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 8100, 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:eb1107b152f5bc50a905689a9226f63fd4cddb13c0e4fb2d248ed66c9f0a2964
|
| 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 sha256:95cbad15eb6275887b4b597d91ea52c39c4659ad4a60501e1866d7d13762b344
|
| 3 |
size 173247691
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17cd930da9783ca70bad4b9cdeee6a06c0acea8f34645a333c93341f487f66a3
|
| 3 |
size 14645
|
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 sha256:2fabf2f9753e61fa1b00808750ada01efeb7b7da9f04e6f05b6eeea127c1e3da
|
| 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":
|
| 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,
|
|
@@ -54608,6 +54608,2106 @@
|
|
| 54608 |
"learning_rate": 3.1144743800585256e-05,
|
| 54609 |
"loss": 0.7813,
|
| 54610 |
"step": 7800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54611 |
}
|
| 54612 |
],
|
| 54613 |
"logging_steps": 1,
|
|
@@ -54627,7 +56727,7 @@
|
|
| 54627 |
"attributes": {}
|
| 54628 |
}
|
| 54629 |
},
|
| 54630 |
-
"total_flos": 4.
|
| 54631 |
"train_batch_size": 8,
|
| 54632 |
"trial_name": null,
|
| 54633 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.225641025641025,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 54608 |
"learning_rate": 3.1144743800585256e-05,
|
| 54609 |
"loss": 0.7813,
|
| 54610 |
"step": 7800
|
| 54611 |
+
},
|
| 54612 |
+
{
|
| 54613 |
+
"epoch": 8.885470085470086,
|
| 54614 |
+
"grad_norm": 0.2184840738773346,
|
| 54615 |
+
"learning_rate": 3.11402274416994e-05,
|
| 54616 |
+
"loss": 0.6826,
|
| 54617 |
+
"step": 7801
|
| 54618 |
+
},
|
| 54619 |
+
{
|
| 54620 |
+
"epoch": 8.886609686609686,
|
| 54621 |
+
"grad_norm": 0.22706322371959686,
|
| 54622 |
+
"learning_rate": 3.1135710869546576e-05,
|
| 54623 |
+
"loss": 0.7256,
|
| 54624 |
+
"step": 7802
|
| 54625 |
+
},
|
| 54626 |
+
{
|
| 54627 |
+
"epoch": 8.887749287749287,
|
| 54628 |
+
"grad_norm": 0.20829591155052185,
|
| 54629 |
+
"learning_rate": 3.113119408428363e-05,
|
| 54630 |
+
"loss": 0.7682,
|
| 54631 |
+
"step": 7803
|
| 54632 |
+
},
|
| 54633 |
+
{
|
| 54634 |
+
"epoch": 8.88888888888889,
|
| 54635 |
+
"grad_norm": 0.19905990362167358,
|
| 54636 |
+
"learning_rate": 3.1126677086067457e-05,
|
| 54637 |
+
"loss": 0.8342,
|
| 54638 |
+
"step": 7804
|
| 54639 |
+
},
|
| 54640 |
+
{
|
| 54641 |
+
"epoch": 8.89002849002849,
|
| 54642 |
+
"grad_norm": 0.19021393358707428,
|
| 54643 |
+
"learning_rate": 3.1122159875054924e-05,
|
| 54644 |
+
"loss": 0.7214,
|
| 54645 |
+
"step": 7805
|
| 54646 |
+
},
|
| 54647 |
+
{
|
| 54648 |
+
"epoch": 8.89116809116809,
|
| 54649 |
+
"grad_norm": 0.2697696089744568,
|
| 54650 |
+
"learning_rate": 3.111764245140296e-05,
|
| 54651 |
+
"loss": 0.7523,
|
| 54652 |
+
"step": 7806
|
| 54653 |
+
},
|
| 54654 |
+
{
|
| 54655 |
+
"epoch": 8.892307692307693,
|
| 54656 |
+
"grad_norm": 0.21230560541152954,
|
| 54657 |
+
"learning_rate": 3.1113124815268444e-05,
|
| 54658 |
+
"loss": 0.6203,
|
| 54659 |
+
"step": 7807
|
| 54660 |
+
},
|
| 54661 |
+
{
|
| 54662 |
+
"epoch": 8.893447293447293,
|
| 54663 |
+
"grad_norm": 0.21342356503009796,
|
| 54664 |
+
"learning_rate": 3.11086069668083e-05,
|
| 54665 |
+
"loss": 0.7195,
|
| 54666 |
+
"step": 7808
|
| 54667 |
+
},
|
| 54668 |
+
{
|
| 54669 |
+
"epoch": 8.894586894586894,
|
| 54670 |
+
"grad_norm": 0.18811871111392975,
|
| 54671 |
+
"learning_rate": 3.110408890617942e-05,
|
| 54672 |
+
"loss": 0.826,
|
| 54673 |
+
"step": 7809
|
| 54674 |
+
},
|
| 54675 |
+
{
|
| 54676 |
+
"epoch": 8.895726495726496,
|
| 54677 |
+
"grad_norm": 0.19298504292964935,
|
| 54678 |
+
"learning_rate": 3.109957063353876e-05,
|
| 54679 |
+
"loss": 0.7805,
|
| 54680 |
+
"step": 7810
|
| 54681 |
+
},
|
| 54682 |
+
{
|
| 54683 |
+
"epoch": 8.896866096866097,
|
| 54684 |
+
"grad_norm": 0.1965564638376236,
|
| 54685 |
+
"learning_rate": 3.109505214904323e-05,
|
| 54686 |
+
"loss": 0.8131,
|
| 54687 |
+
"step": 7811
|
| 54688 |
+
},
|
| 54689 |
+
{
|
| 54690 |
+
"epoch": 8.898005698005697,
|
| 54691 |
+
"grad_norm": 0.24918051064014435,
|
| 54692 |
+
"learning_rate": 3.109053345284979e-05,
|
| 54693 |
+
"loss": 0.6382,
|
| 54694 |
+
"step": 7812
|
| 54695 |
+
},
|
| 54696 |
+
{
|
| 54697 |
+
"epoch": 8.8991452991453,
|
| 54698 |
+
"grad_norm": 0.20430241525173187,
|
| 54699 |
+
"learning_rate": 3.108601454511536e-05,
|
| 54700 |
+
"loss": 0.6763,
|
| 54701 |
+
"step": 7813
|
| 54702 |
+
},
|
| 54703 |
+
{
|
| 54704 |
+
"epoch": 8.9002849002849,
|
| 54705 |
+
"grad_norm": 0.1908400058746338,
|
| 54706 |
+
"learning_rate": 3.108149542599692e-05,
|
| 54707 |
+
"loss": 0.6695,
|
| 54708 |
+
"step": 7814
|
| 54709 |
+
},
|
| 54710 |
+
{
|
| 54711 |
+
"epoch": 8.9014245014245,
|
| 54712 |
+
"grad_norm": 0.20428918302059174,
|
| 54713 |
+
"learning_rate": 3.1076976095651414e-05,
|
| 54714 |
+
"loss": 0.852,
|
| 54715 |
+
"step": 7815
|
| 54716 |
+
},
|
| 54717 |
+
{
|
| 54718 |
+
"epoch": 8.902564102564103,
|
| 54719 |
+
"grad_norm": 0.17677143216133118,
|
| 54720 |
+
"learning_rate": 3.107245655423581e-05,
|
| 54721 |
+
"loss": 0.671,
|
| 54722 |
+
"step": 7816
|
| 54723 |
+
},
|
| 54724 |
+
{
|
| 54725 |
+
"epoch": 8.903703703703703,
|
| 54726 |
+
"grad_norm": 0.2036582976579666,
|
| 54727 |
+
"learning_rate": 3.10679368019071e-05,
|
| 54728 |
+
"loss": 0.595,
|
| 54729 |
+
"step": 7817
|
| 54730 |
+
},
|
| 54731 |
+
{
|
| 54732 |
+
"epoch": 8.904843304843304,
|
| 54733 |
+
"grad_norm": 0.1899828016757965,
|
| 54734 |
+
"learning_rate": 3.106341683882226e-05,
|
| 54735 |
+
"loss": 0.8034,
|
| 54736 |
+
"step": 7818
|
| 54737 |
+
},
|
| 54738 |
+
{
|
| 54739 |
+
"epoch": 8.905982905982906,
|
| 54740 |
+
"grad_norm": 0.17370927333831787,
|
| 54741 |
+
"learning_rate": 3.105889666513827e-05,
|
| 54742 |
+
"loss": 0.8806,
|
| 54743 |
+
"step": 7819
|
| 54744 |
+
},
|
| 54745 |
+
{
|
| 54746 |
+
"epoch": 8.907122507122507,
|
| 54747 |
+
"grad_norm": 0.22656746208667755,
|
| 54748 |
+
"learning_rate": 3.105437628101214e-05,
|
| 54749 |
+
"loss": 0.6355,
|
| 54750 |
+
"step": 7820
|
| 54751 |
+
},
|
| 54752 |
+
{
|
| 54753 |
+
"epoch": 8.908262108262107,
|
| 54754 |
+
"grad_norm": 0.2530188262462616,
|
| 54755 |
+
"learning_rate": 3.104985568660087e-05,
|
| 54756 |
+
"loss": 0.5964,
|
| 54757 |
+
"step": 7821
|
| 54758 |
+
},
|
| 54759 |
+
{
|
| 54760 |
+
"epoch": 8.90940170940171,
|
| 54761 |
+
"grad_norm": 0.25722649693489075,
|
| 54762 |
+
"learning_rate": 3.104533488206148e-05,
|
| 54763 |
+
"loss": 0.5751,
|
| 54764 |
+
"step": 7822
|
| 54765 |
+
},
|
| 54766 |
+
{
|
| 54767 |
+
"epoch": 8.91054131054131,
|
| 54768 |
+
"grad_norm": 0.27463385462760925,
|
| 54769 |
+
"learning_rate": 3.1040813867550984e-05,
|
| 54770 |
+
"loss": 0.5416,
|
| 54771 |
+
"step": 7823
|
| 54772 |
+
},
|
| 54773 |
+
{
|
| 54774 |
+
"epoch": 8.91168091168091,
|
| 54775 |
+
"grad_norm": 0.18324056267738342,
|
| 54776 |
+
"learning_rate": 3.10362926432264e-05,
|
| 54777 |
+
"loss": 0.8647,
|
| 54778 |
+
"step": 7824
|
| 54779 |
+
},
|
| 54780 |
+
{
|
| 54781 |
+
"epoch": 8.912820512820513,
|
| 54782 |
+
"grad_norm": 0.24443140625953674,
|
| 54783 |
+
"learning_rate": 3.103177120924479e-05,
|
| 54784 |
+
"loss": 0.7451,
|
| 54785 |
+
"step": 7825
|
| 54786 |
+
},
|
| 54787 |
+
{
|
| 54788 |
+
"epoch": 8.913960113960114,
|
| 54789 |
+
"grad_norm": 0.1662614941596985,
|
| 54790 |
+
"learning_rate": 3.102724956576317e-05,
|
| 54791 |
+
"loss": 0.8351,
|
| 54792 |
+
"step": 7826
|
| 54793 |
+
},
|
| 54794 |
+
{
|
| 54795 |
+
"epoch": 8.915099715099714,
|
| 54796 |
+
"grad_norm": 0.18487805128097534,
|
| 54797 |
+
"learning_rate": 3.102272771293859e-05,
|
| 54798 |
+
"loss": 0.8716,
|
| 54799 |
+
"step": 7827
|
| 54800 |
+
},
|
| 54801 |
+
{
|
| 54802 |
+
"epoch": 8.916239316239317,
|
| 54803 |
+
"grad_norm": 0.163230761885643,
|
| 54804 |
+
"learning_rate": 3.101820565092812e-05,
|
| 54805 |
+
"loss": 0.8471,
|
| 54806 |
+
"step": 7828
|
| 54807 |
+
},
|
| 54808 |
+
{
|
| 54809 |
+
"epoch": 8.917378917378917,
|
| 54810 |
+
"grad_norm": 0.3384037911891937,
|
| 54811 |
+
"learning_rate": 3.101368337988882e-05,
|
| 54812 |
+
"loss": 0.3097,
|
| 54813 |
+
"step": 7829
|
| 54814 |
+
},
|
| 54815 |
+
{
|
| 54816 |
+
"epoch": 8.918518518518518,
|
| 54817 |
+
"grad_norm": 0.1944686472415924,
|
| 54818 |
+
"learning_rate": 3.1009160899977756e-05,
|
| 54819 |
+
"loss": 0.6428,
|
| 54820 |
+
"step": 7830
|
| 54821 |
+
},
|
| 54822 |
+
{
|
| 54823 |
+
"epoch": 8.91965811965812,
|
| 54824 |
+
"grad_norm": 0.1764814555644989,
|
| 54825 |
+
"learning_rate": 3.100463821135201e-05,
|
| 54826 |
+
"loss": 0.705,
|
| 54827 |
+
"step": 7831
|
| 54828 |
+
},
|
| 54829 |
+
{
|
| 54830 |
+
"epoch": 8.92079772079772,
|
| 54831 |
+
"grad_norm": 0.17810149490833282,
|
| 54832 |
+
"learning_rate": 3.100011531416866e-05,
|
| 54833 |
+
"loss": 0.8209,
|
| 54834 |
+
"step": 7832
|
| 54835 |
+
},
|
| 54836 |
+
{
|
| 54837 |
+
"epoch": 8.921937321937321,
|
| 54838 |
+
"grad_norm": 0.2048386037349701,
|
| 54839 |
+
"learning_rate": 3.0995592208584814e-05,
|
| 54840 |
+
"loss": 0.6529,
|
| 54841 |
+
"step": 7833
|
| 54842 |
+
},
|
| 54843 |
+
{
|
| 54844 |
+
"epoch": 8.923076923076923,
|
| 54845 |
+
"grad_norm": 0.16116826236248016,
|
| 54846 |
+
"learning_rate": 3.099106889475756e-05,
|
| 54847 |
+
"loss": 0.8393,
|
| 54848 |
+
"step": 7834
|
| 54849 |
+
},
|
| 54850 |
+
{
|
| 54851 |
+
"epoch": 8.924216524216524,
|
| 54852 |
+
"grad_norm": 0.2247179001569748,
|
| 54853 |
+
"learning_rate": 3.098654537284401e-05,
|
| 54854 |
+
"loss": 0.705,
|
| 54855 |
+
"step": 7835
|
| 54856 |
+
},
|
| 54857 |
+
{
|
| 54858 |
+
"epoch": 8.925356125356124,
|
| 54859 |
+
"grad_norm": 0.24455715715885162,
|
| 54860 |
+
"learning_rate": 3.098202164300128e-05,
|
| 54861 |
+
"loss": 0.7098,
|
| 54862 |
+
"step": 7836
|
| 54863 |
+
},
|
| 54864 |
+
{
|
| 54865 |
+
"epoch": 8.926495726495727,
|
| 54866 |
+
"grad_norm": 0.2455403357744217,
|
| 54867 |
+
"learning_rate": 3.097749770538648e-05,
|
| 54868 |
+
"loss": 0.5523,
|
| 54869 |
+
"step": 7837
|
| 54870 |
+
},
|
| 54871 |
+
{
|
| 54872 |
+
"epoch": 8.927635327635327,
|
| 54873 |
+
"grad_norm": 0.24926690757274628,
|
| 54874 |
+
"learning_rate": 3.097297356015674e-05,
|
| 54875 |
+
"loss": 0.583,
|
| 54876 |
+
"step": 7838
|
| 54877 |
+
},
|
| 54878 |
+
{
|
| 54879 |
+
"epoch": 8.928774928774928,
|
| 54880 |
+
"grad_norm": 0.19409289956092834,
|
| 54881 |
+
"learning_rate": 3.096844920746921e-05,
|
| 54882 |
+
"loss": 0.7751,
|
| 54883 |
+
"step": 7839
|
| 54884 |
+
},
|
| 54885 |
+
{
|
| 54886 |
+
"epoch": 8.92991452991453,
|
| 54887 |
+
"grad_norm": 0.24124380946159363,
|
| 54888 |
+
"learning_rate": 3.096392464748103e-05,
|
| 54889 |
+
"loss": 0.7231,
|
| 54890 |
+
"step": 7840
|
| 54891 |
+
},
|
| 54892 |
+
{
|
| 54893 |
+
"epoch": 8.93105413105413,
|
| 54894 |
+
"grad_norm": 0.2634790241718292,
|
| 54895 |
+
"learning_rate": 3.095939988034934e-05,
|
| 54896 |
+
"loss": 0.6397,
|
| 54897 |
+
"step": 7841
|
| 54898 |
+
},
|
| 54899 |
+
{
|
| 54900 |
+
"epoch": 8.932193732193731,
|
| 54901 |
+
"grad_norm": 0.16715000569820404,
|
| 54902 |
+
"learning_rate": 3.095487490623131e-05,
|
| 54903 |
+
"loss": 0.8968,
|
| 54904 |
+
"step": 7842
|
| 54905 |
+
},
|
| 54906 |
+
{
|
| 54907 |
+
"epoch": 8.933333333333334,
|
| 54908 |
+
"grad_norm": 0.17600218951702118,
|
| 54909 |
+
"learning_rate": 3.0950349725284085e-05,
|
| 54910 |
+
"loss": 0.7262,
|
| 54911 |
+
"step": 7843
|
| 54912 |
+
},
|
| 54913 |
+
{
|
| 54914 |
+
"epoch": 8.934472934472934,
|
| 54915 |
+
"grad_norm": 0.19259227812290192,
|
| 54916 |
+
"learning_rate": 3.094582433766486e-05,
|
| 54917 |
+
"loss": 0.9158,
|
| 54918 |
+
"step": 7844
|
| 54919 |
+
},
|
| 54920 |
+
{
|
| 54921 |
+
"epoch": 8.935612535612536,
|
| 54922 |
+
"grad_norm": 0.21922144293785095,
|
| 54923 |
+
"learning_rate": 3.09412987435308e-05,
|
| 54924 |
+
"loss": 0.5877,
|
| 54925 |
+
"step": 7845
|
| 54926 |
+
},
|
| 54927 |
+
{
|
| 54928 |
+
"epoch": 8.936752136752137,
|
| 54929 |
+
"grad_norm": 0.24164317548274994,
|
| 54930 |
+
"learning_rate": 3.0936772943039106e-05,
|
| 54931 |
+
"loss": 0.5463,
|
| 54932 |
+
"step": 7846
|
| 54933 |
+
},
|
| 54934 |
+
{
|
| 54935 |
+
"epoch": 8.937891737891738,
|
| 54936 |
+
"grad_norm": 0.2136332392692566,
|
| 54937 |
+
"learning_rate": 3.0932246936346955e-05,
|
| 54938 |
+
"loss": 0.7558,
|
| 54939 |
+
"step": 7847
|
| 54940 |
+
},
|
| 54941 |
+
{
|
| 54942 |
+
"epoch": 8.93903133903134,
|
| 54943 |
+
"grad_norm": 0.23429881036281586,
|
| 54944 |
+
"learning_rate": 3.092772072361156e-05,
|
| 54945 |
+
"loss": 0.7598,
|
| 54946 |
+
"step": 7848
|
| 54947 |
+
},
|
| 54948 |
+
{
|
| 54949 |
+
"epoch": 8.94017094017094,
|
| 54950 |
+
"grad_norm": 0.19063034653663635,
|
| 54951 |
+
"learning_rate": 3.0923194304990116e-05,
|
| 54952 |
+
"loss": 0.896,
|
| 54953 |
+
"step": 7849
|
| 54954 |
+
},
|
| 54955 |
+
{
|
| 54956 |
+
"epoch": 8.941310541310541,
|
| 54957 |
+
"grad_norm": 0.22400988638401031,
|
| 54958 |
+
"learning_rate": 3.0918667680639846e-05,
|
| 54959 |
+
"loss": 0.6574,
|
| 54960 |
+
"step": 7850
|
| 54961 |
+
},
|
| 54962 |
+
{
|
| 54963 |
+
"epoch": 8.942450142450143,
|
| 54964 |
+
"grad_norm": 0.23572759330272675,
|
| 54965 |
+
"learning_rate": 3.091414085071797e-05,
|
| 54966 |
+
"loss": 0.6288,
|
| 54967 |
+
"step": 7851
|
| 54968 |
+
},
|
| 54969 |
+
{
|
| 54970 |
+
"epoch": 8.943589743589744,
|
| 54971 |
+
"grad_norm": 0.25042036175727844,
|
| 54972 |
+
"learning_rate": 3.090961381538172e-05,
|
| 54973 |
+
"loss": 0.6406,
|
| 54974 |
+
"step": 7852
|
| 54975 |
+
},
|
| 54976 |
+
{
|
| 54977 |
+
"epoch": 8.944729344729344,
|
| 54978 |
+
"grad_norm": 0.18161028623580933,
|
| 54979 |
+
"learning_rate": 3.090508657478834e-05,
|
| 54980 |
+
"loss": 0.8103,
|
| 54981 |
+
"step": 7853
|
| 54982 |
+
},
|
| 54983 |
+
{
|
| 54984 |
+
"epoch": 8.945868945868947,
|
| 54985 |
+
"grad_norm": 0.19624114036560059,
|
| 54986 |
+
"learning_rate": 3.090055912909504e-05,
|
| 54987 |
+
"loss": 0.6675,
|
| 54988 |
+
"step": 7854
|
| 54989 |
+
},
|
| 54990 |
+
{
|
| 54991 |
+
"epoch": 8.947008547008547,
|
| 54992 |
+
"grad_norm": 0.15669001638889313,
|
| 54993 |
+
"learning_rate": 3.089603147845911e-05,
|
| 54994 |
+
"loss": 0.7988,
|
| 54995 |
+
"step": 7855
|
| 54996 |
+
},
|
| 54997 |
+
{
|
| 54998 |
+
"epoch": 8.948148148148148,
|
| 54999 |
+
"grad_norm": 0.17270700633525848,
|
| 55000 |
+
"learning_rate": 3.08915036230378e-05,
|
| 55001 |
+
"loss": 0.9235,
|
| 55002 |
+
"step": 7856
|
| 55003 |
+
},
|
| 55004 |
+
{
|
| 55005 |
+
"epoch": 8.94928774928775,
|
| 55006 |
+
"grad_norm": 0.18196718394756317,
|
| 55007 |
+
"learning_rate": 3.0886975562988366e-05,
|
| 55008 |
+
"loss": 0.8509,
|
| 55009 |
+
"step": 7857
|
| 55010 |
+
},
|
| 55011 |
+
{
|
| 55012 |
+
"epoch": 8.95042735042735,
|
| 55013 |
+
"grad_norm": 0.28779137134552,
|
| 55014 |
+
"learning_rate": 3.088244729846807e-05,
|
| 55015 |
+
"loss": 0.704,
|
| 55016 |
+
"step": 7858
|
| 55017 |
+
},
|
| 55018 |
+
{
|
| 55019 |
+
"epoch": 8.951566951566951,
|
| 55020 |
+
"grad_norm": 0.22087204456329346,
|
| 55021 |
+
"learning_rate": 3.0877918829634213e-05,
|
| 55022 |
+
"loss": 0.7136,
|
| 55023 |
+
"step": 7859
|
| 55024 |
+
},
|
| 55025 |
+
{
|
| 55026 |
+
"epoch": 8.952706552706553,
|
| 55027 |
+
"grad_norm": 0.19543227553367615,
|
| 55028 |
+
"learning_rate": 3.087339015664406e-05,
|
| 55029 |
+
"loss": 0.7373,
|
| 55030 |
+
"step": 7860
|
| 55031 |
+
},
|
| 55032 |
+
{
|
| 55033 |
+
"epoch": 8.953846153846154,
|
| 55034 |
+
"grad_norm": 0.1887291520833969,
|
| 55035 |
+
"learning_rate": 3.086886127965492e-05,
|
| 55036 |
+
"loss": 0.7649,
|
| 55037 |
+
"step": 7861
|
| 55038 |
+
},
|
| 55039 |
+
{
|
| 55040 |
+
"epoch": 8.954985754985755,
|
| 55041 |
+
"grad_norm": 0.18013887107372284,
|
| 55042 |
+
"learning_rate": 3.086433219882409e-05,
|
| 55043 |
+
"loss": 0.8074,
|
| 55044 |
+
"step": 7862
|
| 55045 |
+
},
|
| 55046 |
+
{
|
| 55047 |
+
"epoch": 8.956125356125357,
|
| 55048 |
+
"grad_norm": 0.2100178450345993,
|
| 55049 |
+
"learning_rate": 3.085980291430887e-05,
|
| 55050 |
+
"loss": 0.6478,
|
| 55051 |
+
"step": 7863
|
| 55052 |
+
},
|
| 55053 |
+
{
|
| 55054 |
+
"epoch": 8.957264957264957,
|
| 55055 |
+
"grad_norm": 0.18159078061580658,
|
| 55056 |
+
"learning_rate": 3.085527342626658e-05,
|
| 55057 |
+
"loss": 0.8595,
|
| 55058 |
+
"step": 7864
|
| 55059 |
+
},
|
| 55060 |
+
{
|
| 55061 |
+
"epoch": 8.958404558404558,
|
| 55062 |
+
"grad_norm": 0.18629483878612518,
|
| 55063 |
+
"learning_rate": 3.085074373485456e-05,
|
| 55064 |
+
"loss": 0.6951,
|
| 55065 |
+
"step": 7865
|
| 55066 |
+
},
|
| 55067 |
+
{
|
| 55068 |
+
"epoch": 8.95954415954416,
|
| 55069 |
+
"grad_norm": 0.22148196399211884,
|
| 55070 |
+
"learning_rate": 3.0846213840230106e-05,
|
| 55071 |
+
"loss": 0.7306,
|
| 55072 |
+
"step": 7866
|
| 55073 |
+
},
|
| 55074 |
+
{
|
| 55075 |
+
"epoch": 8.96068376068376,
|
| 55076 |
+
"grad_norm": 0.2141670435667038,
|
| 55077 |
+
"learning_rate": 3.0841683742550566e-05,
|
| 55078 |
+
"loss": 0.642,
|
| 55079 |
+
"step": 7867
|
| 55080 |
+
},
|
| 55081 |
+
{
|
| 55082 |
+
"epoch": 8.961823361823361,
|
| 55083 |
+
"grad_norm": 0.22931569814682007,
|
| 55084 |
+
"learning_rate": 3.083715344197329e-05,
|
| 55085 |
+
"loss": 0.5878,
|
| 55086 |
+
"step": 7868
|
| 55087 |
+
},
|
| 55088 |
+
{
|
| 55089 |
+
"epoch": 8.962962962962964,
|
| 55090 |
+
"grad_norm": 0.2777910530567169,
|
| 55091 |
+
"learning_rate": 3.083262293865562e-05,
|
| 55092 |
+
"loss": 0.4543,
|
| 55093 |
+
"step": 7869
|
| 55094 |
+
},
|
| 55095 |
+
{
|
| 55096 |
+
"epoch": 8.964102564102564,
|
| 55097 |
+
"grad_norm": 0.2475350946187973,
|
| 55098 |
+
"learning_rate": 3.082809223275492e-05,
|
| 55099 |
+
"loss": 0.6118,
|
| 55100 |
+
"step": 7870
|
| 55101 |
+
},
|
| 55102 |
+
{
|
| 55103 |
+
"epoch": 8.965242165242165,
|
| 55104 |
+
"grad_norm": 0.2269582450389862,
|
| 55105 |
+
"learning_rate": 3.082356132442854e-05,
|
| 55106 |
+
"loss": 0.7678,
|
| 55107 |
+
"step": 7871
|
| 55108 |
+
},
|
| 55109 |
+
{
|
| 55110 |
+
"epoch": 8.966381766381767,
|
| 55111 |
+
"grad_norm": 0.18349537253379822,
|
| 55112 |
+
"learning_rate": 3.081903021383387e-05,
|
| 55113 |
+
"loss": 0.8643,
|
| 55114 |
+
"step": 7872
|
| 55115 |
+
},
|
| 55116 |
+
{
|
| 55117 |
+
"epoch": 8.967521367521368,
|
| 55118 |
+
"grad_norm": 0.17430894076824188,
|
| 55119 |
+
"learning_rate": 3.081449890112827e-05,
|
| 55120 |
+
"loss": 0.7734,
|
| 55121 |
+
"step": 7873
|
| 55122 |
+
},
|
| 55123 |
+
{
|
| 55124 |
+
"epoch": 8.968660968660968,
|
| 55125 |
+
"grad_norm": 0.25528132915496826,
|
| 55126 |
+
"learning_rate": 3.080996738646914e-05,
|
| 55127 |
+
"loss": 0.5903,
|
| 55128 |
+
"step": 7874
|
| 55129 |
+
},
|
| 55130 |
+
{
|
| 55131 |
+
"epoch": 8.96980056980057,
|
| 55132 |
+
"grad_norm": 0.21637718379497528,
|
| 55133 |
+
"learning_rate": 3.080543567001387e-05,
|
| 55134 |
+
"loss": 0.6596,
|
| 55135 |
+
"step": 7875
|
| 55136 |
+
},
|
| 55137 |
+
{
|
| 55138 |
+
"epoch": 8.970940170940171,
|
| 55139 |
+
"grad_norm": 0.20959778130054474,
|
| 55140 |
+
"learning_rate": 3.080090375191984e-05,
|
| 55141 |
+
"loss": 0.6371,
|
| 55142 |
+
"step": 7876
|
| 55143 |
+
},
|
| 55144 |
+
{
|
| 55145 |
+
"epoch": 8.972079772079772,
|
| 55146 |
+
"grad_norm": 0.19999878108501434,
|
| 55147 |
+
"learning_rate": 3.079637163234448e-05,
|
| 55148 |
+
"loss": 0.6877,
|
| 55149 |
+
"step": 7877
|
| 55150 |
+
},
|
| 55151 |
+
{
|
| 55152 |
+
"epoch": 8.973219373219374,
|
| 55153 |
+
"grad_norm": 0.18591931462287903,
|
| 55154 |
+
"learning_rate": 3.0791839311445184e-05,
|
| 55155 |
+
"loss": 0.8589,
|
| 55156 |
+
"step": 7878
|
| 55157 |
+
},
|
| 55158 |
+
{
|
| 55159 |
+
"epoch": 8.974358974358974,
|
| 55160 |
+
"grad_norm": 0.1909388303756714,
|
| 55161 |
+
"learning_rate": 3.078730678937939e-05,
|
| 55162 |
+
"loss": 0.8331,
|
| 55163 |
+
"step": 7879
|
| 55164 |
+
},
|
| 55165 |
+
{
|
| 55166 |
+
"epoch": 8.975498575498575,
|
| 55167 |
+
"grad_norm": 0.20299936830997467,
|
| 55168 |
+
"learning_rate": 3.078277406630452e-05,
|
| 55169 |
+
"loss": 0.7731,
|
| 55170 |
+
"step": 7880
|
| 55171 |
+
},
|
| 55172 |
+
{
|
| 55173 |
+
"epoch": 8.976638176638177,
|
| 55174 |
+
"grad_norm": 0.19652584195137024,
|
| 55175 |
+
"learning_rate": 3.0778241142378e-05,
|
| 55176 |
+
"loss": 0.8612,
|
| 55177 |
+
"step": 7881
|
| 55178 |
+
},
|
| 55179 |
+
{
|
| 55180 |
+
"epoch": 8.977777777777778,
|
| 55181 |
+
"grad_norm": 0.1882491111755371,
|
| 55182 |
+
"learning_rate": 3.077370801775726e-05,
|
| 55183 |
+
"loss": 0.7031,
|
| 55184 |
+
"step": 7882
|
| 55185 |
+
},
|
| 55186 |
+
{
|
| 55187 |
+
"epoch": 8.978917378917378,
|
| 55188 |
+
"grad_norm": 0.16153548657894135,
|
| 55189 |
+
"learning_rate": 3.0769174692599785e-05,
|
| 55190 |
+
"loss": 0.8683,
|
| 55191 |
+
"step": 7883
|
| 55192 |
+
},
|
| 55193 |
+
{
|
| 55194 |
+
"epoch": 8.98005698005698,
|
| 55195 |
+
"grad_norm": 0.23726435005664825,
|
| 55196 |
+
"learning_rate": 3.0764641167063e-05,
|
| 55197 |
+
"loss": 0.6444,
|
| 55198 |
+
"step": 7884
|
| 55199 |
+
},
|
| 55200 |
+
{
|
| 55201 |
+
"epoch": 8.981196581196581,
|
| 55202 |
+
"grad_norm": 0.21085144579410553,
|
| 55203 |
+
"learning_rate": 3.076010744130437e-05,
|
| 55204 |
+
"loss": 0.8917,
|
| 55205 |
+
"step": 7885
|
| 55206 |
+
},
|
| 55207 |
+
{
|
| 55208 |
+
"epoch": 8.982336182336182,
|
| 55209 |
+
"grad_norm": 0.18745844066143036,
|
| 55210 |
+
"learning_rate": 3.075557351548137e-05,
|
| 55211 |
+
"loss": 0.7833,
|
| 55212 |
+
"step": 7886
|
| 55213 |
+
},
|
| 55214 |
+
{
|
| 55215 |
+
"epoch": 8.983475783475784,
|
| 55216 |
+
"grad_norm": 0.19731897115707397,
|
| 55217 |
+
"learning_rate": 3.075103938975148e-05,
|
| 55218 |
+
"loss": 0.8099,
|
| 55219 |
+
"step": 7887
|
| 55220 |
+
},
|
| 55221 |
+
{
|
| 55222 |
+
"epoch": 8.984615384615385,
|
| 55223 |
+
"grad_norm": 0.1938193440437317,
|
| 55224 |
+
"learning_rate": 3.0746505064272164e-05,
|
| 55225 |
+
"loss": 0.7111,
|
| 55226 |
+
"step": 7888
|
| 55227 |
+
},
|
| 55228 |
+
{
|
| 55229 |
+
"epoch": 8.985754985754985,
|
| 55230 |
+
"grad_norm": 0.21260614693164825,
|
| 55231 |
+
"learning_rate": 3.074197053920093e-05,
|
| 55232 |
+
"loss": 0.7241,
|
| 55233 |
+
"step": 7889
|
| 55234 |
+
},
|
| 55235 |
+
{
|
| 55236 |
+
"epoch": 8.986894586894588,
|
| 55237 |
+
"grad_norm": 0.1491367369890213,
|
| 55238 |
+
"learning_rate": 3.073743581469527e-05,
|
| 55239 |
+
"loss": 0.8752,
|
| 55240 |
+
"step": 7890
|
| 55241 |
+
},
|
| 55242 |
+
{
|
| 55243 |
+
"epoch": 8.988034188034188,
|
| 55244 |
+
"grad_norm": 0.30841800570487976,
|
| 55245 |
+
"learning_rate": 3.0732900890912695e-05,
|
| 55246 |
+
"loss": 0.4057,
|
| 55247 |
+
"step": 7891
|
| 55248 |
+
},
|
| 55249 |
+
{
|
| 55250 |
+
"epoch": 8.989173789173789,
|
| 55251 |
+
"grad_norm": 0.2244536429643631,
|
| 55252 |
+
"learning_rate": 3.072836576801069e-05,
|
| 55253 |
+
"loss": 0.6508,
|
| 55254 |
+
"step": 7892
|
| 55255 |
+
},
|
| 55256 |
+
{
|
| 55257 |
+
"epoch": 8.990313390313391,
|
| 55258 |
+
"grad_norm": 0.22859877347946167,
|
| 55259 |
+
"learning_rate": 3.0723830446146796e-05,
|
| 55260 |
+
"loss": 0.6319,
|
| 55261 |
+
"step": 7893
|
| 55262 |
+
},
|
| 55263 |
+
{
|
| 55264 |
+
"epoch": 8.991452991452991,
|
| 55265 |
+
"grad_norm": 0.20965613424777985,
|
| 55266 |
+
"learning_rate": 3.071929492547853e-05,
|
| 55267 |
+
"loss": 0.542,
|
| 55268 |
+
"step": 7894
|
| 55269 |
+
},
|
| 55270 |
+
{
|
| 55271 |
+
"epoch": 8.992592592592592,
|
| 55272 |
+
"grad_norm": 0.22765378654003143,
|
| 55273 |
+
"learning_rate": 3.071475920616342e-05,
|
| 55274 |
+
"loss": 0.7092,
|
| 55275 |
+
"step": 7895
|
| 55276 |
+
},
|
| 55277 |
+
{
|
| 55278 |
+
"epoch": 8.993732193732194,
|
| 55279 |
+
"grad_norm": 0.1661691665649414,
|
| 55280 |
+
"learning_rate": 3.071022328835902e-05,
|
| 55281 |
+
"loss": 0.898,
|
| 55282 |
+
"step": 7896
|
| 55283 |
+
},
|
| 55284 |
+
{
|
| 55285 |
+
"epoch": 8.994871794871795,
|
| 55286 |
+
"grad_norm": 0.22471977770328522,
|
| 55287 |
+
"learning_rate": 3.070568717222285e-05,
|
| 55288 |
+
"loss": 0.6615,
|
| 55289 |
+
"step": 7897
|
| 55290 |
+
},
|
| 55291 |
+
{
|
| 55292 |
+
"epoch": 8.996011396011395,
|
| 55293 |
+
"grad_norm": 0.2047819197177887,
|
| 55294 |
+
"learning_rate": 3.070115085791248e-05,
|
| 55295 |
+
"loss": 0.8607,
|
| 55296 |
+
"step": 7898
|
| 55297 |
+
},
|
| 55298 |
+
{
|
| 55299 |
+
"epoch": 8.997150997150998,
|
| 55300 |
+
"grad_norm": 0.15379248559474945,
|
| 55301 |
+
"learning_rate": 3.069661434558545e-05,
|
| 55302 |
+
"loss": 0.8015,
|
| 55303 |
+
"step": 7899
|
| 55304 |
+
},
|
| 55305 |
+
{
|
| 55306 |
+
"epoch": 8.998290598290598,
|
| 55307 |
+
"grad_norm": 0.21577894687652588,
|
| 55308 |
+
"learning_rate": 3.0692077635399354e-05,
|
| 55309 |
+
"loss": 0.7617,
|
| 55310 |
+
"step": 7900
|
| 55311 |
+
},
|
| 55312 |
+
{
|
| 55313 |
+
"epoch": 8.999430199430199,
|
| 55314 |
+
"grad_norm": 0.21575061976909637,
|
| 55315 |
+
"learning_rate": 3.0687540727511736e-05,
|
| 55316 |
+
"loss": 0.7665,
|
| 55317 |
+
"step": 7901
|
| 55318 |
+
},
|
| 55319 |
+
{
|
| 55320 |
+
"epoch": 9.0,
|
| 55321 |
+
"grad_norm": 0.3739865720272064,
|
| 55322 |
+
"learning_rate": 3.06830036220802e-05,
|
| 55323 |
+
"loss": 0.4867,
|
| 55324 |
+
"step": 7902
|
| 55325 |
+
},
|
| 55326 |
+
{
|
| 55327 |
+
"epoch": 9.0011396011396,
|
| 55328 |
+
"grad_norm": 0.169849693775177,
|
| 55329 |
+
"learning_rate": 3.067846631926231e-05,
|
| 55330 |
+
"loss": 0.87,
|
| 55331 |
+
"step": 7903
|
| 55332 |
+
},
|
| 55333 |
+
{
|
| 55334 |
+
"epoch": 9.002279202279203,
|
| 55335 |
+
"grad_norm": 0.14331378042697906,
|
| 55336 |
+
"learning_rate": 3.067392881921567e-05,
|
| 55337 |
+
"loss": 0.8204,
|
| 55338 |
+
"step": 7904
|
| 55339 |
+
},
|
| 55340 |
+
{
|
| 55341 |
+
"epoch": 9.003418803418803,
|
| 55342 |
+
"grad_norm": 0.20782536268234253,
|
| 55343 |
+
"learning_rate": 3.066939112209788e-05,
|
| 55344 |
+
"loss": 0.6792,
|
| 55345 |
+
"step": 7905
|
| 55346 |
+
},
|
| 55347 |
+
{
|
| 55348 |
+
"epoch": 9.004558404558404,
|
| 55349 |
+
"grad_norm": 0.23367100954055786,
|
| 55350 |
+
"learning_rate": 3.0664853228066545e-05,
|
| 55351 |
+
"loss": 0.6591,
|
| 55352 |
+
"step": 7906
|
| 55353 |
+
},
|
| 55354 |
+
{
|
| 55355 |
+
"epoch": 9.005698005698006,
|
| 55356 |
+
"grad_norm": 0.20821213722229004,
|
| 55357 |
+
"learning_rate": 3.066031513727928e-05,
|
| 55358 |
+
"loss": 0.6785,
|
| 55359 |
+
"step": 7907
|
| 55360 |
+
},
|
| 55361 |
+
{
|
| 55362 |
+
"epoch": 9.006837606837607,
|
| 55363 |
+
"grad_norm": 0.19033651053905487,
|
| 55364 |
+
"learning_rate": 3.0655776849893716e-05,
|
| 55365 |
+
"loss": 0.7277,
|
| 55366 |
+
"step": 7908
|
| 55367 |
+
},
|
| 55368 |
+
{
|
| 55369 |
+
"epoch": 9.007977207977207,
|
| 55370 |
+
"grad_norm": 0.18766376376152039,
|
| 55371 |
+
"learning_rate": 3.065123836606745e-05,
|
| 55372 |
+
"loss": 0.7571,
|
| 55373 |
+
"step": 7909
|
| 55374 |
+
},
|
| 55375 |
+
{
|
| 55376 |
+
"epoch": 9.00911680911681,
|
| 55377 |
+
"grad_norm": 0.18898771703243256,
|
| 55378 |
+
"learning_rate": 3.064669968595814e-05,
|
| 55379 |
+
"loss": 0.9254,
|
| 55380 |
+
"step": 7910
|
| 55381 |
+
},
|
| 55382 |
+
{
|
| 55383 |
+
"epoch": 9.01025641025641,
|
| 55384 |
+
"grad_norm": 0.20341551303863525,
|
| 55385 |
+
"learning_rate": 3.064216080972342e-05,
|
| 55386 |
+
"loss": 0.7038,
|
| 55387 |
+
"step": 7911
|
| 55388 |
+
},
|
| 55389 |
+
{
|
| 55390 |
+
"epoch": 9.01139601139601,
|
| 55391 |
+
"grad_norm": 0.1814105361700058,
|
| 55392 |
+
"learning_rate": 3.063762173752095e-05,
|
| 55393 |
+
"loss": 0.6781,
|
| 55394 |
+
"step": 7912
|
| 55395 |
+
},
|
| 55396 |
+
{
|
| 55397 |
+
"epoch": 9.012535612535613,
|
| 55398 |
+
"grad_norm": 0.23274095356464386,
|
| 55399 |
+
"learning_rate": 3.0633082469508364e-05,
|
| 55400 |
+
"loss": 0.4745,
|
| 55401 |
+
"step": 7913
|
| 55402 |
+
},
|
| 55403 |
+
{
|
| 55404 |
+
"epoch": 9.013675213675214,
|
| 55405 |
+
"grad_norm": 0.20255059003829956,
|
| 55406 |
+
"learning_rate": 3.062854300584333e-05,
|
| 55407 |
+
"loss": 0.7065,
|
| 55408 |
+
"step": 7914
|
| 55409 |
+
},
|
| 55410 |
+
{
|
| 55411 |
+
"epoch": 9.014814814814814,
|
| 55412 |
+
"grad_norm": 0.22046412527561188,
|
| 55413 |
+
"learning_rate": 3.062400334668353e-05,
|
| 55414 |
+
"loss": 0.6523,
|
| 55415 |
+
"step": 7915
|
| 55416 |
+
},
|
| 55417 |
+
{
|
| 55418 |
+
"epoch": 9.015954415954416,
|
| 55419 |
+
"grad_norm": 0.17578087747097015,
|
| 55420 |
+
"learning_rate": 3.061946349218662e-05,
|
| 55421 |
+
"loss": 0.9795,
|
| 55422 |
+
"step": 7916
|
| 55423 |
+
},
|
| 55424 |
+
{
|
| 55425 |
+
"epoch": 9.017094017094017,
|
| 55426 |
+
"grad_norm": 0.1903984397649765,
|
| 55427 |
+
"learning_rate": 3.061492344251029e-05,
|
| 55428 |
+
"loss": 0.8292,
|
| 55429 |
+
"step": 7917
|
| 55430 |
+
},
|
| 55431 |
+
{
|
| 55432 |
+
"epoch": 9.018233618233618,
|
| 55433 |
+
"grad_norm": 0.20894210040569305,
|
| 55434 |
+
"learning_rate": 3.061038319781223e-05,
|
| 55435 |
+
"loss": 0.7828,
|
| 55436 |
+
"step": 7918
|
| 55437 |
+
},
|
| 55438 |
+
{
|
| 55439 |
+
"epoch": 9.01937321937322,
|
| 55440 |
+
"grad_norm": 0.1967022567987442,
|
| 55441 |
+
"learning_rate": 3.060584275825013e-05,
|
| 55442 |
+
"loss": 0.6703,
|
| 55443 |
+
"step": 7919
|
| 55444 |
+
},
|
| 55445 |
+
{
|
| 55446 |
+
"epoch": 9.02051282051282,
|
| 55447 |
+
"grad_norm": 0.20595534145832062,
|
| 55448 |
+
"learning_rate": 3.0601302123981697e-05,
|
| 55449 |
+
"loss": 0.7336,
|
| 55450 |
+
"step": 7920
|
| 55451 |
+
},
|
| 55452 |
+
{
|
| 55453 |
+
"epoch": 9.021652421652421,
|
| 55454 |
+
"grad_norm": 0.22291889786720276,
|
| 55455 |
+
"learning_rate": 3.0596761295164634e-05,
|
| 55456 |
+
"loss": 0.4897,
|
| 55457 |
+
"step": 7921
|
| 55458 |
+
},
|
| 55459 |
+
{
|
| 55460 |
+
"epoch": 9.022792022792023,
|
| 55461 |
+
"grad_norm": 0.20241078734397888,
|
| 55462 |
+
"learning_rate": 3.059222027195666e-05,
|
| 55463 |
+
"loss": 0.7701,
|
| 55464 |
+
"step": 7922
|
| 55465 |
+
},
|
| 55466 |
+
{
|
| 55467 |
+
"epoch": 9.023931623931624,
|
| 55468 |
+
"grad_norm": 0.19974841177463531,
|
| 55469 |
+
"learning_rate": 3.05876790545155e-05,
|
| 55470 |
+
"loss": 0.6909,
|
| 55471 |
+
"step": 7923
|
| 55472 |
+
},
|
| 55473 |
+
{
|
| 55474 |
+
"epoch": 9.025071225071224,
|
| 55475 |
+
"grad_norm": 0.22207312285900116,
|
| 55476 |
+
"learning_rate": 3.058313764299888e-05,
|
| 55477 |
+
"loss": 0.6557,
|
| 55478 |
+
"step": 7924
|
| 55479 |
+
},
|
| 55480 |
+
{
|
| 55481 |
+
"epoch": 9.026210826210827,
|
| 55482 |
+
"grad_norm": 0.2338474541902542,
|
| 55483 |
+
"learning_rate": 3.0578596037564544e-05,
|
| 55484 |
+
"loss": 0.5804,
|
| 55485 |
+
"step": 7925
|
| 55486 |
+
},
|
| 55487 |
+
{
|
| 55488 |
+
"epoch": 9.027350427350427,
|
| 55489 |
+
"grad_norm": 0.19024735689163208,
|
| 55490 |
+
"learning_rate": 3.057405423837021e-05,
|
| 55491 |
+
"loss": 0.7939,
|
| 55492 |
+
"step": 7926
|
| 55493 |
+
},
|
| 55494 |
+
{
|
| 55495 |
+
"epoch": 9.028490028490028,
|
| 55496 |
+
"grad_norm": 0.18150648474693298,
|
| 55497 |
+
"learning_rate": 3.0569512245573654e-05,
|
| 55498 |
+
"loss": 0.7721,
|
| 55499 |
+
"step": 7927
|
| 55500 |
+
},
|
| 55501 |
+
{
|
| 55502 |
+
"epoch": 9.02962962962963,
|
| 55503 |
+
"grad_norm": 0.19173087179660797,
|
| 55504 |
+
"learning_rate": 3.056497005933262e-05,
|
| 55505 |
+
"loss": 0.7397,
|
| 55506 |
+
"step": 7928
|
| 55507 |
+
},
|
| 55508 |
+
{
|
| 55509 |
+
"epoch": 9.03076923076923,
|
| 55510 |
+
"grad_norm": 0.205705463886261,
|
| 55511 |
+
"learning_rate": 3.056042767980487e-05,
|
| 55512 |
+
"loss": 0.7156,
|
| 55513 |
+
"step": 7929
|
| 55514 |
+
},
|
| 55515 |
+
{
|
| 55516 |
+
"epoch": 9.031908831908831,
|
| 55517 |
+
"grad_norm": 0.21228349208831787,
|
| 55518 |
+
"learning_rate": 3.0555885107148186e-05,
|
| 55519 |
+
"loss": 0.6467,
|
| 55520 |
+
"step": 7930
|
| 55521 |
+
},
|
| 55522 |
+
{
|
| 55523 |
+
"epoch": 9.033048433048434,
|
| 55524 |
+
"grad_norm": 0.1990744024515152,
|
| 55525 |
+
"learning_rate": 3.0551342341520325e-05,
|
| 55526 |
+
"loss": 0.8364,
|
| 55527 |
+
"step": 7931
|
| 55528 |
+
},
|
| 55529 |
+
{
|
| 55530 |
+
"epoch": 9.034188034188034,
|
| 55531 |
+
"grad_norm": 0.18487299978733063,
|
| 55532 |
+
"learning_rate": 3.0546799383079074e-05,
|
| 55533 |
+
"loss": 0.7673,
|
| 55534 |
+
"step": 7932
|
| 55535 |
+
},
|
| 55536 |
+
{
|
| 55537 |
+
"epoch": 9.035327635327635,
|
| 55538 |
+
"grad_norm": 0.17298202216625214,
|
| 55539 |
+
"learning_rate": 3.0542256231982226e-05,
|
| 55540 |
+
"loss": 0.8777,
|
| 55541 |
+
"step": 7933
|
| 55542 |
+
},
|
| 55543 |
+
{
|
| 55544 |
+
"epoch": 9.036467236467237,
|
| 55545 |
+
"grad_norm": 0.17005349695682526,
|
| 55546 |
+
"learning_rate": 3.0537712888387586e-05,
|
| 55547 |
+
"loss": 0.7778,
|
| 55548 |
+
"step": 7934
|
| 55549 |
+
},
|
| 55550 |
+
{
|
| 55551 |
+
"epoch": 9.037606837606837,
|
| 55552 |
+
"grad_norm": 0.2257419377565384,
|
| 55553 |
+
"learning_rate": 3.0533169352452947e-05,
|
| 55554 |
+
"loss": 0.6396,
|
| 55555 |
+
"step": 7935
|
| 55556 |
+
},
|
| 55557 |
+
{
|
| 55558 |
+
"epoch": 9.038746438746438,
|
| 55559 |
+
"grad_norm": 0.24718356132507324,
|
| 55560 |
+
"learning_rate": 3.052862562433611e-05,
|
| 55561 |
+
"loss": 0.6649,
|
| 55562 |
+
"step": 7936
|
| 55563 |
+
},
|
| 55564 |
+
{
|
| 55565 |
+
"epoch": 9.03988603988604,
|
| 55566 |
+
"grad_norm": 0.15201455354690552,
|
| 55567 |
+
"learning_rate": 3.052408170419492e-05,
|
| 55568 |
+
"loss": 0.844,
|
| 55569 |
+
"step": 7937
|
| 55570 |
+
},
|
| 55571 |
+
{
|
| 55572 |
+
"epoch": 9.04102564102564,
|
| 55573 |
+
"grad_norm": 0.17157624661922455,
|
| 55574 |
+
"learning_rate": 3.051953759218717e-05,
|
| 55575 |
+
"loss": 0.9226,
|
| 55576 |
+
"step": 7938
|
| 55577 |
+
},
|
| 55578 |
+
{
|
| 55579 |
+
"epoch": 9.042165242165241,
|
| 55580 |
+
"grad_norm": 0.23245535790920258,
|
| 55581 |
+
"learning_rate": 3.05149932884707e-05,
|
| 55582 |
+
"loss": 0.4737,
|
| 55583 |
+
"step": 7939
|
| 55584 |
+
},
|
| 55585 |
+
{
|
| 55586 |
+
"epoch": 9.043304843304844,
|
| 55587 |
+
"grad_norm": 0.2305932641029358,
|
| 55588 |
+
"learning_rate": 3.0510448793203346e-05,
|
| 55589 |
+
"loss": 0.7596,
|
| 55590 |
+
"step": 7940
|
| 55591 |
+
},
|
| 55592 |
+
{
|
| 55593 |
+
"epoch": 9.044444444444444,
|
| 55594 |
+
"grad_norm": 0.20094603300094604,
|
| 55595 |
+
"learning_rate": 3.0505904106542948e-05,
|
| 55596 |
+
"loss": 0.791,
|
| 55597 |
+
"step": 7941
|
| 55598 |
+
},
|
| 55599 |
+
{
|
| 55600 |
+
"epoch": 9.045584045584045,
|
| 55601 |
+
"grad_norm": 0.21628820896148682,
|
| 55602 |
+
"learning_rate": 3.050135922864737e-05,
|
| 55603 |
+
"loss": 0.7386,
|
| 55604 |
+
"step": 7942
|
| 55605 |
+
},
|
| 55606 |
+
{
|
| 55607 |
+
"epoch": 9.046723646723647,
|
| 55608 |
+
"grad_norm": 0.23067307472229004,
|
| 55609 |
+
"learning_rate": 3.0496814159674453e-05,
|
| 55610 |
+
"loss": 0.6767,
|
| 55611 |
+
"step": 7943
|
| 55612 |
+
},
|
| 55613 |
+
{
|
| 55614 |
+
"epoch": 9.047863247863248,
|
| 55615 |
+
"grad_norm": 0.208968386054039,
|
| 55616 |
+
"learning_rate": 3.049226889978206e-05,
|
| 55617 |
+
"loss": 0.723,
|
| 55618 |
+
"step": 7944
|
| 55619 |
+
},
|
| 55620 |
+
{
|
| 55621 |
+
"epoch": 9.049002849002848,
|
| 55622 |
+
"grad_norm": 0.28499385714530945,
|
| 55623 |
+
"learning_rate": 3.048772344912807e-05,
|
| 55624 |
+
"loss": 0.3641,
|
| 55625 |
+
"step": 7945
|
| 55626 |
+
},
|
| 55627 |
+
{
|
| 55628 |
+
"epoch": 9.05014245014245,
|
| 55629 |
+
"grad_norm": 0.1914040595293045,
|
| 55630 |
+
"learning_rate": 3.048317780787035e-05,
|
| 55631 |
+
"loss": 0.7566,
|
| 55632 |
+
"step": 7946
|
| 55633 |
+
},
|
| 55634 |
+
{
|
| 55635 |
+
"epoch": 9.051282051282051,
|
| 55636 |
+
"grad_norm": 0.20092247426509857,
|
| 55637 |
+
"learning_rate": 3.0478631976166787e-05,
|
| 55638 |
+
"loss": 0.7957,
|
| 55639 |
+
"step": 7947
|
| 55640 |
+
},
|
| 55641 |
+
{
|
| 55642 |
+
"epoch": 9.052421652421652,
|
| 55643 |
+
"grad_norm": 0.21474263072013855,
|
| 55644 |
+
"learning_rate": 3.0474085954175262e-05,
|
| 55645 |
+
"loss": 0.5355,
|
| 55646 |
+
"step": 7948
|
| 55647 |
+
},
|
| 55648 |
+
{
|
| 55649 |
+
"epoch": 9.053561253561254,
|
| 55650 |
+
"grad_norm": 0.1841273009777069,
|
| 55651 |
+
"learning_rate": 3.0469539742053686e-05,
|
| 55652 |
+
"loss": 0.6731,
|
| 55653 |
+
"step": 7949
|
| 55654 |
+
},
|
| 55655 |
+
{
|
| 55656 |
+
"epoch": 9.054700854700855,
|
| 55657 |
+
"grad_norm": 0.18076074123382568,
|
| 55658 |
+
"learning_rate": 3.046499333995995e-05,
|
| 55659 |
+
"loss": 0.7469,
|
| 55660 |
+
"step": 7950
|
| 55661 |
+
},
|
| 55662 |
+
{
|
| 55663 |
+
"epoch": 9.055840455840455,
|
| 55664 |
+
"grad_norm": 0.22733916342258453,
|
| 55665 |
+
"learning_rate": 3.0460446748051973e-05,
|
| 55666 |
+
"loss": 0.6836,
|
| 55667 |
+
"step": 7951
|
| 55668 |
+
},
|
| 55669 |
+
{
|
| 55670 |
+
"epoch": 9.056980056980057,
|
| 55671 |
+
"grad_norm": 0.19410863518714905,
|
| 55672 |
+
"learning_rate": 3.045589996648766e-05,
|
| 55673 |
+
"loss": 0.7948,
|
| 55674 |
+
"step": 7952
|
| 55675 |
+
},
|
| 55676 |
+
{
|
| 55677 |
+
"epoch": 9.058119658119658,
|
| 55678 |
+
"grad_norm": 0.22652725875377655,
|
| 55679 |
+
"learning_rate": 3.045135299542494e-05,
|
| 55680 |
+
"loss": 0.625,
|
| 55681 |
+
"step": 7953
|
| 55682 |
+
},
|
| 55683 |
+
{
|
| 55684 |
+
"epoch": 9.059259259259258,
|
| 55685 |
+
"grad_norm": 0.22382645308971405,
|
| 55686 |
+
"learning_rate": 3.0446805835021737e-05,
|
| 55687 |
+
"loss": 0.6675,
|
| 55688 |
+
"step": 7954
|
| 55689 |
+
},
|
| 55690 |
+
{
|
| 55691 |
+
"epoch": 9.06039886039886,
|
| 55692 |
+
"grad_norm": 0.18913283944129944,
|
| 55693 |
+
"learning_rate": 3.044225848543598e-05,
|
| 55694 |
+
"loss": 0.7916,
|
| 55695 |
+
"step": 7955
|
| 55696 |
+
},
|
| 55697 |
+
{
|
| 55698 |
+
"epoch": 9.061538461538461,
|
| 55699 |
+
"grad_norm": 0.20150530338287354,
|
| 55700 |
+
"learning_rate": 3.0437710946825638e-05,
|
| 55701 |
+
"loss": 0.6819,
|
| 55702 |
+
"step": 7956
|
| 55703 |
+
},
|
| 55704 |
+
{
|
| 55705 |
+
"epoch": 9.062678062678062,
|
| 55706 |
+
"grad_norm": 0.1940554976463318,
|
| 55707 |
+
"learning_rate": 3.0433163219348625e-05,
|
| 55708 |
+
"loss": 0.7243,
|
| 55709 |
+
"step": 7957
|
| 55710 |
+
},
|
| 55711 |
+
{
|
| 55712 |
+
"epoch": 9.063817663817664,
|
| 55713 |
+
"grad_norm": 0.24352307617664337,
|
| 55714 |
+
"learning_rate": 3.042861530316292e-05,
|
| 55715 |
+
"loss": 0.6377,
|
| 55716 |
+
"step": 7958
|
| 55717 |
+
},
|
| 55718 |
+
{
|
| 55719 |
+
"epoch": 9.064957264957265,
|
| 55720 |
+
"grad_norm": 0.1836363524198532,
|
| 55721 |
+
"learning_rate": 3.042406719842647e-05,
|
| 55722 |
+
"loss": 0.8672,
|
| 55723 |
+
"step": 7959
|
| 55724 |
+
},
|
| 55725 |
+
{
|
| 55726 |
+
"epoch": 9.066096866096865,
|
| 55727 |
+
"grad_norm": 0.24205131828784943,
|
| 55728 |
+
"learning_rate": 3.0419518905297255e-05,
|
| 55729 |
+
"loss": 0.6717,
|
| 55730 |
+
"step": 7960
|
| 55731 |
+
},
|
| 55732 |
+
{
|
| 55733 |
+
"epoch": 9.067236467236468,
|
| 55734 |
+
"grad_norm": 0.22637714445590973,
|
| 55735 |
+
"learning_rate": 3.041497042393324e-05,
|
| 55736 |
+
"loss": 0.5596,
|
| 55737 |
+
"step": 7961
|
| 55738 |
+
},
|
| 55739 |
+
{
|
| 55740 |
+
"epoch": 9.068376068376068,
|
| 55741 |
+
"grad_norm": 0.1908290535211563,
|
| 55742 |
+
"learning_rate": 3.0410421754492423e-05,
|
| 55743 |
+
"loss": 0.7181,
|
| 55744 |
+
"step": 7962
|
| 55745 |
+
},
|
| 55746 |
+
{
|
| 55747 |
+
"epoch": 9.069515669515669,
|
| 55748 |
+
"grad_norm": 0.1839943528175354,
|
| 55749 |
+
"learning_rate": 3.040587289713277e-05,
|
| 55750 |
+
"loss": 0.8654,
|
| 55751 |
+
"step": 7963
|
| 55752 |
+
},
|
| 55753 |
+
{
|
| 55754 |
+
"epoch": 9.070655270655271,
|
| 55755 |
+
"grad_norm": 0.20175249874591827,
|
| 55756 |
+
"learning_rate": 3.0401323852012287e-05,
|
| 55757 |
+
"loss": 0.7141,
|
| 55758 |
+
"step": 7964
|
| 55759 |
+
},
|
| 55760 |
+
{
|
| 55761 |
+
"epoch": 9.071794871794872,
|
| 55762 |
+
"grad_norm": 0.3334799110889435,
|
| 55763 |
+
"learning_rate": 3.039677461928897e-05,
|
| 55764 |
+
"loss": 0.5159,
|
| 55765 |
+
"step": 7965
|
| 55766 |
+
},
|
| 55767 |
+
{
|
| 55768 |
+
"epoch": 9.072934472934472,
|
| 55769 |
+
"grad_norm": 0.18899498879909515,
|
| 55770 |
+
"learning_rate": 3.0392225199120832e-05,
|
| 55771 |
+
"loss": 0.8762,
|
| 55772 |
+
"step": 7966
|
| 55773 |
+
},
|
| 55774 |
+
{
|
| 55775 |
+
"epoch": 9.074074074074074,
|
| 55776 |
+
"grad_norm": 0.19922029972076416,
|
| 55777 |
+
"learning_rate": 3.0387675591665882e-05,
|
| 55778 |
+
"loss": 0.6303,
|
| 55779 |
+
"step": 7967
|
| 55780 |
+
},
|
| 55781 |
+
{
|
| 55782 |
+
"epoch": 9.075213675213675,
|
| 55783 |
+
"grad_norm": 0.2401798963546753,
|
| 55784 |
+
"learning_rate": 3.0383125797082153e-05,
|
| 55785 |
+
"loss": 0.5326,
|
| 55786 |
+
"step": 7968
|
| 55787 |
+
},
|
| 55788 |
+
{
|
| 55789 |
+
"epoch": 9.076353276353275,
|
| 55790 |
+
"grad_norm": 0.1890830397605896,
|
| 55791 |
+
"learning_rate": 3.0378575815527647e-05,
|
| 55792 |
+
"loss": 0.8489,
|
| 55793 |
+
"step": 7969
|
| 55794 |
+
},
|
| 55795 |
+
{
|
| 55796 |
+
"epoch": 9.077492877492878,
|
| 55797 |
+
"grad_norm": 0.2172982543706894,
|
| 55798 |
+
"learning_rate": 3.0374025647160422e-05,
|
| 55799 |
+
"loss": 0.5955,
|
| 55800 |
+
"step": 7970
|
| 55801 |
+
},
|
| 55802 |
+
{
|
| 55803 |
+
"epoch": 9.078632478632478,
|
| 55804 |
+
"grad_norm": 0.22764314711093903,
|
| 55805 |
+
"learning_rate": 3.0369475292138505e-05,
|
| 55806 |
+
"loss": 0.7766,
|
| 55807 |
+
"step": 7971
|
| 55808 |
+
},
|
| 55809 |
+
{
|
| 55810 |
+
"epoch": 9.079772079772079,
|
| 55811 |
+
"grad_norm": 0.2294934093952179,
|
| 55812 |
+
"learning_rate": 3.0364924750619937e-05,
|
| 55813 |
+
"loss": 0.5676,
|
| 55814 |
+
"step": 7972
|
| 55815 |
+
},
|
| 55816 |
+
{
|
| 55817 |
+
"epoch": 9.080911680911681,
|
| 55818 |
+
"grad_norm": 0.21727004647254944,
|
| 55819 |
+
"learning_rate": 3.0360374022762788e-05,
|
| 55820 |
+
"loss": 0.5687,
|
| 55821 |
+
"step": 7973
|
| 55822 |
+
},
|
| 55823 |
+
{
|
| 55824 |
+
"epoch": 9.082051282051282,
|
| 55825 |
+
"grad_norm": 0.1839292049407959,
|
| 55826 |
+
"learning_rate": 3.0355823108725106e-05,
|
| 55827 |
+
"loss": 0.8086,
|
| 55828 |
+
"step": 7974
|
| 55829 |
+
},
|
| 55830 |
+
{
|
| 55831 |
+
"epoch": 9.083190883190884,
|
| 55832 |
+
"grad_norm": 0.22737336158752441,
|
| 55833 |
+
"learning_rate": 3.035127200866496e-05,
|
| 55834 |
+
"loss": 0.6477,
|
| 55835 |
+
"step": 7975
|
| 55836 |
+
},
|
| 55837 |
+
{
|
| 55838 |
+
"epoch": 9.084330484330485,
|
| 55839 |
+
"grad_norm": 0.2086174488067627,
|
| 55840 |
+
"learning_rate": 3.0346720722740413e-05,
|
| 55841 |
+
"loss": 0.4085,
|
| 55842 |
+
"step": 7976
|
| 55843 |
+
},
|
| 55844 |
+
{
|
| 55845 |
+
"epoch": 9.085470085470085,
|
| 55846 |
+
"grad_norm": 0.1949806660413742,
|
| 55847 |
+
"learning_rate": 3.0342169251109566e-05,
|
| 55848 |
+
"loss": 0.8199,
|
| 55849 |
+
"step": 7977
|
| 55850 |
+
},
|
| 55851 |
+
{
|
| 55852 |
+
"epoch": 9.086609686609687,
|
| 55853 |
+
"grad_norm": 0.1926809549331665,
|
| 55854 |
+
"learning_rate": 3.033761759393048e-05,
|
| 55855 |
+
"loss": 0.8182,
|
| 55856 |
+
"step": 7978
|
| 55857 |
+
},
|
| 55858 |
+
{
|
| 55859 |
+
"epoch": 9.087749287749288,
|
| 55860 |
+
"grad_norm": 0.22032250463962555,
|
| 55861 |
+
"learning_rate": 3.033306575136126e-05,
|
| 55862 |
+
"loss": 0.5923,
|
| 55863 |
+
"step": 7979
|
| 55864 |
+
},
|
| 55865 |
+
{
|
| 55866 |
+
"epoch": 9.088888888888889,
|
| 55867 |
+
"grad_norm": 0.18312066793441772,
|
| 55868 |
+
"learning_rate": 3.0328513723559997e-05,
|
| 55869 |
+
"loss": 0.7698,
|
| 55870 |
+
"step": 7980
|
| 55871 |
+
},
|
| 55872 |
+
{
|
| 55873 |
+
"epoch": 9.090028490028491,
|
| 55874 |
+
"grad_norm": 0.16672851145267487,
|
| 55875 |
+
"learning_rate": 3.0323961510684797e-05,
|
| 55876 |
+
"loss": 0.7758,
|
| 55877 |
+
"step": 7981
|
| 55878 |
+
},
|
| 55879 |
+
{
|
| 55880 |
+
"epoch": 9.091168091168091,
|
| 55881 |
+
"grad_norm": 0.19653446972370148,
|
| 55882 |
+
"learning_rate": 3.0319409112893775e-05,
|
| 55883 |
+
"loss": 0.7214,
|
| 55884 |
+
"step": 7982
|
| 55885 |
+
},
|
| 55886 |
+
{
|
| 55887 |
+
"epoch": 9.092307692307692,
|
| 55888 |
+
"grad_norm": 0.21093419194221497,
|
| 55889 |
+
"learning_rate": 3.0314856530345055e-05,
|
| 55890 |
+
"loss": 0.642,
|
| 55891 |
+
"step": 7983
|
| 55892 |
+
},
|
| 55893 |
+
{
|
| 55894 |
+
"epoch": 9.093447293447294,
|
| 55895 |
+
"grad_norm": 0.16019900143146515,
|
| 55896 |
+
"learning_rate": 3.031030376319674e-05,
|
| 55897 |
+
"loss": 0.9468,
|
| 55898 |
+
"step": 7984
|
| 55899 |
+
},
|
| 55900 |
+
{
|
| 55901 |
+
"epoch": 9.094586894586895,
|
| 55902 |
+
"grad_norm": 0.20375417172908783,
|
| 55903 |
+
"learning_rate": 3.030575081160698e-05,
|
| 55904 |
+
"loss": 0.5477,
|
| 55905 |
+
"step": 7985
|
| 55906 |
+
},
|
| 55907 |
+
{
|
| 55908 |
+
"epoch": 9.095726495726495,
|
| 55909 |
+
"grad_norm": 0.45640164613723755,
|
| 55910 |
+
"learning_rate": 3.03011976757339e-05,
|
| 55911 |
+
"loss": 0.6721,
|
| 55912 |
+
"step": 7986
|
| 55913 |
+
},
|
| 55914 |
+
{
|
| 55915 |
+
"epoch": 9.096866096866098,
|
| 55916 |
+
"grad_norm": 0.19301548600196838,
|
| 55917 |
+
"learning_rate": 3.029664435573564e-05,
|
| 55918 |
+
"loss": 0.9278,
|
| 55919 |
+
"step": 7987
|
| 55920 |
+
},
|
| 55921 |
+
{
|
| 55922 |
+
"epoch": 9.098005698005698,
|
| 55923 |
+
"grad_norm": 0.23720908164978027,
|
| 55924 |
+
"learning_rate": 3.0292090851770365e-05,
|
| 55925 |
+
"loss": 0.6369,
|
| 55926 |
+
"step": 7988
|
| 55927 |
+
},
|
| 55928 |
+
{
|
| 55929 |
+
"epoch": 9.099145299145299,
|
| 55930 |
+
"grad_norm": 0.2241889387369156,
|
| 55931 |
+
"learning_rate": 3.0287537163996223e-05,
|
| 55932 |
+
"loss": 0.691,
|
| 55933 |
+
"step": 7989
|
| 55934 |
+
},
|
| 55935 |
+
{
|
| 55936 |
+
"epoch": 9.100284900284901,
|
| 55937 |
+
"grad_norm": 0.19245818257331848,
|
| 55938 |
+
"learning_rate": 3.028298329257137e-05,
|
| 55939 |
+
"loss": 0.7764,
|
| 55940 |
+
"step": 7990
|
| 55941 |
+
},
|
| 55942 |
+
{
|
| 55943 |
+
"epoch": 9.101424501424502,
|
| 55944 |
+
"grad_norm": 0.238912895321846,
|
| 55945 |
+
"learning_rate": 3.0278429237653976e-05,
|
| 55946 |
+
"loss": 0.6545,
|
| 55947 |
+
"step": 7991
|
| 55948 |
+
},
|
| 55949 |
+
{
|
| 55950 |
+
"epoch": 9.102564102564102,
|
| 55951 |
+
"grad_norm": 0.2048003375530243,
|
| 55952 |
+
"learning_rate": 3.0273874999402218e-05,
|
| 55953 |
+
"loss": 0.7816,
|
| 55954 |
+
"step": 7992
|
| 55955 |
+
},
|
| 55956 |
+
{
|
| 55957 |
+
"epoch": 9.103703703703705,
|
| 55958 |
+
"grad_norm": 0.19136501848697662,
|
| 55959 |
+
"learning_rate": 3.026932057797428e-05,
|
| 55960 |
+
"loss": 0.8156,
|
| 55961 |
+
"step": 7993
|
| 55962 |
+
},
|
| 55963 |
+
{
|
| 55964 |
+
"epoch": 9.104843304843305,
|
| 55965 |
+
"grad_norm": 0.19424991309642792,
|
| 55966 |
+
"learning_rate": 3.0264765973528353e-05,
|
| 55967 |
+
"loss": 0.8568,
|
| 55968 |
+
"step": 7994
|
| 55969 |
+
},
|
| 55970 |
+
{
|
| 55971 |
+
"epoch": 9.105982905982906,
|
| 55972 |
+
"grad_norm": 0.23728442192077637,
|
| 55973 |
+
"learning_rate": 3.026021118622262e-05,
|
| 55974 |
+
"loss": 0.5536,
|
| 55975 |
+
"step": 7995
|
| 55976 |
+
},
|
| 55977 |
+
{
|
| 55978 |
+
"epoch": 9.107122507122508,
|
| 55979 |
+
"grad_norm": 0.2579558491706848,
|
| 55980 |
+
"learning_rate": 3.0255656216215296e-05,
|
| 55981 |
+
"loss": 0.613,
|
| 55982 |
+
"step": 7996
|
| 55983 |
+
},
|
| 55984 |
+
{
|
| 55985 |
+
"epoch": 9.108262108262108,
|
| 55986 |
+
"grad_norm": 0.19430309534072876,
|
| 55987 |
+
"learning_rate": 3.0251101063664567e-05,
|
| 55988 |
+
"loss": 0.8128,
|
| 55989 |
+
"step": 7997
|
| 55990 |
+
},
|
| 55991 |
+
{
|
| 55992 |
+
"epoch": 9.109401709401709,
|
| 55993 |
+
"grad_norm": 0.17508958280086517,
|
| 55994 |
+
"learning_rate": 3.0246545728728657e-05,
|
| 55995 |
+
"loss": 0.9131,
|
| 55996 |
+
"step": 7998
|
| 55997 |
+
},
|
| 55998 |
+
{
|
| 55999 |
+
"epoch": 9.110541310541311,
|
| 56000 |
+
"grad_norm": 0.21832704544067383,
|
| 56001 |
+
"learning_rate": 3.024199021156579e-05,
|
| 56002 |
+
"loss": 0.7154,
|
| 56003 |
+
"step": 7999
|
| 56004 |
+
},
|
| 56005 |
+
{
|
| 56006 |
+
"epoch": 9.111680911680912,
|
| 56007 |
+
"grad_norm": 0.19524739682674408,
|
| 56008 |
+
"learning_rate": 3.0237434512334196e-05,
|
| 56009 |
+
"loss": 0.7135,
|
| 56010 |
+
"step": 8000
|
| 56011 |
+
},
|
| 56012 |
+
{
|
| 56013 |
+
"epoch": 9.112820512820512,
|
| 56014 |
+
"grad_norm": 0.19931471347808838,
|
| 56015 |
+
"learning_rate": 3.0232878631192086e-05,
|
| 56016 |
+
"loss": 0.6977,
|
| 56017 |
+
"step": 8001
|
| 56018 |
+
},
|
| 56019 |
+
{
|
| 56020 |
+
"epoch": 9.113960113960115,
|
| 56021 |
+
"grad_norm": 0.21324680745601654,
|
| 56022 |
+
"learning_rate": 3.0228322568297718e-05,
|
| 56023 |
+
"loss": 0.5053,
|
| 56024 |
+
"step": 8002
|
| 56025 |
+
},
|
| 56026 |
+
{
|
| 56027 |
+
"epoch": 9.115099715099715,
|
| 56028 |
+
"grad_norm": 0.16571569442749023,
|
| 56029 |
+
"learning_rate": 3.0223766323809326e-05,
|
| 56030 |
+
"loss": 0.8375,
|
| 56031 |
+
"step": 8003
|
| 56032 |
+
},
|
| 56033 |
+
{
|
| 56034 |
+
"epoch": 9.116239316239316,
|
| 56035 |
+
"grad_norm": 0.18001367151737213,
|
| 56036 |
+
"learning_rate": 3.0219209897885165e-05,
|
| 56037 |
+
"loss": 0.7627,
|
| 56038 |
+
"step": 8004
|
| 56039 |
+
},
|
| 56040 |
+
{
|
| 56041 |
+
"epoch": 9.117378917378918,
|
| 56042 |
+
"grad_norm": 0.20142637193202972,
|
| 56043 |
+
"learning_rate": 3.021465329068349e-05,
|
| 56044 |
+
"loss": 0.5493,
|
| 56045 |
+
"step": 8005
|
| 56046 |
+
},
|
| 56047 |
+
{
|
| 56048 |
+
"epoch": 9.118518518518519,
|
| 56049 |
+
"grad_norm": 0.19719557464122772,
|
| 56050 |
+
"learning_rate": 3.0210096502362566e-05,
|
| 56051 |
+
"loss": 0.7908,
|
| 56052 |
+
"step": 8006
|
| 56053 |
+
},
|
| 56054 |
+
{
|
| 56055 |
+
"epoch": 9.11965811965812,
|
| 56056 |
+
"grad_norm": 0.24484696984291077,
|
| 56057 |
+
"learning_rate": 3.0205539533080667e-05,
|
| 56058 |
+
"loss": 0.5803,
|
| 56059 |
+
"step": 8007
|
| 56060 |
+
},
|
| 56061 |
+
{
|
| 56062 |
+
"epoch": 9.120797720797722,
|
| 56063 |
+
"grad_norm": 0.25731462240219116,
|
| 56064 |
+
"learning_rate": 3.0200982382996056e-05,
|
| 56065 |
+
"loss": 0.5803,
|
| 56066 |
+
"step": 8008
|
| 56067 |
+
},
|
| 56068 |
+
{
|
| 56069 |
+
"epoch": 9.121937321937322,
|
| 56070 |
+
"grad_norm": 0.2253497987985611,
|
| 56071 |
+
"learning_rate": 3.019642505226703e-05,
|
| 56072 |
+
"loss": 0.5927,
|
| 56073 |
+
"step": 8009
|
| 56074 |
+
},
|
| 56075 |
+
{
|
| 56076 |
+
"epoch": 9.123076923076923,
|
| 56077 |
+
"grad_norm": 0.2693677842617035,
|
| 56078 |
+
"learning_rate": 3.019186754105187e-05,
|
| 56079 |
+
"loss": 0.58,
|
| 56080 |
+
"step": 8010
|
| 56081 |
+
},
|
| 56082 |
+
{
|
| 56083 |
+
"epoch": 9.124216524216525,
|
| 56084 |
+
"grad_norm": 0.21957387030124664,
|
| 56085 |
+
"learning_rate": 3.0187309849508878e-05,
|
| 56086 |
+
"loss": 0.8018,
|
| 56087 |
+
"step": 8011
|
| 56088 |
+
},
|
| 56089 |
+
{
|
| 56090 |
+
"epoch": 9.125356125356126,
|
| 56091 |
+
"grad_norm": 0.2059958577156067,
|
| 56092 |
+
"learning_rate": 3.0182751977796343e-05,
|
| 56093 |
+
"loss": 0.6538,
|
| 56094 |
+
"step": 8012
|
| 56095 |
+
},
|
| 56096 |
+
{
|
| 56097 |
+
"epoch": 9.126495726495726,
|
| 56098 |
+
"grad_norm": 0.21474669873714447,
|
| 56099 |
+
"learning_rate": 3.0178193926072586e-05,
|
| 56100 |
+
"loss": 0.5963,
|
| 56101 |
+
"step": 8013
|
| 56102 |
+
},
|
| 56103 |
+
{
|
| 56104 |
+
"epoch": 9.127635327635328,
|
| 56105 |
+
"grad_norm": 0.24345733225345612,
|
| 56106 |
+
"learning_rate": 3.0173635694495904e-05,
|
| 56107 |
+
"loss": 0.6136,
|
| 56108 |
+
"step": 8014
|
| 56109 |
+
},
|
| 56110 |
+
{
|
| 56111 |
+
"epoch": 9.128774928774929,
|
| 56112 |
+
"grad_norm": 0.24151192605495453,
|
| 56113 |
+
"learning_rate": 3.0169077283224635e-05,
|
| 56114 |
+
"loss": 0.5686,
|
| 56115 |
+
"step": 8015
|
| 56116 |
+
},
|
| 56117 |
+
{
|
| 56118 |
+
"epoch": 9.12991452991453,
|
| 56119 |
+
"grad_norm": 0.1804502010345459,
|
| 56120 |
+
"learning_rate": 3.0164518692417093e-05,
|
| 56121 |
+
"loss": 0.8,
|
| 56122 |
+
"step": 8016
|
| 56123 |
+
},
|
| 56124 |
+
{
|
| 56125 |
+
"epoch": 9.131054131054132,
|
| 56126 |
+
"grad_norm": 0.19830574095249176,
|
| 56127 |
+
"learning_rate": 3.0159959922231618e-05,
|
| 56128 |
+
"loss": 0.7746,
|
| 56129 |
+
"step": 8017
|
| 56130 |
+
},
|
| 56131 |
+
{
|
| 56132 |
+
"epoch": 9.132193732193732,
|
| 56133 |
+
"grad_norm": 0.22743438184261322,
|
| 56134 |
+
"learning_rate": 3.015540097282654e-05,
|
| 56135 |
+
"loss": 0.5336,
|
| 56136 |
+
"step": 8018
|
| 56137 |
+
},
|
| 56138 |
+
{
|
| 56139 |
+
"epoch": 9.133333333333333,
|
| 56140 |
+
"grad_norm": 0.17095860838890076,
|
| 56141 |
+
"learning_rate": 3.015084184436021e-05,
|
| 56142 |
+
"loss": 0.7969,
|
| 56143 |
+
"step": 8019
|
| 56144 |
+
},
|
| 56145 |
+
{
|
| 56146 |
+
"epoch": 9.134472934472935,
|
| 56147 |
+
"grad_norm": 0.1981702744960785,
|
| 56148 |
+
"learning_rate": 3.0146282536990978e-05,
|
| 56149 |
+
"loss": 0.7442,
|
| 56150 |
+
"step": 8020
|
| 56151 |
+
},
|
| 56152 |
+
{
|
| 56153 |
+
"epoch": 9.135612535612536,
|
| 56154 |
+
"grad_norm": 0.22443892061710358,
|
| 56155 |
+
"learning_rate": 3.0141723050877203e-05,
|
| 56156 |
+
"loss": 0.6122,
|
| 56157 |
+
"step": 8021
|
| 56158 |
+
},
|
| 56159 |
+
{
|
| 56160 |
+
"epoch": 9.136752136752136,
|
| 56161 |
+
"grad_norm": 0.26646047830581665,
|
| 56162 |
+
"learning_rate": 3.0137163386177248e-05,
|
| 56163 |
+
"loss": 0.404,
|
| 56164 |
+
"step": 8022
|
| 56165 |
+
},
|
| 56166 |
+
{
|
| 56167 |
+
"epoch": 9.137891737891739,
|
| 56168 |
+
"grad_norm": 0.20456752181053162,
|
| 56169 |
+
"learning_rate": 3.0132603543049477e-05,
|
| 56170 |
+
"loss": 0.6927,
|
| 56171 |
+
"step": 8023
|
| 56172 |
+
},
|
| 56173 |
+
{
|
| 56174 |
+
"epoch": 9.13903133903134,
|
| 56175 |
+
"grad_norm": 0.17897120118141174,
|
| 56176 |
+
"learning_rate": 3.0128043521652276e-05,
|
| 56177 |
+
"loss": 0.8187,
|
| 56178 |
+
"step": 8024
|
| 56179 |
+
},
|
| 56180 |
+
{
|
| 56181 |
+
"epoch": 9.14017094017094,
|
| 56182 |
+
"grad_norm": 0.2257222980260849,
|
| 56183 |
+
"learning_rate": 3.0123483322144015e-05,
|
| 56184 |
+
"loss": 0.5345,
|
| 56185 |
+
"step": 8025
|
| 56186 |
+
},
|
| 56187 |
+
{
|
| 56188 |
+
"epoch": 9.141310541310542,
|
| 56189 |
+
"grad_norm": 0.23555949330329895,
|
| 56190 |
+
"learning_rate": 3.0118922944683094e-05,
|
| 56191 |
+
"loss": 0.5457,
|
| 56192 |
+
"step": 8026
|
| 56193 |
+
},
|
| 56194 |
+
{
|
| 56195 |
+
"epoch": 9.142450142450143,
|
| 56196 |
+
"grad_norm": 0.19824659824371338,
|
| 56197 |
+
"learning_rate": 3.011436238942789e-05,
|
| 56198 |
+
"loss": 0.7135,
|
| 56199 |
+
"step": 8027
|
| 56200 |
+
},
|
| 56201 |
+
{
|
| 56202 |
+
"epoch": 9.143589743589743,
|
| 56203 |
+
"grad_norm": 0.1848185658454895,
|
| 56204 |
+
"learning_rate": 3.0109801656536834e-05,
|
| 56205 |
+
"loss": 0.7755,
|
| 56206 |
+
"step": 8028
|
| 56207 |
+
},
|
| 56208 |
+
{
|
| 56209 |
+
"epoch": 9.144729344729345,
|
| 56210 |
+
"grad_norm": 0.1790562868118286,
|
| 56211 |
+
"learning_rate": 3.01052407461683e-05,
|
| 56212 |
+
"loss": 0.6638,
|
| 56213 |
+
"step": 8029
|
| 56214 |
+
},
|
| 56215 |
+
{
|
| 56216 |
+
"epoch": 9.145868945868946,
|
| 56217 |
+
"grad_norm": 0.22054655849933624,
|
| 56218 |
+
"learning_rate": 3.0100679658480724e-05,
|
| 56219 |
+
"loss": 0.66,
|
| 56220 |
+
"step": 8030
|
| 56221 |
+
},
|
| 56222 |
+
{
|
| 56223 |
+
"epoch": 9.147008547008546,
|
| 56224 |
+
"grad_norm": 0.2575461268424988,
|
| 56225 |
+
"learning_rate": 3.009611839363251e-05,
|
| 56226 |
+
"loss": 0.6992,
|
| 56227 |
+
"step": 8031
|
| 56228 |
+
},
|
| 56229 |
+
{
|
| 56230 |
+
"epoch": 9.148148148148149,
|
| 56231 |
+
"grad_norm": 0.2213752269744873,
|
| 56232 |
+
"learning_rate": 3.0091556951782095e-05,
|
| 56233 |
+
"loss": 0.6647,
|
| 56234 |
+
"step": 8032
|
| 56235 |
+
},
|
| 56236 |
+
{
|
| 56237 |
+
"epoch": 9.14928774928775,
|
| 56238 |
+
"grad_norm": 0.20892935991287231,
|
| 56239 |
+
"learning_rate": 3.008699533308791e-05,
|
| 56240 |
+
"loss": 0.8171,
|
| 56241 |
+
"step": 8033
|
| 56242 |
+
},
|
| 56243 |
+
{
|
| 56244 |
+
"epoch": 9.15042735042735,
|
| 56245 |
+
"grad_norm": 0.19577014446258545,
|
| 56246 |
+
"learning_rate": 3.0082433537708376e-05,
|
| 56247 |
+
"loss": 0.7467,
|
| 56248 |
+
"step": 8034
|
| 56249 |
+
},
|
| 56250 |
+
{
|
| 56251 |
+
"epoch": 9.151566951566952,
|
| 56252 |
+
"grad_norm": 0.1811130791902542,
|
| 56253 |
+
"learning_rate": 3.007787156580196e-05,
|
| 56254 |
+
"loss": 0.9044,
|
| 56255 |
+
"step": 8035
|
| 56256 |
+
},
|
| 56257 |
+
{
|
| 56258 |
+
"epoch": 9.152706552706553,
|
| 56259 |
+
"grad_norm": 0.21809349954128265,
|
| 56260 |
+
"learning_rate": 3.007330941752709e-05,
|
| 56261 |
+
"loss": 0.6055,
|
| 56262 |
+
"step": 8036
|
| 56263 |
+
},
|
| 56264 |
+
{
|
| 56265 |
+
"epoch": 9.153846153846153,
|
| 56266 |
+
"grad_norm": 0.2638418972492218,
|
| 56267 |
+
"learning_rate": 3.0068747093042233e-05,
|
| 56268 |
+
"loss": 0.5942,
|
| 56269 |
+
"step": 8037
|
| 56270 |
+
},
|
| 56271 |
+
{
|
| 56272 |
+
"epoch": 9.154985754985756,
|
| 56273 |
+
"grad_norm": 0.20913495123386383,
|
| 56274 |
+
"learning_rate": 3.006418459250585e-05,
|
| 56275 |
+
"loss": 0.7034,
|
| 56276 |
+
"step": 8038
|
| 56277 |
+
},
|
| 56278 |
+
{
|
| 56279 |
+
"epoch": 9.156125356125356,
|
| 56280 |
+
"grad_norm": 0.2108583003282547,
|
| 56281 |
+
"learning_rate": 3.005962191607642e-05,
|
| 56282 |
+
"loss": 0.7311,
|
| 56283 |
+
"step": 8039
|
| 56284 |
+
},
|
| 56285 |
+
{
|
| 56286 |
+
"epoch": 9.157264957264957,
|
| 56287 |
+
"grad_norm": 0.17478828132152557,
|
| 56288 |
+
"learning_rate": 3.00550590639124e-05,
|
| 56289 |
+
"loss": 0.7496,
|
| 56290 |
+
"step": 8040
|
| 56291 |
+
},
|
| 56292 |
+
{
|
| 56293 |
+
"epoch": 9.158404558404559,
|
| 56294 |
+
"grad_norm": 0.26220399141311646,
|
| 56295 |
+
"learning_rate": 3.0050496036172283e-05,
|
| 56296 |
+
"loss": 0.6376,
|
| 56297 |
+
"step": 8041
|
| 56298 |
+
},
|
| 56299 |
+
{
|
| 56300 |
+
"epoch": 9.15954415954416,
|
| 56301 |
+
"grad_norm": 0.21376913785934448,
|
| 56302 |
+
"learning_rate": 3.0045932833014536e-05,
|
| 56303 |
+
"loss": 0.5264,
|
| 56304 |
+
"step": 8042
|
| 56305 |
+
},
|
| 56306 |
+
{
|
| 56307 |
+
"epoch": 9.16068376068376,
|
| 56308 |
+
"grad_norm": 0.18874740600585938,
|
| 56309 |
+
"learning_rate": 3.0041369454597672e-05,
|
| 56310 |
+
"loss": 0.7482,
|
| 56311 |
+
"step": 8043
|
| 56312 |
+
},
|
| 56313 |
+
{
|
| 56314 |
+
"epoch": 9.161823361823362,
|
| 56315 |
+
"grad_norm": 0.1886608600616455,
|
| 56316 |
+
"learning_rate": 3.0036805901080185e-05,
|
| 56317 |
+
"loss": 0.7498,
|
| 56318 |
+
"step": 8044
|
| 56319 |
+
},
|
| 56320 |
+
{
|
| 56321 |
+
"epoch": 9.162962962962963,
|
| 56322 |
+
"grad_norm": 0.427082359790802,
|
| 56323 |
+
"learning_rate": 3.003224217262058e-05,
|
| 56324 |
+
"loss": 0.8577,
|
| 56325 |
+
"step": 8045
|
| 56326 |
+
},
|
| 56327 |
+
{
|
| 56328 |
+
"epoch": 9.164102564102564,
|
| 56329 |
+
"grad_norm": 0.2096005082130432,
|
| 56330 |
+
"learning_rate": 3.0027678269377362e-05,
|
| 56331 |
+
"loss": 0.7669,
|
| 56332 |
+
"step": 8046
|
| 56333 |
+
},
|
| 56334 |
+
{
|
| 56335 |
+
"epoch": 9.165242165242166,
|
| 56336 |
+
"grad_norm": 0.20323561131954193,
|
| 56337 |
+
"learning_rate": 3.0023114191509056e-05,
|
| 56338 |
+
"loss": 0.5966,
|
| 56339 |
+
"step": 8047
|
| 56340 |
+
},
|
| 56341 |
+
{
|
| 56342 |
+
"epoch": 9.166381766381766,
|
| 56343 |
+
"grad_norm": 0.21189725399017334,
|
| 56344 |
+
"learning_rate": 3.0018549939174172e-05,
|
| 56345 |
+
"loss": 0.7716,
|
| 56346 |
+
"step": 8048
|
| 56347 |
+
},
|
| 56348 |
+
{
|
| 56349 |
+
"epoch": 9.167521367521367,
|
| 56350 |
+
"grad_norm": 0.18440569937229156,
|
| 56351 |
+
"learning_rate": 3.001398551253125e-05,
|
| 56352 |
+
"loss": 0.7185,
|
| 56353 |
+
"step": 8049
|
| 56354 |
+
},
|
| 56355 |
+
{
|
| 56356 |
+
"epoch": 9.16866096866097,
|
| 56357 |
+
"grad_norm": 0.20738254487514496,
|
| 56358 |
+
"learning_rate": 3.0009420911738827e-05,
|
| 56359 |
+
"loss": 0.6946,
|
| 56360 |
+
"step": 8050
|
| 56361 |
+
},
|
| 56362 |
+
{
|
| 56363 |
+
"epoch": 9.16980056980057,
|
| 56364 |
+
"grad_norm": 0.21101903915405273,
|
| 56365 |
+
"learning_rate": 3.000485613695544e-05,
|
| 56366 |
+
"loss": 0.7349,
|
| 56367 |
+
"step": 8051
|
| 56368 |
+
},
|
| 56369 |
+
{
|
| 56370 |
+
"epoch": 9.17094017094017,
|
| 56371 |
+
"grad_norm": 0.2050398886203766,
|
| 56372 |
+
"learning_rate": 3.0000291188339636e-05,
|
| 56373 |
+
"loss": 0.747,
|
| 56374 |
+
"step": 8052
|
| 56375 |
+
},
|
| 56376 |
+
{
|
| 56377 |
+
"epoch": 9.172079772079773,
|
| 56378 |
+
"grad_norm": 0.2424107789993286,
|
| 56379 |
+
"learning_rate": 2.999572606604996e-05,
|
| 56380 |
+
"loss": 0.5924,
|
| 56381 |
+
"step": 8053
|
| 56382 |
+
},
|
| 56383 |
+
{
|
| 56384 |
+
"epoch": 9.173219373219373,
|
| 56385 |
+
"grad_norm": 0.2001570165157318,
|
| 56386 |
+
"learning_rate": 2.9991160770244985e-05,
|
| 56387 |
+
"loss": 0.7611,
|
| 56388 |
+
"step": 8054
|
| 56389 |
+
},
|
| 56390 |
+
{
|
| 56391 |
+
"epoch": 9.174358974358974,
|
| 56392 |
+
"grad_norm": 0.17317825555801392,
|
| 56393 |
+
"learning_rate": 2.9986595301083277e-05,
|
| 56394 |
+
"loss": 0.9028,
|
| 56395 |
+
"step": 8055
|
| 56396 |
+
},
|
| 56397 |
+
{
|
| 56398 |
+
"epoch": 9.175498575498576,
|
| 56399 |
+
"grad_norm": 0.18667954206466675,
|
| 56400 |
+
"learning_rate": 2.9982029658723392e-05,
|
| 56401 |
+
"loss": 0.6992,
|
| 56402 |
+
"step": 8056
|
| 56403 |
+
},
|
| 56404 |
+
{
|
| 56405 |
+
"epoch": 9.176638176638177,
|
| 56406 |
+
"grad_norm": 0.2017718255519867,
|
| 56407 |
+
"learning_rate": 2.9977463843323923e-05,
|
| 56408 |
+
"loss": 0.6735,
|
| 56409 |
+
"step": 8057
|
| 56410 |
+
},
|
| 56411 |
+
{
|
| 56412 |
+
"epoch": 9.177777777777777,
|
| 56413 |
+
"grad_norm": 0.2579292356967926,
|
| 56414 |
+
"learning_rate": 2.997289785504344e-05,
|
| 56415 |
+
"loss": 0.6174,
|
| 56416 |
+
"step": 8058
|
| 56417 |
+
},
|
| 56418 |
+
{
|
| 56419 |
+
"epoch": 9.17891737891738,
|
| 56420 |
+
"grad_norm": 0.20380988717079163,
|
| 56421 |
+
"learning_rate": 2.9968331694040542e-05,
|
| 56422 |
+
"loss": 0.8659,
|
| 56423 |
+
"step": 8059
|
| 56424 |
+
},
|
| 56425 |
+
{
|
| 56426 |
+
"epoch": 9.18005698005698,
|
| 56427 |
+
"grad_norm": 0.206913560628891,
|
| 56428 |
+
"learning_rate": 2.996376536047382e-05,
|
| 56429 |
+
"loss": 0.7524,
|
| 56430 |
+
"step": 8060
|
| 56431 |
+
},
|
| 56432 |
+
{
|
| 56433 |
+
"epoch": 9.18119658119658,
|
| 56434 |
+
"grad_norm": 0.21928489208221436,
|
| 56435 |
+
"learning_rate": 2.995919885450188e-05,
|
| 56436 |
+
"loss": 0.6095,
|
| 56437 |
+
"step": 8061
|
| 56438 |
+
},
|
| 56439 |
+
{
|
| 56440 |
+
"epoch": 9.182336182336183,
|
| 56441 |
+
"grad_norm": 0.18263733386993408,
|
| 56442 |
+
"learning_rate": 2.9954632176283325e-05,
|
| 56443 |
+
"loss": 0.833,
|
| 56444 |
+
"step": 8062
|
| 56445 |
+
},
|
| 56446 |
+
{
|
| 56447 |
+
"epoch": 9.183475783475783,
|
| 56448 |
+
"grad_norm": 0.18622763454914093,
|
| 56449 |
+
"learning_rate": 2.9950065325976768e-05,
|
| 56450 |
+
"loss": 0.8737,
|
| 56451 |
+
"step": 8063
|
| 56452 |
+
},
|
| 56453 |
+
{
|
| 56454 |
+
"epoch": 9.184615384615384,
|
| 56455 |
+
"grad_norm": 0.2090657502412796,
|
| 56456 |
+
"learning_rate": 2.9945498303740825e-05,
|
| 56457 |
+
"loss": 0.5765,
|
| 56458 |
+
"step": 8064
|
| 56459 |
+
},
|
| 56460 |
+
{
|
| 56461 |
+
"epoch": 9.185754985754986,
|
| 56462 |
+
"grad_norm": 0.19382807612419128,
|
| 56463 |
+
"learning_rate": 2.9940931109734133e-05,
|
| 56464 |
+
"loss": 0.7357,
|
| 56465 |
+
"step": 8065
|
| 56466 |
+
},
|
| 56467 |
+
{
|
| 56468 |
+
"epoch": 9.186894586894587,
|
| 56469 |
+
"grad_norm": 0.21184006333351135,
|
| 56470 |
+
"learning_rate": 2.9936363744115316e-05,
|
| 56471 |
+
"loss": 0.6146,
|
| 56472 |
+
"step": 8066
|
| 56473 |
+
},
|
| 56474 |
+
{
|
| 56475 |
+
"epoch": 9.188034188034187,
|
| 56476 |
+
"grad_norm": 0.18455208837985992,
|
| 56477 |
+
"learning_rate": 2.9931796207043007e-05,
|
| 56478 |
+
"loss": 0.7379,
|
| 56479 |
+
"step": 8067
|
| 56480 |
+
},
|
| 56481 |
+
{
|
| 56482 |
+
"epoch": 9.18917378917379,
|
| 56483 |
+
"grad_norm": 0.1959788054227829,
|
| 56484 |
+
"learning_rate": 2.9927228498675852e-05,
|
| 56485 |
+
"loss": 0.8937,
|
| 56486 |
+
"step": 8068
|
| 56487 |
+
},
|
| 56488 |
+
{
|
| 56489 |
+
"epoch": 9.19031339031339,
|
| 56490 |
+
"grad_norm": 0.26601675152778625,
|
| 56491 |
+
"learning_rate": 2.992266061917251e-05,
|
| 56492 |
+
"loss": 0.6287,
|
| 56493 |
+
"step": 8069
|
| 56494 |
+
},
|
| 56495 |
+
{
|
| 56496 |
+
"epoch": 9.19145299145299,
|
| 56497 |
+
"grad_norm": 0.2321777194738388,
|
| 56498 |
+
"learning_rate": 2.9918092568691614e-05,
|
| 56499 |
+
"loss": 0.5539,
|
| 56500 |
+
"step": 8070
|
| 56501 |
+
},
|
| 56502 |
+
{
|
| 56503 |
+
"epoch": 9.192592592592593,
|
| 56504 |
+
"grad_norm": 0.1900903284549713,
|
| 56505 |
+
"learning_rate": 2.9913524347391847e-05,
|
| 56506 |
+
"loss": 0.7664,
|
| 56507 |
+
"step": 8071
|
| 56508 |
+
},
|
| 56509 |
+
{
|
| 56510 |
+
"epoch": 9.193732193732194,
|
| 56511 |
+
"grad_norm": 0.17832405865192413,
|
| 56512 |
+
"learning_rate": 2.9908955955431868e-05,
|
| 56513 |
+
"loss": 0.7927,
|
| 56514 |
+
"step": 8072
|
| 56515 |
+
},
|
| 56516 |
+
{
|
| 56517 |
+
"epoch": 9.194871794871794,
|
| 56518 |
+
"grad_norm": 0.2156316190958023,
|
| 56519 |
+
"learning_rate": 2.9904387392970347e-05,
|
| 56520 |
+
"loss": 0.5693,
|
| 56521 |
+
"step": 8073
|
| 56522 |
+
},
|
| 56523 |
+
{
|
| 56524 |
+
"epoch": 9.196011396011396,
|
| 56525 |
+
"grad_norm": 0.21304167807102203,
|
| 56526 |
+
"learning_rate": 2.9899818660165963e-05,
|
| 56527 |
+
"loss": 0.6855,
|
| 56528 |
+
"step": 8074
|
| 56529 |
+
},
|
| 56530 |
+
{
|
| 56531 |
+
"epoch": 9.197150997150997,
|
| 56532 |
+
"grad_norm": 0.1971638798713684,
|
| 56533 |
+
"learning_rate": 2.98952497571774e-05,
|
| 56534 |
+
"loss": 0.9238,
|
| 56535 |
+
"step": 8075
|
| 56536 |
+
},
|
| 56537 |
+
{
|
| 56538 |
+
"epoch": 9.198290598290598,
|
| 56539 |
+
"grad_norm": 0.227126345038414,
|
| 56540 |
+
"learning_rate": 2.9890680684163352e-05,
|
| 56541 |
+
"loss": 0.8005,
|
| 56542 |
+
"step": 8076
|
| 56543 |
+
},
|
| 56544 |
+
{
|
| 56545 |
+
"epoch": 9.1994301994302,
|
| 56546 |
+
"grad_norm": 0.14012542366981506,
|
| 56547 |
+
"learning_rate": 2.9886111441282527e-05,
|
| 56548 |
+
"loss": 0.8824,
|
| 56549 |
+
"step": 8077
|
| 56550 |
+
},
|
| 56551 |
+
{
|
| 56552 |
+
"epoch": 9.2005698005698,
|
| 56553 |
+
"grad_norm": 0.20587700605392456,
|
| 56554 |
+
"learning_rate": 2.98815420286936e-05,
|
| 56555 |
+
"loss": 0.6945,
|
| 56556 |
+
"step": 8078
|
| 56557 |
+
},
|
| 56558 |
+
{
|
| 56559 |
+
"epoch": 9.201709401709401,
|
| 56560 |
+
"grad_norm": 0.23867155611515045,
|
| 56561 |
+
"learning_rate": 2.98769724465553e-05,
|
| 56562 |
+
"loss": 0.6181,
|
| 56563 |
+
"step": 8079
|
| 56564 |
+
},
|
| 56565 |
+
{
|
| 56566 |
+
"epoch": 9.202849002849003,
|
| 56567 |
+
"grad_norm": 0.17290520668029785,
|
| 56568 |
+
"learning_rate": 2.9872402695026337e-05,
|
| 56569 |
+
"loss": 0.7346,
|
| 56570 |
+
"step": 8080
|
| 56571 |
+
},
|
| 56572 |
+
{
|
| 56573 |
+
"epoch": 9.203988603988604,
|
| 56574 |
+
"grad_norm": 0.24878010153770447,
|
| 56575 |
+
"learning_rate": 2.9867832774265424e-05,
|
| 56576 |
+
"loss": 0.5777,
|
| 56577 |
+
"step": 8081
|
| 56578 |
+
},
|
| 56579 |
+
{
|
| 56580 |
+
"epoch": 9.205128205128204,
|
| 56581 |
+
"grad_norm": 0.2160666584968567,
|
| 56582 |
+
"learning_rate": 2.9863262684431297e-05,
|
| 56583 |
+
"loss": 0.6324,
|
| 56584 |
+
"step": 8082
|
| 56585 |
+
},
|
| 56586 |
+
{
|
| 56587 |
+
"epoch": 9.206267806267807,
|
| 56588 |
+
"grad_norm": 0.19905027747154236,
|
| 56589 |
+
"learning_rate": 2.9858692425682676e-05,
|
| 56590 |
+
"loss": 0.8479,
|
| 56591 |
+
"step": 8083
|
| 56592 |
+
},
|
| 56593 |
+
{
|
| 56594 |
+
"epoch": 9.207407407407407,
|
| 56595 |
+
"grad_norm": 0.2422788441181183,
|
| 56596 |
+
"learning_rate": 2.985412199817832e-05,
|
| 56597 |
+
"loss": 0.7472,
|
| 56598 |
+
"step": 8084
|
| 56599 |
+
},
|
| 56600 |
+
{
|
| 56601 |
+
"epoch": 9.208547008547008,
|
| 56602 |
+
"grad_norm": 0.21977217495441437,
|
| 56603 |
+
"learning_rate": 2.984955140207694e-05,
|
| 56604 |
+
"loss": 0.7277,
|
| 56605 |
+
"step": 8085
|
| 56606 |
+
},
|
| 56607 |
+
{
|
| 56608 |
+
"epoch": 9.20968660968661,
|
| 56609 |
+
"grad_norm": 0.23536036908626556,
|
| 56610 |
+
"learning_rate": 2.9844980637537313e-05,
|
| 56611 |
+
"loss": 0.5627,
|
| 56612 |
+
"step": 8086
|
| 56613 |
+
},
|
| 56614 |
+
{
|
| 56615 |
+
"epoch": 9.21082621082621,
|
| 56616 |
+
"grad_norm": 0.26169732213020325,
|
| 56617 |
+
"learning_rate": 2.984040970471818e-05,
|
| 56618 |
+
"loss": 0.6232,
|
| 56619 |
+
"step": 8087
|
| 56620 |
+
},
|
| 56621 |
+
{
|
| 56622 |
+
"epoch": 9.211965811965811,
|
| 56623 |
+
"grad_norm": 0.21738310158252716,
|
| 56624 |
+
"learning_rate": 2.9835838603778316e-05,
|
| 56625 |
+
"loss": 0.6676,
|
| 56626 |
+
"step": 8088
|
| 56627 |
+
},
|
| 56628 |
+
{
|
| 56629 |
+
"epoch": 9.213105413105414,
|
| 56630 |
+
"grad_norm": 0.2095075398683548,
|
| 56631 |
+
"learning_rate": 2.9831267334876468e-05,
|
| 56632 |
+
"loss": 0.6409,
|
| 56633 |
+
"step": 8089
|
| 56634 |
+
},
|
| 56635 |
+
{
|
| 56636 |
+
"epoch": 9.214245014245014,
|
| 56637 |
+
"grad_norm": 0.22634997963905334,
|
| 56638 |
+
"learning_rate": 2.982669589817143e-05,
|
| 56639 |
+
"loss": 0.5905,
|
| 56640 |
+
"step": 8090
|
| 56641 |
+
},
|
| 56642 |
+
{
|
| 56643 |
+
"epoch": 9.215384615384615,
|
| 56644 |
+
"grad_norm": 0.21932442486286163,
|
| 56645 |
+
"learning_rate": 2.9822124293821963e-05,
|
| 56646 |
+
"loss": 0.8036,
|
| 56647 |
+
"step": 8091
|
| 56648 |
+
},
|
| 56649 |
+
{
|
| 56650 |
+
"epoch": 9.216524216524217,
|
| 56651 |
+
"grad_norm": 0.20687827467918396,
|
| 56652 |
+
"learning_rate": 2.981755252198686e-05,
|
| 56653 |
+
"loss": 0.7543,
|
| 56654 |
+
"step": 8092
|
| 56655 |
+
},
|
| 56656 |
+
{
|
| 56657 |
+
"epoch": 9.217663817663817,
|
| 56658 |
+
"grad_norm": 0.23628811538219452,
|
| 56659 |
+
"learning_rate": 2.9812980582824912e-05,
|
| 56660 |
+
"loss": 0.6928,
|
| 56661 |
+
"step": 8093
|
| 56662 |
+
},
|
| 56663 |
+
{
|
| 56664 |
+
"epoch": 9.218803418803418,
|
| 56665 |
+
"grad_norm": 0.21168608963489532,
|
| 56666 |
+
"learning_rate": 2.9808408476494908e-05,
|
| 56667 |
+
"loss": 0.5425,
|
| 56668 |
+
"step": 8094
|
| 56669 |
+
},
|
| 56670 |
+
{
|
| 56671 |
+
"epoch": 9.21994301994302,
|
| 56672 |
+
"grad_norm": 0.23283641040325165,
|
| 56673 |
+
"learning_rate": 2.980383620315566e-05,
|
| 56674 |
+
"loss": 0.7824,
|
| 56675 |
+
"step": 8095
|
| 56676 |
+
},
|
| 56677 |
+
{
|
| 56678 |
+
"epoch": 9.221082621082621,
|
| 56679 |
+
"grad_norm": 0.2229052186012268,
|
| 56680 |
+
"learning_rate": 2.979926376296596e-05,
|
| 56681 |
+
"loss": 0.5829,
|
| 56682 |
+
"step": 8096
|
| 56683 |
+
},
|
| 56684 |
+
{
|
| 56685 |
+
"epoch": 9.222222222222221,
|
| 56686 |
+
"grad_norm": 0.16488371789455414,
|
| 56687 |
+
"learning_rate": 2.9794691156084638e-05,
|
| 56688 |
+
"loss": 0.9006,
|
| 56689 |
+
"step": 8097
|
| 56690 |
+
},
|
| 56691 |
+
{
|
| 56692 |
+
"epoch": 9.223361823361824,
|
| 56693 |
+
"grad_norm": 0.18390604853630066,
|
| 56694 |
+
"learning_rate": 2.9790118382670506e-05,
|
| 56695 |
+
"loss": 0.7466,
|
| 56696 |
+
"step": 8098
|
| 56697 |
+
},
|
| 56698 |
+
{
|
| 56699 |
+
"epoch": 9.224501424501424,
|
| 56700 |
+
"grad_norm": 0.20317108929157257,
|
| 56701 |
+
"learning_rate": 2.9785545442882396e-05,
|
| 56702 |
+
"loss": 0.9282,
|
| 56703 |
+
"step": 8099
|
| 56704 |
+
},
|
| 56705 |
+
{
|
| 56706 |
+
"epoch": 9.225641025641025,
|
| 56707 |
+
"grad_norm": 0.18961268663406372,
|
| 56708 |
+
"learning_rate": 2.978097233687912e-05,
|
| 56709 |
+
"loss": 0.8216,
|
| 56710 |
+
"step": 8100
|
| 56711 |
}
|
| 56712 |
],
|
| 56713 |
"logging_steps": 1,
|
|
|
|
| 56727 |
"attributes": {}
|
| 56728 |
}
|
| 56729 |
},
|
| 56730 |
+
"total_flos": 4.5289195694385316e+19,
|
| 56731 |
"train_batch_size": 8,
|
| 56732 |
"trial_name": null,
|
| 56733 |
"trial_params": null
|