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 5400, 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 sha256:0405e84ca95a007c2040ee3ee91c0403c5682fbca6d9792361596203fcfe39ed
|
| 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:d71610cf31d78e6182b8ab792761023ffc9a8307ffe062e7cda85d3d81e9e19e
|
| 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:f196323d7423b60f8e4ceb7dbf8715ee326c0d068e5ff164f13c63b279b9f1a0
|
| 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 sha256:6f48ee6d24c27ae278f723874815af2e0311a1b93573ce6104ccbb9cb1d67569
|
| 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,
|
|
@@ -35708,6 +35708,2106 @@
|
|
| 35708 |
"learning_rate": 4.206886155468316e-05,
|
| 35709 |
"loss": 0.639,
|
| 35710 |
"step": 5100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35711 |
}
|
| 35712 |
],
|
| 35713 |
"logging_steps": 1,
|
|
@@ -35727,7 +37827,7 @@
|
|
| 35727 |
"attributes": {}
|
| 35728 |
}
|
| 35729 |
},
|
| 35730 |
-
"total_flos":
|
| 35731 |
"train_batch_size": 8,
|
| 35732 |
"trial_name": null,
|
| 35733 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.150427350427351,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 35708 |
"learning_rate": 4.206886155468316e-05,
|
| 35709 |
"loss": 0.639,
|
| 35710 |
"step": 5100
|
| 35711 |
+
},
|
| 35712 |
+
{
|
| 35713 |
+
"epoch": 5.81025641025641,
|
| 35714 |
+
"grad_norm": 0.17586733400821686,
|
| 35715 |
+
"learning_rate": 4.2065457037398905e-05,
|
| 35716 |
+
"loss": 0.968,
|
| 35717 |
+
"step": 5101
|
| 35718 |
+
},
|
| 35719 |
+
{
|
| 35720 |
+
"epoch": 5.8113960113960115,
|
| 35721 |
+
"grad_norm": 0.20486289262771606,
|
| 35722 |
+
"learning_rate": 4.206205192738441e-05,
|
| 35723 |
+
"loss": 0.639,
|
| 35724 |
+
"step": 5102
|
| 35725 |
+
},
|
| 35726 |
+
{
|
| 35727 |
+
"epoch": 5.812535612535613,
|
| 35728 |
+
"grad_norm": 0.1609588861465454,
|
| 35729 |
+
"learning_rate": 4.205864622475791e-05,
|
| 35730 |
+
"loss": 0.9063,
|
| 35731 |
+
"step": 5103
|
| 35732 |
+
},
|
| 35733 |
+
{
|
| 35734 |
+
"epoch": 5.8136752136752134,
|
| 35735 |
+
"grad_norm": 0.17861494421958923,
|
| 35736 |
+
"learning_rate": 4.205523992963773e-05,
|
| 35737 |
+
"loss": 0.7507,
|
| 35738 |
+
"step": 5104
|
| 35739 |
+
},
|
| 35740 |
+
{
|
| 35741 |
+
"epoch": 5.814814814814815,
|
| 35742 |
+
"grad_norm": 0.1902887225151062,
|
| 35743 |
+
"learning_rate": 4.2051833042142166e-05,
|
| 35744 |
+
"loss": 0.8143,
|
| 35745 |
+
"step": 5105
|
| 35746 |
+
},
|
| 35747 |
+
{
|
| 35748 |
+
"epoch": 5.815954415954416,
|
| 35749 |
+
"grad_norm": 0.19511087238788605,
|
| 35750 |
+
"learning_rate": 4.204842556238954e-05,
|
| 35751 |
+
"loss": 0.636,
|
| 35752 |
+
"step": 5106
|
| 35753 |
+
},
|
| 35754 |
+
{
|
| 35755 |
+
"epoch": 5.817094017094017,
|
| 35756 |
+
"grad_norm": 0.1550368368625641,
|
| 35757 |
+
"learning_rate": 4.2045017490498214e-05,
|
| 35758 |
+
"loss": 0.823,
|
| 35759 |
+
"step": 5107
|
| 35760 |
+
},
|
| 35761 |
+
{
|
| 35762 |
+
"epoch": 5.818233618233618,
|
| 35763 |
+
"grad_norm": 0.16333742439746857,
|
| 35764 |
+
"learning_rate": 4.2041608826586564e-05,
|
| 35765 |
+
"loss": 0.8188,
|
| 35766 |
+
"step": 5108
|
| 35767 |
+
},
|
| 35768 |
+
{
|
| 35769 |
+
"epoch": 5.81937321937322,
|
| 35770 |
+
"grad_norm": 0.1677020639181137,
|
| 35771 |
+
"learning_rate": 4.2038199570772966e-05,
|
| 35772 |
+
"loss": 0.6652,
|
| 35773 |
+
"step": 5109
|
| 35774 |
+
},
|
| 35775 |
+
{
|
| 35776 |
+
"epoch": 5.82051282051282,
|
| 35777 |
+
"grad_norm": 0.20748074352741241,
|
| 35778 |
+
"learning_rate": 4.2034789723175835e-05,
|
| 35779 |
+
"loss": 0.6676,
|
| 35780 |
+
"step": 5110
|
| 35781 |
+
},
|
| 35782 |
+
{
|
| 35783 |
+
"epoch": 5.821652421652422,
|
| 35784 |
+
"grad_norm": 0.1845245361328125,
|
| 35785 |
+
"learning_rate": 4.203137928391363e-05,
|
| 35786 |
+
"loss": 0.672,
|
| 35787 |
+
"step": 5111
|
| 35788 |
+
},
|
| 35789 |
+
{
|
| 35790 |
+
"epoch": 5.822792022792023,
|
| 35791 |
+
"grad_norm": 0.2240746170282364,
|
| 35792 |
+
"learning_rate": 4.202796825310478e-05,
|
| 35793 |
+
"loss": 0.7392,
|
| 35794 |
+
"step": 5112
|
| 35795 |
+
},
|
| 35796 |
+
{
|
| 35797 |
+
"epoch": 5.823931623931624,
|
| 35798 |
+
"grad_norm": 0.1537604182958603,
|
| 35799 |
+
"learning_rate": 4.202455663086776e-05,
|
| 35800 |
+
"loss": 0.9385,
|
| 35801 |
+
"step": 5113
|
| 35802 |
+
},
|
| 35803 |
+
{
|
| 35804 |
+
"epoch": 5.825071225071225,
|
| 35805 |
+
"grad_norm": 0.2583048343658447,
|
| 35806 |
+
"learning_rate": 4.202114441732107e-05,
|
| 35807 |
+
"loss": 0.4114,
|
| 35808 |
+
"step": 5114
|
| 35809 |
+
},
|
| 35810 |
+
{
|
| 35811 |
+
"epoch": 5.8262108262108265,
|
| 35812 |
+
"grad_norm": 0.15980015695095062,
|
| 35813 |
+
"learning_rate": 4.201773161258323e-05,
|
| 35814 |
+
"loss": 0.8168,
|
| 35815 |
+
"step": 5115
|
| 35816 |
+
},
|
| 35817 |
+
{
|
| 35818 |
+
"epoch": 5.827350427350427,
|
| 35819 |
+
"grad_norm": 0.15042923390865326,
|
| 35820 |
+
"learning_rate": 4.201431821677277e-05,
|
| 35821 |
+
"loss": 0.7829,
|
| 35822 |
+
"step": 5116
|
| 35823 |
+
},
|
| 35824 |
+
{
|
| 35825 |
+
"epoch": 5.8284900284900285,
|
| 35826 |
+
"grad_norm": 0.19120368361473083,
|
| 35827 |
+
"learning_rate": 4.201090423000825e-05,
|
| 35828 |
+
"loss": 0.6365,
|
| 35829 |
+
"step": 5117
|
| 35830 |
+
},
|
| 35831 |
+
{
|
| 35832 |
+
"epoch": 5.82962962962963,
|
| 35833 |
+
"grad_norm": 0.17045742273330688,
|
| 35834 |
+
"learning_rate": 4.2007489652408246e-05,
|
| 35835 |
+
"loss": 0.7093,
|
| 35836 |
+
"step": 5118
|
| 35837 |
+
},
|
| 35838 |
+
{
|
| 35839 |
+
"epoch": 5.8307692307692305,
|
| 35840 |
+
"grad_norm": 0.18401744961738586,
|
| 35841 |
+
"learning_rate": 4.200407448409135e-05,
|
| 35842 |
+
"loss": 0.7326,
|
| 35843 |
+
"step": 5119
|
| 35844 |
+
},
|
| 35845 |
+
{
|
| 35846 |
+
"epoch": 5.831908831908832,
|
| 35847 |
+
"grad_norm": 0.15033607184886932,
|
| 35848 |
+
"learning_rate": 4.200065872517619e-05,
|
| 35849 |
+
"loss": 0.8376,
|
| 35850 |
+
"step": 5120
|
| 35851 |
+
},
|
| 35852 |
+
{
|
| 35853 |
+
"epoch": 5.833048433048433,
|
| 35854 |
+
"grad_norm": 0.15364952385425568,
|
| 35855 |
+
"learning_rate": 4.1997242375781396e-05,
|
| 35856 |
+
"loss": 0.8633,
|
| 35857 |
+
"step": 5121
|
| 35858 |
+
},
|
| 35859 |
+
{
|
| 35860 |
+
"epoch": 5.834188034188034,
|
| 35861 |
+
"grad_norm": 0.21868816018104553,
|
| 35862 |
+
"learning_rate": 4.1993825436025645e-05,
|
| 35863 |
+
"loss": 0.6797,
|
| 35864 |
+
"step": 5122
|
| 35865 |
+
},
|
| 35866 |
+
{
|
| 35867 |
+
"epoch": 5.835327635327635,
|
| 35868 |
+
"grad_norm": 0.15554660558700562,
|
| 35869 |
+
"learning_rate": 4.1990407906027595e-05,
|
| 35870 |
+
"loss": 0.8344,
|
| 35871 |
+
"step": 5123
|
| 35872 |
+
},
|
| 35873 |
+
{
|
| 35874 |
+
"epoch": 5.836467236467237,
|
| 35875 |
+
"grad_norm": 0.16153044998645782,
|
| 35876 |
+
"learning_rate": 4.1986989785905954e-05,
|
| 35877 |
+
"loss": 1.0173,
|
| 35878 |
+
"step": 5124
|
| 35879 |
+
},
|
| 35880 |
+
{
|
| 35881 |
+
"epoch": 5.837606837606837,
|
| 35882 |
+
"grad_norm": 0.18046070635318756,
|
| 35883 |
+
"learning_rate": 4.1983571075779447e-05,
|
| 35884 |
+
"loss": 0.7211,
|
| 35885 |
+
"step": 5125
|
| 35886 |
+
},
|
| 35887 |
+
{
|
| 35888 |
+
"epoch": 5.838746438746439,
|
| 35889 |
+
"grad_norm": 0.15778635442256927,
|
| 35890 |
+
"learning_rate": 4.198015177576681e-05,
|
| 35891 |
+
"loss": 0.825,
|
| 35892 |
+
"step": 5126
|
| 35893 |
+
},
|
| 35894 |
+
{
|
| 35895 |
+
"epoch": 5.83988603988604,
|
| 35896 |
+
"grad_norm": 0.18100708723068237,
|
| 35897 |
+
"learning_rate": 4.19767318859868e-05,
|
| 35898 |
+
"loss": 0.7342,
|
| 35899 |
+
"step": 5127
|
| 35900 |
+
},
|
| 35901 |
+
{
|
| 35902 |
+
"epoch": 5.841025641025641,
|
| 35903 |
+
"grad_norm": 0.2530038058757782,
|
| 35904 |
+
"learning_rate": 4.1973311406558214e-05,
|
| 35905 |
+
"loss": 0.7057,
|
| 35906 |
+
"step": 5128
|
| 35907 |
+
},
|
| 35908 |
+
{
|
| 35909 |
+
"epoch": 5.842165242165242,
|
| 35910 |
+
"grad_norm": 0.1759106069803238,
|
| 35911 |
+
"learning_rate": 4.196989033759984e-05,
|
| 35912 |
+
"loss": 0.7695,
|
| 35913 |
+
"step": 5129
|
| 35914 |
+
},
|
| 35915 |
+
{
|
| 35916 |
+
"epoch": 5.843304843304844,
|
| 35917 |
+
"grad_norm": 0.1924852430820465,
|
| 35918 |
+
"learning_rate": 4.196646867923051e-05,
|
| 35919 |
+
"loss": 0.6453,
|
| 35920 |
+
"step": 5130
|
| 35921 |
+
},
|
| 35922 |
+
{
|
| 35923 |
+
"epoch": 5.844444444444444,
|
| 35924 |
+
"grad_norm": 0.18492716550827026,
|
| 35925 |
+
"learning_rate": 4.1963046431569064e-05,
|
| 35926 |
+
"loss": 0.6236,
|
| 35927 |
+
"step": 5131
|
| 35928 |
+
},
|
| 35929 |
+
{
|
| 35930 |
+
"epoch": 5.8455840455840455,
|
| 35931 |
+
"grad_norm": 0.18507033586502075,
|
| 35932 |
+
"learning_rate": 4.1959623594734365e-05,
|
| 35933 |
+
"loss": 0.6366,
|
| 35934 |
+
"step": 5132
|
| 35935 |
+
},
|
| 35936 |
+
{
|
| 35937 |
+
"epoch": 5.846723646723647,
|
| 35938 |
+
"grad_norm": 0.17751383781433105,
|
| 35939 |
+
"learning_rate": 4.195620016884531e-05,
|
| 35940 |
+
"loss": 0.8312,
|
| 35941 |
+
"step": 5133
|
| 35942 |
+
},
|
| 35943 |
+
{
|
| 35944 |
+
"epoch": 5.8478632478632475,
|
| 35945 |
+
"grad_norm": 0.1232931986451149,
|
| 35946 |
+
"learning_rate": 4.195277615402078e-05,
|
| 35947 |
+
"loss": 0.9088,
|
| 35948 |
+
"step": 5134
|
| 35949 |
+
},
|
| 35950 |
+
{
|
| 35951 |
+
"epoch": 5.849002849002849,
|
| 35952 |
+
"grad_norm": 0.15958844125270844,
|
| 35953 |
+
"learning_rate": 4.194935155037972e-05,
|
| 35954 |
+
"loss": 0.8025,
|
| 35955 |
+
"step": 5135
|
| 35956 |
+
},
|
| 35957 |
+
{
|
| 35958 |
+
"epoch": 5.85014245014245,
|
| 35959 |
+
"grad_norm": 0.16987775266170502,
|
| 35960 |
+
"learning_rate": 4.194592635804106e-05,
|
| 35961 |
+
"loss": 0.914,
|
| 35962 |
+
"step": 5136
|
| 35963 |
+
},
|
| 35964 |
+
{
|
| 35965 |
+
"epoch": 5.851282051282051,
|
| 35966 |
+
"grad_norm": 0.20572727918624878,
|
| 35967 |
+
"learning_rate": 4.194250057712379e-05,
|
| 35968 |
+
"loss": 0.6833,
|
| 35969 |
+
"step": 5137
|
| 35970 |
+
},
|
| 35971 |
+
{
|
| 35972 |
+
"epoch": 5.852421652421652,
|
| 35973 |
+
"grad_norm": 0.1674432009458542,
|
| 35974 |
+
"learning_rate": 4.1939074207746874e-05,
|
| 35975 |
+
"loss": 0.9532,
|
| 35976 |
+
"step": 5138
|
| 35977 |
+
},
|
| 35978 |
+
{
|
| 35979 |
+
"epoch": 5.853561253561254,
|
| 35980 |
+
"grad_norm": 0.17399823665618896,
|
| 35981 |
+
"learning_rate": 4.1935647250029334e-05,
|
| 35982 |
+
"loss": 0.7167,
|
| 35983 |
+
"step": 5139
|
| 35984 |
+
},
|
| 35985 |
+
{
|
| 35986 |
+
"epoch": 5.854700854700854,
|
| 35987 |
+
"grad_norm": 0.19129186868667603,
|
| 35988 |
+
"learning_rate": 4.193221970409019e-05,
|
| 35989 |
+
"loss": 0.8143,
|
| 35990 |
+
"step": 5140
|
| 35991 |
+
},
|
| 35992 |
+
{
|
| 35993 |
+
"epoch": 5.855840455840456,
|
| 35994 |
+
"grad_norm": 0.18846487998962402,
|
| 35995 |
+
"learning_rate": 4.19287915700485e-05,
|
| 35996 |
+
"loss": 0.7287,
|
| 35997 |
+
"step": 5141
|
| 35998 |
+
},
|
| 35999 |
+
{
|
| 36000 |
+
"epoch": 5.856980056980057,
|
| 36001 |
+
"grad_norm": 0.167376309633255,
|
| 36002 |
+
"learning_rate": 4.192536284802331e-05,
|
| 36003 |
+
"loss": 0.8228,
|
| 36004 |
+
"step": 5142
|
| 36005 |
+
},
|
| 36006 |
+
{
|
| 36007 |
+
"epoch": 5.858119658119658,
|
| 36008 |
+
"grad_norm": 0.1933199018239975,
|
| 36009 |
+
"learning_rate": 4.1921933538133726e-05,
|
| 36010 |
+
"loss": 0.7813,
|
| 36011 |
+
"step": 5143
|
| 36012 |
+
},
|
| 36013 |
+
{
|
| 36014 |
+
"epoch": 5.859259259259259,
|
| 36015 |
+
"grad_norm": 0.16732868552207947,
|
| 36016 |
+
"learning_rate": 4.191850364049886e-05,
|
| 36017 |
+
"loss": 0.7563,
|
| 36018 |
+
"step": 5144
|
| 36019 |
+
},
|
| 36020 |
+
{
|
| 36021 |
+
"epoch": 5.860398860398861,
|
| 36022 |
+
"grad_norm": 0.20382776856422424,
|
| 36023 |
+
"learning_rate": 4.1915073155237836e-05,
|
| 36024 |
+
"loss": 0.6792,
|
| 36025 |
+
"step": 5145
|
| 36026 |
+
},
|
| 36027 |
+
{
|
| 36028 |
+
"epoch": 5.861538461538462,
|
| 36029 |
+
"grad_norm": 0.23003341257572174,
|
| 36030 |
+
"learning_rate": 4.1911642082469806e-05,
|
| 36031 |
+
"loss": 0.6546,
|
| 36032 |
+
"step": 5146
|
| 36033 |
+
},
|
| 36034 |
+
{
|
| 36035 |
+
"epoch": 5.862678062678063,
|
| 36036 |
+
"grad_norm": 0.20285111665725708,
|
| 36037 |
+
"learning_rate": 4.190821042231393e-05,
|
| 36038 |
+
"loss": 0.6847,
|
| 36039 |
+
"step": 5147
|
| 36040 |
+
},
|
| 36041 |
+
{
|
| 36042 |
+
"epoch": 5.863817663817664,
|
| 36043 |
+
"grad_norm": 0.17044898867607117,
|
| 36044 |
+
"learning_rate": 4.190477817488941e-05,
|
| 36045 |
+
"loss": 0.9053,
|
| 36046 |
+
"step": 5148
|
| 36047 |
+
},
|
| 36048 |
+
{
|
| 36049 |
+
"epoch": 5.864957264957265,
|
| 36050 |
+
"grad_norm": 0.16001960635185242,
|
| 36051 |
+
"learning_rate": 4.190134534031547e-05,
|
| 36052 |
+
"loss": 0.7839,
|
| 36053 |
+
"step": 5149
|
| 36054 |
+
},
|
| 36055 |
+
{
|
| 36056 |
+
"epoch": 5.866096866096866,
|
| 36057 |
+
"grad_norm": 0.18786023557186127,
|
| 36058 |
+
"learning_rate": 4.1897911918711316e-05,
|
| 36059 |
+
"loss": 0.624,
|
| 36060 |
+
"step": 5150
|
| 36061 |
+
},
|
| 36062 |
+
{
|
| 36063 |
+
"epoch": 5.867236467236467,
|
| 36064 |
+
"grad_norm": 0.19194890558719635,
|
| 36065 |
+
"learning_rate": 4.1894477910196215e-05,
|
| 36066 |
+
"loss": 0.828,
|
| 36067 |
+
"step": 5151
|
| 36068 |
+
},
|
| 36069 |
+
{
|
| 36070 |
+
"epoch": 5.868376068376069,
|
| 36071 |
+
"grad_norm": 0.18132710456848145,
|
| 36072 |
+
"learning_rate": 4.189104331488943e-05,
|
| 36073 |
+
"loss": 0.767,
|
| 36074 |
+
"step": 5152
|
| 36075 |
+
},
|
| 36076 |
+
{
|
| 36077 |
+
"epoch": 5.869515669515669,
|
| 36078 |
+
"grad_norm": 0.19260728359222412,
|
| 36079 |
+
"learning_rate": 4.188760813291027e-05,
|
| 36080 |
+
"loss": 0.7264,
|
| 36081 |
+
"step": 5153
|
| 36082 |
+
},
|
| 36083 |
+
{
|
| 36084 |
+
"epoch": 5.870655270655271,
|
| 36085 |
+
"grad_norm": 0.18859456479549408,
|
| 36086 |
+
"learning_rate": 4.188417236437803e-05,
|
| 36087 |
+
"loss": 0.7041,
|
| 36088 |
+
"step": 5154
|
| 36089 |
+
},
|
| 36090 |
+
{
|
| 36091 |
+
"epoch": 5.871794871794872,
|
| 36092 |
+
"grad_norm": 0.17015713453292847,
|
| 36093 |
+
"learning_rate": 4.188073600941206e-05,
|
| 36094 |
+
"loss": 0.8557,
|
| 36095 |
+
"step": 5155
|
| 36096 |
+
},
|
| 36097 |
+
{
|
| 36098 |
+
"epoch": 5.872934472934473,
|
| 36099 |
+
"grad_norm": 0.15460067987442017,
|
| 36100 |
+
"learning_rate": 4.1877299068131695e-05,
|
| 36101 |
+
"loss": 0.9462,
|
| 36102 |
+
"step": 5156
|
| 36103 |
+
},
|
| 36104 |
+
{
|
| 36105 |
+
"epoch": 5.874074074074074,
|
| 36106 |
+
"grad_norm": 0.15997248888015747,
|
| 36107 |
+
"learning_rate": 4.187386154065633e-05,
|
| 36108 |
+
"loss": 0.9338,
|
| 36109 |
+
"step": 5157
|
| 36110 |
+
},
|
| 36111 |
+
{
|
| 36112 |
+
"epoch": 5.875213675213676,
|
| 36113 |
+
"grad_norm": 0.2065652459859848,
|
| 36114 |
+
"learning_rate": 4.1870423427105347e-05,
|
| 36115 |
+
"loss": 0.7578,
|
| 36116 |
+
"step": 5158
|
| 36117 |
+
},
|
| 36118 |
+
{
|
| 36119 |
+
"epoch": 5.876353276353276,
|
| 36120 |
+
"grad_norm": 0.12909001111984253,
|
| 36121 |
+
"learning_rate": 4.186698472759817e-05,
|
| 36122 |
+
"loss": 0.9939,
|
| 36123 |
+
"step": 5159
|
| 36124 |
+
},
|
| 36125 |
+
{
|
| 36126 |
+
"epoch": 5.877492877492878,
|
| 36127 |
+
"grad_norm": 0.20031005144119263,
|
| 36128 |
+
"learning_rate": 4.186354544225422e-05,
|
| 36129 |
+
"loss": 0.5834,
|
| 36130 |
+
"step": 5160
|
| 36131 |
+
},
|
| 36132 |
+
{
|
| 36133 |
+
"epoch": 5.878632478632479,
|
| 36134 |
+
"grad_norm": 0.1697911024093628,
|
| 36135 |
+
"learning_rate": 4.1860105571192964e-05,
|
| 36136 |
+
"loss": 0.8348,
|
| 36137 |
+
"step": 5161
|
| 36138 |
+
},
|
| 36139 |
+
{
|
| 36140 |
+
"epoch": 5.87977207977208,
|
| 36141 |
+
"grad_norm": 0.1760026067495346,
|
| 36142 |
+
"learning_rate": 4.1856665114533884e-05,
|
| 36143 |
+
"loss": 0.8509,
|
| 36144 |
+
"step": 5162
|
| 36145 |
+
},
|
| 36146 |
+
{
|
| 36147 |
+
"epoch": 5.880911680911681,
|
| 36148 |
+
"grad_norm": 0.17915961146354675,
|
| 36149 |
+
"learning_rate": 4.1853224072396455e-05,
|
| 36150 |
+
"loss": 0.7879,
|
| 36151 |
+
"step": 5163
|
| 36152 |
+
},
|
| 36153 |
+
{
|
| 36154 |
+
"epoch": 5.8820512820512825,
|
| 36155 |
+
"grad_norm": 0.18653781712055206,
|
| 36156 |
+
"learning_rate": 4.184978244490022e-05,
|
| 36157 |
+
"loss": 0.6107,
|
| 36158 |
+
"step": 5164
|
| 36159 |
+
},
|
| 36160 |
+
{
|
| 36161 |
+
"epoch": 5.883190883190883,
|
| 36162 |
+
"grad_norm": 0.1962171345949173,
|
| 36163 |
+
"learning_rate": 4.184634023216469e-05,
|
| 36164 |
+
"loss": 0.6755,
|
| 36165 |
+
"step": 5165
|
| 36166 |
+
},
|
| 36167 |
+
{
|
| 36168 |
+
"epoch": 5.8843304843304844,
|
| 36169 |
+
"grad_norm": 0.17595814168453217,
|
| 36170 |
+
"learning_rate": 4.184289743430945e-05,
|
| 36171 |
+
"loss": 0.6782,
|
| 36172 |
+
"step": 5166
|
| 36173 |
+
},
|
| 36174 |
+
{
|
| 36175 |
+
"epoch": 5.885470085470086,
|
| 36176 |
+
"grad_norm": 0.17818598449230194,
|
| 36177 |
+
"learning_rate": 4.1839454051454066e-05,
|
| 36178 |
+
"loss": 0.8382,
|
| 36179 |
+
"step": 5167
|
| 36180 |
+
},
|
| 36181 |
+
{
|
| 36182 |
+
"epoch": 5.886609686609686,
|
| 36183 |
+
"grad_norm": 0.17707544565200806,
|
| 36184 |
+
"learning_rate": 4.1836010083718126e-05,
|
| 36185 |
+
"loss": 0.7483,
|
| 36186 |
+
"step": 5168
|
| 36187 |
+
},
|
| 36188 |
+
{
|
| 36189 |
+
"epoch": 5.887749287749288,
|
| 36190 |
+
"grad_norm": 0.14160114526748657,
|
| 36191 |
+
"learning_rate": 4.1832565531221254e-05,
|
| 36192 |
+
"loss": 0.9062,
|
| 36193 |
+
"step": 5169
|
| 36194 |
+
},
|
| 36195 |
+
{
|
| 36196 |
+
"epoch": 5.888888888888889,
|
| 36197 |
+
"grad_norm": 0.21327587962150574,
|
| 36198 |
+
"learning_rate": 4.182912039408309e-05,
|
| 36199 |
+
"loss": 0.7015,
|
| 36200 |
+
"step": 5170
|
| 36201 |
+
},
|
| 36202 |
+
{
|
| 36203 |
+
"epoch": 5.89002849002849,
|
| 36204 |
+
"grad_norm": 0.16977612674236298,
|
| 36205 |
+
"learning_rate": 4.1825674672423296e-05,
|
| 36206 |
+
"loss": 0.9099,
|
| 36207 |
+
"step": 5171
|
| 36208 |
+
},
|
| 36209 |
+
{
|
| 36210 |
+
"epoch": 5.891168091168091,
|
| 36211 |
+
"grad_norm": 0.1685507893562317,
|
| 36212 |
+
"learning_rate": 4.182222836636156e-05,
|
| 36213 |
+
"loss": 0.8978,
|
| 36214 |
+
"step": 5172
|
| 36215 |
+
},
|
| 36216 |
+
{
|
| 36217 |
+
"epoch": 5.892307692307693,
|
| 36218 |
+
"grad_norm": 0.20601628720760345,
|
| 36219 |
+
"learning_rate": 4.181878147601756e-05,
|
| 36220 |
+
"loss": 0.7116,
|
| 36221 |
+
"step": 5173
|
| 36222 |
+
},
|
| 36223 |
+
{
|
| 36224 |
+
"epoch": 5.893447293447293,
|
| 36225 |
+
"grad_norm": 0.1586993783712387,
|
| 36226 |
+
"learning_rate": 4.1815334001511045e-05,
|
| 36227 |
+
"loss": 0.7348,
|
| 36228 |
+
"step": 5174
|
| 36229 |
+
},
|
| 36230 |
+
{
|
| 36231 |
+
"epoch": 5.894586894586895,
|
| 36232 |
+
"grad_norm": 0.17004381120204926,
|
| 36233 |
+
"learning_rate": 4.1811885942961716e-05,
|
| 36234 |
+
"loss": 0.8967,
|
| 36235 |
+
"step": 5175
|
| 36236 |
+
},
|
| 36237 |
+
{
|
| 36238 |
+
"epoch": 5.895726495726496,
|
| 36239 |
+
"grad_norm": 0.16897311806678772,
|
| 36240 |
+
"learning_rate": 4.180843730048937e-05,
|
| 36241 |
+
"loss": 0.9032,
|
| 36242 |
+
"step": 5176
|
| 36243 |
+
},
|
| 36244 |
+
{
|
| 36245 |
+
"epoch": 5.896866096866097,
|
| 36246 |
+
"grad_norm": 0.15307942032814026,
|
| 36247 |
+
"learning_rate": 4.1804988074213765e-05,
|
| 36248 |
+
"loss": 0.8533,
|
| 36249 |
+
"step": 5177
|
| 36250 |
+
},
|
| 36251 |
+
{
|
| 36252 |
+
"epoch": 5.898005698005698,
|
| 36253 |
+
"grad_norm": 0.18711508810520172,
|
| 36254 |
+
"learning_rate": 4.1801538264254717e-05,
|
| 36255 |
+
"loss": 0.7271,
|
| 36256 |
+
"step": 5178
|
| 36257 |
+
},
|
| 36258 |
+
{
|
| 36259 |
+
"epoch": 5.8991452991452995,
|
| 36260 |
+
"grad_norm": 0.15038523077964783,
|
| 36261 |
+
"learning_rate": 4.179808787073203e-05,
|
| 36262 |
+
"loss": 0.8249,
|
| 36263 |
+
"step": 5179
|
| 36264 |
+
},
|
| 36265 |
+
{
|
| 36266 |
+
"epoch": 5.9002849002849,
|
| 36267 |
+
"grad_norm": 0.16373242437839508,
|
| 36268 |
+
"learning_rate": 4.1794636893765564e-05,
|
| 36269 |
+
"loss": 0.8624,
|
| 36270 |
+
"step": 5180
|
| 36271 |
+
},
|
| 36272 |
+
{
|
| 36273 |
+
"epoch": 5.9014245014245015,
|
| 36274 |
+
"grad_norm": 0.2116909921169281,
|
| 36275 |
+
"learning_rate": 4.179118533347517e-05,
|
| 36276 |
+
"loss": 0.7566,
|
| 36277 |
+
"step": 5181
|
| 36278 |
+
},
|
| 36279 |
+
{
|
| 36280 |
+
"epoch": 5.902564102564103,
|
| 36281 |
+
"grad_norm": 0.1693403720855713,
|
| 36282 |
+
"learning_rate": 4.178773318998074e-05,
|
| 36283 |
+
"loss": 0.7506,
|
| 36284 |
+
"step": 5182
|
| 36285 |
+
},
|
| 36286 |
+
{
|
| 36287 |
+
"epoch": 5.9037037037037035,
|
| 36288 |
+
"grad_norm": 0.15692570805549622,
|
| 36289 |
+
"learning_rate": 4.178428046340216e-05,
|
| 36290 |
+
"loss": 0.6163,
|
| 36291 |
+
"step": 5183
|
| 36292 |
+
},
|
| 36293 |
+
{
|
| 36294 |
+
"epoch": 5.904843304843305,
|
| 36295 |
+
"grad_norm": 0.1439063400030136,
|
| 36296 |
+
"learning_rate": 4.178082715385937e-05,
|
| 36297 |
+
"loss": 0.9431,
|
| 36298 |
+
"step": 5184
|
| 36299 |
+
},
|
| 36300 |
+
{
|
| 36301 |
+
"epoch": 5.905982905982906,
|
| 36302 |
+
"grad_norm": 0.16660434007644653,
|
| 36303 |
+
"learning_rate": 4.1777373261472305e-05,
|
| 36304 |
+
"loss": 0.9886,
|
| 36305 |
+
"step": 5185
|
| 36306 |
+
},
|
| 36307 |
+
{
|
| 36308 |
+
"epoch": 5.907122507122507,
|
| 36309 |
+
"grad_norm": 0.17003867030143738,
|
| 36310 |
+
"learning_rate": 4.1773918786360925e-05,
|
| 36311 |
+
"loss": 0.6948,
|
| 36312 |
+
"step": 5186
|
| 36313 |
+
},
|
| 36314 |
+
{
|
| 36315 |
+
"epoch": 5.908262108262108,
|
| 36316 |
+
"grad_norm": 0.18516221642494202,
|
| 36317 |
+
"learning_rate": 4.1770463728645214e-05,
|
| 36318 |
+
"loss": 0.5875,
|
| 36319 |
+
"step": 5187
|
| 36320 |
+
},
|
| 36321 |
+
{
|
| 36322 |
+
"epoch": 5.90940170940171,
|
| 36323 |
+
"grad_norm": 0.17292432487010956,
|
| 36324 |
+
"learning_rate": 4.1767008088445185e-05,
|
| 36325 |
+
"loss": 0.9163,
|
| 36326 |
+
"step": 5188
|
| 36327 |
+
},
|
| 36328 |
+
{
|
| 36329 |
+
"epoch": 5.91054131054131,
|
| 36330 |
+
"grad_norm": 0.1750919222831726,
|
| 36331 |
+
"learning_rate": 4.1763551865880854e-05,
|
| 36332 |
+
"loss": 0.7027,
|
| 36333 |
+
"step": 5189
|
| 36334 |
+
},
|
| 36335 |
+
{
|
| 36336 |
+
"epoch": 5.911680911680912,
|
| 36337 |
+
"grad_norm": 0.16704607009887695,
|
| 36338 |
+
"learning_rate": 4.176009506107227e-05,
|
| 36339 |
+
"loss": 0.9621,
|
| 36340 |
+
"step": 5190
|
| 36341 |
+
},
|
| 36342 |
+
{
|
| 36343 |
+
"epoch": 5.912820512820513,
|
| 36344 |
+
"grad_norm": 0.1801830530166626,
|
| 36345 |
+
"learning_rate": 4.175663767413949e-05,
|
| 36346 |
+
"loss": 0.6906,
|
| 36347 |
+
"step": 5191
|
| 36348 |
+
},
|
| 36349 |
+
{
|
| 36350 |
+
"epoch": 5.913960113960114,
|
| 36351 |
+
"grad_norm": 0.26363036036491394,
|
| 36352 |
+
"learning_rate": 4.175317970520261e-05,
|
| 36353 |
+
"loss": 0.938,
|
| 36354 |
+
"step": 5192
|
| 36355 |
+
},
|
| 36356 |
+
{
|
| 36357 |
+
"epoch": 5.915099715099715,
|
| 36358 |
+
"grad_norm": 0.17508383095264435,
|
| 36359 |
+
"learning_rate": 4.174972115438172e-05,
|
| 36360 |
+
"loss": 0.7674,
|
| 36361 |
+
"step": 5193
|
| 36362 |
+
},
|
| 36363 |
+
{
|
| 36364 |
+
"epoch": 5.9162393162393165,
|
| 36365 |
+
"grad_norm": 0.16467712819576263,
|
| 36366 |
+
"learning_rate": 4.1746262021796956e-05,
|
| 36367 |
+
"loss": 0.8915,
|
| 36368 |
+
"step": 5194
|
| 36369 |
+
},
|
| 36370 |
+
{
|
| 36371 |
+
"epoch": 5.917378917378917,
|
| 36372 |
+
"grad_norm": 0.20937953889369965,
|
| 36373 |
+
"learning_rate": 4.174280230756845e-05,
|
| 36374 |
+
"loss": 0.7949,
|
| 36375 |
+
"step": 5195
|
| 36376 |
+
},
|
| 36377 |
+
{
|
| 36378 |
+
"epoch": 5.9185185185185185,
|
| 36379 |
+
"grad_norm": 0.17789477109909058,
|
| 36380 |
+
"learning_rate": 4.173934201181639e-05,
|
| 36381 |
+
"loss": 0.796,
|
| 36382 |
+
"step": 5196
|
| 36383 |
+
},
|
| 36384 |
+
{
|
| 36385 |
+
"epoch": 5.91965811965812,
|
| 36386 |
+
"grad_norm": 0.15541639924049377,
|
| 36387 |
+
"learning_rate": 4.173588113466094e-05,
|
| 36388 |
+
"loss": 0.8389,
|
| 36389 |
+
"step": 5197
|
| 36390 |
+
},
|
| 36391 |
+
{
|
| 36392 |
+
"epoch": 5.9207977207977205,
|
| 36393 |
+
"grad_norm": 0.19931167364120483,
|
| 36394 |
+
"learning_rate": 4.1732419676222315e-05,
|
| 36395 |
+
"loss": 0.761,
|
| 36396 |
+
"step": 5198
|
| 36397 |
+
},
|
| 36398 |
+
{
|
| 36399 |
+
"epoch": 5.921937321937322,
|
| 36400 |
+
"grad_norm": 0.17033979296684265,
|
| 36401 |
+
"learning_rate": 4.172895763662075e-05,
|
| 36402 |
+
"loss": 0.8802,
|
| 36403 |
+
"step": 5199
|
| 36404 |
+
},
|
| 36405 |
+
{
|
| 36406 |
+
"epoch": 5.923076923076923,
|
| 36407 |
+
"grad_norm": 0.14268510043621063,
|
| 36408 |
+
"learning_rate": 4.172549501597647e-05,
|
| 36409 |
+
"loss": 0.9945,
|
| 36410 |
+
"step": 5200
|
| 36411 |
+
},
|
| 36412 |
+
{
|
| 36413 |
+
"epoch": 5.924216524216524,
|
| 36414 |
+
"grad_norm": 0.21729013323783875,
|
| 36415 |
+
"learning_rate": 4.1722031814409754e-05,
|
| 36416 |
+
"loss": 0.7922,
|
| 36417 |
+
"step": 5201
|
| 36418 |
+
},
|
| 36419 |
+
{
|
| 36420 |
+
"epoch": 5.925356125356125,
|
| 36421 |
+
"grad_norm": 0.17441385984420776,
|
| 36422 |
+
"learning_rate": 4.1718568032040895e-05,
|
| 36423 |
+
"loss": 0.8094,
|
| 36424 |
+
"step": 5202
|
| 36425 |
+
},
|
| 36426 |
+
{
|
| 36427 |
+
"epoch": 5.926495726495727,
|
| 36428 |
+
"grad_norm": 0.16148298978805542,
|
| 36429 |
+
"learning_rate": 4.1715103668990184e-05,
|
| 36430 |
+
"loss": 0.9102,
|
| 36431 |
+
"step": 5203
|
| 36432 |
+
},
|
| 36433 |
+
{
|
| 36434 |
+
"epoch": 5.927635327635327,
|
| 36435 |
+
"grad_norm": 0.25135836005210876,
|
| 36436 |
+
"learning_rate": 4.1711638725377955e-05,
|
| 36437 |
+
"loss": 0.5235,
|
| 36438 |
+
"step": 5204
|
| 36439 |
+
},
|
| 36440 |
+
{
|
| 36441 |
+
"epoch": 5.928774928774929,
|
| 36442 |
+
"grad_norm": 0.17879357933998108,
|
| 36443 |
+
"learning_rate": 4.170817320132456e-05,
|
| 36444 |
+
"loss": 0.8012,
|
| 36445 |
+
"step": 5205
|
| 36446 |
+
},
|
| 36447 |
+
{
|
| 36448 |
+
"epoch": 5.92991452991453,
|
| 36449 |
+
"grad_norm": 0.19453158974647522,
|
| 36450 |
+
"learning_rate": 4.170470709695037e-05,
|
| 36451 |
+
"loss": 0.7937,
|
| 36452 |
+
"step": 5206
|
| 36453 |
+
},
|
| 36454 |
+
{
|
| 36455 |
+
"epoch": 5.931054131054131,
|
| 36456 |
+
"grad_norm": 0.1418699026107788,
|
| 36457 |
+
"learning_rate": 4.170124041237575e-05,
|
| 36458 |
+
"loss": 0.8227,
|
| 36459 |
+
"step": 5207
|
| 36460 |
+
},
|
| 36461 |
+
{
|
| 36462 |
+
"epoch": 5.932193732193732,
|
| 36463 |
+
"grad_norm": 0.15917539596557617,
|
| 36464 |
+
"learning_rate": 4.169777314772113e-05,
|
| 36465 |
+
"loss": 0.7265,
|
| 36466 |
+
"step": 5208
|
| 36467 |
+
},
|
| 36468 |
+
{
|
| 36469 |
+
"epoch": 5.933333333333334,
|
| 36470 |
+
"grad_norm": 0.15594954788684845,
|
| 36471 |
+
"learning_rate": 4.169430530310693e-05,
|
| 36472 |
+
"loss": 0.8795,
|
| 36473 |
+
"step": 5209
|
| 36474 |
+
},
|
| 36475 |
+
{
|
| 36476 |
+
"epoch": 5.934472934472934,
|
| 36477 |
+
"grad_norm": 0.16013088822364807,
|
| 36478 |
+
"learning_rate": 4.169083687865359e-05,
|
| 36479 |
+
"loss": 0.9405,
|
| 36480 |
+
"step": 5210
|
| 36481 |
+
},
|
| 36482 |
+
{
|
| 36483 |
+
"epoch": 5.9356125356125355,
|
| 36484 |
+
"grad_norm": 0.1493656039237976,
|
| 36485 |
+
"learning_rate": 4.16873678744816e-05,
|
| 36486 |
+
"loss": 0.8744,
|
| 36487 |
+
"step": 5211
|
| 36488 |
+
},
|
| 36489 |
+
{
|
| 36490 |
+
"epoch": 5.936752136752137,
|
| 36491 |
+
"grad_norm": 0.1798950731754303,
|
| 36492 |
+
"learning_rate": 4.168389829071142e-05,
|
| 36493 |
+
"loss": 0.6973,
|
| 36494 |
+
"step": 5212
|
| 36495 |
+
},
|
| 36496 |
+
{
|
| 36497 |
+
"epoch": 5.9378917378917375,
|
| 36498 |
+
"grad_norm": 0.15619346499443054,
|
| 36499 |
+
"learning_rate": 4.1680428127463576e-05,
|
| 36500 |
+
"loss": 0.9694,
|
| 36501 |
+
"step": 5213
|
| 36502 |
+
},
|
| 36503 |
+
{
|
| 36504 |
+
"epoch": 5.939031339031339,
|
| 36505 |
+
"grad_norm": 0.17171142995357513,
|
| 36506 |
+
"learning_rate": 4.1676957384858584e-05,
|
| 36507 |
+
"loss": 0.7721,
|
| 36508 |
+
"step": 5214
|
| 36509 |
+
},
|
| 36510 |
+
{
|
| 36511 |
+
"epoch": 5.94017094017094,
|
| 36512 |
+
"grad_norm": 0.21483421325683594,
|
| 36513 |
+
"learning_rate": 4.167348606301701e-05,
|
| 36514 |
+
"loss": 0.7483,
|
| 36515 |
+
"step": 5215
|
| 36516 |
+
},
|
| 36517 |
+
{
|
| 36518 |
+
"epoch": 5.941310541310541,
|
| 36519 |
+
"grad_norm": 0.1769595593214035,
|
| 36520 |
+
"learning_rate": 4.167001416205941e-05,
|
| 36521 |
+
"loss": 0.7624,
|
| 36522 |
+
"step": 5216
|
| 36523 |
+
},
|
| 36524 |
+
{
|
| 36525 |
+
"epoch": 5.942450142450142,
|
| 36526 |
+
"grad_norm": 0.17398640513420105,
|
| 36527 |
+
"learning_rate": 4.166654168210637e-05,
|
| 36528 |
+
"loss": 0.7972,
|
| 36529 |
+
"step": 5217
|
| 36530 |
+
},
|
| 36531 |
+
{
|
| 36532 |
+
"epoch": 5.943589743589744,
|
| 36533 |
+
"grad_norm": 0.16116030514240265,
|
| 36534 |
+
"learning_rate": 4.166306862327851e-05,
|
| 36535 |
+
"loss": 0.9679,
|
| 36536 |
+
"step": 5218
|
| 36537 |
+
},
|
| 36538 |
+
{
|
| 36539 |
+
"epoch": 5.944729344729344,
|
| 36540 |
+
"grad_norm": 0.16955454647541046,
|
| 36541 |
+
"learning_rate": 4.165959498569646e-05,
|
| 36542 |
+
"loss": 0.8423,
|
| 36543 |
+
"step": 5219
|
| 36544 |
+
},
|
| 36545 |
+
{
|
| 36546 |
+
"epoch": 5.945868945868946,
|
| 36547 |
+
"grad_norm": 0.14700596034526825,
|
| 36548 |
+
"learning_rate": 4.165612076948086e-05,
|
| 36549 |
+
"loss": 0.8902,
|
| 36550 |
+
"step": 5220
|
| 36551 |
+
},
|
| 36552 |
+
{
|
| 36553 |
+
"epoch": 5.947008547008547,
|
| 36554 |
+
"grad_norm": 0.2059997171163559,
|
| 36555 |
+
"learning_rate": 4.165264597475237e-05,
|
| 36556 |
+
"loss": 0.5552,
|
| 36557 |
+
"step": 5221
|
| 36558 |
+
},
|
| 36559 |
+
{
|
| 36560 |
+
"epoch": 5.948148148148148,
|
| 36561 |
+
"grad_norm": 0.16482126712799072,
|
| 36562 |
+
"learning_rate": 4.164917060163169e-05,
|
| 36563 |
+
"loss": 0.7523,
|
| 36564 |
+
"step": 5222
|
| 36565 |
+
},
|
| 36566 |
+
{
|
| 36567 |
+
"epoch": 5.949287749287749,
|
| 36568 |
+
"grad_norm": 0.17832493782043457,
|
| 36569 |
+
"learning_rate": 4.1645694650239543e-05,
|
| 36570 |
+
"loss": 0.7924,
|
| 36571 |
+
"step": 5223
|
| 36572 |
+
},
|
| 36573 |
+
{
|
| 36574 |
+
"epoch": 5.950427350427351,
|
| 36575 |
+
"grad_norm": 0.1778307408094406,
|
| 36576 |
+
"learning_rate": 4.1642218120696633e-05,
|
| 36577 |
+
"loss": 0.9122,
|
| 36578 |
+
"step": 5224
|
| 36579 |
+
},
|
| 36580 |
+
{
|
| 36581 |
+
"epoch": 5.951566951566951,
|
| 36582 |
+
"grad_norm": 0.16003210842609406,
|
| 36583 |
+
"learning_rate": 4.163874101312373e-05,
|
| 36584 |
+
"loss": 0.741,
|
| 36585 |
+
"step": 5225
|
| 36586 |
+
},
|
| 36587 |
+
{
|
| 36588 |
+
"epoch": 5.952706552706553,
|
| 36589 |
+
"grad_norm": 0.21680839359760284,
|
| 36590 |
+
"learning_rate": 4.163526332764159e-05,
|
| 36591 |
+
"loss": 0.688,
|
| 36592 |
+
"step": 5226
|
| 36593 |
+
},
|
| 36594 |
+
{
|
| 36595 |
+
"epoch": 5.953846153846154,
|
| 36596 |
+
"grad_norm": 0.1745540350675583,
|
| 36597 |
+
"learning_rate": 4.163178506437101e-05,
|
| 36598 |
+
"loss": 0.6564,
|
| 36599 |
+
"step": 5227
|
| 36600 |
+
},
|
| 36601 |
+
{
|
| 36602 |
+
"epoch": 5.9549857549857546,
|
| 36603 |
+
"grad_norm": 0.18622197210788727,
|
| 36604 |
+
"learning_rate": 4.1628306223432796e-05,
|
| 36605 |
+
"loss": 0.7516,
|
| 36606 |
+
"step": 5228
|
| 36607 |
+
},
|
| 36608 |
+
{
|
| 36609 |
+
"epoch": 5.956125356125356,
|
| 36610 |
+
"grad_norm": 0.20277757942676544,
|
| 36611 |
+
"learning_rate": 4.1624826804947776e-05,
|
| 36612 |
+
"loss": 0.6995,
|
| 36613 |
+
"step": 5229
|
| 36614 |
+
},
|
| 36615 |
+
{
|
| 36616 |
+
"epoch": 5.957264957264957,
|
| 36617 |
+
"grad_norm": 0.16135753691196442,
|
| 36618 |
+
"learning_rate": 4.162134680903681e-05,
|
| 36619 |
+
"loss": 0.8785,
|
| 36620 |
+
"step": 5230
|
| 36621 |
+
},
|
| 36622 |
+
{
|
| 36623 |
+
"epoch": 5.958404558404558,
|
| 36624 |
+
"grad_norm": 0.18638533353805542,
|
| 36625 |
+
"learning_rate": 4.161786623582075e-05,
|
| 36626 |
+
"loss": 0.7628,
|
| 36627 |
+
"step": 5231
|
| 36628 |
+
},
|
| 36629 |
+
{
|
| 36630 |
+
"epoch": 5.959544159544159,
|
| 36631 |
+
"grad_norm": 0.1866452842950821,
|
| 36632 |
+
"learning_rate": 4.1614385085420506e-05,
|
| 36633 |
+
"loss": 0.7243,
|
| 36634 |
+
"step": 5232
|
| 36635 |
+
},
|
| 36636 |
+
{
|
| 36637 |
+
"epoch": 5.960683760683761,
|
| 36638 |
+
"grad_norm": 0.1564568281173706,
|
| 36639 |
+
"learning_rate": 4.1610903357956964e-05,
|
| 36640 |
+
"loss": 0.7086,
|
| 36641 |
+
"step": 5233
|
| 36642 |
+
},
|
| 36643 |
+
{
|
| 36644 |
+
"epoch": 5.961823361823361,
|
| 36645 |
+
"grad_norm": 0.18204548954963684,
|
| 36646 |
+
"learning_rate": 4.1607421053551085e-05,
|
| 36647 |
+
"loss": 0.8382,
|
| 36648 |
+
"step": 5234
|
| 36649 |
+
},
|
| 36650 |
+
{
|
| 36651 |
+
"epoch": 5.962962962962963,
|
| 36652 |
+
"grad_norm": 0.17170333862304688,
|
| 36653 |
+
"learning_rate": 4.16039381723238e-05,
|
| 36654 |
+
"loss": 0.83,
|
| 36655 |
+
"step": 5235
|
| 36656 |
+
},
|
| 36657 |
+
{
|
| 36658 |
+
"epoch": 5.964102564102564,
|
| 36659 |
+
"grad_norm": 0.1687270998954773,
|
| 36660 |
+
"learning_rate": 4.160045471439607e-05,
|
| 36661 |
+
"loss": 0.7975,
|
| 36662 |
+
"step": 5236
|
| 36663 |
+
},
|
| 36664 |
+
{
|
| 36665 |
+
"epoch": 5.965242165242165,
|
| 36666 |
+
"grad_norm": 0.18899831175804138,
|
| 36667 |
+
"learning_rate": 4.1596970679888904e-05,
|
| 36668 |
+
"loss": 0.7623,
|
| 36669 |
+
"step": 5237
|
| 36670 |
+
},
|
| 36671 |
+
{
|
| 36672 |
+
"epoch": 5.966381766381766,
|
| 36673 |
+
"grad_norm": 0.2305077463388443,
|
| 36674 |
+
"learning_rate": 4.1593486068923304e-05,
|
| 36675 |
+
"loss": 0.5313,
|
| 36676 |
+
"step": 5238
|
| 36677 |
+
},
|
| 36678 |
+
{
|
| 36679 |
+
"epoch": 5.967521367521368,
|
| 36680 |
+
"grad_norm": 0.15524014830589294,
|
| 36681 |
+
"learning_rate": 4.15900008816203e-05,
|
| 36682 |
+
"loss": 0.889,
|
| 36683 |
+
"step": 5239
|
| 36684 |
+
},
|
| 36685 |
+
{
|
| 36686 |
+
"epoch": 5.968660968660968,
|
| 36687 |
+
"grad_norm": 0.17087559401988983,
|
| 36688 |
+
"learning_rate": 4.158651511810094e-05,
|
| 36689 |
+
"loss": 0.6742,
|
| 36690 |
+
"step": 5240
|
| 36691 |
+
},
|
| 36692 |
+
{
|
| 36693 |
+
"epoch": 5.96980056980057,
|
| 36694 |
+
"grad_norm": 0.18067264556884766,
|
| 36695 |
+
"learning_rate": 4.1583028778486306e-05,
|
| 36696 |
+
"loss": 0.831,
|
| 36697 |
+
"step": 5241
|
| 36698 |
+
},
|
| 36699 |
+
{
|
| 36700 |
+
"epoch": 5.970940170940171,
|
| 36701 |
+
"grad_norm": 0.19102199375629425,
|
| 36702 |
+
"learning_rate": 4.157954186289747e-05,
|
| 36703 |
+
"loss": 0.6895,
|
| 36704 |
+
"step": 5242
|
| 36705 |
+
},
|
| 36706 |
+
{
|
| 36707 |
+
"epoch": 5.972079772079772,
|
| 36708 |
+
"grad_norm": 0.1627579778432846,
|
| 36709 |
+
"learning_rate": 4.1576054371455556e-05,
|
| 36710 |
+
"loss": 0.781,
|
| 36711 |
+
"step": 5243
|
| 36712 |
+
},
|
| 36713 |
+
{
|
| 36714 |
+
"epoch": 5.973219373219373,
|
| 36715 |
+
"grad_norm": 0.2128324806690216,
|
| 36716 |
+
"learning_rate": 4.157256630428169e-05,
|
| 36717 |
+
"loss": 0.5727,
|
| 36718 |
+
"step": 5244
|
| 36719 |
+
},
|
| 36720 |
+
{
|
| 36721 |
+
"epoch": 5.9743589743589745,
|
| 36722 |
+
"grad_norm": 0.18273428082466125,
|
| 36723 |
+
"learning_rate": 4.156907766149701e-05,
|
| 36724 |
+
"loss": 0.8635,
|
| 36725 |
+
"step": 5245
|
| 36726 |
+
},
|
| 36727 |
+
{
|
| 36728 |
+
"epoch": 5.975498575498576,
|
| 36729 |
+
"grad_norm": 0.18876968324184418,
|
| 36730 |
+
"learning_rate": 4.1565588443222717e-05,
|
| 36731 |
+
"loss": 0.7594,
|
| 36732 |
+
"step": 5246
|
| 36733 |
+
},
|
| 36734 |
+
{
|
| 36735 |
+
"epoch": 5.976638176638176,
|
| 36736 |
+
"grad_norm": 0.17812277376651764,
|
| 36737 |
+
"learning_rate": 4.156209864957996e-05,
|
| 36738 |
+
"loss": 0.8341,
|
| 36739 |
+
"step": 5247
|
| 36740 |
+
},
|
| 36741 |
+
{
|
| 36742 |
+
"epoch": 5.977777777777778,
|
| 36743 |
+
"grad_norm": 0.16235648095607758,
|
| 36744 |
+
"learning_rate": 4.155860828068998e-05,
|
| 36745 |
+
"loss": 0.8527,
|
| 36746 |
+
"step": 5248
|
| 36747 |
+
},
|
| 36748 |
+
{
|
| 36749 |
+
"epoch": 5.978917378917379,
|
| 36750 |
+
"grad_norm": 0.16066183149814606,
|
| 36751 |
+
"learning_rate": 4.155511733667401e-05,
|
| 36752 |
+
"loss": 0.8579,
|
| 36753 |
+
"step": 5249
|
| 36754 |
+
},
|
| 36755 |
+
{
|
| 36756 |
+
"epoch": 5.98005698005698,
|
| 36757 |
+
"grad_norm": 0.18555085361003876,
|
| 36758 |
+
"learning_rate": 4.155162581765327e-05,
|
| 36759 |
+
"loss": 0.8633,
|
| 36760 |
+
"step": 5250
|
| 36761 |
+
},
|
| 36762 |
+
{
|
| 36763 |
+
"epoch": 5.981196581196581,
|
| 36764 |
+
"grad_norm": 0.17659147083759308,
|
| 36765 |
+
"learning_rate": 4.1548133723749063e-05,
|
| 36766 |
+
"loss": 0.8195,
|
| 36767 |
+
"step": 5251
|
| 36768 |
+
},
|
| 36769 |
+
{
|
| 36770 |
+
"epoch": 5.982336182336183,
|
| 36771 |
+
"grad_norm": 0.16259127855300903,
|
| 36772 |
+
"learning_rate": 4.1544641055082655e-05,
|
| 36773 |
+
"loss": 0.8269,
|
| 36774 |
+
"step": 5252
|
| 36775 |
+
},
|
| 36776 |
+
{
|
| 36777 |
+
"epoch": 5.983475783475783,
|
| 36778 |
+
"grad_norm": 0.20572814345359802,
|
| 36779 |
+
"learning_rate": 4.154114781177537e-05,
|
| 36780 |
+
"loss": 0.789,
|
| 36781 |
+
"step": 5253
|
| 36782 |
+
},
|
| 36783 |
+
{
|
| 36784 |
+
"epoch": 5.984615384615385,
|
| 36785 |
+
"grad_norm": 0.2040083110332489,
|
| 36786 |
+
"learning_rate": 4.1537653993948534e-05,
|
| 36787 |
+
"loss": 0.7576,
|
| 36788 |
+
"step": 5254
|
| 36789 |
+
},
|
| 36790 |
+
{
|
| 36791 |
+
"epoch": 5.985754985754986,
|
| 36792 |
+
"grad_norm": 0.19470487534999847,
|
| 36793 |
+
"learning_rate": 4.1534159601723485e-05,
|
| 36794 |
+
"loss": 0.7658,
|
| 36795 |
+
"step": 5255
|
| 36796 |
+
},
|
| 36797 |
+
{
|
| 36798 |
+
"epoch": 5.986894586894587,
|
| 36799 |
+
"grad_norm": 0.20511211454868317,
|
| 36800 |
+
"learning_rate": 4.153066463522162e-05,
|
| 36801 |
+
"loss": 0.6674,
|
| 36802 |
+
"step": 5256
|
| 36803 |
+
},
|
| 36804 |
+
{
|
| 36805 |
+
"epoch": 5.988034188034188,
|
| 36806 |
+
"grad_norm": 0.16894656419754028,
|
| 36807 |
+
"learning_rate": 4.15271690945643e-05,
|
| 36808 |
+
"loss": 0.7289,
|
| 36809 |
+
"step": 5257
|
| 36810 |
+
},
|
| 36811 |
+
{
|
| 36812 |
+
"epoch": 5.9891737891737895,
|
| 36813 |
+
"grad_norm": 0.16726945340633392,
|
| 36814 |
+
"learning_rate": 4.152367297987295e-05,
|
| 36815 |
+
"loss": 0.6524,
|
| 36816 |
+
"step": 5258
|
| 36817 |
+
},
|
| 36818 |
+
{
|
| 36819 |
+
"epoch": 5.99031339031339,
|
| 36820 |
+
"grad_norm": 0.2010265290737152,
|
| 36821 |
+
"learning_rate": 4.1520176291269e-05,
|
| 36822 |
+
"loss": 0.7551,
|
| 36823 |
+
"step": 5259
|
| 36824 |
+
},
|
| 36825 |
+
{
|
| 36826 |
+
"epoch": 5.9914529914529915,
|
| 36827 |
+
"grad_norm": 0.22712863981723785,
|
| 36828 |
+
"learning_rate": 4.15166790288739e-05,
|
| 36829 |
+
"loss": 0.6571,
|
| 36830 |
+
"step": 5260
|
| 36831 |
+
},
|
| 36832 |
+
{
|
| 36833 |
+
"epoch": 5.992592592592593,
|
| 36834 |
+
"grad_norm": 0.1745138317346573,
|
| 36835 |
+
"learning_rate": 4.1513181192809116e-05,
|
| 36836 |
+
"loss": 0.9201,
|
| 36837 |
+
"step": 5261
|
| 36838 |
+
},
|
| 36839 |
+
{
|
| 36840 |
+
"epoch": 5.9937321937321935,
|
| 36841 |
+
"grad_norm": 0.16642703115940094,
|
| 36842 |
+
"learning_rate": 4.150968278319614e-05,
|
| 36843 |
+
"loss": 0.7621,
|
| 36844 |
+
"step": 5262
|
| 36845 |
+
},
|
| 36846 |
+
{
|
| 36847 |
+
"epoch": 5.994871794871795,
|
| 36848 |
+
"grad_norm": 0.18345484137535095,
|
| 36849 |
+
"learning_rate": 4.150618380015647e-05,
|
| 36850 |
+
"loss": 0.7618,
|
| 36851 |
+
"step": 5263
|
| 36852 |
+
},
|
| 36853 |
+
{
|
| 36854 |
+
"epoch": 5.996011396011396,
|
| 36855 |
+
"grad_norm": 0.162578746676445,
|
| 36856 |
+
"learning_rate": 4.150268424381164e-05,
|
| 36857 |
+
"loss": 0.8196,
|
| 36858 |
+
"step": 5264
|
| 36859 |
+
},
|
| 36860 |
+
{
|
| 36861 |
+
"epoch": 5.997150997150997,
|
| 36862 |
+
"grad_norm": 0.15569950640201569,
|
| 36863 |
+
"learning_rate": 4.149918411428321e-05,
|
| 36864 |
+
"loss": 0.8533,
|
| 36865 |
+
"step": 5265
|
| 36866 |
+
},
|
| 36867 |
+
{
|
| 36868 |
+
"epoch": 5.998290598290598,
|
| 36869 |
+
"grad_norm": 0.1814025491476059,
|
| 36870 |
+
"learning_rate": 4.149568341169275e-05,
|
| 36871 |
+
"loss": 0.6732,
|
| 36872 |
+
"step": 5266
|
| 36873 |
+
},
|
| 36874 |
+
{
|
| 36875 |
+
"epoch": 5.9994301994302,
|
| 36876 |
+
"grad_norm": 0.1958899050951004,
|
| 36877 |
+
"learning_rate": 4.149218213616184e-05,
|
| 36878 |
+
"loss": 0.8781,
|
| 36879 |
+
"step": 5267
|
| 36880 |
+
},
|
| 36881 |
+
{
|
| 36882 |
+
"epoch": 6.0,
|
| 36883 |
+
"grad_norm": 0.3204585313796997,
|
| 36884 |
+
"learning_rate": 4.1488680287812085e-05,
|
| 36885 |
+
"loss": 0.865,
|
| 36886 |
+
"step": 5268
|
| 36887 |
+
},
|
| 36888 |
+
{
|
| 36889 |
+
"epoch": 6.001139601139601,
|
| 36890 |
+
"grad_norm": 0.1715724766254425,
|
| 36891 |
+
"learning_rate": 4.148517786676512e-05,
|
| 36892 |
+
"loss": 0.8186,
|
| 36893 |
+
"step": 5269
|
| 36894 |
+
},
|
| 36895 |
+
{
|
| 36896 |
+
"epoch": 6.002279202279202,
|
| 36897 |
+
"grad_norm": 0.1656695306301117,
|
| 36898 |
+
"learning_rate": 4.14816748731426e-05,
|
| 36899 |
+
"loss": 0.872,
|
| 36900 |
+
"step": 5270
|
| 36901 |
+
},
|
| 36902 |
+
{
|
| 36903 |
+
"epoch": 6.003418803418803,
|
| 36904 |
+
"grad_norm": 0.16879065334796906,
|
| 36905 |
+
"learning_rate": 4.147817130706617e-05,
|
| 36906 |
+
"loss": 0.7316,
|
| 36907 |
+
"step": 5271
|
| 36908 |
+
},
|
| 36909 |
+
{
|
| 36910 |
+
"epoch": 6.004558404558405,
|
| 36911 |
+
"grad_norm": 0.19011043012142181,
|
| 36912 |
+
"learning_rate": 4.1474667168657556e-05,
|
| 36913 |
+
"loss": 0.9102,
|
| 36914 |
+
"step": 5272
|
| 36915 |
+
},
|
| 36916 |
+
{
|
| 36917 |
+
"epoch": 6.005698005698005,
|
| 36918 |
+
"grad_norm": 0.17683662474155426,
|
| 36919 |
+
"learning_rate": 4.147116245803844e-05,
|
| 36920 |
+
"loss": 0.8387,
|
| 36921 |
+
"step": 5273
|
| 36922 |
+
},
|
| 36923 |
+
{
|
| 36924 |
+
"epoch": 6.006837606837607,
|
| 36925 |
+
"grad_norm": 0.14864976704120636,
|
| 36926 |
+
"learning_rate": 4.146765717533054e-05,
|
| 36927 |
+
"loss": 0.9381,
|
| 36928 |
+
"step": 5274
|
| 36929 |
+
},
|
| 36930 |
+
{
|
| 36931 |
+
"epoch": 6.007977207977208,
|
| 36932 |
+
"grad_norm": 0.1777380406856537,
|
| 36933 |
+
"learning_rate": 4.146415132065564e-05,
|
| 36934 |
+
"loss": 0.8416,
|
| 36935 |
+
"step": 5275
|
| 36936 |
+
},
|
| 36937 |
+
{
|
| 36938 |
+
"epoch": 6.009116809116809,
|
| 36939 |
+
"grad_norm": 0.17405077815055847,
|
| 36940 |
+
"learning_rate": 4.146064489413548e-05,
|
| 36941 |
+
"loss": 0.6389,
|
| 36942 |
+
"step": 5276
|
| 36943 |
+
},
|
| 36944 |
+
{
|
| 36945 |
+
"epoch": 6.01025641025641,
|
| 36946 |
+
"grad_norm": 0.1455533653497696,
|
| 36947 |
+
"learning_rate": 4.145713789589185e-05,
|
| 36948 |
+
"loss": 0.8916,
|
| 36949 |
+
"step": 5277
|
| 36950 |
+
},
|
| 36951 |
+
{
|
| 36952 |
+
"epoch": 6.011396011396012,
|
| 36953 |
+
"grad_norm": 0.15930397808551788,
|
| 36954 |
+
"learning_rate": 4.145363032604658e-05,
|
| 36955 |
+
"loss": 0.8626,
|
| 36956 |
+
"step": 5278
|
| 36957 |
+
},
|
| 36958 |
+
{
|
| 36959 |
+
"epoch": 6.012535612535612,
|
| 36960 |
+
"grad_norm": 0.19944411516189575,
|
| 36961 |
+
"learning_rate": 4.1450122184721465e-05,
|
| 36962 |
+
"loss": 0.6064,
|
| 36963 |
+
"step": 5279
|
| 36964 |
+
},
|
| 36965 |
+
{
|
| 36966 |
+
"epoch": 6.013675213675214,
|
| 36967 |
+
"grad_norm": 0.20567545294761658,
|
| 36968 |
+
"learning_rate": 4.1446613472038376e-05,
|
| 36969 |
+
"loss": 0.632,
|
| 36970 |
+
"step": 5280
|
| 36971 |
+
},
|
| 36972 |
+
{
|
| 36973 |
+
"epoch": 6.014814814814815,
|
| 36974 |
+
"grad_norm": 0.1783902496099472,
|
| 36975 |
+
"learning_rate": 4.144310418811917e-05,
|
| 36976 |
+
"loss": 0.8538,
|
| 36977 |
+
"step": 5281
|
| 36978 |
+
},
|
| 36979 |
+
{
|
| 36980 |
+
"epoch": 6.015954415954416,
|
| 36981 |
+
"grad_norm": 0.17142640054225922,
|
| 36982 |
+
"learning_rate": 4.143959433308574e-05,
|
| 36983 |
+
"loss": 0.76,
|
| 36984 |
+
"step": 5282
|
| 36985 |
+
},
|
| 36986 |
+
{
|
| 36987 |
+
"epoch": 6.017094017094017,
|
| 36988 |
+
"grad_norm": 0.1823304146528244,
|
| 36989 |
+
"learning_rate": 4.1436083907059985e-05,
|
| 36990 |
+
"loss": 0.8067,
|
| 36991 |
+
"step": 5283
|
| 36992 |
+
},
|
| 36993 |
+
{
|
| 36994 |
+
"epoch": 6.0182336182336185,
|
| 36995 |
+
"grad_norm": 0.18380099534988403,
|
| 36996 |
+
"learning_rate": 4.143257291016385e-05,
|
| 36997 |
+
"loss": 0.6778,
|
| 36998 |
+
"step": 5284
|
| 36999 |
+
},
|
| 37000 |
+
{
|
| 37001 |
+
"epoch": 6.019373219373219,
|
| 37002 |
+
"grad_norm": 0.1562369167804718,
|
| 37003 |
+
"learning_rate": 4.1429061342519246e-05,
|
| 37004 |
+
"loss": 0.9111,
|
| 37005 |
+
"step": 5285
|
| 37006 |
+
},
|
| 37007 |
+
{
|
| 37008 |
+
"epoch": 6.02051282051282,
|
| 37009 |
+
"grad_norm": 0.18521913886070251,
|
| 37010 |
+
"learning_rate": 4.142554920424818e-05,
|
| 37011 |
+
"loss": 0.7249,
|
| 37012 |
+
"step": 5286
|
| 37013 |
+
},
|
| 37014 |
+
{
|
| 37015 |
+
"epoch": 6.021652421652422,
|
| 37016 |
+
"grad_norm": 0.22115492820739746,
|
| 37017 |
+
"learning_rate": 4.142203649547261e-05,
|
| 37018 |
+
"loss": 0.6986,
|
| 37019 |
+
"step": 5287
|
| 37020 |
+
},
|
| 37021 |
+
{
|
| 37022 |
+
"epoch": 6.022792022792022,
|
| 37023 |
+
"grad_norm": 0.18572677671909332,
|
| 37024 |
+
"learning_rate": 4.1418523216314555e-05,
|
| 37025 |
+
"loss": 0.6859,
|
| 37026 |
+
"step": 5288
|
| 37027 |
+
},
|
| 37028 |
+
{
|
| 37029 |
+
"epoch": 6.023931623931624,
|
| 37030 |
+
"grad_norm": 0.19951315224170685,
|
| 37031 |
+
"learning_rate": 4.141500936689604e-05,
|
| 37032 |
+
"loss": 0.578,
|
| 37033 |
+
"step": 5289
|
| 37034 |
+
},
|
| 37035 |
+
{
|
| 37036 |
+
"epoch": 6.025071225071225,
|
| 37037 |
+
"grad_norm": 0.16582657396793365,
|
| 37038 |
+
"learning_rate": 4.14114949473391e-05,
|
| 37039 |
+
"loss": 0.7907,
|
| 37040 |
+
"step": 5290
|
| 37041 |
+
},
|
| 37042 |
+
{
|
| 37043 |
+
"epoch": 6.026210826210826,
|
| 37044 |
+
"grad_norm": 0.17808274924755096,
|
| 37045 |
+
"learning_rate": 4.140797995776582e-05,
|
| 37046 |
+
"loss": 0.8106,
|
| 37047 |
+
"step": 5291
|
| 37048 |
+
},
|
| 37049 |
+
{
|
| 37050 |
+
"epoch": 6.027350427350427,
|
| 37051 |
+
"grad_norm": 0.18221062421798706,
|
| 37052 |
+
"learning_rate": 4.1404464398298264e-05,
|
| 37053 |
+
"loss": 0.6451,
|
| 37054 |
+
"step": 5292
|
| 37055 |
+
},
|
| 37056 |
+
{
|
| 37057 |
+
"epoch": 6.028490028490029,
|
| 37058 |
+
"grad_norm": 0.1840764284133911,
|
| 37059 |
+
"learning_rate": 4.1400948269058555e-05,
|
| 37060 |
+
"loss": 0.7731,
|
| 37061 |
+
"step": 5293
|
| 37062 |
+
},
|
| 37063 |
+
{
|
| 37064 |
+
"epoch": 6.029629629629629,
|
| 37065 |
+
"grad_norm": 0.14906363189220428,
|
| 37066 |
+
"learning_rate": 4.1397431570168806e-05,
|
| 37067 |
+
"loss": 0.8789,
|
| 37068 |
+
"step": 5294
|
| 37069 |
+
},
|
| 37070 |
+
{
|
| 37071 |
+
"epoch": 6.030769230769231,
|
| 37072 |
+
"grad_norm": 0.21626117825508118,
|
| 37073 |
+
"learning_rate": 4.1393914301751166e-05,
|
| 37074 |
+
"loss": 0.7083,
|
| 37075 |
+
"step": 5295
|
| 37076 |
+
},
|
| 37077 |
+
{
|
| 37078 |
+
"epoch": 6.031908831908832,
|
| 37079 |
+
"grad_norm": 0.17459997534751892,
|
| 37080 |
+
"learning_rate": 4.13903964639278e-05,
|
| 37081 |
+
"loss": 0.8056,
|
| 37082 |
+
"step": 5296
|
| 37083 |
+
},
|
| 37084 |
+
{
|
| 37085 |
+
"epoch": 6.033048433048433,
|
| 37086 |
+
"grad_norm": 0.19678983092308044,
|
| 37087 |
+
"learning_rate": 4.138687805682089e-05,
|
| 37088 |
+
"loss": 0.7631,
|
| 37089 |
+
"step": 5297
|
| 37090 |
+
},
|
| 37091 |
+
{
|
| 37092 |
+
"epoch": 6.034188034188034,
|
| 37093 |
+
"grad_norm": 0.18847918510437012,
|
| 37094 |
+
"learning_rate": 4.138335908055264e-05,
|
| 37095 |
+
"loss": 0.6923,
|
| 37096 |
+
"step": 5298
|
| 37097 |
+
},
|
| 37098 |
+
{
|
| 37099 |
+
"epoch": 6.0353276353276355,
|
| 37100 |
+
"grad_norm": 0.20920641720294952,
|
| 37101 |
+
"learning_rate": 4.137983953524527e-05,
|
| 37102 |
+
"loss": 0.6162,
|
| 37103 |
+
"step": 5299
|
| 37104 |
+
},
|
| 37105 |
+
{
|
| 37106 |
+
"epoch": 6.036467236467236,
|
| 37107 |
+
"grad_norm": 0.17030276358127594,
|
| 37108 |
+
"learning_rate": 4.137631942102104e-05,
|
| 37109 |
+
"loss": 0.8526,
|
| 37110 |
+
"step": 5300
|
| 37111 |
+
},
|
| 37112 |
+
{
|
| 37113 |
+
"epoch": 6.0376068376068375,
|
| 37114 |
+
"grad_norm": 0.16370107233524323,
|
| 37115 |
+
"learning_rate": 4.137279873800219e-05,
|
| 37116 |
+
"loss": 0.6122,
|
| 37117 |
+
"step": 5301
|
| 37118 |
+
},
|
| 37119 |
+
{
|
| 37120 |
+
"epoch": 6.038746438746439,
|
| 37121 |
+
"grad_norm": 0.20291702449321747,
|
| 37122 |
+
"learning_rate": 4.136927748631102e-05,
|
| 37123 |
+
"loss": 0.749,
|
| 37124 |
+
"step": 5302
|
| 37125 |
+
},
|
| 37126 |
+
{
|
| 37127 |
+
"epoch": 6.0398860398860394,
|
| 37128 |
+
"grad_norm": 0.16677983105182648,
|
| 37129 |
+
"learning_rate": 4.136575566606982e-05,
|
| 37130 |
+
"loss": 0.9102,
|
| 37131 |
+
"step": 5303
|
| 37132 |
+
},
|
| 37133 |
+
{
|
| 37134 |
+
"epoch": 6.041025641025641,
|
| 37135 |
+
"grad_norm": 0.1749075949192047,
|
| 37136 |
+
"learning_rate": 4.136223327740093e-05,
|
| 37137 |
+
"loss": 0.7655,
|
| 37138 |
+
"step": 5304
|
| 37139 |
+
},
|
| 37140 |
+
{
|
| 37141 |
+
"epoch": 6.042165242165242,
|
| 37142 |
+
"grad_norm": 0.20569486916065216,
|
| 37143 |
+
"learning_rate": 4.135871032042668e-05,
|
| 37144 |
+
"loss": 0.6869,
|
| 37145 |
+
"step": 5305
|
| 37146 |
+
},
|
| 37147 |
+
{
|
| 37148 |
+
"epoch": 6.043304843304844,
|
| 37149 |
+
"grad_norm": 0.19171242415905,
|
| 37150 |
+
"learning_rate": 4.135518679526943e-05,
|
| 37151 |
+
"loss": 0.6695,
|
| 37152 |
+
"step": 5306
|
| 37153 |
+
},
|
| 37154 |
+
{
|
| 37155 |
+
"epoch": 6.044444444444444,
|
| 37156 |
+
"grad_norm": 0.16397686302661896,
|
| 37157 |
+
"learning_rate": 4.135166270205157e-05,
|
| 37158 |
+
"loss": 0.7385,
|
| 37159 |
+
"step": 5307
|
| 37160 |
+
},
|
| 37161 |
+
{
|
| 37162 |
+
"epoch": 6.045584045584046,
|
| 37163 |
+
"grad_norm": 0.21968406438827515,
|
| 37164 |
+
"learning_rate": 4.134813804089549e-05,
|
| 37165 |
+
"loss": 0.5997,
|
| 37166 |
+
"step": 5308
|
| 37167 |
+
},
|
| 37168 |
+
{
|
| 37169 |
+
"epoch": 6.046723646723647,
|
| 37170 |
+
"grad_norm": 0.15962359309196472,
|
| 37171 |
+
"learning_rate": 4.1344612811923625e-05,
|
| 37172 |
+
"loss": 0.926,
|
| 37173 |
+
"step": 5309
|
| 37174 |
+
},
|
| 37175 |
+
{
|
| 37176 |
+
"epoch": 6.047863247863248,
|
| 37177 |
+
"grad_norm": 0.1336166262626648,
|
| 37178 |
+
"learning_rate": 4.1341087015258405e-05,
|
| 37179 |
+
"loss": 1.0021,
|
| 37180 |
+
"step": 5310
|
| 37181 |
+
},
|
| 37182 |
+
{
|
| 37183 |
+
"epoch": 6.049002849002849,
|
| 37184 |
+
"grad_norm": 0.171193465590477,
|
| 37185 |
+
"learning_rate": 4.13375606510223e-05,
|
| 37186 |
+
"loss": 0.7357,
|
| 37187 |
+
"step": 5311
|
| 37188 |
+
},
|
| 37189 |
+
{
|
| 37190 |
+
"epoch": 6.050142450142451,
|
| 37191 |
+
"grad_norm": 0.1886366605758667,
|
| 37192 |
+
"learning_rate": 4.133403371933778e-05,
|
| 37193 |
+
"loss": 0.7643,
|
| 37194 |
+
"step": 5312
|
| 37195 |
+
},
|
| 37196 |
+
{
|
| 37197 |
+
"epoch": 6.051282051282051,
|
| 37198 |
+
"grad_norm": 0.17218226194381714,
|
| 37199 |
+
"learning_rate": 4.133050622032736e-05,
|
| 37200 |
+
"loss": 0.742,
|
| 37201 |
+
"step": 5313
|
| 37202 |
+
},
|
| 37203 |
+
{
|
| 37204 |
+
"epoch": 6.0524216524216525,
|
| 37205 |
+
"grad_norm": 0.15594317018985748,
|
| 37206 |
+
"learning_rate": 4.132697815411354e-05,
|
| 37207 |
+
"loss": 0.9512,
|
| 37208 |
+
"step": 5314
|
| 37209 |
+
},
|
| 37210 |
+
{
|
| 37211 |
+
"epoch": 6.053561253561254,
|
| 37212 |
+
"grad_norm": 0.14497053623199463,
|
| 37213 |
+
"learning_rate": 4.132344952081887e-05,
|
| 37214 |
+
"loss": 0.8102,
|
| 37215 |
+
"step": 5315
|
| 37216 |
+
},
|
| 37217 |
+
{
|
| 37218 |
+
"epoch": 6.0547008547008545,
|
| 37219 |
+
"grad_norm": 0.18346065282821655,
|
| 37220 |
+
"learning_rate": 4.1319920320565906e-05,
|
| 37221 |
+
"loss": 0.7741,
|
| 37222 |
+
"step": 5316
|
| 37223 |
+
},
|
| 37224 |
+
{
|
| 37225 |
+
"epoch": 6.055840455840456,
|
| 37226 |
+
"grad_norm": 0.15506385266780853,
|
| 37227 |
+
"learning_rate": 4.1316390553477236e-05,
|
| 37228 |
+
"loss": 0.726,
|
| 37229 |
+
"step": 5317
|
| 37230 |
+
},
|
| 37231 |
+
{
|
| 37232 |
+
"epoch": 6.056980056980057,
|
| 37233 |
+
"grad_norm": 0.20411111414432526,
|
| 37234 |
+
"learning_rate": 4.131286021967545e-05,
|
| 37235 |
+
"loss": 0.6767,
|
| 37236 |
+
"step": 5318
|
| 37237 |
+
},
|
| 37238 |
+
{
|
| 37239 |
+
"epoch": 6.058119658119658,
|
| 37240 |
+
"grad_norm": 0.16498993337154388,
|
| 37241 |
+
"learning_rate": 4.130932931928316e-05,
|
| 37242 |
+
"loss": 0.7701,
|
| 37243 |
+
"step": 5319
|
| 37244 |
+
},
|
| 37245 |
+
{
|
| 37246 |
+
"epoch": 6.059259259259259,
|
| 37247 |
+
"grad_norm": 0.19005899131298065,
|
| 37248 |
+
"learning_rate": 4.130579785242302e-05,
|
| 37249 |
+
"loss": 0.8537,
|
| 37250 |
+
"step": 5320
|
| 37251 |
+
},
|
| 37252 |
+
{
|
| 37253 |
+
"epoch": 6.060398860398861,
|
| 37254 |
+
"grad_norm": 0.15106602013111115,
|
| 37255 |
+
"learning_rate": 4.130226581921768e-05,
|
| 37256 |
+
"loss": 0.8611,
|
| 37257 |
+
"step": 5321
|
| 37258 |
+
},
|
| 37259 |
+
{
|
| 37260 |
+
"epoch": 6.061538461538461,
|
| 37261 |
+
"grad_norm": 0.1821715235710144,
|
| 37262 |
+
"learning_rate": 4.129873321978982e-05,
|
| 37263 |
+
"loss": 0.6789,
|
| 37264 |
+
"step": 5322
|
| 37265 |
+
},
|
| 37266 |
+
{
|
| 37267 |
+
"epoch": 6.062678062678063,
|
| 37268 |
+
"grad_norm": 0.15828917920589447,
|
| 37269 |
+
"learning_rate": 4.129520005426213e-05,
|
| 37270 |
+
"loss": 0.6968,
|
| 37271 |
+
"step": 5323
|
| 37272 |
+
},
|
| 37273 |
+
{
|
| 37274 |
+
"epoch": 6.063817663817664,
|
| 37275 |
+
"grad_norm": 0.15542666614055634,
|
| 37276 |
+
"learning_rate": 4.129166632275733e-05,
|
| 37277 |
+
"loss": 0.9701,
|
| 37278 |
+
"step": 5324
|
| 37279 |
+
},
|
| 37280 |
+
{
|
| 37281 |
+
"epoch": 6.064957264957265,
|
| 37282 |
+
"grad_norm": 0.19357499480247498,
|
| 37283 |
+
"learning_rate": 4.128813202539815e-05,
|
| 37284 |
+
"loss": 0.6658,
|
| 37285 |
+
"step": 5325
|
| 37286 |
+
},
|
| 37287 |
+
{
|
| 37288 |
+
"epoch": 6.066096866096866,
|
| 37289 |
+
"grad_norm": 0.2077610343694687,
|
| 37290 |
+
"learning_rate": 4.128459716230736e-05,
|
| 37291 |
+
"loss": 0.6631,
|
| 37292 |
+
"step": 5326
|
| 37293 |
+
},
|
| 37294 |
+
{
|
| 37295 |
+
"epoch": 6.067236467236468,
|
| 37296 |
+
"grad_norm": 0.14219580590724945,
|
| 37297 |
+
"learning_rate": 4.128106173360773e-05,
|
| 37298 |
+
"loss": 0.9613,
|
| 37299 |
+
"step": 5327
|
| 37300 |
+
},
|
| 37301 |
+
{
|
| 37302 |
+
"epoch": 6.068376068376068,
|
| 37303 |
+
"grad_norm": 0.17766830325126648,
|
| 37304 |
+
"learning_rate": 4.127752573942204e-05,
|
| 37305 |
+
"loss": 0.8159,
|
| 37306 |
+
"step": 5328
|
| 37307 |
+
},
|
| 37308 |
+
{
|
| 37309 |
+
"epoch": 6.06951566951567,
|
| 37310 |
+
"grad_norm": 0.16196675598621368,
|
| 37311 |
+
"learning_rate": 4.1273989179873126e-05,
|
| 37312 |
+
"loss": 0.8398,
|
| 37313 |
+
"step": 5329
|
| 37314 |
+
},
|
| 37315 |
+
{
|
| 37316 |
+
"epoch": 6.070655270655271,
|
| 37317 |
+
"grad_norm": 0.13799361884593964,
|
| 37318 |
+
"learning_rate": 4.127045205508382e-05,
|
| 37319 |
+
"loss": 0.9066,
|
| 37320 |
+
"step": 5330
|
| 37321 |
+
},
|
| 37322 |
+
{
|
| 37323 |
+
"epoch": 6.0717948717948715,
|
| 37324 |
+
"grad_norm": 0.16934914886951447,
|
| 37325 |
+
"learning_rate": 4.126691436517696e-05,
|
| 37326 |
+
"loss": 0.7317,
|
| 37327 |
+
"step": 5331
|
| 37328 |
+
},
|
| 37329 |
+
{
|
| 37330 |
+
"epoch": 6.072934472934473,
|
| 37331 |
+
"grad_norm": 0.16968083381652832,
|
| 37332 |
+
"learning_rate": 4.126337611027544e-05,
|
| 37333 |
+
"loss": 0.8202,
|
| 37334 |
+
"step": 5332
|
| 37335 |
+
},
|
| 37336 |
+
{
|
| 37337 |
+
"epoch": 6.074074074074074,
|
| 37338 |
+
"grad_norm": 0.17433682084083557,
|
| 37339 |
+
"learning_rate": 4.1259837290502135e-05,
|
| 37340 |
+
"loss": 0.7458,
|
| 37341 |
+
"step": 5333
|
| 37342 |
+
},
|
| 37343 |
+
{
|
| 37344 |
+
"epoch": 6.075213675213675,
|
| 37345 |
+
"grad_norm": 0.23448632657527924,
|
| 37346 |
+
"learning_rate": 4.125629790597997e-05,
|
| 37347 |
+
"loss": 0.565,
|
| 37348 |
+
"step": 5334
|
| 37349 |
+
},
|
| 37350 |
+
{
|
| 37351 |
+
"epoch": 6.076353276353276,
|
| 37352 |
+
"grad_norm": 0.18482531607151031,
|
| 37353 |
+
"learning_rate": 4.125275795683187e-05,
|
| 37354 |
+
"loss": 0.723,
|
| 37355 |
+
"step": 5335
|
| 37356 |
+
},
|
| 37357 |
+
{
|
| 37358 |
+
"epoch": 6.077492877492878,
|
| 37359 |
+
"grad_norm": 0.17934885621070862,
|
| 37360 |
+
"learning_rate": 4.1249217443180795e-05,
|
| 37361 |
+
"loss": 0.7322,
|
| 37362 |
+
"step": 5336
|
| 37363 |
+
},
|
| 37364 |
+
{
|
| 37365 |
+
"epoch": 6.078632478632478,
|
| 37366 |
+
"grad_norm": 0.2015325129032135,
|
| 37367 |
+
"learning_rate": 4.124567636514971e-05,
|
| 37368 |
+
"loss": 0.6252,
|
| 37369 |
+
"step": 5337
|
| 37370 |
+
},
|
| 37371 |
+
{
|
| 37372 |
+
"epoch": 6.07977207977208,
|
| 37373 |
+
"grad_norm": 0.2114899903535843,
|
| 37374 |
+
"learning_rate": 4.1242134722861606e-05,
|
| 37375 |
+
"loss": 0.7364,
|
| 37376 |
+
"step": 5338
|
| 37377 |
+
},
|
| 37378 |
+
{
|
| 37379 |
+
"epoch": 6.080911680911681,
|
| 37380 |
+
"grad_norm": 0.15407277643680573,
|
| 37381 |
+
"learning_rate": 4.1238592516439505e-05,
|
| 37382 |
+
"loss": 0.9147,
|
| 37383 |
+
"step": 5339
|
| 37384 |
+
},
|
| 37385 |
+
{
|
| 37386 |
+
"epoch": 6.082051282051282,
|
| 37387 |
+
"grad_norm": 0.1575423777103424,
|
| 37388 |
+
"learning_rate": 4.123504974600643e-05,
|
| 37389 |
+
"loss": 0.7913,
|
| 37390 |
+
"step": 5340
|
| 37391 |
+
},
|
| 37392 |
+
{
|
| 37393 |
+
"epoch": 6.083190883190883,
|
| 37394 |
+
"grad_norm": 0.1540532261133194,
|
| 37395 |
+
"learning_rate": 4.123150641168542e-05,
|
| 37396 |
+
"loss": 0.8318,
|
| 37397 |
+
"step": 5341
|
| 37398 |
+
},
|
| 37399 |
+
{
|
| 37400 |
+
"epoch": 6.084330484330485,
|
| 37401 |
+
"grad_norm": 0.16054439544677734,
|
| 37402 |
+
"learning_rate": 4.122796251359956e-05,
|
| 37403 |
+
"loss": 0.7438,
|
| 37404 |
+
"step": 5342
|
| 37405 |
+
},
|
| 37406 |
+
{
|
| 37407 |
+
"epoch": 6.085470085470085,
|
| 37408 |
+
"grad_norm": 0.1887817233800888,
|
| 37409 |
+
"learning_rate": 4.122441805187194e-05,
|
| 37410 |
+
"loss": 0.7258,
|
| 37411 |
+
"step": 5343
|
| 37412 |
+
},
|
| 37413 |
+
{
|
| 37414 |
+
"epoch": 6.086609686609687,
|
| 37415 |
+
"grad_norm": 0.1544388383626938,
|
| 37416 |
+
"learning_rate": 4.1220873026625664e-05,
|
| 37417 |
+
"loss": 0.9499,
|
| 37418 |
+
"step": 5344
|
| 37419 |
+
},
|
| 37420 |
+
{
|
| 37421 |
+
"epoch": 6.087749287749288,
|
| 37422 |
+
"grad_norm": 0.15911957621574402,
|
| 37423 |
+
"learning_rate": 4.1217327437983854e-05,
|
| 37424 |
+
"loss": 0.8015,
|
| 37425 |
+
"step": 5345
|
| 37426 |
+
},
|
| 37427 |
+
{
|
| 37428 |
+
"epoch": 6.088888888888889,
|
| 37429 |
+
"grad_norm": 0.19378520548343658,
|
| 37430 |
+
"learning_rate": 4.121378128606967e-05,
|
| 37431 |
+
"loss": 0.7329,
|
| 37432 |
+
"step": 5346
|
| 37433 |
+
},
|
| 37434 |
+
{
|
| 37435 |
+
"epoch": 6.09002849002849,
|
| 37436 |
+
"grad_norm": 0.1973607987165451,
|
| 37437 |
+
"learning_rate": 4.121023457100627e-05,
|
| 37438 |
+
"loss": 0.8194,
|
| 37439 |
+
"step": 5347
|
| 37440 |
+
},
|
| 37441 |
+
{
|
| 37442 |
+
"epoch": 6.091168091168091,
|
| 37443 |
+
"grad_norm": 0.2163930982351303,
|
| 37444 |
+
"learning_rate": 4.1206687292916845e-05,
|
| 37445 |
+
"loss": 0.6304,
|
| 37446 |
+
"step": 5348
|
| 37447 |
+
},
|
| 37448 |
+
{
|
| 37449 |
+
"epoch": 6.092307692307692,
|
| 37450 |
+
"grad_norm": 0.1876726597547531,
|
| 37451 |
+
"learning_rate": 4.12031394519246e-05,
|
| 37452 |
+
"loss": 0.6908,
|
| 37453 |
+
"step": 5349
|
| 37454 |
+
},
|
| 37455 |
+
{
|
| 37456 |
+
"epoch": 6.093447293447293,
|
| 37457 |
+
"grad_norm": 0.16954608261585236,
|
| 37458 |
+
"learning_rate": 4.1199591048152766e-05,
|
| 37459 |
+
"loss": 0.9084,
|
| 37460 |
+
"step": 5350
|
| 37461 |
+
},
|
| 37462 |
+
{
|
| 37463 |
+
"epoch": 6.094586894586895,
|
| 37464 |
+
"grad_norm": 0.14664937555789948,
|
| 37465 |
+
"learning_rate": 4.119604208172458e-05,
|
| 37466 |
+
"loss": 0.9353,
|
| 37467 |
+
"step": 5351
|
| 37468 |
+
},
|
| 37469 |
+
{
|
| 37470 |
+
"epoch": 6.095726495726495,
|
| 37471 |
+
"grad_norm": 0.17605088651180267,
|
| 37472 |
+
"learning_rate": 4.119249255276332e-05,
|
| 37473 |
+
"loss": 0.859,
|
| 37474 |
+
"step": 5352
|
| 37475 |
+
},
|
| 37476 |
+
{
|
| 37477 |
+
"epoch": 6.096866096866097,
|
| 37478 |
+
"grad_norm": 0.15377052128314972,
|
| 37479 |
+
"learning_rate": 4.1188942461392266e-05,
|
| 37480 |
+
"loss": 0.8562,
|
| 37481 |
+
"step": 5353
|
| 37482 |
+
},
|
| 37483 |
+
{
|
| 37484 |
+
"epoch": 6.098005698005698,
|
| 37485 |
+
"grad_norm": 0.17394904792308807,
|
| 37486 |
+
"learning_rate": 4.118539180773472e-05,
|
| 37487 |
+
"loss": 0.8247,
|
| 37488 |
+
"step": 5354
|
| 37489 |
+
},
|
| 37490 |
+
{
|
| 37491 |
+
"epoch": 6.099145299145299,
|
| 37492 |
+
"grad_norm": 0.16856645047664642,
|
| 37493 |
+
"learning_rate": 4.1181840591914e-05,
|
| 37494 |
+
"loss": 0.8811,
|
| 37495 |
+
"step": 5355
|
| 37496 |
+
},
|
| 37497 |
+
{
|
| 37498 |
+
"epoch": 6.1002849002849,
|
| 37499 |
+
"grad_norm": 0.2298177182674408,
|
| 37500 |
+
"learning_rate": 4.117828881405346e-05,
|
| 37501 |
+
"loss": 0.6079,
|
| 37502 |
+
"step": 5356
|
| 37503 |
+
},
|
| 37504 |
+
{
|
| 37505 |
+
"epoch": 6.101424501424502,
|
| 37506 |
+
"grad_norm": 0.21722614765167236,
|
| 37507 |
+
"learning_rate": 4.1174736474276464e-05,
|
| 37508 |
+
"loss": 0.6172,
|
| 37509 |
+
"step": 5357
|
| 37510 |
+
},
|
| 37511 |
+
{
|
| 37512 |
+
"epoch": 6.102564102564102,
|
| 37513 |
+
"grad_norm": 0.14236940443515778,
|
| 37514 |
+
"learning_rate": 4.117118357270638e-05,
|
| 37515 |
+
"loss": 0.9813,
|
| 37516 |
+
"step": 5358
|
| 37517 |
+
},
|
| 37518 |
+
{
|
| 37519 |
+
"epoch": 6.103703703703704,
|
| 37520 |
+
"grad_norm": 0.16800394654273987,
|
| 37521 |
+
"learning_rate": 4.1167630109466626e-05,
|
| 37522 |
+
"loss": 0.6162,
|
| 37523 |
+
"step": 5359
|
| 37524 |
+
},
|
| 37525 |
+
{
|
| 37526 |
+
"epoch": 6.104843304843305,
|
| 37527 |
+
"grad_norm": 0.1543532907962799,
|
| 37528 |
+
"learning_rate": 4.116407608468062e-05,
|
| 37529 |
+
"loss": 0.859,
|
| 37530 |
+
"step": 5360
|
| 37531 |
+
},
|
| 37532 |
+
{
|
| 37533 |
+
"epoch": 6.105982905982906,
|
| 37534 |
+
"grad_norm": 0.20111872255802155,
|
| 37535 |
+
"learning_rate": 4.116052149847179e-05,
|
| 37536 |
+
"loss": 0.594,
|
| 37537 |
+
"step": 5361
|
| 37538 |
+
},
|
| 37539 |
+
{
|
| 37540 |
+
"epoch": 6.107122507122507,
|
| 37541 |
+
"grad_norm": 0.19053106009960175,
|
| 37542 |
+
"learning_rate": 4.115696635096361e-05,
|
| 37543 |
+
"loss": 0.7708,
|
| 37544 |
+
"step": 5362
|
| 37545 |
+
},
|
| 37546 |
+
{
|
| 37547 |
+
"epoch": 6.1082621082621085,
|
| 37548 |
+
"grad_norm": 0.18006569147109985,
|
| 37549 |
+
"learning_rate": 4.115341064227956e-05,
|
| 37550 |
+
"loss": 0.8295,
|
| 37551 |
+
"step": 5363
|
| 37552 |
+
},
|
| 37553 |
+
{
|
| 37554 |
+
"epoch": 6.109401709401709,
|
| 37555 |
+
"grad_norm": 0.15343549847602844,
|
| 37556 |
+
"learning_rate": 4.114985437254314e-05,
|
| 37557 |
+
"loss": 0.8868,
|
| 37558 |
+
"step": 5364
|
| 37559 |
+
},
|
| 37560 |
+
{
|
| 37561 |
+
"epoch": 6.1105413105413104,
|
| 37562 |
+
"grad_norm": 0.16695021092891693,
|
| 37563 |
+
"learning_rate": 4.114629754187786e-05,
|
| 37564 |
+
"loss": 0.9424,
|
| 37565 |
+
"step": 5365
|
| 37566 |
+
},
|
| 37567 |
+
{
|
| 37568 |
+
"epoch": 6.111680911680912,
|
| 37569 |
+
"grad_norm": 0.19037920236587524,
|
| 37570 |
+
"learning_rate": 4.114274015040726e-05,
|
| 37571 |
+
"loss": 0.7676,
|
| 37572 |
+
"step": 5366
|
| 37573 |
+
},
|
| 37574 |
+
{
|
| 37575 |
+
"epoch": 6.112820512820512,
|
| 37576 |
+
"grad_norm": 0.16210995614528656,
|
| 37577 |
+
"learning_rate": 4.113918219825491e-05,
|
| 37578 |
+
"loss": 0.8741,
|
| 37579 |
+
"step": 5367
|
| 37580 |
+
},
|
| 37581 |
+
{
|
| 37582 |
+
"epoch": 6.113960113960114,
|
| 37583 |
+
"grad_norm": 0.20548321306705475,
|
| 37584 |
+
"learning_rate": 4.113562368554438e-05,
|
| 37585 |
+
"loss": 0.6218,
|
| 37586 |
+
"step": 5368
|
| 37587 |
+
},
|
| 37588 |
+
{
|
| 37589 |
+
"epoch": 6.115099715099715,
|
| 37590 |
+
"grad_norm": 0.19467325508594513,
|
| 37591 |
+
"learning_rate": 4.113206461239926e-05,
|
| 37592 |
+
"loss": 0.5885,
|
| 37593 |
+
"step": 5369
|
| 37594 |
+
},
|
| 37595 |
+
{
|
| 37596 |
+
"epoch": 6.116239316239316,
|
| 37597 |
+
"grad_norm": 0.2024887353181839,
|
| 37598 |
+
"learning_rate": 4.112850497894317e-05,
|
| 37599 |
+
"loss": 0.9011,
|
| 37600 |
+
"step": 5370
|
| 37601 |
+
},
|
| 37602 |
+
{
|
| 37603 |
+
"epoch": 6.117378917378917,
|
| 37604 |
+
"grad_norm": 0.18437287211418152,
|
| 37605 |
+
"learning_rate": 4.112494478529975e-05,
|
| 37606 |
+
"loss": 0.9799,
|
| 37607 |
+
"step": 5371
|
| 37608 |
+
},
|
| 37609 |
+
{
|
| 37610 |
+
"epoch": 6.118518518518519,
|
| 37611 |
+
"grad_norm": 0.17807888984680176,
|
| 37612 |
+
"learning_rate": 4.112138403159266e-05,
|
| 37613 |
+
"loss": 0.7263,
|
| 37614 |
+
"step": 5372
|
| 37615 |
+
},
|
| 37616 |
+
{
|
| 37617 |
+
"epoch": 6.119658119658119,
|
| 37618 |
+
"grad_norm": 0.19107209146022797,
|
| 37619 |
+
"learning_rate": 4.111782271794556e-05,
|
| 37620 |
+
"loss": 0.761,
|
| 37621 |
+
"step": 5373
|
| 37622 |
+
},
|
| 37623 |
+
{
|
| 37624 |
+
"epoch": 6.120797720797721,
|
| 37625 |
+
"grad_norm": 0.1876402199268341,
|
| 37626 |
+
"learning_rate": 4.111426084448217e-05,
|
| 37627 |
+
"loss": 0.7739,
|
| 37628 |
+
"step": 5374
|
| 37629 |
+
},
|
| 37630 |
+
{
|
| 37631 |
+
"epoch": 6.121937321937322,
|
| 37632 |
+
"grad_norm": 0.17592483758926392,
|
| 37633 |
+
"learning_rate": 4.111069841132617e-05,
|
| 37634 |
+
"loss": 0.8204,
|
| 37635 |
+
"step": 5375
|
| 37636 |
+
},
|
| 37637 |
+
{
|
| 37638 |
+
"epoch": 6.123076923076923,
|
| 37639 |
+
"grad_norm": 0.18379825353622437,
|
| 37640 |
+
"learning_rate": 4.110713541860132e-05,
|
| 37641 |
+
"loss": 0.7587,
|
| 37642 |
+
"step": 5376
|
| 37643 |
+
},
|
| 37644 |
+
{
|
| 37645 |
+
"epoch": 6.124216524216524,
|
| 37646 |
+
"grad_norm": 0.2072933465242386,
|
| 37647 |
+
"learning_rate": 4.110357186643135e-05,
|
| 37648 |
+
"loss": 0.713,
|
| 37649 |
+
"step": 5377
|
| 37650 |
+
},
|
| 37651 |
+
{
|
| 37652 |
+
"epoch": 6.1253561253561255,
|
| 37653 |
+
"grad_norm": 0.22593344748020172,
|
| 37654 |
+
"learning_rate": 4.110000775494005e-05,
|
| 37655 |
+
"loss": 0.74,
|
| 37656 |
+
"step": 5378
|
| 37657 |
+
},
|
| 37658 |
+
{
|
| 37659 |
+
"epoch": 6.126495726495726,
|
| 37660 |
+
"grad_norm": 0.156778022646904,
|
| 37661 |
+
"learning_rate": 4.109644308425121e-05,
|
| 37662 |
+
"loss": 0.8376,
|
| 37663 |
+
"step": 5379
|
| 37664 |
+
},
|
| 37665 |
+
{
|
| 37666 |
+
"epoch": 6.1276353276353275,
|
| 37667 |
+
"grad_norm": 0.20049187541007996,
|
| 37668 |
+
"learning_rate": 4.109287785448863e-05,
|
| 37669 |
+
"loss": 0.7331,
|
| 37670 |
+
"step": 5380
|
| 37671 |
+
},
|
| 37672 |
+
{
|
| 37673 |
+
"epoch": 6.128774928774929,
|
| 37674 |
+
"grad_norm": 0.1793132722377777,
|
| 37675 |
+
"learning_rate": 4.1089312065776146e-05,
|
| 37676 |
+
"loss": 0.8058,
|
| 37677 |
+
"step": 5381
|
| 37678 |
+
},
|
| 37679 |
+
{
|
| 37680 |
+
"epoch": 6.12991452991453,
|
| 37681 |
+
"grad_norm": 0.17604891955852509,
|
| 37682 |
+
"learning_rate": 4.108574571823761e-05,
|
| 37683 |
+
"loss": 0.633,
|
| 37684 |
+
"step": 5382
|
| 37685 |
+
},
|
| 37686 |
+
{
|
| 37687 |
+
"epoch": 6.131054131054131,
|
| 37688 |
+
"grad_norm": 0.16516968607902527,
|
| 37689 |
+
"learning_rate": 4.10821788119969e-05,
|
| 37690 |
+
"loss": 0.9,
|
| 37691 |
+
"step": 5383
|
| 37692 |
+
},
|
| 37693 |
+
{
|
| 37694 |
+
"epoch": 6.132193732193732,
|
| 37695 |
+
"grad_norm": 0.18298101425170898,
|
| 37696 |
+
"learning_rate": 4.107861134717788e-05,
|
| 37697 |
+
"loss": 0.6686,
|
| 37698 |
+
"step": 5384
|
| 37699 |
+
},
|
| 37700 |
+
{
|
| 37701 |
+
"epoch": 6.133333333333334,
|
| 37702 |
+
"grad_norm": 0.18403977155685425,
|
| 37703 |
+
"learning_rate": 4.107504332390447e-05,
|
| 37704 |
+
"loss": 0.6766,
|
| 37705 |
+
"step": 5385
|
| 37706 |
+
},
|
| 37707 |
+
{
|
| 37708 |
+
"epoch": 6.134472934472934,
|
| 37709 |
+
"grad_norm": 0.15163980424404144,
|
| 37710 |
+
"learning_rate": 4.107147474230061e-05,
|
| 37711 |
+
"loss": 0.934,
|
| 37712 |
+
"step": 5386
|
| 37713 |
+
},
|
| 37714 |
+
{
|
| 37715 |
+
"epoch": 6.135612535612536,
|
| 37716 |
+
"grad_norm": 0.1759641021490097,
|
| 37717 |
+
"learning_rate": 4.106790560249023e-05,
|
| 37718 |
+
"loss": 0.8518,
|
| 37719 |
+
"step": 5387
|
| 37720 |
+
},
|
| 37721 |
+
{
|
| 37722 |
+
"epoch": 6.136752136752137,
|
| 37723 |
+
"grad_norm": 0.15870292484760284,
|
| 37724 |
+
"learning_rate": 4.10643359045973e-05,
|
| 37725 |
+
"loss": 0.8359,
|
| 37726 |
+
"step": 5388
|
| 37727 |
+
},
|
| 37728 |
+
{
|
| 37729 |
+
"epoch": 6.137891737891738,
|
| 37730 |
+
"grad_norm": 0.17169325053691864,
|
| 37731 |
+
"learning_rate": 4.106076564874581e-05,
|
| 37732 |
+
"loss": 0.8743,
|
| 37733 |
+
"step": 5389
|
| 37734 |
+
},
|
| 37735 |
+
{
|
| 37736 |
+
"epoch": 6.139031339031339,
|
| 37737 |
+
"grad_norm": 0.19816268980503082,
|
| 37738 |
+
"learning_rate": 4.105719483505976e-05,
|
| 37739 |
+
"loss": 0.8448,
|
| 37740 |
+
"step": 5390
|
| 37741 |
+
},
|
| 37742 |
+
{
|
| 37743 |
+
"epoch": 6.140170940170941,
|
| 37744 |
+
"grad_norm": 0.1616421937942505,
|
| 37745 |
+
"learning_rate": 4.105362346366317e-05,
|
| 37746 |
+
"loss": 0.8303,
|
| 37747 |
+
"step": 5391
|
| 37748 |
+
},
|
| 37749 |
+
{
|
| 37750 |
+
"epoch": 6.141310541310541,
|
| 37751 |
+
"grad_norm": 0.1825469583272934,
|
| 37752 |
+
"learning_rate": 4.10500515346801e-05,
|
| 37753 |
+
"loss": 0.8529,
|
| 37754 |
+
"step": 5392
|
| 37755 |
+
},
|
| 37756 |
+
{
|
| 37757 |
+
"epoch": 6.1424501424501425,
|
| 37758 |
+
"grad_norm": 0.1738435924053192,
|
| 37759 |
+
"learning_rate": 4.10464790482346e-05,
|
| 37760 |
+
"loss": 0.7349,
|
| 37761 |
+
"step": 5393
|
| 37762 |
+
},
|
| 37763 |
+
{
|
| 37764 |
+
"epoch": 6.143589743589744,
|
| 37765 |
+
"grad_norm": 0.15835785865783691,
|
| 37766 |
+
"learning_rate": 4.1042906004450754e-05,
|
| 37767 |
+
"loss": 0.7235,
|
| 37768 |
+
"step": 5394
|
| 37769 |
+
},
|
| 37770 |
+
{
|
| 37771 |
+
"epoch": 6.1447293447293445,
|
| 37772 |
+
"grad_norm": 0.251121461391449,
|
| 37773 |
+
"learning_rate": 4.103933240345266e-05,
|
| 37774 |
+
"loss": 0.6078,
|
| 37775 |
+
"step": 5395
|
| 37776 |
+
},
|
| 37777 |
+
{
|
| 37778 |
+
"epoch": 6.145868945868946,
|
| 37779 |
+
"grad_norm": 0.1763714998960495,
|
| 37780 |
+
"learning_rate": 4.1035758245364455e-05,
|
| 37781 |
+
"loss": 0.6898,
|
| 37782 |
+
"step": 5396
|
| 37783 |
+
},
|
| 37784 |
+
{
|
| 37785 |
+
"epoch": 6.147008547008547,
|
| 37786 |
+
"grad_norm": 0.17268727719783783,
|
| 37787 |
+
"learning_rate": 4.1032183530310256e-05,
|
| 37788 |
+
"loss": 0.7949,
|
| 37789 |
+
"step": 5397
|
| 37790 |
+
},
|
| 37791 |
+
{
|
| 37792 |
+
"epoch": 6.148148148148148,
|
| 37793 |
+
"grad_norm": 0.17881803214550018,
|
| 37794 |
+
"learning_rate": 4.102860825841423e-05,
|
| 37795 |
+
"loss": 0.7018,
|
| 37796 |
+
"step": 5398
|
| 37797 |
+
},
|
| 37798 |
+
{
|
| 37799 |
+
"epoch": 6.149287749287749,
|
| 37800 |
+
"grad_norm": 0.1909571886062622,
|
| 37801 |
+
"learning_rate": 4.102503242980057e-05,
|
| 37802 |
+
"loss": 0.8175,
|
| 37803 |
+
"step": 5399
|
| 37804 |
+
},
|
| 37805 |
+
{
|
| 37806 |
+
"epoch": 6.150427350427351,
|
| 37807 |
+
"grad_norm": 0.1631585657596588,
|
| 37808 |
+
"learning_rate": 4.1021456044593466e-05,
|
| 37809 |
+
"loss": 0.6682,
|
| 37810 |
+
"step": 5400
|
| 37811 |
}
|
| 37812 |
],
|
| 37813 |
"logging_steps": 1,
|
|
|
|
| 37827 |
"attributes": {}
|
| 37828 |
}
|
| 37829 |
},
|
| 37830 |
+
"total_flos": 3.019296425730048e+19,
|
| 37831 |
"train_batch_size": 8,
|
| 37832 |
"trial_name": null,
|
| 37833 |
"trial_params": null
|