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 10200, 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 sha256:1de1bd4debf7b87820f4b8c75ddd37a1ef98b3a8c5819b0fab118a0f3ce973e7
|
| 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 sha256:7a6b626135383d5868a24c42e49f41d7b7a0fb1811d5ea194db085bdf4e4abfa
|
| 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:aa16456ec9b2da7bcecdbf58653b49d761c56edd16d0e4fe3b17961043c4b5ff
|
| 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": 11.
|
| 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,
|
|
@@ -69308,6 +69308,2106 @@
|
|
| 69308 |
"learning_rate": 2.14362596339079e-05,
|
| 69309 |
"loss": 0.6508,
|
| 69310 |
"step": 9900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69311 |
}
|
| 69312 |
],
|
| 69313 |
"logging_steps": 1,
|
|
@@ -69327,7 +71427,7 @@
|
|
| 69327 |
"attributes": {}
|
| 69328 |
}
|
| 69329 |
},
|
| 69330 |
-
"total_flos": 5.
|
| 69331 |
"train_batch_size": 8,
|
| 69332 |
"trial_name": null,
|
| 69333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.617663817663818,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 10200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 69308 |
"learning_rate": 2.14362596339079e-05,
|
| 69309 |
"loss": 0.6508,
|
| 69310 |
"step": 9900
|
| 69311 |
+
},
|
| 69312 |
+
{
|
| 69313 |
+
"epoch": 11.276923076923078,
|
| 69314 |
+
"grad_norm": 0.2265573889017105,
|
| 69315 |
+
"learning_rate": 2.1431648095844463e-05,
|
| 69316 |
+
"loss": 0.7613,
|
| 69317 |
+
"step": 9901
|
| 69318 |
+
},
|
| 69319 |
+
{
|
| 69320 |
+
"epoch": 11.278062678062678,
|
| 69321 |
+
"grad_norm": 0.2591131031513214,
|
| 69322 |
+
"learning_rate": 2.1427036681719718e-05,
|
| 69323 |
+
"loss": 0.6222,
|
| 69324 |
+
"step": 9902
|
| 69325 |
+
},
|
| 69326 |
+
{
|
| 69327 |
+
"epoch": 11.279202279202279,
|
| 69328 |
+
"grad_norm": 0.23359829187393188,
|
| 69329 |
+
"learning_rate": 2.1422425391693807e-05,
|
| 69330 |
+
"loss": 0.841,
|
| 69331 |
+
"step": 9903
|
| 69332 |
+
},
|
| 69333 |
+
{
|
| 69334 |
+
"epoch": 11.280341880341881,
|
| 69335 |
+
"grad_norm": 0.21924211084842682,
|
| 69336 |
+
"learning_rate": 2.1417814225926908e-05,
|
| 69337 |
+
"loss": 0.8135,
|
| 69338 |
+
"step": 9904
|
| 69339 |
+
},
|
| 69340 |
+
{
|
| 69341 |
+
"epoch": 11.281481481481482,
|
| 69342 |
+
"grad_norm": 0.19912149012088776,
|
| 69343 |
+
"learning_rate": 2.141320318457916e-05,
|
| 69344 |
+
"loss": 0.7128,
|
| 69345 |
+
"step": 9905
|
| 69346 |
+
},
|
| 69347 |
+
{
|
| 69348 |
+
"epoch": 11.282621082621082,
|
| 69349 |
+
"grad_norm": 0.22762812674045563,
|
| 69350 |
+
"learning_rate": 2.1408592267810742e-05,
|
| 69351 |
+
"loss": 0.7108,
|
| 69352 |
+
"step": 9906
|
| 69353 |
+
},
|
| 69354 |
+
{
|
| 69355 |
+
"epoch": 11.283760683760685,
|
| 69356 |
+
"grad_norm": 0.1968327760696411,
|
| 69357 |
+
"learning_rate": 2.1403981475781783e-05,
|
| 69358 |
+
"loss": 0.7217,
|
| 69359 |
+
"step": 9907
|
| 69360 |
+
},
|
| 69361 |
+
{
|
| 69362 |
+
"epoch": 11.284900284900285,
|
| 69363 |
+
"grad_norm": 0.2060253620147705,
|
| 69364 |
+
"learning_rate": 2.1399370808652443e-05,
|
| 69365 |
+
"loss": 0.7564,
|
| 69366 |
+
"step": 9908
|
| 69367 |
+
},
|
| 69368 |
+
{
|
| 69369 |
+
"epoch": 11.286039886039886,
|
| 69370 |
+
"grad_norm": 0.17061100900173187,
|
| 69371 |
+
"learning_rate": 2.139476026658285e-05,
|
| 69372 |
+
"loss": 0.8732,
|
| 69373 |
+
"step": 9909
|
| 69374 |
+
},
|
| 69375 |
+
{
|
| 69376 |
+
"epoch": 11.287179487179488,
|
| 69377 |
+
"grad_norm": 0.18478287756443024,
|
| 69378 |
+
"learning_rate": 2.139014984973315e-05,
|
| 69379 |
+
"loss": 0.6568,
|
| 69380 |
+
"step": 9910
|
| 69381 |
+
},
|
| 69382 |
+
{
|
| 69383 |
+
"epoch": 11.288319088319088,
|
| 69384 |
+
"grad_norm": 0.1702798455953598,
|
| 69385 |
+
"learning_rate": 2.138553955826347e-05,
|
| 69386 |
+
"loss": 0.7676,
|
| 69387 |
+
"step": 9911
|
| 69388 |
+
},
|
| 69389 |
+
{
|
| 69390 |
+
"epoch": 11.289458689458689,
|
| 69391 |
+
"grad_norm": 0.2569606900215149,
|
| 69392 |
+
"learning_rate": 2.1380929392333938e-05,
|
| 69393 |
+
"loss": 0.6848,
|
| 69394 |
+
"step": 9912
|
| 69395 |
+
},
|
| 69396 |
+
{
|
| 69397 |
+
"epoch": 11.290598290598291,
|
| 69398 |
+
"grad_norm": 0.16441692411899567,
|
| 69399 |
+
"learning_rate": 2.1376319352104687e-05,
|
| 69400 |
+
"loss": 0.8524,
|
| 69401 |
+
"step": 9913
|
| 69402 |
+
},
|
| 69403 |
+
{
|
| 69404 |
+
"epoch": 11.291737891737892,
|
| 69405 |
+
"grad_norm": 0.23033924400806427,
|
| 69406 |
+
"learning_rate": 2.1371709437735828e-05,
|
| 69407 |
+
"loss": 0.6069,
|
| 69408 |
+
"step": 9914
|
| 69409 |
+
},
|
| 69410 |
+
{
|
| 69411 |
+
"epoch": 11.292877492877492,
|
| 69412 |
+
"grad_norm": 0.18105411529541016,
|
| 69413 |
+
"learning_rate": 2.136709964938748e-05,
|
| 69414 |
+
"loss": 0.7156,
|
| 69415 |
+
"step": 9915
|
| 69416 |
+
},
|
| 69417 |
+
{
|
| 69418 |
+
"epoch": 11.294017094017095,
|
| 69419 |
+
"grad_norm": 0.26649007201194763,
|
| 69420 |
+
"learning_rate": 2.136248998721975e-05,
|
| 69421 |
+
"loss": 0.5712,
|
| 69422 |
+
"step": 9916
|
| 69423 |
+
},
|
| 69424 |
+
{
|
| 69425 |
+
"epoch": 11.295156695156695,
|
| 69426 |
+
"grad_norm": 0.19740529358386993,
|
| 69427 |
+
"learning_rate": 2.135788045139275e-05,
|
| 69428 |
+
"loss": 0.7514,
|
| 69429 |
+
"step": 9917
|
| 69430 |
+
},
|
| 69431 |
+
{
|
| 69432 |
+
"epoch": 11.296296296296296,
|
| 69433 |
+
"grad_norm": 0.21046902239322662,
|
| 69434 |
+
"learning_rate": 2.135327104206657e-05,
|
| 69435 |
+
"loss": 0.7903,
|
| 69436 |
+
"step": 9918
|
| 69437 |
+
},
|
| 69438 |
+
{
|
| 69439 |
+
"epoch": 11.297435897435898,
|
| 69440 |
+
"grad_norm": 0.25303810834884644,
|
| 69441 |
+
"learning_rate": 2.1348661759401325e-05,
|
| 69442 |
+
"loss": 0.6965,
|
| 69443 |
+
"step": 9919
|
| 69444 |
+
},
|
| 69445 |
+
{
|
| 69446 |
+
"epoch": 11.298575498575499,
|
| 69447 |
+
"grad_norm": 0.20778560638427734,
|
| 69448 |
+
"learning_rate": 2.134405260355709e-05,
|
| 69449 |
+
"loss": 0.6021,
|
| 69450 |
+
"step": 9920
|
| 69451 |
+
},
|
| 69452 |
+
{
|
| 69453 |
+
"epoch": 11.2997150997151,
|
| 69454 |
+
"grad_norm": 0.20996792614459991,
|
| 69455 |
+
"learning_rate": 2.1339443574693967e-05,
|
| 69456 |
+
"loss": 0.7712,
|
| 69457 |
+
"step": 9921
|
| 69458 |
+
},
|
| 69459 |
+
{
|
| 69460 |
+
"epoch": 11.300854700854702,
|
| 69461 |
+
"grad_norm": 0.2482452243566513,
|
| 69462 |
+
"learning_rate": 2.133483467297203e-05,
|
| 69463 |
+
"loss": 0.6228,
|
| 69464 |
+
"step": 9922
|
| 69465 |
+
},
|
| 69466 |
+
{
|
| 69467 |
+
"epoch": 11.301994301994302,
|
| 69468 |
+
"grad_norm": 0.20021946728229523,
|
| 69469 |
+
"learning_rate": 2.133022589855136e-05,
|
| 69470 |
+
"loss": 0.629,
|
| 69471 |
+
"step": 9923
|
| 69472 |
+
},
|
| 69473 |
+
{
|
| 69474 |
+
"epoch": 11.303133903133903,
|
| 69475 |
+
"grad_norm": 0.21196231245994568,
|
| 69476 |
+
"learning_rate": 2.132561725159205e-05,
|
| 69477 |
+
"loss": 0.7473,
|
| 69478 |
+
"step": 9924
|
| 69479 |
+
},
|
| 69480 |
+
{
|
| 69481 |
+
"epoch": 11.304273504273505,
|
| 69482 |
+
"grad_norm": 0.15690581500530243,
|
| 69483 |
+
"learning_rate": 2.132100873225415e-05,
|
| 69484 |
+
"loss": 0.866,
|
| 69485 |
+
"step": 9925
|
| 69486 |
+
},
|
| 69487 |
+
{
|
| 69488 |
+
"epoch": 11.305413105413106,
|
| 69489 |
+
"grad_norm": 0.19401024281978607,
|
| 69490 |
+
"learning_rate": 2.1316400340697737e-05,
|
| 69491 |
+
"loss": 0.7815,
|
| 69492 |
+
"step": 9926
|
| 69493 |
+
},
|
| 69494 |
+
{
|
| 69495 |
+
"epoch": 11.306552706552706,
|
| 69496 |
+
"grad_norm": 0.2112329602241516,
|
| 69497 |
+
"learning_rate": 2.1311792077082864e-05,
|
| 69498 |
+
"loss": 0.7375,
|
| 69499 |
+
"step": 9927
|
| 69500 |
+
},
|
| 69501 |
+
{
|
| 69502 |
+
"epoch": 11.307692307692308,
|
| 69503 |
+
"grad_norm": 0.1995096653699875,
|
| 69504 |
+
"learning_rate": 2.13071839415696e-05,
|
| 69505 |
+
"loss": 0.8467,
|
| 69506 |
+
"step": 9928
|
| 69507 |
+
},
|
| 69508 |
+
{
|
| 69509 |
+
"epoch": 11.308831908831909,
|
| 69510 |
+
"grad_norm": 0.17122425138950348,
|
| 69511 |
+
"learning_rate": 2.130257593431799e-05,
|
| 69512 |
+
"loss": 0.8192,
|
| 69513 |
+
"step": 9929
|
| 69514 |
+
},
|
| 69515 |
+
{
|
| 69516 |
+
"epoch": 11.30997150997151,
|
| 69517 |
+
"grad_norm": 0.2505601644515991,
|
| 69518 |
+
"learning_rate": 2.1297968055488092e-05,
|
| 69519 |
+
"loss": 0.5322,
|
| 69520 |
+
"step": 9930
|
| 69521 |
+
},
|
| 69522 |
+
{
|
| 69523 |
+
"epoch": 11.311111111111112,
|
| 69524 |
+
"grad_norm": 0.26188337802886963,
|
| 69525 |
+
"learning_rate": 2.129336030523994e-05,
|
| 69526 |
+
"loss": 0.4682,
|
| 69527 |
+
"step": 9931
|
| 69528 |
+
},
|
| 69529 |
+
{
|
| 69530 |
+
"epoch": 11.312250712250712,
|
| 69531 |
+
"grad_norm": 0.2111901044845581,
|
| 69532 |
+
"learning_rate": 2.128875268373358e-05,
|
| 69533 |
+
"loss": 0.6826,
|
| 69534 |
+
"step": 9932
|
| 69535 |
+
},
|
| 69536 |
+
{
|
| 69537 |
+
"epoch": 11.313390313390313,
|
| 69538 |
+
"grad_norm": 0.21512557566165924,
|
| 69539 |
+
"learning_rate": 2.128414519112904e-05,
|
| 69540 |
+
"loss": 0.6091,
|
| 69541 |
+
"step": 9933
|
| 69542 |
+
},
|
| 69543 |
+
{
|
| 69544 |
+
"epoch": 11.314529914529915,
|
| 69545 |
+
"grad_norm": 0.2135426253080368,
|
| 69546 |
+
"learning_rate": 2.1279537827586355e-05,
|
| 69547 |
+
"loss": 0.512,
|
| 69548 |
+
"step": 9934
|
| 69549 |
+
},
|
| 69550 |
+
{
|
| 69551 |
+
"epoch": 11.315669515669516,
|
| 69552 |
+
"grad_norm": 0.19052626192569733,
|
| 69553 |
+
"learning_rate": 2.1274930593265553e-05,
|
| 69554 |
+
"loss": 0.9078,
|
| 69555 |
+
"step": 9935
|
| 69556 |
+
},
|
| 69557 |
+
{
|
| 69558 |
+
"epoch": 11.316809116809116,
|
| 69559 |
+
"grad_norm": 0.21458658576011658,
|
| 69560 |
+
"learning_rate": 2.1270323488326662e-05,
|
| 69561 |
+
"loss": 0.7339,
|
| 69562 |
+
"step": 9936
|
| 69563 |
+
},
|
| 69564 |
+
{
|
| 69565 |
+
"epoch": 11.317948717948719,
|
| 69566 |
+
"grad_norm": 0.25585073232650757,
|
| 69567 |
+
"learning_rate": 2.1265716512929687e-05,
|
| 69568 |
+
"loss": 0.5645,
|
| 69569 |
+
"step": 9937
|
| 69570 |
+
},
|
| 69571 |
+
{
|
| 69572 |
+
"epoch": 11.31908831908832,
|
| 69573 |
+
"grad_norm": 0.21846206486225128,
|
| 69574 |
+
"learning_rate": 2.1261109667234656e-05,
|
| 69575 |
+
"loss": 0.7172,
|
| 69576 |
+
"step": 9938
|
| 69577 |
+
},
|
| 69578 |
+
{
|
| 69579 |
+
"epoch": 11.32022792022792,
|
| 69580 |
+
"grad_norm": 0.16231784224510193,
|
| 69581 |
+
"learning_rate": 2.1256502951401556e-05,
|
| 69582 |
+
"loss": 0.7898,
|
| 69583 |
+
"step": 9939
|
| 69584 |
+
},
|
| 69585 |
+
{
|
| 69586 |
+
"epoch": 11.321367521367522,
|
| 69587 |
+
"grad_norm": 0.24106508493423462,
|
| 69588 |
+
"learning_rate": 2.1251896365590416e-05,
|
| 69589 |
+
"loss": 0.7337,
|
| 69590 |
+
"step": 9940
|
| 69591 |
+
},
|
| 69592 |
+
{
|
| 69593 |
+
"epoch": 11.322507122507123,
|
| 69594 |
+
"grad_norm": 0.18453285098075867,
|
| 69595 |
+
"learning_rate": 2.1247289909961213e-05,
|
| 69596 |
+
"loss": 0.7732,
|
| 69597 |
+
"step": 9941
|
| 69598 |
+
},
|
| 69599 |
+
{
|
| 69600 |
+
"epoch": 11.323646723646723,
|
| 69601 |
+
"grad_norm": 0.22222761809825897,
|
| 69602 |
+
"learning_rate": 2.1242683584673954e-05,
|
| 69603 |
+
"loss": 0.5541,
|
| 69604 |
+
"step": 9942
|
| 69605 |
+
},
|
| 69606 |
+
{
|
| 69607 |
+
"epoch": 11.324786324786325,
|
| 69608 |
+
"grad_norm": 0.2011951208114624,
|
| 69609 |
+
"learning_rate": 2.1238077389888628e-05,
|
| 69610 |
+
"loss": 0.6079,
|
| 69611 |
+
"step": 9943
|
| 69612 |
+
},
|
| 69613 |
+
{
|
| 69614 |
+
"epoch": 11.325925925925926,
|
| 69615 |
+
"grad_norm": 0.22160476446151733,
|
| 69616 |
+
"learning_rate": 2.123347132576522e-05,
|
| 69617 |
+
"loss": 0.46,
|
| 69618 |
+
"step": 9944
|
| 69619 |
+
},
|
| 69620 |
+
{
|
| 69621 |
+
"epoch": 11.327065527065526,
|
| 69622 |
+
"grad_norm": 0.1950511336326599,
|
| 69623 |
+
"learning_rate": 2.1228865392463704e-05,
|
| 69624 |
+
"loss": 0.6339,
|
| 69625 |
+
"step": 9945
|
| 69626 |
+
},
|
| 69627 |
+
{
|
| 69628 |
+
"epoch": 11.328205128205129,
|
| 69629 |
+
"grad_norm": 0.20166008174419403,
|
| 69630 |
+
"learning_rate": 2.1224259590144067e-05,
|
| 69631 |
+
"loss": 0.905,
|
| 69632 |
+
"step": 9946
|
| 69633 |
+
},
|
| 69634 |
+
{
|
| 69635 |
+
"epoch": 11.32934472934473,
|
| 69636 |
+
"grad_norm": 0.23275083303451538,
|
| 69637 |
+
"learning_rate": 2.1219653918966283e-05,
|
| 69638 |
+
"loss": 0.7707,
|
| 69639 |
+
"step": 9947
|
| 69640 |
+
},
|
| 69641 |
+
{
|
| 69642 |
+
"epoch": 11.33048433048433,
|
| 69643 |
+
"grad_norm": 0.2161443531513214,
|
| 69644 |
+
"learning_rate": 2.1215048379090308e-05,
|
| 69645 |
+
"loss": 0.6015,
|
| 69646 |
+
"step": 9948
|
| 69647 |
+
},
|
| 69648 |
+
{
|
| 69649 |
+
"epoch": 11.331623931623932,
|
| 69650 |
+
"grad_norm": 0.17823894321918488,
|
| 69651 |
+
"learning_rate": 2.1210442970676116e-05,
|
| 69652 |
+
"loss": 0.749,
|
| 69653 |
+
"step": 9949
|
| 69654 |
+
},
|
| 69655 |
+
{
|
| 69656 |
+
"epoch": 11.332763532763533,
|
| 69657 |
+
"grad_norm": 0.2397448718547821,
|
| 69658 |
+
"learning_rate": 2.120583769388366e-05,
|
| 69659 |
+
"loss": 0.6788,
|
| 69660 |
+
"step": 9950
|
| 69661 |
+
},
|
| 69662 |
+
{
|
| 69663 |
+
"epoch": 11.333903133903133,
|
| 69664 |
+
"grad_norm": 0.17530478537082672,
|
| 69665 |
+
"learning_rate": 2.1201232548872895e-05,
|
| 69666 |
+
"loss": 1.0001,
|
| 69667 |
+
"step": 9951
|
| 69668 |
+
},
|
| 69669 |
+
{
|
| 69670 |
+
"epoch": 11.335042735042736,
|
| 69671 |
+
"grad_norm": 0.3379182517528534,
|
| 69672 |
+
"learning_rate": 2.119662753580377e-05,
|
| 69673 |
+
"loss": 0.6362,
|
| 69674 |
+
"step": 9952
|
| 69675 |
+
},
|
| 69676 |
+
{
|
| 69677 |
+
"epoch": 11.336182336182336,
|
| 69678 |
+
"grad_norm": 0.204105406999588,
|
| 69679 |
+
"learning_rate": 2.119202265483623e-05,
|
| 69680 |
+
"loss": 0.758,
|
| 69681 |
+
"step": 9953
|
| 69682 |
+
},
|
| 69683 |
+
{
|
| 69684 |
+
"epoch": 11.337321937321937,
|
| 69685 |
+
"grad_norm": 0.27438604831695557,
|
| 69686 |
+
"learning_rate": 2.1187417906130212e-05,
|
| 69687 |
+
"loss": 0.5061,
|
| 69688 |
+
"step": 9954
|
| 69689 |
+
},
|
| 69690 |
+
{
|
| 69691 |
+
"epoch": 11.338461538461539,
|
| 69692 |
+
"grad_norm": 0.2232668250799179,
|
| 69693 |
+
"learning_rate": 2.1182813289845664e-05,
|
| 69694 |
+
"loss": 0.6069,
|
| 69695 |
+
"step": 9955
|
| 69696 |
+
},
|
| 69697 |
+
{
|
| 69698 |
+
"epoch": 11.33960113960114,
|
| 69699 |
+
"grad_norm": 0.20483927428722382,
|
| 69700 |
+
"learning_rate": 2.1178208806142495e-05,
|
| 69701 |
+
"loss": 0.7208,
|
| 69702 |
+
"step": 9956
|
| 69703 |
+
},
|
| 69704 |
+
{
|
| 69705 |
+
"epoch": 11.34074074074074,
|
| 69706 |
+
"grad_norm": 0.21186719834804535,
|
| 69707 |
+
"learning_rate": 2.1173604455180646e-05,
|
| 69708 |
+
"loss": 0.6007,
|
| 69709 |
+
"step": 9957
|
| 69710 |
+
},
|
| 69711 |
+
{
|
| 69712 |
+
"epoch": 11.341880341880342,
|
| 69713 |
+
"grad_norm": 0.17334899306297302,
|
| 69714 |
+
"learning_rate": 2.1169000237120047e-05,
|
| 69715 |
+
"loss": 0.6903,
|
| 69716 |
+
"step": 9958
|
| 69717 |
+
},
|
| 69718 |
+
{
|
| 69719 |
+
"epoch": 11.343019943019943,
|
| 69720 |
+
"grad_norm": 0.20546293258666992,
|
| 69721 |
+
"learning_rate": 2.1164396152120594e-05,
|
| 69722 |
+
"loss": 0.5858,
|
| 69723 |
+
"step": 9959
|
| 69724 |
+
},
|
| 69725 |
+
{
|
| 69726 |
+
"epoch": 11.344159544159544,
|
| 69727 |
+
"grad_norm": 0.2439803183078766,
|
| 69728 |
+
"learning_rate": 2.115979220034222e-05,
|
| 69729 |
+
"loss": 0.6547,
|
| 69730 |
+
"step": 9960
|
| 69731 |
+
},
|
| 69732 |
+
{
|
| 69733 |
+
"epoch": 11.345299145299146,
|
| 69734 |
+
"grad_norm": 0.21434029936790466,
|
| 69735 |
+
"learning_rate": 2.115518838194482e-05,
|
| 69736 |
+
"loss": 0.5725,
|
| 69737 |
+
"step": 9961
|
| 69738 |
+
},
|
| 69739 |
+
{
|
| 69740 |
+
"epoch": 11.346438746438746,
|
| 69741 |
+
"grad_norm": 0.22616712749004364,
|
| 69742 |
+
"learning_rate": 2.1150584697088302e-05,
|
| 69743 |
+
"loss": 0.5493,
|
| 69744 |
+
"step": 9962
|
| 69745 |
+
},
|
| 69746 |
+
{
|
| 69747 |
+
"epoch": 11.347578347578347,
|
| 69748 |
+
"grad_norm": 0.2434915006160736,
|
| 69749 |
+
"learning_rate": 2.1145981145932557e-05,
|
| 69750 |
+
"loss": 0.5391,
|
| 69751 |
+
"step": 9963
|
| 69752 |
+
},
|
| 69753 |
+
{
|
| 69754 |
+
"epoch": 11.34871794871795,
|
| 69755 |
+
"grad_norm": 0.19631722569465637,
|
| 69756 |
+
"learning_rate": 2.1141377728637495e-05,
|
| 69757 |
+
"loss": 0.7343,
|
| 69758 |
+
"step": 9964
|
| 69759 |
+
},
|
| 69760 |
+
{
|
| 69761 |
+
"epoch": 11.34985754985755,
|
| 69762 |
+
"grad_norm": 0.1945822387933731,
|
| 69763 |
+
"learning_rate": 2.1136774445362988e-05,
|
| 69764 |
+
"loss": 0.7902,
|
| 69765 |
+
"step": 9965
|
| 69766 |
+
},
|
| 69767 |
+
{
|
| 69768 |
+
"epoch": 11.35099715099715,
|
| 69769 |
+
"grad_norm": 0.2038748562335968,
|
| 69770 |
+
"learning_rate": 2.1132171296268935e-05,
|
| 69771 |
+
"loss": 0.6883,
|
| 69772 |
+
"step": 9966
|
| 69773 |
+
},
|
| 69774 |
+
{
|
| 69775 |
+
"epoch": 11.352136752136753,
|
| 69776 |
+
"grad_norm": 0.22871534526348114,
|
| 69777 |
+
"learning_rate": 2.1127568281515198e-05,
|
| 69778 |
+
"loss": 0.6013,
|
| 69779 |
+
"step": 9967
|
| 69780 |
+
},
|
| 69781 |
+
{
|
| 69782 |
+
"epoch": 11.353276353276353,
|
| 69783 |
+
"grad_norm": 0.2101345807313919,
|
| 69784 |
+
"learning_rate": 2.1122965401261667e-05,
|
| 69785 |
+
"loss": 0.8981,
|
| 69786 |
+
"step": 9968
|
| 69787 |
+
},
|
| 69788 |
+
{
|
| 69789 |
+
"epoch": 11.354415954415954,
|
| 69790 |
+
"grad_norm": 0.2620834708213806,
|
| 69791 |
+
"learning_rate": 2.1118362655668218e-05,
|
| 69792 |
+
"loss": 0.5471,
|
| 69793 |
+
"step": 9969
|
| 69794 |
+
},
|
| 69795 |
+
{
|
| 69796 |
+
"epoch": 11.355555555555556,
|
| 69797 |
+
"grad_norm": 0.27750974893569946,
|
| 69798 |
+
"learning_rate": 2.1113760044894703e-05,
|
| 69799 |
+
"loss": 0.4879,
|
| 69800 |
+
"step": 9970
|
| 69801 |
+
},
|
| 69802 |
+
{
|
| 69803 |
+
"epoch": 11.356695156695157,
|
| 69804 |
+
"grad_norm": 0.20539726316928864,
|
| 69805 |
+
"learning_rate": 2.1109157569100997e-05,
|
| 69806 |
+
"loss": 0.6741,
|
| 69807 |
+
"step": 9971
|
| 69808 |
+
},
|
| 69809 |
+
{
|
| 69810 |
+
"epoch": 11.357834757834757,
|
| 69811 |
+
"grad_norm": 0.19485247135162354,
|
| 69812 |
+
"learning_rate": 2.110455522844694e-05,
|
| 69813 |
+
"loss": 0.5967,
|
| 69814 |
+
"step": 9972
|
| 69815 |
+
},
|
| 69816 |
+
{
|
| 69817 |
+
"epoch": 11.35897435897436,
|
| 69818 |
+
"grad_norm": 0.1940249800682068,
|
| 69819 |
+
"learning_rate": 2.1099953023092394e-05,
|
| 69820 |
+
"loss": 0.7604,
|
| 69821 |
+
"step": 9973
|
| 69822 |
+
},
|
| 69823 |
+
{
|
| 69824 |
+
"epoch": 11.36011396011396,
|
| 69825 |
+
"grad_norm": 0.20628228783607483,
|
| 69826 |
+
"learning_rate": 2.1095350953197202e-05,
|
| 69827 |
+
"loss": 0.7112,
|
| 69828 |
+
"step": 9974
|
| 69829 |
+
},
|
| 69830 |
+
{
|
| 69831 |
+
"epoch": 11.36125356125356,
|
| 69832 |
+
"grad_norm": 0.2294902205467224,
|
| 69833 |
+
"learning_rate": 2.109074901892121e-05,
|
| 69834 |
+
"loss": 0.6547,
|
| 69835 |
+
"step": 9975
|
| 69836 |
+
},
|
| 69837 |
+
{
|
| 69838 |
+
"epoch": 11.362393162393163,
|
| 69839 |
+
"grad_norm": 0.22965016961097717,
|
| 69840 |
+
"learning_rate": 2.108614722042426e-05,
|
| 69841 |
+
"loss": 0.532,
|
| 69842 |
+
"step": 9976
|
| 69843 |
+
},
|
| 69844 |
+
{
|
| 69845 |
+
"epoch": 11.363532763532763,
|
| 69846 |
+
"grad_norm": 0.19517067074775696,
|
| 69847 |
+
"learning_rate": 2.1081545557866176e-05,
|
| 69848 |
+
"loss": 0.5695,
|
| 69849 |
+
"step": 9977
|
| 69850 |
+
},
|
| 69851 |
+
{
|
| 69852 |
+
"epoch": 11.364672364672364,
|
| 69853 |
+
"grad_norm": 0.17772167921066284,
|
| 69854 |
+
"learning_rate": 2.1076944031406787e-05,
|
| 69855 |
+
"loss": 0.8712,
|
| 69856 |
+
"step": 9978
|
| 69857 |
+
},
|
| 69858 |
+
{
|
| 69859 |
+
"epoch": 11.365811965811966,
|
| 69860 |
+
"grad_norm": 0.19007042050361633,
|
| 69861 |
+
"learning_rate": 2.1072342641205926e-05,
|
| 69862 |
+
"loss": 0.69,
|
| 69863 |
+
"step": 9979
|
| 69864 |
+
},
|
| 69865 |
+
{
|
| 69866 |
+
"epoch": 11.366951566951567,
|
| 69867 |
+
"grad_norm": 0.2111845165491104,
|
| 69868 |
+
"learning_rate": 2.1067741387423404e-05,
|
| 69869 |
+
"loss": 0.7293,
|
| 69870 |
+
"step": 9980
|
| 69871 |
+
},
|
| 69872 |
+
{
|
| 69873 |
+
"epoch": 11.368091168091167,
|
| 69874 |
+
"grad_norm": 0.23049502074718475,
|
| 69875 |
+
"learning_rate": 2.1063140270219042e-05,
|
| 69876 |
+
"loss": 0.71,
|
| 69877 |
+
"step": 9981
|
| 69878 |
+
},
|
| 69879 |
+
{
|
| 69880 |
+
"epoch": 11.36923076923077,
|
| 69881 |
+
"grad_norm": 0.233639195561409,
|
| 69882 |
+
"learning_rate": 2.105853928975264e-05,
|
| 69883 |
+
"loss": 0.5686,
|
| 69884 |
+
"step": 9982
|
| 69885 |
+
},
|
| 69886 |
+
{
|
| 69887 |
+
"epoch": 11.37037037037037,
|
| 69888 |
+
"grad_norm": 0.21934100985527039,
|
| 69889 |
+
"learning_rate": 2.1053938446184013e-05,
|
| 69890 |
+
"loss": 0.6469,
|
| 69891 |
+
"step": 9983
|
| 69892 |
+
},
|
| 69893 |
+
{
|
| 69894 |
+
"epoch": 11.37150997150997,
|
| 69895 |
+
"grad_norm": 0.17151589691638947,
|
| 69896 |
+
"learning_rate": 2.1049337739672947e-05,
|
| 69897 |
+
"loss": 0.7946,
|
| 69898 |
+
"step": 9984
|
| 69899 |
+
},
|
| 69900 |
+
{
|
| 69901 |
+
"epoch": 11.372649572649573,
|
| 69902 |
+
"grad_norm": 0.17608436942100525,
|
| 69903 |
+
"learning_rate": 2.1044737170379254e-05,
|
| 69904 |
+
"loss": 0.8317,
|
| 69905 |
+
"step": 9985
|
| 69906 |
+
},
|
| 69907 |
+
{
|
| 69908 |
+
"epoch": 11.373789173789174,
|
| 69909 |
+
"grad_norm": 0.25941383838653564,
|
| 69910 |
+
"learning_rate": 2.104013673846271e-05,
|
| 69911 |
+
"loss": 0.5901,
|
| 69912 |
+
"step": 9986
|
| 69913 |
+
},
|
| 69914 |
+
{
|
| 69915 |
+
"epoch": 11.374928774928774,
|
| 69916 |
+
"grad_norm": 0.18507154285907745,
|
| 69917 |
+
"learning_rate": 2.1035536444083112e-05,
|
| 69918 |
+
"loss": 0.62,
|
| 69919 |
+
"step": 9987
|
| 69920 |
+
},
|
| 69921 |
+
{
|
| 69922 |
+
"epoch": 11.376068376068377,
|
| 69923 |
+
"grad_norm": 0.23103323578834534,
|
| 69924 |
+
"learning_rate": 2.103093628740023e-05,
|
| 69925 |
+
"loss": 0.7076,
|
| 69926 |
+
"step": 9988
|
| 69927 |
+
},
|
| 69928 |
+
{
|
| 69929 |
+
"epoch": 11.377207977207977,
|
| 69930 |
+
"grad_norm": 0.25450006127357483,
|
| 69931 |
+
"learning_rate": 2.1026336268573843e-05,
|
| 69932 |
+
"loss": 0.6977,
|
| 69933 |
+
"step": 9989
|
| 69934 |
+
},
|
| 69935 |
+
{
|
| 69936 |
+
"epoch": 11.378347578347578,
|
| 69937 |
+
"grad_norm": 0.23431473970413208,
|
| 69938 |
+
"learning_rate": 2.1021736387763732e-05,
|
| 69939 |
+
"loss": 0.4698,
|
| 69940 |
+
"step": 9990
|
| 69941 |
+
},
|
| 69942 |
+
{
|
| 69943 |
+
"epoch": 11.37948717948718,
|
| 69944 |
+
"grad_norm": 0.2532706558704376,
|
| 69945 |
+
"learning_rate": 2.1017136645129655e-05,
|
| 69946 |
+
"loss": 0.6794,
|
| 69947 |
+
"step": 9991
|
| 69948 |
+
},
|
| 69949 |
+
{
|
| 69950 |
+
"epoch": 11.38062678062678,
|
| 69951 |
+
"grad_norm": 0.2173871099948883,
|
| 69952 |
+
"learning_rate": 2.1012537040831376e-05,
|
| 69953 |
+
"loss": 0.5126,
|
| 69954 |
+
"step": 9992
|
| 69955 |
+
},
|
| 69956 |
+
{
|
| 69957 |
+
"epoch": 11.381766381766381,
|
| 69958 |
+
"grad_norm": 0.18048971891403198,
|
| 69959 |
+
"learning_rate": 2.1007937575028645e-05,
|
| 69960 |
+
"loss": 0.7476,
|
| 69961 |
+
"step": 9993
|
| 69962 |
+
},
|
| 69963 |
+
{
|
| 69964 |
+
"epoch": 11.382905982905983,
|
| 69965 |
+
"grad_norm": 0.2078721523284912,
|
| 69966 |
+
"learning_rate": 2.100333824788123e-05,
|
| 69967 |
+
"loss": 0.7912,
|
| 69968 |
+
"step": 9994
|
| 69969 |
+
},
|
| 69970 |
+
{
|
| 69971 |
+
"epoch": 11.384045584045584,
|
| 69972 |
+
"grad_norm": 0.1874990612268448,
|
| 69973 |
+
"learning_rate": 2.0998739059548865e-05,
|
| 69974 |
+
"loss": 0.8126,
|
| 69975 |
+
"step": 9995
|
| 69976 |
+
},
|
| 69977 |
+
{
|
| 69978 |
+
"epoch": 11.385185185185184,
|
| 69979 |
+
"grad_norm": 0.17952513694763184,
|
| 69980 |
+
"learning_rate": 2.0994140010191296e-05,
|
| 69981 |
+
"loss": 0.8035,
|
| 69982 |
+
"step": 9996
|
| 69983 |
+
},
|
| 69984 |
+
{
|
| 69985 |
+
"epoch": 11.386324786324787,
|
| 69986 |
+
"grad_norm": 0.21788497269153595,
|
| 69987 |
+
"learning_rate": 2.0989541099968257e-05,
|
| 69988 |
+
"loss": 0.726,
|
| 69989 |
+
"step": 9997
|
| 69990 |
+
},
|
| 69991 |
+
{
|
| 69992 |
+
"epoch": 11.387464387464387,
|
| 69993 |
+
"grad_norm": 0.2562752366065979,
|
| 69994 |
+
"learning_rate": 2.098494232903949e-05,
|
| 69995 |
+
"loss": 0.6623,
|
| 69996 |
+
"step": 9998
|
| 69997 |
+
},
|
| 69998 |
+
{
|
| 69999 |
+
"epoch": 11.388603988603988,
|
| 70000 |
+
"grad_norm": 0.21369265019893646,
|
| 70001 |
+
"learning_rate": 2.0980343697564714e-05,
|
| 70002 |
+
"loss": 0.6807,
|
| 70003 |
+
"step": 9999
|
| 70004 |
+
},
|
| 70005 |
+
{
|
| 70006 |
+
"epoch": 11.38974358974359,
|
| 70007 |
+
"grad_norm": 0.2155311405658722,
|
| 70008 |
+
"learning_rate": 2.0975745205703648e-05,
|
| 70009 |
+
"loss": 0.743,
|
| 70010 |
+
"step": 10000
|
| 70011 |
+
},
|
| 70012 |
+
{
|
| 70013 |
+
"epoch": 11.39088319088319,
|
| 70014 |
+
"grad_norm": 0.18946735560894012,
|
| 70015 |
+
"learning_rate": 2.0971146853616032e-05,
|
| 70016 |
+
"loss": 0.83,
|
| 70017 |
+
"step": 10001
|
| 70018 |
+
},
|
| 70019 |
+
{
|
| 70020 |
+
"epoch": 11.392022792022791,
|
| 70021 |
+
"grad_norm": 0.21094633638858795,
|
| 70022 |
+
"learning_rate": 2.0966548641461552e-05,
|
| 70023 |
+
"loss": 0.8659,
|
| 70024 |
+
"step": 10002
|
| 70025 |
+
},
|
| 70026 |
+
{
|
| 70027 |
+
"epoch": 11.393162393162394,
|
| 70028 |
+
"grad_norm": 0.23790320754051208,
|
| 70029 |
+
"learning_rate": 2.0961950569399942e-05,
|
| 70030 |
+
"loss": 0.7358,
|
| 70031 |
+
"step": 10003
|
| 70032 |
+
},
|
| 70033 |
+
{
|
| 70034 |
+
"epoch": 11.394301994301994,
|
| 70035 |
+
"grad_norm": 0.2713351845741272,
|
| 70036 |
+
"learning_rate": 2.0957352637590884e-05,
|
| 70037 |
+
"loss": 0.6183,
|
| 70038 |
+
"step": 10004
|
| 70039 |
+
},
|
| 70040 |
+
{
|
| 70041 |
+
"epoch": 11.395441595441595,
|
| 70042 |
+
"grad_norm": 0.1856396645307541,
|
| 70043 |
+
"learning_rate": 2.0952754846194094e-05,
|
| 70044 |
+
"loss": 0.7679,
|
| 70045 |
+
"step": 10005
|
| 70046 |
+
},
|
| 70047 |
+
{
|
| 70048 |
+
"epoch": 11.396581196581197,
|
| 70049 |
+
"grad_norm": 0.21260108053684235,
|
| 70050 |
+
"learning_rate": 2.0948157195369253e-05,
|
| 70051 |
+
"loss": 0.852,
|
| 70052 |
+
"step": 10006
|
| 70053 |
+
},
|
| 70054 |
+
{
|
| 70055 |
+
"epoch": 11.397720797720797,
|
| 70056 |
+
"grad_norm": 0.18913598358631134,
|
| 70057 |
+
"learning_rate": 2.094355968527606e-05,
|
| 70058 |
+
"loss": 0.6075,
|
| 70059 |
+
"step": 10007
|
| 70060 |
+
},
|
| 70061 |
+
{
|
| 70062 |
+
"epoch": 11.398860398860398,
|
| 70063 |
+
"grad_norm": 0.18461109697818756,
|
| 70064 |
+
"learning_rate": 2.0938962316074186e-05,
|
| 70065 |
+
"loss": 0.8129,
|
| 70066 |
+
"step": 10008
|
| 70067 |
+
},
|
| 70068 |
+
{
|
| 70069 |
+
"epoch": 11.4,
|
| 70070 |
+
"grad_norm": 0.1944519281387329,
|
| 70071 |
+
"learning_rate": 2.0934365087923326e-05,
|
| 70072 |
+
"loss": 0.6931,
|
| 70073 |
+
"step": 10009
|
| 70074 |
+
},
|
| 70075 |
+
{
|
| 70076 |
+
"epoch": 11.401139601139601,
|
| 70077 |
+
"grad_norm": 0.2516137957572937,
|
| 70078 |
+
"learning_rate": 2.0929768000983144e-05,
|
| 70079 |
+
"loss": 0.5684,
|
| 70080 |
+
"step": 10010
|
| 70081 |
+
},
|
| 70082 |
+
{
|
| 70083 |
+
"epoch": 11.402279202279201,
|
| 70084 |
+
"grad_norm": 0.21535034477710724,
|
| 70085 |
+
"learning_rate": 2.0925171055413307e-05,
|
| 70086 |
+
"loss": 0.6137,
|
| 70087 |
+
"step": 10011
|
| 70088 |
+
},
|
| 70089 |
+
{
|
| 70090 |
+
"epoch": 11.403418803418804,
|
| 70091 |
+
"grad_norm": 0.21665510535240173,
|
| 70092 |
+
"learning_rate": 2.0920574251373486e-05,
|
| 70093 |
+
"loss": 0.7792,
|
| 70094 |
+
"step": 10012
|
| 70095 |
+
},
|
| 70096 |
+
{
|
| 70097 |
+
"epoch": 11.404558404558404,
|
| 70098 |
+
"grad_norm": 0.1865619719028473,
|
| 70099 |
+
"learning_rate": 2.091597758902335e-05,
|
| 70100 |
+
"loss": 0.763,
|
| 70101 |
+
"step": 10013
|
| 70102 |
+
},
|
| 70103 |
+
{
|
| 70104 |
+
"epoch": 11.405698005698005,
|
| 70105 |
+
"grad_norm": 0.21660961210727692,
|
| 70106 |
+
"learning_rate": 2.0911381068522535e-05,
|
| 70107 |
+
"loss": 0.7896,
|
| 70108 |
+
"step": 10014
|
| 70109 |
+
},
|
| 70110 |
+
{
|
| 70111 |
+
"epoch": 11.406837606837607,
|
| 70112 |
+
"grad_norm": 0.2145041972398758,
|
| 70113 |
+
"learning_rate": 2.0906784690030705e-05,
|
| 70114 |
+
"loss": 0.7066,
|
| 70115 |
+
"step": 10015
|
| 70116 |
+
},
|
| 70117 |
+
{
|
| 70118 |
+
"epoch": 11.407977207977208,
|
| 70119 |
+
"grad_norm": 0.18325629830360413,
|
| 70120 |
+
"learning_rate": 2.0902188453707498e-05,
|
| 70121 |
+
"loss": 0.7039,
|
| 70122 |
+
"step": 10016
|
| 70123 |
+
},
|
| 70124 |
+
{
|
| 70125 |
+
"epoch": 11.40911680911681,
|
| 70126 |
+
"grad_norm": 0.18648825585842133,
|
| 70127 |
+
"learning_rate": 2.0897592359712554e-05,
|
| 70128 |
+
"loss": 0.9134,
|
| 70129 |
+
"step": 10017
|
| 70130 |
+
},
|
| 70131 |
+
{
|
| 70132 |
+
"epoch": 11.41025641025641,
|
| 70133 |
+
"grad_norm": 0.20018558204174042,
|
| 70134 |
+
"learning_rate": 2.0892996408205507e-05,
|
| 70135 |
+
"loss": 0.773,
|
| 70136 |
+
"step": 10018
|
| 70137 |
+
},
|
| 70138 |
+
{
|
| 70139 |
+
"epoch": 11.411396011396011,
|
| 70140 |
+
"grad_norm": 0.18970166146755219,
|
| 70141 |
+
"learning_rate": 2.0888400599345993e-05,
|
| 70142 |
+
"loss": 0.6343,
|
| 70143 |
+
"step": 10019
|
| 70144 |
+
},
|
| 70145 |
+
{
|
| 70146 |
+
"epoch": 11.412535612535613,
|
| 70147 |
+
"grad_norm": 0.20653219521045685,
|
| 70148 |
+
"learning_rate": 2.088380493329363e-05,
|
| 70149 |
+
"loss": 0.631,
|
| 70150 |
+
"step": 10020
|
| 70151 |
+
},
|
| 70152 |
+
{
|
| 70153 |
+
"epoch": 11.413675213675214,
|
| 70154 |
+
"grad_norm": 0.24264267086982727,
|
| 70155 |
+
"learning_rate": 2.0879209410208044e-05,
|
| 70156 |
+
"loss": 0.6642,
|
| 70157 |
+
"step": 10021
|
| 70158 |
+
},
|
| 70159 |
+
{
|
| 70160 |
+
"epoch": 11.414814814814815,
|
| 70161 |
+
"grad_norm": 0.2044183909893036,
|
| 70162 |
+
"learning_rate": 2.087461403024884e-05,
|
| 70163 |
+
"loss": 0.4789,
|
| 70164 |
+
"step": 10022
|
| 70165 |
+
},
|
| 70166 |
+
{
|
| 70167 |
+
"epoch": 11.415954415954417,
|
| 70168 |
+
"grad_norm": 0.17189714312553406,
|
| 70169 |
+
"learning_rate": 2.087001879357564e-05,
|
| 70170 |
+
"loss": 0.7172,
|
| 70171 |
+
"step": 10023
|
| 70172 |
+
},
|
| 70173 |
+
{
|
| 70174 |
+
"epoch": 11.417094017094017,
|
| 70175 |
+
"grad_norm": 0.18149492144584656,
|
| 70176 |
+
"learning_rate": 2.0865423700348045e-05,
|
| 70177 |
+
"loss": 0.7652,
|
| 70178 |
+
"step": 10024
|
| 70179 |
+
},
|
| 70180 |
+
{
|
| 70181 |
+
"epoch": 11.418233618233618,
|
| 70182 |
+
"grad_norm": 0.30384448170661926,
|
| 70183 |
+
"learning_rate": 2.0860828750725655e-05,
|
| 70184 |
+
"loss": 0.6009,
|
| 70185 |
+
"step": 10025
|
| 70186 |
+
},
|
| 70187 |
+
{
|
| 70188 |
+
"epoch": 11.41937321937322,
|
| 70189 |
+
"grad_norm": 0.20158112049102783,
|
| 70190 |
+
"learning_rate": 2.085623394486807e-05,
|
| 70191 |
+
"loss": 0.6967,
|
| 70192 |
+
"step": 10026
|
| 70193 |
+
},
|
| 70194 |
+
{
|
| 70195 |
+
"epoch": 11.42051282051282,
|
| 70196 |
+
"grad_norm": 0.205727681517601,
|
| 70197 |
+
"learning_rate": 2.085163928293487e-05,
|
| 70198 |
+
"loss": 0.769,
|
| 70199 |
+
"step": 10027
|
| 70200 |
+
},
|
| 70201 |
+
{
|
| 70202 |
+
"epoch": 11.421652421652421,
|
| 70203 |
+
"grad_norm": 0.18823014199733734,
|
| 70204 |
+
"learning_rate": 2.084704476508565e-05,
|
| 70205 |
+
"loss": 0.8645,
|
| 70206 |
+
"step": 10028
|
| 70207 |
+
},
|
| 70208 |
+
{
|
| 70209 |
+
"epoch": 11.422792022792024,
|
| 70210 |
+
"grad_norm": 0.27690598368644714,
|
| 70211 |
+
"learning_rate": 2.0842450391479982e-05,
|
| 70212 |
+
"loss": 0.6291,
|
| 70213 |
+
"step": 10029
|
| 70214 |
+
},
|
| 70215 |
+
{
|
| 70216 |
+
"epoch": 11.423931623931624,
|
| 70217 |
+
"grad_norm": 0.19192315638065338,
|
| 70218 |
+
"learning_rate": 2.0837856162277447e-05,
|
| 70219 |
+
"loss": 0.6176,
|
| 70220 |
+
"step": 10030
|
| 70221 |
+
},
|
| 70222 |
+
{
|
| 70223 |
+
"epoch": 11.425071225071225,
|
| 70224 |
+
"grad_norm": 0.2199936807155609,
|
| 70225 |
+
"learning_rate": 2.0833262077637612e-05,
|
| 70226 |
+
"loss": 0.4781,
|
| 70227 |
+
"step": 10031
|
| 70228 |
+
},
|
| 70229 |
+
{
|
| 70230 |
+
"epoch": 11.426210826210827,
|
| 70231 |
+
"grad_norm": 0.2021743208169937,
|
| 70232 |
+
"learning_rate": 2.0828668137720048e-05,
|
| 70233 |
+
"loss": 0.8053,
|
| 70234 |
+
"step": 10032
|
| 70235 |
+
},
|
| 70236 |
+
{
|
| 70237 |
+
"epoch": 11.427350427350428,
|
| 70238 |
+
"grad_norm": 0.2495376467704773,
|
| 70239 |
+
"learning_rate": 2.08240743426843e-05,
|
| 70240 |
+
"loss": 0.6379,
|
| 70241 |
+
"step": 10033
|
| 70242 |
+
},
|
| 70243 |
+
{
|
| 70244 |
+
"epoch": 11.428490028490028,
|
| 70245 |
+
"grad_norm": 0.23179969191551208,
|
| 70246 |
+
"learning_rate": 2.081948069268994e-05,
|
| 70247 |
+
"loss": 0.7341,
|
| 70248 |
+
"step": 10034
|
| 70249 |
+
},
|
| 70250 |
+
{
|
| 70251 |
+
"epoch": 11.42962962962963,
|
| 70252 |
+
"grad_norm": 0.22318165004253387,
|
| 70253 |
+
"learning_rate": 2.0814887187896513e-05,
|
| 70254 |
+
"loss": 0.4811,
|
| 70255 |
+
"step": 10035
|
| 70256 |
+
},
|
| 70257 |
+
{
|
| 70258 |
+
"epoch": 11.430769230769231,
|
| 70259 |
+
"grad_norm": 0.18104930222034454,
|
| 70260 |
+
"learning_rate": 2.0810293828463563e-05,
|
| 70261 |
+
"loss": 0.9114,
|
| 70262 |
+
"step": 10036
|
| 70263 |
+
},
|
| 70264 |
+
{
|
| 70265 |
+
"epoch": 11.431908831908832,
|
| 70266 |
+
"grad_norm": 0.2621336877346039,
|
| 70267 |
+
"learning_rate": 2.0805700614550633e-05,
|
| 70268 |
+
"loss": 0.4802,
|
| 70269 |
+
"step": 10037
|
| 70270 |
+
},
|
| 70271 |
+
{
|
| 70272 |
+
"epoch": 11.433048433048434,
|
| 70273 |
+
"grad_norm": 0.20020677149295807,
|
| 70274 |
+
"learning_rate": 2.080110754631725e-05,
|
| 70275 |
+
"loss": 0.6964,
|
| 70276 |
+
"step": 10038
|
| 70277 |
+
},
|
| 70278 |
+
{
|
| 70279 |
+
"epoch": 11.434188034188034,
|
| 70280 |
+
"grad_norm": 0.21619516611099243,
|
| 70281 |
+
"learning_rate": 2.0796514623922956e-05,
|
| 70282 |
+
"loss": 0.6739,
|
| 70283 |
+
"step": 10039
|
| 70284 |
+
},
|
| 70285 |
+
{
|
| 70286 |
+
"epoch": 11.435327635327635,
|
| 70287 |
+
"grad_norm": 0.15959975123405457,
|
| 70288 |
+
"learning_rate": 2.0791921847527263e-05,
|
| 70289 |
+
"loss": 0.8328,
|
| 70290 |
+
"step": 10040
|
| 70291 |
+
},
|
| 70292 |
+
{
|
| 70293 |
+
"epoch": 11.436467236467237,
|
| 70294 |
+
"grad_norm": 0.21069657802581787,
|
| 70295 |
+
"learning_rate": 2.07873292172897e-05,
|
| 70296 |
+
"loss": 0.8459,
|
| 70297 |
+
"step": 10041
|
| 70298 |
+
},
|
| 70299 |
+
{
|
| 70300 |
+
"epoch": 11.437606837606838,
|
| 70301 |
+
"grad_norm": 0.20942659676074982,
|
| 70302 |
+
"learning_rate": 2.0782736733369774e-05,
|
| 70303 |
+
"loss": 0.7156,
|
| 70304 |
+
"step": 10042
|
| 70305 |
+
},
|
| 70306 |
+
{
|
| 70307 |
+
"epoch": 11.438746438746438,
|
| 70308 |
+
"grad_norm": 0.18864844739437103,
|
| 70309 |
+
"learning_rate": 2.0778144395927002e-05,
|
| 70310 |
+
"loss": 0.7452,
|
| 70311 |
+
"step": 10043
|
| 70312 |
+
},
|
| 70313 |
+
{
|
| 70314 |
+
"epoch": 11.43988603988604,
|
| 70315 |
+
"grad_norm": 0.21977639198303223,
|
| 70316 |
+
"learning_rate": 2.077355220512088e-05,
|
| 70317 |
+
"loss": 0.7005,
|
| 70318 |
+
"step": 10044
|
| 70319 |
+
},
|
| 70320 |
+
{
|
| 70321 |
+
"epoch": 11.441025641025641,
|
| 70322 |
+
"grad_norm": 0.19923043251037598,
|
| 70323 |
+
"learning_rate": 2.0768960161110913e-05,
|
| 70324 |
+
"loss": 0.6548,
|
| 70325 |
+
"step": 10045
|
| 70326 |
+
},
|
| 70327 |
+
{
|
| 70328 |
+
"epoch": 11.442165242165242,
|
| 70329 |
+
"grad_norm": 0.24817754328250885,
|
| 70330 |
+
"learning_rate": 2.07643682640566e-05,
|
| 70331 |
+
"loss": 0.4917,
|
| 70332 |
+
"step": 10046
|
| 70333 |
+
},
|
| 70334 |
+
{
|
| 70335 |
+
"epoch": 11.443304843304844,
|
| 70336 |
+
"grad_norm": 0.22018466889858246,
|
| 70337 |
+
"learning_rate": 2.075977651411742e-05,
|
| 70338 |
+
"loss": 0.6338,
|
| 70339 |
+
"step": 10047
|
| 70340 |
+
},
|
| 70341 |
+
{
|
| 70342 |
+
"epoch": 11.444444444444445,
|
| 70343 |
+
"grad_norm": 0.20591236650943756,
|
| 70344 |
+
"learning_rate": 2.0755184911452873e-05,
|
| 70345 |
+
"loss": 0.6555,
|
| 70346 |
+
"step": 10048
|
| 70347 |
+
},
|
| 70348 |
+
{
|
| 70349 |
+
"epoch": 11.445584045584045,
|
| 70350 |
+
"grad_norm": 0.18632829189300537,
|
| 70351 |
+
"learning_rate": 2.0750593456222416e-05,
|
| 70352 |
+
"loss": 0.6364,
|
| 70353 |
+
"step": 10049
|
| 70354 |
+
},
|
| 70355 |
+
{
|
| 70356 |
+
"epoch": 11.446723646723648,
|
| 70357 |
+
"grad_norm": 0.23025359213352203,
|
| 70358 |
+
"learning_rate": 2.074600214858554e-05,
|
| 70359 |
+
"loss": 0.6342,
|
| 70360 |
+
"step": 10050
|
| 70361 |
+
},
|
| 70362 |
+
{
|
| 70363 |
+
"epoch": 11.447863247863248,
|
| 70364 |
+
"grad_norm": 0.24396909773349762,
|
| 70365 |
+
"learning_rate": 2.0741410988701706e-05,
|
| 70366 |
+
"loss": 0.6499,
|
| 70367 |
+
"step": 10051
|
| 70368 |
+
},
|
| 70369 |
+
{
|
| 70370 |
+
"epoch": 11.449002849002849,
|
| 70371 |
+
"grad_norm": 0.2707434892654419,
|
| 70372 |
+
"learning_rate": 2.0736819976730385e-05,
|
| 70373 |
+
"loss": 0.3684,
|
| 70374 |
+
"step": 10052
|
| 70375 |
+
},
|
| 70376 |
+
{
|
| 70377 |
+
"epoch": 11.450142450142451,
|
| 70378 |
+
"grad_norm": 0.19455496966838837,
|
| 70379 |
+
"learning_rate": 2.0732229112831023e-05,
|
| 70380 |
+
"loss": 0.6864,
|
| 70381 |
+
"step": 10053
|
| 70382 |
+
},
|
| 70383 |
+
{
|
| 70384 |
+
"epoch": 11.451282051282051,
|
| 70385 |
+
"grad_norm": 0.20653720200061798,
|
| 70386 |
+
"learning_rate": 2.0727638397163078e-05,
|
| 70387 |
+
"loss": 0.9295,
|
| 70388 |
+
"step": 10054
|
| 70389 |
+
},
|
| 70390 |
+
{
|
| 70391 |
+
"epoch": 11.452421652421652,
|
| 70392 |
+
"grad_norm": 0.1749943643808365,
|
| 70393 |
+
"learning_rate": 2.0723047829886e-05,
|
| 70394 |
+
"loss": 0.9289,
|
| 70395 |
+
"step": 10055
|
| 70396 |
+
},
|
| 70397 |
+
{
|
| 70398 |
+
"epoch": 11.453561253561254,
|
| 70399 |
+
"grad_norm": 0.1685071885585785,
|
| 70400 |
+
"learning_rate": 2.071845741115924e-05,
|
| 70401 |
+
"loss": 0.7246,
|
| 70402 |
+
"step": 10056
|
| 70403 |
+
},
|
| 70404 |
+
{
|
| 70405 |
+
"epoch": 11.454700854700855,
|
| 70406 |
+
"grad_norm": 0.18324369192123413,
|
| 70407 |
+
"learning_rate": 2.0713867141142223e-05,
|
| 70408 |
+
"loss": 0.8333,
|
| 70409 |
+
"step": 10057
|
| 70410 |
+
},
|
| 70411 |
+
{
|
| 70412 |
+
"epoch": 11.455840455840455,
|
| 70413 |
+
"grad_norm": 0.21532200276851654,
|
| 70414 |
+
"learning_rate": 2.070927701999439e-05,
|
| 70415 |
+
"loss": 0.6711,
|
| 70416 |
+
"step": 10058
|
| 70417 |
+
},
|
| 70418 |
+
{
|
| 70419 |
+
"epoch": 11.456980056980058,
|
| 70420 |
+
"grad_norm": 0.2650965452194214,
|
| 70421 |
+
"learning_rate": 2.0704687047875166e-05,
|
| 70422 |
+
"loss": 0.3715,
|
| 70423 |
+
"step": 10059
|
| 70424 |
+
},
|
| 70425 |
+
{
|
| 70426 |
+
"epoch": 11.458119658119658,
|
| 70427 |
+
"grad_norm": 0.1903204321861267,
|
| 70428 |
+
"learning_rate": 2.0700097224943975e-05,
|
| 70429 |
+
"loss": 0.741,
|
| 70430 |
+
"step": 10060
|
| 70431 |
+
},
|
| 70432 |
+
{
|
| 70433 |
+
"epoch": 11.459259259259259,
|
| 70434 |
+
"grad_norm": 0.20154109597206116,
|
| 70435 |
+
"learning_rate": 2.0695507551360228e-05,
|
| 70436 |
+
"loss": 0.7265,
|
| 70437 |
+
"step": 10061
|
| 70438 |
+
},
|
| 70439 |
+
{
|
| 70440 |
+
"epoch": 11.460398860398861,
|
| 70441 |
+
"grad_norm": 0.20880548655986786,
|
| 70442 |
+
"learning_rate": 2.0690918027283346e-05,
|
| 70443 |
+
"loss": 0.5857,
|
| 70444 |
+
"step": 10062
|
| 70445 |
+
},
|
| 70446 |
+
{
|
| 70447 |
+
"epoch": 11.461538461538462,
|
| 70448 |
+
"grad_norm": 0.23127515614032745,
|
| 70449 |
+
"learning_rate": 2.0686328652872723e-05,
|
| 70450 |
+
"loss": 0.6208,
|
| 70451 |
+
"step": 10063
|
| 70452 |
+
},
|
| 70453 |
+
{
|
| 70454 |
+
"epoch": 11.462678062678062,
|
| 70455 |
+
"grad_norm": 0.25560060143470764,
|
| 70456 |
+
"learning_rate": 2.068173942828778e-05,
|
| 70457 |
+
"loss": 0.5022,
|
| 70458 |
+
"step": 10064
|
| 70459 |
+
},
|
| 70460 |
+
{
|
| 70461 |
+
"epoch": 11.463817663817665,
|
| 70462 |
+
"grad_norm": 0.1762644499540329,
|
| 70463 |
+
"learning_rate": 2.067715035368789e-05,
|
| 70464 |
+
"loss": 0.7456,
|
| 70465 |
+
"step": 10065
|
| 70466 |
+
},
|
| 70467 |
+
{
|
| 70468 |
+
"epoch": 11.464957264957265,
|
| 70469 |
+
"grad_norm": 0.23545634746551514,
|
| 70470 |
+
"learning_rate": 2.0672561429232458e-05,
|
| 70471 |
+
"loss": 0.5954,
|
| 70472 |
+
"step": 10066
|
| 70473 |
+
},
|
| 70474 |
+
{
|
| 70475 |
+
"epoch": 11.466096866096866,
|
| 70476 |
+
"grad_norm": 0.23931023478507996,
|
| 70477 |
+
"learning_rate": 2.066797265508087e-05,
|
| 70478 |
+
"loss": 0.7562,
|
| 70479 |
+
"step": 10067
|
| 70480 |
+
},
|
| 70481 |
+
{
|
| 70482 |
+
"epoch": 11.467236467236468,
|
| 70483 |
+
"grad_norm": 0.28010281920433044,
|
| 70484 |
+
"learning_rate": 2.0663384031392504e-05,
|
| 70485 |
+
"loss": 0.6851,
|
| 70486 |
+
"step": 10068
|
| 70487 |
+
},
|
| 70488 |
+
{
|
| 70489 |
+
"epoch": 11.468376068376068,
|
| 70490 |
+
"grad_norm": 0.20878314971923828,
|
| 70491 |
+
"learning_rate": 2.0658795558326743e-05,
|
| 70492 |
+
"loss": 0.7336,
|
| 70493 |
+
"step": 10069
|
| 70494 |
+
},
|
| 70495 |
+
{
|
| 70496 |
+
"epoch": 11.469515669515669,
|
| 70497 |
+
"grad_norm": 0.2539985179901123,
|
| 70498 |
+
"learning_rate": 2.0654207236042945e-05,
|
| 70499 |
+
"loss": 0.3877,
|
| 70500 |
+
"step": 10070
|
| 70501 |
+
},
|
| 70502 |
+
{
|
| 70503 |
+
"epoch": 11.470655270655271,
|
| 70504 |
+
"grad_norm": 0.2357361912727356,
|
| 70505 |
+
"learning_rate": 2.0649619064700485e-05,
|
| 70506 |
+
"loss": 0.4854,
|
| 70507 |
+
"step": 10071
|
| 70508 |
+
},
|
| 70509 |
+
{
|
| 70510 |
+
"epoch": 11.471794871794872,
|
| 70511 |
+
"grad_norm": 0.22556303441524506,
|
| 70512 |
+
"learning_rate": 2.0645031044458714e-05,
|
| 70513 |
+
"loss": 0.7931,
|
| 70514 |
+
"step": 10072
|
| 70515 |
+
},
|
| 70516 |
+
{
|
| 70517 |
+
"epoch": 11.472934472934472,
|
| 70518 |
+
"grad_norm": 0.23753730952739716,
|
| 70519 |
+
"learning_rate": 2.064044317547699e-05,
|
| 70520 |
+
"loss": 0.7017,
|
| 70521 |
+
"step": 10073
|
| 70522 |
+
},
|
| 70523 |
+
{
|
| 70524 |
+
"epoch": 11.474074074074075,
|
| 70525 |
+
"grad_norm": 0.18520833551883698,
|
| 70526 |
+
"learning_rate": 2.0635855457914665e-05,
|
| 70527 |
+
"loss": 0.8661,
|
| 70528 |
+
"step": 10074
|
| 70529 |
+
},
|
| 70530 |
+
{
|
| 70531 |
+
"epoch": 11.475213675213675,
|
| 70532 |
+
"grad_norm": 0.2340151071548462,
|
| 70533 |
+
"learning_rate": 2.0631267891931087e-05,
|
| 70534 |
+
"loss": 0.6815,
|
| 70535 |
+
"step": 10075
|
| 70536 |
+
},
|
| 70537 |
+
{
|
| 70538 |
+
"epoch": 11.476353276353276,
|
| 70539 |
+
"grad_norm": 0.1645916998386383,
|
| 70540 |
+
"learning_rate": 2.0626680477685585e-05,
|
| 70541 |
+
"loss": 0.7149,
|
| 70542 |
+
"step": 10076
|
| 70543 |
+
},
|
| 70544 |
+
{
|
| 70545 |
+
"epoch": 11.477492877492878,
|
| 70546 |
+
"grad_norm": 0.17714065313339233,
|
| 70547 |
+
"learning_rate": 2.0622093215337484e-05,
|
| 70548 |
+
"loss": 0.7027,
|
| 70549 |
+
"step": 10077
|
| 70550 |
+
},
|
| 70551 |
+
{
|
| 70552 |
+
"epoch": 11.478632478632479,
|
| 70553 |
+
"grad_norm": 0.22676534950733185,
|
| 70554 |
+
"learning_rate": 2.0617506105046143e-05,
|
| 70555 |
+
"loss": 0.6457,
|
| 70556 |
+
"step": 10078
|
| 70557 |
+
},
|
| 70558 |
+
{
|
| 70559 |
+
"epoch": 11.47977207977208,
|
| 70560 |
+
"grad_norm": 0.2152765840291977,
|
| 70561 |
+
"learning_rate": 2.0612919146970858e-05,
|
| 70562 |
+
"loss": 0.7855,
|
| 70563 |
+
"step": 10079
|
| 70564 |
+
},
|
| 70565 |
+
{
|
| 70566 |
+
"epoch": 11.480911680911682,
|
| 70567 |
+
"grad_norm": 0.26596543192863464,
|
| 70568 |
+
"learning_rate": 2.060833234127096e-05,
|
| 70569 |
+
"loss": 0.5108,
|
| 70570 |
+
"step": 10080
|
| 70571 |
+
},
|
| 70572 |
+
{
|
| 70573 |
+
"epoch": 11.482051282051282,
|
| 70574 |
+
"grad_norm": 0.2279624491930008,
|
| 70575 |
+
"learning_rate": 2.060374568810575e-05,
|
| 70576 |
+
"loss": 0.8589,
|
| 70577 |
+
"step": 10081
|
| 70578 |
+
},
|
| 70579 |
+
{
|
| 70580 |
+
"epoch": 11.483190883190883,
|
| 70581 |
+
"grad_norm": 0.2043648511171341,
|
| 70582 |
+
"learning_rate": 2.0599159187634554e-05,
|
| 70583 |
+
"loss": 0.6467,
|
| 70584 |
+
"step": 10082
|
| 70585 |
+
},
|
| 70586 |
+
{
|
| 70587 |
+
"epoch": 11.484330484330485,
|
| 70588 |
+
"grad_norm": 0.20626182854175568,
|
| 70589 |
+
"learning_rate": 2.0594572840016653e-05,
|
| 70590 |
+
"loss": 0.785,
|
| 70591 |
+
"step": 10083
|
| 70592 |
+
},
|
| 70593 |
+
{
|
| 70594 |
+
"epoch": 11.485470085470086,
|
| 70595 |
+
"grad_norm": 0.23982909321784973,
|
| 70596 |
+
"learning_rate": 2.0589986645411356e-05,
|
| 70597 |
+
"loss": 0.3791,
|
| 70598 |
+
"step": 10084
|
| 70599 |
+
},
|
| 70600 |
+
{
|
| 70601 |
+
"epoch": 11.486609686609686,
|
| 70602 |
+
"grad_norm": 0.22007319331169128,
|
| 70603 |
+
"learning_rate": 2.058540060397795e-05,
|
| 70604 |
+
"loss": 0.7334,
|
| 70605 |
+
"step": 10085
|
| 70606 |
+
},
|
| 70607 |
+
{
|
| 70608 |
+
"epoch": 11.487749287749288,
|
| 70609 |
+
"grad_norm": 0.20136313140392303,
|
| 70610 |
+
"learning_rate": 2.0580814715875722e-05,
|
| 70611 |
+
"loss": 0.8072,
|
| 70612 |
+
"step": 10086
|
| 70613 |
+
},
|
| 70614 |
+
{
|
| 70615 |
+
"epoch": 11.488888888888889,
|
| 70616 |
+
"grad_norm": 0.21298660337924957,
|
| 70617 |
+
"learning_rate": 2.0576228981263947e-05,
|
| 70618 |
+
"loss": 0.773,
|
| 70619 |
+
"step": 10087
|
| 70620 |
+
},
|
| 70621 |
+
{
|
| 70622 |
+
"epoch": 11.49002849002849,
|
| 70623 |
+
"grad_norm": 0.21085113286972046,
|
| 70624 |
+
"learning_rate": 2.057164340030191e-05,
|
| 70625 |
+
"loss": 0.6982,
|
| 70626 |
+
"step": 10088
|
| 70627 |
+
},
|
| 70628 |
+
{
|
| 70629 |
+
"epoch": 11.491168091168092,
|
| 70630 |
+
"grad_norm": 0.21780793368816376,
|
| 70631 |
+
"learning_rate": 2.056705797314886e-05,
|
| 70632 |
+
"loss": 0.5916,
|
| 70633 |
+
"step": 10089
|
| 70634 |
+
},
|
| 70635 |
+
{
|
| 70636 |
+
"epoch": 11.492307692307692,
|
| 70637 |
+
"grad_norm": 0.17957738041877747,
|
| 70638 |
+
"learning_rate": 2.0562472699964092e-05,
|
| 70639 |
+
"loss": 0.833,
|
| 70640 |
+
"step": 10090
|
| 70641 |
+
},
|
| 70642 |
+
{
|
| 70643 |
+
"epoch": 11.493447293447293,
|
| 70644 |
+
"grad_norm": 0.20545561611652374,
|
| 70645 |
+
"learning_rate": 2.055788758090685e-05,
|
| 70646 |
+
"loss": 0.8376,
|
| 70647 |
+
"step": 10091
|
| 70648 |
+
},
|
| 70649 |
+
{
|
| 70650 |
+
"epoch": 11.494586894586895,
|
| 70651 |
+
"grad_norm": 0.16835999488830566,
|
| 70652 |
+
"learning_rate": 2.0553302616136388e-05,
|
| 70653 |
+
"loss": 0.9204,
|
| 70654 |
+
"step": 10092
|
| 70655 |
+
},
|
| 70656 |
+
{
|
| 70657 |
+
"epoch": 11.495726495726496,
|
| 70658 |
+
"grad_norm": 0.1910863220691681,
|
| 70659 |
+
"learning_rate": 2.0548717805811952e-05,
|
| 70660 |
+
"loss": 0.8283,
|
| 70661 |
+
"step": 10093
|
| 70662 |
+
},
|
| 70663 |
+
{
|
| 70664 |
+
"epoch": 11.496866096866096,
|
| 70665 |
+
"grad_norm": 0.18515583872795105,
|
| 70666 |
+
"learning_rate": 2.054413315009279e-05,
|
| 70667 |
+
"loss": 0.7845,
|
| 70668 |
+
"step": 10094
|
| 70669 |
+
},
|
| 70670 |
+
{
|
| 70671 |
+
"epoch": 11.498005698005699,
|
| 70672 |
+
"grad_norm": 0.2434854954481125,
|
| 70673 |
+
"learning_rate": 2.0539548649138136e-05,
|
| 70674 |
+
"loss": 0.5831,
|
| 70675 |
+
"step": 10095
|
| 70676 |
+
},
|
| 70677 |
+
{
|
| 70678 |
+
"epoch": 11.4991452991453,
|
| 70679 |
+
"grad_norm": 0.188311368227005,
|
| 70680 |
+
"learning_rate": 2.0534964303107227e-05,
|
| 70681 |
+
"loss": 1.0584,
|
| 70682 |
+
"step": 10096
|
| 70683 |
+
},
|
| 70684 |
+
{
|
| 70685 |
+
"epoch": 11.5002849002849,
|
| 70686 |
+
"grad_norm": 0.23528143763542175,
|
| 70687 |
+
"learning_rate": 2.053038011215928e-05,
|
| 70688 |
+
"loss": 0.7664,
|
| 70689 |
+
"step": 10097
|
| 70690 |
+
},
|
| 70691 |
+
{
|
| 70692 |
+
"epoch": 11.501424501424502,
|
| 70693 |
+
"grad_norm": 0.21836930513381958,
|
| 70694 |
+
"learning_rate": 2.052579607645353e-05,
|
| 70695 |
+
"loss": 0.7048,
|
| 70696 |
+
"step": 10098
|
| 70697 |
+
},
|
| 70698 |
+
{
|
| 70699 |
+
"epoch": 11.502564102564103,
|
| 70700 |
+
"grad_norm": 0.15405632555484772,
|
| 70701 |
+
"learning_rate": 2.052121219614918e-05,
|
| 70702 |
+
"loss": 0.8787,
|
| 70703 |
+
"step": 10099
|
| 70704 |
+
},
|
| 70705 |
+
{
|
| 70706 |
+
"epoch": 11.503703703703703,
|
| 70707 |
+
"grad_norm": 0.2536327540874481,
|
| 70708 |
+
"learning_rate": 2.0516628471405446e-05,
|
| 70709 |
+
"loss": 0.3659,
|
| 70710 |
+
"step": 10100
|
| 70711 |
+
},
|
| 70712 |
+
{
|
| 70713 |
+
"epoch": 11.504843304843305,
|
| 70714 |
+
"grad_norm": 0.19951657950878143,
|
| 70715 |
+
"learning_rate": 2.0512044902381543e-05,
|
| 70716 |
+
"loss": 0.6577,
|
| 70717 |
+
"step": 10101
|
| 70718 |
+
},
|
| 70719 |
+
{
|
| 70720 |
+
"epoch": 11.505982905982906,
|
| 70721 |
+
"grad_norm": 0.20418404042720795,
|
| 70722 |
+
"learning_rate": 2.0507461489236655e-05,
|
| 70723 |
+
"loss": 0.7083,
|
| 70724 |
+
"step": 10102
|
| 70725 |
+
},
|
| 70726 |
+
{
|
| 70727 |
+
"epoch": 11.507122507122507,
|
| 70728 |
+
"grad_norm": 0.24461476504802704,
|
| 70729 |
+
"learning_rate": 2.0502878232129992e-05,
|
| 70730 |
+
"loss": 0.7458,
|
| 70731 |
+
"step": 10103
|
| 70732 |
+
},
|
| 70733 |
+
{
|
| 70734 |
+
"epoch": 11.508262108262109,
|
| 70735 |
+
"grad_norm": 0.22976773977279663,
|
| 70736 |
+
"learning_rate": 2.0498295131220728e-05,
|
| 70737 |
+
"loss": 0.7533,
|
| 70738 |
+
"step": 10104
|
| 70739 |
+
},
|
| 70740 |
+
{
|
| 70741 |
+
"epoch": 11.50940170940171,
|
| 70742 |
+
"grad_norm": 0.24391049146652222,
|
| 70743 |
+
"learning_rate": 2.049371218666806e-05,
|
| 70744 |
+
"loss": 0.5373,
|
| 70745 |
+
"step": 10105
|
| 70746 |
+
},
|
| 70747 |
+
{
|
| 70748 |
+
"epoch": 11.51054131054131,
|
| 70749 |
+
"grad_norm": 0.19305101037025452,
|
| 70750 |
+
"learning_rate": 2.0489129398631153e-05,
|
| 70751 |
+
"loss": 0.67,
|
| 70752 |
+
"step": 10106
|
| 70753 |
+
},
|
| 70754 |
+
{
|
| 70755 |
+
"epoch": 11.511680911680912,
|
| 70756 |
+
"grad_norm": 0.15466570854187012,
|
| 70757 |
+
"learning_rate": 2.0484546767269196e-05,
|
| 70758 |
+
"loss": 0.813,
|
| 70759 |
+
"step": 10107
|
| 70760 |
+
},
|
| 70761 |
+
{
|
| 70762 |
+
"epoch": 11.512820512820513,
|
| 70763 |
+
"grad_norm": 0.20475360751152039,
|
| 70764 |
+
"learning_rate": 2.0479964292741338e-05,
|
| 70765 |
+
"loss": 0.7488,
|
| 70766 |
+
"step": 10108
|
| 70767 |
+
},
|
| 70768 |
+
{
|
| 70769 |
+
"epoch": 11.513960113960113,
|
| 70770 |
+
"grad_norm": 0.23447205126285553,
|
| 70771 |
+
"learning_rate": 2.0475381975206757e-05,
|
| 70772 |
+
"loss": 0.7557,
|
| 70773 |
+
"step": 10109
|
| 70774 |
+
},
|
| 70775 |
+
{
|
| 70776 |
+
"epoch": 11.515099715099716,
|
| 70777 |
+
"grad_norm": 0.20030346512794495,
|
| 70778 |
+
"learning_rate": 2.04707998148246e-05,
|
| 70779 |
+
"loss": 0.7338,
|
| 70780 |
+
"step": 10110
|
| 70781 |
+
},
|
| 70782 |
+
{
|
| 70783 |
+
"epoch": 11.516239316239316,
|
| 70784 |
+
"grad_norm": 0.30252522230148315,
|
| 70785 |
+
"learning_rate": 2.0466217811754012e-05,
|
| 70786 |
+
"loss": 0.4304,
|
| 70787 |
+
"step": 10111
|
| 70788 |
+
},
|
| 70789 |
+
{
|
| 70790 |
+
"epoch": 11.517378917378917,
|
| 70791 |
+
"grad_norm": 0.23555758595466614,
|
| 70792 |
+
"learning_rate": 2.046163596615416e-05,
|
| 70793 |
+
"loss": 0.4149,
|
| 70794 |
+
"step": 10112
|
| 70795 |
+
},
|
| 70796 |
+
{
|
| 70797 |
+
"epoch": 11.518518518518519,
|
| 70798 |
+
"grad_norm": 0.19094648957252502,
|
| 70799 |
+
"learning_rate": 2.045705427818416e-05,
|
| 70800 |
+
"loss": 0.8094,
|
| 70801 |
+
"step": 10113
|
| 70802 |
+
},
|
| 70803 |
+
{
|
| 70804 |
+
"epoch": 11.51965811965812,
|
| 70805 |
+
"grad_norm": 0.20734092593193054,
|
| 70806 |
+
"learning_rate": 2.0452472748003172e-05,
|
| 70807 |
+
"loss": 0.7286,
|
| 70808 |
+
"step": 10114
|
| 70809 |
+
},
|
| 70810 |
+
{
|
| 70811 |
+
"epoch": 11.52079772079772,
|
| 70812 |
+
"grad_norm": 0.20282462239265442,
|
| 70813 |
+
"learning_rate": 2.0447891375770304e-05,
|
| 70814 |
+
"loss": 0.7188,
|
| 70815 |
+
"step": 10115
|
| 70816 |
+
},
|
| 70817 |
+
{
|
| 70818 |
+
"epoch": 11.521937321937322,
|
| 70819 |
+
"grad_norm": 0.2904427647590637,
|
| 70820 |
+
"learning_rate": 2.044331016164469e-05,
|
| 70821 |
+
"loss": 0.5736,
|
| 70822 |
+
"step": 10116
|
| 70823 |
+
},
|
| 70824 |
+
{
|
| 70825 |
+
"epoch": 11.523076923076923,
|
| 70826 |
+
"grad_norm": 0.18206043541431427,
|
| 70827 |
+
"learning_rate": 2.043872910578544e-05,
|
| 70828 |
+
"loss": 0.6829,
|
| 70829 |
+
"step": 10117
|
| 70830 |
+
},
|
| 70831 |
+
{
|
| 70832 |
+
"epoch": 11.524216524216524,
|
| 70833 |
+
"grad_norm": 0.25908827781677246,
|
| 70834 |
+
"learning_rate": 2.0434148208351676e-05,
|
| 70835 |
+
"loss": 0.6485,
|
| 70836 |
+
"step": 10118
|
| 70837 |
+
},
|
| 70838 |
+
{
|
| 70839 |
+
"epoch": 11.525356125356126,
|
| 70840 |
+
"grad_norm": 0.25546640157699585,
|
| 70841 |
+
"learning_rate": 2.0429567469502497e-05,
|
| 70842 |
+
"loss": 0.608,
|
| 70843 |
+
"step": 10119
|
| 70844 |
+
},
|
| 70845 |
+
{
|
| 70846 |
+
"epoch": 11.526495726495726,
|
| 70847 |
+
"grad_norm": 0.2341763824224472,
|
| 70848 |
+
"learning_rate": 2.0424986889397016e-05,
|
| 70849 |
+
"loss": 0.6356,
|
| 70850 |
+
"step": 10120
|
| 70851 |
+
},
|
| 70852 |
+
{
|
| 70853 |
+
"epoch": 11.527635327635327,
|
| 70854 |
+
"grad_norm": 0.18672235310077667,
|
| 70855 |
+
"learning_rate": 2.0420406468194316e-05,
|
| 70856 |
+
"loss": 0.7211,
|
| 70857 |
+
"step": 10121
|
| 70858 |
+
},
|
| 70859 |
+
{
|
| 70860 |
+
"epoch": 11.52877492877493,
|
| 70861 |
+
"grad_norm": 0.2325475960969925,
|
| 70862 |
+
"learning_rate": 2.0415826206053483e-05,
|
| 70863 |
+
"loss": 0.8141,
|
| 70864 |
+
"step": 10122
|
| 70865 |
+
},
|
| 70866 |
+
{
|
| 70867 |
+
"epoch": 11.52991452991453,
|
| 70868 |
+
"grad_norm": 0.19826440513134003,
|
| 70869 |
+
"learning_rate": 2.041124610313363e-05,
|
| 70870 |
+
"loss": 0.6876,
|
| 70871 |
+
"step": 10123
|
| 70872 |
+
},
|
| 70873 |
+
{
|
| 70874 |
+
"epoch": 11.53105413105413,
|
| 70875 |
+
"grad_norm": 0.22760896384716034,
|
| 70876 |
+
"learning_rate": 2.0406666159593807e-05,
|
| 70877 |
+
"loss": 0.7007,
|
| 70878 |
+
"step": 10124
|
| 70879 |
+
},
|
| 70880 |
+
{
|
| 70881 |
+
"epoch": 11.532193732193733,
|
| 70882 |
+
"grad_norm": 0.21469786763191223,
|
| 70883 |
+
"learning_rate": 2.040208637559311e-05,
|
| 70884 |
+
"loss": 0.5696,
|
| 70885 |
+
"step": 10125
|
| 70886 |
+
},
|
| 70887 |
+
{
|
| 70888 |
+
"epoch": 11.533333333333333,
|
| 70889 |
+
"grad_norm": 0.19663602113723755,
|
| 70890 |
+
"learning_rate": 2.039750675129059e-05,
|
| 70891 |
+
"loss": 0.9364,
|
| 70892 |
+
"step": 10126
|
| 70893 |
+
},
|
| 70894 |
+
{
|
| 70895 |
+
"epoch": 11.534472934472934,
|
| 70896 |
+
"grad_norm": 0.24786512553691864,
|
| 70897 |
+
"learning_rate": 2.0392927286845322e-05,
|
| 70898 |
+
"loss": 0.4917,
|
| 70899 |
+
"step": 10127
|
| 70900 |
+
},
|
| 70901 |
+
{
|
| 70902 |
+
"epoch": 11.535612535612536,
|
| 70903 |
+
"grad_norm": 0.1861061155796051,
|
| 70904 |
+
"learning_rate": 2.0388347982416356e-05,
|
| 70905 |
+
"loss": 0.8017,
|
| 70906 |
+
"step": 10128
|
| 70907 |
+
},
|
| 70908 |
+
{
|
| 70909 |
+
"epoch": 11.536752136752137,
|
| 70910 |
+
"grad_norm": 0.23585036396980286,
|
| 70911 |
+
"learning_rate": 2.038376883816275e-05,
|
| 70912 |
+
"loss": 0.718,
|
| 70913 |
+
"step": 10129
|
| 70914 |
+
},
|
| 70915 |
+
{
|
| 70916 |
+
"epoch": 11.537891737891737,
|
| 70917 |
+
"grad_norm": 0.20937484502792358,
|
| 70918 |
+
"learning_rate": 2.0379189854243542e-05,
|
| 70919 |
+
"loss": 0.7784,
|
| 70920 |
+
"step": 10130
|
| 70921 |
+
},
|
| 70922 |
+
{
|
| 70923 |
+
"epoch": 11.53903133903134,
|
| 70924 |
+
"grad_norm": 0.2120661437511444,
|
| 70925 |
+
"learning_rate": 2.0374611030817782e-05,
|
| 70926 |
+
"loss": 0.7323,
|
| 70927 |
+
"step": 10131
|
| 70928 |
+
},
|
| 70929 |
+
{
|
| 70930 |
+
"epoch": 11.54017094017094,
|
| 70931 |
+
"grad_norm": 0.20045341551303864,
|
| 70932 |
+
"learning_rate": 2.0370032368044497e-05,
|
| 70933 |
+
"loss": 0.7793,
|
| 70934 |
+
"step": 10132
|
| 70935 |
+
},
|
| 70936 |
+
{
|
| 70937 |
+
"epoch": 11.54131054131054,
|
| 70938 |
+
"grad_norm": 0.21167951822280884,
|
| 70939 |
+
"learning_rate": 2.0365453866082716e-05,
|
| 70940 |
+
"loss": 0.7675,
|
| 70941 |
+
"step": 10133
|
| 70942 |
+
},
|
| 70943 |
+
{
|
| 70944 |
+
"epoch": 11.542450142450143,
|
| 70945 |
+
"grad_norm": 0.1805192083120346,
|
| 70946 |
+
"learning_rate": 2.036087552509147e-05,
|
| 70947 |
+
"loss": 0.7142,
|
| 70948 |
+
"step": 10134
|
| 70949 |
+
},
|
| 70950 |
+
{
|
| 70951 |
+
"epoch": 11.543589743589743,
|
| 70952 |
+
"grad_norm": 0.19848741590976715,
|
| 70953 |
+
"learning_rate": 2.035629734522978e-05,
|
| 70954 |
+
"loss": 0.6463,
|
| 70955 |
+
"step": 10135
|
| 70956 |
+
},
|
| 70957 |
+
{
|
| 70958 |
+
"epoch": 11.544729344729344,
|
| 70959 |
+
"grad_norm": 0.24124781787395477,
|
| 70960 |
+
"learning_rate": 2.0351719326656652e-05,
|
| 70961 |
+
"loss": 0.5639,
|
| 70962 |
+
"step": 10136
|
| 70963 |
+
},
|
| 70964 |
+
{
|
| 70965 |
+
"epoch": 11.545868945868946,
|
| 70966 |
+
"grad_norm": 0.24485869705677032,
|
| 70967 |
+
"learning_rate": 2.0347141469531094e-05,
|
| 70968 |
+
"loss": 0.601,
|
| 70969 |
+
"step": 10137
|
| 70970 |
+
},
|
| 70971 |
+
{
|
| 70972 |
+
"epoch": 11.547008547008547,
|
| 70973 |
+
"grad_norm": 0.21613085269927979,
|
| 70974 |
+
"learning_rate": 2.0342563774012107e-05,
|
| 70975 |
+
"loss": 0.5691,
|
| 70976 |
+
"step": 10138
|
| 70977 |
+
},
|
| 70978 |
+
{
|
| 70979 |
+
"epoch": 11.548148148148147,
|
| 70980 |
+
"grad_norm": 0.20234043896198273,
|
| 70981 |
+
"learning_rate": 2.0337986240258696e-05,
|
| 70982 |
+
"loss": 0.7644,
|
| 70983 |
+
"step": 10139
|
| 70984 |
+
},
|
| 70985 |
+
{
|
| 70986 |
+
"epoch": 11.54928774928775,
|
| 70987 |
+
"grad_norm": 0.19480158388614655,
|
| 70988 |
+
"learning_rate": 2.0333408868429832e-05,
|
| 70989 |
+
"loss": 0.6856,
|
| 70990 |
+
"step": 10140
|
| 70991 |
+
},
|
| 70992 |
+
{
|
| 70993 |
+
"epoch": 11.55042735042735,
|
| 70994 |
+
"grad_norm": 0.20556823909282684,
|
| 70995 |
+
"learning_rate": 2.0328831658684518e-05,
|
| 70996 |
+
"loss": 0.7236,
|
| 70997 |
+
"step": 10141
|
| 70998 |
+
},
|
| 70999 |
+
{
|
| 71000 |
+
"epoch": 11.55156695156695,
|
| 71001 |
+
"grad_norm": 0.24399961531162262,
|
| 71002 |
+
"learning_rate": 2.0324254611181724e-05,
|
| 71003 |
+
"loss": 0.6854,
|
| 71004 |
+
"step": 10142
|
| 71005 |
+
},
|
| 71006 |
+
{
|
| 71007 |
+
"epoch": 11.552706552706553,
|
| 71008 |
+
"grad_norm": 0.22309578955173492,
|
| 71009 |
+
"learning_rate": 2.031967772608043e-05,
|
| 71010 |
+
"loss": 0.6263,
|
| 71011 |
+
"step": 10143
|
| 71012 |
+
},
|
| 71013 |
+
{
|
| 71014 |
+
"epoch": 11.553846153846154,
|
| 71015 |
+
"grad_norm": 0.21229925751686096,
|
| 71016 |
+
"learning_rate": 2.0315101003539585e-05,
|
| 71017 |
+
"loss": 0.6705,
|
| 71018 |
+
"step": 10144
|
| 71019 |
+
},
|
| 71020 |
+
{
|
| 71021 |
+
"epoch": 11.554985754985754,
|
| 71022 |
+
"grad_norm": 0.16713200509548187,
|
| 71023 |
+
"learning_rate": 2.0310524443718176e-05,
|
| 71024 |
+
"loss": 0.9225,
|
| 71025 |
+
"step": 10145
|
| 71026 |
+
},
|
| 71027 |
+
{
|
| 71028 |
+
"epoch": 11.556125356125357,
|
| 71029 |
+
"grad_norm": 0.2773817479610443,
|
| 71030 |
+
"learning_rate": 2.0305948046775154e-05,
|
| 71031 |
+
"loss": 0.4484,
|
| 71032 |
+
"step": 10146
|
| 71033 |
+
},
|
| 71034 |
+
{
|
| 71035 |
+
"epoch": 11.557264957264957,
|
| 71036 |
+
"grad_norm": 0.1994384378194809,
|
| 71037 |
+
"learning_rate": 2.0301371812869458e-05,
|
| 71038 |
+
"loss": 0.8305,
|
| 71039 |
+
"step": 10147
|
| 71040 |
+
},
|
| 71041 |
+
{
|
| 71042 |
+
"epoch": 11.558404558404558,
|
| 71043 |
+
"grad_norm": 0.15961970388889313,
|
| 71044 |
+
"learning_rate": 2.0296795742160045e-05,
|
| 71045 |
+
"loss": 0.713,
|
| 71046 |
+
"step": 10148
|
| 71047 |
+
},
|
| 71048 |
+
{
|
| 71049 |
+
"epoch": 11.55954415954416,
|
| 71050 |
+
"grad_norm": 0.19760511815547943,
|
| 71051 |
+
"learning_rate": 2.0292219834805844e-05,
|
| 71052 |
+
"loss": 0.8293,
|
| 71053 |
+
"step": 10149
|
| 71054 |
+
},
|
| 71055 |
+
{
|
| 71056 |
+
"epoch": 11.56068376068376,
|
| 71057 |
+
"grad_norm": 0.23703165352344513,
|
| 71058 |
+
"learning_rate": 2.02876440909658e-05,
|
| 71059 |
+
"loss": 0.7275,
|
| 71060 |
+
"step": 10150
|
| 71061 |
+
},
|
| 71062 |
+
{
|
| 71063 |
+
"epoch": 11.561823361823361,
|
| 71064 |
+
"grad_norm": 0.2209303081035614,
|
| 71065 |
+
"learning_rate": 2.0283068510798833e-05,
|
| 71066 |
+
"loss": 0.6158,
|
| 71067 |
+
"step": 10151
|
| 71068 |
+
},
|
| 71069 |
+
{
|
| 71070 |
+
"epoch": 11.562962962962963,
|
| 71071 |
+
"grad_norm": 0.2222437858581543,
|
| 71072 |
+
"learning_rate": 2.0278493094463872e-05,
|
| 71073 |
+
"loss": 0.5919,
|
| 71074 |
+
"step": 10152
|
| 71075 |
+
},
|
| 71076 |
+
{
|
| 71077 |
+
"epoch": 11.564102564102564,
|
| 71078 |
+
"grad_norm": 0.2404080182313919,
|
| 71079 |
+
"learning_rate": 2.0273917842119823e-05,
|
| 71080 |
+
"loss": 0.4473,
|
| 71081 |
+
"step": 10153
|
| 71082 |
+
},
|
| 71083 |
+
{
|
| 71084 |
+
"epoch": 11.565242165242164,
|
| 71085 |
+
"grad_norm": 0.20224551856517792,
|
| 71086 |
+
"learning_rate": 2.0269342753925613e-05,
|
| 71087 |
+
"loss": 0.7044,
|
| 71088 |
+
"step": 10154
|
| 71089 |
+
},
|
| 71090 |
+
{
|
| 71091 |
+
"epoch": 11.566381766381767,
|
| 71092 |
+
"grad_norm": 0.21260076761245728,
|
| 71093 |
+
"learning_rate": 2.0264767830040127e-05,
|
| 71094 |
+
"loss": 0.8415,
|
| 71095 |
+
"step": 10155
|
| 71096 |
+
},
|
| 71097 |
+
{
|
| 71098 |
+
"epoch": 11.567521367521367,
|
| 71099 |
+
"grad_norm": 0.2516237795352936,
|
| 71100 |
+
"learning_rate": 2.026019307062228e-05,
|
| 71101 |
+
"loss": 0.6052,
|
| 71102 |
+
"step": 10156
|
| 71103 |
+
},
|
| 71104 |
+
{
|
| 71105 |
+
"epoch": 11.568660968660968,
|
| 71106 |
+
"grad_norm": 0.24627673625946045,
|
| 71107 |
+
"learning_rate": 2.025561847583097e-05,
|
| 71108 |
+
"loss": 0.6294,
|
| 71109 |
+
"step": 10157
|
| 71110 |
+
},
|
| 71111 |
+
{
|
| 71112 |
+
"epoch": 11.56980056980057,
|
| 71113 |
+
"grad_norm": 0.23037806153297424,
|
| 71114 |
+
"learning_rate": 2.025104404582507e-05,
|
| 71115 |
+
"loss": 0.4694,
|
| 71116 |
+
"step": 10158
|
| 71117 |
+
},
|
| 71118 |
+
{
|
| 71119 |
+
"epoch": 11.57094017094017,
|
| 71120 |
+
"grad_norm": 0.23542878031730652,
|
| 71121 |
+
"learning_rate": 2.0246469780763473e-05,
|
| 71122 |
+
"loss": 0.635,
|
| 71123 |
+
"step": 10159
|
| 71124 |
+
},
|
| 71125 |
+
{
|
| 71126 |
+
"epoch": 11.572079772079771,
|
| 71127 |
+
"grad_norm": 0.17926007509231567,
|
| 71128 |
+
"learning_rate": 2.0241895680805052e-05,
|
| 71129 |
+
"loss": 0.794,
|
| 71130 |
+
"step": 10160
|
| 71131 |
+
},
|
| 71132 |
+
{
|
| 71133 |
+
"epoch": 11.573219373219374,
|
| 71134 |
+
"grad_norm": 0.19894307851791382,
|
| 71135 |
+
"learning_rate": 2.0237321746108678e-05,
|
| 71136 |
+
"loss": 0.7871,
|
| 71137 |
+
"step": 10161
|
| 71138 |
+
},
|
| 71139 |
+
{
|
| 71140 |
+
"epoch": 11.574358974358974,
|
| 71141 |
+
"grad_norm": 0.20547333359718323,
|
| 71142 |
+
"learning_rate": 2.0232747976833217e-05,
|
| 71143 |
+
"loss": 0.7193,
|
| 71144 |
+
"step": 10162
|
| 71145 |
+
},
|
| 71146 |
+
{
|
| 71147 |
+
"epoch": 11.575498575498575,
|
| 71148 |
+
"grad_norm": 0.2085610032081604,
|
| 71149 |
+
"learning_rate": 2.0228174373137535e-05,
|
| 71150 |
+
"loss": 0.6491,
|
| 71151 |
+
"step": 10163
|
| 71152 |
+
},
|
| 71153 |
+
{
|
| 71154 |
+
"epoch": 11.576638176638177,
|
| 71155 |
+
"grad_norm": 0.2668093740940094,
|
| 71156 |
+
"learning_rate": 2.0223600935180472e-05,
|
| 71157 |
+
"loss": 0.5799,
|
| 71158 |
+
"step": 10164
|
| 71159 |
+
},
|
| 71160 |
+
{
|
| 71161 |
+
"epoch": 11.577777777777778,
|
| 71162 |
+
"grad_norm": 0.20587384700775146,
|
| 71163 |
+
"learning_rate": 2.0219027663120886e-05,
|
| 71164 |
+
"loss": 0.8061,
|
| 71165 |
+
"step": 10165
|
| 71166 |
+
},
|
| 71167 |
+
{
|
| 71168 |
+
"epoch": 11.578917378917378,
|
| 71169 |
+
"grad_norm": 0.20204438269138336,
|
| 71170 |
+
"learning_rate": 2.0214454557117613e-05,
|
| 71171 |
+
"loss": 0.7189,
|
| 71172 |
+
"step": 10166
|
| 71173 |
+
},
|
| 71174 |
+
{
|
| 71175 |
+
"epoch": 11.58005698005698,
|
| 71176 |
+
"grad_norm": 0.1639975756406784,
|
| 71177 |
+
"learning_rate": 2.0209881617329497e-05,
|
| 71178 |
+
"loss": 0.8037,
|
| 71179 |
+
"step": 10167
|
| 71180 |
+
},
|
| 71181 |
+
{
|
| 71182 |
+
"epoch": 11.581196581196581,
|
| 71183 |
+
"grad_norm": 0.22345274686813354,
|
| 71184 |
+
"learning_rate": 2.020530884391536e-05,
|
| 71185 |
+
"loss": 0.5246,
|
| 71186 |
+
"step": 10168
|
| 71187 |
+
},
|
| 71188 |
+
{
|
| 71189 |
+
"epoch": 11.582336182336181,
|
| 71190 |
+
"grad_norm": 0.18317808210849762,
|
| 71191 |
+
"learning_rate": 2.0200736237034042e-05,
|
| 71192 |
+
"loss": 0.7078,
|
| 71193 |
+
"step": 10169
|
| 71194 |
+
},
|
| 71195 |
+
{
|
| 71196 |
+
"epoch": 11.583475783475784,
|
| 71197 |
+
"grad_norm": 0.18807291984558105,
|
| 71198 |
+
"learning_rate": 2.0196163796844348e-05,
|
| 71199 |
+
"loss": 0.8574,
|
| 71200 |
+
"step": 10170
|
| 71201 |
+
},
|
| 71202 |
+
{
|
| 71203 |
+
"epoch": 11.584615384615384,
|
| 71204 |
+
"grad_norm": 0.2099536657333374,
|
| 71205 |
+
"learning_rate": 2.0191591523505098e-05,
|
| 71206 |
+
"loss": 0.6878,
|
| 71207 |
+
"step": 10171
|
| 71208 |
+
},
|
| 71209 |
+
{
|
| 71210 |
+
"epoch": 11.585754985754985,
|
| 71211 |
+
"grad_norm": 0.22654862701892853,
|
| 71212 |
+
"learning_rate": 2.0187019417175097e-05,
|
| 71213 |
+
"loss": 0.8243,
|
| 71214 |
+
"step": 10172
|
| 71215 |
+
},
|
| 71216 |
+
{
|
| 71217 |
+
"epoch": 11.586894586894587,
|
| 71218 |
+
"grad_norm": 0.2792012691497803,
|
| 71219 |
+
"learning_rate": 2.0182447478013147e-05,
|
| 71220 |
+
"loss": 0.4596,
|
| 71221 |
+
"step": 10173
|
| 71222 |
+
},
|
| 71223 |
+
{
|
| 71224 |
+
"epoch": 11.588034188034188,
|
| 71225 |
+
"grad_norm": 0.2196110039949417,
|
| 71226 |
+
"learning_rate": 2.0177875706178043e-05,
|
| 71227 |
+
"loss": 0.7237,
|
| 71228 |
+
"step": 10174
|
| 71229 |
+
},
|
| 71230 |
+
{
|
| 71231 |
+
"epoch": 11.589173789173788,
|
| 71232 |
+
"grad_norm": 0.22355572879314423,
|
| 71233 |
+
"learning_rate": 2.017330410182858e-05,
|
| 71234 |
+
"loss": 0.5842,
|
| 71235 |
+
"step": 10175
|
| 71236 |
+
},
|
| 71237 |
+
{
|
| 71238 |
+
"epoch": 11.59031339031339,
|
| 71239 |
+
"grad_norm": 0.2698277533054352,
|
| 71240 |
+
"learning_rate": 2.0168732665123535e-05,
|
| 71241 |
+
"loss": 0.5167,
|
| 71242 |
+
"step": 10176
|
| 71243 |
+
},
|
| 71244 |
+
{
|
| 71245 |
+
"epoch": 11.591452991452991,
|
| 71246 |
+
"grad_norm": 0.2722584307193756,
|
| 71247 |
+
"learning_rate": 2.0164161396221683e-05,
|
| 71248 |
+
"loss": 0.6275,
|
| 71249 |
+
"step": 10177
|
| 71250 |
+
},
|
| 71251 |
+
{
|
| 71252 |
+
"epoch": 11.592592592592592,
|
| 71253 |
+
"grad_norm": 0.1976955085992813,
|
| 71254 |
+
"learning_rate": 2.015959029528182e-05,
|
| 71255 |
+
"loss": 0.7372,
|
| 71256 |
+
"step": 10178
|
| 71257 |
+
},
|
| 71258 |
+
{
|
| 71259 |
+
"epoch": 11.593732193732194,
|
| 71260 |
+
"grad_norm": 0.23019570112228394,
|
| 71261 |
+
"learning_rate": 2.015501936246269e-05,
|
| 71262 |
+
"loss": 0.5574,
|
| 71263 |
+
"step": 10179
|
| 71264 |
+
},
|
| 71265 |
+
{
|
| 71266 |
+
"epoch": 11.594871794871795,
|
| 71267 |
+
"grad_norm": 0.17158330976963043,
|
| 71268 |
+
"learning_rate": 2.0150448597923062e-05,
|
| 71269 |
+
"loss": 0.7158,
|
| 71270 |
+
"step": 10180
|
| 71271 |
+
},
|
| 71272 |
+
{
|
| 71273 |
+
"epoch": 11.596011396011395,
|
| 71274 |
+
"grad_norm": 0.21241247653961182,
|
| 71275 |
+
"learning_rate": 2.014587800182169e-05,
|
| 71276 |
+
"loss": 0.6826,
|
| 71277 |
+
"step": 10181
|
| 71278 |
+
},
|
| 71279 |
+
{
|
| 71280 |
+
"epoch": 11.597150997150997,
|
| 71281 |
+
"grad_norm": 0.17392486333847046,
|
| 71282 |
+
"learning_rate": 2.0141307574317326e-05,
|
| 71283 |
+
"loss": 0.6694,
|
| 71284 |
+
"step": 10182
|
| 71285 |
+
},
|
| 71286 |
+
{
|
| 71287 |
+
"epoch": 11.598290598290598,
|
| 71288 |
+
"grad_norm": 0.2758224606513977,
|
| 71289 |
+
"learning_rate": 2.013673731556871e-05,
|
| 71290 |
+
"loss": 0.5387,
|
| 71291 |
+
"step": 10183
|
| 71292 |
+
},
|
| 71293 |
+
{
|
| 71294 |
+
"epoch": 11.5994301994302,
|
| 71295 |
+
"grad_norm": 0.25378984212875366,
|
| 71296 |
+
"learning_rate": 2.0132167225734582e-05,
|
| 71297 |
+
"loss": 0.5874,
|
| 71298 |
+
"step": 10184
|
| 71299 |
+
},
|
| 71300 |
+
{
|
| 71301 |
+
"epoch": 11.6005698005698,
|
| 71302 |
+
"grad_norm": 0.2129170149564743,
|
| 71303 |
+
"learning_rate": 2.012759730497367e-05,
|
| 71304 |
+
"loss": 0.7835,
|
| 71305 |
+
"step": 10185
|
| 71306 |
+
},
|
| 71307 |
+
{
|
| 71308 |
+
"epoch": 11.601709401709401,
|
| 71309 |
+
"grad_norm": 0.2610325217247009,
|
| 71310 |
+
"learning_rate": 2.0123027553444708e-05,
|
| 71311 |
+
"loss": 0.5777,
|
| 71312 |
+
"step": 10186
|
| 71313 |
+
},
|
| 71314 |
+
{
|
| 71315 |
+
"epoch": 11.602849002849004,
|
| 71316 |
+
"grad_norm": 0.19810867309570312,
|
| 71317 |
+
"learning_rate": 2.0118457971306402e-05,
|
| 71318 |
+
"loss": 0.6316,
|
| 71319 |
+
"step": 10187
|
| 71320 |
+
},
|
| 71321 |
+
{
|
| 71322 |
+
"epoch": 11.603988603988604,
|
| 71323 |
+
"grad_norm": 0.17435985803604126,
|
| 71324 |
+
"learning_rate": 2.0113888558717475e-05,
|
| 71325 |
+
"loss": 0.8116,
|
| 71326 |
+
"step": 10188
|
| 71327 |
+
},
|
| 71328 |
+
{
|
| 71329 |
+
"epoch": 11.605128205128205,
|
| 71330 |
+
"grad_norm": 0.24193398654460907,
|
| 71331 |
+
"learning_rate": 2.0109319315836644e-05,
|
| 71332 |
+
"loss": 0.6601,
|
| 71333 |
+
"step": 10189
|
| 71334 |
+
},
|
| 71335 |
+
{
|
| 71336 |
+
"epoch": 11.606267806267807,
|
| 71337 |
+
"grad_norm": 0.2750731408596039,
|
| 71338 |
+
"learning_rate": 2.01047502428226e-05,
|
| 71339 |
+
"loss": 0.7409,
|
| 71340 |
+
"step": 10190
|
| 71341 |
+
},
|
| 71342 |
+
{
|
| 71343 |
+
"epoch": 11.607407407407408,
|
| 71344 |
+
"grad_norm": 0.22689788043498993,
|
| 71345 |
+
"learning_rate": 2.010018133983404e-05,
|
| 71346 |
+
"loss": 0.6837,
|
| 71347 |
+
"step": 10191
|
| 71348 |
+
},
|
| 71349 |
+
{
|
| 71350 |
+
"epoch": 11.608547008547008,
|
| 71351 |
+
"grad_norm": 0.1787591278553009,
|
| 71352 |
+
"learning_rate": 2.0095612607029655e-05,
|
| 71353 |
+
"loss": 0.8582,
|
| 71354 |
+
"step": 10192
|
| 71355 |
+
},
|
| 71356 |
+
{
|
| 71357 |
+
"epoch": 11.60968660968661,
|
| 71358 |
+
"grad_norm": 0.22188825905323029,
|
| 71359 |
+
"learning_rate": 2.0091044044568138e-05,
|
| 71360 |
+
"loss": 0.7676,
|
| 71361 |
+
"step": 10193
|
| 71362 |
+
},
|
| 71363 |
+
{
|
| 71364 |
+
"epoch": 11.610826210826211,
|
| 71365 |
+
"grad_norm": 0.2448352873325348,
|
| 71366 |
+
"learning_rate": 2.0086475652608155e-05,
|
| 71367 |
+
"loss": 0.6001,
|
| 71368 |
+
"step": 10194
|
| 71369 |
+
},
|
| 71370 |
+
{
|
| 71371 |
+
"epoch": 11.611965811965812,
|
| 71372 |
+
"grad_norm": 0.22144730389118195,
|
| 71373 |
+
"learning_rate": 2.008190743130839e-05,
|
| 71374 |
+
"loss": 0.742,
|
| 71375 |
+
"step": 10195
|
| 71376 |
+
},
|
| 71377 |
+
{
|
| 71378 |
+
"epoch": 11.613105413105414,
|
| 71379 |
+
"grad_norm": 0.21111179888248444,
|
| 71380 |
+
"learning_rate": 2.0077339380827502e-05,
|
| 71381 |
+
"loss": 0.6029,
|
| 71382 |
+
"step": 10196
|
| 71383 |
+
},
|
| 71384 |
+
{
|
| 71385 |
+
"epoch": 11.614245014245014,
|
| 71386 |
+
"grad_norm": 0.25137585401535034,
|
| 71387 |
+
"learning_rate": 2.0072771501324157e-05,
|
| 71388 |
+
"loss": 0.6591,
|
| 71389 |
+
"step": 10197
|
| 71390 |
+
},
|
| 71391 |
+
{
|
| 71392 |
+
"epoch": 11.615384615384615,
|
| 71393 |
+
"grad_norm": 0.2582457363605499,
|
| 71394 |
+
"learning_rate": 2.0068203792957002e-05,
|
| 71395 |
+
"loss": 0.5815,
|
| 71396 |
+
"step": 10198
|
| 71397 |
+
},
|
| 71398 |
+
{
|
| 71399 |
+
"epoch": 11.616524216524217,
|
| 71400 |
+
"grad_norm": 0.2855578362941742,
|
| 71401 |
+
"learning_rate": 2.0063636255884686e-05,
|
| 71402 |
+
"loss": 0.8637,
|
| 71403 |
+
"step": 10199
|
| 71404 |
+
},
|
| 71405 |
+
{
|
| 71406 |
+
"epoch": 11.617663817663818,
|
| 71407 |
+
"grad_norm": 0.24564269185066223,
|
| 71408 |
+
"learning_rate": 2.005906889026587e-05,
|
| 71409 |
+
"loss": 0.602,
|
| 71410 |
+
"step": 10200
|
| 71411 |
}
|
| 71412 |
],
|
| 71413 |
"logging_steps": 1,
|
|
|
|
| 71427 |
"attributes": {}
|
| 71428 |
}
|
| 71429 |
},
|
| 71430 |
+
"total_flos": 5.703203945288393e+19,
|
| 71431 |
"train_batch_size": 8,
|
| 71432 |
"trial_name": null,
|
| 71433 |
"trial_params": null
|