029 |
+
"loss": 0.9368,
|
| 27030 |
+
"step": 3860
|
| 27031 |
+
},
|
| 27032 |
+
{
|
| 27033 |
+
"epoch": 4.3977207977207975,
|
| 27034 |
+
"grad_norm": 0.16598904132843018,
|
| 27035 |
+
"learning_rate": 4.5796280500595055e-05,
|
| 27036 |
+
"loss": 0.8393,
|
| 27037 |
+
"step": 3861
|
| 27038 |
+
},
|
| 27039 |
+
{
|
| 27040 |
+
"epoch": 4.398860398860399,
|
| 27041 |
+
"grad_norm": 0.16655343770980835,
|
| 27042 |
+
"learning_rate": 4.579369430002163e-05,
|
| 27043 |
+
"loss": 0.7856,
|
| 27044 |
+
"step": 3862
|
| 27045 |
+
},
|
| 27046 |
+
{
|
| 27047 |
+
"epoch": 4.4,
|
| 27048 |
+
"grad_norm": 0.1844964474439621,
|
| 27049 |
+
"learning_rate": 4.5791107377226017e-05,
|
| 27050 |
+
"loss": 0.8161,
|
| 27051 |
+
"step": 3863
|
| 27052 |
+
},
|
| 27053 |
+
{
|
| 27054 |
+
"epoch": 4.401139601139601,
|
| 27055 |
+
"grad_norm": 0.15868549048900604,
|
| 27056 |
+
"learning_rate": 4.578851973229806e-05,
|
| 27057 |
+
"loss": 0.9674,
|
| 27058 |
+
"step": 3864
|
| 27059 |
+
},
|
| 27060 |
+
{
|
| 27061 |
+
"epoch": 4.402279202279202,
|
| 27062 |
+
"grad_norm": 0.17895255982875824,
|
| 27063 |
+
"learning_rate": 4.578593136532766e-05,
|
| 27064 |
+
"loss": 0.8309,
|
| 27065 |
+
"step": 3865
|
| 27066 |
+
},
|
| 27067 |
+
{
|
| 27068 |
+
"epoch": 4.403418803418804,
|
| 27069 |
+
"grad_norm": 0.16036298871040344,
|
| 27070 |
+
"learning_rate": 4.578334227640469e-05,
|
| 27071 |
+
"loss": 0.8343,
|
| 27072 |
+
"step": 3866
|
| 27073 |
+
},
|
| 27074 |
+
{
|
| 27075 |
+
"epoch": 4.404558404558404,
|
| 27076 |
+
"grad_norm": 0.15244902670383453,
|
| 27077 |
+
"learning_rate": 4.578075246561909e-05,
|
| 27078 |
+
"loss": 0.8033,
|
| 27079 |
+
"step": 3867
|
| 27080 |
+
},
|
| 27081 |
+
{
|
| 27082 |
+
"epoch": 4.405698005698006,
|
| 27083 |
+
"grad_norm": 0.18762405216693878,
|
| 27084 |
+
"learning_rate": 4.577816193306081e-05,
|
| 27085 |
+
"loss": 0.7284,
|
| 27086 |
+
"step": 3868
|
| 27087 |
+
},
|
| 27088 |
+
{
|
| 27089 |
+
"epoch": 4.406837606837607,
|
| 27090 |
+
"grad_norm": 0.17961227893829346,
|
| 27091 |
+
"learning_rate": 4.5775570678819835e-05,
|
| 27092 |
+
"loss": 0.8169,
|
| 27093 |
+
"step": 3869
|
| 27094 |
+
},
|
| 27095 |
+
{
|
| 27096 |
+
"epoch": 4.407977207977208,
|
| 27097 |
+
"grad_norm": 0.16521014273166656,
|
| 27098 |
+
"learning_rate": 4.5772978702986155e-05,
|
| 27099 |
+
"loss": 0.8817,
|
| 27100 |
+
"step": 3870
|
| 27101 |
+
},
|
| 27102 |
+
{
|
| 27103 |
+
"epoch": 4.409116809116809,
|
| 27104 |
+
"grad_norm": 0.16002601385116577,
|
| 27105 |
+
"learning_rate": 4.577038600564979e-05,
|
| 27106 |
+
"loss": 0.8827,
|
| 27107 |
+
"step": 3871
|
| 27108 |
+
},
|
| 27109 |
+
{
|
| 27110 |
+
"epoch": 4.410256410256411,
|
| 27111 |
+
"grad_norm": 0.20933003723621368,
|
| 27112 |
+
"learning_rate": 4.5767792586900805e-05,
|
| 27113 |
+
"loss": 0.5519,
|
| 27114 |
+
"step": 3872
|
| 27115 |
+
},
|
| 27116 |
+
{
|
| 27117 |
+
"epoch": 4.411396011396011,
|
| 27118 |
+
"grad_norm": 0.16851255297660828,
|
| 27119 |
+
"learning_rate": 4.5765198446829275e-05,
|
| 27120 |
+
"loss": 0.9285,
|
| 27121 |
+
"step": 3873
|
| 27122 |
+
},
|
| 27123 |
+
{
|
| 27124 |
+
"epoch": 4.4125356125356126,
|
| 27125 |
+
"grad_norm": 0.16128350794315338,
|
| 27126 |
+
"learning_rate": 4.576260358552529e-05,
|
| 27127 |
+
"loss": 0.8966,
|
| 27128 |
+
"step": 3874
|
| 27129 |
+
},
|
| 27130 |
+
{
|
| 27131 |
+
"epoch": 4.413675213675214,
|
| 27132 |
+
"grad_norm": 0.13369476795196533,
|
| 27133 |
+
"learning_rate": 4.576000800307899e-05,
|
| 27134 |
+
"loss": 0.8694,
|
| 27135 |
+
"step": 3875
|
| 27136 |
+
},
|
| 27137 |
+
{
|
| 27138 |
+
"epoch": 4.4148148148148145,
|
| 27139 |
+
"grad_norm": 0.14267423748970032,
|
| 27140 |
+
"learning_rate": 4.5757411699580524e-05,
|
| 27141 |
+
"loss": 0.8961,
|
| 27142 |
+
"step": 3876
|
| 27143 |
+
},
|
| 27144 |
+
{
|
| 27145 |
+
"epoch": 4.415954415954416,
|
| 27146 |
+
"grad_norm": 0.12827791273593903,
|
| 27147 |
+
"learning_rate": 4.5754814675120065e-05,
|
| 27148 |
+
"loss": 0.9615,
|
| 27149 |
+
"step": 3877
|
| 27150 |
+
},
|
| 27151 |
+
{
|
| 27152 |
+
"epoch": 4.417094017094017,
|
| 27153 |
+
"grad_norm": 0.17608094215393066,
|
| 27154 |
+
"learning_rate": 4.575221692978781e-05,
|
| 27155 |
+
"loss": 0.8662,
|
| 27156 |
+
"step": 3878
|
| 27157 |
+
},
|
| 27158 |
+
{
|
| 27159 |
+
"epoch": 4.418233618233618,
|
| 27160 |
+
"grad_norm": 0.13462728261947632,
|
| 27161 |
+
"learning_rate": 4.5749618463673996e-05,
|
| 27162 |
+
"loss": 0.8707,
|
| 27163 |
+
"step": 3879
|
| 27164 |
+
},
|
| 27165 |
+
{
|
| 27166 |
+
"epoch": 4.419373219373219,
|
| 27167 |
+
"grad_norm": 0.13011795282363892,
|
| 27168 |
+
"learning_rate": 4.574701927686887e-05,
|
| 27169 |
+
"loss": 0.9188,
|
| 27170 |
+
"step": 3880
|
| 27171 |
+
},
|
| 27172 |
+
{
|
| 27173 |
+
"epoch": 4.420512820512821,
|
| 27174 |
+
"grad_norm": 0.1956792026758194,
|
| 27175 |
+
"learning_rate": 4.5744419369462714e-05,
|
| 27176 |
+
"loss": 0.7091,
|
| 27177 |
+
"step": 3881
|
| 27178 |
+
},
|
| 27179 |
+
{
|
| 27180 |
+
"epoch": 4.421652421652421,
|
| 27181 |
+
"grad_norm": 0.17394132912158966,
|
| 27182 |
+
"learning_rate": 4.574181874154583e-05,
|
| 27183 |
+
"loss": 0.6981,
|
| 27184 |
+
"step": 3882
|
| 27185 |
+
},
|
| 27186 |
+
{
|
| 27187 |
+
"epoch": 4.422792022792023,
|
| 27188 |
+
"grad_norm": 0.17281357944011688,
|
| 27189 |
+
"learning_rate": 4.5739217393208534e-05,
|
| 27190 |
+
"loss": 0.8199,
|
| 27191 |
+
"step": 3883
|
| 27192 |
+
},
|
| 27193 |
+
{
|
| 27194 |
+
"epoch": 4.423931623931624,
|
| 27195 |
+
"grad_norm": 0.16370278596878052,
|
| 27196 |
+
"learning_rate": 4.573661532454119e-05,
|
| 27197 |
+
"loss": 0.8011,
|
| 27198 |
+
"step": 3884
|
| 27199 |
+
},
|
| 27200 |
+
{
|
| 27201 |
+
"epoch": 4.425071225071225,
|
| 27202 |
+
"grad_norm": 0.19170215725898743,
|
| 27203 |
+
"learning_rate": 4.5734012535634165e-05,
|
| 27204 |
+
"loss": 0.7614,
|
| 27205 |
+
"step": 3885
|
| 27206 |
+
},
|
| 27207 |
+
{
|
| 27208 |
+
"epoch": 4.426210826210826,
|
| 27209 |
+
"grad_norm": 0.15054161846637726,
|
| 27210 |
+
"learning_rate": 4.5731409026577866e-05,
|
| 27211 |
+
"loss": 0.8119,
|
| 27212 |
+
"step": 3886
|
| 27213 |
+
},
|
| 27214 |
+
{
|
| 27215 |
+
"epoch": 4.427350427350428,
|
| 27216 |
+
"grad_norm": 0.1631488800048828,
|
| 27217 |
+
"learning_rate": 4.572880479746272e-05,
|
| 27218 |
+
"loss": 0.7561,
|
| 27219 |
+
"step": 3887
|
| 27220 |
+
},
|
| 27221 |
+
{
|
| 27222 |
+
"epoch": 4.428490028490028,
|
| 27223 |
+
"grad_norm": 0.1880662888288498,
|
| 27224 |
+
"learning_rate": 4.572619984837918e-05,
|
| 27225 |
+
"loss": 0.7763,
|
| 27226 |
+
"step": 3888
|
| 27227 |
+
},
|
| 27228 |
+
{
|
| 27229 |
+
"epoch": 4.42962962962963,
|
| 27230 |
+
"grad_norm": 0.16619880497455597,
|
| 27231 |
+
"learning_rate": 4.572359417941772e-05,
|
| 27232 |
+
"loss": 0.8941,
|
| 27233 |
+
"step": 3889
|
| 27234 |
+
},
|
| 27235 |
+
{
|
| 27236 |
+
"epoch": 4.430769230769231,
|
| 27237 |
+
"grad_norm": 0.14971984922885895,
|
| 27238 |
+
"learning_rate": 4.572098779066884e-05,
|
| 27239 |
+
"loss": 0.8543,
|
| 27240 |
+
"step": 3890
|
| 27241 |
+
},
|
| 27242 |
+
{
|
| 27243 |
+
"epoch": 4.431908831908832,
|
| 27244 |
+
"grad_norm": 0.15457306802272797,
|
| 27245 |
+
"learning_rate": 4.571838068222308e-05,
|
| 27246 |
+
"loss": 0.9068,
|
| 27247 |
+
"step": 3891
|
| 27248 |
+
},
|
| 27249 |
+
{
|
| 27250 |
+
"epoch": 4.433048433048433,
|
| 27251 |
+
"grad_norm": 0.1719190776348114,
|
| 27252 |
+
"learning_rate": 4.571577285417098e-05,
|
| 27253 |
+
"loss": 0.78,
|
| 27254 |
+
"step": 3892
|
| 27255 |
+
},
|
| 27256 |
+
{
|
| 27257 |
+
"epoch": 4.434188034188034,
|
| 27258 |
+
"grad_norm": 0.14716239273548126,
|
| 27259 |
+
"learning_rate": 4.571316430660312e-05,
|
| 27260 |
+
"loss": 0.9203,
|
| 27261 |
+
"step": 3893
|
| 27262 |
+
},
|
| 27263 |
+
{
|
| 27264 |
+
"epoch": 4.435327635327635,
|
| 27265 |
+
"grad_norm": 0.14677460491657257,
|
| 27266 |
+
"learning_rate": 4.5710555039610106e-05,
|
| 27267 |
+
"loss": 0.7262,
|
| 27268 |
+
"step": 3894
|
| 27269 |
+
},
|
| 27270 |
+
{
|
| 27271 |
+
"epoch": 4.436467236467236,
|
| 27272 |
+
"grad_norm": 0.14483967423439026,
|
| 27273 |
+
"learning_rate": 4.570794505328256e-05,
|
| 27274 |
+
"loss": 0.8542,
|
| 27275 |
+
"step": 3895
|
| 27276 |
+
},
|
| 27277 |
+
{
|
| 27278 |
+
"epoch": 4.437606837606838,
|
| 27279 |
+
"grad_norm": 0.16969621181488037,
|
| 27280 |
+
"learning_rate": 4.570533434771113e-05,
|
| 27281 |
+
"loss": 0.86,
|
| 27282 |
+
"step": 3896
|
| 27283 |
+
},
|
| 27284 |
+
{
|
| 27285 |
+
"epoch": 4.438746438746438,
|
| 27286 |
+
"grad_norm": 0.15677432715892792,
|
| 27287 |
+
"learning_rate": 4.57027229229865e-05,
|
| 27288 |
+
"loss": 0.946,
|
| 27289 |
+
"step": 3897
|
| 27290 |
+
},
|
| 27291 |
+
{
|
| 27292 |
+
"epoch": 4.43988603988604,
|
| 27293 |
+
"grad_norm": 0.13845199346542358,
|
| 27294 |
+
"learning_rate": 4.570011077919937e-05,
|
| 27295 |
+
"loss": 0.9291,
|
| 27296 |
+
"step": 3898
|
| 27297 |
+
},
|
| 27298 |
+
{
|
| 27299 |
+
"epoch": 4.441025641025641,
|
| 27300 |
+
"grad_norm": 0.1764078140258789,
|
| 27301 |
+
"learning_rate": 4.5697497916440466e-05,
|
| 27302 |
+
"loss": 0.8655,
|
| 27303 |
+
"step": 3899
|
| 27304 |
+
},
|
| 27305 |
+
{
|
| 27306 |
+
"epoch": 4.442165242165242,
|
| 27307 |
+
"grad_norm": 0.1658494621515274,
|
| 27308 |
+
"learning_rate": 4.5694884334800545e-05,
|
| 27309 |
+
"loss": 0.7908,
|
| 27310 |
+
"step": 3900
|
| 27311 |
}
|
| 27312 |
],
|
| 27313 |
"logging_steps": 1,
|
|
|
|
| 27327 |
"attributes": {}
|
| 27328 |
}
|
| 27329 |
},
|
| 27330 |
+
"total_flos": 2.1807216636539535e+19,
|
| 27331 |
"train_batch_size": 8,
|
| 27332 |
"trial_name": null,
|
| 27333 |
"trial_params": null
|