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 17100, 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 sha256:6da2943ace62702c36e7609317ca55716c02251d2d609ca4fd9a21b6f70857f9
|
| 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 sha256:8d1c7ef64f8ba4cd67854066fb11332ce05ea653504083f9c525ab7e918bb270
|
| 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:f8f97c1f65821251e06de1607966a6606e98b47202dfa63fdf051782f2be0415
|
| 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": 19.
|
| 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,
|
|
@@ -117608,6 +117608,2106 @@
|
|
| 117608 |
"learning_rate": 2.510096449981569e-07,
|
| 117609 |
"loss": 0.4266,
|
| 117610 |
"step": 16800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117611 |
}
|
| 117612 |
],
|
| 117613 |
"logging_steps": 1,
|
|
@@ -117627,7 +119727,7 @@
|
|
| 117627 |
"attributes": {}
|
| 117628 |
}
|
| 117629 |
},
|
| 117630 |
-
"total_flos": 9.
|
| 117631 |
"train_batch_size": 8,
|
| 117632 |
"trial_name": null,
|
| 117633 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.476353276353276,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 17100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 117608 |
"learning_rate": 2.510096449981569e-07,
|
| 117609 |
"loss": 0.4266,
|
| 117610 |
"step": 16800
|
| 117611 |
+
},
|
| 117612 |
+
{
|
| 117613 |
+
"epoch": 19.135612535612534,
|
| 117614 |
+
"grad_norm": 0.18098628520965576,
|
| 117615 |
+
"learning_rate": 2.503514972459653e-07,
|
| 117616 |
+
"loss": 0.6132,
|
| 117617 |
+
"step": 16801
|
| 117618 |
+
},
|
| 117619 |
+
{
|
| 117620 |
+
"epoch": 19.136752136752136,
|
| 117621 |
+
"grad_norm": 0.18563774228096008,
|
| 117622 |
+
"learning_rate": 2.496942091171267e-07,
|
| 117623 |
+
"loss": 0.6306,
|
| 117624 |
+
"step": 16802
|
| 117625 |
+
},
|
| 117626 |
+
{
|
| 117627 |
+
"epoch": 19.13789173789174,
|
| 117628 |
+
"grad_norm": 0.23148155212402344,
|
| 117629 |
+
"learning_rate": 2.490377806344729e-07,
|
| 117630 |
+
"loss": 0.5569,
|
| 117631 |
+
"step": 16803
|
| 117632 |
+
},
|
| 117633 |
+
{
|
| 117634 |
+
"epoch": 19.139031339031337,
|
| 117635 |
+
"grad_norm": 0.1684509962797165,
|
| 117636 |
+
"learning_rate": 2.4838221182080233e-07,
|
| 117637 |
+
"loss": 0.7662,
|
| 117638 |
+
"step": 16804
|
| 117639 |
+
},
|
| 117640 |
+
{
|
| 117641 |
+
"epoch": 19.14017094017094,
|
| 117642 |
+
"grad_norm": 0.20798934996128082,
|
| 117643 |
+
"learning_rate": 2.477275026988829e-07,
|
| 117644 |
+
"loss": 0.7302,
|
| 117645 |
+
"step": 16805
|
| 117646 |
+
},
|
| 117647 |
+
{
|
| 117648 |
+
"epoch": 19.141310541310542,
|
| 117649 |
+
"grad_norm": 0.1976047158241272,
|
| 117650 |
+
"learning_rate": 2.470736532914575e-07,
|
| 117651 |
+
"loss": 0.5272,
|
| 117652 |
+
"step": 16806
|
| 117653 |
+
},
|
| 117654 |
+
{
|
| 117655 |
+
"epoch": 19.14245014245014,
|
| 117656 |
+
"grad_norm": 0.16313964128494263,
|
| 117657 |
+
"learning_rate": 2.4642066362123575e-07,
|
| 117658 |
+
"loss": 0.9377,
|
| 117659 |
+
"step": 16807
|
| 117660 |
+
},
|
| 117661 |
+
{
|
| 117662 |
+
"epoch": 19.143589743589743,
|
| 117663 |
+
"grad_norm": 0.1853342205286026,
|
| 117664 |
+
"learning_rate": 2.457685337108995e-07,
|
| 117665 |
+
"loss": 0.6412,
|
| 117666 |
+
"step": 16808
|
| 117667 |
+
},
|
| 117668 |
+
{
|
| 117669 |
+
"epoch": 19.144729344729345,
|
| 117670 |
+
"grad_norm": 0.2047988474369049,
|
| 117671 |
+
"learning_rate": 2.4511726358309175e-07,
|
| 117672 |
+
"loss": 0.5575,
|
| 117673 |
+
"step": 16809
|
| 117674 |
+
},
|
| 117675 |
+
{
|
| 117676 |
+
"epoch": 19.145868945868944,
|
| 117677 |
+
"grad_norm": 0.1794224977493286,
|
| 117678 |
+
"learning_rate": 2.4446685326043885e-07,
|
| 117679 |
+
"loss": 0.3465,
|
| 117680 |
+
"step": 16810
|
| 117681 |
+
},
|
| 117682 |
+
{
|
| 117683 |
+
"epoch": 19.147008547008546,
|
| 117684 |
+
"grad_norm": 0.201945498585701,
|
| 117685 |
+
"learning_rate": 2.4381730276553104e-07,
|
| 117686 |
+
"loss": 0.5762,
|
| 117687 |
+
"step": 16811
|
| 117688 |
+
},
|
| 117689 |
+
{
|
| 117690 |
+
"epoch": 19.14814814814815,
|
| 117691 |
+
"grad_norm": 0.21642912924289703,
|
| 117692 |
+
"learning_rate": 2.431686121209281e-07,
|
| 117693 |
+
"loss": 0.5324,
|
| 117694 |
+
"step": 16812
|
| 117695 |
+
},
|
| 117696 |
+
{
|
| 117697 |
+
"epoch": 19.149287749287748,
|
| 117698 |
+
"grad_norm": 0.19446443021297455,
|
| 117699 |
+
"learning_rate": 2.42520781349162e-07,
|
| 117700 |
+
"loss": 0.825,
|
| 117701 |
+
"step": 16813
|
| 117702 |
+
},
|
| 117703 |
+
{
|
| 117704 |
+
"epoch": 19.15042735042735,
|
| 117705 |
+
"grad_norm": 0.19116437435150146,
|
| 117706 |
+
"learning_rate": 2.418738104727286e-07,
|
| 117707 |
+
"loss": 0.4555,
|
| 117708 |
+
"step": 16814
|
| 117709 |
+
},
|
| 117710 |
+
{
|
| 117711 |
+
"epoch": 19.151566951566952,
|
| 117712 |
+
"grad_norm": 0.1666492372751236,
|
| 117713 |
+
"learning_rate": 2.412276995141072e-07,
|
| 117714 |
+
"loss": 0.8135,
|
| 117715 |
+
"step": 16815
|
| 117716 |
+
},
|
| 117717 |
+
{
|
| 117718 |
+
"epoch": 19.15270655270655,
|
| 117719 |
+
"grad_norm": 0.20728255808353424,
|
| 117720 |
+
"learning_rate": 2.4058244849573253e-07,
|
| 117721 |
+
"loss": 0.5597,
|
| 117722 |
+
"step": 16816
|
| 117723 |
+
},
|
| 117724 |
+
{
|
| 117725 |
+
"epoch": 19.153846153846153,
|
| 117726 |
+
"grad_norm": 0.15866397321224213,
|
| 117727 |
+
"learning_rate": 2.399380574400173e-07,
|
| 117728 |
+
"loss": 0.6154,
|
| 117729 |
+
"step": 16817
|
| 117730 |
+
},
|
| 117731 |
+
{
|
| 117732 |
+
"epoch": 19.154985754985756,
|
| 117733 |
+
"grad_norm": 0.19906434416770935,
|
| 117734 |
+
"learning_rate": 2.3929452636934356e-07,
|
| 117735 |
+
"loss": 0.6288,
|
| 117736 |
+
"step": 16818
|
| 117737 |
+
},
|
| 117738 |
+
{
|
| 117739 |
+
"epoch": 19.156125356125354,
|
| 117740 |
+
"grad_norm": 0.19023805856704712,
|
| 117741 |
+
"learning_rate": 2.3865185530606296e-07,
|
| 117742 |
+
"loss": 0.6966,
|
| 117743 |
+
"step": 16819
|
| 117744 |
+
},
|
| 117745 |
+
{
|
| 117746 |
+
"epoch": 19.157264957264957,
|
| 117747 |
+
"grad_norm": 0.19843755662441254,
|
| 117748 |
+
"learning_rate": 2.3801004427250196e-07,
|
| 117749 |
+
"loss": 0.7683,
|
| 117750 |
+
"step": 16820
|
| 117751 |
+
},
|
| 117752 |
+
{
|
| 117753 |
+
"epoch": 19.15840455840456,
|
| 117754 |
+
"grad_norm": 0.18582892417907715,
|
| 117755 |
+
"learning_rate": 2.373690932909428e-07,
|
| 117756 |
+
"loss": 0.4512,
|
| 117757 |
+
"step": 16821
|
| 117758 |
+
},
|
| 117759 |
+
{
|
| 117760 |
+
"epoch": 19.159544159544158,
|
| 117761 |
+
"grad_norm": 0.2121107578277588,
|
| 117762 |
+
"learning_rate": 2.3672900238365382e-07,
|
| 117763 |
+
"loss": 0.6215,
|
| 117764 |
+
"step": 16822
|
| 117765 |
+
},
|
| 117766 |
+
{
|
| 117767 |
+
"epoch": 19.16068376068376,
|
| 117768 |
+
"grad_norm": 0.19985079765319824,
|
| 117769 |
+
"learning_rate": 2.3608977157286716e-07,
|
| 117770 |
+
"loss": 0.7261,
|
| 117771 |
+
"step": 16823
|
| 117772 |
+
},
|
| 117773 |
+
{
|
| 117774 |
+
"epoch": 19.161823361823362,
|
| 117775 |
+
"grad_norm": 0.21276366710662842,
|
| 117776 |
+
"learning_rate": 2.3545140088078454e-07,
|
| 117777 |
+
"loss": 0.8637,
|
| 117778 |
+
"step": 16824
|
| 117779 |
+
},
|
| 117780 |
+
{
|
| 117781 |
+
"epoch": 19.162962962962965,
|
| 117782 |
+
"grad_norm": 0.22821033000946045,
|
| 117783 |
+
"learning_rate": 2.3481389032957435e-07,
|
| 117784 |
+
"loss": 0.6965,
|
| 117785 |
+
"step": 16825
|
| 117786 |
+
},
|
| 117787 |
+
{
|
| 117788 |
+
"epoch": 19.164102564102564,
|
| 117789 |
+
"grad_norm": 0.22390399873256683,
|
| 117790 |
+
"learning_rate": 2.3417723994138552e-07,
|
| 117791 |
+
"loss": 0.6692,
|
| 117792 |
+
"step": 16826
|
| 117793 |
+
},
|
| 117794 |
+
{
|
| 117795 |
+
"epoch": 19.165242165242166,
|
| 117796 |
+
"grad_norm": 0.17491723597049713,
|
| 117797 |
+
"learning_rate": 2.3354144973832537e-07,
|
| 117798 |
+
"loss": 0.684,
|
| 117799 |
+
"step": 16827
|
| 117800 |
+
},
|
| 117801 |
+
{
|
| 117802 |
+
"epoch": 19.166381766381768,
|
| 117803 |
+
"grad_norm": 0.21670633554458618,
|
| 117804 |
+
"learning_rate": 2.3290651974247902e-07,
|
| 117805 |
+
"loss": 0.4624,
|
| 117806 |
+
"step": 16828
|
| 117807 |
+
},
|
| 117808 |
+
{
|
| 117809 |
+
"epoch": 19.167521367521367,
|
| 117810 |
+
"grad_norm": 0.20747022330760956,
|
| 117811 |
+
"learning_rate": 2.3227244997589825e-07,
|
| 117812 |
+
"loss": 0.7757,
|
| 117813 |
+
"step": 16829
|
| 117814 |
+
},
|
| 117815 |
+
{
|
| 117816 |
+
"epoch": 19.16866096866097,
|
| 117817 |
+
"grad_norm": 0.16009530425071716,
|
| 117818 |
+
"learning_rate": 2.3163924046060714e-07,
|
| 117819 |
+
"loss": 0.8162,
|
| 117820 |
+
"step": 16830
|
| 117821 |
+
},
|
| 117822 |
+
{
|
| 117823 |
+
"epoch": 19.16980056980057,
|
| 117824 |
+
"grad_norm": 0.2176835536956787,
|
| 117825 |
+
"learning_rate": 2.310068912185992e-07,
|
| 117826 |
+
"loss": 0.4587,
|
| 117827 |
+
"step": 16831
|
| 117828 |
+
},
|
| 117829 |
+
{
|
| 117830 |
+
"epoch": 19.17094017094017,
|
| 117831 |
+
"grad_norm": 0.16527660191059113,
|
| 117832 |
+
"learning_rate": 2.303754022718374e-07,
|
| 117833 |
+
"loss": 0.9056,
|
| 117834 |
+
"step": 16832
|
| 117835 |
+
},
|
| 117836 |
+
{
|
| 117837 |
+
"epoch": 19.172079772079773,
|
| 117838 |
+
"grad_norm": 0.19874820113182068,
|
| 117839 |
+
"learning_rate": 2.2974477364225423e-07,
|
| 117840 |
+
"loss": 0.701,
|
| 117841 |
+
"step": 16833
|
| 117842 |
+
},
|
| 117843 |
+
{
|
| 117844 |
+
"epoch": 19.173219373219375,
|
| 117845 |
+
"grad_norm": 0.18765230476856232,
|
| 117846 |
+
"learning_rate": 2.2911500535175157e-07,
|
| 117847 |
+
"loss": 0.4855,
|
| 117848 |
+
"step": 16834
|
| 117849 |
+
},
|
| 117850 |
+
{
|
| 117851 |
+
"epoch": 19.174358974358974,
|
| 117852 |
+
"grad_norm": 0.21307937800884247,
|
| 117853 |
+
"learning_rate": 2.2848609742220916e-07,
|
| 117854 |
+
"loss": 0.5144,
|
| 117855 |
+
"step": 16835
|
| 117856 |
+
},
|
| 117857 |
+
{
|
| 117858 |
+
"epoch": 19.175498575498576,
|
| 117859 |
+
"grad_norm": 0.1848912090063095,
|
| 117860 |
+
"learning_rate": 2.2785804987546233e-07,
|
| 117861 |
+
"loss": 0.6323,
|
| 117862 |
+
"step": 16836
|
| 117863 |
+
},
|
| 117864 |
+
{
|
| 117865 |
+
"epoch": 19.17663817663818,
|
| 117866 |
+
"grad_norm": 0.19322006404399872,
|
| 117867 |
+
"learning_rate": 2.2723086273332971e-07,
|
| 117868 |
+
"loss": 0.6738,
|
| 117869 |
+
"step": 16837
|
| 117870 |
+
},
|
| 117871 |
+
{
|
| 117872 |
+
"epoch": 19.177777777777777,
|
| 117873 |
+
"grad_norm": 0.18617932498455048,
|
| 117874 |
+
"learning_rate": 2.2660453601759668e-07,
|
| 117875 |
+
"loss": 0.7185,
|
| 117876 |
+
"step": 16838
|
| 117877 |
+
},
|
| 117878 |
+
{
|
| 117879 |
+
"epoch": 19.17891737891738,
|
| 117880 |
+
"grad_norm": 0.21446798741817474,
|
| 117881 |
+
"learning_rate": 2.259790697500125e-07,
|
| 117882 |
+
"loss": 0.6248,
|
| 117883 |
+
"step": 16839
|
| 117884 |
+
},
|
| 117885 |
+
{
|
| 117886 |
+
"epoch": 19.180056980056982,
|
| 117887 |
+
"grad_norm": 0.1776348054409027,
|
| 117888 |
+
"learning_rate": 2.2535446395230697e-07,
|
| 117889 |
+
"loss": 0.8214,
|
| 117890 |
+
"step": 16840
|
| 117891 |
+
},
|
| 117892 |
+
{
|
| 117893 |
+
"epoch": 19.18119658119658,
|
| 117894 |
+
"grad_norm": 0.25483688712120056,
|
| 117895 |
+
"learning_rate": 2.2473071864616836e-07,
|
| 117896 |
+
"loss": 0.5343,
|
| 117897 |
+
"step": 16841
|
| 117898 |
+
},
|
| 117899 |
+
{
|
| 117900 |
+
"epoch": 19.182336182336183,
|
| 117901 |
+
"grad_norm": 0.18243196606636047,
|
| 117902 |
+
"learning_rate": 2.2410783385326816e-07,
|
| 117903 |
+
"loss": 0.8342,
|
| 117904 |
+
"step": 16842
|
| 117905 |
+
},
|
| 117906 |
+
{
|
| 117907 |
+
"epoch": 19.183475783475785,
|
| 117908 |
+
"grad_norm": 0.2042977213859558,
|
| 117909 |
+
"learning_rate": 2.2348580959523357e-07,
|
| 117910 |
+
"loss": 0.5783,
|
| 117911 |
+
"step": 16843
|
| 117912 |
+
},
|
| 117913 |
+
{
|
| 117914 |
+
"epoch": 19.184615384615384,
|
| 117915 |
+
"grad_norm": 0.19970044493675232,
|
| 117916 |
+
"learning_rate": 2.2286464589367507e-07,
|
| 117917 |
+
"loss": 0.6981,
|
| 117918 |
+
"step": 16844
|
| 117919 |
+
},
|
| 117920 |
+
{
|
| 117921 |
+
"epoch": 19.185754985754986,
|
| 117922 |
+
"grad_norm": 0.17871545255184174,
|
| 117923 |
+
"learning_rate": 2.222443427701615e-07,
|
| 117924 |
+
"loss": 0.625,
|
| 117925 |
+
"step": 16845
|
| 117926 |
+
},
|
| 117927 |
+
{
|
| 117928 |
+
"epoch": 19.18689458689459,
|
| 117929 |
+
"grad_norm": 0.2101234495639801,
|
| 117930 |
+
"learning_rate": 2.2162490024624506e-07,
|
| 117931 |
+
"loss": 0.6554,
|
| 117932 |
+
"step": 16846
|
| 117933 |
+
},
|
| 117934 |
+
{
|
| 117935 |
+
"epoch": 19.188034188034187,
|
| 117936 |
+
"grad_norm": 0.15810169279575348,
|
| 117937 |
+
"learning_rate": 2.2100631834343356e-07,
|
| 117938 |
+
"loss": 0.8116,
|
| 117939 |
+
"step": 16847
|
| 117940 |
+
},
|
| 117941 |
+
{
|
| 117942 |
+
"epoch": 19.18917378917379,
|
| 117943 |
+
"grad_norm": 0.24820293486118317,
|
| 117944 |
+
"learning_rate": 2.2038859708321535e-07,
|
| 117945 |
+
"loss": 0.4985,
|
| 117946 |
+
"step": 16848
|
| 117947 |
+
},
|
| 117948 |
+
{
|
| 117949 |
+
"epoch": 19.190313390313392,
|
| 117950 |
+
"grad_norm": 0.17996817827224731,
|
| 117951 |
+
"learning_rate": 2.1977173648704552e-07,
|
| 117952 |
+
"loss": 0.6283,
|
| 117953 |
+
"step": 16849
|
| 117954 |
+
},
|
| 117955 |
+
{
|
| 117956 |
+
"epoch": 19.19145299145299,
|
| 117957 |
+
"grad_norm": 0.18732857704162598,
|
| 117958 |
+
"learning_rate": 2.191557365763486e-07,
|
| 117959 |
+
"loss": 0.6905,
|
| 117960 |
+
"step": 16850
|
| 117961 |
+
},
|
| 117962 |
+
{
|
| 117963 |
+
"epoch": 19.192592592592593,
|
| 117964 |
+
"grad_norm": 0.16504479944705963,
|
| 117965 |
+
"learning_rate": 2.185405973725213e-07,
|
| 117966 |
+
"loss": 0.75,
|
| 117967 |
+
"step": 16851
|
| 117968 |
+
},
|
| 117969 |
+
{
|
| 117970 |
+
"epoch": 19.193732193732195,
|
| 117971 |
+
"grad_norm": 0.2545555830001831,
|
| 117972 |
+
"learning_rate": 2.1792631889692994e-07,
|
| 117973 |
+
"loss": 0.5674,
|
| 117974 |
+
"step": 16852
|
| 117975 |
+
},
|
| 117976 |
+
{
|
| 117977 |
+
"epoch": 19.194871794871794,
|
| 117978 |
+
"grad_norm": 0.18723373115062714,
|
| 117979 |
+
"learning_rate": 2.1731290117090742e-07,
|
| 117980 |
+
"loss": 0.7629,
|
| 117981 |
+
"step": 16853
|
| 117982 |
+
},
|
| 117983 |
+
{
|
| 117984 |
+
"epoch": 19.196011396011396,
|
| 117985 |
+
"grad_norm": 0.1995868682861328,
|
| 117986 |
+
"learning_rate": 2.167003442157589e-07,
|
| 117987 |
+
"loss": 0.5315,
|
| 117988 |
+
"step": 16854
|
| 117989 |
+
},
|
| 117990 |
+
{
|
| 117991 |
+
"epoch": 19.197150997151,
|
| 117992 |
+
"grad_norm": 0.18103499710559845,
|
| 117993 |
+
"learning_rate": 2.1608864805276464e-07,
|
| 117994 |
+
"loss": 0.5966,
|
| 117995 |
+
"step": 16855
|
| 117996 |
+
},
|
| 117997 |
+
{
|
| 117998 |
+
"epoch": 19.198290598290598,
|
| 117999 |
+
"grad_norm": 0.19257839024066925,
|
| 118000 |
+
"learning_rate": 2.154778127031659e-07,
|
| 118001 |
+
"loss": 0.6129,
|
| 118002 |
+
"step": 16856
|
| 118003 |
+
},
|
| 118004 |
+
{
|
| 118005 |
+
"epoch": 19.1994301994302,
|
| 118006 |
+
"grad_norm": 0.22365933656692505,
|
| 118007 |
+
"learning_rate": 2.148678381881819e-07,
|
| 118008 |
+
"loss": 0.6032,
|
| 118009 |
+
"step": 16857
|
| 118010 |
+
},
|
| 118011 |
+
{
|
| 118012 |
+
"epoch": 19.200569800569802,
|
| 118013 |
+
"grad_norm": 0.16736818850040436,
|
| 118014 |
+
"learning_rate": 2.1425872452899565e-07,
|
| 118015 |
+
"loss": 0.8442,
|
| 118016 |
+
"step": 16858
|
| 118017 |
+
},
|
| 118018 |
+
{
|
| 118019 |
+
"epoch": 19.2017094017094,
|
| 118020 |
+
"grad_norm": 0.1844698041677475,
|
| 118021 |
+
"learning_rate": 2.1365047174676524e-07,
|
| 118022 |
+
"loss": 0.6009,
|
| 118023 |
+
"step": 16859
|
| 118024 |
+
},
|
| 118025 |
+
{
|
| 118026 |
+
"epoch": 19.202849002849003,
|
| 118027 |
+
"grad_norm": 0.19384139776229858,
|
| 118028 |
+
"learning_rate": 2.1304307986261262e-07,
|
| 118029 |
+
"loss": 0.6999,
|
| 118030 |
+
"step": 16860
|
| 118031 |
+
},
|
| 118032 |
+
{
|
| 118033 |
+
"epoch": 19.203988603988606,
|
| 118034 |
+
"grad_norm": 0.1743377447128296,
|
| 118035 |
+
"learning_rate": 2.1243654889764596e-07,
|
| 118036 |
+
"loss": 0.8152,
|
| 118037 |
+
"step": 16861
|
| 118038 |
+
},
|
| 118039 |
+
{
|
| 118040 |
+
"epoch": 19.205128205128204,
|
| 118041 |
+
"grad_norm": 0.15852127969264984,
|
| 118042 |
+
"learning_rate": 2.1183087887291787e-07,
|
| 118043 |
+
"loss": 0.4292,
|
| 118044 |
+
"step": 16862
|
| 118045 |
+
},
|
| 118046 |
+
{
|
| 118047 |
+
"epoch": 19.206267806267807,
|
| 118048 |
+
"grad_norm": 0.2069716453552246,
|
| 118049 |
+
"learning_rate": 2.1122606980947535e-07,
|
| 118050 |
+
"loss": 0.7713,
|
| 118051 |
+
"step": 16863
|
| 118052 |
+
},
|
| 118053 |
+
{
|
| 118054 |
+
"epoch": 19.20740740740741,
|
| 118055 |
+
"grad_norm": 0.27197206020355225,
|
| 118056 |
+
"learning_rate": 2.106221217283183e-07,
|
| 118057 |
+
"loss": 0.4657,
|
| 118058 |
+
"step": 16864
|
| 118059 |
+
},
|
| 118060 |
+
{
|
| 118061 |
+
"epoch": 19.208547008547008,
|
| 118062 |
+
"grad_norm": 0.20752044022083282,
|
| 118063 |
+
"learning_rate": 2.1001903465042716e-07,
|
| 118064 |
+
"loss": 0.4611,
|
| 118065 |
+
"step": 16865
|
| 118066 |
+
},
|
| 118067 |
+
{
|
| 118068 |
+
"epoch": 19.20968660968661,
|
| 118069 |
+
"grad_norm": 0.18452784419059753,
|
| 118070 |
+
"learning_rate": 2.0941680859674627e-07,
|
| 118071 |
+
"loss": 0.59,
|
| 118072 |
+
"step": 16866
|
| 118073 |
+
},
|
| 118074 |
+
{
|
| 118075 |
+
"epoch": 19.210826210826212,
|
| 118076 |
+
"grad_norm": 0.20244835317134857,
|
| 118077 |
+
"learning_rate": 2.0881544358819506e-07,
|
| 118078 |
+
"loss": 0.6333,
|
| 118079 |
+
"step": 16867
|
| 118080 |
+
},
|
| 118081 |
+
{
|
| 118082 |
+
"epoch": 19.21196581196581,
|
| 118083 |
+
"grad_norm": 0.18190540373325348,
|
| 118084 |
+
"learning_rate": 2.0821493964565953e-07,
|
| 118085 |
+
"loss": 0.8249,
|
| 118086 |
+
"step": 16868
|
| 118087 |
+
},
|
| 118088 |
+
{
|
| 118089 |
+
"epoch": 19.213105413105414,
|
| 118090 |
+
"grad_norm": 0.1976470798254013,
|
| 118091 |
+
"learning_rate": 2.0761529678999802e-07,
|
| 118092 |
+
"loss": 0.4892,
|
| 118093 |
+
"step": 16869
|
| 118094 |
+
},
|
| 118095 |
+
{
|
| 118096 |
+
"epoch": 19.214245014245016,
|
| 118097 |
+
"grad_norm": 0.21269537508487701,
|
| 118098 |
+
"learning_rate": 2.0701651504203557e-07,
|
| 118099 |
+
"loss": 0.8091,
|
| 118100 |
+
"step": 16870
|
| 118101 |
+
},
|
| 118102 |
+
{
|
| 118103 |
+
"epoch": 19.215384615384615,
|
| 118104 |
+
"grad_norm": 0.1921021044254303,
|
| 118105 |
+
"learning_rate": 2.064185944225666e-07,
|
| 118106 |
+
"loss": 0.7302,
|
| 118107 |
+
"step": 16871
|
| 118108 |
+
},
|
| 118109 |
+
{
|
| 118110 |
+
"epoch": 19.216524216524217,
|
| 118111 |
+
"grad_norm": 0.22277995944023132,
|
| 118112 |
+
"learning_rate": 2.05821534952369e-07,
|
| 118113 |
+
"loss": 0.7242,
|
| 118114 |
+
"step": 16872
|
| 118115 |
+
},
|
| 118116 |
+
{
|
| 118117 |
+
"epoch": 19.21766381766382,
|
| 118118 |
+
"grad_norm": 0.23242759704589844,
|
| 118119 |
+
"learning_rate": 2.052253366521706e-07,
|
| 118120 |
+
"loss": 0.7776,
|
| 118121 |
+
"step": 16873
|
| 118122 |
+
},
|
| 118123 |
+
{
|
| 118124 |
+
"epoch": 19.218803418803418,
|
| 118125 |
+
"grad_norm": 0.20705784857273102,
|
| 118126 |
+
"learning_rate": 2.0462999954267982e-07,
|
| 118127 |
+
"loss": 0.6455,
|
| 118128 |
+
"step": 16874
|
| 118129 |
+
},
|
| 118130 |
+
{
|
| 118131 |
+
"epoch": 19.21994301994302,
|
| 118132 |
+
"grad_norm": 0.2073516994714737,
|
| 118133 |
+
"learning_rate": 2.0403552364458011e-07,
|
| 118134 |
+
"loss": 0.6994,
|
| 118135 |
+
"step": 16875
|
| 118136 |
+
},
|
| 118137 |
+
{
|
| 118138 |
+
"epoch": 19.221082621082623,
|
| 118139 |
+
"grad_norm": 0.1903194934129715,
|
| 118140 |
+
"learning_rate": 2.034419089785161e-07,
|
| 118141 |
+
"loss": 0.6894,
|
| 118142 |
+
"step": 16876
|
| 118143 |
+
},
|
| 118144 |
+
{
|
| 118145 |
+
"epoch": 19.22222222222222,
|
| 118146 |
+
"grad_norm": 0.18921184539794922,
|
| 118147 |
+
"learning_rate": 2.0284915556510465e-07,
|
| 118148 |
+
"loss": 0.5576,
|
| 118149 |
+
"step": 16877
|
| 118150 |
+
},
|
| 118151 |
+
{
|
| 118152 |
+
"epoch": 19.223361823361824,
|
| 118153 |
+
"grad_norm": 0.17695850133895874,
|
| 118154 |
+
"learning_rate": 2.02257263424932e-07,
|
| 118155 |
+
"loss": 0.6882,
|
| 118156 |
+
"step": 16878
|
| 118157 |
+
},
|
| 118158 |
+
{
|
| 118159 |
+
"epoch": 19.224501424501426,
|
| 118160 |
+
"grad_norm": 0.20833054184913635,
|
| 118161 |
+
"learning_rate": 2.0166623257856233e-07,
|
| 118162 |
+
"loss": 0.4894,
|
| 118163 |
+
"step": 16879
|
| 118164 |
+
},
|
| 118165 |
+
{
|
| 118166 |
+
"epoch": 19.225641025641025,
|
| 118167 |
+
"grad_norm": 0.2087348997592926,
|
| 118168 |
+
"learning_rate": 2.0107606304651805e-07,
|
| 118169 |
+
"loss": 0.5712,
|
| 118170 |
+
"step": 16880
|
| 118171 |
+
},
|
| 118172 |
+
{
|
| 118173 |
+
"epoch": 19.226780626780627,
|
| 118174 |
+
"grad_norm": 0.19440957903862,
|
| 118175 |
+
"learning_rate": 2.0048675484929947e-07,
|
| 118176 |
+
"loss": 0.606,
|
| 118177 |
+
"step": 16881
|
| 118178 |
+
},
|
| 118179 |
+
{
|
| 118180 |
+
"epoch": 19.22792022792023,
|
| 118181 |
+
"grad_norm": 0.19782736897468567,
|
| 118182 |
+
"learning_rate": 1.9989830800737351e-07,
|
| 118183 |
+
"loss": 0.6482,
|
| 118184 |
+
"step": 16882
|
| 118185 |
+
},
|
| 118186 |
+
{
|
| 118187 |
+
"epoch": 19.22905982905983,
|
| 118188 |
+
"grad_norm": 0.2040553241968155,
|
| 118189 |
+
"learning_rate": 1.9931072254118222e-07,
|
| 118190 |
+
"loss": 0.5844,
|
| 118191 |
+
"step": 16883
|
| 118192 |
+
},
|
| 118193 |
+
{
|
| 118194 |
+
"epoch": 19.23019943019943,
|
| 118195 |
+
"grad_norm": 0.18802884221076965,
|
| 118196 |
+
"learning_rate": 1.9872399847113144e-07,
|
| 118197 |
+
"loss": 0.6887,
|
| 118198 |
+
"step": 16884
|
| 118199 |
+
},
|
| 118200 |
+
{
|
| 118201 |
+
"epoch": 19.231339031339033,
|
| 118202 |
+
"grad_norm": 0.22762954235076904,
|
| 118203 |
+
"learning_rate": 1.9813813581759933e-07,
|
| 118204 |
+
"loss": 0.4754,
|
| 118205 |
+
"step": 16885
|
| 118206 |
+
},
|
| 118207 |
+
{
|
| 118208 |
+
"epoch": 19.23247863247863,
|
| 118209 |
+
"grad_norm": 0.21052877604961395,
|
| 118210 |
+
"learning_rate": 1.9755313460093626e-07,
|
| 118211 |
+
"loss": 0.8026,
|
| 118212 |
+
"step": 16886
|
| 118213 |
+
},
|
| 118214 |
+
{
|
| 118215 |
+
"epoch": 19.233618233618234,
|
| 118216 |
+
"grad_norm": 0.20105506479740143,
|
| 118217 |
+
"learning_rate": 1.9696899484145936e-07,
|
| 118218 |
+
"loss": 0.3103,
|
| 118219 |
+
"step": 16887
|
| 118220 |
+
},
|
| 118221 |
+
{
|
| 118222 |
+
"epoch": 19.234757834757836,
|
| 118223 |
+
"grad_norm": 0.22901511192321777,
|
| 118224 |
+
"learning_rate": 1.9638571655945793e-07,
|
| 118225 |
+
"loss": 0.5651,
|
| 118226 |
+
"step": 16888
|
| 118227 |
+
},
|
| 118228 |
+
{
|
| 118229 |
+
"epoch": 19.235897435897435,
|
| 118230 |
+
"grad_norm": 0.18789878487586975,
|
| 118231 |
+
"learning_rate": 1.9580329977518795e-07,
|
| 118232 |
+
"loss": 0.663,
|
| 118233 |
+
"step": 16889
|
| 118234 |
+
},
|
| 118235 |
+
{
|
| 118236 |
+
"epoch": 19.237037037037037,
|
| 118237 |
+
"grad_norm": 0.22932597994804382,
|
| 118238 |
+
"learning_rate": 1.952217445088833e-07,
|
| 118239 |
+
"loss": 0.682,
|
| 118240 |
+
"step": 16890
|
| 118241 |
+
},
|
| 118242 |
+
{
|
| 118243 |
+
"epoch": 19.23817663817664,
|
| 118244 |
+
"grad_norm": 0.19326689839363098,
|
| 118245 |
+
"learning_rate": 1.9464105078074169e-07,
|
| 118246 |
+
"loss": 0.5318,
|
| 118247 |
+
"step": 16891
|
| 118248 |
+
},
|
| 118249 |
+
{
|
| 118250 |
+
"epoch": 19.23931623931624,
|
| 118251 |
+
"grad_norm": 0.2046305388212204,
|
| 118252 |
+
"learning_rate": 1.940612186109303e-07,
|
| 118253 |
+
"loss": 0.7213,
|
| 118254 |
+
"step": 16892
|
| 118255 |
+
},
|
| 118256 |
+
{
|
| 118257 |
+
"epoch": 19.24045584045584,
|
| 118258 |
+
"grad_norm": 0.17293988168239594,
|
| 118259 |
+
"learning_rate": 1.9348224801958857e-07,
|
| 118260 |
+
"loss": 0.7,
|
| 118261 |
+
"step": 16893
|
| 118262 |
+
},
|
| 118263 |
+
{
|
| 118264 |
+
"epoch": 19.241595441595443,
|
| 118265 |
+
"grad_norm": 0.26575911045074463,
|
| 118266 |
+
"learning_rate": 1.9290413902682825e-07,
|
| 118267 |
+
"loss": 0.5475,
|
| 118268 |
+
"step": 16894
|
| 118269 |
+
},
|
| 118270 |
+
{
|
| 118271 |
+
"epoch": 19.242735042735042,
|
| 118272 |
+
"grad_norm": 0.22037792205810547,
|
| 118273 |
+
"learning_rate": 1.9232689165272767e-07,
|
| 118274 |
+
"loss": 0.6524,
|
| 118275 |
+
"step": 16895
|
| 118276 |
+
},
|
| 118277 |
+
{
|
| 118278 |
+
"epoch": 19.243874643874644,
|
| 118279 |
+
"grad_norm": 0.18646907806396484,
|
| 118280 |
+
"learning_rate": 1.9175050591733468e-07,
|
| 118281 |
+
"loss": 0.7682,
|
| 118282 |
+
"step": 16896
|
| 118283 |
+
},
|
| 118284 |
+
{
|
| 118285 |
+
"epoch": 19.245014245014247,
|
| 118286 |
+
"grad_norm": 0.21266423165798187,
|
| 118287 |
+
"learning_rate": 1.911749818406694e-07,
|
| 118288 |
+
"loss": 0.6346,
|
| 118289 |
+
"step": 16897
|
| 118290 |
+
},
|
| 118291 |
+
{
|
| 118292 |
+
"epoch": 19.246153846153845,
|
| 118293 |
+
"grad_norm": 0.1926053911447525,
|
| 118294 |
+
"learning_rate": 1.9060031944271862e-07,
|
| 118295 |
+
"loss": 0.7582,
|
| 118296 |
+
"step": 16898
|
| 118297 |
+
},
|
| 118298 |
+
{
|
| 118299 |
+
"epoch": 19.247293447293448,
|
| 118300 |
+
"grad_norm": 0.20515741407871246,
|
| 118301 |
+
"learning_rate": 1.9002651874344967e-07,
|
| 118302 |
+
"loss": 0.5199,
|
| 118303 |
+
"step": 16899
|
| 118304 |
+
},
|
| 118305 |
+
{
|
| 118306 |
+
"epoch": 19.24843304843305,
|
| 118307 |
+
"grad_norm": 0.1906573623418808,
|
| 118308 |
+
"learning_rate": 1.8945357976278555e-07,
|
| 118309 |
+
"loss": 0.8215,
|
| 118310 |
+
"step": 16900
|
| 118311 |
+
},
|
| 118312 |
+
{
|
| 118313 |
+
"epoch": 19.24957264957265,
|
| 118314 |
+
"grad_norm": 0.2508430480957031,
|
| 118315 |
+
"learning_rate": 1.8888150252062698e-07,
|
| 118316 |
+
"loss": 0.5091,
|
| 118317 |
+
"step": 16901
|
| 118318 |
+
},
|
| 118319 |
+
{
|
| 118320 |
+
"epoch": 19.25071225071225,
|
| 118321 |
+
"grad_norm": 0.19548311829566956,
|
| 118322 |
+
"learning_rate": 1.8831028703684417e-07,
|
| 118323 |
+
"loss": 0.7222,
|
| 118324 |
+
"step": 16902
|
| 118325 |
+
},
|
| 118326 |
+
{
|
| 118327 |
+
"epoch": 19.251851851851853,
|
| 118328 |
+
"grad_norm": 0.18210169672966003,
|
| 118329 |
+
"learning_rate": 1.877399333312796e-07,
|
| 118330 |
+
"loss": 0.6195,
|
| 118331 |
+
"step": 16903
|
| 118332 |
+
},
|
| 118333 |
+
{
|
| 118334 |
+
"epoch": 19.252991452991452,
|
| 118335 |
+
"grad_norm": 0.15801532566547394,
|
| 118336 |
+
"learning_rate": 1.8717044142373963e-07,
|
| 118337 |
+
"loss": 0.8909,
|
| 118338 |
+
"step": 16904
|
| 118339 |
+
},
|
| 118340 |
+
{
|
| 118341 |
+
"epoch": 19.254131054131054,
|
| 118342 |
+
"grad_norm": 0.1779741793870926,
|
| 118343 |
+
"learning_rate": 1.8660181133400568e-07,
|
| 118344 |
+
"loss": 0.756,
|
| 118345 |
+
"step": 16905
|
| 118346 |
+
},
|
| 118347 |
+
{
|
| 118348 |
+
"epoch": 19.255270655270657,
|
| 118349 |
+
"grad_norm": 0.1532481163740158,
|
| 118350 |
+
"learning_rate": 1.8603404308182858e-07,
|
| 118351 |
+
"loss": 0.792,
|
| 118352 |
+
"step": 16906
|
| 118353 |
+
},
|
| 118354 |
+
{
|
| 118355 |
+
"epoch": 19.256410256410255,
|
| 118356 |
+
"grad_norm": 0.20334388315677643,
|
| 118357 |
+
"learning_rate": 1.8546713668692873e-07,
|
| 118358 |
+
"loss": 0.478,
|
| 118359 |
+
"step": 16907
|
| 118360 |
+
},
|
| 118361 |
+
{
|
| 118362 |
+
"epoch": 19.257549857549858,
|
| 118363 |
+
"grad_norm": 0.18965454399585724,
|
| 118364 |
+
"learning_rate": 1.8490109216899587e-07,
|
| 118365 |
+
"loss": 0.5404,
|
| 118366 |
+
"step": 16908
|
| 118367 |
+
},
|
| 118368 |
+
{
|
| 118369 |
+
"epoch": 19.25868945868946,
|
| 118370 |
+
"grad_norm": 0.2065407931804657,
|
| 118371 |
+
"learning_rate": 1.8433590954768653e-07,
|
| 118372 |
+
"loss": 0.5383,
|
| 118373 |
+
"step": 16909
|
| 118374 |
+
},
|
| 118375 |
+
{
|
| 118376 |
+
"epoch": 19.25982905982906,
|
| 118377 |
+
"grad_norm": 0.19230175018310547,
|
| 118378 |
+
"learning_rate": 1.837715888426378e-07,
|
| 118379 |
+
"loss": 0.8586,
|
| 118380 |
+
"step": 16910
|
| 118381 |
+
},
|
| 118382 |
+
{
|
| 118383 |
+
"epoch": 19.26096866096866,
|
| 118384 |
+
"grad_norm": 0.15374523401260376,
|
| 118385 |
+
"learning_rate": 1.8320813007344507e-07,
|
| 118386 |
+
"loss": 0.7498,
|
| 118387 |
+
"step": 16911
|
| 118388 |
+
},
|
| 118389 |
+
{
|
| 118390 |
+
"epoch": 19.262108262108264,
|
| 118391 |
+
"grad_norm": 0.22920438647270203,
|
| 118392 |
+
"learning_rate": 1.826455332596816e-07,
|
| 118393 |
+
"loss": 0.6152,
|
| 118394 |
+
"step": 16912
|
| 118395 |
+
},
|
| 118396 |
+
{
|
| 118397 |
+
"epoch": 19.263247863247862,
|
| 118398 |
+
"grad_norm": 0.19025102257728577,
|
| 118399 |
+
"learning_rate": 1.8208379842088452e-07,
|
| 118400 |
+
"loss": 0.7298,
|
| 118401 |
+
"step": 16913
|
| 118402 |
+
},
|
| 118403 |
+
{
|
| 118404 |
+
"epoch": 19.264387464387465,
|
| 118405 |
+
"grad_norm": 0.1733146458864212,
|
| 118406 |
+
"learning_rate": 1.815229255765688e-07,
|
| 118407 |
+
"loss": 0.6172,
|
| 118408 |
+
"step": 16914
|
| 118409 |
+
},
|
| 118410 |
+
{
|
| 118411 |
+
"epoch": 19.265527065527067,
|
| 118412 |
+
"grad_norm": 0.20255063474178314,
|
| 118413 |
+
"learning_rate": 1.8096291474621052e-07,
|
| 118414 |
+
"loss": 0.3158,
|
| 118415 |
+
"step": 16915
|
| 118416 |
+
},
|
| 118417 |
+
{
|
| 118418 |
+
"epoch": 19.266666666666666,
|
| 118419 |
+
"grad_norm": 0.21574810147285461,
|
| 118420 |
+
"learning_rate": 1.8040376594926355e-07,
|
| 118421 |
+
"loss": 0.2767,
|
| 118422 |
+
"step": 16916
|
| 118423 |
+
},
|
| 118424 |
+
{
|
| 118425 |
+
"epoch": 19.267806267806268,
|
| 118426 |
+
"grad_norm": 0.1896638572216034,
|
| 118427 |
+
"learning_rate": 1.7984547920515127e-07,
|
| 118428 |
+
"loss": 0.7195,
|
| 118429 |
+
"step": 16917
|
| 118430 |
+
},
|
| 118431 |
+
{
|
| 118432 |
+
"epoch": 19.26894586894587,
|
| 118433 |
+
"grad_norm": 0.18451404571533203,
|
| 118434 |
+
"learning_rate": 1.7928805453325814e-07,
|
| 118435 |
+
"loss": 0.5955,
|
| 118436 |
+
"step": 16918
|
| 118437 |
+
},
|
| 118438 |
+
{
|
| 118439 |
+
"epoch": 19.27008547008547,
|
| 118440 |
+
"grad_norm": 0.22833938896656036,
|
| 118441 |
+
"learning_rate": 1.7873149195294647e-07,
|
| 118442 |
+
"loss": 0.4586,
|
| 118443 |
+
"step": 16919
|
| 118444 |
+
},
|
| 118445 |
+
{
|
| 118446 |
+
"epoch": 19.27122507122507,
|
| 118447 |
+
"grad_norm": 0.277601957321167,
|
| 118448 |
+
"learning_rate": 1.7817579148355078e-07,
|
| 118449 |
+
"loss": 0.624,
|
| 118450 |
+
"step": 16920
|
| 118451 |
+
},
|
| 118452 |
+
{
|
| 118453 |
+
"epoch": 19.272364672364674,
|
| 118454 |
+
"grad_norm": 0.21973587572574615,
|
| 118455 |
+
"learning_rate": 1.7762095314437233e-07,
|
| 118456 |
+
"loss": 0.5225,
|
| 118457 |
+
"step": 16921
|
| 118458 |
+
},
|
| 118459 |
+
{
|
| 118460 |
+
"epoch": 19.273504273504273,
|
| 118461 |
+
"grad_norm": 0.26785463094711304,
|
| 118462 |
+
"learning_rate": 1.77066976954679e-07,
|
| 118463 |
+
"loss": 0.5603,
|
| 118464 |
+
"step": 16922
|
| 118465 |
+
},
|
| 118466 |
+
{
|
| 118467 |
+
"epoch": 19.274643874643875,
|
| 118468 |
+
"grad_norm": 0.17875657975673676,
|
| 118469 |
+
"learning_rate": 1.7651386293371098e-07,
|
| 118470 |
+
"loss": 0.7083,
|
| 118471 |
+
"step": 16923
|
| 118472 |
+
},
|
| 118473 |
+
{
|
| 118474 |
+
"epoch": 19.275783475783477,
|
| 118475 |
+
"grad_norm": 0.191822811961174,
|
| 118476 |
+
"learning_rate": 1.7596161110068065e-07,
|
| 118477 |
+
"loss": 0.4877,
|
| 118478 |
+
"step": 16924
|
| 118479 |
+
},
|
| 118480 |
+
{
|
| 118481 |
+
"epoch": 19.276923076923076,
|
| 118482 |
+
"grad_norm": 0.18875642120838165,
|
| 118483 |
+
"learning_rate": 1.754102214747727e-07,
|
| 118484 |
+
"loss": 0.512,
|
| 118485 |
+
"step": 16925
|
| 118486 |
+
},
|
| 118487 |
+
{
|
| 118488 |
+
"epoch": 19.27806267806268,
|
| 118489 |
+
"grad_norm": 0.21474966406822205,
|
| 118490 |
+
"learning_rate": 1.7485969407513293e-07,
|
| 118491 |
+
"loss": 0.6143,
|
| 118492 |
+
"step": 16926
|
| 118493 |
+
},
|
| 118494 |
+
{
|
| 118495 |
+
"epoch": 19.27920227920228,
|
| 118496 |
+
"grad_norm": 0.19494162499904633,
|
| 118497 |
+
"learning_rate": 1.7431002892088766e-07,
|
| 118498 |
+
"loss": 0.5833,
|
| 118499 |
+
"step": 16927
|
| 118500 |
+
},
|
| 118501 |
+
{
|
| 118502 |
+
"epoch": 19.28034188034188,
|
| 118503 |
+
"grad_norm": 0.162825345993042,
|
| 118504 |
+
"learning_rate": 1.737612260311272e-07,
|
| 118505 |
+
"loss": 0.6457,
|
| 118506 |
+
"step": 16928
|
| 118507 |
+
},
|
| 118508 |
+
{
|
| 118509 |
+
"epoch": 19.28148148148148,
|
| 118510 |
+
"grad_norm": 0.19001635909080505,
|
| 118511 |
+
"learning_rate": 1.7321328542490855e-07,
|
| 118512 |
+
"loss": 0.7186,
|
| 118513 |
+
"step": 16929
|
| 118514 |
+
},
|
| 118515 |
+
{
|
| 118516 |
+
"epoch": 19.282621082621084,
|
| 118517 |
+
"grad_norm": 0.21253564953804016,
|
| 118518 |
+
"learning_rate": 1.7266620712126645e-07,
|
| 118519 |
+
"loss": 0.6209,
|
| 118520 |
+
"step": 16930
|
| 118521 |
+
},
|
| 118522 |
+
{
|
| 118523 |
+
"epoch": 19.283760683760683,
|
| 118524 |
+
"grad_norm": 0.2037236988544464,
|
| 118525 |
+
"learning_rate": 1.7211999113920518e-07,
|
| 118526 |
+
"loss": 0.5061,
|
| 118527 |
+
"step": 16931
|
| 118528 |
+
},
|
| 118529 |
+
{
|
| 118530 |
+
"epoch": 19.284900284900285,
|
| 118531 |
+
"grad_norm": 0.1651899516582489,
|
| 118532 |
+
"learning_rate": 1.7157463749769288e-07,
|
| 118533 |
+
"loss": 0.5641,
|
| 118534 |
+
"step": 16932
|
| 118535 |
+
},
|
| 118536 |
+
{
|
| 118537 |
+
"epoch": 19.286039886039887,
|
| 118538 |
+
"grad_norm": 0.19152629375457764,
|
| 118539 |
+
"learning_rate": 1.7103014621566993e-07,
|
| 118540 |
+
"loss": 0.5588,
|
| 118541 |
+
"step": 16933
|
| 118542 |
+
},
|
| 118543 |
+
{
|
| 118544 |
+
"epoch": 19.287179487179486,
|
| 118545 |
+
"grad_norm": 0.20283615589141846,
|
| 118546 |
+
"learning_rate": 1.7048651731205179e-07,
|
| 118547 |
+
"loss": 0.6209,
|
| 118548 |
+
"step": 16934
|
| 118549 |
+
},
|
| 118550 |
+
{
|
| 118551 |
+
"epoch": 19.28831908831909,
|
| 118552 |
+
"grad_norm": 0.20604069530963898,
|
| 118553 |
+
"learning_rate": 1.6994375080571777e-07,
|
| 118554 |
+
"loss": 0.57,
|
| 118555 |
+
"step": 16935
|
| 118556 |
+
},
|
| 118557 |
+
{
|
| 118558 |
+
"epoch": 19.28945868945869,
|
| 118559 |
+
"grad_norm": 0.18033136427402496,
|
| 118560 |
+
"learning_rate": 1.694018467155195e-07,
|
| 118561 |
+
"loss": 0.8617,
|
| 118562 |
+
"step": 16936
|
| 118563 |
+
},
|
| 118564 |
+
{
|
| 118565 |
+
"epoch": 19.29059829059829,
|
| 118566 |
+
"grad_norm": 0.18603329360485077,
|
| 118567 |
+
"learning_rate": 1.6886080506027801e-07,
|
| 118568 |
+
"loss": 0.491,
|
| 118569 |
+
"step": 16937
|
| 118570 |
+
},
|
| 118571 |
+
{
|
| 118572 |
+
"epoch": 19.291737891737892,
|
| 118573 |
+
"grad_norm": 0.16204974055290222,
|
| 118574 |
+
"learning_rate": 1.6832062585878937e-07,
|
| 118575 |
+
"loss": 0.4305,
|
| 118576 |
+
"step": 16938
|
| 118577 |
+
},
|
| 118578 |
+
{
|
| 118579 |
+
"epoch": 19.292877492877494,
|
| 118580 |
+
"grad_norm": 0.20586009323596954,
|
| 118581 |
+
"learning_rate": 1.6778130912981084e-07,
|
| 118582 |
+
"loss": 0.6284,
|
| 118583 |
+
"step": 16939
|
| 118584 |
+
},
|
| 118585 |
+
{
|
| 118586 |
+
"epoch": 19.294017094017093,
|
| 118587 |
+
"grad_norm": 0.16173145174980164,
|
| 118588 |
+
"learning_rate": 1.6724285489208013e-07,
|
| 118589 |
+
"loss": 0.6411,
|
| 118590 |
+
"step": 16940
|
| 118591 |
+
},
|
| 118592 |
+
{
|
| 118593 |
+
"epoch": 19.295156695156695,
|
| 118594 |
+
"grad_norm": 0.16894316673278809,
|
| 118595 |
+
"learning_rate": 1.6670526316429346e-07,
|
| 118596 |
+
"loss": 0.5615,
|
| 118597 |
+
"step": 16941
|
| 118598 |
+
},
|
| 118599 |
+
{
|
| 118600 |
+
"epoch": 19.296296296296298,
|
| 118601 |
+
"grad_norm": 0.18487438559532166,
|
| 118602 |
+
"learning_rate": 1.66168533965122e-07,
|
| 118603 |
+
"loss": 0.5633,
|
| 118604 |
+
"step": 16942
|
| 118605 |
+
},
|
| 118606 |
+
{
|
| 118607 |
+
"epoch": 19.297435897435896,
|
| 118608 |
+
"grad_norm": 0.19690082967281342,
|
| 118609 |
+
"learning_rate": 1.6563266731321192e-07,
|
| 118610 |
+
"loss": 0.9356,
|
| 118611 |
+
"step": 16943
|
| 118612 |
+
},
|
| 118613 |
+
{
|
| 118614 |
+
"epoch": 19.2985754985755,
|
| 118615 |
+
"grad_norm": 0.1948634684085846,
|
| 118616 |
+
"learning_rate": 1.6509766322717612e-07,
|
| 118617 |
+
"loss": 0.8312,
|
| 118618 |
+
"step": 16944
|
| 118619 |
+
},
|
| 118620 |
+
{
|
| 118621 |
+
"epoch": 19.2997150997151,
|
| 118622 |
+
"grad_norm": 0.2944418787956238,
|
| 118623 |
+
"learning_rate": 1.645635217255942e-07,
|
| 118624 |
+
"loss": 0.5003,
|
| 118625 |
+
"step": 16945
|
| 118626 |
+
},
|
| 118627 |
+
{
|
| 118628 |
+
"epoch": 19.3008547008547,
|
| 118629 |
+
"grad_norm": 0.23983515799045563,
|
| 118630 |
+
"learning_rate": 1.6403024282701795e-07,
|
| 118631 |
+
"loss": 0.5651,
|
| 118632 |
+
"step": 16946
|
| 118633 |
+
},
|
| 118634 |
+
{
|
| 118635 |
+
"epoch": 19.301994301994302,
|
| 118636 |
+
"grad_norm": 0.2157278060913086,
|
| 118637 |
+
"learning_rate": 1.6349782654997148e-07,
|
| 118638 |
+
"loss": 0.654,
|
| 118639 |
+
"step": 16947
|
| 118640 |
+
},
|
| 118641 |
+
{
|
| 118642 |
+
"epoch": 19.303133903133904,
|
| 118643 |
+
"grad_norm": 0.2278202325105667,
|
| 118644 |
+
"learning_rate": 1.6296627291294552e-07,
|
| 118645 |
+
"loss": 0.5393,
|
| 118646 |
+
"step": 16948
|
| 118647 |
+
},
|
| 118648 |
+
{
|
| 118649 |
+
"epoch": 19.304273504273503,
|
| 118650 |
+
"grad_norm": 0.1552683413028717,
|
| 118651 |
+
"learning_rate": 1.6243558193440313e-07,
|
| 118652 |
+
"loss": 0.8572,
|
| 118653 |
+
"step": 16949
|
| 118654 |
+
},
|
| 118655 |
+
{
|
| 118656 |
+
"epoch": 19.305413105413106,
|
| 118657 |
+
"grad_norm": 0.2274259477853775,
|
| 118658 |
+
"learning_rate": 1.6190575363277395e-07,
|
| 118659 |
+
"loss": 0.6418,
|
| 118660 |
+
"step": 16950
|
| 118661 |
+
},
|
| 118662 |
+
{
|
| 118663 |
+
"epoch": 19.306552706552708,
|
| 118664 |
+
"grad_norm": 0.21096357703208923,
|
| 118665 |
+
"learning_rate": 1.6137678802646827e-07,
|
| 118666 |
+
"loss": 0.5175,
|
| 118667 |
+
"step": 16951
|
| 118668 |
+
},
|
| 118669 |
+
{
|
| 118670 |
+
"epoch": 19.307692307692307,
|
| 118671 |
+
"grad_norm": 0.17654189467430115,
|
| 118672 |
+
"learning_rate": 1.6084868513384921e-07,
|
| 118673 |
+
"loss": 0.696,
|
| 118674 |
+
"step": 16952
|
| 118675 |
+
},
|
| 118676 |
+
{
|
| 118677 |
+
"epoch": 19.30883190883191,
|
| 118678 |
+
"grad_norm": 0.22242681682109833,
|
| 118679 |
+
"learning_rate": 1.6032144497326594e-07,
|
| 118680 |
+
"loss": 0.5559,
|
| 118681 |
+
"step": 16953
|
| 118682 |
+
},
|
| 118683 |
+
{
|
| 118684 |
+
"epoch": 19.30997150997151,
|
| 118685 |
+
"grad_norm": 0.22529473900794983,
|
| 118686 |
+
"learning_rate": 1.597950675630261e-07,
|
| 118687 |
+
"loss": 0.7854,
|
| 118688 |
+
"step": 16954
|
| 118689 |
+
},
|
| 118690 |
+
{
|
| 118691 |
+
"epoch": 19.31111111111111,
|
| 118692 |
+
"grad_norm": 0.23013631999492645,
|
| 118693 |
+
"learning_rate": 1.59269552921415e-07,
|
| 118694 |
+
"loss": 0.3146,
|
| 118695 |
+
"step": 16955
|
| 118696 |
+
},
|
| 118697 |
+
{
|
| 118698 |
+
"epoch": 19.312250712250712,
|
| 118699 |
+
"grad_norm": 0.1959642767906189,
|
| 118700 |
+
"learning_rate": 1.587449010666847e-07,
|
| 118701 |
+
"loss": 0.6456,
|
| 118702 |
+
"step": 16956
|
| 118703 |
+
},
|
| 118704 |
+
{
|
| 118705 |
+
"epoch": 19.313390313390315,
|
| 118706 |
+
"grad_norm": 0.2010372281074524,
|
| 118707 |
+
"learning_rate": 1.5822111201705682e-07,
|
| 118708 |
+
"loss": 0.6799,
|
| 118709 |
+
"step": 16957
|
| 118710 |
+
},
|
| 118711 |
+
{
|
| 118712 |
+
"epoch": 19.314529914529913,
|
| 118713 |
+
"grad_norm": 0.21289879083633423,
|
| 118714 |
+
"learning_rate": 1.5769818579072505e-07,
|
| 118715 |
+
"loss": 0.7041,
|
| 118716 |
+
"step": 16958
|
| 118717 |
+
},
|
| 118718 |
+
{
|
| 118719 |
+
"epoch": 19.315669515669516,
|
| 118720 |
+
"grad_norm": 0.2144283801317215,
|
| 118721 |
+
"learning_rate": 1.5717612240585266e-07,
|
| 118722 |
+
"loss": 0.5488,
|
| 118723 |
+
"step": 16959
|
| 118724 |
+
},
|
| 118725 |
+
{
|
| 118726 |
+
"epoch": 19.316809116809118,
|
| 118727 |
+
"grad_norm": 0.21097925305366516,
|
| 118728 |
+
"learning_rate": 1.566549218805724e-07,
|
| 118729 |
+
"loss": 0.593,
|
| 118730 |
+
"step": 16960
|
| 118731 |
+
},
|
| 118732 |
+
{
|
| 118733 |
+
"epoch": 19.317948717948717,
|
| 118734 |
+
"grad_norm": 0.2372552901506424,
|
| 118735 |
+
"learning_rate": 1.5613458423298365e-07,
|
| 118736 |
+
"loss": 0.6971,
|
| 118737 |
+
"step": 16961
|
| 118738 |
+
},
|
| 118739 |
+
{
|
| 118740 |
+
"epoch": 19.31908831908832,
|
| 118741 |
+
"grad_norm": 0.20000500977039337,
|
| 118742 |
+
"learning_rate": 1.5561510948116642e-07,
|
| 118743 |
+
"loss": 0.7047,
|
| 118744 |
+
"step": 16962
|
| 118745 |
+
},
|
| 118746 |
+
{
|
| 118747 |
+
"epoch": 19.32022792022792,
|
| 118748 |
+
"grad_norm": 0.17207293212413788,
|
| 118749 |
+
"learning_rate": 1.5509649764315347e-07,
|
| 118750 |
+
"loss": 0.6819,
|
| 118751 |
+
"step": 16963
|
| 118752 |
+
},
|
| 118753 |
+
{
|
| 118754 |
+
"epoch": 19.32136752136752,
|
| 118755 |
+
"grad_norm": 0.18278390169143677,
|
| 118756 |
+
"learning_rate": 1.5457874873696653e-07,
|
| 118757 |
+
"loss": 0.544,
|
| 118758 |
+
"step": 16964
|
| 118759 |
+
},
|
| 118760 |
+
{
|
| 118761 |
+
"epoch": 19.322507122507123,
|
| 118762 |
+
"grad_norm": 0.20752927660942078,
|
| 118763 |
+
"learning_rate": 1.5406186278058286e-07,
|
| 118764 |
+
"loss": 0.519,
|
| 118765 |
+
"step": 16965
|
| 118766 |
+
},
|
| 118767 |
+
{
|
| 118768 |
+
"epoch": 19.323646723646725,
|
| 118769 |
+
"grad_norm": 0.16611790657043457,
|
| 118770 |
+
"learning_rate": 1.5354583979195758e-07,
|
| 118771 |
+
"loss": 0.5877,
|
| 118772 |
+
"step": 16966
|
| 118773 |
+
},
|
| 118774 |
+
{
|
| 118775 |
+
"epoch": 19.324786324786324,
|
| 118776 |
+
"grad_norm": 0.16754280030727386,
|
| 118777 |
+
"learning_rate": 1.5303067978901242e-07,
|
| 118778 |
+
"loss": 0.7034,
|
| 118779 |
+
"step": 16967
|
| 118780 |
+
},
|
| 118781 |
+
{
|
| 118782 |
+
"epoch": 19.325925925925926,
|
| 118783 |
+
"grad_norm": 0.17728129029273987,
|
| 118784 |
+
"learning_rate": 1.5251638278964419e-07,
|
| 118785 |
+
"loss": 0.7641,
|
| 118786 |
+
"step": 16968
|
| 118787 |
+
},
|
| 118788 |
+
{
|
| 118789 |
+
"epoch": 19.32706552706553,
|
| 118790 |
+
"grad_norm": 0.16807030141353607,
|
| 118791 |
+
"learning_rate": 1.5200294881171084e-07,
|
| 118792 |
+
"loss": 0.8213,
|
| 118793 |
+
"step": 16969
|
| 118794 |
+
},
|
| 118795 |
+
{
|
| 118796 |
+
"epoch": 19.328205128205127,
|
| 118797 |
+
"grad_norm": 0.19782152771949768,
|
| 118798 |
+
"learning_rate": 1.514903778730481e-07,
|
| 118799 |
+
"loss": 0.5519,
|
| 118800 |
+
"step": 16970
|
| 118801 |
+
},
|
| 118802 |
+
{
|
| 118803 |
+
"epoch": 19.32934472934473,
|
| 118804 |
+
"grad_norm": 0.19398966431617737,
|
| 118805 |
+
"learning_rate": 1.509786699914556e-07,
|
| 118806 |
+
"loss": 0.7432,
|
| 118807 |
+
"step": 16971
|
| 118808 |
+
},
|
| 118809 |
+
{
|
| 118810 |
+
"epoch": 19.33048433048433,
|
| 118811 |
+
"grad_norm": 0.1973167508840561,
|
| 118812 |
+
"learning_rate": 1.504678251847108e-07,
|
| 118813 |
+
"loss": 0.8417,
|
| 118814 |
+
"step": 16972
|
| 118815 |
+
},
|
| 118816 |
+
{
|
| 118817 |
+
"epoch": 19.33162393162393,
|
| 118818 |
+
"grad_norm": 0.1974257081747055,
|
| 118819 |
+
"learning_rate": 1.4995784347055508e-07,
|
| 118820 |
+
"loss": 0.7497,
|
| 118821 |
+
"step": 16973
|
| 118822 |
+
},
|
| 118823 |
+
{
|
| 118824 |
+
"epoch": 19.332763532763533,
|
| 118825 |
+
"grad_norm": 0.15442010760307312,
|
| 118826 |
+
"learning_rate": 1.4944872486670204e-07,
|
| 118827 |
+
"loss": 0.7071,
|
| 118828 |
+
"step": 16974
|
| 118829 |
+
},
|
| 118830 |
+
{
|
| 118831 |
+
"epoch": 19.333903133903135,
|
| 118832 |
+
"grad_norm": 0.22179816663265228,
|
| 118833 |
+
"learning_rate": 1.4894046939083195e-07,
|
| 118834 |
+
"loss": 0.6395,
|
| 118835 |
+
"step": 16975
|
| 118836 |
+
},
|
| 118837 |
+
{
|
| 118838 |
+
"epoch": 19.335042735042734,
|
| 118839 |
+
"grad_norm": 0.17436963319778442,
|
| 118840 |
+
"learning_rate": 1.4843307706060016e-07,
|
| 118841 |
+
"loss": 0.7704,
|
| 118842 |
+
"step": 16976
|
| 118843 |
+
},
|
| 118844 |
+
{
|
| 118845 |
+
"epoch": 19.336182336182336,
|
| 118846 |
+
"grad_norm": 0.1819789707660675,
|
| 118847 |
+
"learning_rate": 1.4792654789363148e-07,
|
| 118848 |
+
"loss": 0.8175,
|
| 118849 |
+
"step": 16977
|
| 118850 |
+
},
|
| 118851 |
+
{
|
| 118852 |
+
"epoch": 19.33732193732194,
|
| 118853 |
+
"grad_norm": 0.20858220756053925,
|
| 118854 |
+
"learning_rate": 1.4742088190751735e-07,
|
| 118855 |
+
"loss": 0.3258,
|
| 118856 |
+
"step": 16978
|
| 118857 |
+
},
|
| 118858 |
+
{
|
| 118859 |
+
"epoch": 19.338461538461537,
|
| 118860 |
+
"grad_norm": 0.17292723059654236,
|
| 118861 |
+
"learning_rate": 1.4691607911981875e-07,
|
| 118862 |
+
"loss": 0.6172,
|
| 118863 |
+
"step": 16979
|
| 118864 |
+
},
|
| 118865 |
+
{
|
| 118866 |
+
"epoch": 19.33960113960114,
|
| 118867 |
+
"grad_norm": 0.20629368722438812,
|
| 118868 |
+
"learning_rate": 1.4641213954807442e-07,
|
| 118869 |
+
"loss": 0.7085,
|
| 118870 |
+
"step": 16980
|
| 118871 |
+
},
|
| 118872 |
+
{
|
| 118873 |
+
"epoch": 19.340740740740742,
|
| 118874 |
+
"grad_norm": 0.25998514890670776,
|
| 118875 |
+
"learning_rate": 1.4590906320978148e-07,
|
| 118876 |
+
"loss": 0.594,
|
| 118877 |
+
"step": 16981
|
| 118878 |
+
},
|
| 118879 |
+
{
|
| 118880 |
+
"epoch": 19.34188034188034,
|
| 118881 |
+
"grad_norm": 0.23073017597198486,
|
| 118882 |
+
"learning_rate": 1.4540685012241483e-07,
|
| 118883 |
+
"loss": 0.6886,
|
| 118884 |
+
"step": 16982
|
| 118885 |
+
},
|
| 118886 |
+
{
|
| 118887 |
+
"epoch": 19.343019943019943,
|
| 118888 |
+
"grad_norm": 0.23051905632019043,
|
| 118889 |
+
"learning_rate": 1.4490550030342165e-07,
|
| 118890 |
+
"loss": 0.4629,
|
| 118891 |
+
"step": 16983
|
| 118892 |
+
},
|
| 118893 |
+
{
|
| 118894 |
+
"epoch": 19.344159544159545,
|
| 118895 |
+
"grad_norm": 0.1976567953824997,
|
| 118896 |
+
"learning_rate": 1.444050137702102e-07,
|
| 118897 |
+
"loss": 0.8199,
|
| 118898 |
+
"step": 16984
|
| 118899 |
+
},
|
| 118900 |
+
{
|
| 118901 |
+
"epoch": 19.345299145299144,
|
| 118902 |
+
"grad_norm": 0.2493298351764679,
|
| 118903 |
+
"learning_rate": 1.439053905401666e-07,
|
| 118904 |
+
"loss": 0.5049,
|
| 118905 |
+
"step": 16985
|
| 118906 |
+
},
|
| 118907 |
+
{
|
| 118908 |
+
"epoch": 19.346438746438746,
|
| 118909 |
+
"grad_norm": 0.2229515016078949,
|
| 118910 |
+
"learning_rate": 1.4340663063064363e-07,
|
| 118911 |
+
"loss": 0.5099,
|
| 118912 |
+
"step": 16986
|
| 118913 |
+
},
|
| 118914 |
+
{
|
| 118915 |
+
"epoch": 19.34757834757835,
|
| 118916 |
+
"grad_norm": 0.19988198578357697,
|
| 118917 |
+
"learning_rate": 1.4290873405896354e-07,
|
| 118918 |
+
"loss": 0.7719,
|
| 118919 |
+
"step": 16987
|
| 118920 |
+
},
|
| 118921 |
+
{
|
| 118922 |
+
"epoch": 19.348717948717947,
|
| 118923 |
+
"grad_norm": 0.17936088144779205,
|
| 118924 |
+
"learning_rate": 1.4241170084241806e-07,
|
| 118925 |
+
"loss": 0.6148,
|
| 118926 |
+
"step": 16988
|
| 118927 |
+
},
|
| 118928 |
+
{
|
| 118929 |
+
"epoch": 19.34985754985755,
|
| 118930 |
+
"grad_norm": 0.16914109885692596,
|
| 118931 |
+
"learning_rate": 1.419155309982767e-07,
|
| 118932 |
+
"loss": 0.4429,
|
| 118933 |
+
"step": 16989
|
| 118934 |
+
},
|
| 118935 |
+
{
|
| 118936 |
+
"epoch": 19.350997150997152,
|
| 118937 |
+
"grad_norm": 0.17672418057918549,
|
| 118938 |
+
"learning_rate": 1.4142022454376736e-07,
|
| 118939 |
+
"loss": 0.5318,
|
| 118940 |
+
"step": 16990
|
| 118941 |
+
},
|
| 118942 |
+
{
|
| 118943 |
+
"epoch": 19.35213675213675,
|
| 118944 |
+
"grad_norm": 0.1927495002746582,
|
| 118945 |
+
"learning_rate": 1.409257814960957e-07,
|
| 118946 |
+
"loss": 0.6414,
|
| 118947 |
+
"step": 16991
|
| 118948 |
+
},
|
| 118949 |
+
{
|
| 118950 |
+
"epoch": 19.353276353276353,
|
| 118951 |
+
"grad_norm": 0.18565373122692108,
|
| 118952 |
+
"learning_rate": 1.404322018724341e-07,
|
| 118953 |
+
"loss": 0.7684,
|
| 118954 |
+
"step": 16992
|
| 118955 |
+
},
|
| 118956 |
+
{
|
| 118957 |
+
"epoch": 19.354415954415956,
|
| 118958 |
+
"grad_norm": 0.20426031947135925,
|
| 118959 |
+
"learning_rate": 1.3993948568992443e-07,
|
| 118960 |
+
"loss": 0.4539,
|
| 118961 |
+
"step": 16993
|
| 118962 |
+
},
|
| 118963 |
+
{
|
| 118964 |
+
"epoch": 19.355555555555554,
|
| 118965 |
+
"grad_norm": 0.20206066966056824,
|
| 118966 |
+
"learning_rate": 1.3944763296568353e-07,
|
| 118967 |
+
"loss": 0.6285,
|
| 118968 |
+
"step": 16994
|
| 118969 |
+
},
|
| 118970 |
+
{
|
| 118971 |
+
"epoch": 19.356695156695157,
|
| 118972 |
+
"grad_norm": 0.2475404143333435,
|
| 118973 |
+
"learning_rate": 1.3895664371679218e-07,
|
| 118974 |
+
"loss": 0.8911,
|
| 118975 |
+
"step": 16995
|
| 118976 |
+
},
|
| 118977 |
+
{
|
| 118978 |
+
"epoch": 19.35783475783476,
|
| 118979 |
+
"grad_norm": 0.1861857771873474,
|
| 118980 |
+
"learning_rate": 1.3846651796030617e-07,
|
| 118981 |
+
"loss": 0.7475,
|
| 118982 |
+
"step": 16996
|
| 118983 |
+
},
|
| 118984 |
+
{
|
| 118985 |
+
"epoch": 19.358974358974358,
|
| 118986 |
+
"grad_norm": 0.21384894847869873,
|
| 118987 |
+
"learning_rate": 1.3797725571324805e-07,
|
| 118988 |
+
"loss": 0.4894,
|
| 118989 |
+
"step": 16997
|
| 118990 |
+
},
|
| 118991 |
+
{
|
| 118992 |
+
"epoch": 19.36011396011396,
|
| 118993 |
+
"grad_norm": 0.16749976575374603,
|
| 118994 |
+
"learning_rate": 1.3748885699260972e-07,
|
| 118995 |
+
"loss": 0.7155,
|
| 118996 |
+
"step": 16998
|
| 118997 |
+
},
|
| 118998 |
+
{
|
| 118999 |
+
"epoch": 19.361253561253562,
|
| 119000 |
+
"grad_norm": 0.20118291676044464,
|
| 119001 |
+
"learning_rate": 1.3700132181535264e-07,
|
| 119002 |
+
"loss": 0.7377,
|
| 119003 |
+
"step": 16999
|
| 119004 |
+
},
|
| 119005 |
+
{
|
| 119006 |
+
"epoch": 19.36239316239316,
|
| 119007 |
+
"grad_norm": 0.20364977419376373,
|
| 119008 |
+
"learning_rate": 1.365146501984188e-07,
|
| 119009 |
+
"loss": 0.7462,
|
| 119010 |
+
"step": 17000
|
| 119011 |
+
},
|
| 119012 |
+
{
|
| 119013 |
+
"epoch": 19.363532763532763,
|
| 119014 |
+
"grad_norm": 0.24547569453716278,
|
| 119015 |
+
"learning_rate": 1.3602884215870305e-07,
|
| 119016 |
+
"loss": 0.6276,
|
| 119017 |
+
"step": 17001
|
| 119018 |
+
},
|
| 119019 |
+
{
|
| 119020 |
+
"epoch": 19.364672364672366,
|
| 119021 |
+
"grad_norm": 0.25913381576538086,
|
| 119022 |
+
"learning_rate": 1.3554389771308073e-07,
|
| 119023 |
+
"loss": 0.6307,
|
| 119024 |
+
"step": 17002
|
| 119025 |
+
},
|
| 119026 |
+
{
|
| 119027 |
+
"epoch": 19.365811965811965,
|
| 119028 |
+
"grad_norm": 0.19459164142608643,
|
| 119029 |
+
"learning_rate": 1.3505981687839674e-07,
|
| 119030 |
+
"loss": 0.4771,
|
| 119031 |
+
"step": 17003
|
| 119032 |
+
},
|
| 119033 |
+
{
|
| 119034 |
+
"epoch": 19.366951566951567,
|
| 119035 |
+
"grad_norm": 0.14924933016300201,
|
| 119036 |
+
"learning_rate": 1.345765996714654e-07,
|
| 119037 |
+
"loss": 0.8247,
|
| 119038 |
+
"step": 17004
|
| 119039 |
+
},
|
| 119040 |
+
{
|
| 119041 |
+
"epoch": 19.36809116809117,
|
| 119042 |
+
"grad_norm": 0.2035389095544815,
|
| 119043 |
+
"learning_rate": 1.3409424610906772e-07,
|
| 119044 |
+
"loss": 0.5336,
|
| 119045 |
+
"step": 17005
|
| 119046 |
+
},
|
| 119047 |
+
{
|
| 119048 |
+
"epoch": 19.369230769230768,
|
| 119049 |
+
"grad_norm": 0.17139534652233124,
|
| 119050 |
+
"learning_rate": 1.33612756207957e-07,
|
| 119051 |
+
"loss": 0.7279,
|
| 119052 |
+
"step": 17006
|
| 119053 |
+
},
|
| 119054 |
+
{
|
| 119055 |
+
"epoch": 19.37037037037037,
|
| 119056 |
+
"grad_norm": 0.22130882740020752,
|
| 119057 |
+
"learning_rate": 1.3313212998486146e-07,
|
| 119058 |
+
"loss": 0.7468,
|
| 119059 |
+
"step": 17007
|
| 119060 |
+
},
|
| 119061 |
+
{
|
| 119062 |
+
"epoch": 19.371509971509973,
|
| 119063 |
+
"grad_norm": 0.20196962356567383,
|
| 119064 |
+
"learning_rate": 1.3265236745647058e-07,
|
| 119065 |
+
"loss": 0.7199,
|
| 119066 |
+
"step": 17008
|
| 119067 |
+
},
|
| 119068 |
+
{
|
| 119069 |
+
"epoch": 19.37264957264957,
|
| 119070 |
+
"grad_norm": 0.18781882524490356,
|
| 119071 |
+
"learning_rate": 1.32173468639446e-07,
|
| 119072 |
+
"loss": 0.5938,
|
| 119073 |
+
"step": 17009
|
| 119074 |
+
},
|
| 119075 |
+
{
|
| 119076 |
+
"epoch": 19.373789173789174,
|
| 119077 |
+
"grad_norm": 0.18114197254180908,
|
| 119078 |
+
"learning_rate": 1.3169543355042723e-07,
|
| 119079 |
+
"loss": 0.7466,
|
| 119080 |
+
"step": 17010
|
| 119081 |
+
},
|
| 119082 |
+
{
|
| 119083 |
+
"epoch": 19.374928774928776,
|
| 119084 |
+
"grad_norm": 0.19962655007839203,
|
| 119085 |
+
"learning_rate": 1.3121826220601207e-07,
|
| 119086 |
+
"loss": 0.5502,
|
| 119087 |
+
"step": 17011
|
| 119088 |
+
},
|
| 119089 |
+
{
|
| 119090 |
+
"epoch": 19.376068376068375,
|
| 119091 |
+
"grad_norm": 0.18108335137367249,
|
| 119092 |
+
"learning_rate": 1.3074195462277617e-07,
|
| 119093 |
+
"loss": 0.7512,
|
| 119094 |
+
"step": 17012
|
| 119095 |
+
},
|
| 119096 |
+
{
|
| 119097 |
+
"epoch": 19.377207977207977,
|
| 119098 |
+
"grad_norm": 0.20177017152309418,
|
| 119099 |
+
"learning_rate": 1.302665108172618e-07,
|
| 119100 |
+
"loss": 0.7553,
|
| 119101 |
+
"step": 17013
|
| 119102 |
+
},
|
| 119103 |
+
{
|
| 119104 |
+
"epoch": 19.37834757834758,
|
| 119105 |
+
"grad_norm": 0.2146926075220108,
|
| 119106 |
+
"learning_rate": 1.2979193080598363e-07,
|
| 119107 |
+
"loss": 0.3559,
|
| 119108 |
+
"step": 17014
|
| 119109 |
+
},
|
| 119110 |
+
{
|
| 119111 |
+
"epoch": 19.379487179487178,
|
| 119112 |
+
"grad_norm": 0.22491852939128876,
|
| 119113 |
+
"learning_rate": 1.2931821460542837e-07,
|
| 119114 |
+
"loss": 0.7937,
|
| 119115 |
+
"step": 17015
|
| 119116 |
+
},
|
| 119117 |
+
{
|
| 119118 |
+
"epoch": 19.38062678062678,
|
| 119119 |
+
"grad_norm": 0.18990732729434967,
|
| 119120 |
+
"learning_rate": 1.2884536223204124e-07,
|
| 119121 |
+
"loss": 0.6904,
|
| 119122 |
+
"step": 17016
|
| 119123 |
+
},
|
| 119124 |
+
{
|
| 119125 |
+
"epoch": 19.381766381766383,
|
| 119126 |
+
"grad_norm": 0.1621163934469223,
|
| 119127 |
+
"learning_rate": 1.2837337370225356e-07,
|
| 119128 |
+
"loss": 0.3372,
|
| 119129 |
+
"step": 17017
|
| 119130 |
+
},
|
| 119131 |
+
{
|
| 119132 |
+
"epoch": 19.38290598290598,
|
| 119133 |
+
"grad_norm": 0.1749613732099533,
|
| 119134 |
+
"learning_rate": 1.2790224903245495e-07,
|
| 119135 |
+
"loss": 0.5611,
|
| 119136 |
+
"step": 17018
|
| 119137 |
+
},
|
| 119138 |
+
{
|
| 119139 |
+
"epoch": 19.384045584045584,
|
| 119140 |
+
"grad_norm": 0.19548732042312622,
|
| 119141 |
+
"learning_rate": 1.2743198823901293e-07,
|
| 119142 |
+
"loss": 0.7064,
|
| 119143 |
+
"step": 17019
|
| 119144 |
+
},
|
| 119145 |
+
{
|
| 119146 |
+
"epoch": 19.385185185185186,
|
| 119147 |
+
"grad_norm": 0.20567107200622559,
|
| 119148 |
+
"learning_rate": 1.2696259133825329e-07,
|
| 119149 |
+
"loss": 0.6203,
|
| 119150 |
+
"step": 17020
|
| 119151 |
+
},
|
| 119152 |
+
{
|
| 119153 |
+
"epoch": 19.386324786324785,
|
| 119154 |
+
"grad_norm": 0.20791058242321014,
|
| 119155 |
+
"learning_rate": 1.2649405834648798e-07,
|
| 119156 |
+
"loss": 0.8267,
|
| 119157 |
+
"step": 17021
|
| 119158 |
+
},
|
| 119159 |
+
{
|
| 119160 |
+
"epoch": 19.387464387464387,
|
| 119161 |
+
"grad_norm": 0.20129592716693878,
|
| 119162 |
+
"learning_rate": 1.260263892799818e-07,
|
| 119163 |
+
"loss": 0.874,
|
| 119164 |
+
"step": 17022
|
| 119165 |
+
},
|
| 119166 |
+
{
|
| 119167 |
+
"epoch": 19.38860398860399,
|
| 119168 |
+
"grad_norm": 0.25185975432395935,
|
| 119169 |
+
"learning_rate": 1.2555958415498836e-07,
|
| 119170 |
+
"loss": 0.4448,
|
| 119171 |
+
"step": 17023
|
| 119172 |
+
},
|
| 119173 |
+
{
|
| 119174 |
+
"epoch": 19.38974358974359,
|
| 119175 |
+
"grad_norm": 0.20412062108516693,
|
| 119176 |
+
"learning_rate": 1.2509364298771143e-07,
|
| 119177 |
+
"loss": 0.5128,
|
| 119178 |
+
"step": 17024
|
| 119179 |
+
},
|
| 119180 |
+
{
|
| 119181 |
+
"epoch": 19.39088319088319,
|
| 119182 |
+
"grad_norm": 0.24313119053840637,
|
| 119183 |
+
"learning_rate": 1.2462856579434078e-07,
|
| 119184 |
+
"loss": 0.6976,
|
| 119185 |
+
"step": 17025
|
| 119186 |
+
},
|
| 119187 |
+
{
|
| 119188 |
+
"epoch": 19.392022792022793,
|
| 119189 |
+
"grad_norm": 0.190816268324852,
|
| 119190 |
+
"learning_rate": 1.2416435259102466e-07,
|
| 119191 |
+
"loss": 0.6577,
|
| 119192 |
+
"step": 17026
|
| 119193 |
+
},
|
| 119194 |
+
{
|
| 119195 |
+
"epoch": 19.39316239316239,
|
| 119196 |
+
"grad_norm": 0.17809267342090607,
|
| 119197 |
+
"learning_rate": 1.237010033938918e-07,
|
| 119198 |
+
"loss": 0.6978,
|
| 119199 |
+
"step": 17027
|
| 119200 |
+
},
|
| 119201 |
+
{
|
| 119202 |
+
"epoch": 19.394301994301994,
|
| 119203 |
+
"grad_norm": 0.17608125507831573,
|
| 119204 |
+
"learning_rate": 1.232385182190321e-07,
|
| 119205 |
+
"loss": 0.7697,
|
| 119206 |
+
"step": 17028
|
| 119207 |
+
},
|
| 119208 |
+
{
|
| 119209 |
+
"epoch": 19.395441595441596,
|
| 119210 |
+
"grad_norm": 0.1857132464647293,
|
| 119211 |
+
"learning_rate": 1.227768970825105e-07,
|
| 119212 |
+
"loss": 0.7473,
|
| 119213 |
+
"step": 17029
|
| 119214 |
+
},
|
| 119215 |
+
{
|
| 119216 |
+
"epoch": 19.396581196581195,
|
| 119217 |
+
"grad_norm": 0.18189045786857605,
|
| 119218 |
+
"learning_rate": 1.223161400003614e-07,
|
| 119219 |
+
"loss": 0.7103,
|
| 119220 |
+
"step": 17030
|
| 119221 |
+
},
|
| 119222 |
+
{
|
| 119223 |
+
"epoch": 19.397720797720797,
|
| 119224 |
+
"grad_norm": 0.1787533015012741,
|
| 119225 |
+
"learning_rate": 1.218562469885831e-07,
|
| 119226 |
+
"loss": 0.7709,
|
| 119227 |
+
"step": 17031
|
| 119228 |
+
},
|
| 119229 |
+
{
|
| 119230 |
+
"epoch": 19.3988603988604,
|
| 119231 |
+
"grad_norm": 0.16988062858581543,
|
| 119232 |
+
"learning_rate": 1.2139721806315452e-07,
|
| 119233 |
+
"loss": 0.7394,
|
| 119234 |
+
"step": 17032
|
| 119235 |
+
},
|
| 119236 |
+
{
|
| 119237 |
+
"epoch": 19.4,
|
| 119238 |
+
"grad_norm": 0.1955726146697998,
|
| 119239 |
+
"learning_rate": 1.209390532400184e-07,
|
| 119240 |
+
"loss": 0.7282,
|
| 119241 |
+
"step": 17033
|
| 119242 |
+
},
|
| 119243 |
+
{
|
| 119244 |
+
"epoch": 19.4011396011396,
|
| 119245 |
+
"grad_norm": 0.17550189793109894,
|
| 119246 |
+
"learning_rate": 1.2048175253508433e-07,
|
| 119247 |
+
"loss": 0.6783,
|
| 119248 |
+
"step": 17034
|
| 119249 |
+
},
|
| 119250 |
+
{
|
| 119251 |
+
"epoch": 19.402279202279203,
|
| 119252 |
+
"grad_norm": 0.17031417787075043,
|
| 119253 |
+
"learning_rate": 1.2002531596423949e-07,
|
| 119254 |
+
"loss": 0.5903,
|
| 119255 |
+
"step": 17035
|
| 119256 |
+
},
|
| 119257 |
+
{
|
| 119258 |
+
"epoch": 19.403418803418802,
|
| 119259 |
+
"grad_norm": 0.18011051416397095,
|
| 119260 |
+
"learning_rate": 1.1956974354333516e-07,
|
| 119261 |
+
"loss": 0.8027,
|
| 119262 |
+
"step": 17036
|
| 119263 |
+
},
|
| 119264 |
+
{
|
| 119265 |
+
"epoch": 19.404558404558404,
|
| 119266 |
+
"grad_norm": 0.20305760204792023,
|
| 119267 |
+
"learning_rate": 1.191150352881948e-07,
|
| 119268 |
+
"loss": 0.7499,
|
| 119269 |
+
"step": 17037
|
| 119270 |
+
},
|
| 119271 |
+
{
|
| 119272 |
+
"epoch": 19.405698005698007,
|
| 119273 |
+
"grad_norm": 0.1608572006225586,
|
| 119274 |
+
"learning_rate": 1.1866119121461128e-07,
|
| 119275 |
+
"loss": 0.6855,
|
| 119276 |
+
"step": 17038
|
| 119277 |
+
},
|
| 119278 |
+
{
|
| 119279 |
+
"epoch": 19.406837606837605,
|
| 119280 |
+
"grad_norm": 0.19151221215724945,
|
| 119281 |
+
"learning_rate": 1.182082113383498e-07,
|
| 119282 |
+
"loss": 0.5605,
|
| 119283 |
+
"step": 17039
|
| 119284 |
+
},
|
| 119285 |
+
{
|
| 119286 |
+
"epoch": 19.407977207977208,
|
| 119287 |
+
"grad_norm": 0.2052474319934845,
|
| 119288 |
+
"learning_rate": 1.1775609567513946e-07,
|
| 119289 |
+
"loss": 0.7317,
|
| 119290 |
+
"step": 17040
|
| 119291 |
+
},
|
| 119292 |
+
{
|
| 119293 |
+
"epoch": 19.40911680911681,
|
| 119294 |
+
"grad_norm": 0.21271418035030365,
|
| 119295 |
+
"learning_rate": 1.1730484424068989e-07,
|
| 119296 |
+
"loss": 0.6543,
|
| 119297 |
+
"step": 17041
|
| 119298 |
+
},
|
| 119299 |
+
{
|
| 119300 |
+
"epoch": 19.41025641025641,
|
| 119301 |
+
"grad_norm": 0.20730236172676086,
|
| 119302 |
+
"learning_rate": 1.1685445705066911e-07,
|
| 119303 |
+
"loss": 0.5903,
|
| 119304 |
+
"step": 17042
|
| 119305 |
+
},
|
| 119306 |
+
{
|
| 119307 |
+
"epoch": 19.41139601139601,
|
| 119308 |
+
"grad_norm": 0.3019479513168335,
|
| 119309 |
+
"learning_rate": 1.1640493412072295e-07,
|
| 119310 |
+
"loss": 0.5455,
|
| 119311 |
+
"step": 17043
|
| 119312 |
+
},
|
| 119313 |
+
{
|
| 119314 |
+
"epoch": 19.412535612535613,
|
| 119315 |
+
"grad_norm": 0.2187756597995758,
|
| 119316 |
+
"learning_rate": 1.1595627546646393e-07,
|
| 119317 |
+
"loss": 0.6563,
|
| 119318 |
+
"step": 17044
|
| 119319 |
+
},
|
| 119320 |
+
{
|
| 119321 |
+
"epoch": 19.413675213675212,
|
| 119322 |
+
"grad_norm": 0.21233493089675903,
|
| 119323 |
+
"learning_rate": 1.1550848110347401e-07,
|
| 119324 |
+
"loss": 0.6528,
|
| 119325 |
+
"step": 17045
|
| 119326 |
+
},
|
| 119327 |
+
{
|
| 119328 |
+
"epoch": 19.414814814814815,
|
| 119329 |
+
"grad_norm": 0.2932858467102051,
|
| 119330 |
+
"learning_rate": 1.1506155104730743e-07,
|
| 119331 |
+
"loss": 0.4308,
|
| 119332 |
+
"step": 17046
|
| 119333 |
+
},
|
| 119334 |
+
{
|
| 119335 |
+
"epoch": 19.415954415954417,
|
| 119336 |
+
"grad_norm": 0.21783111989498138,
|
| 119337 |
+
"learning_rate": 1.1461548531348509e-07,
|
| 119338 |
+
"loss": 0.4531,
|
| 119339 |
+
"step": 17047
|
| 119340 |
+
},
|
| 119341 |
+
{
|
| 119342 |
+
"epoch": 19.417094017094016,
|
| 119343 |
+
"grad_norm": 0.17653638124465942,
|
| 119344 |
+
"learning_rate": 1.1417028391750296e-07,
|
| 119345 |
+
"loss": 0.8428,
|
| 119346 |
+
"step": 17048
|
| 119347 |
+
},
|
| 119348 |
+
{
|
| 119349 |
+
"epoch": 19.418233618233618,
|
| 119350 |
+
"grad_norm": 0.19558821618556976,
|
| 119351 |
+
"learning_rate": 1.1372594687482363e-07,
|
| 119352 |
+
"loss": 0.5278,
|
| 119353 |
+
"step": 17049
|
| 119354 |
+
},
|
| 119355 |
+
{
|
| 119356 |
+
"epoch": 19.41937321937322,
|
| 119357 |
+
"grad_norm": 0.18002977967262268,
|
| 119358 |
+
"learning_rate": 1.1328247420088201e-07,
|
| 119359 |
+
"loss": 0.6476,
|
| 119360 |
+
"step": 17050
|
| 119361 |
+
},
|
| 119362 |
+
{
|
| 119363 |
+
"epoch": 19.42051282051282,
|
| 119364 |
+
"grad_norm": 0.2039240598678589,
|
| 119365 |
+
"learning_rate": 1.128398659110741e-07,
|
| 119366 |
+
"loss": 0.6512,
|
| 119367 |
+
"step": 17051
|
| 119368 |
+
},
|
| 119369 |
+
{
|
| 119370 |
+
"epoch": 19.42165242165242,
|
| 119371 |
+
"grad_norm": 0.21624480187892914,
|
| 119372 |
+
"learning_rate": 1.1239812202078204e-07,
|
| 119373 |
+
"loss": 0.5828,
|
| 119374 |
+
"step": 17052
|
| 119375 |
+
},
|
| 119376 |
+
{
|
| 119377 |
+
"epoch": 19.422792022792024,
|
| 119378 |
+
"grad_norm": 0.22936004400253296,
|
| 119379 |
+
"learning_rate": 1.1195724254534356e-07,
|
| 119380 |
+
"loss": 0.4879,
|
| 119381 |
+
"step": 17053
|
| 119382 |
+
},
|
| 119383 |
+
{
|
| 119384 |
+
"epoch": 19.423931623931622,
|
| 119385 |
+
"grad_norm": 0.16383817791938782,
|
| 119386 |
+
"learning_rate": 1.1151722750007143e-07,
|
| 119387 |
+
"loss": 0.7886,
|
| 119388 |
+
"step": 17054
|
| 119389 |
+
},
|
| 119390 |
+
{
|
| 119391 |
+
"epoch": 19.425071225071225,
|
| 119392 |
+
"grad_norm": 0.22113212943077087,
|
| 119393 |
+
"learning_rate": 1.1107807690024785e-07,
|
| 119394 |
+
"loss": 0.6697,
|
| 119395 |
+
"step": 17055
|
| 119396 |
+
},
|
| 119397 |
+
{
|
| 119398 |
+
"epoch": 19.426210826210827,
|
| 119399 |
+
"grad_norm": 0.18560701608657837,
|
| 119400 |
+
"learning_rate": 1.1063979076113006e-07,
|
| 119401 |
+
"loss": 0.6258,
|
| 119402 |
+
"step": 17056
|
| 119403 |
+
},
|
| 119404 |
+
{
|
| 119405 |
+
"epoch": 19.427350427350426,
|
| 119406 |
+
"grad_norm": 0.2129720002412796,
|
| 119407 |
+
"learning_rate": 1.1020236909793646e-07,
|
| 119408 |
+
"loss": 0.644,
|
| 119409 |
+
"step": 17057
|
| 119410 |
+
},
|
| 119411 |
+
{
|
| 119412 |
+
"epoch": 19.428490028490028,
|
| 119413 |
+
"grad_norm": 0.21148735284805298,
|
| 119414 |
+
"learning_rate": 1.0976581192586321e-07,
|
| 119415 |
+
"loss": 0.6784,
|
| 119416 |
+
"step": 17058
|
| 119417 |
+
},
|
| 119418 |
+
{
|
| 119419 |
+
"epoch": 19.42962962962963,
|
| 119420 |
+
"grad_norm": 0.17602939903736115,
|
| 119421 |
+
"learning_rate": 1.0933011926007042e-07,
|
| 119422 |
+
"loss": 0.9103,
|
| 119423 |
+
"step": 17059
|
| 119424 |
+
},
|
| 119425 |
+
{
|
| 119426 |
+
"epoch": 19.43076923076923,
|
| 119427 |
+
"grad_norm": 0.2385375201702118,
|
| 119428 |
+
"learning_rate": 1.0889529111569319e-07,
|
| 119429 |
+
"loss": 0.5282,
|
| 119430 |
+
"step": 17060
|
| 119431 |
+
},
|
| 119432 |
+
{
|
| 119433 |
+
"epoch": 19.43190883190883,
|
| 119434 |
+
"grad_norm": 0.16205713152885437,
|
| 119435 |
+
"learning_rate": 1.0846132750783334e-07,
|
| 119436 |
+
"loss": 0.6132,
|
| 119437 |
+
"step": 17061
|
| 119438 |
+
},
|
| 119439 |
+
{
|
| 119440 |
+
"epoch": 19.433048433048434,
|
| 119441 |
+
"grad_norm": 0.1841961294412613,
|
| 119442 |
+
"learning_rate": 1.0802822845156213e-07,
|
| 119443 |
+
"loss": 0.6327,
|
| 119444 |
+
"step": 17062
|
| 119445 |
+
},
|
| 119446 |
+
{
|
| 119447 |
+
"epoch": 19.434188034188033,
|
| 119448 |
+
"grad_norm": 0.21208113431930542,
|
| 119449 |
+
"learning_rate": 1.0759599396192588e-07,
|
| 119450 |
+
"loss": 0.3572,
|
| 119451 |
+
"step": 17063
|
| 119452 |
+
},
|
| 119453 |
+
{
|
| 119454 |
+
"epoch": 19.435327635327635,
|
| 119455 |
+
"grad_norm": 0.18539439141750336,
|
| 119456 |
+
"learning_rate": 1.0716462405393479e-07,
|
| 119457 |
+
"loss": 0.6487,
|
| 119458 |
+
"step": 17064
|
| 119459 |
+
},
|
| 119460 |
+
{
|
| 119461 |
+
"epoch": 19.436467236467237,
|
| 119462 |
+
"grad_norm": 0.18167999386787415,
|
| 119463 |
+
"learning_rate": 1.0673411874257134e-07,
|
| 119464 |
+
"loss": 0.5201,
|
| 119465 |
+
"step": 17065
|
| 119466 |
+
},
|
| 119467 |
+
{
|
| 119468 |
+
"epoch": 19.437606837606836,
|
| 119469 |
+
"grad_norm": 0.23086227476596832,
|
| 119470 |
+
"learning_rate": 1.0630447804278743e-07,
|
| 119471 |
+
"loss": 0.6721,
|
| 119472 |
+
"step": 17066
|
| 119473 |
+
},
|
| 119474 |
+
{
|
| 119475 |
+
"epoch": 19.43874643874644,
|
| 119476 |
+
"grad_norm": 0.24957765638828278,
|
| 119477 |
+
"learning_rate": 1.0587570196951002e-07,
|
| 119478 |
+
"loss": 0.4445,
|
| 119479 |
+
"step": 17067
|
| 119480 |
+
},
|
| 119481 |
+
{
|
| 119482 |
+
"epoch": 19.43988603988604,
|
| 119483 |
+
"grad_norm": 0.23669400811195374,
|
| 119484 |
+
"learning_rate": 1.0544779053762722e-07,
|
| 119485 |
+
"loss": 0.5032,
|
| 119486 |
+
"step": 17068
|
| 119487 |
+
},
|
| 119488 |
+
{
|
| 119489 |
+
"epoch": 19.44102564102564,
|
| 119490 |
+
"grad_norm": 0.2455901950597763,
|
| 119491 |
+
"learning_rate": 1.0502074376200211e-07,
|
| 119492 |
+
"loss": 0.648,
|
| 119493 |
+
"step": 17069
|
| 119494 |
+
},
|
| 119495 |
+
{
|
| 119496 |
+
"epoch": 19.442165242165242,
|
| 119497 |
+
"grad_norm": 0.16316574811935425,
|
| 119498 |
+
"learning_rate": 1.0459456165746728e-07,
|
| 119499 |
+
"loss": 0.7501,
|
| 119500 |
+
"step": 17070
|
| 119501 |
+
},
|
| 119502 |
+
{
|
| 119503 |
+
"epoch": 19.443304843304844,
|
| 119504 |
+
"grad_norm": 0.22059044241905212,
|
| 119505 |
+
"learning_rate": 1.0416924423882757e-07,
|
| 119506 |
+
"loss": 0.6406,
|
| 119507 |
+
"step": 17071
|
| 119508 |
+
},
|
| 119509 |
+
{
|
| 119510 |
+
"epoch": 19.444444444444443,
|
| 119511 |
+
"grad_norm": 0.19195523858070374,
|
| 119512 |
+
"learning_rate": 1.0374479152085447e-07,
|
| 119513 |
+
"loss": 0.5575,
|
| 119514 |
+
"step": 17072
|
| 119515 |
+
},
|
| 119516 |
+
{
|
| 119517 |
+
"epoch": 19.445584045584045,
|
| 119518 |
+
"grad_norm": 0.1592654287815094,
|
| 119519 |
+
"learning_rate": 1.0332120351828622e-07,
|
| 119520 |
+
"loss": 0.9012,
|
| 119521 |
+
"step": 17073
|
| 119522 |
+
},
|
| 119523 |
+
{
|
| 119524 |
+
"epoch": 19.446723646723648,
|
| 119525 |
+
"grad_norm": 0.18094578385353088,
|
| 119526 |
+
"learning_rate": 1.0289848024584159e-07,
|
| 119527 |
+
"loss": 0.5166,
|
| 119528 |
+
"step": 17074
|
| 119529 |
+
},
|
| 119530 |
+
{
|
| 119531 |
+
"epoch": 19.447863247863246,
|
| 119532 |
+
"grad_norm": 0.21522584557533264,
|
| 119533 |
+
"learning_rate": 1.0247662171820049e-07,
|
| 119534 |
+
"loss": 0.6894,
|
| 119535 |
+
"step": 17075
|
| 119536 |
+
},
|
| 119537 |
+
{
|
| 119538 |
+
"epoch": 19.44900284900285,
|
| 119539 |
+
"grad_norm": 0.16932497918605804,
|
| 119540 |
+
"learning_rate": 1.0205562795001234e-07,
|
| 119541 |
+
"loss": 0.636,
|
| 119542 |
+
"step": 17076
|
| 119543 |
+
},
|
| 119544 |
+
{
|
| 119545 |
+
"epoch": 19.45014245014245,
|
| 119546 |
+
"grad_norm": 0.1994141936302185,
|
| 119547 |
+
"learning_rate": 1.0163549895590429e-07,
|
| 119548 |
+
"loss": 0.5816,
|
| 119549 |
+
"step": 17077
|
| 119550 |
+
},
|
| 119551 |
+
{
|
| 119552 |
+
"epoch": 19.45128205128205,
|
| 119553 |
+
"grad_norm": 0.1876506209373474,
|
| 119554 |
+
"learning_rate": 1.012162347504647e-07,
|
| 119555 |
+
"loss": 0.7251,
|
| 119556 |
+
"step": 17078
|
| 119557 |
+
},
|
| 119558 |
+
{
|
| 119559 |
+
"epoch": 19.452421652421652,
|
| 119560 |
+
"grad_norm": 0.17867793142795563,
|
| 119561 |
+
"learning_rate": 1.0079783534825971e-07,
|
| 119562 |
+
"loss": 0.7104,
|
| 119563 |
+
"step": 17079
|
| 119564 |
+
},
|
| 119565 |
+
{
|
| 119566 |
+
"epoch": 19.453561253561254,
|
| 119567 |
+
"grad_norm": 0.2122046947479248,
|
| 119568 |
+
"learning_rate": 1.0038030076381655e-07,
|
| 119569 |
+
"loss": 0.6158,
|
| 119570 |
+
"step": 17080
|
| 119571 |
+
},
|
| 119572 |
+
{
|
| 119573 |
+
"epoch": 19.454700854700853,
|
| 119574 |
+
"grad_norm": 0.1705094575881958,
|
| 119575 |
+
"learning_rate": 9.996363101163752e-08,
|
| 119576 |
+
"loss": 0.6513,
|
| 119577 |
+
"step": 17081
|
| 119578 |
+
},
|
| 119579 |
+
{
|
| 119580 |
+
"epoch": 19.455840455840455,
|
| 119581 |
+
"grad_norm": 0.1612125188112259,
|
| 119582 |
+
"learning_rate": 9.954782610619995e-08,
|
| 119583 |
+
"loss": 0.6573,
|
| 119584 |
+
"step": 17082
|
| 119585 |
+
},
|
| 119586 |
+
{
|
| 119587 |
+
"epoch": 19.456980056980058,
|
| 119588 |
+
"grad_norm": 0.1886008083820343,
|
| 119589 |
+
"learning_rate": 9.913288606194226e-08,
|
| 119590 |
+
"loss": 0.5259,
|
| 119591 |
+
"step": 17083
|
| 119592 |
+
},
|
| 119593 |
+
{
|
| 119594 |
+
"epoch": 19.458119658119656,
|
| 119595 |
+
"grad_norm": 0.19780634343624115,
|
| 119596 |
+
"learning_rate": 9.871881089327795e-08,
|
| 119597 |
+
"loss": 0.5057,
|
| 119598 |
+
"step": 17084
|
| 119599 |
+
},
|
| 119600 |
+
{
|
| 119601 |
+
"epoch": 19.45925925925926,
|
| 119602 |
+
"grad_norm": 0.24414218962192535,
|
| 119603 |
+
"learning_rate": 9.830560061458716e-08,
|
| 119604 |
+
"loss": 0.5972,
|
| 119605 |
+
"step": 17085
|
| 119606 |
+
},
|
| 119607 |
+
{
|
| 119608 |
+
"epoch": 19.46039886039886,
|
| 119609 |
+
"grad_norm": 0.2200600504875183,
|
| 119610 |
+
"learning_rate": 9.78932552402223e-08,
|
| 119611 |
+
"loss": 0.6678,
|
| 119612 |
+
"step": 17086
|
| 119613 |
+
},
|
| 119614 |
+
{
|
| 119615 |
+
"epoch": 19.46153846153846,
|
| 119616 |
+
"grad_norm": 0.18297740817070007,
|
| 119617 |
+
"learning_rate": 9.748177478450805e-08,
|
| 119618 |
+
"loss": 0.5821,
|
| 119619 |
+
"step": 17087
|
| 119620 |
+
},
|
| 119621 |
+
{
|
| 119622 |
+
"epoch": 19.462678062678062,
|
| 119623 |
+
"grad_norm": 0.1705702394247055,
|
| 119624 |
+
"learning_rate": 9.707115926173293e-08,
|
| 119625 |
+
"loss": 0.6605,
|
| 119626 |
+
"step": 17088
|
| 119627 |
+
},
|
| 119628 |
+
{
|
| 119629 |
+
"epoch": 19.463817663817665,
|
| 119630 |
+
"grad_norm": 0.20623593032360077,
|
| 119631 |
+
"learning_rate": 9.666140868615781e-08,
|
| 119632 |
+
"loss": 0.5991,
|
| 119633 |
+
"step": 17089
|
| 119634 |
+
},
|
| 119635 |
+
{
|
| 119636 |
+
"epoch": 19.464957264957263,
|
| 119637 |
+
"grad_norm": 0.22248166799545288,
|
| 119638 |
+
"learning_rate": 9.625252307201849e-08,
|
| 119639 |
+
"loss": 0.6856,
|
| 119640 |
+
"step": 17090
|
| 119641 |
+
},
|
| 119642 |
+
{
|
| 119643 |
+
"epoch": 19.466096866096866,
|
| 119644 |
+
"grad_norm": 0.17112231254577637,
|
| 119645 |
+
"learning_rate": 9.584450243351472e-08,
|
| 119646 |
+
"loss": 0.4216,
|
| 119647 |
+
"step": 17091
|
| 119648 |
+
},
|
| 119649 |
+
{
|
| 119650 |
+
"epoch": 19.467236467236468,
|
| 119651 |
+
"grad_norm": 0.192648783326149,
|
| 119652 |
+
"learning_rate": 9.543734678481575e-08,
|
| 119653 |
+
"loss": 0.4736,
|
| 119654 |
+
"step": 17092
|
| 119655 |
+
},
|
| 119656 |
+
{
|
| 119657 |
+
"epoch": 19.468376068376067,
|
| 119658 |
+
"grad_norm": 0.1831110119819641,
|
| 119659 |
+
"learning_rate": 9.50310561400658e-08,
|
| 119660 |
+
"loss": 0.6742,
|
| 119661 |
+
"step": 17093
|
| 119662 |
+
},
|
| 119663 |
+
{
|
| 119664 |
+
"epoch": 19.46951566951567,
|
| 119665 |
+
"grad_norm": 0.17312107980251312,
|
| 119666 |
+
"learning_rate": 9.462563051337858e-08,
|
| 119667 |
+
"loss": 0.5684,
|
| 119668 |
+
"step": 17094
|
| 119669 |
+
},
|
| 119670 |
+
{
|
| 119671 |
+
"epoch": 19.47065527065527,
|
| 119672 |
+
"grad_norm": 0.2026345431804657,
|
| 119673 |
+
"learning_rate": 9.422106991883173e-08,
|
| 119674 |
+
"loss": 0.7492,
|
| 119675 |
+
"step": 17095
|
| 119676 |
+
},
|
| 119677 |
+
{
|
| 119678 |
+
"epoch": 19.47179487179487,
|
| 119679 |
+
"grad_norm": 0.21089421212673187,
|
| 119680 |
+
"learning_rate": 9.381737437047788e-08,
|
| 119681 |
+
"loss": 0.6088,
|
| 119682 |
+
"step": 17096
|
| 119683 |
+
},
|
| 119684 |
+
{
|
| 119685 |
+
"epoch": 19.472934472934472,
|
| 119686 |
+
"grad_norm": 0.20423763990402222,
|
| 119687 |
+
"learning_rate": 9.341454388234194e-08,
|
| 119688 |
+
"loss": 0.7286,
|
| 119689 |
+
"step": 17097
|
| 119690 |
+
},
|
| 119691 |
+
{
|
| 119692 |
+
"epoch": 19.474074074074075,
|
| 119693 |
+
"grad_norm": 0.17863865196704865,
|
| 119694 |
+
"learning_rate": 9.301257846840994e-08,
|
| 119695 |
+
"loss": 0.7831,
|
| 119696 |
+
"step": 17098
|
| 119697 |
+
},
|
| 119698 |
+
{
|
| 119699 |
+
"epoch": 19.475213675213674,
|
| 119700 |
+
"grad_norm": 0.17470353841781616,
|
| 119701 |
+
"learning_rate": 9.26114781426457e-08,
|
| 119702 |
+
"loss": 0.6797,
|
| 119703 |
+
"step": 17099
|
| 119704 |
+
},
|
| 119705 |
+
{
|
| 119706 |
+
"epoch": 19.476353276353276,
|
| 119707 |
+
"grad_norm": 0.24701328575611115,
|
| 119708 |
+
"learning_rate": 9.221124291897976e-08,
|
| 119709 |
+
"loss": 0.3647,
|
| 119710 |
+
"step": 17100
|
| 119711 |
}
|
| 119712 |
],
|
| 119713 |
"logging_steps": 1,
|
|
|
|
| 119727 |
"attributes": {}
|
| 119728 |
}
|
| 119729 |
},
|
| 119730 |
+
"total_flos": 9.560943229712302e+19,
|
| 119731 |
"train_batch_size": 8,
|
| 119732 |
"trial_name": null,
|
| 119733 |
"trial_params": null
|