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 12000, 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 sha256:74f26b71f918f35f82b7619b7c0474c84f5458cb0a59a763857b46d8d8b8dcd5
|
| 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:db1fae40f906bedad506735429fcfbcbdd3393be8e7d10b46a2fb1208afc69ed
|
| 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 sha256:1aa3d0afef84dbf8ef9b1a8d797126e838811675bb833ab5844a6a0c43d19b2b
|
| 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": 13.
|
| 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,
|
|
@@ -81908,6 +81908,2106 @@
|
|
| 81908 |
"learning_rate": 1.3488842449949418e-05,
|
| 81909 |
"loss": 0.6381,
|
| 81910 |
"step": 11700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81911 |
}
|
| 81912 |
],
|
| 81913 |
"logging_steps": 1,
|
|
@@ -81927,7 +84027,7 @@
|
|
| 81927 |
"attributes": {}
|
| 81928 |
}
|
| 81929 |
},
|
| 81930 |
-
"total_flos": 6.
|
| 81931 |
"train_batch_size": 8,
|
| 81932 |
"trial_name": null,
|
| 81933 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.667806267806268,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 12000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 81908 |
"learning_rate": 1.3488842449949418e-05,
|
| 81909 |
"loss": 0.6381,
|
| 81910 |
"step": 11700
|
| 81911 |
+
},
|
| 81912 |
+
{
|
| 81913 |
+
"epoch": 13.327065527065526,
|
| 81914 |
+
"grad_norm": 0.23498138785362244,
|
| 81915 |
+
"learning_rate": 1.3484706752753065e-05,
|
| 81916 |
+
"loss": 0.7115,
|
| 81917 |
+
"step": 11701
|
| 81918 |
+
},
|
| 81919 |
+
{
|
| 81920 |
+
"epoch": 13.328205128205129,
|
| 81921 |
+
"grad_norm": 0.26574021577835083,
|
| 81922 |
+
"learning_rate": 1.3480571455514512e-05,
|
| 81923 |
+
"loss": 0.618,
|
| 81924 |
+
"step": 11702
|
| 81925 |
+
},
|
| 81926 |
+
{
|
| 81927 |
+
"epoch": 13.32934472934473,
|
| 81928 |
+
"grad_norm": 0.2008192092180252,
|
| 81929 |
+
"learning_rate": 1.3476436558377392e-05,
|
| 81930 |
+
"loss": 0.8789,
|
| 81931 |
+
"step": 11703
|
| 81932 |
+
},
|
| 81933 |
+
{
|
| 81934 |
+
"epoch": 13.33048433048433,
|
| 81935 |
+
"grad_norm": 0.19755418598651886,
|
| 81936 |
+
"learning_rate": 1.347230206148533e-05,
|
| 81937 |
+
"loss": 0.7185,
|
| 81938 |
+
"step": 11704
|
| 81939 |
+
},
|
| 81940 |
+
{
|
| 81941 |
+
"epoch": 13.331623931623932,
|
| 81942 |
+
"grad_norm": 0.17471033334732056,
|
| 81943 |
+
"learning_rate": 1.346816796498191e-05,
|
| 81944 |
+
"loss": 0.8852,
|
| 81945 |
+
"step": 11705
|
| 81946 |
+
},
|
| 81947 |
+
{
|
| 81948 |
+
"epoch": 13.332763532763533,
|
| 81949 |
+
"grad_norm": 0.8952785134315491,
|
| 81950 |
+
"learning_rate": 1.3464034269010728e-05,
|
| 81951 |
+
"loss": 0.7773,
|
| 81952 |
+
"step": 11706
|
| 81953 |
+
},
|
| 81954 |
+
{
|
| 81955 |
+
"epoch": 13.333903133903133,
|
| 81956 |
+
"grad_norm": 0.17916469275951385,
|
| 81957 |
+
"learning_rate": 1.3459900973715362e-05,
|
| 81958 |
+
"loss": 0.7367,
|
| 81959 |
+
"step": 11707
|
| 81960 |
+
},
|
| 81961 |
+
{
|
| 81962 |
+
"epoch": 13.335042735042736,
|
| 81963 |
+
"grad_norm": 0.21020612120628357,
|
| 81964 |
+
"learning_rate": 1.3455768079239375e-05,
|
| 81965 |
+
"loss": 0.7739,
|
| 81966 |
+
"step": 11708
|
| 81967 |
+
},
|
| 81968 |
+
{
|
| 81969 |
+
"epoch": 13.336182336182336,
|
| 81970 |
+
"grad_norm": 0.15315940976142883,
|
| 81971 |
+
"learning_rate": 1.3451635585726303e-05,
|
| 81972 |
+
"loss": 0.6165,
|
| 81973 |
+
"step": 11709
|
| 81974 |
+
},
|
| 81975 |
+
{
|
| 81976 |
+
"epoch": 13.337321937321937,
|
| 81977 |
+
"grad_norm": 0.21983729302883148,
|
| 81978 |
+
"learning_rate": 1.3447503493319686e-05,
|
| 81979 |
+
"loss": 0.5992,
|
| 81980 |
+
"step": 11710
|
| 81981 |
+
},
|
| 81982 |
+
{
|
| 81983 |
+
"epoch": 13.338461538461539,
|
| 81984 |
+
"grad_norm": 0.23087336122989655,
|
| 81985 |
+
"learning_rate": 1.344337180216304e-05,
|
| 81986 |
+
"loss": 0.4929,
|
| 81987 |
+
"step": 11711
|
| 81988 |
+
},
|
| 81989 |
+
{
|
| 81990 |
+
"epoch": 13.33960113960114,
|
| 81991 |
+
"grad_norm": 0.19386158883571625,
|
| 81992 |
+
"learning_rate": 1.3439240512399875e-05,
|
| 81993 |
+
"loss": 0.6294,
|
| 81994 |
+
"step": 11712
|
| 81995 |
+
},
|
| 81996 |
+
{
|
| 81997 |
+
"epoch": 13.34074074074074,
|
| 81998 |
+
"grad_norm": 0.213854119181633,
|
| 81999 |
+
"learning_rate": 1.3435109624173675e-05,
|
| 82000 |
+
"loss": 0.3712,
|
| 82001 |
+
"step": 11713
|
| 82002 |
+
},
|
| 82003 |
+
{
|
| 82004 |
+
"epoch": 13.341880341880342,
|
| 82005 |
+
"grad_norm": 0.20322713255882263,
|
| 82006 |
+
"learning_rate": 1.3430979137627924e-05,
|
| 82007 |
+
"loss": 0.7028,
|
| 82008 |
+
"step": 11714
|
| 82009 |
+
},
|
| 82010 |
+
{
|
| 82011 |
+
"epoch": 13.343019943019943,
|
| 82012 |
+
"grad_norm": 0.25743451714515686,
|
| 82013 |
+
"learning_rate": 1.3426849052906094e-05,
|
| 82014 |
+
"loss": 0.5265,
|
| 82015 |
+
"step": 11715
|
| 82016 |
+
},
|
| 82017 |
+
{
|
| 82018 |
+
"epoch": 13.344159544159544,
|
| 82019 |
+
"grad_norm": 0.15938548743724823,
|
| 82020 |
+
"learning_rate": 1.342271937015161e-05,
|
| 82021 |
+
"loss": 0.7474,
|
| 82022 |
+
"step": 11716
|
| 82023 |
+
},
|
| 82024 |
+
{
|
| 82025 |
+
"epoch": 13.345299145299146,
|
| 82026 |
+
"grad_norm": 0.2237337827682495,
|
| 82027 |
+
"learning_rate": 1.3418590089507921e-05,
|
| 82028 |
+
"loss": 0.6901,
|
| 82029 |
+
"step": 11717
|
| 82030 |
+
},
|
| 82031 |
+
{
|
| 82032 |
+
"epoch": 13.346438746438746,
|
| 82033 |
+
"grad_norm": 0.20207485556602478,
|
| 82034 |
+
"learning_rate": 1.3414461211118447e-05,
|
| 82035 |
+
"loss": 0.6515,
|
| 82036 |
+
"step": 11718
|
| 82037 |
+
},
|
| 82038 |
+
{
|
| 82039 |
+
"epoch": 13.347578347578347,
|
| 82040 |
+
"grad_norm": 0.1879969835281372,
|
| 82041 |
+
"learning_rate": 1.3410332735126607e-05,
|
| 82042 |
+
"loss": 0.6928,
|
| 82043 |
+
"step": 11719
|
| 82044 |
+
},
|
| 82045 |
+
{
|
| 82046 |
+
"epoch": 13.34871794871795,
|
| 82047 |
+
"grad_norm": 0.18650564551353455,
|
| 82048 |
+
"learning_rate": 1.340620466167577e-05,
|
| 82049 |
+
"loss": 0.8326,
|
| 82050 |
+
"step": 11720
|
| 82051 |
+
},
|
| 82052 |
+
{
|
| 82053 |
+
"epoch": 13.34985754985755,
|
| 82054 |
+
"grad_norm": 0.21093356609344482,
|
| 82055 |
+
"learning_rate": 1.340207699090933e-05,
|
| 82056 |
+
"loss": 0.6828,
|
| 82057 |
+
"step": 11721
|
| 82058 |
+
},
|
| 82059 |
+
{
|
| 82060 |
+
"epoch": 13.35099715099715,
|
| 82061 |
+
"grad_norm": 0.23285485804080963,
|
| 82062 |
+
"learning_rate": 1.3397949722970649e-05,
|
| 82063 |
+
"loss": 0.5843,
|
| 82064 |
+
"step": 11722
|
| 82065 |
+
},
|
| 82066 |
+
{
|
| 82067 |
+
"epoch": 13.352136752136753,
|
| 82068 |
+
"grad_norm": 0.25672730803489685,
|
| 82069 |
+
"learning_rate": 1.3393822858003083e-05,
|
| 82070 |
+
"loss": 0.6111,
|
| 82071 |
+
"step": 11723
|
| 82072 |
+
},
|
| 82073 |
+
{
|
| 82074 |
+
"epoch": 13.353276353276353,
|
| 82075 |
+
"grad_norm": 0.2889954447746277,
|
| 82076 |
+
"learning_rate": 1.3389696396149965e-05,
|
| 82077 |
+
"loss": 0.4769,
|
| 82078 |
+
"step": 11724
|
| 82079 |
+
},
|
| 82080 |
+
{
|
| 82081 |
+
"epoch": 13.354415954415954,
|
| 82082 |
+
"grad_norm": 0.2774520516395569,
|
| 82083 |
+
"learning_rate": 1.3385570337554617e-05,
|
| 82084 |
+
"loss": 0.739,
|
| 82085 |
+
"step": 11725
|
| 82086 |
+
},
|
| 82087 |
+
{
|
| 82088 |
+
"epoch": 13.355555555555556,
|
| 82089 |
+
"grad_norm": 0.2050815224647522,
|
| 82090 |
+
"learning_rate": 1.3381444682360365e-05,
|
| 82091 |
+
"loss": 0.6947,
|
| 82092 |
+
"step": 11726
|
| 82093 |
+
},
|
| 82094 |
+
{
|
| 82095 |
+
"epoch": 13.356695156695157,
|
| 82096 |
+
"grad_norm": 0.2372182309627533,
|
| 82097 |
+
"learning_rate": 1.3377319430710477e-05,
|
| 82098 |
+
"loss": 0.6744,
|
| 82099 |
+
"step": 11727
|
| 82100 |
+
},
|
| 82101 |
+
{
|
| 82102 |
+
"epoch": 13.357834757834757,
|
| 82103 |
+
"grad_norm": 0.1729559451341629,
|
| 82104 |
+
"learning_rate": 1.337319458274825e-05,
|
| 82105 |
+
"loss": 0.5814,
|
| 82106 |
+
"step": 11728
|
| 82107 |
+
},
|
| 82108 |
+
{
|
| 82109 |
+
"epoch": 13.35897435897436,
|
| 82110 |
+
"grad_norm": 0.2525213062763214,
|
| 82111 |
+
"learning_rate": 1.3369070138616945e-05,
|
| 82112 |
+
"loss": 0.5186,
|
| 82113 |
+
"step": 11729
|
| 82114 |
+
},
|
| 82115 |
+
{
|
| 82116 |
+
"epoch": 13.36011396011396,
|
| 82117 |
+
"grad_norm": 0.24681463837623596,
|
| 82118 |
+
"learning_rate": 1.3364946098459835e-05,
|
| 82119 |
+
"loss": 0.5953,
|
| 82120 |
+
"step": 11730
|
| 82121 |
+
},
|
| 82122 |
+
{
|
| 82123 |
+
"epoch": 13.36125356125356,
|
| 82124 |
+
"grad_norm": 0.2084857076406479,
|
| 82125 |
+
"learning_rate": 1.336082246242013e-05,
|
| 82126 |
+
"loss": 0.6919,
|
| 82127 |
+
"step": 11731
|
| 82128 |
+
},
|
| 82129 |
+
{
|
| 82130 |
+
"epoch": 13.362393162393163,
|
| 82131 |
+
"grad_norm": 0.1615460366010666,
|
| 82132 |
+
"learning_rate": 1.3356699230641067e-05,
|
| 82133 |
+
"loss": 0.9097,
|
| 82134 |
+
"step": 11732
|
| 82135 |
+
},
|
| 82136 |
+
{
|
| 82137 |
+
"epoch": 13.363532763532763,
|
| 82138 |
+
"grad_norm": 0.200116828083992,
|
| 82139 |
+
"learning_rate": 1.3352576403265862e-05,
|
| 82140 |
+
"loss": 0.8498,
|
| 82141 |
+
"step": 11733
|
| 82142 |
+
},
|
| 82143 |
+
{
|
| 82144 |
+
"epoch": 13.364672364672364,
|
| 82145 |
+
"grad_norm": 0.22976773977279663,
|
| 82146 |
+
"learning_rate": 1.3348453980437708e-05,
|
| 82147 |
+
"loss": 0.6947,
|
| 82148 |
+
"step": 11734
|
| 82149 |
+
},
|
| 82150 |
+
{
|
| 82151 |
+
"epoch": 13.365811965811966,
|
| 82152 |
+
"grad_norm": 0.21923796832561493,
|
| 82153 |
+
"learning_rate": 1.334433196229979e-05,
|
| 82154 |
+
"loss": 0.676,
|
| 82155 |
+
"step": 11735
|
| 82156 |
+
},
|
| 82157 |
+
{
|
| 82158 |
+
"epoch": 13.366951566951567,
|
| 82159 |
+
"grad_norm": 0.21256579458713531,
|
| 82160 |
+
"learning_rate": 1.3340210348995274e-05,
|
| 82161 |
+
"loss": 0.7264,
|
| 82162 |
+
"step": 11736
|
| 82163 |
+
},
|
| 82164 |
+
{
|
| 82165 |
+
"epoch": 13.368091168091167,
|
| 82166 |
+
"grad_norm": 0.1874372810125351,
|
| 82167 |
+
"learning_rate": 1.3336089140667321e-05,
|
| 82168 |
+
"loss": 0.7775,
|
| 82169 |
+
"step": 11737
|
| 82170 |
+
},
|
| 82171 |
+
{
|
| 82172 |
+
"epoch": 13.36923076923077,
|
| 82173 |
+
"grad_norm": 0.1841961294412613,
|
| 82174 |
+
"learning_rate": 1.3331968337459078e-05,
|
| 82175 |
+
"loss": 0.5427,
|
| 82176 |
+
"step": 11738
|
| 82177 |
+
},
|
| 82178 |
+
{
|
| 82179 |
+
"epoch": 13.37037037037037,
|
| 82180 |
+
"grad_norm": 0.2150958627462387,
|
| 82181 |
+
"learning_rate": 1.332784793951365e-05,
|
| 82182 |
+
"loss": 0.5171,
|
| 82183 |
+
"step": 11739
|
| 82184 |
+
},
|
| 82185 |
+
{
|
| 82186 |
+
"epoch": 13.37150997150997,
|
| 82187 |
+
"grad_norm": 0.21831750869750977,
|
| 82188 |
+
"learning_rate": 1.3323727946974158e-05,
|
| 82189 |
+
"loss": 0.6129,
|
| 82190 |
+
"step": 11740
|
| 82191 |
+
},
|
| 82192 |
+
{
|
| 82193 |
+
"epoch": 13.372649572649573,
|
| 82194 |
+
"grad_norm": 0.22264201939105988,
|
| 82195 |
+
"learning_rate": 1.331960835998371e-05,
|
| 82196 |
+
"loss": 0.5797,
|
| 82197 |
+
"step": 11741
|
| 82198 |
+
},
|
| 82199 |
+
{
|
| 82200 |
+
"epoch": 13.373789173789174,
|
| 82201 |
+
"grad_norm": 0.22739334404468536,
|
| 82202 |
+
"learning_rate": 1.3315489178685391e-05,
|
| 82203 |
+
"loss": 0.626,
|
| 82204 |
+
"step": 11742
|
| 82205 |
+
},
|
| 82206 |
+
{
|
| 82207 |
+
"epoch": 13.374928774928774,
|
| 82208 |
+
"grad_norm": 0.26020103693008423,
|
| 82209 |
+
"learning_rate": 1.3311370403222256e-05,
|
| 82210 |
+
"loss": 0.5647,
|
| 82211 |
+
"step": 11743
|
| 82212 |
+
},
|
| 82213 |
+
{
|
| 82214 |
+
"epoch": 13.376068376068377,
|
| 82215 |
+
"grad_norm": 0.27008765935897827,
|
| 82216 |
+
"learning_rate": 1.3307252033737372e-05,
|
| 82217 |
+
"loss": 0.545,
|
| 82218 |
+
"step": 11744
|
| 82219 |
+
},
|
| 82220 |
+
{
|
| 82221 |
+
"epoch": 13.377207977207977,
|
| 82222 |
+
"grad_norm": 0.2193966954946518,
|
| 82223 |
+
"learning_rate": 1.330313407037378e-05,
|
| 82224 |
+
"loss": 0.8023,
|
| 82225 |
+
"step": 11745
|
| 82226 |
+
},
|
| 82227 |
+
{
|
| 82228 |
+
"epoch": 13.378347578347578,
|
| 82229 |
+
"grad_norm": 0.1801786571741104,
|
| 82230 |
+
"learning_rate": 1.3299016513274507e-05,
|
| 82231 |
+
"loss": 0.7572,
|
| 82232 |
+
"step": 11746
|
| 82233 |
+
},
|
| 82234 |
+
{
|
| 82235 |
+
"epoch": 13.37948717948718,
|
| 82236 |
+
"grad_norm": 0.20420002937316895,
|
| 82237 |
+
"learning_rate": 1.329489936258257e-05,
|
| 82238 |
+
"loss": 0.6427,
|
| 82239 |
+
"step": 11747
|
| 82240 |
+
},
|
| 82241 |
+
{
|
| 82242 |
+
"epoch": 13.38062678062678,
|
| 82243 |
+
"grad_norm": 0.2570120394229889,
|
| 82244 |
+
"learning_rate": 1.3290782618440966e-05,
|
| 82245 |
+
"loss": 0.4259,
|
| 82246 |
+
"step": 11748
|
| 82247 |
+
},
|
| 82248 |
+
{
|
| 82249 |
+
"epoch": 13.381766381766381,
|
| 82250 |
+
"grad_norm": 0.18940019607543945,
|
| 82251 |
+
"learning_rate": 1.3286666280992694e-05,
|
| 82252 |
+
"loss": 0.694,
|
| 82253 |
+
"step": 11749
|
| 82254 |
+
},
|
| 82255 |
+
{
|
| 82256 |
+
"epoch": 13.382905982905983,
|
| 82257 |
+
"grad_norm": 0.20675398409366608,
|
| 82258 |
+
"learning_rate": 1.3282550350380702e-05,
|
| 82259 |
+
"loss": 0.5802,
|
| 82260 |
+
"step": 11750
|
| 82261 |
+
},
|
| 82262 |
+
{
|
| 82263 |
+
"epoch": 13.384045584045584,
|
| 82264 |
+
"grad_norm": 0.2542724907398224,
|
| 82265 |
+
"learning_rate": 1.327843482674796e-05,
|
| 82266 |
+
"loss": 0.7778,
|
| 82267 |
+
"step": 11751
|
| 82268 |
+
},
|
| 82269 |
+
{
|
| 82270 |
+
"epoch": 13.385185185185184,
|
| 82271 |
+
"grad_norm": 0.19304198026657104,
|
| 82272 |
+
"learning_rate": 1.3274319710237409e-05,
|
| 82273 |
+
"loss": 0.7178,
|
| 82274 |
+
"step": 11752
|
| 82275 |
+
},
|
| 82276 |
+
{
|
| 82277 |
+
"epoch": 13.386324786324787,
|
| 82278 |
+
"grad_norm": 0.2127370536327362,
|
| 82279 |
+
"learning_rate": 1.3270205000991992e-05,
|
| 82280 |
+
"loss": 0.4982,
|
| 82281 |
+
"step": 11753
|
| 82282 |
+
},
|
| 82283 |
+
{
|
| 82284 |
+
"epoch": 13.387464387464387,
|
| 82285 |
+
"grad_norm": 0.21912941336631775,
|
| 82286 |
+
"learning_rate": 1.32660906991546e-05,
|
| 82287 |
+
"loss": 0.6523,
|
| 82288 |
+
"step": 11754
|
| 82289 |
+
},
|
| 82290 |
+
{
|
| 82291 |
+
"epoch": 13.388603988603988,
|
| 82292 |
+
"grad_norm": 0.22796490788459778,
|
| 82293 |
+
"learning_rate": 1.326197680486815e-05,
|
| 82294 |
+
"loss": 0.8008,
|
| 82295 |
+
"step": 11755
|
| 82296 |
+
},
|
| 82297 |
+
{
|
| 82298 |
+
"epoch": 13.38974358974359,
|
| 82299 |
+
"grad_norm": 0.2455299347639084,
|
| 82300 |
+
"learning_rate": 1.3257863318275526e-05,
|
| 82301 |
+
"loss": 0.6711,
|
| 82302 |
+
"step": 11756
|
| 82303 |
+
},
|
| 82304 |
+
{
|
| 82305 |
+
"epoch": 13.39088319088319,
|
| 82306 |
+
"grad_norm": 0.21852083504199982,
|
| 82307 |
+
"learning_rate": 1.3253750239519596e-05,
|
| 82308 |
+
"loss": 0.4091,
|
| 82309 |
+
"step": 11757
|
| 82310 |
+
},
|
| 82311 |
+
{
|
| 82312 |
+
"epoch": 13.392022792022791,
|
| 82313 |
+
"grad_norm": 0.18607379496097565,
|
| 82314 |
+
"learning_rate": 1.3249637568743226e-05,
|
| 82315 |
+
"loss": 0.6097,
|
| 82316 |
+
"step": 11758
|
| 82317 |
+
},
|
| 82318 |
+
{
|
| 82319 |
+
"epoch": 13.393162393162394,
|
| 82320 |
+
"grad_norm": 0.25612539052963257,
|
| 82321 |
+
"learning_rate": 1.3245525306089254e-05,
|
| 82322 |
+
"loss": 0.6545,
|
| 82323 |
+
"step": 11759
|
| 82324 |
+
},
|
| 82325 |
+
{
|
| 82326 |
+
"epoch": 13.394301994301994,
|
| 82327 |
+
"grad_norm": 0.2174026370048523,
|
| 82328 |
+
"learning_rate": 1.3241413451700523e-05,
|
| 82329 |
+
"loss": 0.6602,
|
| 82330 |
+
"step": 11760
|
| 82331 |
+
},
|
| 82332 |
+
{
|
| 82333 |
+
"epoch": 13.395441595441595,
|
| 82334 |
+
"grad_norm": 0.18675318360328674,
|
| 82335 |
+
"learning_rate": 1.3237302005719832e-05,
|
| 82336 |
+
"loss": 0.5977,
|
| 82337 |
+
"step": 11761
|
| 82338 |
+
},
|
| 82339 |
+
{
|
| 82340 |
+
"epoch": 13.396581196581197,
|
| 82341 |
+
"grad_norm": 0.19634675979614258,
|
| 82342 |
+
"learning_rate": 1.3233190968289988e-05,
|
| 82343 |
+
"loss": 0.8069,
|
| 82344 |
+
"step": 11762
|
| 82345 |
+
},
|
| 82346 |
+
{
|
| 82347 |
+
"epoch": 13.397720797720797,
|
| 82348 |
+
"grad_norm": 0.24026522040367126,
|
| 82349 |
+
"learning_rate": 1.322908033955378e-05,
|
| 82350 |
+
"loss": 0.6805,
|
| 82351 |
+
"step": 11763
|
| 82352 |
+
},
|
| 82353 |
+
{
|
| 82354 |
+
"epoch": 13.398860398860398,
|
| 82355 |
+
"grad_norm": 0.16847091913223267,
|
| 82356 |
+
"learning_rate": 1.3224970119653993e-05,
|
| 82357 |
+
"loss": 0.9449,
|
| 82358 |
+
"step": 11764
|
| 82359 |
+
},
|
| 82360 |
+
{
|
| 82361 |
+
"epoch": 13.4,
|
| 82362 |
+
"grad_norm": 0.1692194938659668,
|
| 82363 |
+
"learning_rate": 1.3220860308733365e-05,
|
| 82364 |
+
"loss": 0.7029,
|
| 82365 |
+
"step": 11765
|
| 82366 |
+
},
|
| 82367 |
+
{
|
| 82368 |
+
"epoch": 13.401139601139601,
|
| 82369 |
+
"grad_norm": 0.22036419808864594,
|
| 82370 |
+
"learning_rate": 1.321675090693465e-05,
|
| 82371 |
+
"loss": 0.8559,
|
| 82372 |
+
"step": 11766
|
| 82373 |
+
},
|
| 82374 |
+
{
|
| 82375 |
+
"epoch": 13.402279202279201,
|
| 82376 |
+
"grad_norm": 0.21671216189861298,
|
| 82377 |
+
"learning_rate": 1.3212641914400581e-05,
|
| 82378 |
+
"loss": 0.6499,
|
| 82379 |
+
"step": 11767
|
| 82380 |
+
},
|
| 82381 |
+
{
|
| 82382 |
+
"epoch": 13.403418803418804,
|
| 82383 |
+
"grad_norm": 0.2525615096092224,
|
| 82384 |
+
"learning_rate": 1.3208533331273875e-05,
|
| 82385 |
+
"loss": 0.4299,
|
| 82386 |
+
"step": 11768
|
| 82387 |
+
},
|
| 82388 |
+
{
|
| 82389 |
+
"epoch": 13.404558404558404,
|
| 82390 |
+
"grad_norm": 0.24309319257736206,
|
| 82391 |
+
"learning_rate": 1.3204425157697232e-05,
|
| 82392 |
+
"loss": 0.7435,
|
| 82393 |
+
"step": 11769
|
| 82394 |
+
},
|
| 82395 |
+
{
|
| 82396 |
+
"epoch": 13.405698005698005,
|
| 82397 |
+
"grad_norm": 0.2587674856185913,
|
| 82398 |
+
"learning_rate": 1.3200317393813342e-05,
|
| 82399 |
+
"loss": 0.5602,
|
| 82400 |
+
"step": 11770
|
| 82401 |
+
},
|
| 82402 |
+
{
|
| 82403 |
+
"epoch": 13.406837606837607,
|
| 82404 |
+
"grad_norm": 0.22008532285690308,
|
| 82405 |
+
"learning_rate": 1.3196210039764886e-05,
|
| 82406 |
+
"loss": 0.6589,
|
| 82407 |
+
"step": 11771
|
| 82408 |
+
},
|
| 82409 |
+
{
|
| 82410 |
+
"epoch": 13.407977207977208,
|
| 82411 |
+
"grad_norm": 0.22189222276210785,
|
| 82412 |
+
"learning_rate": 1.3192103095694508e-05,
|
| 82413 |
+
"loss": 0.6874,
|
| 82414 |
+
"step": 11772
|
| 82415 |
+
},
|
| 82416 |
+
{
|
| 82417 |
+
"epoch": 13.40911680911681,
|
| 82418 |
+
"grad_norm": 0.17690376937389374,
|
| 82419 |
+
"learning_rate": 1.3187996561744862e-05,
|
| 82420 |
+
"loss": 0.7136,
|
| 82421 |
+
"step": 11773
|
| 82422 |
+
},
|
| 82423 |
+
{
|
| 82424 |
+
"epoch": 13.41025641025641,
|
| 82425 |
+
"grad_norm": 0.20434725284576416,
|
| 82426 |
+
"learning_rate": 1.3183890438058578e-05,
|
| 82427 |
+
"loss": 0.6152,
|
| 82428 |
+
"step": 11774
|
| 82429 |
+
},
|
| 82430 |
+
{
|
| 82431 |
+
"epoch": 13.411396011396011,
|
| 82432 |
+
"grad_norm": 0.18098989129066467,
|
| 82433 |
+
"learning_rate": 1.3179784724778271e-05,
|
| 82434 |
+
"loss": 0.6763,
|
| 82435 |
+
"step": 11775
|
| 82436 |
+
},
|
| 82437 |
+
{
|
| 82438 |
+
"epoch": 13.412535612535613,
|
| 82439 |
+
"grad_norm": 0.2281097024679184,
|
| 82440 |
+
"learning_rate": 1.3175679422046557e-05,
|
| 82441 |
+
"loss": 0.4836,
|
| 82442 |
+
"step": 11776
|
| 82443 |
+
},
|
| 82444 |
+
{
|
| 82445 |
+
"epoch": 13.413675213675214,
|
| 82446 |
+
"grad_norm": 0.23284488916397095,
|
| 82447 |
+
"learning_rate": 1.3171574530006003e-05,
|
| 82448 |
+
"loss": 0.7279,
|
| 82449 |
+
"step": 11777
|
| 82450 |
+
},
|
| 82451 |
+
{
|
| 82452 |
+
"epoch": 13.414814814814815,
|
| 82453 |
+
"grad_norm": 0.23388147354125977,
|
| 82454 |
+
"learning_rate": 1.3167470048799196e-05,
|
| 82455 |
+
"loss": 0.6055,
|
| 82456 |
+
"step": 11778
|
| 82457 |
+
},
|
| 82458 |
+
{
|
| 82459 |
+
"epoch": 13.415954415954417,
|
| 82460 |
+
"grad_norm": 0.24649496376514435,
|
| 82461 |
+
"learning_rate": 1.3163365978568693e-05,
|
| 82462 |
+
"loss": 0.6982,
|
| 82463 |
+
"step": 11779
|
| 82464 |
+
},
|
| 82465 |
+
{
|
| 82466 |
+
"epoch": 13.417094017094017,
|
| 82467 |
+
"grad_norm": 0.2163296341896057,
|
| 82468 |
+
"learning_rate": 1.3159262319457043e-05,
|
| 82469 |
+
"loss": 0.6715,
|
| 82470 |
+
"step": 11780
|
| 82471 |
+
},
|
| 82472 |
+
{
|
| 82473 |
+
"epoch": 13.418233618233618,
|
| 82474 |
+
"grad_norm": 0.25945591926574707,
|
| 82475 |
+
"learning_rate": 1.3155159071606771e-05,
|
| 82476 |
+
"loss": 0.3567,
|
| 82477 |
+
"step": 11781
|
| 82478 |
+
},
|
| 82479 |
+
{
|
| 82480 |
+
"epoch": 13.41937321937322,
|
| 82481 |
+
"grad_norm": 0.20381131768226624,
|
| 82482 |
+
"learning_rate": 1.31510562351604e-05,
|
| 82483 |
+
"loss": 0.5506,
|
| 82484 |
+
"step": 11782
|
| 82485 |
+
},
|
| 82486 |
+
{
|
| 82487 |
+
"epoch": 13.42051282051282,
|
| 82488 |
+
"grad_norm": 0.2540411651134491,
|
| 82489 |
+
"learning_rate": 1.314695381026044e-05,
|
| 82490 |
+
"loss": 0.5988,
|
| 82491 |
+
"step": 11783
|
| 82492 |
+
},
|
| 82493 |
+
{
|
| 82494 |
+
"epoch": 13.421652421652421,
|
| 82495 |
+
"grad_norm": 0.16043323278427124,
|
| 82496 |
+
"learning_rate": 1.314285179704936e-05,
|
| 82497 |
+
"loss": 0.7278,
|
| 82498 |
+
"step": 11784
|
| 82499 |
+
},
|
| 82500 |
+
{
|
| 82501 |
+
"epoch": 13.422792022792024,
|
| 82502 |
+
"grad_norm": 0.18081732094287872,
|
| 82503 |
+
"learning_rate": 1.3138750195669644e-05,
|
| 82504 |
+
"loss": 0.6862,
|
| 82505 |
+
"step": 11785
|
| 82506 |
+
},
|
| 82507 |
+
{
|
| 82508 |
+
"epoch": 13.423931623931624,
|
| 82509 |
+
"grad_norm": 0.1803949624300003,
|
| 82510 |
+
"learning_rate": 1.3134649006263755e-05,
|
| 82511 |
+
"loss": 0.8005,
|
| 82512 |
+
"step": 11786
|
| 82513 |
+
},
|
| 82514 |
+
{
|
| 82515 |
+
"epoch": 13.425071225071225,
|
| 82516 |
+
"grad_norm": 0.16201768815517426,
|
| 82517 |
+
"learning_rate": 1.3130548228974143e-05,
|
| 82518 |
+
"loss": 0.766,
|
| 82519 |
+
"step": 11787
|
| 82520 |
+
},
|
| 82521 |
+
{
|
| 82522 |
+
"epoch": 13.426210826210827,
|
| 82523 |
+
"grad_norm": 0.22643521428108215,
|
| 82524 |
+
"learning_rate": 1.312644786394322e-05,
|
| 82525 |
+
"loss": 0.8755,
|
| 82526 |
+
"step": 11788
|
| 82527 |
+
},
|
| 82528 |
+
{
|
| 82529 |
+
"epoch": 13.427350427350428,
|
| 82530 |
+
"grad_norm": 0.207927405834198,
|
| 82531 |
+
"learning_rate": 1.312234791131342e-05,
|
| 82532 |
+
"loss": 0.7667,
|
| 82533 |
+
"step": 11789
|
| 82534 |
+
},
|
| 82535 |
+
{
|
| 82536 |
+
"epoch": 13.428490028490028,
|
| 82537 |
+
"grad_norm": 0.21223682165145874,
|
| 82538 |
+
"learning_rate": 1.3118248371227138e-05,
|
| 82539 |
+
"loss": 0.5855,
|
| 82540 |
+
"step": 11790
|
| 82541 |
+
},
|
| 82542 |
+
{
|
| 82543 |
+
"epoch": 13.42962962962963,
|
| 82544 |
+
"grad_norm": 0.22653348743915558,
|
| 82545 |
+
"learning_rate": 1.3114149243826765e-05,
|
| 82546 |
+
"loss": 0.7142,
|
| 82547 |
+
"step": 11791
|
| 82548 |
+
},
|
| 82549 |
+
{
|
| 82550 |
+
"epoch": 13.430769230769231,
|
| 82551 |
+
"grad_norm": 0.24808557331562042,
|
| 82552 |
+
"learning_rate": 1.3110050529254675e-05,
|
| 82553 |
+
"loss": 0.6013,
|
| 82554 |
+
"step": 11792
|
| 82555 |
+
},
|
| 82556 |
+
{
|
| 82557 |
+
"epoch": 13.431908831908832,
|
| 82558 |
+
"grad_norm": 0.15929973125457764,
|
| 82559 |
+
"learning_rate": 1.3105952227653228e-05,
|
| 82560 |
+
"loss": 0.8077,
|
| 82561 |
+
"step": 11793
|
| 82562 |
+
},
|
| 82563 |
+
{
|
| 82564 |
+
"epoch": 13.433048433048434,
|
| 82565 |
+
"grad_norm": 0.18594641983509064,
|
| 82566 |
+
"learning_rate": 1.3101854339164782e-05,
|
| 82567 |
+
"loss": 0.7346,
|
| 82568 |
+
"step": 11794
|
| 82569 |
+
},
|
| 82570 |
+
{
|
| 82571 |
+
"epoch": 13.434188034188034,
|
| 82572 |
+
"grad_norm": 0.2075185775756836,
|
| 82573 |
+
"learning_rate": 1.309775686393164e-05,
|
| 82574 |
+
"loss": 0.671,
|
| 82575 |
+
"step": 11795
|
| 82576 |
+
},
|
| 82577 |
+
{
|
| 82578 |
+
"epoch": 13.435327635327635,
|
| 82579 |
+
"grad_norm": 0.2374790608882904,
|
| 82580 |
+
"learning_rate": 1.3093659802096136e-05,
|
| 82581 |
+
"loss": 0.6618,
|
| 82582 |
+
"step": 11796
|
| 82583 |
+
},
|
| 82584 |
+
{
|
| 82585 |
+
"epoch": 13.436467236467237,
|
| 82586 |
+
"grad_norm": 0.25639960169792175,
|
| 82587 |
+
"learning_rate": 1.308956315380057e-05,
|
| 82588 |
+
"loss": 0.4616,
|
| 82589 |
+
"step": 11797
|
| 82590 |
+
},
|
| 82591 |
+
{
|
| 82592 |
+
"epoch": 13.437606837606838,
|
| 82593 |
+
"grad_norm": 0.2293757051229477,
|
| 82594 |
+
"learning_rate": 1.3085466919187236e-05,
|
| 82595 |
+
"loss": 0.5088,
|
| 82596 |
+
"step": 11798
|
| 82597 |
+
},
|
| 82598 |
+
{
|
| 82599 |
+
"epoch": 13.438746438746438,
|
| 82600 |
+
"grad_norm": 0.171857088804245,
|
| 82601 |
+
"learning_rate": 1.3081371098398393e-05,
|
| 82602 |
+
"loss": 0.8437,
|
| 82603 |
+
"step": 11799
|
| 82604 |
+
},
|
| 82605 |
+
{
|
| 82606 |
+
"epoch": 13.43988603988604,
|
| 82607 |
+
"grad_norm": 0.18606480956077576,
|
| 82608 |
+
"learning_rate": 1.3077275691576307e-05,
|
| 82609 |
+
"loss": 0.5405,
|
| 82610 |
+
"step": 11800
|
| 82611 |
+
},
|
| 82612 |
+
{
|
| 82613 |
+
"epoch": 13.441025641025641,
|
| 82614 |
+
"grad_norm": 0.2071981281042099,
|
| 82615 |
+
"learning_rate": 1.3073180698863228e-05,
|
| 82616 |
+
"loss": 0.6098,
|
| 82617 |
+
"step": 11801
|
| 82618 |
+
},
|
| 82619 |
+
{
|
| 82620 |
+
"epoch": 13.442165242165242,
|
| 82621 |
+
"grad_norm": 0.2265680581331253,
|
| 82622 |
+
"learning_rate": 1.306908612040138e-05,
|
| 82623 |
+
"loss": 0.7493,
|
| 82624 |
+
"step": 11802
|
| 82625 |
+
},
|
| 82626 |
+
{
|
| 82627 |
+
"epoch": 13.443304843304844,
|
| 82628 |
+
"grad_norm": 0.21974751353263855,
|
| 82629 |
+
"learning_rate": 1.3064991956332977e-05,
|
| 82630 |
+
"loss": 0.514,
|
| 82631 |
+
"step": 11803
|
| 82632 |
+
},
|
| 82633 |
+
{
|
| 82634 |
+
"epoch": 13.444444444444445,
|
| 82635 |
+
"grad_norm": 0.1616891324520111,
|
| 82636 |
+
"learning_rate": 1.3060898206800231e-05,
|
| 82637 |
+
"loss": 1.0072,
|
| 82638 |
+
"step": 11804
|
| 82639 |
+
},
|
| 82640 |
+
{
|
| 82641 |
+
"epoch": 13.445584045584045,
|
| 82642 |
+
"grad_norm": 0.192517951130867,
|
| 82643 |
+
"learning_rate": 1.305680487194533e-05,
|
| 82644 |
+
"loss": 0.7794,
|
| 82645 |
+
"step": 11805
|
| 82646 |
+
},
|
| 82647 |
+
{
|
| 82648 |
+
"epoch": 13.446723646723648,
|
| 82649 |
+
"grad_norm": 0.1810740977525711,
|
| 82650 |
+
"learning_rate": 1.3052711951910429e-05,
|
| 82651 |
+
"loss": 0.767,
|
| 82652 |
+
"step": 11806
|
| 82653 |
+
},
|
| 82654 |
+
{
|
| 82655 |
+
"epoch": 13.447863247863248,
|
| 82656 |
+
"grad_norm": 0.17321431636810303,
|
| 82657 |
+
"learning_rate": 1.30486194468377e-05,
|
| 82658 |
+
"loss": 0.8547,
|
| 82659 |
+
"step": 11807
|
| 82660 |
+
},
|
| 82661 |
+
{
|
| 82662 |
+
"epoch": 13.449002849002849,
|
| 82663 |
+
"grad_norm": 0.17997126281261444,
|
| 82664 |
+
"learning_rate": 1.3044527356869283e-05,
|
| 82665 |
+
"loss": 0.7351,
|
| 82666 |
+
"step": 11808
|
| 82667 |
+
},
|
| 82668 |
+
{
|
| 82669 |
+
"epoch": 13.450142450142451,
|
| 82670 |
+
"grad_norm": 0.22150816023349762,
|
| 82671 |
+
"learning_rate": 1.3040435682147317e-05,
|
| 82672 |
+
"loss": 0.7567,
|
| 82673 |
+
"step": 11809
|
| 82674 |
+
},
|
| 82675 |
+
{
|
| 82676 |
+
"epoch": 13.451282051282051,
|
| 82677 |
+
"grad_norm": 0.20686297118663788,
|
| 82678 |
+
"learning_rate": 1.3036344422813902e-05,
|
| 82679 |
+
"loss": 0.6055,
|
| 82680 |
+
"step": 11810
|
| 82681 |
+
},
|
| 82682 |
+
{
|
| 82683 |
+
"epoch": 13.452421652421652,
|
| 82684 |
+
"grad_norm": 0.16225579380989075,
|
| 82685 |
+
"learning_rate": 1.3032253579011138e-05,
|
| 82686 |
+
"loss": 0.7329,
|
| 82687 |
+
"step": 11811
|
| 82688 |
+
},
|
| 82689 |
+
{
|
| 82690 |
+
"epoch": 13.453561253561254,
|
| 82691 |
+
"grad_norm": 0.25011882185935974,
|
| 82692 |
+
"learning_rate": 1.3028163150881117e-05,
|
| 82693 |
+
"loss": 0.5926,
|
| 82694 |
+
"step": 11812
|
| 82695 |
+
},
|
| 82696 |
+
{
|
| 82697 |
+
"epoch": 13.454700854700855,
|
| 82698 |
+
"grad_norm": 0.2048470824956894,
|
| 82699 |
+
"learning_rate": 1.3024073138565929e-05,
|
| 82700 |
+
"loss": 0.6826,
|
| 82701 |
+
"step": 11813
|
| 82702 |
+
},
|
| 82703 |
+
{
|
| 82704 |
+
"epoch": 13.455840455840455,
|
| 82705 |
+
"grad_norm": 0.18196135759353638,
|
| 82706 |
+
"learning_rate": 1.3019983542207603e-05,
|
| 82707 |
+
"loss": 0.8431,
|
| 82708 |
+
"step": 11814
|
| 82709 |
+
},
|
| 82710 |
+
{
|
| 82711 |
+
"epoch": 13.456980056980058,
|
| 82712 |
+
"grad_norm": 0.19810007512569427,
|
| 82713 |
+
"learning_rate": 1.3015894361948197e-05,
|
| 82714 |
+
"loss": 0.7068,
|
| 82715 |
+
"step": 11815
|
| 82716 |
+
},
|
| 82717 |
+
{
|
| 82718 |
+
"epoch": 13.458119658119658,
|
| 82719 |
+
"grad_norm": 0.16278612613677979,
|
| 82720 |
+
"learning_rate": 1.3011805597929733e-05,
|
| 82721 |
+
"loss": 0.6735,
|
| 82722 |
+
"step": 11816
|
| 82723 |
+
},
|
| 82724 |
+
{
|
| 82725 |
+
"epoch": 13.459259259259259,
|
| 82726 |
+
"grad_norm": 0.23491507768630981,
|
| 82727 |
+
"learning_rate": 1.300771725029424e-05,
|
| 82728 |
+
"loss": 0.6551,
|
| 82729 |
+
"step": 11817
|
| 82730 |
+
},
|
| 82731 |
+
{
|
| 82732 |
+
"epoch": 13.460398860398861,
|
| 82733 |
+
"grad_norm": 0.2680200934410095,
|
| 82734 |
+
"learning_rate": 1.3003629319183697e-05,
|
| 82735 |
+
"loss": 0.6771,
|
| 82736 |
+
"step": 11818
|
| 82737 |
+
},
|
| 82738 |
+
{
|
| 82739 |
+
"epoch": 13.461538461538462,
|
| 82740 |
+
"grad_norm": 0.21170486509799957,
|
| 82741 |
+
"learning_rate": 1.2999541804740094e-05,
|
| 82742 |
+
"loss": 0.78,
|
| 82743 |
+
"step": 11819
|
| 82744 |
+
},
|
| 82745 |
+
{
|
| 82746 |
+
"epoch": 13.462678062678062,
|
| 82747 |
+
"grad_norm": 0.182427316904068,
|
| 82748 |
+
"learning_rate": 1.2995454707105409e-05,
|
| 82749 |
+
"loss": 0.5947,
|
| 82750 |
+
"step": 11820
|
| 82751 |
+
},
|
| 82752 |
+
{
|
| 82753 |
+
"epoch": 13.463817663817665,
|
| 82754 |
+
"grad_norm": 0.19571854174137115,
|
| 82755 |
+
"learning_rate": 1.2991368026421607e-05,
|
| 82756 |
+
"loss": 0.4616,
|
| 82757 |
+
"step": 11821
|
| 82758 |
+
},
|
| 82759 |
+
{
|
| 82760 |
+
"epoch": 13.464957264957265,
|
| 82761 |
+
"grad_norm": 0.202408105134964,
|
| 82762 |
+
"learning_rate": 1.2987281762830603e-05,
|
| 82763 |
+
"loss": 0.8652,
|
| 82764 |
+
"step": 11822
|
| 82765 |
+
},
|
| 82766 |
+
{
|
| 82767 |
+
"epoch": 13.466096866096866,
|
| 82768 |
+
"grad_norm": 0.2505589723587036,
|
| 82769 |
+
"learning_rate": 1.2983195916474327e-05,
|
| 82770 |
+
"loss": 0.7532,
|
| 82771 |
+
"step": 11823
|
| 82772 |
+
},
|
| 82773 |
+
{
|
| 82774 |
+
"epoch": 13.467236467236468,
|
| 82775 |
+
"grad_norm": 0.2218238115310669,
|
| 82776 |
+
"learning_rate": 1.2979110487494729e-05,
|
| 82777 |
+
"loss": 0.2192,
|
| 82778 |
+
"step": 11824
|
| 82779 |
+
},
|
| 82780 |
+
{
|
| 82781 |
+
"epoch": 13.468376068376068,
|
| 82782 |
+
"grad_norm": 0.20187053084373474,
|
| 82783 |
+
"learning_rate": 1.2975025476033667e-05,
|
| 82784 |
+
"loss": 0.6784,
|
| 82785 |
+
"step": 11825
|
| 82786 |
+
},
|
| 82787 |
+
{
|
| 82788 |
+
"epoch": 13.469515669515669,
|
| 82789 |
+
"grad_norm": 0.2052537202835083,
|
| 82790 |
+
"learning_rate": 1.297094088223304e-05,
|
| 82791 |
+
"loss": 0.7748,
|
| 82792 |
+
"step": 11826
|
| 82793 |
+
},
|
| 82794 |
+
{
|
| 82795 |
+
"epoch": 13.470655270655271,
|
| 82796 |
+
"grad_norm": 0.22300845384597778,
|
| 82797 |
+
"learning_rate": 1.2966856706234717e-05,
|
| 82798 |
+
"loss": 0.5471,
|
| 82799 |
+
"step": 11827
|
| 82800 |
+
},
|
| 82801 |
+
{
|
| 82802 |
+
"epoch": 13.471794871794872,
|
| 82803 |
+
"grad_norm": 0.16977225244045258,
|
| 82804 |
+
"learning_rate": 1.2962772948180562e-05,
|
| 82805 |
+
"loss": 0.7442,
|
| 82806 |
+
"step": 11828
|
| 82807 |
+
},
|
| 82808 |
+
{
|
| 82809 |
+
"epoch": 13.472934472934472,
|
| 82810 |
+
"grad_norm": 0.21880266070365906,
|
| 82811 |
+
"learning_rate": 1.2958689608212392e-05,
|
| 82812 |
+
"loss": 0.8785,
|
| 82813 |
+
"step": 11829
|
| 82814 |
+
},
|
| 82815 |
+
{
|
| 82816 |
+
"epoch": 13.474074074074075,
|
| 82817 |
+
"grad_norm": 0.2288815826177597,
|
| 82818 |
+
"learning_rate": 1.2954606686472048e-05,
|
| 82819 |
+
"loss": 0.5701,
|
| 82820 |
+
"step": 11830
|
| 82821 |
+
},
|
| 82822 |
+
{
|
| 82823 |
+
"epoch": 13.475213675213675,
|
| 82824 |
+
"grad_norm": 0.1787015199661255,
|
| 82825 |
+
"learning_rate": 1.295052418310134e-05,
|
| 82826 |
+
"loss": 0.6599,
|
| 82827 |
+
"step": 11831
|
| 82828 |
+
},
|
| 82829 |
+
{
|
| 82830 |
+
"epoch": 13.476353276353276,
|
| 82831 |
+
"grad_norm": 0.18069544434547424,
|
| 82832 |
+
"learning_rate": 1.2946442098242073e-05,
|
| 82833 |
+
"loss": 0.8786,
|
| 82834 |
+
"step": 11832
|
| 82835 |
+
},
|
| 82836 |
+
{
|
| 82837 |
+
"epoch": 13.477492877492878,
|
| 82838 |
+
"grad_norm": 0.15547680854797363,
|
| 82839 |
+
"learning_rate": 1.2942360432036008e-05,
|
| 82840 |
+
"loss": 0.7813,
|
| 82841 |
+
"step": 11833
|
| 82842 |
+
},
|
| 82843 |
+
{
|
| 82844 |
+
"epoch": 13.478632478632479,
|
| 82845 |
+
"grad_norm": 0.26197972893714905,
|
| 82846 |
+
"learning_rate": 1.2938279184624912e-05,
|
| 82847 |
+
"loss": 0.5559,
|
| 82848 |
+
"step": 11834
|
| 82849 |
+
},
|
| 82850 |
+
{
|
| 82851 |
+
"epoch": 13.47977207977208,
|
| 82852 |
+
"grad_norm": 0.24245873093605042,
|
| 82853 |
+
"learning_rate": 1.2934198356150573e-05,
|
| 82854 |
+
"loss": 0.5394,
|
| 82855 |
+
"step": 11835
|
| 82856 |
+
},
|
| 82857 |
+
{
|
| 82858 |
+
"epoch": 13.480911680911682,
|
| 82859 |
+
"grad_norm": 0.20734834671020508,
|
| 82860 |
+
"learning_rate": 1.2930117946754693e-05,
|
| 82861 |
+
"loss": 0.3662,
|
| 82862 |
+
"step": 11836
|
| 82863 |
+
},
|
| 82864 |
+
{
|
| 82865 |
+
"epoch": 13.482051282051282,
|
| 82866 |
+
"grad_norm": 0.22213418781757355,
|
| 82867 |
+
"learning_rate": 1.2926037956579013e-05,
|
| 82868 |
+
"loss": 0.4171,
|
| 82869 |
+
"step": 11837
|
| 82870 |
+
},
|
| 82871 |
+
{
|
| 82872 |
+
"epoch": 13.483190883190883,
|
| 82873 |
+
"grad_norm": 0.18396912515163422,
|
| 82874 |
+
"learning_rate": 1.2921958385765238e-05,
|
| 82875 |
+
"loss": 0.8424,
|
| 82876 |
+
"step": 11838
|
| 82877 |
+
},
|
| 82878 |
+
{
|
| 82879 |
+
"epoch": 13.484330484330485,
|
| 82880 |
+
"grad_norm": 0.2207166850566864,
|
| 82881 |
+
"learning_rate": 1.2917879234455072e-05,
|
| 82882 |
+
"loss": 0.6613,
|
| 82883 |
+
"step": 11839
|
| 82884 |
+
},
|
| 82885 |
+
{
|
| 82886 |
+
"epoch": 13.485470085470086,
|
| 82887 |
+
"grad_norm": 0.3201916515827179,
|
| 82888 |
+
"learning_rate": 1.2913800502790174e-05,
|
| 82889 |
+
"loss": 0.5973,
|
| 82890 |
+
"step": 11840
|
| 82891 |
+
},
|
| 82892 |
+
{
|
| 82893 |
+
"epoch": 13.486609686609686,
|
| 82894 |
+
"grad_norm": 0.2347378432750702,
|
| 82895 |
+
"learning_rate": 1.2909722190912222e-05,
|
| 82896 |
+
"loss": 0.7864,
|
| 82897 |
+
"step": 11841
|
| 82898 |
+
},
|
| 82899 |
+
{
|
| 82900 |
+
"epoch": 13.487749287749288,
|
| 82901 |
+
"grad_norm": 0.21414105594158173,
|
| 82902 |
+
"learning_rate": 1.2905644298962868e-05,
|
| 82903 |
+
"loss": 0.7357,
|
| 82904 |
+
"step": 11842
|
| 82905 |
+
},
|
| 82906 |
+
{
|
| 82907 |
+
"epoch": 13.488888888888889,
|
| 82908 |
+
"grad_norm": 0.1687665730714798,
|
| 82909 |
+
"learning_rate": 1.2901566827083758e-05,
|
| 82910 |
+
"loss": 0.6911,
|
| 82911 |
+
"step": 11843
|
| 82912 |
+
},
|
| 82913 |
+
{
|
| 82914 |
+
"epoch": 13.49002849002849,
|
| 82915 |
+
"grad_norm": 0.19328096508979797,
|
| 82916 |
+
"learning_rate": 1.2897489775416494e-05,
|
| 82917 |
+
"loss": 0.6803,
|
| 82918 |
+
"step": 11844
|
| 82919 |
+
},
|
| 82920 |
+
{
|
| 82921 |
+
"epoch": 13.491168091168092,
|
| 82922 |
+
"grad_norm": 0.2298462986946106,
|
| 82923 |
+
"learning_rate": 1.2893413144102678e-05,
|
| 82924 |
+
"loss": 0.6843,
|
| 82925 |
+
"step": 11845
|
| 82926 |
+
},
|
| 82927 |
+
{
|
| 82928 |
+
"epoch": 13.492307692307692,
|
| 82929 |
+
"grad_norm": 0.23529808223247528,
|
| 82930 |
+
"learning_rate": 1.2889336933283938e-05,
|
| 82931 |
+
"loss": 0.6027,
|
| 82932 |
+
"step": 11846
|
| 82933 |
+
},
|
| 82934 |
+
{
|
| 82935 |
+
"epoch": 13.493447293447293,
|
| 82936 |
+
"grad_norm": 0.21353775262832642,
|
| 82937 |
+
"learning_rate": 1.2885261143101824e-05,
|
| 82938 |
+
"loss": 0.7785,
|
| 82939 |
+
"step": 11847
|
| 82940 |
+
},
|
| 82941 |
+
{
|
| 82942 |
+
"epoch": 13.494586894586895,
|
| 82943 |
+
"grad_norm": 0.24823594093322754,
|
| 82944 |
+
"learning_rate": 1.2881185773697902e-05,
|
| 82945 |
+
"loss": 0.4019,
|
| 82946 |
+
"step": 11848
|
| 82947 |
+
},
|
| 82948 |
+
{
|
| 82949 |
+
"epoch": 13.495726495726496,
|
| 82950 |
+
"grad_norm": 0.19683465361595154,
|
| 82951 |
+
"learning_rate": 1.2877110825213729e-05,
|
| 82952 |
+
"loss": 0.6757,
|
| 82953 |
+
"step": 11849
|
| 82954 |
+
},
|
| 82955 |
+
{
|
| 82956 |
+
"epoch": 13.496866096866096,
|
| 82957 |
+
"grad_norm": 0.21291722357273102,
|
| 82958 |
+
"learning_rate": 1.2873036297790842e-05,
|
| 82959 |
+
"loss": 0.5452,
|
| 82960 |
+
"step": 11850
|
| 82961 |
+
},
|
| 82962 |
+
{
|
| 82963 |
+
"epoch": 13.498005698005699,
|
| 82964 |
+
"grad_norm": 0.20584151148796082,
|
| 82965 |
+
"learning_rate": 1.2868962191570744e-05,
|
| 82966 |
+
"loss": 0.6438,
|
| 82967 |
+
"step": 11851
|
| 82968 |
+
},
|
| 82969 |
+
{
|
| 82970 |
+
"epoch": 13.4991452991453,
|
| 82971 |
+
"grad_norm": 0.1875271201133728,
|
| 82972 |
+
"learning_rate": 1.286488850669495e-05,
|
| 82973 |
+
"loss": 0.6734,
|
| 82974 |
+
"step": 11852
|
| 82975 |
+
},
|
| 82976 |
+
{
|
| 82977 |
+
"epoch": 13.5002849002849,
|
| 82978 |
+
"grad_norm": 0.26178422570228577,
|
| 82979 |
+
"learning_rate": 1.2860815243304949e-05,
|
| 82980 |
+
"loss": 0.5763,
|
| 82981 |
+
"step": 11853
|
| 82982 |
+
},
|
| 82983 |
+
{
|
| 82984 |
+
"epoch": 13.501424501424502,
|
| 82985 |
+
"grad_norm": 0.19995729625225067,
|
| 82986 |
+
"learning_rate": 1.2856742401542218e-05,
|
| 82987 |
+
"loss": 0.9195,
|
| 82988 |
+
"step": 11854
|
| 82989 |
+
},
|
| 82990 |
+
{
|
| 82991 |
+
"epoch": 13.502564102564103,
|
| 82992 |
+
"grad_norm": 0.2521830201148987,
|
| 82993 |
+
"learning_rate": 1.2852669981548227e-05,
|
| 82994 |
+
"loss": 0.7433,
|
| 82995 |
+
"step": 11855
|
| 82996 |
+
},
|
| 82997 |
+
{
|
| 82998 |
+
"epoch": 13.503703703703703,
|
| 82999 |
+
"grad_norm": 0.23248237371444702,
|
| 83000 |
+
"learning_rate": 1.2848597983464394e-05,
|
| 83001 |
+
"loss": 0.5707,
|
| 83002 |
+
"step": 11856
|
| 83003 |
+
},
|
| 83004 |
+
{
|
| 83005 |
+
"epoch": 13.504843304843305,
|
| 83006 |
+
"grad_norm": 0.18612810969352722,
|
| 83007 |
+
"learning_rate": 1.284452640743218e-05,
|
| 83008 |
+
"loss": 0.7798,
|
| 83009 |
+
"step": 11857
|
| 83010 |
+
},
|
| 83011 |
+
{
|
| 83012 |
+
"epoch": 13.505982905982906,
|
| 83013 |
+
"grad_norm": 0.22991402447223663,
|
| 83014 |
+
"learning_rate": 1.2840455253593001e-05,
|
| 83015 |
+
"loss": 0.6549,
|
| 83016 |
+
"step": 11858
|
| 83017 |
+
},
|
| 83018 |
+
{
|
| 83019 |
+
"epoch": 13.507122507122507,
|
| 83020 |
+
"grad_norm": 0.24886555969715118,
|
| 83021 |
+
"learning_rate": 1.2836384522088241e-05,
|
| 83022 |
+
"loss": 0.5469,
|
| 83023 |
+
"step": 11859
|
| 83024 |
+
},
|
| 83025 |
+
{
|
| 83026 |
+
"epoch": 13.508262108262109,
|
| 83027 |
+
"grad_norm": 0.18751516938209534,
|
| 83028 |
+
"learning_rate": 1.2832314213059294e-05,
|
| 83029 |
+
"loss": 0.567,
|
| 83030 |
+
"step": 11860
|
| 83031 |
+
},
|
| 83032 |
+
{
|
| 83033 |
+
"epoch": 13.50940170940171,
|
| 83034 |
+
"grad_norm": 0.25968310236930847,
|
| 83035 |
+
"learning_rate": 1.2828244326647537e-05,
|
| 83036 |
+
"loss": 0.5357,
|
| 83037 |
+
"step": 11861
|
| 83038 |
+
},
|
| 83039 |
+
{
|
| 83040 |
+
"epoch": 13.51054131054131,
|
| 83041 |
+
"grad_norm": 0.21097686886787415,
|
| 83042 |
+
"learning_rate": 1.2824174862994337e-05,
|
| 83043 |
+
"loss": 0.7197,
|
| 83044 |
+
"step": 11862
|
| 83045 |
+
},
|
| 83046 |
+
{
|
| 83047 |
+
"epoch": 13.511680911680912,
|
| 83048 |
+
"grad_norm": 0.15692934393882751,
|
| 83049 |
+
"learning_rate": 1.282010582224102e-05,
|
| 83050 |
+
"loss": 0.8723,
|
| 83051 |
+
"step": 11863
|
| 83052 |
+
},
|
| 83053 |
+
{
|
| 83054 |
+
"epoch": 13.512820512820513,
|
| 83055 |
+
"grad_norm": 0.18831391632556915,
|
| 83056 |
+
"learning_rate": 1.281603720452892e-05,
|
| 83057 |
+
"loss": 0.6201,
|
| 83058 |
+
"step": 11864
|
| 83059 |
+
},
|
| 83060 |
+
{
|
| 83061 |
+
"epoch": 13.513960113960113,
|
| 83062 |
+
"grad_norm": 0.21477819979190826,
|
| 83063 |
+
"learning_rate": 1.2811969009999353e-05,
|
| 83064 |
+
"loss": 0.7348,
|
| 83065 |
+
"step": 11865
|
| 83066 |
+
},
|
| 83067 |
+
{
|
| 83068 |
+
"epoch": 13.515099715099716,
|
| 83069 |
+
"grad_norm": 0.18301048874855042,
|
| 83070 |
+
"learning_rate": 1.2807901238793629e-05,
|
| 83071 |
+
"loss": 0.8579,
|
| 83072 |
+
"step": 11866
|
| 83073 |
+
},
|
| 83074 |
+
{
|
| 83075 |
+
"epoch": 13.516239316239316,
|
| 83076 |
+
"grad_norm": 0.24501535296440125,
|
| 83077 |
+
"learning_rate": 1.2803833891053005e-05,
|
| 83078 |
+
"loss": 0.4058,
|
| 83079 |
+
"step": 11867
|
| 83080 |
+
},
|
| 83081 |
+
{
|
| 83082 |
+
"epoch": 13.517378917378917,
|
| 83083 |
+
"grad_norm": 0.21062730252742767,
|
| 83084 |
+
"learning_rate": 1.279976696691878e-05,
|
| 83085 |
+
"loss": 0.887,
|
| 83086 |
+
"step": 11868
|
| 83087 |
+
},
|
| 83088 |
+
{
|
| 83089 |
+
"epoch": 13.518518518518519,
|
| 83090 |
+
"grad_norm": 0.2024749517440796,
|
| 83091 |
+
"learning_rate": 1.2795700466532207e-05,
|
| 83092 |
+
"loss": 0.637,
|
| 83093 |
+
"step": 11869
|
| 83094 |
+
},
|
| 83095 |
+
{
|
| 83096 |
+
"epoch": 13.51965811965812,
|
| 83097 |
+
"grad_norm": 0.24022068083286285,
|
| 83098 |
+
"learning_rate": 1.2791634390034512e-05,
|
| 83099 |
+
"loss": 0.5854,
|
| 83100 |
+
"step": 11870
|
| 83101 |
+
},
|
| 83102 |
+
{
|
| 83103 |
+
"epoch": 13.52079772079772,
|
| 83104 |
+
"grad_norm": 0.2260151356458664,
|
| 83105 |
+
"learning_rate": 1.2787568737566924e-05,
|
| 83106 |
+
"loss": 0.6486,
|
| 83107 |
+
"step": 11871
|
| 83108 |
+
},
|
| 83109 |
+
{
|
| 83110 |
+
"epoch": 13.521937321937322,
|
| 83111 |
+
"grad_norm": 0.2462989091873169,
|
| 83112 |
+
"learning_rate": 1.278350350927066e-05,
|
| 83113 |
+
"loss": 0.6885,
|
| 83114 |
+
"step": 11872
|
| 83115 |
+
},
|
| 83116 |
+
{
|
| 83117 |
+
"epoch": 13.523076923076923,
|
| 83118 |
+
"grad_norm": 0.1758878380060196,
|
| 83119 |
+
"learning_rate": 1.2779438705286927e-05,
|
| 83120 |
+
"loss": 0.7826,
|
| 83121 |
+
"step": 11873
|
| 83122 |
+
},
|
| 83123 |
+
{
|
| 83124 |
+
"epoch": 13.524216524216524,
|
| 83125 |
+
"grad_norm": 0.2048841118812561,
|
| 83126 |
+
"learning_rate": 1.2775374325756883e-05,
|
| 83127 |
+
"loss": 0.6602,
|
| 83128 |
+
"step": 11874
|
| 83129 |
+
},
|
| 83130 |
+
{
|
| 83131 |
+
"epoch": 13.525356125356126,
|
| 83132 |
+
"grad_norm": 0.19689778983592987,
|
| 83133 |
+
"learning_rate": 1.2771310370821703e-05,
|
| 83134 |
+
"loss": 0.6727,
|
| 83135 |
+
"step": 11875
|
| 83136 |
+
},
|
| 83137 |
+
{
|
| 83138 |
+
"epoch": 13.526495726495726,
|
| 83139 |
+
"grad_norm": 0.23123781383037567,
|
| 83140 |
+
"learning_rate": 1.2767246840622549e-05,
|
| 83141 |
+
"loss": 0.7002,
|
| 83142 |
+
"step": 11876
|
| 83143 |
+
},
|
| 83144 |
+
{
|
| 83145 |
+
"epoch": 13.527635327635327,
|
| 83146 |
+
"grad_norm": 0.1996956318616867,
|
| 83147 |
+
"learning_rate": 1.2763183735300557e-05,
|
| 83148 |
+
"loss": 0.6125,
|
| 83149 |
+
"step": 11877
|
| 83150 |
+
},
|
| 83151 |
+
{
|
| 83152 |
+
"epoch": 13.52877492877493,
|
| 83153 |
+
"grad_norm": 0.17822016775608063,
|
| 83154 |
+
"learning_rate": 1.2759121054996825e-05,
|
| 83155 |
+
"loss": 0.6241,
|
| 83156 |
+
"step": 11878
|
| 83157 |
+
},
|
| 83158 |
+
{
|
| 83159 |
+
"epoch": 13.52991452991453,
|
| 83160 |
+
"grad_norm": 0.21769826114177704,
|
| 83161 |
+
"learning_rate": 1.2755058799852495e-05,
|
| 83162 |
+
"loss": 0.7486,
|
| 83163 |
+
"step": 11879
|
| 83164 |
+
},
|
| 83165 |
+
{
|
| 83166 |
+
"epoch": 13.53105413105413,
|
| 83167 |
+
"grad_norm": 0.19557489454746246,
|
| 83168 |
+
"learning_rate": 1.2750996970008654e-05,
|
| 83169 |
+
"loss": 0.7319,
|
| 83170 |
+
"step": 11880
|
| 83171 |
+
},
|
| 83172 |
+
{
|
| 83173 |
+
"epoch": 13.532193732193733,
|
| 83174 |
+
"grad_norm": 0.17155064642429352,
|
| 83175 |
+
"learning_rate": 1.2746935565606366e-05,
|
| 83176 |
+
"loss": 0.6238,
|
| 83177 |
+
"step": 11881
|
| 83178 |
+
},
|
| 83179 |
+
{
|
| 83180 |
+
"epoch": 13.533333333333333,
|
| 83181 |
+
"grad_norm": 0.21221791207790375,
|
| 83182 |
+
"learning_rate": 1.27428745867867e-05,
|
| 83183 |
+
"loss": 0.6154,
|
| 83184 |
+
"step": 11882
|
| 83185 |
+
},
|
| 83186 |
+
{
|
| 83187 |
+
"epoch": 13.534472934472934,
|
| 83188 |
+
"grad_norm": 0.2187795341014862,
|
| 83189 |
+
"learning_rate": 1.2738814033690707e-05,
|
| 83190 |
+
"loss": 0.7899,
|
| 83191 |
+
"step": 11883
|
| 83192 |
+
},
|
| 83193 |
+
{
|
| 83194 |
+
"epoch": 13.535612535612536,
|
| 83195 |
+
"grad_norm": 0.2055298388004303,
|
| 83196 |
+
"learning_rate": 1.2734753906459432e-05,
|
| 83197 |
+
"loss": 0.7316,
|
| 83198 |
+
"step": 11884
|
| 83199 |
+
},
|
| 83200 |
+
{
|
| 83201 |
+
"epoch": 13.536752136752137,
|
| 83202 |
+
"grad_norm": 0.1997203379869461,
|
| 83203 |
+
"learning_rate": 1.2730694205233873e-05,
|
| 83204 |
+
"loss": 0.9362,
|
| 83205 |
+
"step": 11885
|
| 83206 |
+
},
|
| 83207 |
+
{
|
| 83208 |
+
"epoch": 13.537891737891737,
|
| 83209 |
+
"grad_norm": 0.2273198515176773,
|
| 83210 |
+
"learning_rate": 1.2726634930155042e-05,
|
| 83211 |
+
"loss": 0.6449,
|
| 83212 |
+
"step": 11886
|
| 83213 |
+
},
|
| 83214 |
+
{
|
| 83215 |
+
"epoch": 13.53903133903134,
|
| 83216 |
+
"grad_norm": 0.2319500744342804,
|
| 83217 |
+
"learning_rate": 1.2722576081363935e-05,
|
| 83218 |
+
"loss": 0.6131,
|
| 83219 |
+
"step": 11887
|
| 83220 |
+
},
|
| 83221 |
+
{
|
| 83222 |
+
"epoch": 13.54017094017094,
|
| 83223 |
+
"grad_norm": 0.19878043234348297,
|
| 83224 |
+
"learning_rate": 1.2718517659001533e-05,
|
| 83225 |
+
"loss": 0.7458,
|
| 83226 |
+
"step": 11888
|
| 83227 |
+
},
|
| 83228 |
+
{
|
| 83229 |
+
"epoch": 13.54131054131054,
|
| 83230 |
+
"grad_norm": 0.2034902125597,
|
| 83231 |
+
"learning_rate": 1.2714459663208767e-05,
|
| 83232 |
+
"loss": 0.622,
|
| 83233 |
+
"step": 11889
|
| 83234 |
+
},
|
| 83235 |
+
{
|
| 83236 |
+
"epoch": 13.542450142450143,
|
| 83237 |
+
"grad_norm": 0.23946736752986908,
|
| 83238 |
+
"learning_rate": 1.271040209412661e-05,
|
| 83239 |
+
"loss": 0.4904,
|
| 83240 |
+
"step": 11890
|
| 83241 |
+
},
|
| 83242 |
+
{
|
| 83243 |
+
"epoch": 13.543589743589743,
|
| 83244 |
+
"grad_norm": 0.2752933204174042,
|
| 83245 |
+
"learning_rate": 1.2706344951895988e-05,
|
| 83246 |
+
"loss": 0.7497,
|
| 83247 |
+
"step": 11891
|
| 83248 |
+
},
|
| 83249 |
+
{
|
| 83250 |
+
"epoch": 13.544729344729344,
|
| 83251 |
+
"grad_norm": 0.2005884200334549,
|
| 83252 |
+
"learning_rate": 1.2702288236657821e-05,
|
| 83253 |
+
"loss": 0.6766,
|
| 83254 |
+
"step": 11892
|
| 83255 |
+
},
|
| 83256 |
+
{
|
| 83257 |
+
"epoch": 13.545868945868946,
|
| 83258 |
+
"grad_norm": 0.1786276251077652,
|
| 83259 |
+
"learning_rate": 1.2698231948552997e-05,
|
| 83260 |
+
"loss": 0.7305,
|
| 83261 |
+
"step": 11893
|
| 83262 |
+
},
|
| 83263 |
+
{
|
| 83264 |
+
"epoch": 13.547008547008547,
|
| 83265 |
+
"grad_norm": 0.24155272543430328,
|
| 83266 |
+
"learning_rate": 1.2694176087722404e-05,
|
| 83267 |
+
"loss": 0.721,
|
| 83268 |
+
"step": 11894
|
| 83269 |
+
},
|
| 83270 |
+
{
|
| 83271 |
+
"epoch": 13.548148148148147,
|
| 83272 |
+
"grad_norm": 0.23642794787883759,
|
| 83273 |
+
"learning_rate": 1.2690120654306914e-05,
|
| 83274 |
+
"loss": 0.7851,
|
| 83275 |
+
"step": 11895
|
| 83276 |
+
},
|
| 83277 |
+
{
|
| 83278 |
+
"epoch": 13.54928774928775,
|
| 83279 |
+
"grad_norm": 0.19893379509449005,
|
| 83280 |
+
"learning_rate": 1.2686065648447399e-05,
|
| 83281 |
+
"loss": 0.5975,
|
| 83282 |
+
"step": 11896
|
| 83283 |
+
},
|
| 83284 |
+
{
|
| 83285 |
+
"epoch": 13.55042735042735,
|
| 83286 |
+
"grad_norm": 0.2467699944972992,
|
| 83287 |
+
"learning_rate": 1.2682011070284678e-05,
|
| 83288 |
+
"loss": 0.6753,
|
| 83289 |
+
"step": 11897
|
| 83290 |
+
},
|
| 83291 |
+
{
|
| 83292 |
+
"epoch": 13.55156695156695,
|
| 83293 |
+
"grad_norm": 0.22657524049282074,
|
| 83294 |
+
"learning_rate": 1.2677956919959588e-05,
|
| 83295 |
+
"loss": 0.3883,
|
| 83296 |
+
"step": 11898
|
| 83297 |
+
},
|
| 83298 |
+
{
|
| 83299 |
+
"epoch": 13.552706552706553,
|
| 83300 |
+
"grad_norm": 0.24406392872333527,
|
| 83301 |
+
"learning_rate": 1.2673903197612935e-05,
|
| 83302 |
+
"loss": 0.4954,
|
| 83303 |
+
"step": 11899
|
| 83304 |
+
},
|
| 83305 |
+
{
|
| 83306 |
+
"epoch": 13.553846153846154,
|
| 83307 |
+
"grad_norm": 0.17373217642307281,
|
| 83308 |
+
"learning_rate": 1.2669849903385525e-05,
|
| 83309 |
+
"loss": 0.7426,
|
| 83310 |
+
"step": 11900
|
| 83311 |
+
},
|
| 83312 |
+
{
|
| 83313 |
+
"epoch": 13.554985754985754,
|
| 83314 |
+
"grad_norm": 0.16287533938884735,
|
| 83315 |
+
"learning_rate": 1.2665797037418136e-05,
|
| 83316 |
+
"loss": 0.8058,
|
| 83317 |
+
"step": 11901
|
| 83318 |
+
},
|
| 83319 |
+
{
|
| 83320 |
+
"epoch": 13.556125356125357,
|
| 83321 |
+
"grad_norm": 0.18679316341876984,
|
| 83322 |
+
"learning_rate": 1.2661744599851533e-05,
|
| 83323 |
+
"loss": 0.7145,
|
| 83324 |
+
"step": 11902
|
| 83325 |
+
},
|
| 83326 |
+
{
|
| 83327 |
+
"epoch": 13.557264957264957,
|
| 83328 |
+
"grad_norm": 0.17649011313915253,
|
| 83329 |
+
"learning_rate": 1.2657692590826481e-05,
|
| 83330 |
+
"loss": 0.757,
|
| 83331 |
+
"step": 11903
|
| 83332 |
+
},
|
| 83333 |
+
{
|
| 83334 |
+
"epoch": 13.558404558404558,
|
| 83335 |
+
"grad_norm": 0.2134092003107071,
|
| 83336 |
+
"learning_rate": 1.2653641010483697e-05,
|
| 83337 |
+
"loss": 0.7175,
|
| 83338 |
+
"step": 11904
|
| 83339 |
+
},
|
| 83340 |
+
{
|
| 83341 |
+
"epoch": 13.55954415954416,
|
| 83342 |
+
"grad_norm": 0.21499109268188477,
|
| 83343 |
+
"learning_rate": 1.2649589858963914e-05,
|
| 83344 |
+
"loss": 0.6921,
|
| 83345 |
+
"step": 11905
|
| 83346 |
+
},
|
| 83347 |
+
{
|
| 83348 |
+
"epoch": 13.56068376068376,
|
| 83349 |
+
"grad_norm": 0.21749883890151978,
|
| 83350 |
+
"learning_rate": 1.2645539136407842e-05,
|
| 83351 |
+
"loss": 0.6565,
|
| 83352 |
+
"step": 11906
|
| 83353 |
+
},
|
| 83354 |
+
{
|
| 83355 |
+
"epoch": 13.561823361823361,
|
| 83356 |
+
"grad_norm": 0.18136462569236755,
|
| 83357 |
+
"learning_rate": 1.2641488842956172e-05,
|
| 83358 |
+
"loss": 0.7308,
|
| 83359 |
+
"step": 11907
|
| 83360 |
+
},
|
| 83361 |
+
{
|
| 83362 |
+
"epoch": 13.562962962962963,
|
| 83363 |
+
"grad_norm": 0.21715889871120453,
|
| 83364 |
+
"learning_rate": 1.2637438978749577e-05,
|
| 83365 |
+
"loss": 0.7452,
|
| 83366 |
+
"step": 11908
|
| 83367 |
+
},
|
| 83368 |
+
{
|
| 83369 |
+
"epoch": 13.564102564102564,
|
| 83370 |
+
"grad_norm": 0.20942451059818268,
|
| 83371 |
+
"learning_rate": 1.2633389543928726e-05,
|
| 83372 |
+
"loss": 0.7688,
|
| 83373 |
+
"step": 11909
|
| 83374 |
+
},
|
| 83375 |
+
{
|
| 83376 |
+
"epoch": 13.565242165242164,
|
| 83377 |
+
"grad_norm": 0.18523932993412018,
|
| 83378 |
+
"learning_rate": 1.2629340538634257e-05,
|
| 83379 |
+
"loss": 0.7706,
|
| 83380 |
+
"step": 11910
|
| 83381 |
+
},
|
| 83382 |
+
{
|
| 83383 |
+
"epoch": 13.566381766381767,
|
| 83384 |
+
"grad_norm": 0.23703047633171082,
|
| 83385 |
+
"learning_rate": 1.2625291963006814e-05,
|
| 83386 |
+
"loss": 0.6041,
|
| 83387 |
+
"step": 11911
|
| 83388 |
+
},
|
| 83389 |
+
{
|
| 83390 |
+
"epoch": 13.567521367521367,
|
| 83391 |
+
"grad_norm": 0.21664546430110931,
|
| 83392 |
+
"learning_rate": 1.2621243817187013e-05,
|
| 83393 |
+
"loss": 0.6085,
|
| 83394 |
+
"step": 11912
|
| 83395 |
+
},
|
| 83396 |
+
{
|
| 83397 |
+
"epoch": 13.568660968660968,
|
| 83398 |
+
"grad_norm": 0.239175483584404,
|
| 83399 |
+
"learning_rate": 1.2617196101315453e-05,
|
| 83400 |
+
"loss": 0.4718,
|
| 83401 |
+
"step": 11913
|
| 83402 |
+
},
|
| 83403 |
+
{
|
| 83404 |
+
"epoch": 13.56980056980057,
|
| 83405 |
+
"grad_norm": 0.2262725681066513,
|
| 83406 |
+
"learning_rate": 1.2613148815532738e-05,
|
| 83407 |
+
"loss": 0.6674,
|
| 83408 |
+
"step": 11914
|
| 83409 |
+
},
|
| 83410 |
+
{
|
| 83411 |
+
"epoch": 13.57094017094017,
|
| 83412 |
+
"grad_norm": 0.23112249374389648,
|
| 83413 |
+
"learning_rate": 1.260910195997942e-05,
|
| 83414 |
+
"loss": 0.5022,
|
| 83415 |
+
"step": 11915
|
| 83416 |
+
},
|
| 83417 |
+
{
|
| 83418 |
+
"epoch": 13.572079772079771,
|
| 83419 |
+
"grad_norm": 0.22211824357509613,
|
| 83420 |
+
"learning_rate": 1.2605055534796062e-05,
|
| 83421 |
+
"loss": 0.7274,
|
| 83422 |
+
"step": 11916
|
| 83423 |
+
},
|
| 83424 |
+
{
|
| 83425 |
+
"epoch": 13.573219373219374,
|
| 83426 |
+
"grad_norm": 0.2197098433971405,
|
| 83427 |
+
"learning_rate": 1.2601009540123213e-05,
|
| 83428 |
+
"loss": 0.4865,
|
| 83429 |
+
"step": 11917
|
| 83430 |
+
},
|
| 83431 |
+
{
|
| 83432 |
+
"epoch": 13.574358974358974,
|
| 83433 |
+
"grad_norm": 0.2433994561433792,
|
| 83434 |
+
"learning_rate": 1.259696397610141e-05,
|
| 83435 |
+
"loss": 0.6374,
|
| 83436 |
+
"step": 11918
|
| 83437 |
+
},
|
| 83438 |
+
{
|
| 83439 |
+
"epoch": 13.575498575498575,
|
| 83440 |
+
"grad_norm": 0.25643351674079895,
|
| 83441 |
+
"learning_rate": 1.259291884287115e-05,
|
| 83442 |
+
"loss": 0.5213,
|
| 83443 |
+
"step": 11919
|
| 83444 |
+
},
|
| 83445 |
+
{
|
| 83446 |
+
"epoch": 13.576638176638177,
|
| 83447 |
+
"grad_norm": 0.1962897628545761,
|
| 83448 |
+
"learning_rate": 1.2588874140572932e-05,
|
| 83449 |
+
"loss": 0.8476,
|
| 83450 |
+
"step": 11920
|
| 83451 |
+
},
|
| 83452 |
+
{
|
| 83453 |
+
"epoch": 13.577777777777778,
|
| 83454 |
+
"grad_norm": 0.23479922115802765,
|
| 83455 |
+
"learning_rate": 1.2584829869347247e-05,
|
| 83456 |
+
"loss": 0.6863,
|
| 83457 |
+
"step": 11921
|
| 83458 |
+
},
|
| 83459 |
+
{
|
| 83460 |
+
"epoch": 13.578917378917378,
|
| 83461 |
+
"grad_norm": 0.18647314608097076,
|
| 83462 |
+
"learning_rate": 1.2580786029334569e-05,
|
| 83463 |
+
"loss": 0.8135,
|
| 83464 |
+
"step": 11922
|
| 83465 |
+
},
|
| 83466 |
+
{
|
| 83467 |
+
"epoch": 13.58005698005698,
|
| 83468 |
+
"grad_norm": 0.19278664886951447,
|
| 83469 |
+
"learning_rate": 1.2576742620675336e-05,
|
| 83470 |
+
"loss": 0.5966,
|
| 83471 |
+
"step": 11923
|
| 83472 |
+
},
|
| 83473 |
+
{
|
| 83474 |
+
"epoch": 13.581196581196581,
|
| 83475 |
+
"grad_norm": 0.1958315074443817,
|
| 83476 |
+
"learning_rate": 1.2572699643510003e-05,
|
| 83477 |
+
"loss": 0.5162,
|
| 83478 |
+
"step": 11924
|
| 83479 |
+
},
|
| 83480 |
+
{
|
| 83481 |
+
"epoch": 13.582336182336181,
|
| 83482 |
+
"grad_norm": 0.16626198589801788,
|
| 83483 |
+
"learning_rate": 1.2568657097978992e-05,
|
| 83484 |
+
"loss": 0.774,
|
| 83485 |
+
"step": 11925
|
| 83486 |
+
},
|
| 83487 |
+
{
|
| 83488 |
+
"epoch": 13.583475783475784,
|
| 83489 |
+
"grad_norm": 0.24117280542850494,
|
| 83490 |
+
"learning_rate": 1.25646149842227e-05,
|
| 83491 |
+
"loss": 0.6517,
|
| 83492 |
+
"step": 11926
|
| 83493 |
+
},
|
| 83494 |
+
{
|
| 83495 |
+
"epoch": 13.584615384615384,
|
| 83496 |
+
"grad_norm": 0.17913152277469635,
|
| 83497 |
+
"learning_rate": 1.2560573302381524e-05,
|
| 83498 |
+
"loss": 0.8523,
|
| 83499 |
+
"step": 11927
|
| 83500 |
+
},
|
| 83501 |
+
{
|
| 83502 |
+
"epoch": 13.585754985754985,
|
| 83503 |
+
"grad_norm": 0.2595483660697937,
|
| 83504 |
+
"learning_rate": 1.2556532052595848e-05,
|
| 83505 |
+
"loss": 0.5177,
|
| 83506 |
+
"step": 11928
|
| 83507 |
+
},
|
| 83508 |
+
{
|
| 83509 |
+
"epoch": 13.586894586894587,
|
| 83510 |
+
"grad_norm": 0.200043186545372,
|
| 83511 |
+
"learning_rate": 1.2552491235006041e-05,
|
| 83512 |
+
"loss": 0.8274,
|
| 83513 |
+
"step": 11929
|
| 83514 |
+
},
|
| 83515 |
+
{
|
| 83516 |
+
"epoch": 13.588034188034188,
|
| 83517 |
+
"grad_norm": 0.21147392690181732,
|
| 83518 |
+
"learning_rate": 1.2548450849752435e-05,
|
| 83519 |
+
"loss": 0.7123,
|
| 83520 |
+
"step": 11930
|
| 83521 |
+
},
|
| 83522 |
+
{
|
| 83523 |
+
"epoch": 13.589173789173788,
|
| 83524 |
+
"grad_norm": 0.22863133251667023,
|
| 83525 |
+
"learning_rate": 1.2544410896975376e-05,
|
| 83526 |
+
"loss": 0.569,
|
| 83527 |
+
"step": 11931
|
| 83528 |
+
},
|
| 83529 |
+
{
|
| 83530 |
+
"epoch": 13.59031339031339,
|
| 83531 |
+
"grad_norm": 0.17246928811073303,
|
| 83532 |
+
"learning_rate": 1.2540371376815177e-05,
|
| 83533 |
+
"loss": 0.7866,
|
| 83534 |
+
"step": 11932
|
| 83535 |
+
},
|
| 83536 |
+
{
|
| 83537 |
+
"epoch": 13.591452991452991,
|
| 83538 |
+
"grad_norm": 0.16606873273849487,
|
| 83539 |
+
"learning_rate": 1.2536332289412145e-05,
|
| 83540 |
+
"loss": 0.8087,
|
| 83541 |
+
"step": 11933
|
| 83542 |
+
},
|
| 83543 |
+
{
|
| 83544 |
+
"epoch": 13.592592592592592,
|
| 83545 |
+
"grad_norm": 0.21755880117416382,
|
| 83546 |
+
"learning_rate": 1.2532293634906567e-05,
|
| 83547 |
+
"loss": 0.6748,
|
| 83548 |
+
"step": 11934
|
| 83549 |
+
},
|
| 83550 |
+
{
|
| 83551 |
+
"epoch": 13.593732193732194,
|
| 83552 |
+
"grad_norm": 0.1909179836511612,
|
| 83553 |
+
"learning_rate": 1.2528255413438716e-05,
|
| 83554 |
+
"loss": 0.7769,
|
| 83555 |
+
"step": 11935
|
| 83556 |
+
},
|
| 83557 |
+
{
|
| 83558 |
+
"epoch": 13.594871794871795,
|
| 83559 |
+
"grad_norm": 0.2857014536857605,
|
| 83560 |
+
"learning_rate": 1.2524217625148854e-05,
|
| 83561 |
+
"loss": 0.4679,
|
| 83562 |
+
"step": 11936
|
| 83563 |
+
},
|
| 83564 |
+
{
|
| 83565 |
+
"epoch": 13.596011396011395,
|
| 83566 |
+
"grad_norm": 0.2215040922164917,
|
| 83567 |
+
"learning_rate": 1.2520180270177231e-05,
|
| 83568 |
+
"loss": 0.6349,
|
| 83569 |
+
"step": 11937
|
| 83570 |
+
},
|
| 83571 |
+
{
|
| 83572 |
+
"epoch": 13.597150997150997,
|
| 83573 |
+
"grad_norm": 0.20099647343158722,
|
| 83574 |
+
"learning_rate": 1.2516143348664058e-05,
|
| 83575 |
+
"loss": 0.7075,
|
| 83576 |
+
"step": 11938
|
| 83577 |
+
},
|
| 83578 |
+
{
|
| 83579 |
+
"epoch": 13.598290598290598,
|
| 83580 |
+
"grad_norm": 0.2536945939064026,
|
| 83581 |
+
"learning_rate": 1.2512106860749556e-05,
|
| 83582 |
+
"loss": 0.6181,
|
| 83583 |
+
"step": 11939
|
| 83584 |
+
},
|
| 83585 |
+
{
|
| 83586 |
+
"epoch": 13.5994301994302,
|
| 83587 |
+
"grad_norm": 0.19861255586147308,
|
| 83588 |
+
"learning_rate": 1.2508070806573927e-05,
|
| 83589 |
+
"loss": 0.8053,
|
| 83590 |
+
"step": 11940
|
| 83591 |
+
},
|
| 83592 |
+
{
|
| 83593 |
+
"epoch": 13.6005698005698,
|
| 83594 |
+
"grad_norm": 0.22227483987808228,
|
| 83595 |
+
"learning_rate": 1.250403518627736e-05,
|
| 83596 |
+
"loss": 0.66,
|
| 83597 |
+
"step": 11941
|
| 83598 |
+
},
|
| 83599 |
+
{
|
| 83600 |
+
"epoch": 13.601709401709401,
|
| 83601 |
+
"grad_norm": 0.23981639742851257,
|
| 83602 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 83603 |
+
"loss": 0.6902,
|
| 83604 |
+
"step": 11942
|
| 83605 |
+
},
|
| 83606 |
+
{
|
| 83607 |
+
"epoch": 13.602849002849004,
|
| 83608 |
+
"grad_norm": 0.20598097145557404,
|
| 83609 |
+
"learning_rate": 1.2495965247882027e-05,
|
| 83610 |
+
"loss": 0.6442,
|
| 83611 |
+
"step": 11943
|
| 83612 |
+
},
|
| 83613 |
+
{
|
| 83614 |
+
"epoch": 13.603988603988604,
|
| 83615 |
+
"grad_norm": 0.18238377571105957,
|
| 83616 |
+
"learning_rate": 1.249193093006356e-05,
|
| 83617 |
+
"loss": 0.7795,
|
| 83618 |
+
"step": 11944
|
| 83619 |
+
},
|
| 83620 |
+
{
|
| 83621 |
+
"epoch": 13.605128205128205,
|
| 83622 |
+
"grad_norm": 0.21116027235984802,
|
| 83623 |
+
"learning_rate": 1.2487897046684729e-05,
|
| 83624 |
+
"loss": 0.7298,
|
| 83625 |
+
"step": 11945
|
| 83626 |
+
},
|
| 83627 |
+
{
|
| 83628 |
+
"epoch": 13.606267806267807,
|
| 83629 |
+
"grad_norm": 0.23421117663383484,
|
| 83630 |
+
"learning_rate": 1.2483863597885642e-05,
|
| 83631 |
+
"loss": 0.6085,
|
| 83632 |
+
"step": 11946
|
| 83633 |
+
},
|
| 83634 |
+
{
|
| 83635 |
+
"epoch": 13.607407407407408,
|
| 83636 |
+
"grad_norm": 0.2317437380552292,
|
| 83637 |
+
"learning_rate": 1.2479830583806392e-05,
|
| 83638 |
+
"loss": 0.7832,
|
| 83639 |
+
"step": 11947
|
| 83640 |
+
},
|
| 83641 |
+
{
|
| 83642 |
+
"epoch": 13.608547008547008,
|
| 83643 |
+
"grad_norm": 0.2056443840265274,
|
| 83644 |
+
"learning_rate": 1.247579800458707e-05,
|
| 83645 |
+
"loss": 0.7342,
|
| 83646 |
+
"step": 11948
|
| 83647 |
+
},
|
| 83648 |
+
{
|
| 83649 |
+
"epoch": 13.60968660968661,
|
| 83650 |
+
"grad_norm": 0.16647958755493164,
|
| 83651 |
+
"learning_rate": 1.247176586036771e-05,
|
| 83652 |
+
"loss": 0.8492,
|
| 83653 |
+
"step": 11949
|
| 83654 |
+
},
|
| 83655 |
+
{
|
| 83656 |
+
"epoch": 13.610826210826211,
|
| 83657 |
+
"grad_norm": 0.18847352266311646,
|
| 83658 |
+
"learning_rate": 1.2467734151288377e-05,
|
| 83659 |
+
"loss": 0.7253,
|
| 83660 |
+
"step": 11950
|
| 83661 |
+
},
|
| 83662 |
+
{
|
| 83663 |
+
"epoch": 13.611965811965812,
|
| 83664 |
+
"grad_norm": 0.23761668801307678,
|
| 83665 |
+
"learning_rate": 1.24637028774891e-05,
|
| 83666 |
+
"loss": 0.5955,
|
| 83667 |
+
"step": 11951
|
| 83668 |
+
},
|
| 83669 |
+
{
|
| 83670 |
+
"epoch": 13.613105413105414,
|
| 83671 |
+
"grad_norm": 0.1838001161813736,
|
| 83672 |
+
"learning_rate": 1.2459672039109907e-05,
|
| 83673 |
+
"loss": 0.7702,
|
| 83674 |
+
"step": 11952
|
| 83675 |
+
},
|
| 83676 |
+
{
|
| 83677 |
+
"epoch": 13.614245014245014,
|
| 83678 |
+
"grad_norm": 0.18846701085567474,
|
| 83679 |
+
"learning_rate": 1.245564163629078e-05,
|
| 83680 |
+
"loss": 0.771,
|
| 83681 |
+
"step": 11953
|
| 83682 |
+
},
|
| 83683 |
+
{
|
| 83684 |
+
"epoch": 13.615384615384615,
|
| 83685 |
+
"grad_norm": 0.1988699734210968,
|
| 83686 |
+
"learning_rate": 1.2451611669171717e-05,
|
| 83687 |
+
"loss": 0.6131,
|
| 83688 |
+
"step": 11954
|
| 83689 |
+
},
|
| 83690 |
+
{
|
| 83691 |
+
"epoch": 13.616524216524217,
|
| 83692 |
+
"grad_norm": 0.16885283589363098,
|
| 83693 |
+
"learning_rate": 1.2447582137892688e-05,
|
| 83694 |
+
"loss": 0.6178,
|
| 83695 |
+
"step": 11955
|
| 83696 |
+
},
|
| 83697 |
+
{
|
| 83698 |
+
"epoch": 13.617663817663818,
|
| 83699 |
+
"grad_norm": 0.2070610374212265,
|
| 83700 |
+
"learning_rate": 1.244355304259365e-05,
|
| 83701 |
+
"loss": 0.3871,
|
| 83702 |
+
"step": 11956
|
| 83703 |
+
},
|
| 83704 |
+
{
|
| 83705 |
+
"epoch": 13.618803418803418,
|
| 83706 |
+
"grad_norm": 0.2371179312467575,
|
| 83707 |
+
"learning_rate": 1.2439524383414547e-05,
|
| 83708 |
+
"loss": 0.6418,
|
| 83709 |
+
"step": 11957
|
| 83710 |
+
},
|
| 83711 |
+
{
|
| 83712 |
+
"epoch": 13.61994301994302,
|
| 83713 |
+
"grad_norm": 0.2366572618484497,
|
| 83714 |
+
"learning_rate": 1.2435496160495302e-05,
|
| 83715 |
+
"loss": 0.7808,
|
| 83716 |
+
"step": 11958
|
| 83717 |
+
},
|
| 83718 |
+
{
|
| 83719 |
+
"epoch": 13.621082621082621,
|
| 83720 |
+
"grad_norm": 0.3098319470882416,
|
| 83721 |
+
"learning_rate": 1.2431468373975841e-05,
|
| 83722 |
+
"loss": 0.4199,
|
| 83723 |
+
"step": 11959
|
| 83724 |
+
},
|
| 83725 |
+
{
|
| 83726 |
+
"epoch": 13.622222222222222,
|
| 83727 |
+
"grad_norm": 0.22360925376415253,
|
| 83728 |
+
"learning_rate": 1.2427441023996033e-05,
|
| 83729 |
+
"loss": 0.6718,
|
| 83730 |
+
"step": 11960
|
| 83731 |
+
},
|
| 83732 |
+
{
|
| 83733 |
+
"epoch": 13.623361823361824,
|
| 83734 |
+
"grad_norm": 0.19217972457408905,
|
| 83735 |
+
"learning_rate": 1.2423414110695775e-05,
|
| 83736 |
+
"loss": 0.578,
|
| 83737 |
+
"step": 11961
|
| 83738 |
+
},
|
| 83739 |
+
{
|
| 83740 |
+
"epoch": 13.624501424501425,
|
| 83741 |
+
"grad_norm": 0.2236679196357727,
|
| 83742 |
+
"learning_rate": 1.241938763421493e-05,
|
| 83743 |
+
"loss": 0.6048,
|
| 83744 |
+
"step": 11962
|
| 83745 |
+
},
|
| 83746 |
+
{
|
| 83747 |
+
"epoch": 13.625641025641025,
|
| 83748 |
+
"grad_norm": 0.2347201257944107,
|
| 83749 |
+
"learning_rate": 1.2415361594693358e-05,
|
| 83750 |
+
"loss": 0.5748,
|
| 83751 |
+
"step": 11963
|
| 83752 |
+
},
|
| 83753 |
+
{
|
| 83754 |
+
"epoch": 13.626780626780628,
|
| 83755 |
+
"grad_norm": 0.18007099628448486,
|
| 83756 |
+
"learning_rate": 1.2411335992270878e-05,
|
| 83757 |
+
"loss": 0.6316,
|
| 83758 |
+
"step": 11964
|
| 83759 |
+
},
|
| 83760 |
+
{
|
| 83761 |
+
"epoch": 13.627920227920228,
|
| 83762 |
+
"grad_norm": 0.241592139005661,
|
| 83763 |
+
"learning_rate": 1.2407310827087318e-05,
|
| 83764 |
+
"loss": 0.5624,
|
| 83765 |
+
"step": 11965
|
| 83766 |
+
},
|
| 83767 |
+
{
|
| 83768 |
+
"epoch": 13.629059829059829,
|
| 83769 |
+
"grad_norm": 0.2217334806919098,
|
| 83770 |
+
"learning_rate": 1.2403286099282474e-05,
|
| 83771 |
+
"loss": 0.7087,
|
| 83772 |
+
"step": 11966
|
| 83773 |
+
},
|
| 83774 |
+
{
|
| 83775 |
+
"epoch": 13.630199430199431,
|
| 83776 |
+
"grad_norm": 0.19712881743907928,
|
| 83777 |
+
"learning_rate": 1.2399261808996162e-05,
|
| 83778 |
+
"loss": 0.8149,
|
| 83779 |
+
"step": 11967
|
| 83780 |
+
},
|
| 83781 |
+
{
|
| 83782 |
+
"epoch": 13.631339031339031,
|
| 83783 |
+
"grad_norm": 0.22485846281051636,
|
| 83784 |
+
"learning_rate": 1.239523795636813e-05,
|
| 83785 |
+
"loss": 0.8697,
|
| 83786 |
+
"step": 11968
|
| 83787 |
+
},
|
| 83788 |
+
{
|
| 83789 |
+
"epoch": 13.632478632478632,
|
| 83790 |
+
"grad_norm": 0.19370786845684052,
|
| 83791 |
+
"learning_rate": 1.2391214541538149e-05,
|
| 83792 |
+
"loss": 0.797,
|
| 83793 |
+
"step": 11969
|
| 83794 |
+
},
|
| 83795 |
+
{
|
| 83796 |
+
"epoch": 13.633618233618234,
|
| 83797 |
+
"grad_norm": 0.2015693038702011,
|
| 83798 |
+
"learning_rate": 1.2387191564645958e-05,
|
| 83799 |
+
"loss": 0.7652,
|
| 83800 |
+
"step": 11970
|
| 83801 |
+
},
|
| 83802 |
+
{
|
| 83803 |
+
"epoch": 13.634757834757835,
|
| 83804 |
+
"grad_norm": 0.3329710364341736,
|
| 83805 |
+
"learning_rate": 1.23831690258313e-05,
|
| 83806 |
+
"loss": 0.3782,
|
| 83807 |
+
"step": 11971
|
| 83808 |
+
},
|
| 83809 |
+
{
|
| 83810 |
+
"epoch": 13.635897435897435,
|
| 83811 |
+
"grad_norm": 0.24312107264995575,
|
| 83812 |
+
"learning_rate": 1.237914692523387e-05,
|
| 83813 |
+
"loss": 0.7565,
|
| 83814 |
+
"step": 11972
|
| 83815 |
+
},
|
| 83816 |
+
{
|
| 83817 |
+
"epoch": 13.637037037037038,
|
| 83818 |
+
"grad_norm": 0.1755981296300888,
|
| 83819 |
+
"learning_rate": 1.2375125262993376e-05,
|
| 83820 |
+
"loss": 0.7782,
|
| 83821 |
+
"step": 11973
|
| 83822 |
+
},
|
| 83823 |
+
{
|
| 83824 |
+
"epoch": 13.638176638176638,
|
| 83825 |
+
"grad_norm": 0.26076728105545044,
|
| 83826 |
+
"learning_rate": 1.2371104039249498e-05,
|
| 83827 |
+
"loss": 0.5249,
|
| 83828 |
+
"step": 11974
|
| 83829 |
+
},
|
| 83830 |
+
{
|
| 83831 |
+
"epoch": 13.639316239316239,
|
| 83832 |
+
"grad_norm": 0.19592714309692383,
|
| 83833 |
+
"learning_rate": 1.2367083254141915e-05,
|
| 83834 |
+
"loss": 0.6927,
|
| 83835 |
+
"step": 11975
|
| 83836 |
+
},
|
| 83837 |
+
{
|
| 83838 |
+
"epoch": 13.640455840455841,
|
| 83839 |
+
"grad_norm": 0.21158058941364288,
|
| 83840 |
+
"learning_rate": 1.2363062907810263e-05,
|
| 83841 |
+
"loss": 0.6754,
|
| 83842 |
+
"step": 11976
|
| 83843 |
+
},
|
| 83844 |
+
{
|
| 83845 |
+
"epoch": 13.641595441595442,
|
| 83846 |
+
"grad_norm": 0.21058164536952972,
|
| 83847 |
+
"learning_rate": 1.2359043000394178e-05,
|
| 83848 |
+
"loss": 0.6716,
|
| 83849 |
+
"step": 11977
|
| 83850 |
+
},
|
| 83851 |
+
{
|
| 83852 |
+
"epoch": 13.642735042735042,
|
| 83853 |
+
"grad_norm": 0.1837356686592102,
|
| 83854 |
+
"learning_rate": 1.2355023532033311e-05,
|
| 83855 |
+
"loss": 0.9676,
|
| 83856 |
+
"step": 11978
|
| 83857 |
+
},
|
| 83858 |
+
{
|
| 83859 |
+
"epoch": 13.643874643874645,
|
| 83860 |
+
"grad_norm": 0.17448551952838898,
|
| 83861 |
+
"learning_rate": 1.2351004502867242e-05,
|
| 83862 |
+
"loss": 0.8437,
|
| 83863 |
+
"step": 11979
|
| 83864 |
+
},
|
| 83865 |
+
{
|
| 83866 |
+
"epoch": 13.645014245014245,
|
| 83867 |
+
"grad_norm": 0.2007696032524109,
|
| 83868 |
+
"learning_rate": 1.2346985913035572e-05,
|
| 83869 |
+
"loss": 0.814,
|
| 83870 |
+
"step": 11980
|
| 83871 |
+
},
|
| 83872 |
+
{
|
| 83873 |
+
"epoch": 13.646153846153846,
|
| 83874 |
+
"grad_norm": 0.2008890062570572,
|
| 83875 |
+
"learning_rate": 1.2342967762677876e-05,
|
| 83876 |
+
"loss": 0.7094,
|
| 83877 |
+
"step": 11981
|
| 83878 |
+
},
|
| 83879 |
+
{
|
| 83880 |
+
"epoch": 13.647293447293448,
|
| 83881 |
+
"grad_norm": 0.1742667853832245,
|
| 83882 |
+
"learning_rate": 1.2338950051933726e-05,
|
| 83883 |
+
"loss": 0.8423,
|
| 83884 |
+
"step": 11982
|
| 83885 |
+
},
|
| 83886 |
+
{
|
| 83887 |
+
"epoch": 13.648433048433048,
|
| 83888 |
+
"grad_norm": 0.22775019705295563,
|
| 83889 |
+
"learning_rate": 1.2334932780942648e-05,
|
| 83890 |
+
"loss": 0.3184,
|
| 83891 |
+
"step": 11983
|
| 83892 |
+
},
|
| 83893 |
+
{
|
| 83894 |
+
"epoch": 13.649572649572649,
|
| 83895 |
+
"grad_norm": 0.23534031212329865,
|
| 83896 |
+
"learning_rate": 1.2330915949844187e-05,
|
| 83897 |
+
"loss": 0.7006,
|
| 83898 |
+
"step": 11984
|
| 83899 |
+
},
|
| 83900 |
+
{
|
| 83901 |
+
"epoch": 13.650712250712251,
|
| 83902 |
+
"grad_norm": 0.17848096787929535,
|
| 83903 |
+
"learning_rate": 1.2326899558777855e-05,
|
| 83904 |
+
"loss": 0.7268,
|
| 83905 |
+
"step": 11985
|
| 83906 |
+
},
|
| 83907 |
+
{
|
| 83908 |
+
"epoch": 13.651851851851852,
|
| 83909 |
+
"grad_norm": 0.2199409306049347,
|
| 83910 |
+
"learning_rate": 1.232288360788316e-05,
|
| 83911 |
+
"loss": 0.6399,
|
| 83912 |
+
"step": 11986
|
| 83913 |
+
},
|
| 83914 |
+
{
|
| 83915 |
+
"epoch": 13.652991452991452,
|
| 83916 |
+
"grad_norm": 0.20777131617069244,
|
| 83917 |
+
"learning_rate": 1.2318868097299568e-05,
|
| 83918 |
+
"loss": 0.8304,
|
| 83919 |
+
"step": 11987
|
| 83920 |
+
},
|
| 83921 |
+
{
|
| 83922 |
+
"epoch": 13.654131054131055,
|
| 83923 |
+
"grad_norm": 0.20312553644180298,
|
| 83924 |
+
"learning_rate": 1.2314853027166565e-05,
|
| 83925 |
+
"loss": 0.8173,
|
| 83926 |
+
"step": 11988
|
| 83927 |
+
},
|
| 83928 |
+
{
|
| 83929 |
+
"epoch": 13.655270655270655,
|
| 83930 |
+
"grad_norm": 0.15953557193279266,
|
| 83931 |
+
"learning_rate": 1.2310838397623598e-05,
|
| 83932 |
+
"loss": 0.7031,
|
| 83933 |
+
"step": 11989
|
| 83934 |
+
},
|
| 83935 |
+
{
|
| 83936 |
+
"epoch": 13.656410256410256,
|
| 83937 |
+
"grad_norm": 0.2103070765733719,
|
| 83938 |
+
"learning_rate": 1.2306824208810108e-05,
|
| 83939 |
+
"loss": 0.89,
|
| 83940 |
+
"step": 11990
|
| 83941 |
+
},
|
| 83942 |
+
{
|
| 83943 |
+
"epoch": 13.657549857549858,
|
| 83944 |
+
"grad_norm": 0.2311912178993225,
|
| 83945 |
+
"learning_rate": 1.2302810460865522e-05,
|
| 83946 |
+
"loss": 0.4565,
|
| 83947 |
+
"step": 11991
|
| 83948 |
+
},
|
| 83949 |
+
{
|
| 83950 |
+
"epoch": 13.658689458689459,
|
| 83951 |
+
"grad_norm": 0.2704470753669739,
|
| 83952 |
+
"learning_rate": 1.2298797153929243e-05,
|
| 83953 |
+
"loss": 0.5362,
|
| 83954 |
+
"step": 11992
|
| 83955 |
+
},
|
| 83956 |
+
{
|
| 83957 |
+
"epoch": 13.65982905982906,
|
| 83958 |
+
"grad_norm": 0.23101139068603516,
|
| 83959 |
+
"learning_rate": 1.2294784288140679e-05,
|
| 83960 |
+
"loss": 0.6446,
|
| 83961 |
+
"step": 11993
|
| 83962 |
+
},
|
| 83963 |
+
{
|
| 83964 |
+
"epoch": 13.660968660968662,
|
| 83965 |
+
"grad_norm": 0.21261920034885406,
|
| 83966 |
+
"learning_rate": 1.2290771863639186e-05,
|
| 83967 |
+
"loss": 0.8463,
|
| 83968 |
+
"step": 11994
|
| 83969 |
+
},
|
| 83970 |
+
{
|
| 83971 |
+
"epoch": 13.662108262108262,
|
| 83972 |
+
"grad_norm": 0.19150252640247345,
|
| 83973 |
+
"learning_rate": 1.2286759880564136e-05,
|
| 83974 |
+
"loss": 0.6388,
|
| 83975 |
+
"step": 11995
|
| 83976 |
+
},
|
| 83977 |
+
{
|
| 83978 |
+
"epoch": 13.663247863247863,
|
| 83979 |
+
"grad_norm": 0.18911303579807281,
|
| 83980 |
+
"learning_rate": 1.2282748339054878e-05,
|
| 83981 |
+
"loss": 0.5826,
|
| 83982 |
+
"step": 11996
|
| 83983 |
+
},
|
| 83984 |
+
{
|
| 83985 |
+
"epoch": 13.664387464387465,
|
| 83986 |
+
"grad_norm": 0.21570447087287903,
|
| 83987 |
+
"learning_rate": 1.2278737239250754e-05,
|
| 83988 |
+
"loss": 0.6871,
|
| 83989 |
+
"step": 11997
|
| 83990 |
+
},
|
| 83991 |
+
{
|
| 83992 |
+
"epoch": 13.665527065527066,
|
| 83993 |
+
"grad_norm": 0.18554680049419403,
|
| 83994 |
+
"learning_rate": 1.2274726581291057e-05,
|
| 83995 |
+
"loss": 0.6245,
|
| 83996 |
+
"step": 11998
|
| 83997 |
+
},
|
| 83998 |
+
{
|
| 83999 |
+
"epoch": 13.666666666666666,
|
| 84000 |
+
"grad_norm": 0.20974911749362946,
|
| 84001 |
+
"learning_rate": 1.2270716365315101e-05,
|
| 84002 |
+
"loss": 0.7523,
|
| 84003 |
+
"step": 11999
|
| 84004 |
+
},
|
| 84005 |
+
{
|
| 84006 |
+
"epoch": 13.667806267806268,
|
| 84007 |
+
"grad_norm": 0.1708163470029831,
|
| 84008 |
+
"learning_rate": 1.226670659146217e-05,
|
| 84009 |
+
"loss": 0.5978,
|
| 84010 |
+
"step": 12000
|
| 84011 |
}
|
| 84012 |
],
|
| 84013 |
"logging_steps": 1,
|
|
|
|
| 84027 |
"attributes": {}
|
| 84028 |
}
|
| 84029 |
},
|
| 84030 |
+
"total_flos": 6.709617939952484e+19,
|
| 84031 |
"train_batch_size": 8,
|
| 84032 |
"trial_name": null,
|
| 84033 |
"trial_params": null
|