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 7200, 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 sha256:4cb64c7db2f1579d57c1b1d9bacec5208a9f5b12f16d946c2ec45d357921d4c9
|
| 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:c159b733684422e1344e50f321df940cc20b30b7a3dff3642ec24da33d447aea
|
| 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 sha256:363c5df1543d2c82b2f13164f35bdd0367ceb32e7fa1b2f67c19df073a08b17b
|
| 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 sha256:7ae718034f418dc4aa7d81249fed5ba2707015aa8e3d4a15fac01041e9e995ad
|
| 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,
|
|
@@ -48308,6 +48308,2106 @@
|
|
| 48308 |
"learning_rate": 3.5104104654037106e-05,
|
| 48309 |
"loss": 0.6419,
|
| 48310 |
"step": 6900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48311 |
}
|
| 48312 |
],
|
| 48313 |
"logging_steps": 1,
|
|
@@ -48327,7 +50427,7 @@
|
|
| 48327 |
"attributes": {}
|
| 48328 |
}
|
| 48329 |
},
|
| 48330 |
-
"total_flos":
|
| 48331 |
"train_batch_size": 8,
|
| 48332 |
"trial_name": null,
|
| 48333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.2005698005698,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 48308 |
"learning_rate": 3.5104104654037106e-05,
|
| 48309 |
"loss": 0.6419,
|
| 48310 |
"step": 6900
|
| 48311 |
+
},
|
| 48312 |
+
{
|
| 48313 |
+
"epoch": 7.860398860398861,
|
| 48314 |
+
"grad_norm": 0.21475614607334137,
|
| 48315 |
+
"learning_rate": 3.509984278871826e-05,
|
| 48316 |
+
"loss": 0.7055,
|
| 48317 |
+
"step": 6901
|
| 48318 |
+
},
|
| 48319 |
+
{
|
| 48320 |
+
"epoch": 7.861538461538462,
|
| 48321 |
+
"grad_norm": 0.20276354253292084,
|
| 48322 |
+
"learning_rate": 3.50955805726041e-05,
|
| 48323 |
+
"loss": 0.7792,
|
| 48324 |
+
"step": 6902
|
| 48325 |
+
},
|
| 48326 |
+
{
|
| 48327 |
+
"epoch": 7.862678062678063,
|
| 48328 |
+
"grad_norm": 0.2001870721578598,
|
| 48329 |
+
"learning_rate": 3.509131800584267e-05,
|
| 48330 |
+
"loss": 0.7039,
|
| 48331 |
+
"step": 6903
|
| 48332 |
+
},
|
| 48333 |
+
{
|
| 48334 |
+
"epoch": 7.863817663817664,
|
| 48335 |
+
"grad_norm": 0.27086666226387024,
|
| 48336 |
+
"learning_rate": 3.5087055088581996e-05,
|
| 48337 |
+
"loss": 0.5863,
|
| 48338 |
+
"step": 6904
|
| 48339 |
+
},
|
| 48340 |
+
{
|
| 48341 |
+
"epoch": 7.864957264957265,
|
| 48342 |
+
"grad_norm": 0.18609215319156647,
|
| 48343 |
+
"learning_rate": 3.5082791820970175e-05,
|
| 48344 |
+
"loss": 0.766,
|
| 48345 |
+
"step": 6905
|
| 48346 |
+
},
|
| 48347 |
+
{
|
| 48348 |
+
"epoch": 7.866096866096866,
|
| 48349 |
+
"grad_norm": 0.20789191126823425,
|
| 48350 |
+
"learning_rate": 3.507852820315525e-05,
|
| 48351 |
+
"loss": 0.7687,
|
| 48352 |
+
"step": 6906
|
| 48353 |
+
},
|
| 48354 |
+
{
|
| 48355 |
+
"epoch": 7.867236467236467,
|
| 48356 |
+
"grad_norm": 0.20047178864479065,
|
| 48357 |
+
"learning_rate": 3.507426423528534e-05,
|
| 48358 |
+
"loss": 0.6216,
|
| 48359 |
+
"step": 6907
|
| 48360 |
+
},
|
| 48361 |
+
{
|
| 48362 |
+
"epoch": 7.868376068376069,
|
| 48363 |
+
"grad_norm": 0.16607266664505005,
|
| 48364 |
+
"learning_rate": 3.506999991750852e-05,
|
| 48365 |
+
"loss": 0.7783,
|
| 48366 |
+
"step": 6908
|
| 48367 |
+
},
|
| 48368 |
+
{
|
| 48369 |
+
"epoch": 7.869515669515669,
|
| 48370 |
+
"grad_norm": 0.17001698911190033,
|
| 48371 |
+
"learning_rate": 3.506573524997292e-05,
|
| 48372 |
+
"loss": 0.7621,
|
| 48373 |
+
"step": 6909
|
| 48374 |
+
},
|
| 48375 |
+
{
|
| 48376 |
+
"epoch": 7.870655270655271,
|
| 48377 |
+
"grad_norm": 0.23012277483940125,
|
| 48378 |
+
"learning_rate": 3.506147023282665e-05,
|
| 48379 |
+
"loss": 0.6566,
|
| 48380 |
+
"step": 6910
|
| 48381 |
+
},
|
| 48382 |
+
{
|
| 48383 |
+
"epoch": 7.871794871794872,
|
| 48384 |
+
"grad_norm": 0.20534779131412506,
|
| 48385 |
+
"learning_rate": 3.505720486621785e-05,
|
| 48386 |
+
"loss": 0.7052,
|
| 48387 |
+
"step": 6911
|
| 48388 |
+
},
|
| 48389 |
+
{
|
| 48390 |
+
"epoch": 7.872934472934473,
|
| 48391 |
+
"grad_norm": 0.15706349909305573,
|
| 48392 |
+
"learning_rate": 3.5052939150294664e-05,
|
| 48393 |
+
"loss": 0.9746,
|
| 48394 |
+
"step": 6912
|
| 48395 |
+
},
|
| 48396 |
+
{
|
| 48397 |
+
"epoch": 7.874074074074074,
|
| 48398 |
+
"grad_norm": 0.17365200817584991,
|
| 48399 |
+
"learning_rate": 3.5048673085205255e-05,
|
| 48400 |
+
"loss": 0.8463,
|
| 48401 |
+
"step": 6913
|
| 48402 |
+
},
|
| 48403 |
+
{
|
| 48404 |
+
"epoch": 7.875213675213676,
|
| 48405 |
+
"grad_norm": 0.18620894849300385,
|
| 48406 |
+
"learning_rate": 3.50444066710978e-05,
|
| 48407 |
+
"loss": 0.7948,
|
| 48408 |
+
"step": 6914
|
| 48409 |
+
},
|
| 48410 |
+
{
|
| 48411 |
+
"epoch": 7.876353276353276,
|
| 48412 |
+
"grad_norm": 0.1837530881166458,
|
| 48413 |
+
"learning_rate": 3.5040139908120466e-05,
|
| 48414 |
+
"loss": 0.6109,
|
| 48415 |
+
"step": 6915
|
| 48416 |
+
},
|
| 48417 |
+
{
|
| 48418 |
+
"epoch": 7.877492877492878,
|
| 48419 |
+
"grad_norm": 0.1721877157688141,
|
| 48420 |
+
"learning_rate": 3.503587279642148e-05,
|
| 48421 |
+
"loss": 0.9464,
|
| 48422 |
+
"step": 6916
|
| 48423 |
+
},
|
| 48424 |
+
{
|
| 48425 |
+
"epoch": 7.878632478632479,
|
| 48426 |
+
"grad_norm": 0.19873687624931335,
|
| 48427 |
+
"learning_rate": 3.503160533614903e-05,
|
| 48428 |
+
"loss": 0.7423,
|
| 48429 |
+
"step": 6917
|
| 48430 |
+
},
|
| 48431 |
+
{
|
| 48432 |
+
"epoch": 7.87977207977208,
|
| 48433 |
+
"grad_norm": 0.2068408578634262,
|
| 48434 |
+
"learning_rate": 3.502733752745133e-05,
|
| 48435 |
+
"loss": 0.6031,
|
| 48436 |
+
"step": 6918
|
| 48437 |
+
},
|
| 48438 |
+
{
|
| 48439 |
+
"epoch": 7.880911680911681,
|
| 48440 |
+
"grad_norm": 0.21217504143714905,
|
| 48441 |
+
"learning_rate": 3.502306937047663e-05,
|
| 48442 |
+
"loss": 0.7438,
|
| 48443 |
+
"step": 6919
|
| 48444 |
+
},
|
| 48445 |
+
{
|
| 48446 |
+
"epoch": 7.8820512820512825,
|
| 48447 |
+
"grad_norm": 0.17609016597270966,
|
| 48448 |
+
"learning_rate": 3.5018800865373166e-05,
|
| 48449 |
+
"loss": 0.7646,
|
| 48450 |
+
"step": 6920
|
| 48451 |
+
},
|
| 48452 |
+
{
|
| 48453 |
+
"epoch": 7.883190883190883,
|
| 48454 |
+
"grad_norm": 0.2181202918291092,
|
| 48455 |
+
"learning_rate": 3.50145320122892e-05,
|
| 48456 |
+
"loss": 0.81,
|
| 48457 |
+
"step": 6921
|
| 48458 |
+
},
|
| 48459 |
+
{
|
| 48460 |
+
"epoch": 7.8843304843304844,
|
| 48461 |
+
"grad_norm": 0.2040448784828186,
|
| 48462 |
+
"learning_rate": 3.5010262811372984e-05,
|
| 48463 |
+
"loss": 0.8014,
|
| 48464 |
+
"step": 6922
|
| 48465 |
+
},
|
| 48466 |
+
{
|
| 48467 |
+
"epoch": 7.885470085470086,
|
| 48468 |
+
"grad_norm": 0.21069930493831635,
|
| 48469 |
+
"learning_rate": 3.5005993262772826e-05,
|
| 48470 |
+
"loss": 0.7258,
|
| 48471 |
+
"step": 6923
|
| 48472 |
+
},
|
| 48473 |
+
{
|
| 48474 |
+
"epoch": 7.886609686609686,
|
| 48475 |
+
"grad_norm": 0.2277589589357376,
|
| 48476 |
+
"learning_rate": 3.5001723366637e-05,
|
| 48477 |
+
"loss": 0.5516,
|
| 48478 |
+
"step": 6924
|
| 48479 |
+
},
|
| 48480 |
+
{
|
| 48481 |
+
"epoch": 7.887749287749288,
|
| 48482 |
+
"grad_norm": 0.24380171298980713,
|
| 48483 |
+
"learning_rate": 3.4997453123113816e-05,
|
| 48484 |
+
"loss": 0.6724,
|
| 48485 |
+
"step": 6925
|
| 48486 |
+
},
|
| 48487 |
+
{
|
| 48488 |
+
"epoch": 7.888888888888889,
|
| 48489 |
+
"grad_norm": 0.19442526996135712,
|
| 48490 |
+
"learning_rate": 3.499318253235159e-05,
|
| 48491 |
+
"loss": 0.7346,
|
| 48492 |
+
"step": 6926
|
| 48493 |
+
},
|
| 48494 |
+
{
|
| 48495 |
+
"epoch": 7.89002849002849,
|
| 48496 |
+
"grad_norm": 0.16563531756401062,
|
| 48497 |
+
"learning_rate": 3.4988911594498656e-05,
|
| 48498 |
+
"loss": 0.874,
|
| 48499 |
+
"step": 6927
|
| 48500 |
+
},
|
| 48501 |
+
{
|
| 48502 |
+
"epoch": 7.891168091168091,
|
| 48503 |
+
"grad_norm": 0.16393303871154785,
|
| 48504 |
+
"learning_rate": 3.498464030970335e-05,
|
| 48505 |
+
"loss": 0.7987,
|
| 48506 |
+
"step": 6928
|
| 48507 |
+
},
|
| 48508 |
+
{
|
| 48509 |
+
"epoch": 7.892307692307693,
|
| 48510 |
+
"grad_norm": 0.19510045647621155,
|
| 48511 |
+
"learning_rate": 3.498036867811404e-05,
|
| 48512 |
+
"loss": 0.8063,
|
| 48513 |
+
"step": 6929
|
| 48514 |
+
},
|
| 48515 |
+
{
|
| 48516 |
+
"epoch": 7.893447293447293,
|
| 48517 |
+
"grad_norm": 0.16404707729816437,
|
| 48518 |
+
"learning_rate": 3.4976096699879066e-05,
|
| 48519 |
+
"loss": 0.7595,
|
| 48520 |
+
"step": 6930
|
| 48521 |
+
},
|
| 48522 |
+
{
|
| 48523 |
+
"epoch": 7.894586894586895,
|
| 48524 |
+
"grad_norm": 0.21610978245735168,
|
| 48525 |
+
"learning_rate": 3.497182437514683e-05,
|
| 48526 |
+
"loss": 0.7916,
|
| 48527 |
+
"step": 6931
|
| 48528 |
+
},
|
| 48529 |
+
{
|
| 48530 |
+
"epoch": 7.895726495726496,
|
| 48531 |
+
"grad_norm": 0.22689557075500488,
|
| 48532 |
+
"learning_rate": 3.49675517040657e-05,
|
| 48533 |
+
"loss": 0.6256,
|
| 48534 |
+
"step": 6932
|
| 48535 |
+
},
|
| 48536 |
+
{
|
| 48537 |
+
"epoch": 7.896866096866097,
|
| 48538 |
+
"grad_norm": 0.1903616040945053,
|
| 48539 |
+
"learning_rate": 3.4963278686784096e-05,
|
| 48540 |
+
"loss": 0.6609,
|
| 48541 |
+
"step": 6933
|
| 48542 |
+
},
|
| 48543 |
+
{
|
| 48544 |
+
"epoch": 7.898005698005698,
|
| 48545 |
+
"grad_norm": 0.1872972548007965,
|
| 48546 |
+
"learning_rate": 3.4959005323450416e-05,
|
| 48547 |
+
"loss": 0.8125,
|
| 48548 |
+
"step": 6934
|
| 48549 |
+
},
|
| 48550 |
+
{
|
| 48551 |
+
"epoch": 7.8991452991452995,
|
| 48552 |
+
"grad_norm": 0.20764897763729095,
|
| 48553 |
+
"learning_rate": 3.4954731614213105e-05,
|
| 48554 |
+
"loss": 0.7985,
|
| 48555 |
+
"step": 6935
|
| 48556 |
+
},
|
| 48557 |
+
{
|
| 48558 |
+
"epoch": 7.9002849002849,
|
| 48559 |
+
"grad_norm": 0.17833660542964935,
|
| 48560 |
+
"learning_rate": 3.495045755922058e-05,
|
| 48561 |
+
"loss": 0.78,
|
| 48562 |
+
"step": 6936
|
| 48563 |
+
},
|
| 48564 |
+
{
|
| 48565 |
+
"epoch": 7.9014245014245015,
|
| 48566 |
+
"grad_norm": 0.30074813961982727,
|
| 48567 |
+
"learning_rate": 3.4946183158621306e-05,
|
| 48568 |
+
"loss": 0.777,
|
| 48569 |
+
"step": 6937
|
| 48570 |
+
},
|
| 48571 |
+
{
|
| 48572 |
+
"epoch": 7.902564102564103,
|
| 48573 |
+
"grad_norm": 0.21130868792533875,
|
| 48574 |
+
"learning_rate": 3.4941908412563735e-05,
|
| 48575 |
+
"loss": 0.6284,
|
| 48576 |
+
"step": 6938
|
| 48577 |
+
},
|
| 48578 |
+
{
|
| 48579 |
+
"epoch": 7.9037037037037035,
|
| 48580 |
+
"grad_norm": 0.19078730046749115,
|
| 48581 |
+
"learning_rate": 3.493763332119634e-05,
|
| 48582 |
+
"loss": 0.7542,
|
| 48583 |
+
"step": 6939
|
| 48584 |
+
},
|
| 48585 |
+
{
|
| 48586 |
+
"epoch": 7.904843304843305,
|
| 48587 |
+
"grad_norm": 0.22114410996437073,
|
| 48588 |
+
"learning_rate": 3.4933357884667626e-05,
|
| 48589 |
+
"loss": 0.593,
|
| 48590 |
+
"step": 6940
|
| 48591 |
+
},
|
| 48592 |
+
{
|
| 48593 |
+
"epoch": 7.905982905982906,
|
| 48594 |
+
"grad_norm": 0.27360519766807556,
|
| 48595 |
+
"learning_rate": 3.4929082103126066e-05,
|
| 48596 |
+
"loss": 0.5625,
|
| 48597 |
+
"step": 6941
|
| 48598 |
+
},
|
| 48599 |
+
{
|
| 48600 |
+
"epoch": 7.907122507122507,
|
| 48601 |
+
"grad_norm": 0.21668018400669098,
|
| 48602 |
+
"learning_rate": 3.4924805976720185e-05,
|
| 48603 |
+
"loss": 0.6908,
|
| 48604 |
+
"step": 6942
|
| 48605 |
+
},
|
| 48606 |
+
{
|
| 48607 |
+
"epoch": 7.908262108262108,
|
| 48608 |
+
"grad_norm": 0.1980413794517517,
|
| 48609 |
+
"learning_rate": 3.4920529505598484e-05,
|
| 48610 |
+
"loss": 0.6576,
|
| 48611 |
+
"step": 6943
|
| 48612 |
+
},
|
| 48613 |
+
{
|
| 48614 |
+
"epoch": 7.90940170940171,
|
| 48615 |
+
"grad_norm": 0.17020384967327118,
|
| 48616 |
+
"learning_rate": 3.4916252689909527e-05,
|
| 48617 |
+
"loss": 0.886,
|
| 48618 |
+
"step": 6944
|
| 48619 |
+
},
|
| 48620 |
+
{
|
| 48621 |
+
"epoch": 7.91054131054131,
|
| 48622 |
+
"grad_norm": 0.22337353229522705,
|
| 48623 |
+
"learning_rate": 3.491197552980184e-05,
|
| 48624 |
+
"loss": 0.7651,
|
| 48625 |
+
"step": 6945
|
| 48626 |
+
},
|
| 48627 |
+
{
|
| 48628 |
+
"epoch": 7.911680911680912,
|
| 48629 |
+
"grad_norm": 0.24993619322776794,
|
| 48630 |
+
"learning_rate": 3.4907698025423984e-05,
|
| 48631 |
+
"loss": 0.5218,
|
| 48632 |
+
"step": 6946
|
| 48633 |
+
},
|
| 48634 |
+
{
|
| 48635 |
+
"epoch": 7.912820512820513,
|
| 48636 |
+
"grad_norm": 0.18221551179885864,
|
| 48637 |
+
"learning_rate": 3.4903420176924525e-05,
|
| 48638 |
+
"loss": 0.8951,
|
| 48639 |
+
"step": 6947
|
| 48640 |
+
},
|
| 48641 |
+
{
|
| 48642 |
+
"epoch": 7.913960113960114,
|
| 48643 |
+
"grad_norm": 0.24022223055362701,
|
| 48644 |
+
"learning_rate": 3.489914198445206e-05,
|
| 48645 |
+
"loss": 0.5555,
|
| 48646 |
+
"step": 6948
|
| 48647 |
+
},
|
| 48648 |
+
{
|
| 48649 |
+
"epoch": 7.915099715099715,
|
| 48650 |
+
"grad_norm": 0.21565523743629456,
|
| 48651 |
+
"learning_rate": 3.489486344815516e-05,
|
| 48652 |
+
"loss": 0.7623,
|
| 48653 |
+
"step": 6949
|
| 48654 |
+
},
|
| 48655 |
+
{
|
| 48656 |
+
"epoch": 7.9162393162393165,
|
| 48657 |
+
"grad_norm": 0.19092397391796112,
|
| 48658 |
+
"learning_rate": 3.489058456818244e-05,
|
| 48659 |
+
"loss": 0.7738,
|
| 48660 |
+
"step": 6950
|
| 48661 |
+
},
|
| 48662 |
+
{
|
| 48663 |
+
"epoch": 7.917378917378917,
|
| 48664 |
+
"grad_norm": 0.2190237194299698,
|
| 48665 |
+
"learning_rate": 3.4886305344682526e-05,
|
| 48666 |
+
"loss": 0.7363,
|
| 48667 |
+
"step": 6951
|
| 48668 |
+
},
|
| 48669 |
+
{
|
| 48670 |
+
"epoch": 7.9185185185185185,
|
| 48671 |
+
"grad_norm": 0.19466805458068848,
|
| 48672 |
+
"learning_rate": 3.488202577780405e-05,
|
| 48673 |
+
"loss": 0.7224,
|
| 48674 |
+
"step": 6952
|
| 48675 |
+
},
|
| 48676 |
+
{
|
| 48677 |
+
"epoch": 7.91965811965812,
|
| 48678 |
+
"grad_norm": 0.2089778035879135,
|
| 48679 |
+
"learning_rate": 3.487774586769562e-05,
|
| 48680 |
+
"loss": 0.6605,
|
| 48681 |
+
"step": 6953
|
| 48682 |
+
},
|
| 48683 |
+
{
|
| 48684 |
+
"epoch": 7.9207977207977205,
|
| 48685 |
+
"grad_norm": 0.20725427567958832,
|
| 48686 |
+
"learning_rate": 3.487346561450593e-05,
|
| 48687 |
+
"loss": 0.7964,
|
| 48688 |
+
"step": 6954
|
| 48689 |
+
},
|
| 48690 |
+
{
|
| 48691 |
+
"epoch": 7.921937321937322,
|
| 48692 |
+
"grad_norm": 0.16331282258033752,
|
| 48693 |
+
"learning_rate": 3.4869185018383624e-05,
|
| 48694 |
+
"loss": 0.9115,
|
| 48695 |
+
"step": 6955
|
| 48696 |
+
},
|
| 48697 |
+
{
|
| 48698 |
+
"epoch": 7.923076923076923,
|
| 48699 |
+
"grad_norm": 0.18405237793922424,
|
| 48700 |
+
"learning_rate": 3.4864904079477376e-05,
|
| 48701 |
+
"loss": 0.8216,
|
| 48702 |
+
"step": 6956
|
| 48703 |
+
},
|
| 48704 |
+
{
|
| 48705 |
+
"epoch": 7.924216524216524,
|
| 48706 |
+
"grad_norm": 0.17434020340442657,
|
| 48707 |
+
"learning_rate": 3.4860622797935885e-05,
|
| 48708 |
+
"loss": 0.7459,
|
| 48709 |
+
"step": 6957
|
| 48710 |
+
},
|
| 48711 |
+
{
|
| 48712 |
+
"epoch": 7.925356125356125,
|
| 48713 |
+
"grad_norm": 0.2535775899887085,
|
| 48714 |
+
"learning_rate": 3.4856341173907844e-05,
|
| 48715 |
+
"loss": 0.4788,
|
| 48716 |
+
"step": 6958
|
| 48717 |
+
},
|
| 48718 |
+
{
|
| 48719 |
+
"epoch": 7.926495726495727,
|
| 48720 |
+
"grad_norm": 0.2321566939353943,
|
| 48721 |
+
"learning_rate": 3.485205920754198e-05,
|
| 48722 |
+
"loss": 0.5672,
|
| 48723 |
+
"step": 6959
|
| 48724 |
+
},
|
| 48725 |
+
{
|
| 48726 |
+
"epoch": 7.927635327635327,
|
| 48727 |
+
"grad_norm": 0.21712049841880798,
|
| 48728 |
+
"learning_rate": 3.484777689898698e-05,
|
| 48729 |
+
"loss": 0.5446,
|
| 48730 |
+
"step": 6960
|
| 48731 |
+
},
|
| 48732 |
+
{
|
| 48733 |
+
"epoch": 7.928774928774929,
|
| 48734 |
+
"grad_norm": 0.210310697555542,
|
| 48735 |
+
"learning_rate": 3.484349424839163e-05,
|
| 48736 |
+
"loss": 0.7157,
|
| 48737 |
+
"step": 6961
|
| 48738 |
+
},
|
| 48739 |
+
{
|
| 48740 |
+
"epoch": 7.92991452991453,
|
| 48741 |
+
"grad_norm": 0.18413089215755463,
|
| 48742 |
+
"learning_rate": 3.4839211255904646e-05,
|
| 48743 |
+
"loss": 0.8803,
|
| 48744 |
+
"step": 6962
|
| 48745 |
+
},
|
| 48746 |
+
{
|
| 48747 |
+
"epoch": 7.931054131054131,
|
| 48748 |
+
"grad_norm": 0.23209485411643982,
|
| 48749 |
+
"learning_rate": 3.4834927921674807e-05,
|
| 48750 |
+
"loss": 0.5997,
|
| 48751 |
+
"step": 6963
|
| 48752 |
+
},
|
| 48753 |
+
{
|
| 48754 |
+
"epoch": 7.932193732193732,
|
| 48755 |
+
"grad_norm": 0.16725648939609528,
|
| 48756 |
+
"learning_rate": 3.4830644245850864e-05,
|
| 48757 |
+
"loss": 0.943,
|
| 48758 |
+
"step": 6964
|
| 48759 |
+
},
|
| 48760 |
+
{
|
| 48761 |
+
"epoch": 7.933333333333334,
|
| 48762 |
+
"grad_norm": 0.23912696540355682,
|
| 48763 |
+
"learning_rate": 3.482636022858162e-05,
|
| 48764 |
+
"loss": 0.602,
|
| 48765 |
+
"step": 6965
|
| 48766 |
+
},
|
| 48767 |
+
{
|
| 48768 |
+
"epoch": 7.934472934472934,
|
| 48769 |
+
"grad_norm": 0.1723431497812271,
|
| 48770 |
+
"learning_rate": 3.482207587001585e-05,
|
| 48771 |
+
"loss": 0.8787,
|
| 48772 |
+
"step": 6966
|
| 48773 |
+
},
|
| 48774 |
+
{
|
| 48775 |
+
"epoch": 7.9356125356125355,
|
| 48776 |
+
"grad_norm": 0.20418599247932434,
|
| 48777 |
+
"learning_rate": 3.48177911703024e-05,
|
| 48778 |
+
"loss": 0.6305,
|
| 48779 |
+
"step": 6967
|
| 48780 |
+
},
|
| 48781 |
+
{
|
| 48782 |
+
"epoch": 7.936752136752137,
|
| 48783 |
+
"grad_norm": 0.19222919642925262,
|
| 48784 |
+
"learning_rate": 3.4813506129590035e-05,
|
| 48785 |
+
"loss": 0.8004,
|
| 48786 |
+
"step": 6968
|
| 48787 |
+
},
|
| 48788 |
+
{
|
| 48789 |
+
"epoch": 7.9378917378917375,
|
| 48790 |
+
"grad_norm": 0.1631591022014618,
|
| 48791 |
+
"learning_rate": 3.480922074802763e-05,
|
| 48792 |
+
"loss": 0.8736,
|
| 48793 |
+
"step": 6969
|
| 48794 |
+
},
|
| 48795 |
+
{
|
| 48796 |
+
"epoch": 7.939031339031339,
|
| 48797 |
+
"grad_norm": 0.20801420509815216,
|
| 48798 |
+
"learning_rate": 3.480493502576401e-05,
|
| 48799 |
+
"loss": 0.7844,
|
| 48800 |
+
"step": 6970
|
| 48801 |
+
},
|
| 48802 |
+
{
|
| 48803 |
+
"epoch": 7.94017094017094,
|
| 48804 |
+
"grad_norm": 0.18752451241016388,
|
| 48805 |
+
"learning_rate": 3.480064896294803e-05,
|
| 48806 |
+
"loss": 0.8168,
|
| 48807 |
+
"step": 6971
|
| 48808 |
+
},
|
| 48809 |
+
{
|
| 48810 |
+
"epoch": 7.941310541310541,
|
| 48811 |
+
"grad_norm": 0.20247039198875427,
|
| 48812 |
+
"learning_rate": 3.479636255972857e-05,
|
| 48813 |
+
"loss": 0.7284,
|
| 48814 |
+
"step": 6972
|
| 48815 |
+
},
|
| 48816 |
+
{
|
| 48817 |
+
"epoch": 7.942450142450142,
|
| 48818 |
+
"grad_norm": 0.16914136707782745,
|
| 48819 |
+
"learning_rate": 3.479207581625448e-05,
|
| 48820 |
+
"loss": 0.9514,
|
| 48821 |
+
"step": 6973
|
| 48822 |
+
},
|
| 48823 |
+
{
|
| 48824 |
+
"epoch": 7.943589743589744,
|
| 48825 |
+
"grad_norm": 0.19120515882968903,
|
| 48826 |
+
"learning_rate": 3.478778873267468e-05,
|
| 48827 |
+
"loss": 0.7901,
|
| 48828 |
+
"step": 6974
|
| 48829 |
+
},
|
| 48830 |
+
{
|
| 48831 |
+
"epoch": 7.944729344729344,
|
| 48832 |
+
"grad_norm": 0.17753508687019348,
|
| 48833 |
+
"learning_rate": 3.478350130913807e-05,
|
| 48834 |
+
"loss": 0.9008,
|
| 48835 |
+
"step": 6975
|
| 48836 |
+
},
|
| 48837 |
+
{
|
| 48838 |
+
"epoch": 7.945868945868946,
|
| 48839 |
+
"grad_norm": 0.14952565729618073,
|
| 48840 |
+
"learning_rate": 3.4779213545793536e-05,
|
| 48841 |
+
"loss": 0.872,
|
| 48842 |
+
"step": 6976
|
| 48843 |
+
},
|
| 48844 |
+
{
|
| 48845 |
+
"epoch": 7.947008547008547,
|
| 48846 |
+
"grad_norm": 0.22527769207954407,
|
| 48847 |
+
"learning_rate": 3.477492544279003e-05,
|
| 48848 |
+
"loss": 0.5966,
|
| 48849 |
+
"step": 6977
|
| 48850 |
+
},
|
| 48851 |
+
{
|
| 48852 |
+
"epoch": 7.948148148148148,
|
| 48853 |
+
"grad_norm": 0.20993876457214355,
|
| 48854 |
+
"learning_rate": 3.477063700027648e-05,
|
| 48855 |
+
"loss": 0.6283,
|
| 48856 |
+
"step": 6978
|
| 48857 |
+
},
|
| 48858 |
+
{
|
| 48859 |
+
"epoch": 7.949287749287749,
|
| 48860 |
+
"grad_norm": 0.19296513497829437,
|
| 48861 |
+
"learning_rate": 3.4766348218401846e-05,
|
| 48862 |
+
"loss": 0.791,
|
| 48863 |
+
"step": 6979
|
| 48864 |
+
},
|
| 48865 |
+
{
|
| 48866 |
+
"epoch": 7.950427350427351,
|
| 48867 |
+
"grad_norm": 0.18066520988941193,
|
| 48868 |
+
"learning_rate": 3.476205909731508e-05,
|
| 48869 |
+
"loss": 0.7611,
|
| 48870 |
+
"step": 6980
|
| 48871 |
+
},
|
| 48872 |
+
{
|
| 48873 |
+
"epoch": 7.951566951566951,
|
| 48874 |
+
"grad_norm": 0.2059728056192398,
|
| 48875 |
+
"learning_rate": 3.475776963716515e-05,
|
| 48876 |
+
"loss": 0.7608,
|
| 48877 |
+
"step": 6981
|
| 48878 |
+
},
|
| 48879 |
+
{
|
| 48880 |
+
"epoch": 7.952706552706553,
|
| 48881 |
+
"grad_norm": 0.18269841372966766,
|
| 48882 |
+
"learning_rate": 3.475347983810105e-05,
|
| 48883 |
+
"loss": 0.7013,
|
| 48884 |
+
"step": 6982
|
| 48885 |
+
},
|
| 48886 |
+
{
|
| 48887 |
+
"epoch": 7.953846153846154,
|
| 48888 |
+
"grad_norm": 0.2518905997276306,
|
| 48889 |
+
"learning_rate": 3.474918970027177e-05,
|
| 48890 |
+
"loss": 1.0275,
|
| 48891 |
+
"step": 6983
|
| 48892 |
+
},
|
| 48893 |
+
{
|
| 48894 |
+
"epoch": 7.9549857549857546,
|
| 48895 |
+
"grad_norm": 0.2201099395751953,
|
| 48896 |
+
"learning_rate": 3.474489922382632e-05,
|
| 48897 |
+
"loss": 0.7612,
|
| 48898 |
+
"step": 6984
|
| 48899 |
+
},
|
| 48900 |
+
{
|
| 48901 |
+
"epoch": 7.956125356125356,
|
| 48902 |
+
"grad_norm": 0.21568866074085236,
|
| 48903 |
+
"learning_rate": 3.474060840891372e-05,
|
| 48904 |
+
"loss": 0.7361,
|
| 48905 |
+
"step": 6985
|
| 48906 |
+
},
|
| 48907 |
+
{
|
| 48908 |
+
"epoch": 7.957264957264957,
|
| 48909 |
+
"grad_norm": 0.22379179298877716,
|
| 48910 |
+
"learning_rate": 3.4736317255683015e-05,
|
| 48911 |
+
"loss": 0.656,
|
| 48912 |
+
"step": 6986
|
| 48913 |
+
},
|
| 48914 |
+
{
|
| 48915 |
+
"epoch": 7.958404558404558,
|
| 48916 |
+
"grad_norm": 0.1808573603630066,
|
| 48917 |
+
"learning_rate": 3.473202576428323e-05,
|
| 48918 |
+
"loss": 0.7515,
|
| 48919 |
+
"step": 6987
|
| 48920 |
+
},
|
| 48921 |
+
{
|
| 48922 |
+
"epoch": 7.959544159544159,
|
| 48923 |
+
"grad_norm": 0.18532869219779968,
|
| 48924 |
+
"learning_rate": 3.472773393486342e-05,
|
| 48925 |
+
"loss": 0.7191,
|
| 48926 |
+
"step": 6988
|
| 48927 |
+
},
|
| 48928 |
+
{
|
| 48929 |
+
"epoch": 7.960683760683761,
|
| 48930 |
+
"grad_norm": 0.18520545959472656,
|
| 48931 |
+
"learning_rate": 3.472344176757267e-05,
|
| 48932 |
+
"loss": 0.9918,
|
| 48933 |
+
"step": 6989
|
| 48934 |
+
},
|
| 48935 |
+
{
|
| 48936 |
+
"epoch": 7.961823361823361,
|
| 48937 |
+
"grad_norm": 0.19397109746932983,
|
| 48938 |
+
"learning_rate": 3.471914926256004e-05,
|
| 48939 |
+
"loss": 0.758,
|
| 48940 |
+
"step": 6990
|
| 48941 |
+
},
|
| 48942 |
+
{
|
| 48943 |
+
"epoch": 7.962962962962963,
|
| 48944 |
+
"grad_norm": 0.24348177015781403,
|
| 48945 |
+
"learning_rate": 3.471485641997463e-05,
|
| 48946 |
+
"loss": 0.6164,
|
| 48947 |
+
"step": 6991
|
| 48948 |
+
},
|
| 48949 |
+
{
|
| 48950 |
+
"epoch": 7.964102564102564,
|
| 48951 |
+
"grad_norm": 0.41862666606903076,
|
| 48952 |
+
"learning_rate": 3.471056323996554e-05,
|
| 48953 |
+
"loss": 0.8977,
|
| 48954 |
+
"step": 6992
|
| 48955 |
+
},
|
| 48956 |
+
{
|
| 48957 |
+
"epoch": 7.965242165242165,
|
| 48958 |
+
"grad_norm": 0.18165546655654907,
|
| 48959 |
+
"learning_rate": 3.470626972268189e-05,
|
| 48960 |
+
"loss": 0.7355,
|
| 48961 |
+
"step": 6993
|
| 48962 |
+
},
|
| 48963 |
+
{
|
| 48964 |
+
"epoch": 7.966381766381766,
|
| 48965 |
+
"grad_norm": 0.19281134009361267,
|
| 48966 |
+
"learning_rate": 3.47019758682728e-05,
|
| 48967 |
+
"loss": 0.7676,
|
| 48968 |
+
"step": 6994
|
| 48969 |
+
},
|
| 48970 |
+
{
|
| 48971 |
+
"epoch": 7.967521367521368,
|
| 48972 |
+
"grad_norm": 0.21593524515628815,
|
| 48973 |
+
"learning_rate": 3.46976816768874e-05,
|
| 48974 |
+
"loss": 0.762,
|
| 48975 |
+
"step": 6995
|
| 48976 |
+
},
|
| 48977 |
+
{
|
| 48978 |
+
"epoch": 7.968660968660968,
|
| 48979 |
+
"grad_norm": 0.230185404419899,
|
| 48980 |
+
"learning_rate": 3.469338714867485e-05,
|
| 48981 |
+
"loss": 0.6806,
|
| 48982 |
+
"step": 6996
|
| 48983 |
+
},
|
| 48984 |
+
{
|
| 48985 |
+
"epoch": 7.96980056980057,
|
| 48986 |
+
"grad_norm": 0.17793694138526917,
|
| 48987 |
+
"learning_rate": 3.468909228378431e-05,
|
| 48988 |
+
"loss": 0.9328,
|
| 48989 |
+
"step": 6997
|
| 48990 |
+
},
|
| 48991 |
+
{
|
| 48992 |
+
"epoch": 7.970940170940171,
|
| 48993 |
+
"grad_norm": 0.17860686779022217,
|
| 48994 |
+
"learning_rate": 3.468479708236495e-05,
|
| 48995 |
+
"loss": 0.6889,
|
| 48996 |
+
"step": 6998
|
| 48997 |
+
},
|
| 48998 |
+
{
|
| 48999 |
+
"epoch": 7.972079772079772,
|
| 49000 |
+
"grad_norm": 0.2190643548965454,
|
| 49001 |
+
"learning_rate": 3.468050154456595e-05,
|
| 49002 |
+
"loss": 0.6826,
|
| 49003 |
+
"step": 6999
|
| 49004 |
+
},
|
| 49005 |
+
{
|
| 49006 |
+
"epoch": 7.973219373219373,
|
| 49007 |
+
"grad_norm": 0.19970053434371948,
|
| 49008 |
+
"learning_rate": 3.467620567053651e-05,
|
| 49009 |
+
"loss": 0.6507,
|
| 49010 |
+
"step": 7000
|
| 49011 |
+
},
|
| 49012 |
+
{
|
| 49013 |
+
"epoch": 7.9743589743589745,
|
| 49014 |
+
"grad_norm": 0.2116745263338089,
|
| 49015 |
+
"learning_rate": 3.467190946042584e-05,
|
| 49016 |
+
"loss": 0.8031,
|
| 49017 |
+
"step": 7001
|
| 49018 |
+
},
|
| 49019 |
+
{
|
| 49020 |
+
"epoch": 7.975498575498576,
|
| 49021 |
+
"grad_norm": 0.18867363035678864,
|
| 49022 |
+
"learning_rate": 3.466761291438315e-05,
|
| 49023 |
+
"loss": 0.7361,
|
| 49024 |
+
"step": 7002
|
| 49025 |
+
},
|
| 49026 |
+
{
|
| 49027 |
+
"epoch": 7.976638176638176,
|
| 49028 |
+
"grad_norm": 0.19578492641448975,
|
| 49029 |
+
"learning_rate": 3.466331603255769e-05,
|
| 49030 |
+
"loss": 0.8706,
|
| 49031 |
+
"step": 7003
|
| 49032 |
+
},
|
| 49033 |
+
{
|
| 49034 |
+
"epoch": 7.977777777777778,
|
| 49035 |
+
"grad_norm": 0.23488479852676392,
|
| 49036 |
+
"learning_rate": 3.4659018815098684e-05,
|
| 49037 |
+
"loss": 0.5953,
|
| 49038 |
+
"step": 7004
|
| 49039 |
+
},
|
| 49040 |
+
{
|
| 49041 |
+
"epoch": 7.978917378917379,
|
| 49042 |
+
"grad_norm": 0.20616556704044342,
|
| 49043 |
+
"learning_rate": 3.4654721262155385e-05,
|
| 49044 |
+
"loss": 0.6429,
|
| 49045 |
+
"step": 7005
|
| 49046 |
+
},
|
| 49047 |
+
{
|
| 49048 |
+
"epoch": 7.98005698005698,
|
| 49049 |
+
"grad_norm": 0.1781628131866455,
|
| 49050 |
+
"learning_rate": 3.4650423373877076e-05,
|
| 49051 |
+
"loss": 0.8953,
|
| 49052 |
+
"step": 7006
|
| 49053 |
+
},
|
| 49054 |
+
{
|
| 49055 |
+
"epoch": 7.981196581196581,
|
| 49056 |
+
"grad_norm": 0.17765744030475616,
|
| 49057 |
+
"learning_rate": 3.464612515041302e-05,
|
| 49058 |
+
"loss": 0.7049,
|
| 49059 |
+
"step": 7007
|
| 49060 |
+
},
|
| 49061 |
+
{
|
| 49062 |
+
"epoch": 7.982336182336183,
|
| 49063 |
+
"grad_norm": 0.2767314016819,
|
| 49064 |
+
"learning_rate": 3.464182659191252e-05,
|
| 49065 |
+
"loss": 0.4096,
|
| 49066 |
+
"step": 7008
|
| 49067 |
+
},
|
| 49068 |
+
{
|
| 49069 |
+
"epoch": 7.983475783475783,
|
| 49070 |
+
"grad_norm": 0.18152180314064026,
|
| 49071 |
+
"learning_rate": 3.463752769852485e-05,
|
| 49072 |
+
"loss": 0.8218,
|
| 49073 |
+
"step": 7009
|
| 49074 |
+
},
|
| 49075 |
+
{
|
| 49076 |
+
"epoch": 7.984615384615385,
|
| 49077 |
+
"grad_norm": 0.2066626101732254,
|
| 49078 |
+
"learning_rate": 3.463322847039935e-05,
|
| 49079 |
+
"loss": 0.7268,
|
| 49080 |
+
"step": 7010
|
| 49081 |
+
},
|
| 49082 |
+
{
|
| 49083 |
+
"epoch": 7.985754985754986,
|
| 49084 |
+
"grad_norm": 0.2450648546218872,
|
| 49085 |
+
"learning_rate": 3.462892890768533e-05,
|
| 49086 |
+
"loss": 0.5793,
|
| 49087 |
+
"step": 7011
|
| 49088 |
+
},
|
| 49089 |
+
{
|
| 49090 |
+
"epoch": 7.986894586894587,
|
| 49091 |
+
"grad_norm": 0.2684401571750641,
|
| 49092 |
+
"learning_rate": 3.4624629010532136e-05,
|
| 49093 |
+
"loss": 0.7406,
|
| 49094 |
+
"step": 7012
|
| 49095 |
+
},
|
| 49096 |
+
{
|
| 49097 |
+
"epoch": 7.988034188034188,
|
| 49098 |
+
"grad_norm": 0.25210240483283997,
|
| 49099 |
+
"learning_rate": 3.46203287790891e-05,
|
| 49100 |
+
"loss": 0.6941,
|
| 49101 |
+
"step": 7013
|
| 49102 |
+
},
|
| 49103 |
+
{
|
| 49104 |
+
"epoch": 7.9891737891737895,
|
| 49105 |
+
"grad_norm": 0.17891636490821838,
|
| 49106 |
+
"learning_rate": 3.46160282135056e-05,
|
| 49107 |
+
"loss": 0.8529,
|
| 49108 |
+
"step": 7014
|
| 49109 |
+
},
|
| 49110 |
+
{
|
| 49111 |
+
"epoch": 7.99031339031339,
|
| 49112 |
+
"grad_norm": 0.16356289386749268,
|
| 49113 |
+
"learning_rate": 3.461172731393098e-05,
|
| 49114 |
+
"loss": 0.9962,
|
| 49115 |
+
"step": 7015
|
| 49116 |
+
},
|
| 49117 |
+
{
|
| 49118 |
+
"epoch": 7.9914529914529915,
|
| 49119 |
+
"grad_norm": 0.23235754668712616,
|
| 49120 |
+
"learning_rate": 3.460742608051466e-05,
|
| 49121 |
+
"loss": 0.6886,
|
| 49122 |
+
"step": 7016
|
| 49123 |
+
},
|
| 49124 |
+
{
|
| 49125 |
+
"epoch": 7.992592592592593,
|
| 49126 |
+
"grad_norm": 0.15596100687980652,
|
| 49127 |
+
"learning_rate": 3.4603124513405995e-05,
|
| 49128 |
+
"loss": 1.047,
|
| 49129 |
+
"step": 7017
|
| 49130 |
+
},
|
| 49131 |
+
{
|
| 49132 |
+
"epoch": 7.9937321937321935,
|
| 49133 |
+
"grad_norm": 0.23271232843399048,
|
| 49134 |
+
"learning_rate": 3.4598822612754413e-05,
|
| 49135 |
+
"loss": 0.8109,
|
| 49136 |
+
"step": 7018
|
| 49137 |
+
},
|
| 49138 |
+
{
|
| 49139 |
+
"epoch": 7.994871794871795,
|
| 49140 |
+
"grad_norm": 0.15891754627227783,
|
| 49141 |
+
"learning_rate": 3.459452037870933e-05,
|
| 49142 |
+
"loss": 0.8591,
|
| 49143 |
+
"step": 7019
|
| 49144 |
+
},
|
| 49145 |
+
{
|
| 49146 |
+
"epoch": 7.996011396011396,
|
| 49147 |
+
"grad_norm": 0.23841074109077454,
|
| 49148 |
+
"learning_rate": 3.459021781142015e-05,
|
| 49149 |
+
"loss": 0.6763,
|
| 49150 |
+
"step": 7020
|
| 49151 |
+
},
|
| 49152 |
+
{
|
| 49153 |
+
"epoch": 7.997150997150997,
|
| 49154 |
+
"grad_norm": 0.25842007994651794,
|
| 49155 |
+
"learning_rate": 3.458591491103635e-05,
|
| 49156 |
+
"loss": 0.7704,
|
| 49157 |
+
"step": 7021
|
| 49158 |
+
},
|
| 49159 |
+
{
|
| 49160 |
+
"epoch": 7.998290598290598,
|
| 49161 |
+
"grad_norm": 0.16829439997673035,
|
| 49162 |
+
"learning_rate": 3.458161167770735e-05,
|
| 49163 |
+
"loss": 0.8967,
|
| 49164 |
+
"step": 7022
|
| 49165 |
+
},
|
| 49166 |
+
{
|
| 49167 |
+
"epoch": 7.9994301994302,
|
| 49168 |
+
"grad_norm": 0.19539670646190643,
|
| 49169 |
+
"learning_rate": 3.457730811158264e-05,
|
| 49170 |
+
"loss": 0.7824,
|
| 49171 |
+
"step": 7023
|
| 49172 |
+
},
|
| 49173 |
+
{
|
| 49174 |
+
"epoch": 8.0,
|
| 49175 |
+
"grad_norm": 0.36949995160102844,
|
| 49176 |
+
"learning_rate": 3.4573004212811675e-05,
|
| 49177 |
+
"loss": 0.6208,
|
| 49178 |
+
"step": 7024
|
| 49179 |
+
},
|
| 49180 |
+
{
|
| 49181 |
+
"epoch": 8.0011396011396,
|
| 49182 |
+
"grad_norm": 0.16737952828407288,
|
| 49183 |
+
"learning_rate": 3.456869998154396e-05,
|
| 49184 |
+
"loss": 0.789,
|
| 49185 |
+
"step": 7025
|
| 49186 |
+
},
|
| 49187 |
+
{
|
| 49188 |
+
"epoch": 8.002279202279203,
|
| 49189 |
+
"grad_norm": 0.1565866768360138,
|
| 49190 |
+
"learning_rate": 3.456439541792896e-05,
|
| 49191 |
+
"loss": 0.8853,
|
| 49192 |
+
"step": 7026
|
| 49193 |
+
},
|
| 49194 |
+
{
|
| 49195 |
+
"epoch": 8.003418803418803,
|
| 49196 |
+
"grad_norm": 0.17611169815063477,
|
| 49197 |
+
"learning_rate": 3.456009052211622e-05,
|
| 49198 |
+
"loss": 0.8464,
|
| 49199 |
+
"step": 7027
|
| 49200 |
+
},
|
| 49201 |
+
{
|
| 49202 |
+
"epoch": 8.004558404558404,
|
| 49203 |
+
"grad_norm": 0.18413347005844116,
|
| 49204 |
+
"learning_rate": 3.455578529425524e-05,
|
| 49205 |
+
"loss": 0.8049,
|
| 49206 |
+
"step": 7028
|
| 49207 |
+
},
|
| 49208 |
+
{
|
| 49209 |
+
"epoch": 8.005698005698006,
|
| 49210 |
+
"grad_norm": 0.1993255913257599,
|
| 49211 |
+
"learning_rate": 3.455147973449556e-05,
|
| 49212 |
+
"loss": 0.6136,
|
| 49213 |
+
"step": 7029
|
| 49214 |
+
},
|
| 49215 |
+
{
|
| 49216 |
+
"epoch": 8.006837606837607,
|
| 49217 |
+
"grad_norm": 0.18642333149909973,
|
| 49218 |
+
"learning_rate": 3.454717384298672e-05,
|
| 49219 |
+
"loss": 0.81,
|
| 49220 |
+
"step": 7030
|
| 49221 |
+
},
|
| 49222 |
+
{
|
| 49223 |
+
"epoch": 8.007977207977207,
|
| 49224 |
+
"grad_norm": 0.21787570416927338,
|
| 49225 |
+
"learning_rate": 3.4542867619878275e-05,
|
| 49226 |
+
"loss": 0.7353,
|
| 49227 |
+
"step": 7031
|
| 49228 |
+
},
|
| 49229 |
+
{
|
| 49230 |
+
"epoch": 8.00911680911681,
|
| 49231 |
+
"grad_norm": 0.1952671855688095,
|
| 49232 |
+
"learning_rate": 3.45385610653198e-05,
|
| 49233 |
+
"loss": 0.807,
|
| 49234 |
+
"step": 7032
|
| 49235 |
+
},
|
| 49236 |
+
{
|
| 49237 |
+
"epoch": 8.01025641025641,
|
| 49238 |
+
"grad_norm": 0.2039884477853775,
|
| 49239 |
+
"learning_rate": 3.453425417946087e-05,
|
| 49240 |
+
"loss": 0.7051,
|
| 49241 |
+
"step": 7033
|
| 49242 |
+
},
|
| 49243 |
+
{
|
| 49244 |
+
"epoch": 8.01139601139601,
|
| 49245 |
+
"grad_norm": 0.1795361191034317,
|
| 49246 |
+
"learning_rate": 3.452994696245107e-05,
|
| 49247 |
+
"loss": 0.7775,
|
| 49248 |
+
"step": 7034
|
| 49249 |
+
},
|
| 49250 |
+
{
|
| 49251 |
+
"epoch": 8.012535612535613,
|
| 49252 |
+
"grad_norm": 0.1974959373474121,
|
| 49253 |
+
"learning_rate": 3.452563941444e-05,
|
| 49254 |
+
"loss": 0.6406,
|
| 49255 |
+
"step": 7035
|
| 49256 |
+
},
|
| 49257 |
+
{
|
| 49258 |
+
"epoch": 8.013675213675214,
|
| 49259 |
+
"grad_norm": 0.21458816528320312,
|
| 49260 |
+
"learning_rate": 3.452133153557729e-05,
|
| 49261 |
+
"loss": 0.6946,
|
| 49262 |
+
"step": 7036
|
| 49263 |
+
},
|
| 49264 |
+
{
|
| 49265 |
+
"epoch": 8.014814814814814,
|
| 49266 |
+
"grad_norm": 0.23039047420024872,
|
| 49267 |
+
"learning_rate": 3.451702332601254e-05,
|
| 49268 |
+
"loss": 0.4753,
|
| 49269 |
+
"step": 7037
|
| 49270 |
+
},
|
| 49271 |
+
{
|
| 49272 |
+
"epoch": 8.015954415954416,
|
| 49273 |
+
"grad_norm": 0.17048563063144684,
|
| 49274 |
+
"learning_rate": 3.45127147858954e-05,
|
| 49275 |
+
"loss": 0.6948,
|
| 49276 |
+
"step": 7038
|
| 49277 |
+
},
|
| 49278 |
+
{
|
| 49279 |
+
"epoch": 8.017094017094017,
|
| 49280 |
+
"grad_norm": 0.2207256555557251,
|
| 49281 |
+
"learning_rate": 3.450840591537552e-05,
|
| 49282 |
+
"loss": 0.5992,
|
| 49283 |
+
"step": 7039
|
| 49284 |
+
},
|
| 49285 |
+
{
|
| 49286 |
+
"epoch": 8.018233618233618,
|
| 49287 |
+
"grad_norm": 0.22948038578033447,
|
| 49288 |
+
"learning_rate": 3.4504096714602554e-05,
|
| 49289 |
+
"loss": 0.5309,
|
| 49290 |
+
"step": 7040
|
| 49291 |
+
},
|
| 49292 |
+
{
|
| 49293 |
+
"epoch": 8.01937321937322,
|
| 49294 |
+
"grad_norm": 0.17594662308692932,
|
| 49295 |
+
"learning_rate": 3.4499787183726165e-05,
|
| 49296 |
+
"loss": 0.6524,
|
| 49297 |
+
"step": 7041
|
| 49298 |
+
},
|
| 49299 |
+
{
|
| 49300 |
+
"epoch": 8.02051282051282,
|
| 49301 |
+
"grad_norm": 0.15962903201580048,
|
| 49302 |
+
"learning_rate": 3.4495477322896047e-05,
|
| 49303 |
+
"loss": 0.8802,
|
| 49304 |
+
"step": 7042
|
| 49305 |
+
},
|
| 49306 |
+
{
|
| 49307 |
+
"epoch": 8.021652421652421,
|
| 49308 |
+
"grad_norm": 0.17640933394432068,
|
| 49309 |
+
"learning_rate": 3.4491167132261886e-05,
|
| 49310 |
+
"loss": 0.7508,
|
| 49311 |
+
"step": 7043
|
| 49312 |
+
},
|
| 49313 |
+
{
|
| 49314 |
+
"epoch": 8.022792022792023,
|
| 49315 |
+
"grad_norm": 0.18207409977912903,
|
| 49316 |
+
"learning_rate": 3.44868566119734e-05,
|
| 49317 |
+
"loss": 0.7672,
|
| 49318 |
+
"step": 7044
|
| 49319 |
+
},
|
| 49320 |
+
{
|
| 49321 |
+
"epoch": 8.023931623931624,
|
| 49322 |
+
"grad_norm": 0.20971670746803284,
|
| 49323 |
+
"learning_rate": 3.448254576218029e-05,
|
| 49324 |
+
"loss": 0.6199,
|
| 49325 |
+
"step": 7045
|
| 49326 |
+
},
|
| 49327 |
+
{
|
| 49328 |
+
"epoch": 8.025071225071224,
|
| 49329 |
+
"grad_norm": 0.20471307635307312,
|
| 49330 |
+
"learning_rate": 3.4478234583032284e-05,
|
| 49331 |
+
"loss": 0.6351,
|
| 49332 |
+
"step": 7046
|
| 49333 |
+
},
|
| 49334 |
+
{
|
| 49335 |
+
"epoch": 8.026210826210827,
|
| 49336 |
+
"grad_norm": 0.18834306299686432,
|
| 49337 |
+
"learning_rate": 3.4473923074679126e-05,
|
| 49338 |
+
"loss": 0.6741,
|
| 49339 |
+
"step": 7047
|
| 49340 |
+
},
|
| 49341 |
+
{
|
| 49342 |
+
"epoch": 8.027350427350427,
|
| 49343 |
+
"grad_norm": 0.1725883185863495,
|
| 49344 |
+
"learning_rate": 3.4469611237270574e-05,
|
| 49345 |
+
"loss": 0.8075,
|
| 49346 |
+
"step": 7048
|
| 49347 |
+
},
|
| 49348 |
+
{
|
| 49349 |
+
"epoch": 8.028490028490028,
|
| 49350 |
+
"grad_norm": 0.16943272948265076,
|
| 49351 |
+
"learning_rate": 3.446529907095638e-05,
|
| 49352 |
+
"loss": 0.667,
|
| 49353 |
+
"step": 7049
|
| 49354 |
+
},
|
| 49355 |
+
{
|
| 49356 |
+
"epoch": 8.02962962962963,
|
| 49357 |
+
"grad_norm": 0.1960059255361557,
|
| 49358 |
+
"learning_rate": 3.446098657588631e-05,
|
| 49359 |
+
"loss": 0.6117,
|
| 49360 |
+
"step": 7050
|
| 49361 |
+
},
|
| 49362 |
+
{
|
| 49363 |
+
"epoch": 8.03076923076923,
|
| 49364 |
+
"grad_norm": 0.20933693647384644,
|
| 49365 |
+
"learning_rate": 3.445667375221017e-05,
|
| 49366 |
+
"loss": 0.6904,
|
| 49367 |
+
"step": 7051
|
| 49368 |
+
},
|
| 49369 |
+
{
|
| 49370 |
+
"epoch": 8.031908831908831,
|
| 49371 |
+
"grad_norm": 0.1454627364873886,
|
| 49372 |
+
"learning_rate": 3.445236060007774e-05,
|
| 49373 |
+
"loss": 0.9105,
|
| 49374 |
+
"step": 7052
|
| 49375 |
+
},
|
| 49376 |
+
{
|
| 49377 |
+
"epoch": 8.033048433048434,
|
| 49378 |
+
"grad_norm": 0.20399250090122223,
|
| 49379 |
+
"learning_rate": 3.4448047119638824e-05,
|
| 49380 |
+
"loss": 0.8021,
|
| 49381 |
+
"step": 7053
|
| 49382 |
+
},
|
| 49383 |
+
{
|
| 49384 |
+
"epoch": 8.034188034188034,
|
| 49385 |
+
"grad_norm": 0.19561836123466492,
|
| 49386 |
+
"learning_rate": 3.444373331104326e-05,
|
| 49387 |
+
"loss": 0.8751,
|
| 49388 |
+
"step": 7054
|
| 49389 |
+
},
|
| 49390 |
+
{
|
| 49391 |
+
"epoch": 8.035327635327635,
|
| 49392 |
+
"grad_norm": 0.17703506350517273,
|
| 49393 |
+
"learning_rate": 3.4439419174440865e-05,
|
| 49394 |
+
"loss": 0.7238,
|
| 49395 |
+
"step": 7055
|
| 49396 |
+
},
|
| 49397 |
+
{
|
| 49398 |
+
"epoch": 8.036467236467237,
|
| 49399 |
+
"grad_norm": 0.1614612489938736,
|
| 49400 |
+
"learning_rate": 3.443510470998149e-05,
|
| 49401 |
+
"loss": 0.8676,
|
| 49402 |
+
"step": 7056
|
| 49403 |
+
},
|
| 49404 |
+
{
|
| 49405 |
+
"epoch": 8.037606837606837,
|
| 49406 |
+
"grad_norm": 0.20640437304973602,
|
| 49407 |
+
"learning_rate": 3.443078991781498e-05,
|
| 49408 |
+
"loss": 0.4616,
|
| 49409 |
+
"step": 7057
|
| 49410 |
+
},
|
| 49411 |
+
{
|
| 49412 |
+
"epoch": 8.038746438746438,
|
| 49413 |
+
"grad_norm": 0.21130231022834778,
|
| 49414 |
+
"learning_rate": 3.442647479809119e-05,
|
| 49415 |
+
"loss": 0.7574,
|
| 49416 |
+
"step": 7058
|
| 49417 |
+
},
|
| 49418 |
+
{
|
| 49419 |
+
"epoch": 8.03988603988604,
|
| 49420 |
+
"grad_norm": 0.18179568648338318,
|
| 49421 |
+
"learning_rate": 3.442215935096001e-05,
|
| 49422 |
+
"loss": 0.7957,
|
| 49423 |
+
"step": 7059
|
| 49424 |
+
},
|
| 49425 |
+
{
|
| 49426 |
+
"epoch": 8.04102564102564,
|
| 49427 |
+
"grad_norm": 0.21558696031570435,
|
| 49428 |
+
"learning_rate": 3.441784357657133e-05,
|
| 49429 |
+
"loss": 0.6683,
|
| 49430 |
+
"step": 7060
|
| 49431 |
+
},
|
| 49432 |
+
{
|
| 49433 |
+
"epoch": 8.042165242165241,
|
| 49434 |
+
"grad_norm": 0.18749386072158813,
|
| 49435 |
+
"learning_rate": 3.441352747507504e-05,
|
| 49436 |
+
"loss": 0.7306,
|
| 49437 |
+
"step": 7061
|
| 49438 |
+
},
|
| 49439 |
+
{
|
| 49440 |
+
"epoch": 8.043304843304844,
|
| 49441 |
+
"grad_norm": 0.19328436255455017,
|
| 49442 |
+
"learning_rate": 3.440921104662106e-05,
|
| 49443 |
+
"loss": 0.6622,
|
| 49444 |
+
"step": 7062
|
| 49445 |
+
},
|
| 49446 |
+
{
|
| 49447 |
+
"epoch": 8.044444444444444,
|
| 49448 |
+
"grad_norm": 0.14162495732307434,
|
| 49449 |
+
"learning_rate": 3.44048942913593e-05,
|
| 49450 |
+
"loss": 0.9996,
|
| 49451 |
+
"step": 7063
|
| 49452 |
+
},
|
| 49453 |
+
{
|
| 49454 |
+
"epoch": 8.045584045584045,
|
| 49455 |
+
"grad_norm": 0.19856049120426178,
|
| 49456 |
+
"learning_rate": 3.44005772094397e-05,
|
| 49457 |
+
"loss": 0.678,
|
| 49458 |
+
"step": 7064
|
| 49459 |
+
},
|
| 49460 |
+
{
|
| 49461 |
+
"epoch": 8.046723646723647,
|
| 49462 |
+
"grad_norm": 0.21557380259037018,
|
| 49463 |
+
"learning_rate": 3.43962598010122e-05,
|
| 49464 |
+
"loss": 0.8354,
|
| 49465 |
+
"step": 7065
|
| 49466 |
+
},
|
| 49467 |
+
{
|
| 49468 |
+
"epoch": 8.047863247863248,
|
| 49469 |
+
"grad_norm": 0.21577595174312592,
|
| 49470 |
+
"learning_rate": 3.4391942066226755e-05,
|
| 49471 |
+
"loss": 0.8101,
|
| 49472 |
+
"step": 7066
|
| 49473 |
+
},
|
| 49474 |
+
{
|
| 49475 |
+
"epoch": 8.049002849002848,
|
| 49476 |
+
"grad_norm": 0.18127447366714478,
|
| 49477 |
+
"learning_rate": 3.438762400523334e-05,
|
| 49478 |
+
"loss": 0.6539,
|
| 49479 |
+
"step": 7067
|
| 49480 |
+
},
|
| 49481 |
+
{
|
| 49482 |
+
"epoch": 8.05014245014245,
|
| 49483 |
+
"grad_norm": 0.17225967347621918,
|
| 49484 |
+
"learning_rate": 3.4383305618181925e-05,
|
| 49485 |
+
"loss": 0.7079,
|
| 49486 |
+
"step": 7068
|
| 49487 |
+
},
|
| 49488 |
+
{
|
| 49489 |
+
"epoch": 8.051282051282051,
|
| 49490 |
+
"grad_norm": 0.2191513627767563,
|
| 49491 |
+
"learning_rate": 3.43789869052225e-05,
|
| 49492 |
+
"loss": 0.7383,
|
| 49493 |
+
"step": 7069
|
| 49494 |
+
},
|
| 49495 |
+
{
|
| 49496 |
+
"epoch": 8.052421652421652,
|
| 49497 |
+
"grad_norm": 0.19804395735263824,
|
| 49498 |
+
"learning_rate": 3.437466786650506e-05,
|
| 49499 |
+
"loss": 0.8199,
|
| 49500 |
+
"step": 7070
|
| 49501 |
+
},
|
| 49502 |
+
{
|
| 49503 |
+
"epoch": 8.053561253561254,
|
| 49504 |
+
"grad_norm": 0.17152638733386993,
|
| 49505 |
+
"learning_rate": 3.4370348502179634e-05,
|
| 49506 |
+
"loss": 0.9667,
|
| 49507 |
+
"step": 7071
|
| 49508 |
+
},
|
| 49509 |
+
{
|
| 49510 |
+
"epoch": 8.054700854700855,
|
| 49511 |
+
"grad_norm": 0.21188904345035553,
|
| 49512 |
+
"learning_rate": 3.436602881239624e-05,
|
| 49513 |
+
"loss": 0.7232,
|
| 49514 |
+
"step": 7072
|
| 49515 |
+
},
|
| 49516 |
+
{
|
| 49517 |
+
"epoch": 8.055840455840455,
|
| 49518 |
+
"grad_norm": 0.5748328566551208,
|
| 49519 |
+
"learning_rate": 3.43617087973049e-05,
|
| 49520 |
+
"loss": 0.5792,
|
| 49521 |
+
"step": 7073
|
| 49522 |
+
},
|
| 49523 |
+
{
|
| 49524 |
+
"epoch": 8.056980056980057,
|
| 49525 |
+
"grad_norm": 0.13886001706123352,
|
| 49526 |
+
"learning_rate": 3.435738845705567e-05,
|
| 49527 |
+
"loss": 0.9684,
|
| 49528 |
+
"step": 7074
|
| 49529 |
+
},
|
| 49530 |
+
{
|
| 49531 |
+
"epoch": 8.058119658119658,
|
| 49532 |
+
"grad_norm": 0.36263221502304077,
|
| 49533 |
+
"learning_rate": 3.435306779179861e-05,
|
| 49534 |
+
"loss": 0.7062,
|
| 49535 |
+
"step": 7075
|
| 49536 |
+
},
|
| 49537 |
+
{
|
| 49538 |
+
"epoch": 8.059259259259258,
|
| 49539 |
+
"grad_norm": 0.17102155089378357,
|
| 49540 |
+
"learning_rate": 3.4348746801683784e-05,
|
| 49541 |
+
"loss": 0.7513,
|
| 49542 |
+
"step": 7076
|
| 49543 |
+
},
|
| 49544 |
+
{
|
| 49545 |
+
"epoch": 8.06039886039886,
|
| 49546 |
+
"grad_norm": 0.2088032364845276,
|
| 49547 |
+
"learning_rate": 3.434442548686127e-05,
|
| 49548 |
+
"loss": 0.6356,
|
| 49549 |
+
"step": 7077
|
| 49550 |
+
},
|
| 49551 |
+
{
|
| 49552 |
+
"epoch": 8.061538461538461,
|
| 49553 |
+
"grad_norm": 0.26760900020599365,
|
| 49554 |
+
"learning_rate": 3.4340103847481165e-05,
|
| 49555 |
+
"loss": 0.661,
|
| 49556 |
+
"step": 7078
|
| 49557 |
+
},
|
| 49558 |
+
{
|
| 49559 |
+
"epoch": 8.062678062678062,
|
| 49560 |
+
"grad_norm": 0.2030276656150818,
|
| 49561 |
+
"learning_rate": 3.433578188369356e-05,
|
| 49562 |
+
"loss": 0.6599,
|
| 49563 |
+
"step": 7079
|
| 49564 |
+
},
|
| 49565 |
+
{
|
| 49566 |
+
"epoch": 8.063817663817664,
|
| 49567 |
+
"grad_norm": 0.21676896512508392,
|
| 49568 |
+
"learning_rate": 3.433145959564859e-05,
|
| 49569 |
+
"loss": 0.7473,
|
| 49570 |
+
"step": 7080
|
| 49571 |
+
},
|
| 49572 |
+
{
|
| 49573 |
+
"epoch": 8.064957264957265,
|
| 49574 |
+
"grad_norm": 0.17342697083950043,
|
| 49575 |
+
"learning_rate": 3.4327136983496356e-05,
|
| 49576 |
+
"loss": 0.9241,
|
| 49577 |
+
"step": 7081
|
| 49578 |
+
},
|
| 49579 |
+
{
|
| 49580 |
+
"epoch": 8.066096866096865,
|
| 49581 |
+
"grad_norm": 0.22797280550003052,
|
| 49582 |
+
"learning_rate": 3.4322814047387e-05,
|
| 49583 |
+
"loss": 0.5714,
|
| 49584 |
+
"step": 7082
|
| 49585 |
+
},
|
| 49586 |
+
{
|
| 49587 |
+
"epoch": 8.067236467236468,
|
| 49588 |
+
"grad_norm": 0.24386514723300934,
|
| 49589 |
+
"learning_rate": 3.431849078747069e-05,
|
| 49590 |
+
"loss": 0.6692,
|
| 49591 |
+
"step": 7083
|
| 49592 |
+
},
|
| 49593 |
+
{
|
| 49594 |
+
"epoch": 8.068376068376068,
|
| 49595 |
+
"grad_norm": 0.24640591442584991,
|
| 49596 |
+
"learning_rate": 3.4314167203897555e-05,
|
| 49597 |
+
"loss": 0.6181,
|
| 49598 |
+
"step": 7084
|
| 49599 |
+
},
|
| 49600 |
+
{
|
| 49601 |
+
"epoch": 8.069515669515669,
|
| 49602 |
+
"grad_norm": 0.2500792443752289,
|
| 49603 |
+
"learning_rate": 3.430984329681779e-05,
|
| 49604 |
+
"loss": 0.653,
|
| 49605 |
+
"step": 7085
|
| 49606 |
+
},
|
| 49607 |
+
{
|
| 49608 |
+
"epoch": 8.070655270655271,
|
| 49609 |
+
"grad_norm": 0.2008410394191742,
|
| 49610 |
+
"learning_rate": 3.4305519066381556e-05,
|
| 49611 |
+
"loss": 0.6139,
|
| 49612 |
+
"step": 7086
|
| 49613 |
+
},
|
| 49614 |
+
{
|
| 49615 |
+
"epoch": 8.071794871794872,
|
| 49616 |
+
"grad_norm": 0.2510213255882263,
|
| 49617 |
+
"learning_rate": 3.4301194512739055e-05,
|
| 49618 |
+
"loss": 0.4839,
|
| 49619 |
+
"step": 7087
|
| 49620 |
+
},
|
| 49621 |
+
{
|
| 49622 |
+
"epoch": 8.072934472934472,
|
| 49623 |
+
"grad_norm": 0.2027340531349182,
|
| 49624 |
+
"learning_rate": 3.42968696360405e-05,
|
| 49625 |
+
"loss": 0.6899,
|
| 49626 |
+
"step": 7088
|
| 49627 |
+
},
|
| 49628 |
+
{
|
| 49629 |
+
"epoch": 8.074074074074074,
|
| 49630 |
+
"grad_norm": 0.1756913959980011,
|
| 49631 |
+
"learning_rate": 3.429254443643609e-05,
|
| 49632 |
+
"loss": 0.8085,
|
| 49633 |
+
"step": 7089
|
| 49634 |
+
},
|
| 49635 |
+
{
|
| 49636 |
+
"epoch": 8.075213675213675,
|
| 49637 |
+
"grad_norm": 0.20395086705684662,
|
| 49638 |
+
"learning_rate": 3.4288218914076056e-05,
|
| 49639 |
+
"loss": 0.7696,
|
| 49640 |
+
"step": 7090
|
| 49641 |
+
},
|
| 49642 |
+
{
|
| 49643 |
+
"epoch": 8.076353276353275,
|
| 49644 |
+
"grad_norm": 0.1912129819393158,
|
| 49645 |
+
"learning_rate": 3.428389306911064e-05,
|
| 49646 |
+
"loss": 0.844,
|
| 49647 |
+
"step": 7091
|
| 49648 |
+
},
|
| 49649 |
+
{
|
| 49650 |
+
"epoch": 8.077492877492878,
|
| 49651 |
+
"grad_norm": 0.2174018770456314,
|
| 49652 |
+
"learning_rate": 3.427956690169008e-05,
|
| 49653 |
+
"loss": 0.6293,
|
| 49654 |
+
"step": 7092
|
| 49655 |
+
},
|
| 49656 |
+
{
|
| 49657 |
+
"epoch": 8.078632478632478,
|
| 49658 |
+
"grad_norm": 0.18037767708301544,
|
| 49659 |
+
"learning_rate": 3.427524041196464e-05,
|
| 49660 |
+
"loss": 0.9507,
|
| 49661 |
+
"step": 7093
|
| 49662 |
+
},
|
| 49663 |
+
{
|
| 49664 |
+
"epoch": 8.079772079772079,
|
| 49665 |
+
"grad_norm": 0.1751590073108673,
|
| 49666 |
+
"learning_rate": 3.427091360008461e-05,
|
| 49667 |
+
"loss": 0.7677,
|
| 49668 |
+
"step": 7094
|
| 49669 |
+
},
|
| 49670 |
+
{
|
| 49671 |
+
"epoch": 8.080911680911681,
|
| 49672 |
+
"grad_norm": 0.19041262567043304,
|
| 49673 |
+
"learning_rate": 3.426658646620024e-05,
|
| 49674 |
+
"loss": 0.7292,
|
| 49675 |
+
"step": 7095
|
| 49676 |
+
},
|
| 49677 |
+
{
|
| 49678 |
+
"epoch": 8.082051282051282,
|
| 49679 |
+
"grad_norm": 0.20226050913333893,
|
| 49680 |
+
"learning_rate": 3.426225901046185e-05,
|
| 49681 |
+
"loss": 0.7366,
|
| 49682 |
+
"step": 7096
|
| 49683 |
+
},
|
| 49684 |
+
{
|
| 49685 |
+
"epoch": 8.083190883190884,
|
| 49686 |
+
"grad_norm": 0.18322516977787018,
|
| 49687 |
+
"learning_rate": 3.425793123301973e-05,
|
| 49688 |
+
"loss": 0.6936,
|
| 49689 |
+
"step": 7097
|
| 49690 |
+
},
|
| 49691 |
+
{
|
| 49692 |
+
"epoch": 8.084330484330485,
|
| 49693 |
+
"grad_norm": 0.2583000659942627,
|
| 49694 |
+
"learning_rate": 3.4253603134024195e-05,
|
| 49695 |
+
"loss": 0.5171,
|
| 49696 |
+
"step": 7098
|
| 49697 |
+
},
|
| 49698 |
+
{
|
| 49699 |
+
"epoch": 8.085470085470085,
|
| 49700 |
+
"grad_norm": 0.19763217866420746,
|
| 49701 |
+
"learning_rate": 3.424927471362557e-05,
|
| 49702 |
+
"loss": 0.697,
|
| 49703 |
+
"step": 7099
|
| 49704 |
+
},
|
| 49705 |
+
{
|
| 49706 |
+
"epoch": 8.086609686609687,
|
| 49707 |
+
"grad_norm": 0.16299405694007874,
|
| 49708 |
+
"learning_rate": 3.424494597197421e-05,
|
| 49709 |
+
"loss": 0.8714,
|
| 49710 |
+
"step": 7100
|
| 49711 |
+
},
|
| 49712 |
+
{
|
| 49713 |
+
"epoch": 8.087749287749288,
|
| 49714 |
+
"grad_norm": 0.17452651262283325,
|
| 49715 |
+
"learning_rate": 3.424061690922045e-05,
|
| 49716 |
+
"loss": 0.8544,
|
| 49717 |
+
"step": 7101
|
| 49718 |
+
},
|
| 49719 |
+
{
|
| 49720 |
+
"epoch": 8.088888888888889,
|
| 49721 |
+
"grad_norm": 0.2546103596687317,
|
| 49722 |
+
"learning_rate": 3.423628752551466e-05,
|
| 49723 |
+
"loss": 0.5386,
|
| 49724 |
+
"step": 7102
|
| 49725 |
+
},
|
| 49726 |
+
{
|
| 49727 |
+
"epoch": 8.090028490028491,
|
| 49728 |
+
"grad_norm": 0.16574569046497345,
|
| 49729 |
+
"learning_rate": 3.4231957821007185e-05,
|
| 49730 |
+
"loss": 0.8548,
|
| 49731 |
+
"step": 7103
|
| 49732 |
+
},
|
| 49733 |
+
{
|
| 49734 |
+
"epoch": 8.091168091168091,
|
| 49735 |
+
"grad_norm": 0.15770331025123596,
|
| 49736 |
+
"learning_rate": 3.422762779584844e-05,
|
| 49737 |
+
"loss": 0.9192,
|
| 49738 |
+
"step": 7104
|
| 49739 |
+
},
|
| 49740 |
+
{
|
| 49741 |
+
"epoch": 8.092307692307692,
|
| 49742 |
+
"grad_norm": 0.1630685031414032,
|
| 49743 |
+
"learning_rate": 3.4223297450188796e-05,
|
| 49744 |
+
"loss": 0.772,
|
| 49745 |
+
"step": 7105
|
| 49746 |
+
},
|
| 49747 |
+
{
|
| 49748 |
+
"epoch": 8.093447293447294,
|
| 49749 |
+
"grad_norm": 0.20278406143188477,
|
| 49750 |
+
"learning_rate": 3.421896678417868e-05,
|
| 49751 |
+
"loss": 0.6406,
|
| 49752 |
+
"step": 7106
|
| 49753 |
+
},
|
| 49754 |
+
{
|
| 49755 |
+
"epoch": 8.094586894586895,
|
| 49756 |
+
"grad_norm": 0.2626460790634155,
|
| 49757 |
+
"learning_rate": 3.421463579796849e-05,
|
| 49758 |
+
"loss": 0.56,
|
| 49759 |
+
"step": 7107
|
| 49760 |
+
},
|
| 49761 |
+
{
|
| 49762 |
+
"epoch": 8.095726495726495,
|
| 49763 |
+
"grad_norm": 0.24302344024181366,
|
| 49764 |
+
"learning_rate": 3.421030449170866e-05,
|
| 49765 |
+
"loss": 0.5718,
|
| 49766 |
+
"step": 7108
|
| 49767 |
+
},
|
| 49768 |
+
{
|
| 49769 |
+
"epoch": 8.096866096866098,
|
| 49770 |
+
"grad_norm": 0.20670919120311737,
|
| 49771 |
+
"learning_rate": 3.4205972865549624e-05,
|
| 49772 |
+
"loss": 0.6991,
|
| 49773 |
+
"step": 7109
|
| 49774 |
+
},
|
| 49775 |
+
{
|
| 49776 |
+
"epoch": 8.098005698005698,
|
| 49777 |
+
"grad_norm": 0.2587011754512787,
|
| 49778 |
+
"learning_rate": 3.420164091964183e-05,
|
| 49779 |
+
"loss": 0.6819,
|
| 49780 |
+
"step": 7110
|
| 49781 |
+
},
|
| 49782 |
+
{
|
| 49783 |
+
"epoch": 8.099145299145299,
|
| 49784 |
+
"grad_norm": 0.20296776294708252,
|
| 49785 |
+
"learning_rate": 3.419730865413575e-05,
|
| 49786 |
+
"loss": 0.7154,
|
| 49787 |
+
"step": 7111
|
| 49788 |
+
},
|
| 49789 |
+
{
|
| 49790 |
+
"epoch": 8.100284900284901,
|
| 49791 |
+
"grad_norm": 0.2368420660495758,
|
| 49792 |
+
"learning_rate": 3.419297606918185e-05,
|
| 49793 |
+
"loss": 0.7073,
|
| 49794 |
+
"step": 7112
|
| 49795 |
+
},
|
| 49796 |
+
{
|
| 49797 |
+
"epoch": 8.101424501424502,
|
| 49798 |
+
"grad_norm": 0.1704382449388504,
|
| 49799 |
+
"learning_rate": 3.418864316493061e-05,
|
| 49800 |
+
"loss": 0.6907,
|
| 49801 |
+
"step": 7113
|
| 49802 |
+
},
|
| 49803 |
+
{
|
| 49804 |
+
"epoch": 8.102564102564102,
|
| 49805 |
+
"grad_norm": 0.2472260594367981,
|
| 49806 |
+
"learning_rate": 3.418430994153251e-05,
|
| 49807 |
+
"loss": 0.5698,
|
| 49808 |
+
"step": 7114
|
| 49809 |
+
},
|
| 49810 |
+
{
|
| 49811 |
+
"epoch": 8.103703703703705,
|
| 49812 |
+
"grad_norm": 0.19436900317668915,
|
| 49813 |
+
"learning_rate": 3.417997639913808e-05,
|
| 49814 |
+
"loss": 0.8179,
|
| 49815 |
+
"step": 7115
|
| 49816 |
+
},
|
| 49817 |
+
{
|
| 49818 |
+
"epoch": 8.104843304843305,
|
| 49819 |
+
"grad_norm": 0.20320023596286774,
|
| 49820 |
+
"learning_rate": 3.4175642537897824e-05,
|
| 49821 |
+
"loss": 0.7338,
|
| 49822 |
+
"step": 7116
|
| 49823 |
+
},
|
| 49824 |
+
{
|
| 49825 |
+
"epoch": 8.105982905982906,
|
| 49826 |
+
"grad_norm": 0.19544652104377747,
|
| 49827 |
+
"learning_rate": 3.417130835796227e-05,
|
| 49828 |
+
"loss": 0.6937,
|
| 49829 |
+
"step": 7117
|
| 49830 |
+
},
|
| 49831 |
+
{
|
| 49832 |
+
"epoch": 8.107122507122508,
|
| 49833 |
+
"grad_norm": 0.22964812815189362,
|
| 49834 |
+
"learning_rate": 3.4166973859481946e-05,
|
| 49835 |
+
"loss": 0.6568,
|
| 49836 |
+
"step": 7118
|
| 49837 |
+
},
|
| 49838 |
+
{
|
| 49839 |
+
"epoch": 8.108262108262108,
|
| 49840 |
+
"grad_norm": 0.19748233258724213,
|
| 49841 |
+
"learning_rate": 3.416263904260743e-05,
|
| 49842 |
+
"loss": 0.6063,
|
| 49843 |
+
"step": 7119
|
| 49844 |
+
},
|
| 49845 |
+
{
|
| 49846 |
+
"epoch": 8.109401709401709,
|
| 49847 |
+
"grad_norm": 0.26273640990257263,
|
| 49848 |
+
"learning_rate": 3.415830390748924e-05,
|
| 49849 |
+
"loss": 0.5052,
|
| 49850 |
+
"step": 7120
|
| 49851 |
+
},
|
| 49852 |
+
{
|
| 49853 |
+
"epoch": 8.110541310541311,
|
| 49854 |
+
"grad_norm": 0.1507258266210556,
|
| 49855 |
+
"learning_rate": 3.4153968454277984e-05,
|
| 49856 |
+
"loss": 0.7803,
|
| 49857 |
+
"step": 7121
|
| 49858 |
+
},
|
| 49859 |
+
{
|
| 49860 |
+
"epoch": 8.111680911680912,
|
| 49861 |
+
"grad_norm": 0.18942983448505402,
|
| 49862 |
+
"learning_rate": 3.414963268312422e-05,
|
| 49863 |
+
"loss": 0.7394,
|
| 49864 |
+
"step": 7122
|
| 49865 |
+
},
|
| 49866 |
+
{
|
| 49867 |
+
"epoch": 8.112820512820512,
|
| 49868 |
+
"grad_norm": 0.23636314272880554,
|
| 49869 |
+
"learning_rate": 3.4145296594178565e-05,
|
| 49870 |
+
"loss": 0.5983,
|
| 49871 |
+
"step": 7123
|
| 49872 |
+
},
|
| 49873 |
+
{
|
| 49874 |
+
"epoch": 8.113960113960115,
|
| 49875 |
+
"grad_norm": 0.20422495901584625,
|
| 49876 |
+
"learning_rate": 3.41409601875916e-05,
|
| 49877 |
+
"loss": 0.7172,
|
| 49878 |
+
"step": 7124
|
| 49879 |
+
},
|
| 49880 |
+
{
|
| 49881 |
+
"epoch": 8.115099715099715,
|
| 49882 |
+
"grad_norm": 0.14250652492046356,
|
| 49883 |
+
"learning_rate": 3.413662346351395e-05,
|
| 49884 |
+
"loss": 0.8622,
|
| 49885 |
+
"step": 7125
|
| 49886 |
+
},
|
| 49887 |
+
{
|
| 49888 |
+
"epoch": 8.116239316239316,
|
| 49889 |
+
"grad_norm": 0.2178293615579605,
|
| 49890 |
+
"learning_rate": 3.413228642209625e-05,
|
| 49891 |
+
"loss": 0.6593,
|
| 49892 |
+
"step": 7126
|
| 49893 |
+
},
|
| 49894 |
+
{
|
| 49895 |
+
"epoch": 8.117378917378918,
|
| 49896 |
+
"grad_norm": 0.2105027437210083,
|
| 49897 |
+
"learning_rate": 3.412794906348912e-05,
|
| 49898 |
+
"loss": 0.7712,
|
| 49899 |
+
"step": 7127
|
| 49900 |
+
},
|
| 49901 |
+
{
|
| 49902 |
+
"epoch": 8.118518518518519,
|
| 49903 |
+
"grad_norm": 0.1878097504377365,
|
| 49904 |
+
"learning_rate": 3.4123611387843223e-05,
|
| 49905 |
+
"loss": 0.7691,
|
| 49906 |
+
"step": 7128
|
| 49907 |
+
},
|
| 49908 |
+
{
|
| 49909 |
+
"epoch": 8.11965811965812,
|
| 49910 |
+
"grad_norm": 0.22846786677837372,
|
| 49911 |
+
"learning_rate": 3.411927339530921e-05,
|
| 49912 |
+
"loss": 0.6266,
|
| 49913 |
+
"step": 7129
|
| 49914 |
+
},
|
| 49915 |
+
{
|
| 49916 |
+
"epoch": 8.120797720797722,
|
| 49917 |
+
"grad_norm": 0.1520662158727646,
|
| 49918 |
+
"learning_rate": 3.411493508603776e-05,
|
| 49919 |
+
"loss": 0.8268,
|
| 49920 |
+
"step": 7130
|
| 49921 |
+
},
|
| 49922 |
+
{
|
| 49923 |
+
"epoch": 8.121937321937322,
|
| 49924 |
+
"grad_norm": 0.28886398673057556,
|
| 49925 |
+
"learning_rate": 3.4110596460179537e-05,
|
| 49926 |
+
"loss": 0.5266,
|
| 49927 |
+
"step": 7131
|
| 49928 |
+
},
|
| 49929 |
+
{
|
| 49930 |
+
"epoch": 8.123076923076923,
|
| 49931 |
+
"grad_norm": 0.25251293182373047,
|
| 49932 |
+
"learning_rate": 3.4106257517885246e-05,
|
| 49933 |
+
"loss": 0.435,
|
| 49934 |
+
"step": 7132
|
| 49935 |
+
},
|
| 49936 |
+
{
|
| 49937 |
+
"epoch": 8.124216524216525,
|
| 49938 |
+
"grad_norm": 0.18864810466766357,
|
| 49939 |
+
"learning_rate": 3.4101918259305586e-05,
|
| 49940 |
+
"loss": 0.6886,
|
| 49941 |
+
"step": 7133
|
| 49942 |
+
},
|
| 49943 |
+
{
|
| 49944 |
+
"epoch": 8.125356125356126,
|
| 49945 |
+
"grad_norm": 0.2172015905380249,
|
| 49946 |
+
"learning_rate": 3.409757868459129e-05,
|
| 49947 |
+
"loss": 0.5421,
|
| 49948 |
+
"step": 7134
|
| 49949 |
+
},
|
| 49950 |
+
{
|
| 49951 |
+
"epoch": 8.126495726495726,
|
| 49952 |
+
"grad_norm": 0.1778659224510193,
|
| 49953 |
+
"learning_rate": 3.409323879389306e-05,
|
| 49954 |
+
"loss": 0.6555,
|
| 49955 |
+
"step": 7135
|
| 49956 |
+
},
|
| 49957 |
+
{
|
| 49958 |
+
"epoch": 8.127635327635328,
|
| 49959 |
+
"grad_norm": 0.2387818694114685,
|
| 49960 |
+
"learning_rate": 3.4088898587361634e-05,
|
| 49961 |
+
"loss": 0.8124,
|
| 49962 |
+
"step": 7136
|
| 49963 |
+
},
|
| 49964 |
+
{
|
| 49965 |
+
"epoch": 8.128774928774929,
|
| 49966 |
+
"grad_norm": 0.21289221942424774,
|
| 49967 |
+
"learning_rate": 3.408455806514777e-05,
|
| 49968 |
+
"loss": 0.6962,
|
| 49969 |
+
"step": 7137
|
| 49970 |
+
},
|
| 49971 |
+
{
|
| 49972 |
+
"epoch": 8.12991452991453,
|
| 49973 |
+
"grad_norm": 0.20071299374103546,
|
| 49974 |
+
"learning_rate": 3.408021722740222e-05,
|
| 49975 |
+
"loss": 0.6872,
|
| 49976 |
+
"step": 7138
|
| 49977 |
+
},
|
| 49978 |
+
{
|
| 49979 |
+
"epoch": 8.131054131054132,
|
| 49980 |
+
"grad_norm": 0.20584726333618164,
|
| 49981 |
+
"learning_rate": 3.407587607427576e-05,
|
| 49982 |
+
"loss": 0.6627,
|
| 49983 |
+
"step": 7139
|
| 49984 |
+
},
|
| 49985 |
+
{
|
| 49986 |
+
"epoch": 8.132193732193732,
|
| 49987 |
+
"grad_norm": 0.14742788672447205,
|
| 49988 |
+
"learning_rate": 3.4071534605919164e-05,
|
| 49989 |
+
"loss": 0.9505,
|
| 49990 |
+
"step": 7140
|
| 49991 |
+
},
|
| 49992 |
+
{
|
| 49993 |
+
"epoch": 8.133333333333333,
|
| 49994 |
+
"grad_norm": 0.2064577341079712,
|
| 49995 |
+
"learning_rate": 3.406719282248322e-05,
|
| 49996 |
+
"loss": 0.7713,
|
| 49997 |
+
"step": 7141
|
| 49998 |
+
},
|
| 49999 |
+
{
|
| 50000 |
+
"epoch": 8.134472934472935,
|
| 50001 |
+
"grad_norm": 0.22255748510360718,
|
| 50002 |
+
"learning_rate": 3.4062850724118735e-05,
|
| 50003 |
+
"loss": 0.7487,
|
| 50004 |
+
"step": 7142
|
| 50005 |
+
},
|
| 50006 |
+
{
|
| 50007 |
+
"epoch": 8.135612535612536,
|
| 50008 |
+
"grad_norm": 0.20696209371089935,
|
| 50009 |
+
"learning_rate": 3.4058508310976526e-05,
|
| 50010 |
+
"loss": 0.7442,
|
| 50011 |
+
"step": 7143
|
| 50012 |
+
},
|
| 50013 |
+
{
|
| 50014 |
+
"epoch": 8.136752136752136,
|
| 50015 |
+
"grad_norm": 0.22416678071022034,
|
| 50016 |
+
"learning_rate": 3.4054165583207406e-05,
|
| 50017 |
+
"loss": 0.6652,
|
| 50018 |
+
"step": 7144
|
| 50019 |
+
},
|
| 50020 |
+
{
|
| 50021 |
+
"epoch": 8.137891737891739,
|
| 50022 |
+
"grad_norm": 0.20389822125434875,
|
| 50023 |
+
"learning_rate": 3.404982254096223e-05,
|
| 50024 |
+
"loss": 0.9133,
|
| 50025 |
+
"step": 7145
|
| 50026 |
+
},
|
| 50027 |
+
{
|
| 50028 |
+
"epoch": 8.13903133903134,
|
| 50029 |
+
"grad_norm": 0.15410453081130981,
|
| 50030 |
+
"learning_rate": 3.4045479184391816e-05,
|
| 50031 |
+
"loss": 0.8412,
|
| 50032 |
+
"step": 7146
|
| 50033 |
+
},
|
| 50034 |
+
{
|
| 50035 |
+
"epoch": 8.14017094017094,
|
| 50036 |
+
"grad_norm": 0.1810719519853592,
|
| 50037 |
+
"learning_rate": 3.404113551364704e-05,
|
| 50038 |
+
"loss": 0.7553,
|
| 50039 |
+
"step": 7147
|
| 50040 |
+
},
|
| 50041 |
+
{
|
| 50042 |
+
"epoch": 8.141310541310542,
|
| 50043 |
+
"grad_norm": 0.15530860424041748,
|
| 50044 |
+
"learning_rate": 3.403679152887876e-05,
|
| 50045 |
+
"loss": 0.8006,
|
| 50046 |
+
"step": 7148
|
| 50047 |
+
},
|
| 50048 |
+
{
|
| 50049 |
+
"epoch": 8.142450142450143,
|
| 50050 |
+
"grad_norm": 0.19188271462917328,
|
| 50051 |
+
"learning_rate": 3.4032447230237865e-05,
|
| 50052 |
+
"loss": 0.7097,
|
| 50053 |
+
"step": 7149
|
| 50054 |
+
},
|
| 50055 |
+
{
|
| 50056 |
+
"epoch": 8.143589743589743,
|
| 50057 |
+
"grad_norm": 0.19926056265830994,
|
| 50058 |
+
"learning_rate": 3.4028102617875237e-05,
|
| 50059 |
+
"loss": 0.7841,
|
| 50060 |
+
"step": 7150
|
| 50061 |
+
},
|
| 50062 |
+
{
|
| 50063 |
+
"epoch": 8.144729344729345,
|
| 50064 |
+
"grad_norm": 0.17562030255794525,
|
| 50065 |
+
"learning_rate": 3.402375769194177e-05,
|
| 50066 |
+
"loss": 0.7486,
|
| 50067 |
+
"step": 7151
|
| 50068 |
+
},
|
| 50069 |
+
{
|
| 50070 |
+
"epoch": 8.145868945868946,
|
| 50071 |
+
"grad_norm": 0.20137180387973785,
|
| 50072 |
+
"learning_rate": 3.401941245258839e-05,
|
| 50073 |
+
"loss": 0.6086,
|
| 50074 |
+
"step": 7152
|
| 50075 |
+
},
|
| 50076 |
+
{
|
| 50077 |
+
"epoch": 8.147008547008546,
|
| 50078 |
+
"grad_norm": 0.20159313082695007,
|
| 50079 |
+
"learning_rate": 3.401506689996601e-05,
|
| 50080 |
+
"loss": 0.6215,
|
| 50081 |
+
"step": 7153
|
| 50082 |
+
},
|
| 50083 |
+
{
|
| 50084 |
+
"epoch": 8.148148148148149,
|
| 50085 |
+
"grad_norm": 0.21637333929538727,
|
| 50086 |
+
"learning_rate": 3.4010721034225566e-05,
|
| 50087 |
+
"loss": 0.723,
|
| 50088 |
+
"step": 7154
|
| 50089 |
+
},
|
| 50090 |
+
{
|
| 50091 |
+
"epoch": 8.14928774928775,
|
| 50092 |
+
"grad_norm": 0.174230694770813,
|
| 50093 |
+
"learning_rate": 3.4006374855518004e-05,
|
| 50094 |
+
"loss": 0.7396,
|
| 50095 |
+
"step": 7155
|
| 50096 |
+
},
|
| 50097 |
+
{
|
| 50098 |
+
"epoch": 8.15042735042735,
|
| 50099 |
+
"grad_norm": 0.17579050362110138,
|
| 50100 |
+
"learning_rate": 3.4002028363994276e-05,
|
| 50101 |
+
"loss": 0.8874,
|
| 50102 |
+
"step": 7156
|
| 50103 |
+
},
|
| 50104 |
+
{
|
| 50105 |
+
"epoch": 8.151566951566952,
|
| 50106 |
+
"grad_norm": 0.18470925092697144,
|
| 50107 |
+
"learning_rate": 3.399768155980534e-05,
|
| 50108 |
+
"loss": 0.6751,
|
| 50109 |
+
"step": 7157
|
| 50110 |
+
},
|
| 50111 |
+
{
|
| 50112 |
+
"epoch": 8.152706552706553,
|
| 50113 |
+
"grad_norm": 0.1878298968076706,
|
| 50114 |
+
"learning_rate": 3.3993334443102184e-05,
|
| 50115 |
+
"loss": 0.7811,
|
| 50116 |
+
"step": 7158
|
| 50117 |
+
},
|
| 50118 |
+
{
|
| 50119 |
+
"epoch": 8.153846153846153,
|
| 50120 |
+
"grad_norm": 0.16194337606430054,
|
| 50121 |
+
"learning_rate": 3.398898701403579e-05,
|
| 50122 |
+
"loss": 0.9992,
|
| 50123 |
+
"step": 7159
|
| 50124 |
+
},
|
| 50125 |
+
{
|
| 50126 |
+
"epoch": 8.154985754985756,
|
| 50127 |
+
"grad_norm": 0.25477665662765503,
|
| 50128 |
+
"learning_rate": 3.398463927275716e-05,
|
| 50129 |
+
"loss": 0.5095,
|
| 50130 |
+
"step": 7160
|
| 50131 |
+
},
|
| 50132 |
+
{
|
| 50133 |
+
"epoch": 8.156125356125356,
|
| 50134 |
+
"grad_norm": 0.21325922012329102,
|
| 50135 |
+
"learning_rate": 3.39802912194173e-05,
|
| 50136 |
+
"loss": 0.6449,
|
| 50137 |
+
"step": 7161
|
| 50138 |
+
},
|
| 50139 |
+
{
|
| 50140 |
+
"epoch": 8.157264957264957,
|
| 50141 |
+
"grad_norm": 0.20713818073272705,
|
| 50142 |
+
"learning_rate": 3.397594285416723e-05,
|
| 50143 |
+
"loss": 0.7,
|
| 50144 |
+
"step": 7162
|
| 50145 |
+
},
|
| 50146 |
+
{
|
| 50147 |
+
"epoch": 8.158404558404559,
|
| 50148 |
+
"grad_norm": 0.18533176183700562,
|
| 50149 |
+
"learning_rate": 3.397159417715797e-05,
|
| 50150 |
+
"loss": 0.7912,
|
| 50151 |
+
"step": 7163
|
| 50152 |
+
},
|
| 50153 |
+
{
|
| 50154 |
+
"epoch": 8.15954415954416,
|
| 50155 |
+
"grad_norm": 0.18421204388141632,
|
| 50156 |
+
"learning_rate": 3.396724518854059e-05,
|
| 50157 |
+
"loss": 0.8206,
|
| 50158 |
+
"step": 7164
|
| 50159 |
+
},
|
| 50160 |
+
{
|
| 50161 |
+
"epoch": 8.16068376068376,
|
| 50162 |
+
"grad_norm": 0.19567228853702545,
|
| 50163 |
+
"learning_rate": 3.3962895888466105e-05,
|
| 50164 |
+
"loss": 0.6666,
|
| 50165 |
+
"step": 7165
|
| 50166 |
+
},
|
| 50167 |
+
{
|
| 50168 |
+
"epoch": 8.161823361823362,
|
| 50169 |
+
"grad_norm": 0.18482913076877594,
|
| 50170 |
+
"learning_rate": 3.3958546277085615e-05,
|
| 50171 |
+
"loss": 0.7562,
|
| 50172 |
+
"step": 7166
|
| 50173 |
+
},
|
| 50174 |
+
{
|
| 50175 |
+
"epoch": 8.162962962962963,
|
| 50176 |
+
"grad_norm": 0.24270056188106537,
|
| 50177 |
+
"learning_rate": 3.3954196354550174e-05,
|
| 50178 |
+
"loss": 0.4988,
|
| 50179 |
+
"step": 7167
|
| 50180 |
+
},
|
| 50181 |
+
{
|
| 50182 |
+
"epoch": 8.164102564102564,
|
| 50183 |
+
"grad_norm": 0.23909823596477509,
|
| 50184 |
+
"learning_rate": 3.3949846121010865e-05,
|
| 50185 |
+
"loss": 0.6893,
|
| 50186 |
+
"step": 7168
|
| 50187 |
+
},
|
| 50188 |
+
{
|
| 50189 |
+
"epoch": 8.165242165242166,
|
| 50190 |
+
"grad_norm": 0.16294808685779572,
|
| 50191 |
+
"learning_rate": 3.3945495576618785e-05,
|
| 50192 |
+
"loss": 0.8472,
|
| 50193 |
+
"step": 7169
|
| 50194 |
+
},
|
| 50195 |
+
{
|
| 50196 |
+
"epoch": 8.166381766381766,
|
| 50197 |
+
"grad_norm": 0.19857490062713623,
|
| 50198 |
+
"learning_rate": 3.3941144721525046e-05,
|
| 50199 |
+
"loss": 0.8641,
|
| 50200 |
+
"step": 7170
|
| 50201 |
+
},
|
| 50202 |
+
{
|
| 50203 |
+
"epoch": 8.167521367521367,
|
| 50204 |
+
"grad_norm": 0.19892112910747528,
|
| 50205 |
+
"learning_rate": 3.393679355588077e-05,
|
| 50206 |
+
"loss": 0.7258,
|
| 50207 |
+
"step": 7171
|
| 50208 |
+
},
|
| 50209 |
+
{
|
| 50210 |
+
"epoch": 8.16866096866097,
|
| 50211 |
+
"grad_norm": 0.23370476067066193,
|
| 50212 |
+
"learning_rate": 3.3932442079837066e-05,
|
| 50213 |
+
"loss": 0.6543,
|
| 50214 |
+
"step": 7172
|
| 50215 |
+
},
|
| 50216 |
+
{
|
| 50217 |
+
"epoch": 8.16980056980057,
|
| 50218 |
+
"grad_norm": 0.23885028064250946,
|
| 50219 |
+
"learning_rate": 3.392809029354509e-05,
|
| 50220 |
+
"loss": 0.7123,
|
| 50221 |
+
"step": 7173
|
| 50222 |
+
},
|
| 50223 |
+
{
|
| 50224 |
+
"epoch": 8.17094017094017,
|
| 50225 |
+
"grad_norm": 0.2139512449502945,
|
| 50226 |
+
"learning_rate": 3.3923738197155984e-05,
|
| 50227 |
+
"loss": 0.7092,
|
| 50228 |
+
"step": 7174
|
| 50229 |
+
},
|
| 50230 |
+
{
|
| 50231 |
+
"epoch": 8.172079772079773,
|
| 50232 |
+
"grad_norm": 0.2665398120880127,
|
| 50233 |
+
"learning_rate": 3.391938579082091e-05,
|
| 50234 |
+
"loss": 0.6516,
|
| 50235 |
+
"step": 7175
|
| 50236 |
+
},
|
| 50237 |
+
{
|
| 50238 |
+
"epoch": 8.173219373219373,
|
| 50239 |
+
"grad_norm": 0.1842581331729889,
|
| 50240 |
+
"learning_rate": 3.391503307469104e-05,
|
| 50241 |
+
"loss": 0.8499,
|
| 50242 |
+
"step": 7176
|
| 50243 |
+
},
|
| 50244 |
+
{
|
| 50245 |
+
"epoch": 8.174358974358974,
|
| 50246 |
+
"grad_norm": 0.21950329840183258,
|
| 50247 |
+
"learning_rate": 3.391068004891756e-05,
|
| 50248 |
+
"loss": 0.6333,
|
| 50249 |
+
"step": 7177
|
| 50250 |
+
},
|
| 50251 |
+
{
|
| 50252 |
+
"epoch": 8.175498575498576,
|
| 50253 |
+
"grad_norm": 0.19671662151813507,
|
| 50254 |
+
"learning_rate": 3.390632671365165e-05,
|
| 50255 |
+
"loss": 0.5673,
|
| 50256 |
+
"step": 7178
|
| 50257 |
+
},
|
| 50258 |
+
{
|
| 50259 |
+
"epoch": 8.176638176638177,
|
| 50260 |
+
"grad_norm": 0.16526201367378235,
|
| 50261 |
+
"learning_rate": 3.390197306904453e-05,
|
| 50262 |
+
"loss": 0.8273,
|
| 50263 |
+
"step": 7179
|
| 50264 |
+
},
|
| 50265 |
+
{
|
| 50266 |
+
"epoch": 8.177777777777777,
|
| 50267 |
+
"grad_norm": 0.19709545373916626,
|
| 50268 |
+
"learning_rate": 3.3897619115247395e-05,
|
| 50269 |
+
"loss": 0.6213,
|
| 50270 |
+
"step": 7180
|
| 50271 |
+
},
|
| 50272 |
+
{
|
| 50273 |
+
"epoch": 8.17891737891738,
|
| 50274 |
+
"grad_norm": 0.20775169134140015,
|
| 50275 |
+
"learning_rate": 3.3893264852411475e-05,
|
| 50276 |
+
"loss": 0.6329,
|
| 50277 |
+
"step": 7181
|
| 50278 |
+
},
|
| 50279 |
+
{
|
| 50280 |
+
"epoch": 8.18005698005698,
|
| 50281 |
+
"grad_norm": 0.24375586211681366,
|
| 50282 |
+
"learning_rate": 3.3888910280688024e-05,
|
| 50283 |
+
"loss": 0.494,
|
| 50284 |
+
"step": 7182
|
| 50285 |
+
},
|
| 50286 |
+
{
|
| 50287 |
+
"epoch": 8.18119658119658,
|
| 50288 |
+
"grad_norm": 0.22048993408679962,
|
| 50289 |
+
"learning_rate": 3.3884555400228266e-05,
|
| 50290 |
+
"loss": 0.7548,
|
| 50291 |
+
"step": 7183
|
| 50292 |
+
},
|
| 50293 |
+
{
|
| 50294 |
+
"epoch": 8.182336182336183,
|
| 50295 |
+
"grad_norm": 0.20597326755523682,
|
| 50296 |
+
"learning_rate": 3.388020021118347e-05,
|
| 50297 |
+
"loss": 0.7958,
|
| 50298 |
+
"step": 7184
|
| 50299 |
+
},
|
| 50300 |
+
{
|
| 50301 |
+
"epoch": 8.183475783475783,
|
| 50302 |
+
"grad_norm": 0.2033444046974182,
|
| 50303 |
+
"learning_rate": 3.3875844713704905e-05,
|
| 50304 |
+
"loss": 0.7194,
|
| 50305 |
+
"step": 7185
|
| 50306 |
+
},
|
| 50307 |
+
{
|
| 50308 |
+
"epoch": 8.184615384615384,
|
| 50309 |
+
"grad_norm": 0.23415708541870117,
|
| 50310 |
+
"learning_rate": 3.3871488907943835e-05,
|
| 50311 |
+
"loss": 0.709,
|
| 50312 |
+
"step": 7186
|
| 50313 |
+
},
|
| 50314 |
+
{
|
| 50315 |
+
"epoch": 8.185754985754986,
|
| 50316 |
+
"grad_norm": 0.1721237301826477,
|
| 50317 |
+
"learning_rate": 3.386713279405156e-05,
|
| 50318 |
+
"loss": 0.8547,
|
| 50319 |
+
"step": 7187
|
| 50320 |
+
},
|
| 50321 |
+
{
|
| 50322 |
+
"epoch": 8.186894586894587,
|
| 50323 |
+
"grad_norm": 0.19792774319648743,
|
| 50324 |
+
"learning_rate": 3.3862776372179384e-05,
|
| 50325 |
+
"loss": 0.7481,
|
| 50326 |
+
"step": 7188
|
| 50327 |
+
},
|
| 50328 |
+
{
|
| 50329 |
+
"epoch": 8.188034188034187,
|
| 50330 |
+
"grad_norm": 0.19219958782196045,
|
| 50331 |
+
"learning_rate": 3.38584196424786e-05,
|
| 50332 |
+
"loss": 0.6374,
|
| 50333 |
+
"step": 7189
|
| 50334 |
+
},
|
| 50335 |
+
{
|
| 50336 |
+
"epoch": 8.18917378917379,
|
| 50337 |
+
"grad_norm": 0.19490176439285278,
|
| 50338 |
+
"learning_rate": 3.385406260510056e-05,
|
| 50339 |
+
"loss": 0.7085,
|
| 50340 |
+
"step": 7190
|
| 50341 |
+
},
|
| 50342 |
+
{
|
| 50343 |
+
"epoch": 8.19031339031339,
|
| 50344 |
+
"grad_norm": 0.22433261573314667,
|
| 50345 |
+
"learning_rate": 3.384970526019656e-05,
|
| 50346 |
+
"loss": 0.64,
|
| 50347 |
+
"step": 7191
|
| 50348 |
+
},
|
| 50349 |
+
{
|
| 50350 |
+
"epoch": 8.19145299145299,
|
| 50351 |
+
"grad_norm": 0.2058522254228592,
|
| 50352 |
+
"learning_rate": 3.384534760791797e-05,
|
| 50353 |
+
"loss": 0.7725,
|
| 50354 |
+
"step": 7192
|
| 50355 |
+
},
|
| 50356 |
+
{
|
| 50357 |
+
"epoch": 8.192592592592593,
|
| 50358 |
+
"grad_norm": 0.18015679717063904,
|
| 50359 |
+
"learning_rate": 3.384098964841612e-05,
|
| 50360 |
+
"loss": 0.6959,
|
| 50361 |
+
"step": 7193
|
| 50362 |
+
},
|
| 50363 |
+
{
|
| 50364 |
+
"epoch": 8.193732193732194,
|
| 50365 |
+
"grad_norm": 0.19807380437850952,
|
| 50366 |
+
"learning_rate": 3.38366313818424e-05,
|
| 50367 |
+
"loss": 0.7339,
|
| 50368 |
+
"step": 7194
|
| 50369 |
+
},
|
| 50370 |
+
{
|
| 50371 |
+
"epoch": 8.194871794871794,
|
| 50372 |
+
"grad_norm": 0.2094758152961731,
|
| 50373 |
+
"learning_rate": 3.383227280834816e-05,
|
| 50374 |
+
"loss": 0.7301,
|
| 50375 |
+
"step": 7195
|
| 50376 |
+
},
|
| 50377 |
+
{
|
| 50378 |
+
"epoch": 8.196011396011396,
|
| 50379 |
+
"grad_norm": 0.26335787773132324,
|
| 50380 |
+
"learning_rate": 3.382791392808481e-05,
|
| 50381 |
+
"loss": 0.7256,
|
| 50382 |
+
"step": 7196
|
| 50383 |
+
},
|
| 50384 |
+
{
|
| 50385 |
+
"epoch": 8.197150997150997,
|
| 50386 |
+
"grad_norm": 0.2601282000541687,
|
| 50387 |
+
"learning_rate": 3.3823554741203716e-05,
|
| 50388 |
+
"loss": 0.4856,
|
| 50389 |
+
"step": 7197
|
| 50390 |
+
},
|
| 50391 |
+
{
|
| 50392 |
+
"epoch": 8.198290598290598,
|
| 50393 |
+
"grad_norm": 0.21603776514530182,
|
| 50394 |
+
"learning_rate": 3.381919524785631e-05,
|
| 50395 |
+
"loss": 0.7389,
|
| 50396 |
+
"step": 7198
|
| 50397 |
+
},
|
| 50398 |
+
{
|
| 50399 |
+
"epoch": 8.1994301994302,
|
| 50400 |
+
"grad_norm": 0.24947494268417358,
|
| 50401 |
+
"learning_rate": 3.3814835448194e-05,
|
| 50402 |
+
"loss": 0.4968,
|
| 50403 |
+
"step": 7199
|
| 50404 |
+
},
|
| 50405 |
+
{
|
| 50406 |
+
"epoch": 8.2005698005698,
|
| 50407 |
+
"grad_norm": 0.23176923394203186,
|
| 50408 |
+
"learning_rate": 3.381047534236822e-05,
|
| 50409 |
+
"loss": 0.6624,
|
| 50410 |
+
"step": 7200
|
| 50411 |
}
|
| 50412 |
],
|
| 50413 |
"logging_steps": 1,
|
|
|
|
| 50427 |
"attributes": {}
|
| 50428 |
}
|
| 50429 |
},
|
| 50430 |
+
"total_flos": 4.0257197103268086e+19,
|
| 50431 |
"train_batch_size": 8,
|
| 50432 |
"trial_name": null,
|
| 50433 |
"trial_params": null
|