Instructions to use shareit/chatbot-supervisor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shareit/chatbot-supervisor with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shareit/chatbot-supervisor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Training in progress, step 12900, 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:ceb0e890e218fe8e20c570a29b107068d016b17399173eb62d7689077c05da7d
|
| 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:a560f7248f63961009833d41c63f03d479fd58b7badc181df5db2d7b4be82385
|
| 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 sha256:42553d0064a74656206f2fbca8f83414bac13ee836f77c0a48e15078898b1fa8
|
| 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": 14.
|
| 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,
|
|
@@ -88208,6 +88208,2106 @@
|
|
| 88208 |
"learning_rate": 9.945509570496425e-06,
|
| 88209 |
"loss": 0.8745,
|
| 88210 |
"step": 12600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88211 |
}
|
| 88212 |
],
|
| 88213 |
"logging_steps": 1,
|
|
@@ -88227,7 +90327,7 @@
|
|
| 88227 |
"attributes": {}
|
| 88228 |
}
|
| 88229 |
},
|
| 88230 |
-
"total_flos": 7.
|
| 88231 |
"train_batch_size": 8,
|
| 88232 |
"trial_name": null,
|
| 88233 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.692877492877493,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 12900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 88208 |
"learning_rate": 9.945509570496425e-06,
|
| 88209 |
"loss": 0.8745,
|
| 88210 |
"step": 12600
|
| 88211 |
+
},
|
| 88212 |
+
{
|
| 88213 |
+
"epoch": 14.352136752136753,
|
| 88214 |
+
"grad_norm": 0.20757326483726501,
|
| 88215 |
+
"learning_rate": 9.941790125137888e-06,
|
| 88216 |
+
"loss": 0.8031,
|
| 88217 |
+
"step": 12601
|
| 88218 |
+
},
|
| 88219 |
+
{
|
| 88220 |
+
"epoch": 14.353276353276353,
|
| 88221 |
+
"grad_norm": 0.16720442473888397,
|
| 88222 |
+
"learning_rate": 9.938071202792398e-06,
|
| 88223 |
+
"loss": 0.5974,
|
| 88224 |
+
"step": 12602
|
| 88225 |
+
},
|
| 88226 |
+
{
|
| 88227 |
+
"epoch": 14.354415954415954,
|
| 88228 |
+
"grad_norm": 0.23214448988437653,
|
| 88229 |
+
"learning_rate": 9.934352803589108e-06,
|
| 88230 |
+
"loss": 0.4563,
|
| 88231 |
+
"step": 12603
|
| 88232 |
+
},
|
| 88233 |
+
{
|
| 88234 |
+
"epoch": 14.355555555555556,
|
| 88235 |
+
"grad_norm": 0.21899637579917908,
|
| 88236 |
+
"learning_rate": 9.930634927657173e-06,
|
| 88237 |
+
"loss": 0.7588,
|
| 88238 |
+
"step": 12604
|
| 88239 |
+
},
|
| 88240 |
+
{
|
| 88241 |
+
"epoch": 14.356695156695157,
|
| 88242 |
+
"grad_norm": 0.17524579167366028,
|
| 88243 |
+
"learning_rate": 9.92691757512573e-06,
|
| 88244 |
+
"loss": 0.705,
|
| 88245 |
+
"step": 12605
|
| 88246 |
+
},
|
| 88247 |
+
{
|
| 88248 |
+
"epoch": 14.357834757834757,
|
| 88249 |
+
"grad_norm": 0.34279492497444153,
|
| 88250 |
+
"learning_rate": 9.923200746123902e-06,
|
| 88251 |
+
"loss": 0.4724,
|
| 88252 |
+
"step": 12606
|
| 88253 |
+
},
|
| 88254 |
+
{
|
| 88255 |
+
"epoch": 14.35897435897436,
|
| 88256 |
+
"grad_norm": 0.212101548910141,
|
| 88257 |
+
"learning_rate": 9.919484440780752e-06,
|
| 88258 |
+
"loss": 0.4934,
|
| 88259 |
+
"step": 12607
|
| 88260 |
+
},
|
| 88261 |
+
{
|
| 88262 |
+
"epoch": 14.36011396011396,
|
| 88263 |
+
"grad_norm": 0.23800750076770782,
|
| 88264 |
+
"learning_rate": 9.915768659225389e-06,
|
| 88265 |
+
"loss": 0.5828,
|
| 88266 |
+
"step": 12608
|
| 88267 |
+
},
|
| 88268 |
+
{
|
| 88269 |
+
"epoch": 14.36125356125356,
|
| 88270 |
+
"grad_norm": 0.18548652529716492,
|
| 88271 |
+
"learning_rate": 9.912053401586871e-06,
|
| 88272 |
+
"loss": 0.7144,
|
| 88273 |
+
"step": 12609
|
| 88274 |
+
},
|
| 88275 |
+
{
|
| 88276 |
+
"epoch": 14.362393162393163,
|
| 88277 |
+
"grad_norm": 0.19872426986694336,
|
| 88278 |
+
"learning_rate": 9.908338667994221e-06,
|
| 88279 |
+
"loss": 0.8539,
|
| 88280 |
+
"step": 12610
|
| 88281 |
+
},
|
| 88282 |
+
{
|
| 88283 |
+
"epoch": 14.363532763532763,
|
| 88284 |
+
"grad_norm": 0.2006315290927887,
|
| 88285 |
+
"learning_rate": 9.904624458576472e-06,
|
| 88286 |
+
"loss": 0.5649,
|
| 88287 |
+
"step": 12611
|
| 88288 |
+
},
|
| 88289 |
+
{
|
| 88290 |
+
"epoch": 14.364672364672364,
|
| 88291 |
+
"grad_norm": 0.20271030068397522,
|
| 88292 |
+
"learning_rate": 9.900910773462626e-06,
|
| 88293 |
+
"loss": 0.7093,
|
| 88294 |
+
"step": 12612
|
| 88295 |
+
},
|
| 88296 |
+
{
|
| 88297 |
+
"epoch": 14.365811965811966,
|
| 88298 |
+
"grad_norm": 0.18042854964733124,
|
| 88299 |
+
"learning_rate": 9.897197612781684e-06,
|
| 88300 |
+
"loss": 0.7431,
|
| 88301 |
+
"step": 12613
|
| 88302 |
+
},
|
| 88303 |
+
{
|
| 88304 |
+
"epoch": 14.366951566951567,
|
| 88305 |
+
"grad_norm": 0.2093563824892044,
|
| 88306 |
+
"learning_rate": 9.89348497666259e-06,
|
| 88307 |
+
"loss": 0.6083,
|
| 88308 |
+
"step": 12614
|
| 88309 |
+
},
|
| 88310 |
+
{
|
| 88311 |
+
"epoch": 14.368091168091167,
|
| 88312 |
+
"grad_norm": 0.19551311433315277,
|
| 88313 |
+
"learning_rate": 9.889772865234306e-06,
|
| 88314 |
+
"loss": 0.7185,
|
| 88315 |
+
"step": 12615
|
| 88316 |
+
},
|
| 88317 |
+
{
|
| 88318 |
+
"epoch": 14.36923076923077,
|
| 88319 |
+
"grad_norm": 0.22333300113677979,
|
| 88320 |
+
"learning_rate": 9.886061278625766e-06,
|
| 88321 |
+
"loss": 0.6666,
|
| 88322 |
+
"step": 12616
|
| 88323 |
+
},
|
| 88324 |
+
{
|
| 88325 |
+
"epoch": 14.37037037037037,
|
| 88326 |
+
"grad_norm": 0.30139651894569397,
|
| 88327 |
+
"learning_rate": 9.882350216965889e-06,
|
| 88328 |
+
"loss": 0.4693,
|
| 88329 |
+
"step": 12617
|
| 88330 |
+
},
|
| 88331 |
+
{
|
| 88332 |
+
"epoch": 14.37150997150997,
|
| 88333 |
+
"grad_norm": 0.19599662721157074,
|
| 88334 |
+
"learning_rate": 9.878639680383544e-06,
|
| 88335 |
+
"loss": 0.8895,
|
| 88336 |
+
"step": 12618
|
| 88337 |
+
},
|
| 88338 |
+
{
|
| 88339 |
+
"epoch": 14.372649572649573,
|
| 88340 |
+
"grad_norm": 0.18975095450878143,
|
| 88341 |
+
"learning_rate": 9.874929669007637e-06,
|
| 88342 |
+
"loss": 0.7269,
|
| 88343 |
+
"step": 12619
|
| 88344 |
+
},
|
| 88345 |
+
{
|
| 88346 |
+
"epoch": 14.373789173789174,
|
| 88347 |
+
"grad_norm": 0.17602480947971344,
|
| 88348 |
+
"learning_rate": 9.871220182967026e-06,
|
| 88349 |
+
"loss": 0.7736,
|
| 88350 |
+
"step": 12620
|
| 88351 |
+
},
|
| 88352 |
+
{
|
| 88353 |
+
"epoch": 14.374928774928774,
|
| 88354 |
+
"grad_norm": 0.21895572543144226,
|
| 88355 |
+
"learning_rate": 9.86751122239053e-06,
|
| 88356 |
+
"loss": 0.5928,
|
| 88357 |
+
"step": 12621
|
| 88358 |
+
},
|
| 88359 |
+
{
|
| 88360 |
+
"epoch": 14.376068376068377,
|
| 88361 |
+
"grad_norm": 0.20463977754116058,
|
| 88362 |
+
"learning_rate": 9.863802787406987e-06,
|
| 88363 |
+
"loss": 0.6022,
|
| 88364 |
+
"step": 12622
|
| 88365 |
+
},
|
| 88366 |
+
{
|
| 88367 |
+
"epoch": 14.377207977207977,
|
| 88368 |
+
"grad_norm": 0.21554405987262726,
|
| 88369 |
+
"learning_rate": 9.860094878145195e-06,
|
| 88370 |
+
"loss": 0.5576,
|
| 88371 |
+
"step": 12623
|
| 88372 |
+
},
|
| 88373 |
+
{
|
| 88374 |
+
"epoch": 14.378347578347578,
|
| 88375 |
+
"grad_norm": 0.2489200383424759,
|
| 88376 |
+
"learning_rate": 9.856387494733957e-06,
|
| 88377 |
+
"loss": 0.7404,
|
| 88378 |
+
"step": 12624
|
| 88379 |
+
},
|
| 88380 |
+
{
|
| 88381 |
+
"epoch": 14.37948717948718,
|
| 88382 |
+
"grad_norm": 0.17984764277935028,
|
| 88383 |
+
"learning_rate": 9.852680637302011e-06,
|
| 88384 |
+
"loss": 0.773,
|
| 88385 |
+
"step": 12625
|
| 88386 |
+
},
|
| 88387 |
+
{
|
| 88388 |
+
"epoch": 14.38062678062678,
|
| 88389 |
+
"grad_norm": 0.21617358922958374,
|
| 88390 |
+
"learning_rate": 9.848974305978125e-06,
|
| 88391 |
+
"loss": 0.6936,
|
| 88392 |
+
"step": 12626
|
| 88393 |
+
},
|
| 88394 |
+
{
|
| 88395 |
+
"epoch": 14.381766381766381,
|
| 88396 |
+
"grad_norm": 0.2192595899105072,
|
| 88397 |
+
"learning_rate": 9.845268500891027e-06,
|
| 88398 |
+
"loss": 0.5369,
|
| 88399 |
+
"step": 12627
|
| 88400 |
+
},
|
| 88401 |
+
{
|
| 88402 |
+
"epoch": 14.382905982905983,
|
| 88403 |
+
"grad_norm": 0.16107606887817383,
|
| 88404 |
+
"learning_rate": 9.841563222169438e-06,
|
| 88405 |
+
"loss": 0.8325,
|
| 88406 |
+
"step": 12628
|
| 88407 |
+
},
|
| 88408 |
+
{
|
| 88409 |
+
"epoch": 14.384045584045584,
|
| 88410 |
+
"grad_norm": 0.28030702471733093,
|
| 88411 |
+
"learning_rate": 9.837858469942029e-06,
|
| 88412 |
+
"loss": 0.4332,
|
| 88413 |
+
"step": 12629
|
| 88414 |
+
},
|
| 88415 |
+
{
|
| 88416 |
+
"epoch": 14.385185185185184,
|
| 88417 |
+
"grad_norm": 0.1888609230518341,
|
| 88418 |
+
"learning_rate": 9.834154244337498e-06,
|
| 88419 |
+
"loss": 0.7117,
|
| 88420 |
+
"step": 12630
|
| 88421 |
+
},
|
| 88422 |
+
{
|
| 88423 |
+
"epoch": 14.386324786324787,
|
| 88424 |
+
"grad_norm": 0.18952858448028564,
|
| 88425 |
+
"learning_rate": 9.830450545484503e-06,
|
| 88426 |
+
"loss": 0.7184,
|
| 88427 |
+
"step": 12631
|
| 88428 |
+
},
|
| 88429 |
+
{
|
| 88430 |
+
"epoch": 14.387464387464387,
|
| 88431 |
+
"grad_norm": 0.20389395952224731,
|
| 88432 |
+
"learning_rate": 9.826747373511672e-06,
|
| 88433 |
+
"loss": 0.4769,
|
| 88434 |
+
"step": 12632
|
| 88435 |
+
},
|
| 88436 |
+
{
|
| 88437 |
+
"epoch": 14.388603988603988,
|
| 88438 |
+
"grad_norm": 0.202254980802536,
|
| 88439 |
+
"learning_rate": 9.823044728547628e-06,
|
| 88440 |
+
"loss": 0.6136,
|
| 88441 |
+
"step": 12633
|
| 88442 |
+
},
|
| 88443 |
+
{
|
| 88444 |
+
"epoch": 14.38974358974359,
|
| 88445 |
+
"grad_norm": 0.21321870386600494,
|
| 88446 |
+
"learning_rate": 9.81934261072098e-06,
|
| 88447 |
+
"loss": 0.7592,
|
| 88448 |
+
"step": 12634
|
| 88449 |
+
},
|
| 88450 |
+
{
|
| 88451 |
+
"epoch": 14.39088319088319,
|
| 88452 |
+
"grad_norm": 0.24171572923660278,
|
| 88453 |
+
"learning_rate": 9.81564102016031e-06,
|
| 88454 |
+
"loss": 0.5723,
|
| 88455 |
+
"step": 12635
|
| 88456 |
+
},
|
| 88457 |
+
{
|
| 88458 |
+
"epoch": 14.392022792022791,
|
| 88459 |
+
"grad_norm": 0.1769031584262848,
|
| 88460 |
+
"learning_rate": 9.811939956994194e-06,
|
| 88461 |
+
"loss": 0.6639,
|
| 88462 |
+
"step": 12636
|
| 88463 |
+
},
|
| 88464 |
+
{
|
| 88465 |
+
"epoch": 14.393162393162394,
|
| 88466 |
+
"grad_norm": 0.2373218834400177,
|
| 88467 |
+
"learning_rate": 9.80823942135116e-06,
|
| 88468 |
+
"loss": 0.603,
|
| 88469 |
+
"step": 12637
|
| 88470 |
+
},
|
| 88471 |
+
{
|
| 88472 |
+
"epoch": 14.394301994301994,
|
| 88473 |
+
"grad_norm": 0.21972903609275818,
|
| 88474 |
+
"learning_rate": 9.804539413359748e-06,
|
| 88475 |
+
"loss": 0.5304,
|
| 88476 |
+
"step": 12638
|
| 88477 |
+
},
|
| 88478 |
+
{
|
| 88479 |
+
"epoch": 14.395441595441595,
|
| 88480 |
+
"grad_norm": 0.19349251687526703,
|
| 88481 |
+
"learning_rate": 9.80083993314847e-06,
|
| 88482 |
+
"loss": 0.7405,
|
| 88483 |
+
"step": 12639
|
| 88484 |
+
},
|
| 88485 |
+
{
|
| 88486 |
+
"epoch": 14.396581196581197,
|
| 88487 |
+
"grad_norm": 0.22350339591503143,
|
| 88488 |
+
"learning_rate": 9.797140980845817e-06,
|
| 88489 |
+
"loss": 0.3881,
|
| 88490 |
+
"step": 12640
|
| 88491 |
+
},
|
| 88492 |
+
{
|
| 88493 |
+
"epoch": 14.397720797720797,
|
| 88494 |
+
"grad_norm": 0.17995622754096985,
|
| 88495 |
+
"learning_rate": 9.79344255658027e-06,
|
| 88496 |
+
"loss": 0.6166,
|
| 88497 |
+
"step": 12641
|
| 88498 |
+
},
|
| 88499 |
+
{
|
| 88500 |
+
"epoch": 14.398860398860398,
|
| 88501 |
+
"grad_norm": 0.21553608775138855,
|
| 88502 |
+
"learning_rate": 9.789744660480279e-06,
|
| 88503 |
+
"loss": 0.7,
|
| 88504 |
+
"step": 12642
|
| 88505 |
+
},
|
| 88506 |
+
{
|
| 88507 |
+
"epoch": 14.4,
|
| 88508 |
+
"grad_norm": 0.23543411493301392,
|
| 88509 |
+
"learning_rate": 9.786047292674294e-06,
|
| 88510 |
+
"loss": 0.4783,
|
| 88511 |
+
"step": 12643
|
| 88512 |
+
},
|
| 88513 |
+
{
|
| 88514 |
+
"epoch": 14.401139601139601,
|
| 88515 |
+
"grad_norm": 0.16944937407970428,
|
| 88516 |
+
"learning_rate": 9.782350453290715e-06,
|
| 88517 |
+
"loss": 0.7924,
|
| 88518 |
+
"step": 12644
|
| 88519 |
+
},
|
| 88520 |
+
{
|
| 88521 |
+
"epoch": 14.402279202279201,
|
| 88522 |
+
"grad_norm": 0.2010875940322876,
|
| 88523 |
+
"learning_rate": 9.778654142457954e-06,
|
| 88524 |
+
"loss": 0.7968,
|
| 88525 |
+
"step": 12645
|
| 88526 |
+
},
|
| 88527 |
+
{
|
| 88528 |
+
"epoch": 14.403418803418804,
|
| 88529 |
+
"grad_norm": 0.2124527394771576,
|
| 88530 |
+
"learning_rate": 9.774958360304396e-06,
|
| 88531 |
+
"loss": 0.6406,
|
| 88532 |
+
"step": 12646
|
| 88533 |
+
},
|
| 88534 |
+
{
|
| 88535 |
+
"epoch": 14.404558404558404,
|
| 88536 |
+
"grad_norm": 0.23077209293842316,
|
| 88537 |
+
"learning_rate": 9.771263106958409e-06,
|
| 88538 |
+
"loss": 0.6283,
|
| 88539 |
+
"step": 12647
|
| 88540 |
+
},
|
| 88541 |
+
{
|
| 88542 |
+
"epoch": 14.405698005698005,
|
| 88543 |
+
"grad_norm": 0.20528383553028107,
|
| 88544 |
+
"learning_rate": 9.767568382548326e-06,
|
| 88545 |
+
"loss": 0.7679,
|
| 88546 |
+
"step": 12648
|
| 88547 |
+
},
|
| 88548 |
+
{
|
| 88549 |
+
"epoch": 14.406837606837607,
|
| 88550 |
+
"grad_norm": 0.2082781195640564,
|
| 88551 |
+
"learning_rate": 9.76387418720248e-06,
|
| 88552 |
+
"loss": 0.8894,
|
| 88553 |
+
"step": 12649
|
| 88554 |
+
},
|
| 88555 |
+
{
|
| 88556 |
+
"epoch": 14.407977207977208,
|
| 88557 |
+
"grad_norm": 0.22017930448055267,
|
| 88558 |
+
"learning_rate": 9.760180521049186e-06,
|
| 88559 |
+
"loss": 0.6447,
|
| 88560 |
+
"step": 12650
|
| 88561 |
+
},
|
| 88562 |
+
{
|
| 88563 |
+
"epoch": 14.40911680911681,
|
| 88564 |
+
"grad_norm": 0.20738565921783447,
|
| 88565 |
+
"learning_rate": 9.756487384216732e-06,
|
| 88566 |
+
"loss": 0.4011,
|
| 88567 |
+
"step": 12651
|
| 88568 |
+
},
|
| 88569 |
+
{
|
| 88570 |
+
"epoch": 14.41025641025641,
|
| 88571 |
+
"grad_norm": 0.2789316177368164,
|
| 88572 |
+
"learning_rate": 9.752794776833387e-06,
|
| 88573 |
+
"loss": 0.6055,
|
| 88574 |
+
"step": 12652
|
| 88575 |
+
},
|
| 88576 |
+
{
|
| 88577 |
+
"epoch": 14.411396011396011,
|
| 88578 |
+
"grad_norm": 0.2477440983057022,
|
| 88579 |
+
"learning_rate": 9.749102699027413e-06,
|
| 88580 |
+
"loss": 0.7176,
|
| 88581 |
+
"step": 12653
|
| 88582 |
+
},
|
| 88583 |
+
{
|
| 88584 |
+
"epoch": 14.412535612535613,
|
| 88585 |
+
"grad_norm": 0.21437858045101166,
|
| 88586 |
+
"learning_rate": 9.74541115092705e-06,
|
| 88587 |
+
"loss": 0.7332,
|
| 88588 |
+
"step": 12654
|
| 88589 |
+
},
|
| 88590 |
+
{
|
| 88591 |
+
"epoch": 14.413675213675214,
|
| 88592 |
+
"grad_norm": 0.26130738854408264,
|
| 88593 |
+
"learning_rate": 9.741720132660501e-06,
|
| 88594 |
+
"loss": 0.5266,
|
| 88595 |
+
"step": 12655
|
| 88596 |
+
},
|
| 88597 |
+
{
|
| 88598 |
+
"epoch": 14.414814814814815,
|
| 88599 |
+
"grad_norm": 0.43563970923423767,
|
| 88600 |
+
"learning_rate": 9.738029644355969e-06,
|
| 88601 |
+
"loss": 0.7076,
|
| 88602 |
+
"step": 12656
|
| 88603 |
+
},
|
| 88604 |
+
{
|
| 88605 |
+
"epoch": 14.415954415954417,
|
| 88606 |
+
"grad_norm": 0.23455193638801575,
|
| 88607 |
+
"learning_rate": 9.734339686141642e-06,
|
| 88608 |
+
"loss": 0.5697,
|
| 88609 |
+
"step": 12657
|
| 88610 |
+
},
|
| 88611 |
+
{
|
| 88612 |
+
"epoch": 14.417094017094017,
|
| 88613 |
+
"grad_norm": 0.1981157809495926,
|
| 88614 |
+
"learning_rate": 9.730650258145684e-06,
|
| 88615 |
+
"loss": 0.6551,
|
| 88616 |
+
"step": 12658
|
| 88617 |
+
},
|
| 88618 |
+
{
|
| 88619 |
+
"epoch": 14.418233618233618,
|
| 88620 |
+
"grad_norm": 0.2522953748703003,
|
| 88621 |
+
"learning_rate": 9.726961360496226e-06,
|
| 88622 |
+
"loss": 0.6056,
|
| 88623 |
+
"step": 12659
|
| 88624 |
+
},
|
| 88625 |
+
{
|
| 88626 |
+
"epoch": 14.41937321937322,
|
| 88627 |
+
"grad_norm": 0.23770654201507568,
|
| 88628 |
+
"learning_rate": 9.7232729933214e-06,
|
| 88629 |
+
"loss": 0.7018,
|
| 88630 |
+
"step": 12660
|
| 88631 |
+
},
|
| 88632 |
+
{
|
| 88633 |
+
"epoch": 14.42051282051282,
|
| 88634 |
+
"grad_norm": 0.16990040242671967,
|
| 88635 |
+
"learning_rate": 9.719585156749317e-06,
|
| 88636 |
+
"loss": 0.7571,
|
| 88637 |
+
"step": 12661
|
| 88638 |
+
},
|
| 88639 |
+
{
|
| 88640 |
+
"epoch": 14.421652421652421,
|
| 88641 |
+
"grad_norm": 0.22051633894443512,
|
| 88642 |
+
"learning_rate": 9.71589785090806e-06,
|
| 88643 |
+
"loss": 0.5478,
|
| 88644 |
+
"step": 12662
|
| 88645 |
+
},
|
| 88646 |
+
{
|
| 88647 |
+
"epoch": 14.422792022792024,
|
| 88648 |
+
"grad_norm": 0.1829424798488617,
|
| 88649 |
+
"learning_rate": 9.712211075925704e-06,
|
| 88650 |
+
"loss": 0.7772,
|
| 88651 |
+
"step": 12663
|
| 88652 |
+
},
|
| 88653 |
+
{
|
| 88654 |
+
"epoch": 14.423931623931624,
|
| 88655 |
+
"grad_norm": 0.23964989185333252,
|
| 88656 |
+
"learning_rate": 9.708524831930297e-06,
|
| 88657 |
+
"loss": 0.6042,
|
| 88658 |
+
"step": 12664
|
| 88659 |
+
},
|
| 88660 |
+
{
|
| 88661 |
+
"epoch": 14.425071225071225,
|
| 88662 |
+
"grad_norm": 0.22030949592590332,
|
| 88663 |
+
"learning_rate": 9.704839119049883e-06,
|
| 88664 |
+
"loss": 0.6522,
|
| 88665 |
+
"step": 12665
|
| 88666 |
+
},
|
| 88667 |
+
{
|
| 88668 |
+
"epoch": 14.426210826210827,
|
| 88669 |
+
"grad_norm": 0.17135785520076752,
|
| 88670 |
+
"learning_rate": 9.70115393741246e-06,
|
| 88671 |
+
"loss": 0.5605,
|
| 88672 |
+
"step": 12666
|
| 88673 |
+
},
|
| 88674 |
+
{
|
| 88675 |
+
"epoch": 14.427350427350428,
|
| 88676 |
+
"grad_norm": 0.23122885823249817,
|
| 88677 |
+
"learning_rate": 9.697469287146033e-06,
|
| 88678 |
+
"loss": 0.6656,
|
| 88679 |
+
"step": 12667
|
| 88680 |
+
},
|
| 88681 |
+
{
|
| 88682 |
+
"epoch": 14.428490028490028,
|
| 88683 |
+
"grad_norm": 0.2249332070350647,
|
| 88684 |
+
"learning_rate": 9.69378516837858e-06,
|
| 88685 |
+
"loss": 0.4033,
|
| 88686 |
+
"step": 12668
|
| 88687 |
+
},
|
| 88688 |
+
{
|
| 88689 |
+
"epoch": 14.42962962962963,
|
| 88690 |
+
"grad_norm": 0.2665773332118988,
|
| 88691 |
+
"learning_rate": 9.690101581238067e-06,
|
| 88692 |
+
"loss": 0.4533,
|
| 88693 |
+
"step": 12669
|
| 88694 |
+
},
|
| 88695 |
+
{
|
| 88696 |
+
"epoch": 14.430769230769231,
|
| 88697 |
+
"grad_norm": 0.21018235385417938,
|
| 88698 |
+
"learning_rate": 9.686418525852423e-06,
|
| 88699 |
+
"loss": 0.6598,
|
| 88700 |
+
"step": 12670
|
| 88701 |
+
},
|
| 88702 |
+
{
|
| 88703 |
+
"epoch": 14.431908831908832,
|
| 88704 |
+
"grad_norm": 0.21335472166538239,
|
| 88705 |
+
"learning_rate": 9.682736002349574e-06,
|
| 88706 |
+
"loss": 0.6232,
|
| 88707 |
+
"step": 12671
|
| 88708 |
+
},
|
| 88709 |
+
{
|
| 88710 |
+
"epoch": 14.433048433048434,
|
| 88711 |
+
"grad_norm": 0.19291336834430695,
|
| 88712 |
+
"learning_rate": 9.679054010857427e-06,
|
| 88713 |
+
"loss": 0.6159,
|
| 88714 |
+
"step": 12672
|
| 88715 |
+
},
|
| 88716 |
+
{
|
| 88717 |
+
"epoch": 14.434188034188034,
|
| 88718 |
+
"grad_norm": 0.23985837399959564,
|
| 88719 |
+
"learning_rate": 9.675372551503867e-06,
|
| 88720 |
+
"loss": 0.4108,
|
| 88721 |
+
"step": 12673
|
| 88722 |
+
},
|
| 88723 |
+
{
|
| 88724 |
+
"epoch": 14.435327635327635,
|
| 88725 |
+
"grad_norm": 0.190646231174469,
|
| 88726 |
+
"learning_rate": 9.671691624416762e-06,
|
| 88727 |
+
"loss": 0.7489,
|
| 88728 |
+
"step": 12674
|
| 88729 |
+
},
|
| 88730 |
+
{
|
| 88731 |
+
"epoch": 14.436467236467237,
|
| 88732 |
+
"grad_norm": 0.1992843747138977,
|
| 88733 |
+
"learning_rate": 9.668011229723958e-06,
|
| 88734 |
+
"loss": 0.7786,
|
| 88735 |
+
"step": 12675
|
| 88736 |
+
},
|
| 88737 |
+
{
|
| 88738 |
+
"epoch": 14.437606837606838,
|
| 88739 |
+
"grad_norm": 0.18717506527900696,
|
| 88740 |
+
"learning_rate": 9.66433136755329e-06,
|
| 88741 |
+
"loss": 0.7573,
|
| 88742 |
+
"step": 12676
|
| 88743 |
+
},
|
| 88744 |
+
{
|
| 88745 |
+
"epoch": 14.438746438746438,
|
| 88746 |
+
"grad_norm": 0.20367279648780823,
|
| 88747 |
+
"learning_rate": 9.660652038032571e-06,
|
| 88748 |
+
"loss": 0.6206,
|
| 88749 |
+
"step": 12677
|
| 88750 |
+
},
|
| 88751 |
+
{
|
| 88752 |
+
"epoch": 14.43988603988604,
|
| 88753 |
+
"grad_norm": 0.22619666159152985,
|
| 88754 |
+
"learning_rate": 9.656973241289585e-06,
|
| 88755 |
+
"loss": 0.5807,
|
| 88756 |
+
"step": 12678
|
| 88757 |
+
},
|
| 88758 |
+
{
|
| 88759 |
+
"epoch": 14.441025641025641,
|
| 88760 |
+
"grad_norm": 0.21882672607898712,
|
| 88761 |
+
"learning_rate": 9.653294977452113e-06,
|
| 88762 |
+
"loss": 0.5644,
|
| 88763 |
+
"step": 12679
|
| 88764 |
+
},
|
| 88765 |
+
{
|
| 88766 |
+
"epoch": 14.442165242165242,
|
| 88767 |
+
"grad_norm": 0.25762587785720825,
|
| 88768 |
+
"learning_rate": 9.649617246647907e-06,
|
| 88769 |
+
"loss": 0.625,
|
| 88770 |
+
"step": 12680
|
| 88771 |
+
},
|
| 88772 |
+
{
|
| 88773 |
+
"epoch": 14.443304843304844,
|
| 88774 |
+
"grad_norm": 0.19522501528263092,
|
| 88775 |
+
"learning_rate": 9.645940049004718e-06,
|
| 88776 |
+
"loss": 0.8747,
|
| 88777 |
+
"step": 12681
|
| 88778 |
+
},
|
| 88779 |
+
{
|
| 88780 |
+
"epoch": 14.444444444444445,
|
| 88781 |
+
"grad_norm": 0.2014218121767044,
|
| 88782 |
+
"learning_rate": 9.642263384650243e-06,
|
| 88783 |
+
"loss": 0.5604,
|
| 88784 |
+
"step": 12682
|
| 88785 |
+
},
|
| 88786 |
+
{
|
| 88787 |
+
"epoch": 14.445584045584045,
|
| 88788 |
+
"grad_norm": 0.2044072151184082,
|
| 88789 |
+
"learning_rate": 9.6385872537122e-06,
|
| 88790 |
+
"loss": 0.7574,
|
| 88791 |
+
"step": 12683
|
| 88792 |
+
},
|
| 88793 |
+
{
|
| 88794 |
+
"epoch": 14.446723646723648,
|
| 88795 |
+
"grad_norm": 0.19156105816364288,
|
| 88796 |
+
"learning_rate": 9.634911656318263e-06,
|
| 88797 |
+
"loss": 0.7064,
|
| 88798 |
+
"step": 12684
|
| 88799 |
+
},
|
| 88800 |
+
{
|
| 88801 |
+
"epoch": 14.447863247863248,
|
| 88802 |
+
"grad_norm": 0.29438427090644836,
|
| 88803 |
+
"learning_rate": 9.631236592596097e-06,
|
| 88804 |
+
"loss": 0.5793,
|
| 88805 |
+
"step": 12685
|
| 88806 |
+
},
|
| 88807 |
+
{
|
| 88808 |
+
"epoch": 14.449002849002849,
|
| 88809 |
+
"grad_norm": 0.21377675235271454,
|
| 88810 |
+
"learning_rate": 9.62756206267335e-06,
|
| 88811 |
+
"loss": 0.4958,
|
| 88812 |
+
"step": 12686
|
| 88813 |
+
},
|
| 88814 |
+
{
|
| 88815 |
+
"epoch": 14.450142450142451,
|
| 88816 |
+
"grad_norm": 0.18951386213302612,
|
| 88817 |
+
"learning_rate": 9.623888066677648e-06,
|
| 88818 |
+
"loss": 0.6728,
|
| 88819 |
+
"step": 12687
|
| 88820 |
+
},
|
| 88821 |
+
{
|
| 88822 |
+
"epoch": 14.451282051282051,
|
| 88823 |
+
"grad_norm": 0.179488405585289,
|
| 88824 |
+
"learning_rate": 9.620214604736604e-06,
|
| 88825 |
+
"loss": 0.8694,
|
| 88826 |
+
"step": 12688
|
| 88827 |
+
},
|
| 88828 |
+
{
|
| 88829 |
+
"epoch": 14.452421652421652,
|
| 88830 |
+
"grad_norm": 0.25905686616897583,
|
| 88831 |
+
"learning_rate": 9.616541676977794e-06,
|
| 88832 |
+
"loss": 0.6106,
|
| 88833 |
+
"step": 12689
|
| 88834 |
+
},
|
| 88835 |
+
{
|
| 88836 |
+
"epoch": 14.453561253561254,
|
| 88837 |
+
"grad_norm": 0.18401479721069336,
|
| 88838 |
+
"learning_rate": 9.612869283528795e-06,
|
| 88839 |
+
"loss": 0.7346,
|
| 88840 |
+
"step": 12690
|
| 88841 |
+
},
|
| 88842 |
+
{
|
| 88843 |
+
"epoch": 14.454700854700855,
|
| 88844 |
+
"grad_norm": 0.22364789247512817,
|
| 88845 |
+
"learning_rate": 9.609197424517163e-06,
|
| 88846 |
+
"loss": 0.659,
|
| 88847 |
+
"step": 12691
|
| 88848 |
+
},
|
| 88849 |
+
{
|
| 88850 |
+
"epoch": 14.455840455840455,
|
| 88851 |
+
"grad_norm": 0.2187655121088028,
|
| 88852 |
+
"learning_rate": 9.605526100070437e-06,
|
| 88853 |
+
"loss": 0.6353,
|
| 88854 |
+
"step": 12692
|
| 88855 |
+
},
|
| 88856 |
+
{
|
| 88857 |
+
"epoch": 14.456980056980058,
|
| 88858 |
+
"grad_norm": 0.2196253538131714,
|
| 88859 |
+
"learning_rate": 9.601855310316113e-06,
|
| 88860 |
+
"loss": 0.9079,
|
| 88861 |
+
"step": 12693
|
| 88862 |
+
},
|
| 88863 |
+
{
|
| 88864 |
+
"epoch": 14.458119658119658,
|
| 88865 |
+
"grad_norm": 0.21198168396949768,
|
| 88866 |
+
"learning_rate": 9.598185055381704e-06,
|
| 88867 |
+
"loss": 0.7966,
|
| 88868 |
+
"step": 12694
|
| 88869 |
+
},
|
| 88870 |
+
{
|
| 88871 |
+
"epoch": 14.459259259259259,
|
| 88872 |
+
"grad_norm": 0.21943166851997375,
|
| 88873 |
+
"learning_rate": 9.59451533539468e-06,
|
| 88874 |
+
"loss": 0.7434,
|
| 88875 |
+
"step": 12695
|
| 88876 |
+
},
|
| 88877 |
+
{
|
| 88878 |
+
"epoch": 14.460398860398861,
|
| 88879 |
+
"grad_norm": 0.205881729722023,
|
| 88880 |
+
"learning_rate": 9.590846150482505e-06,
|
| 88881 |
+
"loss": 0.7832,
|
| 88882 |
+
"step": 12696
|
| 88883 |
+
},
|
| 88884 |
+
{
|
| 88885 |
+
"epoch": 14.461538461538462,
|
| 88886 |
+
"grad_norm": 0.18034107983112335,
|
| 88887 |
+
"learning_rate": 9.587177500772618e-06,
|
| 88888 |
+
"loss": 0.8069,
|
| 88889 |
+
"step": 12697
|
| 88890 |
+
},
|
| 88891 |
+
{
|
| 88892 |
+
"epoch": 14.462678062678062,
|
| 88893 |
+
"grad_norm": 0.24824191629886627,
|
| 88894 |
+
"learning_rate": 9.583509386392441e-06,
|
| 88895 |
+
"loss": 0.5957,
|
| 88896 |
+
"step": 12698
|
| 88897 |
+
},
|
| 88898 |
+
{
|
| 88899 |
+
"epoch": 14.463817663817665,
|
| 88900 |
+
"grad_norm": 0.26811710000038147,
|
| 88901 |
+
"learning_rate": 9.579841807469388e-06,
|
| 88902 |
+
"loss": 0.7547,
|
| 88903 |
+
"step": 12699
|
| 88904 |
+
},
|
| 88905 |
+
{
|
| 88906 |
+
"epoch": 14.464957264957265,
|
| 88907 |
+
"grad_norm": 0.18017862737178802,
|
| 88908 |
+
"learning_rate": 9.576174764130826e-06,
|
| 88909 |
+
"loss": 0.7503,
|
| 88910 |
+
"step": 12700
|
| 88911 |
+
},
|
| 88912 |
+
{
|
| 88913 |
+
"epoch": 14.466096866096866,
|
| 88914 |
+
"grad_norm": 0.2223409116268158,
|
| 88915 |
+
"learning_rate": 9.572508256504128e-06,
|
| 88916 |
+
"loss": 0.7536,
|
| 88917 |
+
"step": 12701
|
| 88918 |
+
},
|
| 88919 |
+
{
|
| 88920 |
+
"epoch": 14.467236467236468,
|
| 88921 |
+
"grad_norm": 0.1825609803199768,
|
| 88922 |
+
"learning_rate": 9.568842284716648e-06,
|
| 88923 |
+
"loss": 0.7122,
|
| 88924 |
+
"step": 12702
|
| 88925 |
+
},
|
| 88926 |
+
{
|
| 88927 |
+
"epoch": 14.468376068376068,
|
| 88928 |
+
"grad_norm": 0.22106508910655975,
|
| 88929 |
+
"learning_rate": 9.565176848895719e-06,
|
| 88930 |
+
"loss": 0.773,
|
| 88931 |
+
"step": 12703
|
| 88932 |
+
},
|
| 88933 |
+
{
|
| 88934 |
+
"epoch": 14.469515669515669,
|
| 88935 |
+
"grad_norm": 0.19889645278453827,
|
| 88936 |
+
"learning_rate": 9.561511949168634e-06,
|
| 88937 |
+
"loss": 0.6686,
|
| 88938 |
+
"step": 12704
|
| 88939 |
+
},
|
| 88940 |
+
{
|
| 88941 |
+
"epoch": 14.470655270655271,
|
| 88942 |
+
"grad_norm": 0.22566333413124084,
|
| 88943 |
+
"learning_rate": 9.557847585662694e-06,
|
| 88944 |
+
"loss": 0.4029,
|
| 88945 |
+
"step": 12705
|
| 88946 |
+
},
|
| 88947 |
+
{
|
| 88948 |
+
"epoch": 14.471794871794872,
|
| 88949 |
+
"grad_norm": 0.17428520321846008,
|
| 88950 |
+
"learning_rate": 9.554183758505176e-06,
|
| 88951 |
+
"loss": 0.6488,
|
| 88952 |
+
"step": 12706
|
| 88953 |
+
},
|
| 88954 |
+
{
|
| 88955 |
+
"epoch": 14.472934472934472,
|
| 88956 |
+
"grad_norm": 0.24169154465198517,
|
| 88957 |
+
"learning_rate": 9.55052046782333e-06,
|
| 88958 |
+
"loss": 0.6469,
|
| 88959 |
+
"step": 12707
|
| 88960 |
+
},
|
| 88961 |
+
{
|
| 88962 |
+
"epoch": 14.474074074074075,
|
| 88963 |
+
"grad_norm": 0.18107205629348755,
|
| 88964 |
+
"learning_rate": 9.546857713744396e-06,
|
| 88965 |
+
"loss": 0.5757,
|
| 88966 |
+
"step": 12708
|
| 88967 |
+
},
|
| 88968 |
+
{
|
| 88969 |
+
"epoch": 14.475213675213675,
|
| 88970 |
+
"grad_norm": 0.2407011091709137,
|
| 88971 |
+
"learning_rate": 9.543195496395588e-06,
|
| 88972 |
+
"loss": 0.494,
|
| 88973 |
+
"step": 12709
|
| 88974 |
+
},
|
| 88975 |
+
{
|
| 88976 |
+
"epoch": 14.476353276353276,
|
| 88977 |
+
"grad_norm": 0.19166330993175507,
|
| 88978 |
+
"learning_rate": 9.539533815904116e-06,
|
| 88979 |
+
"loss": 0.4467,
|
| 88980 |
+
"step": 12710
|
| 88981 |
+
},
|
| 88982 |
+
{
|
| 88983 |
+
"epoch": 14.477492877492878,
|
| 88984 |
+
"grad_norm": 0.2439434826374054,
|
| 88985 |
+
"learning_rate": 9.535872672397145e-06,
|
| 88986 |
+
"loss": 0.5605,
|
| 88987 |
+
"step": 12711
|
| 88988 |
+
},
|
| 88989 |
+
{
|
| 88990 |
+
"epoch": 14.478632478632479,
|
| 88991 |
+
"grad_norm": 0.2717639207839966,
|
| 88992 |
+
"learning_rate": 9.532212066001842e-06,
|
| 88993 |
+
"loss": 0.7126,
|
| 88994 |
+
"step": 12712
|
| 88995 |
+
},
|
| 88996 |
+
{
|
| 88997 |
+
"epoch": 14.47977207977208,
|
| 88998 |
+
"grad_norm": 0.22379228472709656,
|
| 88999 |
+
"learning_rate": 9.528551996845347e-06,
|
| 89000 |
+
"loss": 0.5616,
|
| 89001 |
+
"step": 12713
|
| 89002 |
+
},
|
| 89003 |
+
{
|
| 89004 |
+
"epoch": 14.480911680911682,
|
| 89005 |
+
"grad_norm": 0.22340011596679688,
|
| 89006 |
+
"learning_rate": 9.52489246505479e-06,
|
| 89007 |
+
"loss": 0.4267,
|
| 89008 |
+
"step": 12714
|
| 89009 |
+
},
|
| 89010 |
+
{
|
| 89011 |
+
"epoch": 14.482051282051282,
|
| 89012 |
+
"grad_norm": 0.17172454297542572,
|
| 89013 |
+
"learning_rate": 9.521233470757285e-06,
|
| 89014 |
+
"loss": 0.8249,
|
| 89015 |
+
"step": 12715
|
| 89016 |
+
},
|
| 89017 |
+
{
|
| 89018 |
+
"epoch": 14.483190883190883,
|
| 89019 |
+
"grad_norm": 0.19228993356227875,
|
| 89020 |
+
"learning_rate": 9.517575014079897e-06,
|
| 89021 |
+
"loss": 0.5293,
|
| 89022 |
+
"step": 12716
|
| 89023 |
+
},
|
| 89024 |
+
{
|
| 89025 |
+
"epoch": 14.484330484330485,
|
| 89026 |
+
"grad_norm": 0.17538754642009735,
|
| 89027 |
+
"learning_rate": 9.513917095149708e-06,
|
| 89028 |
+
"loss": 0.7077,
|
| 89029 |
+
"step": 12717
|
| 89030 |
+
},
|
| 89031 |
+
{
|
| 89032 |
+
"epoch": 14.485470085470086,
|
| 89033 |
+
"grad_norm": 0.16558973491191864,
|
| 89034 |
+
"learning_rate": 9.510259714093761e-06,
|
| 89035 |
+
"loss": 0.6564,
|
| 89036 |
+
"step": 12718
|
| 89037 |
+
},
|
| 89038 |
+
{
|
| 89039 |
+
"epoch": 14.486609686609686,
|
| 89040 |
+
"grad_norm": 0.15310008823871613,
|
| 89041 |
+
"learning_rate": 9.506602871039094e-06,
|
| 89042 |
+
"loss": 0.8839,
|
| 89043 |
+
"step": 12719
|
| 89044 |
+
},
|
| 89045 |
+
{
|
| 89046 |
+
"epoch": 14.487749287749288,
|
| 89047 |
+
"grad_norm": 0.20456555485725403,
|
| 89048 |
+
"learning_rate": 9.502946566112716e-06,
|
| 89049 |
+
"loss": 0.712,
|
| 89050 |
+
"step": 12720
|
| 89051 |
+
},
|
| 89052 |
+
{
|
| 89053 |
+
"epoch": 14.488888888888889,
|
| 89054 |
+
"grad_norm": 0.1737065464258194,
|
| 89055 |
+
"learning_rate": 9.49929079944162e-06,
|
| 89056 |
+
"loss": 0.8899,
|
| 89057 |
+
"step": 12721
|
| 89058 |
+
},
|
| 89059 |
+
{
|
| 89060 |
+
"epoch": 14.49002849002849,
|
| 89061 |
+
"grad_norm": 0.2662432789802551,
|
| 89062 |
+
"learning_rate": 9.495635571152792e-06,
|
| 89063 |
+
"loss": 0.536,
|
| 89064 |
+
"step": 12722
|
| 89065 |
+
},
|
| 89066 |
+
{
|
| 89067 |
+
"epoch": 14.491168091168092,
|
| 89068 |
+
"grad_norm": 0.22410637140274048,
|
| 89069 |
+
"learning_rate": 9.49198088137317e-06,
|
| 89070 |
+
"loss": 0.7734,
|
| 89071 |
+
"step": 12723
|
| 89072 |
+
},
|
| 89073 |
+
{
|
| 89074 |
+
"epoch": 14.492307692307692,
|
| 89075 |
+
"grad_norm": 0.23314222693443298,
|
| 89076 |
+
"learning_rate": 9.488326730229695e-06,
|
| 89077 |
+
"loss": 0.5753,
|
| 89078 |
+
"step": 12724
|
| 89079 |
+
},
|
| 89080 |
+
{
|
| 89081 |
+
"epoch": 14.493447293447293,
|
| 89082 |
+
"grad_norm": 0.19664184749126434,
|
| 89083 |
+
"learning_rate": 9.484673117849293e-06,
|
| 89084 |
+
"loss": 0.6002,
|
| 89085 |
+
"step": 12725
|
| 89086 |
+
},
|
| 89087 |
+
{
|
| 89088 |
+
"epoch": 14.494586894586895,
|
| 89089 |
+
"grad_norm": 0.17529739439487457,
|
| 89090 |
+
"learning_rate": 9.481020044358867e-06,
|
| 89091 |
+
"loss": 0.5262,
|
| 89092 |
+
"step": 12726
|
| 89093 |
+
},
|
| 89094 |
+
{
|
| 89095 |
+
"epoch": 14.495726495726496,
|
| 89096 |
+
"grad_norm": 0.18910002708435059,
|
| 89097 |
+
"learning_rate": 9.477367509885287e-06,
|
| 89098 |
+
"loss": 0.6401,
|
| 89099 |
+
"step": 12727
|
| 89100 |
+
},
|
| 89101 |
+
{
|
| 89102 |
+
"epoch": 14.496866096866096,
|
| 89103 |
+
"grad_norm": 0.1735510379076004,
|
| 89104 |
+
"learning_rate": 9.47371551455542e-06,
|
| 89105 |
+
"loss": 0.8743,
|
| 89106 |
+
"step": 12728
|
| 89107 |
+
},
|
| 89108 |
+
{
|
| 89109 |
+
"epoch": 14.498005698005699,
|
| 89110 |
+
"grad_norm": 0.1674593836069107,
|
| 89111 |
+
"learning_rate": 9.470064058496108e-06,
|
| 89112 |
+
"loss": 0.584,
|
| 89113 |
+
"step": 12729
|
| 89114 |
+
},
|
| 89115 |
+
{
|
| 89116 |
+
"epoch": 14.4991452991453,
|
| 89117 |
+
"grad_norm": 0.23148374259471893,
|
| 89118 |
+
"learning_rate": 9.466413141834182e-06,
|
| 89119 |
+
"loss": 0.7386,
|
| 89120 |
+
"step": 12730
|
| 89121 |
+
},
|
| 89122 |
+
{
|
| 89123 |
+
"epoch": 14.5002849002849,
|
| 89124 |
+
"grad_norm": 0.21370823681354523,
|
| 89125 |
+
"learning_rate": 9.462762764696442e-06,
|
| 89126 |
+
"loss": 0.7967,
|
| 89127 |
+
"step": 12731
|
| 89128 |
+
},
|
| 89129 |
+
{
|
| 89130 |
+
"epoch": 14.501424501424502,
|
| 89131 |
+
"grad_norm": 0.26482513546943665,
|
| 89132 |
+
"learning_rate": 9.459112927209681e-06,
|
| 89133 |
+
"loss": 0.3715,
|
| 89134 |
+
"step": 12732
|
| 89135 |
+
},
|
| 89136 |
+
{
|
| 89137 |
+
"epoch": 14.502564102564103,
|
| 89138 |
+
"grad_norm": 0.2443828582763672,
|
| 89139 |
+
"learning_rate": 9.455463629500675e-06,
|
| 89140 |
+
"loss": 0.5561,
|
| 89141 |
+
"step": 12733
|
| 89142 |
+
},
|
| 89143 |
+
{
|
| 89144 |
+
"epoch": 14.503703703703703,
|
| 89145 |
+
"grad_norm": 0.17528831958770752,
|
| 89146 |
+
"learning_rate": 9.451814871696154e-06,
|
| 89147 |
+
"loss": 0.7589,
|
| 89148 |
+
"step": 12734
|
| 89149 |
+
},
|
| 89150 |
+
{
|
| 89151 |
+
"epoch": 14.504843304843305,
|
| 89152 |
+
"grad_norm": 0.2478124499320984,
|
| 89153 |
+
"learning_rate": 9.448166653922863e-06,
|
| 89154 |
+
"loss": 0.6932,
|
| 89155 |
+
"step": 12735
|
| 89156 |
+
},
|
| 89157 |
+
{
|
| 89158 |
+
"epoch": 14.505982905982906,
|
| 89159 |
+
"grad_norm": 0.1701100468635559,
|
| 89160 |
+
"learning_rate": 9.444518976307509e-06,
|
| 89161 |
+
"loss": 0.8498,
|
| 89162 |
+
"step": 12736
|
| 89163 |
+
},
|
| 89164 |
+
{
|
| 89165 |
+
"epoch": 14.507122507122507,
|
| 89166 |
+
"grad_norm": 0.18891778588294983,
|
| 89167 |
+
"learning_rate": 9.440871838976797e-06,
|
| 89168 |
+
"loss": 0.4025,
|
| 89169 |
+
"step": 12737
|
| 89170 |
+
},
|
| 89171 |
+
{
|
| 89172 |
+
"epoch": 14.508262108262109,
|
| 89173 |
+
"grad_norm": 0.23873752355575562,
|
| 89174 |
+
"learning_rate": 9.437225242057388e-06,
|
| 89175 |
+
"loss": 0.4546,
|
| 89176 |
+
"step": 12738
|
| 89177 |
+
},
|
| 89178 |
+
{
|
| 89179 |
+
"epoch": 14.50940170940171,
|
| 89180 |
+
"grad_norm": 0.21752510964870453,
|
| 89181 |
+
"learning_rate": 9.433579185675942e-06,
|
| 89182 |
+
"loss": 0.7138,
|
| 89183 |
+
"step": 12739
|
| 89184 |
+
},
|
| 89185 |
+
{
|
| 89186 |
+
"epoch": 14.51054131054131,
|
| 89187 |
+
"grad_norm": 0.21618473529815674,
|
| 89188 |
+
"learning_rate": 9.429933669959098e-06,
|
| 89189 |
+
"loss": 0.6962,
|
| 89190 |
+
"step": 12740
|
| 89191 |
+
},
|
| 89192 |
+
{
|
| 89193 |
+
"epoch": 14.511680911680912,
|
| 89194 |
+
"grad_norm": 0.30999991297721863,
|
| 89195 |
+
"learning_rate": 9.426288695033478e-06,
|
| 89196 |
+
"loss": 0.2891,
|
| 89197 |
+
"step": 12741
|
| 89198 |
+
},
|
| 89199 |
+
{
|
| 89200 |
+
"epoch": 14.512820512820513,
|
| 89201 |
+
"grad_norm": 0.21715053915977478,
|
| 89202 |
+
"learning_rate": 9.422644261025678e-06,
|
| 89203 |
+
"loss": 0.6074,
|
| 89204 |
+
"step": 12742
|
| 89205 |
+
},
|
| 89206 |
+
{
|
| 89207 |
+
"epoch": 14.513960113960113,
|
| 89208 |
+
"grad_norm": 0.2191510945558548,
|
| 89209 |
+
"learning_rate": 9.419000368062281e-06,
|
| 89210 |
+
"loss": 0.7092,
|
| 89211 |
+
"step": 12743
|
| 89212 |
+
},
|
| 89213 |
+
{
|
| 89214 |
+
"epoch": 14.515099715099716,
|
| 89215 |
+
"grad_norm": 0.2763567268848419,
|
| 89216 |
+
"learning_rate": 9.415357016269857e-06,
|
| 89217 |
+
"loss": 0.6448,
|
| 89218 |
+
"step": 12744
|
| 89219 |
+
},
|
| 89220 |
+
{
|
| 89221 |
+
"epoch": 14.516239316239316,
|
| 89222 |
+
"grad_norm": 0.23002742230892181,
|
| 89223 |
+
"learning_rate": 9.411714205774935e-06,
|
| 89224 |
+
"loss": 0.6477,
|
| 89225 |
+
"step": 12745
|
| 89226 |
+
},
|
| 89227 |
+
{
|
| 89228 |
+
"epoch": 14.517378917378917,
|
| 89229 |
+
"grad_norm": 0.21072138845920563,
|
| 89230 |
+
"learning_rate": 9.408071936704044e-06,
|
| 89231 |
+
"loss": 0.5799,
|
| 89232 |
+
"step": 12746
|
| 89233 |
+
},
|
| 89234 |
+
{
|
| 89235 |
+
"epoch": 14.518518518518519,
|
| 89236 |
+
"grad_norm": 0.19315801560878754,
|
| 89237 |
+
"learning_rate": 9.404430209183695e-06,
|
| 89238 |
+
"loss": 0.8153,
|
| 89239 |
+
"step": 12747
|
| 89240 |
+
},
|
| 89241 |
+
{
|
| 89242 |
+
"epoch": 14.51965811965812,
|
| 89243 |
+
"grad_norm": 0.22192391753196716,
|
| 89244 |
+
"learning_rate": 9.40078902334038e-06,
|
| 89245 |
+
"loss": 0.7123,
|
| 89246 |
+
"step": 12748
|
| 89247 |
+
},
|
| 89248 |
+
{
|
| 89249 |
+
"epoch": 14.52079772079772,
|
| 89250 |
+
"grad_norm": 0.17423202097415924,
|
| 89251 |
+
"learning_rate": 9.397148379300552e-06,
|
| 89252 |
+
"loss": 0.725,
|
| 89253 |
+
"step": 12749
|
| 89254 |
+
},
|
| 89255 |
+
{
|
| 89256 |
+
"epoch": 14.521937321937322,
|
| 89257 |
+
"grad_norm": 0.20946653187274933,
|
| 89258 |
+
"learning_rate": 9.393508277190669e-06,
|
| 89259 |
+
"loss": 0.6635,
|
| 89260 |
+
"step": 12750
|
| 89261 |
+
},
|
| 89262 |
+
{
|
| 89263 |
+
"epoch": 14.523076923076923,
|
| 89264 |
+
"grad_norm": 0.2139614373445511,
|
| 89265 |
+
"learning_rate": 9.389868717137154e-06,
|
| 89266 |
+
"loss": 0.573,
|
| 89267 |
+
"step": 12751
|
| 89268 |
+
},
|
| 89269 |
+
{
|
| 89270 |
+
"epoch": 14.524216524216524,
|
| 89271 |
+
"grad_norm": 0.18973661959171295,
|
| 89272 |
+
"learning_rate": 9.386229699266441e-06,
|
| 89273 |
+
"loss": 0.6132,
|
| 89274 |
+
"step": 12752
|
| 89275 |
+
},
|
| 89276 |
+
{
|
| 89277 |
+
"epoch": 14.525356125356126,
|
| 89278 |
+
"grad_norm": 0.2118040919303894,
|
| 89279 |
+
"learning_rate": 9.3825912237049e-06,
|
| 89280 |
+
"loss": 0.5701,
|
| 89281 |
+
"step": 12753
|
| 89282 |
+
},
|
| 89283 |
+
{
|
| 89284 |
+
"epoch": 14.526495726495726,
|
| 89285 |
+
"grad_norm": 0.24053429067134857,
|
| 89286 |
+
"learning_rate": 9.378953290578917e-06,
|
| 89287 |
+
"loss": 0.9265,
|
| 89288 |
+
"step": 12754
|
| 89289 |
+
},
|
| 89290 |
+
{
|
| 89291 |
+
"epoch": 14.527635327635327,
|
| 89292 |
+
"grad_norm": 0.20716017484664917,
|
| 89293 |
+
"learning_rate": 9.375315900014842e-06,
|
| 89294 |
+
"loss": 0.7185,
|
| 89295 |
+
"step": 12755
|
| 89296 |
+
},
|
| 89297 |
+
{
|
| 89298 |
+
"epoch": 14.52877492877493,
|
| 89299 |
+
"grad_norm": 0.20687194168567657,
|
| 89300 |
+
"learning_rate": 9.371679052139023e-06,
|
| 89301 |
+
"loss": 0.7313,
|
| 89302 |
+
"step": 12756
|
| 89303 |
+
},
|
| 89304 |
+
{
|
| 89305 |
+
"epoch": 14.52991452991453,
|
| 89306 |
+
"grad_norm": 0.22021609544754028,
|
| 89307 |
+
"learning_rate": 9.36804274707776e-06,
|
| 89308 |
+
"loss": 0.5323,
|
| 89309 |
+
"step": 12757
|
| 89310 |
+
},
|
| 89311 |
+
{
|
| 89312 |
+
"epoch": 14.53105413105413,
|
| 89313 |
+
"grad_norm": 0.18618431687355042,
|
| 89314 |
+
"learning_rate": 9.364406984957361e-06,
|
| 89315 |
+
"loss": 0.7662,
|
| 89316 |
+
"step": 12758
|
| 89317 |
+
},
|
| 89318 |
+
{
|
| 89319 |
+
"epoch": 14.532193732193733,
|
| 89320 |
+
"grad_norm": 0.2050783634185791,
|
| 89321 |
+
"learning_rate": 9.360771765904105e-06,
|
| 89322 |
+
"loss": 0.5422,
|
| 89323 |
+
"step": 12759
|
| 89324 |
+
},
|
| 89325 |
+
{
|
| 89326 |
+
"epoch": 14.533333333333333,
|
| 89327 |
+
"grad_norm": 0.27364587783813477,
|
| 89328 |
+
"learning_rate": 9.357137090044263e-06,
|
| 89329 |
+
"loss": 0.689,
|
| 89330 |
+
"step": 12760
|
| 89331 |
+
},
|
| 89332 |
+
{
|
| 89333 |
+
"epoch": 14.534472934472934,
|
| 89334 |
+
"grad_norm": 0.19753402471542358,
|
| 89335 |
+
"learning_rate": 9.353502957504057e-06,
|
| 89336 |
+
"loss": 0.5316,
|
| 89337 |
+
"step": 12761
|
| 89338 |
+
},
|
| 89339 |
+
{
|
| 89340 |
+
"epoch": 14.535612535612536,
|
| 89341 |
+
"grad_norm": 0.18314433097839355,
|
| 89342 |
+
"learning_rate": 9.349869368409713e-06,
|
| 89343 |
+
"loss": 0.7352,
|
| 89344 |
+
"step": 12762
|
| 89345 |
+
},
|
| 89346 |
+
{
|
| 89347 |
+
"epoch": 14.536752136752137,
|
| 89348 |
+
"grad_norm": 0.22073610126972198,
|
| 89349 |
+
"learning_rate": 9.346236322887464e-06,
|
| 89350 |
+
"loss": 0.7738,
|
| 89351 |
+
"step": 12763
|
| 89352 |
+
},
|
| 89353 |
+
{
|
| 89354 |
+
"epoch": 14.537891737891737,
|
| 89355 |
+
"grad_norm": 0.24817657470703125,
|
| 89356 |
+
"learning_rate": 9.342603821063463e-06,
|
| 89357 |
+
"loss": 0.5084,
|
| 89358 |
+
"step": 12764
|
| 89359 |
+
},
|
| 89360 |
+
{
|
| 89361 |
+
"epoch": 14.53903133903134,
|
| 89362 |
+
"grad_norm": 0.19437846541404724,
|
| 89363 |
+
"learning_rate": 9.338971863063892e-06,
|
| 89364 |
+
"loss": 0.6462,
|
| 89365 |
+
"step": 12765
|
| 89366 |
+
},
|
| 89367 |
+
{
|
| 89368 |
+
"epoch": 14.54017094017094,
|
| 89369 |
+
"grad_norm": 0.1540386974811554,
|
| 89370 |
+
"learning_rate": 9.335340449014896e-06,
|
| 89371 |
+
"loss": 0.7037,
|
| 89372 |
+
"step": 12766
|
| 89373 |
+
},
|
| 89374 |
+
{
|
| 89375 |
+
"epoch": 14.54131054131054,
|
| 89376 |
+
"grad_norm": 0.21783535182476044,
|
| 89377 |
+
"learning_rate": 9.331709579042613e-06,
|
| 89378 |
+
"loss": 0.5213,
|
| 89379 |
+
"step": 12767
|
| 89380 |
+
},
|
| 89381 |
+
{
|
| 89382 |
+
"epoch": 14.542450142450143,
|
| 89383 |
+
"grad_norm": 0.1780288964509964,
|
| 89384 |
+
"learning_rate": 9.328079253273133e-06,
|
| 89385 |
+
"loss": 0.7168,
|
| 89386 |
+
"step": 12768
|
| 89387 |
+
},
|
| 89388 |
+
{
|
| 89389 |
+
"epoch": 14.543589743589743,
|
| 89390 |
+
"grad_norm": 0.1799340695142746,
|
| 89391 |
+
"learning_rate": 9.324449471832564e-06,
|
| 89392 |
+
"loss": 0.591,
|
| 89393 |
+
"step": 12769
|
| 89394 |
+
},
|
| 89395 |
+
{
|
| 89396 |
+
"epoch": 14.544729344729344,
|
| 89397 |
+
"grad_norm": 0.21395541727542877,
|
| 89398 |
+
"learning_rate": 9.320820234846966e-06,
|
| 89399 |
+
"loss": 0.7872,
|
| 89400 |
+
"step": 12770
|
| 89401 |
+
},
|
| 89402 |
+
{
|
| 89403 |
+
"epoch": 14.545868945868946,
|
| 89404 |
+
"grad_norm": 0.25342968106269836,
|
| 89405 |
+
"learning_rate": 9.317191542442413e-06,
|
| 89406 |
+
"loss": 0.6905,
|
| 89407 |
+
"step": 12771
|
| 89408 |
+
},
|
| 89409 |
+
{
|
| 89410 |
+
"epoch": 14.547008547008547,
|
| 89411 |
+
"grad_norm": 0.1848641335964203,
|
| 89412 |
+
"learning_rate": 9.313563394744915e-06,
|
| 89413 |
+
"loss": 0.6439,
|
| 89414 |
+
"step": 12772
|
| 89415 |
+
},
|
| 89416 |
+
{
|
| 89417 |
+
"epoch": 14.548148148148147,
|
| 89418 |
+
"grad_norm": 0.24846234917640686,
|
| 89419 |
+
"learning_rate": 9.309935791880489e-06,
|
| 89420 |
+
"loss": 0.765,
|
| 89421 |
+
"step": 12773
|
| 89422 |
+
},
|
| 89423 |
+
{
|
| 89424 |
+
"epoch": 14.54928774928775,
|
| 89425 |
+
"grad_norm": 0.23958313465118408,
|
| 89426 |
+
"learning_rate": 9.306308733975158e-06,
|
| 89427 |
+
"loss": 0.5846,
|
| 89428 |
+
"step": 12774
|
| 89429 |
+
},
|
| 89430 |
+
{
|
| 89431 |
+
"epoch": 14.55042735042735,
|
| 89432 |
+
"grad_norm": 0.23163294792175293,
|
| 89433 |
+
"learning_rate": 9.302682221154877e-06,
|
| 89434 |
+
"loss": 0.5904,
|
| 89435 |
+
"step": 12775
|
| 89436 |
+
},
|
| 89437 |
+
{
|
| 89438 |
+
"epoch": 14.55156695156695,
|
| 89439 |
+
"grad_norm": 0.2353852093219757,
|
| 89440 |
+
"learning_rate": 9.299056253545608e-06,
|
| 89441 |
+
"loss": 0.6717,
|
| 89442 |
+
"step": 12776
|
| 89443 |
+
},
|
| 89444 |
+
{
|
| 89445 |
+
"epoch": 14.552706552706553,
|
| 89446 |
+
"grad_norm": 0.1862393021583557,
|
| 89447 |
+
"learning_rate": 9.29543083127329e-06,
|
| 89448 |
+
"loss": 0.6082,
|
| 89449 |
+
"step": 12777
|
| 89450 |
+
},
|
| 89451 |
+
{
|
| 89452 |
+
"epoch": 14.553846153846154,
|
| 89453 |
+
"grad_norm": 0.19592125713825226,
|
| 89454 |
+
"learning_rate": 9.291805954463859e-06,
|
| 89455 |
+
"loss": 0.8035,
|
| 89456 |
+
"step": 12778
|
| 89457 |
+
},
|
| 89458 |
+
{
|
| 89459 |
+
"epoch": 14.554985754985754,
|
| 89460 |
+
"grad_norm": 0.23634620010852814,
|
| 89461 |
+
"learning_rate": 9.288181623243197e-06,
|
| 89462 |
+
"loss": 0.7024,
|
| 89463 |
+
"step": 12779
|
| 89464 |
+
},
|
| 89465 |
+
{
|
| 89466 |
+
"epoch": 14.556125356125357,
|
| 89467 |
+
"grad_norm": 0.19568602740764618,
|
| 89468 |
+
"learning_rate": 9.284557837737193e-06,
|
| 89469 |
+
"loss": 0.5394,
|
| 89470 |
+
"step": 12780
|
| 89471 |
+
},
|
| 89472 |
+
{
|
| 89473 |
+
"epoch": 14.557264957264957,
|
| 89474 |
+
"grad_norm": 0.22622573375701904,
|
| 89475 |
+
"learning_rate": 9.280934598071713e-06,
|
| 89476 |
+
"loss": 0.6091,
|
| 89477 |
+
"step": 12781
|
| 89478 |
+
},
|
| 89479 |
+
{
|
| 89480 |
+
"epoch": 14.558404558404558,
|
| 89481 |
+
"grad_norm": 0.1921817809343338,
|
| 89482 |
+
"learning_rate": 9.277311904372612e-06,
|
| 89483 |
+
"loss": 0.6438,
|
| 89484 |
+
"step": 12782
|
| 89485 |
+
},
|
| 89486 |
+
{
|
| 89487 |
+
"epoch": 14.55954415954416,
|
| 89488 |
+
"grad_norm": 0.20838889479637146,
|
| 89489 |
+
"learning_rate": 9.273689756765697e-06,
|
| 89490 |
+
"loss": 0.6498,
|
| 89491 |
+
"step": 12783
|
| 89492 |
+
},
|
| 89493 |
+
{
|
| 89494 |
+
"epoch": 14.56068376068376,
|
| 89495 |
+
"grad_norm": 0.22933794558048248,
|
| 89496 |
+
"learning_rate": 9.270068155376773e-06,
|
| 89497 |
+
"loss": 0.5626,
|
| 89498 |
+
"step": 12784
|
| 89499 |
+
},
|
| 89500 |
+
{
|
| 89501 |
+
"epoch": 14.561823361823361,
|
| 89502 |
+
"grad_norm": 0.22988249361515045,
|
| 89503 |
+
"learning_rate": 9.26644710033166e-06,
|
| 89504 |
+
"loss": 0.4697,
|
| 89505 |
+
"step": 12785
|
| 89506 |
+
},
|
| 89507 |
+
{
|
| 89508 |
+
"epoch": 14.562962962962963,
|
| 89509 |
+
"grad_norm": 0.19771137833595276,
|
| 89510 |
+
"learning_rate": 9.262826591756096e-06,
|
| 89511 |
+
"loss": 0.4922,
|
| 89512 |
+
"step": 12786
|
| 89513 |
+
},
|
| 89514 |
+
{
|
| 89515 |
+
"epoch": 14.564102564102564,
|
| 89516 |
+
"grad_norm": 0.21506692469120026,
|
| 89517 |
+
"learning_rate": 9.259206629775843e-06,
|
| 89518 |
+
"loss": 0.7956,
|
| 89519 |
+
"step": 12787
|
| 89520 |
+
},
|
| 89521 |
+
{
|
| 89522 |
+
"epoch": 14.565242165242164,
|
| 89523 |
+
"grad_norm": 0.26526808738708496,
|
| 89524 |
+
"learning_rate": 9.255587214516631e-06,
|
| 89525 |
+
"loss": 0.4643,
|
| 89526 |
+
"step": 12788
|
| 89527 |
+
},
|
| 89528 |
+
{
|
| 89529 |
+
"epoch": 14.566381766381767,
|
| 89530 |
+
"grad_norm": 0.22599969804286957,
|
| 89531 |
+
"learning_rate": 9.25196834610418e-06,
|
| 89532 |
+
"loss": 0.6884,
|
| 89533 |
+
"step": 12789
|
| 89534 |
+
},
|
| 89535 |
+
{
|
| 89536 |
+
"epoch": 14.567521367521367,
|
| 89537 |
+
"grad_norm": 0.23053516447544098,
|
| 89538 |
+
"learning_rate": 9.24835002466417e-06,
|
| 89539 |
+
"loss": 0.7369,
|
| 89540 |
+
"step": 12790
|
| 89541 |
+
},
|
| 89542 |
+
{
|
| 89543 |
+
"epoch": 14.568660968660968,
|
| 89544 |
+
"grad_norm": 0.23256726562976837,
|
| 89545 |
+
"learning_rate": 9.24473225032228e-06,
|
| 89546 |
+
"loss": 0.3916,
|
| 89547 |
+
"step": 12791
|
| 89548 |
+
},
|
| 89549 |
+
{
|
| 89550 |
+
"epoch": 14.56980056980057,
|
| 89551 |
+
"grad_norm": 0.19544029235839844,
|
| 89552 |
+
"learning_rate": 9.241115023204164e-06,
|
| 89553 |
+
"loss": 0.6617,
|
| 89554 |
+
"step": 12792
|
| 89555 |
+
},
|
| 89556 |
+
{
|
| 89557 |
+
"epoch": 14.57094017094017,
|
| 89558 |
+
"grad_norm": 0.19380274415016174,
|
| 89559 |
+
"learning_rate": 9.23749834343546e-06,
|
| 89560 |
+
"loss": 0.6968,
|
| 89561 |
+
"step": 12793
|
| 89562 |
+
},
|
| 89563 |
+
{
|
| 89564 |
+
"epoch": 14.572079772079771,
|
| 89565 |
+
"grad_norm": 0.255537748336792,
|
| 89566 |
+
"learning_rate": 9.233882211141797e-06,
|
| 89567 |
+
"loss": 0.6371,
|
| 89568 |
+
"step": 12794
|
| 89569 |
+
},
|
| 89570 |
+
{
|
| 89571 |
+
"epoch": 14.573219373219374,
|
| 89572 |
+
"grad_norm": 0.20726673305034637,
|
| 89573 |
+
"learning_rate": 9.230266626448741e-06,
|
| 89574 |
+
"loss": 0.7882,
|
| 89575 |
+
"step": 12795
|
| 89576 |
+
},
|
| 89577 |
+
{
|
| 89578 |
+
"epoch": 14.574358974358974,
|
| 89579 |
+
"grad_norm": 0.2502824068069458,
|
| 89580 |
+
"learning_rate": 9.226651589481906e-06,
|
| 89581 |
+
"loss": 0.409,
|
| 89582 |
+
"step": 12796
|
| 89583 |
+
},
|
| 89584 |
+
{
|
| 89585 |
+
"epoch": 14.575498575498575,
|
| 89586 |
+
"grad_norm": 0.19566868245601654,
|
| 89587 |
+
"learning_rate": 9.22303710036684e-06,
|
| 89588 |
+
"loss": 0.6197,
|
| 89589 |
+
"step": 12797
|
| 89590 |
+
},
|
| 89591 |
+
{
|
| 89592 |
+
"epoch": 14.576638176638177,
|
| 89593 |
+
"grad_norm": 0.22269435226917267,
|
| 89594 |
+
"learning_rate": 9.219423159229078e-06,
|
| 89595 |
+
"loss": 0.557,
|
| 89596 |
+
"step": 12798
|
| 89597 |
+
},
|
| 89598 |
+
{
|
| 89599 |
+
"epoch": 14.577777777777778,
|
| 89600 |
+
"grad_norm": 0.2081078439950943,
|
| 89601 |
+
"learning_rate": 9.215809766194144e-06,
|
| 89602 |
+
"loss": 0.6,
|
| 89603 |
+
"step": 12799
|
| 89604 |
+
},
|
| 89605 |
+
{
|
| 89606 |
+
"epoch": 14.578917378917378,
|
| 89607 |
+
"grad_norm": 0.25893324613571167,
|
| 89608 |
+
"learning_rate": 9.212196921387548e-06,
|
| 89609 |
+
"loss": 0.4348,
|
| 89610 |
+
"step": 12800
|
| 89611 |
+
},
|
| 89612 |
+
{
|
| 89613 |
+
"epoch": 14.58005698005698,
|
| 89614 |
+
"grad_norm": 0.20001818239688873,
|
| 89615 |
+
"learning_rate": 9.208584624934774e-06,
|
| 89616 |
+
"loss": 0.7304,
|
| 89617 |
+
"step": 12801
|
| 89618 |
+
},
|
| 89619 |
+
{
|
| 89620 |
+
"epoch": 14.581196581196581,
|
| 89621 |
+
"grad_norm": 0.1583530753850937,
|
| 89622 |
+
"learning_rate": 9.204972876961277e-06,
|
| 89623 |
+
"loss": 0.9084,
|
| 89624 |
+
"step": 12802
|
| 89625 |
+
},
|
| 89626 |
+
{
|
| 89627 |
+
"epoch": 14.582336182336181,
|
| 89628 |
+
"grad_norm": 0.17533500492572784,
|
| 89629 |
+
"learning_rate": 9.201361677592505e-06,
|
| 89630 |
+
"loss": 0.8482,
|
| 89631 |
+
"step": 12803
|
| 89632 |
+
},
|
| 89633 |
+
{
|
| 89634 |
+
"epoch": 14.583475783475784,
|
| 89635 |
+
"grad_norm": 0.19490677118301392,
|
| 89636 |
+
"learning_rate": 9.19775102695389e-06,
|
| 89637 |
+
"loss": 0.7168,
|
| 89638 |
+
"step": 12804
|
| 89639 |
+
},
|
| 89640 |
+
{
|
| 89641 |
+
"epoch": 14.584615384615384,
|
| 89642 |
+
"grad_norm": 0.23321951925754547,
|
| 89643 |
+
"learning_rate": 9.194140925170847e-06,
|
| 89644 |
+
"loss": 0.4843,
|
| 89645 |
+
"step": 12805
|
| 89646 |
+
},
|
| 89647 |
+
{
|
| 89648 |
+
"epoch": 14.585754985754985,
|
| 89649 |
+
"grad_norm": 0.18963153660297394,
|
| 89650 |
+
"learning_rate": 9.190531372368737e-06,
|
| 89651 |
+
"loss": 0.4558,
|
| 89652 |
+
"step": 12806
|
| 89653 |
+
},
|
| 89654 |
+
{
|
| 89655 |
+
"epoch": 14.586894586894587,
|
| 89656 |
+
"grad_norm": 0.1767222136259079,
|
| 89657 |
+
"learning_rate": 9.186922368672959e-06,
|
| 89658 |
+
"loss": 0.5863,
|
| 89659 |
+
"step": 12807
|
| 89660 |
+
},
|
| 89661 |
+
{
|
| 89662 |
+
"epoch": 14.588034188034188,
|
| 89663 |
+
"grad_norm": 0.29822349548339844,
|
| 89664 |
+
"learning_rate": 9.183313914208863e-06,
|
| 89665 |
+
"loss": 0.5253,
|
| 89666 |
+
"step": 12808
|
| 89667 |
+
},
|
| 89668 |
+
{
|
| 89669 |
+
"epoch": 14.589173789173788,
|
| 89670 |
+
"grad_norm": 0.18491874635219574,
|
| 89671 |
+
"learning_rate": 9.17970600910176e-06,
|
| 89672 |
+
"loss": 0.6101,
|
| 89673 |
+
"step": 12809
|
| 89674 |
+
},
|
| 89675 |
+
{
|
| 89676 |
+
"epoch": 14.59031339031339,
|
| 89677 |
+
"grad_norm": 0.21525131165981293,
|
| 89678 |
+
"learning_rate": 9.176098653476975e-06,
|
| 89679 |
+
"loss": 0.7278,
|
| 89680 |
+
"step": 12810
|
| 89681 |
+
},
|
| 89682 |
+
{
|
| 89683 |
+
"epoch": 14.591452991452991,
|
| 89684 |
+
"grad_norm": 0.21279139816761017,
|
| 89685 |
+
"learning_rate": 9.172491847459797e-06,
|
| 89686 |
+
"loss": 0.8417,
|
| 89687 |
+
"step": 12811
|
| 89688 |
+
},
|
| 89689 |
+
{
|
| 89690 |
+
"epoch": 14.592592592592592,
|
| 89691 |
+
"grad_norm": 0.20600202679634094,
|
| 89692 |
+
"learning_rate": 9.168885591175514e-06,
|
| 89693 |
+
"loss": 0.7268,
|
| 89694 |
+
"step": 12812
|
| 89695 |
+
},
|
| 89696 |
+
{
|
| 89697 |
+
"epoch": 14.593732193732194,
|
| 89698 |
+
"grad_norm": 0.1988891363143921,
|
| 89699 |
+
"learning_rate": 9.165279884749362e-06,
|
| 89700 |
+
"loss": 0.7926,
|
| 89701 |
+
"step": 12813
|
| 89702 |
+
},
|
| 89703 |
+
{
|
| 89704 |
+
"epoch": 14.594871794871795,
|
| 89705 |
+
"grad_norm": 0.17967242002487183,
|
| 89706 |
+
"learning_rate": 9.161674728306582e-06,
|
| 89707 |
+
"loss": 0.4623,
|
| 89708 |
+
"step": 12814
|
| 89709 |
+
},
|
| 89710 |
+
{
|
| 89711 |
+
"epoch": 14.596011396011395,
|
| 89712 |
+
"grad_norm": 0.17472924292087555,
|
| 89713 |
+
"learning_rate": 9.158070121972398e-06,
|
| 89714 |
+
"loss": 0.7645,
|
| 89715 |
+
"step": 12815
|
| 89716 |
+
},
|
| 89717 |
+
{
|
| 89718 |
+
"epoch": 14.597150997150997,
|
| 89719 |
+
"grad_norm": 0.22233867645263672,
|
| 89720 |
+
"learning_rate": 9.154466065872011e-06,
|
| 89721 |
+
"loss": 0.5888,
|
| 89722 |
+
"step": 12816
|
| 89723 |
+
},
|
| 89724 |
+
{
|
| 89725 |
+
"epoch": 14.598290598290598,
|
| 89726 |
+
"grad_norm": 0.18700459599494934,
|
| 89727 |
+
"learning_rate": 9.150862560130574e-06,
|
| 89728 |
+
"loss": 0.637,
|
| 89729 |
+
"step": 12817
|
| 89730 |
+
},
|
| 89731 |
+
{
|
| 89732 |
+
"epoch": 14.5994301994302,
|
| 89733 |
+
"grad_norm": 0.2434198260307312,
|
| 89734 |
+
"learning_rate": 9.147259604873276e-06,
|
| 89735 |
+
"loss": 0.7316,
|
| 89736 |
+
"step": 12818
|
| 89737 |
+
},
|
| 89738 |
+
{
|
| 89739 |
+
"epoch": 14.6005698005698,
|
| 89740 |
+
"grad_norm": 0.2834024429321289,
|
| 89741 |
+
"learning_rate": 9.143657200225256e-06,
|
| 89742 |
+
"loss": 0.6003,
|
| 89743 |
+
"step": 12819
|
| 89744 |
+
},
|
| 89745 |
+
{
|
| 89746 |
+
"epoch": 14.601709401709401,
|
| 89747 |
+
"grad_norm": 0.2045540064573288,
|
| 89748 |
+
"learning_rate": 9.140055346311619e-06,
|
| 89749 |
+
"loss": 0.7706,
|
| 89750 |
+
"step": 12820
|
| 89751 |
+
},
|
| 89752 |
+
{
|
| 89753 |
+
"epoch": 14.602849002849004,
|
| 89754 |
+
"grad_norm": 0.21345989406108856,
|
| 89755 |
+
"learning_rate": 9.136454043257472e-06,
|
| 89756 |
+
"loss": 0.43,
|
| 89757 |
+
"step": 12821
|
| 89758 |
+
},
|
| 89759 |
+
{
|
| 89760 |
+
"epoch": 14.603988603988604,
|
| 89761 |
+
"grad_norm": 0.2493118792772293,
|
| 89762 |
+
"learning_rate": 9.132853291187904e-06,
|
| 89763 |
+
"loss": 0.6509,
|
| 89764 |
+
"step": 12822
|
| 89765 |
+
},
|
| 89766 |
+
{
|
| 89767 |
+
"epoch": 14.605128205128205,
|
| 89768 |
+
"grad_norm": 0.19616162776947021,
|
| 89769 |
+
"learning_rate": 9.129253090227981e-06,
|
| 89770 |
+
"loss": 0.7401,
|
| 89771 |
+
"step": 12823
|
| 89772 |
+
},
|
| 89773 |
+
{
|
| 89774 |
+
"epoch": 14.606267806267807,
|
| 89775 |
+
"grad_norm": 0.22674551606178284,
|
| 89776 |
+
"learning_rate": 9.125653440502738e-06,
|
| 89777 |
+
"loss": 0.7348,
|
| 89778 |
+
"step": 12824
|
| 89779 |
+
},
|
| 89780 |
+
{
|
| 89781 |
+
"epoch": 14.607407407407408,
|
| 89782 |
+
"grad_norm": 0.19461093842983246,
|
| 89783 |
+
"learning_rate": 9.122054342137203e-06,
|
| 89784 |
+
"loss": 0.6387,
|
| 89785 |
+
"step": 12825
|
| 89786 |
+
},
|
| 89787 |
+
{
|
| 89788 |
+
"epoch": 14.608547008547008,
|
| 89789 |
+
"grad_norm": 0.18842506408691406,
|
| 89790 |
+
"learning_rate": 9.118455795256386e-06,
|
| 89791 |
+
"loss": 0.7617,
|
| 89792 |
+
"step": 12826
|
| 89793 |
+
},
|
| 89794 |
+
{
|
| 89795 |
+
"epoch": 14.60968660968661,
|
| 89796 |
+
"grad_norm": 0.18397743999958038,
|
| 89797 |
+
"learning_rate": 9.114857799985282e-06,
|
| 89798 |
+
"loss": 0.7431,
|
| 89799 |
+
"step": 12827
|
| 89800 |
+
},
|
| 89801 |
+
{
|
| 89802 |
+
"epoch": 14.610826210826211,
|
| 89803 |
+
"grad_norm": 0.22190988063812256,
|
| 89804 |
+
"learning_rate": 9.111260356448836e-06,
|
| 89805 |
+
"loss": 0.774,
|
| 89806 |
+
"step": 12828
|
| 89807 |
+
},
|
| 89808 |
+
{
|
| 89809 |
+
"epoch": 14.611965811965812,
|
| 89810 |
+
"grad_norm": 0.26174870133399963,
|
| 89811 |
+
"learning_rate": 9.107663464772018e-06,
|
| 89812 |
+
"loss": 0.4364,
|
| 89813 |
+
"step": 12829
|
| 89814 |
+
},
|
| 89815 |
+
{
|
| 89816 |
+
"epoch": 14.613105413105414,
|
| 89817 |
+
"grad_norm": 0.2167321890592575,
|
| 89818 |
+
"learning_rate": 9.104067125079754e-06,
|
| 89819 |
+
"loss": 0.6935,
|
| 89820 |
+
"step": 12830
|
| 89821 |
+
},
|
| 89822 |
+
{
|
| 89823 |
+
"epoch": 14.614245014245014,
|
| 89824 |
+
"grad_norm": 0.15865680575370789,
|
| 89825 |
+
"learning_rate": 9.10047133749696e-06,
|
| 89826 |
+
"loss": 0.7962,
|
| 89827 |
+
"step": 12831
|
| 89828 |
+
},
|
| 89829 |
+
{
|
| 89830 |
+
"epoch": 14.615384615384615,
|
| 89831 |
+
"grad_norm": 0.19315698742866516,
|
| 89832 |
+
"learning_rate": 9.096876102148511e-06,
|
| 89833 |
+
"loss": 0.7019,
|
| 89834 |
+
"step": 12832
|
| 89835 |
+
},
|
| 89836 |
+
{
|
| 89837 |
+
"epoch": 14.616524216524217,
|
| 89838 |
+
"grad_norm": 0.2170671969652176,
|
| 89839 |
+
"learning_rate": 9.093281419159292e-06,
|
| 89840 |
+
"loss": 0.8031,
|
| 89841 |
+
"step": 12833
|
| 89842 |
+
},
|
| 89843 |
+
{
|
| 89844 |
+
"epoch": 14.617663817663818,
|
| 89845 |
+
"grad_norm": 0.20496302843093872,
|
| 89846 |
+
"learning_rate": 9.089687288654147e-06,
|
| 89847 |
+
"loss": 0.6789,
|
| 89848 |
+
"step": 12834
|
| 89849 |
+
},
|
| 89850 |
+
{
|
| 89851 |
+
"epoch": 14.618803418803418,
|
| 89852 |
+
"grad_norm": 0.22105635702610016,
|
| 89853 |
+
"learning_rate": 9.086093710757928e-06,
|
| 89854 |
+
"loss": 0.4857,
|
| 89855 |
+
"step": 12835
|
| 89856 |
+
},
|
| 89857 |
+
{
|
| 89858 |
+
"epoch": 14.61994301994302,
|
| 89859 |
+
"grad_norm": 0.17714130878448486,
|
| 89860 |
+
"learning_rate": 9.08250068559543e-06,
|
| 89861 |
+
"loss": 0.7495,
|
| 89862 |
+
"step": 12836
|
| 89863 |
+
},
|
| 89864 |
+
{
|
| 89865 |
+
"epoch": 14.621082621082621,
|
| 89866 |
+
"grad_norm": 0.23276539146900177,
|
| 89867 |
+
"learning_rate": 9.078908213291457e-06,
|
| 89868 |
+
"loss": 0.6358,
|
| 89869 |
+
"step": 12837
|
| 89870 |
+
},
|
| 89871 |
+
{
|
| 89872 |
+
"epoch": 14.622222222222222,
|
| 89873 |
+
"grad_norm": 0.23377883434295654,
|
| 89874 |
+
"learning_rate": 9.075316293970783e-06,
|
| 89875 |
+
"loss": 0.7701,
|
| 89876 |
+
"step": 12838
|
| 89877 |
+
},
|
| 89878 |
+
{
|
| 89879 |
+
"epoch": 14.623361823361824,
|
| 89880 |
+
"grad_norm": 0.27861806750297546,
|
| 89881 |
+
"learning_rate": 9.07172492775817e-06,
|
| 89882 |
+
"loss": 0.6524,
|
| 89883 |
+
"step": 12839
|
| 89884 |
+
},
|
| 89885 |
+
{
|
| 89886 |
+
"epoch": 14.624501424501425,
|
| 89887 |
+
"grad_norm": 0.2254713773727417,
|
| 89888 |
+
"learning_rate": 9.068134114778352e-06,
|
| 89889 |
+
"loss": 0.7804,
|
| 89890 |
+
"step": 12840
|
| 89891 |
+
},
|
| 89892 |
+
{
|
| 89893 |
+
"epoch": 14.625641025641025,
|
| 89894 |
+
"grad_norm": 0.20277513563632965,
|
| 89895 |
+
"learning_rate": 9.064543855156046e-06,
|
| 89896 |
+
"loss": 0.7296,
|
| 89897 |
+
"step": 12841
|
| 89898 |
+
},
|
| 89899 |
+
{
|
| 89900 |
+
"epoch": 14.626780626780628,
|
| 89901 |
+
"grad_norm": 0.25616806745529175,
|
| 89902 |
+
"learning_rate": 9.060954149015966e-06,
|
| 89903 |
+
"loss": 0.4441,
|
| 89904 |
+
"step": 12842
|
| 89905 |
+
},
|
| 89906 |
+
{
|
| 89907 |
+
"epoch": 14.627920227920228,
|
| 89908 |
+
"grad_norm": 0.23563611507415771,
|
| 89909 |
+
"learning_rate": 9.05736499648277e-06,
|
| 89910 |
+
"loss": 0.6675,
|
| 89911 |
+
"step": 12843
|
| 89912 |
+
},
|
| 89913 |
+
{
|
| 89914 |
+
"epoch": 14.629059829059829,
|
| 89915 |
+
"grad_norm": 0.22810997068881989,
|
| 89916 |
+
"learning_rate": 9.053776397681133e-06,
|
| 89917 |
+
"loss": 0.3929,
|
| 89918 |
+
"step": 12844
|
| 89919 |
+
},
|
| 89920 |
+
{
|
| 89921 |
+
"epoch": 14.630199430199431,
|
| 89922 |
+
"grad_norm": 0.20193806290626526,
|
| 89923 |
+
"learning_rate": 9.050188352735692e-06,
|
| 89924 |
+
"loss": 0.5998,
|
| 89925 |
+
"step": 12845
|
| 89926 |
+
},
|
| 89927 |
+
{
|
| 89928 |
+
"epoch": 14.631339031339031,
|
| 89929 |
+
"grad_norm": 0.23286187648773193,
|
| 89930 |
+
"learning_rate": 9.046600861771082e-06,
|
| 89931 |
+
"loss": 0.6299,
|
| 89932 |
+
"step": 12846
|
| 89933 |
+
},
|
| 89934 |
+
{
|
| 89935 |
+
"epoch": 14.632478632478632,
|
| 89936 |
+
"grad_norm": 0.19484420120716095,
|
| 89937 |
+
"learning_rate": 9.043013924911886e-06,
|
| 89938 |
+
"loss": 0.7678,
|
| 89939 |
+
"step": 12847
|
| 89940 |
+
},
|
| 89941 |
+
{
|
| 89942 |
+
"epoch": 14.633618233618234,
|
| 89943 |
+
"grad_norm": 0.23107795417308807,
|
| 89944 |
+
"learning_rate": 9.0394275422827e-06,
|
| 89945 |
+
"loss": 0.5326,
|
| 89946 |
+
"step": 12848
|
| 89947 |
+
},
|
| 89948 |
+
{
|
| 89949 |
+
"epoch": 14.634757834757835,
|
| 89950 |
+
"grad_norm": 0.22537994384765625,
|
| 89951 |
+
"learning_rate": 9.035841714008084e-06,
|
| 89952 |
+
"loss": 0.6991,
|
| 89953 |
+
"step": 12849
|
| 89954 |
+
},
|
| 89955 |
+
{
|
| 89956 |
+
"epoch": 14.635897435897435,
|
| 89957 |
+
"grad_norm": 0.18735532462596893,
|
| 89958 |
+
"learning_rate": 9.032256440212589e-06,
|
| 89959 |
+
"loss": 0.7035,
|
| 89960 |
+
"step": 12850
|
| 89961 |
+
},
|
| 89962 |
+
{
|
| 89963 |
+
"epoch": 14.637037037037038,
|
| 89964 |
+
"grad_norm": 0.21662990748882294,
|
| 89965 |
+
"learning_rate": 9.02867172102074e-06,
|
| 89966 |
+
"loss": 0.7339,
|
| 89967 |
+
"step": 12851
|
| 89968 |
+
},
|
| 89969 |
+
{
|
| 89970 |
+
"epoch": 14.638176638176638,
|
| 89971 |
+
"grad_norm": 0.21480605006217957,
|
| 89972 |
+
"learning_rate": 9.02508755655704e-06,
|
| 89973 |
+
"loss": 0.7108,
|
| 89974 |
+
"step": 12852
|
| 89975 |
+
},
|
| 89976 |
+
{
|
| 89977 |
+
"epoch": 14.639316239316239,
|
| 89978 |
+
"grad_norm": 0.2904488444328308,
|
| 89979 |
+
"learning_rate": 9.021503946945994e-06,
|
| 89980 |
+
"loss": 0.4803,
|
| 89981 |
+
"step": 12853
|
| 89982 |
+
},
|
| 89983 |
+
{
|
| 89984 |
+
"epoch": 14.640455840455841,
|
| 89985 |
+
"grad_norm": 0.1873403638601303,
|
| 89986 |
+
"learning_rate": 9.017920892312046e-06,
|
| 89987 |
+
"loss": 0.6105,
|
| 89988 |
+
"step": 12854
|
| 89989 |
+
},
|
| 89990 |
+
{
|
| 89991 |
+
"epoch": 14.641595441595442,
|
| 89992 |
+
"grad_norm": 0.2191169559955597,
|
| 89993 |
+
"learning_rate": 9.014338392779655e-06,
|
| 89994 |
+
"loss": 0.4706,
|
| 89995 |
+
"step": 12855
|
| 89996 |
+
},
|
| 89997 |
+
{
|
| 89998 |
+
"epoch": 14.642735042735042,
|
| 89999 |
+
"grad_norm": 0.24094586074352264,
|
| 90000 |
+
"learning_rate": 9.010756448473254e-06,
|
| 90001 |
+
"loss": 0.6251,
|
| 90002 |
+
"step": 12856
|
| 90003 |
+
},
|
| 90004 |
+
{
|
| 90005 |
+
"epoch": 14.643874643874645,
|
| 90006 |
+
"grad_norm": 0.2248314917087555,
|
| 90007 |
+
"learning_rate": 9.007175059517262e-06,
|
| 90008 |
+
"loss": 0.6546,
|
| 90009 |
+
"step": 12857
|
| 90010 |
+
},
|
| 90011 |
+
{
|
| 90012 |
+
"epoch": 14.645014245014245,
|
| 90013 |
+
"grad_norm": 0.1848820000886917,
|
| 90014 |
+
"learning_rate": 9.00359422603605e-06,
|
| 90015 |
+
"loss": 0.8862,
|
| 90016 |
+
"step": 12858
|
| 90017 |
+
},
|
| 90018 |
+
{
|
| 90019 |
+
"epoch": 14.646153846153846,
|
| 90020 |
+
"grad_norm": 0.1982840746641159,
|
| 90021 |
+
"learning_rate": 9.000013948153998e-06,
|
| 90022 |
+
"loss": 0.7922,
|
| 90023 |
+
"step": 12859
|
| 90024 |
+
},
|
| 90025 |
+
{
|
| 90026 |
+
"epoch": 14.647293447293448,
|
| 90027 |
+
"grad_norm": 0.2248876541852951,
|
| 90028 |
+
"learning_rate": 8.996434225995467e-06,
|
| 90029 |
+
"loss": 0.6102,
|
| 90030 |
+
"step": 12860
|
| 90031 |
+
},
|
| 90032 |
+
{
|
| 90033 |
+
"epoch": 14.648433048433048,
|
| 90034 |
+
"grad_norm": 0.16222314536571503,
|
| 90035 |
+
"learning_rate": 8.992855059684783e-06,
|
| 90036 |
+
"loss": 0.8696,
|
| 90037 |
+
"step": 12861
|
| 90038 |
+
},
|
| 90039 |
+
{
|
| 90040 |
+
"epoch": 14.649572649572649,
|
| 90041 |
+
"grad_norm": 0.2841748893260956,
|
| 90042 |
+
"learning_rate": 8.989276449346262e-06,
|
| 90043 |
+
"loss": 0.7772,
|
| 90044 |
+
"step": 12862
|
| 90045 |
+
},
|
| 90046 |
+
{
|
| 90047 |
+
"epoch": 14.650712250712251,
|
| 90048 |
+
"grad_norm": 0.18035295605659485,
|
| 90049 |
+
"learning_rate": 8.9856983951042e-06,
|
| 90050 |
+
"loss": 0.6827,
|
| 90051 |
+
"step": 12863
|
| 90052 |
+
},
|
| 90053 |
+
{
|
| 90054 |
+
"epoch": 14.651851851851852,
|
| 90055 |
+
"grad_norm": 0.22114045917987823,
|
| 90056 |
+
"learning_rate": 8.982120897082882e-06,
|
| 90057 |
+
"loss": 0.485,
|
| 90058 |
+
"step": 12864
|
| 90059 |
+
},
|
| 90060 |
+
{
|
| 90061 |
+
"epoch": 14.652991452991452,
|
| 90062 |
+
"grad_norm": 0.22197026014328003,
|
| 90063 |
+
"learning_rate": 8.978543955406545e-06,
|
| 90064 |
+
"loss": 0.4146,
|
| 90065 |
+
"step": 12865
|
| 90066 |
+
},
|
| 90067 |
+
{
|
| 90068 |
+
"epoch": 14.654131054131055,
|
| 90069 |
+
"grad_norm": 0.21953082084655762,
|
| 90070 |
+
"learning_rate": 8.974967570199435e-06,
|
| 90071 |
+
"loss": 0.7247,
|
| 90072 |
+
"step": 12866
|
| 90073 |
+
},
|
| 90074 |
+
{
|
| 90075 |
+
"epoch": 14.655270655270655,
|
| 90076 |
+
"grad_norm": 0.2214314192533493,
|
| 90077 |
+
"learning_rate": 8.971391741585772e-06,
|
| 90078 |
+
"loss": 0.5547,
|
| 90079 |
+
"step": 12867
|
| 90080 |
+
},
|
| 90081 |
+
{
|
| 90082 |
+
"epoch": 14.656410256410256,
|
| 90083 |
+
"grad_norm": 0.2568795680999756,
|
| 90084 |
+
"learning_rate": 8.96781646968976e-06,
|
| 90085 |
+
"loss": 0.5693,
|
| 90086 |
+
"step": 12868
|
| 90087 |
+
},
|
| 90088 |
+
{
|
| 90089 |
+
"epoch": 14.657549857549858,
|
| 90090 |
+
"grad_norm": 0.20167192816734314,
|
| 90091 |
+
"learning_rate": 8.964241754635563e-06,
|
| 90092 |
+
"loss": 0.6874,
|
| 90093 |
+
"step": 12869
|
| 90094 |
+
},
|
| 90095 |
+
{
|
| 90096 |
+
"epoch": 14.658689458689459,
|
| 90097 |
+
"grad_norm": 0.20127788186073303,
|
| 90098 |
+
"learning_rate": 8.960667596547348e-06,
|
| 90099 |
+
"loss": 0.6502,
|
| 90100 |
+
"step": 12870
|
| 90101 |
+
},
|
| 90102 |
+
{
|
| 90103 |
+
"epoch": 14.65982905982906,
|
| 90104 |
+
"grad_norm": 0.19613531231880188,
|
| 90105 |
+
"learning_rate": 8.957093995549253e-06,
|
| 90106 |
+
"loss": 0.7393,
|
| 90107 |
+
"step": 12871
|
| 90108 |
+
},
|
| 90109 |
+
{
|
| 90110 |
+
"epoch": 14.660968660968662,
|
| 90111 |
+
"grad_norm": 0.2337152659893036,
|
| 90112 |
+
"learning_rate": 8.953520951765406e-06,
|
| 90113 |
+
"loss": 0.5703,
|
| 90114 |
+
"step": 12872
|
| 90115 |
+
},
|
| 90116 |
+
{
|
| 90117 |
+
"epoch": 14.662108262108262,
|
| 90118 |
+
"grad_norm": 0.18300464749336243,
|
| 90119 |
+
"learning_rate": 8.949948465319901e-06,
|
| 90120 |
+
"loss": 0.4934,
|
| 90121 |
+
"step": 12873
|
| 90122 |
+
},
|
| 90123 |
+
{
|
| 90124 |
+
"epoch": 14.663247863247863,
|
| 90125 |
+
"grad_norm": 0.23022036254405975,
|
| 90126 |
+
"learning_rate": 8.946376536336826e-06,
|
| 90127 |
+
"loss": 0.8773,
|
| 90128 |
+
"step": 12874
|
| 90129 |
+
},
|
| 90130 |
+
{
|
| 90131 |
+
"epoch": 14.664387464387465,
|
| 90132 |
+
"grad_norm": 0.1827642321586609,
|
| 90133 |
+
"learning_rate": 8.942805164940241e-06,
|
| 90134 |
+
"loss": 0.592,
|
| 90135 |
+
"step": 12875
|
| 90136 |
+
},
|
| 90137 |
+
{
|
| 90138 |
+
"epoch": 14.665527065527066,
|
| 90139 |
+
"grad_norm": 0.23409932851791382,
|
| 90140 |
+
"learning_rate": 8.939234351254198e-06,
|
| 90141 |
+
"loss": 0.6742,
|
| 90142 |
+
"step": 12876
|
| 90143 |
+
},
|
| 90144 |
+
{
|
| 90145 |
+
"epoch": 14.666666666666666,
|
| 90146 |
+
"grad_norm": 0.20597197115421295,
|
| 90147 |
+
"learning_rate": 8.935664095402705e-06,
|
| 90148 |
+
"loss": 0.7454,
|
| 90149 |
+
"step": 12877
|
| 90150 |
+
},
|
| 90151 |
+
{
|
| 90152 |
+
"epoch": 14.667806267806268,
|
| 90153 |
+
"grad_norm": 0.23554804921150208,
|
| 90154 |
+
"learning_rate": 8.932094397509774e-06,
|
| 90155 |
+
"loss": 0.4539,
|
| 90156 |
+
"step": 12878
|
| 90157 |
+
},
|
| 90158 |
+
{
|
| 90159 |
+
"epoch": 14.668945868945869,
|
| 90160 |
+
"grad_norm": 0.24082693457603455,
|
| 90161 |
+
"learning_rate": 8.928525257699394e-06,
|
| 90162 |
+
"loss": 0.5551,
|
| 90163 |
+
"step": 12879
|
| 90164 |
+
},
|
| 90165 |
+
{
|
| 90166 |
+
"epoch": 14.67008547008547,
|
| 90167 |
+
"grad_norm": 0.18054941296577454,
|
| 90168 |
+
"learning_rate": 8.924956676095537e-06,
|
| 90169 |
+
"loss": 0.967,
|
| 90170 |
+
"step": 12880
|
| 90171 |
+
},
|
| 90172 |
+
{
|
| 90173 |
+
"epoch": 14.671225071225072,
|
| 90174 |
+
"grad_norm": 0.18954972922801971,
|
| 90175 |
+
"learning_rate": 8.921388652822129e-06,
|
| 90176 |
+
"loss": 0.5843,
|
| 90177 |
+
"step": 12881
|
| 90178 |
+
},
|
| 90179 |
+
{
|
| 90180 |
+
"epoch": 14.672364672364672,
|
| 90181 |
+
"grad_norm": 0.20438851416110992,
|
| 90182 |
+
"learning_rate": 8.917821188003112e-06,
|
| 90183 |
+
"loss": 0.7102,
|
| 90184 |
+
"step": 12882
|
| 90185 |
+
},
|
| 90186 |
+
{
|
| 90187 |
+
"epoch": 14.673504273504273,
|
| 90188 |
+
"grad_norm": 0.19364258646965027,
|
| 90189 |
+
"learning_rate": 8.91425428176239e-06,
|
| 90190 |
+
"loss": 0.6255,
|
| 90191 |
+
"step": 12883
|
| 90192 |
+
},
|
| 90193 |
+
{
|
| 90194 |
+
"epoch": 14.674643874643875,
|
| 90195 |
+
"grad_norm": 0.15404297411441803,
|
| 90196 |
+
"learning_rate": 8.910687934223854e-06,
|
| 90197 |
+
"loss": 0.8145,
|
| 90198 |
+
"step": 12884
|
| 90199 |
+
},
|
| 90200 |
+
{
|
| 90201 |
+
"epoch": 14.675783475783476,
|
| 90202 |
+
"grad_norm": 0.20459187030792236,
|
| 90203 |
+
"learning_rate": 8.90712214551137e-06,
|
| 90204 |
+
"loss": 0.5912,
|
| 90205 |
+
"step": 12885
|
| 90206 |
+
},
|
| 90207 |
+
{
|
| 90208 |
+
"epoch": 14.676923076923076,
|
| 90209 |
+
"grad_norm": 0.24483807384967804,
|
| 90210 |
+
"learning_rate": 8.903556915748792e-06,
|
| 90211 |
+
"loss": 0.7708,
|
| 90212 |
+
"step": 12886
|
| 90213 |
+
},
|
| 90214 |
+
{
|
| 90215 |
+
"epoch": 14.678062678062679,
|
| 90216 |
+
"grad_norm": 0.18246497213840485,
|
| 90217 |
+
"learning_rate": 8.899992245059956e-06,
|
| 90218 |
+
"loss": 0.6854,
|
| 90219 |
+
"step": 12887
|
| 90220 |
+
},
|
| 90221 |
+
{
|
| 90222 |
+
"epoch": 14.67920227920228,
|
| 90223 |
+
"grad_norm": 0.18728506565093994,
|
| 90224 |
+
"learning_rate": 8.896428133568654e-06,
|
| 90225 |
+
"loss": 0.7306,
|
| 90226 |
+
"step": 12888
|
| 90227 |
+
},
|
| 90228 |
+
{
|
| 90229 |
+
"epoch": 14.68034188034188,
|
| 90230 |
+
"grad_norm": 0.1966158151626587,
|
| 90231 |
+
"learning_rate": 8.892864581398691e-06,
|
| 90232 |
+
"loss": 0.7761,
|
| 90233 |
+
"step": 12889
|
| 90234 |
+
},
|
| 90235 |
+
{
|
| 90236 |
+
"epoch": 14.681481481481482,
|
| 90237 |
+
"grad_norm": 0.166145920753479,
|
| 90238 |
+
"learning_rate": 8.889301588673835e-06,
|
| 90239 |
+
"loss": 0.7806,
|
| 90240 |
+
"step": 12890
|
| 90241 |
+
},
|
| 90242 |
+
{
|
| 90243 |
+
"epoch": 14.682621082621083,
|
| 90244 |
+
"grad_norm": 0.18172600865364075,
|
| 90245 |
+
"learning_rate": 8.885739155517845e-06,
|
| 90246 |
+
"loss": 0.6886,
|
| 90247 |
+
"step": 12891
|
| 90248 |
+
},
|
| 90249 |
+
{
|
| 90250 |
+
"epoch": 14.683760683760683,
|
| 90251 |
+
"grad_norm": 0.26016733050346375,
|
| 90252 |
+
"learning_rate": 8.882177282054443e-06,
|
| 90253 |
+
"loss": 0.4099,
|
| 90254 |
+
"step": 12892
|
| 90255 |
+
},
|
| 90256 |
+
{
|
| 90257 |
+
"epoch": 14.684900284900285,
|
| 90258 |
+
"grad_norm": 0.2189798653125763,
|
| 90259 |
+
"learning_rate": 8.878615968407347e-06,
|
| 90260 |
+
"loss": 0.6603,
|
| 90261 |
+
"step": 12893
|
| 90262 |
+
},
|
| 90263 |
+
{
|
| 90264 |
+
"epoch": 14.686039886039886,
|
| 90265 |
+
"grad_norm": 0.20690695941448212,
|
| 90266 |
+
"learning_rate": 8.875055214700251e-06,
|
| 90267 |
+
"loss": 0.6559,
|
| 90268 |
+
"step": 12894
|
| 90269 |
+
},
|
| 90270 |
+
{
|
| 90271 |
+
"epoch": 14.687179487179487,
|
| 90272 |
+
"grad_norm": 0.17047905921936035,
|
| 90273 |
+
"learning_rate": 8.871495021056834e-06,
|
| 90274 |
+
"loss": 0.9431,
|
| 90275 |
+
"step": 12895
|
| 90276 |
+
},
|
| 90277 |
+
{
|
| 90278 |
+
"epoch": 14.688319088319089,
|
| 90279 |
+
"grad_norm": 0.2584533095359802,
|
| 90280 |
+
"learning_rate": 8.867935387600745e-06,
|
| 90281 |
+
"loss": 0.6573,
|
| 90282 |
+
"step": 12896
|
| 90283 |
+
},
|
| 90284 |
+
{
|
| 90285 |
+
"epoch": 14.68945868945869,
|
| 90286 |
+
"grad_norm": 0.18696272373199463,
|
| 90287 |
+
"learning_rate": 8.864376314455627e-06,
|
| 90288 |
+
"loss": 0.6192,
|
| 90289 |
+
"step": 12897
|
| 90290 |
+
},
|
| 90291 |
+
{
|
| 90292 |
+
"epoch": 14.69059829059829,
|
| 90293 |
+
"grad_norm": 0.20733846724033356,
|
| 90294 |
+
"learning_rate": 8.8608178017451e-06,
|
| 90295 |
+
"loss": 0.8758,
|
| 90296 |
+
"step": 12898
|
| 90297 |
+
},
|
| 90298 |
+
{
|
| 90299 |
+
"epoch": 14.691737891737892,
|
| 90300 |
+
"grad_norm": 0.19508017599582672,
|
| 90301 |
+
"learning_rate": 8.857259849592744e-06,
|
| 90302 |
+
"loss": 0.7261,
|
| 90303 |
+
"step": 12899
|
| 90304 |
+
},
|
| 90305 |
+
{
|
| 90306 |
+
"epoch": 14.692877492877493,
|
| 90307 |
+
"grad_norm": 0.20132368803024292,
|
| 90308 |
+
"learning_rate": 8.853702458122149e-06,
|
| 90309 |
+
"loss": 0.6758,
|
| 90310 |
+
"step": 12900
|
| 90311 |
}
|
| 90312 |
],
|
| 90313 |
"logging_steps": 1,
|
|
|
|
| 90327 |
"attributes": {}
|
| 90328 |
}
|
| 90329 |
},
|
| 90330 |
+
"total_flos": 7.212793208065966e+19,
|
| 90331 |
"train_batch_size": 8,
|
| 90332 |
"trial_name": null,
|
| 90333 |
"trial_params": null
|