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:
# 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 11700, 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 sha256:31dc6af81f60afbf72c1d6b6517f7db3cefd0077cfc6ec2c9ef4c45ca24d454d
|
| 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 sha256:7c7f74c2f77e139810b3b4907dd3c12f391e56210c6b1c25a5254ad3df23c3d0
|
| 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 sha256:20ea3a198ff666cb4ace1c684b598fe43fc7c3c276b83efc553a1b787e12a304
|
| 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 sha256:8f671294e462dfbe328bbe4c87252e126fddc2297376bb75c9d81010a634ffe9
|
| 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,
|
|
@@ -79808,6 +79808,2106 @@
|
|
| 79808 |
"learning_rate": 1.4746952210208604e-05,
|
| 79809 |
"loss": 0.7257,
|
| 79810 |
"step": 11400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79811 |
}
|
| 79812 |
],
|
| 79813 |
"logging_steps": 1,
|
|
@@ -79827,7 +81927,7 @@
|
|
| 79827 |
"attributes": {}
|
| 79828 |
}
|
| 79829 |
},
|
| 79830 |
-
"total_flos": 6.
|
| 79831 |
"train_batch_size": 8,
|
| 79832 |
"trial_name": null,
|
| 79833 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.325925925925926,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 11700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 79808 |
"learning_rate": 1.4746952210208604e-05,
|
| 79809 |
"loss": 0.7257,
|
| 79810 |
"step": 11400
|
| 79811 |
+
},
|
| 79812 |
+
{
|
| 79813 |
+
"epoch": 12.985754985754985,
|
| 79814 |
+
"grad_norm": 0.2548161447048187,
|
| 79815 |
+
"learning_rate": 1.474270307201156e-05,
|
| 79816 |
+
"loss": 0.5794,
|
| 79817 |
+
"step": 11401
|
| 79818 |
+
},
|
| 79819 |
+
{
|
| 79820 |
+
"epoch": 12.986894586894588,
|
| 79821 |
+
"grad_norm": 0.23451417684555054,
|
| 79822 |
+
"learning_rate": 1.4738454290078637e-05,
|
| 79823 |
+
"loss": 0.5691,
|
| 79824 |
+
"step": 11402
|
| 79825 |
+
},
|
| 79826 |
+
{
|
| 79827 |
+
"epoch": 12.988034188034188,
|
| 79828 |
+
"grad_norm": 0.24653545022010803,
|
| 79829 |
+
"learning_rate": 1.4734205864557412e-05,
|
| 79830 |
+
"loss": 0.63,
|
| 79831 |
+
"step": 11403
|
| 79832 |
+
},
|
| 79833 |
+
{
|
| 79834 |
+
"epoch": 12.989173789173789,
|
| 79835 |
+
"grad_norm": 0.2059410810470581,
|
| 79836 |
+
"learning_rate": 1.472995779559546e-05,
|
| 79837 |
+
"loss": 0.8472,
|
| 79838 |
+
"step": 11404
|
| 79839 |
+
},
|
| 79840 |
+
{
|
| 79841 |
+
"epoch": 12.990313390313391,
|
| 79842 |
+
"grad_norm": 0.24840520322322845,
|
| 79843 |
+
"learning_rate": 1.4725710083340311e-05,
|
| 79844 |
+
"loss": 0.7161,
|
| 79845 |
+
"step": 11405
|
| 79846 |
+
},
|
| 79847 |
+
{
|
| 79848 |
+
"epoch": 12.991452991452991,
|
| 79849 |
+
"grad_norm": 0.19748952984809875,
|
| 79850 |
+
"learning_rate": 1.472146272793951e-05,
|
| 79851 |
+
"loss": 0.6585,
|
| 79852 |
+
"step": 11406
|
| 79853 |
+
},
|
| 79854 |
+
{
|
| 79855 |
+
"epoch": 12.992592592592592,
|
| 79856 |
+
"grad_norm": 0.19665081799030304,
|
| 79857 |
+
"learning_rate": 1.4717215729540568e-05,
|
| 79858 |
+
"loss": 0.863,
|
| 79859 |
+
"step": 11407
|
| 79860 |
+
},
|
| 79861 |
+
{
|
| 79862 |
+
"epoch": 12.993732193732194,
|
| 79863 |
+
"grad_norm": 0.23738694190979004,
|
| 79864 |
+
"learning_rate": 1.471296908829101e-05,
|
| 79865 |
+
"loss": 0.5315,
|
| 79866 |
+
"step": 11408
|
| 79867 |
+
},
|
| 79868 |
+
{
|
| 79869 |
+
"epoch": 12.994871794871795,
|
| 79870 |
+
"grad_norm": 0.22886839509010315,
|
| 79871 |
+
"learning_rate": 1.4708722804338315e-05,
|
| 79872 |
+
"loss": 0.6378,
|
| 79873 |
+
"step": 11409
|
| 79874 |
+
},
|
| 79875 |
+
{
|
| 79876 |
+
"epoch": 12.996011396011395,
|
| 79877 |
+
"grad_norm": 0.20925356447696686,
|
| 79878 |
+
"learning_rate": 1.4704476877829987e-05,
|
| 79879 |
+
"loss": 0.7843,
|
| 79880 |
+
"step": 11410
|
| 79881 |
+
},
|
| 79882 |
+
{
|
| 79883 |
+
"epoch": 12.997150997150998,
|
| 79884 |
+
"grad_norm": 0.29935958981513977,
|
| 79885 |
+
"learning_rate": 1.4700231308913483e-05,
|
| 79886 |
+
"loss": 0.5282,
|
| 79887 |
+
"step": 11411
|
| 79888 |
+
},
|
| 79889 |
+
{
|
| 79890 |
+
"epoch": 12.998290598290598,
|
| 79891 |
+
"grad_norm": 0.2766572833061218,
|
| 79892 |
+
"learning_rate": 1.4695986097736279e-05,
|
| 79893 |
+
"loss": 0.5435,
|
| 79894 |
+
"step": 11412
|
| 79895 |
+
},
|
| 79896 |
+
{
|
| 79897 |
+
"epoch": 12.999430199430199,
|
| 79898 |
+
"grad_norm": 0.2087930589914322,
|
| 79899 |
+
"learning_rate": 1.4691741244445807e-05,
|
| 79900 |
+
"loss": 0.901,
|
| 79901 |
+
"step": 11413
|
| 79902 |
+
},
|
| 79903 |
+
{
|
| 79904 |
+
"epoch": 13.0,
|
| 79905 |
+
"grad_norm": 0.2996289134025574,
|
| 79906 |
+
"learning_rate": 1.46874967491895e-05,
|
| 79907 |
+
"loss": 0.9528,
|
| 79908 |
+
"step": 11414
|
| 79909 |
+
},
|
| 79910 |
+
{
|
| 79911 |
+
"epoch": 13.0011396011396,
|
| 79912 |
+
"grad_norm": 0.21519289910793304,
|
| 79913 |
+
"learning_rate": 1.4683252612114806e-05,
|
| 79914 |
+
"loss": 0.7741,
|
| 79915 |
+
"step": 11415
|
| 79916 |
+
},
|
| 79917 |
+
{
|
| 79918 |
+
"epoch": 13.002279202279203,
|
| 79919 |
+
"grad_norm": 0.2124188244342804,
|
| 79920 |
+
"learning_rate": 1.4679008833369113e-05,
|
| 79921 |
+
"loss": 0.7446,
|
| 79922 |
+
"step": 11416
|
| 79923 |
+
},
|
| 79924 |
+
{
|
| 79925 |
+
"epoch": 13.003418803418803,
|
| 79926 |
+
"grad_norm": 0.17165492475032806,
|
| 79927 |
+
"learning_rate": 1.4674765413099828e-05,
|
| 79928 |
+
"loss": 0.7705,
|
| 79929 |
+
"step": 11417
|
| 79930 |
+
},
|
| 79931 |
+
{
|
| 79932 |
+
"epoch": 13.004558404558404,
|
| 79933 |
+
"grad_norm": 0.15280818939208984,
|
| 79934 |
+
"learning_rate": 1.4670522351454332e-05,
|
| 79935 |
+
"loss": 0.6471,
|
| 79936 |
+
"step": 11418
|
| 79937 |
+
},
|
| 79938 |
+
{
|
| 79939 |
+
"epoch": 13.005698005698006,
|
| 79940 |
+
"grad_norm": 0.17679402232170105,
|
| 79941 |
+
"learning_rate": 1.4666279648580005e-05,
|
| 79942 |
+
"loss": 0.7578,
|
| 79943 |
+
"step": 11419
|
| 79944 |
+
},
|
| 79945 |
+
{
|
| 79946 |
+
"epoch": 13.006837606837607,
|
| 79947 |
+
"grad_norm": 0.21650585532188416,
|
| 79948 |
+
"learning_rate": 1.46620373046242e-05,
|
| 79949 |
+
"loss": 0.6234,
|
| 79950 |
+
"step": 11420
|
| 79951 |
+
},
|
| 79952 |
+
{
|
| 79953 |
+
"epoch": 13.007977207977207,
|
| 79954 |
+
"grad_norm": 0.18113601207733154,
|
| 79955 |
+
"learning_rate": 1.4657795319734274e-05,
|
| 79956 |
+
"loss": 0.5055,
|
| 79957 |
+
"step": 11421
|
| 79958 |
+
},
|
| 79959 |
+
{
|
| 79960 |
+
"epoch": 13.00911680911681,
|
| 79961 |
+
"grad_norm": 0.23416933417320251,
|
| 79962 |
+
"learning_rate": 1.4653553694057553e-05,
|
| 79963 |
+
"loss": 0.5932,
|
| 79964 |
+
"step": 11422
|
| 79965 |
+
},
|
| 79966 |
+
{
|
| 79967 |
+
"epoch": 13.01025641025641,
|
| 79968 |
+
"grad_norm": 0.18027664721012115,
|
| 79969 |
+
"learning_rate": 1.4649312427741366e-05,
|
| 79970 |
+
"loss": 0.6091,
|
| 79971 |
+
"step": 11423
|
| 79972 |
+
},
|
| 79973 |
+
{
|
| 79974 |
+
"epoch": 13.01139601139601,
|
| 79975 |
+
"grad_norm": 0.17871034145355225,
|
| 79976 |
+
"learning_rate": 1.4645071520933027e-05,
|
| 79977 |
+
"loss": 0.8529,
|
| 79978 |
+
"step": 11424
|
| 79979 |
+
},
|
| 79980 |
+
{
|
| 79981 |
+
"epoch": 13.012535612535613,
|
| 79982 |
+
"grad_norm": 0.1923864185810089,
|
| 79983 |
+
"learning_rate": 1.4640830973779818e-05,
|
| 79984 |
+
"loss": 0.8046,
|
| 79985 |
+
"step": 11425
|
| 79986 |
+
},
|
| 79987 |
+
{
|
| 79988 |
+
"epoch": 13.013675213675214,
|
| 79989 |
+
"grad_norm": 0.2389516979455948,
|
| 79990 |
+
"learning_rate": 1.4636590786429043e-05,
|
| 79991 |
+
"loss": 0.5703,
|
| 79992 |
+
"step": 11426
|
| 79993 |
+
},
|
| 79994 |
+
{
|
| 79995 |
+
"epoch": 13.014814814814814,
|
| 79996 |
+
"grad_norm": 0.24037589132785797,
|
| 79997 |
+
"learning_rate": 1.4632350959027976e-05,
|
| 79998 |
+
"loss": 0.5333,
|
| 79999 |
+
"step": 11427
|
| 80000 |
+
},
|
| 80001 |
+
{
|
| 80002 |
+
"epoch": 13.015954415954416,
|
| 80003 |
+
"grad_norm": 0.16341760754585266,
|
| 80004 |
+
"learning_rate": 1.4628111491723868e-05,
|
| 80005 |
+
"loss": 0.8563,
|
| 80006 |
+
"step": 11428
|
| 80007 |
+
},
|
| 80008 |
+
{
|
| 80009 |
+
"epoch": 13.017094017094017,
|
| 80010 |
+
"grad_norm": 0.21553219854831696,
|
| 80011 |
+
"learning_rate": 1.4623872384663973e-05,
|
| 80012 |
+
"loss": 0.6649,
|
| 80013 |
+
"step": 11429
|
| 80014 |
+
},
|
| 80015 |
+
{
|
| 80016 |
+
"epoch": 13.018233618233618,
|
| 80017 |
+
"grad_norm": 0.2237376719713211,
|
| 80018 |
+
"learning_rate": 1.461963363799552e-05,
|
| 80019 |
+
"loss": 0.5996,
|
| 80020 |
+
"step": 11430
|
| 80021 |
+
},
|
| 80022 |
+
{
|
| 80023 |
+
"epoch": 13.01937321937322,
|
| 80024 |
+
"grad_norm": 0.19841177761554718,
|
| 80025 |
+
"learning_rate": 1.461539525186574e-05,
|
| 80026 |
+
"loss": 0.8854,
|
| 80027 |
+
"step": 11431
|
| 80028 |
+
},
|
| 80029 |
+
{
|
| 80030 |
+
"epoch": 13.02051282051282,
|
| 80031 |
+
"grad_norm": 0.22623202204704285,
|
| 80032 |
+
"learning_rate": 1.461115722642184e-05,
|
| 80033 |
+
"loss": 0.6766,
|
| 80034 |
+
"step": 11432
|
| 80035 |
+
},
|
| 80036 |
+
{
|
| 80037 |
+
"epoch": 13.021652421652421,
|
| 80038 |
+
"grad_norm": 0.22455154359340668,
|
| 80039 |
+
"learning_rate": 1.4606919561811019e-05,
|
| 80040 |
+
"loss": 0.6496,
|
| 80041 |
+
"step": 11433
|
| 80042 |
+
},
|
| 80043 |
+
{
|
| 80044 |
+
"epoch": 13.022792022792023,
|
| 80045 |
+
"grad_norm": 0.24419784545898438,
|
| 80046 |
+
"learning_rate": 1.4602682258180461e-05,
|
| 80047 |
+
"loss": 0.4354,
|
| 80048 |
+
"step": 11434
|
| 80049 |
+
},
|
| 80050 |
+
{
|
| 80051 |
+
"epoch": 13.023931623931624,
|
| 80052 |
+
"grad_norm": 0.200229212641716,
|
| 80053 |
+
"learning_rate": 1.4598445315677345e-05,
|
| 80054 |
+
"loss": 0.7056,
|
| 80055 |
+
"step": 11435
|
| 80056 |
+
},
|
| 80057 |
+
{
|
| 80058 |
+
"epoch": 13.025071225071224,
|
| 80059 |
+
"grad_norm": 0.18830811977386475,
|
| 80060 |
+
"learning_rate": 1.4594208734448811e-05,
|
| 80061 |
+
"loss": 0.4923,
|
| 80062 |
+
"step": 11436
|
| 80063 |
+
},
|
| 80064 |
+
{
|
| 80065 |
+
"epoch": 13.026210826210827,
|
| 80066 |
+
"grad_norm": 0.1918337345123291,
|
| 80067 |
+
"learning_rate": 1.4589972514642048e-05,
|
| 80068 |
+
"loss": 0.597,
|
| 80069 |
+
"step": 11437
|
| 80070 |
+
},
|
| 80071 |
+
{
|
| 80072 |
+
"epoch": 13.027350427350427,
|
| 80073 |
+
"grad_norm": 0.1658741682767868,
|
| 80074 |
+
"learning_rate": 1.4585736656404152e-05,
|
| 80075 |
+
"loss": 0.7869,
|
| 80076 |
+
"step": 11438
|
| 80077 |
+
},
|
| 80078 |
+
{
|
| 80079 |
+
"epoch": 13.028490028490028,
|
| 80080 |
+
"grad_norm": 0.2372065633535385,
|
| 80081 |
+
"learning_rate": 1.4581501159882267e-05,
|
| 80082 |
+
"loss": 0.5721,
|
| 80083 |
+
"step": 11439
|
| 80084 |
+
},
|
| 80085 |
+
{
|
| 80086 |
+
"epoch": 13.02962962962963,
|
| 80087 |
+
"grad_norm": 0.21426714956760406,
|
| 80088 |
+
"learning_rate": 1.457726602522349e-05,
|
| 80089 |
+
"loss": 0.6547,
|
| 80090 |
+
"step": 11440
|
| 80091 |
+
},
|
| 80092 |
+
{
|
| 80093 |
+
"epoch": 13.03076923076923,
|
| 80094 |
+
"grad_norm": 0.18508793413639069,
|
| 80095 |
+
"learning_rate": 1.4573031252574943e-05,
|
| 80096 |
+
"loss": 0.8496,
|
| 80097 |
+
"step": 11441
|
| 80098 |
+
},
|
| 80099 |
+
{
|
| 80100 |
+
"epoch": 13.031908831908831,
|
| 80101 |
+
"grad_norm": 0.19948071241378784,
|
| 80102 |
+
"learning_rate": 1.4568796842083682e-05,
|
| 80103 |
+
"loss": 0.7428,
|
| 80104 |
+
"step": 11442
|
| 80105 |
+
},
|
| 80106 |
+
{
|
| 80107 |
+
"epoch": 13.033048433048434,
|
| 80108 |
+
"grad_norm": 0.2422424852848053,
|
| 80109 |
+
"learning_rate": 1.4564562793896797e-05,
|
| 80110 |
+
"loss": 0.7462,
|
| 80111 |
+
"step": 11443
|
| 80112 |
+
},
|
| 80113 |
+
{
|
| 80114 |
+
"epoch": 13.034188034188034,
|
| 80115 |
+
"grad_norm": 0.1996956318616867,
|
| 80116 |
+
"learning_rate": 1.4560329108161338e-05,
|
| 80117 |
+
"loss": 0.4969,
|
| 80118 |
+
"step": 11444
|
| 80119 |
+
},
|
| 80120 |
+
{
|
| 80121 |
+
"epoch": 13.035327635327635,
|
| 80122 |
+
"grad_norm": 0.23708593845367432,
|
| 80123 |
+
"learning_rate": 1.4556095785024371e-05,
|
| 80124 |
+
"loss": 0.7164,
|
| 80125 |
+
"step": 11445
|
| 80126 |
+
},
|
| 80127 |
+
{
|
| 80128 |
+
"epoch": 13.036467236467237,
|
| 80129 |
+
"grad_norm": 0.21722626686096191,
|
| 80130 |
+
"learning_rate": 1.4551862824632907e-05,
|
| 80131 |
+
"loss": 0.5624,
|
| 80132 |
+
"step": 11446
|
| 80133 |
+
},
|
| 80134 |
+
{
|
| 80135 |
+
"epoch": 13.037606837606837,
|
| 80136 |
+
"grad_norm": 0.3021351099014282,
|
| 80137 |
+
"learning_rate": 1.4547630227133972e-05,
|
| 80138 |
+
"loss": 0.4409,
|
| 80139 |
+
"step": 11447
|
| 80140 |
+
},
|
| 80141 |
+
{
|
| 80142 |
+
"epoch": 13.038746438746438,
|
| 80143 |
+
"grad_norm": 0.22942470014095306,
|
| 80144 |
+
"learning_rate": 1.4543397992674601e-05,
|
| 80145 |
+
"loss": 0.5466,
|
| 80146 |
+
"step": 11448
|
| 80147 |
+
},
|
| 80148 |
+
{
|
| 80149 |
+
"epoch": 13.03988603988604,
|
| 80150 |
+
"grad_norm": 0.2294406145811081,
|
| 80151 |
+
"learning_rate": 1.4539166121401765e-05,
|
| 80152 |
+
"loss": 0.6643,
|
| 80153 |
+
"step": 11449
|
| 80154 |
+
},
|
| 80155 |
+
{
|
| 80156 |
+
"epoch": 13.04102564102564,
|
| 80157 |
+
"grad_norm": 0.2203741818666458,
|
| 80158 |
+
"learning_rate": 1.4534934613462453e-05,
|
| 80159 |
+
"loss": 0.5618,
|
| 80160 |
+
"step": 11450
|
| 80161 |
+
},
|
| 80162 |
+
{
|
| 80163 |
+
"epoch": 13.042165242165241,
|
| 80164 |
+
"grad_norm": 0.21978648006916046,
|
| 80165 |
+
"learning_rate": 1.4530703469003645e-05,
|
| 80166 |
+
"loss": 0.5467,
|
| 80167 |
+
"step": 11451
|
| 80168 |
+
},
|
| 80169 |
+
{
|
| 80170 |
+
"epoch": 13.043304843304844,
|
| 80171 |
+
"grad_norm": 0.17470145225524902,
|
| 80172 |
+
"learning_rate": 1.4526472688172305e-05,
|
| 80173 |
+
"loss": 0.704,
|
| 80174 |
+
"step": 11452
|
| 80175 |
+
},
|
| 80176 |
+
{
|
| 80177 |
+
"epoch": 13.044444444444444,
|
| 80178 |
+
"grad_norm": 0.23567743599414825,
|
| 80179 |
+
"learning_rate": 1.4522242271115361e-05,
|
| 80180 |
+
"loss": 0.5294,
|
| 80181 |
+
"step": 11453
|
| 80182 |
+
},
|
| 80183 |
+
{
|
| 80184 |
+
"epoch": 13.045584045584045,
|
| 80185 |
+
"grad_norm": 0.191808819770813,
|
| 80186 |
+
"learning_rate": 1.451801221797976e-05,
|
| 80187 |
+
"loss": 0.696,
|
| 80188 |
+
"step": 11454
|
| 80189 |
+
},
|
| 80190 |
+
{
|
| 80191 |
+
"epoch": 13.046723646723647,
|
| 80192 |
+
"grad_norm": 0.21488399803638458,
|
| 80193 |
+
"learning_rate": 1.4513782528912418e-05,
|
| 80194 |
+
"loss": 0.575,
|
| 80195 |
+
"step": 11455
|
| 80196 |
+
},
|
| 80197 |
+
{
|
| 80198 |
+
"epoch": 13.047863247863248,
|
| 80199 |
+
"grad_norm": 0.2066238671541214,
|
| 80200 |
+
"learning_rate": 1.4509553204060253e-05,
|
| 80201 |
+
"loss": 0.7023,
|
| 80202 |
+
"step": 11456
|
| 80203 |
+
},
|
| 80204 |
+
{
|
| 80205 |
+
"epoch": 13.049002849002848,
|
| 80206 |
+
"grad_norm": 0.20625387132167816,
|
| 80207 |
+
"learning_rate": 1.4505324243570145e-05,
|
| 80208 |
+
"loss": 0.7823,
|
| 80209 |
+
"step": 11457
|
| 80210 |
+
},
|
| 80211 |
+
{
|
| 80212 |
+
"epoch": 13.05014245014245,
|
| 80213 |
+
"grad_norm": 0.18600556254386902,
|
| 80214 |
+
"learning_rate": 1.4501095647588981e-05,
|
| 80215 |
+
"loss": 0.69,
|
| 80216 |
+
"step": 11458
|
| 80217 |
+
},
|
| 80218 |
+
{
|
| 80219 |
+
"epoch": 13.051282051282051,
|
| 80220 |
+
"grad_norm": 0.21689251065254211,
|
| 80221 |
+
"learning_rate": 1.4496867416263644e-05,
|
| 80222 |
+
"loss": 0.5559,
|
| 80223 |
+
"step": 11459
|
| 80224 |
+
},
|
| 80225 |
+
{
|
| 80226 |
+
"epoch": 13.052421652421652,
|
| 80227 |
+
"grad_norm": 0.23860739171504974,
|
| 80228 |
+
"learning_rate": 1.4492639549740994e-05,
|
| 80229 |
+
"loss": 0.4703,
|
| 80230 |
+
"step": 11460
|
| 80231 |
+
},
|
| 80232 |
+
{
|
| 80233 |
+
"epoch": 13.053561253561254,
|
| 80234 |
+
"grad_norm": 0.23685714602470398,
|
| 80235 |
+
"learning_rate": 1.448841204816786e-05,
|
| 80236 |
+
"loss": 0.7486,
|
| 80237 |
+
"step": 11461
|
| 80238 |
+
},
|
| 80239 |
+
{
|
| 80240 |
+
"epoch": 13.054700854700855,
|
| 80241 |
+
"grad_norm": 0.23470570147037506,
|
| 80242 |
+
"learning_rate": 1.4484184911691079e-05,
|
| 80243 |
+
"loss": 0.7676,
|
| 80244 |
+
"step": 11462
|
| 80245 |
+
},
|
| 80246 |
+
{
|
| 80247 |
+
"epoch": 13.055840455840455,
|
| 80248 |
+
"grad_norm": 0.2473776936531067,
|
| 80249 |
+
"learning_rate": 1.4479958140457479e-05,
|
| 80250 |
+
"loss": 0.5993,
|
| 80251 |
+
"step": 11463
|
| 80252 |
+
},
|
| 80253 |
+
{
|
| 80254 |
+
"epoch": 13.056980056980057,
|
| 80255 |
+
"grad_norm": 0.1980896145105362,
|
| 80256 |
+
"learning_rate": 1.447573173461387e-05,
|
| 80257 |
+
"loss": 0.6698,
|
| 80258 |
+
"step": 11464
|
| 80259 |
+
},
|
| 80260 |
+
{
|
| 80261 |
+
"epoch": 13.058119658119658,
|
| 80262 |
+
"grad_norm": 0.21760006248950958,
|
| 80263 |
+
"learning_rate": 1.447150569430703e-05,
|
| 80264 |
+
"loss": 0.644,
|
| 80265 |
+
"step": 11465
|
| 80266 |
+
},
|
| 80267 |
+
{
|
| 80268 |
+
"epoch": 13.059259259259258,
|
| 80269 |
+
"grad_norm": 0.21926675736904144,
|
| 80270 |
+
"learning_rate": 1.4467280019683755e-05,
|
| 80271 |
+
"loss": 0.5746,
|
| 80272 |
+
"step": 11466
|
| 80273 |
+
},
|
| 80274 |
+
{
|
| 80275 |
+
"epoch": 13.06039886039886,
|
| 80276 |
+
"grad_norm": 0.2303035706281662,
|
| 80277 |
+
"learning_rate": 1.4463054710890805e-05,
|
| 80278 |
+
"loss": 0.5843,
|
| 80279 |
+
"step": 11467
|
| 80280 |
+
},
|
| 80281 |
+
{
|
| 80282 |
+
"epoch": 13.061538461538461,
|
| 80283 |
+
"grad_norm": 0.22751690447330475,
|
| 80284 |
+
"learning_rate": 1.4458829768074956e-05,
|
| 80285 |
+
"loss": 0.5984,
|
| 80286 |
+
"step": 11468
|
| 80287 |
+
},
|
| 80288 |
+
{
|
| 80289 |
+
"epoch": 13.062678062678062,
|
| 80290 |
+
"grad_norm": 0.1822330802679062,
|
| 80291 |
+
"learning_rate": 1.4454605191382914e-05,
|
| 80292 |
+
"loss": 0.7939,
|
| 80293 |
+
"step": 11469
|
| 80294 |
+
},
|
| 80295 |
+
{
|
| 80296 |
+
"epoch": 13.063817663817664,
|
| 80297 |
+
"grad_norm": 0.23645171523094177,
|
| 80298 |
+
"learning_rate": 1.4450380980961441e-05,
|
| 80299 |
+
"loss": 0.5233,
|
| 80300 |
+
"step": 11470
|
| 80301 |
+
},
|
| 80302 |
+
{
|
| 80303 |
+
"epoch": 13.064957264957265,
|
| 80304 |
+
"grad_norm": 0.16785389184951782,
|
| 80305 |
+
"learning_rate": 1.4446157136957263e-05,
|
| 80306 |
+
"loss": 0.7826,
|
| 80307 |
+
"step": 11471
|
| 80308 |
+
},
|
| 80309 |
+
{
|
| 80310 |
+
"epoch": 13.066096866096865,
|
| 80311 |
+
"grad_norm": 0.20599152147769928,
|
| 80312 |
+
"learning_rate": 1.444193365951706e-05,
|
| 80313 |
+
"loss": 0.9462,
|
| 80314 |
+
"step": 11472
|
| 80315 |
+
},
|
| 80316 |
+
{
|
| 80317 |
+
"epoch": 13.067236467236468,
|
| 80318 |
+
"grad_norm": 0.17982584238052368,
|
| 80319 |
+
"learning_rate": 1.4437710548787537e-05,
|
| 80320 |
+
"loss": 0.8866,
|
| 80321 |
+
"step": 11473
|
| 80322 |
+
},
|
| 80323 |
+
{
|
| 80324 |
+
"epoch": 13.068376068376068,
|
| 80325 |
+
"grad_norm": 0.20019139349460602,
|
| 80326 |
+
"learning_rate": 1.4433487804915368e-05,
|
| 80327 |
+
"loss": 0.6199,
|
| 80328 |
+
"step": 11474
|
| 80329 |
+
},
|
| 80330 |
+
{
|
| 80331 |
+
"epoch": 13.069515669515669,
|
| 80332 |
+
"grad_norm": 0.2203243225812912,
|
| 80333 |
+
"learning_rate": 1.442926542804724e-05,
|
| 80334 |
+
"loss": 0.515,
|
| 80335 |
+
"step": 11475
|
| 80336 |
+
},
|
| 80337 |
+
{
|
| 80338 |
+
"epoch": 13.070655270655271,
|
| 80339 |
+
"grad_norm": 0.23264262080192566,
|
| 80340 |
+
"learning_rate": 1.4425043418329782e-05,
|
| 80341 |
+
"loss": 0.6896,
|
| 80342 |
+
"step": 11476
|
| 80343 |
+
},
|
| 80344 |
+
{
|
| 80345 |
+
"epoch": 13.071794871794872,
|
| 80346 |
+
"grad_norm": 0.20378360152244568,
|
| 80347 |
+
"learning_rate": 1.4420821775909649e-05,
|
| 80348 |
+
"loss": 0.6089,
|
| 80349 |
+
"step": 11477
|
| 80350 |
+
},
|
| 80351 |
+
{
|
| 80352 |
+
"epoch": 13.072934472934472,
|
| 80353 |
+
"grad_norm": 0.19463470578193665,
|
| 80354 |
+
"learning_rate": 1.4416600500933466e-05,
|
| 80355 |
+
"loss": 0.6047,
|
| 80356 |
+
"step": 11478
|
| 80357 |
+
},
|
| 80358 |
+
{
|
| 80359 |
+
"epoch": 13.074074074074074,
|
| 80360 |
+
"grad_norm": 0.19807323813438416,
|
| 80361 |
+
"learning_rate": 1.4412379593547864e-05,
|
| 80362 |
+
"loss": 0.7472,
|
| 80363 |
+
"step": 11479
|
| 80364 |
+
},
|
| 80365 |
+
{
|
| 80366 |
+
"epoch": 13.075213675213675,
|
| 80367 |
+
"grad_norm": 0.17974790930747986,
|
| 80368 |
+
"learning_rate": 1.4408159053899412e-05,
|
| 80369 |
+
"loss": 0.8,
|
| 80370 |
+
"step": 11480
|
| 80371 |
+
},
|
| 80372 |
+
{
|
| 80373 |
+
"epoch": 13.076353276353275,
|
| 80374 |
+
"grad_norm": 0.19811110198497772,
|
| 80375 |
+
"learning_rate": 1.4403938882134738e-05,
|
| 80376 |
+
"loss": 0.6622,
|
| 80377 |
+
"step": 11481
|
| 80378 |
+
},
|
| 80379 |
+
{
|
| 80380 |
+
"epoch": 13.077492877492878,
|
| 80381 |
+
"grad_norm": 0.21380451321601868,
|
| 80382 |
+
"learning_rate": 1.4399719078400415e-05,
|
| 80383 |
+
"loss": 0.6306,
|
| 80384 |
+
"step": 11482
|
| 80385 |
+
},
|
| 80386 |
+
{
|
| 80387 |
+
"epoch": 13.078632478632478,
|
| 80388 |
+
"grad_norm": 0.2382928878068924,
|
| 80389 |
+
"learning_rate": 1.4395499642842986e-05,
|
| 80390 |
+
"loss": 0.6166,
|
| 80391 |
+
"step": 11483
|
| 80392 |
+
},
|
| 80393 |
+
{
|
| 80394 |
+
"epoch": 13.079772079772079,
|
| 80395 |
+
"grad_norm": 0.23316870629787445,
|
| 80396 |
+
"learning_rate": 1.4391280575609018e-05,
|
| 80397 |
+
"loss": 0.518,
|
| 80398 |
+
"step": 11484
|
| 80399 |
+
},
|
| 80400 |
+
{
|
| 80401 |
+
"epoch": 13.080911680911681,
|
| 80402 |
+
"grad_norm": 0.21876977384090424,
|
| 80403 |
+
"learning_rate": 1.4387061876845051e-05,
|
| 80404 |
+
"loss": 0.5918,
|
| 80405 |
+
"step": 11485
|
| 80406 |
+
},
|
| 80407 |
+
{
|
| 80408 |
+
"epoch": 13.082051282051282,
|
| 80409 |
+
"grad_norm": 0.2160615772008896,
|
| 80410 |
+
"learning_rate": 1.4382843546697619e-05,
|
| 80411 |
+
"loss": 0.666,
|
| 80412 |
+
"step": 11486
|
| 80413 |
+
},
|
| 80414 |
+
{
|
| 80415 |
+
"epoch": 13.083190883190884,
|
| 80416 |
+
"grad_norm": 0.21719148755073547,
|
| 80417 |
+
"learning_rate": 1.437862558531322e-05,
|
| 80418 |
+
"loss": 0.7148,
|
| 80419 |
+
"step": 11487
|
| 80420 |
+
},
|
| 80421 |
+
{
|
| 80422 |
+
"epoch": 13.084330484330485,
|
| 80423 |
+
"grad_norm": 0.2050594538450241,
|
| 80424 |
+
"learning_rate": 1.4374407992838363e-05,
|
| 80425 |
+
"loss": 0.4238,
|
| 80426 |
+
"step": 11488
|
| 80427 |
+
},
|
| 80428 |
+
{
|
| 80429 |
+
"epoch": 13.085470085470085,
|
| 80430 |
+
"grad_norm": 0.21120205521583557,
|
| 80431 |
+
"learning_rate": 1.4370190769419535e-05,
|
| 80432 |
+
"loss": 0.7231,
|
| 80433 |
+
"step": 11489
|
| 80434 |
+
},
|
| 80435 |
+
{
|
| 80436 |
+
"epoch": 13.086609686609687,
|
| 80437 |
+
"grad_norm": 0.207522451877594,
|
| 80438 |
+
"learning_rate": 1.4365973915203223e-05,
|
| 80439 |
+
"loss": 0.6889,
|
| 80440 |
+
"step": 11490
|
| 80441 |
+
},
|
| 80442 |
+
{
|
| 80443 |
+
"epoch": 13.087749287749288,
|
| 80444 |
+
"grad_norm": 0.19271396100521088,
|
| 80445 |
+
"learning_rate": 1.4361757430335864e-05,
|
| 80446 |
+
"loss": 0.8723,
|
| 80447 |
+
"step": 11491
|
| 80448 |
+
},
|
| 80449 |
+
{
|
| 80450 |
+
"epoch": 13.088888888888889,
|
| 80451 |
+
"grad_norm": 0.19991078972816467,
|
| 80452 |
+
"learning_rate": 1.4357541314963934e-05,
|
| 80453 |
+
"loss": 0.6813,
|
| 80454 |
+
"step": 11492
|
| 80455 |
+
},
|
| 80456 |
+
{
|
| 80457 |
+
"epoch": 13.090028490028491,
|
| 80458 |
+
"grad_norm": 0.21781806647777557,
|
| 80459 |
+
"learning_rate": 1.4353325569233873e-05,
|
| 80460 |
+
"loss": 0.6675,
|
| 80461 |
+
"step": 11493
|
| 80462 |
+
},
|
| 80463 |
+
{
|
| 80464 |
+
"epoch": 13.091168091168091,
|
| 80465 |
+
"grad_norm": 0.20519177615642548,
|
| 80466 |
+
"learning_rate": 1.4349110193292079e-05,
|
| 80467 |
+
"loss": 0.78,
|
| 80468 |
+
"step": 11494
|
| 80469 |
+
},
|
| 80470 |
+
{
|
| 80471 |
+
"epoch": 13.092307692307692,
|
| 80472 |
+
"grad_norm": 0.19230076670646667,
|
| 80473 |
+
"learning_rate": 1.4344895187284978e-05,
|
| 80474 |
+
"loss": 0.6574,
|
| 80475 |
+
"step": 11495
|
| 80476 |
+
},
|
| 80477 |
+
{
|
| 80478 |
+
"epoch": 13.093447293447294,
|
| 80479 |
+
"grad_norm": 0.18990492820739746,
|
| 80480 |
+
"learning_rate": 1.434068055135897e-05,
|
| 80481 |
+
"loss": 0.7134,
|
| 80482 |
+
"step": 11496
|
| 80483 |
+
},
|
| 80484 |
+
{
|
| 80485 |
+
"epoch": 13.094586894586895,
|
| 80486 |
+
"grad_norm": 0.19751523435115814,
|
| 80487 |
+
"learning_rate": 1.4336466285660451e-05,
|
| 80488 |
+
"loss": 0.6944,
|
| 80489 |
+
"step": 11497
|
| 80490 |
+
},
|
| 80491 |
+
{
|
| 80492 |
+
"epoch": 13.095726495726495,
|
| 80493 |
+
"grad_norm": 0.1749780774116516,
|
| 80494 |
+
"learning_rate": 1.4332252390335771e-05,
|
| 80495 |
+
"loss": 0.6119,
|
| 80496 |
+
"step": 11498
|
| 80497 |
+
},
|
| 80498 |
+
{
|
| 80499 |
+
"epoch": 13.096866096866098,
|
| 80500 |
+
"grad_norm": 0.21589112281799316,
|
| 80501 |
+
"learning_rate": 1.4328038865531305e-05,
|
| 80502 |
+
"loss": 0.7532,
|
| 80503 |
+
"step": 11499
|
| 80504 |
+
},
|
| 80505 |
+
{
|
| 80506 |
+
"epoch": 13.098005698005698,
|
| 80507 |
+
"grad_norm": 0.22464151680469513,
|
| 80508 |
+
"learning_rate": 1.4323825711393396e-05,
|
| 80509 |
+
"loss": 0.7189,
|
| 80510 |
+
"step": 11500
|
| 80511 |
+
},
|
| 80512 |
+
{
|
| 80513 |
+
"epoch": 13.099145299145299,
|
| 80514 |
+
"grad_norm": 0.23879218101501465,
|
| 80515 |
+
"learning_rate": 1.4319612928068388e-05,
|
| 80516 |
+
"loss": 0.5596,
|
| 80517 |
+
"step": 11501
|
| 80518 |
+
},
|
| 80519 |
+
{
|
| 80520 |
+
"epoch": 13.100284900284901,
|
| 80521 |
+
"grad_norm": 0.1787513941526413,
|
| 80522 |
+
"learning_rate": 1.4315400515702576e-05,
|
| 80523 |
+
"loss": 0.8427,
|
| 80524 |
+
"step": 11502
|
| 80525 |
+
},
|
| 80526 |
+
{
|
| 80527 |
+
"epoch": 13.101424501424502,
|
| 80528 |
+
"grad_norm": 0.2210531383752823,
|
| 80529 |
+
"learning_rate": 1.4311188474442295e-05,
|
| 80530 |
+
"loss": 0.5092,
|
| 80531 |
+
"step": 11503
|
| 80532 |
+
},
|
| 80533 |
+
{
|
| 80534 |
+
"epoch": 13.102564102564102,
|
| 80535 |
+
"grad_norm": 0.3780690133571625,
|
| 80536 |
+
"learning_rate": 1.430697680443383e-05,
|
| 80537 |
+
"loss": 0.815,
|
| 80538 |
+
"step": 11504
|
| 80539 |
+
},
|
| 80540 |
+
{
|
| 80541 |
+
"epoch": 13.103703703703705,
|
| 80542 |
+
"grad_norm": 0.2050284892320633,
|
| 80543 |
+
"learning_rate": 1.4302765505823482e-05,
|
| 80544 |
+
"loss": 0.8659,
|
| 80545 |
+
"step": 11505
|
| 80546 |
+
},
|
| 80547 |
+
{
|
| 80548 |
+
"epoch": 13.104843304843305,
|
| 80549 |
+
"grad_norm": 0.19268076121807098,
|
| 80550 |
+
"learning_rate": 1.4298554578757496e-05,
|
| 80551 |
+
"loss": 0.6517,
|
| 80552 |
+
"step": 11506
|
| 80553 |
+
},
|
| 80554 |
+
{
|
| 80555 |
+
"epoch": 13.105982905982906,
|
| 80556 |
+
"grad_norm": 0.18988528847694397,
|
| 80557 |
+
"learning_rate": 1.4294344023382133e-05,
|
| 80558 |
+
"loss": 0.568,
|
| 80559 |
+
"step": 11507
|
| 80560 |
+
},
|
| 80561 |
+
{
|
| 80562 |
+
"epoch": 13.107122507122508,
|
| 80563 |
+
"grad_norm": 0.14905154705047607,
|
| 80564 |
+
"learning_rate": 1.4290133839843644e-05,
|
| 80565 |
+
"loss": 0.7074,
|
| 80566 |
+
"step": 11508
|
| 80567 |
+
},
|
| 80568 |
+
{
|
| 80569 |
+
"epoch": 13.108262108262108,
|
| 80570 |
+
"grad_norm": 0.2254278063774109,
|
| 80571 |
+
"learning_rate": 1.4285924028288272e-05,
|
| 80572 |
+
"loss": 0.5758,
|
| 80573 |
+
"step": 11509
|
| 80574 |
+
},
|
| 80575 |
+
{
|
| 80576 |
+
"epoch": 13.109401709401709,
|
| 80577 |
+
"grad_norm": 0.2876284420490265,
|
| 80578 |
+
"learning_rate": 1.428171458886221e-05,
|
| 80579 |
+
"loss": 0.3755,
|
| 80580 |
+
"step": 11510
|
| 80581 |
+
},
|
| 80582 |
+
{
|
| 80583 |
+
"epoch": 13.110541310541311,
|
| 80584 |
+
"grad_norm": 0.2649424076080322,
|
| 80585 |
+
"learning_rate": 1.4277505521711679e-05,
|
| 80586 |
+
"loss": 0.7619,
|
| 80587 |
+
"step": 11511
|
| 80588 |
+
},
|
| 80589 |
+
{
|
| 80590 |
+
"epoch": 13.111680911680912,
|
| 80591 |
+
"grad_norm": 0.22738780081272125,
|
| 80592 |
+
"learning_rate": 1.4273296826982866e-05,
|
| 80593 |
+
"loss": 0.647,
|
| 80594 |
+
"step": 11512
|
| 80595 |
+
},
|
| 80596 |
+
{
|
| 80597 |
+
"epoch": 13.112820512820512,
|
| 80598 |
+
"grad_norm": 0.2185848206281662,
|
| 80599 |
+
"learning_rate": 1.4269088504821963e-05,
|
| 80600 |
+
"loss": 0.5954,
|
| 80601 |
+
"step": 11513
|
| 80602 |
+
},
|
| 80603 |
+
{
|
| 80604 |
+
"epoch": 13.113960113960115,
|
| 80605 |
+
"grad_norm": 0.2230282723903656,
|
| 80606 |
+
"learning_rate": 1.4264880555375104e-05,
|
| 80607 |
+
"loss": 0.4998,
|
| 80608 |
+
"step": 11514
|
| 80609 |
+
},
|
| 80610 |
+
{
|
| 80611 |
+
"epoch": 13.115099715099715,
|
| 80612 |
+
"grad_norm": 0.2161315530538559,
|
| 80613 |
+
"learning_rate": 1.4260672978788477e-05,
|
| 80614 |
+
"loss": 0.6973,
|
| 80615 |
+
"step": 11515
|
| 80616 |
+
},
|
| 80617 |
+
{
|
| 80618 |
+
"epoch": 13.116239316239316,
|
| 80619 |
+
"grad_norm": 0.24731765687465668,
|
| 80620 |
+
"learning_rate": 1.4256465775208222e-05,
|
| 80621 |
+
"loss": 0.5941,
|
| 80622 |
+
"step": 11516
|
| 80623 |
+
},
|
| 80624 |
+
{
|
| 80625 |
+
"epoch": 13.117378917378918,
|
| 80626 |
+
"grad_norm": 0.2210257649421692,
|
| 80627 |
+
"learning_rate": 1.4252258944780445e-05,
|
| 80628 |
+
"loss": 0.5394,
|
| 80629 |
+
"step": 11517
|
| 80630 |
+
},
|
| 80631 |
+
{
|
| 80632 |
+
"epoch": 13.118518518518519,
|
| 80633 |
+
"grad_norm": 0.18674232065677643,
|
| 80634 |
+
"learning_rate": 1.424805248765127e-05,
|
| 80635 |
+
"loss": 0.7684,
|
| 80636 |
+
"step": 11518
|
| 80637 |
+
},
|
| 80638 |
+
{
|
| 80639 |
+
"epoch": 13.11965811965812,
|
| 80640 |
+
"grad_norm": 0.19959892332553864,
|
| 80641 |
+
"learning_rate": 1.4243846403966799e-05,
|
| 80642 |
+
"loss": 0.7202,
|
| 80643 |
+
"step": 11519
|
| 80644 |
+
},
|
| 80645 |
+
{
|
| 80646 |
+
"epoch": 13.120797720797722,
|
| 80647 |
+
"grad_norm": 0.1804495006799698,
|
| 80648 |
+
"learning_rate": 1.4239640693873135e-05,
|
| 80649 |
+
"loss": 0.9416,
|
| 80650 |
+
"step": 11520
|
| 80651 |
+
},
|
| 80652 |
+
{
|
| 80653 |
+
"epoch": 13.121937321937322,
|
| 80654 |
+
"grad_norm": 0.22852128744125366,
|
| 80655 |
+
"learning_rate": 1.423543535751633e-05,
|
| 80656 |
+
"loss": 0.5582,
|
| 80657 |
+
"step": 11521
|
| 80658 |
+
},
|
| 80659 |
+
{
|
| 80660 |
+
"epoch": 13.123076923076923,
|
| 80661 |
+
"grad_norm": 0.23781459033489227,
|
| 80662 |
+
"learning_rate": 1.4231230395042455e-05,
|
| 80663 |
+
"loss": 0.5017,
|
| 80664 |
+
"step": 11522
|
| 80665 |
+
},
|
| 80666 |
+
{
|
| 80667 |
+
"epoch": 13.124216524216525,
|
| 80668 |
+
"grad_norm": 0.18285304307937622,
|
| 80669 |
+
"learning_rate": 1.4227025806597566e-05,
|
| 80670 |
+
"loss": 0.5944,
|
| 80671 |
+
"step": 11523
|
| 80672 |
+
},
|
| 80673 |
+
{
|
| 80674 |
+
"epoch": 13.125356125356126,
|
| 80675 |
+
"grad_norm": 0.22835831344127655,
|
| 80676 |
+
"learning_rate": 1.4222821592327707e-05,
|
| 80677 |
+
"loss": 0.7405,
|
| 80678 |
+
"step": 11524
|
| 80679 |
+
},
|
| 80680 |
+
{
|
| 80681 |
+
"epoch": 13.126495726495726,
|
| 80682 |
+
"grad_norm": 0.20321674644947052,
|
| 80683 |
+
"learning_rate": 1.4218617752378865e-05,
|
| 80684 |
+
"loss": 0.3524,
|
| 80685 |
+
"step": 11525
|
| 80686 |
+
},
|
| 80687 |
+
{
|
| 80688 |
+
"epoch": 13.127635327635328,
|
| 80689 |
+
"grad_norm": 0.2231002002954483,
|
| 80690 |
+
"learning_rate": 1.4214414286897094e-05,
|
| 80691 |
+
"loss": 0.8003,
|
| 80692 |
+
"step": 11526
|
| 80693 |
+
},
|
| 80694 |
+
{
|
| 80695 |
+
"epoch": 13.128774928774929,
|
| 80696 |
+
"grad_norm": 0.18399591743946075,
|
| 80697 |
+
"learning_rate": 1.4210211196028383e-05,
|
| 80698 |
+
"loss": 0.7674,
|
| 80699 |
+
"step": 11527
|
| 80700 |
+
},
|
| 80701 |
+
{
|
| 80702 |
+
"epoch": 13.12991452991453,
|
| 80703 |
+
"grad_norm": 0.18497677147388458,
|
| 80704 |
+
"learning_rate": 1.4206008479918701e-05,
|
| 80705 |
+
"loss": 0.6735,
|
| 80706 |
+
"step": 11528
|
| 80707 |
+
},
|
| 80708 |
+
{
|
| 80709 |
+
"epoch": 13.131054131054132,
|
| 80710 |
+
"grad_norm": 0.24679137766361237,
|
| 80711 |
+
"learning_rate": 1.4201806138714025e-05,
|
| 80712 |
+
"loss": 0.5597,
|
| 80713 |
+
"step": 11529
|
| 80714 |
+
},
|
| 80715 |
+
{
|
| 80716 |
+
"epoch": 13.132193732193732,
|
| 80717 |
+
"grad_norm": 0.23271405696868896,
|
| 80718 |
+
"learning_rate": 1.4197604172560319e-05,
|
| 80719 |
+
"loss": 0.605,
|
| 80720 |
+
"step": 11530
|
| 80721 |
+
},
|
| 80722 |
+
{
|
| 80723 |
+
"epoch": 13.133333333333333,
|
| 80724 |
+
"grad_norm": 0.20882228016853333,
|
| 80725 |
+
"learning_rate": 1.4193402581603538e-05,
|
| 80726 |
+
"loss": 0.7401,
|
| 80727 |
+
"step": 11531
|
| 80728 |
+
},
|
| 80729 |
+
{
|
| 80730 |
+
"epoch": 13.134472934472935,
|
| 80731 |
+
"grad_norm": 0.15231657028198242,
|
| 80732 |
+
"learning_rate": 1.4189201365989591e-05,
|
| 80733 |
+
"loss": 0.7368,
|
| 80734 |
+
"step": 11532
|
| 80735 |
+
},
|
| 80736 |
+
{
|
| 80737 |
+
"epoch": 13.135612535612536,
|
| 80738 |
+
"grad_norm": 0.17907041311264038,
|
| 80739 |
+
"learning_rate": 1.4185000525864412e-05,
|
| 80740 |
+
"loss": 0.8759,
|
| 80741 |
+
"step": 11533
|
| 80742 |
+
},
|
| 80743 |
+
{
|
| 80744 |
+
"epoch": 13.136752136752136,
|
| 80745 |
+
"grad_norm": 0.17270059883594513,
|
| 80746 |
+
"learning_rate": 1.4180800061373903e-05,
|
| 80747 |
+
"loss": 0.7135,
|
| 80748 |
+
"step": 11534
|
| 80749 |
+
},
|
| 80750 |
+
{
|
| 80751 |
+
"epoch": 13.137891737891739,
|
| 80752 |
+
"grad_norm": 0.20590460300445557,
|
| 80753 |
+
"learning_rate": 1.4176599972663972e-05,
|
| 80754 |
+
"loss": 0.6557,
|
| 80755 |
+
"step": 11535
|
| 80756 |
+
},
|
| 80757 |
+
{
|
| 80758 |
+
"epoch": 13.13903133903134,
|
| 80759 |
+
"grad_norm": 0.1744016408920288,
|
| 80760 |
+
"learning_rate": 1.4172400259880469e-05,
|
| 80761 |
+
"loss": 0.8199,
|
| 80762 |
+
"step": 11536
|
| 80763 |
+
},
|
| 80764 |
+
{
|
| 80765 |
+
"epoch": 13.14017094017094,
|
| 80766 |
+
"grad_norm": 0.190405011177063,
|
| 80767 |
+
"learning_rate": 1.4168200923169294e-05,
|
| 80768 |
+
"loss": 0.6,
|
| 80769 |
+
"step": 11537
|
| 80770 |
+
},
|
| 80771 |
+
{
|
| 80772 |
+
"epoch": 13.141310541310542,
|
| 80773 |
+
"grad_norm": 0.20549336075782776,
|
| 80774 |
+
"learning_rate": 1.4164001962676285e-05,
|
| 80775 |
+
"loss": 0.7205,
|
| 80776 |
+
"step": 11538
|
| 80777 |
+
},
|
| 80778 |
+
{
|
| 80779 |
+
"epoch": 13.142450142450143,
|
| 80780 |
+
"grad_norm": 0.18362568318843842,
|
| 80781 |
+
"learning_rate": 1.4159803378547299e-05,
|
| 80782 |
+
"loss": 0.9011,
|
| 80783 |
+
"step": 11539
|
| 80784 |
+
},
|
| 80785 |
+
{
|
| 80786 |
+
"epoch": 13.143589743589743,
|
| 80787 |
+
"grad_norm": 0.19862878322601318,
|
| 80788 |
+
"learning_rate": 1.4155605170928141e-05,
|
| 80789 |
+
"loss": 0.715,
|
| 80790 |
+
"step": 11540
|
| 80791 |
+
},
|
| 80792 |
+
{
|
| 80793 |
+
"epoch": 13.144729344729345,
|
| 80794 |
+
"grad_norm": 0.2534286081790924,
|
| 80795 |
+
"learning_rate": 1.415140733996464e-05,
|
| 80796 |
+
"loss": 0.727,
|
| 80797 |
+
"step": 11541
|
| 80798 |
+
},
|
| 80799 |
+
{
|
| 80800 |
+
"epoch": 13.145868945868946,
|
| 80801 |
+
"grad_norm": 0.19345135986804962,
|
| 80802 |
+
"learning_rate": 1.4147209885802593e-05,
|
| 80803 |
+
"loss": 0.4794,
|
| 80804 |
+
"step": 11542
|
| 80805 |
+
},
|
| 80806 |
+
{
|
| 80807 |
+
"epoch": 13.147008547008546,
|
| 80808 |
+
"grad_norm": 0.21531400084495544,
|
| 80809 |
+
"learning_rate": 1.4143012808587802e-05,
|
| 80810 |
+
"loss": 0.4436,
|
| 80811 |
+
"step": 11543
|
| 80812 |
+
},
|
| 80813 |
+
{
|
| 80814 |
+
"epoch": 13.148148148148149,
|
| 80815 |
+
"grad_norm": 0.21644629538059235,
|
| 80816 |
+
"learning_rate": 1.4138816108466024e-05,
|
| 80817 |
+
"loss": 0.4643,
|
| 80818 |
+
"step": 11544
|
| 80819 |
+
},
|
| 80820 |
+
{
|
| 80821 |
+
"epoch": 13.14928774928775,
|
| 80822 |
+
"grad_norm": 0.182317852973938,
|
| 80823 |
+
"learning_rate": 1.4134619785583032e-05,
|
| 80824 |
+
"loss": 0.7638,
|
| 80825 |
+
"step": 11545
|
| 80826 |
+
},
|
| 80827 |
+
{
|
| 80828 |
+
"epoch": 13.15042735042735,
|
| 80829 |
+
"grad_norm": 0.25152501463890076,
|
| 80830 |
+
"learning_rate": 1.4130423840084572e-05,
|
| 80831 |
+
"loss": 0.4686,
|
| 80832 |
+
"step": 11546
|
| 80833 |
+
},
|
| 80834 |
+
{
|
| 80835 |
+
"epoch": 13.151566951566952,
|
| 80836 |
+
"grad_norm": 0.2344987988471985,
|
| 80837 |
+
"learning_rate": 1.4126228272116382e-05,
|
| 80838 |
+
"loss": 0.4872,
|
| 80839 |
+
"step": 11547
|
| 80840 |
+
},
|
| 80841 |
+
{
|
| 80842 |
+
"epoch": 13.152706552706553,
|
| 80843 |
+
"grad_norm": 0.2786315381526947,
|
| 80844 |
+
"learning_rate": 1.4122033081824192e-05,
|
| 80845 |
+
"loss": 0.3465,
|
| 80846 |
+
"step": 11548
|
| 80847 |
+
},
|
| 80848 |
+
{
|
| 80849 |
+
"epoch": 13.153846153846153,
|
| 80850 |
+
"grad_norm": 0.19070546329021454,
|
| 80851 |
+
"learning_rate": 1.4117838269353705e-05,
|
| 80852 |
+
"loss": 0.6071,
|
| 80853 |
+
"step": 11549
|
| 80854 |
+
},
|
| 80855 |
+
{
|
| 80856 |
+
"epoch": 13.154985754985756,
|
| 80857 |
+
"grad_norm": 0.23821833729743958,
|
| 80858 |
+
"learning_rate": 1.4113643834850632e-05,
|
| 80859 |
+
"loss": 0.6572,
|
| 80860 |
+
"step": 11550
|
| 80861 |
+
},
|
| 80862 |
+
{
|
| 80863 |
+
"epoch": 13.156125356125356,
|
| 80864 |
+
"grad_norm": 0.20713569223880768,
|
| 80865 |
+
"learning_rate": 1.4109449778460634e-05,
|
| 80866 |
+
"loss": 0.5809,
|
| 80867 |
+
"step": 11551
|
| 80868 |
+
},
|
| 80869 |
+
{
|
| 80870 |
+
"epoch": 13.157264957264957,
|
| 80871 |
+
"grad_norm": 0.19106636941432953,
|
| 80872 |
+
"learning_rate": 1.4105256100329397e-05,
|
| 80873 |
+
"loss": 0.9459,
|
| 80874 |
+
"step": 11552
|
| 80875 |
+
},
|
| 80876 |
+
{
|
| 80877 |
+
"epoch": 13.158404558404559,
|
| 80878 |
+
"grad_norm": 0.22153536975383759,
|
| 80879 |
+
"learning_rate": 1.4101062800602578e-05,
|
| 80880 |
+
"loss": 0.8085,
|
| 80881 |
+
"step": 11553
|
| 80882 |
+
},
|
| 80883 |
+
{
|
| 80884 |
+
"epoch": 13.15954415954416,
|
| 80885 |
+
"grad_norm": 0.24223750829696655,
|
| 80886 |
+
"learning_rate": 1.4096869879425826e-05,
|
| 80887 |
+
"loss": 0.56,
|
| 80888 |
+
"step": 11554
|
| 80889 |
+
},
|
| 80890 |
+
{
|
| 80891 |
+
"epoch": 13.16068376068376,
|
| 80892 |
+
"grad_norm": 0.18808935582637787,
|
| 80893 |
+
"learning_rate": 1.4092677336944757e-05,
|
| 80894 |
+
"loss": 0.8308,
|
| 80895 |
+
"step": 11555
|
| 80896 |
+
},
|
| 80897 |
+
{
|
| 80898 |
+
"epoch": 13.161823361823362,
|
| 80899 |
+
"grad_norm": 0.24668224155902863,
|
| 80900 |
+
"learning_rate": 1.4088485173304999e-05,
|
| 80901 |
+
"loss": 0.4897,
|
| 80902 |
+
"step": 11556
|
| 80903 |
+
},
|
| 80904 |
+
{
|
| 80905 |
+
"epoch": 13.162962962962963,
|
| 80906 |
+
"grad_norm": 0.20698751509189606,
|
| 80907 |
+
"learning_rate": 1.408429338865216e-05,
|
| 80908 |
+
"loss": 0.6295,
|
| 80909 |
+
"step": 11557
|
| 80910 |
+
},
|
| 80911 |
+
{
|
| 80912 |
+
"epoch": 13.164102564102564,
|
| 80913 |
+
"grad_norm": 0.2100403904914856,
|
| 80914 |
+
"learning_rate": 1.408010198313183e-05,
|
| 80915 |
+
"loss": 0.7904,
|
| 80916 |
+
"step": 11558
|
| 80917 |
+
},
|
| 80918 |
+
{
|
| 80919 |
+
"epoch": 13.165242165242166,
|
| 80920 |
+
"grad_norm": 0.23687000572681427,
|
| 80921 |
+
"learning_rate": 1.4075910956889588e-05,
|
| 80922 |
+
"loss": 0.5746,
|
| 80923 |
+
"step": 11559
|
| 80924 |
+
},
|
| 80925 |
+
{
|
| 80926 |
+
"epoch": 13.166381766381766,
|
| 80927 |
+
"grad_norm": 0.2089221477508545,
|
| 80928 |
+
"learning_rate": 1.4071720310070999e-05,
|
| 80929 |
+
"loss": 0.4951,
|
| 80930 |
+
"step": 11560
|
| 80931 |
+
},
|
| 80932 |
+
{
|
| 80933 |
+
"epoch": 13.167521367521367,
|
| 80934 |
+
"grad_norm": 0.20603562891483307,
|
| 80935 |
+
"learning_rate": 1.4067530042821624e-05,
|
| 80936 |
+
"loss": 0.6948,
|
| 80937 |
+
"step": 11561
|
| 80938 |
+
},
|
| 80939 |
+
{
|
| 80940 |
+
"epoch": 13.16866096866097,
|
| 80941 |
+
"grad_norm": 0.18587876856327057,
|
| 80942 |
+
"learning_rate": 1.4063340155286988e-05,
|
| 80943 |
+
"loss": 0.7913,
|
| 80944 |
+
"step": 11562
|
| 80945 |
+
},
|
| 80946 |
+
{
|
| 80947 |
+
"epoch": 13.16980056980057,
|
| 80948 |
+
"grad_norm": 0.22771002352237701,
|
| 80949 |
+
"learning_rate": 1.4059150647612624e-05,
|
| 80950 |
+
"loss": 0.6707,
|
| 80951 |
+
"step": 11563
|
| 80952 |
+
},
|
| 80953 |
+
{
|
| 80954 |
+
"epoch": 13.17094017094017,
|
| 80955 |
+
"grad_norm": 0.17967014014720917,
|
| 80956 |
+
"learning_rate": 1.4054961519944046e-05,
|
| 80957 |
+
"loss": 0.7811,
|
| 80958 |
+
"step": 11564
|
| 80959 |
+
},
|
| 80960 |
+
{
|
| 80961 |
+
"epoch": 13.172079772079773,
|
| 80962 |
+
"grad_norm": 0.20775778591632843,
|
| 80963 |
+
"learning_rate": 1.4050772772426762e-05,
|
| 80964 |
+
"loss": 0.6791,
|
| 80965 |
+
"step": 11565
|
| 80966 |
+
},
|
| 80967 |
+
{
|
| 80968 |
+
"epoch": 13.173219373219373,
|
| 80969 |
+
"grad_norm": 0.18925908207893372,
|
| 80970 |
+
"learning_rate": 1.4046584405206242e-05,
|
| 80971 |
+
"loss": 0.7388,
|
| 80972 |
+
"step": 11566
|
| 80973 |
+
},
|
| 80974 |
+
{
|
| 80975 |
+
"epoch": 13.174358974358974,
|
| 80976 |
+
"grad_norm": 0.2153882533311844,
|
| 80977 |
+
"learning_rate": 1.4042396418427966e-05,
|
| 80978 |
+
"loss": 0.6407,
|
| 80979 |
+
"step": 11567
|
| 80980 |
+
},
|
| 80981 |
+
{
|
| 80982 |
+
"epoch": 13.175498575498576,
|
| 80983 |
+
"grad_norm": 0.20188970863819122,
|
| 80984 |
+
"learning_rate": 1.4038208812237397e-05,
|
| 80985 |
+
"loss": 0.635,
|
| 80986 |
+
"step": 11568
|
| 80987 |
+
},
|
| 80988 |
+
{
|
| 80989 |
+
"epoch": 13.176638176638177,
|
| 80990 |
+
"grad_norm": 0.21654903888702393,
|
| 80991 |
+
"learning_rate": 1.4034021586779981e-05,
|
| 80992 |
+
"loss": 0.6413,
|
| 80993 |
+
"step": 11569
|
| 80994 |
+
},
|
| 80995 |
+
{
|
| 80996 |
+
"epoch": 13.177777777777777,
|
| 80997 |
+
"grad_norm": 0.18344613909721375,
|
| 80998 |
+
"learning_rate": 1.402983474220115e-05,
|
| 80999 |
+
"loss": 0.7784,
|
| 81000 |
+
"step": 11570
|
| 81001 |
+
},
|
| 81002 |
+
{
|
| 81003 |
+
"epoch": 13.17891737891738,
|
| 81004 |
+
"grad_norm": 0.18774652481079102,
|
| 81005 |
+
"learning_rate": 1.4025648278646328e-05,
|
| 81006 |
+
"loss": 0.6506,
|
| 81007 |
+
"step": 11571
|
| 81008 |
+
},
|
| 81009 |
+
{
|
| 81010 |
+
"epoch": 13.18005698005698,
|
| 81011 |
+
"grad_norm": 0.2177322953939438,
|
| 81012 |
+
"learning_rate": 1.4021462196260931e-05,
|
| 81013 |
+
"loss": 0.6103,
|
| 81014 |
+
"step": 11572
|
| 81015 |
+
},
|
| 81016 |
+
{
|
| 81017 |
+
"epoch": 13.18119658119658,
|
| 81018 |
+
"grad_norm": 0.23880016803741455,
|
| 81019 |
+
"learning_rate": 1.4017276495190331e-05,
|
| 81020 |
+
"loss": 0.4566,
|
| 81021 |
+
"step": 11573
|
| 81022 |
+
},
|
| 81023 |
+
{
|
| 81024 |
+
"epoch": 13.182336182336183,
|
| 81025 |
+
"grad_norm": 0.20434992015361786,
|
| 81026 |
+
"learning_rate": 1.4013091175579923e-05,
|
| 81027 |
+
"loss": 0.7283,
|
| 81028 |
+
"step": 11574
|
| 81029 |
+
},
|
| 81030 |
+
{
|
| 81031 |
+
"epoch": 13.183475783475783,
|
| 81032 |
+
"grad_norm": 0.19964273273944855,
|
| 81033 |
+
"learning_rate": 1.4008906237575073e-05,
|
| 81034 |
+
"loss": 0.6593,
|
| 81035 |
+
"step": 11575
|
| 81036 |
+
},
|
| 81037 |
+
{
|
| 81038 |
+
"epoch": 13.184615384615384,
|
| 81039 |
+
"grad_norm": 0.23219776153564453,
|
| 81040 |
+
"learning_rate": 1.4004721681321142e-05,
|
| 81041 |
+
"loss": 0.511,
|
| 81042 |
+
"step": 11576
|
| 81043 |
+
},
|
| 81044 |
+
{
|
| 81045 |
+
"epoch": 13.185754985754986,
|
| 81046 |
+
"grad_norm": 0.21062827110290527,
|
| 81047 |
+
"learning_rate": 1.4000537506963456e-05,
|
| 81048 |
+
"loss": 0.6972,
|
| 81049 |
+
"step": 11577
|
| 81050 |
+
},
|
| 81051 |
+
{
|
| 81052 |
+
"epoch": 13.186894586894587,
|
| 81053 |
+
"grad_norm": 0.19703301787376404,
|
| 81054 |
+
"learning_rate": 1.3996353714647353e-05,
|
| 81055 |
+
"loss": 0.5974,
|
| 81056 |
+
"step": 11578
|
| 81057 |
+
},
|
| 81058 |
+
{
|
| 81059 |
+
"epoch": 13.188034188034187,
|
| 81060 |
+
"grad_norm": 0.19937114417552948,
|
| 81061 |
+
"learning_rate": 1.3992170304518142e-05,
|
| 81062 |
+
"loss": 0.7851,
|
| 81063 |
+
"step": 11579
|
| 81064 |
+
},
|
| 81065 |
+
{
|
| 81066 |
+
"epoch": 13.18917378917379,
|
| 81067 |
+
"grad_norm": 0.21336285769939423,
|
| 81068 |
+
"learning_rate": 1.3987987276721132e-05,
|
| 81069 |
+
"loss": 0.7405,
|
| 81070 |
+
"step": 11580
|
| 81071 |
+
},
|
| 81072 |
+
{
|
| 81073 |
+
"epoch": 13.19031339031339,
|
| 81074 |
+
"grad_norm": 0.20813515782356262,
|
| 81075 |
+
"learning_rate": 1.3983804631401604e-05,
|
| 81076 |
+
"loss": 0.7038,
|
| 81077 |
+
"step": 11581
|
| 81078 |
+
},
|
| 81079 |
+
{
|
| 81080 |
+
"epoch": 13.19145299145299,
|
| 81081 |
+
"grad_norm": 0.1741720587015152,
|
| 81082 |
+
"learning_rate": 1.3979622368704837e-05,
|
| 81083 |
+
"loss": 0.6571,
|
| 81084 |
+
"step": 11582
|
| 81085 |
+
},
|
| 81086 |
+
{
|
| 81087 |
+
"epoch": 13.192592592592593,
|
| 81088 |
+
"grad_norm": 0.17021405696868896,
|
| 81089 |
+
"learning_rate": 1.3975440488776093e-05,
|
| 81090 |
+
"loss": 0.5768,
|
| 81091 |
+
"step": 11583
|
| 81092 |
+
},
|
| 81093 |
+
{
|
| 81094 |
+
"epoch": 13.193732193732194,
|
| 81095 |
+
"grad_norm": 0.1774616241455078,
|
| 81096 |
+
"learning_rate": 1.3971258991760625e-05,
|
| 81097 |
+
"loss": 0.6787,
|
| 81098 |
+
"step": 11584
|
| 81099 |
+
},
|
| 81100 |
+
{
|
| 81101 |
+
"epoch": 13.194871794871794,
|
| 81102 |
+
"grad_norm": 0.20216669142246246,
|
| 81103 |
+
"learning_rate": 1.3967077877803653e-05,
|
| 81104 |
+
"loss": 0.8463,
|
| 81105 |
+
"step": 11585
|
| 81106 |
+
},
|
| 81107 |
+
{
|
| 81108 |
+
"epoch": 13.196011396011396,
|
| 81109 |
+
"grad_norm": 0.17637847363948822,
|
| 81110 |
+
"learning_rate": 1.3962897147050408e-05,
|
| 81111 |
+
"loss": 0.7966,
|
| 81112 |
+
"step": 11586
|
| 81113 |
+
},
|
| 81114 |
+
{
|
| 81115 |
+
"epoch": 13.197150997150997,
|
| 81116 |
+
"grad_norm": 0.280303418636322,
|
| 81117 |
+
"learning_rate": 1.3958716799646093e-05,
|
| 81118 |
+
"loss": 0.3728,
|
| 81119 |
+
"step": 11587
|
| 81120 |
+
},
|
| 81121 |
+
{
|
| 81122 |
+
"epoch": 13.198290598290598,
|
| 81123 |
+
"grad_norm": 0.2020619660615921,
|
| 81124 |
+
"learning_rate": 1.3954536835735922e-05,
|
| 81125 |
+
"loss": 0.6231,
|
| 81126 |
+
"step": 11588
|
| 81127 |
+
},
|
| 81128 |
+
{
|
| 81129 |
+
"epoch": 13.1994301994302,
|
| 81130 |
+
"grad_norm": 0.2249068021774292,
|
| 81131 |
+
"learning_rate": 1.3950357255465049e-05,
|
| 81132 |
+
"loss": 0.7047,
|
| 81133 |
+
"step": 11589
|
| 81134 |
+
},
|
| 81135 |
+
{
|
| 81136 |
+
"epoch": 13.2005698005698,
|
| 81137 |
+
"grad_norm": 0.1925133913755417,
|
| 81138 |
+
"learning_rate": 1.3946178058978657e-05,
|
| 81139 |
+
"loss": 0.7707,
|
| 81140 |
+
"step": 11590
|
| 81141 |
+
},
|
| 81142 |
+
{
|
| 81143 |
+
"epoch": 13.201709401709401,
|
| 81144 |
+
"grad_norm": 0.22543399035930634,
|
| 81145 |
+
"learning_rate": 1.39419992464219e-05,
|
| 81146 |
+
"loss": 0.5175,
|
| 81147 |
+
"step": 11591
|
| 81148 |
+
},
|
| 81149 |
+
{
|
| 81150 |
+
"epoch": 13.202849002849003,
|
| 81151 |
+
"grad_norm": 0.2181890457868576,
|
| 81152 |
+
"learning_rate": 1.3937820817939917e-05,
|
| 81153 |
+
"loss": 0.6261,
|
| 81154 |
+
"step": 11592
|
| 81155 |
+
},
|
| 81156 |
+
{
|
| 81157 |
+
"epoch": 13.203988603988604,
|
| 81158 |
+
"grad_norm": 0.18290166556835175,
|
| 81159 |
+
"learning_rate": 1.3933642773677836e-05,
|
| 81160 |
+
"loss": 0.7239,
|
| 81161 |
+
"step": 11593
|
| 81162 |
+
},
|
| 81163 |
+
{
|
| 81164 |
+
"epoch": 13.205128205128204,
|
| 81165 |
+
"grad_norm": 0.1689101755619049,
|
| 81166 |
+
"learning_rate": 1.3929465113780776e-05,
|
| 81167 |
+
"loss": 0.7861,
|
| 81168 |
+
"step": 11594
|
| 81169 |
+
},
|
| 81170 |
+
{
|
| 81171 |
+
"epoch": 13.206267806267807,
|
| 81172 |
+
"grad_norm": 0.1998259276151657,
|
| 81173 |
+
"learning_rate": 1.3925287838393846e-05,
|
| 81174 |
+
"loss": 0.5791,
|
| 81175 |
+
"step": 11595
|
| 81176 |
+
},
|
| 81177 |
+
{
|
| 81178 |
+
"epoch": 13.207407407407407,
|
| 81179 |
+
"grad_norm": 0.19786402583122253,
|
| 81180 |
+
"learning_rate": 1.392111094766212e-05,
|
| 81181 |
+
"loss": 0.2011,
|
| 81182 |
+
"step": 11596
|
| 81183 |
+
},
|
| 81184 |
+
{
|
| 81185 |
+
"epoch": 13.208547008547008,
|
| 81186 |
+
"grad_norm": 0.20233529806137085,
|
| 81187 |
+
"learning_rate": 1.3916934441730672e-05,
|
| 81188 |
+
"loss": 0.7028,
|
| 81189 |
+
"step": 11597
|
| 81190 |
+
},
|
| 81191 |
+
{
|
| 81192 |
+
"epoch": 13.20968660968661,
|
| 81193 |
+
"grad_norm": 0.19939535856246948,
|
| 81194 |
+
"learning_rate": 1.391275832074457e-05,
|
| 81195 |
+
"loss": 0.727,
|
| 81196 |
+
"step": 11598
|
| 81197 |
+
},
|
| 81198 |
+
{
|
| 81199 |
+
"epoch": 13.21082621082621,
|
| 81200 |
+
"grad_norm": 0.2780725955963135,
|
| 81201 |
+
"learning_rate": 1.3908582584848872e-05,
|
| 81202 |
+
"loss": 0.3274,
|
| 81203 |
+
"step": 11599
|
| 81204 |
+
},
|
| 81205 |
+
{
|
| 81206 |
+
"epoch": 13.211965811965811,
|
| 81207 |
+
"grad_norm": 0.23216119408607483,
|
| 81208 |
+
"learning_rate": 1.3904407234188594e-05,
|
| 81209 |
+
"loss": 0.6895,
|
| 81210 |
+
"step": 11600
|
| 81211 |
+
},
|
| 81212 |
+
{
|
| 81213 |
+
"epoch": 13.213105413105414,
|
| 81214 |
+
"grad_norm": 0.24538558721542358,
|
| 81215 |
+
"learning_rate": 1.3900232268908763e-05,
|
| 81216 |
+
"loss": 0.5244,
|
| 81217 |
+
"step": 11601
|
| 81218 |
+
},
|
| 81219 |
+
{
|
| 81220 |
+
"epoch": 13.214245014245014,
|
| 81221 |
+
"grad_norm": 0.2178601175546646,
|
| 81222 |
+
"learning_rate": 1.3896057689154396e-05,
|
| 81223 |
+
"loss": 0.7729,
|
| 81224 |
+
"step": 11602
|
| 81225 |
+
},
|
| 81226 |
+
{
|
| 81227 |
+
"epoch": 13.215384615384615,
|
| 81228 |
+
"grad_norm": 0.25279882550239563,
|
| 81229 |
+
"learning_rate": 1.3891883495070473e-05,
|
| 81230 |
+
"loss": 0.4163,
|
| 81231 |
+
"step": 11603
|
| 81232 |
+
},
|
| 81233 |
+
{
|
| 81234 |
+
"epoch": 13.216524216524217,
|
| 81235 |
+
"grad_norm": 0.18254736065864563,
|
| 81236 |
+
"learning_rate": 1.3887709686801992e-05,
|
| 81237 |
+
"loss": 0.7246,
|
| 81238 |
+
"step": 11604
|
| 81239 |
+
},
|
| 81240 |
+
{
|
| 81241 |
+
"epoch": 13.217663817663817,
|
| 81242 |
+
"grad_norm": 0.19879871606826782,
|
| 81243 |
+
"learning_rate": 1.3883536264493907e-05,
|
| 81244 |
+
"loss": 0.4122,
|
| 81245 |
+
"step": 11605
|
| 81246 |
+
},
|
| 81247 |
+
{
|
| 81248 |
+
"epoch": 13.218803418803418,
|
| 81249 |
+
"grad_norm": 0.22978079319000244,
|
| 81250 |
+
"learning_rate": 1.3879363228291187e-05,
|
| 81251 |
+
"loss": 0.5717,
|
| 81252 |
+
"step": 11606
|
| 81253 |
+
},
|
| 81254 |
+
{
|
| 81255 |
+
"epoch": 13.21994301994302,
|
| 81256 |
+
"grad_norm": 0.18433459103107452,
|
| 81257 |
+
"learning_rate": 1.3875190578338756e-05,
|
| 81258 |
+
"loss": 0.8107,
|
| 81259 |
+
"step": 11607
|
| 81260 |
+
},
|
| 81261 |
+
{
|
| 81262 |
+
"epoch": 13.221082621082621,
|
| 81263 |
+
"grad_norm": 0.1832319051027298,
|
| 81264 |
+
"learning_rate": 1.387101831478155e-05,
|
| 81265 |
+
"loss": 0.666,
|
| 81266 |
+
"step": 11608
|
| 81267 |
+
},
|
| 81268 |
+
{
|
| 81269 |
+
"epoch": 13.222222222222221,
|
| 81270 |
+
"grad_norm": 0.20097021758556366,
|
| 81271 |
+
"learning_rate": 1.3866846437764483e-05,
|
| 81272 |
+
"loss": 0.6026,
|
| 81273 |
+
"step": 11609
|
| 81274 |
+
},
|
| 81275 |
+
{
|
| 81276 |
+
"epoch": 13.223361823361824,
|
| 81277 |
+
"grad_norm": 0.19776402413845062,
|
| 81278 |
+
"learning_rate": 1.3862674947432463e-05,
|
| 81279 |
+
"loss": 0.6121,
|
| 81280 |
+
"step": 11610
|
| 81281 |
+
},
|
| 81282 |
+
{
|
| 81283 |
+
"epoch": 13.224501424501424,
|
| 81284 |
+
"grad_norm": 0.287895143032074,
|
| 81285 |
+
"learning_rate": 1.3858503843930365e-05,
|
| 81286 |
+
"loss": 0.5031,
|
| 81287 |
+
"step": 11611
|
| 81288 |
+
},
|
| 81289 |
+
{
|
| 81290 |
+
"epoch": 13.225641025641025,
|
| 81291 |
+
"grad_norm": 0.2561202049255371,
|
| 81292 |
+
"learning_rate": 1.3854333127403063e-05,
|
| 81293 |
+
"loss": 0.478,
|
| 81294 |
+
"step": 11612
|
| 81295 |
+
},
|
| 81296 |
+
{
|
| 81297 |
+
"epoch": 13.226780626780627,
|
| 81298 |
+
"grad_norm": 0.21733428537845612,
|
| 81299 |
+
"learning_rate": 1.3850162797995426e-05,
|
| 81300 |
+
"loss": 0.8118,
|
| 81301 |
+
"step": 11613
|
| 81302 |
+
},
|
| 81303 |
+
{
|
| 81304 |
+
"epoch": 13.227920227920228,
|
| 81305 |
+
"grad_norm": 0.2504943311214447,
|
| 81306 |
+
"learning_rate": 1.384599285585229e-05,
|
| 81307 |
+
"loss": 0.6361,
|
| 81308 |
+
"step": 11614
|
| 81309 |
+
},
|
| 81310 |
+
{
|
| 81311 |
+
"epoch": 13.229059829059828,
|
| 81312 |
+
"grad_norm": 0.243933767080307,
|
| 81313 |
+
"learning_rate": 1.3841823301118503e-05,
|
| 81314 |
+
"loss": 0.7141,
|
| 81315 |
+
"step": 11615
|
| 81316 |
+
},
|
| 81317 |
+
{
|
| 81318 |
+
"epoch": 13.23019943019943,
|
| 81319 |
+
"grad_norm": 0.22382576763629913,
|
| 81320 |
+
"learning_rate": 1.3837654133938876e-05,
|
| 81321 |
+
"loss": 0.4717,
|
| 81322 |
+
"step": 11616
|
| 81323 |
+
},
|
| 81324 |
+
{
|
| 81325 |
+
"epoch": 13.231339031339031,
|
| 81326 |
+
"grad_norm": 0.2521352469921112,
|
| 81327 |
+
"learning_rate": 1.3833485354458214e-05,
|
| 81328 |
+
"loss": 0.6739,
|
| 81329 |
+
"step": 11617
|
| 81330 |
+
},
|
| 81331 |
+
{
|
| 81332 |
+
"epoch": 13.232478632478632,
|
| 81333 |
+
"grad_norm": 0.24256514012813568,
|
| 81334 |
+
"learning_rate": 1.3829316962821328e-05,
|
| 81335 |
+
"loss": 0.6928,
|
| 81336 |
+
"step": 11618
|
| 81337 |
+
},
|
| 81338 |
+
{
|
| 81339 |
+
"epoch": 13.233618233618234,
|
| 81340 |
+
"grad_norm": 0.23227514326572418,
|
| 81341 |
+
"learning_rate": 1.3825148959172973e-05,
|
| 81342 |
+
"loss": 0.518,
|
| 81343 |
+
"step": 11619
|
| 81344 |
+
},
|
| 81345 |
+
{
|
| 81346 |
+
"epoch": 13.234757834757835,
|
| 81347 |
+
"grad_norm": 0.2246641367673874,
|
| 81348 |
+
"learning_rate": 1.3820981343657924e-05,
|
| 81349 |
+
"loss": 0.5972,
|
| 81350 |
+
"step": 11620
|
| 81351 |
+
},
|
| 81352 |
+
{
|
| 81353 |
+
"epoch": 13.235897435897435,
|
| 81354 |
+
"grad_norm": 0.20608285069465637,
|
| 81355 |
+
"learning_rate": 1.3816814116420938e-05,
|
| 81356 |
+
"loss": 0.5933,
|
| 81357 |
+
"step": 11621
|
| 81358 |
+
},
|
| 81359 |
+
{
|
| 81360 |
+
"epoch": 13.237037037037037,
|
| 81361 |
+
"grad_norm": 0.23809665441513062,
|
| 81362 |
+
"learning_rate": 1.3812647277606758e-05,
|
| 81363 |
+
"loss": 0.69,
|
| 81364 |
+
"step": 11622
|
| 81365 |
+
},
|
| 81366 |
+
{
|
| 81367 |
+
"epoch": 13.238176638176638,
|
| 81368 |
+
"grad_norm": 0.23365621268749237,
|
| 81369 |
+
"learning_rate": 1.3808480827360092e-05,
|
| 81370 |
+
"loss": 0.6051,
|
| 81371 |
+
"step": 11623
|
| 81372 |
+
},
|
| 81373 |
+
{
|
| 81374 |
+
"epoch": 13.239316239316238,
|
| 81375 |
+
"grad_norm": 0.18482758104801178,
|
| 81376 |
+
"learning_rate": 1.380431476582566e-05,
|
| 81377 |
+
"loss": 0.6293,
|
| 81378 |
+
"step": 11624
|
| 81379 |
+
},
|
| 81380 |
+
{
|
| 81381 |
+
"epoch": 13.24045584045584,
|
| 81382 |
+
"grad_norm": 0.2261316329240799,
|
| 81383 |
+
"learning_rate": 1.3800149093148179e-05,
|
| 81384 |
+
"loss": 0.8503,
|
| 81385 |
+
"step": 11625
|
| 81386 |
+
},
|
| 81387 |
+
{
|
| 81388 |
+
"epoch": 13.241595441595441,
|
| 81389 |
+
"grad_norm": 0.2567899525165558,
|
| 81390 |
+
"learning_rate": 1.3795983809472313e-05,
|
| 81391 |
+
"loss": 0.4726,
|
| 81392 |
+
"step": 11626
|
| 81393 |
+
},
|
| 81394 |
+
{
|
| 81395 |
+
"epoch": 13.242735042735042,
|
| 81396 |
+
"grad_norm": 0.20920339226722717,
|
| 81397 |
+
"learning_rate": 1.379181891494274e-05,
|
| 81398 |
+
"loss": 0.5162,
|
| 81399 |
+
"step": 11627
|
| 81400 |
+
},
|
| 81401 |
+
{
|
| 81402 |
+
"epoch": 13.243874643874644,
|
| 81403 |
+
"grad_norm": 0.1641882061958313,
|
| 81404 |
+
"learning_rate": 1.3787654409704118e-05,
|
| 81405 |
+
"loss": 0.6192,
|
| 81406 |
+
"step": 11628
|
| 81407 |
+
},
|
| 81408 |
+
{
|
| 81409 |
+
"epoch": 13.245014245014245,
|
| 81410 |
+
"grad_norm": 0.20723962783813477,
|
| 81411 |
+
"learning_rate": 1.3783490293901102e-05,
|
| 81412 |
+
"loss": 0.6878,
|
| 81413 |
+
"step": 11629
|
| 81414 |
+
},
|
| 81415 |
+
{
|
| 81416 |
+
"epoch": 13.246153846153845,
|
| 81417 |
+
"grad_norm": 0.22747716307640076,
|
| 81418 |
+
"learning_rate": 1.3779326567678303e-05,
|
| 81419 |
+
"loss": 0.6497,
|
| 81420 |
+
"step": 11630
|
| 81421 |
+
},
|
| 81422 |
+
{
|
| 81423 |
+
"epoch": 13.247293447293448,
|
| 81424 |
+
"grad_norm": 0.27678728103637695,
|
| 81425 |
+
"learning_rate": 1.3775163231180349e-05,
|
| 81426 |
+
"loss": 0.5673,
|
| 81427 |
+
"step": 11631
|
| 81428 |
+
},
|
| 81429 |
+
{
|
| 81430 |
+
"epoch": 13.248433048433048,
|
| 81431 |
+
"grad_norm": 0.2180687040090561,
|
| 81432 |
+
"learning_rate": 1.377100028455185e-05,
|
| 81433 |
+
"loss": 0.7948,
|
| 81434 |
+
"step": 11632
|
| 81435 |
+
},
|
| 81436 |
+
{
|
| 81437 |
+
"epoch": 13.249572649572649,
|
| 81438 |
+
"grad_norm": 0.23409755527973175,
|
| 81439 |
+
"learning_rate": 1.3766837727937392e-05,
|
| 81440 |
+
"loss": 0.7267,
|
| 81441 |
+
"step": 11633
|
| 81442 |
+
},
|
| 81443 |
+
{
|
| 81444 |
+
"epoch": 13.250712250712251,
|
| 81445 |
+
"grad_norm": 0.18900719285011292,
|
| 81446 |
+
"learning_rate": 1.3762675561481547e-05,
|
| 81447 |
+
"loss": 0.6484,
|
| 81448 |
+
"step": 11634
|
| 81449 |
+
},
|
| 81450 |
+
{
|
| 81451 |
+
"epoch": 13.251851851851852,
|
| 81452 |
+
"grad_norm": 0.23243440687656403,
|
| 81453 |
+
"learning_rate": 1.3758513785328872e-05,
|
| 81454 |
+
"loss": 0.5069,
|
| 81455 |
+
"step": 11635
|
| 81456 |
+
},
|
| 81457 |
+
{
|
| 81458 |
+
"epoch": 13.252991452991452,
|
| 81459 |
+
"grad_norm": 0.18046048283576965,
|
| 81460 |
+
"learning_rate": 1.3754352399623946e-05,
|
| 81461 |
+
"loss": 0.8074,
|
| 81462 |
+
"step": 11636
|
| 81463 |
+
},
|
| 81464 |
+
{
|
| 81465 |
+
"epoch": 13.254131054131054,
|
| 81466 |
+
"grad_norm": 0.19376908242702484,
|
| 81467 |
+
"learning_rate": 1.3750191404511278e-05,
|
| 81468 |
+
"loss": 0.6343,
|
| 81469 |
+
"step": 11637
|
| 81470 |
+
},
|
| 81471 |
+
{
|
| 81472 |
+
"epoch": 13.255270655270655,
|
| 81473 |
+
"grad_norm": 0.23857325315475464,
|
| 81474 |
+
"learning_rate": 1.3746030800135398e-05,
|
| 81475 |
+
"loss": 0.5676,
|
| 81476 |
+
"step": 11638
|
| 81477 |
+
},
|
| 81478 |
+
{
|
| 81479 |
+
"epoch": 13.256410256410255,
|
| 81480 |
+
"grad_norm": 0.20566202700138092,
|
| 81481 |
+
"learning_rate": 1.374187058664082e-05,
|
| 81482 |
+
"loss": 0.4449,
|
| 81483 |
+
"step": 11639
|
| 81484 |
+
},
|
| 81485 |
+
{
|
| 81486 |
+
"epoch": 13.257549857549858,
|
| 81487 |
+
"grad_norm": 0.16072019934654236,
|
| 81488 |
+
"learning_rate": 1.3737710764172044e-05,
|
| 81489 |
+
"loss": 0.7824,
|
| 81490 |
+
"step": 11640
|
| 81491 |
+
},
|
| 81492 |
+
{
|
| 81493 |
+
"epoch": 13.258689458689458,
|
| 81494 |
+
"grad_norm": 0.17833319306373596,
|
| 81495 |
+
"learning_rate": 1.3733551332873534e-05,
|
| 81496 |
+
"loss": 0.7401,
|
| 81497 |
+
"step": 11641
|
| 81498 |
+
},
|
| 81499 |
+
{
|
| 81500 |
+
"epoch": 13.25982905982906,
|
| 81501 |
+
"grad_norm": 0.20904269814491272,
|
| 81502 |
+
"learning_rate": 1.372939229288977e-05,
|
| 81503 |
+
"loss": 0.6093,
|
| 81504 |
+
"step": 11642
|
| 81505 |
+
},
|
| 81506 |
+
{
|
| 81507 |
+
"epoch": 13.260968660968661,
|
| 81508 |
+
"grad_norm": 0.19811105728149414,
|
| 81509 |
+
"learning_rate": 1.3725233644365204e-05,
|
| 81510 |
+
"loss": 0.6425,
|
| 81511 |
+
"step": 11643
|
| 81512 |
+
},
|
| 81513 |
+
{
|
| 81514 |
+
"epoch": 13.262108262108262,
|
| 81515 |
+
"grad_norm": 0.2192060351371765,
|
| 81516 |
+
"learning_rate": 1.3721075387444293e-05,
|
| 81517 |
+
"loss": 0.7129,
|
| 81518 |
+
"step": 11644
|
| 81519 |
+
},
|
| 81520 |
+
{
|
| 81521 |
+
"epoch": 13.263247863247864,
|
| 81522 |
+
"grad_norm": 0.19724543392658234,
|
| 81523 |
+
"learning_rate": 1.3716917522271439e-05,
|
| 81524 |
+
"loss": 0.7193,
|
| 81525 |
+
"step": 11645
|
| 81526 |
+
},
|
| 81527 |
+
{
|
| 81528 |
+
"epoch": 13.264387464387465,
|
| 81529 |
+
"grad_norm": 0.20687972009181976,
|
| 81530 |
+
"learning_rate": 1.3712760048991058e-05,
|
| 81531 |
+
"loss": 0.7468,
|
| 81532 |
+
"step": 11646
|
| 81533 |
+
},
|
| 81534 |
+
{
|
| 81535 |
+
"epoch": 13.265527065527065,
|
| 81536 |
+
"grad_norm": 0.24772727489471436,
|
| 81537 |
+
"learning_rate": 1.370860296774758e-05,
|
| 81538 |
+
"loss": 0.5926,
|
| 81539 |
+
"step": 11647
|
| 81540 |
+
},
|
| 81541 |
+
{
|
| 81542 |
+
"epoch": 13.266666666666667,
|
| 81543 |
+
"grad_norm": 0.20096513628959656,
|
| 81544 |
+
"learning_rate": 1.3704446278685362e-05,
|
| 81545 |
+
"loss": 0.6094,
|
| 81546 |
+
"step": 11648
|
| 81547 |
+
},
|
| 81548 |
+
{
|
| 81549 |
+
"epoch": 13.267806267806268,
|
| 81550 |
+
"grad_norm": 0.2793840765953064,
|
| 81551 |
+
"learning_rate": 1.3700289981948792e-05,
|
| 81552 |
+
"loss": 0.5776,
|
| 81553 |
+
"step": 11649
|
| 81554 |
+
},
|
| 81555 |
+
{
|
| 81556 |
+
"epoch": 13.268945868945869,
|
| 81557 |
+
"grad_norm": 0.2074030041694641,
|
| 81558 |
+
"learning_rate": 1.369613407768222e-05,
|
| 81559 |
+
"loss": 0.6481,
|
| 81560 |
+
"step": 11650
|
| 81561 |
+
},
|
| 81562 |
+
{
|
| 81563 |
+
"epoch": 13.270085470085471,
|
| 81564 |
+
"grad_norm": 0.25681355595588684,
|
| 81565 |
+
"learning_rate": 1.3691978566030011e-05,
|
| 81566 |
+
"loss": 0.8151,
|
| 81567 |
+
"step": 11651
|
| 81568 |
+
},
|
| 81569 |
+
{
|
| 81570 |
+
"epoch": 13.271225071225071,
|
| 81571 |
+
"grad_norm": 0.21756432950496674,
|
| 81572 |
+
"learning_rate": 1.3687823447136471e-05,
|
| 81573 |
+
"loss": 0.7279,
|
| 81574 |
+
"step": 11652
|
| 81575 |
+
},
|
| 81576 |
+
{
|
| 81577 |
+
"epoch": 13.272364672364672,
|
| 81578 |
+
"grad_norm": 0.25154349207878113,
|
| 81579 |
+
"learning_rate": 1.3683668721145931e-05,
|
| 81580 |
+
"loss": 0.6369,
|
| 81581 |
+
"step": 11653
|
| 81582 |
+
},
|
| 81583 |
+
{
|
| 81584 |
+
"epoch": 13.273504273504274,
|
| 81585 |
+
"grad_norm": 0.1960681527853012,
|
| 81586 |
+
"learning_rate": 1.3679514388202696e-05,
|
| 81587 |
+
"loss": 0.7955,
|
| 81588 |
+
"step": 11654
|
| 81589 |
+
},
|
| 81590 |
+
{
|
| 81591 |
+
"epoch": 13.274643874643875,
|
| 81592 |
+
"grad_norm": 0.2003762274980545,
|
| 81593 |
+
"learning_rate": 1.3675360448451072e-05,
|
| 81594 |
+
"loss": 0.7032,
|
| 81595 |
+
"step": 11655
|
| 81596 |
+
},
|
| 81597 |
+
{
|
| 81598 |
+
"epoch": 13.275783475783475,
|
| 81599 |
+
"grad_norm": 0.2773532271385193,
|
| 81600 |
+
"learning_rate": 1.3671206902035311e-05,
|
| 81601 |
+
"loss": 0.5724,
|
| 81602 |
+
"step": 11656
|
| 81603 |
+
},
|
| 81604 |
+
{
|
| 81605 |
+
"epoch": 13.276923076923078,
|
| 81606 |
+
"grad_norm": 0.22172974050045013,
|
| 81607 |
+
"learning_rate": 1.3667053749099675e-05,
|
| 81608 |
+
"loss": 0.9324,
|
| 81609 |
+
"step": 11657
|
| 81610 |
+
},
|
| 81611 |
+
{
|
| 81612 |
+
"epoch": 13.278062678062678,
|
| 81613 |
+
"grad_norm": 0.15701836347579956,
|
| 81614 |
+
"learning_rate": 1.366290098978844e-05,
|
| 81615 |
+
"loss": 0.8745,
|
| 81616 |
+
"step": 11658
|
| 81617 |
+
},
|
| 81618 |
+
{
|
| 81619 |
+
"epoch": 13.279202279202279,
|
| 81620 |
+
"grad_norm": 0.24879899621009827,
|
| 81621 |
+
"learning_rate": 1.3658748624245843e-05,
|
| 81622 |
+
"loss": 0.5656,
|
| 81623 |
+
"step": 11659
|
| 81624 |
+
},
|
| 81625 |
+
{
|
| 81626 |
+
"epoch": 13.280341880341881,
|
| 81627 |
+
"grad_norm": 0.19226278364658356,
|
| 81628 |
+
"learning_rate": 1.365459665261608e-05,
|
| 81629 |
+
"loss": 0.7775,
|
| 81630 |
+
"step": 11660
|
| 81631 |
+
},
|
| 81632 |
+
{
|
| 81633 |
+
"epoch": 13.281481481481482,
|
| 81634 |
+
"grad_norm": 0.2153489738702774,
|
| 81635 |
+
"learning_rate": 1.365044507504338e-05,
|
| 81636 |
+
"loss": 0.8125,
|
| 81637 |
+
"step": 11661
|
| 81638 |
+
},
|
| 81639 |
+
{
|
| 81640 |
+
"epoch": 13.282621082621082,
|
| 81641 |
+
"grad_norm": 0.22412502765655518,
|
| 81642 |
+
"learning_rate": 1.3646293891671932e-05,
|
| 81643 |
+
"loss": 0.6856,
|
| 81644 |
+
"step": 11662
|
| 81645 |
+
},
|
| 81646 |
+
{
|
| 81647 |
+
"epoch": 13.283760683760685,
|
| 81648 |
+
"grad_norm": 0.2342052310705185,
|
| 81649 |
+
"learning_rate": 1.3642143102645933e-05,
|
| 81650 |
+
"loss": 0.589,
|
| 81651 |
+
"step": 11663
|
| 81652 |
+
},
|
| 81653 |
+
{
|
| 81654 |
+
"epoch": 13.284900284900285,
|
| 81655 |
+
"grad_norm": 0.22180594503879547,
|
| 81656 |
+
"learning_rate": 1.3637992708109524e-05,
|
| 81657 |
+
"loss": 0.5019,
|
| 81658 |
+
"step": 11664
|
| 81659 |
+
},
|
| 81660 |
+
{
|
| 81661 |
+
"epoch": 13.286039886039886,
|
| 81662 |
+
"grad_norm": 0.1808266043663025,
|
| 81663 |
+
"learning_rate": 1.3633842708206873e-05,
|
| 81664 |
+
"loss": 0.6718,
|
| 81665 |
+
"step": 11665
|
| 81666 |
+
},
|
| 81667 |
+
{
|
| 81668 |
+
"epoch": 13.287179487179488,
|
| 81669 |
+
"grad_norm": 0.22990697622299194,
|
| 81670 |
+
"learning_rate": 1.3629693103082124e-05,
|
| 81671 |
+
"loss": 0.5513,
|
| 81672 |
+
"step": 11666
|
| 81673 |
+
},
|
| 81674 |
+
{
|
| 81675 |
+
"epoch": 13.288319088319088,
|
| 81676 |
+
"grad_norm": 0.1747976541519165,
|
| 81677 |
+
"learning_rate": 1.3625543892879411e-05,
|
| 81678 |
+
"loss": 0.7103,
|
| 81679 |
+
"step": 11667
|
| 81680 |
+
},
|
| 81681 |
+
{
|
| 81682 |
+
"epoch": 13.289458689458689,
|
| 81683 |
+
"grad_norm": 0.30305853486061096,
|
| 81684 |
+
"learning_rate": 1.3621395077742821e-05,
|
| 81685 |
+
"loss": 0.3237,
|
| 81686 |
+
"step": 11668
|
| 81687 |
+
},
|
| 81688 |
+
{
|
| 81689 |
+
"epoch": 13.290598290598291,
|
| 81690 |
+
"grad_norm": 0.17665137350559235,
|
| 81691 |
+
"learning_rate": 1.361724665781648e-05,
|
| 81692 |
+
"loss": 0.7229,
|
| 81693 |
+
"step": 11669
|
| 81694 |
+
},
|
| 81695 |
+
{
|
| 81696 |
+
"epoch": 13.291737891737892,
|
| 81697 |
+
"grad_norm": 0.252114862203598,
|
| 81698 |
+
"learning_rate": 1.3613098633244475e-05,
|
| 81699 |
+
"loss": 0.5299,
|
| 81700 |
+
"step": 11670
|
| 81701 |
+
},
|
| 81702 |
+
{
|
| 81703 |
+
"epoch": 13.292877492877492,
|
| 81704 |
+
"grad_norm": 0.1885116994380951,
|
| 81705 |
+
"learning_rate": 1.3608951004170859e-05,
|
| 81706 |
+
"loss": 0.791,
|
| 81707 |
+
"step": 11671
|
| 81708 |
+
},
|
| 81709 |
+
{
|
| 81710 |
+
"epoch": 13.294017094017095,
|
| 81711 |
+
"grad_norm": 0.25263312458992004,
|
| 81712 |
+
"learning_rate": 1.3604803770739699e-05,
|
| 81713 |
+
"loss": 0.5148,
|
| 81714 |
+
"step": 11672
|
| 81715 |
+
},
|
| 81716 |
+
{
|
| 81717 |
+
"epoch": 13.295156695156695,
|
| 81718 |
+
"grad_norm": 0.1892181932926178,
|
| 81719 |
+
"learning_rate": 1.360065693309504e-05,
|
| 81720 |
+
"loss": 0.6974,
|
| 81721 |
+
"step": 11673
|
| 81722 |
+
},
|
| 81723 |
+
{
|
| 81724 |
+
"epoch": 13.296296296296296,
|
| 81725 |
+
"grad_norm": 0.22764094173908234,
|
| 81726 |
+
"learning_rate": 1.3596510491380926e-05,
|
| 81727 |
+
"loss": 0.4453,
|
| 81728 |
+
"step": 11674
|
| 81729 |
+
},
|
| 81730 |
+
{
|
| 81731 |
+
"epoch": 13.297435897435898,
|
| 81732 |
+
"grad_norm": 0.1909138262271881,
|
| 81733 |
+
"learning_rate": 1.3592364445741355e-05,
|
| 81734 |
+
"loss": 0.7589,
|
| 81735 |
+
"step": 11675
|
| 81736 |
+
},
|
| 81737 |
+
{
|
| 81738 |
+
"epoch": 13.298575498575499,
|
| 81739 |
+
"grad_norm": 0.20127205550670624,
|
| 81740 |
+
"learning_rate": 1.3588218796320335e-05,
|
| 81741 |
+
"loss": 0.7262,
|
| 81742 |
+
"step": 11676
|
| 81743 |
+
},
|
| 81744 |
+
{
|
| 81745 |
+
"epoch": 13.2997150997151,
|
| 81746 |
+
"grad_norm": 0.18755756318569183,
|
| 81747 |
+
"learning_rate": 1.3584073543261857e-05,
|
| 81748 |
+
"loss": 0.7694,
|
| 81749 |
+
"step": 11677
|
| 81750 |
+
},
|
| 81751 |
+
{
|
| 81752 |
+
"epoch": 13.300854700854702,
|
| 81753 |
+
"grad_norm": 0.1816464513540268,
|
| 81754 |
+
"learning_rate": 1.357992868670991e-05,
|
| 81755 |
+
"loss": 0.7881,
|
| 81756 |
+
"step": 11678
|
| 81757 |
+
},
|
| 81758 |
+
{
|
| 81759 |
+
"epoch": 13.301994301994302,
|
| 81760 |
+
"grad_norm": 0.2296556532382965,
|
| 81761 |
+
"learning_rate": 1.3575784226808424e-05,
|
| 81762 |
+
"loss": 0.5905,
|
| 81763 |
+
"step": 11679
|
| 81764 |
+
},
|
| 81765 |
+
{
|
| 81766 |
+
"epoch": 13.303133903133903,
|
| 81767 |
+
"grad_norm": 0.21964482963085175,
|
| 81768 |
+
"learning_rate": 1.3571640163701382e-05,
|
| 81769 |
+
"loss": 0.6905,
|
| 81770 |
+
"step": 11680
|
| 81771 |
+
},
|
| 81772 |
+
{
|
| 81773 |
+
"epoch": 13.304273504273505,
|
| 81774 |
+
"grad_norm": 0.19504858553409576,
|
| 81775 |
+
"learning_rate": 1.3567496497532714e-05,
|
| 81776 |
+
"loss": 0.7416,
|
| 81777 |
+
"step": 11681
|
| 81778 |
+
},
|
| 81779 |
+
{
|
| 81780 |
+
"epoch": 13.305413105413106,
|
| 81781 |
+
"grad_norm": 0.1960165798664093,
|
| 81782 |
+
"learning_rate": 1.3563353228446322e-05,
|
| 81783 |
+
"loss": 0.8115,
|
| 81784 |
+
"step": 11682
|
| 81785 |
+
},
|
| 81786 |
+
{
|
| 81787 |
+
"epoch": 13.306552706552706,
|
| 81788 |
+
"grad_norm": 0.1789308488368988,
|
| 81789 |
+
"learning_rate": 1.3559210356586122e-05,
|
| 81790 |
+
"loss": 0.9033,
|
| 81791 |
+
"step": 11683
|
| 81792 |
+
},
|
| 81793 |
+
{
|
| 81794 |
+
"epoch": 13.307692307692308,
|
| 81795 |
+
"grad_norm": 0.20353779196739197,
|
| 81796 |
+
"learning_rate": 1.355506788209601e-05,
|
| 81797 |
+
"loss": 0.6144,
|
| 81798 |
+
"step": 11684
|
| 81799 |
+
},
|
| 81800 |
+
{
|
| 81801 |
+
"epoch": 13.308831908831909,
|
| 81802 |
+
"grad_norm": 0.22314287722110748,
|
| 81803 |
+
"learning_rate": 1.3550925805119874e-05,
|
| 81804 |
+
"loss": 0.7909,
|
| 81805 |
+
"step": 11685
|
| 81806 |
+
},
|
| 81807 |
+
{
|
| 81808 |
+
"epoch": 13.30997150997151,
|
| 81809 |
+
"grad_norm": 0.24087511003017426,
|
| 81810 |
+
"learning_rate": 1.3546784125801559e-05,
|
| 81811 |
+
"loss": 0.5125,
|
| 81812 |
+
"step": 11686
|
| 81813 |
+
},
|
| 81814 |
+
{
|
| 81815 |
+
"epoch": 13.311111111111112,
|
| 81816 |
+
"grad_norm": 0.24155688285827637,
|
| 81817 |
+
"learning_rate": 1.3542642844284925e-05,
|
| 81818 |
+
"loss": 0.6512,
|
| 81819 |
+
"step": 11687
|
| 81820 |
+
},
|
| 81821 |
+
{
|
| 81822 |
+
"epoch": 13.312250712250712,
|
| 81823 |
+
"grad_norm": 0.2127622663974762,
|
| 81824 |
+
"learning_rate": 1.3538501960713817e-05,
|
| 81825 |
+
"loss": 0.6409,
|
| 81826 |
+
"step": 11688
|
| 81827 |
+
},
|
| 81828 |
+
{
|
| 81829 |
+
"epoch": 13.313390313390313,
|
| 81830 |
+
"grad_norm": 0.19076725840568542,
|
| 81831 |
+
"learning_rate": 1.3534361475232066e-05,
|
| 81832 |
+
"loss": 0.5577,
|
| 81833 |
+
"step": 11689
|
| 81834 |
+
},
|
| 81835 |
+
{
|
| 81836 |
+
"epoch": 13.314529914529915,
|
| 81837 |
+
"grad_norm": 0.2386363446712494,
|
| 81838 |
+
"learning_rate": 1.3530221387983449e-05,
|
| 81839 |
+
"loss": 0.6635,
|
| 81840 |
+
"step": 11690
|
| 81841 |
+
},
|
| 81842 |
+
{
|
| 81843 |
+
"epoch": 13.315669515669516,
|
| 81844 |
+
"grad_norm": 0.27781039476394653,
|
| 81845 |
+
"learning_rate": 1.3526081699111795e-05,
|
| 81846 |
+
"loss": 0.4627,
|
| 81847 |
+
"step": 11691
|
| 81848 |
+
},
|
| 81849 |
+
{
|
| 81850 |
+
"epoch": 13.316809116809116,
|
| 81851 |
+
"grad_norm": 0.2276037037372589,
|
| 81852 |
+
"learning_rate": 1.3521942408760887e-05,
|
| 81853 |
+
"loss": 0.5927,
|
| 81854 |
+
"step": 11692
|
| 81855 |
+
},
|
| 81856 |
+
{
|
| 81857 |
+
"epoch": 13.317948717948719,
|
| 81858 |
+
"grad_norm": 0.1818503886461258,
|
| 81859 |
+
"learning_rate": 1.3517803517074476e-05,
|
| 81860 |
+
"loss": 0.7698,
|
| 81861 |
+
"step": 11693
|
| 81862 |
+
},
|
| 81863 |
+
{
|
| 81864 |
+
"epoch": 13.31908831908832,
|
| 81865 |
+
"grad_norm": 0.22993409633636475,
|
| 81866 |
+
"learning_rate": 1.3513665024196323e-05,
|
| 81867 |
+
"loss": 0.5875,
|
| 81868 |
+
"step": 11694
|
| 81869 |
+
},
|
| 81870 |
+
{
|
| 81871 |
+
"epoch": 13.32022792022792,
|
| 81872 |
+
"grad_norm": 0.18451379239559174,
|
| 81873 |
+
"learning_rate": 1.3509526930270171e-05,
|
| 81874 |
+
"loss": 0.7612,
|
| 81875 |
+
"step": 11695
|
| 81876 |
+
},
|
| 81877 |
+
{
|
| 81878 |
+
"epoch": 13.321367521367522,
|
| 81879 |
+
"grad_norm": 0.2384960800409317,
|
| 81880 |
+
"learning_rate": 1.350538923543975e-05,
|
| 81881 |
+
"loss": 0.6317,
|
| 81882 |
+
"step": 11696
|
| 81883 |
+
},
|
| 81884 |
+
{
|
| 81885 |
+
"epoch": 13.322507122507123,
|
| 81886 |
+
"grad_norm": 0.2107928842306137,
|
| 81887 |
+
"learning_rate": 1.350125193984878e-05,
|
| 81888 |
+
"loss": 0.4457,
|
| 81889 |
+
"step": 11697
|
| 81890 |
+
},
|
| 81891 |
+
{
|
| 81892 |
+
"epoch": 13.323646723646723,
|
| 81893 |
+
"grad_norm": 0.24160587787628174,
|
| 81894 |
+
"learning_rate": 1.349711504364094e-05,
|
| 81895 |
+
"loss": 0.5347,
|
| 81896 |
+
"step": 11698
|
| 81897 |
+
},
|
| 81898 |
+
{
|
| 81899 |
+
"epoch": 13.324786324786325,
|
| 81900 |
+
"grad_norm": 0.1711517721414566,
|
| 81901 |
+
"learning_rate": 1.349297854695993e-05,
|
| 81902 |
+
"loss": 0.7233,
|
| 81903 |
+
"step": 11699
|
| 81904 |
+
},
|
| 81905 |
+
{
|
| 81906 |
+
"epoch": 13.325925925925926,
|
| 81907 |
+
"grad_norm": 0.20796626806259155,
|
| 81908 |
+
"learning_rate": 1.3488842449949418e-05,
|
| 81909 |
+
"loss": 0.6381,
|
| 81910 |
+
"step": 11700
|
| 81911 |
}
|
| 81912 |
],
|
| 81913 |
"logging_steps": 1,
|
|
|
|
| 81927 |
"attributes": {}
|
| 81928 |
}
|
| 81929 |
},
|
| 81930 |
+
"total_flos": 6.5417433919586796e+19,
|
| 81931 |
"train_batch_size": 8,
|
| 81932 |
"trial_name": null,
|
| 81933 |
"trial_params": null
|