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 8700, 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 sha256:99f1ae055ebcebac89fea13e2cc741312a161fab96b2503cc1bc04fb5f546202
|
| 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 sha256:118f315680e6a862ba820d904ca76ffc4e962956a159918150b39774d1b92dc8
|
| 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 sha256:0c1d25019f50d0cc97f65bd84f5da86e7c504c172c5bf81dc52ce83fbd1fd7ae
|
| 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": 9.
|
| 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,
|
|
@@ -58808,6 +58808,2106 @@
|
|
| 58808 |
"learning_rate": 2.840225969732049e-05,
|
| 58809 |
"loss": 0.7079,
|
| 58810 |
"step": 8400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58811 |
}
|
| 58812 |
],
|
| 58813 |
"logging_steps": 1,
|
|
@@ -58827,7 +60927,7 @@
|
|
| 58827 |
"attributes": {}
|
| 58828 |
}
|
| 58829 |
},
|
| 58830 |
-
"total_flos": 4.
|
| 58831 |
"train_batch_size": 8,
|
| 58832 |
"trial_name": null,
|
| 58833 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.90940170940171,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 58808 |
"learning_rate": 2.840225969732049e-05,
|
| 58809 |
"loss": 0.7079,
|
| 58810 |
"step": 8400
|
| 58811 |
+
},
|
| 58812 |
+
{
|
| 58813 |
+
"epoch": 9.568660968660968,
|
| 58814 |
+
"grad_norm": 0.1844741702079773,
|
| 58815 |
+
"learning_rate": 2.8397643804171957e-05,
|
| 58816 |
+
"loss": 0.8422,
|
| 58817 |
+
"step": 8401
|
| 58818 |
+
},
|
| 58819 |
+
{
|
| 58820 |
+
"epoch": 9.56980056980057,
|
| 58821 |
+
"grad_norm": 0.24361716210842133,
|
| 58822 |
+
"learning_rate": 2.839302779301392e-05,
|
| 58823 |
+
"loss": 0.5547,
|
| 58824 |
+
"step": 8402
|
| 58825 |
+
},
|
| 58826 |
+
{
|
| 58827 |
+
"epoch": 9.57094017094017,
|
| 58828 |
+
"grad_norm": 0.18238916993141174,
|
| 58829 |
+
"learning_rate": 2.8388411664006702e-05,
|
| 58830 |
+
"loss": 0.842,
|
| 58831 |
+
"step": 8403
|
| 58832 |
+
},
|
| 58833 |
+
{
|
| 58834 |
+
"epoch": 9.572079772079771,
|
| 58835 |
+
"grad_norm": 0.2600004971027374,
|
| 58836 |
+
"learning_rate": 2.8383795417310623e-05,
|
| 58837 |
+
"loss": 0.5572,
|
| 58838 |
+
"step": 8404
|
| 58839 |
+
},
|
| 58840 |
+
{
|
| 58841 |
+
"epoch": 9.573219373219374,
|
| 58842 |
+
"grad_norm": 0.2804044485092163,
|
| 58843 |
+
"learning_rate": 2.8379179053086032e-05,
|
| 58844 |
+
"loss": 0.4059,
|
| 58845 |
+
"step": 8405
|
| 58846 |
+
},
|
| 58847 |
+
{
|
| 58848 |
+
"epoch": 9.574358974358974,
|
| 58849 |
+
"grad_norm": 0.1579924374818802,
|
| 58850 |
+
"learning_rate": 2.8374562571493245e-05,
|
| 58851 |
+
"loss": 0.7915,
|
| 58852 |
+
"step": 8406
|
| 58853 |
+
},
|
| 58854 |
+
{
|
| 58855 |
+
"epoch": 9.575498575498575,
|
| 58856 |
+
"grad_norm": 0.22872616350650787,
|
| 58857 |
+
"learning_rate": 2.836994597269263e-05,
|
| 58858 |
+
"loss": 0.729,
|
| 58859 |
+
"step": 8407
|
| 58860 |
+
},
|
| 58861 |
+
{
|
| 58862 |
+
"epoch": 9.576638176638177,
|
| 58863 |
+
"grad_norm": 0.2375708818435669,
|
| 58864 |
+
"learning_rate": 2.836532925684452e-05,
|
| 58865 |
+
"loss": 0.7186,
|
| 58866 |
+
"step": 8408
|
| 58867 |
+
},
|
| 58868 |
+
{
|
| 58869 |
+
"epoch": 9.577777777777778,
|
| 58870 |
+
"grad_norm": 0.23086920380592346,
|
| 58871 |
+
"learning_rate": 2.8360712424109272e-05,
|
| 58872 |
+
"loss": 0.6302,
|
| 58873 |
+
"step": 8409
|
| 58874 |
+
},
|
| 58875 |
+
{
|
| 58876 |
+
"epoch": 9.578917378917378,
|
| 58877 |
+
"grad_norm": 0.17449885606765747,
|
| 58878 |
+
"learning_rate": 2.835609547464724e-05,
|
| 58879 |
+
"loss": 0.7291,
|
| 58880 |
+
"step": 8410
|
| 58881 |
+
},
|
| 58882 |
+
{
|
| 58883 |
+
"epoch": 9.58005698005698,
|
| 58884 |
+
"grad_norm": 0.2576386034488678,
|
| 58885 |
+
"learning_rate": 2.835147840861878e-05,
|
| 58886 |
+
"loss": 0.5856,
|
| 58887 |
+
"step": 8411
|
| 58888 |
+
},
|
| 58889 |
+
{
|
| 58890 |
+
"epoch": 9.581196581196581,
|
| 58891 |
+
"grad_norm": 0.1862577348947525,
|
| 58892 |
+
"learning_rate": 2.8346861226184256e-05,
|
| 58893 |
+
"loss": 0.7679,
|
| 58894 |
+
"step": 8412
|
| 58895 |
+
},
|
| 58896 |
+
{
|
| 58897 |
+
"epoch": 9.582336182336181,
|
| 58898 |
+
"grad_norm": 0.2355736792087555,
|
| 58899 |
+
"learning_rate": 2.8342243927504047e-05,
|
| 58900 |
+
"loss": 0.6464,
|
| 58901 |
+
"step": 8413
|
| 58902 |
+
},
|
| 58903 |
+
{
|
| 58904 |
+
"epoch": 9.583475783475784,
|
| 58905 |
+
"grad_norm": 0.1800006777048111,
|
| 58906 |
+
"learning_rate": 2.833762651273851e-05,
|
| 58907 |
+
"loss": 0.6567,
|
| 58908 |
+
"step": 8414
|
| 58909 |
+
},
|
| 58910 |
+
{
|
| 58911 |
+
"epoch": 9.584615384615384,
|
| 58912 |
+
"grad_norm": 0.18470345437526703,
|
| 58913 |
+
"learning_rate": 2.8333008982048027e-05,
|
| 58914 |
+
"loss": 0.8081,
|
| 58915 |
+
"step": 8415
|
| 58916 |
+
},
|
| 58917 |
+
{
|
| 58918 |
+
"epoch": 9.585754985754985,
|
| 58919 |
+
"grad_norm": 0.20250608026981354,
|
| 58920 |
+
"learning_rate": 2.8328391335592973e-05,
|
| 58921 |
+
"loss": 0.7836,
|
| 58922 |
+
"step": 8416
|
| 58923 |
+
},
|
| 58924 |
+
{
|
| 58925 |
+
"epoch": 9.586894586894587,
|
| 58926 |
+
"grad_norm": 0.23904845118522644,
|
| 58927 |
+
"learning_rate": 2.832377357353374e-05,
|
| 58928 |
+
"loss": 0.6268,
|
| 58929 |
+
"step": 8417
|
| 58930 |
+
},
|
| 58931 |
+
{
|
| 58932 |
+
"epoch": 9.588034188034188,
|
| 58933 |
+
"grad_norm": 0.20193591713905334,
|
| 58934 |
+
"learning_rate": 2.831915569603071e-05,
|
| 58935 |
+
"loss": 0.7641,
|
| 58936 |
+
"step": 8418
|
| 58937 |
+
},
|
| 58938 |
+
{
|
| 58939 |
+
"epoch": 9.589173789173788,
|
| 58940 |
+
"grad_norm": 0.18129391968250275,
|
| 58941 |
+
"learning_rate": 2.8314537703244265e-05,
|
| 58942 |
+
"loss": 0.7474,
|
| 58943 |
+
"step": 8419
|
| 58944 |
+
},
|
| 58945 |
+
{
|
| 58946 |
+
"epoch": 9.59031339031339,
|
| 58947 |
+
"grad_norm": 0.2015620619058609,
|
| 58948 |
+
"learning_rate": 2.830991959533482e-05,
|
| 58949 |
+
"loss": 0.6556,
|
| 58950 |
+
"step": 8420
|
| 58951 |
+
},
|
| 58952 |
+
{
|
| 58953 |
+
"epoch": 9.591452991452991,
|
| 58954 |
+
"grad_norm": 0.19163182377815247,
|
| 58955 |
+
"learning_rate": 2.830530137246276e-05,
|
| 58956 |
+
"loss": 0.8212,
|
| 58957 |
+
"step": 8421
|
| 58958 |
+
},
|
| 58959 |
+
{
|
| 58960 |
+
"epoch": 9.592592592592592,
|
| 58961 |
+
"grad_norm": 0.2748200297355652,
|
| 58962 |
+
"learning_rate": 2.83006830347885e-05,
|
| 58963 |
+
"loss": 0.5025,
|
| 58964 |
+
"step": 8422
|
| 58965 |
+
},
|
| 58966 |
+
{
|
| 58967 |
+
"epoch": 9.593732193732194,
|
| 58968 |
+
"grad_norm": 0.2064012885093689,
|
| 58969 |
+
"learning_rate": 2.829606458247243e-05,
|
| 58970 |
+
"loss": 0.8288,
|
| 58971 |
+
"step": 8423
|
| 58972 |
+
},
|
| 58973 |
+
{
|
| 58974 |
+
"epoch": 9.594871794871795,
|
| 58975 |
+
"grad_norm": 0.18211974203586578,
|
| 58976 |
+
"learning_rate": 2.829144601567499e-05,
|
| 58977 |
+
"loss": 0.8086,
|
| 58978 |
+
"step": 8424
|
| 58979 |
+
},
|
| 58980 |
+
{
|
| 58981 |
+
"epoch": 9.596011396011395,
|
| 58982 |
+
"grad_norm": 0.20421072840690613,
|
| 58983 |
+
"learning_rate": 2.8286827334556566e-05,
|
| 58984 |
+
"loss": 0.7935,
|
| 58985 |
+
"step": 8425
|
| 58986 |
+
},
|
| 58987 |
+
{
|
| 58988 |
+
"epoch": 9.597150997150997,
|
| 58989 |
+
"grad_norm": 0.15879186987876892,
|
| 58990 |
+
"learning_rate": 2.8282208539277594e-05,
|
| 58991 |
+
"loss": 0.8622,
|
| 58992 |
+
"step": 8426
|
| 58993 |
+
},
|
| 58994 |
+
{
|
| 58995 |
+
"epoch": 9.598290598290598,
|
| 58996 |
+
"grad_norm": 0.23644597828388214,
|
| 58997 |
+
"learning_rate": 2.827758962999849e-05,
|
| 58998 |
+
"loss": 0.6415,
|
| 58999 |
+
"step": 8427
|
| 59000 |
+
},
|
| 59001 |
+
{
|
| 59002 |
+
"epoch": 9.5994301994302,
|
| 59003 |
+
"grad_norm": 0.19257822632789612,
|
| 59004 |
+
"learning_rate": 2.827297060687969e-05,
|
| 59005 |
+
"loss": 0.7557,
|
| 59006 |
+
"step": 8428
|
| 59007 |
+
},
|
| 59008 |
+
{
|
| 59009 |
+
"epoch": 9.6005698005698,
|
| 59010 |
+
"grad_norm": 0.24540145695209503,
|
| 59011 |
+
"learning_rate": 2.826835147008161e-05,
|
| 59012 |
+
"loss": 0.6768,
|
| 59013 |
+
"step": 8429
|
| 59014 |
+
},
|
| 59015 |
+
{
|
| 59016 |
+
"epoch": 9.601709401709401,
|
| 59017 |
+
"grad_norm": 0.21854540705680847,
|
| 59018 |
+
"learning_rate": 2.8263732219764703e-05,
|
| 59019 |
+
"loss": 0.8531,
|
| 59020 |
+
"step": 8430
|
| 59021 |
+
},
|
| 59022 |
+
{
|
| 59023 |
+
"epoch": 9.602849002849004,
|
| 59024 |
+
"grad_norm": 0.196981742978096,
|
| 59025 |
+
"learning_rate": 2.8259112856089405e-05,
|
| 59026 |
+
"loss": 0.6341,
|
| 59027 |
+
"step": 8431
|
| 59028 |
+
},
|
| 59029 |
+
{
|
| 59030 |
+
"epoch": 9.603988603988604,
|
| 59031 |
+
"grad_norm": 0.21874146163463593,
|
| 59032 |
+
"learning_rate": 2.8254493379216152e-05,
|
| 59033 |
+
"loss": 0.7642,
|
| 59034 |
+
"step": 8432
|
| 59035 |
+
},
|
| 59036 |
+
{
|
| 59037 |
+
"epoch": 9.605128205128205,
|
| 59038 |
+
"grad_norm": 0.15934787690639496,
|
| 59039 |
+
"learning_rate": 2.8249873789305394e-05,
|
| 59040 |
+
"loss": 0.6682,
|
| 59041 |
+
"step": 8433
|
| 59042 |
+
},
|
| 59043 |
+
{
|
| 59044 |
+
"epoch": 9.606267806267807,
|
| 59045 |
+
"grad_norm": 0.2906241714954376,
|
| 59046 |
+
"learning_rate": 2.8245254086517575e-05,
|
| 59047 |
+
"loss": 0.5481,
|
| 59048 |
+
"step": 8434
|
| 59049 |
+
},
|
| 59050 |
+
{
|
| 59051 |
+
"epoch": 9.607407407407408,
|
| 59052 |
+
"grad_norm": 0.21550823748111725,
|
| 59053 |
+
"learning_rate": 2.8240634271013167e-05,
|
| 59054 |
+
"loss": 0.6166,
|
| 59055 |
+
"step": 8435
|
| 59056 |
+
},
|
| 59057 |
+
{
|
| 59058 |
+
"epoch": 9.608547008547008,
|
| 59059 |
+
"grad_norm": 0.21351531147956848,
|
| 59060 |
+
"learning_rate": 2.823601434295261e-05,
|
| 59061 |
+
"loss": 0.6378,
|
| 59062 |
+
"step": 8436
|
| 59063 |
+
},
|
| 59064 |
+
{
|
| 59065 |
+
"epoch": 9.60968660968661,
|
| 59066 |
+
"grad_norm": 0.20039942860603333,
|
| 59067 |
+
"learning_rate": 2.8231394302496383e-05,
|
| 59068 |
+
"loss": 0.8,
|
| 59069 |
+
"step": 8437
|
| 59070 |
+
},
|
| 59071 |
+
{
|
| 59072 |
+
"epoch": 9.610826210826211,
|
| 59073 |
+
"grad_norm": 0.17776717245578766,
|
| 59074 |
+
"learning_rate": 2.822677414980494e-05,
|
| 59075 |
+
"loss": 0.933,
|
| 59076 |
+
"step": 8438
|
| 59077 |
+
},
|
| 59078 |
+
{
|
| 59079 |
+
"epoch": 9.611965811965812,
|
| 59080 |
+
"grad_norm": 0.25148046016693115,
|
| 59081 |
+
"learning_rate": 2.8222153885038767e-05,
|
| 59082 |
+
"loss": 0.4991,
|
| 59083 |
+
"step": 8439
|
| 59084 |
+
},
|
| 59085 |
+
{
|
| 59086 |
+
"epoch": 9.613105413105414,
|
| 59087 |
+
"grad_norm": 0.20714183151721954,
|
| 59088 |
+
"learning_rate": 2.821753350835831e-05,
|
| 59089 |
+
"loss": 0.7522,
|
| 59090 |
+
"step": 8440
|
| 59091 |
+
},
|
| 59092 |
+
{
|
| 59093 |
+
"epoch": 9.614245014245014,
|
| 59094 |
+
"grad_norm": 0.18635442852973938,
|
| 59095 |
+
"learning_rate": 2.8212913019924086e-05,
|
| 59096 |
+
"loss": 0.7363,
|
| 59097 |
+
"step": 8441
|
| 59098 |
+
},
|
| 59099 |
+
{
|
| 59100 |
+
"epoch": 9.615384615384615,
|
| 59101 |
+
"grad_norm": 0.2570042610168457,
|
| 59102 |
+
"learning_rate": 2.8208292419896543e-05,
|
| 59103 |
+
"loss": 0.4784,
|
| 59104 |
+
"step": 8442
|
| 59105 |
+
},
|
| 59106 |
+
{
|
| 59107 |
+
"epoch": 9.616524216524217,
|
| 59108 |
+
"grad_norm": 0.2306656539440155,
|
| 59109 |
+
"learning_rate": 2.820367170843619e-05,
|
| 59110 |
+
"loss": 0.6339,
|
| 59111 |
+
"step": 8443
|
| 59112 |
+
},
|
| 59113 |
+
{
|
| 59114 |
+
"epoch": 9.617663817663818,
|
| 59115 |
+
"grad_norm": 0.22380559146404266,
|
| 59116 |
+
"learning_rate": 2.8199050885703504e-05,
|
| 59117 |
+
"loss": 0.5676,
|
| 59118 |
+
"step": 8444
|
| 59119 |
+
},
|
| 59120 |
+
{
|
| 59121 |
+
"epoch": 9.618803418803418,
|
| 59122 |
+
"grad_norm": 0.2236308753490448,
|
| 59123 |
+
"learning_rate": 2.8194429951858985e-05,
|
| 59124 |
+
"loss": 0.7608,
|
| 59125 |
+
"step": 8445
|
| 59126 |
+
},
|
| 59127 |
+
{
|
| 59128 |
+
"epoch": 9.61994301994302,
|
| 59129 |
+
"grad_norm": 0.21724647283554077,
|
| 59130 |
+
"learning_rate": 2.8189808907063132e-05,
|
| 59131 |
+
"loss": 0.6835,
|
| 59132 |
+
"step": 8446
|
| 59133 |
+
},
|
| 59134 |
+
{
|
| 59135 |
+
"epoch": 9.621082621082621,
|
| 59136 |
+
"grad_norm": 0.21728353202342987,
|
| 59137 |
+
"learning_rate": 2.818518775147644e-05,
|
| 59138 |
+
"loss": 0.7744,
|
| 59139 |
+
"step": 8447
|
| 59140 |
+
},
|
| 59141 |
+
{
|
| 59142 |
+
"epoch": 9.622222222222222,
|
| 59143 |
+
"grad_norm": 0.2925417125225067,
|
| 59144 |
+
"learning_rate": 2.8180566485259425e-05,
|
| 59145 |
+
"loss": 0.6382,
|
| 59146 |
+
"step": 8448
|
| 59147 |
+
},
|
| 59148 |
+
{
|
| 59149 |
+
"epoch": 9.623361823361824,
|
| 59150 |
+
"grad_norm": 0.157082661986351,
|
| 59151 |
+
"learning_rate": 2.8175945108572577e-05,
|
| 59152 |
+
"loss": 0.8076,
|
| 59153 |
+
"step": 8449
|
| 59154 |
+
},
|
| 59155 |
+
{
|
| 59156 |
+
"epoch": 9.624501424501425,
|
| 59157 |
+
"grad_norm": 0.2292805165052414,
|
| 59158 |
+
"learning_rate": 2.8171323621576428e-05,
|
| 59159 |
+
"loss": 0.6967,
|
| 59160 |
+
"step": 8450
|
| 59161 |
+
},
|
| 59162 |
+
{
|
| 59163 |
+
"epoch": 9.625641025641025,
|
| 59164 |
+
"grad_norm": 0.2331184446811676,
|
| 59165 |
+
"learning_rate": 2.8166702024431484e-05,
|
| 59166 |
+
"loss": 0.6488,
|
| 59167 |
+
"step": 8451
|
| 59168 |
+
},
|
| 59169 |
+
{
|
| 59170 |
+
"epoch": 9.626780626780628,
|
| 59171 |
+
"grad_norm": 0.20063607394695282,
|
| 59172 |
+
"learning_rate": 2.816208031729828e-05,
|
| 59173 |
+
"loss": 0.5961,
|
| 59174 |
+
"step": 8452
|
| 59175 |
+
},
|
| 59176 |
+
{
|
| 59177 |
+
"epoch": 9.627920227920228,
|
| 59178 |
+
"grad_norm": 0.2293260097503662,
|
| 59179 |
+
"learning_rate": 2.8157458500337318e-05,
|
| 59180 |
+
"loss": 0.6886,
|
| 59181 |
+
"step": 8453
|
| 59182 |
+
},
|
| 59183 |
+
{
|
| 59184 |
+
"epoch": 9.629059829059829,
|
| 59185 |
+
"grad_norm": 0.22276504337787628,
|
| 59186 |
+
"learning_rate": 2.8152836573709152e-05,
|
| 59187 |
+
"loss": 0.6444,
|
| 59188 |
+
"step": 8454
|
| 59189 |
+
},
|
| 59190 |
+
{
|
| 59191 |
+
"epoch": 9.630199430199431,
|
| 59192 |
+
"grad_norm": 0.25844740867614746,
|
| 59193 |
+
"learning_rate": 2.8148214537574296e-05,
|
| 59194 |
+
"loss": 0.6206,
|
| 59195 |
+
"step": 8455
|
| 59196 |
+
},
|
| 59197 |
+
{
|
| 59198 |
+
"epoch": 9.631339031339031,
|
| 59199 |
+
"grad_norm": 0.2520429790019989,
|
| 59200 |
+
"learning_rate": 2.8143592392093287e-05,
|
| 59201 |
+
"loss": 0.4121,
|
| 59202 |
+
"step": 8456
|
| 59203 |
+
},
|
| 59204 |
+
{
|
| 59205 |
+
"epoch": 9.632478632478632,
|
| 59206 |
+
"grad_norm": 0.2038751244544983,
|
| 59207 |
+
"learning_rate": 2.8138970137426675e-05,
|
| 59208 |
+
"loss": 0.7226,
|
| 59209 |
+
"step": 8457
|
| 59210 |
+
},
|
| 59211 |
+
{
|
| 59212 |
+
"epoch": 9.633618233618234,
|
| 59213 |
+
"grad_norm": 0.2728098928928375,
|
| 59214 |
+
"learning_rate": 2.8134347773734996e-05,
|
| 59215 |
+
"loss": 0.5881,
|
| 59216 |
+
"step": 8458
|
| 59217 |
+
},
|
| 59218 |
+
{
|
| 59219 |
+
"epoch": 9.634757834757835,
|
| 59220 |
+
"grad_norm": 0.1946948915719986,
|
| 59221 |
+
"learning_rate": 2.81297253011788e-05,
|
| 59222 |
+
"loss": 0.9104,
|
| 59223 |
+
"step": 8459
|
| 59224 |
+
},
|
| 59225 |
+
{
|
| 59226 |
+
"epoch": 9.635897435897435,
|
| 59227 |
+
"grad_norm": 0.18152308464050293,
|
| 59228 |
+
"learning_rate": 2.812510271991864e-05,
|
| 59229 |
+
"loss": 0.655,
|
| 59230 |
+
"step": 8460
|
| 59231 |
+
},
|
| 59232 |
+
{
|
| 59233 |
+
"epoch": 9.637037037037038,
|
| 59234 |
+
"grad_norm": 0.17640575766563416,
|
| 59235 |
+
"learning_rate": 2.8120480030115065e-05,
|
| 59236 |
+
"loss": 0.7666,
|
| 59237 |
+
"step": 8461
|
| 59238 |
+
},
|
| 59239 |
+
{
|
| 59240 |
+
"epoch": 9.638176638176638,
|
| 59241 |
+
"grad_norm": 0.2305549532175064,
|
| 59242 |
+
"learning_rate": 2.8115857231928638e-05,
|
| 59243 |
+
"loss": 0.6757,
|
| 59244 |
+
"step": 8462
|
| 59245 |
+
},
|
| 59246 |
+
{
|
| 59247 |
+
"epoch": 9.639316239316239,
|
| 59248 |
+
"grad_norm": 0.28918159008026123,
|
| 59249 |
+
"learning_rate": 2.8111234325519924e-05,
|
| 59250 |
+
"loss": 0.4352,
|
| 59251 |
+
"step": 8463
|
| 59252 |
+
},
|
| 59253 |
+
{
|
| 59254 |
+
"epoch": 9.640455840455841,
|
| 59255 |
+
"grad_norm": 0.19419384002685547,
|
| 59256 |
+
"learning_rate": 2.810661131104948e-05,
|
| 59257 |
+
"loss": 0.7367,
|
| 59258 |
+
"step": 8464
|
| 59259 |
+
},
|
| 59260 |
+
{
|
| 59261 |
+
"epoch": 9.641595441595442,
|
| 59262 |
+
"grad_norm": 0.18359477818012238,
|
| 59263 |
+
"learning_rate": 2.8101988188677887e-05,
|
| 59264 |
+
"loss": 0.7335,
|
| 59265 |
+
"step": 8465
|
| 59266 |
+
},
|
| 59267 |
+
{
|
| 59268 |
+
"epoch": 9.642735042735042,
|
| 59269 |
+
"grad_norm": 0.27075687050819397,
|
| 59270 |
+
"learning_rate": 2.8097364958565707e-05,
|
| 59271 |
+
"loss": 0.4621,
|
| 59272 |
+
"step": 8466
|
| 59273 |
+
},
|
| 59274 |
+
{
|
| 59275 |
+
"epoch": 9.643874643874645,
|
| 59276 |
+
"grad_norm": 0.15775761008262634,
|
| 59277 |
+
"learning_rate": 2.809274162087353e-05,
|
| 59278 |
+
"loss": 0.8219,
|
| 59279 |
+
"step": 8467
|
| 59280 |
+
},
|
| 59281 |
+
{
|
| 59282 |
+
"epoch": 9.645014245014245,
|
| 59283 |
+
"grad_norm": 0.267281174659729,
|
| 59284 |
+
"learning_rate": 2.808811817576193e-05,
|
| 59285 |
+
"loss": 0.55,
|
| 59286 |
+
"step": 8468
|
| 59287 |
+
},
|
| 59288 |
+
{
|
| 59289 |
+
"epoch": 9.646153846153846,
|
| 59290 |
+
"grad_norm": 0.2001519352197647,
|
| 59291 |
+
"learning_rate": 2.8083494623391492e-05,
|
| 59292 |
+
"loss": 0.7807,
|
| 59293 |
+
"step": 8469
|
| 59294 |
+
},
|
| 59295 |
+
{
|
| 59296 |
+
"epoch": 9.647293447293448,
|
| 59297 |
+
"grad_norm": 0.215030699968338,
|
| 59298 |
+
"learning_rate": 2.807887096392281e-05,
|
| 59299 |
+
"loss": 0.7114,
|
| 59300 |
+
"step": 8470
|
| 59301 |
+
},
|
| 59302 |
+
{
|
| 59303 |
+
"epoch": 9.648433048433048,
|
| 59304 |
+
"grad_norm": 0.26007959246635437,
|
| 59305 |
+
"learning_rate": 2.8074247197516474e-05,
|
| 59306 |
+
"loss": 0.5199,
|
| 59307 |
+
"step": 8471
|
| 59308 |
+
},
|
| 59309 |
+
{
|
| 59310 |
+
"epoch": 9.649572649572649,
|
| 59311 |
+
"grad_norm": 0.2286146730184555,
|
| 59312 |
+
"learning_rate": 2.8069623324333072e-05,
|
| 59313 |
+
"loss": 0.6747,
|
| 59314 |
+
"step": 8472
|
| 59315 |
+
},
|
| 59316 |
+
{
|
| 59317 |
+
"epoch": 9.650712250712251,
|
| 59318 |
+
"grad_norm": 0.24231044948101044,
|
| 59319 |
+
"learning_rate": 2.806499934453321e-05,
|
| 59320 |
+
"loss": 0.6583,
|
| 59321 |
+
"step": 8473
|
| 59322 |
+
},
|
| 59323 |
+
{
|
| 59324 |
+
"epoch": 9.651851851851852,
|
| 59325 |
+
"grad_norm": 0.22648459672927856,
|
| 59326 |
+
"learning_rate": 2.8060375258277494e-05,
|
| 59327 |
+
"loss": 0.5948,
|
| 59328 |
+
"step": 8474
|
| 59329 |
+
},
|
| 59330 |
+
{
|
| 59331 |
+
"epoch": 9.652991452991452,
|
| 59332 |
+
"grad_norm": 0.21289721131324768,
|
| 59333 |
+
"learning_rate": 2.805575106572653e-05,
|
| 59334 |
+
"loss": 0.7268,
|
| 59335 |
+
"step": 8475
|
| 59336 |
+
},
|
| 59337 |
+
{
|
| 59338 |
+
"epoch": 9.654131054131055,
|
| 59339 |
+
"grad_norm": 0.2718423902988434,
|
| 59340 |
+
"learning_rate": 2.8051126767040932e-05,
|
| 59341 |
+
"loss": 0.6427,
|
| 59342 |
+
"step": 8476
|
| 59343 |
+
},
|
| 59344 |
+
{
|
| 59345 |
+
"epoch": 9.655270655270655,
|
| 59346 |
+
"grad_norm": 0.19400310516357422,
|
| 59347 |
+
"learning_rate": 2.8046502362381304e-05,
|
| 59348 |
+
"loss": 0.8316,
|
| 59349 |
+
"step": 8477
|
| 59350 |
+
},
|
| 59351 |
+
{
|
| 59352 |
+
"epoch": 9.656410256410256,
|
| 59353 |
+
"grad_norm": 0.1917850524187088,
|
| 59354 |
+
"learning_rate": 2.8041877851908276e-05,
|
| 59355 |
+
"loss": 0.7485,
|
| 59356 |
+
"step": 8478
|
| 59357 |
+
},
|
| 59358 |
+
{
|
| 59359 |
+
"epoch": 9.657549857549858,
|
| 59360 |
+
"grad_norm": 0.14941884577274323,
|
| 59361 |
+
"learning_rate": 2.803725323578246e-05,
|
| 59362 |
+
"loss": 0.9673,
|
| 59363 |
+
"step": 8479
|
| 59364 |
+
},
|
| 59365 |
+
{
|
| 59366 |
+
"epoch": 9.658689458689459,
|
| 59367 |
+
"grad_norm": 0.19698305428028107,
|
| 59368 |
+
"learning_rate": 2.8032628514164493e-05,
|
| 59369 |
+
"loss": 0.6372,
|
| 59370 |
+
"step": 8480
|
| 59371 |
+
},
|
| 59372 |
+
{
|
| 59373 |
+
"epoch": 9.65982905982906,
|
| 59374 |
+
"grad_norm": 0.23960430920124054,
|
| 59375 |
+
"learning_rate": 2.8028003687214993e-05,
|
| 59376 |
+
"loss": 0.7234,
|
| 59377 |
+
"step": 8481
|
| 59378 |
+
},
|
| 59379 |
+
{
|
| 59380 |
+
"epoch": 9.660968660968662,
|
| 59381 |
+
"grad_norm": 0.22642646729946136,
|
| 59382 |
+
"learning_rate": 2.8023378755094605e-05,
|
| 59383 |
+
"loss": 0.6822,
|
| 59384 |
+
"step": 8482
|
| 59385 |
+
},
|
| 59386 |
+
{
|
| 59387 |
+
"epoch": 9.662108262108262,
|
| 59388 |
+
"grad_norm": 0.16527873277664185,
|
| 59389 |
+
"learning_rate": 2.8018753717963952e-05,
|
| 59390 |
+
"loss": 0.826,
|
| 59391 |
+
"step": 8483
|
| 59392 |
+
},
|
| 59393 |
+
{
|
| 59394 |
+
"epoch": 9.663247863247863,
|
| 59395 |
+
"grad_norm": 0.1699703484773636,
|
| 59396 |
+
"learning_rate": 2.8014128575983678e-05,
|
| 59397 |
+
"loss": 0.9285,
|
| 59398 |
+
"step": 8484
|
| 59399 |
+
},
|
| 59400 |
+
{
|
| 59401 |
+
"epoch": 9.664387464387465,
|
| 59402 |
+
"grad_norm": 0.2637763023376465,
|
| 59403 |
+
"learning_rate": 2.8009503329314428e-05,
|
| 59404 |
+
"loss": 0.617,
|
| 59405 |
+
"step": 8485
|
| 59406 |
+
},
|
| 59407 |
+
{
|
| 59408 |
+
"epoch": 9.665527065527066,
|
| 59409 |
+
"grad_norm": 0.2114337682723999,
|
| 59410 |
+
"learning_rate": 2.800487797811686e-05,
|
| 59411 |
+
"loss": 0.7386,
|
| 59412 |
+
"step": 8486
|
| 59413 |
+
},
|
| 59414 |
+
{
|
| 59415 |
+
"epoch": 9.666666666666666,
|
| 59416 |
+
"grad_norm": 0.20547452569007874,
|
| 59417 |
+
"learning_rate": 2.800025252255162e-05,
|
| 59418 |
+
"loss": 0.7259,
|
| 59419 |
+
"step": 8487
|
| 59420 |
+
},
|
| 59421 |
+
{
|
| 59422 |
+
"epoch": 9.667806267806268,
|
| 59423 |
+
"grad_norm": 0.1680016666650772,
|
| 59424 |
+
"learning_rate": 2.7995626962779354e-05,
|
| 59425 |
+
"loss": 0.9245,
|
| 59426 |
+
"step": 8488
|
| 59427 |
+
},
|
| 59428 |
+
{
|
| 59429 |
+
"epoch": 9.668945868945869,
|
| 59430 |
+
"grad_norm": 0.2023734748363495,
|
| 59431 |
+
"learning_rate": 2.799100129896072e-05,
|
| 59432 |
+
"loss": 0.8274,
|
| 59433 |
+
"step": 8489
|
| 59434 |
+
},
|
| 59435 |
+
{
|
| 59436 |
+
"epoch": 9.67008547008547,
|
| 59437 |
+
"grad_norm": 0.2510012984275818,
|
| 59438 |
+
"learning_rate": 2.7986375531256386e-05,
|
| 59439 |
+
"loss": 0.8166,
|
| 59440 |
+
"step": 8490
|
| 59441 |
+
},
|
| 59442 |
+
{
|
| 59443 |
+
"epoch": 9.671225071225072,
|
| 59444 |
+
"grad_norm": 0.21623970568180084,
|
| 59445 |
+
"learning_rate": 2.798174965982702e-05,
|
| 59446 |
+
"loss": 0.8594,
|
| 59447 |
+
"step": 8491
|
| 59448 |
+
},
|
| 59449 |
+
{
|
| 59450 |
+
"epoch": 9.672364672364672,
|
| 59451 |
+
"grad_norm": 0.21272176504135132,
|
| 59452 |
+
"learning_rate": 2.797712368483329e-05,
|
| 59453 |
+
"loss": 0.7567,
|
| 59454 |
+
"step": 8492
|
| 59455 |
+
},
|
| 59456 |
+
{
|
| 59457 |
+
"epoch": 9.673504273504273,
|
| 59458 |
+
"grad_norm": 0.18072400987148285,
|
| 59459 |
+
"learning_rate": 2.7972497606435866e-05,
|
| 59460 |
+
"loss": 0.8329,
|
| 59461 |
+
"step": 8493
|
| 59462 |
+
},
|
| 59463 |
+
{
|
| 59464 |
+
"epoch": 9.674643874643875,
|
| 59465 |
+
"grad_norm": 0.21961405873298645,
|
| 59466 |
+
"learning_rate": 2.7967871424795433e-05,
|
| 59467 |
+
"loss": 0.6713,
|
| 59468 |
+
"step": 8494
|
| 59469 |
+
},
|
| 59470 |
+
{
|
| 59471 |
+
"epoch": 9.675783475783476,
|
| 59472 |
+
"grad_norm": 0.20609161257743835,
|
| 59473 |
+
"learning_rate": 2.7963245140072653e-05,
|
| 59474 |
+
"loss": 0.779,
|
| 59475 |
+
"step": 8495
|
| 59476 |
+
},
|
| 59477 |
+
{
|
| 59478 |
+
"epoch": 9.676923076923076,
|
| 59479 |
+
"grad_norm": 0.25514522194862366,
|
| 59480 |
+
"learning_rate": 2.7958618752428223e-05,
|
| 59481 |
+
"loss": 0.432,
|
| 59482 |
+
"step": 8496
|
| 59483 |
+
},
|
| 59484 |
+
{
|
| 59485 |
+
"epoch": 9.678062678062679,
|
| 59486 |
+
"grad_norm": 0.17109011113643646,
|
| 59487 |
+
"learning_rate": 2.7953992262022834e-05,
|
| 59488 |
+
"loss": 0.8166,
|
| 59489 |
+
"step": 8497
|
| 59490 |
+
},
|
| 59491 |
+
{
|
| 59492 |
+
"epoch": 9.67920227920228,
|
| 59493 |
+
"grad_norm": 0.21235273778438568,
|
| 59494 |
+
"learning_rate": 2.7949365669017157e-05,
|
| 59495 |
+
"loss": 0.6714,
|
| 59496 |
+
"step": 8498
|
| 59497 |
+
},
|
| 59498 |
+
{
|
| 59499 |
+
"epoch": 9.68034188034188,
|
| 59500 |
+
"grad_norm": 0.23909524083137512,
|
| 59501 |
+
"learning_rate": 2.7944738973571915e-05,
|
| 59502 |
+
"loss": 0.5226,
|
| 59503 |
+
"step": 8499
|
| 59504 |
+
},
|
| 59505 |
+
{
|
| 59506 |
+
"epoch": 9.681481481481482,
|
| 59507 |
+
"grad_norm": 0.24783433973789215,
|
| 59508 |
+
"learning_rate": 2.7940112175847784e-05,
|
| 59509 |
+
"loss": 0.4658,
|
| 59510 |
+
"step": 8500
|
| 59511 |
+
},
|
| 59512 |
+
{
|
| 59513 |
+
"epoch": 9.682621082621083,
|
| 59514 |
+
"grad_norm": 0.22748740017414093,
|
| 59515 |
+
"learning_rate": 2.793548527600546e-05,
|
| 59516 |
+
"loss": 0.5848,
|
| 59517 |
+
"step": 8501
|
| 59518 |
+
},
|
| 59519 |
+
{
|
| 59520 |
+
"epoch": 9.683760683760683,
|
| 59521 |
+
"grad_norm": 0.19321490824222565,
|
| 59522 |
+
"learning_rate": 2.7930858274205672e-05,
|
| 59523 |
+
"loss": 0.778,
|
| 59524 |
+
"step": 8502
|
| 59525 |
+
},
|
| 59526 |
+
{
|
| 59527 |
+
"epoch": 9.684900284900285,
|
| 59528 |
+
"grad_norm": 0.22267040610313416,
|
| 59529 |
+
"learning_rate": 2.7926231170609117e-05,
|
| 59530 |
+
"loss": 0.5523,
|
| 59531 |
+
"step": 8503
|
| 59532 |
+
},
|
| 59533 |
+
{
|
| 59534 |
+
"epoch": 9.686039886039886,
|
| 59535 |
+
"grad_norm": 0.20147395133972168,
|
| 59536 |
+
"learning_rate": 2.7921603965376503e-05,
|
| 59537 |
+
"loss": 0.7143,
|
| 59538 |
+
"step": 8504
|
| 59539 |
+
},
|
| 59540 |
+
{
|
| 59541 |
+
"epoch": 9.687179487179487,
|
| 59542 |
+
"grad_norm": 0.2002495974302292,
|
| 59543 |
+
"learning_rate": 2.7916976658668552e-05,
|
| 59544 |
+
"loss": 0.5548,
|
| 59545 |
+
"step": 8505
|
| 59546 |
+
},
|
| 59547 |
+
{
|
| 59548 |
+
"epoch": 9.688319088319089,
|
| 59549 |
+
"grad_norm": 0.23312561213970184,
|
| 59550 |
+
"learning_rate": 2.7912349250645975e-05,
|
| 59551 |
+
"loss": 0.7927,
|
| 59552 |
+
"step": 8506
|
| 59553 |
+
},
|
| 59554 |
+
{
|
| 59555 |
+
"epoch": 9.68945868945869,
|
| 59556 |
+
"grad_norm": 0.16021563112735748,
|
| 59557 |
+
"learning_rate": 2.7907721741469506e-05,
|
| 59558 |
+
"loss": 0.6837,
|
| 59559 |
+
"step": 8507
|
| 59560 |
+
},
|
| 59561 |
+
{
|
| 59562 |
+
"epoch": 9.69059829059829,
|
| 59563 |
+
"grad_norm": 0.1961434930562973,
|
| 59564 |
+
"learning_rate": 2.7903094131299855e-05,
|
| 59565 |
+
"loss": 0.7884,
|
| 59566 |
+
"step": 8508
|
| 59567 |
+
},
|
| 59568 |
+
{
|
| 59569 |
+
"epoch": 9.691737891737892,
|
| 59570 |
+
"grad_norm": 0.19885706901550293,
|
| 59571 |
+
"learning_rate": 2.7898466420297777e-05,
|
| 59572 |
+
"loss": 0.7048,
|
| 59573 |
+
"step": 8509
|
| 59574 |
+
},
|
| 59575 |
+
{
|
| 59576 |
+
"epoch": 9.692877492877493,
|
| 59577 |
+
"grad_norm": 0.2357889711856842,
|
| 59578 |
+
"learning_rate": 2.7893838608623972e-05,
|
| 59579 |
+
"loss": 0.55,
|
| 59580 |
+
"step": 8510
|
| 59581 |
+
},
|
| 59582 |
+
{
|
| 59583 |
+
"epoch": 9.694017094017093,
|
| 59584 |
+
"grad_norm": 0.23352935910224915,
|
| 59585 |
+
"learning_rate": 2.7889210696439205e-05,
|
| 59586 |
+
"loss": 0.7906,
|
| 59587 |
+
"step": 8511
|
| 59588 |
+
},
|
| 59589 |
+
{
|
| 59590 |
+
"epoch": 9.695156695156696,
|
| 59591 |
+
"grad_norm": 0.18605369329452515,
|
| 59592 |
+
"learning_rate": 2.7884582683904205e-05,
|
| 59593 |
+
"loss": 0.9088,
|
| 59594 |
+
"step": 8512
|
| 59595 |
+
},
|
| 59596 |
+
{
|
| 59597 |
+
"epoch": 9.696296296296296,
|
| 59598 |
+
"grad_norm": 0.1729101985692978,
|
| 59599 |
+
"learning_rate": 2.7879954571179705e-05,
|
| 59600 |
+
"loss": 0.6314,
|
| 59601 |
+
"step": 8513
|
| 59602 |
+
},
|
| 59603 |
+
{
|
| 59604 |
+
"epoch": 9.697435897435897,
|
| 59605 |
+
"grad_norm": 0.2530671954154968,
|
| 59606 |
+
"learning_rate": 2.787532635842648e-05,
|
| 59607 |
+
"loss": 0.6066,
|
| 59608 |
+
"step": 8514
|
| 59609 |
+
},
|
| 59610 |
+
{
|
| 59611 |
+
"epoch": 9.698575498575499,
|
| 59612 |
+
"grad_norm": 0.23992305994033813,
|
| 59613 |
+
"learning_rate": 2.787069804580525e-05,
|
| 59614 |
+
"loss": 0.6046,
|
| 59615 |
+
"step": 8515
|
| 59616 |
+
},
|
| 59617 |
+
{
|
| 59618 |
+
"epoch": 9.6997150997151,
|
| 59619 |
+
"grad_norm": 0.1798892617225647,
|
| 59620 |
+
"learning_rate": 2.7866069633476787e-05,
|
| 59621 |
+
"loss": 0.7873,
|
| 59622 |
+
"step": 8516
|
| 59623 |
+
},
|
| 59624 |
+
{
|
| 59625 |
+
"epoch": 9.7008547008547,
|
| 59626 |
+
"grad_norm": 0.21981604397296906,
|
| 59627 |
+
"learning_rate": 2.7861441121601838e-05,
|
| 59628 |
+
"loss": 0.5761,
|
| 59629 |
+
"step": 8517
|
| 59630 |
+
},
|
| 59631 |
+
{
|
| 59632 |
+
"epoch": 9.701994301994302,
|
| 59633 |
+
"grad_norm": 0.1948310285806656,
|
| 59634 |
+
"learning_rate": 2.785681251034118e-05,
|
| 59635 |
+
"loss": 0.759,
|
| 59636 |
+
"step": 8518
|
| 59637 |
+
},
|
| 59638 |
+
{
|
| 59639 |
+
"epoch": 9.703133903133903,
|
| 59640 |
+
"grad_norm": 0.21624235808849335,
|
| 59641 |
+
"learning_rate": 2.7852183799855558e-05,
|
| 59642 |
+
"loss": 0.6875,
|
| 59643 |
+
"step": 8519
|
| 59644 |
+
},
|
| 59645 |
+
{
|
| 59646 |
+
"epoch": 9.704273504273504,
|
| 59647 |
+
"grad_norm": 0.23673588037490845,
|
| 59648 |
+
"learning_rate": 2.7847554990305756e-05,
|
| 59649 |
+
"loss": 0.8201,
|
| 59650 |
+
"step": 8520
|
| 59651 |
+
},
|
| 59652 |
+
{
|
| 59653 |
+
"epoch": 9.705413105413106,
|
| 59654 |
+
"grad_norm": 0.20163588225841522,
|
| 59655 |
+
"learning_rate": 2.7842926081852533e-05,
|
| 59656 |
+
"loss": 0.7495,
|
| 59657 |
+
"step": 8521
|
| 59658 |
+
},
|
| 59659 |
+
{
|
| 59660 |
+
"epoch": 9.706552706552706,
|
| 59661 |
+
"grad_norm": 0.18318887054920197,
|
| 59662 |
+
"learning_rate": 2.7838297074656677e-05,
|
| 59663 |
+
"loss": 0.924,
|
| 59664 |
+
"step": 8522
|
| 59665 |
+
},
|
| 59666 |
+
{
|
| 59667 |
+
"epoch": 9.707692307692307,
|
| 59668 |
+
"grad_norm": 0.2320988029241562,
|
| 59669 |
+
"learning_rate": 2.7833667968878952e-05,
|
| 59670 |
+
"loss": 0.6304,
|
| 59671 |
+
"step": 8523
|
| 59672 |
+
},
|
| 59673 |
+
{
|
| 59674 |
+
"epoch": 9.70883190883191,
|
| 59675 |
+
"grad_norm": 0.21639958024024963,
|
| 59676 |
+
"learning_rate": 2.7829038764680143e-05,
|
| 59677 |
+
"loss": 0.6043,
|
| 59678 |
+
"step": 8524
|
| 59679 |
+
},
|
| 59680 |
+
{
|
| 59681 |
+
"epoch": 9.70997150997151,
|
| 59682 |
+
"grad_norm": 0.21211375296115875,
|
| 59683 |
+
"learning_rate": 2.7824409462221047e-05,
|
| 59684 |
+
"loss": 0.8569,
|
| 59685 |
+
"step": 8525
|
| 59686 |
+
},
|
| 59687 |
+
{
|
| 59688 |
+
"epoch": 9.71111111111111,
|
| 59689 |
+
"grad_norm": 0.20413239300251007,
|
| 59690 |
+
"learning_rate": 2.7819780061662436e-05,
|
| 59691 |
+
"loss": 0.7475,
|
| 59692 |
+
"step": 8526
|
| 59693 |
+
},
|
| 59694 |
+
{
|
| 59695 |
+
"epoch": 9.712250712250713,
|
| 59696 |
+
"grad_norm": 0.2298765927553177,
|
| 59697 |
+
"learning_rate": 2.7815150563165116e-05,
|
| 59698 |
+
"loss": 0.6669,
|
| 59699 |
+
"step": 8527
|
| 59700 |
+
},
|
| 59701 |
+
{
|
| 59702 |
+
"epoch": 9.713390313390313,
|
| 59703 |
+
"grad_norm": 0.19131982326507568,
|
| 59704 |
+
"learning_rate": 2.7810520966889863e-05,
|
| 59705 |
+
"loss": 0.6668,
|
| 59706 |
+
"step": 8528
|
| 59707 |
+
},
|
| 59708 |
+
{
|
| 59709 |
+
"epoch": 9.714529914529914,
|
| 59710 |
+
"grad_norm": 0.2224835306406021,
|
| 59711 |
+
"learning_rate": 2.78058912729975e-05,
|
| 59712 |
+
"loss": 0.8234,
|
| 59713 |
+
"step": 8529
|
| 59714 |
+
},
|
| 59715 |
+
{
|
| 59716 |
+
"epoch": 9.715669515669516,
|
| 59717 |
+
"grad_norm": 0.17884741723537445,
|
| 59718 |
+
"learning_rate": 2.7801261481648807e-05,
|
| 59719 |
+
"loss": 0.7831,
|
| 59720 |
+
"step": 8530
|
| 59721 |
+
},
|
| 59722 |
+
{
|
| 59723 |
+
"epoch": 9.716809116809117,
|
| 59724 |
+
"grad_norm": 0.22266241908073425,
|
| 59725 |
+
"learning_rate": 2.7796631593004608e-05,
|
| 59726 |
+
"loss": 0.6715,
|
| 59727 |
+
"step": 8531
|
| 59728 |
+
},
|
| 59729 |
+
{
|
| 59730 |
+
"epoch": 9.717948717948717,
|
| 59731 |
+
"grad_norm": 0.2213110327720642,
|
| 59732 |
+
"learning_rate": 2.77920016072257e-05,
|
| 59733 |
+
"loss": 0.7549,
|
| 59734 |
+
"step": 8532
|
| 59735 |
+
},
|
| 59736 |
+
{
|
| 59737 |
+
"epoch": 9.71908831908832,
|
| 59738 |
+
"grad_norm": 0.21489235758781433,
|
| 59739 |
+
"learning_rate": 2.77873715244729e-05,
|
| 59740 |
+
"loss": 0.7453,
|
| 59741 |
+
"step": 8533
|
| 59742 |
+
},
|
| 59743 |
+
{
|
| 59744 |
+
"epoch": 9.72022792022792,
|
| 59745 |
+
"grad_norm": 0.2805543839931488,
|
| 59746 |
+
"learning_rate": 2.7782741344907008e-05,
|
| 59747 |
+
"loss": 0.5758,
|
| 59748 |
+
"step": 8534
|
| 59749 |
+
},
|
| 59750 |
+
{
|
| 59751 |
+
"epoch": 9.72136752136752,
|
| 59752 |
+
"grad_norm": 0.20469795167446136,
|
| 59753 |
+
"learning_rate": 2.777811106868887e-05,
|
| 59754 |
+
"loss": 0.7528,
|
| 59755 |
+
"step": 8535
|
| 59756 |
+
},
|
| 59757 |
+
{
|
| 59758 |
+
"epoch": 9.722507122507123,
|
| 59759 |
+
"grad_norm": 0.21546640992164612,
|
| 59760 |
+
"learning_rate": 2.777348069597929e-05,
|
| 59761 |
+
"loss": 0.8487,
|
| 59762 |
+
"step": 8536
|
| 59763 |
+
},
|
| 59764 |
+
{
|
| 59765 |
+
"epoch": 9.723646723646723,
|
| 59766 |
+
"grad_norm": 0.2270408421754837,
|
| 59767 |
+
"learning_rate": 2.7768850226939108e-05,
|
| 59768 |
+
"loss": 0.6702,
|
| 59769 |
+
"step": 8537
|
| 59770 |
+
},
|
| 59771 |
+
{
|
| 59772 |
+
"epoch": 9.724786324786324,
|
| 59773 |
+
"grad_norm": 0.20566929876804352,
|
| 59774 |
+
"learning_rate": 2.7764219661729135e-05,
|
| 59775 |
+
"loss": 0.7752,
|
| 59776 |
+
"step": 8538
|
| 59777 |
+
},
|
| 59778 |
+
{
|
| 59779 |
+
"epoch": 9.725925925925926,
|
| 59780 |
+
"grad_norm": 0.21666070818901062,
|
| 59781 |
+
"learning_rate": 2.775958900051021e-05,
|
| 59782 |
+
"loss": 0.6814,
|
| 59783 |
+
"step": 8539
|
| 59784 |
+
},
|
| 59785 |
+
{
|
| 59786 |
+
"epoch": 9.727065527065527,
|
| 59787 |
+
"grad_norm": 0.19858340919017792,
|
| 59788 |
+
"learning_rate": 2.7754958243443174e-05,
|
| 59789 |
+
"loss": 0.5329,
|
| 59790 |
+
"step": 8540
|
| 59791 |
+
},
|
| 59792 |
+
{
|
| 59793 |
+
"epoch": 9.728205128205127,
|
| 59794 |
+
"grad_norm": 0.18944010138511658,
|
| 59795 |
+
"learning_rate": 2.7750327390688856e-05,
|
| 59796 |
+
"loss": 0.8507,
|
| 59797 |
+
"step": 8541
|
| 59798 |
+
},
|
| 59799 |
+
{
|
| 59800 |
+
"epoch": 9.72934472934473,
|
| 59801 |
+
"grad_norm": 0.21177950501441956,
|
| 59802 |
+
"learning_rate": 2.7745696442408114e-05,
|
| 59803 |
+
"loss": 0.7086,
|
| 59804 |
+
"step": 8542
|
| 59805 |
+
},
|
| 59806 |
+
{
|
| 59807 |
+
"epoch": 9.73048433048433,
|
| 59808 |
+
"grad_norm": 0.19310303032398224,
|
| 59809 |
+
"learning_rate": 2.774106539876178e-05,
|
| 59810 |
+
"loss": 0.8071,
|
| 59811 |
+
"step": 8543
|
| 59812 |
+
},
|
| 59813 |
+
{
|
| 59814 |
+
"epoch": 9.73162393162393,
|
| 59815 |
+
"grad_norm": 0.2265753597021103,
|
| 59816 |
+
"learning_rate": 2.773643425991071e-05,
|
| 59817 |
+
"loss": 0.7076,
|
| 59818 |
+
"step": 8544
|
| 59819 |
+
},
|
| 59820 |
+
{
|
| 59821 |
+
"epoch": 9.732763532763533,
|
| 59822 |
+
"grad_norm": 0.25541719794273376,
|
| 59823 |
+
"learning_rate": 2.773180302601574e-05,
|
| 59824 |
+
"loss": 0.5428,
|
| 59825 |
+
"step": 8545
|
| 59826 |
+
},
|
| 59827 |
+
{
|
| 59828 |
+
"epoch": 9.733903133903134,
|
| 59829 |
+
"grad_norm": 0.25014615058898926,
|
| 59830 |
+
"learning_rate": 2.7727171697237747e-05,
|
| 59831 |
+
"loss": 0.5156,
|
| 59832 |
+
"step": 8546
|
| 59833 |
+
},
|
| 59834 |
+
{
|
| 59835 |
+
"epoch": 9.735042735042736,
|
| 59836 |
+
"grad_norm": 0.24546726047992706,
|
| 59837 |
+
"learning_rate": 2.772254027373758e-05,
|
| 59838 |
+
"loss": 0.582,
|
| 59839 |
+
"step": 8547
|
| 59840 |
+
},
|
| 59841 |
+
{
|
| 59842 |
+
"epoch": 9.736182336182337,
|
| 59843 |
+
"grad_norm": 0.20591729879379272,
|
| 59844 |
+
"learning_rate": 2.771790875567611e-05,
|
| 59845 |
+
"loss": 0.8366,
|
| 59846 |
+
"step": 8548
|
| 59847 |
+
},
|
| 59848 |
+
{
|
| 59849 |
+
"epoch": 9.737321937321937,
|
| 59850 |
+
"grad_norm": 0.20504891872406006,
|
| 59851 |
+
"learning_rate": 2.7713277143214184e-05,
|
| 59852 |
+
"loss": 0.7317,
|
| 59853 |
+
"step": 8549
|
| 59854 |
+
},
|
| 59855 |
+
{
|
| 59856 |
+
"epoch": 9.73846153846154,
|
| 59857 |
+
"grad_norm": 0.21834293007850647,
|
| 59858 |
+
"learning_rate": 2.770864543651268e-05,
|
| 59859 |
+
"loss": 0.6696,
|
| 59860 |
+
"step": 8550
|
| 59861 |
+
},
|
| 59862 |
+
{
|
| 59863 |
+
"epoch": 9.73960113960114,
|
| 59864 |
+
"grad_norm": 0.1837180107831955,
|
| 59865 |
+
"learning_rate": 2.7704013635732477e-05,
|
| 59866 |
+
"loss": 0.7439,
|
| 59867 |
+
"step": 8551
|
| 59868 |
+
},
|
| 59869 |
+
{
|
| 59870 |
+
"epoch": 9.74074074074074,
|
| 59871 |
+
"grad_norm": 0.1709396094083786,
|
| 59872 |
+
"learning_rate": 2.7699381741034447e-05,
|
| 59873 |
+
"loss": 0.8316,
|
| 59874 |
+
"step": 8552
|
| 59875 |
+
},
|
| 59876 |
+
{
|
| 59877 |
+
"epoch": 9.741880341880343,
|
| 59878 |
+
"grad_norm": 0.22776567935943604,
|
| 59879 |
+
"learning_rate": 2.769474975257946e-05,
|
| 59880 |
+
"loss": 0.6377,
|
| 59881 |
+
"step": 8553
|
| 59882 |
+
},
|
| 59883 |
+
{
|
| 59884 |
+
"epoch": 9.743019943019943,
|
| 59885 |
+
"grad_norm": 0.18397639691829681,
|
| 59886 |
+
"learning_rate": 2.769011767052841e-05,
|
| 59887 |
+
"loss": 0.7457,
|
| 59888 |
+
"step": 8554
|
| 59889 |
+
},
|
| 59890 |
+
{
|
| 59891 |
+
"epoch": 9.744159544159544,
|
| 59892 |
+
"grad_norm": 0.2865777015686035,
|
| 59893 |
+
"learning_rate": 2.768548549504217e-05,
|
| 59894 |
+
"loss": 0.6397,
|
| 59895 |
+
"step": 8555
|
| 59896 |
+
},
|
| 59897 |
+
{
|
| 59898 |
+
"epoch": 9.745299145299146,
|
| 59899 |
+
"grad_norm": 0.19933927059173584,
|
| 59900 |
+
"learning_rate": 2.7680853226281632e-05,
|
| 59901 |
+
"loss": 0.8608,
|
| 59902 |
+
"step": 8556
|
| 59903 |
+
},
|
| 59904 |
+
{
|
| 59905 |
+
"epoch": 9.746438746438747,
|
| 59906 |
+
"grad_norm": 0.2017425298690796,
|
| 59907 |
+
"learning_rate": 2.76762208644077e-05,
|
| 59908 |
+
"loss": 0.7348,
|
| 59909 |
+
"step": 8557
|
| 59910 |
+
},
|
| 59911 |
+
{
|
| 59912 |
+
"epoch": 9.747578347578347,
|
| 59913 |
+
"grad_norm": 0.21706503629684448,
|
| 59914 |
+
"learning_rate": 2.7671588409581245e-05,
|
| 59915 |
+
"loss": 0.7129,
|
| 59916 |
+
"step": 8558
|
| 59917 |
+
},
|
| 59918 |
+
{
|
| 59919 |
+
"epoch": 9.74871794871795,
|
| 59920 |
+
"grad_norm": 0.20259225368499756,
|
| 59921 |
+
"learning_rate": 2.7666955861963185e-05,
|
| 59922 |
+
"loss": 0.6993,
|
| 59923 |
+
"step": 8559
|
| 59924 |
+
},
|
| 59925 |
+
{
|
| 59926 |
+
"epoch": 9.74985754985755,
|
| 59927 |
+
"grad_norm": 0.18231546878814697,
|
| 59928 |
+
"learning_rate": 2.766232322171441e-05,
|
| 59929 |
+
"loss": 0.7069,
|
| 59930 |
+
"step": 8560
|
| 59931 |
+
},
|
| 59932 |
+
{
|
| 59933 |
+
"epoch": 9.75099715099715,
|
| 59934 |
+
"grad_norm": 0.24575591087341309,
|
| 59935 |
+
"learning_rate": 2.765769048899583e-05,
|
| 59936 |
+
"loss": 0.6927,
|
| 59937 |
+
"step": 8561
|
| 59938 |
+
},
|
| 59939 |
+
{
|
| 59940 |
+
"epoch": 9.752136752136753,
|
| 59941 |
+
"grad_norm": 0.18512912094593048,
|
| 59942 |
+
"learning_rate": 2.7653057663968345e-05,
|
| 59943 |
+
"loss": 0.842,
|
| 59944 |
+
"step": 8562
|
| 59945 |
+
},
|
| 59946 |
+
{
|
| 59947 |
+
"epoch": 9.753276353276354,
|
| 59948 |
+
"grad_norm": 0.20622968673706055,
|
| 59949 |
+
"learning_rate": 2.7648424746792883e-05,
|
| 59950 |
+
"loss": 0.5028,
|
| 59951 |
+
"step": 8563
|
| 59952 |
+
},
|
| 59953 |
+
{
|
| 59954 |
+
"epoch": 9.754415954415954,
|
| 59955 |
+
"grad_norm": 0.20363913476467133,
|
| 59956 |
+
"learning_rate": 2.7643791737630338e-05,
|
| 59957 |
+
"loss": 0.7849,
|
| 59958 |
+
"step": 8564
|
| 59959 |
+
},
|
| 59960 |
+
{
|
| 59961 |
+
"epoch": 9.755555555555556,
|
| 59962 |
+
"grad_norm": 0.1941133737564087,
|
| 59963 |
+
"learning_rate": 2.763915863664164e-05,
|
| 59964 |
+
"loss": 0.7551,
|
| 59965 |
+
"step": 8565
|
| 59966 |
+
},
|
| 59967 |
+
{
|
| 59968 |
+
"epoch": 9.756695156695157,
|
| 59969 |
+
"grad_norm": 0.24222709238529205,
|
| 59970 |
+
"learning_rate": 2.7634525443987698e-05,
|
| 59971 |
+
"loss": 0.6559,
|
| 59972 |
+
"step": 8566
|
| 59973 |
+
},
|
| 59974 |
+
{
|
| 59975 |
+
"epoch": 9.757834757834758,
|
| 59976 |
+
"grad_norm": 0.2114405781030655,
|
| 59977 |
+
"learning_rate": 2.7629892159829445e-05,
|
| 59978 |
+
"loss": 0.6597,
|
| 59979 |
+
"step": 8567
|
| 59980 |
+
},
|
| 59981 |
+
{
|
| 59982 |
+
"epoch": 9.75897435897436,
|
| 59983 |
+
"grad_norm": 0.2961379587650299,
|
| 59984 |
+
"learning_rate": 2.7625258784327806e-05,
|
| 59985 |
+
"loss": 0.6928,
|
| 59986 |
+
"step": 8568
|
| 59987 |
+
},
|
| 59988 |
+
{
|
| 59989 |
+
"epoch": 9.76011396011396,
|
| 59990 |
+
"grad_norm": 0.19896571338176727,
|
| 59991 |
+
"learning_rate": 2.762062531764371e-05,
|
| 59992 |
+
"loss": 0.6149,
|
| 59993 |
+
"step": 8569
|
| 59994 |
+
},
|
| 59995 |
+
{
|
| 59996 |
+
"epoch": 9.761253561253561,
|
| 59997 |
+
"grad_norm": 0.2416018843650818,
|
| 59998 |
+
"learning_rate": 2.7615991759938092e-05,
|
| 59999 |
+
"loss": 0.518,
|
| 60000 |
+
"step": 8570
|
| 60001 |
+
},
|
| 60002 |
+
{
|
| 60003 |
+
"epoch": 9.762393162393163,
|
| 60004 |
+
"grad_norm": 0.22412768006324768,
|
| 60005 |
+
"learning_rate": 2.7611358111371886e-05,
|
| 60006 |
+
"loss": 0.6632,
|
| 60007 |
+
"step": 8571
|
| 60008 |
+
},
|
| 60009 |
+
{
|
| 60010 |
+
"epoch": 9.763532763532764,
|
| 60011 |
+
"grad_norm": 0.23438774049282074,
|
| 60012 |
+
"learning_rate": 2.760672437210603e-05,
|
| 60013 |
+
"loss": 0.6062,
|
| 60014 |
+
"step": 8572
|
| 60015 |
+
},
|
| 60016 |
+
{
|
| 60017 |
+
"epoch": 9.764672364672364,
|
| 60018 |
+
"grad_norm": 0.2205171287059784,
|
| 60019 |
+
"learning_rate": 2.7602090542301468e-05,
|
| 60020 |
+
"loss": 0.6381,
|
| 60021 |
+
"step": 8573
|
| 60022 |
+
},
|
| 60023 |
+
{
|
| 60024 |
+
"epoch": 9.765811965811967,
|
| 60025 |
+
"grad_norm": 0.22630876302719116,
|
| 60026 |
+
"learning_rate": 2.759745662211915e-05,
|
| 60027 |
+
"loss": 0.7963,
|
| 60028 |
+
"step": 8574
|
| 60029 |
+
},
|
| 60030 |
+
{
|
| 60031 |
+
"epoch": 9.766951566951567,
|
| 60032 |
+
"grad_norm": 0.23154351115226746,
|
| 60033 |
+
"learning_rate": 2.7592822611720016e-05,
|
| 60034 |
+
"loss": 0.5376,
|
| 60035 |
+
"step": 8575
|
| 60036 |
+
},
|
| 60037 |
+
{
|
| 60038 |
+
"epoch": 9.768091168091168,
|
| 60039 |
+
"grad_norm": 0.21721205115318298,
|
| 60040 |
+
"learning_rate": 2.7588188511265023e-05,
|
| 60041 |
+
"loss": 0.5719,
|
| 60042 |
+
"step": 8576
|
| 60043 |
+
},
|
| 60044 |
+
{
|
| 60045 |
+
"epoch": 9.76923076923077,
|
| 60046 |
+
"grad_norm": 0.22528202831745148,
|
| 60047 |
+
"learning_rate": 2.7583554320915124e-05,
|
| 60048 |
+
"loss": 0.5727,
|
| 60049 |
+
"step": 8577
|
| 60050 |
+
},
|
| 60051 |
+
{
|
| 60052 |
+
"epoch": 9.77037037037037,
|
| 60053 |
+
"grad_norm": 0.22177764773368835,
|
| 60054 |
+
"learning_rate": 2.7578920040831273e-05,
|
| 60055 |
+
"loss": 0.7164,
|
| 60056 |
+
"step": 8578
|
| 60057 |
+
},
|
| 60058 |
+
{
|
| 60059 |
+
"epoch": 9.771509971509971,
|
| 60060 |
+
"grad_norm": 0.2995389997959137,
|
| 60061 |
+
"learning_rate": 2.7574285671174444e-05,
|
| 60062 |
+
"loss": 0.5085,
|
| 60063 |
+
"step": 8579
|
| 60064 |
+
},
|
| 60065 |
+
{
|
| 60066 |
+
"epoch": 9.772649572649573,
|
| 60067 |
+
"grad_norm": 0.1767067164182663,
|
| 60068 |
+
"learning_rate": 2.7569651212105602e-05,
|
| 60069 |
+
"loss": 0.8467,
|
| 60070 |
+
"step": 8580
|
| 60071 |
+
},
|
| 60072 |
+
{
|
| 60073 |
+
"epoch": 9.773789173789174,
|
| 60074 |
+
"grad_norm": 0.2124761939048767,
|
| 60075 |
+
"learning_rate": 2.7565016663785692e-05,
|
| 60076 |
+
"loss": 0.7081,
|
| 60077 |
+
"step": 8581
|
| 60078 |
+
},
|
| 60079 |
+
{
|
| 60080 |
+
"epoch": 9.774928774928775,
|
| 60081 |
+
"grad_norm": 0.2243443727493286,
|
| 60082 |
+
"learning_rate": 2.7560382026375714e-05,
|
| 60083 |
+
"loss": 0.5879,
|
| 60084 |
+
"step": 8582
|
| 60085 |
+
},
|
| 60086 |
+
{
|
| 60087 |
+
"epoch": 9.776068376068377,
|
| 60088 |
+
"grad_norm": 0.2404758781194687,
|
| 60089 |
+
"learning_rate": 2.7555747300036617e-05,
|
| 60090 |
+
"loss": 0.7576,
|
| 60091 |
+
"step": 8583
|
| 60092 |
+
},
|
| 60093 |
+
{
|
| 60094 |
+
"epoch": 9.777207977207977,
|
| 60095 |
+
"grad_norm": 0.2202008217573166,
|
| 60096 |
+
"learning_rate": 2.7551112484929385e-05,
|
| 60097 |
+
"loss": 0.7425,
|
| 60098 |
+
"step": 8584
|
| 60099 |
+
},
|
| 60100 |
+
{
|
| 60101 |
+
"epoch": 9.778347578347578,
|
| 60102 |
+
"grad_norm": 0.20645569264888763,
|
| 60103 |
+
"learning_rate": 2.7546477581215006e-05,
|
| 60104 |
+
"loss": 0.7184,
|
| 60105 |
+
"step": 8585
|
| 60106 |
+
},
|
| 60107 |
+
{
|
| 60108 |
+
"epoch": 9.77948717948718,
|
| 60109 |
+
"grad_norm": 0.174381285905838,
|
| 60110 |
+
"learning_rate": 2.7541842589054463e-05,
|
| 60111 |
+
"loss": 0.8345,
|
| 60112 |
+
"step": 8586
|
| 60113 |
+
},
|
| 60114 |
+
{
|
| 60115 |
+
"epoch": 9.78062678062678,
|
| 60116 |
+
"grad_norm": 0.20073771476745605,
|
| 60117 |
+
"learning_rate": 2.753720750860873e-05,
|
| 60118 |
+
"loss": 0.783,
|
| 60119 |
+
"step": 8587
|
| 60120 |
+
},
|
| 60121 |
+
{
|
| 60122 |
+
"epoch": 9.781766381766381,
|
| 60123 |
+
"grad_norm": 0.20477743446826935,
|
| 60124 |
+
"learning_rate": 2.753257234003881e-05,
|
| 60125 |
+
"loss": 0.8477,
|
| 60126 |
+
"step": 8588
|
| 60127 |
+
},
|
| 60128 |
+
{
|
| 60129 |
+
"epoch": 9.782905982905984,
|
| 60130 |
+
"grad_norm": 0.2629711925983429,
|
| 60131 |
+
"learning_rate": 2.7527937083505677e-05,
|
| 60132 |
+
"loss": 0.7077,
|
| 60133 |
+
"step": 8589
|
| 60134 |
+
},
|
| 60135 |
+
{
|
| 60136 |
+
"epoch": 9.784045584045584,
|
| 60137 |
+
"grad_norm": 0.16403615474700928,
|
| 60138 |
+
"learning_rate": 2.7523301739170343e-05,
|
| 60139 |
+
"loss": 1.0227,
|
| 60140 |
+
"step": 8590
|
| 60141 |
+
},
|
| 60142 |
+
{
|
| 60143 |
+
"epoch": 9.785185185185185,
|
| 60144 |
+
"grad_norm": 0.23415862023830414,
|
| 60145 |
+
"learning_rate": 2.7518666307193803e-05,
|
| 60146 |
+
"loss": 0.7995,
|
| 60147 |
+
"step": 8591
|
| 60148 |
+
},
|
| 60149 |
+
{
|
| 60150 |
+
"epoch": 9.786324786324787,
|
| 60151 |
+
"grad_norm": 0.22708284854888916,
|
| 60152 |
+
"learning_rate": 2.751403078773705e-05,
|
| 60153 |
+
"loss": 0.6878,
|
| 60154 |
+
"step": 8592
|
| 60155 |
+
},
|
| 60156 |
+
{
|
| 60157 |
+
"epoch": 9.787464387464388,
|
| 60158 |
+
"grad_norm": 0.2390306442975998,
|
| 60159 |
+
"learning_rate": 2.75093951809611e-05,
|
| 60160 |
+
"loss": 0.5568,
|
| 60161 |
+
"step": 8593
|
| 60162 |
+
},
|
| 60163 |
+
{
|
| 60164 |
+
"epoch": 9.788603988603988,
|
| 60165 |
+
"grad_norm": 0.19914384186267853,
|
| 60166 |
+
"learning_rate": 2.750475948702695e-05,
|
| 60167 |
+
"loss": 0.7419,
|
| 60168 |
+
"step": 8594
|
| 60169 |
+
},
|
| 60170 |
+
{
|
| 60171 |
+
"epoch": 9.78974358974359,
|
| 60172 |
+
"grad_norm": 0.2082630842924118,
|
| 60173 |
+
"learning_rate": 2.7500123706095614e-05,
|
| 60174 |
+
"loss": 0.8309,
|
| 60175 |
+
"step": 8595
|
| 60176 |
+
},
|
| 60177 |
+
{
|
| 60178 |
+
"epoch": 9.790883190883191,
|
| 60179 |
+
"grad_norm": 0.237423375248909,
|
| 60180 |
+
"learning_rate": 2.749548783832811e-05,
|
| 60181 |
+
"loss": 0.6335,
|
| 60182 |
+
"step": 8596
|
| 60183 |
+
},
|
| 60184 |
+
{
|
| 60185 |
+
"epoch": 9.792022792022792,
|
| 60186 |
+
"grad_norm": 0.24349914491176605,
|
| 60187 |
+
"learning_rate": 2.7490851883885454e-05,
|
| 60188 |
+
"loss": 0.6496,
|
| 60189 |
+
"step": 8597
|
| 60190 |
+
},
|
| 60191 |
+
{
|
| 60192 |
+
"epoch": 9.793162393162394,
|
| 60193 |
+
"grad_norm": 0.22968685626983643,
|
| 60194 |
+
"learning_rate": 2.7486215842928658e-05,
|
| 60195 |
+
"loss": 0.6947,
|
| 60196 |
+
"step": 8598
|
| 60197 |
+
},
|
| 60198 |
+
{
|
| 60199 |
+
"epoch": 9.794301994301994,
|
| 60200 |
+
"grad_norm": 0.20698566734790802,
|
| 60201 |
+
"learning_rate": 2.748157971561875e-05,
|
| 60202 |
+
"loss": 0.7617,
|
| 60203 |
+
"step": 8599
|
| 60204 |
+
},
|
| 60205 |
+
{
|
| 60206 |
+
"epoch": 9.795441595441595,
|
| 60207 |
+
"grad_norm": 0.203297957777977,
|
| 60208 |
+
"learning_rate": 2.7476943502116752e-05,
|
| 60209 |
+
"loss": 0.6874,
|
| 60210 |
+
"step": 8600
|
| 60211 |
+
},
|
| 60212 |
+
{
|
| 60213 |
+
"epoch": 9.796581196581197,
|
| 60214 |
+
"grad_norm": 0.2980722486972809,
|
| 60215 |
+
"learning_rate": 2.747230720258369e-05,
|
| 60216 |
+
"loss": 0.6644,
|
| 60217 |
+
"step": 8601
|
| 60218 |
+
},
|
| 60219 |
+
{
|
| 60220 |
+
"epoch": 9.797720797720798,
|
| 60221 |
+
"grad_norm": 0.2615736722946167,
|
| 60222 |
+
"learning_rate": 2.7467670817180612e-05,
|
| 60223 |
+
"loss": 0.5958,
|
| 60224 |
+
"step": 8602
|
| 60225 |
+
},
|
| 60226 |
+
{
|
| 60227 |
+
"epoch": 9.798860398860398,
|
| 60228 |
+
"grad_norm": 0.25255948305130005,
|
| 60229 |
+
"learning_rate": 2.7463034346068532e-05,
|
| 60230 |
+
"loss": 0.4842,
|
| 60231 |
+
"step": 8603
|
| 60232 |
+
},
|
| 60233 |
+
{
|
| 60234 |
+
"epoch": 9.8,
|
| 60235 |
+
"grad_norm": 0.20887507498264313,
|
| 60236 |
+
"learning_rate": 2.7458397789408503e-05,
|
| 60237 |
+
"loss": 0.8247,
|
| 60238 |
+
"step": 8604
|
| 60239 |
+
},
|
| 60240 |
+
{
|
| 60241 |
+
"epoch": 9.801139601139601,
|
| 60242 |
+
"grad_norm": 0.19382621347904205,
|
| 60243 |
+
"learning_rate": 2.7453761147361552e-05,
|
| 60244 |
+
"loss": 0.8055,
|
| 60245 |
+
"step": 8605
|
| 60246 |
+
},
|
| 60247 |
+
{
|
| 60248 |
+
"epoch": 9.802279202279202,
|
| 60249 |
+
"grad_norm": 0.20952007174491882,
|
| 60250 |
+
"learning_rate": 2.7449124420088725e-05,
|
| 60251 |
+
"loss": 0.8727,
|
| 60252 |
+
"step": 8606
|
| 60253 |
+
},
|
| 60254 |
+
{
|
| 60255 |
+
"epoch": 9.803418803418804,
|
| 60256 |
+
"grad_norm": 0.20277926325798035,
|
| 60257 |
+
"learning_rate": 2.7444487607751075e-05,
|
| 60258 |
+
"loss": 0.7493,
|
| 60259 |
+
"step": 8607
|
| 60260 |
+
},
|
| 60261 |
+
{
|
| 60262 |
+
"epoch": 9.804558404558405,
|
| 60263 |
+
"grad_norm": 0.23700590431690216,
|
| 60264 |
+
"learning_rate": 2.7439850710509652e-05,
|
| 60265 |
+
"loss": 0.5966,
|
| 60266 |
+
"step": 8608
|
| 60267 |
+
},
|
| 60268 |
+
{
|
| 60269 |
+
"epoch": 9.805698005698005,
|
| 60270 |
+
"grad_norm": 0.1902497410774231,
|
| 60271 |
+
"learning_rate": 2.74352137285255e-05,
|
| 60272 |
+
"loss": 0.8184,
|
| 60273 |
+
"step": 8609
|
| 60274 |
+
},
|
| 60275 |
+
{
|
| 60276 |
+
"epoch": 9.806837606837608,
|
| 60277 |
+
"grad_norm": 0.25543636083602905,
|
| 60278 |
+
"learning_rate": 2.743057666195968e-05,
|
| 60279 |
+
"loss": 0.5711,
|
| 60280 |
+
"step": 8610
|
| 60281 |
+
},
|
| 60282 |
+
{
|
| 60283 |
+
"epoch": 9.807977207977208,
|
| 60284 |
+
"grad_norm": 0.21522241830825806,
|
| 60285 |
+
"learning_rate": 2.7425939510973243e-05,
|
| 60286 |
+
"loss": 0.7143,
|
| 60287 |
+
"step": 8611
|
| 60288 |
+
},
|
| 60289 |
+
{
|
| 60290 |
+
"epoch": 9.809116809116809,
|
| 60291 |
+
"grad_norm": 0.1974640190601349,
|
| 60292 |
+
"learning_rate": 2.7421302275727263e-05,
|
| 60293 |
+
"loss": 0.805,
|
| 60294 |
+
"step": 8612
|
| 60295 |
+
},
|
| 60296 |
+
{
|
| 60297 |
+
"epoch": 9.810256410256411,
|
| 60298 |
+
"grad_norm": 0.22378608584403992,
|
| 60299 |
+
"learning_rate": 2.7416664956382793e-05,
|
| 60300 |
+
"loss": 0.6073,
|
| 60301 |
+
"step": 8613
|
| 60302 |
+
},
|
| 60303 |
+
{
|
| 60304 |
+
"epoch": 9.811396011396011,
|
| 60305 |
+
"grad_norm": 0.21204134821891785,
|
| 60306 |
+
"learning_rate": 2.7412027553100905e-05,
|
| 60307 |
+
"loss": 0.6566,
|
| 60308 |
+
"step": 8614
|
| 60309 |
+
},
|
| 60310 |
+
{
|
| 60311 |
+
"epoch": 9.812535612535612,
|
| 60312 |
+
"grad_norm": 0.2479940950870514,
|
| 60313 |
+
"learning_rate": 2.7407390066042665e-05,
|
| 60314 |
+
"loss": 0.6049,
|
| 60315 |
+
"step": 8615
|
| 60316 |
+
},
|
| 60317 |
+
{
|
| 60318 |
+
"epoch": 9.813675213675214,
|
| 60319 |
+
"grad_norm": 0.20882539451122284,
|
| 60320 |
+
"learning_rate": 2.740275249536915e-05,
|
| 60321 |
+
"loss": 0.7491,
|
| 60322 |
+
"step": 8616
|
| 60323 |
+
},
|
| 60324 |
+
{
|
| 60325 |
+
"epoch": 9.814814814814815,
|
| 60326 |
+
"grad_norm": 0.2341488152742386,
|
| 60327 |
+
"learning_rate": 2.739811484124143e-05,
|
| 60328 |
+
"loss": 0.7128,
|
| 60329 |
+
"step": 8617
|
| 60330 |
+
},
|
| 60331 |
+
{
|
| 60332 |
+
"epoch": 9.815954415954415,
|
| 60333 |
+
"grad_norm": 0.208388552069664,
|
| 60334 |
+
"learning_rate": 2.7393477103820586e-05,
|
| 60335 |
+
"loss": 0.7572,
|
| 60336 |
+
"step": 8618
|
| 60337 |
+
},
|
| 60338 |
+
{
|
| 60339 |
+
"epoch": 9.817094017094018,
|
| 60340 |
+
"grad_norm": 0.19041959941387177,
|
| 60341 |
+
"learning_rate": 2.738883928326771e-05,
|
| 60342 |
+
"loss": 0.7578,
|
| 60343 |
+
"step": 8619
|
| 60344 |
+
},
|
| 60345 |
+
{
|
| 60346 |
+
"epoch": 9.818233618233618,
|
| 60347 |
+
"grad_norm": 0.20121407508850098,
|
| 60348 |
+
"learning_rate": 2.7384201379743868e-05,
|
| 60349 |
+
"loss": 0.7521,
|
| 60350 |
+
"step": 8620
|
| 60351 |
+
},
|
| 60352 |
+
{
|
| 60353 |
+
"epoch": 9.819373219373219,
|
| 60354 |
+
"grad_norm": 0.20214299857616425,
|
| 60355 |
+
"learning_rate": 2.7379563393410158e-05,
|
| 60356 |
+
"loss": 0.836,
|
| 60357 |
+
"step": 8621
|
| 60358 |
+
},
|
| 60359 |
+
{
|
| 60360 |
+
"epoch": 9.820512820512821,
|
| 60361 |
+
"grad_norm": 0.18229928612709045,
|
| 60362 |
+
"learning_rate": 2.737492532442766e-05,
|
| 60363 |
+
"loss": 0.8039,
|
| 60364 |
+
"step": 8622
|
| 60365 |
+
},
|
| 60366 |
+
{
|
| 60367 |
+
"epoch": 9.821652421652422,
|
| 60368 |
+
"grad_norm": 0.23522637784481049,
|
| 60369 |
+
"learning_rate": 2.7370287172957483e-05,
|
| 60370 |
+
"loss": 0.763,
|
| 60371 |
+
"step": 8623
|
| 60372 |
+
},
|
| 60373 |
+
{
|
| 60374 |
+
"epoch": 9.822792022792022,
|
| 60375 |
+
"grad_norm": 0.21190528571605682,
|
| 60376 |
+
"learning_rate": 2.736564893916071e-05,
|
| 60377 |
+
"loss": 0.6686,
|
| 60378 |
+
"step": 8624
|
| 60379 |
+
},
|
| 60380 |
+
{
|
| 60381 |
+
"epoch": 9.823931623931625,
|
| 60382 |
+
"grad_norm": 0.21622231602668762,
|
| 60383 |
+
"learning_rate": 2.7361010623198445e-05,
|
| 60384 |
+
"loss": 0.6791,
|
| 60385 |
+
"step": 8625
|
| 60386 |
+
},
|
| 60387 |
+
{
|
| 60388 |
+
"epoch": 9.825071225071225,
|
| 60389 |
+
"grad_norm": 0.18883854150772095,
|
| 60390 |
+
"learning_rate": 2.735637222523179e-05,
|
| 60391 |
+
"loss": 0.7064,
|
| 60392 |
+
"step": 8626
|
| 60393 |
+
},
|
| 60394 |
+
{
|
| 60395 |
+
"epoch": 9.826210826210826,
|
| 60396 |
+
"grad_norm": 0.2039935290813446,
|
| 60397 |
+
"learning_rate": 2.735173374542185e-05,
|
| 60398 |
+
"loss": 0.7518,
|
| 60399 |
+
"step": 8627
|
| 60400 |
+
},
|
| 60401 |
+
{
|
| 60402 |
+
"epoch": 9.827350427350428,
|
| 60403 |
+
"grad_norm": 0.19084110856056213,
|
| 60404 |
+
"learning_rate": 2.7347095183929716e-05,
|
| 60405 |
+
"loss": 0.8417,
|
| 60406 |
+
"step": 8628
|
| 60407 |
+
},
|
| 60408 |
+
{
|
| 60409 |
+
"epoch": 9.828490028490029,
|
| 60410 |
+
"grad_norm": 0.17323356866836548,
|
| 60411 |
+
"learning_rate": 2.734245654091653e-05,
|
| 60412 |
+
"loss": 0.9049,
|
| 60413 |
+
"step": 8629
|
| 60414 |
+
},
|
| 60415 |
+
{
|
| 60416 |
+
"epoch": 9.829629629629629,
|
| 60417 |
+
"grad_norm": 0.2370297610759735,
|
| 60418 |
+
"learning_rate": 2.733781781654337e-05,
|
| 60419 |
+
"loss": 0.6323,
|
| 60420 |
+
"step": 8630
|
| 60421 |
+
},
|
| 60422 |
+
{
|
| 60423 |
+
"epoch": 9.830769230769231,
|
| 60424 |
+
"grad_norm": 0.22816629707813263,
|
| 60425 |
+
"learning_rate": 2.733317901097138e-05,
|
| 60426 |
+
"loss": 0.5564,
|
| 60427 |
+
"step": 8631
|
| 60428 |
+
},
|
| 60429 |
+
{
|
| 60430 |
+
"epoch": 9.831908831908832,
|
| 60431 |
+
"grad_norm": 0.2457447350025177,
|
| 60432 |
+
"learning_rate": 2.7328540124361662e-05,
|
| 60433 |
+
"loss": 0.6702,
|
| 60434 |
+
"step": 8632
|
| 60435 |
+
},
|
| 60436 |
+
{
|
| 60437 |
+
"epoch": 9.833048433048432,
|
| 60438 |
+
"grad_norm": 0.21235868334770203,
|
| 60439 |
+
"learning_rate": 2.732390115687534e-05,
|
| 60440 |
+
"loss": 0.7327,
|
| 60441 |
+
"step": 8633
|
| 60442 |
+
},
|
| 60443 |
+
{
|
| 60444 |
+
"epoch": 9.834188034188035,
|
| 60445 |
+
"grad_norm": 0.2475348562002182,
|
| 60446 |
+
"learning_rate": 2.731926210867355e-05,
|
| 60447 |
+
"loss": 0.6758,
|
| 60448 |
+
"step": 8634
|
| 60449 |
+
},
|
| 60450 |
+
{
|
| 60451 |
+
"epoch": 9.835327635327635,
|
| 60452 |
+
"grad_norm": 0.20760078728199005,
|
| 60453 |
+
"learning_rate": 2.7314622979917398e-05,
|
| 60454 |
+
"loss": 0.6831,
|
| 60455 |
+
"step": 8635
|
| 60456 |
+
},
|
| 60457 |
+
{
|
| 60458 |
+
"epoch": 9.836467236467236,
|
| 60459 |
+
"grad_norm": 0.1691773384809494,
|
| 60460 |
+
"learning_rate": 2.7309983770768033e-05,
|
| 60461 |
+
"loss": 1.002,
|
| 60462 |
+
"step": 8636
|
| 60463 |
+
},
|
| 60464 |
+
{
|
| 60465 |
+
"epoch": 9.837606837606838,
|
| 60466 |
+
"grad_norm": 0.1824226826429367,
|
| 60467 |
+
"learning_rate": 2.7305344481386576e-05,
|
| 60468 |
+
"loss": 0.7868,
|
| 60469 |
+
"step": 8637
|
| 60470 |
+
},
|
| 60471 |
+
{
|
| 60472 |
+
"epoch": 9.838746438746439,
|
| 60473 |
+
"grad_norm": 0.19655545055866241,
|
| 60474 |
+
"learning_rate": 2.7300705111934165e-05,
|
| 60475 |
+
"loss": 0.7432,
|
| 60476 |
+
"step": 8638
|
| 60477 |
+
},
|
| 60478 |
+
{
|
| 60479 |
+
"epoch": 9.83988603988604,
|
| 60480 |
+
"grad_norm": 0.17179349064826965,
|
| 60481 |
+
"learning_rate": 2.7296065662571935e-05,
|
| 60482 |
+
"loss": 0.792,
|
| 60483 |
+
"step": 8639
|
| 60484 |
+
},
|
| 60485 |
+
{
|
| 60486 |
+
"epoch": 9.841025641025642,
|
| 60487 |
+
"grad_norm": 0.273364394903183,
|
| 60488 |
+
"learning_rate": 2.7291426133461034e-05,
|
| 60489 |
+
"loss": 0.6771,
|
| 60490 |
+
"step": 8640
|
| 60491 |
+
},
|
| 60492 |
+
{
|
| 60493 |
+
"epoch": 9.842165242165242,
|
| 60494 |
+
"grad_norm": 0.20707401633262634,
|
| 60495 |
+
"learning_rate": 2.72867865247626e-05,
|
| 60496 |
+
"loss": 0.8326,
|
| 60497 |
+
"step": 8641
|
| 60498 |
+
},
|
| 60499 |
+
{
|
| 60500 |
+
"epoch": 9.843304843304843,
|
| 60501 |
+
"grad_norm": 0.22714680433273315,
|
| 60502 |
+
"learning_rate": 2.7282146836637783e-05,
|
| 60503 |
+
"loss": 0.6631,
|
| 60504 |
+
"step": 8642
|
| 60505 |
+
},
|
| 60506 |
+
{
|
| 60507 |
+
"epoch": 9.844444444444445,
|
| 60508 |
+
"grad_norm": 0.204382985830307,
|
| 60509 |
+
"learning_rate": 2.7277507069247732e-05,
|
| 60510 |
+
"loss": 0.5877,
|
| 60511 |
+
"step": 8643
|
| 60512 |
+
},
|
| 60513 |
+
{
|
| 60514 |
+
"epoch": 9.845584045584046,
|
| 60515 |
+
"grad_norm": 0.22668123245239258,
|
| 60516 |
+
"learning_rate": 2.727286722275359e-05,
|
| 60517 |
+
"loss": 0.5728,
|
| 60518 |
+
"step": 8644
|
| 60519 |
+
},
|
| 60520 |
+
{
|
| 60521 |
+
"epoch": 9.846723646723646,
|
| 60522 |
+
"grad_norm": 0.2232021540403366,
|
| 60523 |
+
"learning_rate": 2.7268227297316525e-05,
|
| 60524 |
+
"loss": 0.628,
|
| 60525 |
+
"step": 8645
|
| 60526 |
+
},
|
| 60527 |
+
{
|
| 60528 |
+
"epoch": 9.847863247863248,
|
| 60529 |
+
"grad_norm": 0.22668619453907013,
|
| 60530 |
+
"learning_rate": 2.726358729309769e-05,
|
| 60531 |
+
"loss": 0.6794,
|
| 60532 |
+
"step": 8646
|
| 60533 |
+
},
|
| 60534 |
+
{
|
| 60535 |
+
"epoch": 9.849002849002849,
|
| 60536 |
+
"grad_norm": 0.17795786261558533,
|
| 60537 |
+
"learning_rate": 2.725894721025824e-05,
|
| 60538 |
+
"loss": 0.7246,
|
| 60539 |
+
"step": 8647
|
| 60540 |
+
},
|
| 60541 |
+
{
|
| 60542 |
+
"epoch": 9.85014245014245,
|
| 60543 |
+
"grad_norm": 0.21658514440059662,
|
| 60544 |
+
"learning_rate": 2.7254307048959345e-05,
|
| 60545 |
+
"loss": 0.6665,
|
| 60546 |
+
"step": 8648
|
| 60547 |
+
},
|
| 60548 |
+
{
|
| 60549 |
+
"epoch": 9.851282051282052,
|
| 60550 |
+
"grad_norm": 0.1895408183336258,
|
| 60551 |
+
"learning_rate": 2.724966680936216e-05,
|
| 60552 |
+
"loss": 0.8378,
|
| 60553 |
+
"step": 8649
|
| 60554 |
+
},
|
| 60555 |
+
{
|
| 60556 |
+
"epoch": 9.852421652421652,
|
| 60557 |
+
"grad_norm": 0.20734098553657532,
|
| 60558 |
+
"learning_rate": 2.7245026491627862e-05,
|
| 60559 |
+
"loss": 0.7603,
|
| 60560 |
+
"step": 8650
|
| 60561 |
+
},
|
| 60562 |
+
{
|
| 60563 |
+
"epoch": 9.853561253561253,
|
| 60564 |
+
"grad_norm": 0.2191520631313324,
|
| 60565 |
+
"learning_rate": 2.7240386095917624e-05,
|
| 60566 |
+
"loss": 0.8362,
|
| 60567 |
+
"step": 8651
|
| 60568 |
+
},
|
| 60569 |
+
{
|
| 60570 |
+
"epoch": 9.854700854700855,
|
| 60571 |
+
"grad_norm": 0.1940697282552719,
|
| 60572 |
+
"learning_rate": 2.7235745622392617e-05,
|
| 60573 |
+
"loss": 0.817,
|
| 60574 |
+
"step": 8652
|
| 60575 |
+
},
|
| 60576 |
+
{
|
| 60577 |
+
"epoch": 9.855840455840456,
|
| 60578 |
+
"grad_norm": 0.19857257604599,
|
| 60579 |
+
"learning_rate": 2.7231105071214015e-05,
|
| 60580 |
+
"loss": 0.6497,
|
| 60581 |
+
"step": 8653
|
| 60582 |
+
},
|
| 60583 |
+
{
|
| 60584 |
+
"epoch": 9.856980056980056,
|
| 60585 |
+
"grad_norm": 0.1806962490081787,
|
| 60586 |
+
"learning_rate": 2.722646444254299e-05,
|
| 60587 |
+
"loss": 0.824,
|
| 60588 |
+
"step": 8654
|
| 60589 |
+
},
|
| 60590 |
+
{
|
| 60591 |
+
"epoch": 9.858119658119659,
|
| 60592 |
+
"grad_norm": 0.18675166368484497,
|
| 60593 |
+
"learning_rate": 2.7221823736540742e-05,
|
| 60594 |
+
"loss": 0.6341,
|
| 60595 |
+
"step": 8655
|
| 60596 |
+
},
|
| 60597 |
+
{
|
| 60598 |
+
"epoch": 9.85925925925926,
|
| 60599 |
+
"grad_norm": 0.20888161659240723,
|
| 60600 |
+
"learning_rate": 2.7217182953368442e-05,
|
| 60601 |
+
"loss": 0.8685,
|
| 60602 |
+
"step": 8656
|
| 60603 |
+
},
|
| 60604 |
+
{
|
| 60605 |
+
"epoch": 9.86039886039886,
|
| 60606 |
+
"grad_norm": 0.1748548150062561,
|
| 60607 |
+
"learning_rate": 2.721254209318728e-05,
|
| 60608 |
+
"loss": 0.8589,
|
| 60609 |
+
"step": 8657
|
| 60610 |
+
},
|
| 60611 |
+
{
|
| 60612 |
+
"epoch": 9.861538461538462,
|
| 60613 |
+
"grad_norm": 0.21147984266281128,
|
| 60614 |
+
"learning_rate": 2.720790115615845e-05,
|
| 60615 |
+
"loss": 0.7148,
|
| 60616 |
+
"step": 8658
|
| 60617 |
+
},
|
| 60618 |
+
{
|
| 60619 |
+
"epoch": 9.862678062678063,
|
| 60620 |
+
"grad_norm": 0.1968158334493637,
|
| 60621 |
+
"learning_rate": 2.7203260142443137e-05,
|
| 60622 |
+
"loss": 0.8946,
|
| 60623 |
+
"step": 8659
|
| 60624 |
+
},
|
| 60625 |
+
{
|
| 60626 |
+
"epoch": 9.863817663817663,
|
| 60627 |
+
"grad_norm": 0.21211007237434387,
|
| 60628 |
+
"learning_rate": 2.7198619052202545e-05,
|
| 60629 |
+
"loss": 0.6632,
|
| 60630 |
+
"step": 8660
|
| 60631 |
+
},
|
| 60632 |
+
{
|
| 60633 |
+
"epoch": 9.864957264957265,
|
| 60634 |
+
"grad_norm": 0.24838034808635712,
|
| 60635 |
+
"learning_rate": 2.719397788559786e-05,
|
| 60636 |
+
"loss": 0.7353,
|
| 60637 |
+
"step": 8661
|
| 60638 |
+
},
|
| 60639 |
+
{
|
| 60640 |
+
"epoch": 9.866096866096866,
|
| 60641 |
+
"grad_norm": 0.19553515315055847,
|
| 60642 |
+
"learning_rate": 2.7189336642790297e-05,
|
| 60643 |
+
"loss": 0.7358,
|
| 60644 |
+
"step": 8662
|
| 60645 |
+
},
|
| 60646 |
+
{
|
| 60647 |
+
"epoch": 9.867236467236467,
|
| 60648 |
+
"grad_norm": 0.20539981126785278,
|
| 60649 |
+
"learning_rate": 2.7184695323941046e-05,
|
| 60650 |
+
"loss": 0.7182,
|
| 60651 |
+
"step": 8663
|
| 60652 |
+
},
|
| 60653 |
+
{
|
| 60654 |
+
"epoch": 9.868376068376069,
|
| 60655 |
+
"grad_norm": 0.19742438197135925,
|
| 60656 |
+
"learning_rate": 2.718005392921132e-05,
|
| 60657 |
+
"loss": 0.8297,
|
| 60658 |
+
"step": 8664
|
| 60659 |
+
},
|
| 60660 |
+
{
|
| 60661 |
+
"epoch": 9.86951566951567,
|
| 60662 |
+
"grad_norm": 0.37122297286987305,
|
| 60663 |
+
"learning_rate": 2.7175412458762328e-05,
|
| 60664 |
+
"loss": 0.4323,
|
| 60665 |
+
"step": 8665
|
| 60666 |
+
},
|
| 60667 |
+
{
|
| 60668 |
+
"epoch": 9.87065527065527,
|
| 60669 |
+
"grad_norm": 0.17589843273162842,
|
| 60670 |
+
"learning_rate": 2.717077091275528e-05,
|
| 60671 |
+
"loss": 0.8281,
|
| 60672 |
+
"step": 8666
|
| 60673 |
+
},
|
| 60674 |
+
{
|
| 60675 |
+
"epoch": 9.871794871794872,
|
| 60676 |
+
"grad_norm": 0.15270763635635376,
|
| 60677 |
+
"learning_rate": 2.7166129291351382e-05,
|
| 60678 |
+
"loss": 0.7995,
|
| 60679 |
+
"step": 8667
|
| 60680 |
+
},
|
| 60681 |
+
{
|
| 60682 |
+
"epoch": 9.872934472934473,
|
| 60683 |
+
"grad_norm": 0.1615580916404724,
|
| 60684 |
+
"learning_rate": 2.7161487594711866e-05,
|
| 60685 |
+
"loss": 1.0074,
|
| 60686 |
+
"step": 8668
|
| 60687 |
+
},
|
| 60688 |
+
{
|
| 60689 |
+
"epoch": 9.874074074074073,
|
| 60690 |
+
"grad_norm": 0.1597990244626999,
|
| 60691 |
+
"learning_rate": 2.7156845822997934e-05,
|
| 60692 |
+
"loss": 1.0043,
|
| 60693 |
+
"step": 8669
|
| 60694 |
+
},
|
| 60695 |
+
{
|
| 60696 |
+
"epoch": 9.875213675213676,
|
| 60697 |
+
"grad_norm": 0.20243625342845917,
|
| 60698 |
+
"learning_rate": 2.715220397637082e-05,
|
| 60699 |
+
"loss": 0.802,
|
| 60700 |
+
"step": 8670
|
| 60701 |
+
},
|
| 60702 |
+
{
|
| 60703 |
+
"epoch": 9.876353276353276,
|
| 60704 |
+
"grad_norm": 0.20510946214199066,
|
| 60705 |
+
"learning_rate": 2.7147562054991737e-05,
|
| 60706 |
+
"loss": 0.7117,
|
| 60707 |
+
"step": 8671
|
| 60708 |
+
},
|
| 60709 |
+
{
|
| 60710 |
+
"epoch": 9.877492877492877,
|
| 60711 |
+
"grad_norm": 0.2172488123178482,
|
| 60712 |
+
"learning_rate": 2.714292005902192e-05,
|
| 60713 |
+
"loss": 0.7563,
|
| 60714 |
+
"step": 8672
|
| 60715 |
+
},
|
| 60716 |
+
{
|
| 60717 |
+
"epoch": 9.878632478632479,
|
| 60718 |
+
"grad_norm": 0.23654407262802124,
|
| 60719 |
+
"learning_rate": 2.71382779886226e-05,
|
| 60720 |
+
"loss": 0.7729,
|
| 60721 |
+
"step": 8673
|
| 60722 |
+
},
|
| 60723 |
+
{
|
| 60724 |
+
"epoch": 9.87977207977208,
|
| 60725 |
+
"grad_norm": 0.21040476858615875,
|
| 60726 |
+
"learning_rate": 2.713363584395501e-05,
|
| 60727 |
+
"loss": 0.7365,
|
| 60728 |
+
"step": 8674
|
| 60729 |
+
},
|
| 60730 |
+
{
|
| 60731 |
+
"epoch": 9.88091168091168,
|
| 60732 |
+
"grad_norm": 0.2197181135416031,
|
| 60733 |
+
"learning_rate": 2.7128993625180366e-05,
|
| 60734 |
+
"loss": 0.6031,
|
| 60735 |
+
"step": 8675
|
| 60736 |
+
},
|
| 60737 |
+
{
|
| 60738 |
+
"epoch": 9.882051282051282,
|
| 60739 |
+
"grad_norm": 0.20595000684261322,
|
| 60740 |
+
"learning_rate": 2.712435133245993e-05,
|
| 60741 |
+
"loss": 0.6825,
|
| 60742 |
+
"step": 8676
|
| 60743 |
+
},
|
| 60744 |
+
{
|
| 60745 |
+
"epoch": 9.883190883190883,
|
| 60746 |
+
"grad_norm": 0.24480144679546356,
|
| 60747 |
+
"learning_rate": 2.7119708965954925e-05,
|
| 60748 |
+
"loss": 0.4792,
|
| 60749 |
+
"step": 8677
|
| 60750 |
+
},
|
| 60751 |
+
{
|
| 60752 |
+
"epoch": 9.884330484330484,
|
| 60753 |
+
"grad_norm": 0.28222033381462097,
|
| 60754 |
+
"learning_rate": 2.71150665258266e-05,
|
| 60755 |
+
"loss": 0.4097,
|
| 60756 |
+
"step": 8678
|
| 60757 |
+
},
|
| 60758 |
+
{
|
| 60759 |
+
"epoch": 9.885470085470086,
|
| 60760 |
+
"grad_norm": 0.21712517738342285,
|
| 60761 |
+
"learning_rate": 2.7110424012236197e-05,
|
| 60762 |
+
"loss": 0.6584,
|
| 60763 |
+
"step": 8679
|
| 60764 |
+
},
|
| 60765 |
+
{
|
| 60766 |
+
"epoch": 9.886609686609686,
|
| 60767 |
+
"grad_norm": 0.24547608196735382,
|
| 60768 |
+
"learning_rate": 2.7105781425344966e-05,
|
| 60769 |
+
"loss": 0.7856,
|
| 60770 |
+
"step": 8680
|
| 60771 |
+
},
|
| 60772 |
+
{
|
| 60773 |
+
"epoch": 9.887749287749287,
|
| 60774 |
+
"grad_norm": 0.19895847141742706,
|
| 60775 |
+
"learning_rate": 2.7101138765314154e-05,
|
| 60776 |
+
"loss": 0.7386,
|
| 60777 |
+
"step": 8681
|
| 60778 |
+
},
|
| 60779 |
+
{
|
| 60780 |
+
"epoch": 9.88888888888889,
|
| 60781 |
+
"grad_norm": 0.19437870383262634,
|
| 60782 |
+
"learning_rate": 2.7096496032305013e-05,
|
| 60783 |
+
"loss": 0.989,
|
| 60784 |
+
"step": 8682
|
| 60785 |
+
},
|
| 60786 |
+
{
|
| 60787 |
+
"epoch": 9.89002849002849,
|
| 60788 |
+
"grad_norm": 0.22372710704803467,
|
| 60789 |
+
"learning_rate": 2.7091853226478804e-05,
|
| 60790 |
+
"loss": 0.6882,
|
| 60791 |
+
"step": 8683
|
| 60792 |
+
},
|
| 60793 |
+
{
|
| 60794 |
+
"epoch": 9.89116809116809,
|
| 60795 |
+
"grad_norm": 0.2139015793800354,
|
| 60796 |
+
"learning_rate": 2.7087210347996772e-05,
|
| 60797 |
+
"loss": 0.7785,
|
| 60798 |
+
"step": 8684
|
| 60799 |
+
},
|
| 60800 |
+
{
|
| 60801 |
+
"epoch": 9.892307692307693,
|
| 60802 |
+
"grad_norm": 0.23976415395736694,
|
| 60803 |
+
"learning_rate": 2.7082567397020192e-05,
|
| 60804 |
+
"loss": 0.6503,
|
| 60805 |
+
"step": 8685
|
| 60806 |
+
},
|
| 60807 |
+
{
|
| 60808 |
+
"epoch": 9.893447293447293,
|
| 60809 |
+
"grad_norm": 0.2095179259777069,
|
| 60810 |
+
"learning_rate": 2.7077924373710316e-05,
|
| 60811 |
+
"loss": 0.7618,
|
| 60812 |
+
"step": 8686
|
| 60813 |
+
},
|
| 60814 |
+
{
|
| 60815 |
+
"epoch": 9.894586894586894,
|
| 60816 |
+
"grad_norm": 0.2666536271572113,
|
| 60817 |
+
"learning_rate": 2.7073281278228417e-05,
|
| 60818 |
+
"loss": 0.3682,
|
| 60819 |
+
"step": 8687
|
| 60820 |
+
},
|
| 60821 |
+
{
|
| 60822 |
+
"epoch": 9.895726495726496,
|
| 60823 |
+
"grad_norm": 0.21089398860931396,
|
| 60824 |
+
"learning_rate": 2.7068638110735745e-05,
|
| 60825 |
+
"loss": 0.9049,
|
| 60826 |
+
"step": 8688
|
| 60827 |
+
},
|
| 60828 |
+
{
|
| 60829 |
+
"epoch": 9.896866096866097,
|
| 60830 |
+
"grad_norm": 0.1931055635213852,
|
| 60831 |
+
"learning_rate": 2.7063994871393595e-05,
|
| 60832 |
+
"loss": 0.6098,
|
| 60833 |
+
"step": 8689
|
| 60834 |
+
},
|
| 60835 |
+
{
|
| 60836 |
+
"epoch": 9.898005698005697,
|
| 60837 |
+
"grad_norm": 0.18896043300628662,
|
| 60838 |
+
"learning_rate": 2.705935156036322e-05,
|
| 60839 |
+
"loss": 0.8139,
|
| 60840 |
+
"step": 8690
|
| 60841 |
+
},
|
| 60842 |
+
{
|
| 60843 |
+
"epoch": 9.8991452991453,
|
| 60844 |
+
"grad_norm": 0.2181152105331421,
|
| 60845 |
+
"learning_rate": 2.705470817780591e-05,
|
| 60846 |
+
"loss": 0.5171,
|
| 60847 |
+
"step": 8691
|
| 60848 |
+
},
|
| 60849 |
+
{
|
| 60850 |
+
"epoch": 9.9002849002849,
|
| 60851 |
+
"grad_norm": 0.15674111247062683,
|
| 60852 |
+
"learning_rate": 2.7050064723882927e-05,
|
| 60853 |
+
"loss": 0.8819,
|
| 60854 |
+
"step": 8692
|
| 60855 |
+
},
|
| 60856 |
+
{
|
| 60857 |
+
"epoch": 9.9014245014245,
|
| 60858 |
+
"grad_norm": 0.24580217897891998,
|
| 60859 |
+
"learning_rate": 2.7045421198755567e-05,
|
| 60860 |
+
"loss": 0.6895,
|
| 60861 |
+
"step": 8693
|
| 60862 |
+
},
|
| 60863 |
+
{
|
| 60864 |
+
"epoch": 9.902564102564103,
|
| 60865 |
+
"grad_norm": 0.2359219491481781,
|
| 60866 |
+
"learning_rate": 2.7040777602585098e-05,
|
| 60867 |
+
"loss": 0.7899,
|
| 60868 |
+
"step": 8694
|
| 60869 |
+
},
|
| 60870 |
+
{
|
| 60871 |
+
"epoch": 9.903703703703703,
|
| 60872 |
+
"grad_norm": 0.1815393567085266,
|
| 60873 |
+
"learning_rate": 2.703613393553281e-05,
|
| 60874 |
+
"loss": 0.7982,
|
| 60875 |
+
"step": 8695
|
| 60876 |
+
},
|
| 60877 |
+
{
|
| 60878 |
+
"epoch": 9.904843304843304,
|
| 60879 |
+
"grad_norm": 0.20599913597106934,
|
| 60880 |
+
"learning_rate": 2.7031490197759997e-05,
|
| 60881 |
+
"loss": 0.6765,
|
| 60882 |
+
"step": 8696
|
| 60883 |
+
},
|
| 60884 |
+
{
|
| 60885 |
+
"epoch": 9.905982905982906,
|
| 60886 |
+
"grad_norm": 0.22677111625671387,
|
| 60887 |
+
"learning_rate": 2.7026846389427934e-05,
|
| 60888 |
+
"loss": 0.7334,
|
| 60889 |
+
"step": 8697
|
| 60890 |
+
},
|
| 60891 |
+
{
|
| 60892 |
+
"epoch": 9.907122507122507,
|
| 60893 |
+
"grad_norm": 0.1993129551410675,
|
| 60894 |
+
"learning_rate": 2.702220251069793e-05,
|
| 60895 |
+
"loss": 0.821,
|
| 60896 |
+
"step": 8698
|
| 60897 |
+
},
|
| 60898 |
+
{
|
| 60899 |
+
"epoch": 9.908262108262107,
|
| 60900 |
+
"grad_norm": 0.2008620649576187,
|
| 60901 |
+
"learning_rate": 2.701755856173126e-05,
|
| 60902 |
+
"loss": 0.786,
|
| 60903 |
+
"step": 8699
|
| 60904 |
+
},
|
| 60905 |
+
{
|
| 60906 |
+
"epoch": 9.90940170940171,
|
| 60907 |
+
"grad_norm": 0.31846582889556885,
|
| 60908 |
+
"learning_rate": 2.7012914542689244e-05,
|
| 60909 |
+
"loss": 0.7542,
|
| 60910 |
+
"step": 8700
|
| 60911 |
}
|
| 60912 |
],
|
| 60913 |
"logging_steps": 1,
|
|
|
|
| 60927 |
"attributes": {}
|
| 60928 |
}
|
| 60929 |
},
|
| 60930 |
+
"total_flos": 4.864655208685437e+19,
|
| 60931 |
"train_batch_size": 8,
|
| 60932 |
"trial_name": null,
|
| 60933 |
"trial_params": null
|