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 5100, 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 sha256:588669eb9e972ad3fdf3e6183f51136f13f25f1a7e733901aac30160422b7d93
|
| 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 sha256:2a8617eabb8df4eff80edaa559aa286bbf527e02f149879325a1a36db77b703f
|
| 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 sha256:085620e8d7934df3d1ed8a46d582674c90af05eefe71b6c5c322ef6fee4dd435
|
| 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": 5.
|
| 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,
|
|
@@ -33608,6 +33608,2106 @@
|
|
| 33608 |
"learning_rate": 4.3062924597148974e-05,
|
| 33609 |
"loss": 0.7352,
|
| 33610 |
"step": 4800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33611 |
}
|
| 33612 |
],
|
| 33613 |
"logging_steps": 1,
|
|
@@ -33627,7 +35727,7 @@
|
|
| 33627 |
"attributes": {}
|
| 33628 |
}
|
| 33629 |
},
|
| 33630 |
-
"total_flos": 2.
|
| 33631 |
"train_batch_size": 8,
|
| 33632 |
"trial_name": null,
|
| 33633 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.8091168091168095,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 33608 |
"learning_rate": 4.3062924597148974e-05,
|
| 33609 |
"loss": 0.7352,
|
| 33610 |
"step": 4800
|
| 33611 |
+
},
|
| 33612 |
+
{
|
| 33613 |
+
"epoch": 5.4683760683760685,
|
| 33614 |
+
"grad_norm": 0.17996075749397278,
|
| 33615 |
+
"learning_rate": 4.305970314382714e-05,
|
| 33616 |
+
"loss": 0.9359,
|
| 33617 |
+
"step": 4801
|
| 33618 |
+
},
|
| 33619 |
+
{
|
| 33620 |
+
"epoch": 5.46951566951567,
|
| 33621 |
+
"grad_norm": 0.1547965258359909,
|
| 33622 |
+
"learning_rate": 4.305648106324215e-05,
|
| 33623 |
+
"loss": 0.8512,
|
| 33624 |
+
"step": 4802
|
| 33625 |
+
},
|
| 33626 |
+
{
|
| 33627 |
+
"epoch": 5.4706552706552705,
|
| 33628 |
+
"grad_norm": 0.1951674520969391,
|
| 33629 |
+
"learning_rate": 4.305325835550592e-05,
|
| 33630 |
+
"loss": 0.7304,
|
| 33631 |
+
"step": 4803
|
| 33632 |
+
},
|
| 33633 |
+
{
|
| 33634 |
+
"epoch": 5.471794871794872,
|
| 33635 |
+
"grad_norm": 0.16296637058258057,
|
| 33636 |
+
"learning_rate": 4.3050035020730385e-05,
|
| 33637 |
+
"loss": 0.8394,
|
| 33638 |
+
"step": 4804
|
| 33639 |
+
},
|
| 33640 |
+
{
|
| 33641 |
+
"epoch": 5.472934472934473,
|
| 33642 |
+
"grad_norm": 0.2014588862657547,
|
| 33643 |
+
"learning_rate": 4.304681105902749e-05,
|
| 33644 |
+
"loss": 0.7037,
|
| 33645 |
+
"step": 4805
|
| 33646 |
+
},
|
| 33647 |
+
{
|
| 33648 |
+
"epoch": 5.474074074074074,
|
| 33649 |
+
"grad_norm": 0.20429980754852295,
|
| 33650 |
+
"learning_rate": 4.304358647050922e-05,
|
| 33651 |
+
"loss": 0.8858,
|
| 33652 |
+
"step": 4806
|
| 33653 |
+
},
|
| 33654 |
+
{
|
| 33655 |
+
"epoch": 5.475213675213675,
|
| 33656 |
+
"grad_norm": 0.15735960006713867,
|
| 33657 |
+
"learning_rate": 4.3040361255287574e-05,
|
| 33658 |
+
"loss": 0.7007,
|
| 33659 |
+
"step": 4807
|
| 33660 |
+
},
|
| 33661 |
+
{
|
| 33662 |
+
"epoch": 5.476353276353277,
|
| 33663 |
+
"grad_norm": 0.16200728714466095,
|
| 33664 |
+
"learning_rate": 4.303713541347456e-05,
|
| 33665 |
+
"loss": 0.7849,
|
| 33666 |
+
"step": 4808
|
| 33667 |
+
},
|
| 33668 |
+
{
|
| 33669 |
+
"epoch": 5.477492877492877,
|
| 33670 |
+
"grad_norm": 0.16980691254138947,
|
| 33671 |
+
"learning_rate": 4.303390894518224e-05,
|
| 33672 |
+
"loss": 0.7656,
|
| 33673 |
+
"step": 4809
|
| 33674 |
+
},
|
| 33675 |
+
{
|
| 33676 |
+
"epoch": 5.478632478632479,
|
| 33677 |
+
"grad_norm": 0.18173424899578094,
|
| 33678 |
+
"learning_rate": 4.303068185052267e-05,
|
| 33679 |
+
"loss": 0.6668,
|
| 33680 |
+
"step": 4810
|
| 33681 |
+
},
|
| 33682 |
+
{
|
| 33683 |
+
"epoch": 5.47977207977208,
|
| 33684 |
+
"grad_norm": 0.18690398335456848,
|
| 33685 |
+
"learning_rate": 4.3027454129607935e-05,
|
| 33686 |
+
"loss": 0.7381,
|
| 33687 |
+
"step": 4811
|
| 33688 |
+
},
|
| 33689 |
+
{
|
| 33690 |
+
"epoch": 5.480911680911681,
|
| 33691 |
+
"grad_norm": 0.17304465174674988,
|
| 33692 |
+
"learning_rate": 4.302422578255014e-05,
|
| 33693 |
+
"loss": 0.7926,
|
| 33694 |
+
"step": 4812
|
| 33695 |
+
},
|
| 33696 |
+
{
|
| 33697 |
+
"epoch": 5.482051282051282,
|
| 33698 |
+
"grad_norm": 0.15293779969215393,
|
| 33699 |
+
"learning_rate": 4.3020996809461414e-05,
|
| 33700 |
+
"loss": 0.6334,
|
| 33701 |
+
"step": 4813
|
| 33702 |
+
},
|
| 33703 |
+
{
|
| 33704 |
+
"epoch": 5.4831908831908835,
|
| 33705 |
+
"grad_norm": 0.1855514496564865,
|
| 33706 |
+
"learning_rate": 4.301776721045392e-05,
|
| 33707 |
+
"loss": 0.787,
|
| 33708 |
+
"step": 4814
|
| 33709 |
+
},
|
| 33710 |
+
{
|
| 33711 |
+
"epoch": 5.484330484330484,
|
| 33712 |
+
"grad_norm": 0.17089486122131348,
|
| 33713 |
+
"learning_rate": 4.301453698563981e-05,
|
| 33714 |
+
"loss": 0.7256,
|
| 33715 |
+
"step": 4815
|
| 33716 |
+
},
|
| 33717 |
+
{
|
| 33718 |
+
"epoch": 5.4854700854700855,
|
| 33719 |
+
"grad_norm": 0.18133726716041565,
|
| 33720 |
+
"learning_rate": 4.301130613513129e-05,
|
| 33721 |
+
"loss": 0.7665,
|
| 33722 |
+
"step": 4816
|
| 33723 |
+
},
|
| 33724 |
+
{
|
| 33725 |
+
"epoch": 5.486609686609687,
|
| 33726 |
+
"grad_norm": 0.1925647258758545,
|
| 33727 |
+
"learning_rate": 4.3008074659040586e-05,
|
| 33728 |
+
"loss": 0.5695,
|
| 33729 |
+
"step": 4817
|
| 33730 |
+
},
|
| 33731 |
+
{
|
| 33732 |
+
"epoch": 5.4877492877492875,
|
| 33733 |
+
"grad_norm": 0.18926025927066803,
|
| 33734 |
+
"learning_rate": 4.300484255747992e-05,
|
| 33735 |
+
"loss": 0.6418,
|
| 33736 |
+
"step": 4818
|
| 33737 |
+
},
|
| 33738 |
+
{
|
| 33739 |
+
"epoch": 5.488888888888889,
|
| 33740 |
+
"grad_norm": 0.18105900287628174,
|
| 33741 |
+
"learning_rate": 4.300160983056156e-05,
|
| 33742 |
+
"loss": 0.7047,
|
| 33743 |
+
"step": 4819
|
| 33744 |
+
},
|
| 33745 |
+
{
|
| 33746 |
+
"epoch": 5.49002849002849,
|
| 33747 |
+
"grad_norm": 0.17401130497455597,
|
| 33748 |
+
"learning_rate": 4.29983764783978e-05,
|
| 33749 |
+
"loss": 0.7611,
|
| 33750 |
+
"step": 4820
|
| 33751 |
+
},
|
| 33752 |
+
{
|
| 33753 |
+
"epoch": 5.491168091168091,
|
| 33754 |
+
"grad_norm": 0.1705498993396759,
|
| 33755 |
+
"learning_rate": 4.29951425011009e-05,
|
| 33756 |
+
"loss": 0.7604,
|
| 33757 |
+
"step": 4821
|
| 33758 |
+
},
|
| 33759 |
+
{
|
| 33760 |
+
"epoch": 5.492307692307692,
|
| 33761 |
+
"grad_norm": 0.15717458724975586,
|
| 33762 |
+
"learning_rate": 4.2991907898783235e-05,
|
| 33763 |
+
"loss": 0.9174,
|
| 33764 |
+
"step": 4822
|
| 33765 |
+
},
|
| 33766 |
+
{
|
| 33767 |
+
"epoch": 5.493447293447294,
|
| 33768 |
+
"grad_norm": 0.16977642476558685,
|
| 33769 |
+
"learning_rate": 4.298867267155713e-05,
|
| 33770 |
+
"loss": 0.8904,
|
| 33771 |
+
"step": 4823
|
| 33772 |
+
},
|
| 33773 |
+
{
|
| 33774 |
+
"epoch": 5.494586894586894,
|
| 33775 |
+
"grad_norm": 0.1568237841129303,
|
| 33776 |
+
"learning_rate": 4.298543681953495e-05,
|
| 33777 |
+
"loss": 0.7963,
|
| 33778 |
+
"step": 4824
|
| 33779 |
+
},
|
| 33780 |
+
{
|
| 33781 |
+
"epoch": 5.495726495726496,
|
| 33782 |
+
"grad_norm": 0.18053722381591797,
|
| 33783 |
+
"learning_rate": 4.2982200342829094e-05,
|
| 33784 |
+
"loss": 0.8133,
|
| 33785 |
+
"step": 4825
|
| 33786 |
+
},
|
| 33787 |
+
{
|
| 33788 |
+
"epoch": 5.496866096866097,
|
| 33789 |
+
"grad_norm": 0.20148184895515442,
|
| 33790 |
+
"learning_rate": 4.297896324155196e-05,
|
| 33791 |
+
"loss": 0.7223,
|
| 33792 |
+
"step": 4826
|
| 33793 |
+
},
|
| 33794 |
+
{
|
| 33795 |
+
"epoch": 5.498005698005698,
|
| 33796 |
+
"grad_norm": 0.15087102353572845,
|
| 33797 |
+
"learning_rate": 4.297572551581599e-05,
|
| 33798 |
+
"loss": 0.7705,
|
| 33799 |
+
"step": 4827
|
| 33800 |
+
},
|
| 33801 |
+
{
|
| 33802 |
+
"epoch": 5.499145299145299,
|
| 33803 |
+
"grad_norm": 0.1942681074142456,
|
| 33804 |
+
"learning_rate": 4.297248716573365e-05,
|
| 33805 |
+
"loss": 0.7027,
|
| 33806 |
+
"step": 4828
|
| 33807 |
+
},
|
| 33808 |
+
{
|
| 33809 |
+
"epoch": 5.500284900284901,
|
| 33810 |
+
"grad_norm": 0.1641755998134613,
|
| 33811 |
+
"learning_rate": 4.29692481914174e-05,
|
| 33812 |
+
"loss": 0.8382,
|
| 33813 |
+
"step": 4829
|
| 33814 |
+
},
|
| 33815 |
+
{
|
| 33816 |
+
"epoch": 5.501424501424501,
|
| 33817 |
+
"grad_norm": 0.16210035979747772,
|
| 33818 |
+
"learning_rate": 4.296600859297974e-05,
|
| 33819 |
+
"loss": 0.8203,
|
| 33820 |
+
"step": 4830
|
| 33821 |
+
},
|
| 33822 |
+
{
|
| 33823 |
+
"epoch": 5.5025641025641026,
|
| 33824 |
+
"grad_norm": 0.23534131050109863,
|
| 33825 |
+
"learning_rate": 4.29627683705332e-05,
|
| 33826 |
+
"loss": 0.5255,
|
| 33827 |
+
"step": 4831
|
| 33828 |
+
},
|
| 33829 |
+
{
|
| 33830 |
+
"epoch": 5.503703703703704,
|
| 33831 |
+
"grad_norm": 0.18147152662277222,
|
| 33832 |
+
"learning_rate": 4.295952752419032e-05,
|
| 33833 |
+
"loss": 0.8388,
|
| 33834 |
+
"step": 4832
|
| 33835 |
+
},
|
| 33836 |
+
{
|
| 33837 |
+
"epoch": 5.5048433048433045,
|
| 33838 |
+
"grad_norm": 0.1641654372215271,
|
| 33839 |
+
"learning_rate": 4.2956286054063656e-05,
|
| 33840 |
+
"loss": 0.8352,
|
| 33841 |
+
"step": 4833
|
| 33842 |
+
},
|
| 33843 |
+
{
|
| 33844 |
+
"epoch": 5.505982905982906,
|
| 33845 |
+
"grad_norm": 0.1740059107542038,
|
| 33846 |
+
"learning_rate": 4.2953043960265793e-05,
|
| 33847 |
+
"loss": 0.6831,
|
| 33848 |
+
"step": 4834
|
| 33849 |
+
},
|
| 33850 |
+
{
|
| 33851 |
+
"epoch": 5.507122507122507,
|
| 33852 |
+
"grad_norm": 0.16150124371051788,
|
| 33853 |
+
"learning_rate": 4.294980124290935e-05,
|
| 33854 |
+
"loss": 0.9212,
|
| 33855 |
+
"step": 4835
|
| 33856 |
+
},
|
| 33857 |
+
{
|
| 33858 |
+
"epoch": 5.508262108262108,
|
| 33859 |
+
"grad_norm": 0.17982876300811768,
|
| 33860 |
+
"learning_rate": 4.2946557902106944e-05,
|
| 33861 |
+
"loss": 0.6717,
|
| 33862 |
+
"step": 4836
|
| 33863 |
+
},
|
| 33864 |
+
{
|
| 33865 |
+
"epoch": 5.509401709401709,
|
| 33866 |
+
"grad_norm": 0.19507353007793427,
|
| 33867 |
+
"learning_rate": 4.294331393797123e-05,
|
| 33868 |
+
"loss": 0.6143,
|
| 33869 |
+
"step": 4837
|
| 33870 |
+
},
|
| 33871 |
+
{
|
| 33872 |
+
"epoch": 5.510541310541311,
|
| 33873 |
+
"grad_norm": 0.17204579710960388,
|
| 33874 |
+
"learning_rate": 4.294006935061488e-05,
|
| 33875 |
+
"loss": 0.8285,
|
| 33876 |
+
"step": 4838
|
| 33877 |
+
},
|
| 33878 |
+
{
|
| 33879 |
+
"epoch": 5.511680911680911,
|
| 33880 |
+
"grad_norm": 0.2067815661430359,
|
| 33881 |
+
"learning_rate": 4.293682414015059e-05,
|
| 33882 |
+
"loss": 0.6785,
|
| 33883 |
+
"step": 4839
|
| 33884 |
+
},
|
| 33885 |
+
{
|
| 33886 |
+
"epoch": 5.512820512820513,
|
| 33887 |
+
"grad_norm": 0.17989838123321533,
|
| 33888 |
+
"learning_rate": 4.293357830669106e-05,
|
| 33889 |
+
"loss": 0.6755,
|
| 33890 |
+
"step": 4840
|
| 33891 |
+
},
|
| 33892 |
+
{
|
| 33893 |
+
"epoch": 5.513960113960114,
|
| 33894 |
+
"grad_norm": 0.1755257546901703,
|
| 33895 |
+
"learning_rate": 4.293033185034904e-05,
|
| 33896 |
+
"loss": 0.7745,
|
| 33897 |
+
"step": 4841
|
| 33898 |
+
},
|
| 33899 |
+
{
|
| 33900 |
+
"epoch": 5.515099715099715,
|
| 33901 |
+
"grad_norm": 0.16593924164772034,
|
| 33902 |
+
"learning_rate": 4.292708477123729e-05,
|
| 33903 |
+
"loss": 0.6809,
|
| 33904 |
+
"step": 4842
|
| 33905 |
+
},
|
| 33906 |
+
{
|
| 33907 |
+
"epoch": 5.516239316239316,
|
| 33908 |
+
"grad_norm": 0.18866293132305145,
|
| 33909 |
+
"learning_rate": 4.2923837069468586e-05,
|
| 33910 |
+
"loss": 0.7132,
|
| 33911 |
+
"step": 4843
|
| 33912 |
+
},
|
| 33913 |
+
{
|
| 33914 |
+
"epoch": 5.517378917378918,
|
| 33915 |
+
"grad_norm": 0.16058719158172607,
|
| 33916 |
+
"learning_rate": 4.292058874515573e-05,
|
| 33917 |
+
"loss": 0.7929,
|
| 33918 |
+
"step": 4844
|
| 33919 |
+
},
|
| 33920 |
+
{
|
| 33921 |
+
"epoch": 5.518518518518518,
|
| 33922 |
+
"grad_norm": 0.18849186599254608,
|
| 33923 |
+
"learning_rate": 4.291733979841155e-05,
|
| 33924 |
+
"loss": 0.6137,
|
| 33925 |
+
"step": 4845
|
| 33926 |
+
},
|
| 33927 |
+
{
|
| 33928 |
+
"epoch": 5.51965811965812,
|
| 33929 |
+
"grad_norm": 0.20065782964229584,
|
| 33930 |
+
"learning_rate": 4.291409022934888e-05,
|
| 33931 |
+
"loss": 0.6236,
|
| 33932 |
+
"step": 4846
|
| 33933 |
+
},
|
| 33934 |
+
{
|
| 33935 |
+
"epoch": 5.520797720797721,
|
| 33936 |
+
"grad_norm": 0.22605036199092865,
|
| 33937 |
+
"learning_rate": 4.2910840038080594e-05,
|
| 33938 |
+
"loss": 0.5011,
|
| 33939 |
+
"step": 4847
|
| 33940 |
+
},
|
| 33941 |
+
{
|
| 33942 |
+
"epoch": 5.521937321937322,
|
| 33943 |
+
"grad_norm": 0.192116841673851,
|
| 33944 |
+
"learning_rate": 4.290758922471957e-05,
|
| 33945 |
+
"loss": 0.7773,
|
| 33946 |
+
"step": 4848
|
| 33947 |
+
},
|
| 33948 |
+
{
|
| 33949 |
+
"epoch": 5.523076923076923,
|
| 33950 |
+
"grad_norm": 0.17766951024532318,
|
| 33951 |
+
"learning_rate": 4.290433778937873e-05,
|
| 33952 |
+
"loss": 0.8467,
|
| 33953 |
+
"step": 4849
|
| 33954 |
+
},
|
| 33955 |
+
{
|
| 33956 |
+
"epoch": 5.524216524216524,
|
| 33957 |
+
"grad_norm": 0.1707712709903717,
|
| 33958 |
+
"learning_rate": 4.290108573217101e-05,
|
| 33959 |
+
"loss": 0.8411,
|
| 33960 |
+
"step": 4850
|
| 33961 |
+
},
|
| 33962 |
+
{
|
| 33963 |
+
"epoch": 5.525356125356125,
|
| 33964 |
+
"grad_norm": 0.15306320786476135,
|
| 33965 |
+
"learning_rate": 4.289783305320935e-05,
|
| 33966 |
+
"loss": 0.9233,
|
| 33967 |
+
"step": 4851
|
| 33968 |
+
},
|
| 33969 |
+
{
|
| 33970 |
+
"epoch": 5.526495726495726,
|
| 33971 |
+
"grad_norm": 0.12808679044246674,
|
| 33972 |
+
"learning_rate": 4.289457975260673e-05,
|
| 33973 |
+
"loss": 0.8705,
|
| 33974 |
+
"step": 4852
|
| 33975 |
+
},
|
| 33976 |
+
{
|
| 33977 |
+
"epoch": 5.527635327635328,
|
| 33978 |
+
"grad_norm": 0.18593312799930573,
|
| 33979 |
+
"learning_rate": 4.2891325830476146e-05,
|
| 33980 |
+
"loss": 0.6938,
|
| 33981 |
+
"step": 4853
|
| 33982 |
+
},
|
| 33983 |
+
{
|
| 33984 |
+
"epoch": 5.528774928774929,
|
| 33985 |
+
"grad_norm": 0.18112976849079132,
|
| 33986 |
+
"learning_rate": 4.288807128693061e-05,
|
| 33987 |
+
"loss": 0.7557,
|
| 33988 |
+
"step": 4854
|
| 33989 |
+
},
|
| 33990 |
+
{
|
| 33991 |
+
"epoch": 5.52991452991453,
|
| 33992 |
+
"grad_norm": 0.21150390803813934,
|
| 33993 |
+
"learning_rate": 4.288481612208317e-05,
|
| 33994 |
+
"loss": 0.6065,
|
| 33995 |
+
"step": 4855
|
| 33996 |
+
},
|
| 33997 |
+
{
|
| 33998 |
+
"epoch": 5.531054131054131,
|
| 33999 |
+
"grad_norm": 0.19397857785224915,
|
| 34000 |
+
"learning_rate": 4.2881560336046874e-05,
|
| 34001 |
+
"loss": 0.7736,
|
| 34002 |
+
"step": 4856
|
| 34003 |
+
},
|
| 34004 |
+
{
|
| 34005 |
+
"epoch": 5.532193732193733,
|
| 34006 |
+
"grad_norm": 0.17135579884052277,
|
| 34007 |
+
"learning_rate": 4.287830392893482e-05,
|
| 34008 |
+
"loss": 0.9113,
|
| 34009 |
+
"step": 4857
|
| 34010 |
+
},
|
| 34011 |
+
{
|
| 34012 |
+
"epoch": 5.533333333333333,
|
| 34013 |
+
"grad_norm": 0.24377498030662537,
|
| 34014 |
+
"learning_rate": 4.287504690086011e-05,
|
| 34015 |
+
"loss": 0.8753,
|
| 34016 |
+
"step": 4858
|
| 34017 |
+
},
|
| 34018 |
+
{
|
| 34019 |
+
"epoch": 5.534472934472935,
|
| 34020 |
+
"grad_norm": 0.18869635462760925,
|
| 34021 |
+
"learning_rate": 4.287178925193586e-05,
|
| 34022 |
+
"loss": 0.6228,
|
| 34023 |
+
"step": 4859
|
| 34024 |
+
},
|
| 34025 |
+
{
|
| 34026 |
+
"epoch": 5.535612535612536,
|
| 34027 |
+
"grad_norm": 0.18486569821834564,
|
| 34028 |
+
"learning_rate": 4.2868530982275215e-05,
|
| 34029 |
+
"loss": 0.6519,
|
| 34030 |
+
"step": 4860
|
| 34031 |
+
},
|
| 34032 |
+
{
|
| 34033 |
+
"epoch": 5.536752136752137,
|
| 34034 |
+
"grad_norm": 0.1529039591550827,
|
| 34035 |
+
"learning_rate": 4.286527209199136e-05,
|
| 34036 |
+
"loss": 0.8446,
|
| 34037 |
+
"step": 4861
|
| 34038 |
+
},
|
| 34039 |
+
{
|
| 34040 |
+
"epoch": 5.537891737891738,
|
| 34041 |
+
"grad_norm": 0.18323606252670288,
|
| 34042 |
+
"learning_rate": 4.286201258119746e-05,
|
| 34043 |
+
"loss": 0.6771,
|
| 34044 |
+
"step": 4862
|
| 34045 |
+
},
|
| 34046 |
+
{
|
| 34047 |
+
"epoch": 5.5390313390313395,
|
| 34048 |
+
"grad_norm": 0.17818498611450195,
|
| 34049 |
+
"learning_rate": 4.2858752450006764e-05,
|
| 34050 |
+
"loss": 0.6363,
|
| 34051 |
+
"step": 4863
|
| 34052 |
+
},
|
| 34053 |
+
{
|
| 34054 |
+
"epoch": 5.54017094017094,
|
| 34055 |
+
"grad_norm": 0.20588888227939606,
|
| 34056 |
+
"learning_rate": 4.285549169853247e-05,
|
| 34057 |
+
"loss": 0.6694,
|
| 34058 |
+
"step": 4864
|
| 34059 |
+
},
|
| 34060 |
+
{
|
| 34061 |
+
"epoch": 5.5413105413105415,
|
| 34062 |
+
"grad_norm": 0.14603447914123535,
|
| 34063 |
+
"learning_rate": 4.285223032688785e-05,
|
| 34064 |
+
"loss": 0.919,
|
| 34065 |
+
"step": 4865
|
| 34066 |
+
},
|
| 34067 |
+
{
|
| 34068 |
+
"epoch": 5.542450142450143,
|
| 34069 |
+
"grad_norm": 0.18710605800151825,
|
| 34070 |
+
"learning_rate": 4.284896833518618e-05,
|
| 34071 |
+
"loss": 0.7944,
|
| 34072 |
+
"step": 4866
|
| 34073 |
+
},
|
| 34074 |
+
{
|
| 34075 |
+
"epoch": 5.543589743589743,
|
| 34076 |
+
"grad_norm": 0.1813526749610901,
|
| 34077 |
+
"learning_rate": 4.284570572354075e-05,
|
| 34078 |
+
"loss": 0.8102,
|
| 34079 |
+
"step": 4867
|
| 34080 |
+
},
|
| 34081 |
+
{
|
| 34082 |
+
"epoch": 5.544729344729345,
|
| 34083 |
+
"grad_norm": 0.18585647642612457,
|
| 34084 |
+
"learning_rate": 4.284244249206488e-05,
|
| 34085 |
+
"loss": 0.6563,
|
| 34086 |
+
"step": 4868
|
| 34087 |
+
},
|
| 34088 |
+
{
|
| 34089 |
+
"epoch": 5.545868945868946,
|
| 34090 |
+
"grad_norm": 0.1963941752910614,
|
| 34091 |
+
"learning_rate": 4.2839178640871926e-05,
|
| 34092 |
+
"loss": 0.6104,
|
| 34093 |
+
"step": 4869
|
| 34094 |
+
},
|
| 34095 |
+
{
|
| 34096 |
+
"epoch": 5.547008547008547,
|
| 34097 |
+
"grad_norm": 0.17948034405708313,
|
| 34098 |
+
"learning_rate": 4.2835914170075237e-05,
|
| 34099 |
+
"loss": 0.6885,
|
| 34100 |
+
"step": 4870
|
| 34101 |
+
},
|
| 34102 |
+
{
|
| 34103 |
+
"epoch": 5.548148148148148,
|
| 34104 |
+
"grad_norm": 0.20369914174079895,
|
| 34105 |
+
"learning_rate": 4.28326490797882e-05,
|
| 34106 |
+
"loss": 0.5942,
|
| 34107 |
+
"step": 4871
|
| 34108 |
+
},
|
| 34109 |
+
{
|
| 34110 |
+
"epoch": 5.54928774928775,
|
| 34111 |
+
"grad_norm": 0.16400721669197083,
|
| 34112 |
+
"learning_rate": 4.282938337012421e-05,
|
| 34113 |
+
"loss": 0.94,
|
| 34114 |
+
"step": 4872
|
| 34115 |
+
},
|
| 34116 |
+
{
|
| 34117 |
+
"epoch": 5.55042735042735,
|
| 34118 |
+
"grad_norm": 0.17267654836177826,
|
| 34119 |
+
"learning_rate": 4.2826117041196714e-05,
|
| 34120 |
+
"loss": 0.8322,
|
| 34121 |
+
"step": 4873
|
| 34122 |
+
},
|
| 34123 |
+
{
|
| 34124 |
+
"epoch": 5.551566951566952,
|
| 34125 |
+
"grad_norm": 0.20895081758499146,
|
| 34126 |
+
"learning_rate": 4.282285009311915e-05,
|
| 34127 |
+
"loss": 0.6476,
|
| 34128 |
+
"step": 4874
|
| 34129 |
+
},
|
| 34130 |
+
{
|
| 34131 |
+
"epoch": 5.552706552706553,
|
| 34132 |
+
"grad_norm": 0.1930321305990219,
|
| 34133 |
+
"learning_rate": 4.2819582526005e-05,
|
| 34134 |
+
"loss": 0.7806,
|
| 34135 |
+
"step": 4875
|
| 34136 |
+
},
|
| 34137 |
+
{
|
| 34138 |
+
"epoch": 5.553846153846154,
|
| 34139 |
+
"grad_norm": 0.1591208130121231,
|
| 34140 |
+
"learning_rate": 4.281631433996773e-05,
|
| 34141 |
+
"loss": 0.8056,
|
| 34142 |
+
"step": 4876
|
| 34143 |
+
},
|
| 34144 |
+
{
|
| 34145 |
+
"epoch": 5.554985754985755,
|
| 34146 |
+
"grad_norm": 0.23983530700206757,
|
| 34147 |
+
"learning_rate": 4.281304553512087e-05,
|
| 34148 |
+
"loss": 0.7979,
|
| 34149 |
+
"step": 4877
|
| 34150 |
+
},
|
| 34151 |
+
{
|
| 34152 |
+
"epoch": 5.5561253561253565,
|
| 34153 |
+
"grad_norm": 0.19674810767173767,
|
| 34154 |
+
"learning_rate": 4.280977611157796e-05,
|
| 34155 |
+
"loss": 0.5482,
|
| 34156 |
+
"step": 4878
|
| 34157 |
+
},
|
| 34158 |
+
{
|
| 34159 |
+
"epoch": 5.557264957264957,
|
| 34160 |
+
"grad_norm": 0.17274408042430878,
|
| 34161 |
+
"learning_rate": 4.280650606945254e-05,
|
| 34162 |
+
"loss": 0.8055,
|
| 34163 |
+
"step": 4879
|
| 34164 |
+
},
|
| 34165 |
+
{
|
| 34166 |
+
"epoch": 5.5584045584045585,
|
| 34167 |
+
"grad_norm": 0.16266362369060516,
|
| 34168 |
+
"learning_rate": 4.28032354088582e-05,
|
| 34169 |
+
"loss": 0.7655,
|
| 34170 |
+
"step": 4880
|
| 34171 |
+
},
|
| 34172 |
+
{
|
| 34173 |
+
"epoch": 5.55954415954416,
|
| 34174 |
+
"grad_norm": 0.14792993664741516,
|
| 34175 |
+
"learning_rate": 4.2799964129908533e-05,
|
| 34176 |
+
"loss": 0.8576,
|
| 34177 |
+
"step": 4881
|
| 34178 |
+
},
|
| 34179 |
+
{
|
| 34180 |
+
"epoch": 5.5606837606837605,
|
| 34181 |
+
"grad_norm": 0.16226008534431458,
|
| 34182 |
+
"learning_rate": 4.279669223271716e-05,
|
| 34183 |
+
"loss": 0.7377,
|
| 34184 |
+
"step": 4882
|
| 34185 |
+
},
|
| 34186 |
+
{
|
| 34187 |
+
"epoch": 5.561823361823362,
|
| 34188 |
+
"grad_norm": 0.1945132315158844,
|
| 34189 |
+
"learning_rate": 4.2793419717397734e-05,
|
| 34190 |
+
"loss": 0.7414,
|
| 34191 |
+
"step": 4883
|
| 34192 |
+
},
|
| 34193 |
+
{
|
| 34194 |
+
"epoch": 5.562962962962963,
|
| 34195 |
+
"grad_norm": 0.19473624229431152,
|
| 34196 |
+
"learning_rate": 4.27901465840639e-05,
|
| 34197 |
+
"loss": 0.784,
|
| 34198 |
+
"step": 4884
|
| 34199 |
+
},
|
| 34200 |
+
{
|
| 34201 |
+
"epoch": 5.564102564102564,
|
| 34202 |
+
"grad_norm": 0.20556029677391052,
|
| 34203 |
+
"learning_rate": 4.278687283282936e-05,
|
| 34204 |
+
"loss": 0.6137,
|
| 34205 |
+
"step": 4885
|
| 34206 |
+
},
|
| 34207 |
+
{
|
| 34208 |
+
"epoch": 5.565242165242165,
|
| 34209 |
+
"grad_norm": 0.1734907478094101,
|
| 34210 |
+
"learning_rate": 4.278359846380781e-05,
|
| 34211 |
+
"loss": 0.7178,
|
| 34212 |
+
"step": 4886
|
| 34213 |
+
},
|
| 34214 |
+
{
|
| 34215 |
+
"epoch": 5.566381766381767,
|
| 34216 |
+
"grad_norm": 0.2000545710325241,
|
| 34217 |
+
"learning_rate": 4.278032347711297e-05,
|
| 34218 |
+
"loss": 0.5692,
|
| 34219 |
+
"step": 4887
|
| 34220 |
+
},
|
| 34221 |
+
{
|
| 34222 |
+
"epoch": 5.567521367521367,
|
| 34223 |
+
"grad_norm": 0.18035154044628143,
|
| 34224 |
+
"learning_rate": 4.277704787285861e-05,
|
| 34225 |
+
"loss": 0.8012,
|
| 34226 |
+
"step": 4888
|
| 34227 |
+
},
|
| 34228 |
+
{
|
| 34229 |
+
"epoch": 5.568660968660969,
|
| 34230 |
+
"grad_norm": 0.21270377933979034,
|
| 34231 |
+
"learning_rate": 4.277377165115849e-05,
|
| 34232 |
+
"loss": 0.664,
|
| 34233 |
+
"step": 4889
|
| 34234 |
+
},
|
| 34235 |
+
{
|
| 34236 |
+
"epoch": 5.56980056980057,
|
| 34237 |
+
"grad_norm": 0.1641324758529663,
|
| 34238 |
+
"learning_rate": 4.277049481212639e-05,
|
| 34239 |
+
"loss": 0.9684,
|
| 34240 |
+
"step": 4890
|
| 34241 |
+
},
|
| 34242 |
+
{
|
| 34243 |
+
"epoch": 5.570940170940171,
|
| 34244 |
+
"grad_norm": 0.16035698354244232,
|
| 34245 |
+
"learning_rate": 4.2767217355876155e-05,
|
| 34246 |
+
"loss": 0.7883,
|
| 34247 |
+
"step": 4891
|
| 34248 |
+
},
|
| 34249 |
+
{
|
| 34250 |
+
"epoch": 5.572079772079772,
|
| 34251 |
+
"grad_norm": 0.1673315018415451,
|
| 34252 |
+
"learning_rate": 4.276393928252159e-05,
|
| 34253 |
+
"loss": 0.7712,
|
| 34254 |
+
"step": 4892
|
| 34255 |
+
},
|
| 34256 |
+
{
|
| 34257 |
+
"epoch": 5.5732193732193736,
|
| 34258 |
+
"grad_norm": 0.1887262910604477,
|
| 34259 |
+
"learning_rate": 4.2760660592176565e-05,
|
| 34260 |
+
"loss": 0.6812,
|
| 34261 |
+
"step": 4893
|
| 34262 |
+
},
|
| 34263 |
+
{
|
| 34264 |
+
"epoch": 5.574358974358974,
|
| 34265 |
+
"grad_norm": 0.17907768487930298,
|
| 34266 |
+
"learning_rate": 4.2757381284954955e-05,
|
| 34267 |
+
"loss": 0.7801,
|
| 34268 |
+
"step": 4894
|
| 34269 |
+
},
|
| 34270 |
+
{
|
| 34271 |
+
"epoch": 5.5754985754985755,
|
| 34272 |
+
"grad_norm": 0.14310143887996674,
|
| 34273 |
+
"learning_rate": 4.275410136097067e-05,
|
| 34274 |
+
"loss": 0.91,
|
| 34275 |
+
"step": 4895
|
| 34276 |
+
},
|
| 34277 |
+
{
|
| 34278 |
+
"epoch": 5.576638176638177,
|
| 34279 |
+
"grad_norm": 0.16130873560905457,
|
| 34280 |
+
"learning_rate": 4.2750820820337605e-05,
|
| 34281 |
+
"loss": 0.9366,
|
| 34282 |
+
"step": 4896
|
| 34283 |
+
},
|
| 34284 |
+
{
|
| 34285 |
+
"epoch": 5.5777777777777775,
|
| 34286 |
+
"grad_norm": 0.18696458637714386,
|
| 34287 |
+
"learning_rate": 4.2747539663169725e-05,
|
| 34288 |
+
"loss": 0.6416,
|
| 34289 |
+
"step": 4897
|
| 34290 |
+
},
|
| 34291 |
+
{
|
| 34292 |
+
"epoch": 5.578917378917379,
|
| 34293 |
+
"grad_norm": 0.19012431800365448,
|
| 34294 |
+
"learning_rate": 4.274425788958098e-05,
|
| 34295 |
+
"loss": 0.9844,
|
| 34296 |
+
"step": 4898
|
| 34297 |
+
},
|
| 34298 |
+
{
|
| 34299 |
+
"epoch": 5.58005698005698,
|
| 34300 |
+
"grad_norm": 0.18784600496292114,
|
| 34301 |
+
"learning_rate": 4.274097549968538e-05,
|
| 34302 |
+
"loss": 0.8611,
|
| 34303 |
+
"step": 4899
|
| 34304 |
+
},
|
| 34305 |
+
{
|
| 34306 |
+
"epoch": 5.581196581196581,
|
| 34307 |
+
"grad_norm": 0.1906341016292572,
|
| 34308 |
+
"learning_rate": 4.273769249359689e-05,
|
| 34309 |
+
"loss": 0.7214,
|
| 34310 |
+
"step": 4900
|
| 34311 |
+
},
|
| 34312 |
+
{
|
| 34313 |
+
"epoch": 5.582336182336182,
|
| 34314 |
+
"grad_norm": 0.1430826038122177,
|
| 34315 |
+
"learning_rate": 4.2734408871429574e-05,
|
| 34316 |
+
"loss": 0.9122,
|
| 34317 |
+
"step": 4901
|
| 34318 |
+
},
|
| 34319 |
+
{
|
| 34320 |
+
"epoch": 5.583475783475784,
|
| 34321 |
+
"grad_norm": 0.2282940298318863,
|
| 34322 |
+
"learning_rate": 4.273112463329747e-05,
|
| 34323 |
+
"loss": 0.5778,
|
| 34324 |
+
"step": 4902
|
| 34325 |
+
},
|
| 34326 |
+
{
|
| 34327 |
+
"epoch": 5.584615384615384,
|
| 34328 |
+
"grad_norm": 0.15738672018051147,
|
| 34329 |
+
"learning_rate": 4.272783977931464e-05,
|
| 34330 |
+
"loss": 0.8408,
|
| 34331 |
+
"step": 4903
|
| 34332 |
+
},
|
| 34333 |
+
{
|
| 34334 |
+
"epoch": 5.585754985754986,
|
| 34335 |
+
"grad_norm": 0.1856355220079422,
|
| 34336 |
+
"learning_rate": 4.2724554309595186e-05,
|
| 34337 |
+
"loss": 0.8689,
|
| 34338 |
+
"step": 4904
|
| 34339 |
+
},
|
| 34340 |
+
{
|
| 34341 |
+
"epoch": 5.586894586894587,
|
| 34342 |
+
"grad_norm": 0.17705173790454865,
|
| 34343 |
+
"learning_rate": 4.272126822425322e-05,
|
| 34344 |
+
"loss": 0.7853,
|
| 34345 |
+
"step": 4905
|
| 34346 |
+
},
|
| 34347 |
+
{
|
| 34348 |
+
"epoch": 5.588034188034188,
|
| 34349 |
+
"grad_norm": 0.1721915900707245,
|
| 34350 |
+
"learning_rate": 4.271798152340287e-05,
|
| 34351 |
+
"loss": 0.8317,
|
| 34352 |
+
"step": 4906
|
| 34353 |
+
},
|
| 34354 |
+
{
|
| 34355 |
+
"epoch": 5.589173789173789,
|
| 34356 |
+
"grad_norm": 0.18221662938594818,
|
| 34357 |
+
"learning_rate": 4.27146942071583e-05,
|
| 34358 |
+
"loss": 0.7288,
|
| 34359 |
+
"step": 4907
|
| 34360 |
+
},
|
| 34361 |
+
{
|
| 34362 |
+
"epoch": 5.590313390313391,
|
| 34363 |
+
"grad_norm": 0.17120833694934845,
|
| 34364 |
+
"learning_rate": 4.271140627563368e-05,
|
| 34365 |
+
"loss": 0.7885,
|
| 34366 |
+
"step": 4908
|
| 34367 |
+
},
|
| 34368 |
+
{
|
| 34369 |
+
"epoch": 5.591452991452991,
|
| 34370 |
+
"grad_norm": 0.1811331957578659,
|
| 34371 |
+
"learning_rate": 4.270811772894322e-05,
|
| 34372 |
+
"loss": 0.7704,
|
| 34373 |
+
"step": 4909
|
| 34374 |
+
},
|
| 34375 |
+
{
|
| 34376 |
+
"epoch": 5.592592592592593,
|
| 34377 |
+
"grad_norm": 0.16168002784252167,
|
| 34378 |
+
"learning_rate": 4.270482856720113e-05,
|
| 34379 |
+
"loss": 0.8568,
|
| 34380 |
+
"step": 4910
|
| 34381 |
+
},
|
| 34382 |
+
{
|
| 34383 |
+
"epoch": 5.593732193732194,
|
| 34384 |
+
"grad_norm": 0.15206867456436157,
|
| 34385 |
+
"learning_rate": 4.2701538790521655e-05,
|
| 34386 |
+
"loss": 0.891,
|
| 34387 |
+
"step": 4911
|
| 34388 |
+
},
|
| 34389 |
+
{
|
| 34390 |
+
"epoch": 5.5948717948717945,
|
| 34391 |
+
"grad_norm": 0.18935824930667877,
|
| 34392 |
+
"learning_rate": 4.2698248399019056e-05,
|
| 34393 |
+
"loss": 0.7073,
|
| 34394 |
+
"step": 4912
|
| 34395 |
+
},
|
| 34396 |
+
{
|
| 34397 |
+
"epoch": 5.596011396011396,
|
| 34398 |
+
"grad_norm": 0.15101583302021027,
|
| 34399 |
+
"learning_rate": 4.269495739280763e-05,
|
| 34400 |
+
"loss": 0.92,
|
| 34401 |
+
"step": 4913
|
| 34402 |
+
},
|
| 34403 |
+
{
|
| 34404 |
+
"epoch": 5.597150997150997,
|
| 34405 |
+
"grad_norm": 0.17057983577251434,
|
| 34406 |
+
"learning_rate": 4.2691665772001665e-05,
|
| 34407 |
+
"loss": 0.7265,
|
| 34408 |
+
"step": 4914
|
| 34409 |
+
},
|
| 34410 |
+
{
|
| 34411 |
+
"epoch": 5.598290598290598,
|
| 34412 |
+
"grad_norm": 0.17918899655342102,
|
| 34413 |
+
"learning_rate": 4.26883735367155e-05,
|
| 34414 |
+
"loss": 0.7757,
|
| 34415 |
+
"step": 4915
|
| 34416 |
+
},
|
| 34417 |
+
{
|
| 34418 |
+
"epoch": 5.599430199430199,
|
| 34419 |
+
"grad_norm": 0.1816730946302414,
|
| 34420 |
+
"learning_rate": 4.268508068706347e-05,
|
| 34421 |
+
"loss": 0.6764,
|
| 34422 |
+
"step": 4916
|
| 34423 |
+
},
|
| 34424 |
+
{
|
| 34425 |
+
"epoch": 5.600569800569801,
|
| 34426 |
+
"grad_norm": 0.14690978825092316,
|
| 34427 |
+
"learning_rate": 4.2681787223159964e-05,
|
| 34428 |
+
"loss": 0.9026,
|
| 34429 |
+
"step": 4917
|
| 34430 |
+
},
|
| 34431 |
+
{
|
| 34432 |
+
"epoch": 5.601709401709401,
|
| 34433 |
+
"grad_norm": 0.18491557240486145,
|
| 34434 |
+
"learning_rate": 4.267849314511936e-05,
|
| 34435 |
+
"loss": 0.5996,
|
| 34436 |
+
"step": 4918
|
| 34437 |
+
},
|
| 34438 |
+
{
|
| 34439 |
+
"epoch": 5.602849002849003,
|
| 34440 |
+
"grad_norm": 0.1776413768529892,
|
| 34441 |
+
"learning_rate": 4.2675198453056065e-05,
|
| 34442 |
+
"loss": 0.7781,
|
| 34443 |
+
"step": 4919
|
| 34444 |
+
},
|
| 34445 |
+
{
|
| 34446 |
+
"epoch": 5.603988603988604,
|
| 34447 |
+
"grad_norm": 0.17524947226047516,
|
| 34448 |
+
"learning_rate": 4.267190314708453e-05,
|
| 34449 |
+
"loss": 0.6182,
|
| 34450 |
+
"step": 4920
|
| 34451 |
+
},
|
| 34452 |
+
{
|
| 34453 |
+
"epoch": 5.605128205128205,
|
| 34454 |
+
"grad_norm": 0.1926114559173584,
|
| 34455 |
+
"learning_rate": 4.2668607227319193e-05,
|
| 34456 |
+
"loss": 0.7867,
|
| 34457 |
+
"step": 4921
|
| 34458 |
+
},
|
| 34459 |
+
{
|
| 34460 |
+
"epoch": 5.606267806267806,
|
| 34461 |
+
"grad_norm": 0.16125115752220154,
|
| 34462 |
+
"learning_rate": 4.2665310693874544e-05,
|
| 34463 |
+
"loss": 0.8537,
|
| 34464 |
+
"step": 4922
|
| 34465 |
+
},
|
| 34466 |
+
{
|
| 34467 |
+
"epoch": 5.607407407407408,
|
| 34468 |
+
"grad_norm": 0.1547136753797531,
|
| 34469 |
+
"learning_rate": 4.266201354686508e-05,
|
| 34470 |
+
"loss": 0.9099,
|
| 34471 |
+
"step": 4923
|
| 34472 |
+
},
|
| 34473 |
+
{
|
| 34474 |
+
"epoch": 5.608547008547008,
|
| 34475 |
+
"grad_norm": 0.1847689300775528,
|
| 34476 |
+
"learning_rate": 4.2658715786405303e-05,
|
| 34477 |
+
"loss": 0.8013,
|
| 34478 |
+
"step": 4924
|
| 34479 |
+
},
|
| 34480 |
+
{
|
| 34481 |
+
"epoch": 5.60968660968661,
|
| 34482 |
+
"grad_norm": 0.1845116764307022,
|
| 34483 |
+
"learning_rate": 4.2655417412609764e-05,
|
| 34484 |
+
"loss": 0.7532,
|
| 34485 |
+
"step": 4925
|
| 34486 |
+
},
|
| 34487 |
+
{
|
| 34488 |
+
"epoch": 5.610826210826211,
|
| 34489 |
+
"grad_norm": 0.1838240772485733,
|
| 34490 |
+
"learning_rate": 4.265211842559303e-05,
|
| 34491 |
+
"loss": 0.8396,
|
| 34492 |
+
"step": 4926
|
| 34493 |
+
},
|
| 34494 |
+
{
|
| 34495 |
+
"epoch": 5.611965811965812,
|
| 34496 |
+
"grad_norm": 0.17016226053237915,
|
| 34497 |
+
"learning_rate": 4.2648818825469684e-05,
|
| 34498 |
+
"loss": 0.7146,
|
| 34499 |
+
"step": 4927
|
| 34500 |
+
},
|
| 34501 |
+
{
|
| 34502 |
+
"epoch": 5.613105413105413,
|
| 34503 |
+
"grad_norm": 0.1836037039756775,
|
| 34504 |
+
"learning_rate": 4.2645518612354324e-05,
|
| 34505 |
+
"loss": 0.5695,
|
| 34506 |
+
"step": 4928
|
| 34507 |
+
},
|
| 34508 |
+
{
|
| 34509 |
+
"epoch": 5.614245014245014,
|
| 34510 |
+
"grad_norm": 0.16213347017765045,
|
| 34511 |
+
"learning_rate": 4.264221778636158e-05,
|
| 34512 |
+
"loss": 0.8066,
|
| 34513 |
+
"step": 4929
|
| 34514 |
+
},
|
| 34515 |
+
{
|
| 34516 |
+
"epoch": 5.615384615384615,
|
| 34517 |
+
"grad_norm": 0.14991053938865662,
|
| 34518 |
+
"learning_rate": 4.263891634760609e-05,
|
| 34519 |
+
"loss": 0.9105,
|
| 34520 |
+
"step": 4930
|
| 34521 |
+
},
|
| 34522 |
+
{
|
| 34523 |
+
"epoch": 5.616524216524216,
|
| 34524 |
+
"grad_norm": 0.1772087812423706,
|
| 34525 |
+
"learning_rate": 4.263561429620253e-05,
|
| 34526 |
+
"loss": 0.8621,
|
| 34527 |
+
"step": 4931
|
| 34528 |
+
},
|
| 34529 |
+
{
|
| 34530 |
+
"epoch": 5.617663817663818,
|
| 34531 |
+
"grad_norm": 0.16358356177806854,
|
| 34532 |
+
"learning_rate": 4.263231163226559e-05,
|
| 34533 |
+
"loss": 0.8971,
|
| 34534 |
+
"step": 4932
|
| 34535 |
+
},
|
| 34536 |
+
{
|
| 34537 |
+
"epoch": 5.618803418803418,
|
| 34538 |
+
"grad_norm": 0.1786920428276062,
|
| 34539 |
+
"learning_rate": 4.262900835590997e-05,
|
| 34540 |
+
"loss": 0.6598,
|
| 34541 |
+
"step": 4933
|
| 34542 |
+
},
|
| 34543 |
+
{
|
| 34544 |
+
"epoch": 5.61994301994302,
|
| 34545 |
+
"grad_norm": 0.1441824585199356,
|
| 34546 |
+
"learning_rate": 4.2625704467250416e-05,
|
| 34547 |
+
"loss": 0.8508,
|
| 34548 |
+
"step": 4934
|
| 34549 |
+
},
|
| 34550 |
+
{
|
| 34551 |
+
"epoch": 5.621082621082621,
|
| 34552 |
+
"grad_norm": 0.1651386171579361,
|
| 34553 |
+
"learning_rate": 4.262239996640168e-05,
|
| 34554 |
+
"loss": 0.7861,
|
| 34555 |
+
"step": 4935
|
| 34556 |
+
},
|
| 34557 |
+
{
|
| 34558 |
+
"epoch": 5.622222222222222,
|
| 34559 |
+
"grad_norm": 0.19873394072055817,
|
| 34560 |
+
"learning_rate": 4.2619094853478526e-05,
|
| 34561 |
+
"loss": 0.7008,
|
| 34562 |
+
"step": 4936
|
| 34563 |
+
},
|
| 34564 |
+
{
|
| 34565 |
+
"epoch": 5.623361823361823,
|
| 34566 |
+
"grad_norm": 0.1520562618970871,
|
| 34567 |
+
"learning_rate": 4.261578912859575e-05,
|
| 34568 |
+
"loss": 0.8863,
|
| 34569 |
+
"step": 4937
|
| 34570 |
+
},
|
| 34571 |
+
{
|
| 34572 |
+
"epoch": 5.624501424501425,
|
| 34573 |
+
"grad_norm": 0.19953817129135132,
|
| 34574 |
+
"learning_rate": 4.261248279186818e-05,
|
| 34575 |
+
"loss": 0.77,
|
| 34576 |
+
"step": 4938
|
| 34577 |
+
},
|
| 34578 |
+
{
|
| 34579 |
+
"epoch": 5.625641025641025,
|
| 34580 |
+
"grad_norm": 0.15713857114315033,
|
| 34581 |
+
"learning_rate": 4.2609175843410645e-05,
|
| 34582 |
+
"loss": 0.8491,
|
| 34583 |
+
"step": 4939
|
| 34584 |
+
},
|
| 34585 |
+
{
|
| 34586 |
+
"epoch": 5.626780626780627,
|
| 34587 |
+
"grad_norm": 0.17172771692276,
|
| 34588 |
+
"learning_rate": 4.2605868283338014e-05,
|
| 34589 |
+
"loss": 0.7961,
|
| 34590 |
+
"step": 4940
|
| 34591 |
+
},
|
| 34592 |
+
{
|
| 34593 |
+
"epoch": 5.627920227920228,
|
| 34594 |
+
"grad_norm": 0.1584072858095169,
|
| 34595 |
+
"learning_rate": 4.260256011176515e-05,
|
| 34596 |
+
"loss": 0.8584,
|
| 34597 |
+
"step": 4941
|
| 34598 |
+
},
|
| 34599 |
+
{
|
| 34600 |
+
"epoch": 5.629059829059829,
|
| 34601 |
+
"grad_norm": 0.14709335565567017,
|
| 34602 |
+
"learning_rate": 4.259925132880698e-05,
|
| 34603 |
+
"loss": 0.8929,
|
| 34604 |
+
"step": 4942
|
| 34605 |
+
},
|
| 34606 |
+
{
|
| 34607 |
+
"epoch": 5.63019943019943,
|
| 34608 |
+
"grad_norm": 0.2108181267976761,
|
| 34609 |
+
"learning_rate": 4.2595941934578406e-05,
|
| 34610 |
+
"loss": 0.7498,
|
| 34611 |
+
"step": 4943
|
| 34612 |
+
},
|
| 34613 |
+
{
|
| 34614 |
+
"epoch": 5.6313390313390315,
|
| 34615 |
+
"grad_norm": 0.17729757726192474,
|
| 34616 |
+
"learning_rate": 4.259263192919438e-05,
|
| 34617 |
+
"loss": 0.7161,
|
| 34618 |
+
"step": 4944
|
| 34619 |
+
},
|
| 34620 |
+
{
|
| 34621 |
+
"epoch": 5.632478632478632,
|
| 34622 |
+
"grad_norm": 0.18931356072425842,
|
| 34623 |
+
"learning_rate": 4.258932131276986e-05,
|
| 34624 |
+
"loss": 0.7106,
|
| 34625 |
+
"step": 4945
|
| 34626 |
+
},
|
| 34627 |
+
{
|
| 34628 |
+
"epoch": 5.633618233618233,
|
| 34629 |
+
"grad_norm": 0.19616897404193878,
|
| 34630 |
+
"learning_rate": 4.2586010085419847e-05,
|
| 34631 |
+
"loss": 0.7033,
|
| 34632 |
+
"step": 4946
|
| 34633 |
+
},
|
| 34634 |
+
{
|
| 34635 |
+
"epoch": 5.634757834757835,
|
| 34636 |
+
"grad_norm": 0.1599295288324356,
|
| 34637 |
+
"learning_rate": 4.258269824725934e-05,
|
| 34638 |
+
"loss": 0.8281,
|
| 34639 |
+
"step": 4947
|
| 34640 |
+
},
|
| 34641 |
+
{
|
| 34642 |
+
"epoch": 5.635897435897435,
|
| 34643 |
+
"grad_norm": 0.2065536081790924,
|
| 34644 |
+
"learning_rate": 4.257938579840338e-05,
|
| 34645 |
+
"loss": 0.6753,
|
| 34646 |
+
"step": 4948
|
| 34647 |
+
},
|
| 34648 |
+
{
|
| 34649 |
+
"epoch": 5.637037037037037,
|
| 34650 |
+
"grad_norm": 0.1769915074110031,
|
| 34651 |
+
"learning_rate": 4.2576072738967e-05,
|
| 34652 |
+
"loss": 0.6098,
|
| 34653 |
+
"step": 4949
|
| 34654 |
+
},
|
| 34655 |
+
{
|
| 34656 |
+
"epoch": 5.638176638176638,
|
| 34657 |
+
"grad_norm": 0.18057970702648163,
|
| 34658 |
+
"learning_rate": 4.257275906906527e-05,
|
| 34659 |
+
"loss": 0.8321,
|
| 34660 |
+
"step": 4950
|
| 34661 |
+
},
|
| 34662 |
+
{
|
| 34663 |
+
"epoch": 5.639316239316239,
|
| 34664 |
+
"grad_norm": 0.14909537136554718,
|
| 34665 |
+
"learning_rate": 4.256944478881331e-05,
|
| 34666 |
+
"loss": 0.7847,
|
| 34667 |
+
"step": 4951
|
| 34668 |
+
},
|
| 34669 |
+
{
|
| 34670 |
+
"epoch": 5.64045584045584,
|
| 34671 |
+
"grad_norm": 0.18198081851005554,
|
| 34672 |
+
"learning_rate": 4.2566129898326205e-05,
|
| 34673 |
+
"loss": 0.8104,
|
| 34674 |
+
"step": 4952
|
| 34675 |
+
},
|
| 34676 |
+
{
|
| 34677 |
+
"epoch": 5.641595441595442,
|
| 34678 |
+
"grad_norm": 0.16259215772151947,
|
| 34679 |
+
"learning_rate": 4.2562814397719106e-05,
|
| 34680 |
+
"loss": 0.7178,
|
| 34681 |
+
"step": 4953
|
| 34682 |
+
},
|
| 34683 |
+
{
|
| 34684 |
+
"epoch": 5.642735042735043,
|
| 34685 |
+
"grad_norm": 0.15607447922229767,
|
| 34686 |
+
"learning_rate": 4.255949828710716e-05,
|
| 34687 |
+
"loss": 0.9134,
|
| 34688 |
+
"step": 4954
|
| 34689 |
+
},
|
| 34690 |
+
{
|
| 34691 |
+
"epoch": 5.643874643874644,
|
| 34692 |
+
"grad_norm": 0.15382663905620575,
|
| 34693 |
+
"learning_rate": 4.255618156660555e-05,
|
| 34694 |
+
"loss": 0.8821,
|
| 34695 |
+
"step": 4955
|
| 34696 |
+
},
|
| 34697 |
+
{
|
| 34698 |
+
"epoch": 5.645014245014245,
|
| 34699 |
+
"grad_norm": 0.1556910276412964,
|
| 34700 |
+
"learning_rate": 4.255286423632948e-05,
|
| 34701 |
+
"loss": 0.8285,
|
| 34702 |
+
"step": 4956
|
| 34703 |
+
},
|
| 34704 |
+
{
|
| 34705 |
+
"epoch": 5.6461538461538465,
|
| 34706 |
+
"grad_norm": 0.16671329736709595,
|
| 34707 |
+
"learning_rate": 4.254954629639416e-05,
|
| 34708 |
+
"loss": 0.8298,
|
| 34709 |
+
"step": 4957
|
| 34710 |
+
},
|
| 34711 |
+
{
|
| 34712 |
+
"epoch": 5.647293447293447,
|
| 34713 |
+
"grad_norm": 0.1555967479944229,
|
| 34714 |
+
"learning_rate": 4.254622774691484e-05,
|
| 34715 |
+
"loss": 0.8776,
|
| 34716 |
+
"step": 4958
|
| 34717 |
+
},
|
| 34718 |
+
{
|
| 34719 |
+
"epoch": 5.6484330484330485,
|
| 34720 |
+
"grad_norm": 0.16595129668712616,
|
| 34721 |
+
"learning_rate": 4.254290858800678e-05,
|
| 34722 |
+
"loss": 0.7158,
|
| 34723 |
+
"step": 4959
|
| 34724 |
+
},
|
| 34725 |
+
{
|
| 34726 |
+
"epoch": 5.64957264957265,
|
| 34727 |
+
"grad_norm": 0.1903461515903473,
|
| 34728 |
+
"learning_rate": 4.2539588819785255e-05,
|
| 34729 |
+
"loss": 0.7337,
|
| 34730 |
+
"step": 4960
|
| 34731 |
+
},
|
| 34732 |
+
{
|
| 34733 |
+
"epoch": 5.6507122507122505,
|
| 34734 |
+
"grad_norm": 0.16233199834823608,
|
| 34735 |
+
"learning_rate": 4.253626844236558e-05,
|
| 34736 |
+
"loss": 0.8324,
|
| 34737 |
+
"step": 4961
|
| 34738 |
+
},
|
| 34739 |
+
{
|
| 34740 |
+
"epoch": 5.651851851851852,
|
| 34741 |
+
"grad_norm": 0.18301106989383698,
|
| 34742 |
+
"learning_rate": 4.253294745586307e-05,
|
| 34743 |
+
"loss": 0.8412,
|
| 34744 |
+
"step": 4962
|
| 34745 |
+
},
|
| 34746 |
+
{
|
| 34747 |
+
"epoch": 5.652991452991453,
|
| 34748 |
+
"grad_norm": 0.1980588436126709,
|
| 34749 |
+
"learning_rate": 4.2529625860393085e-05,
|
| 34750 |
+
"loss": 0.8236,
|
| 34751 |
+
"step": 4963
|
| 34752 |
+
},
|
| 34753 |
+
{
|
| 34754 |
+
"epoch": 5.654131054131054,
|
| 34755 |
+
"grad_norm": 0.18101529777050018,
|
| 34756 |
+
"learning_rate": 4.252630365607099e-05,
|
| 34757 |
+
"loss": 0.7715,
|
| 34758 |
+
"step": 4964
|
| 34759 |
+
},
|
| 34760 |
+
{
|
| 34761 |
+
"epoch": 5.655270655270655,
|
| 34762 |
+
"grad_norm": 0.20688144862651825,
|
| 34763 |
+
"learning_rate": 4.2522980843012175e-05,
|
| 34764 |
+
"loss": 0.8297,
|
| 34765 |
+
"step": 4965
|
| 34766 |
+
},
|
| 34767 |
+
{
|
| 34768 |
+
"epoch": 5.656410256410257,
|
| 34769 |
+
"grad_norm": 0.179339200258255,
|
| 34770 |
+
"learning_rate": 4.251965742133203e-05,
|
| 34771 |
+
"loss": 0.6817,
|
| 34772 |
+
"step": 4966
|
| 34773 |
+
},
|
| 34774 |
+
{
|
| 34775 |
+
"epoch": 5.657549857549857,
|
| 34776 |
+
"grad_norm": 0.16479340195655823,
|
| 34777 |
+
"learning_rate": 4.2516333391146014e-05,
|
| 34778 |
+
"loss": 0.8987,
|
| 34779 |
+
"step": 4967
|
| 34780 |
+
},
|
| 34781 |
+
{
|
| 34782 |
+
"epoch": 5.658689458689459,
|
| 34783 |
+
"grad_norm": 0.19317205250263214,
|
| 34784 |
+
"learning_rate": 4.251300875256957e-05,
|
| 34785 |
+
"loss": 0.6499,
|
| 34786 |
+
"step": 4968
|
| 34787 |
+
},
|
| 34788 |
+
{
|
| 34789 |
+
"epoch": 5.65982905982906,
|
| 34790 |
+
"grad_norm": 0.17912079393863678,
|
| 34791 |
+
"learning_rate": 4.250968350571817e-05,
|
| 34792 |
+
"loss": 0.7337,
|
| 34793 |
+
"step": 4969
|
| 34794 |
+
},
|
| 34795 |
+
{
|
| 34796 |
+
"epoch": 5.660968660968661,
|
| 34797 |
+
"grad_norm": 0.19748400151729584,
|
| 34798 |
+
"learning_rate": 4.250635765070731e-05,
|
| 34799 |
+
"loss": 0.7389,
|
| 34800 |
+
"step": 4970
|
| 34801 |
+
},
|
| 34802 |
+
{
|
| 34803 |
+
"epoch": 5.662108262108262,
|
| 34804 |
+
"grad_norm": 0.1881670206785202,
|
| 34805 |
+
"learning_rate": 4.250303118765251e-05,
|
| 34806 |
+
"loss": 0.619,
|
| 34807 |
+
"step": 4971
|
| 34808 |
+
},
|
| 34809 |
+
{
|
| 34810 |
+
"epoch": 5.663247863247864,
|
| 34811 |
+
"grad_norm": 0.1812215894460678,
|
| 34812 |
+
"learning_rate": 4.2499704116669295e-05,
|
| 34813 |
+
"loss": 0.6389,
|
| 34814 |
+
"step": 4972
|
| 34815 |
+
},
|
| 34816 |
+
{
|
| 34817 |
+
"epoch": 5.664387464387464,
|
| 34818 |
+
"grad_norm": 0.15834550559520721,
|
| 34819 |
+
"learning_rate": 4.2496376437873245e-05,
|
| 34820 |
+
"loss": 0.7883,
|
| 34821 |
+
"step": 4973
|
| 34822 |
+
},
|
| 34823 |
+
{
|
| 34824 |
+
"epoch": 5.6655270655270655,
|
| 34825 |
+
"grad_norm": 0.16520103812217712,
|
| 34826 |
+
"learning_rate": 4.249304815137991e-05,
|
| 34827 |
+
"loss": 0.8922,
|
| 34828 |
+
"step": 4974
|
| 34829 |
+
},
|
| 34830 |
+
{
|
| 34831 |
+
"epoch": 5.666666666666667,
|
| 34832 |
+
"grad_norm": 0.1468709409236908,
|
| 34833 |
+
"learning_rate": 4.248971925730492e-05,
|
| 34834 |
+
"loss": 0.866,
|
| 34835 |
+
"step": 4975
|
| 34836 |
+
},
|
| 34837 |
+
{
|
| 34838 |
+
"epoch": 5.6678062678062675,
|
| 34839 |
+
"grad_norm": 0.15948764979839325,
|
| 34840 |
+
"learning_rate": 4.248638975576387e-05,
|
| 34841 |
+
"loss": 0.877,
|
| 34842 |
+
"step": 4976
|
| 34843 |
+
},
|
| 34844 |
+
{
|
| 34845 |
+
"epoch": 5.668945868945869,
|
| 34846 |
+
"grad_norm": 0.19492647051811218,
|
| 34847 |
+
"learning_rate": 4.248305964687242e-05,
|
| 34848 |
+
"loss": 0.8116,
|
| 34849 |
+
"step": 4977
|
| 34850 |
+
},
|
| 34851 |
+
{
|
| 34852 |
+
"epoch": 5.67008547008547,
|
| 34853 |
+
"grad_norm": 0.1607757806777954,
|
| 34854 |
+
"learning_rate": 4.2479728930746246e-05,
|
| 34855 |
+
"loss": 0.8762,
|
| 34856 |
+
"step": 4978
|
| 34857 |
+
},
|
| 34858 |
+
{
|
| 34859 |
+
"epoch": 5.671225071225071,
|
| 34860 |
+
"grad_norm": 0.1571768820285797,
|
| 34861 |
+
"learning_rate": 4.247639760750099e-05,
|
| 34862 |
+
"loss": 0.8207,
|
| 34863 |
+
"step": 4979
|
| 34864 |
+
},
|
| 34865 |
+
{
|
| 34866 |
+
"epoch": 5.672364672364672,
|
| 34867 |
+
"grad_norm": 0.19270595908164978,
|
| 34868 |
+
"learning_rate": 4.247306567725241e-05,
|
| 34869 |
+
"loss": 0.6118,
|
| 34870 |
+
"step": 4980
|
| 34871 |
+
},
|
| 34872 |
+
{
|
| 34873 |
+
"epoch": 5.673504273504274,
|
| 34874 |
+
"grad_norm": 0.16036999225616455,
|
| 34875 |
+
"learning_rate": 4.24697331401162e-05,
|
| 34876 |
+
"loss": 0.8286,
|
| 34877 |
+
"step": 4981
|
| 34878 |
+
},
|
| 34879 |
+
{
|
| 34880 |
+
"epoch": 5.674643874643874,
|
| 34881 |
+
"grad_norm": 0.20208951830863953,
|
| 34882 |
+
"learning_rate": 4.246639999620811e-05,
|
| 34883 |
+
"loss": 0.6747,
|
| 34884 |
+
"step": 4982
|
| 34885 |
+
},
|
| 34886 |
+
{
|
| 34887 |
+
"epoch": 5.675783475783476,
|
| 34888 |
+
"grad_norm": 0.1437763273715973,
|
| 34889 |
+
"learning_rate": 4.246306624564391e-05,
|
| 34890 |
+
"loss": 0.8368,
|
| 34891 |
+
"step": 4983
|
| 34892 |
+
},
|
| 34893 |
+
{
|
| 34894 |
+
"epoch": 5.676923076923077,
|
| 34895 |
+
"grad_norm": 0.19348663091659546,
|
| 34896 |
+
"learning_rate": 4.2459731888539406e-05,
|
| 34897 |
+
"loss": 0.7593,
|
| 34898 |
+
"step": 4984
|
| 34899 |
+
},
|
| 34900 |
+
{
|
| 34901 |
+
"epoch": 5.678062678062678,
|
| 34902 |
+
"grad_norm": 0.1824321150779724,
|
| 34903 |
+
"learning_rate": 4.24563969250104e-05,
|
| 34904 |
+
"loss": 0.7766,
|
| 34905 |
+
"step": 4985
|
| 34906 |
+
},
|
| 34907 |
+
{
|
| 34908 |
+
"epoch": 5.679202279202279,
|
| 34909 |
+
"grad_norm": 0.1617376059293747,
|
| 34910 |
+
"learning_rate": 4.245306135517272e-05,
|
| 34911 |
+
"loss": 0.8278,
|
| 34912 |
+
"step": 4986
|
| 34913 |
+
},
|
| 34914 |
+
{
|
| 34915 |
+
"epoch": 5.680341880341881,
|
| 34916 |
+
"grad_norm": 0.20494359731674194,
|
| 34917 |
+
"learning_rate": 4.244972517914222e-05,
|
| 34918 |
+
"loss": 0.8161,
|
| 34919 |
+
"step": 4987
|
| 34920 |
+
},
|
| 34921 |
+
{
|
| 34922 |
+
"epoch": 5.681481481481481,
|
| 34923 |
+
"grad_norm": 0.19541950523853302,
|
| 34924 |
+
"learning_rate": 4.244638839703478e-05,
|
| 34925 |
+
"loss": 0.5734,
|
| 34926 |
+
"step": 4988
|
| 34927 |
+
},
|
| 34928 |
+
{
|
| 34929 |
+
"epoch": 5.682621082621083,
|
| 34930 |
+
"grad_norm": 0.17641092836856842,
|
| 34931 |
+
"learning_rate": 4.24430510089663e-05,
|
| 34932 |
+
"loss": 0.8392,
|
| 34933 |
+
"step": 4989
|
| 34934 |
+
},
|
| 34935 |
+
{
|
| 34936 |
+
"epoch": 5.683760683760684,
|
| 34937 |
+
"grad_norm": 0.18785534799098969,
|
| 34938 |
+
"learning_rate": 4.243971301505268e-05,
|
| 34939 |
+
"loss": 0.7964,
|
| 34940 |
+
"step": 4990
|
| 34941 |
+
},
|
| 34942 |
+
{
|
| 34943 |
+
"epoch": 5.6849002849002845,
|
| 34944 |
+
"grad_norm": 0.21321099996566772,
|
| 34945 |
+
"learning_rate": 4.2436374415409875e-05,
|
| 34946 |
+
"loss": 0.669,
|
| 34947 |
+
"step": 4991
|
| 34948 |
+
},
|
| 34949 |
+
{
|
| 34950 |
+
"epoch": 5.686039886039886,
|
| 34951 |
+
"grad_norm": 0.1813569813966751,
|
| 34952 |
+
"learning_rate": 4.243303521015383e-05,
|
| 34953 |
+
"loss": 0.6711,
|
| 34954 |
+
"step": 4992
|
| 34955 |
+
},
|
| 34956 |
+
{
|
| 34957 |
+
"epoch": 5.687179487179487,
|
| 34958 |
+
"grad_norm": 0.17279620468616486,
|
| 34959 |
+
"learning_rate": 4.2429695399400535e-05,
|
| 34960 |
+
"loss": 0.827,
|
| 34961 |
+
"step": 4993
|
| 34962 |
+
},
|
| 34963 |
+
{
|
| 34964 |
+
"epoch": 5.688319088319088,
|
| 34965 |
+
"grad_norm": 0.1700081080198288,
|
| 34966 |
+
"learning_rate": 4.2426354983265984e-05,
|
| 34967 |
+
"loss": 0.864,
|
| 34968 |
+
"step": 4994
|
| 34969 |
+
},
|
| 34970 |
+
{
|
| 34971 |
+
"epoch": 5.689458689458689,
|
| 34972 |
+
"grad_norm": 0.1332874298095703,
|
| 34973 |
+
"learning_rate": 4.2423013961866206e-05,
|
| 34974 |
+
"loss": 0.8532,
|
| 34975 |
+
"step": 4995
|
| 34976 |
+
},
|
| 34977 |
+
{
|
| 34978 |
+
"epoch": 5.690598290598291,
|
| 34979 |
+
"grad_norm": 0.14816050231456757,
|
| 34980 |
+
"learning_rate": 4.2419672335317237e-05,
|
| 34981 |
+
"loss": 0.8706,
|
| 34982 |
+
"step": 4996
|
| 34983 |
+
},
|
| 34984 |
+
{
|
| 34985 |
+
"epoch": 5.691737891737891,
|
| 34986 |
+
"grad_norm": 0.1966293901205063,
|
| 34987 |
+
"learning_rate": 4.241633010373515e-05,
|
| 34988 |
+
"loss": 0.732,
|
| 34989 |
+
"step": 4997
|
| 34990 |
+
},
|
| 34991 |
+
{
|
| 34992 |
+
"epoch": 5.692877492877493,
|
| 34993 |
+
"grad_norm": 0.19324849545955658,
|
| 34994 |
+
"learning_rate": 4.2412987267236015e-05,
|
| 34995 |
+
"loss": 0.6829,
|
| 34996 |
+
"step": 4998
|
| 34997 |
+
},
|
| 34998 |
+
{
|
| 34999 |
+
"epoch": 5.694017094017094,
|
| 35000 |
+
"grad_norm": 0.15970183908939362,
|
| 35001 |
+
"learning_rate": 4.2409643825935944e-05,
|
| 35002 |
+
"loss": 0.8116,
|
| 35003 |
+
"step": 4999
|
| 35004 |
+
},
|
| 35005 |
+
{
|
| 35006 |
+
"epoch": 5.695156695156696,
|
| 35007 |
+
"grad_norm": 0.20089729130268097,
|
| 35008 |
+
"learning_rate": 4.2406299779951067e-05,
|
| 35009 |
+
"loss": 0.6485,
|
| 35010 |
+
"step": 5000
|
| 35011 |
+
},
|
| 35012 |
+
{
|
| 35013 |
+
"epoch": 5.696296296296296,
|
| 35014 |
+
"grad_norm": 0.1744430661201477,
|
| 35015 |
+
"learning_rate": 4.2402955129397534e-05,
|
| 35016 |
+
"loss": 0.8652,
|
| 35017 |
+
"step": 5001
|
| 35018 |
+
},
|
| 35019 |
+
{
|
| 35020 |
+
"epoch": 5.697435897435898,
|
| 35021 |
+
"grad_norm": 0.17672611773014069,
|
| 35022 |
+
"learning_rate": 4.239960987439152e-05,
|
| 35023 |
+
"loss": 0.7967,
|
| 35024 |
+
"step": 5002
|
| 35025 |
+
},
|
| 35026 |
+
{
|
| 35027 |
+
"epoch": 5.698575498575499,
|
| 35028 |
+
"grad_norm": 0.17788653075695038,
|
| 35029 |
+
"learning_rate": 4.2396264015049195e-05,
|
| 35030 |
+
"loss": 0.8278,
|
| 35031 |
+
"step": 5003
|
| 35032 |
+
},
|
| 35033 |
+
{
|
| 35034 |
+
"epoch": 5.6997150997151,
|
| 35035 |
+
"grad_norm": 0.15854409337043762,
|
| 35036 |
+
"learning_rate": 4.2392917551486786e-05,
|
| 35037 |
+
"loss": 0.884,
|
| 35038 |
+
"step": 5004
|
| 35039 |
+
},
|
| 35040 |
+
{
|
| 35041 |
+
"epoch": 5.700854700854701,
|
| 35042 |
+
"grad_norm": 0.18261882662773132,
|
| 35043 |
+
"learning_rate": 4.238957048382052e-05,
|
| 35044 |
+
"loss": 0.7924,
|
| 35045 |
+
"step": 5005
|
| 35046 |
+
},
|
| 35047 |
+
{
|
| 35048 |
+
"epoch": 5.7019943019943025,
|
| 35049 |
+
"grad_norm": 0.16455203294754028,
|
| 35050 |
+
"learning_rate": 4.238622281216664e-05,
|
| 35051 |
+
"loss": 0.916,
|
| 35052 |
+
"step": 5006
|
| 35053 |
+
},
|
| 35054 |
+
{
|
| 35055 |
+
"epoch": 5.703133903133903,
|
| 35056 |
+
"grad_norm": 0.17314814031124115,
|
| 35057 |
+
"learning_rate": 4.2382874536641436e-05,
|
| 35058 |
+
"loss": 0.7614,
|
| 35059 |
+
"step": 5007
|
| 35060 |
+
},
|
| 35061 |
+
{
|
| 35062 |
+
"epoch": 5.704273504273504,
|
| 35063 |
+
"grad_norm": 0.1945575624704361,
|
| 35064 |
+
"learning_rate": 4.2379525657361194e-05,
|
| 35065 |
+
"loss": 0.6869,
|
| 35066 |
+
"step": 5008
|
| 35067 |
+
},
|
| 35068 |
+
{
|
| 35069 |
+
"epoch": 5.705413105413106,
|
| 35070 |
+
"grad_norm": 0.18877752125263214,
|
| 35071 |
+
"learning_rate": 4.237617617444224e-05,
|
| 35072 |
+
"loss": 0.7701,
|
| 35073 |
+
"step": 5009
|
| 35074 |
+
},
|
| 35075 |
+
{
|
| 35076 |
+
"epoch": 5.706552706552706,
|
| 35077 |
+
"grad_norm": 0.18141210079193115,
|
| 35078 |
+
"learning_rate": 4.2372826088000895e-05,
|
| 35079 |
+
"loss": 0.6616,
|
| 35080 |
+
"step": 5010
|
| 35081 |
+
},
|
| 35082 |
+
{
|
| 35083 |
+
"epoch": 5.707692307692308,
|
| 35084 |
+
"grad_norm": 0.1711808443069458,
|
| 35085 |
+
"learning_rate": 4.236947539815353e-05,
|
| 35086 |
+
"loss": 0.7514,
|
| 35087 |
+
"step": 5011
|
| 35088 |
+
},
|
| 35089 |
+
{
|
| 35090 |
+
"epoch": 5.708831908831909,
|
| 35091 |
+
"grad_norm": 0.19431094825267792,
|
| 35092 |
+
"learning_rate": 4.2366124105016513e-05,
|
| 35093 |
+
"loss": 0.6112,
|
| 35094 |
+
"step": 5012
|
| 35095 |
+
},
|
| 35096 |
+
{
|
| 35097 |
+
"epoch": 5.70997150997151,
|
| 35098 |
+
"grad_norm": 0.17094816267490387,
|
| 35099 |
+
"learning_rate": 4.236277220870626e-05,
|
| 35100 |
+
"loss": 0.78,
|
| 35101 |
+
"step": 5013
|
| 35102 |
+
},
|
| 35103 |
+
{
|
| 35104 |
+
"epoch": 5.711111111111111,
|
| 35105 |
+
"grad_norm": 0.1716306060552597,
|
| 35106 |
+
"learning_rate": 4.235941970933917e-05,
|
| 35107 |
+
"loss": 0.8503,
|
| 35108 |
+
"step": 5014
|
| 35109 |
+
},
|
| 35110 |
+
{
|
| 35111 |
+
"epoch": 5.712250712250713,
|
| 35112 |
+
"grad_norm": 0.14870516955852509,
|
| 35113 |
+
"learning_rate": 4.235606660703169e-05,
|
| 35114 |
+
"loss": 0.8315,
|
| 35115 |
+
"step": 5015
|
| 35116 |
+
},
|
| 35117 |
+
{
|
| 35118 |
+
"epoch": 5.713390313390313,
|
| 35119 |
+
"grad_norm": 0.16047079861164093,
|
| 35120 |
+
"learning_rate": 4.235271290190029e-05,
|
| 35121 |
+
"loss": 0.8526,
|
| 35122 |
+
"step": 5016
|
| 35123 |
+
},
|
| 35124 |
+
{
|
| 35125 |
+
"epoch": 5.714529914529915,
|
| 35126 |
+
"grad_norm": 0.16539376974105835,
|
| 35127 |
+
"learning_rate": 4.234935859406146e-05,
|
| 35128 |
+
"loss": 0.7944,
|
| 35129 |
+
"step": 5017
|
| 35130 |
+
},
|
| 35131 |
+
{
|
| 35132 |
+
"epoch": 5.715669515669516,
|
| 35133 |
+
"grad_norm": 0.1937294900417328,
|
| 35134 |
+
"learning_rate": 4.234600368363169e-05,
|
| 35135 |
+
"loss": 0.7728,
|
| 35136 |
+
"step": 5018
|
| 35137 |
+
},
|
| 35138 |
+
{
|
| 35139 |
+
"epoch": 5.716809116809117,
|
| 35140 |
+
"grad_norm": 0.25908979773521423,
|
| 35141 |
+
"learning_rate": 4.234264817072751e-05,
|
| 35142 |
+
"loss": 0.6999,
|
| 35143 |
+
"step": 5019
|
| 35144 |
+
},
|
| 35145 |
+
{
|
| 35146 |
+
"epoch": 5.717948717948718,
|
| 35147 |
+
"grad_norm": 0.251360684633255,
|
| 35148 |
+
"learning_rate": 4.233929205546547e-05,
|
| 35149 |
+
"loss": 0.6301,
|
| 35150 |
+
"step": 5020
|
| 35151 |
+
},
|
| 35152 |
+
{
|
| 35153 |
+
"epoch": 5.7190883190883195,
|
| 35154 |
+
"grad_norm": 0.1455957293510437,
|
| 35155 |
+
"learning_rate": 4.233593533796213e-05,
|
| 35156 |
+
"loss": 0.7768,
|
| 35157 |
+
"step": 5021
|
| 35158 |
+
},
|
| 35159 |
+
{
|
| 35160 |
+
"epoch": 5.72022792022792,
|
| 35161 |
+
"grad_norm": 0.18815159797668457,
|
| 35162 |
+
"learning_rate": 4.233257801833408e-05,
|
| 35163 |
+
"loss": 0.7348,
|
| 35164 |
+
"step": 5022
|
| 35165 |
+
},
|
| 35166 |
+
{
|
| 35167 |
+
"epoch": 5.7213675213675215,
|
| 35168 |
+
"grad_norm": 0.18029174208641052,
|
| 35169 |
+
"learning_rate": 4.232922009669793e-05,
|
| 35170 |
+
"loss": 0.7225,
|
| 35171 |
+
"step": 5023
|
| 35172 |
+
},
|
| 35173 |
+
{
|
| 35174 |
+
"epoch": 5.722507122507123,
|
| 35175 |
+
"grad_norm": 0.1669107973575592,
|
| 35176 |
+
"learning_rate": 4.2325861573170316e-05,
|
| 35177 |
+
"loss": 0.9198,
|
| 35178 |
+
"step": 5024
|
| 35179 |
+
},
|
| 35180 |
+
{
|
| 35181 |
+
"epoch": 5.7236467236467234,
|
| 35182 |
+
"grad_norm": 0.17809349298477173,
|
| 35183 |
+
"learning_rate": 4.2322502447867884e-05,
|
| 35184 |
+
"loss": 0.792,
|
| 35185 |
+
"step": 5025
|
| 35186 |
+
},
|
| 35187 |
+
{
|
| 35188 |
+
"epoch": 5.724786324786325,
|
| 35189 |
+
"grad_norm": 0.17792947590351105,
|
| 35190 |
+
"learning_rate": 4.2319142720907296e-05,
|
| 35191 |
+
"loss": 0.7769,
|
| 35192 |
+
"step": 5026
|
| 35193 |
+
},
|
| 35194 |
+
{
|
| 35195 |
+
"epoch": 5.725925925925926,
|
| 35196 |
+
"grad_norm": 0.17586131393909454,
|
| 35197 |
+
"learning_rate": 4.2315782392405255e-05,
|
| 35198 |
+
"loss": 0.7883,
|
| 35199 |
+
"step": 5027
|
| 35200 |
+
},
|
| 35201 |
+
{
|
| 35202 |
+
"epoch": 5.727065527065527,
|
| 35203 |
+
"grad_norm": 0.16819684207439423,
|
| 35204 |
+
"learning_rate": 4.231242146247848e-05,
|
| 35205 |
+
"loss": 0.7843,
|
| 35206 |
+
"step": 5028
|
| 35207 |
+
},
|
| 35208 |
+
{
|
| 35209 |
+
"epoch": 5.728205128205128,
|
| 35210 |
+
"grad_norm": 0.19293169677257538,
|
| 35211 |
+
"learning_rate": 4.23090599312437e-05,
|
| 35212 |
+
"loss": 0.6307,
|
| 35213 |
+
"step": 5029
|
| 35214 |
+
},
|
| 35215 |
+
{
|
| 35216 |
+
"epoch": 5.72934472934473,
|
| 35217 |
+
"grad_norm": 0.21308547258377075,
|
| 35218 |
+
"learning_rate": 4.230569779881766e-05,
|
| 35219 |
+
"loss": 0.6307,
|
| 35220 |
+
"step": 5030
|
| 35221 |
+
},
|
| 35222 |
+
{
|
| 35223 |
+
"epoch": 5.73048433048433,
|
| 35224 |
+
"grad_norm": 0.1603964865207672,
|
| 35225 |
+
"learning_rate": 4.230233506531715e-05,
|
| 35226 |
+
"loss": 0.7958,
|
| 35227 |
+
"step": 5031
|
| 35228 |
+
},
|
| 35229 |
+
{
|
| 35230 |
+
"epoch": 5.731623931623932,
|
| 35231 |
+
"grad_norm": 0.15044721961021423,
|
| 35232 |
+
"learning_rate": 4.229897173085896e-05,
|
| 35233 |
+
"loss": 0.8002,
|
| 35234 |
+
"step": 5032
|
| 35235 |
+
},
|
| 35236 |
+
{
|
| 35237 |
+
"epoch": 5.732763532763533,
|
| 35238 |
+
"grad_norm": 0.18368439376354218,
|
| 35239 |
+
"learning_rate": 4.229560779555991e-05,
|
| 35240 |
+
"loss": 0.7507,
|
| 35241 |
+
"step": 5033
|
| 35242 |
+
},
|
| 35243 |
+
{
|
| 35244 |
+
"epoch": 5.733903133903134,
|
| 35245 |
+
"grad_norm": 0.18186402320861816,
|
| 35246 |
+
"learning_rate": 4.229224325953684e-05,
|
| 35247 |
+
"loss": 0.6836,
|
| 35248 |
+
"step": 5034
|
| 35249 |
+
},
|
| 35250 |
+
{
|
| 35251 |
+
"epoch": 5.735042735042735,
|
| 35252 |
+
"grad_norm": 0.15832217037677765,
|
| 35253 |
+
"learning_rate": 4.22888781229066e-05,
|
| 35254 |
+
"loss": 0.7728,
|
| 35255 |
+
"step": 5035
|
| 35256 |
+
},
|
| 35257 |
+
{
|
| 35258 |
+
"epoch": 5.7361823361823365,
|
| 35259 |
+
"grad_norm": 0.16162727773189545,
|
| 35260 |
+
"learning_rate": 4.228551238578609e-05,
|
| 35261 |
+
"loss": 0.8511,
|
| 35262 |
+
"step": 5036
|
| 35263 |
+
},
|
| 35264 |
+
{
|
| 35265 |
+
"epoch": 5.737321937321937,
|
| 35266 |
+
"grad_norm": 0.18553316593170166,
|
| 35267 |
+
"learning_rate": 4.2282146048292186e-05,
|
| 35268 |
+
"loss": 0.7614,
|
| 35269 |
+
"step": 5037
|
| 35270 |
+
},
|
| 35271 |
+
{
|
| 35272 |
+
"epoch": 5.7384615384615385,
|
| 35273 |
+
"grad_norm": 0.2758096754550934,
|
| 35274 |
+
"learning_rate": 4.227877911054183e-05,
|
| 35275 |
+
"loss": 0.8668,
|
| 35276 |
+
"step": 5038
|
| 35277 |
+
},
|
| 35278 |
+
{
|
| 35279 |
+
"epoch": 5.73960113960114,
|
| 35280 |
+
"grad_norm": 0.16694800555706024,
|
| 35281 |
+
"learning_rate": 4.227541157265196e-05,
|
| 35282 |
+
"loss": 0.7571,
|
| 35283 |
+
"step": 5039
|
| 35284 |
+
},
|
| 35285 |
+
{
|
| 35286 |
+
"epoch": 5.7407407407407405,
|
| 35287 |
+
"grad_norm": 0.206983745098114,
|
| 35288 |
+
"learning_rate": 4.227204343473954e-05,
|
| 35289 |
+
"loss": 0.691,
|
| 35290 |
+
"step": 5040
|
| 35291 |
+
},
|
| 35292 |
+
{
|
| 35293 |
+
"epoch": 5.741880341880342,
|
| 35294 |
+
"grad_norm": 0.1555628925561905,
|
| 35295 |
+
"learning_rate": 4.226867469692155e-05,
|
| 35296 |
+
"loss": 0.9326,
|
| 35297 |
+
"step": 5041
|
| 35298 |
+
},
|
| 35299 |
+
{
|
| 35300 |
+
"epoch": 5.743019943019943,
|
| 35301 |
+
"grad_norm": 0.16682085394859314,
|
| 35302 |
+
"learning_rate": 4.2265305359315e-05,
|
| 35303 |
+
"loss": 0.7891,
|
| 35304 |
+
"step": 5042
|
| 35305 |
+
},
|
| 35306 |
+
{
|
| 35307 |
+
"epoch": 5.744159544159544,
|
| 35308 |
+
"grad_norm": 0.1864742785692215,
|
| 35309 |
+
"learning_rate": 4.2261935422036916e-05,
|
| 35310 |
+
"loss": 0.6711,
|
| 35311 |
+
"step": 5043
|
| 35312 |
+
},
|
| 35313 |
+
{
|
| 35314 |
+
"epoch": 5.745299145299145,
|
| 35315 |
+
"grad_norm": 0.15288496017456055,
|
| 35316 |
+
"learning_rate": 4.2258564885204335e-05,
|
| 35317 |
+
"loss": 0.9792,
|
| 35318 |
+
"step": 5044
|
| 35319 |
+
},
|
| 35320 |
+
{
|
| 35321 |
+
"epoch": 5.746438746438747,
|
| 35322 |
+
"grad_norm": 0.15460316836833954,
|
| 35323 |
+
"learning_rate": 4.2255193748934344e-05,
|
| 35324 |
+
"loss": 0.6918,
|
| 35325 |
+
"step": 5045
|
| 35326 |
+
},
|
| 35327 |
+
{
|
| 35328 |
+
"epoch": 5.747578347578347,
|
| 35329 |
+
"grad_norm": 0.18567848205566406,
|
| 35330 |
+
"learning_rate": 4.225182201334402e-05,
|
| 35331 |
+
"loss": 0.9028,
|
| 35332 |
+
"step": 5046
|
| 35333 |
+
},
|
| 35334 |
+
{
|
| 35335 |
+
"epoch": 5.748717948717949,
|
| 35336 |
+
"grad_norm": 0.18545792996883392,
|
| 35337 |
+
"learning_rate": 4.224844967855048e-05,
|
| 35338 |
+
"loss": 0.7331,
|
| 35339 |
+
"step": 5047
|
| 35340 |
+
},
|
| 35341 |
+
{
|
| 35342 |
+
"epoch": 5.74985754985755,
|
| 35343 |
+
"grad_norm": 0.16540810465812683,
|
| 35344 |
+
"learning_rate": 4.224507674467084e-05,
|
| 35345 |
+
"loss": 0.7839,
|
| 35346 |
+
"step": 5048
|
| 35347 |
+
},
|
| 35348 |
+
{
|
| 35349 |
+
"epoch": 5.750997150997151,
|
| 35350 |
+
"grad_norm": 0.12994205951690674,
|
| 35351 |
+
"learning_rate": 4.2241703211822266e-05,
|
| 35352 |
+
"loss": 1.0731,
|
| 35353 |
+
"step": 5049
|
| 35354 |
+
},
|
| 35355 |
+
{
|
| 35356 |
+
"epoch": 5.752136752136752,
|
| 35357 |
+
"grad_norm": 0.17859558761119843,
|
| 35358 |
+
"learning_rate": 4.223832908012192e-05,
|
| 35359 |
+
"loss": 0.8567,
|
| 35360 |
+
"step": 5050
|
| 35361 |
+
},
|
| 35362 |
+
{
|
| 35363 |
+
"epoch": 5.753276353276354,
|
| 35364 |
+
"grad_norm": 0.19815339148044586,
|
| 35365 |
+
"learning_rate": 4.223495434968701e-05,
|
| 35366 |
+
"loss": 0.6952,
|
| 35367 |
+
"step": 5051
|
| 35368 |
+
},
|
| 35369 |
+
{
|
| 35370 |
+
"epoch": 5.754415954415954,
|
| 35371 |
+
"grad_norm": 0.16859059035778046,
|
| 35372 |
+
"learning_rate": 4.2231579020634725e-05,
|
| 35373 |
+
"loss": 0.8569,
|
| 35374 |
+
"step": 5052
|
| 35375 |
+
},
|
| 35376 |
+
{
|
| 35377 |
+
"epoch": 5.7555555555555555,
|
| 35378 |
+
"grad_norm": 0.16981007158756256,
|
| 35379 |
+
"learning_rate": 4.2228203093082326e-05,
|
| 35380 |
+
"loss": 0.729,
|
| 35381 |
+
"step": 5053
|
| 35382 |
+
},
|
| 35383 |
+
{
|
| 35384 |
+
"epoch": 5.756695156695157,
|
| 35385 |
+
"grad_norm": 0.18223218619823456,
|
| 35386 |
+
"learning_rate": 4.2224826567147045e-05,
|
| 35387 |
+
"loss": 0.9647,
|
| 35388 |
+
"step": 5054
|
| 35389 |
+
},
|
| 35390 |
+
{
|
| 35391 |
+
"epoch": 5.7578347578347575,
|
| 35392 |
+
"grad_norm": 0.17027547955513,
|
| 35393 |
+
"learning_rate": 4.222144944294618e-05,
|
| 35394 |
+
"loss": 0.9492,
|
| 35395 |
+
"step": 5055
|
| 35396 |
+
},
|
| 35397 |
+
{
|
| 35398 |
+
"epoch": 5.758974358974359,
|
| 35399 |
+
"grad_norm": 0.17369578778743744,
|
| 35400 |
+
"learning_rate": 4.2218071720597006e-05,
|
| 35401 |
+
"loss": 0.7478,
|
| 35402 |
+
"step": 5056
|
| 35403 |
+
},
|
| 35404 |
+
{
|
| 35405 |
+
"epoch": 5.76011396011396,
|
| 35406 |
+
"grad_norm": 0.1581421196460724,
|
| 35407 |
+
"learning_rate": 4.221469340021686e-05,
|
| 35408 |
+
"loss": 0.7778,
|
| 35409 |
+
"step": 5057
|
| 35410 |
+
},
|
| 35411 |
+
{
|
| 35412 |
+
"epoch": 5.761253561253561,
|
| 35413 |
+
"grad_norm": 0.1838197261095047,
|
| 35414 |
+
"learning_rate": 4.2211314481923067e-05,
|
| 35415 |
+
"loss": 0.7994,
|
| 35416 |
+
"step": 5058
|
| 35417 |
+
},
|
| 35418 |
+
{
|
| 35419 |
+
"epoch": 5.762393162393162,
|
| 35420 |
+
"grad_norm": 0.15999150276184082,
|
| 35421 |
+
"learning_rate": 4.2207934965833e-05,
|
| 35422 |
+
"loss": 0.8862,
|
| 35423 |
+
"step": 5059
|
| 35424 |
+
},
|
| 35425 |
+
{
|
| 35426 |
+
"epoch": 5.763532763532764,
|
| 35427 |
+
"grad_norm": 0.1751394122838974,
|
| 35428 |
+
"learning_rate": 4.220455485206402e-05,
|
| 35429 |
+
"loss": 0.7856,
|
| 35430 |
+
"step": 5060
|
| 35431 |
+
},
|
| 35432 |
+
{
|
| 35433 |
+
"epoch": 5.764672364672364,
|
| 35434 |
+
"grad_norm": 0.13892380893230438,
|
| 35435 |
+
"learning_rate": 4.2201174140733535e-05,
|
| 35436 |
+
"loss": 0.9042,
|
| 35437 |
+
"step": 5061
|
| 35438 |
+
},
|
| 35439 |
+
{
|
| 35440 |
+
"epoch": 5.765811965811966,
|
| 35441 |
+
"grad_norm": 0.16788841784000397,
|
| 35442 |
+
"learning_rate": 4.219779283195897e-05,
|
| 35443 |
+
"loss": 0.9338,
|
| 35444 |
+
"step": 5062
|
| 35445 |
+
},
|
| 35446 |
+
{
|
| 35447 |
+
"epoch": 5.766951566951567,
|
| 35448 |
+
"grad_norm": 0.22517052292823792,
|
| 35449 |
+
"learning_rate": 4.219441092585777e-05,
|
| 35450 |
+
"loss": 0.7178,
|
| 35451 |
+
"step": 5063
|
| 35452 |
+
},
|
| 35453 |
+
{
|
| 35454 |
+
"epoch": 5.768091168091168,
|
| 35455 |
+
"grad_norm": 0.1257663071155548,
|
| 35456 |
+
"learning_rate": 4.219102842254739e-05,
|
| 35457 |
+
"loss": 0.9102,
|
| 35458 |
+
"step": 5064
|
| 35459 |
+
},
|
| 35460 |
+
{
|
| 35461 |
+
"epoch": 5.769230769230769,
|
| 35462 |
+
"grad_norm": 0.1383146196603775,
|
| 35463 |
+
"learning_rate": 4.218764532214532e-05,
|
| 35464 |
+
"loss": 0.8179,
|
| 35465 |
+
"step": 5065
|
| 35466 |
+
},
|
| 35467 |
+
{
|
| 35468 |
+
"epoch": 5.770370370370371,
|
| 35469 |
+
"grad_norm": 0.19434872269630432,
|
| 35470 |
+
"learning_rate": 4.2184261624769064e-05,
|
| 35471 |
+
"loss": 0.6797,
|
| 35472 |
+
"step": 5066
|
| 35473 |
+
},
|
| 35474 |
+
{
|
| 35475 |
+
"epoch": 5.771509971509971,
|
| 35476 |
+
"grad_norm": 0.15667624771595,
|
| 35477 |
+
"learning_rate": 4.218087733053614e-05,
|
| 35478 |
+
"loss": 0.981,
|
| 35479 |
+
"step": 5067
|
| 35480 |
+
},
|
| 35481 |
+
{
|
| 35482 |
+
"epoch": 5.772649572649573,
|
| 35483 |
+
"grad_norm": 0.1542641520500183,
|
| 35484 |
+
"learning_rate": 4.21774924395641e-05,
|
| 35485 |
+
"loss": 0.9116,
|
| 35486 |
+
"step": 5068
|
| 35487 |
+
},
|
| 35488 |
+
{
|
| 35489 |
+
"epoch": 5.773789173789174,
|
| 35490 |
+
"grad_norm": 0.18515565991401672,
|
| 35491 |
+
"learning_rate": 4.217410695197051e-05,
|
| 35492 |
+
"loss": 0.8837,
|
| 35493 |
+
"step": 5069
|
| 35494 |
+
},
|
| 35495 |
+
{
|
| 35496 |
+
"epoch": 5.7749287749287745,
|
| 35497 |
+
"grad_norm": 0.17671780288219452,
|
| 35498 |
+
"learning_rate": 4.2170720867872954e-05,
|
| 35499 |
+
"loss": 0.854,
|
| 35500 |
+
"step": 5070
|
| 35501 |
+
},
|
| 35502 |
+
{
|
| 35503 |
+
"epoch": 5.776068376068376,
|
| 35504 |
+
"grad_norm": 0.18356047570705414,
|
| 35505 |
+
"learning_rate": 4.216733418738904e-05,
|
| 35506 |
+
"loss": 0.8568,
|
| 35507 |
+
"step": 5071
|
| 35508 |
+
},
|
| 35509 |
+
{
|
| 35510 |
+
"epoch": 5.777207977207977,
|
| 35511 |
+
"grad_norm": 0.19212129712104797,
|
| 35512 |
+
"learning_rate": 4.216394691063641e-05,
|
| 35513 |
+
"loss": 0.6283,
|
| 35514 |
+
"step": 5072
|
| 35515 |
+
},
|
| 35516 |
+
{
|
| 35517 |
+
"epoch": 5.778347578347578,
|
| 35518 |
+
"grad_norm": 0.17566898465156555,
|
| 35519 |
+
"learning_rate": 4.2160559037732694e-05,
|
| 35520 |
+
"loss": 0.84,
|
| 35521 |
+
"step": 5073
|
| 35522 |
+
},
|
| 35523 |
+
{
|
| 35524 |
+
"epoch": 5.779487179487179,
|
| 35525 |
+
"grad_norm": 0.15893234312534332,
|
| 35526 |
+
"learning_rate": 4.215717056879558e-05,
|
| 35527 |
+
"loss": 0.785,
|
| 35528 |
+
"step": 5074
|
| 35529 |
+
},
|
| 35530 |
+
{
|
| 35531 |
+
"epoch": 5.780626780626781,
|
| 35532 |
+
"grad_norm": 0.15502238273620605,
|
| 35533 |
+
"learning_rate": 4.2153781503942744e-05,
|
| 35534 |
+
"loss": 0.9261,
|
| 35535 |
+
"step": 5075
|
| 35536 |
+
},
|
| 35537 |
+
{
|
| 35538 |
+
"epoch": 5.781766381766381,
|
| 35539 |
+
"grad_norm": 0.18266864120960236,
|
| 35540 |
+
"learning_rate": 4.21503918432919e-05,
|
| 35541 |
+
"loss": 0.6755,
|
| 35542 |
+
"step": 5076
|
| 35543 |
+
},
|
| 35544 |
+
{
|
| 35545 |
+
"epoch": 5.782905982905983,
|
| 35546 |
+
"grad_norm": 0.17326800525188446,
|
| 35547 |
+
"learning_rate": 4.214700158696079e-05,
|
| 35548 |
+
"loss": 0.7029,
|
| 35549 |
+
"step": 5077
|
| 35550 |
+
},
|
| 35551 |
+
{
|
| 35552 |
+
"epoch": 5.784045584045584,
|
| 35553 |
+
"grad_norm": 0.1718059480190277,
|
| 35554 |
+
"learning_rate": 4.214361073506715e-05,
|
| 35555 |
+
"loss": 0.8196,
|
| 35556 |
+
"step": 5078
|
| 35557 |
+
},
|
| 35558 |
+
{
|
| 35559 |
+
"epoch": 5.785185185185185,
|
| 35560 |
+
"grad_norm": 0.18499065935611725,
|
| 35561 |
+
"learning_rate": 4.2140219287728776e-05,
|
| 35562 |
+
"loss": 0.7205,
|
| 35563 |
+
"step": 5079
|
| 35564 |
+
},
|
| 35565 |
+
{
|
| 35566 |
+
"epoch": 5.786324786324786,
|
| 35567 |
+
"grad_norm": 0.1749192476272583,
|
| 35568 |
+
"learning_rate": 4.2136827245063444e-05,
|
| 35569 |
+
"loss": 0.8313,
|
| 35570 |
+
"step": 5080
|
| 35571 |
+
},
|
| 35572 |
+
{
|
| 35573 |
+
"epoch": 5.787464387464388,
|
| 35574 |
+
"grad_norm": 0.16277176141738892,
|
| 35575 |
+
"learning_rate": 4.2133434607188973e-05,
|
| 35576 |
+
"loss": 0.7105,
|
| 35577 |
+
"step": 5081
|
| 35578 |
+
},
|
| 35579 |
+
{
|
| 35580 |
+
"epoch": 5.788603988603988,
|
| 35581 |
+
"grad_norm": 0.1911974400281906,
|
| 35582 |
+
"learning_rate": 4.2130041374223205e-05,
|
| 35583 |
+
"loss": 0.6628,
|
| 35584 |
+
"step": 5082
|
| 35585 |
+
},
|
| 35586 |
+
{
|
| 35587 |
+
"epoch": 5.78974358974359,
|
| 35588 |
+
"grad_norm": 0.2054838091135025,
|
| 35589 |
+
"learning_rate": 4.212664754628399e-05,
|
| 35590 |
+
"loss": 0.6555,
|
| 35591 |
+
"step": 5083
|
| 35592 |
+
},
|
| 35593 |
+
{
|
| 35594 |
+
"epoch": 5.790883190883191,
|
| 35595 |
+
"grad_norm": 0.22773410379886627,
|
| 35596 |
+
"learning_rate": 4.212325312348921e-05,
|
| 35597 |
+
"loss": 0.5956,
|
| 35598 |
+
"step": 5084
|
| 35599 |
+
},
|
| 35600 |
+
{
|
| 35601 |
+
"epoch": 5.792022792022792,
|
| 35602 |
+
"grad_norm": 0.19942957162857056,
|
| 35603 |
+
"learning_rate": 4.211985810595677e-05,
|
| 35604 |
+
"loss": 0.577,
|
| 35605 |
+
"step": 5085
|
| 35606 |
+
},
|
| 35607 |
+
{
|
| 35608 |
+
"epoch": 5.793162393162393,
|
| 35609 |
+
"grad_norm": 0.1661948412656784,
|
| 35610 |
+
"learning_rate": 4.211646249380456e-05,
|
| 35611 |
+
"loss": 0.8215,
|
| 35612 |
+
"step": 5086
|
| 35613 |
+
},
|
| 35614 |
+
{
|
| 35615 |
+
"epoch": 5.794301994301994,
|
| 35616 |
+
"grad_norm": 0.16536158323287964,
|
| 35617 |
+
"learning_rate": 4.211306628715054e-05,
|
| 35618 |
+
"loss": 0.6998,
|
| 35619 |
+
"step": 5087
|
| 35620 |
+
},
|
| 35621 |
+
{
|
| 35622 |
+
"epoch": 5.795441595441595,
|
| 35623 |
+
"grad_norm": 0.15531805157661438,
|
| 35624 |
+
"learning_rate": 4.210966948611267e-05,
|
| 35625 |
+
"loss": 0.8808,
|
| 35626 |
+
"step": 5088
|
| 35627 |
+
},
|
| 35628 |
+
{
|
| 35629 |
+
"epoch": 5.796581196581196,
|
| 35630 |
+
"grad_norm": 0.23157507181167603,
|
| 35631 |
+
"learning_rate": 4.210627209080893e-05,
|
| 35632 |
+
"loss": 0.6034,
|
| 35633 |
+
"step": 5089
|
| 35634 |
+
},
|
| 35635 |
+
{
|
| 35636 |
+
"epoch": 5.797720797720798,
|
| 35637 |
+
"grad_norm": 0.19956889748573303,
|
| 35638 |
+
"learning_rate": 4.210287410135732e-05,
|
| 35639 |
+
"loss": 0.7874,
|
| 35640 |
+
"step": 5090
|
| 35641 |
+
},
|
| 35642 |
+
{
|
| 35643 |
+
"epoch": 5.798860398860398,
|
| 35644 |
+
"grad_norm": 0.17820307612419128,
|
| 35645 |
+
"learning_rate": 4.209947551787585e-05,
|
| 35646 |
+
"loss": 0.7935,
|
| 35647 |
+
"step": 5091
|
| 35648 |
+
},
|
| 35649 |
+
{
|
| 35650 |
+
"epoch": 5.8,
|
| 35651 |
+
"grad_norm": 0.198835089802742,
|
| 35652 |
+
"learning_rate": 4.2096076340482585e-05,
|
| 35653 |
+
"loss": 0.768,
|
| 35654 |
+
"step": 5092
|
| 35655 |
+
},
|
| 35656 |
+
{
|
| 35657 |
+
"epoch": 5.801139601139601,
|
| 35658 |
+
"grad_norm": 0.19154450297355652,
|
| 35659 |
+
"learning_rate": 4.2092676569295566e-05,
|
| 35660 |
+
"loss": 0.641,
|
| 35661 |
+
"step": 5093
|
| 35662 |
+
},
|
| 35663 |
+
{
|
| 35664 |
+
"epoch": 5.802279202279202,
|
| 35665 |
+
"grad_norm": 0.1891769915819168,
|
| 35666 |
+
"learning_rate": 4.2089276204432884e-05,
|
| 35667 |
+
"loss": 0.8174,
|
| 35668 |
+
"step": 5094
|
| 35669 |
+
},
|
| 35670 |
+
{
|
| 35671 |
+
"epoch": 5.803418803418803,
|
| 35672 |
+
"grad_norm": 0.17773933708667755,
|
| 35673 |
+
"learning_rate": 4.2085875246012644e-05,
|
| 35674 |
+
"loss": 0.7182,
|
| 35675 |
+
"step": 5095
|
| 35676 |
+
},
|
| 35677 |
+
{
|
| 35678 |
+
"epoch": 5.804558404558405,
|
| 35679 |
+
"grad_norm": 0.18512803316116333,
|
| 35680 |
+
"learning_rate": 4.208247369415297e-05,
|
| 35681 |
+
"loss": 0.8497,
|
| 35682 |
+
"step": 5096
|
| 35683 |
+
},
|
| 35684 |
+
{
|
| 35685 |
+
"epoch": 5.805698005698005,
|
| 35686 |
+
"grad_norm": 0.15735124051570892,
|
| 35687 |
+
"learning_rate": 4.2079071548972e-05,
|
| 35688 |
+
"loss": 0.9022,
|
| 35689 |
+
"step": 5097
|
| 35690 |
+
},
|
| 35691 |
+
{
|
| 35692 |
+
"epoch": 5.806837606837607,
|
| 35693 |
+
"grad_norm": 0.17104484140872955,
|
| 35694 |
+
"learning_rate": 4.207566881058792e-05,
|
| 35695 |
+
"loss": 0.7536,
|
| 35696 |
+
"step": 5098
|
| 35697 |
+
},
|
| 35698 |
+
{
|
| 35699 |
+
"epoch": 5.807977207977208,
|
| 35700 |
+
"grad_norm": 0.15059272944927216,
|
| 35701 |
+
"learning_rate": 4.20722654791189e-05,
|
| 35702 |
+
"loss": 0.9023,
|
| 35703 |
+
"step": 5099
|
| 35704 |
+
},
|
| 35705 |
+
{
|
| 35706 |
+
"epoch": 5.8091168091168095,
|
| 35707 |
+
"grad_norm": 0.2025473415851593,
|
| 35708 |
+
"learning_rate": 4.206886155468316e-05,
|
| 35709 |
+
"loss": 0.639,
|
| 35710 |
+
"step": 5100
|
| 35711 |
}
|
| 35712 |
],
|
| 35713 |
"logging_steps": 1,
|
|
|
|
| 35727 |
"attributes": {}
|
| 35728 |
}
|
| 35729 |
},
|
| 35730 |
+
"total_flos": 2.8518065902420623e+19,
|
| 35731 |
"train_batch_size": 8,
|
| 35732 |
"trial_name": null,
|
| 35733 |
"trial_params": null
|