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 12600, 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 sha256:3a20664f21f67960397ecf10c53f8d7fa1b17824067922595b5a2a9a09a19128
|
| 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 sha256:0e64a8832c1eda3176c4f49c8485f0fe338d444692a667769a10769b85de6e7a
|
| 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 sha256:8c715f87d211f812cf7c159d87a3f646bec48b19b1807ffb9fcf4d8ecf512392
|
| 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,
|
|
@@ -86108,6 +86108,2106 @@
|
|
| 86108 |
"learning_rate": 1.1084363972214346e-05,
|
| 86109 |
"loss": 0.6547,
|
| 86110 |
"step": 12300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86111 |
}
|
| 86112 |
],
|
| 86113 |
"logging_steps": 1,
|
|
@@ -86127,7 +88227,7 @@
|
|
| 86127 |
"attributes": {}
|
| 86128 |
}
|
| 86129 |
},
|
| 86130 |
-
"total_flos":
|
| 86131 |
"train_batch_size": 8,
|
| 86132 |
"trial_name": null,
|
| 86133 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.35099715099715,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 12600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 86108 |
"learning_rate": 1.1084363972214346e-05,
|
| 86109 |
"loss": 0.6547,
|
| 86110 |
"step": 12300
|
| 86111 |
+
},
|
| 86112 |
+
{
|
| 86113 |
+
"epoch": 14.01025641025641,
|
| 86114 |
+
"grad_norm": 0.18465548753738403,
|
| 86115 |
+
"learning_rate": 1.1080493535925104e-05,
|
| 86116 |
+
"loss": 0.7208,
|
| 86117 |
+
"step": 12301
|
| 86118 |
+
},
|
| 86119 |
+
{
|
| 86120 |
+
"epoch": 14.01139601139601,
|
| 86121 |
+
"grad_norm": 0.21446870267391205,
|
| 86122 |
+
"learning_rate": 1.1076623583098592e-05,
|
| 86123 |
+
"loss": 0.5847,
|
| 86124 |
+
"step": 12302
|
| 86125 |
+
},
|
| 86126 |
+
{
|
| 86127 |
+
"epoch": 14.012535612535613,
|
| 86128 |
+
"grad_norm": 0.25414398312568665,
|
| 86129 |
+
"learning_rate": 1.1072754113869232e-05,
|
| 86130 |
+
"loss": 0.6065,
|
| 86131 |
+
"step": 12303
|
| 86132 |
+
},
|
| 86133 |
+
{
|
| 86134 |
+
"epoch": 14.013675213675214,
|
| 86135 |
+
"grad_norm": 0.1874278336763382,
|
| 86136 |
+
"learning_rate": 1.1068885128371423e-05,
|
| 86137 |
+
"loss": 0.9341,
|
| 86138 |
+
"step": 12304
|
| 86139 |
+
},
|
| 86140 |
+
{
|
| 86141 |
+
"epoch": 14.014814814814814,
|
| 86142 |
+
"grad_norm": 0.15696552395820618,
|
| 86143 |
+
"learning_rate": 1.1065016626739553e-05,
|
| 86144 |
+
"loss": 0.9722,
|
| 86145 |
+
"step": 12305
|
| 86146 |
+
},
|
| 86147 |
+
{
|
| 86148 |
+
"epoch": 14.015954415954416,
|
| 86149 |
+
"grad_norm": 0.21116121113300323,
|
| 86150 |
+
"learning_rate": 1.1061148609107967e-05,
|
| 86151 |
+
"loss": 0.5474,
|
| 86152 |
+
"step": 12306
|
| 86153 |
+
},
|
| 86154 |
+
{
|
| 86155 |
+
"epoch": 14.017094017094017,
|
| 86156 |
+
"grad_norm": 0.17223501205444336,
|
| 86157 |
+
"learning_rate": 1.105728107561102e-05,
|
| 86158 |
+
"loss": 0.8862,
|
| 86159 |
+
"step": 12307
|
| 86160 |
+
},
|
| 86161 |
+
{
|
| 86162 |
+
"epoch": 14.018233618233618,
|
| 86163 |
+
"grad_norm": 0.17481198906898499,
|
| 86164 |
+
"learning_rate": 1.1053414026383047e-05,
|
| 86165 |
+
"loss": 0.7221,
|
| 86166 |
+
"step": 12308
|
| 86167 |
+
},
|
| 86168 |
+
{
|
| 86169 |
+
"epoch": 14.01937321937322,
|
| 86170 |
+
"grad_norm": 0.17188280820846558,
|
| 86171 |
+
"learning_rate": 1.1049547461558356e-05,
|
| 86172 |
+
"loss": 0.6618,
|
| 86173 |
+
"step": 12309
|
| 86174 |
+
},
|
| 86175 |
+
{
|
| 86176 |
+
"epoch": 14.02051282051282,
|
| 86177 |
+
"grad_norm": 0.20560085773468018,
|
| 86178 |
+
"learning_rate": 1.1045681381271247e-05,
|
| 86179 |
+
"loss": 0.5322,
|
| 86180 |
+
"step": 12310
|
| 86181 |
+
},
|
| 86182 |
+
{
|
| 86183 |
+
"epoch": 14.021652421652421,
|
| 86184 |
+
"grad_norm": 0.23315249383449554,
|
| 86185 |
+
"learning_rate": 1.1041815785655999e-05,
|
| 86186 |
+
"loss": 0.415,
|
| 86187 |
+
"step": 12311
|
| 86188 |
+
},
|
| 86189 |
+
{
|
| 86190 |
+
"epoch": 14.022792022792023,
|
| 86191 |
+
"grad_norm": 0.17557953298091888,
|
| 86192 |
+
"learning_rate": 1.103795067484688e-05,
|
| 86193 |
+
"loss": 0.7647,
|
| 86194 |
+
"step": 12312
|
| 86195 |
+
},
|
| 86196 |
+
{
|
| 86197 |
+
"epoch": 14.023931623931624,
|
| 86198 |
+
"grad_norm": 0.18308015167713165,
|
| 86199 |
+
"learning_rate": 1.1034086048978123e-05,
|
| 86200 |
+
"loss": 0.7229,
|
| 86201 |
+
"step": 12313
|
| 86202 |
+
},
|
| 86203 |
+
{
|
| 86204 |
+
"epoch": 14.025071225071224,
|
| 86205 |
+
"grad_norm": 0.2320505976676941,
|
| 86206 |
+
"learning_rate": 1.1030221908183966e-05,
|
| 86207 |
+
"loss": 0.5286,
|
| 86208 |
+
"step": 12314
|
| 86209 |
+
},
|
| 86210 |
+
{
|
| 86211 |
+
"epoch": 14.026210826210827,
|
| 86212 |
+
"grad_norm": 0.19315651059150696,
|
| 86213 |
+
"learning_rate": 1.1026358252598615e-05,
|
| 86214 |
+
"loss": 0.8859,
|
| 86215 |
+
"step": 12315
|
| 86216 |
+
},
|
| 86217 |
+
{
|
| 86218 |
+
"epoch": 14.027350427350427,
|
| 86219 |
+
"grad_norm": 0.20136956870555878,
|
| 86220 |
+
"learning_rate": 1.1022495082356283e-05,
|
| 86221 |
+
"loss": 0.7242,
|
| 86222 |
+
"step": 12316
|
| 86223 |
+
},
|
| 86224 |
+
{
|
| 86225 |
+
"epoch": 14.028490028490028,
|
| 86226 |
+
"grad_norm": 0.220159649848938,
|
| 86227 |
+
"learning_rate": 1.1018632397591122e-05,
|
| 86228 |
+
"loss": 0.5997,
|
| 86229 |
+
"step": 12317
|
| 86230 |
+
},
|
| 86231 |
+
{
|
| 86232 |
+
"epoch": 14.02962962962963,
|
| 86233 |
+
"grad_norm": 0.18217402696609497,
|
| 86234 |
+
"learning_rate": 1.1014770198437307e-05,
|
| 86235 |
+
"loss": 0.6722,
|
| 86236 |
+
"step": 12318
|
| 86237 |
+
},
|
| 86238 |
+
{
|
| 86239 |
+
"epoch": 14.03076923076923,
|
| 86240 |
+
"grad_norm": 0.23696590960025787,
|
| 86241 |
+
"learning_rate": 1.1010908485028984e-05,
|
| 86242 |
+
"loss": 0.6736,
|
| 86243 |
+
"step": 12319
|
| 86244 |
+
},
|
| 86245 |
+
{
|
| 86246 |
+
"epoch": 14.031908831908831,
|
| 86247 |
+
"grad_norm": 0.21605245769023895,
|
| 86248 |
+
"learning_rate": 1.1007047257500278e-05,
|
| 86249 |
+
"loss": 0.6124,
|
| 86250 |
+
"step": 12320
|
| 86251 |
+
},
|
| 86252 |
+
{
|
| 86253 |
+
"epoch": 14.033048433048434,
|
| 86254 |
+
"grad_norm": 0.22143849730491638,
|
| 86255 |
+
"learning_rate": 1.1003186515985304e-05,
|
| 86256 |
+
"loss": 0.7573,
|
| 86257 |
+
"step": 12321
|
| 86258 |
+
},
|
| 86259 |
+
{
|
| 86260 |
+
"epoch": 14.034188034188034,
|
| 86261 |
+
"grad_norm": 0.1849474161863327,
|
| 86262 |
+
"learning_rate": 1.0999326260618151e-05,
|
| 86263 |
+
"loss": 0.8574,
|
| 86264 |
+
"step": 12322
|
| 86265 |
+
},
|
| 86266 |
+
{
|
| 86267 |
+
"epoch": 14.035327635327635,
|
| 86268 |
+
"grad_norm": 0.18730638921260834,
|
| 86269 |
+
"learning_rate": 1.0995466491532901e-05,
|
| 86270 |
+
"loss": 0.5309,
|
| 86271 |
+
"step": 12323
|
| 86272 |
+
},
|
| 86273 |
+
{
|
| 86274 |
+
"epoch": 14.036467236467237,
|
| 86275 |
+
"grad_norm": 0.19191278517246246,
|
| 86276 |
+
"learning_rate": 1.0991607208863621e-05,
|
| 86277 |
+
"loss": 0.7682,
|
| 86278 |
+
"step": 12324
|
| 86279 |
+
},
|
| 86280 |
+
{
|
| 86281 |
+
"epoch": 14.037606837606837,
|
| 86282 |
+
"grad_norm": 0.22057481110095978,
|
| 86283 |
+
"learning_rate": 1.0987748412744337e-05,
|
| 86284 |
+
"loss": 0.6396,
|
| 86285 |
+
"step": 12325
|
| 86286 |
+
},
|
| 86287 |
+
{
|
| 86288 |
+
"epoch": 14.038746438746438,
|
| 86289 |
+
"grad_norm": 0.2798022925853729,
|
| 86290 |
+
"learning_rate": 1.0983890103309083e-05,
|
| 86291 |
+
"loss": 0.4859,
|
| 86292 |
+
"step": 12326
|
| 86293 |
+
},
|
| 86294 |
+
{
|
| 86295 |
+
"epoch": 14.03988603988604,
|
| 86296 |
+
"grad_norm": 0.14839540421962738,
|
| 86297 |
+
"learning_rate": 1.0980032280691871e-05,
|
| 86298 |
+
"loss": 0.8717,
|
| 86299 |
+
"step": 12327
|
| 86300 |
+
},
|
| 86301 |
+
{
|
| 86302 |
+
"epoch": 14.04102564102564,
|
| 86303 |
+
"grad_norm": 0.2074902355670929,
|
| 86304 |
+
"learning_rate": 1.0976174945026701e-05,
|
| 86305 |
+
"loss": 0.8141,
|
| 86306 |
+
"step": 12328
|
| 86307 |
+
},
|
| 86308 |
+
{
|
| 86309 |
+
"epoch": 14.042165242165241,
|
| 86310 |
+
"grad_norm": 0.20386825501918793,
|
| 86311 |
+
"learning_rate": 1.0972318096447534e-05,
|
| 86312 |
+
"loss": 0.64,
|
| 86313 |
+
"step": 12329
|
| 86314 |
+
},
|
| 86315 |
+
{
|
| 86316 |
+
"epoch": 14.043304843304844,
|
| 86317 |
+
"grad_norm": 0.23736783862113953,
|
| 86318 |
+
"learning_rate": 1.0968461735088334e-05,
|
| 86319 |
+
"loss": 0.54,
|
| 86320 |
+
"step": 12330
|
| 86321 |
+
},
|
| 86322 |
+
{
|
| 86323 |
+
"epoch": 14.044444444444444,
|
| 86324 |
+
"grad_norm": 0.1977514922618866,
|
| 86325 |
+
"learning_rate": 1.0964605861083047e-05,
|
| 86326 |
+
"loss": 0.7307,
|
| 86327 |
+
"step": 12331
|
| 86328 |
+
},
|
| 86329 |
+
{
|
| 86330 |
+
"epoch": 14.045584045584045,
|
| 86331 |
+
"grad_norm": 0.16288281977176666,
|
| 86332 |
+
"learning_rate": 1.0960750474565593e-05,
|
| 86333 |
+
"loss": 0.654,
|
| 86334 |
+
"step": 12332
|
| 86335 |
+
},
|
| 86336 |
+
{
|
| 86337 |
+
"epoch": 14.046723646723647,
|
| 86338 |
+
"grad_norm": 0.19778847694396973,
|
| 86339 |
+
"learning_rate": 1.0956895575669884e-05,
|
| 86340 |
+
"loss": 0.6935,
|
| 86341 |
+
"step": 12333
|
| 86342 |
+
},
|
| 86343 |
+
{
|
| 86344 |
+
"epoch": 14.047863247863248,
|
| 86345 |
+
"grad_norm": 0.17810329794883728,
|
| 86346 |
+
"learning_rate": 1.0953041164529811e-05,
|
| 86347 |
+
"loss": 0.811,
|
| 86348 |
+
"step": 12334
|
| 86349 |
+
},
|
| 86350 |
+
{
|
| 86351 |
+
"epoch": 14.049002849002848,
|
| 86352 |
+
"grad_norm": 0.1680774688720703,
|
| 86353 |
+
"learning_rate": 1.0949187241279257e-05,
|
| 86354 |
+
"loss": 0.7736,
|
| 86355 |
+
"step": 12335
|
| 86356 |
+
},
|
| 86357 |
+
{
|
| 86358 |
+
"epoch": 14.05014245014245,
|
| 86359 |
+
"grad_norm": 0.17708034813404083,
|
| 86360 |
+
"learning_rate": 1.094533380605206e-05,
|
| 86361 |
+
"loss": 0.7097,
|
| 86362 |
+
"step": 12336
|
| 86363 |
+
},
|
| 86364 |
+
{
|
| 86365 |
+
"epoch": 14.051282051282051,
|
| 86366 |
+
"grad_norm": 0.2512058615684509,
|
| 86367 |
+
"learning_rate": 1.0941480858982072e-05,
|
| 86368 |
+
"loss": 0.5888,
|
| 86369 |
+
"step": 12337
|
| 86370 |
+
},
|
| 86371 |
+
{
|
| 86372 |
+
"epoch": 14.052421652421652,
|
| 86373 |
+
"grad_norm": 0.14486335217952728,
|
| 86374 |
+
"learning_rate": 1.0937628400203112e-05,
|
| 86375 |
+
"loss": 0.833,
|
| 86376 |
+
"step": 12338
|
| 86377 |
+
},
|
| 86378 |
+
{
|
| 86379 |
+
"epoch": 14.053561253561254,
|
| 86380 |
+
"grad_norm": 0.18729153275489807,
|
| 86381 |
+
"learning_rate": 1.0933776429849002e-05,
|
| 86382 |
+
"loss": 0.722,
|
| 86383 |
+
"step": 12339
|
| 86384 |
+
},
|
| 86385 |
+
{
|
| 86386 |
+
"epoch": 14.054700854700855,
|
| 86387 |
+
"grad_norm": 0.21226993203163147,
|
| 86388 |
+
"learning_rate": 1.0929924948053508e-05,
|
| 86389 |
+
"loss": 0.7348,
|
| 86390 |
+
"step": 12340
|
| 86391 |
+
},
|
| 86392 |
+
{
|
| 86393 |
+
"epoch": 14.055840455840455,
|
| 86394 |
+
"grad_norm": 0.2136608362197876,
|
| 86395 |
+
"learning_rate": 1.0926073954950413e-05,
|
| 86396 |
+
"loss": 0.7359,
|
| 86397 |
+
"step": 12341
|
| 86398 |
+
},
|
| 86399 |
+
{
|
| 86400 |
+
"epoch": 14.056980056980057,
|
| 86401 |
+
"grad_norm": 0.22670835256576538,
|
| 86402 |
+
"learning_rate": 1.0922223450673471e-05,
|
| 86403 |
+
"loss": 0.7195,
|
| 86404 |
+
"step": 12342
|
| 86405 |
+
},
|
| 86406 |
+
{
|
| 86407 |
+
"epoch": 14.058119658119658,
|
| 86408 |
+
"grad_norm": 0.17434194684028625,
|
| 86409 |
+
"learning_rate": 1.0918373435356427e-05,
|
| 86410 |
+
"loss": 0.8143,
|
| 86411 |
+
"step": 12343
|
| 86412 |
+
},
|
| 86413 |
+
{
|
| 86414 |
+
"epoch": 14.059259259259258,
|
| 86415 |
+
"grad_norm": 0.17531150579452515,
|
| 86416 |
+
"learning_rate": 1.0914523909132995e-05,
|
| 86417 |
+
"loss": 0.7685,
|
| 86418 |
+
"step": 12344
|
| 86419 |
+
},
|
| 86420 |
+
{
|
| 86421 |
+
"epoch": 14.06039886039886,
|
| 86422 |
+
"grad_norm": 0.2420409470796585,
|
| 86423 |
+
"learning_rate": 1.0910674872136886e-05,
|
| 86424 |
+
"loss": 0.4934,
|
| 86425 |
+
"step": 12345
|
| 86426 |
+
},
|
| 86427 |
+
{
|
| 86428 |
+
"epoch": 14.061538461538461,
|
| 86429 |
+
"grad_norm": 0.2355288714170456,
|
| 86430 |
+
"learning_rate": 1.090682632450179e-05,
|
| 86431 |
+
"loss": 0.5055,
|
| 86432 |
+
"step": 12346
|
| 86433 |
+
},
|
| 86434 |
+
{
|
| 86435 |
+
"epoch": 14.062678062678062,
|
| 86436 |
+
"grad_norm": 0.22175931930541992,
|
| 86437 |
+
"learning_rate": 1.0902978266361366e-05,
|
| 86438 |
+
"loss": 0.8557,
|
| 86439 |
+
"step": 12347
|
| 86440 |
+
},
|
| 86441 |
+
{
|
| 86442 |
+
"epoch": 14.063817663817664,
|
| 86443 |
+
"grad_norm": 0.27604639530181885,
|
| 86444 |
+
"learning_rate": 1.0899130697849272e-05,
|
| 86445 |
+
"loss": 0.4887,
|
| 86446 |
+
"step": 12348
|
| 86447 |
+
},
|
| 86448 |
+
{
|
| 86449 |
+
"epoch": 14.064957264957265,
|
| 86450 |
+
"grad_norm": 0.21475738286972046,
|
| 86451 |
+
"learning_rate": 1.0895283619099145e-05,
|
| 86452 |
+
"loss": 0.6099,
|
| 86453 |
+
"step": 12349
|
| 86454 |
+
},
|
| 86455 |
+
{
|
| 86456 |
+
"epoch": 14.066096866096865,
|
| 86457 |
+
"grad_norm": 0.211808443069458,
|
| 86458 |
+
"learning_rate": 1.0891437030244617e-05,
|
| 86459 |
+
"loss": 0.7819,
|
| 86460 |
+
"step": 12350
|
| 86461 |
+
},
|
| 86462 |
+
{
|
| 86463 |
+
"epoch": 14.067236467236468,
|
| 86464 |
+
"grad_norm": 0.18572334945201874,
|
| 86465 |
+
"learning_rate": 1.0887590931419272e-05,
|
| 86466 |
+
"loss": 0.7291,
|
| 86467 |
+
"step": 12351
|
| 86468 |
+
},
|
| 86469 |
+
{
|
| 86470 |
+
"epoch": 14.068376068376068,
|
| 86471 |
+
"grad_norm": 0.21492944657802582,
|
| 86472 |
+
"learning_rate": 1.08837453227567e-05,
|
| 86473 |
+
"loss": 0.6636,
|
| 86474 |
+
"step": 12352
|
| 86475 |
+
},
|
| 86476 |
+
{
|
| 86477 |
+
"epoch": 14.069515669515669,
|
| 86478 |
+
"grad_norm": 0.16860584914684296,
|
| 86479 |
+
"learning_rate": 1.0879900204390476e-05,
|
| 86480 |
+
"loss": 0.6948,
|
| 86481 |
+
"step": 12353
|
| 86482 |
+
},
|
| 86483 |
+
{
|
| 86484 |
+
"epoch": 14.070655270655271,
|
| 86485 |
+
"grad_norm": 0.19749948382377625,
|
| 86486 |
+
"learning_rate": 1.0876055576454147e-05,
|
| 86487 |
+
"loss": 0.7881,
|
| 86488 |
+
"step": 12354
|
| 86489 |
+
},
|
| 86490 |
+
{
|
| 86491 |
+
"epoch": 14.071794871794872,
|
| 86492 |
+
"grad_norm": 0.18017134070396423,
|
| 86493 |
+
"learning_rate": 1.0872211439081249e-05,
|
| 86494 |
+
"loss": 0.8742,
|
| 86495 |
+
"step": 12355
|
| 86496 |
+
},
|
| 86497 |
+
{
|
| 86498 |
+
"epoch": 14.072934472934472,
|
| 86499 |
+
"grad_norm": 0.2028505951166153,
|
| 86500 |
+
"learning_rate": 1.0868367792405298e-05,
|
| 86501 |
+
"loss": 0.8055,
|
| 86502 |
+
"step": 12356
|
| 86503 |
+
},
|
| 86504 |
+
{
|
| 86505 |
+
"epoch": 14.074074074074074,
|
| 86506 |
+
"grad_norm": 0.28165650367736816,
|
| 86507 |
+
"learning_rate": 1.0864524636559807e-05,
|
| 86508 |
+
"loss": 0.4472,
|
| 86509 |
+
"step": 12357
|
| 86510 |
+
},
|
| 86511 |
+
{
|
| 86512 |
+
"epoch": 14.075213675213675,
|
| 86513 |
+
"grad_norm": 0.24868755042552948,
|
| 86514 |
+
"learning_rate": 1.0860681971678235e-05,
|
| 86515 |
+
"loss": 0.6308,
|
| 86516 |
+
"step": 12358
|
| 86517 |
+
},
|
| 86518 |
+
{
|
| 86519 |
+
"epoch": 14.076353276353275,
|
| 86520 |
+
"grad_norm": 0.1929575353860855,
|
| 86521 |
+
"learning_rate": 1.0856839797894065e-05,
|
| 86522 |
+
"loss": 0.695,
|
| 86523 |
+
"step": 12359
|
| 86524 |
+
},
|
| 86525 |
+
{
|
| 86526 |
+
"epoch": 14.077492877492878,
|
| 86527 |
+
"grad_norm": 0.16340765357017517,
|
| 86528 |
+
"learning_rate": 1.0852998115340743e-05,
|
| 86529 |
+
"loss": 0.7069,
|
| 86530 |
+
"step": 12360
|
| 86531 |
+
},
|
| 86532 |
+
{
|
| 86533 |
+
"epoch": 14.078632478632478,
|
| 86534 |
+
"grad_norm": 0.18964308500289917,
|
| 86535 |
+
"learning_rate": 1.08491569241517e-05,
|
| 86536 |
+
"loss": 0.7345,
|
| 86537 |
+
"step": 12361
|
| 86538 |
+
},
|
| 86539 |
+
{
|
| 86540 |
+
"epoch": 14.079772079772079,
|
| 86541 |
+
"grad_norm": 0.2203982174396515,
|
| 86542 |
+
"learning_rate": 1.0845316224460358e-05,
|
| 86543 |
+
"loss": 0.5722,
|
| 86544 |
+
"step": 12362
|
| 86545 |
+
},
|
| 86546 |
+
{
|
| 86547 |
+
"epoch": 14.080911680911681,
|
| 86548 |
+
"grad_norm": 0.1602632701396942,
|
| 86549 |
+
"learning_rate": 1.0841476016400103e-05,
|
| 86550 |
+
"loss": 0.7135,
|
| 86551 |
+
"step": 12363
|
| 86552 |
+
},
|
| 86553 |
+
{
|
| 86554 |
+
"epoch": 14.082051282051282,
|
| 86555 |
+
"grad_norm": 0.18844416737556458,
|
| 86556 |
+
"learning_rate": 1.0837636300104311e-05,
|
| 86557 |
+
"loss": 0.7949,
|
| 86558 |
+
"step": 12364
|
| 86559 |
+
},
|
| 86560 |
+
{
|
| 86561 |
+
"epoch": 14.083190883190884,
|
| 86562 |
+
"grad_norm": 0.24189259111881256,
|
| 86563 |
+
"learning_rate": 1.0833797075706378e-05,
|
| 86564 |
+
"loss": 0.6145,
|
| 86565 |
+
"step": 12365
|
| 86566 |
+
},
|
| 86567 |
+
{
|
| 86568 |
+
"epoch": 14.084330484330485,
|
| 86569 |
+
"grad_norm": 0.2609337568283081,
|
| 86570 |
+
"learning_rate": 1.082995834333962e-05,
|
| 86571 |
+
"loss": 0.5039,
|
| 86572 |
+
"step": 12366
|
| 86573 |
+
},
|
| 86574 |
+
{
|
| 86575 |
+
"epoch": 14.085470085470085,
|
| 86576 |
+
"grad_norm": 0.18424765765666962,
|
| 86577 |
+
"learning_rate": 1.0826120103137377e-05,
|
| 86578 |
+
"loss": 0.6723,
|
| 86579 |
+
"step": 12367
|
| 86580 |
+
},
|
| 86581 |
+
{
|
| 86582 |
+
"epoch": 14.086609686609687,
|
| 86583 |
+
"grad_norm": 0.19361767172813416,
|
| 86584 |
+
"learning_rate": 1.082228235523296e-05,
|
| 86585 |
+
"loss": 0.6373,
|
| 86586 |
+
"step": 12368
|
| 86587 |
+
},
|
| 86588 |
+
{
|
| 86589 |
+
"epoch": 14.087749287749288,
|
| 86590 |
+
"grad_norm": 0.26636993885040283,
|
| 86591 |
+
"learning_rate": 1.0818445099759674e-05,
|
| 86592 |
+
"loss": 0.6688,
|
| 86593 |
+
"step": 12369
|
| 86594 |
+
},
|
| 86595 |
+
{
|
| 86596 |
+
"epoch": 14.088888888888889,
|
| 86597 |
+
"grad_norm": 0.21687738597393036,
|
| 86598 |
+
"learning_rate": 1.0814608336850781e-05,
|
| 86599 |
+
"loss": 0.6995,
|
| 86600 |
+
"step": 12370
|
| 86601 |
+
},
|
| 86602 |
+
{
|
| 86603 |
+
"epoch": 14.090028490028491,
|
| 86604 |
+
"grad_norm": 0.2350667119026184,
|
| 86605 |
+
"learning_rate": 1.081077206663955e-05,
|
| 86606 |
+
"loss": 0.678,
|
| 86607 |
+
"step": 12371
|
| 86608 |
+
},
|
| 86609 |
+
{
|
| 86610 |
+
"epoch": 14.091168091168091,
|
| 86611 |
+
"grad_norm": 0.18176552653312683,
|
| 86612 |
+
"learning_rate": 1.0806936289259226e-05,
|
| 86613 |
+
"loss": 0.6437,
|
| 86614 |
+
"step": 12372
|
| 86615 |
+
},
|
| 86616 |
+
{
|
| 86617 |
+
"epoch": 14.092307692307692,
|
| 86618 |
+
"grad_norm": 0.2433783859014511,
|
| 86619 |
+
"learning_rate": 1.0803101004843044e-05,
|
| 86620 |
+
"loss": 0.5479,
|
| 86621 |
+
"step": 12373
|
| 86622 |
+
},
|
| 86623 |
+
{
|
| 86624 |
+
"epoch": 14.093447293447294,
|
| 86625 |
+
"grad_norm": 0.24452243745326996,
|
| 86626 |
+
"learning_rate": 1.0799266213524198e-05,
|
| 86627 |
+
"loss": 0.534,
|
| 86628 |
+
"step": 12374
|
| 86629 |
+
},
|
| 86630 |
+
{
|
| 86631 |
+
"epoch": 14.094586894586895,
|
| 86632 |
+
"grad_norm": 0.19095490872859955,
|
| 86633 |
+
"learning_rate": 1.0795431915435877e-05,
|
| 86634 |
+
"loss": 0.5522,
|
| 86635 |
+
"step": 12375
|
| 86636 |
+
},
|
| 86637 |
+
{
|
| 86638 |
+
"epoch": 14.095726495726495,
|
| 86639 |
+
"grad_norm": 0.18320217728614807,
|
| 86640 |
+
"learning_rate": 1.079159811071129e-05,
|
| 86641 |
+
"loss": 0.6218,
|
| 86642 |
+
"step": 12376
|
| 86643 |
+
},
|
| 86644 |
+
{
|
| 86645 |
+
"epoch": 14.096866096866098,
|
| 86646 |
+
"grad_norm": 0.2664496600627899,
|
| 86647 |
+
"learning_rate": 1.0787764799483564e-05,
|
| 86648 |
+
"loss": 0.4221,
|
| 86649 |
+
"step": 12377
|
| 86650 |
+
},
|
| 86651 |
+
{
|
| 86652 |
+
"epoch": 14.098005698005698,
|
| 86653 |
+
"grad_norm": 0.22277627885341644,
|
| 86654 |
+
"learning_rate": 1.0783931981885847e-05,
|
| 86655 |
+
"loss": 0.7926,
|
| 86656 |
+
"step": 12378
|
| 86657 |
+
},
|
| 86658 |
+
{
|
| 86659 |
+
"epoch": 14.099145299145299,
|
| 86660 |
+
"grad_norm": 0.18079183995723724,
|
| 86661 |
+
"learning_rate": 1.0780099658051271e-05,
|
| 86662 |
+
"loss": 0.7459,
|
| 86663 |
+
"step": 12379
|
| 86664 |
+
},
|
| 86665 |
+
{
|
| 86666 |
+
"epoch": 14.100284900284901,
|
| 86667 |
+
"grad_norm": 0.18426795303821564,
|
| 86668 |
+
"learning_rate": 1.0776267828112945e-05,
|
| 86669 |
+
"loss": 0.7996,
|
| 86670 |
+
"step": 12380
|
| 86671 |
+
},
|
| 86672 |
+
{
|
| 86673 |
+
"epoch": 14.101424501424502,
|
| 86674 |
+
"grad_norm": 0.17334656417369843,
|
| 86675 |
+
"learning_rate": 1.0772436492203945e-05,
|
| 86676 |
+
"loss": 0.8267,
|
| 86677 |
+
"step": 12381
|
| 86678 |
+
},
|
| 86679 |
+
{
|
| 86680 |
+
"epoch": 14.102564102564102,
|
| 86681 |
+
"grad_norm": 0.2253703474998474,
|
| 86682 |
+
"learning_rate": 1.076860565045735e-05,
|
| 86683 |
+
"loss": 0.5896,
|
| 86684 |
+
"step": 12382
|
| 86685 |
+
},
|
| 86686 |
+
{
|
| 86687 |
+
"epoch": 14.103703703703705,
|
| 86688 |
+
"grad_norm": 0.1944139003753662,
|
| 86689 |
+
"learning_rate": 1.0764775303006219e-05,
|
| 86690 |
+
"loss": 0.8137,
|
| 86691 |
+
"step": 12383
|
| 86692 |
+
},
|
| 86693 |
+
{
|
| 86694 |
+
"epoch": 14.104843304843305,
|
| 86695 |
+
"grad_norm": 0.17105910181999207,
|
| 86696 |
+
"learning_rate": 1.0760945449983597e-05,
|
| 86697 |
+
"loss": 0.7884,
|
| 86698 |
+
"step": 12384
|
| 86699 |
+
},
|
| 86700 |
+
{
|
| 86701 |
+
"epoch": 14.105982905982906,
|
| 86702 |
+
"grad_norm": 0.23568369448184967,
|
| 86703 |
+
"learning_rate": 1.075711609152249e-05,
|
| 86704 |
+
"loss": 0.627,
|
| 86705 |
+
"step": 12385
|
| 86706 |
+
},
|
| 86707 |
+
{
|
| 86708 |
+
"epoch": 14.107122507122508,
|
| 86709 |
+
"grad_norm": 0.2039739191532135,
|
| 86710 |
+
"learning_rate": 1.0753287227755898e-05,
|
| 86711 |
+
"loss": 0.6716,
|
| 86712 |
+
"step": 12386
|
| 86713 |
+
},
|
| 86714 |
+
{
|
| 86715 |
+
"epoch": 14.108262108262108,
|
| 86716 |
+
"grad_norm": 0.21701957285404205,
|
| 86717 |
+
"learning_rate": 1.0749458858816835e-05,
|
| 86718 |
+
"loss": 0.6981,
|
| 86719 |
+
"step": 12387
|
| 86720 |
+
},
|
| 86721 |
+
{
|
| 86722 |
+
"epoch": 14.109401709401709,
|
| 86723 |
+
"grad_norm": 0.19791172444820404,
|
| 86724 |
+
"learning_rate": 1.0745630984838252e-05,
|
| 86725 |
+
"loss": 0.9376,
|
| 86726 |
+
"step": 12388
|
| 86727 |
+
},
|
| 86728 |
+
{
|
| 86729 |
+
"epoch": 14.110541310541311,
|
| 86730 |
+
"grad_norm": 0.15801367163658142,
|
| 86731 |
+
"learning_rate": 1.0741803605953099e-05,
|
| 86732 |
+
"loss": 0.8482,
|
| 86733 |
+
"step": 12389
|
| 86734 |
+
},
|
| 86735 |
+
{
|
| 86736 |
+
"epoch": 14.111680911680912,
|
| 86737 |
+
"grad_norm": 0.17341923713684082,
|
| 86738 |
+
"learning_rate": 1.0737976722294319e-05,
|
| 86739 |
+
"loss": 0.705,
|
| 86740 |
+
"step": 12390
|
| 86741 |
+
},
|
| 86742 |
+
{
|
| 86743 |
+
"epoch": 14.112820512820512,
|
| 86744 |
+
"grad_norm": 0.1802707016468048,
|
| 86745 |
+
"learning_rate": 1.0734150333994838e-05,
|
| 86746 |
+
"loss": 0.6471,
|
| 86747 |
+
"step": 12391
|
| 86748 |
+
},
|
| 86749 |
+
{
|
| 86750 |
+
"epoch": 14.113960113960115,
|
| 86751 |
+
"grad_norm": 0.24691151082515717,
|
| 86752 |
+
"learning_rate": 1.0730324441187536e-05,
|
| 86753 |
+
"loss": 0.5223,
|
| 86754 |
+
"step": 12392
|
| 86755 |
+
},
|
| 86756 |
+
{
|
| 86757 |
+
"epoch": 14.115099715099715,
|
| 86758 |
+
"grad_norm": 0.21251699328422546,
|
| 86759 |
+
"learning_rate": 1.0726499044005312e-05,
|
| 86760 |
+
"loss": 0.8608,
|
| 86761 |
+
"step": 12393
|
| 86762 |
+
},
|
| 86763 |
+
{
|
| 86764 |
+
"epoch": 14.116239316239316,
|
| 86765 |
+
"grad_norm": 0.19166982173919678,
|
| 86766 |
+
"learning_rate": 1.0722674142581024e-05,
|
| 86767 |
+
"loss": 0.6466,
|
| 86768 |
+
"step": 12394
|
| 86769 |
+
},
|
| 86770 |
+
{
|
| 86771 |
+
"epoch": 14.117378917378918,
|
| 86772 |
+
"grad_norm": 0.23904511332511902,
|
| 86773 |
+
"learning_rate": 1.0718849737047537e-05,
|
| 86774 |
+
"loss": 0.6871,
|
| 86775 |
+
"step": 12395
|
| 86776 |
+
},
|
| 86777 |
+
{
|
| 86778 |
+
"epoch": 14.118518518518519,
|
| 86779 |
+
"grad_norm": 0.2263159304857254,
|
| 86780 |
+
"learning_rate": 1.071502582753766e-05,
|
| 86781 |
+
"loss": 0.5115,
|
| 86782 |
+
"step": 12396
|
| 86783 |
+
},
|
| 86784 |
+
{
|
| 86785 |
+
"epoch": 14.11965811965812,
|
| 86786 |
+
"grad_norm": 0.18796271085739136,
|
| 86787 |
+
"learning_rate": 1.0711202414184216e-05,
|
| 86788 |
+
"loss": 0.5348,
|
| 86789 |
+
"step": 12397
|
| 86790 |
+
},
|
| 86791 |
+
{
|
| 86792 |
+
"epoch": 14.120797720797722,
|
| 86793 |
+
"grad_norm": 0.24163362383842468,
|
| 86794 |
+
"learning_rate": 1.0707379497120013e-05,
|
| 86795 |
+
"loss": 0.6685,
|
| 86796 |
+
"step": 12398
|
| 86797 |
+
},
|
| 86798 |
+
{
|
| 86799 |
+
"epoch": 14.121937321937322,
|
| 86800 |
+
"grad_norm": 0.18093737959861755,
|
| 86801 |
+
"learning_rate": 1.0703557076477833e-05,
|
| 86802 |
+
"loss": 0.806,
|
| 86803 |
+
"step": 12399
|
| 86804 |
+
},
|
| 86805 |
+
{
|
| 86806 |
+
"epoch": 14.123076923076923,
|
| 86807 |
+
"grad_norm": 0.21274122595787048,
|
| 86808 |
+
"learning_rate": 1.0699735152390422e-05,
|
| 86809 |
+
"loss": 0.7044,
|
| 86810 |
+
"step": 12400
|
| 86811 |
+
},
|
| 86812 |
+
{
|
| 86813 |
+
"epoch": 14.124216524216525,
|
| 86814 |
+
"grad_norm": 0.2155819535255432,
|
| 86815 |
+
"learning_rate": 1.0695913724990535e-05,
|
| 86816 |
+
"loss": 0.7369,
|
| 86817 |
+
"step": 12401
|
| 86818 |
+
},
|
| 86819 |
+
{
|
| 86820 |
+
"epoch": 14.125356125356126,
|
| 86821 |
+
"grad_norm": 0.1662980169057846,
|
| 86822 |
+
"learning_rate": 1.0692092794410904e-05,
|
| 86823 |
+
"loss": 0.8839,
|
| 86824 |
+
"step": 12402
|
| 86825 |
+
},
|
| 86826 |
+
{
|
| 86827 |
+
"epoch": 14.126495726495726,
|
| 86828 |
+
"grad_norm": 0.21541108191013336,
|
| 86829 |
+
"learning_rate": 1.0688272360784244e-05,
|
| 86830 |
+
"loss": 0.4945,
|
| 86831 |
+
"step": 12403
|
| 86832 |
+
},
|
| 86833 |
+
{
|
| 86834 |
+
"epoch": 14.127635327635328,
|
| 86835 |
+
"grad_norm": 0.19884797930717468,
|
| 86836 |
+
"learning_rate": 1.0684452424243232e-05,
|
| 86837 |
+
"loss": 0.4722,
|
| 86838 |
+
"step": 12404
|
| 86839 |
+
},
|
| 86840 |
+
{
|
| 86841 |
+
"epoch": 14.128774928774929,
|
| 86842 |
+
"grad_norm": 0.2191683053970337,
|
| 86843 |
+
"learning_rate": 1.0680632984920558e-05,
|
| 86844 |
+
"loss": 0.5608,
|
| 86845 |
+
"step": 12405
|
| 86846 |
+
},
|
| 86847 |
+
{
|
| 86848 |
+
"epoch": 14.12991452991453,
|
| 86849 |
+
"grad_norm": 0.17608490586280823,
|
| 86850 |
+
"learning_rate": 1.0676814042948876e-05,
|
| 86851 |
+
"loss": 0.8601,
|
| 86852 |
+
"step": 12406
|
| 86853 |
+
},
|
| 86854 |
+
{
|
| 86855 |
+
"epoch": 14.131054131054132,
|
| 86856 |
+
"grad_norm": 0.23183391988277435,
|
| 86857 |
+
"learning_rate": 1.0672995598460841e-05,
|
| 86858 |
+
"loss": 0.6027,
|
| 86859 |
+
"step": 12407
|
| 86860 |
+
},
|
| 86861 |
+
{
|
| 86862 |
+
"epoch": 14.132193732193732,
|
| 86863 |
+
"grad_norm": 0.1913665384054184,
|
| 86864 |
+
"learning_rate": 1.0669177651589051e-05,
|
| 86865 |
+
"loss": 0.6524,
|
| 86866 |
+
"step": 12408
|
| 86867 |
+
},
|
| 86868 |
+
{
|
| 86869 |
+
"epoch": 14.133333333333333,
|
| 86870 |
+
"grad_norm": 0.18311044573783875,
|
| 86871 |
+
"learning_rate": 1.066536020246614e-05,
|
| 86872 |
+
"loss": 0.8798,
|
| 86873 |
+
"step": 12409
|
| 86874 |
+
},
|
| 86875 |
+
{
|
| 86876 |
+
"epoch": 14.134472934472935,
|
| 86877 |
+
"grad_norm": 0.18477991223335266,
|
| 86878 |
+
"learning_rate": 1.0661543251224699e-05,
|
| 86879 |
+
"loss": 0.6599,
|
| 86880 |
+
"step": 12410
|
| 86881 |
+
},
|
| 86882 |
+
{
|
| 86883 |
+
"epoch": 14.135612535612536,
|
| 86884 |
+
"grad_norm": 0.22089451551437378,
|
| 86885 |
+
"learning_rate": 1.065772679799728e-05,
|
| 86886 |
+
"loss": 0.6662,
|
| 86887 |
+
"step": 12411
|
| 86888 |
+
},
|
| 86889 |
+
{
|
| 86890 |
+
"epoch": 14.136752136752136,
|
| 86891 |
+
"grad_norm": 0.2456071823835373,
|
| 86892 |
+
"learning_rate": 1.0653910842916454e-05,
|
| 86893 |
+
"loss": 0.6785,
|
| 86894 |
+
"step": 12412
|
| 86895 |
+
},
|
| 86896 |
+
{
|
| 86897 |
+
"epoch": 14.137891737891739,
|
| 86898 |
+
"grad_norm": 0.212762251496315,
|
| 86899 |
+
"learning_rate": 1.0650095386114756e-05,
|
| 86900 |
+
"loss": 0.7099,
|
| 86901 |
+
"step": 12413
|
| 86902 |
+
},
|
| 86903 |
+
{
|
| 86904 |
+
"epoch": 14.13903133903134,
|
| 86905 |
+
"grad_norm": 0.22029614448547363,
|
| 86906 |
+
"learning_rate": 1.0646280427724715e-05,
|
| 86907 |
+
"loss": 0.7065,
|
| 86908 |
+
"step": 12414
|
| 86909 |
+
},
|
| 86910 |
+
{
|
| 86911 |
+
"epoch": 14.14017094017094,
|
| 86912 |
+
"grad_norm": 0.20419296622276306,
|
| 86913 |
+
"learning_rate": 1.064246596787882e-05,
|
| 86914 |
+
"loss": 0.706,
|
| 86915 |
+
"step": 12415
|
| 86916 |
+
},
|
| 86917 |
+
{
|
| 86918 |
+
"epoch": 14.141310541310542,
|
| 86919 |
+
"grad_norm": 0.25089824199676514,
|
| 86920 |
+
"learning_rate": 1.0638652006709565e-05,
|
| 86921 |
+
"loss": 0.5925,
|
| 86922 |
+
"step": 12416
|
| 86923 |
+
},
|
| 86924 |
+
{
|
| 86925 |
+
"epoch": 14.142450142450143,
|
| 86926 |
+
"grad_norm": 0.2615416347980499,
|
| 86927 |
+
"learning_rate": 1.0634838544349417e-05,
|
| 86928 |
+
"loss": 0.5556,
|
| 86929 |
+
"step": 12417
|
| 86930 |
+
},
|
| 86931 |
+
{
|
| 86932 |
+
"epoch": 14.143589743589743,
|
| 86933 |
+
"grad_norm": 0.1994006484746933,
|
| 86934 |
+
"learning_rate": 1.0631025580930846e-05,
|
| 86935 |
+
"loss": 0.7281,
|
| 86936 |
+
"step": 12418
|
| 86937 |
+
},
|
| 86938 |
+
{
|
| 86939 |
+
"epoch": 14.144729344729345,
|
| 86940 |
+
"grad_norm": 0.1971782147884369,
|
| 86941 |
+
"learning_rate": 1.062721311658625e-05,
|
| 86942 |
+
"loss": 0.6861,
|
| 86943 |
+
"step": 12419
|
| 86944 |
+
},
|
| 86945 |
+
{
|
| 86946 |
+
"epoch": 14.145868945868946,
|
| 86947 |
+
"grad_norm": 0.203592911362648,
|
| 86948 |
+
"learning_rate": 1.0623401151448073e-05,
|
| 86949 |
+
"loss": 0.6064,
|
| 86950 |
+
"step": 12420
|
| 86951 |
+
},
|
| 86952 |
+
{
|
| 86953 |
+
"epoch": 14.147008547008546,
|
| 86954 |
+
"grad_norm": 0.21394099295139313,
|
| 86955 |
+
"learning_rate": 1.0619589685648723e-05,
|
| 86956 |
+
"loss": 0.5012,
|
| 86957 |
+
"step": 12421
|
| 86958 |
+
},
|
| 86959 |
+
{
|
| 86960 |
+
"epoch": 14.148148148148149,
|
| 86961 |
+
"grad_norm": 0.18990157544612885,
|
| 86962 |
+
"learning_rate": 1.061577871932056e-05,
|
| 86963 |
+
"loss": 0.7969,
|
| 86964 |
+
"step": 12422
|
| 86965 |
+
},
|
| 86966 |
+
{
|
| 86967 |
+
"epoch": 14.14928774928775,
|
| 86968 |
+
"grad_norm": 0.22332452237606049,
|
| 86969 |
+
"learning_rate": 1.0611968252595959e-05,
|
| 86970 |
+
"loss": 0.6604,
|
| 86971 |
+
"step": 12423
|
| 86972 |
+
},
|
| 86973 |
+
{
|
| 86974 |
+
"epoch": 14.15042735042735,
|
| 86975 |
+
"grad_norm": 0.24588967859745026,
|
| 86976 |
+
"learning_rate": 1.0608158285607266e-05,
|
| 86977 |
+
"loss": 0.6556,
|
| 86978 |
+
"step": 12424
|
| 86979 |
+
},
|
| 86980 |
+
{
|
| 86981 |
+
"epoch": 14.151566951566952,
|
| 86982 |
+
"grad_norm": 0.28720003366470337,
|
| 86983 |
+
"learning_rate": 1.0604348818486823e-05,
|
| 86984 |
+
"loss": 0.4166,
|
| 86985 |
+
"step": 12425
|
| 86986 |
+
},
|
| 86987 |
+
{
|
| 86988 |
+
"epoch": 14.152706552706553,
|
| 86989 |
+
"grad_norm": 0.17065948247909546,
|
| 86990 |
+
"learning_rate": 1.0600539851366925e-05,
|
| 86991 |
+
"loss": 0.596,
|
| 86992 |
+
"step": 12426
|
| 86993 |
+
},
|
| 86994 |
+
{
|
| 86995 |
+
"epoch": 14.153846153846153,
|
| 86996 |
+
"grad_norm": 0.21314504742622375,
|
| 86997 |
+
"learning_rate": 1.059673138437988e-05,
|
| 86998 |
+
"loss": 0.6275,
|
| 86999 |
+
"step": 12427
|
| 87000 |
+
},
|
| 87001 |
+
{
|
| 87002 |
+
"epoch": 14.154985754985756,
|
| 87003 |
+
"grad_norm": 0.19009727239608765,
|
| 87004 |
+
"learning_rate": 1.0592923417657958e-05,
|
| 87005 |
+
"loss": 0.6682,
|
| 87006 |
+
"step": 12428
|
| 87007 |
+
},
|
| 87008 |
+
{
|
| 87009 |
+
"epoch": 14.156125356125356,
|
| 87010 |
+
"grad_norm": 0.20869901776313782,
|
| 87011 |
+
"learning_rate": 1.0589115951333436e-05,
|
| 87012 |
+
"loss": 0.7042,
|
| 87013 |
+
"step": 12429
|
| 87014 |
+
},
|
| 87015 |
+
{
|
| 87016 |
+
"epoch": 14.157264957264957,
|
| 87017 |
+
"grad_norm": 0.20850737392902374,
|
| 87018 |
+
"learning_rate": 1.058530898553853e-05,
|
| 87019 |
+
"loss": 0.4879,
|
| 87020 |
+
"step": 12430
|
| 87021 |
+
},
|
| 87022 |
+
{
|
| 87023 |
+
"epoch": 14.158404558404559,
|
| 87024 |
+
"grad_norm": 0.18836501240730286,
|
| 87025 |
+
"learning_rate": 1.0581502520405492e-05,
|
| 87026 |
+
"loss": 0.7744,
|
| 87027 |
+
"step": 12431
|
| 87028 |
+
},
|
| 87029 |
+
{
|
| 87030 |
+
"epoch": 14.15954415954416,
|
| 87031 |
+
"grad_norm": 0.23801569640636444,
|
| 87032 |
+
"learning_rate": 1.0577696556066533e-05,
|
| 87033 |
+
"loss": 0.3337,
|
| 87034 |
+
"step": 12432
|
| 87035 |
+
},
|
| 87036 |
+
{
|
| 87037 |
+
"epoch": 14.16068376068376,
|
| 87038 |
+
"grad_norm": 0.2107766717672348,
|
| 87039 |
+
"learning_rate": 1.0573891092653823e-05,
|
| 87040 |
+
"loss": 0.5125,
|
| 87041 |
+
"step": 12433
|
| 87042 |
+
},
|
| 87043 |
+
{
|
| 87044 |
+
"epoch": 14.161823361823362,
|
| 87045 |
+
"grad_norm": 0.2487872987985611,
|
| 87046 |
+
"learning_rate": 1.0570086130299548e-05,
|
| 87047 |
+
"loss": 0.5924,
|
| 87048 |
+
"step": 12434
|
| 87049 |
+
},
|
| 87050 |
+
{
|
| 87051 |
+
"epoch": 14.162962962962963,
|
| 87052 |
+
"grad_norm": 0.24329927563667297,
|
| 87053 |
+
"learning_rate": 1.0566281669135863e-05,
|
| 87054 |
+
"loss": 0.3506,
|
| 87055 |
+
"step": 12435
|
| 87056 |
+
},
|
| 87057 |
+
{
|
| 87058 |
+
"epoch": 14.164102564102564,
|
| 87059 |
+
"grad_norm": 0.181972935795784,
|
| 87060 |
+
"learning_rate": 1.0562477709294919e-05,
|
| 87061 |
+
"loss": 0.7264,
|
| 87062 |
+
"step": 12436
|
| 87063 |
+
},
|
| 87064 |
+
{
|
| 87065 |
+
"epoch": 14.165242165242166,
|
| 87066 |
+
"grad_norm": 0.18620088696479797,
|
| 87067 |
+
"learning_rate": 1.0558674250908818e-05,
|
| 87068 |
+
"loss": 0.7772,
|
| 87069 |
+
"step": 12437
|
| 87070 |
+
},
|
| 87071 |
+
{
|
| 87072 |
+
"epoch": 14.166381766381766,
|
| 87073 |
+
"grad_norm": 0.19572575390338898,
|
| 87074 |
+
"learning_rate": 1.0554871294109675e-05,
|
| 87075 |
+
"loss": 0.7916,
|
| 87076 |
+
"step": 12438
|
| 87077 |
+
},
|
| 87078 |
+
{
|
| 87079 |
+
"epoch": 14.167521367521367,
|
| 87080 |
+
"grad_norm": 0.20265932381153107,
|
| 87081 |
+
"learning_rate": 1.0551068839029576e-05,
|
| 87082 |
+
"loss": 0.6412,
|
| 87083 |
+
"step": 12439
|
| 87084 |
+
},
|
| 87085 |
+
{
|
| 87086 |
+
"epoch": 14.16866096866097,
|
| 87087 |
+
"grad_norm": 0.20510506629943848,
|
| 87088 |
+
"learning_rate": 1.0547266885800588e-05,
|
| 87089 |
+
"loss": 0.4159,
|
| 87090 |
+
"step": 12440
|
| 87091 |
+
},
|
| 87092 |
+
{
|
| 87093 |
+
"epoch": 14.16980056980057,
|
| 87094 |
+
"grad_norm": 0.15745452046394348,
|
| 87095 |
+
"learning_rate": 1.0543465434554769e-05,
|
| 87096 |
+
"loss": 0.6387,
|
| 87097 |
+
"step": 12441
|
| 87098 |
+
},
|
| 87099 |
+
{
|
| 87100 |
+
"epoch": 14.17094017094017,
|
| 87101 |
+
"grad_norm": 0.18906773626804352,
|
| 87102 |
+
"learning_rate": 1.0539664485424153e-05,
|
| 87103 |
+
"loss": 0.7071,
|
| 87104 |
+
"step": 12442
|
| 87105 |
+
},
|
| 87106 |
+
{
|
| 87107 |
+
"epoch": 14.172079772079773,
|
| 87108 |
+
"grad_norm": 0.19148340821266174,
|
| 87109 |
+
"learning_rate": 1.0535864038540751e-05,
|
| 87110 |
+
"loss": 0.5026,
|
| 87111 |
+
"step": 12443
|
| 87112 |
+
},
|
| 87113 |
+
{
|
| 87114 |
+
"epoch": 14.173219373219373,
|
| 87115 |
+
"grad_norm": 0.22974300384521484,
|
| 87116 |
+
"learning_rate": 1.0532064094036582e-05,
|
| 87117 |
+
"loss": 0.6189,
|
| 87118 |
+
"step": 12444
|
| 87119 |
+
},
|
| 87120 |
+
{
|
| 87121 |
+
"epoch": 14.174358974358974,
|
| 87122 |
+
"grad_norm": 0.20122529566287994,
|
| 87123 |
+
"learning_rate": 1.0528264652043598e-05,
|
| 87124 |
+
"loss": 0.6045,
|
| 87125 |
+
"step": 12445
|
| 87126 |
+
},
|
| 87127 |
+
{
|
| 87128 |
+
"epoch": 14.175498575498576,
|
| 87129 |
+
"grad_norm": 0.19866183400154114,
|
| 87130 |
+
"learning_rate": 1.0524465712693784e-05,
|
| 87131 |
+
"loss": 0.4626,
|
| 87132 |
+
"step": 12446
|
| 87133 |
+
},
|
| 87134 |
+
{
|
| 87135 |
+
"epoch": 14.176638176638177,
|
| 87136 |
+
"grad_norm": 0.1823773980140686,
|
| 87137 |
+
"learning_rate": 1.0520667276119084e-05,
|
| 87138 |
+
"loss": 0.7385,
|
| 87139 |
+
"step": 12447
|
| 87140 |
+
},
|
| 87141 |
+
{
|
| 87142 |
+
"epoch": 14.177777777777777,
|
| 87143 |
+
"grad_norm": 0.22166435420513153,
|
| 87144 |
+
"learning_rate": 1.0516869342451436e-05,
|
| 87145 |
+
"loss": 0.6146,
|
| 87146 |
+
"step": 12448
|
| 87147 |
+
},
|
| 87148 |
+
{
|
| 87149 |
+
"epoch": 14.17891737891738,
|
| 87150 |
+
"grad_norm": 0.18655037879943848,
|
| 87151 |
+
"learning_rate": 1.0513071911822736e-05,
|
| 87152 |
+
"loss": 0.7272,
|
| 87153 |
+
"step": 12449
|
| 87154 |
+
},
|
| 87155 |
+
{
|
| 87156 |
+
"epoch": 14.18005698005698,
|
| 87157 |
+
"grad_norm": 0.2278573364019394,
|
| 87158 |
+
"learning_rate": 1.0509274984364886e-05,
|
| 87159 |
+
"loss": 0.5605,
|
| 87160 |
+
"step": 12450
|
| 87161 |
+
},
|
| 87162 |
+
{
|
| 87163 |
+
"epoch": 14.18119658119658,
|
| 87164 |
+
"grad_norm": 0.23333711922168732,
|
| 87165 |
+
"learning_rate": 1.050547856020977e-05,
|
| 87166 |
+
"loss": 0.6219,
|
| 87167 |
+
"step": 12451
|
| 87168 |
+
},
|
| 87169 |
+
{
|
| 87170 |
+
"epoch": 14.182336182336183,
|
| 87171 |
+
"grad_norm": 0.22250933945178986,
|
| 87172 |
+
"learning_rate": 1.0501682639489239e-05,
|
| 87173 |
+
"loss": 0.6751,
|
| 87174 |
+
"step": 12452
|
| 87175 |
+
},
|
| 87176 |
+
{
|
| 87177 |
+
"epoch": 14.183475783475783,
|
| 87178 |
+
"grad_norm": 0.18318895995616913,
|
| 87179 |
+
"learning_rate": 1.0497887222335143e-05,
|
| 87180 |
+
"loss": 0.7053,
|
| 87181 |
+
"step": 12453
|
| 87182 |
+
},
|
| 87183 |
+
{
|
| 87184 |
+
"epoch": 14.184615384615384,
|
| 87185 |
+
"grad_norm": 0.1692780703306198,
|
| 87186 |
+
"learning_rate": 1.0494092308879302e-05,
|
| 87187 |
+
"loss": 0.5763,
|
| 87188 |
+
"step": 12454
|
| 87189 |
+
},
|
| 87190 |
+
{
|
| 87191 |
+
"epoch": 14.185754985754986,
|
| 87192 |
+
"grad_norm": 0.2442038357257843,
|
| 87193 |
+
"learning_rate": 1.0490297899253537e-05,
|
| 87194 |
+
"loss": 0.5009,
|
| 87195 |
+
"step": 12455
|
| 87196 |
+
},
|
| 87197 |
+
{
|
| 87198 |
+
"epoch": 14.186894586894587,
|
| 87199 |
+
"grad_norm": 0.2019973248243332,
|
| 87200 |
+
"learning_rate": 1.0486503993589619e-05,
|
| 87201 |
+
"loss": 0.6492,
|
| 87202 |
+
"step": 12456
|
| 87203 |
+
},
|
| 87204 |
+
{
|
| 87205 |
+
"epoch": 14.188034188034187,
|
| 87206 |
+
"grad_norm": 0.16503944993019104,
|
| 87207 |
+
"learning_rate": 1.048271059201933e-05,
|
| 87208 |
+
"loss": 0.8739,
|
| 87209 |
+
"step": 12457
|
| 87210 |
+
},
|
| 87211 |
+
{
|
| 87212 |
+
"epoch": 14.18917378917379,
|
| 87213 |
+
"grad_norm": 0.19559434056282043,
|
| 87214 |
+
"learning_rate": 1.0478917694674426e-05,
|
| 87215 |
+
"loss": 0.8488,
|
| 87216 |
+
"step": 12458
|
| 87217 |
+
},
|
| 87218 |
+
{
|
| 87219 |
+
"epoch": 14.19031339031339,
|
| 87220 |
+
"grad_norm": 0.17246732115745544,
|
| 87221 |
+
"learning_rate": 1.047512530168665e-05,
|
| 87222 |
+
"loss": 0.8205,
|
| 87223 |
+
"step": 12459
|
| 87224 |
+
},
|
| 87225 |
+
{
|
| 87226 |
+
"epoch": 14.19145299145299,
|
| 87227 |
+
"grad_norm": 0.2481149286031723,
|
| 87228 |
+
"learning_rate": 1.0471333413187706e-05,
|
| 87229 |
+
"loss": 0.5811,
|
| 87230 |
+
"step": 12460
|
| 87231 |
+
},
|
| 87232 |
+
{
|
| 87233 |
+
"epoch": 14.192592592592593,
|
| 87234 |
+
"grad_norm": 0.19406673312187195,
|
| 87235 |
+
"learning_rate": 1.046754202930931e-05,
|
| 87236 |
+
"loss": 0.5999,
|
| 87237 |
+
"step": 12461
|
| 87238 |
+
},
|
| 87239 |
+
{
|
| 87240 |
+
"epoch": 14.193732193732194,
|
| 87241 |
+
"grad_norm": 0.19021573662757874,
|
| 87242 |
+
"learning_rate": 1.0463751150183143e-05,
|
| 87243 |
+
"loss": 0.7711,
|
| 87244 |
+
"step": 12462
|
| 87245 |
+
},
|
| 87246 |
+
{
|
| 87247 |
+
"epoch": 14.194871794871794,
|
| 87248 |
+
"grad_norm": 0.22574403882026672,
|
| 87249 |
+
"learning_rate": 1.045996077594088e-05,
|
| 87250 |
+
"loss": 0.5977,
|
| 87251 |
+
"step": 12463
|
| 87252 |
+
},
|
| 87253 |
+
{
|
| 87254 |
+
"epoch": 14.196011396011396,
|
| 87255 |
+
"grad_norm": 0.16467835009098053,
|
| 87256 |
+
"learning_rate": 1.045617090671415e-05,
|
| 87257 |
+
"loss": 0.843,
|
| 87258 |
+
"step": 12464
|
| 87259 |
+
},
|
| 87260 |
+
{
|
| 87261 |
+
"epoch": 14.197150997150997,
|
| 87262 |
+
"grad_norm": 0.20068757236003876,
|
| 87263 |
+
"learning_rate": 1.0452381542634607e-05,
|
| 87264 |
+
"loss": 0.822,
|
| 87265 |
+
"step": 12465
|
| 87266 |
+
},
|
| 87267 |
+
{
|
| 87268 |
+
"epoch": 14.198290598290598,
|
| 87269 |
+
"grad_norm": 0.18333548307418823,
|
| 87270 |
+
"learning_rate": 1.0448592683833866e-05,
|
| 87271 |
+
"loss": 0.6512,
|
| 87272 |
+
"step": 12466
|
| 87273 |
+
},
|
| 87274 |
+
{
|
| 87275 |
+
"epoch": 14.1994301994302,
|
| 87276 |
+
"grad_norm": 0.2103206366300583,
|
| 87277 |
+
"learning_rate": 1.044480433044351e-05,
|
| 87278 |
+
"loss": 0.5612,
|
| 87279 |
+
"step": 12467
|
| 87280 |
+
},
|
| 87281 |
+
{
|
| 87282 |
+
"epoch": 14.2005698005698,
|
| 87283 |
+
"grad_norm": 0.20221920311450958,
|
| 87284 |
+
"learning_rate": 1.0441016482595129e-05,
|
| 87285 |
+
"loss": 0.5504,
|
| 87286 |
+
"step": 12468
|
| 87287 |
+
},
|
| 87288 |
+
{
|
| 87289 |
+
"epoch": 14.201709401709401,
|
| 87290 |
+
"grad_norm": 0.19960333406925201,
|
| 87291 |
+
"learning_rate": 1.0437229140420282e-05,
|
| 87292 |
+
"loss": 0.7304,
|
| 87293 |
+
"step": 12469
|
| 87294 |
+
},
|
| 87295 |
+
{
|
| 87296 |
+
"epoch": 14.202849002849003,
|
| 87297 |
+
"grad_norm": 0.2146003097295761,
|
| 87298 |
+
"learning_rate": 1.0433442304050522e-05,
|
| 87299 |
+
"loss": 0.7793,
|
| 87300 |
+
"step": 12470
|
| 87301 |
+
},
|
| 87302 |
+
{
|
| 87303 |
+
"epoch": 14.203988603988604,
|
| 87304 |
+
"grad_norm": 0.17417925596237183,
|
| 87305 |
+
"learning_rate": 1.042965597361736e-05,
|
| 87306 |
+
"loss": 0.7855,
|
| 87307 |
+
"step": 12471
|
| 87308 |
+
},
|
| 87309 |
+
{
|
| 87310 |
+
"epoch": 14.205128205128204,
|
| 87311 |
+
"grad_norm": 0.17933909595012665,
|
| 87312 |
+
"learning_rate": 1.0425870149252317e-05,
|
| 87313 |
+
"loss": 0.8203,
|
| 87314 |
+
"step": 12472
|
| 87315 |
+
},
|
| 87316 |
+
{
|
| 87317 |
+
"epoch": 14.206267806267807,
|
| 87318 |
+
"grad_norm": 0.15111088752746582,
|
| 87319 |
+
"learning_rate": 1.042208483108688e-05,
|
| 87320 |
+
"loss": 0.7666,
|
| 87321 |
+
"step": 12473
|
| 87322 |
+
},
|
| 87323 |
+
{
|
| 87324 |
+
"epoch": 14.207407407407407,
|
| 87325 |
+
"grad_norm": 0.2167760282754898,
|
| 87326 |
+
"learning_rate": 1.0418300019252539e-05,
|
| 87327 |
+
"loss": 0.6168,
|
| 87328 |
+
"step": 12474
|
| 87329 |
+
},
|
| 87330 |
+
{
|
| 87331 |
+
"epoch": 14.208547008547008,
|
| 87332 |
+
"grad_norm": 0.19389691948890686,
|
| 87333 |
+
"learning_rate": 1.0414515713880717e-05,
|
| 87334 |
+
"loss": 0.5633,
|
| 87335 |
+
"step": 12475
|
| 87336 |
+
},
|
| 87337 |
+
{
|
| 87338 |
+
"epoch": 14.20968660968661,
|
| 87339 |
+
"grad_norm": 0.22056040167808533,
|
| 87340 |
+
"learning_rate": 1.0410731915102883e-05,
|
| 87341 |
+
"loss": 0.4671,
|
| 87342 |
+
"step": 12476
|
| 87343 |
+
},
|
| 87344 |
+
{
|
| 87345 |
+
"epoch": 14.21082621082621,
|
| 87346 |
+
"grad_norm": 0.21271564066410065,
|
| 87347 |
+
"learning_rate": 1.0406948623050453e-05,
|
| 87348 |
+
"loss": 0.5757,
|
| 87349 |
+
"step": 12477
|
| 87350 |
+
},
|
| 87351 |
+
{
|
| 87352 |
+
"epoch": 14.211965811965811,
|
| 87353 |
+
"grad_norm": 0.20088516175746918,
|
| 87354 |
+
"learning_rate": 1.0403165837854837e-05,
|
| 87355 |
+
"loss": 0.5874,
|
| 87356 |
+
"step": 12478
|
| 87357 |
+
},
|
| 87358 |
+
{
|
| 87359 |
+
"epoch": 14.213105413105414,
|
| 87360 |
+
"grad_norm": 0.22104431688785553,
|
| 87361 |
+
"learning_rate": 1.0399383559647402e-05,
|
| 87362 |
+
"loss": 0.397,
|
| 87363 |
+
"step": 12479
|
| 87364 |
+
},
|
| 87365 |
+
{
|
| 87366 |
+
"epoch": 14.214245014245014,
|
| 87367 |
+
"grad_norm": 0.22194375097751617,
|
| 87368 |
+
"learning_rate": 1.0395601788559527e-05,
|
| 87369 |
+
"loss": 0.4472,
|
| 87370 |
+
"step": 12480
|
| 87371 |
+
},
|
| 87372 |
+
{
|
| 87373 |
+
"epoch": 14.215384615384615,
|
| 87374 |
+
"grad_norm": 0.2375565469264984,
|
| 87375 |
+
"learning_rate": 1.0391820524722568e-05,
|
| 87376 |
+
"loss": 0.5376,
|
| 87377 |
+
"step": 12481
|
| 87378 |
+
},
|
| 87379 |
+
{
|
| 87380 |
+
"epoch": 14.216524216524217,
|
| 87381 |
+
"grad_norm": 0.2139328122138977,
|
| 87382 |
+
"learning_rate": 1.038803976826786e-05,
|
| 87383 |
+
"loss": 0.692,
|
| 87384 |
+
"step": 12482
|
| 87385 |
+
},
|
| 87386 |
+
{
|
| 87387 |
+
"epoch": 14.217663817663817,
|
| 87388 |
+
"grad_norm": 0.16154590249061584,
|
| 87389 |
+
"learning_rate": 1.0384259519326706e-05,
|
| 87390 |
+
"loss": 0.5521,
|
| 87391 |
+
"step": 12483
|
| 87392 |
+
},
|
| 87393 |
+
{
|
| 87394 |
+
"epoch": 14.218803418803418,
|
| 87395 |
+
"grad_norm": 0.16744598746299744,
|
| 87396 |
+
"learning_rate": 1.0380479778030414e-05,
|
| 87397 |
+
"loss": 0.8703,
|
| 87398 |
+
"step": 12484
|
| 87399 |
+
},
|
| 87400 |
+
{
|
| 87401 |
+
"epoch": 14.21994301994302,
|
| 87402 |
+
"grad_norm": 0.1954227089881897,
|
| 87403 |
+
"learning_rate": 1.0376700544510262e-05,
|
| 87404 |
+
"loss": 0.3635,
|
| 87405 |
+
"step": 12485
|
| 87406 |
+
},
|
| 87407 |
+
{
|
| 87408 |
+
"epoch": 14.221082621082621,
|
| 87409 |
+
"grad_norm": 0.18372157216072083,
|
| 87410 |
+
"learning_rate": 1.0372921818897512e-05,
|
| 87411 |
+
"loss": 0.6228,
|
| 87412 |
+
"step": 12486
|
| 87413 |
+
},
|
| 87414 |
+
{
|
| 87415 |
+
"epoch": 14.222222222222221,
|
| 87416 |
+
"grad_norm": 0.2358933389186859,
|
| 87417 |
+
"learning_rate": 1.0369143601323417e-05,
|
| 87418 |
+
"loss": 0.8105,
|
| 87419 |
+
"step": 12487
|
| 87420 |
+
},
|
| 87421 |
+
{
|
| 87422 |
+
"epoch": 14.223361823361824,
|
| 87423 |
+
"grad_norm": 0.2836482524871826,
|
| 87424 |
+
"learning_rate": 1.0365365891919197e-05,
|
| 87425 |
+
"loss": 0.6668,
|
| 87426 |
+
"step": 12488
|
| 87427 |
+
},
|
| 87428 |
+
{
|
| 87429 |
+
"epoch": 14.224501424501424,
|
| 87430 |
+
"grad_norm": 0.2542872726917267,
|
| 87431 |
+
"learning_rate": 1.0361588690816072e-05,
|
| 87432 |
+
"loss": 0.3758,
|
| 87433 |
+
"step": 12489
|
| 87434 |
+
},
|
| 87435 |
+
{
|
| 87436 |
+
"epoch": 14.225641025641025,
|
| 87437 |
+
"grad_norm": 0.17217014729976654,
|
| 87438 |
+
"learning_rate": 1.035781199814522e-05,
|
| 87439 |
+
"loss": 0.8552,
|
| 87440 |
+
"step": 12490
|
| 87441 |
+
},
|
| 87442 |
+
{
|
| 87443 |
+
"epoch": 14.226780626780627,
|
| 87444 |
+
"grad_norm": 0.19940514862537384,
|
| 87445 |
+
"learning_rate": 1.0354035814037824e-05,
|
| 87446 |
+
"loss": 0.755,
|
| 87447 |
+
"step": 12491
|
| 87448 |
+
},
|
| 87449 |
+
{
|
| 87450 |
+
"epoch": 14.227920227920228,
|
| 87451 |
+
"grad_norm": 0.1901174634695053,
|
| 87452 |
+
"learning_rate": 1.035026013862504e-05,
|
| 87453 |
+
"loss": 0.8924,
|
| 87454 |
+
"step": 12492
|
| 87455 |
+
},
|
| 87456 |
+
{
|
| 87457 |
+
"epoch": 14.229059829059828,
|
| 87458 |
+
"grad_norm": 0.18908625841140747,
|
| 87459 |
+
"learning_rate": 1.034648497203802e-05,
|
| 87460 |
+
"loss": 0.7233,
|
| 87461 |
+
"step": 12493
|
| 87462 |
+
},
|
| 87463 |
+
{
|
| 87464 |
+
"epoch": 14.23019943019943,
|
| 87465 |
+
"grad_norm": 0.21587686240673065,
|
| 87466 |
+
"learning_rate": 1.034271031440786e-05,
|
| 87467 |
+
"loss": 0.5469,
|
| 87468 |
+
"step": 12494
|
| 87469 |
+
},
|
| 87470 |
+
{
|
| 87471 |
+
"epoch": 14.231339031339031,
|
| 87472 |
+
"grad_norm": 0.21032138168811798,
|
| 87473 |
+
"learning_rate": 1.0338936165865684e-05,
|
| 87474 |
+
"loss": 0.7043,
|
| 87475 |
+
"step": 12495
|
| 87476 |
+
},
|
| 87477 |
+
{
|
| 87478 |
+
"epoch": 14.232478632478632,
|
| 87479 |
+
"grad_norm": 0.24204450845718384,
|
| 87480 |
+
"learning_rate": 1.0335162526542572e-05,
|
| 87481 |
+
"loss": 0.4976,
|
| 87482 |
+
"step": 12496
|
| 87483 |
+
},
|
| 87484 |
+
{
|
| 87485 |
+
"epoch": 14.233618233618234,
|
| 87486 |
+
"grad_norm": 0.20440852642059326,
|
| 87487 |
+
"learning_rate": 1.0331389396569591e-05,
|
| 87488 |
+
"loss": 0.7422,
|
| 87489 |
+
"step": 12497
|
| 87490 |
+
},
|
| 87491 |
+
{
|
| 87492 |
+
"epoch": 14.234757834757835,
|
| 87493 |
+
"grad_norm": 0.20793507993221283,
|
| 87494 |
+
"learning_rate": 1.0327616776077798e-05,
|
| 87495 |
+
"loss": 0.4419,
|
| 87496 |
+
"step": 12498
|
| 87497 |
+
},
|
| 87498 |
+
{
|
| 87499 |
+
"epoch": 14.235897435897435,
|
| 87500 |
+
"grad_norm": 0.2090797871351242,
|
| 87501 |
+
"learning_rate": 1.032384466519822e-05,
|
| 87502 |
+
"loss": 0.6576,
|
| 87503 |
+
"step": 12499
|
| 87504 |
+
},
|
| 87505 |
+
{
|
| 87506 |
+
"epoch": 14.237037037037037,
|
| 87507 |
+
"grad_norm": 0.20034758746623993,
|
| 87508 |
+
"learning_rate": 1.0320073064061889e-05,
|
| 87509 |
+
"loss": 0.6086,
|
| 87510 |
+
"step": 12500
|
| 87511 |
+
},
|
| 87512 |
+
{
|
| 87513 |
+
"epoch": 14.238176638176638,
|
| 87514 |
+
"grad_norm": 0.2248711735010147,
|
| 87515 |
+
"learning_rate": 1.031630197279978e-05,
|
| 87516 |
+
"loss": 0.5257,
|
| 87517 |
+
"step": 12501
|
| 87518 |
+
},
|
| 87519 |
+
{
|
| 87520 |
+
"epoch": 14.239316239316238,
|
| 87521 |
+
"grad_norm": 0.23908962309360504,
|
| 87522 |
+
"learning_rate": 1.0312531391542884e-05,
|
| 87523 |
+
"loss": 0.6444,
|
| 87524 |
+
"step": 12502
|
| 87525 |
+
},
|
| 87526 |
+
{
|
| 87527 |
+
"epoch": 14.24045584045584,
|
| 87528 |
+
"grad_norm": 0.1608385592699051,
|
| 87529 |
+
"learning_rate": 1.0308761320422164e-05,
|
| 87530 |
+
"loss": 0.8326,
|
| 87531 |
+
"step": 12503
|
| 87532 |
+
},
|
| 87533 |
+
{
|
| 87534 |
+
"epoch": 14.241595441595441,
|
| 87535 |
+
"grad_norm": 0.23936578631401062,
|
| 87536 |
+
"learning_rate": 1.0304991759568572e-05,
|
| 87537 |
+
"loss": 0.5167,
|
| 87538 |
+
"step": 12504
|
| 87539 |
+
},
|
| 87540 |
+
{
|
| 87541 |
+
"epoch": 14.242735042735042,
|
| 87542 |
+
"grad_norm": 0.21087776124477386,
|
| 87543 |
+
"learning_rate": 1.0301222709113018e-05,
|
| 87544 |
+
"loss": 0.6822,
|
| 87545 |
+
"step": 12505
|
| 87546 |
+
},
|
| 87547 |
+
{
|
| 87548 |
+
"epoch": 14.243874643874644,
|
| 87549 |
+
"grad_norm": 0.18673694133758545,
|
| 87550 |
+
"learning_rate": 1.0297454169186424e-05,
|
| 87551 |
+
"loss": 0.7186,
|
| 87552 |
+
"step": 12506
|
| 87553 |
+
},
|
| 87554 |
+
{
|
| 87555 |
+
"epoch": 14.245014245014245,
|
| 87556 |
+
"grad_norm": 0.1787559539079666,
|
| 87557 |
+
"learning_rate": 1.0293686139919676e-05,
|
| 87558 |
+
"loss": 0.6647,
|
| 87559 |
+
"step": 12507
|
| 87560 |
+
},
|
| 87561 |
+
{
|
| 87562 |
+
"epoch": 14.246153846153845,
|
| 87563 |
+
"grad_norm": 0.18746985495090485,
|
| 87564 |
+
"learning_rate": 1.0289918621443654e-05,
|
| 87565 |
+
"loss": 0.6668,
|
| 87566 |
+
"step": 12508
|
| 87567 |
+
},
|
| 87568 |
+
{
|
| 87569 |
+
"epoch": 14.247293447293448,
|
| 87570 |
+
"grad_norm": 0.23913775384426117,
|
| 87571 |
+
"learning_rate": 1.0286151613889208e-05,
|
| 87572 |
+
"loss": 0.6226,
|
| 87573 |
+
"step": 12509
|
| 87574 |
+
},
|
| 87575 |
+
{
|
| 87576 |
+
"epoch": 14.248433048433048,
|
| 87577 |
+
"grad_norm": 0.264639675617218,
|
| 87578 |
+
"learning_rate": 1.028238511738718e-05,
|
| 87579 |
+
"loss": 0.5012,
|
| 87580 |
+
"step": 12510
|
| 87581 |
+
},
|
| 87582 |
+
{
|
| 87583 |
+
"epoch": 14.249572649572649,
|
| 87584 |
+
"grad_norm": 0.21155546605587006,
|
| 87585 |
+
"learning_rate": 1.0278619132068402e-05,
|
| 87586 |
+
"loss": 0.6076,
|
| 87587 |
+
"step": 12511
|
| 87588 |
+
},
|
| 87589 |
+
{
|
| 87590 |
+
"epoch": 14.250712250712251,
|
| 87591 |
+
"grad_norm": 0.17297117412090302,
|
| 87592 |
+
"learning_rate": 1.0274853658063654e-05,
|
| 87593 |
+
"loss": 0.7893,
|
| 87594 |
+
"step": 12512
|
| 87595 |
+
},
|
| 87596 |
+
{
|
| 87597 |
+
"epoch": 14.251851851851852,
|
| 87598 |
+
"grad_norm": 0.2185525894165039,
|
| 87599 |
+
"learning_rate": 1.0271088695503733e-05,
|
| 87600 |
+
"loss": 0.6084,
|
| 87601 |
+
"step": 12513
|
| 87602 |
+
},
|
| 87603 |
+
{
|
| 87604 |
+
"epoch": 14.252991452991452,
|
| 87605 |
+
"grad_norm": 0.17372500896453857,
|
| 87606 |
+
"learning_rate": 1.0267324244519408e-05,
|
| 87607 |
+
"loss": 0.6831,
|
| 87608 |
+
"step": 12514
|
| 87609 |
+
},
|
| 87610 |
+
{
|
| 87611 |
+
"epoch": 14.254131054131054,
|
| 87612 |
+
"grad_norm": 0.17546038329601288,
|
| 87613 |
+
"learning_rate": 1.0263560305241435e-05,
|
| 87614 |
+
"loss": 0.6158,
|
| 87615 |
+
"step": 12515
|
| 87616 |
+
},
|
| 87617 |
+
{
|
| 87618 |
+
"epoch": 14.255270655270655,
|
| 87619 |
+
"grad_norm": 0.18271692097187042,
|
| 87620 |
+
"learning_rate": 1.0259796877800528e-05,
|
| 87621 |
+
"loss": 0.852,
|
| 87622 |
+
"step": 12516
|
| 87623 |
+
},
|
| 87624 |
+
{
|
| 87625 |
+
"epoch": 14.256410256410255,
|
| 87626 |
+
"grad_norm": 0.2003297060728073,
|
| 87627 |
+
"learning_rate": 1.0256033962327413e-05,
|
| 87628 |
+
"loss": 0.5634,
|
| 87629 |
+
"step": 12517
|
| 87630 |
+
},
|
| 87631 |
+
{
|
| 87632 |
+
"epoch": 14.257549857549858,
|
| 87633 |
+
"grad_norm": 0.5301342606544495,
|
| 87634 |
+
"learning_rate": 1.0252271558952784e-05,
|
| 87635 |
+
"loss": 0.6528,
|
| 87636 |
+
"step": 12518
|
| 87637 |
+
},
|
| 87638 |
+
{
|
| 87639 |
+
"epoch": 14.258689458689458,
|
| 87640 |
+
"grad_norm": 0.19460567831993103,
|
| 87641 |
+
"learning_rate": 1.0248509667807321e-05,
|
| 87642 |
+
"loss": 0.7132,
|
| 87643 |
+
"step": 12519
|
| 87644 |
+
},
|
| 87645 |
+
{
|
| 87646 |
+
"epoch": 14.25982905982906,
|
| 87647 |
+
"grad_norm": 0.20641255378723145,
|
| 87648 |
+
"learning_rate": 1.0244748289021682e-05,
|
| 87649 |
+
"loss": 0.6365,
|
| 87650 |
+
"step": 12520
|
| 87651 |
+
},
|
| 87652 |
+
{
|
| 87653 |
+
"epoch": 14.260968660968661,
|
| 87654 |
+
"grad_norm": 0.22458617389202118,
|
| 87655 |
+
"learning_rate": 1.0240987422726514e-05,
|
| 87656 |
+
"loss": 0.6479,
|
| 87657 |
+
"step": 12521
|
| 87658 |
+
},
|
| 87659 |
+
{
|
| 87660 |
+
"epoch": 14.262108262108262,
|
| 87661 |
+
"grad_norm": 0.19180619716644287,
|
| 87662 |
+
"learning_rate": 1.0237227069052438e-05,
|
| 87663 |
+
"loss": 0.783,
|
| 87664 |
+
"step": 12522
|
| 87665 |
+
},
|
| 87666 |
+
{
|
| 87667 |
+
"epoch": 14.263247863247864,
|
| 87668 |
+
"grad_norm": 0.2833923399448395,
|
| 87669 |
+
"learning_rate": 1.0233467228130072e-05,
|
| 87670 |
+
"loss": 0.5121,
|
| 87671 |
+
"step": 12523
|
| 87672 |
+
},
|
| 87673 |
+
{
|
| 87674 |
+
"epoch": 14.264387464387465,
|
| 87675 |
+
"grad_norm": 0.21777388453483582,
|
| 87676 |
+
"learning_rate": 1.022970790008999e-05,
|
| 87677 |
+
"loss": 0.6168,
|
| 87678 |
+
"step": 12524
|
| 87679 |
+
},
|
| 87680 |
+
{
|
| 87681 |
+
"epoch": 14.265527065527065,
|
| 87682 |
+
"grad_norm": 0.21849891543388367,
|
| 87683 |
+
"learning_rate": 1.0225949085062773e-05,
|
| 87684 |
+
"loss": 0.5956,
|
| 87685 |
+
"step": 12525
|
| 87686 |
+
},
|
| 87687 |
+
{
|
| 87688 |
+
"epoch": 14.266666666666667,
|
| 87689 |
+
"grad_norm": 0.17699994146823883,
|
| 87690 |
+
"learning_rate": 1.0222190783178973e-05,
|
| 87691 |
+
"loss": 0.744,
|
| 87692 |
+
"step": 12526
|
| 87693 |
+
},
|
| 87694 |
+
{
|
| 87695 |
+
"epoch": 14.267806267806268,
|
| 87696 |
+
"grad_norm": 0.1658196747303009,
|
| 87697 |
+
"learning_rate": 1.0218432994569132e-05,
|
| 87698 |
+
"loss": 0.7725,
|
| 87699 |
+
"step": 12527
|
| 87700 |
+
},
|
| 87701 |
+
{
|
| 87702 |
+
"epoch": 14.268945868945869,
|
| 87703 |
+
"grad_norm": 0.21563325822353363,
|
| 87704 |
+
"learning_rate": 1.0214675719363756e-05,
|
| 87705 |
+
"loss": 0.8035,
|
| 87706 |
+
"step": 12528
|
| 87707 |
+
},
|
| 87708 |
+
{
|
| 87709 |
+
"epoch": 14.270085470085471,
|
| 87710 |
+
"grad_norm": 0.19161447882652283,
|
| 87711 |
+
"learning_rate": 1.021091895769335e-05,
|
| 87712 |
+
"loss": 0.7857,
|
| 87713 |
+
"step": 12529
|
| 87714 |
+
},
|
| 87715 |
+
{
|
| 87716 |
+
"epoch": 14.271225071225071,
|
| 87717 |
+
"grad_norm": 0.1977480798959732,
|
| 87718 |
+
"learning_rate": 1.02071627096884e-05,
|
| 87719 |
+
"loss": 0.775,
|
| 87720 |
+
"step": 12530
|
| 87721 |
+
},
|
| 87722 |
+
{
|
| 87723 |
+
"epoch": 14.272364672364672,
|
| 87724 |
+
"grad_norm": 0.23712819814682007,
|
| 87725 |
+
"learning_rate": 1.0203406975479369e-05,
|
| 87726 |
+
"loss": 0.6548,
|
| 87727 |
+
"step": 12531
|
| 87728 |
+
},
|
| 87729 |
+
{
|
| 87730 |
+
"epoch": 14.273504273504274,
|
| 87731 |
+
"grad_norm": 0.20612823963165283,
|
| 87732 |
+
"learning_rate": 1.0199651755196704e-05,
|
| 87733 |
+
"loss": 0.6778,
|
| 87734 |
+
"step": 12532
|
| 87735 |
+
},
|
| 87736 |
+
{
|
| 87737 |
+
"epoch": 14.274643874643875,
|
| 87738 |
+
"grad_norm": 0.1673448234796524,
|
| 87739 |
+
"learning_rate": 1.0195897048970837e-05,
|
| 87740 |
+
"loss": 0.9221,
|
| 87741 |
+
"step": 12533
|
| 87742 |
+
},
|
| 87743 |
+
{
|
| 87744 |
+
"epoch": 14.275783475783475,
|
| 87745 |
+
"grad_norm": 0.1959383487701416,
|
| 87746 |
+
"learning_rate": 1.0192142856932186e-05,
|
| 87747 |
+
"loss": 0.7079,
|
| 87748 |
+
"step": 12534
|
| 87749 |
+
},
|
| 87750 |
+
{
|
| 87751 |
+
"epoch": 14.276923076923078,
|
| 87752 |
+
"grad_norm": 0.23128730058670044,
|
| 87753 |
+
"learning_rate": 1.0188389179211122e-05,
|
| 87754 |
+
"loss": 0.3848,
|
| 87755 |
+
"step": 12535
|
| 87756 |
+
},
|
| 87757 |
+
{
|
| 87758 |
+
"epoch": 14.278062678062678,
|
| 87759 |
+
"grad_norm": 0.20712505280971527,
|
| 87760 |
+
"learning_rate": 1.0184636015938037e-05,
|
| 87761 |
+
"loss": 0.7334,
|
| 87762 |
+
"step": 12536
|
| 87763 |
+
},
|
| 87764 |
+
{
|
| 87765 |
+
"epoch": 14.279202279202279,
|
| 87766 |
+
"grad_norm": 0.18095332384109497,
|
| 87767 |
+
"learning_rate": 1.0180883367243285e-05,
|
| 87768 |
+
"loss": 0.7478,
|
| 87769 |
+
"step": 12537
|
| 87770 |
+
},
|
| 87771 |
+
{
|
| 87772 |
+
"epoch": 14.280341880341881,
|
| 87773 |
+
"grad_norm": 0.24853791296482086,
|
| 87774 |
+
"learning_rate": 1.0177131233257216e-05,
|
| 87775 |
+
"loss": 0.8098,
|
| 87776 |
+
"step": 12538
|
| 87777 |
+
},
|
| 87778 |
+
{
|
| 87779 |
+
"epoch": 14.281481481481482,
|
| 87780 |
+
"grad_norm": 0.17238964140415192,
|
| 87781 |
+
"learning_rate": 1.0173379614110134e-05,
|
| 87782 |
+
"loss": 0.7795,
|
| 87783 |
+
"step": 12539
|
| 87784 |
+
},
|
| 87785 |
+
{
|
| 87786 |
+
"epoch": 14.282621082621082,
|
| 87787 |
+
"grad_norm": 0.17710372805595398,
|
| 87788 |
+
"learning_rate": 1.016962850993235e-05,
|
| 87789 |
+
"loss": 0.807,
|
| 87790 |
+
"step": 12540
|
| 87791 |
+
},
|
| 87792 |
+
{
|
| 87793 |
+
"epoch": 14.283760683760685,
|
| 87794 |
+
"grad_norm": 0.19814150035381317,
|
| 87795 |
+
"learning_rate": 1.0165877920854153e-05,
|
| 87796 |
+
"loss": 0.8465,
|
| 87797 |
+
"step": 12541
|
| 87798 |
+
},
|
| 87799 |
+
{
|
| 87800 |
+
"epoch": 14.284900284900285,
|
| 87801 |
+
"grad_norm": 0.2516099214553833,
|
| 87802 |
+
"learning_rate": 1.016212784700581e-05,
|
| 87803 |
+
"loss": 0.7151,
|
| 87804 |
+
"step": 12542
|
| 87805 |
+
},
|
| 87806 |
+
{
|
| 87807 |
+
"epoch": 14.286039886039886,
|
| 87808 |
+
"grad_norm": 0.20676739513874054,
|
| 87809 |
+
"learning_rate": 1.0158378288517568e-05,
|
| 87810 |
+
"loss": 0.5998,
|
| 87811 |
+
"step": 12543
|
| 87812 |
+
},
|
| 87813 |
+
{
|
| 87814 |
+
"epoch": 14.287179487179488,
|
| 87815 |
+
"grad_norm": 0.22322627902030945,
|
| 87816 |
+
"learning_rate": 1.0154629245519664e-05,
|
| 87817 |
+
"loss": 0.6966,
|
| 87818 |
+
"step": 12544
|
| 87819 |
+
},
|
| 87820 |
+
{
|
| 87821 |
+
"epoch": 14.288319088319088,
|
| 87822 |
+
"grad_norm": 0.2299807369709015,
|
| 87823 |
+
"learning_rate": 1.0150880718142322e-05,
|
| 87824 |
+
"loss": 0.6949,
|
| 87825 |
+
"step": 12545
|
| 87826 |
+
},
|
| 87827 |
+
{
|
| 87828 |
+
"epoch": 14.289458689458689,
|
| 87829 |
+
"grad_norm": 0.2129308134317398,
|
| 87830 |
+
"learning_rate": 1.0147132706515717e-05,
|
| 87831 |
+
"loss": 0.5363,
|
| 87832 |
+
"step": 12546
|
| 87833 |
+
},
|
| 87834 |
+
{
|
| 87835 |
+
"epoch": 14.290598290598291,
|
| 87836 |
+
"grad_norm": 0.22439347207546234,
|
| 87837 |
+
"learning_rate": 1.014338521077004e-05,
|
| 87838 |
+
"loss": 0.4882,
|
| 87839 |
+
"step": 12547
|
| 87840 |
+
},
|
| 87841 |
+
{
|
| 87842 |
+
"epoch": 14.291737891737892,
|
| 87843 |
+
"grad_norm": 0.19620387256145477,
|
| 87844 |
+
"learning_rate": 1.013963823103545e-05,
|
| 87845 |
+
"loss": 0.4752,
|
| 87846 |
+
"step": 12548
|
| 87847 |
+
},
|
| 87848 |
+
{
|
| 87849 |
+
"epoch": 14.292877492877492,
|
| 87850 |
+
"grad_norm": 0.20802806317806244,
|
| 87851 |
+
"learning_rate": 1.0135891767442099e-05,
|
| 87852 |
+
"loss": 0.7296,
|
| 87853 |
+
"step": 12549
|
| 87854 |
+
},
|
| 87855 |
+
{
|
| 87856 |
+
"epoch": 14.294017094017095,
|
| 87857 |
+
"grad_norm": 0.18960729241371155,
|
| 87858 |
+
"learning_rate": 1.0132145820120095e-05,
|
| 87859 |
+
"loss": 0.6289,
|
| 87860 |
+
"step": 12550
|
| 87861 |
+
},
|
| 87862 |
+
{
|
| 87863 |
+
"epoch": 14.295156695156695,
|
| 87864 |
+
"grad_norm": 0.24108396470546722,
|
| 87865 |
+
"learning_rate": 1.0128400389199552e-05,
|
| 87866 |
+
"loss": 0.5268,
|
| 87867 |
+
"step": 12551
|
| 87868 |
+
},
|
| 87869 |
+
{
|
| 87870 |
+
"epoch": 14.296296296296296,
|
| 87871 |
+
"grad_norm": 0.2624680995941162,
|
| 87872 |
+
"learning_rate": 1.0124655474810563e-05,
|
| 87873 |
+
"loss": 0.6078,
|
| 87874 |
+
"step": 12552
|
| 87875 |
+
},
|
| 87876 |
+
{
|
| 87877 |
+
"epoch": 14.297435897435898,
|
| 87878 |
+
"grad_norm": 0.24978230893611908,
|
| 87879 |
+
"learning_rate": 1.0120911077083195e-05,
|
| 87880 |
+
"loss": 0.5362,
|
| 87881 |
+
"step": 12553
|
| 87882 |
+
},
|
| 87883 |
+
{
|
| 87884 |
+
"epoch": 14.298575498575499,
|
| 87885 |
+
"grad_norm": 0.23368790745735168,
|
| 87886 |
+
"learning_rate": 1.0117167196147503e-05,
|
| 87887 |
+
"loss": 0.4848,
|
| 87888 |
+
"step": 12554
|
| 87889 |
+
},
|
| 87890 |
+
{
|
| 87891 |
+
"epoch": 14.2997150997151,
|
| 87892 |
+
"grad_norm": 0.2671913504600525,
|
| 87893 |
+
"learning_rate": 1.0113423832133523e-05,
|
| 87894 |
+
"loss": 0.6892,
|
| 87895 |
+
"step": 12555
|
| 87896 |
+
},
|
| 87897 |
+
{
|
| 87898 |
+
"epoch": 14.300854700854702,
|
| 87899 |
+
"grad_norm": 0.17675843834877014,
|
| 87900 |
+
"learning_rate": 1.0109680985171269e-05,
|
| 87901 |
+
"loss": 0.7545,
|
| 87902 |
+
"step": 12556
|
| 87903 |
+
},
|
| 87904 |
+
{
|
| 87905 |
+
"epoch": 14.301994301994302,
|
| 87906 |
+
"grad_norm": 0.2433677464723587,
|
| 87907 |
+
"learning_rate": 1.0105938655390753e-05,
|
| 87908 |
+
"loss": 0.6221,
|
| 87909 |
+
"step": 12557
|
| 87910 |
+
},
|
| 87911 |
+
{
|
| 87912 |
+
"epoch": 14.303133903133903,
|
| 87913 |
+
"grad_norm": 0.20102357864379883,
|
| 87914 |
+
"learning_rate": 1.0102196842921941e-05,
|
| 87915 |
+
"loss": 0.461,
|
| 87916 |
+
"step": 12558
|
| 87917 |
+
},
|
| 87918 |
+
{
|
| 87919 |
+
"epoch": 14.304273504273505,
|
| 87920 |
+
"grad_norm": 0.21794714033603668,
|
| 87921 |
+
"learning_rate": 1.0098455547894797e-05,
|
| 87922 |
+
"loss": 0.5659,
|
| 87923 |
+
"step": 12559
|
| 87924 |
+
},
|
| 87925 |
+
{
|
| 87926 |
+
"epoch": 14.305413105413106,
|
| 87927 |
+
"grad_norm": 0.2754895091056824,
|
| 87928 |
+
"learning_rate": 1.0094714770439273e-05,
|
| 87929 |
+
"loss": 0.3729,
|
| 87930 |
+
"step": 12560
|
| 87931 |
+
},
|
| 87932 |
+
{
|
| 87933 |
+
"epoch": 14.306552706552706,
|
| 87934 |
+
"grad_norm": 0.2294369786977768,
|
| 87935 |
+
"learning_rate": 1.0090974510685306e-05,
|
| 87936 |
+
"loss": 0.6324,
|
| 87937 |
+
"step": 12561
|
| 87938 |
+
},
|
| 87939 |
+
{
|
| 87940 |
+
"epoch": 14.307692307692308,
|
| 87941 |
+
"grad_norm": 0.20590168237686157,
|
| 87942 |
+
"learning_rate": 1.0087234768762782e-05,
|
| 87943 |
+
"loss": 0.6657,
|
| 87944 |
+
"step": 12562
|
| 87945 |
+
},
|
| 87946 |
+
{
|
| 87947 |
+
"epoch": 14.308831908831909,
|
| 87948 |
+
"grad_norm": 0.21124283969402313,
|
| 87949 |
+
"learning_rate": 1.0083495544801597e-05,
|
| 87950 |
+
"loss": 0.6746,
|
| 87951 |
+
"step": 12563
|
| 87952 |
+
},
|
| 87953 |
+
{
|
| 87954 |
+
"epoch": 14.30997150997151,
|
| 87955 |
+
"grad_norm": 0.1777198761701584,
|
| 87956 |
+
"learning_rate": 1.007975683893165e-05,
|
| 87957 |
+
"loss": 0.7074,
|
| 87958 |
+
"step": 12564
|
| 87959 |
+
},
|
| 87960 |
+
{
|
| 87961 |
+
"epoch": 14.311111111111112,
|
| 87962 |
+
"grad_norm": 0.20538261532783508,
|
| 87963 |
+
"learning_rate": 1.007601865128277e-05,
|
| 87964 |
+
"loss": 0.7295,
|
| 87965 |
+
"step": 12565
|
| 87966 |
+
},
|
| 87967 |
+
{
|
| 87968 |
+
"epoch": 14.312250712250712,
|
| 87969 |
+
"grad_norm": 0.18561547994613647,
|
| 87970 |
+
"learning_rate": 1.0072280981984802e-05,
|
| 87971 |
+
"loss": 0.7966,
|
| 87972 |
+
"step": 12566
|
| 87973 |
+
},
|
| 87974 |
+
{
|
| 87975 |
+
"epoch": 14.313390313390313,
|
| 87976 |
+
"grad_norm": 0.17395226657390594,
|
| 87977 |
+
"learning_rate": 1.006854383116757e-05,
|
| 87978 |
+
"loss": 0.9315,
|
| 87979 |
+
"step": 12567
|
| 87980 |
+
},
|
| 87981 |
+
{
|
| 87982 |
+
"epoch": 14.314529914529915,
|
| 87983 |
+
"grad_norm": 0.20632939040660858,
|
| 87984 |
+
"learning_rate": 1.006480719896088e-05,
|
| 87985 |
+
"loss": 0.6052,
|
| 87986 |
+
"step": 12568
|
| 87987 |
+
},
|
| 87988 |
+
{
|
| 87989 |
+
"epoch": 14.315669515669516,
|
| 87990 |
+
"grad_norm": 0.14955343306064606,
|
| 87991 |
+
"learning_rate": 1.0061071085494498e-05,
|
| 87992 |
+
"loss": 0.5612,
|
| 87993 |
+
"step": 12569
|
| 87994 |
+
},
|
| 87995 |
+
{
|
| 87996 |
+
"epoch": 14.316809116809116,
|
| 87997 |
+
"grad_norm": 0.2069385051727295,
|
| 87998 |
+
"learning_rate": 1.00573354908982e-05,
|
| 87999 |
+
"loss": 0.5874,
|
| 88000 |
+
"step": 12570
|
| 88001 |
+
},
|
| 88002 |
+
{
|
| 88003 |
+
"epoch": 14.317948717948719,
|
| 88004 |
+
"grad_norm": 0.17582623660564423,
|
| 88005 |
+
"learning_rate": 1.0053600415301734e-05,
|
| 88006 |
+
"loss": 0.7139,
|
| 88007 |
+
"step": 12571
|
| 88008 |
+
},
|
| 88009 |
+
{
|
| 88010 |
+
"epoch": 14.31908831908832,
|
| 88011 |
+
"grad_norm": 0.1767067313194275,
|
| 88012 |
+
"learning_rate": 1.0049865858834835e-05,
|
| 88013 |
+
"loss": 0.8682,
|
| 88014 |
+
"step": 12572
|
| 88015 |
+
},
|
| 88016 |
+
{
|
| 88017 |
+
"epoch": 14.32022792022792,
|
| 88018 |
+
"grad_norm": 0.1552984118461609,
|
| 88019 |
+
"learning_rate": 1.00461318216272e-05,
|
| 88020 |
+
"loss": 0.8311,
|
| 88021 |
+
"step": 12573
|
| 88022 |
+
},
|
| 88023 |
+
{
|
| 88024 |
+
"epoch": 14.321367521367522,
|
| 88025 |
+
"grad_norm": 0.20522622764110565,
|
| 88026 |
+
"learning_rate": 1.004239830380852e-05,
|
| 88027 |
+
"loss": 0.5753,
|
| 88028 |
+
"step": 12574
|
| 88029 |
+
},
|
| 88030 |
+
{
|
| 88031 |
+
"epoch": 14.322507122507123,
|
| 88032 |
+
"grad_norm": 0.20223551988601685,
|
| 88033 |
+
"learning_rate": 1.00386653055085e-05,
|
| 88034 |
+
"loss": 0.7066,
|
| 88035 |
+
"step": 12575
|
| 88036 |
+
},
|
| 88037 |
+
{
|
| 88038 |
+
"epoch": 14.323646723646723,
|
| 88039 |
+
"grad_norm": 0.1999504119157791,
|
| 88040 |
+
"learning_rate": 1.0034932826856768e-05,
|
| 88041 |
+
"loss": 0.7068,
|
| 88042 |
+
"step": 12576
|
| 88043 |
+
},
|
| 88044 |
+
{
|
| 88045 |
+
"epoch": 14.324786324786325,
|
| 88046 |
+
"grad_norm": 0.2503112554550171,
|
| 88047 |
+
"learning_rate": 1.0031200867982974e-05,
|
| 88048 |
+
"loss": 0.7009,
|
| 88049 |
+
"step": 12577
|
| 88050 |
+
},
|
| 88051 |
+
{
|
| 88052 |
+
"epoch": 14.325925925925926,
|
| 88053 |
+
"grad_norm": 0.18654067814350128,
|
| 88054 |
+
"learning_rate": 1.0027469429016737e-05,
|
| 88055 |
+
"loss": 0.7889,
|
| 88056 |
+
"step": 12578
|
| 88057 |
+
},
|
| 88058 |
+
{
|
| 88059 |
+
"epoch": 14.327065527065526,
|
| 88060 |
+
"grad_norm": 0.17514781653881073,
|
| 88061 |
+
"learning_rate": 1.0023738510087672e-05,
|
| 88062 |
+
"loss": 0.9534,
|
| 88063 |
+
"step": 12579
|
| 88064 |
+
},
|
| 88065 |
+
{
|
| 88066 |
+
"epoch": 14.328205128205129,
|
| 88067 |
+
"grad_norm": 0.18068872392177582,
|
| 88068 |
+
"learning_rate": 1.0020008111325343e-05,
|
| 88069 |
+
"loss": 0.5792,
|
| 88070 |
+
"step": 12580
|
| 88071 |
+
},
|
| 88072 |
+
{
|
| 88073 |
+
"epoch": 14.32934472934473,
|
| 88074 |
+
"grad_norm": 0.23751656711101532,
|
| 88075 |
+
"learning_rate": 1.0016278232859328e-05,
|
| 88076 |
+
"loss": 0.5473,
|
| 88077 |
+
"step": 12581
|
| 88078 |
+
},
|
| 88079 |
+
{
|
| 88080 |
+
"epoch": 14.33048433048433,
|
| 88081 |
+
"grad_norm": 0.22508838772773743,
|
| 88082 |
+
"learning_rate": 1.0012548874819174e-05,
|
| 88083 |
+
"loss": 0.5833,
|
| 88084 |
+
"step": 12582
|
| 88085 |
+
},
|
| 88086 |
+
{
|
| 88087 |
+
"epoch": 14.331623931623932,
|
| 88088 |
+
"grad_norm": 0.28413140773773193,
|
| 88089 |
+
"learning_rate": 1.0008820037334423e-05,
|
| 88090 |
+
"loss": 0.4477,
|
| 88091 |
+
"step": 12583
|
| 88092 |
+
},
|
| 88093 |
+
{
|
| 88094 |
+
"epoch": 14.332763532763533,
|
| 88095 |
+
"grad_norm": 0.4132240116596222,
|
| 88096 |
+
"learning_rate": 1.000509172053457e-05,
|
| 88097 |
+
"loss": 0.6586,
|
| 88098 |
+
"step": 12584
|
| 88099 |
+
},
|
| 88100 |
+
{
|
| 88101 |
+
"epoch": 14.333903133903133,
|
| 88102 |
+
"grad_norm": 0.1827618032693863,
|
| 88103 |
+
"learning_rate": 1.0001363924549109e-05,
|
| 88104 |
+
"loss": 0.5916,
|
| 88105 |
+
"step": 12585
|
| 88106 |
+
},
|
| 88107 |
+
{
|
| 88108 |
+
"epoch": 14.335042735042736,
|
| 88109 |
+
"grad_norm": 0.166161447763443,
|
| 88110 |
+
"learning_rate": 9.997636649507541e-06,
|
| 88111 |
+
"loss": 0.8675,
|
| 88112 |
+
"step": 12586
|
| 88113 |
+
},
|
| 88114 |
+
{
|
| 88115 |
+
"epoch": 14.336182336182336,
|
| 88116 |
+
"grad_norm": 0.23401637375354767,
|
| 88117 |
+
"learning_rate": 9.993909895539303e-06,
|
| 88118 |
+
"loss": 0.6625,
|
| 88119 |
+
"step": 12587
|
| 88120 |
+
},
|
| 88121 |
+
{
|
| 88122 |
+
"epoch": 14.337321937321937,
|
| 88123 |
+
"grad_norm": 0.18541036546230316,
|
| 88124 |
+
"learning_rate": 9.990183662773838e-06,
|
| 88125 |
+
"loss": 0.759,
|
| 88126 |
+
"step": 12588
|
| 88127 |
+
},
|
| 88128 |
+
{
|
| 88129 |
+
"epoch": 14.338461538461539,
|
| 88130 |
+
"grad_norm": 0.2001301795244217,
|
| 88131 |
+
"learning_rate": 9.986457951340571e-06,
|
| 88132 |
+
"loss": 0.6406,
|
| 88133 |
+
"step": 12589
|
| 88134 |
+
},
|
| 88135 |
+
{
|
| 88136 |
+
"epoch": 14.33960113960114,
|
| 88137 |
+
"grad_norm": 0.20283040404319763,
|
| 88138 |
+
"learning_rate": 9.982732761368918e-06,
|
| 88139 |
+
"loss": 0.8171,
|
| 88140 |
+
"step": 12590
|
| 88141 |
+
},
|
| 88142 |
+
{
|
| 88143 |
+
"epoch": 14.34074074074074,
|
| 88144 |
+
"grad_norm": 0.19369982182979584,
|
| 88145 |
+
"learning_rate": 9.979008092988245e-06,
|
| 88146 |
+
"loss": 0.5343,
|
| 88147 |
+
"step": 12591
|
| 88148 |
+
},
|
| 88149 |
+
{
|
| 88150 |
+
"epoch": 14.341880341880342,
|
| 88151 |
+
"grad_norm": 0.18374225497245789,
|
| 88152 |
+
"learning_rate": 9.975283946327929e-06,
|
| 88153 |
+
"loss": 0.6343,
|
| 88154 |
+
"step": 12592
|
| 88155 |
+
},
|
| 88156 |
+
{
|
| 88157 |
+
"epoch": 14.343019943019943,
|
| 88158 |
+
"grad_norm": 0.20221012830734253,
|
| 88159 |
+
"learning_rate": 9.97156032151732e-06,
|
| 88160 |
+
"loss": 0.5739,
|
| 88161 |
+
"step": 12593
|
| 88162 |
+
},
|
| 88163 |
+
{
|
| 88164 |
+
"epoch": 14.344159544159544,
|
| 88165 |
+
"grad_norm": 0.18787631392478943,
|
| 88166 |
+
"learning_rate": 9.967837218685758e-06,
|
| 88167 |
+
"loss": 0.4307,
|
| 88168 |
+
"step": 12594
|
| 88169 |
+
},
|
| 88170 |
+
{
|
| 88171 |
+
"epoch": 14.345299145299146,
|
| 88172 |
+
"grad_norm": 0.2108217030763626,
|
| 88173 |
+
"learning_rate": 9.964114637962537e-06,
|
| 88174 |
+
"loss": 0.8173,
|
| 88175 |
+
"step": 12595
|
| 88176 |
+
},
|
| 88177 |
+
{
|
| 88178 |
+
"epoch": 14.346438746438746,
|
| 88179 |
+
"grad_norm": 0.19228532910346985,
|
| 88180 |
+
"learning_rate": 9.960392579476957e-06,
|
| 88181 |
+
"loss": 0.7508,
|
| 88182 |
+
"step": 12596
|
| 88183 |
+
},
|
| 88184 |
+
{
|
| 88185 |
+
"epoch": 14.347578347578347,
|
| 88186 |
+
"grad_norm": 0.19072678685188293,
|
| 88187 |
+
"learning_rate": 9.95667104335831e-06,
|
| 88188 |
+
"loss": 0.7076,
|
| 88189 |
+
"step": 12597
|
| 88190 |
+
},
|
| 88191 |
+
{
|
| 88192 |
+
"epoch": 14.34871794871795,
|
| 88193 |
+
"grad_norm": 0.25872674584388733,
|
| 88194 |
+
"learning_rate": 9.952950029735855e-06,
|
| 88195 |
+
"loss": 0.6042,
|
| 88196 |
+
"step": 12598
|
| 88197 |
+
},
|
| 88198 |
+
{
|
| 88199 |
+
"epoch": 14.34985754985755,
|
| 88200 |
+
"grad_norm": 0.17833420634269714,
|
| 88201 |
+
"learning_rate": 9.949229538738817e-06,
|
| 88202 |
+
"loss": 0.7411,
|
| 88203 |
+
"step": 12599
|
| 88204 |
+
},
|
| 88205 |
+
{
|
| 88206 |
+
"epoch": 14.35099715099715,
|
| 88207 |
+
"grad_norm": 0.18916936218738556,
|
| 88208 |
+
"learning_rate": 9.945509570496425e-06,
|
| 88209 |
+
"loss": 0.8745,
|
| 88210 |
+
"step": 12600
|
| 88211 |
}
|
| 88212 |
],
|
| 88213 |
"logging_steps": 1,
|
|
|
|
| 88227 |
"attributes": {}
|
| 88228 |
}
|
| 88229 |
},
|
| 88230 |
+
"total_flos": 7.044918660072161e+19,
|
| 88231 |
"train_batch_size": 8,
|
| 88232 |
"trial_name": null,
|
| 88233 |
"trial_params": null
|