Instructions to use shareit/chatbot-supervisor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shareit/chatbot-supervisor with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shareit/chatbot-supervisor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Training in progress, step 3300, 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 sha256:1c3017063904676f209d101d20c758d2e5f4c1824b93ca04d6ea11d26879bcc0
|
| 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:e9f92620fd7619417f615ad4da596960b71c37913cf076756cae69f8a55244a9
|
| 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 sha256:5ad42b3d0771e80b8c0644458a69408da8974e695653969b398fa4fe480cae16
|
| 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": 3.
|
| 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,
|
|
@@ -21008,6 +21008,2106 @@
|
|
| 21008 |
"learning_rate": 4.774598768572377e-05,
|
| 21009 |
"loss": 0.8015,
|
| 21010 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21011 |
}
|
| 21012 |
],
|
| 21013 |
"logging_steps": 1,
|
|
@@ -21027,7 +23127,7 @@
|
|
| 21027 |
"attributes": {}
|
| 21028 |
}
|
| 21029 |
},
|
| 21030 |
-
"total_flos": 1.
|
| 21031 |
"train_batch_size": 8,
|
| 21032 |
"trial_name": null,
|
| 21033 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.758974358974359,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 21008 |
"learning_rate": 4.774598768572377e-05,
|
| 21009 |
"loss": 0.8015,
|
| 21010 |
"step": 3000
|
| 21011 |
+
},
|
| 21012 |
+
{
|
| 21013 |
+
"epoch": 3.4182336182336184,
|
| 21014 |
+
"grad_norm": 0.14148254692554474,
|
| 21015 |
+
"learning_rate": 4.774405391540628e-05,
|
| 21016 |
+
"loss": 0.7828,
|
| 21017 |
+
"step": 3001
|
| 21018 |
+
},
|
| 21019 |
+
{
|
| 21020 |
+
"epoch": 3.4193732193732194,
|
| 21021 |
+
"grad_norm": 0.19590474665164948,
|
| 21022 |
+
"learning_rate": 4.774211935512526e-05,
|
| 21023 |
+
"loss": 0.5977,
|
| 21024 |
+
"step": 3002
|
| 21025 |
+
},
|
| 21026 |
+
{
|
| 21027 |
+
"epoch": 3.4205128205128204,
|
| 21028 |
+
"grad_norm": 0.16398891806602478,
|
| 21029 |
+
"learning_rate": 4.774018400494788e-05,
|
| 21030 |
+
"loss": 0.87,
|
| 21031 |
+
"step": 3003
|
| 21032 |
+
},
|
| 21033 |
+
{
|
| 21034 |
+
"epoch": 3.421652421652422,
|
| 21035 |
+
"grad_norm": 0.1326790750026703,
|
| 21036 |
+
"learning_rate": 4.773824786494139e-05,
|
| 21037 |
+
"loss": 0.903,
|
| 21038 |
+
"step": 3004
|
| 21039 |
+
},
|
| 21040 |
+
{
|
| 21041 |
+
"epoch": 3.4227920227920228,
|
| 21042 |
+
"grad_norm": 0.1271533966064453,
|
| 21043 |
+
"learning_rate": 4.7736310935173013e-05,
|
| 21044 |
+
"loss": 0.8567,
|
| 21045 |
+
"step": 3005
|
| 21046 |
+
},
|
| 21047 |
+
{
|
| 21048 |
+
"epoch": 3.4239316239316238,
|
| 21049 |
+
"grad_norm": 0.17647764086723328,
|
| 21050 |
+
"learning_rate": 4.773437321571003e-05,
|
| 21051 |
+
"loss": 0.7339,
|
| 21052 |
+
"step": 3006
|
| 21053 |
+
},
|
| 21054 |
+
{
|
| 21055 |
+
"epoch": 3.425071225071225,
|
| 21056 |
+
"grad_norm": 0.1769576370716095,
|
| 21057 |
+
"learning_rate": 4.773243470661975e-05,
|
| 21058 |
+
"loss": 0.5728,
|
| 21059 |
+
"step": 3007
|
| 21060 |
+
},
|
| 21061 |
+
{
|
| 21062 |
+
"epoch": 3.426210826210826,
|
| 21063 |
+
"grad_norm": 0.12879271805286407,
|
| 21064 |
+
"learning_rate": 4.77304954079695e-05,
|
| 21065 |
+
"loss": 0.831,
|
| 21066 |
+
"step": 3008
|
| 21067 |
+
},
|
| 21068 |
+
{
|
| 21069 |
+
"epoch": 3.427350427350427,
|
| 21070 |
+
"grad_norm": 0.16009968519210815,
|
| 21071 |
+
"learning_rate": 4.772855531982663e-05,
|
| 21072 |
+
"loss": 0.7828,
|
| 21073 |
+
"step": 3009
|
| 21074 |
+
},
|
| 21075 |
+
{
|
| 21076 |
+
"epoch": 3.4284900284900286,
|
| 21077 |
+
"grad_norm": 0.14020909368991852,
|
| 21078 |
+
"learning_rate": 4.772661444225853e-05,
|
| 21079 |
+
"loss": 0.8271,
|
| 21080 |
+
"step": 3010
|
| 21081 |
+
},
|
| 21082 |
+
{
|
| 21083 |
+
"epoch": 3.4296296296296296,
|
| 21084 |
+
"grad_norm": 0.15442004799842834,
|
| 21085 |
+
"learning_rate": 4.7724672775332615e-05,
|
| 21086 |
+
"loss": 0.8451,
|
| 21087 |
+
"step": 3011
|
| 21088 |
+
},
|
| 21089 |
+
{
|
| 21090 |
+
"epoch": 3.430769230769231,
|
| 21091 |
+
"grad_norm": 0.16702589392662048,
|
| 21092 |
+
"learning_rate": 4.7722730319116314e-05,
|
| 21093 |
+
"loss": 0.8092,
|
| 21094 |
+
"step": 3012
|
| 21095 |
+
},
|
| 21096 |
+
{
|
| 21097 |
+
"epoch": 3.431908831908832,
|
| 21098 |
+
"grad_norm": 0.14913535118103027,
|
| 21099 |
+
"learning_rate": 4.772078707367711e-05,
|
| 21100 |
+
"loss": 0.726,
|
| 21101 |
+
"step": 3013
|
| 21102 |
+
},
|
| 21103 |
+
{
|
| 21104 |
+
"epoch": 3.433048433048433,
|
| 21105 |
+
"grad_norm": 0.1301717758178711,
|
| 21106 |
+
"learning_rate": 4.7718843039082485e-05,
|
| 21107 |
+
"loss": 1.0495,
|
| 21108 |
+
"step": 3014
|
| 21109 |
+
},
|
| 21110 |
+
{
|
| 21111 |
+
"epoch": 3.4341880341880344,
|
| 21112 |
+
"grad_norm": 0.15527473390102386,
|
| 21113 |
+
"learning_rate": 4.771689821539996e-05,
|
| 21114 |
+
"loss": 0.7916,
|
| 21115 |
+
"step": 3015
|
| 21116 |
+
},
|
| 21117 |
+
{
|
| 21118 |
+
"epoch": 3.4353276353276354,
|
| 21119 |
+
"grad_norm": 0.1384832262992859,
|
| 21120 |
+
"learning_rate": 4.771495260269709e-05,
|
| 21121 |
+
"loss": 1.0,
|
| 21122 |
+
"step": 3016
|
| 21123 |
+
},
|
| 21124 |
+
{
|
| 21125 |
+
"epoch": 3.4364672364672364,
|
| 21126 |
+
"grad_norm": 0.1275806427001953,
|
| 21127 |
+
"learning_rate": 4.771300620104146e-05,
|
| 21128 |
+
"loss": 0.9059,
|
| 21129 |
+
"step": 3017
|
| 21130 |
+
},
|
| 21131 |
+
{
|
| 21132 |
+
"epoch": 3.437606837606838,
|
| 21133 |
+
"grad_norm": 0.13449861109256744,
|
| 21134 |
+
"learning_rate": 4.771105901050066e-05,
|
| 21135 |
+
"loss": 0.9651,
|
| 21136 |
+
"step": 3018
|
| 21137 |
+
},
|
| 21138 |
+
{
|
| 21139 |
+
"epoch": 3.438746438746439,
|
| 21140 |
+
"grad_norm": 0.14235353469848633,
|
| 21141 |
+
"learning_rate": 4.7709111031142315e-05,
|
| 21142 |
+
"loss": 1.0003,
|
| 21143 |
+
"step": 3019
|
| 21144 |
+
},
|
| 21145 |
+
{
|
| 21146 |
+
"epoch": 3.43988603988604,
|
| 21147 |
+
"grad_norm": 0.15162557363510132,
|
| 21148 |
+
"learning_rate": 4.77071622630341e-05,
|
| 21149 |
+
"loss": 0.8483,
|
| 21150 |
+
"step": 3020
|
| 21151 |
+
},
|
| 21152 |
+
{
|
| 21153 |
+
"epoch": 3.4410256410256412,
|
| 21154 |
+
"grad_norm": 0.1523604840040207,
|
| 21155 |
+
"learning_rate": 4.7705212706243696e-05,
|
| 21156 |
+
"loss": 0.8053,
|
| 21157 |
+
"step": 3021
|
| 21158 |
+
},
|
| 21159 |
+
{
|
| 21160 |
+
"epoch": 3.4421652421652422,
|
| 21161 |
+
"grad_norm": 0.15889766812324524,
|
| 21162 |
+
"learning_rate": 4.770326236083881e-05,
|
| 21163 |
+
"loss": 0.6381,
|
| 21164 |
+
"step": 3022
|
| 21165 |
+
},
|
| 21166 |
+
{
|
| 21167 |
+
"epoch": 3.443304843304843,
|
| 21168 |
+
"grad_norm": 0.15443409979343414,
|
| 21169 |
+
"learning_rate": 4.7701311226887194e-05,
|
| 21170 |
+
"loss": 0.9534,
|
| 21171 |
+
"step": 3023
|
| 21172 |
+
},
|
| 21173 |
+
{
|
| 21174 |
+
"epoch": 3.4444444444444446,
|
| 21175 |
+
"grad_norm": 0.13383810222148895,
|
| 21176 |
+
"learning_rate": 4.769935930445661e-05,
|
| 21177 |
+
"loss": 0.9529,
|
| 21178 |
+
"step": 3024
|
| 21179 |
+
},
|
| 21180 |
+
{
|
| 21181 |
+
"epoch": 3.4455840455840456,
|
| 21182 |
+
"grad_norm": 0.15414220094680786,
|
| 21183 |
+
"learning_rate": 4.769740659361485e-05,
|
| 21184 |
+
"loss": 0.7851,
|
| 21185 |
+
"step": 3025
|
| 21186 |
+
},
|
| 21187 |
+
{
|
| 21188 |
+
"epoch": 3.4467236467236466,
|
| 21189 |
+
"grad_norm": 0.12543773651123047,
|
| 21190 |
+
"learning_rate": 4.769545309442974e-05,
|
| 21191 |
+
"loss": 0.9761,
|
| 21192 |
+
"step": 3026
|
| 21193 |
+
},
|
| 21194 |
+
{
|
| 21195 |
+
"epoch": 3.447863247863248,
|
| 21196 |
+
"grad_norm": 0.16195324063301086,
|
| 21197 |
+
"learning_rate": 4.769349880696914e-05,
|
| 21198 |
+
"loss": 0.832,
|
| 21199 |
+
"step": 3027
|
| 21200 |
+
},
|
| 21201 |
+
{
|
| 21202 |
+
"epoch": 3.449002849002849,
|
| 21203 |
+
"grad_norm": 0.14392708241939545,
|
| 21204 |
+
"learning_rate": 4.769154373130091e-05,
|
| 21205 |
+
"loss": 0.8292,
|
| 21206 |
+
"step": 3028
|
| 21207 |
+
},
|
| 21208 |
+
{
|
| 21209 |
+
"epoch": 3.45014245014245,
|
| 21210 |
+
"grad_norm": 0.14125484228134155,
|
| 21211 |
+
"learning_rate": 4.768958786749297e-05,
|
| 21212 |
+
"loss": 0.8413,
|
| 21213 |
+
"step": 3029
|
| 21214 |
+
},
|
| 21215 |
+
{
|
| 21216 |
+
"epoch": 3.4512820512820515,
|
| 21217 |
+
"grad_norm": 0.17190024256706238,
|
| 21218 |
+
"learning_rate": 4.768763121561324e-05,
|
| 21219 |
+
"loss": 0.7695,
|
| 21220 |
+
"step": 3030
|
| 21221 |
+
},
|
| 21222 |
+
{
|
| 21223 |
+
"epoch": 3.4524216524216524,
|
| 21224 |
+
"grad_norm": 0.1310916244983673,
|
| 21225 |
+
"learning_rate": 4.768567377572969e-05,
|
| 21226 |
+
"loss": 0.9733,
|
| 21227 |
+
"step": 3031
|
| 21228 |
+
},
|
| 21229 |
+
{
|
| 21230 |
+
"epoch": 3.4535612535612534,
|
| 21231 |
+
"grad_norm": 0.1735365092754364,
|
| 21232 |
+
"learning_rate": 4.768371554791031e-05,
|
| 21233 |
+
"loss": 0.8854,
|
| 21234 |
+
"step": 3032
|
| 21235 |
+
},
|
| 21236 |
+
{
|
| 21237 |
+
"epoch": 3.454700854700855,
|
| 21238 |
+
"grad_norm": 0.16494423151016235,
|
| 21239 |
+
"learning_rate": 4.76817565322231e-05,
|
| 21240 |
+
"loss": 0.8977,
|
| 21241 |
+
"step": 3033
|
| 21242 |
+
},
|
| 21243 |
+
{
|
| 21244 |
+
"epoch": 3.455840455840456,
|
| 21245 |
+
"grad_norm": 0.13473758101463318,
|
| 21246 |
+
"learning_rate": 4.7679796728736115e-05,
|
| 21247 |
+
"loss": 0.9667,
|
| 21248 |
+
"step": 3034
|
| 21249 |
+
},
|
| 21250 |
+
{
|
| 21251 |
+
"epoch": 3.456980056980057,
|
| 21252 |
+
"grad_norm": 0.16762381792068481,
|
| 21253 |
+
"learning_rate": 4.7677836137517416e-05,
|
| 21254 |
+
"loss": 0.8502,
|
| 21255 |
+
"step": 3035
|
| 21256 |
+
},
|
| 21257 |
+
{
|
| 21258 |
+
"epoch": 3.4581196581196583,
|
| 21259 |
+
"grad_norm": 0.15547460317611694,
|
| 21260 |
+
"learning_rate": 4.767587475863511e-05,
|
| 21261 |
+
"loss": 0.8049,
|
| 21262 |
+
"step": 3036
|
| 21263 |
+
},
|
| 21264 |
+
{
|
| 21265 |
+
"epoch": 3.4592592592592593,
|
| 21266 |
+
"grad_norm": 0.15720248222351074,
|
| 21267 |
+
"learning_rate": 4.767391259215731e-05,
|
| 21268 |
+
"loss": 0.7653,
|
| 21269 |
+
"step": 3037
|
| 21270 |
+
},
|
| 21271 |
+
{
|
| 21272 |
+
"epoch": 3.4603988603988602,
|
| 21273 |
+
"grad_norm": 0.15790072083473206,
|
| 21274 |
+
"learning_rate": 4.767194963815217e-05,
|
| 21275 |
+
"loss": 0.878,
|
| 21276 |
+
"step": 3038
|
| 21277 |
+
},
|
| 21278 |
+
{
|
| 21279 |
+
"epoch": 3.4615384615384617,
|
| 21280 |
+
"grad_norm": 0.14522385597229004,
|
| 21281 |
+
"learning_rate": 4.766998589668788e-05,
|
| 21282 |
+
"loss": 0.7098,
|
| 21283 |
+
"step": 3039
|
| 21284 |
+
},
|
| 21285 |
+
{
|
| 21286 |
+
"epoch": 3.4626780626780627,
|
| 21287 |
+
"grad_norm": 0.14111749827861786,
|
| 21288 |
+
"learning_rate": 4.7668021367832625e-05,
|
| 21289 |
+
"loss": 0.8254,
|
| 21290 |
+
"step": 3040
|
| 21291 |
+
},
|
| 21292 |
+
{
|
| 21293 |
+
"epoch": 3.4638176638176637,
|
| 21294 |
+
"grad_norm": 0.15024295449256897,
|
| 21295 |
+
"learning_rate": 4.7666056051654665e-05,
|
| 21296 |
+
"loss": 0.843,
|
| 21297 |
+
"step": 3041
|
| 21298 |
+
},
|
| 21299 |
+
{
|
| 21300 |
+
"epoch": 3.464957264957265,
|
| 21301 |
+
"grad_norm": 0.1455540657043457,
|
| 21302 |
+
"learning_rate": 4.766408994822223e-05,
|
| 21303 |
+
"loss": 0.764,
|
| 21304 |
+
"step": 3042
|
| 21305 |
+
},
|
| 21306 |
+
{
|
| 21307 |
+
"epoch": 3.466096866096866,
|
| 21308 |
+
"grad_norm": 0.20096252858638763,
|
| 21309 |
+
"learning_rate": 4.7662123057603636e-05,
|
| 21310 |
+
"loss": 0.6538,
|
| 21311 |
+
"step": 3043
|
| 21312 |
+
},
|
| 21313 |
+
{
|
| 21314 |
+
"epoch": 3.467236467236467,
|
| 21315 |
+
"grad_norm": 0.1540260910987854,
|
| 21316 |
+
"learning_rate": 4.7660155379867184e-05,
|
| 21317 |
+
"loss": 0.8088,
|
| 21318 |
+
"step": 3044
|
| 21319 |
+
},
|
| 21320 |
+
{
|
| 21321 |
+
"epoch": 3.4683760683760685,
|
| 21322 |
+
"grad_norm": 0.14348721504211426,
|
| 21323 |
+
"learning_rate": 4.7658186915081215e-05,
|
| 21324 |
+
"loss": 0.7288,
|
| 21325 |
+
"step": 3045
|
| 21326 |
+
},
|
| 21327 |
+
{
|
| 21328 |
+
"epoch": 3.4695156695156695,
|
| 21329 |
+
"grad_norm": 0.14723597466945648,
|
| 21330 |
+
"learning_rate": 4.765621766331411e-05,
|
| 21331 |
+
"loss": 0.8305,
|
| 21332 |
+
"step": 3046
|
| 21333 |
+
},
|
| 21334 |
+
{
|
| 21335 |
+
"epoch": 3.4706552706552705,
|
| 21336 |
+
"grad_norm": 0.15247543156147003,
|
| 21337 |
+
"learning_rate": 4.7654247624634266e-05,
|
| 21338 |
+
"loss": 0.6852,
|
| 21339 |
+
"step": 3047
|
| 21340 |
+
},
|
| 21341 |
+
{
|
| 21342 |
+
"epoch": 3.471794871794872,
|
| 21343 |
+
"grad_norm": 0.15918880701065063,
|
| 21344 |
+
"learning_rate": 4.765227679911009e-05,
|
| 21345 |
+
"loss": 0.7662,
|
| 21346 |
+
"step": 3048
|
| 21347 |
+
},
|
| 21348 |
+
{
|
| 21349 |
+
"epoch": 3.472934472934473,
|
| 21350 |
+
"grad_norm": 0.17041854560375214,
|
| 21351 |
+
"learning_rate": 4.7650305186810054e-05,
|
| 21352 |
+
"loss": 0.7827,
|
| 21353 |
+
"step": 3049
|
| 21354 |
+
},
|
| 21355 |
+
{
|
| 21356 |
+
"epoch": 3.474074074074074,
|
| 21357 |
+
"grad_norm": 0.1634455770254135,
|
| 21358 |
+
"learning_rate": 4.764833278780263e-05,
|
| 21359 |
+
"loss": 0.7868,
|
| 21360 |
+
"step": 3050
|
| 21361 |
+
},
|
| 21362 |
+
{
|
| 21363 |
+
"epoch": 3.4752136752136753,
|
| 21364 |
+
"grad_norm": 0.13534197211265564,
|
| 21365 |
+
"learning_rate": 4.764635960215632e-05,
|
| 21366 |
+
"loss": 1.0153,
|
| 21367 |
+
"step": 3051
|
| 21368 |
+
},
|
| 21369 |
+
{
|
| 21370 |
+
"epoch": 3.4763532763532763,
|
| 21371 |
+
"grad_norm": 0.17341741919517517,
|
| 21372 |
+
"learning_rate": 4.764438562993967e-05,
|
| 21373 |
+
"loss": 0.6822,
|
| 21374 |
+
"step": 3052
|
| 21375 |
+
},
|
| 21376 |
+
{
|
| 21377 |
+
"epoch": 3.4774928774928773,
|
| 21378 |
+
"grad_norm": 0.13949541747570038,
|
| 21379 |
+
"learning_rate": 4.764241087122123e-05,
|
| 21380 |
+
"loss": 1.0058,
|
| 21381 |
+
"step": 3053
|
| 21382 |
+
},
|
| 21383 |
+
{
|
| 21384 |
+
"epoch": 3.4786324786324787,
|
| 21385 |
+
"grad_norm": 0.13739712536334991,
|
| 21386 |
+
"learning_rate": 4.7640435326069597e-05,
|
| 21387 |
+
"loss": 0.8821,
|
| 21388 |
+
"step": 3054
|
| 21389 |
+
},
|
| 21390 |
+
{
|
| 21391 |
+
"epoch": 3.4797720797720797,
|
| 21392 |
+
"grad_norm": 0.1282612532377243,
|
| 21393 |
+
"learning_rate": 4.7638458994553384e-05,
|
| 21394 |
+
"loss": 0.8529,
|
| 21395 |
+
"step": 3055
|
| 21396 |
+
},
|
| 21397 |
+
{
|
| 21398 |
+
"epoch": 3.4809116809116807,
|
| 21399 |
+
"grad_norm": 0.21667225658893585,
|
| 21400 |
+
"learning_rate": 4.763648187674124e-05,
|
| 21401 |
+
"loss": 0.4698,
|
| 21402 |
+
"step": 3056
|
| 21403 |
+
},
|
| 21404 |
+
{
|
| 21405 |
+
"epoch": 3.482051282051282,
|
| 21406 |
+
"grad_norm": 0.1563890129327774,
|
| 21407 |
+
"learning_rate": 4.763450397270182e-05,
|
| 21408 |
+
"loss": 0.8811,
|
| 21409 |
+
"step": 3057
|
| 21410 |
+
},
|
| 21411 |
+
{
|
| 21412 |
+
"epoch": 3.483190883190883,
|
| 21413 |
+
"grad_norm": 0.17969991266727448,
|
| 21414 |
+
"learning_rate": 4.7632525282503835e-05,
|
| 21415 |
+
"loss": 0.7609,
|
| 21416 |
+
"step": 3058
|
| 21417 |
+
},
|
| 21418 |
+
{
|
| 21419 |
+
"epoch": 3.484330484330484,
|
| 21420 |
+
"grad_norm": 0.17439280450344086,
|
| 21421 |
+
"learning_rate": 4.763054580621601e-05,
|
| 21422 |
+
"loss": 0.8125,
|
| 21423 |
+
"step": 3059
|
| 21424 |
+
},
|
| 21425 |
+
{
|
| 21426 |
+
"epoch": 3.4854700854700855,
|
| 21427 |
+
"grad_norm": 0.1651092767715454,
|
| 21428 |
+
"learning_rate": 4.762856554390709e-05,
|
| 21429 |
+
"loss": 0.6987,
|
| 21430 |
+
"step": 3060
|
| 21431 |
+
},
|
| 21432 |
+
{
|
| 21433 |
+
"epoch": 3.4866096866096865,
|
| 21434 |
+
"grad_norm": 0.17362132668495178,
|
| 21435 |
+
"learning_rate": 4.762658449564586e-05,
|
| 21436 |
+
"loss": 0.8971,
|
| 21437 |
+
"step": 3061
|
| 21438 |
+
},
|
| 21439 |
+
{
|
| 21440 |
+
"epoch": 3.487749287749288,
|
| 21441 |
+
"grad_norm": 0.16419439017772675,
|
| 21442 |
+
"learning_rate": 4.762460266150113e-05,
|
| 21443 |
+
"loss": 0.6536,
|
| 21444 |
+
"step": 3062
|
| 21445 |
+
},
|
| 21446 |
+
{
|
| 21447 |
+
"epoch": 3.488888888888889,
|
| 21448 |
+
"grad_norm": 0.14855636656284332,
|
| 21449 |
+
"learning_rate": 4.762262004154173e-05,
|
| 21450 |
+
"loss": 0.9623,
|
| 21451 |
+
"step": 3063
|
| 21452 |
+
},
|
| 21453 |
+
{
|
| 21454 |
+
"epoch": 3.49002849002849,
|
| 21455 |
+
"grad_norm": 0.16179607808589935,
|
| 21456 |
+
"learning_rate": 4.7620636635836525e-05,
|
| 21457 |
+
"loss": 0.8504,
|
| 21458 |
+
"step": 3064
|
| 21459 |
+
},
|
| 21460 |
+
{
|
| 21461 |
+
"epoch": 3.4911680911680913,
|
| 21462 |
+
"grad_norm": 0.14565414190292358,
|
| 21463 |
+
"learning_rate": 4.7618652444454404e-05,
|
| 21464 |
+
"loss": 0.7869,
|
| 21465 |
+
"step": 3065
|
| 21466 |
+
},
|
| 21467 |
+
{
|
| 21468 |
+
"epoch": 3.4923076923076923,
|
| 21469 |
+
"grad_norm": 0.17142000794410706,
|
| 21470 |
+
"learning_rate": 4.7616667467464274e-05,
|
| 21471 |
+
"loss": 0.7129,
|
| 21472 |
+
"step": 3066
|
| 21473 |
+
},
|
| 21474 |
+
{
|
| 21475 |
+
"epoch": 3.4934472934472933,
|
| 21476 |
+
"grad_norm": 0.13818399608135223,
|
| 21477 |
+
"learning_rate": 4.761468170493509e-05,
|
| 21478 |
+
"loss": 0.9723,
|
| 21479 |
+
"step": 3067
|
| 21480 |
+
},
|
| 21481 |
+
{
|
| 21482 |
+
"epoch": 3.4945868945868948,
|
| 21483 |
+
"grad_norm": 0.14472275972366333,
|
| 21484 |
+
"learning_rate": 4.7612695156935824e-05,
|
| 21485 |
+
"loss": 0.8437,
|
| 21486 |
+
"step": 3068
|
| 21487 |
+
},
|
| 21488 |
+
{
|
| 21489 |
+
"epoch": 3.4957264957264957,
|
| 21490 |
+
"grad_norm": 0.14463575184345245,
|
| 21491 |
+
"learning_rate": 4.7610707823535475e-05,
|
| 21492 |
+
"loss": 0.8419,
|
| 21493 |
+
"step": 3069
|
| 21494 |
+
},
|
| 21495 |
+
{
|
| 21496 |
+
"epoch": 3.4968660968660967,
|
| 21497 |
+
"grad_norm": 0.1572341024875641,
|
| 21498 |
+
"learning_rate": 4.760871970480305e-05,
|
| 21499 |
+
"loss": 0.8705,
|
| 21500 |
+
"step": 3070
|
| 21501 |
+
},
|
| 21502 |
+
{
|
| 21503 |
+
"epoch": 3.498005698005698,
|
| 21504 |
+
"grad_norm": 0.17815126478672028,
|
| 21505 |
+
"learning_rate": 4.760673080080762e-05,
|
| 21506 |
+
"loss": 0.6992,
|
| 21507 |
+
"step": 3071
|
| 21508 |
+
},
|
| 21509 |
+
{
|
| 21510 |
+
"epoch": 3.499145299145299,
|
| 21511 |
+
"grad_norm": 0.1395833045244217,
|
| 21512 |
+
"learning_rate": 4.760474111161827e-05,
|
| 21513 |
+
"loss": 0.9855,
|
| 21514 |
+
"step": 3072
|
| 21515 |
+
},
|
| 21516 |
+
{
|
| 21517 |
+
"epoch": 3.5002849002849,
|
| 21518 |
+
"grad_norm": 0.16465449333190918,
|
| 21519 |
+
"learning_rate": 4.760275063730409e-05,
|
| 21520 |
+
"loss": 0.7593,
|
| 21521 |
+
"step": 3073
|
| 21522 |
+
},
|
| 21523 |
+
{
|
| 21524 |
+
"epoch": 3.5014245014245016,
|
| 21525 |
+
"grad_norm": 0.15138347446918488,
|
| 21526 |
+
"learning_rate": 4.7600759377934223e-05,
|
| 21527 |
+
"loss": 0.774,
|
| 21528 |
+
"step": 3074
|
| 21529 |
+
},
|
| 21530 |
+
{
|
| 21531 |
+
"epoch": 3.5025641025641026,
|
| 21532 |
+
"grad_norm": 0.1572001874446869,
|
| 21533 |
+
"learning_rate": 4.759876733357783e-05,
|
| 21534 |
+
"loss": 0.7944,
|
| 21535 |
+
"step": 3075
|
| 21536 |
+
},
|
| 21537 |
+
{
|
| 21538 |
+
"epoch": 3.5037037037037035,
|
| 21539 |
+
"grad_norm": 0.15404963493347168,
|
| 21540 |
+
"learning_rate": 4.75967745043041e-05,
|
| 21541 |
+
"loss": 0.7147,
|
| 21542 |
+
"step": 3076
|
| 21543 |
+
},
|
| 21544 |
+
{
|
| 21545 |
+
"epoch": 3.504843304843305,
|
| 21546 |
+
"grad_norm": 0.13912785053253174,
|
| 21547 |
+
"learning_rate": 4.7594780890182255e-05,
|
| 21548 |
+
"loss": 0.847,
|
| 21549 |
+
"step": 3077
|
| 21550 |
+
},
|
| 21551 |
+
{
|
| 21552 |
+
"epoch": 3.505982905982906,
|
| 21553 |
+
"grad_norm": 0.13626809418201447,
|
| 21554 |
+
"learning_rate": 4.7592786491281526e-05,
|
| 21555 |
+
"loss": 0.8828,
|
| 21556 |
+
"step": 3078
|
| 21557 |
+
},
|
| 21558 |
+
{
|
| 21559 |
+
"epoch": 3.5071225071225074,
|
| 21560 |
+
"grad_norm": 0.14898303151130676,
|
| 21561 |
+
"learning_rate": 4.75907913076712e-05,
|
| 21562 |
+
"loss": 0.8821,
|
| 21563 |
+
"step": 3079
|
| 21564 |
+
},
|
| 21565 |
+
{
|
| 21566 |
+
"epoch": 3.5082621082621084,
|
| 21567 |
+
"grad_norm": 0.1598164439201355,
|
| 21568 |
+
"learning_rate": 4.758879533942057e-05,
|
| 21569 |
+
"loss": 0.7792,
|
| 21570 |
+
"step": 3080
|
| 21571 |
+
},
|
| 21572 |
+
{
|
| 21573 |
+
"epoch": 3.5094017094017094,
|
| 21574 |
+
"grad_norm": 0.1513209193944931,
|
| 21575 |
+
"learning_rate": 4.758679858659894e-05,
|
| 21576 |
+
"loss": 0.7868,
|
| 21577 |
+
"step": 3081
|
| 21578 |
+
},
|
| 21579 |
+
{
|
| 21580 |
+
"epoch": 3.510541310541311,
|
| 21581 |
+
"grad_norm": 0.12373489141464233,
|
| 21582 |
+
"learning_rate": 4.7584801049275696e-05,
|
| 21583 |
+
"loss": 0.9528,
|
| 21584 |
+
"step": 3082
|
| 21585 |
+
},
|
| 21586 |
+
{
|
| 21587 |
+
"epoch": 3.511680911680912,
|
| 21588 |
+
"grad_norm": 0.15823349356651306,
|
| 21589 |
+
"learning_rate": 4.75828027275202e-05,
|
| 21590 |
+
"loss": 0.604,
|
| 21591 |
+
"step": 3083
|
| 21592 |
+
},
|
| 21593 |
+
{
|
| 21594 |
+
"epoch": 3.5128205128205128,
|
| 21595 |
+
"grad_norm": 0.15279988944530487,
|
| 21596 |
+
"learning_rate": 4.758080362140186e-05,
|
| 21597 |
+
"loss": 0.8486,
|
| 21598 |
+
"step": 3084
|
| 21599 |
+
},
|
| 21600 |
+
{
|
| 21601 |
+
"epoch": 3.513960113960114,
|
| 21602 |
+
"grad_norm": 0.1481696516275406,
|
| 21603 |
+
"learning_rate": 4.757880373099012e-05,
|
| 21604 |
+
"loss": 0.7861,
|
| 21605 |
+
"step": 3085
|
| 21606 |
+
},
|
| 21607 |
+
{
|
| 21608 |
+
"epoch": 3.515099715099715,
|
| 21609 |
+
"grad_norm": 0.15903371572494507,
|
| 21610 |
+
"learning_rate": 4.7576803056354427e-05,
|
| 21611 |
+
"loss": 0.7997,
|
| 21612 |
+
"step": 3086
|
| 21613 |
+
},
|
| 21614 |
+
{
|
| 21615 |
+
"epoch": 3.516239316239316,
|
| 21616 |
+
"grad_norm": 0.1583215892314911,
|
| 21617 |
+
"learning_rate": 4.7574801597564275e-05,
|
| 21618 |
+
"loss": 0.7687,
|
| 21619 |
+
"step": 3087
|
| 21620 |
+
},
|
| 21621 |
+
{
|
| 21622 |
+
"epoch": 3.5173789173789176,
|
| 21623 |
+
"grad_norm": 0.1464768797159195,
|
| 21624 |
+
"learning_rate": 4.757279935468919e-05,
|
| 21625 |
+
"loss": 0.9386,
|
| 21626 |
+
"step": 3088
|
| 21627 |
+
},
|
| 21628 |
+
{
|
| 21629 |
+
"epoch": 3.5185185185185186,
|
| 21630 |
+
"grad_norm": 0.17636044323444366,
|
| 21631 |
+
"learning_rate": 4.7570796327798706e-05,
|
| 21632 |
+
"loss": 0.7182,
|
| 21633 |
+
"step": 3089
|
| 21634 |
+
},
|
| 21635 |
+
{
|
| 21636 |
+
"epoch": 3.5196581196581196,
|
| 21637 |
+
"grad_norm": 0.1644255369901657,
|
| 21638 |
+
"learning_rate": 4.7568792516962404e-05,
|
| 21639 |
+
"loss": 0.7191,
|
| 21640 |
+
"step": 3090
|
| 21641 |
+
},
|
| 21642 |
+
{
|
| 21643 |
+
"epoch": 3.520797720797721,
|
| 21644 |
+
"grad_norm": 0.18549492955207825,
|
| 21645 |
+
"learning_rate": 4.756678792224986e-05,
|
| 21646 |
+
"loss": 0.7867,
|
| 21647 |
+
"step": 3091
|
| 21648 |
+
},
|
| 21649 |
+
{
|
| 21650 |
+
"epoch": 3.521937321937322,
|
| 21651 |
+
"grad_norm": 0.1530570387840271,
|
| 21652 |
+
"learning_rate": 4.756478254373071e-05,
|
| 21653 |
+
"loss": 0.9241,
|
| 21654 |
+
"step": 3092
|
| 21655 |
+
},
|
| 21656 |
+
{
|
| 21657 |
+
"epoch": 3.523076923076923,
|
| 21658 |
+
"grad_norm": 0.15714332461357117,
|
| 21659 |
+
"learning_rate": 4.756277638147462e-05,
|
| 21660 |
+
"loss": 0.7939,
|
| 21661 |
+
"step": 3093
|
| 21662 |
+
},
|
| 21663 |
+
{
|
| 21664 |
+
"epoch": 3.5242165242165244,
|
| 21665 |
+
"grad_norm": 0.16354434192180634,
|
| 21666 |
+
"learning_rate": 4.7560769435551256e-05,
|
| 21667 |
+
"loss": 0.8097,
|
| 21668 |
+
"step": 3094
|
| 21669 |
+
},
|
| 21670 |
+
{
|
| 21671 |
+
"epoch": 3.5253561253561254,
|
| 21672 |
+
"grad_norm": 0.14795003831386566,
|
| 21673 |
+
"learning_rate": 4.755876170603032e-05,
|
| 21674 |
+
"loss": 0.7605,
|
| 21675 |
+
"step": 3095
|
| 21676 |
+
},
|
| 21677 |
+
{
|
| 21678 |
+
"epoch": 3.5264957264957264,
|
| 21679 |
+
"grad_norm": 0.16275209188461304,
|
| 21680 |
+
"learning_rate": 4.755675319298156e-05,
|
| 21681 |
+
"loss": 0.9156,
|
| 21682 |
+
"step": 3096
|
| 21683 |
+
},
|
| 21684 |
+
{
|
| 21685 |
+
"epoch": 3.527635327635328,
|
| 21686 |
+
"grad_norm": 0.12918637692928314,
|
| 21687 |
+
"learning_rate": 4.7554743896474726e-05,
|
| 21688 |
+
"loss": 0.9186,
|
| 21689 |
+
"step": 3097
|
| 21690 |
+
},
|
| 21691 |
+
{
|
| 21692 |
+
"epoch": 3.528774928774929,
|
| 21693 |
+
"grad_norm": 0.14242558181285858,
|
| 21694 |
+
"learning_rate": 4.755273381657962e-05,
|
| 21695 |
+
"loss": 0.896,
|
| 21696 |
+
"step": 3098
|
| 21697 |
+
},
|
| 21698 |
+
{
|
| 21699 |
+
"epoch": 3.52991452991453,
|
| 21700 |
+
"grad_norm": 0.15556873381137848,
|
| 21701 |
+
"learning_rate": 4.755072295336605e-05,
|
| 21702 |
+
"loss": 0.8993,
|
| 21703 |
+
"step": 3099
|
| 21704 |
+
},
|
| 21705 |
+
{
|
| 21706 |
+
"epoch": 3.5310541310541312,
|
| 21707 |
+
"grad_norm": 0.134568452835083,
|
| 21708 |
+
"learning_rate": 4.754871130690384e-05,
|
| 21709 |
+
"loss": 0.9547,
|
| 21710 |
+
"step": 3100
|
| 21711 |
+
},
|
| 21712 |
+
{
|
| 21713 |
+
"epoch": 3.5321937321937322,
|
| 21714 |
+
"grad_norm": 0.18947847187519073,
|
| 21715 |
+
"learning_rate": 4.754669887726289e-05,
|
| 21716 |
+
"loss": 0.6513,
|
| 21717 |
+
"step": 3101
|
| 21718 |
+
},
|
| 21719 |
+
{
|
| 21720 |
+
"epoch": 3.533333333333333,
|
| 21721 |
+
"grad_norm": 0.1824527382850647,
|
| 21722 |
+
"learning_rate": 4.754468566451308e-05,
|
| 21723 |
+
"loss": 0.724,
|
| 21724 |
+
"step": 3102
|
| 21725 |
+
},
|
| 21726 |
+
{
|
| 21727 |
+
"epoch": 3.5344729344729346,
|
| 21728 |
+
"grad_norm": 0.14512591063976288,
|
| 21729 |
+
"learning_rate": 4.7542671668724335e-05,
|
| 21730 |
+
"loss": 0.9582,
|
| 21731 |
+
"step": 3103
|
| 21732 |
+
},
|
| 21733 |
+
{
|
| 21734 |
+
"epoch": 3.5356125356125356,
|
| 21735 |
+
"grad_norm": 0.13544780015945435,
|
| 21736 |
+
"learning_rate": 4.754065688996662e-05,
|
| 21737 |
+
"loss": 0.878,
|
| 21738 |
+
"step": 3104
|
| 21739 |
+
},
|
| 21740 |
+
{
|
| 21741 |
+
"epoch": 3.5367521367521366,
|
| 21742 |
+
"grad_norm": 0.156879261136055,
|
| 21743 |
+
"learning_rate": 4.7538641328309894e-05,
|
| 21744 |
+
"loss": 0.747,
|
| 21745 |
+
"step": 3105
|
| 21746 |
+
},
|
| 21747 |
+
{
|
| 21748 |
+
"epoch": 3.537891737891738,
|
| 21749 |
+
"grad_norm": 0.14823807775974274,
|
| 21750 |
+
"learning_rate": 4.7536624983824174e-05,
|
| 21751 |
+
"loss": 0.7952,
|
| 21752 |
+
"step": 3106
|
| 21753 |
+
},
|
| 21754 |
+
{
|
| 21755 |
+
"epoch": 3.539031339031339,
|
| 21756 |
+
"grad_norm": 0.14617039263248444,
|
| 21757 |
+
"learning_rate": 4.75346078565795e-05,
|
| 21758 |
+
"loss": 0.9083,
|
| 21759 |
+
"step": 3107
|
| 21760 |
+
},
|
| 21761 |
+
{
|
| 21762 |
+
"epoch": 3.54017094017094,
|
| 21763 |
+
"grad_norm": 0.1773999184370041,
|
| 21764 |
+
"learning_rate": 4.753258994664592e-05,
|
| 21765 |
+
"loss": 0.979,
|
| 21766 |
+
"step": 3108
|
| 21767 |
+
},
|
| 21768 |
+
{
|
| 21769 |
+
"epoch": 3.5413105413105415,
|
| 21770 |
+
"grad_norm": 0.17309634387493134,
|
| 21771 |
+
"learning_rate": 4.753057125409352e-05,
|
| 21772 |
+
"loss": 0.7047,
|
| 21773 |
+
"step": 3109
|
| 21774 |
+
},
|
| 21775 |
+
{
|
| 21776 |
+
"epoch": 3.5424501424501424,
|
| 21777 |
+
"grad_norm": 0.17175230383872986,
|
| 21778 |
+
"learning_rate": 4.7528551778992434e-05,
|
| 21779 |
+
"loss": 0.6613,
|
| 21780 |
+
"step": 3110
|
| 21781 |
+
},
|
| 21782 |
+
{
|
| 21783 |
+
"epoch": 3.5435897435897434,
|
| 21784 |
+
"grad_norm": 0.12826001644134521,
|
| 21785 |
+
"learning_rate": 4.7526531521412785e-05,
|
| 21786 |
+
"loss": 0.9728,
|
| 21787 |
+
"step": 3111
|
| 21788 |
+
},
|
| 21789 |
+
{
|
| 21790 |
+
"epoch": 3.544729344729345,
|
| 21791 |
+
"grad_norm": 0.14230799674987793,
|
| 21792 |
+
"learning_rate": 4.752451048142476e-05,
|
| 21793 |
+
"loss": 0.9293,
|
| 21794 |
+
"step": 3112
|
| 21795 |
+
},
|
| 21796 |
+
{
|
| 21797 |
+
"epoch": 3.545868945868946,
|
| 21798 |
+
"grad_norm": 0.1300976276397705,
|
| 21799 |
+
"learning_rate": 4.752248865909853e-05,
|
| 21800 |
+
"loss": 1.0119,
|
| 21801 |
+
"step": 3113
|
| 21802 |
+
},
|
| 21803 |
+
{
|
| 21804 |
+
"epoch": 3.547008547008547,
|
| 21805 |
+
"grad_norm": 0.13346892595291138,
|
| 21806 |
+
"learning_rate": 4.752046605450433e-05,
|
| 21807 |
+
"loss": 0.9862,
|
| 21808 |
+
"step": 3114
|
| 21809 |
+
},
|
| 21810 |
+
{
|
| 21811 |
+
"epoch": 3.5481481481481483,
|
| 21812 |
+
"grad_norm": 0.15452101826667786,
|
| 21813 |
+
"learning_rate": 4.751844266771242e-05,
|
| 21814 |
+
"loss": 0.7844,
|
| 21815 |
+
"step": 3115
|
| 21816 |
+
},
|
| 21817 |
+
{
|
| 21818 |
+
"epoch": 3.5492877492877493,
|
| 21819 |
+
"grad_norm": 0.11814556270837784,
|
| 21820 |
+
"learning_rate": 4.751641849879306e-05,
|
| 21821 |
+
"loss": 0.9023,
|
| 21822 |
+
"step": 3116
|
| 21823 |
+
},
|
| 21824 |
+
{
|
| 21825 |
+
"epoch": 3.5504273504273502,
|
| 21826 |
+
"grad_norm": 0.14452509582042694,
|
| 21827 |
+
"learning_rate": 4.7514393547816574e-05,
|
| 21828 |
+
"loss": 0.8339,
|
| 21829 |
+
"step": 3117
|
| 21830 |
+
},
|
| 21831 |
+
{
|
| 21832 |
+
"epoch": 3.5515669515669517,
|
| 21833 |
+
"grad_norm": 0.1519222855567932,
|
| 21834 |
+
"learning_rate": 4.751236781485328e-05,
|
| 21835 |
+
"loss": 0.8992,
|
| 21836 |
+
"step": 3118
|
| 21837 |
+
},
|
| 21838 |
+
{
|
| 21839 |
+
"epoch": 3.5527065527065527,
|
| 21840 |
+
"grad_norm": 0.16835427284240723,
|
| 21841 |
+
"learning_rate": 4.7510341299973544e-05,
|
| 21842 |
+
"loss": 0.6874,
|
| 21843 |
+
"step": 3119
|
| 21844 |
+
},
|
| 21845 |
+
{
|
| 21846 |
+
"epoch": 3.5538461538461537,
|
| 21847 |
+
"grad_norm": 0.1623925268650055,
|
| 21848 |
+
"learning_rate": 4.7508314003247753e-05,
|
| 21849 |
+
"loss": 0.5674,
|
| 21850 |
+
"step": 3120
|
| 21851 |
+
},
|
| 21852 |
+
{
|
| 21853 |
+
"epoch": 3.554985754985755,
|
| 21854 |
+
"grad_norm": 0.1429547369480133,
|
| 21855 |
+
"learning_rate": 4.750628592474632e-05,
|
| 21856 |
+
"loss": 0.852,
|
| 21857 |
+
"step": 3121
|
| 21858 |
+
},
|
| 21859 |
+
{
|
| 21860 |
+
"epoch": 3.556125356125356,
|
| 21861 |
+
"grad_norm": 0.17852966487407684,
|
| 21862 |
+
"learning_rate": 4.7504257064539676e-05,
|
| 21863 |
+
"loss": 0.7445,
|
| 21864 |
+
"step": 3122
|
| 21865 |
+
},
|
| 21866 |
+
{
|
| 21867 |
+
"epoch": 3.557264957264957,
|
| 21868 |
+
"grad_norm": 0.15837563574314117,
|
| 21869 |
+
"learning_rate": 4.75022274226983e-05,
|
| 21870 |
+
"loss": 0.7572,
|
| 21871 |
+
"step": 3123
|
| 21872 |
+
},
|
| 21873 |
+
{
|
| 21874 |
+
"epoch": 3.5584045584045585,
|
| 21875 |
+
"grad_norm": 0.1362544149160385,
|
| 21876 |
+
"learning_rate": 4.750019699929269e-05,
|
| 21877 |
+
"loss": 0.9731,
|
| 21878 |
+
"step": 3124
|
| 21879 |
+
},
|
| 21880 |
+
{
|
| 21881 |
+
"epoch": 3.5595441595441595,
|
| 21882 |
+
"grad_norm": 0.15003323554992676,
|
| 21883 |
+
"learning_rate": 4.7498165794393356e-05,
|
| 21884 |
+
"loss": 0.689,
|
| 21885 |
+
"step": 3125
|
| 21886 |
+
},
|
| 21887 |
+
{
|
| 21888 |
+
"epoch": 3.5606837606837605,
|
| 21889 |
+
"grad_norm": 0.19216139614582062,
|
| 21890 |
+
"learning_rate": 4.7496133808070866e-05,
|
| 21891 |
+
"loss": 0.769,
|
| 21892 |
+
"step": 3126
|
| 21893 |
+
},
|
| 21894 |
+
{
|
| 21895 |
+
"epoch": 3.561823361823362,
|
| 21896 |
+
"grad_norm": 0.16024665534496307,
|
| 21897 |
+
"learning_rate": 4.749410104039577e-05,
|
| 21898 |
+
"loss": 0.7634,
|
| 21899 |
+
"step": 3127
|
| 21900 |
+
},
|
| 21901 |
+
{
|
| 21902 |
+
"epoch": 3.562962962962963,
|
| 21903 |
+
"grad_norm": 0.140433669090271,
|
| 21904 |
+
"learning_rate": 4.74920674914387e-05,
|
| 21905 |
+
"loss": 0.9262,
|
| 21906 |
+
"step": 3128
|
| 21907 |
+
},
|
| 21908 |
+
{
|
| 21909 |
+
"epoch": 3.564102564102564,
|
| 21910 |
+
"grad_norm": 0.14482799172401428,
|
| 21911 |
+
"learning_rate": 4.749003316127026e-05,
|
| 21912 |
+
"loss": 0.8689,
|
| 21913 |
+
"step": 3129
|
| 21914 |
+
},
|
| 21915 |
+
{
|
| 21916 |
+
"epoch": 3.5652421652421653,
|
| 21917 |
+
"grad_norm": 0.18085375428199768,
|
| 21918 |
+
"learning_rate": 4.7487998049961125e-05,
|
| 21919 |
+
"loss": 0.6887,
|
| 21920 |
+
"step": 3130
|
| 21921 |
+
},
|
| 21922 |
+
{
|
| 21923 |
+
"epoch": 3.5663817663817663,
|
| 21924 |
+
"grad_norm": 0.16813300549983978,
|
| 21925 |
+
"learning_rate": 4.748596215758198e-05,
|
| 21926 |
+
"loss": 0.7823,
|
| 21927 |
+
"step": 3131
|
| 21928 |
+
},
|
| 21929 |
+
{
|
| 21930 |
+
"epoch": 3.5675213675213673,
|
| 21931 |
+
"grad_norm": 0.1730300337076187,
|
| 21932 |
+
"learning_rate": 4.748392548420352e-05,
|
| 21933 |
+
"loss": 0.6934,
|
| 21934 |
+
"step": 3132
|
| 21935 |
+
},
|
| 21936 |
+
{
|
| 21937 |
+
"epoch": 3.5686609686609687,
|
| 21938 |
+
"grad_norm": 0.18341879546642303,
|
| 21939 |
+
"learning_rate": 4.7481888029896506e-05,
|
| 21940 |
+
"loss": 0.843,
|
| 21941 |
+
"step": 3133
|
| 21942 |
+
},
|
| 21943 |
+
{
|
| 21944 |
+
"epoch": 3.5698005698005697,
|
| 21945 |
+
"grad_norm": 0.14152836799621582,
|
| 21946 |
+
"learning_rate": 4.747984979473169e-05,
|
| 21947 |
+
"loss": 0.7443,
|
| 21948 |
+
"step": 3134
|
| 21949 |
+
},
|
| 21950 |
+
{
|
| 21951 |
+
"epoch": 3.5709401709401707,
|
| 21952 |
+
"grad_norm": 0.16617611050605774,
|
| 21953 |
+
"learning_rate": 4.7477810778779875e-05,
|
| 21954 |
+
"loss": 0.7803,
|
| 21955 |
+
"step": 3135
|
| 21956 |
+
},
|
| 21957 |
+
{
|
| 21958 |
+
"epoch": 3.572079772079772,
|
| 21959 |
+
"grad_norm": 0.1385413557291031,
|
| 21960 |
+
"learning_rate": 4.7475770982111875e-05,
|
| 21961 |
+
"loss": 0.7995,
|
| 21962 |
+
"step": 3136
|
| 21963 |
+
},
|
| 21964 |
+
{
|
| 21965 |
+
"epoch": 3.573219373219373,
|
| 21966 |
+
"grad_norm": 0.15684014558792114,
|
| 21967 |
+
"learning_rate": 4.7473730404798544e-05,
|
| 21968 |
+
"loss": 0.7581,
|
| 21969 |
+
"step": 3137
|
| 21970 |
+
},
|
| 21971 |
+
{
|
| 21972 |
+
"epoch": 3.574358974358974,
|
| 21973 |
+
"grad_norm": 0.16094832122325897,
|
| 21974 |
+
"learning_rate": 4.7471689046910756e-05,
|
| 21975 |
+
"loss": 0.7769,
|
| 21976 |
+
"step": 3138
|
| 21977 |
+
},
|
| 21978 |
+
{
|
| 21979 |
+
"epoch": 3.5754985754985755,
|
| 21980 |
+
"grad_norm": 0.13003958761692047,
|
| 21981 |
+
"learning_rate": 4.7469646908519404e-05,
|
| 21982 |
+
"loss": 0.9816,
|
| 21983 |
+
"step": 3139
|
| 21984 |
+
},
|
| 21985 |
+
{
|
| 21986 |
+
"epoch": 3.5766381766381765,
|
| 21987 |
+
"grad_norm": 0.16533993184566498,
|
| 21988 |
+
"learning_rate": 4.746760398969543e-05,
|
| 21989 |
+
"loss": 0.7451,
|
| 21990 |
+
"step": 3140
|
| 21991 |
+
},
|
| 21992 |
+
{
|
| 21993 |
+
"epoch": 3.5777777777777775,
|
| 21994 |
+
"grad_norm": 0.13551752269268036,
|
| 21995 |
+
"learning_rate": 4.746556029050977e-05,
|
| 21996 |
+
"loss": 0.9916,
|
| 21997 |
+
"step": 3141
|
| 21998 |
+
},
|
| 21999 |
+
{
|
| 22000 |
+
"epoch": 3.578917378917379,
|
| 22001 |
+
"grad_norm": 0.17578278481960297,
|
| 22002 |
+
"learning_rate": 4.7463515811033435e-05,
|
| 22003 |
+
"loss": 0.661,
|
| 22004 |
+
"step": 3142
|
| 22005 |
+
},
|
| 22006 |
+
{
|
| 22007 |
+
"epoch": 3.58005698005698,
|
| 22008 |
+
"grad_norm": 0.1797582507133484,
|
| 22009 |
+
"learning_rate": 4.746147055133741e-05,
|
| 22010 |
+
"loss": 0.6817,
|
| 22011 |
+
"step": 3143
|
| 22012 |
+
},
|
| 22013 |
+
{
|
| 22014 |
+
"epoch": 3.5811965811965814,
|
| 22015 |
+
"grad_norm": 0.12641745805740356,
|
| 22016 |
+
"learning_rate": 4.7459424511492745e-05,
|
| 22017 |
+
"loss": 1.1176,
|
| 22018 |
+
"step": 3144
|
| 22019 |
+
},
|
| 22020 |
+
{
|
| 22021 |
+
"epoch": 3.5823361823361823,
|
| 22022 |
+
"grad_norm": 0.16470804810523987,
|
| 22023 |
+
"learning_rate": 4.745737769157051e-05,
|
| 22024 |
+
"loss": 0.8451,
|
| 22025 |
+
"step": 3145
|
| 22026 |
+
},
|
| 22027 |
+
{
|
| 22028 |
+
"epoch": 3.5834757834757833,
|
| 22029 |
+
"grad_norm": 0.1253516972064972,
|
| 22030 |
+
"learning_rate": 4.7455330091641784e-05,
|
| 22031 |
+
"loss": 0.8838,
|
| 22032 |
+
"step": 3146
|
| 22033 |
+
},
|
| 22034 |
+
{
|
| 22035 |
+
"epoch": 3.5846153846153848,
|
| 22036 |
+
"grad_norm": 0.15218587219715118,
|
| 22037 |
+
"learning_rate": 4.745328171177769e-05,
|
| 22038 |
+
"loss": 0.7625,
|
| 22039 |
+
"step": 3147
|
| 22040 |
+
},
|
| 22041 |
+
{
|
| 22042 |
+
"epoch": 3.5857549857549857,
|
| 22043 |
+
"grad_norm": 0.168340802192688,
|
| 22044 |
+
"learning_rate": 4.7451232552049385e-05,
|
| 22045 |
+
"loss": 0.8593,
|
| 22046 |
+
"step": 3148
|
| 22047 |
+
},
|
| 22048 |
+
{
|
| 22049 |
+
"epoch": 3.5868945868945867,
|
| 22050 |
+
"grad_norm": 0.18887469172477722,
|
| 22051 |
+
"learning_rate": 4.744918261252802e-05,
|
| 22052 |
+
"loss": 0.7663,
|
| 22053 |
+
"step": 3149
|
| 22054 |
+
},
|
| 22055 |
+
{
|
| 22056 |
+
"epoch": 3.588034188034188,
|
| 22057 |
+
"grad_norm": 0.1507597118616104,
|
| 22058 |
+
"learning_rate": 4.7447131893284815e-05,
|
| 22059 |
+
"loss": 0.8658,
|
| 22060 |
+
"step": 3150
|
| 22061 |
+
},
|
| 22062 |
+
{
|
| 22063 |
+
"epoch": 3.589173789173789,
|
| 22064 |
+
"grad_norm": 0.15251576900482178,
|
| 22065 |
+
"learning_rate": 4.744508039439099e-05,
|
| 22066 |
+
"loss": 0.6719,
|
| 22067 |
+
"step": 3151
|
| 22068 |
+
},
|
| 22069 |
+
{
|
| 22070 |
+
"epoch": 3.5903133903133906,
|
| 22071 |
+
"grad_norm": 0.141212597489357,
|
| 22072 |
+
"learning_rate": 4.74430281159178e-05,
|
| 22073 |
+
"loss": 0.9153,
|
| 22074 |
+
"step": 3152
|
| 22075 |
+
},
|
| 22076 |
+
{
|
| 22077 |
+
"epoch": 3.5914529914529916,
|
| 22078 |
+
"grad_norm": 0.17158134281635284,
|
| 22079 |
+
"learning_rate": 4.744097505793652e-05,
|
| 22080 |
+
"loss": 0.5871,
|
| 22081 |
+
"step": 3153
|
| 22082 |
+
},
|
| 22083 |
+
{
|
| 22084 |
+
"epoch": 3.5925925925925926,
|
| 22085 |
+
"grad_norm": 0.1644529551267624,
|
| 22086 |
+
"learning_rate": 4.743892122051846e-05,
|
| 22087 |
+
"loss": 0.7573,
|
| 22088 |
+
"step": 3154
|
| 22089 |
+
},
|
| 22090 |
+
{
|
| 22091 |
+
"epoch": 3.593732193732194,
|
| 22092 |
+
"grad_norm": 0.12898863852024078,
|
| 22093 |
+
"learning_rate": 4.7436866603734964e-05,
|
| 22094 |
+
"loss": 0.8707,
|
| 22095 |
+
"step": 3155
|
| 22096 |
+
},
|
| 22097 |
+
{
|
| 22098 |
+
"epoch": 3.594871794871795,
|
| 22099 |
+
"grad_norm": 0.15508373081684113,
|
| 22100 |
+
"learning_rate": 4.743481120765739e-05,
|
| 22101 |
+
"loss": 0.8554,
|
| 22102 |
+
"step": 3156
|
| 22103 |
+
},
|
| 22104 |
+
{
|
| 22105 |
+
"epoch": 3.596011396011396,
|
| 22106 |
+
"grad_norm": 0.1768398880958557,
|
| 22107 |
+
"learning_rate": 4.743275503235712e-05,
|
| 22108 |
+
"loss": 0.6901,
|
| 22109 |
+
"step": 3157
|
| 22110 |
+
},
|
| 22111 |
+
{
|
| 22112 |
+
"epoch": 3.5971509971509974,
|
| 22113 |
+
"grad_norm": 0.16949577629566193,
|
| 22114 |
+
"learning_rate": 4.743069807790559e-05,
|
| 22115 |
+
"loss": 0.7631,
|
| 22116 |
+
"step": 3158
|
| 22117 |
+
},
|
| 22118 |
+
{
|
| 22119 |
+
"epoch": 3.5982905982905984,
|
| 22120 |
+
"grad_norm": 0.15541768074035645,
|
| 22121 |
+
"learning_rate": 4.742864034437422e-05,
|
| 22122 |
+
"loss": 0.8703,
|
| 22123 |
+
"step": 3159
|
| 22124 |
+
},
|
| 22125 |
+
{
|
| 22126 |
+
"epoch": 3.5994301994301994,
|
| 22127 |
+
"grad_norm": 0.1964762657880783,
|
| 22128 |
+
"learning_rate": 4.742658183183449e-05,
|
| 22129 |
+
"loss": 0.6899,
|
| 22130 |
+
"step": 3160
|
| 22131 |
+
},
|
| 22132 |
+
{
|
| 22133 |
+
"epoch": 3.600569800569801,
|
| 22134 |
+
"grad_norm": 0.15012037754058838,
|
| 22135 |
+
"learning_rate": 4.742452254035791e-05,
|
| 22136 |
+
"loss": 0.7818,
|
| 22137 |
+
"step": 3161
|
| 22138 |
+
},
|
| 22139 |
+
{
|
| 22140 |
+
"epoch": 3.601709401709402,
|
| 22141 |
+
"grad_norm": 0.17907105386257172,
|
| 22142 |
+
"learning_rate": 4.742246247001599e-05,
|
| 22143 |
+
"loss": 0.7718,
|
| 22144 |
+
"step": 3162
|
| 22145 |
+
},
|
| 22146 |
+
{
|
| 22147 |
+
"epoch": 3.602849002849003,
|
| 22148 |
+
"grad_norm": 0.16445888578891754,
|
| 22149 |
+
"learning_rate": 4.742040162088029e-05,
|
| 22150 |
+
"loss": 0.7743,
|
| 22151 |
+
"step": 3163
|
| 22152 |
+
},
|
| 22153 |
+
{
|
| 22154 |
+
"epoch": 3.603988603988604,
|
| 22155 |
+
"grad_norm": 0.18797078728675842,
|
| 22156 |
+
"learning_rate": 4.741833999302238e-05,
|
| 22157 |
+
"loss": 0.6795,
|
| 22158 |
+
"step": 3164
|
| 22159 |
+
},
|
| 22160 |
+
{
|
| 22161 |
+
"epoch": 3.605128205128205,
|
| 22162 |
+
"grad_norm": 0.15027131140232086,
|
| 22163 |
+
"learning_rate": 4.7416277586513876e-05,
|
| 22164 |
+
"loss": 0.8253,
|
| 22165 |
+
"step": 3165
|
| 22166 |
+
},
|
| 22167 |
+
{
|
| 22168 |
+
"epoch": 3.606267806267806,
|
| 22169 |
+
"grad_norm": 0.14495904743671417,
|
| 22170 |
+
"learning_rate": 4.7414214401426406e-05,
|
| 22171 |
+
"loss": 0.8755,
|
| 22172 |
+
"step": 3166
|
| 22173 |
+
},
|
| 22174 |
+
{
|
| 22175 |
+
"epoch": 3.6074074074074076,
|
| 22176 |
+
"grad_norm": 0.16689111292362213,
|
| 22177 |
+
"learning_rate": 4.7412150437831625e-05,
|
| 22178 |
+
"loss": 0.8236,
|
| 22179 |
+
"step": 3167
|
| 22180 |
+
},
|
| 22181 |
+
{
|
| 22182 |
+
"epoch": 3.6085470085470086,
|
| 22183 |
+
"grad_norm": 0.1899695247411728,
|
| 22184 |
+
"learning_rate": 4.7410085695801226e-05,
|
| 22185 |
+
"loss": 0.7957,
|
| 22186 |
+
"step": 3168
|
| 22187 |
+
},
|
| 22188 |
+
{
|
| 22189 |
+
"epoch": 3.6096866096866096,
|
| 22190 |
+
"grad_norm": 0.13431382179260254,
|
| 22191 |
+
"learning_rate": 4.740802017540692e-05,
|
| 22192 |
+
"loss": 0.9913,
|
| 22193 |
+
"step": 3169
|
| 22194 |
+
},
|
| 22195 |
+
{
|
| 22196 |
+
"epoch": 3.610826210826211,
|
| 22197 |
+
"grad_norm": 0.18161001801490784,
|
| 22198 |
+
"learning_rate": 4.740595387672047e-05,
|
| 22199 |
+
"loss": 0.853,
|
| 22200 |
+
"step": 3170
|
| 22201 |
+
},
|
| 22202 |
+
{
|
| 22203 |
+
"epoch": 3.611965811965812,
|
| 22204 |
+
"grad_norm": 0.14907872676849365,
|
| 22205 |
+
"learning_rate": 4.74038867998136e-05,
|
| 22206 |
+
"loss": 0.9096,
|
| 22207 |
+
"step": 3171
|
| 22208 |
+
},
|
| 22209 |
+
{
|
| 22210 |
+
"epoch": 3.613105413105413,
|
| 22211 |
+
"grad_norm": 0.14314506947994232,
|
| 22212 |
+
"learning_rate": 4.740181894475815e-05,
|
| 22213 |
+
"loss": 0.9571,
|
| 22214 |
+
"step": 3172
|
| 22215 |
+
},
|
| 22216 |
+
{
|
| 22217 |
+
"epoch": 3.6142450142450144,
|
| 22218 |
+
"grad_norm": 0.14771422743797302,
|
| 22219 |
+
"learning_rate": 4.739975031162591e-05,
|
| 22220 |
+
"loss": 0.8377,
|
| 22221 |
+
"step": 3173
|
| 22222 |
+
},
|
| 22223 |
+
{
|
| 22224 |
+
"epoch": 3.6153846153846154,
|
| 22225 |
+
"grad_norm": 0.1530153453350067,
|
| 22226 |
+
"learning_rate": 4.739768090048875e-05,
|
| 22227 |
+
"loss": 0.7473,
|
| 22228 |
+
"step": 3174
|
| 22229 |
+
},
|
| 22230 |
+
{
|
| 22231 |
+
"epoch": 3.6165242165242164,
|
| 22232 |
+
"grad_norm": 0.15972135961055756,
|
| 22233 |
+
"learning_rate": 4.739561071141854e-05,
|
| 22234 |
+
"loss": 0.8732,
|
| 22235 |
+
"step": 3175
|
| 22236 |
+
},
|
| 22237 |
+
{
|
| 22238 |
+
"epoch": 3.617663817663818,
|
| 22239 |
+
"grad_norm": 0.1361907720565796,
|
| 22240 |
+
"learning_rate": 4.739353974448717e-05,
|
| 22241 |
+
"loss": 0.9092,
|
| 22242 |
+
"step": 3176
|
| 22243 |
+
},
|
| 22244 |
+
{
|
| 22245 |
+
"epoch": 3.618803418803419,
|
| 22246 |
+
"grad_norm": 0.16396193206310272,
|
| 22247 |
+
"learning_rate": 4.739146799976659e-05,
|
| 22248 |
+
"loss": 0.7726,
|
| 22249 |
+
"step": 3177
|
| 22250 |
+
},
|
| 22251 |
+
{
|
| 22252 |
+
"epoch": 3.61994301994302,
|
| 22253 |
+
"grad_norm": 0.16118596494197845,
|
| 22254 |
+
"learning_rate": 4.738939547732875e-05,
|
| 22255 |
+
"loss": 0.8619,
|
| 22256 |
+
"step": 3178
|
| 22257 |
+
},
|
| 22258 |
+
{
|
| 22259 |
+
"epoch": 3.6210826210826212,
|
| 22260 |
+
"grad_norm": 0.1634664088487625,
|
| 22261 |
+
"learning_rate": 4.7387322177245635e-05,
|
| 22262 |
+
"loss": 0.6513,
|
| 22263 |
+
"step": 3179
|
| 22264 |
+
},
|
| 22265 |
+
{
|
| 22266 |
+
"epoch": 3.6222222222222222,
|
| 22267 |
+
"grad_norm": 0.1703759729862213,
|
| 22268 |
+
"learning_rate": 4.7385248099589255e-05,
|
| 22269 |
+
"loss": 0.6414,
|
| 22270 |
+
"step": 3180
|
| 22271 |
+
},
|
| 22272 |
+
{
|
| 22273 |
+
"epoch": 3.623361823361823,
|
| 22274 |
+
"grad_norm": 0.14178255200386047,
|
| 22275 |
+
"learning_rate": 4.738317324443164e-05,
|
| 22276 |
+
"loss": 0.8136,
|
| 22277 |
+
"step": 3181
|
| 22278 |
+
},
|
| 22279 |
+
{
|
| 22280 |
+
"epoch": 3.6245014245014247,
|
| 22281 |
+
"grad_norm": 0.1369297355413437,
|
| 22282 |
+
"learning_rate": 4.7381097611844876e-05,
|
| 22283 |
+
"loss": 0.9897,
|
| 22284 |
+
"step": 3182
|
| 22285 |
+
},
|
| 22286 |
+
{
|
| 22287 |
+
"epoch": 3.6256410256410256,
|
| 22288 |
+
"grad_norm": 0.15781539678573608,
|
| 22289 |
+
"learning_rate": 4.737902120190104e-05,
|
| 22290 |
+
"loss": 0.7981,
|
| 22291 |
+
"step": 3183
|
| 22292 |
+
},
|
| 22293 |
+
{
|
| 22294 |
+
"epoch": 3.6267806267806266,
|
| 22295 |
+
"grad_norm": 0.17928865551948547,
|
| 22296 |
+
"learning_rate": 4.7376944014672255e-05,
|
| 22297 |
+
"loss": 0.6701,
|
| 22298 |
+
"step": 3184
|
| 22299 |
+
},
|
| 22300 |
+
{
|
| 22301 |
+
"epoch": 3.627920227920228,
|
| 22302 |
+
"grad_norm": 0.17236638069152832,
|
| 22303 |
+
"learning_rate": 4.737486605023067e-05,
|
| 22304 |
+
"loss": 0.8286,
|
| 22305 |
+
"step": 3185
|
| 22306 |
+
},
|
| 22307 |
+
{
|
| 22308 |
+
"epoch": 3.629059829059829,
|
| 22309 |
+
"grad_norm": 0.12563465535640717,
|
| 22310 |
+
"learning_rate": 4.7372787308648444e-05,
|
| 22311 |
+
"loss": 1.1561,
|
| 22312 |
+
"step": 3186
|
| 22313 |
+
},
|
| 22314 |
+
{
|
| 22315 |
+
"epoch": 3.63019943019943,
|
| 22316 |
+
"grad_norm": 0.15684127807617188,
|
| 22317 |
+
"learning_rate": 4.7370707789997804e-05,
|
| 22318 |
+
"loss": 0.6536,
|
| 22319 |
+
"step": 3187
|
| 22320 |
+
},
|
| 22321 |
+
{
|
| 22322 |
+
"epoch": 3.6313390313390315,
|
| 22323 |
+
"grad_norm": 0.18025460839271545,
|
| 22324 |
+
"learning_rate": 4.736862749435096e-05,
|
| 22325 |
+
"loss": 0.7383,
|
| 22326 |
+
"step": 3188
|
| 22327 |
+
},
|
| 22328 |
+
{
|
| 22329 |
+
"epoch": 3.6324786324786325,
|
| 22330 |
+
"grad_norm": 0.13752953708171844,
|
| 22331 |
+
"learning_rate": 4.7366546421780165e-05,
|
| 22332 |
+
"loss": 0.7251,
|
| 22333 |
+
"step": 3189
|
| 22334 |
+
},
|
| 22335 |
+
{
|
| 22336 |
+
"epoch": 3.6336182336182334,
|
| 22337 |
+
"grad_norm": 0.14074869453907013,
|
| 22338 |
+
"learning_rate": 4.7364464572357705e-05,
|
| 22339 |
+
"loss": 0.8969,
|
| 22340 |
+
"step": 3190
|
| 22341 |
+
},
|
| 22342 |
+
{
|
| 22343 |
+
"epoch": 3.634757834757835,
|
| 22344 |
+
"grad_norm": 0.1559051275253296,
|
| 22345 |
+
"learning_rate": 4.736238194615589e-05,
|
| 22346 |
+
"loss": 0.7639,
|
| 22347 |
+
"step": 3191
|
| 22348 |
+
},
|
| 22349 |
+
{
|
| 22350 |
+
"epoch": 3.635897435897436,
|
| 22351 |
+
"grad_norm": 0.15167847275733948,
|
| 22352 |
+
"learning_rate": 4.736029854324705e-05,
|
| 22353 |
+
"loss": 0.8245,
|
| 22354 |
+
"step": 3192
|
| 22355 |
+
},
|
| 22356 |
+
{
|
| 22357 |
+
"epoch": 3.637037037037037,
|
| 22358 |
+
"grad_norm": 0.17585301399230957,
|
| 22359 |
+
"learning_rate": 4.7358214363703555e-05,
|
| 22360 |
+
"loss": 0.8256,
|
| 22361 |
+
"step": 3193
|
| 22362 |
+
},
|
| 22363 |
+
{
|
| 22364 |
+
"epoch": 3.6381766381766383,
|
| 22365 |
+
"grad_norm": 0.162922203540802,
|
| 22366 |
+
"learning_rate": 4.735612940759778e-05,
|
| 22367 |
+
"loss": 0.7108,
|
| 22368 |
+
"step": 3194
|
| 22369 |
+
},
|
| 22370 |
+
{
|
| 22371 |
+
"epoch": 3.6393162393162393,
|
| 22372 |
+
"grad_norm": 0.12826752662658691,
|
| 22373 |
+
"learning_rate": 4.735404367500217e-05,
|
| 22374 |
+
"loss": 0.8953,
|
| 22375 |
+
"step": 3195
|
| 22376 |
+
},
|
| 22377 |
+
{
|
| 22378 |
+
"epoch": 3.6404558404558403,
|
| 22379 |
+
"grad_norm": 0.15029852092266083,
|
| 22380 |
+
"learning_rate": 4.7351957165989136e-05,
|
| 22381 |
+
"loss": 0.7577,
|
| 22382 |
+
"step": 3196
|
| 22383 |
+
},
|
| 22384 |
+
{
|
| 22385 |
+
"epoch": 3.6415954415954417,
|
| 22386 |
+
"grad_norm": 0.16467316448688507,
|
| 22387 |
+
"learning_rate": 4.734986988063116e-05,
|
| 22388 |
+
"loss": 0.8308,
|
| 22389 |
+
"step": 3197
|
| 22390 |
+
},
|
| 22391 |
+
{
|
| 22392 |
+
"epoch": 3.6427350427350427,
|
| 22393 |
+
"grad_norm": 0.1632472723722458,
|
| 22394 |
+
"learning_rate": 4.7347781819000747e-05,
|
| 22395 |
+
"loss": 0.7183,
|
| 22396 |
+
"step": 3198
|
| 22397 |
+
},
|
| 22398 |
+
{
|
| 22399 |
+
"epoch": 3.6438746438746437,
|
| 22400 |
+
"grad_norm": 0.18199078738689423,
|
| 22401 |
+
"learning_rate": 4.734569298117041e-05,
|
| 22402 |
+
"loss": 0.7075,
|
| 22403 |
+
"step": 3199
|
| 22404 |
+
},
|
| 22405 |
+
{
|
| 22406 |
+
"epoch": 3.645014245014245,
|
| 22407 |
+
"grad_norm": 0.17410241067409515,
|
| 22408 |
+
"learning_rate": 4.734360336721271e-05,
|
| 22409 |
+
"loss": 1.0027,
|
| 22410 |
+
"step": 3200
|
| 22411 |
+
},
|
| 22412 |
+
{
|
| 22413 |
+
"epoch": 3.646153846153846,
|
| 22414 |
+
"grad_norm": 0.1600143015384674,
|
| 22415 |
+
"learning_rate": 4.734151297720021e-05,
|
| 22416 |
+
"loss": 0.8422,
|
| 22417 |
+
"step": 3201
|
| 22418 |
+
},
|
| 22419 |
+
{
|
| 22420 |
+
"epoch": 3.647293447293447,
|
| 22421 |
+
"grad_norm": 0.17152932286262512,
|
| 22422 |
+
"learning_rate": 4.7339421811205534e-05,
|
| 22423 |
+
"loss": 0.7428,
|
| 22424 |
+
"step": 3202
|
| 22425 |
+
},
|
| 22426 |
+
{
|
| 22427 |
+
"epoch": 3.6484330484330485,
|
| 22428 |
+
"grad_norm": 0.1582898199558258,
|
| 22429 |
+
"learning_rate": 4.73373298693013e-05,
|
| 22430 |
+
"loss": 0.9045,
|
| 22431 |
+
"step": 3203
|
| 22432 |
+
},
|
| 22433 |
+
{
|
| 22434 |
+
"epoch": 3.6495726495726495,
|
| 22435 |
+
"grad_norm": 0.18901553750038147,
|
| 22436 |
+
"learning_rate": 4.7335237151560176e-05,
|
| 22437 |
+
"loss": 0.6705,
|
| 22438 |
+
"step": 3204
|
| 22439 |
+
},
|
| 22440 |
+
{
|
| 22441 |
+
"epoch": 3.6507122507122505,
|
| 22442 |
+
"grad_norm": 0.13323083519935608,
|
| 22443 |
+
"learning_rate": 4.733314365805484e-05,
|
| 22444 |
+
"loss": 0.8926,
|
| 22445 |
+
"step": 3205
|
| 22446 |
+
},
|
| 22447 |
+
{
|
| 22448 |
+
"epoch": 3.651851851851852,
|
| 22449 |
+
"grad_norm": 0.13110944628715515,
|
| 22450 |
+
"learning_rate": 4.733104938885801e-05,
|
| 22451 |
+
"loss": 0.8441,
|
| 22452 |
+
"step": 3206
|
| 22453 |
+
},
|
| 22454 |
+
{
|
| 22455 |
+
"epoch": 3.652991452991453,
|
| 22456 |
+
"grad_norm": 0.18995679914951324,
|
| 22457 |
+
"learning_rate": 4.732895434404242e-05,
|
| 22458 |
+
"loss": 0.7849,
|
| 22459 |
+
"step": 3207
|
| 22460 |
+
},
|
| 22461 |
+
{
|
| 22462 |
+
"epoch": 3.654131054131054,
|
| 22463 |
+
"grad_norm": 0.1365271657705307,
|
| 22464 |
+
"learning_rate": 4.732685852368085e-05,
|
| 22465 |
+
"loss": 1.0407,
|
| 22466 |
+
"step": 3208
|
| 22467 |
+
},
|
| 22468 |
+
{
|
| 22469 |
+
"epoch": 3.6552706552706553,
|
| 22470 |
+
"grad_norm": 0.16701480746269226,
|
| 22471 |
+
"learning_rate": 4.732476192784608e-05,
|
| 22472 |
+
"loss": 0.5978,
|
| 22473 |
+
"step": 3209
|
| 22474 |
+
},
|
| 22475 |
+
{
|
| 22476 |
+
"epoch": 3.6564102564102563,
|
| 22477 |
+
"grad_norm": 0.1443236917257309,
|
| 22478 |
+
"learning_rate": 4.732266455661093e-05,
|
| 22479 |
+
"loss": 0.8791,
|
| 22480 |
+
"step": 3210
|
| 22481 |
+
},
|
| 22482 |
+
{
|
| 22483 |
+
"epoch": 3.6575498575498573,
|
| 22484 |
+
"grad_norm": 0.15609289705753326,
|
| 22485 |
+
"learning_rate": 4.732056641004826e-05,
|
| 22486 |
+
"loss": 0.7923,
|
| 22487 |
+
"step": 3211
|
| 22488 |
+
},
|
| 22489 |
+
{
|
| 22490 |
+
"epoch": 3.6586894586894587,
|
| 22491 |
+
"grad_norm": 0.17128822207450867,
|
| 22492 |
+
"learning_rate": 4.731846748823093e-05,
|
| 22493 |
+
"loss": 0.7968,
|
| 22494 |
+
"step": 3212
|
| 22495 |
+
},
|
| 22496 |
+
{
|
| 22497 |
+
"epoch": 3.6598290598290597,
|
| 22498 |
+
"grad_norm": 0.16645938158035278,
|
| 22499 |
+
"learning_rate": 4.731636779123185e-05,
|
| 22500 |
+
"loss": 0.7756,
|
| 22501 |
+
"step": 3213
|
| 22502 |
+
},
|
| 22503 |
+
{
|
| 22504 |
+
"epoch": 3.6609686609686607,
|
| 22505 |
+
"grad_norm": 0.1768391877412796,
|
| 22506 |
+
"learning_rate": 4.731426731912395e-05,
|
| 22507 |
+
"loss": 0.6578,
|
| 22508 |
+
"step": 3214
|
| 22509 |
+
},
|
| 22510 |
+
{
|
| 22511 |
+
"epoch": 3.662108262108262,
|
| 22512 |
+
"grad_norm": 0.14515741169452667,
|
| 22513 |
+
"learning_rate": 4.731216607198018e-05,
|
| 22514 |
+
"loss": 0.9738,
|
| 22515 |
+
"step": 3215
|
| 22516 |
+
},
|
| 22517 |
+
{
|
| 22518 |
+
"epoch": 3.663247863247863,
|
| 22519 |
+
"grad_norm": 0.15290328860282898,
|
| 22520 |
+
"learning_rate": 4.7310064049873525e-05,
|
| 22521 |
+
"loss": 0.8501,
|
| 22522 |
+
"step": 3216
|
| 22523 |
+
},
|
| 22524 |
+
{
|
| 22525 |
+
"epoch": 3.6643874643874645,
|
| 22526 |
+
"grad_norm": 0.1539739966392517,
|
| 22527 |
+
"learning_rate": 4.7307961252876985e-05,
|
| 22528 |
+
"loss": 0.8498,
|
| 22529 |
+
"step": 3217
|
| 22530 |
+
},
|
| 22531 |
+
{
|
| 22532 |
+
"epoch": 3.6655270655270655,
|
| 22533 |
+
"grad_norm": 0.170927956700325,
|
| 22534 |
+
"learning_rate": 4.730585768106362e-05,
|
| 22535 |
+
"loss": 0.7508,
|
| 22536 |
+
"step": 3218
|
| 22537 |
+
},
|
| 22538 |
+
{
|
| 22539 |
+
"epoch": 3.6666666666666665,
|
| 22540 |
+
"grad_norm": 0.17547346651554108,
|
| 22541 |
+
"learning_rate": 4.730375333450646e-05,
|
| 22542 |
+
"loss": 0.8683,
|
| 22543 |
+
"step": 3219
|
| 22544 |
+
},
|
| 22545 |
+
{
|
| 22546 |
+
"epoch": 3.667806267806268,
|
| 22547 |
+
"grad_norm": 0.1330338418483734,
|
| 22548 |
+
"learning_rate": 4.730164821327861e-05,
|
| 22549 |
+
"loss": 0.9195,
|
| 22550 |
+
"step": 3220
|
| 22551 |
+
},
|
| 22552 |
+
{
|
| 22553 |
+
"epoch": 3.668945868945869,
|
| 22554 |
+
"grad_norm": 0.13993962109088898,
|
| 22555 |
+
"learning_rate": 4.72995423174532e-05,
|
| 22556 |
+
"loss": 0.8747,
|
| 22557 |
+
"step": 3221
|
| 22558 |
+
},
|
| 22559 |
+
{
|
| 22560 |
+
"epoch": 3.67008547008547,
|
| 22561 |
+
"grad_norm": 0.1791338473558426,
|
| 22562 |
+
"learning_rate": 4.729743564710336e-05,
|
| 22563 |
+
"loss": 0.7849,
|
| 22564 |
+
"step": 3222
|
| 22565 |
+
},
|
| 22566 |
+
{
|
| 22567 |
+
"epoch": 3.6712250712250714,
|
| 22568 |
+
"grad_norm": 0.1725768744945526,
|
| 22569 |
+
"learning_rate": 4.729532820230225e-05,
|
| 22570 |
+
"loss": 0.9448,
|
| 22571 |
+
"step": 3223
|
| 22572 |
+
},
|
| 22573 |
+
{
|
| 22574 |
+
"epoch": 3.6723646723646723,
|
| 22575 |
+
"grad_norm": 0.16085100173950195,
|
| 22576 |
+
"learning_rate": 4.72932199831231e-05,
|
| 22577 |
+
"loss": 0.7872,
|
| 22578 |
+
"step": 3224
|
| 22579 |
+
},
|
| 22580 |
+
{
|
| 22581 |
+
"epoch": 3.6735042735042738,
|
| 22582 |
+
"grad_norm": 0.15714609622955322,
|
| 22583 |
+
"learning_rate": 4.729111098963909e-05,
|
| 22584 |
+
"loss": 0.7453,
|
| 22585 |
+
"step": 3225
|
| 22586 |
+
},
|
| 22587 |
+
{
|
| 22588 |
+
"epoch": 3.6746438746438748,
|
| 22589 |
+
"grad_norm": 0.17268367111682892,
|
| 22590 |
+
"learning_rate": 4.728900122192351e-05,
|
| 22591 |
+
"loss": 0.7574,
|
| 22592 |
+
"step": 3226
|
| 22593 |
+
},
|
| 22594 |
+
{
|
| 22595 |
+
"epoch": 3.6757834757834758,
|
| 22596 |
+
"grad_norm": 0.14194540679454803,
|
| 22597 |
+
"learning_rate": 4.728689068004961e-05,
|
| 22598 |
+
"loss": 0.6415,
|
| 22599 |
+
"step": 3227
|
| 22600 |
+
},
|
| 22601 |
+
{
|
| 22602 |
+
"epoch": 3.676923076923077,
|
| 22603 |
+
"grad_norm": 0.18830282986164093,
|
| 22604 |
+
"learning_rate": 4.7284779364090716e-05,
|
| 22605 |
+
"loss": 0.7544,
|
| 22606 |
+
"step": 3228
|
| 22607 |
+
},
|
| 22608 |
+
{
|
| 22609 |
+
"epoch": 3.678062678062678,
|
| 22610 |
+
"grad_norm": 0.14973561465740204,
|
| 22611 |
+
"learning_rate": 4.7282667274120153e-05,
|
| 22612 |
+
"loss": 0.9419,
|
| 22613 |
+
"step": 3229
|
| 22614 |
+
},
|
| 22615 |
+
{
|
| 22616 |
+
"epoch": 3.679202279202279,
|
| 22617 |
+
"grad_norm": 0.17502374947071075,
|
| 22618 |
+
"learning_rate": 4.728055441021128e-05,
|
| 22619 |
+
"loss": 0.7105,
|
| 22620 |
+
"step": 3230
|
| 22621 |
+
},
|
| 22622 |
+
{
|
| 22623 |
+
"epoch": 3.6803418803418806,
|
| 22624 |
+
"grad_norm": 0.15161217749118805,
|
| 22625 |
+
"learning_rate": 4.7278440772437473e-05,
|
| 22626 |
+
"loss": 0.7876,
|
| 22627 |
+
"step": 3231
|
| 22628 |
+
},
|
| 22629 |
+
{
|
| 22630 |
+
"epoch": 3.6814814814814816,
|
| 22631 |
+
"grad_norm": 0.1851918250322342,
|
| 22632 |
+
"learning_rate": 4.727632636087215e-05,
|
| 22633 |
+
"loss": 0.5753,
|
| 22634 |
+
"step": 3232
|
| 22635 |
+
},
|
| 22636 |
+
{
|
| 22637 |
+
"epoch": 3.6826210826210826,
|
| 22638 |
+
"grad_norm": 0.17830820381641388,
|
| 22639 |
+
"learning_rate": 4.7274211175588757e-05,
|
| 22640 |
+
"loss": 0.6505,
|
| 22641 |
+
"step": 3233
|
| 22642 |
+
},
|
| 22643 |
+
{
|
| 22644 |
+
"epoch": 3.683760683760684,
|
| 22645 |
+
"grad_norm": 0.1459147185087204,
|
| 22646 |
+
"learning_rate": 4.727209521666075e-05,
|
| 22647 |
+
"loss": 0.7728,
|
| 22648 |
+
"step": 3234
|
| 22649 |
+
},
|
| 22650 |
+
{
|
| 22651 |
+
"epoch": 3.684900284900285,
|
| 22652 |
+
"grad_norm": 0.14419788122177124,
|
| 22653 |
+
"learning_rate": 4.7269978484161633e-05,
|
| 22654 |
+
"loss": 0.9277,
|
| 22655 |
+
"step": 3235
|
| 22656 |
+
},
|
| 22657 |
+
{
|
| 22658 |
+
"epoch": 3.686039886039886,
|
| 22659 |
+
"grad_norm": 0.12847690284252167,
|
| 22660 |
+
"learning_rate": 4.726786097816492e-05,
|
| 22661 |
+
"loss": 1.0063,
|
| 22662 |
+
"step": 3236
|
| 22663 |
+
},
|
| 22664 |
+
{
|
| 22665 |
+
"epoch": 3.6871794871794874,
|
| 22666 |
+
"grad_norm": 0.16791048645973206,
|
| 22667 |
+
"learning_rate": 4.726574269874416e-05,
|
| 22668 |
+
"loss": 0.8008,
|
| 22669 |
+
"step": 3237
|
| 22670 |
+
},
|
| 22671 |
+
{
|
| 22672 |
+
"epoch": 3.6883190883190884,
|
| 22673 |
+
"grad_norm": 0.13223494589328766,
|
| 22674 |
+
"learning_rate": 4.7263623645972935e-05,
|
| 22675 |
+
"loss": 0.8122,
|
| 22676 |
+
"step": 3238
|
| 22677 |
+
},
|
| 22678 |
+
{
|
| 22679 |
+
"epoch": 3.6894586894586894,
|
| 22680 |
+
"grad_norm": 0.16067475080490112,
|
| 22681 |
+
"learning_rate": 4.726150381992482e-05,
|
| 22682 |
+
"loss": 0.7976,
|
| 22683 |
+
"step": 3239
|
| 22684 |
+
},
|
| 22685 |
+
{
|
| 22686 |
+
"epoch": 3.690598290598291,
|
| 22687 |
+
"grad_norm": 0.17711344361305237,
|
| 22688 |
+
"learning_rate": 4.725938322067346e-05,
|
| 22689 |
+
"loss": 0.8262,
|
| 22690 |
+
"step": 3240
|
| 22691 |
+
},
|
| 22692 |
+
{
|
| 22693 |
+
"epoch": 3.691737891737892,
|
| 22694 |
+
"grad_norm": 0.1587996780872345,
|
| 22695 |
+
"learning_rate": 4.725726184829251e-05,
|
| 22696 |
+
"loss": 0.7744,
|
| 22697 |
+
"step": 3241
|
| 22698 |
+
},
|
| 22699 |
+
{
|
| 22700 |
+
"epoch": 3.692877492877493,
|
| 22701 |
+
"grad_norm": 0.14792990684509277,
|
| 22702 |
+
"learning_rate": 4.725513970285565e-05,
|
| 22703 |
+
"loss": 0.9333,
|
| 22704 |
+
"step": 3242
|
| 22705 |
+
},
|
| 22706 |
+
{
|
| 22707 |
+
"epoch": 3.694017094017094,
|
| 22708 |
+
"grad_norm": 0.16375887393951416,
|
| 22709 |
+
"learning_rate": 4.725301678443659e-05,
|
| 22710 |
+
"loss": 0.8978,
|
| 22711 |
+
"step": 3243
|
| 22712 |
+
},
|
| 22713 |
+
{
|
| 22714 |
+
"epoch": 3.695156695156695,
|
| 22715 |
+
"grad_norm": 0.1641547977924347,
|
| 22716 |
+
"learning_rate": 4.725089309310905e-05,
|
| 22717 |
+
"loss": 0.7527,
|
| 22718 |
+
"step": 3244
|
| 22719 |
+
},
|
| 22720 |
+
{
|
| 22721 |
+
"epoch": 3.696296296296296,
|
| 22722 |
+
"grad_norm": 0.1527947634458542,
|
| 22723 |
+
"learning_rate": 4.7248768628946805e-05,
|
| 22724 |
+
"loss": 0.8253,
|
| 22725 |
+
"step": 3245
|
| 22726 |
+
},
|
| 22727 |
+
{
|
| 22728 |
+
"epoch": 3.6974358974358976,
|
| 22729 |
+
"grad_norm": 0.17005781829357147,
|
| 22730 |
+
"learning_rate": 4.7246643392023647e-05,
|
| 22731 |
+
"loss": 0.6966,
|
| 22732 |
+
"step": 3246
|
| 22733 |
+
},
|
| 22734 |
+
{
|
| 22735 |
+
"epoch": 3.6985754985754986,
|
| 22736 |
+
"grad_norm": 0.19834214448928833,
|
| 22737 |
+
"learning_rate": 4.7244517382413385e-05,
|
| 22738 |
+
"loss": 0.7864,
|
| 22739 |
+
"step": 3247
|
| 22740 |
+
},
|
| 22741 |
+
{
|
| 22742 |
+
"epoch": 3.6997150997150996,
|
| 22743 |
+
"grad_norm": 0.1645403653383255,
|
| 22744 |
+
"learning_rate": 4.724239060018985e-05,
|
| 22745 |
+
"loss": 0.8421,
|
| 22746 |
+
"step": 3248
|
| 22747 |
+
},
|
| 22748 |
+
{
|
| 22749 |
+
"epoch": 3.700854700854701,
|
| 22750 |
+
"grad_norm": 0.15105541050434113,
|
| 22751 |
+
"learning_rate": 4.7240263045426934e-05,
|
| 22752 |
+
"loss": 0.8767,
|
| 22753 |
+
"step": 3249
|
| 22754 |
+
},
|
| 22755 |
+
{
|
| 22756 |
+
"epoch": 3.701994301994302,
|
| 22757 |
+
"grad_norm": 0.13681286573410034,
|
| 22758 |
+
"learning_rate": 4.723813471819852e-05,
|
| 22759 |
+
"loss": 0.8714,
|
| 22760 |
+
"step": 3250
|
| 22761 |
+
},
|
| 22762 |
+
{
|
| 22763 |
+
"epoch": 3.703133903133903,
|
| 22764 |
+
"grad_norm": 0.15862339735031128,
|
| 22765 |
+
"learning_rate": 4.723600561857854e-05,
|
| 22766 |
+
"loss": 0.6707,
|
| 22767 |
+
"step": 3251
|
| 22768 |
+
},
|
| 22769 |
+
{
|
| 22770 |
+
"epoch": 3.7042735042735044,
|
| 22771 |
+
"grad_norm": 0.14312617480754852,
|
| 22772 |
+
"learning_rate": 4.723387574664092e-05,
|
| 22773 |
+
"loss": 0.8925,
|
| 22774 |
+
"step": 3252
|
| 22775 |
+
},
|
| 22776 |
+
{
|
| 22777 |
+
"epoch": 3.7054131054131054,
|
| 22778 |
+
"grad_norm": 0.1338813751935959,
|
| 22779 |
+
"learning_rate": 4.723174510245966e-05,
|
| 22780 |
+
"loss": 1.0258,
|
| 22781 |
+
"step": 3253
|
| 22782 |
+
},
|
| 22783 |
+
{
|
| 22784 |
+
"epoch": 3.7065527065527064,
|
| 22785 |
+
"grad_norm": 0.1546410769224167,
|
| 22786 |
+
"learning_rate": 4.722961368610876e-05,
|
| 22787 |
+
"loss": 0.78,
|
| 22788 |
+
"step": 3254
|
| 22789 |
+
},
|
| 22790 |
+
{
|
| 22791 |
+
"epoch": 3.707692307692308,
|
| 22792 |
+
"grad_norm": 0.1816253811120987,
|
| 22793 |
+
"learning_rate": 4.722748149766224e-05,
|
| 22794 |
+
"loss": 0.8125,
|
| 22795 |
+
"step": 3255
|
| 22796 |
+
},
|
| 22797 |
+
{
|
| 22798 |
+
"epoch": 3.708831908831909,
|
| 22799 |
+
"grad_norm": 0.1573161780834198,
|
| 22800 |
+
"learning_rate": 4.722534853719416e-05,
|
| 22801 |
+
"loss": 0.8516,
|
| 22802 |
+
"step": 3256
|
| 22803 |
+
},
|
| 22804 |
+
{
|
| 22805 |
+
"epoch": 3.70997150997151,
|
| 22806 |
+
"grad_norm": 0.158403217792511,
|
| 22807 |
+
"learning_rate": 4.7223214804778604e-05,
|
| 22808 |
+
"loss": 0.8635,
|
| 22809 |
+
"step": 3257
|
| 22810 |
+
},
|
| 22811 |
+
{
|
| 22812 |
+
"epoch": 3.7111111111111112,
|
| 22813 |
+
"grad_norm": 0.17837317287921906,
|
| 22814 |
+
"learning_rate": 4.722108030048968e-05,
|
| 22815 |
+
"loss": 0.9281,
|
| 22816 |
+
"step": 3258
|
| 22817 |
+
},
|
| 22818 |
+
{
|
| 22819 |
+
"epoch": 3.7122507122507122,
|
| 22820 |
+
"grad_norm": 0.14864912629127502,
|
| 22821 |
+
"learning_rate": 4.721894502440154e-05,
|
| 22822 |
+
"loss": 0.8862,
|
| 22823 |
+
"step": 3259
|
| 22824 |
+
},
|
| 22825 |
+
{
|
| 22826 |
+
"epoch": 3.7133903133903132,
|
| 22827 |
+
"grad_norm": 0.17327450215816498,
|
| 22828 |
+
"learning_rate": 4.721680897658833e-05,
|
| 22829 |
+
"loss": 0.7906,
|
| 22830 |
+
"step": 3260
|
| 22831 |
+
},
|
| 22832 |
+
{
|
| 22833 |
+
"epoch": 3.7145299145299147,
|
| 22834 |
+
"grad_norm": 0.1560973972082138,
|
| 22835 |
+
"learning_rate": 4.721467215712425e-05,
|
| 22836 |
+
"loss": 0.9117,
|
| 22837 |
+
"step": 3261
|
| 22838 |
+
},
|
| 22839 |
+
{
|
| 22840 |
+
"epoch": 3.7156695156695156,
|
| 22841 |
+
"grad_norm": 0.1419924944639206,
|
| 22842 |
+
"learning_rate": 4.721253456608352e-05,
|
| 22843 |
+
"loss": 0.9314,
|
| 22844 |
+
"step": 3262
|
| 22845 |
+
},
|
| 22846 |
+
{
|
| 22847 |
+
"epoch": 3.7168091168091166,
|
| 22848 |
+
"grad_norm": 0.16928216814994812,
|
| 22849 |
+
"learning_rate": 4.721039620354038e-05,
|
| 22850 |
+
"loss": 0.6262,
|
| 22851 |
+
"step": 3263
|
| 22852 |
+
},
|
| 22853 |
+
{
|
| 22854 |
+
"epoch": 3.717948717948718,
|
| 22855 |
+
"grad_norm": 0.15330585837364197,
|
| 22856 |
+
"learning_rate": 4.720825706956909e-05,
|
| 22857 |
+
"loss": 0.8932,
|
| 22858 |
+
"step": 3264
|
| 22859 |
+
},
|
| 22860 |
+
{
|
| 22861 |
+
"epoch": 3.719088319088319,
|
| 22862 |
+
"grad_norm": 0.14610134065151215,
|
| 22863 |
+
"learning_rate": 4.7206117164243966e-05,
|
| 22864 |
+
"loss": 0.8271,
|
| 22865 |
+
"step": 3265
|
| 22866 |
+
},
|
| 22867 |
+
{
|
| 22868 |
+
"epoch": 3.72022792022792,
|
| 22869 |
+
"grad_norm": 0.1372208148241043,
|
| 22870 |
+
"learning_rate": 4.7203976487639326e-05,
|
| 22871 |
+
"loss": 0.8912,
|
| 22872 |
+
"step": 3266
|
| 22873 |
+
},
|
| 22874 |
+
{
|
| 22875 |
+
"epoch": 3.7213675213675215,
|
| 22876 |
+
"grad_norm": 0.1757371574640274,
|
| 22877 |
+
"learning_rate": 4.7201835039829524e-05,
|
| 22878 |
+
"loss": 0.8377,
|
| 22879 |
+
"step": 3267
|
| 22880 |
+
},
|
| 22881 |
+
{
|
| 22882 |
+
"epoch": 3.7225071225071225,
|
| 22883 |
+
"grad_norm": 0.17159296572208405,
|
| 22884 |
+
"learning_rate": 4.719969282088893e-05,
|
| 22885 |
+
"loss": 0.7907,
|
| 22886 |
+
"step": 3268
|
| 22887 |
+
},
|
| 22888 |
+
{
|
| 22889 |
+
"epoch": 3.7236467236467234,
|
| 22890 |
+
"grad_norm": 0.13616004586219788,
|
| 22891 |
+
"learning_rate": 4.719754983089195e-05,
|
| 22892 |
+
"loss": 0.8665,
|
| 22893 |
+
"step": 3269
|
| 22894 |
+
},
|
| 22895 |
+
{
|
| 22896 |
+
"epoch": 3.724786324786325,
|
| 22897 |
+
"grad_norm": 0.14465661346912384,
|
| 22898 |
+
"learning_rate": 4.719540606991303e-05,
|
| 22899 |
+
"loss": 0.8498,
|
| 22900 |
+
"step": 3270
|
| 22901 |
+
},
|
| 22902 |
+
{
|
| 22903 |
+
"epoch": 3.725925925925926,
|
| 22904 |
+
"grad_norm": 0.1675175577402115,
|
| 22905 |
+
"learning_rate": 4.719326153802662e-05,
|
| 22906 |
+
"loss": 0.6964,
|
| 22907 |
+
"step": 3271
|
| 22908 |
+
},
|
| 22909 |
+
{
|
| 22910 |
+
"epoch": 3.727065527065527,
|
| 22911 |
+
"grad_norm": 0.14356575906276703,
|
| 22912 |
+
"learning_rate": 4.71911162353072e-05,
|
| 22913 |
+
"loss": 0.8681,
|
| 22914 |
+
"step": 3272
|
| 22915 |
+
},
|
| 22916 |
+
{
|
| 22917 |
+
"epoch": 3.7282051282051283,
|
| 22918 |
+
"grad_norm": 0.14403332769870758,
|
| 22919 |
+
"learning_rate": 4.718897016182929e-05,
|
| 22920 |
+
"loss": 0.8282,
|
| 22921 |
+
"step": 3273
|
| 22922 |
+
},
|
| 22923 |
+
{
|
| 22924 |
+
"epoch": 3.7293447293447293,
|
| 22925 |
+
"grad_norm": 0.13207969069480896,
|
| 22926 |
+
"learning_rate": 4.7186823317667425e-05,
|
| 22927 |
+
"loss": 0.8278,
|
| 22928 |
+
"step": 3274
|
| 22929 |
+
},
|
| 22930 |
+
{
|
| 22931 |
+
"epoch": 3.7304843304843303,
|
| 22932 |
+
"grad_norm": 0.1665349304676056,
|
| 22933 |
+
"learning_rate": 4.718467570289618e-05,
|
| 22934 |
+
"loss": 0.7893,
|
| 22935 |
+
"step": 3275
|
| 22936 |
+
},
|
| 22937 |
+
{
|
| 22938 |
+
"epoch": 3.7316239316239317,
|
| 22939 |
+
"grad_norm": 0.16078945994377136,
|
| 22940 |
+
"learning_rate": 4.718252731759013e-05,
|
| 22941 |
+
"loss": 0.7598,
|
| 22942 |
+
"step": 3276
|
| 22943 |
+
},
|
| 22944 |
+
{
|
| 22945 |
+
"epoch": 3.7327635327635327,
|
| 22946 |
+
"grad_norm": 0.18205560743808746,
|
| 22947 |
+
"learning_rate": 4.718037816182391e-05,
|
| 22948 |
+
"loss": 0.7266,
|
| 22949 |
+
"step": 3277
|
| 22950 |
+
},
|
| 22951 |
+
{
|
| 22952 |
+
"epoch": 3.7339031339031337,
|
| 22953 |
+
"grad_norm": 0.2010476142168045,
|
| 22954 |
+
"learning_rate": 4.717822823567216e-05,
|
| 22955 |
+
"loss": 0.6091,
|
| 22956 |
+
"step": 3278
|
| 22957 |
+
},
|
| 22958 |
+
{
|
| 22959 |
+
"epoch": 3.735042735042735,
|
| 22960 |
+
"grad_norm": 0.16430054605007172,
|
| 22961 |
+
"learning_rate": 4.717607753920955e-05,
|
| 22962 |
+
"loss": 0.8155,
|
| 22963 |
+
"step": 3279
|
| 22964 |
+
},
|
| 22965 |
+
{
|
| 22966 |
+
"epoch": 3.736182336182336,
|
| 22967 |
+
"grad_norm": 0.1744856834411621,
|
| 22968 |
+
"learning_rate": 4.7173926072510774e-05,
|
| 22969 |
+
"loss": 0.7571,
|
| 22970 |
+
"step": 3280
|
| 22971 |
+
},
|
| 22972 |
+
{
|
| 22973 |
+
"epoch": 3.737321937321937,
|
| 22974 |
+
"grad_norm": 0.15343201160430908,
|
| 22975 |
+
"learning_rate": 4.717177383565058e-05,
|
| 22976 |
+
"loss": 0.8475,
|
| 22977 |
+
"step": 3281
|
| 22978 |
+
},
|
| 22979 |
+
{
|
| 22980 |
+
"epoch": 3.7384615384615385,
|
| 22981 |
+
"grad_norm": 0.1410541534423828,
|
| 22982 |
+
"learning_rate": 4.716962082870371e-05,
|
| 22983 |
+
"loss": 0.8938,
|
| 22984 |
+
"step": 3282
|
| 22985 |
+
},
|
| 22986 |
+
{
|
| 22987 |
+
"epoch": 3.7396011396011395,
|
| 22988 |
+
"grad_norm": 0.14926479756832123,
|
| 22989 |
+
"learning_rate": 4.7167467051744926e-05,
|
| 22990 |
+
"loss": 0.7719,
|
| 22991 |
+
"step": 3283
|
| 22992 |
+
},
|
| 22993 |
+
{
|
| 22994 |
+
"epoch": 3.7407407407407405,
|
| 22995 |
+
"grad_norm": 0.1376180797815323,
|
| 22996 |
+
"learning_rate": 4.7165312504849065e-05,
|
| 22997 |
+
"loss": 0.8868,
|
| 22998 |
+
"step": 3284
|
| 22999 |
+
},
|
| 23000 |
+
{
|
| 23001 |
+
"epoch": 3.741880341880342,
|
| 23002 |
+
"grad_norm": 0.1488949954509735,
|
| 23003 |
+
"learning_rate": 4.716315718809094e-05,
|
| 23004 |
+
"loss": 0.8712,
|
| 23005 |
+
"step": 3285
|
| 23006 |
+
},
|
| 23007 |
+
{
|
| 23008 |
+
"epoch": 3.743019943019943,
|
| 23009 |
+
"grad_norm": 0.13525907695293427,
|
| 23010 |
+
"learning_rate": 4.716100110154542e-05,
|
| 23011 |
+
"loss": 0.8757,
|
| 23012 |
+
"step": 3286
|
| 23013 |
+
},
|
| 23014 |
+
{
|
| 23015 |
+
"epoch": 3.744159544159544,
|
| 23016 |
+
"grad_norm": 0.1648627072572708,
|
| 23017 |
+
"learning_rate": 4.715884424528739e-05,
|
| 23018 |
+
"loss": 0.7802,
|
| 23019 |
+
"step": 3287
|
| 23020 |
+
},
|
| 23021 |
+
{
|
| 23022 |
+
"epoch": 3.7452991452991453,
|
| 23023 |
+
"grad_norm": 0.13732190430164337,
|
| 23024 |
+
"learning_rate": 4.7156686619391755e-05,
|
| 23025 |
+
"loss": 1.07,
|
| 23026 |
+
"step": 3288
|
| 23027 |
+
},
|
| 23028 |
+
{
|
| 23029 |
+
"epoch": 3.7464387464387463,
|
| 23030 |
+
"grad_norm": 0.1729089766740799,
|
| 23031 |
+
"learning_rate": 4.715452822393347e-05,
|
| 23032 |
+
"loss": 0.7759,
|
| 23033 |
+
"step": 3289
|
| 23034 |
+
},
|
| 23035 |
+
{
|
| 23036 |
+
"epoch": 3.7475783475783477,
|
| 23037 |
+
"grad_norm": 0.14817307889461517,
|
| 23038 |
+
"learning_rate": 4.715236905898749e-05,
|
| 23039 |
+
"loss": 0.9599,
|
| 23040 |
+
"step": 3290
|
| 23041 |
+
},
|
| 23042 |
+
{
|
| 23043 |
+
"epoch": 3.7487179487179487,
|
| 23044 |
+
"grad_norm": 0.1385723501443863,
|
| 23045 |
+
"learning_rate": 4.715020912462882e-05,
|
| 23046 |
+
"loss": 0.9544,
|
| 23047 |
+
"step": 3291
|
| 23048 |
+
},
|
| 23049 |
+
{
|
| 23050 |
+
"epoch": 3.7498575498575497,
|
| 23051 |
+
"grad_norm": 0.1851496547460556,
|
| 23052 |
+
"learning_rate": 4.714804842093247e-05,
|
| 23053 |
+
"loss": 0.7674,
|
| 23054 |
+
"step": 3292
|
| 23055 |
+
},
|
| 23056 |
+
{
|
| 23057 |
+
"epoch": 3.750997150997151,
|
| 23058 |
+
"grad_norm": 0.1579301357269287,
|
| 23059 |
+
"learning_rate": 4.7145886947973485e-05,
|
| 23060 |
+
"loss": 0.7869,
|
| 23061 |
+
"step": 3293
|
| 23062 |
+
},
|
| 23063 |
+
{
|
| 23064 |
+
"epoch": 3.752136752136752,
|
| 23065 |
+
"grad_norm": 0.19079633057117462,
|
| 23066 |
+
"learning_rate": 4.714372470582695e-05,
|
| 23067 |
+
"loss": 0.7055,
|
| 23068 |
+
"step": 3294
|
| 23069 |
+
},
|
| 23070 |
+
{
|
| 23071 |
+
"epoch": 3.753276353276353,
|
| 23072 |
+
"grad_norm": 0.15140880644321442,
|
| 23073 |
+
"learning_rate": 4.714156169456796e-05,
|
| 23074 |
+
"loss": 0.9413,
|
| 23075 |
+
"step": 3295
|
| 23076 |
+
},
|
| 23077 |
+
{
|
| 23078 |
+
"epoch": 3.7544159544159545,
|
| 23079 |
+
"grad_norm": 0.17241929471492767,
|
| 23080 |
+
"learning_rate": 4.7139397914271646e-05,
|
| 23081 |
+
"loss": 0.8051,
|
| 23082 |
+
"step": 3296
|
| 23083 |
+
},
|
| 23084 |
+
{
|
| 23085 |
+
"epoch": 3.7555555555555555,
|
| 23086 |
+
"grad_norm": 0.1487005650997162,
|
| 23087 |
+
"learning_rate": 4.713723336501316e-05,
|
| 23088 |
+
"loss": 0.9048,
|
| 23089 |
+
"step": 3297
|
| 23090 |
+
},
|
| 23091 |
+
{
|
| 23092 |
+
"epoch": 3.756695156695157,
|
| 23093 |
+
"grad_norm": 0.1777118444442749,
|
| 23094 |
+
"learning_rate": 4.713506804686767e-05,
|
| 23095 |
+
"loss": 0.7942,
|
| 23096 |
+
"step": 3298
|
| 23097 |
+
},
|
| 23098 |
+
{
|
| 23099 |
+
"epoch": 3.757834757834758,
|
| 23100 |
+
"grad_norm": 0.12350175529718399,
|
| 23101 |
+
"learning_rate": 4.71329019599104e-05,
|
| 23102 |
+
"loss": 0.965,
|
| 23103 |
+
"step": 3299
|
| 23104 |
+
},
|
| 23105 |
+
{
|
| 23106 |
+
"epoch": 3.758974358974359,
|
| 23107 |
+
"grad_norm": 0.1593742072582245,
|
| 23108 |
+
"learning_rate": 4.7130735104216584e-05,
|
| 23109 |
+
"loss": 0.7879,
|
| 23110 |
+
"step": 3300
|
| 23111 |
}
|
| 23112 |
],
|
| 23113 |
"logging_steps": 1,
|
|
|
|
| 23127 |
"attributes": {}
|
| 23128 |
}
|
| 23129 |
},
|
| 23130 |
+
"total_flos": 1.845375586804187e+19,
|
| 23131 |
"train_batch_size": 8,
|
| 23132 |
"trial_name": null,
|
| 23133 |
"trial_params": null
|