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 10800, 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 sha256:8bb0c45b5ab871f50887ba6bbbfe5e7121af2f552a471f417acb35e961bbc729
|
| 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:d31463acc048c9c9f841071200b15dc702817b1daae105c4d867f3c71fc3fcf5
|
| 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 sha256:236304ae89e49aae8260113165ee63419b9b745f79120014328a7fa31ed79b42
|
| 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 sha256:672fe16c74c00144bd0d3f082dee75d596ac539ec9c693a3c5951b94b52798b5
|
| 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,
|
|
@@ -73508,6 +73508,2106 @@
|
|
| 73508 |
"learning_rate": 1.8697319214963897e-05,
|
| 73509 |
"loss": 0.5798,
|
| 73510 |
"step": 10500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73511 |
}
|
| 73512 |
],
|
| 73513 |
"logging_steps": 1,
|
|
@@ -73527,7 +75627,7 @@
|
|
| 73527 |
"attributes": {}
|
| 73528 |
}
|
| 73529 |
},
|
| 73530 |
-
"total_flos":
|
| 73531 |
"train_batch_size": 8,
|
| 73532 |
"trial_name": null,
|
| 73533 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.300854700854702,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 10800,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 73508 |
"learning_rate": 1.8697319214963897e-05,
|
| 73509 |
"loss": 0.5798,
|
| 73510 |
"step": 10500
|
| 73511 |
+
},
|
| 73512 |
+
{
|
| 73513 |
+
"epoch": 11.96068376068376,
|
| 73514 |
+
"grad_norm": 0.16201630234718323,
|
| 73515 |
+
"learning_rate": 1.8692810638104013e-05,
|
| 73516 |
+
"loss": 0.9224,
|
| 73517 |
+
"step": 10501
|
| 73518 |
+
},
|
| 73519 |
+
{
|
| 73520 |
+
"epoch": 11.961823361823361,
|
| 73521 |
+
"grad_norm": 0.19255182147026062,
|
| 73522 |
+
"learning_rate": 1.8688302280310152e-05,
|
| 73523 |
+
"loss": 0.7875,
|
| 73524 |
+
"step": 10502
|
| 73525 |
+
},
|
| 73526 |
+
{
|
| 73527 |
+
"epoch": 11.962962962962964,
|
| 73528 |
+
"grad_norm": 0.1905059814453125,
|
| 73529 |
+
"learning_rate": 1.8683794141738915e-05,
|
| 73530 |
+
"loss": 0.8075,
|
| 73531 |
+
"step": 10503
|
| 73532 |
+
},
|
| 73533 |
+
{
|
| 73534 |
+
"epoch": 11.964102564102564,
|
| 73535 |
+
"grad_norm": 0.220254048705101,
|
| 73536 |
+
"learning_rate": 1.8679286222546873e-05,
|
| 73537 |
+
"loss": 0.7947,
|
| 73538 |
+
"step": 10504
|
| 73539 |
+
},
|
| 73540 |
+
{
|
| 73541 |
+
"epoch": 11.965242165242165,
|
| 73542 |
+
"grad_norm": 0.20022335648536682,
|
| 73543 |
+
"learning_rate": 1.8674778522890605e-05,
|
| 73544 |
+
"loss": 0.7204,
|
| 73545 |
+
"step": 10505
|
| 73546 |
+
},
|
| 73547 |
+
{
|
| 73548 |
+
"epoch": 11.966381766381767,
|
| 73549 |
+
"grad_norm": 0.2103656828403473,
|
| 73550 |
+
"learning_rate": 1.8670271042926675e-05,
|
| 73551 |
+
"loss": 0.6555,
|
| 73552 |
+
"step": 10506
|
| 73553 |
+
},
|
| 73554 |
+
{
|
| 73555 |
+
"epoch": 11.967521367521368,
|
| 73556 |
+
"grad_norm": 0.21049273014068604,
|
| 73557 |
+
"learning_rate": 1.866576378281164e-05,
|
| 73558 |
+
"loss": 0.6235,
|
| 73559 |
+
"step": 10507
|
| 73560 |
+
},
|
| 73561 |
+
{
|
| 73562 |
+
"epoch": 11.968660968660968,
|
| 73563 |
+
"grad_norm": 0.23613597452640533,
|
| 73564 |
+
"learning_rate": 1.8661256742702036e-05,
|
| 73565 |
+
"loss": 0.6448,
|
| 73566 |
+
"step": 10508
|
| 73567 |
+
},
|
| 73568 |
+
{
|
| 73569 |
+
"epoch": 11.96980056980057,
|
| 73570 |
+
"grad_norm": 0.21678756177425385,
|
| 73571 |
+
"learning_rate": 1.8656749922754424e-05,
|
| 73572 |
+
"loss": 0.8768,
|
| 73573 |
+
"step": 10509
|
| 73574 |
+
},
|
| 73575 |
+
{
|
| 73576 |
+
"epoch": 11.970940170940171,
|
| 73577 |
+
"grad_norm": 0.20622332394123077,
|
| 73578 |
+
"learning_rate": 1.8652243323125334e-05,
|
| 73579 |
+
"loss": 0.7321,
|
| 73580 |
+
"step": 10510
|
| 73581 |
+
},
|
| 73582 |
+
{
|
| 73583 |
+
"epoch": 11.972079772079772,
|
| 73584 |
+
"grad_norm": 0.22001869976520538,
|
| 73585 |
+
"learning_rate": 1.8647736943971287e-05,
|
| 73586 |
+
"loss": 0.6975,
|
| 73587 |
+
"step": 10511
|
| 73588 |
+
},
|
| 73589 |
+
{
|
| 73590 |
+
"epoch": 11.973219373219374,
|
| 73591 |
+
"grad_norm": 0.23506364226341248,
|
| 73592 |
+
"learning_rate": 1.864323078544881e-05,
|
| 73593 |
+
"loss": 0.7675,
|
| 73594 |
+
"step": 10512
|
| 73595 |
+
},
|
| 73596 |
+
{
|
| 73597 |
+
"epoch": 11.974358974358974,
|
| 73598 |
+
"grad_norm": 0.23605220019817352,
|
| 73599 |
+
"learning_rate": 1.86387248477144e-05,
|
| 73600 |
+
"loss": 0.7852,
|
| 73601 |
+
"step": 10513
|
| 73602 |
+
},
|
| 73603 |
+
{
|
| 73604 |
+
"epoch": 11.975498575498575,
|
| 73605 |
+
"grad_norm": 0.22302347421646118,
|
| 73606 |
+
"learning_rate": 1.863421913092458e-05,
|
| 73607 |
+
"loss": 0.7394,
|
| 73608 |
+
"step": 10514
|
| 73609 |
+
},
|
| 73610 |
+
{
|
| 73611 |
+
"epoch": 11.976638176638177,
|
| 73612 |
+
"grad_norm": 0.17315006256103516,
|
| 73613 |
+
"learning_rate": 1.862971363523583e-05,
|
| 73614 |
+
"loss": 0.6575,
|
| 73615 |
+
"step": 10515
|
| 73616 |
+
},
|
| 73617 |
+
{
|
| 73618 |
+
"epoch": 11.977777777777778,
|
| 73619 |
+
"grad_norm": 0.22734105587005615,
|
| 73620 |
+
"learning_rate": 1.8625208360804646e-05,
|
| 73621 |
+
"loss": 0.7262,
|
| 73622 |
+
"step": 10516
|
| 73623 |
+
},
|
| 73624 |
+
{
|
| 73625 |
+
"epoch": 11.978917378917378,
|
| 73626 |
+
"grad_norm": 0.2036786675453186,
|
| 73627 |
+
"learning_rate": 1.86207033077875e-05,
|
| 73628 |
+
"loss": 0.6624,
|
| 73629 |
+
"step": 10517
|
| 73630 |
+
},
|
| 73631 |
+
{
|
| 73632 |
+
"epoch": 11.98005698005698,
|
| 73633 |
+
"grad_norm": 0.24453534185886383,
|
| 73634 |
+
"learning_rate": 1.8616198476340878e-05,
|
| 73635 |
+
"loss": 0.7948,
|
| 73636 |
+
"step": 10518
|
| 73637 |
+
},
|
| 73638 |
+
{
|
| 73639 |
+
"epoch": 11.981196581196581,
|
| 73640 |
+
"grad_norm": 0.19842353463172913,
|
| 73641 |
+
"learning_rate": 1.8611693866621225e-05,
|
| 73642 |
+
"loss": 0.849,
|
| 73643 |
+
"step": 10519
|
| 73644 |
+
},
|
| 73645 |
+
{
|
| 73646 |
+
"epoch": 11.982336182336182,
|
| 73647 |
+
"grad_norm": 0.22061681747436523,
|
| 73648 |
+
"learning_rate": 1.8607189478785025e-05,
|
| 73649 |
+
"loss": 0.5082,
|
| 73650 |
+
"step": 10520
|
| 73651 |
+
},
|
| 73652 |
+
{
|
| 73653 |
+
"epoch": 11.983475783475784,
|
| 73654 |
+
"grad_norm": 0.25918304920196533,
|
| 73655 |
+
"learning_rate": 1.860268531298871e-05,
|
| 73656 |
+
"loss": 0.5882,
|
| 73657 |
+
"step": 10521
|
| 73658 |
+
},
|
| 73659 |
+
{
|
| 73660 |
+
"epoch": 11.984615384615385,
|
| 73661 |
+
"grad_norm": 0.26322653889656067,
|
| 73662 |
+
"learning_rate": 1.8598181369388733e-05,
|
| 73663 |
+
"loss": 0.3666,
|
| 73664 |
+
"step": 10522
|
| 73665 |
+
},
|
| 73666 |
+
{
|
| 73667 |
+
"epoch": 11.985754985754985,
|
| 73668 |
+
"grad_norm": 0.24528221786022186,
|
| 73669 |
+
"learning_rate": 1.8593677648141515e-05,
|
| 73670 |
+
"loss": 0.6525,
|
| 73671 |
+
"step": 10523
|
| 73672 |
+
},
|
| 73673 |
+
{
|
| 73674 |
+
"epoch": 11.986894586894588,
|
| 73675 |
+
"grad_norm": 0.24048669636249542,
|
| 73676 |
+
"learning_rate": 1.85891741494035e-05,
|
| 73677 |
+
"loss": 0.7327,
|
| 73678 |
+
"step": 10524
|
| 73679 |
+
},
|
| 73680 |
+
{
|
| 73681 |
+
"epoch": 11.988034188034188,
|
| 73682 |
+
"grad_norm": 0.2024715095758438,
|
| 73683 |
+
"learning_rate": 1.8584670873331087e-05,
|
| 73684 |
+
"loss": 0.6911,
|
| 73685 |
+
"step": 10525
|
| 73686 |
+
},
|
| 73687 |
+
{
|
| 73688 |
+
"epoch": 11.989173789173789,
|
| 73689 |
+
"grad_norm": 0.21110621094703674,
|
| 73690 |
+
"learning_rate": 1.8580167820080703e-05,
|
| 73691 |
+
"loss": 0.5711,
|
| 73692 |
+
"step": 10526
|
| 73693 |
+
},
|
| 73694 |
+
{
|
| 73695 |
+
"epoch": 11.990313390313391,
|
| 73696 |
+
"grad_norm": 0.19894184172153473,
|
| 73697 |
+
"learning_rate": 1.857566498980874e-05,
|
| 73698 |
+
"loss": 0.8353,
|
| 73699 |
+
"step": 10527
|
| 73700 |
+
},
|
| 73701 |
+
{
|
| 73702 |
+
"epoch": 11.991452991452991,
|
| 73703 |
+
"grad_norm": 0.24942967295646667,
|
| 73704 |
+
"learning_rate": 1.8571162382671602e-05,
|
| 73705 |
+
"loss": 0.56,
|
| 73706 |
+
"step": 10528
|
| 73707 |
+
},
|
| 73708 |
+
{
|
| 73709 |
+
"epoch": 11.992592592592592,
|
| 73710 |
+
"grad_norm": 0.23511634767055511,
|
| 73711 |
+
"learning_rate": 1.8566659998825674e-05,
|
| 73712 |
+
"loss": 0.6542,
|
| 73713 |
+
"step": 10529
|
| 73714 |
+
},
|
| 73715 |
+
{
|
| 73716 |
+
"epoch": 11.993732193732194,
|
| 73717 |
+
"grad_norm": 0.2347230464220047,
|
| 73718 |
+
"learning_rate": 1.8562157838427325e-05,
|
| 73719 |
+
"loss": 0.6325,
|
| 73720 |
+
"step": 10530
|
| 73721 |
+
},
|
| 73722 |
+
{
|
| 73723 |
+
"epoch": 11.994871794871795,
|
| 73724 |
+
"grad_norm": 0.2472597360610962,
|
| 73725 |
+
"learning_rate": 1.8557655901632952e-05,
|
| 73726 |
+
"loss": 0.696,
|
| 73727 |
+
"step": 10531
|
| 73728 |
+
},
|
| 73729 |
+
{
|
| 73730 |
+
"epoch": 11.996011396011395,
|
| 73731 |
+
"grad_norm": 0.19690778851509094,
|
| 73732 |
+
"learning_rate": 1.8553154188598897e-05,
|
| 73733 |
+
"loss": 0.7692,
|
| 73734 |
+
"step": 10532
|
| 73735 |
+
},
|
| 73736 |
+
{
|
| 73737 |
+
"epoch": 11.997150997150998,
|
| 73738 |
+
"grad_norm": 0.1885654628276825,
|
| 73739 |
+
"learning_rate": 1.8548652699481535e-05,
|
| 73740 |
+
"loss": 0.728,
|
| 73741 |
+
"step": 10533
|
| 73742 |
+
},
|
| 73743 |
+
{
|
| 73744 |
+
"epoch": 11.998290598290598,
|
| 73745 |
+
"grad_norm": 0.19377920031547546,
|
| 73746 |
+
"learning_rate": 1.8544151434437202e-05,
|
| 73747 |
+
"loss": 0.824,
|
| 73748 |
+
"step": 10534
|
| 73749 |
+
},
|
| 73750 |
+
{
|
| 73751 |
+
"epoch": 11.999430199430199,
|
| 73752 |
+
"grad_norm": 0.2881132662296295,
|
| 73753 |
+
"learning_rate": 1.8539650393622246e-05,
|
| 73754 |
+
"loss": 0.5325,
|
| 73755 |
+
"step": 10535
|
| 73756 |
+
},
|
| 73757 |
+
{
|
| 73758 |
+
"epoch": 12.0,
|
| 73759 |
+
"grad_norm": 0.30600935220718384,
|
| 73760 |
+
"learning_rate": 1.8535149577192993e-05,
|
| 73761 |
+
"loss": 0.5586,
|
| 73762 |
+
"step": 10536
|
| 73763 |
+
},
|
| 73764 |
+
{
|
| 73765 |
+
"epoch": 12.0011396011396,
|
| 73766 |
+
"grad_norm": 0.23088836669921875,
|
| 73767 |
+
"learning_rate": 1.853064898530578e-05,
|
| 73768 |
+
"loss": 0.6768,
|
| 73769 |
+
"step": 10537
|
| 73770 |
+
},
|
| 73771 |
+
{
|
| 73772 |
+
"epoch": 12.002279202279203,
|
| 73773 |
+
"grad_norm": 0.1733100265264511,
|
| 73774 |
+
"learning_rate": 1.8526148618116913e-05,
|
| 73775 |
+
"loss": 0.8816,
|
| 73776 |
+
"step": 10538
|
| 73777 |
+
},
|
| 73778 |
+
{
|
| 73779 |
+
"epoch": 12.003418803418803,
|
| 73780 |
+
"grad_norm": 0.21051400899887085,
|
| 73781 |
+
"learning_rate": 1.852164847578271e-05,
|
| 73782 |
+
"loss": 0.732,
|
| 73783 |
+
"step": 10539
|
| 73784 |
+
},
|
| 73785 |
+
{
|
| 73786 |
+
"epoch": 12.004558404558404,
|
| 73787 |
+
"grad_norm": 0.17774631083011627,
|
| 73788 |
+
"learning_rate": 1.8517148558459468e-05,
|
| 73789 |
+
"loss": 0.8163,
|
| 73790 |
+
"step": 10540
|
| 73791 |
+
},
|
| 73792 |
+
{
|
| 73793 |
+
"epoch": 12.005698005698006,
|
| 73794 |
+
"grad_norm": 0.17382650077342987,
|
| 73795 |
+
"learning_rate": 1.851264886630348e-05,
|
| 73796 |
+
"loss": 0.9052,
|
| 73797 |
+
"step": 10541
|
| 73798 |
+
},
|
| 73799 |
+
{
|
| 73800 |
+
"epoch": 12.006837606837607,
|
| 73801 |
+
"grad_norm": 0.2258656919002533,
|
| 73802 |
+
"learning_rate": 1.850814939947105e-05,
|
| 73803 |
+
"loss": 0.5748,
|
| 73804 |
+
"step": 10542
|
| 73805 |
+
},
|
| 73806 |
+
{
|
| 73807 |
+
"epoch": 12.007977207977207,
|
| 73808 |
+
"grad_norm": 0.19269326329231262,
|
| 73809 |
+
"learning_rate": 1.850365015811843e-05,
|
| 73810 |
+
"loss": 0.6872,
|
| 73811 |
+
"step": 10543
|
| 73812 |
+
},
|
| 73813 |
+
{
|
| 73814 |
+
"epoch": 12.00911680911681,
|
| 73815 |
+
"grad_norm": 0.20680245757102966,
|
| 73816 |
+
"learning_rate": 1.8499151142401915e-05,
|
| 73817 |
+
"loss": 0.6299,
|
| 73818 |
+
"step": 10544
|
| 73819 |
+
},
|
| 73820 |
+
{
|
| 73821 |
+
"epoch": 12.01025641025641,
|
| 73822 |
+
"grad_norm": 0.16280394792556763,
|
| 73823 |
+
"learning_rate": 1.8494652352477755e-05,
|
| 73824 |
+
"loss": 0.711,
|
| 73825 |
+
"step": 10545
|
| 73826 |
+
},
|
| 73827 |
+
{
|
| 73828 |
+
"epoch": 12.01139601139601,
|
| 73829 |
+
"grad_norm": 0.19511796534061432,
|
| 73830 |
+
"learning_rate": 1.849015378850221e-05,
|
| 73831 |
+
"loss": 0.6957,
|
| 73832 |
+
"step": 10546
|
| 73833 |
+
},
|
| 73834 |
+
{
|
| 73835 |
+
"epoch": 12.012535612535613,
|
| 73836 |
+
"grad_norm": 0.18030062317848206,
|
| 73837 |
+
"learning_rate": 1.8485655450631528e-05,
|
| 73838 |
+
"loss": 0.5629,
|
| 73839 |
+
"step": 10547
|
| 73840 |
+
},
|
| 73841 |
+
{
|
| 73842 |
+
"epoch": 12.013675213675214,
|
| 73843 |
+
"grad_norm": 0.2140948325395584,
|
| 73844 |
+
"learning_rate": 1.8481157339021946e-05,
|
| 73845 |
+
"loss": 0.724,
|
| 73846 |
+
"step": 10548
|
| 73847 |
+
},
|
| 73848 |
+
{
|
| 73849 |
+
"epoch": 12.014814814814814,
|
| 73850 |
+
"grad_norm": 0.17993023991584778,
|
| 73851 |
+
"learning_rate": 1.8476659453829692e-05,
|
| 73852 |
+
"loss": 0.778,
|
| 73853 |
+
"step": 10549
|
| 73854 |
+
},
|
| 73855 |
+
{
|
| 73856 |
+
"epoch": 12.015954415954416,
|
| 73857 |
+
"grad_norm": 0.26871827244758606,
|
| 73858 |
+
"learning_rate": 1.8472161795211003e-05,
|
| 73859 |
+
"loss": 0.5918,
|
| 73860 |
+
"step": 10550
|
| 73861 |
+
},
|
| 73862 |
+
{
|
| 73863 |
+
"epoch": 12.017094017094017,
|
| 73864 |
+
"grad_norm": 0.2065512090921402,
|
| 73865 |
+
"learning_rate": 1.8467664363322075e-05,
|
| 73866 |
+
"loss": 0.6549,
|
| 73867 |
+
"step": 10551
|
| 73868 |
+
},
|
| 73869 |
+
{
|
| 73870 |
+
"epoch": 12.018233618233618,
|
| 73871 |
+
"grad_norm": 0.1633397936820984,
|
| 73872 |
+
"learning_rate": 1.8463167158319127e-05,
|
| 73873 |
+
"loss": 0.8051,
|
| 73874 |
+
"step": 10552
|
| 73875 |
+
},
|
| 73876 |
+
{
|
| 73877 |
+
"epoch": 12.01937321937322,
|
| 73878 |
+
"grad_norm": 0.1748124659061432,
|
| 73879 |
+
"learning_rate": 1.845867018035837e-05,
|
| 73880 |
+
"loss": 0.7225,
|
| 73881 |
+
"step": 10553
|
| 73882 |
+
},
|
| 73883 |
+
{
|
| 73884 |
+
"epoch": 12.02051282051282,
|
| 73885 |
+
"grad_norm": 0.21973411738872528,
|
| 73886 |
+
"learning_rate": 1.845417342959598e-05,
|
| 73887 |
+
"loss": 0.6511,
|
| 73888 |
+
"step": 10554
|
| 73889 |
+
},
|
| 73890 |
+
{
|
| 73891 |
+
"epoch": 12.021652421652421,
|
| 73892 |
+
"grad_norm": 0.20660950243473053,
|
| 73893 |
+
"learning_rate": 1.8449676906188154e-05,
|
| 73894 |
+
"loss": 0.6641,
|
| 73895 |
+
"step": 10555
|
| 73896 |
+
},
|
| 73897 |
+
{
|
| 73898 |
+
"epoch": 12.022792022792023,
|
| 73899 |
+
"grad_norm": 0.18575088679790497,
|
| 73900 |
+
"learning_rate": 1.8445180610291056e-05,
|
| 73901 |
+
"loss": 0.7962,
|
| 73902 |
+
"step": 10556
|
| 73903 |
+
},
|
| 73904 |
+
{
|
| 73905 |
+
"epoch": 12.023931623931624,
|
| 73906 |
+
"grad_norm": 0.19864317774772644,
|
| 73907 |
+
"learning_rate": 1.844068454206087e-05,
|
| 73908 |
+
"loss": 0.6913,
|
| 73909 |
+
"step": 10557
|
| 73910 |
+
},
|
| 73911 |
+
{
|
| 73912 |
+
"epoch": 12.025071225071224,
|
| 73913 |
+
"grad_norm": 0.1899966448545456,
|
| 73914 |
+
"learning_rate": 1.843618870165374e-05,
|
| 73915 |
+
"loss": 0.746,
|
| 73916 |
+
"step": 10558
|
| 73917 |
+
},
|
| 73918 |
+
{
|
| 73919 |
+
"epoch": 12.026210826210827,
|
| 73920 |
+
"grad_norm": 0.21713949739933014,
|
| 73921 |
+
"learning_rate": 1.8431693089225833e-05,
|
| 73922 |
+
"loss": 0.5305,
|
| 73923 |
+
"step": 10559
|
| 73924 |
+
},
|
| 73925 |
+
{
|
| 73926 |
+
"epoch": 12.027350427350427,
|
| 73927 |
+
"grad_norm": 0.23974689841270447,
|
| 73928 |
+
"learning_rate": 1.842719770493328e-05,
|
| 73929 |
+
"loss": 0.5182,
|
| 73930 |
+
"step": 10560
|
| 73931 |
+
},
|
| 73932 |
+
{
|
| 73933 |
+
"epoch": 12.028490028490028,
|
| 73934 |
+
"grad_norm": 0.22211728990077972,
|
| 73935 |
+
"learning_rate": 1.8422702548932232e-05,
|
| 73936 |
+
"loss": 0.6479,
|
| 73937 |
+
"step": 10561
|
| 73938 |
+
},
|
| 73939 |
+
{
|
| 73940 |
+
"epoch": 12.02962962962963,
|
| 73941 |
+
"grad_norm": 0.18979617953300476,
|
| 73942 |
+
"learning_rate": 1.8418207621378808e-05,
|
| 73943 |
+
"loss": 0.7081,
|
| 73944 |
+
"step": 10562
|
| 73945 |
+
},
|
| 73946 |
+
{
|
| 73947 |
+
"epoch": 12.03076923076923,
|
| 73948 |
+
"grad_norm": 0.286356121301651,
|
| 73949 |
+
"learning_rate": 1.841371292242913e-05,
|
| 73950 |
+
"loss": 0.3239,
|
| 73951 |
+
"step": 10563
|
| 73952 |
+
},
|
| 73953 |
+
{
|
| 73954 |
+
"epoch": 12.031908831908831,
|
| 73955 |
+
"grad_norm": 0.22852590680122375,
|
| 73956 |
+
"learning_rate": 1.840921845223932e-05,
|
| 73957 |
+
"loss": 0.5668,
|
| 73958 |
+
"step": 10564
|
| 73959 |
+
},
|
| 73960 |
+
{
|
| 73961 |
+
"epoch": 12.033048433048434,
|
| 73962 |
+
"grad_norm": 0.1991380751132965,
|
| 73963 |
+
"learning_rate": 1.840472421096548e-05,
|
| 73964 |
+
"loss": 0.6964,
|
| 73965 |
+
"step": 10565
|
| 73966 |
+
},
|
| 73967 |
+
{
|
| 73968 |
+
"epoch": 12.034188034188034,
|
| 73969 |
+
"grad_norm": 0.18954479694366455,
|
| 73970 |
+
"learning_rate": 1.84002301987637e-05,
|
| 73971 |
+
"loss": 0.6792,
|
| 73972 |
+
"step": 10566
|
| 73973 |
+
},
|
| 73974 |
+
{
|
| 73975 |
+
"epoch": 12.035327635327635,
|
| 73976 |
+
"grad_norm": 0.26388251781463623,
|
| 73977 |
+
"learning_rate": 1.839573641579008e-05,
|
| 73978 |
+
"loss": 0.4905,
|
| 73979 |
+
"step": 10567
|
| 73980 |
+
},
|
| 73981 |
+
{
|
| 73982 |
+
"epoch": 12.036467236467237,
|
| 73983 |
+
"grad_norm": 0.19882208108901978,
|
| 73984 |
+
"learning_rate": 1.839124286220069e-05,
|
| 73985 |
+
"loss": 0.7282,
|
| 73986 |
+
"step": 10568
|
| 73987 |
+
},
|
| 73988 |
+
{
|
| 73989 |
+
"epoch": 12.037606837606837,
|
| 73990 |
+
"grad_norm": 0.21259771287441254,
|
| 73991 |
+
"learning_rate": 1.8386749538151618e-05,
|
| 73992 |
+
"loss": 0.6895,
|
| 73993 |
+
"step": 10569
|
| 73994 |
+
},
|
| 73995 |
+
{
|
| 73996 |
+
"epoch": 12.038746438746438,
|
| 73997 |
+
"grad_norm": 0.2104126363992691,
|
| 73998 |
+
"learning_rate": 1.8382256443798916e-05,
|
| 73999 |
+
"loss": 0.721,
|
| 74000 |
+
"step": 10570
|
| 74001 |
+
},
|
| 74002 |
+
{
|
| 74003 |
+
"epoch": 12.03988603988604,
|
| 74004 |
+
"grad_norm": 0.20652472972869873,
|
| 74005 |
+
"learning_rate": 1.8377763579298647e-05,
|
| 74006 |
+
"loss": 0.8174,
|
| 74007 |
+
"step": 10571
|
| 74008 |
+
},
|
| 74009 |
+
{
|
| 74010 |
+
"epoch": 12.04102564102564,
|
| 74011 |
+
"grad_norm": 0.1936299055814743,
|
| 74012 |
+
"learning_rate": 1.837327094480686e-05,
|
| 74013 |
+
"loss": 0.6497,
|
| 74014 |
+
"step": 10572
|
| 74015 |
+
},
|
| 74016 |
+
{
|
| 74017 |
+
"epoch": 12.042165242165241,
|
| 74018 |
+
"grad_norm": 0.17510229349136353,
|
| 74019 |
+
"learning_rate": 1.83687785404796e-05,
|
| 74020 |
+
"loss": 0.7237,
|
| 74021 |
+
"step": 10573
|
| 74022 |
+
},
|
| 74023 |
+
{
|
| 74024 |
+
"epoch": 12.043304843304844,
|
| 74025 |
+
"grad_norm": 0.2524392008781433,
|
| 74026 |
+
"learning_rate": 1.8364286366472892e-05,
|
| 74027 |
+
"loss": 0.6238,
|
| 74028 |
+
"step": 10574
|
| 74029 |
+
},
|
| 74030 |
+
{
|
| 74031 |
+
"epoch": 12.044444444444444,
|
| 74032 |
+
"grad_norm": 0.15890449285507202,
|
| 74033 |
+
"learning_rate": 1.835979442294276e-05,
|
| 74034 |
+
"loss": 0.6447,
|
| 74035 |
+
"step": 10575
|
| 74036 |
+
},
|
| 74037 |
+
{
|
| 74038 |
+
"epoch": 12.045584045584045,
|
| 74039 |
+
"grad_norm": 0.2702021896839142,
|
| 74040 |
+
"learning_rate": 1.8355302710045242e-05,
|
| 74041 |
+
"loss": 0.5137,
|
| 74042 |
+
"step": 10576
|
| 74043 |
+
},
|
| 74044 |
+
{
|
| 74045 |
+
"epoch": 12.046723646723647,
|
| 74046 |
+
"grad_norm": 0.23867960274219513,
|
| 74047 |
+
"learning_rate": 1.8350811227936326e-05,
|
| 74048 |
+
"loss": 0.6878,
|
| 74049 |
+
"step": 10577
|
| 74050 |
+
},
|
| 74051 |
+
{
|
| 74052 |
+
"epoch": 12.047863247863248,
|
| 74053 |
+
"grad_norm": 0.2099626511335373,
|
| 74054 |
+
"learning_rate": 1.8346319976772028e-05,
|
| 74055 |
+
"loss": 0.6631,
|
| 74056 |
+
"step": 10578
|
| 74057 |
+
},
|
| 74058 |
+
{
|
| 74059 |
+
"epoch": 12.049002849002848,
|
| 74060 |
+
"grad_norm": 0.22138890624046326,
|
| 74061 |
+
"learning_rate": 1.834182895670833e-05,
|
| 74062 |
+
"loss": 0.6583,
|
| 74063 |
+
"step": 10579
|
| 74064 |
+
},
|
| 74065 |
+
{
|
| 74066 |
+
"epoch": 12.05014245014245,
|
| 74067 |
+
"grad_norm": 0.25138336420059204,
|
| 74068 |
+
"learning_rate": 1.8337338167901224e-05,
|
| 74069 |
+
"loss": 0.4966,
|
| 74070 |
+
"step": 10580
|
| 74071 |
+
},
|
| 74072 |
+
{
|
| 74073 |
+
"epoch": 12.051282051282051,
|
| 74074 |
+
"grad_norm": 0.1850442737340927,
|
| 74075 |
+
"learning_rate": 1.8332847610506688e-05,
|
| 74076 |
+
"loss": 0.6409,
|
| 74077 |
+
"step": 10581
|
| 74078 |
+
},
|
| 74079 |
+
{
|
| 74080 |
+
"epoch": 12.052421652421652,
|
| 74081 |
+
"grad_norm": 0.1915789395570755,
|
| 74082 |
+
"learning_rate": 1.8328357284680687e-05,
|
| 74083 |
+
"loss": 0.7341,
|
| 74084 |
+
"step": 10582
|
| 74085 |
+
},
|
| 74086 |
+
{
|
| 74087 |
+
"epoch": 12.053561253561254,
|
| 74088 |
+
"grad_norm": 0.19199860095977783,
|
| 74089 |
+
"learning_rate": 1.8323867190579183e-05,
|
| 74090 |
+
"loss": 0.8708,
|
| 74091 |
+
"step": 10583
|
| 74092 |
+
},
|
| 74093 |
+
{
|
| 74094 |
+
"epoch": 12.054700854700855,
|
| 74095 |
+
"grad_norm": 0.19183555245399475,
|
| 74096 |
+
"learning_rate": 1.8319377328358133e-05,
|
| 74097 |
+
"loss": 0.8864,
|
| 74098 |
+
"step": 10584
|
| 74099 |
+
},
|
| 74100 |
+
{
|
| 74101 |
+
"epoch": 12.055840455840455,
|
| 74102 |
+
"grad_norm": 0.1983659416437149,
|
| 74103 |
+
"learning_rate": 1.831488769817348e-05,
|
| 74104 |
+
"loss": 0.6469,
|
| 74105 |
+
"step": 10585
|
| 74106 |
+
},
|
| 74107 |
+
{
|
| 74108 |
+
"epoch": 12.056980056980057,
|
| 74109 |
+
"grad_norm": 0.21458525955677032,
|
| 74110 |
+
"learning_rate": 1.8310398300181153e-05,
|
| 74111 |
+
"loss": 0.6234,
|
| 74112 |
+
"step": 10586
|
| 74113 |
+
},
|
| 74114 |
+
{
|
| 74115 |
+
"epoch": 12.058119658119658,
|
| 74116 |
+
"grad_norm": 0.2103472352027893,
|
| 74117 |
+
"learning_rate": 1.83059091345371e-05,
|
| 74118 |
+
"loss": 0.8083,
|
| 74119 |
+
"step": 10587
|
| 74120 |
+
},
|
| 74121 |
+
{
|
| 74122 |
+
"epoch": 12.059259259259258,
|
| 74123 |
+
"grad_norm": 0.19039538502693176,
|
| 74124 |
+
"learning_rate": 1.830142020139723e-05,
|
| 74125 |
+
"loss": 0.79,
|
| 74126 |
+
"step": 10588
|
| 74127 |
+
},
|
| 74128 |
+
{
|
| 74129 |
+
"epoch": 12.06039886039886,
|
| 74130 |
+
"grad_norm": 0.2611573040485382,
|
| 74131 |
+
"learning_rate": 1.829693150091746e-05,
|
| 74132 |
+
"loss": 0.5305,
|
| 74133 |
+
"step": 10589
|
| 74134 |
+
},
|
| 74135 |
+
{
|
| 74136 |
+
"epoch": 12.061538461538461,
|
| 74137 |
+
"grad_norm": 0.25013938546180725,
|
| 74138 |
+
"learning_rate": 1.8292443033253682e-05,
|
| 74139 |
+
"loss": 0.6069,
|
| 74140 |
+
"step": 10590
|
| 74141 |
+
},
|
| 74142 |
+
{
|
| 74143 |
+
"epoch": 12.062678062678062,
|
| 74144 |
+
"grad_norm": 0.2411351501941681,
|
| 74145 |
+
"learning_rate": 1.8287954798561815e-05,
|
| 74146 |
+
"loss": 0.5709,
|
| 74147 |
+
"step": 10591
|
| 74148 |
+
},
|
| 74149 |
+
{
|
| 74150 |
+
"epoch": 12.063817663817664,
|
| 74151 |
+
"grad_norm": 0.20945434272289276,
|
| 74152 |
+
"learning_rate": 1.8283466796997728e-05,
|
| 74153 |
+
"loss": 0.6245,
|
| 74154 |
+
"step": 10592
|
| 74155 |
+
},
|
| 74156 |
+
{
|
| 74157 |
+
"epoch": 12.064957264957265,
|
| 74158 |
+
"grad_norm": 0.22989006340503693,
|
| 74159 |
+
"learning_rate": 1.827897902871732e-05,
|
| 74160 |
+
"loss": 0.53,
|
| 74161 |
+
"step": 10593
|
| 74162 |
+
},
|
| 74163 |
+
{
|
| 74164 |
+
"epoch": 12.066096866096865,
|
| 74165 |
+
"grad_norm": 0.19135035574436188,
|
| 74166 |
+
"learning_rate": 1.8274491493876442e-05,
|
| 74167 |
+
"loss": 0.6933,
|
| 74168 |
+
"step": 10594
|
| 74169 |
+
},
|
| 74170 |
+
{
|
| 74171 |
+
"epoch": 12.067236467236468,
|
| 74172 |
+
"grad_norm": 0.2087395340204239,
|
| 74173 |
+
"learning_rate": 1.8270004192630976e-05,
|
| 74174 |
+
"loss": 0.8001,
|
| 74175 |
+
"step": 10595
|
| 74176 |
+
},
|
| 74177 |
+
{
|
| 74178 |
+
"epoch": 12.068376068376068,
|
| 74179 |
+
"grad_norm": 0.24208243191242218,
|
| 74180 |
+
"learning_rate": 1.8265517125136768e-05,
|
| 74181 |
+
"loss": 0.6004,
|
| 74182 |
+
"step": 10596
|
| 74183 |
+
},
|
| 74184 |
+
{
|
| 74185 |
+
"epoch": 12.069515669515669,
|
| 74186 |
+
"grad_norm": 0.21831801533699036,
|
| 74187 |
+
"learning_rate": 1.8261030291549664e-05,
|
| 74188 |
+
"loss": 0.7293,
|
| 74189 |
+
"step": 10597
|
| 74190 |
+
},
|
| 74191 |
+
{
|
| 74192 |
+
"epoch": 12.070655270655271,
|
| 74193 |
+
"grad_norm": 0.22201023995876312,
|
| 74194 |
+
"learning_rate": 1.825654369202552e-05,
|
| 74195 |
+
"loss": 0.7607,
|
| 74196 |
+
"step": 10598
|
| 74197 |
+
},
|
| 74198 |
+
{
|
| 74199 |
+
"epoch": 12.071794871794872,
|
| 74200 |
+
"grad_norm": 0.19370655715465546,
|
| 74201 |
+
"learning_rate": 1.8252057326720157e-05,
|
| 74202 |
+
"loss": 0.6662,
|
| 74203 |
+
"step": 10599
|
| 74204 |
+
},
|
| 74205 |
+
{
|
| 74206 |
+
"epoch": 12.072934472934472,
|
| 74207 |
+
"grad_norm": 0.21607200801372528,
|
| 74208 |
+
"learning_rate": 1.8247571195789398e-05,
|
| 74209 |
+
"loss": 0.6671,
|
| 74210 |
+
"step": 10600
|
| 74211 |
+
},
|
| 74212 |
+
{
|
| 74213 |
+
"epoch": 12.074074074074074,
|
| 74214 |
+
"grad_norm": 0.18963831663131714,
|
| 74215 |
+
"learning_rate": 1.824308529938906e-05,
|
| 74216 |
+
"loss": 0.6537,
|
| 74217 |
+
"step": 10601
|
| 74218 |
+
},
|
| 74219 |
+
{
|
| 74220 |
+
"epoch": 12.075213675213675,
|
| 74221 |
+
"grad_norm": 0.22693610191345215,
|
| 74222 |
+
"learning_rate": 1.8238599637674954e-05,
|
| 74223 |
+
"loss": 0.5216,
|
| 74224 |
+
"step": 10602
|
| 74225 |
+
},
|
| 74226 |
+
{
|
| 74227 |
+
"epoch": 12.076353276353275,
|
| 74228 |
+
"grad_norm": 0.20524661242961884,
|
| 74229 |
+
"learning_rate": 1.823411421080288e-05,
|
| 74230 |
+
"loss": 0.8214,
|
| 74231 |
+
"step": 10603
|
| 74232 |
+
},
|
| 74233 |
+
{
|
| 74234 |
+
"epoch": 12.077492877492878,
|
| 74235 |
+
"grad_norm": 0.205473855137825,
|
| 74236 |
+
"learning_rate": 1.8229629018928617e-05,
|
| 74237 |
+
"loss": 0.553,
|
| 74238 |
+
"step": 10604
|
| 74239 |
+
},
|
| 74240 |
+
{
|
| 74241 |
+
"epoch": 12.078632478632478,
|
| 74242 |
+
"grad_norm": 0.1943778395652771,
|
| 74243 |
+
"learning_rate": 1.8225144062207966e-05,
|
| 74244 |
+
"loss": 0.681,
|
| 74245 |
+
"step": 10605
|
| 74246 |
+
},
|
| 74247 |
+
{
|
| 74248 |
+
"epoch": 12.079772079772079,
|
| 74249 |
+
"grad_norm": 0.20552857220172882,
|
| 74250 |
+
"learning_rate": 1.8220659340796684e-05,
|
| 74251 |
+
"loss": 0.797,
|
| 74252 |
+
"step": 10606
|
| 74253 |
+
},
|
| 74254 |
+
{
|
| 74255 |
+
"epoch": 12.080911680911681,
|
| 74256 |
+
"grad_norm": 0.21533159911632538,
|
| 74257 |
+
"learning_rate": 1.8216174854850556e-05,
|
| 74258 |
+
"loss": 0.6133,
|
| 74259 |
+
"step": 10607
|
| 74260 |
+
},
|
| 74261 |
+
{
|
| 74262 |
+
"epoch": 12.082051282051282,
|
| 74263 |
+
"grad_norm": 0.17289423942565918,
|
| 74264 |
+
"learning_rate": 1.8211690604525317e-05,
|
| 74265 |
+
"loss": 0.8102,
|
| 74266 |
+
"step": 10608
|
| 74267 |
+
},
|
| 74268 |
+
{
|
| 74269 |
+
"epoch": 12.083190883190884,
|
| 74270 |
+
"grad_norm": 0.21243703365325928,
|
| 74271 |
+
"learning_rate": 1.8207206589976734e-05,
|
| 74272 |
+
"loss": 0.8116,
|
| 74273 |
+
"step": 10609
|
| 74274 |
+
},
|
| 74275 |
+
{
|
| 74276 |
+
"epoch": 12.084330484330485,
|
| 74277 |
+
"grad_norm": 0.19925470650196075,
|
| 74278 |
+
"learning_rate": 1.8202722811360556e-05,
|
| 74279 |
+
"loss": 0.8322,
|
| 74280 |
+
"step": 10610
|
| 74281 |
+
},
|
| 74282 |
+
{
|
| 74283 |
+
"epoch": 12.085470085470085,
|
| 74284 |
+
"grad_norm": 0.18746793270111084,
|
| 74285 |
+
"learning_rate": 1.81982392688325e-05,
|
| 74286 |
+
"loss": 0.8362,
|
| 74287 |
+
"step": 10611
|
| 74288 |
+
},
|
| 74289 |
+
{
|
| 74290 |
+
"epoch": 12.086609686609687,
|
| 74291 |
+
"grad_norm": 0.2454654425382614,
|
| 74292 |
+
"learning_rate": 1.8193755962548304e-05,
|
| 74293 |
+
"loss": 0.5467,
|
| 74294 |
+
"step": 10612
|
| 74295 |
+
},
|
| 74296 |
+
{
|
| 74297 |
+
"epoch": 12.087749287749288,
|
| 74298 |
+
"grad_norm": 0.21298150718212128,
|
| 74299 |
+
"learning_rate": 1.8189272892663678e-05,
|
| 74300 |
+
"loss": 0.7309,
|
| 74301 |
+
"step": 10613
|
| 74302 |
+
},
|
| 74303 |
+
{
|
| 74304 |
+
"epoch": 12.088888888888889,
|
| 74305 |
+
"grad_norm": 0.21078455448150635,
|
| 74306 |
+
"learning_rate": 1.8184790059334338e-05,
|
| 74307 |
+
"loss": 0.6125,
|
| 74308 |
+
"step": 10614
|
| 74309 |
+
},
|
| 74310 |
+
{
|
| 74311 |
+
"epoch": 12.090028490028491,
|
| 74312 |
+
"grad_norm": 0.2133013904094696,
|
| 74313 |
+
"learning_rate": 1.8180307462715974e-05,
|
| 74314 |
+
"loss": 0.6139,
|
| 74315 |
+
"step": 10615
|
| 74316 |
+
},
|
| 74317 |
+
{
|
| 74318 |
+
"epoch": 12.091168091168091,
|
| 74319 |
+
"grad_norm": 0.2306240051984787,
|
| 74320 |
+
"learning_rate": 1.8175825102964293e-05,
|
| 74321 |
+
"loss": 0.5439,
|
| 74322 |
+
"step": 10616
|
| 74323 |
+
},
|
| 74324 |
+
{
|
| 74325 |
+
"epoch": 12.092307692307692,
|
| 74326 |
+
"grad_norm": 0.25794631242752075,
|
| 74327 |
+
"learning_rate": 1.8171342980234968e-05,
|
| 74328 |
+
"loss": 0.551,
|
| 74329 |
+
"step": 10617
|
| 74330 |
+
},
|
| 74331 |
+
{
|
| 74332 |
+
"epoch": 12.093447293447294,
|
| 74333 |
+
"grad_norm": 0.16845683753490448,
|
| 74334 |
+
"learning_rate": 1.8166861094683685e-05,
|
| 74335 |
+
"loss": 0.7664,
|
| 74336 |
+
"step": 10618
|
| 74337 |
+
},
|
| 74338 |
+
{
|
| 74339 |
+
"epoch": 12.094586894586895,
|
| 74340 |
+
"grad_norm": 0.21890786290168762,
|
| 74341 |
+
"learning_rate": 1.8162379446466096e-05,
|
| 74342 |
+
"loss": 0.7552,
|
| 74343 |
+
"step": 10619
|
| 74344 |
+
},
|
| 74345 |
+
{
|
| 74346 |
+
"epoch": 12.095726495726495,
|
| 74347 |
+
"grad_norm": 0.2112084925174713,
|
| 74348 |
+
"learning_rate": 1.815789803573788e-05,
|
| 74349 |
+
"loss": 0.6463,
|
| 74350 |
+
"step": 10620
|
| 74351 |
+
},
|
| 74352 |
+
{
|
| 74353 |
+
"epoch": 12.096866096866098,
|
| 74354 |
+
"grad_norm": 0.2195863425731659,
|
| 74355 |
+
"learning_rate": 1.8153416862654683e-05,
|
| 74356 |
+
"loss": 0.6289,
|
| 74357 |
+
"step": 10621
|
| 74358 |
+
},
|
| 74359 |
+
{
|
| 74360 |
+
"epoch": 12.098005698005698,
|
| 74361 |
+
"grad_norm": 0.18846504390239716,
|
| 74362 |
+
"learning_rate": 1.8148935927372143e-05,
|
| 74363 |
+
"loss": 0.8093,
|
| 74364 |
+
"step": 10622
|
| 74365 |
+
},
|
| 74366 |
+
{
|
| 74367 |
+
"epoch": 12.099145299145299,
|
| 74368 |
+
"grad_norm": 0.22838300466537476,
|
| 74369 |
+
"learning_rate": 1.8144455230045904e-05,
|
| 74370 |
+
"loss": 0.8178,
|
| 74371 |
+
"step": 10623
|
| 74372 |
+
},
|
| 74373 |
+
{
|
| 74374 |
+
"epoch": 12.100284900284901,
|
| 74375 |
+
"grad_norm": 0.2297404259443283,
|
| 74376 |
+
"learning_rate": 1.8139974770831584e-05,
|
| 74377 |
+
"loss": 0.5972,
|
| 74378 |
+
"step": 10624
|
| 74379 |
+
},
|
| 74380 |
+
{
|
| 74381 |
+
"epoch": 12.101424501424502,
|
| 74382 |
+
"grad_norm": 0.20052561163902283,
|
| 74383 |
+
"learning_rate": 1.8135494549884807e-05,
|
| 74384 |
+
"loss": 0.7274,
|
| 74385 |
+
"step": 10625
|
| 74386 |
+
},
|
| 74387 |
+
{
|
| 74388 |
+
"epoch": 12.102564102564102,
|
| 74389 |
+
"grad_norm": 0.19281281530857086,
|
| 74390 |
+
"learning_rate": 1.813101456736118e-05,
|
| 74391 |
+
"loss": 0.8087,
|
| 74392 |
+
"step": 10626
|
| 74393 |
+
},
|
| 74394 |
+
{
|
| 74395 |
+
"epoch": 12.103703703703705,
|
| 74396 |
+
"grad_norm": 0.18218734860420227,
|
| 74397 |
+
"learning_rate": 1.8126534823416306e-05,
|
| 74398 |
+
"loss": 0.6348,
|
| 74399 |
+
"step": 10627
|
| 74400 |
+
},
|
| 74401 |
+
{
|
| 74402 |
+
"epoch": 12.104843304843305,
|
| 74403 |
+
"grad_norm": 0.1917387694120407,
|
| 74404 |
+
"learning_rate": 1.8122055318205783e-05,
|
| 74405 |
+
"loss": 0.5225,
|
| 74406 |
+
"step": 10628
|
| 74407 |
+
},
|
| 74408 |
+
{
|
| 74409 |
+
"epoch": 12.105982905982906,
|
| 74410 |
+
"grad_norm": 0.19612638652324677,
|
| 74411 |
+
"learning_rate": 1.8117576051885195e-05,
|
| 74412 |
+
"loss": 0.4922,
|
| 74413 |
+
"step": 10629
|
| 74414 |
+
},
|
| 74415 |
+
{
|
| 74416 |
+
"epoch": 12.107122507122508,
|
| 74417 |
+
"grad_norm": 0.18411149084568024,
|
| 74418 |
+
"learning_rate": 1.8113097024610105e-05,
|
| 74419 |
+
"loss": 0.7932,
|
| 74420 |
+
"step": 10630
|
| 74421 |
+
},
|
| 74422 |
+
{
|
| 74423 |
+
"epoch": 12.108262108262108,
|
| 74424 |
+
"grad_norm": 0.19481295347213745,
|
| 74425 |
+
"learning_rate": 1.8108618236536103e-05,
|
| 74426 |
+
"loss": 0.6664,
|
| 74427 |
+
"step": 10631
|
| 74428 |
+
},
|
| 74429 |
+
{
|
| 74430 |
+
"epoch": 12.109401709401709,
|
| 74431 |
+
"grad_norm": 0.20142966508865356,
|
| 74432 |
+
"learning_rate": 1.8104139687818744e-05,
|
| 74433 |
+
"loss": 0.7496,
|
| 74434 |
+
"step": 10632
|
| 74435 |
+
},
|
| 74436 |
+
{
|
| 74437 |
+
"epoch": 12.110541310541311,
|
| 74438 |
+
"grad_norm": 0.20151075720787048,
|
| 74439 |
+
"learning_rate": 1.809966137861357e-05,
|
| 74440 |
+
"loss": 0.7564,
|
| 74441 |
+
"step": 10633
|
| 74442 |
+
},
|
| 74443 |
+
{
|
| 74444 |
+
"epoch": 12.111680911680912,
|
| 74445 |
+
"grad_norm": 0.22322115302085876,
|
| 74446 |
+
"learning_rate": 1.8095183309076142e-05,
|
| 74447 |
+
"loss": 0.6657,
|
| 74448 |
+
"step": 10634
|
| 74449 |
+
},
|
| 74450 |
+
{
|
| 74451 |
+
"epoch": 12.112820512820512,
|
| 74452 |
+
"grad_norm": 0.25068724155426025,
|
| 74453 |
+
"learning_rate": 1.809070547936198e-05,
|
| 74454 |
+
"loss": 0.7064,
|
| 74455 |
+
"step": 10635
|
| 74456 |
+
},
|
| 74457 |
+
{
|
| 74458 |
+
"epoch": 12.113960113960115,
|
| 74459 |
+
"grad_norm": 0.18898867070674896,
|
| 74460 |
+
"learning_rate": 1.808622788962662e-05,
|
| 74461 |
+
"loss": 0.7723,
|
| 74462 |
+
"step": 10636
|
| 74463 |
+
},
|
| 74464 |
+
{
|
| 74465 |
+
"epoch": 12.115099715099715,
|
| 74466 |
+
"grad_norm": 0.2050749659538269,
|
| 74467 |
+
"learning_rate": 1.8081750540025574e-05,
|
| 74468 |
+
"loss": 0.6587,
|
| 74469 |
+
"step": 10637
|
| 74470 |
+
},
|
| 74471 |
+
{
|
| 74472 |
+
"epoch": 12.116239316239316,
|
| 74473 |
+
"grad_norm": 0.2101127654314041,
|
| 74474 |
+
"learning_rate": 1.8077273430714363e-05,
|
| 74475 |
+
"loss": 0.7324,
|
| 74476 |
+
"step": 10638
|
| 74477 |
+
},
|
| 74478 |
+
{
|
| 74479 |
+
"epoch": 12.117378917378918,
|
| 74480 |
+
"grad_norm": 0.2138822227716446,
|
| 74481 |
+
"learning_rate": 1.8072796561848477e-05,
|
| 74482 |
+
"loss": 0.5844,
|
| 74483 |
+
"step": 10639
|
| 74484 |
+
},
|
| 74485 |
+
{
|
| 74486 |
+
"epoch": 12.118518518518519,
|
| 74487 |
+
"grad_norm": 0.21547774970531464,
|
| 74488 |
+
"learning_rate": 1.806831993358342e-05,
|
| 74489 |
+
"loss": 0.7531,
|
| 74490 |
+
"step": 10640
|
| 74491 |
+
},
|
| 74492 |
+
{
|
| 74493 |
+
"epoch": 12.11965811965812,
|
| 74494 |
+
"grad_norm": 0.17853891849517822,
|
| 74495 |
+
"learning_rate": 1.8063843546074663e-05,
|
| 74496 |
+
"loss": 0.743,
|
| 74497 |
+
"step": 10641
|
| 74498 |
+
},
|
| 74499 |
+
{
|
| 74500 |
+
"epoch": 12.120797720797722,
|
| 74501 |
+
"grad_norm": 0.16555222868919373,
|
| 74502 |
+
"learning_rate": 1.8059367399477707e-05,
|
| 74503 |
+
"loss": 0.7745,
|
| 74504 |
+
"step": 10642
|
| 74505 |
+
},
|
| 74506 |
+
{
|
| 74507 |
+
"epoch": 12.121937321937322,
|
| 74508 |
+
"grad_norm": 0.22953662276268005,
|
| 74509 |
+
"learning_rate": 1.8054891493948003e-05,
|
| 74510 |
+
"loss": 0.7267,
|
| 74511 |
+
"step": 10643
|
| 74512 |
+
},
|
| 74513 |
+
{
|
| 74514 |
+
"epoch": 12.123076923076923,
|
| 74515 |
+
"grad_norm": 0.16581910848617554,
|
| 74516 |
+
"learning_rate": 1.805041582964102e-05,
|
| 74517 |
+
"loss": 0.968,
|
| 74518 |
+
"step": 10644
|
| 74519 |
+
},
|
| 74520 |
+
{
|
| 74521 |
+
"epoch": 12.124216524216525,
|
| 74522 |
+
"grad_norm": 0.2142912894487381,
|
| 74523 |
+
"learning_rate": 1.8045940406712206e-05,
|
| 74524 |
+
"loss": 0.7086,
|
| 74525 |
+
"step": 10645
|
| 74526 |
+
},
|
| 74527 |
+
{
|
| 74528 |
+
"epoch": 12.125356125356126,
|
| 74529 |
+
"grad_norm": 0.21221700310707092,
|
| 74530 |
+
"learning_rate": 1.8041465225317006e-05,
|
| 74531 |
+
"loss": 0.4142,
|
| 74532 |
+
"step": 10646
|
| 74533 |
+
},
|
| 74534 |
+
{
|
| 74535 |
+
"epoch": 12.126495726495726,
|
| 74536 |
+
"grad_norm": 0.1971280425786972,
|
| 74537 |
+
"learning_rate": 1.8036990285610853e-05,
|
| 74538 |
+
"loss": 0.5309,
|
| 74539 |
+
"step": 10647
|
| 74540 |
+
},
|
| 74541 |
+
{
|
| 74542 |
+
"epoch": 12.127635327635328,
|
| 74543 |
+
"grad_norm": 0.24733866751194,
|
| 74544 |
+
"learning_rate": 1.803251558774918e-05,
|
| 74545 |
+
"loss": 0.5366,
|
| 74546 |
+
"step": 10648
|
| 74547 |
+
},
|
| 74548 |
+
{
|
| 74549 |
+
"epoch": 12.128774928774929,
|
| 74550 |
+
"grad_norm": 0.22367709875106812,
|
| 74551 |
+
"learning_rate": 1.8028041131887397e-05,
|
| 74552 |
+
"loss": 0.7881,
|
| 74553 |
+
"step": 10649
|
| 74554 |
+
},
|
| 74555 |
+
{
|
| 74556 |
+
"epoch": 12.12991452991453,
|
| 74557 |
+
"grad_norm": 0.18362602591514587,
|
| 74558 |
+
"learning_rate": 1.802356691818092e-05,
|
| 74559 |
+
"loss": 0.5632,
|
| 74560 |
+
"step": 10650
|
| 74561 |
+
},
|
| 74562 |
+
{
|
| 74563 |
+
"epoch": 12.131054131054132,
|
| 74564 |
+
"grad_norm": 0.23956923186779022,
|
| 74565 |
+
"learning_rate": 1.8019092946785147e-05,
|
| 74566 |
+
"loss": 0.5352,
|
| 74567 |
+
"step": 10651
|
| 74568 |
+
},
|
| 74569 |
+
{
|
| 74570 |
+
"epoch": 12.132193732193732,
|
| 74571 |
+
"grad_norm": 0.2240896075963974,
|
| 74572 |
+
"learning_rate": 1.8014619217855465e-05,
|
| 74573 |
+
"loss": 0.6053,
|
| 74574 |
+
"step": 10652
|
| 74575 |
+
},
|
| 74576 |
+
{
|
| 74577 |
+
"epoch": 12.133333333333333,
|
| 74578 |
+
"grad_norm": 0.19277696311473846,
|
| 74579 |
+
"learning_rate": 1.801014573154728e-05,
|
| 74580 |
+
"loss": 0.7914,
|
| 74581 |
+
"step": 10653
|
| 74582 |
+
},
|
| 74583 |
+
{
|
| 74584 |
+
"epoch": 12.134472934472935,
|
| 74585 |
+
"grad_norm": 0.21935196220874786,
|
| 74586 |
+
"learning_rate": 1.8005672488015952e-05,
|
| 74587 |
+
"loss": 0.6107,
|
| 74588 |
+
"step": 10654
|
| 74589 |
+
},
|
| 74590 |
+
{
|
| 74591 |
+
"epoch": 12.135612535612536,
|
| 74592 |
+
"grad_norm": 0.1736196130514145,
|
| 74593 |
+
"learning_rate": 1.800119948741686e-05,
|
| 74594 |
+
"loss": 0.6358,
|
| 74595 |
+
"step": 10655
|
| 74596 |
+
},
|
| 74597 |
+
{
|
| 74598 |
+
"epoch": 12.136752136752136,
|
| 74599 |
+
"grad_norm": 0.1652590036392212,
|
| 74600 |
+
"learning_rate": 1.7996726729905348e-05,
|
| 74601 |
+
"loss": 0.6313,
|
| 74602 |
+
"step": 10656
|
| 74603 |
+
},
|
| 74604 |
+
{
|
| 74605 |
+
"epoch": 12.137891737891739,
|
| 74606 |
+
"grad_norm": 0.2022676318883896,
|
| 74607 |
+
"learning_rate": 1.7992254215636782e-05,
|
| 74608 |
+
"loss": 0.5496,
|
| 74609 |
+
"step": 10657
|
| 74610 |
+
},
|
| 74611 |
+
{
|
| 74612 |
+
"epoch": 12.13903133903134,
|
| 74613 |
+
"grad_norm": 0.16930244863033295,
|
| 74614 |
+
"learning_rate": 1.798778194476649e-05,
|
| 74615 |
+
"loss": 0.8777,
|
| 74616 |
+
"step": 10658
|
| 74617 |
+
},
|
| 74618 |
+
{
|
| 74619 |
+
"epoch": 12.14017094017094,
|
| 74620 |
+
"grad_norm": 0.22526149451732635,
|
| 74621 |
+
"learning_rate": 1.7983309917449824e-05,
|
| 74622 |
+
"loss": 0.6807,
|
| 74623 |
+
"step": 10659
|
| 74624 |
+
},
|
| 74625 |
+
{
|
| 74626 |
+
"epoch": 12.141310541310542,
|
| 74627 |
+
"grad_norm": 0.18134568631649017,
|
| 74628 |
+
"learning_rate": 1.7978838133842094e-05,
|
| 74629 |
+
"loss": 0.5725,
|
| 74630 |
+
"step": 10660
|
| 74631 |
+
},
|
| 74632 |
+
{
|
| 74633 |
+
"epoch": 12.142450142450143,
|
| 74634 |
+
"grad_norm": 0.23000963032245636,
|
| 74635 |
+
"learning_rate": 1.797436659409863e-05,
|
| 74636 |
+
"loss": 0.7334,
|
| 74637 |
+
"step": 10661
|
| 74638 |
+
},
|
| 74639 |
+
{
|
| 74640 |
+
"epoch": 12.143589743589743,
|
| 74641 |
+
"grad_norm": 0.1757991462945938,
|
| 74642 |
+
"learning_rate": 1.7969895298374727e-05,
|
| 74643 |
+
"loss": 0.7157,
|
| 74644 |
+
"step": 10662
|
| 74645 |
+
},
|
| 74646 |
+
{
|
| 74647 |
+
"epoch": 12.144729344729345,
|
| 74648 |
+
"grad_norm": 0.21834725141525269,
|
| 74649 |
+
"learning_rate": 1.796542424682569e-05,
|
| 74650 |
+
"loss": 0.5902,
|
| 74651 |
+
"step": 10663
|
| 74652 |
+
},
|
| 74653 |
+
{
|
| 74654 |
+
"epoch": 12.145868945868946,
|
| 74655 |
+
"grad_norm": 0.1912463903427124,
|
| 74656 |
+
"learning_rate": 1.7960953439606824e-05,
|
| 74657 |
+
"loss": 0.7046,
|
| 74658 |
+
"step": 10664
|
| 74659 |
+
},
|
| 74660 |
+
{
|
| 74661 |
+
"epoch": 12.147008547008546,
|
| 74662 |
+
"grad_norm": 0.2624971270561218,
|
| 74663 |
+
"learning_rate": 1.7956482876873397e-05,
|
| 74664 |
+
"loss": 0.6282,
|
| 74665 |
+
"step": 10665
|
| 74666 |
+
},
|
| 74667 |
+
{
|
| 74668 |
+
"epoch": 12.148148148148149,
|
| 74669 |
+
"grad_norm": 0.20026636123657227,
|
| 74670 |
+
"learning_rate": 1.7952012558780696e-05,
|
| 74671 |
+
"loss": 0.6087,
|
| 74672 |
+
"step": 10666
|
| 74673 |
+
},
|
| 74674 |
+
{
|
| 74675 |
+
"epoch": 12.14928774928775,
|
| 74676 |
+
"grad_norm": 0.29310810565948486,
|
| 74677 |
+
"learning_rate": 1.7947542485483976e-05,
|
| 74678 |
+
"loss": 0.2775,
|
| 74679 |
+
"step": 10667
|
| 74680 |
+
},
|
| 74681 |
+
{
|
| 74682 |
+
"epoch": 12.15042735042735,
|
| 74683 |
+
"grad_norm": 0.18996065855026245,
|
| 74684 |
+
"learning_rate": 1.7943072657138506e-05,
|
| 74685 |
+
"loss": 0.6303,
|
| 74686 |
+
"step": 10668
|
| 74687 |
+
},
|
| 74688 |
+
{
|
| 74689 |
+
"epoch": 12.151566951566952,
|
| 74690 |
+
"grad_norm": 0.24515536427497864,
|
| 74691 |
+
"learning_rate": 1.7938603073899518e-05,
|
| 74692 |
+
"loss": 0.5606,
|
| 74693 |
+
"step": 10669
|
| 74694 |
+
},
|
| 74695 |
+
{
|
| 74696 |
+
"epoch": 12.152706552706553,
|
| 74697 |
+
"grad_norm": 0.22369220852851868,
|
| 74698 |
+
"learning_rate": 1.7934133735922274e-05,
|
| 74699 |
+
"loss": 0.5143,
|
| 74700 |
+
"step": 10670
|
| 74701 |
+
},
|
| 74702 |
+
{
|
| 74703 |
+
"epoch": 12.153846153846153,
|
| 74704 |
+
"grad_norm": 0.2261112481355667,
|
| 74705 |
+
"learning_rate": 1.792966464336199e-05,
|
| 74706 |
+
"loss": 0.6097,
|
| 74707 |
+
"step": 10671
|
| 74708 |
+
},
|
| 74709 |
+
{
|
| 74710 |
+
"epoch": 12.154985754985756,
|
| 74711 |
+
"grad_norm": 0.20036981999874115,
|
| 74712 |
+
"learning_rate": 1.79251957963739e-05,
|
| 74713 |
+
"loss": 0.6883,
|
| 74714 |
+
"step": 10672
|
| 74715 |
+
},
|
| 74716 |
+
{
|
| 74717 |
+
"epoch": 12.156125356125356,
|
| 74718 |
+
"grad_norm": 0.17598126828670502,
|
| 74719 |
+
"learning_rate": 1.7920727195113213e-05,
|
| 74720 |
+
"loss": 0.8462,
|
| 74721 |
+
"step": 10673
|
| 74722 |
+
},
|
| 74723 |
+
{
|
| 74724 |
+
"epoch": 12.157264957264957,
|
| 74725 |
+
"grad_norm": 0.2102530598640442,
|
| 74726 |
+
"learning_rate": 1.7916258839735133e-05,
|
| 74727 |
+
"loss": 0.5979,
|
| 74728 |
+
"step": 10674
|
| 74729 |
+
},
|
| 74730 |
+
{
|
| 74731 |
+
"epoch": 12.158404558404559,
|
| 74732 |
+
"grad_norm": 0.21557404100894928,
|
| 74733 |
+
"learning_rate": 1.7911790730394877e-05,
|
| 74734 |
+
"loss": 0.4804,
|
| 74735 |
+
"step": 10675
|
| 74736 |
+
},
|
| 74737 |
+
{
|
| 74738 |
+
"epoch": 12.15954415954416,
|
| 74739 |
+
"grad_norm": 0.15740369260311127,
|
| 74740 |
+
"learning_rate": 1.7907322867247613e-05,
|
| 74741 |
+
"loss": 0.6584,
|
| 74742 |
+
"step": 10676
|
| 74743 |
+
},
|
| 74744 |
+
{
|
| 74745 |
+
"epoch": 12.16068376068376,
|
| 74746 |
+
"grad_norm": 0.23590488731861115,
|
| 74747 |
+
"learning_rate": 1.790285525044853e-05,
|
| 74748 |
+
"loss": 0.5028,
|
| 74749 |
+
"step": 10677
|
| 74750 |
+
},
|
| 74751 |
+
{
|
| 74752 |
+
"epoch": 12.161823361823362,
|
| 74753 |
+
"grad_norm": 0.207161083817482,
|
| 74754 |
+
"learning_rate": 1.789838788015281e-05,
|
| 74755 |
+
"loss": 0.6426,
|
| 74756 |
+
"step": 10678
|
| 74757 |
+
},
|
| 74758 |
+
{
|
| 74759 |
+
"epoch": 12.162962962962963,
|
| 74760 |
+
"grad_norm": 0.19174276292324066,
|
| 74761 |
+
"learning_rate": 1.78939207565156e-05,
|
| 74762 |
+
"loss": 0.7633,
|
| 74763 |
+
"step": 10679
|
| 74764 |
+
},
|
| 74765 |
+
{
|
| 74766 |
+
"epoch": 12.164102564102564,
|
| 74767 |
+
"grad_norm": 0.20363642275333405,
|
| 74768 |
+
"learning_rate": 1.788945387969207e-05,
|
| 74769 |
+
"loss": 0.6449,
|
| 74770 |
+
"step": 10680
|
| 74771 |
+
},
|
| 74772 |
+
{
|
| 74773 |
+
"epoch": 12.165242165242166,
|
| 74774 |
+
"grad_norm": 0.217159241437912,
|
| 74775 |
+
"learning_rate": 1.7884987249837355e-05,
|
| 74776 |
+
"loss": 0.5507,
|
| 74777 |
+
"step": 10681
|
| 74778 |
+
},
|
| 74779 |
+
{
|
| 74780 |
+
"epoch": 12.166381766381766,
|
| 74781 |
+
"grad_norm": 0.16143184900283813,
|
| 74782 |
+
"learning_rate": 1.788052086710661e-05,
|
| 74783 |
+
"loss": 0.663,
|
| 74784 |
+
"step": 10682
|
| 74785 |
+
},
|
| 74786 |
+
{
|
| 74787 |
+
"epoch": 12.167521367521367,
|
| 74788 |
+
"grad_norm": 0.19331926107406616,
|
| 74789 |
+
"learning_rate": 1.787605473165494e-05,
|
| 74790 |
+
"loss": 0.6403,
|
| 74791 |
+
"step": 10683
|
| 74792 |
+
},
|
| 74793 |
+
{
|
| 74794 |
+
"epoch": 12.16866096866097,
|
| 74795 |
+
"grad_norm": 0.2204113006591797,
|
| 74796 |
+
"learning_rate": 1.787158884363749e-05,
|
| 74797 |
+
"loss": 0.5189,
|
| 74798 |
+
"step": 10684
|
| 74799 |
+
},
|
| 74800 |
+
{
|
| 74801 |
+
"epoch": 12.16980056980057,
|
| 74802 |
+
"grad_norm": 0.19390377402305603,
|
| 74803 |
+
"learning_rate": 1.786712320320935e-05,
|
| 74804 |
+
"loss": 0.6982,
|
| 74805 |
+
"step": 10685
|
| 74806 |
+
},
|
| 74807 |
+
{
|
| 74808 |
+
"epoch": 12.17094017094017,
|
| 74809 |
+
"grad_norm": 0.1998767852783203,
|
| 74810 |
+
"learning_rate": 1.7862657810525644e-05,
|
| 74811 |
+
"loss": 0.6942,
|
| 74812 |
+
"step": 10686
|
| 74813 |
+
},
|
| 74814 |
+
{
|
| 74815 |
+
"epoch": 12.172079772079773,
|
| 74816 |
+
"grad_norm": 0.2072298377752304,
|
| 74817 |
+
"learning_rate": 1.785819266574147e-05,
|
| 74818 |
+
"loss": 0.8303,
|
| 74819 |
+
"step": 10687
|
| 74820 |
+
},
|
| 74821 |
+
{
|
| 74822 |
+
"epoch": 12.173219373219373,
|
| 74823 |
+
"grad_norm": 0.20465919375419617,
|
| 74824 |
+
"learning_rate": 1.785372776901189e-05,
|
| 74825 |
+
"loss": 0.6879,
|
| 74826 |
+
"step": 10688
|
| 74827 |
+
},
|
| 74828 |
+
{
|
| 74829 |
+
"epoch": 12.174358974358974,
|
| 74830 |
+
"grad_norm": 0.2517319917678833,
|
| 74831 |
+
"learning_rate": 1.7849263120492006e-05,
|
| 74832 |
+
"loss": 0.3552,
|
| 74833 |
+
"step": 10689
|
| 74834 |
+
},
|
| 74835 |
+
{
|
| 74836 |
+
"epoch": 12.175498575498576,
|
| 74837 |
+
"grad_norm": 0.20104607939720154,
|
| 74838 |
+
"learning_rate": 1.7844798720336876e-05,
|
| 74839 |
+
"loss": 0.7055,
|
| 74840 |
+
"step": 10690
|
| 74841 |
+
},
|
| 74842 |
+
{
|
| 74843 |
+
"epoch": 12.176638176638177,
|
| 74844 |
+
"grad_norm": 0.2130606472492218,
|
| 74845 |
+
"learning_rate": 1.7840334568701565e-05,
|
| 74846 |
+
"loss": 0.8386,
|
| 74847 |
+
"step": 10691
|
| 74848 |
+
},
|
| 74849 |
+
{
|
| 74850 |
+
"epoch": 12.177777777777777,
|
| 74851 |
+
"grad_norm": 0.1965247541666031,
|
| 74852 |
+
"learning_rate": 1.783587066574112e-05,
|
| 74853 |
+
"loss": 0.7466,
|
| 74854 |
+
"step": 10692
|
| 74855 |
+
},
|
| 74856 |
+
{
|
| 74857 |
+
"epoch": 12.17891737891738,
|
| 74858 |
+
"grad_norm": 0.18730469048023224,
|
| 74859 |
+
"learning_rate": 1.783140701161059e-05,
|
| 74860 |
+
"loss": 0.5807,
|
| 74861 |
+
"step": 10693
|
| 74862 |
+
},
|
| 74863 |
+
{
|
| 74864 |
+
"epoch": 12.18005698005698,
|
| 74865 |
+
"grad_norm": 0.24426794052124023,
|
| 74866 |
+
"learning_rate": 1.7826943606465007e-05,
|
| 74867 |
+
"loss": 0.5245,
|
| 74868 |
+
"step": 10694
|
| 74869 |
+
},
|
| 74870 |
+
{
|
| 74871 |
+
"epoch": 12.18119658119658,
|
| 74872 |
+
"grad_norm": 0.19502083957195282,
|
| 74873 |
+
"learning_rate": 1.7822480450459405e-05,
|
| 74874 |
+
"loss": 0.7117,
|
| 74875 |
+
"step": 10695
|
| 74876 |
+
},
|
| 74877 |
+
{
|
| 74878 |
+
"epoch": 12.182336182336183,
|
| 74879 |
+
"grad_norm": 0.20117051899433136,
|
| 74880 |
+
"learning_rate": 1.7818017543748783e-05,
|
| 74881 |
+
"loss": 0.7298,
|
| 74882 |
+
"step": 10696
|
| 74883 |
+
},
|
| 74884 |
+
{
|
| 74885 |
+
"epoch": 12.183475783475783,
|
| 74886 |
+
"grad_norm": 0.19388437271118164,
|
| 74887 |
+
"learning_rate": 1.7813554886488165e-05,
|
| 74888 |
+
"loss": 0.8489,
|
| 74889 |
+
"step": 10697
|
| 74890 |
+
},
|
| 74891 |
+
{
|
| 74892 |
+
"epoch": 12.184615384615384,
|
| 74893 |
+
"grad_norm": 0.15525661408901215,
|
| 74894 |
+
"learning_rate": 1.7809092478832557e-05,
|
| 74895 |
+
"loss": 0.9988,
|
| 74896 |
+
"step": 10698
|
| 74897 |
+
},
|
| 74898 |
+
{
|
| 74899 |
+
"epoch": 12.185754985754986,
|
| 74900 |
+
"grad_norm": 0.20999334752559662,
|
| 74901 |
+
"learning_rate": 1.780463032093694e-05,
|
| 74902 |
+
"loss": 0.7525,
|
| 74903 |
+
"step": 10699
|
| 74904 |
+
},
|
| 74905 |
+
{
|
| 74906 |
+
"epoch": 12.186894586894587,
|
| 74907 |
+
"grad_norm": 0.2047741711139679,
|
| 74908 |
+
"learning_rate": 1.78001684129563e-05,
|
| 74909 |
+
"loss": 0.7616,
|
| 74910 |
+
"step": 10700
|
| 74911 |
+
},
|
| 74912 |
+
{
|
| 74913 |
+
"epoch": 12.188034188034187,
|
| 74914 |
+
"grad_norm": 0.18242231011390686,
|
| 74915 |
+
"learning_rate": 1.7795706755045602e-05,
|
| 74916 |
+
"loss": 0.7656,
|
| 74917 |
+
"step": 10701
|
| 74918 |
+
},
|
| 74919 |
+
{
|
| 74920 |
+
"epoch": 12.18917378917379,
|
| 74921 |
+
"grad_norm": 0.17030739784240723,
|
| 74922 |
+
"learning_rate": 1.779124534735983e-05,
|
| 74923 |
+
"loss": 0.788,
|
| 74924 |
+
"step": 10702
|
| 74925 |
+
},
|
| 74926 |
+
{
|
| 74927 |
+
"epoch": 12.19031339031339,
|
| 74928 |
+
"grad_norm": 0.2390817552804947,
|
| 74929 |
+
"learning_rate": 1.7786784190053922e-05,
|
| 74930 |
+
"loss": 0.4655,
|
| 74931 |
+
"step": 10703
|
| 74932 |
+
},
|
| 74933 |
+
{
|
| 74934 |
+
"epoch": 12.19145299145299,
|
| 74935 |
+
"grad_norm": 0.24233390390872955,
|
| 74936 |
+
"learning_rate": 1.7782323283282848e-05,
|
| 74937 |
+
"loss": 0.7488,
|
| 74938 |
+
"step": 10704
|
| 74939 |
+
},
|
| 74940 |
+
{
|
| 74941 |
+
"epoch": 12.192592592592593,
|
| 74942 |
+
"grad_norm": 0.25977823138237,
|
| 74943 |
+
"learning_rate": 1.7777862627201525e-05,
|
| 74944 |
+
"loss": 0.5433,
|
| 74945 |
+
"step": 10705
|
| 74946 |
+
},
|
| 74947 |
+
{
|
| 74948 |
+
"epoch": 12.193732193732194,
|
| 74949 |
+
"grad_norm": 0.21289107203483582,
|
| 74950 |
+
"learning_rate": 1.77734022219649e-05,
|
| 74951 |
+
"loss": 0.7498,
|
| 74952 |
+
"step": 10706
|
| 74953 |
+
},
|
| 74954 |
+
{
|
| 74955 |
+
"epoch": 12.194871794871794,
|
| 74956 |
+
"grad_norm": 0.21533629298210144,
|
| 74957 |
+
"learning_rate": 1.7768942067727877e-05,
|
| 74958 |
+
"loss": 0.6468,
|
| 74959 |
+
"step": 10707
|
| 74960 |
+
},
|
| 74961 |
+
{
|
| 74962 |
+
"epoch": 12.196011396011396,
|
| 74963 |
+
"grad_norm": 0.2645060122013092,
|
| 74964 |
+
"learning_rate": 1.776448216464539e-05,
|
| 74965 |
+
"loss": 0.5044,
|
| 74966 |
+
"step": 10708
|
| 74967 |
+
},
|
| 74968 |
+
{
|
| 74969 |
+
"epoch": 12.197150997150997,
|
| 74970 |
+
"grad_norm": 0.19389687478542328,
|
| 74971 |
+
"learning_rate": 1.7760022512872337e-05,
|
| 74972 |
+
"loss": 0.6738,
|
| 74973 |
+
"step": 10709
|
| 74974 |
+
},
|
| 74975 |
+
{
|
| 74976 |
+
"epoch": 12.198290598290598,
|
| 74977 |
+
"grad_norm": 0.24795565009117126,
|
| 74978 |
+
"learning_rate": 1.775556311256361e-05,
|
| 74979 |
+
"loss": 0.6541,
|
| 74980 |
+
"step": 10710
|
| 74981 |
+
},
|
| 74982 |
+
{
|
| 74983 |
+
"epoch": 12.1994301994302,
|
| 74984 |
+
"grad_norm": 0.2238483428955078,
|
| 74985 |
+
"learning_rate": 1.7751103963874104e-05,
|
| 74986 |
+
"loss": 0.564,
|
| 74987 |
+
"step": 10711
|
| 74988 |
+
},
|
| 74989 |
+
{
|
| 74990 |
+
"epoch": 12.2005698005698,
|
| 74991 |
+
"grad_norm": 0.20205016434192657,
|
| 74992 |
+
"learning_rate": 1.7746645066958683e-05,
|
| 74993 |
+
"loss": 0.7781,
|
| 74994 |
+
"step": 10712
|
| 74995 |
+
},
|
| 74996 |
+
{
|
| 74997 |
+
"epoch": 12.201709401709401,
|
| 74998 |
+
"grad_norm": 0.19284003973007202,
|
| 74999 |
+
"learning_rate": 1.7742186421972234e-05,
|
| 75000 |
+
"loss": 0.6534,
|
| 75001 |
+
"step": 10713
|
| 75002 |
+
},
|
| 75003 |
+
{
|
| 75004 |
+
"epoch": 12.202849002849003,
|
| 75005 |
+
"grad_norm": 0.21559850871562958,
|
| 75006 |
+
"learning_rate": 1.77377280290696e-05,
|
| 75007 |
+
"loss": 0.6882,
|
| 75008 |
+
"step": 10714
|
| 75009 |
+
},
|
| 75010 |
+
{
|
| 75011 |
+
"epoch": 12.203988603988604,
|
| 75012 |
+
"grad_norm": 0.3090205192565918,
|
| 75013 |
+
"learning_rate": 1.7733269888405652e-05,
|
| 75014 |
+
"loss": 0.432,
|
| 75015 |
+
"step": 10715
|
| 75016 |
+
},
|
| 75017 |
+
{
|
| 75018 |
+
"epoch": 12.205128205128204,
|
| 75019 |
+
"grad_norm": 0.17751125991344452,
|
| 75020 |
+
"learning_rate": 1.772881200013522e-05,
|
| 75021 |
+
"loss": 0.9052,
|
| 75022 |
+
"step": 10716
|
| 75023 |
+
},
|
| 75024 |
+
{
|
| 75025 |
+
"epoch": 12.206267806267807,
|
| 75026 |
+
"grad_norm": 0.22450704872608185,
|
| 75027 |
+
"learning_rate": 1.7724354364413144e-05,
|
| 75028 |
+
"loss": 0.5813,
|
| 75029 |
+
"step": 10717
|
| 75030 |
+
},
|
| 75031 |
+
{
|
| 75032 |
+
"epoch": 12.207407407407407,
|
| 75033 |
+
"grad_norm": 0.22953973710536957,
|
| 75034 |
+
"learning_rate": 1.7719896981394238e-05,
|
| 75035 |
+
"loss": 0.6634,
|
| 75036 |
+
"step": 10718
|
| 75037 |
+
},
|
| 75038 |
+
{
|
| 75039 |
+
"epoch": 12.208547008547008,
|
| 75040 |
+
"grad_norm": 0.19475506246089935,
|
| 75041 |
+
"learning_rate": 1.7715439851233346e-05,
|
| 75042 |
+
"loss": 0.7875,
|
| 75043 |
+
"step": 10719
|
| 75044 |
+
},
|
| 75045 |
+
{
|
| 75046 |
+
"epoch": 12.20968660968661,
|
| 75047 |
+
"grad_norm": 0.2490365356206894,
|
| 75048 |
+
"learning_rate": 1.771098297408525e-05,
|
| 75049 |
+
"loss": 0.7025,
|
| 75050 |
+
"step": 10720
|
| 75051 |
+
},
|
| 75052 |
+
{
|
| 75053 |
+
"epoch": 12.21082621082621,
|
| 75054 |
+
"grad_norm": 0.23320597410202026,
|
| 75055 |
+
"learning_rate": 1.7706526350104767e-05,
|
| 75056 |
+
"loss": 0.5894,
|
| 75057 |
+
"step": 10721
|
| 75058 |
+
},
|
| 75059 |
+
{
|
| 75060 |
+
"epoch": 12.211965811965811,
|
| 75061 |
+
"grad_norm": 0.19566142559051514,
|
| 75062 |
+
"learning_rate": 1.7702069979446677e-05,
|
| 75063 |
+
"loss": 0.554,
|
| 75064 |
+
"step": 10722
|
| 75065 |
+
},
|
| 75066 |
+
{
|
| 75067 |
+
"epoch": 12.213105413105414,
|
| 75068 |
+
"grad_norm": 0.2419247329235077,
|
| 75069 |
+
"learning_rate": 1.7697613862265775e-05,
|
| 75070 |
+
"loss": 0.5138,
|
| 75071 |
+
"step": 10723
|
| 75072 |
+
},
|
| 75073 |
+
{
|
| 75074 |
+
"epoch": 12.214245014245014,
|
| 75075 |
+
"grad_norm": 0.2230897694826126,
|
| 75076 |
+
"learning_rate": 1.7693157998716813e-05,
|
| 75077 |
+
"loss": 0.6378,
|
| 75078 |
+
"step": 10724
|
| 75079 |
+
},
|
| 75080 |
+
{
|
| 75081 |
+
"epoch": 12.215384615384615,
|
| 75082 |
+
"grad_norm": 0.20686529576778412,
|
| 75083 |
+
"learning_rate": 1.7688702388954583e-05,
|
| 75084 |
+
"loss": 0.7026,
|
| 75085 |
+
"step": 10725
|
| 75086 |
+
},
|
| 75087 |
+
{
|
| 75088 |
+
"epoch": 12.216524216524217,
|
| 75089 |
+
"grad_norm": 0.2121909260749817,
|
| 75090 |
+
"learning_rate": 1.768424703313381e-05,
|
| 75091 |
+
"loss": 0.8471,
|
| 75092 |
+
"step": 10726
|
| 75093 |
+
},
|
| 75094 |
+
{
|
| 75095 |
+
"epoch": 12.217663817663817,
|
| 75096 |
+
"grad_norm": 0.2286602407693863,
|
| 75097 |
+
"learning_rate": 1.7679791931409265e-05,
|
| 75098 |
+
"loss": 0.5637,
|
| 75099 |
+
"step": 10727
|
| 75100 |
+
},
|
| 75101 |
+
{
|
| 75102 |
+
"epoch": 12.218803418803418,
|
| 75103 |
+
"grad_norm": 0.20954394340515137,
|
| 75104 |
+
"learning_rate": 1.7675337083935674e-05,
|
| 75105 |
+
"loss": 0.7747,
|
| 75106 |
+
"step": 10728
|
| 75107 |
+
},
|
| 75108 |
+
{
|
| 75109 |
+
"epoch": 12.21994301994302,
|
| 75110 |
+
"grad_norm": 0.1756397783756256,
|
| 75111 |
+
"learning_rate": 1.7670882490867758e-05,
|
| 75112 |
+
"loss": 0.859,
|
| 75113 |
+
"step": 10729
|
| 75114 |
+
},
|
| 75115 |
+
{
|
| 75116 |
+
"epoch": 12.221082621082621,
|
| 75117 |
+
"grad_norm": 0.2088949978351593,
|
| 75118 |
+
"learning_rate": 1.766642815236026e-05,
|
| 75119 |
+
"loss": 0.7268,
|
| 75120 |
+
"step": 10730
|
| 75121 |
+
},
|
| 75122 |
+
{
|
| 75123 |
+
"epoch": 12.222222222222221,
|
| 75124 |
+
"grad_norm": 0.17804178595542908,
|
| 75125 |
+
"learning_rate": 1.7661974068567876e-05,
|
| 75126 |
+
"loss": 0.7313,
|
| 75127 |
+
"step": 10731
|
| 75128 |
+
},
|
| 75129 |
+
{
|
| 75130 |
+
"epoch": 12.223361823361824,
|
| 75131 |
+
"grad_norm": 0.19555315375328064,
|
| 75132 |
+
"learning_rate": 1.765752023964532e-05,
|
| 75133 |
+
"loss": 0.6368,
|
| 75134 |
+
"step": 10732
|
| 75135 |
+
},
|
| 75136 |
+
{
|
| 75137 |
+
"epoch": 12.224501424501424,
|
| 75138 |
+
"grad_norm": 0.18006379902362823,
|
| 75139 |
+
"learning_rate": 1.765306666574727e-05,
|
| 75140 |
+
"loss": 0.7287,
|
| 75141 |
+
"step": 10733
|
| 75142 |
+
},
|
| 75143 |
+
{
|
| 75144 |
+
"epoch": 12.225641025641025,
|
| 75145 |
+
"grad_norm": 0.21815355122089386,
|
| 75146 |
+
"learning_rate": 1.7648613347028424e-05,
|
| 75147 |
+
"loss": 0.656,
|
| 75148 |
+
"step": 10734
|
| 75149 |
+
},
|
| 75150 |
+
{
|
| 75151 |
+
"epoch": 12.226780626780627,
|
| 75152 |
+
"grad_norm": 0.2285873293876648,
|
| 75153 |
+
"learning_rate": 1.7644160283643446e-05,
|
| 75154 |
+
"loss": 0.6461,
|
| 75155 |
+
"step": 10735
|
| 75156 |
+
},
|
| 75157 |
+
{
|
| 75158 |
+
"epoch": 12.227920227920228,
|
| 75159 |
+
"grad_norm": 0.24663476645946503,
|
| 75160 |
+
"learning_rate": 1.7639707475747018e-05,
|
| 75161 |
+
"loss": 0.5885,
|
| 75162 |
+
"step": 10736
|
| 75163 |
+
},
|
| 75164 |
+
{
|
| 75165 |
+
"epoch": 12.229059829059828,
|
| 75166 |
+
"grad_norm": 0.22460223734378815,
|
| 75167 |
+
"learning_rate": 1.7635254923493783e-05,
|
| 75168 |
+
"loss": 0.5982,
|
| 75169 |
+
"step": 10737
|
| 75170 |
+
},
|
| 75171 |
+
{
|
| 75172 |
+
"epoch": 12.23019943019943,
|
| 75173 |
+
"grad_norm": 0.21745523810386658,
|
| 75174 |
+
"learning_rate": 1.7630802627038405e-05,
|
| 75175 |
+
"loss": 0.6841,
|
| 75176 |
+
"step": 10738
|
| 75177 |
+
},
|
| 75178 |
+
{
|
| 75179 |
+
"epoch": 12.231339031339031,
|
| 75180 |
+
"grad_norm": 0.20803306996822357,
|
| 75181 |
+
"learning_rate": 1.762635058653551e-05,
|
| 75182 |
+
"loss": 0.9838,
|
| 75183 |
+
"step": 10739
|
| 75184 |
+
},
|
| 75185 |
+
{
|
| 75186 |
+
"epoch": 12.232478632478632,
|
| 75187 |
+
"grad_norm": 0.1870354264974594,
|
| 75188 |
+
"learning_rate": 1.7621898802139736e-05,
|
| 75189 |
+
"loss": 0.7261,
|
| 75190 |
+
"step": 10740
|
| 75191 |
+
},
|
| 75192 |
+
{
|
| 75193 |
+
"epoch": 12.233618233618234,
|
| 75194 |
+
"grad_norm": 0.18768827617168427,
|
| 75195 |
+
"learning_rate": 1.761744727400571e-05,
|
| 75196 |
+
"loss": 0.7957,
|
| 75197 |
+
"step": 10741
|
| 75198 |
+
},
|
| 75199 |
+
{
|
| 75200 |
+
"epoch": 12.234757834757835,
|
| 75201 |
+
"grad_norm": 0.24852044880390167,
|
| 75202 |
+
"learning_rate": 1.761299600228804e-05,
|
| 75203 |
+
"loss": 0.7304,
|
| 75204 |
+
"step": 10742
|
| 75205 |
+
},
|
| 75206 |
+
{
|
| 75207 |
+
"epoch": 12.235897435897435,
|
| 75208 |
+
"grad_norm": 0.19052305817604065,
|
| 75209 |
+
"learning_rate": 1.760854498714134e-05,
|
| 75210 |
+
"loss": 0.6378,
|
| 75211 |
+
"step": 10743
|
| 75212 |
+
},
|
| 75213 |
+
{
|
| 75214 |
+
"epoch": 12.237037037037037,
|
| 75215 |
+
"grad_norm": 0.21809840202331543,
|
| 75216 |
+
"learning_rate": 1.7604094228720194e-05,
|
| 75217 |
+
"loss": 0.7439,
|
| 75218 |
+
"step": 10744
|
| 75219 |
+
},
|
| 75220 |
+
{
|
| 75221 |
+
"epoch": 12.238176638176638,
|
| 75222 |
+
"grad_norm": 0.20084500312805176,
|
| 75223 |
+
"learning_rate": 1.75996437271792e-05,
|
| 75224 |
+
"loss": 0.6188,
|
| 75225 |
+
"step": 10745
|
| 75226 |
+
},
|
| 75227 |
+
{
|
| 75228 |
+
"epoch": 12.239316239316238,
|
| 75229 |
+
"grad_norm": 0.199592724442482,
|
| 75230 |
+
"learning_rate": 1.7595193482672924e-05,
|
| 75231 |
+
"loss": 0.8747,
|
| 75232 |
+
"step": 10746
|
| 75233 |
+
},
|
| 75234 |
+
{
|
| 75235 |
+
"epoch": 12.24045584045584,
|
| 75236 |
+
"grad_norm": 0.19660794734954834,
|
| 75237 |
+
"learning_rate": 1.7590743495355945e-05,
|
| 75238 |
+
"loss": 0.639,
|
| 75239 |
+
"step": 10747
|
| 75240 |
+
},
|
| 75241 |
+
{
|
| 75242 |
+
"epoch": 12.241595441595441,
|
| 75243 |
+
"grad_norm": 0.2428426593542099,
|
| 75244 |
+
"learning_rate": 1.7586293765382815e-05,
|
| 75245 |
+
"loss": 0.5828,
|
| 75246 |
+
"step": 10748
|
| 75247 |
+
},
|
| 75248 |
+
{
|
| 75249 |
+
"epoch": 12.242735042735042,
|
| 75250 |
+
"grad_norm": 0.21701796352863312,
|
| 75251 |
+
"learning_rate": 1.7581844292908095e-05,
|
| 75252 |
+
"loss": 0.6053,
|
| 75253 |
+
"step": 10749
|
| 75254 |
+
},
|
| 75255 |
+
{
|
| 75256 |
+
"epoch": 12.243874643874644,
|
| 75257 |
+
"grad_norm": 0.22236555814743042,
|
| 75258 |
+
"learning_rate": 1.757739507808632e-05,
|
| 75259 |
+
"loss": 0.6185,
|
| 75260 |
+
"step": 10750
|
| 75261 |
+
},
|
| 75262 |
+
{
|
| 75263 |
+
"epoch": 12.245014245014245,
|
| 75264 |
+
"grad_norm": 0.24517688155174255,
|
| 75265 |
+
"learning_rate": 1.757294612107202e-05,
|
| 75266 |
+
"loss": 0.6609,
|
| 75267 |
+
"step": 10751
|
| 75268 |
+
},
|
| 75269 |
+
{
|
| 75270 |
+
"epoch": 12.246153846153845,
|
| 75271 |
+
"grad_norm": 0.19971169531345367,
|
| 75272 |
+
"learning_rate": 1.7568497422019737e-05,
|
| 75273 |
+
"loss": 0.6233,
|
| 75274 |
+
"step": 10752
|
| 75275 |
+
},
|
| 75276 |
+
{
|
| 75277 |
+
"epoch": 12.247293447293448,
|
| 75278 |
+
"grad_norm": 0.22031354904174805,
|
| 75279 |
+
"learning_rate": 1.756404898108397e-05,
|
| 75280 |
+
"loss": 0.7641,
|
| 75281 |
+
"step": 10753
|
| 75282 |
+
},
|
| 75283 |
+
{
|
| 75284 |
+
"epoch": 12.248433048433048,
|
| 75285 |
+
"grad_norm": 0.20710423588752747,
|
| 75286 |
+
"learning_rate": 1.7559600798419233e-05,
|
| 75287 |
+
"loss": 0.4968,
|
| 75288 |
+
"step": 10754
|
| 75289 |
+
},
|
| 75290 |
+
{
|
| 75291 |
+
"epoch": 12.249572649572649,
|
| 75292 |
+
"grad_norm": 0.23224996030330658,
|
| 75293 |
+
"learning_rate": 1.755515287418002e-05,
|
| 75294 |
+
"loss": 0.7139,
|
| 75295 |
+
"step": 10755
|
| 75296 |
+
},
|
| 75297 |
+
{
|
| 75298 |
+
"epoch": 12.250712250712251,
|
| 75299 |
+
"grad_norm": 0.21826957166194916,
|
| 75300 |
+
"learning_rate": 1.7550705208520817e-05,
|
| 75301 |
+
"loss": 0.6562,
|
| 75302 |
+
"step": 10756
|
| 75303 |
+
},
|
| 75304 |
+
{
|
| 75305 |
+
"epoch": 12.251851851851852,
|
| 75306 |
+
"grad_norm": 0.23644167184829712,
|
| 75307 |
+
"learning_rate": 1.7546257801596115e-05,
|
| 75308 |
+
"loss": 0.7466,
|
| 75309 |
+
"step": 10757
|
| 75310 |
+
},
|
| 75311 |
+
{
|
| 75312 |
+
"epoch": 12.252991452991452,
|
| 75313 |
+
"grad_norm": 0.22611716389656067,
|
| 75314 |
+
"learning_rate": 1.7541810653560376e-05,
|
| 75315 |
+
"loss": 0.5025,
|
| 75316 |
+
"step": 10758
|
| 75317 |
+
},
|
| 75318 |
+
{
|
| 75319 |
+
"epoch": 12.254131054131054,
|
| 75320 |
+
"grad_norm": 0.25908517837524414,
|
| 75321 |
+
"learning_rate": 1.7537363764568067e-05,
|
| 75322 |
+
"loss": 0.6044,
|
| 75323 |
+
"step": 10759
|
| 75324 |
+
},
|
| 75325 |
+
{
|
| 75326 |
+
"epoch": 12.255270655270655,
|
| 75327 |
+
"grad_norm": 0.24921810626983643,
|
| 75328 |
+
"learning_rate": 1.7532917134773627e-05,
|
| 75329 |
+
"loss": 0.6788,
|
| 75330 |
+
"step": 10760
|
| 75331 |
+
},
|
| 75332 |
+
{
|
| 75333 |
+
"epoch": 12.256410256410255,
|
| 75334 |
+
"grad_norm": 0.21592481434345245,
|
| 75335 |
+
"learning_rate": 1.7528470764331518e-05,
|
| 75336 |
+
"loss": 0.5031,
|
| 75337 |
+
"step": 10761
|
| 75338 |
+
},
|
| 75339 |
+
{
|
| 75340 |
+
"epoch": 12.257549857549858,
|
| 75341 |
+
"grad_norm": 0.23294512927532196,
|
| 75342 |
+
"learning_rate": 1.7524024653396153e-05,
|
| 75343 |
+
"loss": 0.5266,
|
| 75344 |
+
"step": 10762
|
| 75345 |
+
},
|
| 75346 |
+
{
|
| 75347 |
+
"epoch": 12.258689458689458,
|
| 75348 |
+
"grad_norm": 0.1757514774799347,
|
| 75349 |
+
"learning_rate": 1.7519578802121977e-05,
|
| 75350 |
+
"loss": 0.7011,
|
| 75351 |
+
"step": 10763
|
| 75352 |
+
},
|
| 75353 |
+
{
|
| 75354 |
+
"epoch": 12.25982905982906,
|
| 75355 |
+
"grad_norm": 0.17363764345645905,
|
| 75356 |
+
"learning_rate": 1.751513321066341e-05,
|
| 75357 |
+
"loss": 0.7961,
|
| 75358 |
+
"step": 10764
|
| 75359 |
+
},
|
| 75360 |
+
{
|
| 75361 |
+
"epoch": 12.260968660968661,
|
| 75362 |
+
"grad_norm": 0.23321864008903503,
|
| 75363 |
+
"learning_rate": 1.751068787917484e-05,
|
| 75364 |
+
"loss": 0.7313,
|
| 75365 |
+
"step": 10765
|
| 75366 |
+
},
|
| 75367 |
+
{
|
| 75368 |
+
"epoch": 12.262108262108262,
|
| 75369 |
+
"grad_norm": 0.17034848034381866,
|
| 75370 |
+
"learning_rate": 1.7506242807810684e-05,
|
| 75371 |
+
"loss": 0.8433,
|
| 75372 |
+
"step": 10766
|
| 75373 |
+
},
|
| 75374 |
+
{
|
| 75375 |
+
"epoch": 12.263247863247864,
|
| 75376 |
+
"grad_norm": 0.23170049488544464,
|
| 75377 |
+
"learning_rate": 1.7501797996725317e-05,
|
| 75378 |
+
"loss": 0.5912,
|
| 75379 |
+
"step": 10767
|
| 75380 |
+
},
|
| 75381 |
+
{
|
| 75382 |
+
"epoch": 12.264387464387465,
|
| 75383 |
+
"grad_norm": 0.2036147117614746,
|
| 75384 |
+
"learning_rate": 1.7497353446073128e-05,
|
| 75385 |
+
"loss": 0.7455,
|
| 75386 |
+
"step": 10768
|
| 75387 |
+
},
|
| 75388 |
+
{
|
| 75389 |
+
"epoch": 12.265527065527065,
|
| 75390 |
+
"grad_norm": 0.24861375987529755,
|
| 75391 |
+
"learning_rate": 1.7492909156008484e-05,
|
| 75392 |
+
"loss": 0.6507,
|
| 75393 |
+
"step": 10769
|
| 75394 |
+
},
|
| 75395 |
+
{
|
| 75396 |
+
"epoch": 12.266666666666667,
|
| 75397 |
+
"grad_norm": 0.26345381140708923,
|
| 75398 |
+
"learning_rate": 1.7488465126685756e-05,
|
| 75399 |
+
"loss": 0.8334,
|
| 75400 |
+
"step": 10770
|
| 75401 |
+
},
|
| 75402 |
+
{
|
| 75403 |
+
"epoch": 12.267806267806268,
|
| 75404 |
+
"grad_norm": 0.21005362272262573,
|
| 75405 |
+
"learning_rate": 1.7484021358259285e-05,
|
| 75406 |
+
"loss": 0.6203,
|
| 75407 |
+
"step": 10771
|
| 75408 |
+
},
|
| 75409 |
+
{
|
| 75410 |
+
"epoch": 12.268945868945869,
|
| 75411 |
+
"grad_norm": 0.21710240840911865,
|
| 75412 |
+
"learning_rate": 1.7479577850883422e-05,
|
| 75413 |
+
"loss": 0.6095,
|
| 75414 |
+
"step": 10772
|
| 75415 |
+
},
|
| 75416 |
+
{
|
| 75417 |
+
"epoch": 12.270085470085471,
|
| 75418 |
+
"grad_norm": 0.22123247385025024,
|
| 75419 |
+
"learning_rate": 1.7475134604712496e-05,
|
| 75420 |
+
"loss": 0.6514,
|
| 75421 |
+
"step": 10773
|
| 75422 |
+
},
|
| 75423 |
+
{
|
| 75424 |
+
"epoch": 12.271225071225071,
|
| 75425 |
+
"grad_norm": 0.21868394315242767,
|
| 75426 |
+
"learning_rate": 1.7470691619900843e-05,
|
| 75427 |
+
"loss": 0.6075,
|
| 75428 |
+
"step": 10774
|
| 75429 |
+
},
|
| 75430 |
+
{
|
| 75431 |
+
"epoch": 12.272364672364672,
|
| 75432 |
+
"grad_norm": 0.1895763874053955,
|
| 75433 |
+
"learning_rate": 1.7466248896602776e-05,
|
| 75434 |
+
"loss": 0.8371,
|
| 75435 |
+
"step": 10775
|
| 75436 |
+
},
|
| 75437 |
+
{
|
| 75438 |
+
"epoch": 12.273504273504274,
|
| 75439 |
+
"grad_norm": 0.22064198553562164,
|
| 75440 |
+
"learning_rate": 1.7461806434972604e-05,
|
| 75441 |
+
"loss": 0.6574,
|
| 75442 |
+
"step": 10776
|
| 75443 |
+
},
|
| 75444 |
+
{
|
| 75445 |
+
"epoch": 12.274643874643875,
|
| 75446 |
+
"grad_norm": 0.2188696265220642,
|
| 75447 |
+
"learning_rate": 1.7457364235164625e-05,
|
| 75448 |
+
"loss": 0.5647,
|
| 75449 |
+
"step": 10777
|
| 75450 |
+
},
|
| 75451 |
+
{
|
| 75452 |
+
"epoch": 12.275783475783475,
|
| 75453 |
+
"grad_norm": 0.26082390546798706,
|
| 75454 |
+
"learning_rate": 1.7452922297333125e-05,
|
| 75455 |
+
"loss": 0.5591,
|
| 75456 |
+
"step": 10778
|
| 75457 |
+
},
|
| 75458 |
+
{
|
| 75459 |
+
"epoch": 12.276923076923078,
|
| 75460 |
+
"grad_norm": 0.21436484158039093,
|
| 75461 |
+
"learning_rate": 1.7448480621632397e-05,
|
| 75462 |
+
"loss": 0.7713,
|
| 75463 |
+
"step": 10779
|
| 75464 |
+
},
|
| 75465 |
+
{
|
| 75466 |
+
"epoch": 12.278062678062678,
|
| 75467 |
+
"grad_norm": 0.1950216293334961,
|
| 75468 |
+
"learning_rate": 1.7444039208216695e-05,
|
| 75469 |
+
"loss": 0.6866,
|
| 75470 |
+
"step": 10780
|
| 75471 |
+
},
|
| 75472 |
+
{
|
| 75473 |
+
"epoch": 12.279202279202279,
|
| 75474 |
+
"grad_norm": 0.1890411376953125,
|
| 75475 |
+
"learning_rate": 1.7439598057240297e-05,
|
| 75476 |
+
"loss": 0.8617,
|
| 75477 |
+
"step": 10781
|
| 75478 |
+
},
|
| 75479 |
+
{
|
| 75480 |
+
"epoch": 12.280341880341881,
|
| 75481 |
+
"grad_norm": 0.19841855764389038,
|
| 75482 |
+
"learning_rate": 1.7435157168857442e-05,
|
| 75483 |
+
"loss": 0.6381,
|
| 75484 |
+
"step": 10782
|
| 75485 |
+
},
|
| 75486 |
+
{
|
| 75487 |
+
"epoch": 12.281481481481482,
|
| 75488 |
+
"grad_norm": 0.22863084077835083,
|
| 75489 |
+
"learning_rate": 1.7430716543222388e-05,
|
| 75490 |
+
"loss": 0.4503,
|
| 75491 |
+
"step": 10783
|
| 75492 |
+
},
|
| 75493 |
+
{
|
| 75494 |
+
"epoch": 12.282621082621082,
|
| 75495 |
+
"grad_norm": 0.1743665486574173,
|
| 75496 |
+
"learning_rate": 1.7426276180489355e-05,
|
| 75497 |
+
"loss": 0.6095,
|
| 75498 |
+
"step": 10784
|
| 75499 |
+
},
|
| 75500 |
+
{
|
| 75501 |
+
"epoch": 12.283760683760685,
|
| 75502 |
+
"grad_norm": 0.2586623430252075,
|
| 75503 |
+
"learning_rate": 1.7421836080812583e-05,
|
| 75504 |
+
"loss": 0.4805,
|
| 75505 |
+
"step": 10785
|
| 75506 |
+
},
|
| 75507 |
+
{
|
| 75508 |
+
"epoch": 12.284900284900285,
|
| 75509 |
+
"grad_norm": 0.21026919782161713,
|
| 75510 |
+
"learning_rate": 1.741739624434629e-05,
|
| 75511 |
+
"loss": 0.5799,
|
| 75512 |
+
"step": 10786
|
| 75513 |
+
},
|
| 75514 |
+
{
|
| 75515 |
+
"epoch": 12.286039886039886,
|
| 75516 |
+
"grad_norm": 0.21374911069869995,
|
| 75517 |
+
"learning_rate": 1.741295667124467e-05,
|
| 75518 |
+
"loss": 0.7512,
|
| 75519 |
+
"step": 10787
|
| 75520 |
+
},
|
| 75521 |
+
{
|
| 75522 |
+
"epoch": 12.287179487179488,
|
| 75523 |
+
"grad_norm": 0.21112634241580963,
|
| 75524 |
+
"learning_rate": 1.7408517361661934e-05,
|
| 75525 |
+
"loss": 0.7029,
|
| 75526 |
+
"step": 10788
|
| 75527 |
+
},
|
| 75528 |
+
{
|
| 75529 |
+
"epoch": 12.288319088319088,
|
| 75530 |
+
"grad_norm": 0.20958742499351501,
|
| 75531 |
+
"learning_rate": 1.7404078315752265e-05,
|
| 75532 |
+
"loss": 0.6727,
|
| 75533 |
+
"step": 10789
|
| 75534 |
+
},
|
| 75535 |
+
{
|
| 75536 |
+
"epoch": 12.289458689458689,
|
| 75537 |
+
"grad_norm": 0.27278652787208557,
|
| 75538 |
+
"learning_rate": 1.7399639533669848e-05,
|
| 75539 |
+
"loss": 0.6567,
|
| 75540 |
+
"step": 10790
|
| 75541 |
+
},
|
| 75542 |
+
{
|
| 75543 |
+
"epoch": 12.290598290598291,
|
| 75544 |
+
"grad_norm": 0.20039872825145721,
|
| 75545 |
+
"learning_rate": 1.7395201015568847e-05,
|
| 75546 |
+
"loss": 0.7497,
|
| 75547 |
+
"step": 10791
|
| 75548 |
+
},
|
| 75549 |
+
{
|
| 75550 |
+
"epoch": 12.291737891737892,
|
| 75551 |
+
"grad_norm": 0.1941027045249939,
|
| 75552 |
+
"learning_rate": 1.7390762761603433e-05,
|
| 75553 |
+
"loss": 0.5699,
|
| 75554 |
+
"step": 10792
|
| 75555 |
+
},
|
| 75556 |
+
{
|
| 75557 |
+
"epoch": 12.292877492877492,
|
| 75558 |
+
"grad_norm": 0.27816611528396606,
|
| 75559 |
+
"learning_rate": 1.7386324771927748e-05,
|
| 75560 |
+
"loss": 0.5251,
|
| 75561 |
+
"step": 10793
|
| 75562 |
+
},
|
| 75563 |
+
{
|
| 75564 |
+
"epoch": 12.294017094017095,
|
| 75565 |
+
"grad_norm": 0.20026326179504395,
|
| 75566 |
+
"learning_rate": 1.7381887046695945e-05,
|
| 75567 |
+
"loss": 0.7609,
|
| 75568 |
+
"step": 10794
|
| 75569 |
+
},
|
| 75570 |
+
{
|
| 75571 |
+
"epoch": 12.295156695156695,
|
| 75572 |
+
"grad_norm": 0.23853638768196106,
|
| 75573 |
+
"learning_rate": 1.737744958606215e-05,
|
| 75574 |
+
"loss": 0.6327,
|
| 75575 |
+
"step": 10795
|
| 75576 |
+
},
|
| 75577 |
+
{
|
| 75578 |
+
"epoch": 12.296296296296296,
|
| 75579 |
+
"grad_norm": 0.21739494800567627,
|
| 75580 |
+
"learning_rate": 1.737301239018049e-05,
|
| 75581 |
+
"loss": 0.5109,
|
| 75582 |
+
"step": 10796
|
| 75583 |
+
},
|
| 75584 |
+
{
|
| 75585 |
+
"epoch": 12.297435897435898,
|
| 75586 |
+
"grad_norm": 0.2554258406162262,
|
| 75587 |
+
"learning_rate": 1.736857545920509e-05,
|
| 75588 |
+
"loss": 0.351,
|
| 75589 |
+
"step": 10797
|
| 75590 |
+
},
|
| 75591 |
+
{
|
| 75592 |
+
"epoch": 12.298575498575499,
|
| 75593 |
+
"grad_norm": 0.20038418471813202,
|
| 75594 |
+
"learning_rate": 1.736413879329005e-05,
|
| 75595 |
+
"loss": 0.6367,
|
| 75596 |
+
"step": 10798
|
| 75597 |
+
},
|
| 75598 |
+
{
|
| 75599 |
+
"epoch": 12.2997150997151,
|
| 75600 |
+
"grad_norm": 0.19856251776218414,
|
| 75601 |
+
"learning_rate": 1.735970239258947e-05,
|
| 75602 |
+
"loss": 0.8322,
|
| 75603 |
+
"step": 10799
|
| 75604 |
+
},
|
| 75605 |
+
{
|
| 75606 |
+
"epoch": 12.300854700854702,
|
| 75607 |
+
"grad_norm": 0.2430545538663864,
|
| 75608 |
+
"learning_rate": 1.7355266257257438e-05,
|
| 75609 |
+
"loss": 0.5878,
|
| 75610 |
+
"step": 10800
|
| 75611 |
}
|
| 75612 |
],
|
| 75613 |
"logging_steps": 1,
|
|
|
|
| 75627 |
"attributes": {}
|
| 75628 |
}
|
| 75629 |
},
|
| 75630 |
+
"total_flos": 6.0385087639077765e+19,
|
| 75631 |
"train_batch_size": 8,
|
| 75632 |
"trial_name": null,
|
| 75633 |
"trial_params": null
|