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 11400, 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 sha256:643cde44700aacfd0d39797cebf5c0e75118e3682193958f478e6d29585fd043
|
| 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 sha256:13e6a7a3a125b5a0737661fbda8b9397bbdc7f6d4f233b1c1dd46eed796f9b8e
|
| 3 |
size 173247691
|
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 sha256:92b52a71c6e7867d05793534f71d387ff91ff71d86c3b1b820a177d51183edd2
|
| 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": 12.
|
| 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,
|
|
@@ -77708,6 +77708,2106 @@
|
|
| 77708 |
"learning_rate": 1.6037104111533897e-05,
|
| 77709 |
"loss": 0.7505,
|
| 77710 |
"step": 11100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77711 |
}
|
| 77712 |
],
|
| 77713 |
"logging_steps": 1,
|
|
@@ -77727,7 +79827,7 @@
|
|
| 77727 |
"attributes": {}
|
| 77728 |
}
|
| 77729 |
},
|
| 77730 |
-
"total_flos": 6.
|
| 77731 |
"train_batch_size": 8,
|
| 77732 |
"trial_name": null,
|
| 77733 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.984615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 11400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 77708 |
"learning_rate": 1.6037104111533897e-05,
|
| 77709 |
"loss": 0.7505,
|
| 77710 |
"step": 11100
|
| 77711 |
+
},
|
| 77712 |
+
{
|
| 77713 |
+
"epoch": 12.643874643874645,
|
| 77714 |
+
"grad_norm": 0.2057197391986847,
|
| 77715 |
+
"learning_rate": 1.603275481145942e-05,
|
| 77716 |
+
"loss": 0.6726,
|
| 77717 |
+
"step": 11101
|
| 77718 |
+
},
|
| 77719 |
+
{
|
| 77720 |
+
"epoch": 12.645014245014245,
|
| 77721 |
+
"grad_norm": 0.2566360831260681,
|
| 77722 |
+
"learning_rate": 1.6028405822842036e-05,
|
| 77723 |
+
"loss": 0.5354,
|
| 77724 |
+
"step": 11102
|
| 77725 |
+
},
|
| 77726 |
+
{
|
| 77727 |
+
"epoch": 12.646153846153846,
|
| 77728 |
+
"grad_norm": 0.19007746875286102,
|
| 77729 |
+
"learning_rate": 1.6024057145832782e-05,
|
| 77730 |
+
"loss": 0.9406,
|
| 77731 |
+
"step": 11103
|
| 77732 |
+
},
|
| 77733 |
+
{
|
| 77734 |
+
"epoch": 12.647293447293448,
|
| 77735 |
+
"grad_norm": 0.17702710628509521,
|
| 77736 |
+
"learning_rate": 1.6019708780582715e-05,
|
| 77737 |
+
"loss": 0.8956,
|
| 77738 |
+
"step": 11104
|
| 77739 |
+
},
|
| 77740 |
+
{
|
| 77741 |
+
"epoch": 12.648433048433048,
|
| 77742 |
+
"grad_norm": 0.22386471927165985,
|
| 77743 |
+
"learning_rate": 1.6015360727242844e-05,
|
| 77744 |
+
"loss": 0.4807,
|
| 77745 |
+
"step": 11105
|
| 77746 |
+
},
|
| 77747 |
+
{
|
| 77748 |
+
"epoch": 12.649572649572649,
|
| 77749 |
+
"grad_norm": 0.23359254002571106,
|
| 77750 |
+
"learning_rate": 1.6011012985964212e-05,
|
| 77751 |
+
"loss": 0.5094,
|
| 77752 |
+
"step": 11106
|
| 77753 |
+
},
|
| 77754 |
+
{
|
| 77755 |
+
"epoch": 12.650712250712251,
|
| 77756 |
+
"grad_norm": 0.17404289543628693,
|
| 77757 |
+
"learning_rate": 1.6006665556897815e-05,
|
| 77758 |
+
"loss": 0.7101,
|
| 77759 |
+
"step": 11107
|
| 77760 |
+
},
|
| 77761 |
+
{
|
| 77762 |
+
"epoch": 12.651851851851852,
|
| 77763 |
+
"grad_norm": 0.22402898967266083,
|
| 77764 |
+
"learning_rate": 1.6002318440194664e-05,
|
| 77765 |
+
"loss": 0.7611,
|
| 77766 |
+
"step": 11108
|
| 77767 |
+
},
|
| 77768 |
+
{
|
| 77769 |
+
"epoch": 12.652991452991452,
|
| 77770 |
+
"grad_norm": 0.16277088224887848,
|
| 77771 |
+
"learning_rate": 1.599797163600573e-05,
|
| 77772 |
+
"loss": 0.7209,
|
| 77773 |
+
"step": 11109
|
| 77774 |
+
},
|
| 77775 |
+
{
|
| 77776 |
+
"epoch": 12.654131054131055,
|
| 77777 |
+
"grad_norm": 0.22703644633293152,
|
| 77778 |
+
"learning_rate": 1.5993625144482e-05,
|
| 77779 |
+
"loss": 0.5067,
|
| 77780 |
+
"step": 11110
|
| 77781 |
+
},
|
| 77782 |
+
{
|
| 77783 |
+
"epoch": 12.655270655270655,
|
| 77784 |
+
"grad_norm": 0.27813565731048584,
|
| 77785 |
+
"learning_rate": 1.5989278965774433e-05,
|
| 77786 |
+
"loss": 0.6124,
|
| 77787 |
+
"step": 11111
|
| 77788 |
+
},
|
| 77789 |
+
{
|
| 77790 |
+
"epoch": 12.656410256410256,
|
| 77791 |
+
"grad_norm": 0.2167578786611557,
|
| 77792 |
+
"learning_rate": 1.5984933100033995e-05,
|
| 77793 |
+
"loss": 0.6381,
|
| 77794 |
+
"step": 11112
|
| 77795 |
+
},
|
| 77796 |
+
{
|
| 77797 |
+
"epoch": 12.657549857549858,
|
| 77798 |
+
"grad_norm": 0.19387587904930115,
|
| 77799 |
+
"learning_rate": 1.5980587547411612e-05,
|
| 77800 |
+
"loss": 0.6903,
|
| 77801 |
+
"step": 11113
|
| 77802 |
+
},
|
| 77803 |
+
{
|
| 77804 |
+
"epoch": 12.658689458689459,
|
| 77805 |
+
"grad_norm": 0.24054613709449768,
|
| 77806 |
+
"learning_rate": 1.5976242308058235e-05,
|
| 77807 |
+
"loss": 0.7076,
|
| 77808 |
+
"step": 11114
|
| 77809 |
+
},
|
| 77810 |
+
{
|
| 77811 |
+
"epoch": 12.65982905982906,
|
| 77812 |
+
"grad_norm": 0.2635744512081146,
|
| 77813 |
+
"learning_rate": 1.5971897382124773e-05,
|
| 77814 |
+
"loss": 0.5763,
|
| 77815 |
+
"step": 11115
|
| 77816 |
+
},
|
| 77817 |
+
{
|
| 77818 |
+
"epoch": 12.660968660968662,
|
| 77819 |
+
"grad_norm": 0.18814826011657715,
|
| 77820 |
+
"learning_rate": 1.5967552769762138e-05,
|
| 77821 |
+
"loss": 0.5222,
|
| 77822 |
+
"step": 11116
|
| 77823 |
+
},
|
| 77824 |
+
{
|
| 77825 |
+
"epoch": 12.662108262108262,
|
| 77826 |
+
"grad_norm": 0.2089758962392807,
|
| 77827 |
+
"learning_rate": 1.5963208471121245e-05,
|
| 77828 |
+
"loss": 0.6821,
|
| 77829 |
+
"step": 11117
|
| 77830 |
+
},
|
| 77831 |
+
{
|
| 77832 |
+
"epoch": 12.663247863247863,
|
| 77833 |
+
"grad_norm": 0.23014183342456818,
|
| 77834 |
+
"learning_rate": 1.5958864486352964e-05,
|
| 77835 |
+
"loss": 0.6499,
|
| 77836 |
+
"step": 11118
|
| 77837 |
+
},
|
| 77838 |
+
{
|
| 77839 |
+
"epoch": 12.664387464387465,
|
| 77840 |
+
"grad_norm": 0.31964734196662903,
|
| 77841 |
+
"learning_rate": 1.595452081560819e-05,
|
| 77842 |
+
"loss": 0.5052,
|
| 77843 |
+
"step": 11119
|
| 77844 |
+
},
|
| 77845 |
+
{
|
| 77846 |
+
"epoch": 12.665527065527066,
|
| 77847 |
+
"grad_norm": 0.22384202480316162,
|
| 77848 |
+
"learning_rate": 1.595017745903778e-05,
|
| 77849 |
+
"loss": 0.7366,
|
| 77850 |
+
"step": 11120
|
| 77851 |
+
},
|
| 77852 |
+
{
|
| 77853 |
+
"epoch": 12.666666666666666,
|
| 77854 |
+
"grad_norm": 0.18546050786972046,
|
| 77855 |
+
"learning_rate": 1.5945834416792596e-05,
|
| 77856 |
+
"loss": 0.7342,
|
| 77857 |
+
"step": 11121
|
| 77858 |
+
},
|
| 77859 |
+
{
|
| 77860 |
+
"epoch": 12.667806267806268,
|
| 77861 |
+
"grad_norm": 0.22354067862033844,
|
| 77862 |
+
"learning_rate": 1.594149168902348e-05,
|
| 77863 |
+
"loss": 0.8117,
|
| 77864 |
+
"step": 11122
|
| 77865 |
+
},
|
| 77866 |
+
{
|
| 77867 |
+
"epoch": 12.668945868945869,
|
| 77868 |
+
"grad_norm": 0.2659115791320801,
|
| 77869 |
+
"learning_rate": 1.5937149275881268e-05,
|
| 77870 |
+
"loss": 0.5371,
|
| 77871 |
+
"step": 11123
|
| 77872 |
+
},
|
| 77873 |
+
{
|
| 77874 |
+
"epoch": 12.67008547008547,
|
| 77875 |
+
"grad_norm": 0.22612543404102325,
|
| 77876 |
+
"learning_rate": 1.5932807177516784e-05,
|
| 77877 |
+
"loss": 0.673,
|
| 77878 |
+
"step": 11124
|
| 77879 |
+
},
|
| 77880 |
+
{
|
| 77881 |
+
"epoch": 12.671225071225072,
|
| 77882 |
+
"grad_norm": 0.21471258997917175,
|
| 77883 |
+
"learning_rate": 1.5928465394080848e-05,
|
| 77884 |
+
"loss": 0.722,
|
| 77885 |
+
"step": 11125
|
| 77886 |
+
},
|
| 77887 |
+
{
|
| 77888 |
+
"epoch": 12.672364672364672,
|
| 77889 |
+
"grad_norm": 0.2103831171989441,
|
| 77890 |
+
"learning_rate": 1.5924123925724248e-05,
|
| 77891 |
+
"loss": 0.838,
|
| 77892 |
+
"step": 11126
|
| 77893 |
+
},
|
| 77894 |
+
{
|
| 77895 |
+
"epoch": 12.673504273504273,
|
| 77896 |
+
"grad_norm": 0.2037634402513504,
|
| 77897 |
+
"learning_rate": 1.5919782772597776e-05,
|
| 77898 |
+
"loss": 0.4347,
|
| 77899 |
+
"step": 11127
|
| 77900 |
+
},
|
| 77901 |
+
{
|
| 77902 |
+
"epoch": 12.674643874643875,
|
| 77903 |
+
"grad_norm": 0.18816131353378296,
|
| 77904 |
+
"learning_rate": 1.591544193485223e-05,
|
| 77905 |
+
"loss": 0.8471,
|
| 77906 |
+
"step": 11128
|
| 77907 |
+
},
|
| 77908 |
+
{
|
| 77909 |
+
"epoch": 12.675783475783476,
|
| 77910 |
+
"grad_norm": 0.19635280966758728,
|
| 77911 |
+
"learning_rate": 1.591110141263837e-05,
|
| 77912 |
+
"loss": 0.6587,
|
| 77913 |
+
"step": 11129
|
| 77914 |
+
},
|
| 77915 |
+
{
|
| 77916 |
+
"epoch": 12.676923076923076,
|
| 77917 |
+
"grad_norm": 0.19508196413516998,
|
| 77918 |
+
"learning_rate": 1.5906761206106953e-05,
|
| 77919 |
+
"loss": 0.7512,
|
| 77920 |
+
"step": 11130
|
| 77921 |
+
},
|
| 77922 |
+
{
|
| 77923 |
+
"epoch": 12.678062678062679,
|
| 77924 |
+
"grad_norm": 0.2978247106075287,
|
| 77925 |
+
"learning_rate": 1.5902421315408716e-05,
|
| 77926 |
+
"loss": 0.6487,
|
| 77927 |
+
"step": 11131
|
| 77928 |
+
},
|
| 77929 |
+
{
|
| 77930 |
+
"epoch": 12.67920227920228,
|
| 77931 |
+
"grad_norm": 0.2564646601676941,
|
| 77932 |
+
"learning_rate": 1.5898081740694416e-05,
|
| 77933 |
+
"loss": 0.6217,
|
| 77934 |
+
"step": 11132
|
| 77935 |
+
},
|
| 77936 |
+
{
|
| 77937 |
+
"epoch": 12.68034188034188,
|
| 77938 |
+
"grad_norm": 0.23250678181648254,
|
| 77939 |
+
"learning_rate": 1.589374248211476e-05,
|
| 77940 |
+
"loss": 0.6793,
|
| 77941 |
+
"step": 11133
|
| 77942 |
+
},
|
| 77943 |
+
{
|
| 77944 |
+
"epoch": 12.681481481481482,
|
| 77945 |
+
"grad_norm": 0.2524375319480896,
|
| 77946 |
+
"learning_rate": 1.5889403539820476e-05,
|
| 77947 |
+
"loss": 0.4932,
|
| 77948 |
+
"step": 11134
|
| 77949 |
+
},
|
| 77950 |
+
{
|
| 77951 |
+
"epoch": 12.682621082621083,
|
| 77952 |
+
"grad_norm": 0.18259340524673462,
|
| 77953 |
+
"learning_rate": 1.5885064913962255e-05,
|
| 77954 |
+
"loss": 0.6859,
|
| 77955 |
+
"step": 11135
|
| 77956 |
+
},
|
| 77957 |
+
{
|
| 77958 |
+
"epoch": 12.683760683760683,
|
| 77959 |
+
"grad_norm": 0.1866711527109146,
|
| 77960 |
+
"learning_rate": 1.58807266046908e-05,
|
| 77961 |
+
"loss": 0.688,
|
| 77962 |
+
"step": 11136
|
| 77963 |
+
},
|
| 77964 |
+
{
|
| 77965 |
+
"epoch": 12.684900284900285,
|
| 77966 |
+
"grad_norm": 0.22629667818546295,
|
| 77967 |
+
"learning_rate": 1.5876388612156782e-05,
|
| 77968 |
+
"loss": 0.588,
|
| 77969 |
+
"step": 11137
|
| 77970 |
+
},
|
| 77971 |
+
{
|
| 77972 |
+
"epoch": 12.686039886039886,
|
| 77973 |
+
"grad_norm": 0.19245080649852753,
|
| 77974 |
+
"learning_rate": 1.587205093651088e-05,
|
| 77975 |
+
"loss": 0.8236,
|
| 77976 |
+
"step": 11138
|
| 77977 |
+
},
|
| 77978 |
+
{
|
| 77979 |
+
"epoch": 12.687179487179487,
|
| 77980 |
+
"grad_norm": 0.21643824875354767,
|
| 77981 |
+
"learning_rate": 1.5867713577903752e-05,
|
| 77982 |
+
"loss": 0.5575,
|
| 77983 |
+
"step": 11139
|
| 77984 |
+
},
|
| 77985 |
+
{
|
| 77986 |
+
"epoch": 12.688319088319089,
|
| 77987 |
+
"grad_norm": 0.18831786513328552,
|
| 77988 |
+
"learning_rate": 1.5863376536486046e-05,
|
| 77989 |
+
"loss": 0.6612,
|
| 77990 |
+
"step": 11140
|
| 77991 |
+
},
|
| 77992 |
+
{
|
| 77993 |
+
"epoch": 12.68945868945869,
|
| 77994 |
+
"grad_norm": 0.1758168339729309,
|
| 77995 |
+
"learning_rate": 1.5859039812408404e-05,
|
| 77996 |
+
"loss": 0.6423,
|
| 77997 |
+
"step": 11141
|
| 77998 |
+
},
|
| 77999 |
+
{
|
| 78000 |
+
"epoch": 12.69059829059829,
|
| 78001 |
+
"grad_norm": 0.2479313611984253,
|
| 78002 |
+
"learning_rate": 1.5854703405821438e-05,
|
| 78003 |
+
"loss": 0.5712,
|
| 78004 |
+
"step": 11142
|
| 78005 |
+
},
|
| 78006 |
+
{
|
| 78007 |
+
"epoch": 12.691737891737892,
|
| 78008 |
+
"grad_norm": 0.1954648196697235,
|
| 78009 |
+
"learning_rate": 1.585036731687578e-05,
|
| 78010 |
+
"loss": 0.7463,
|
| 78011 |
+
"step": 11143
|
| 78012 |
+
},
|
| 78013 |
+
{
|
| 78014 |
+
"epoch": 12.692877492877493,
|
| 78015 |
+
"grad_norm": 0.22821049392223358,
|
| 78016 |
+
"learning_rate": 1.5846031545722022e-05,
|
| 78017 |
+
"loss": 0.6038,
|
| 78018 |
+
"step": 11144
|
| 78019 |
+
},
|
| 78020 |
+
{
|
| 78021 |
+
"epoch": 12.694017094017093,
|
| 78022 |
+
"grad_norm": 0.17145420610904694,
|
| 78023 |
+
"learning_rate": 1.5841696092510767e-05,
|
| 78024 |
+
"loss": 0.7862,
|
| 78025 |
+
"step": 11145
|
| 78026 |
+
},
|
| 78027 |
+
{
|
| 78028 |
+
"epoch": 12.695156695156696,
|
| 78029 |
+
"grad_norm": 0.2066497951745987,
|
| 78030 |
+
"learning_rate": 1.5837360957392584e-05,
|
| 78031 |
+
"loss": 0.7199,
|
| 78032 |
+
"step": 11146
|
| 78033 |
+
},
|
| 78034 |
+
{
|
| 78035 |
+
"epoch": 12.696296296296296,
|
| 78036 |
+
"grad_norm": 0.2200264185667038,
|
| 78037 |
+
"learning_rate": 1.5833026140518063e-05,
|
| 78038 |
+
"loss": 0.7711,
|
| 78039 |
+
"step": 11147
|
| 78040 |
+
},
|
| 78041 |
+
{
|
| 78042 |
+
"epoch": 12.697435897435897,
|
| 78043 |
+
"grad_norm": 0.2565844655036926,
|
| 78044 |
+
"learning_rate": 1.5828691642037742e-05,
|
| 78045 |
+
"loss": 0.4629,
|
| 78046 |
+
"step": 11148
|
| 78047 |
+
},
|
| 78048 |
+
{
|
| 78049 |
+
"epoch": 12.698575498575499,
|
| 78050 |
+
"grad_norm": 0.16445843875408173,
|
| 78051 |
+
"learning_rate": 1.5824357462102178e-05,
|
| 78052 |
+
"loss": 0.8913,
|
| 78053 |
+
"step": 11149
|
| 78054 |
+
},
|
| 78055 |
+
{
|
| 78056 |
+
"epoch": 12.6997150997151,
|
| 78057 |
+
"grad_norm": 0.22528819739818573,
|
| 78058 |
+
"learning_rate": 1.582002360086192e-05,
|
| 78059 |
+
"loss": 0.6493,
|
| 78060 |
+
"step": 11150
|
| 78061 |
+
},
|
| 78062 |
+
{
|
| 78063 |
+
"epoch": 12.7008547008547,
|
| 78064 |
+
"grad_norm": 0.19773760437965393,
|
| 78065 |
+
"learning_rate": 1.581569005846749e-05,
|
| 78066 |
+
"loss": 0.7771,
|
| 78067 |
+
"step": 11151
|
| 78068 |
+
},
|
| 78069 |
+
{
|
| 78070 |
+
"epoch": 12.701994301994302,
|
| 78071 |
+
"grad_norm": 0.25532928109169006,
|
| 78072 |
+
"learning_rate": 1.5811356835069402e-05,
|
| 78073 |
+
"loss": 0.7498,
|
| 78074 |
+
"step": 11152
|
| 78075 |
+
},
|
| 78076 |
+
{
|
| 78077 |
+
"epoch": 12.703133903133903,
|
| 78078 |
+
"grad_norm": 0.22465664148330688,
|
| 78079 |
+
"learning_rate": 1.580702393081816e-05,
|
| 78080 |
+
"loss": 0.5811,
|
| 78081 |
+
"step": 11153
|
| 78082 |
+
},
|
| 78083 |
+
{
|
| 78084 |
+
"epoch": 12.704273504273504,
|
| 78085 |
+
"grad_norm": 0.2509215772151947,
|
| 78086 |
+
"learning_rate": 1.580269134586425e-05,
|
| 78087 |
+
"loss": 0.5316,
|
| 78088 |
+
"step": 11154
|
| 78089 |
+
},
|
| 78090 |
+
{
|
| 78091 |
+
"epoch": 12.705413105413106,
|
| 78092 |
+
"grad_norm": 0.22902412712574005,
|
| 78093 |
+
"learning_rate": 1.579835908035817e-05,
|
| 78094 |
+
"loss": 0.3799,
|
| 78095 |
+
"step": 11155
|
| 78096 |
+
},
|
| 78097 |
+
{
|
| 78098 |
+
"epoch": 12.706552706552706,
|
| 78099 |
+
"grad_norm": 0.2320164144039154,
|
| 78100 |
+
"learning_rate": 1.5794027134450382e-05,
|
| 78101 |
+
"loss": 0.627,
|
| 78102 |
+
"step": 11156
|
| 78103 |
+
},
|
| 78104 |
+
{
|
| 78105 |
+
"epoch": 12.707692307692307,
|
| 78106 |
+
"grad_norm": 0.2339378446340561,
|
| 78107 |
+
"learning_rate": 1.5789695508291348e-05,
|
| 78108 |
+
"loss": 0.5747,
|
| 78109 |
+
"step": 11157
|
| 78110 |
+
},
|
| 78111 |
+
{
|
| 78112 |
+
"epoch": 12.70883190883191,
|
| 78113 |
+
"grad_norm": 0.2223222702741623,
|
| 78114 |
+
"learning_rate": 1.5785364202031515e-05,
|
| 78115 |
+
"loss": 0.6875,
|
| 78116 |
+
"step": 11158
|
| 78117 |
+
},
|
| 78118 |
+
{
|
| 78119 |
+
"epoch": 12.70997150997151,
|
| 78120 |
+
"grad_norm": 0.1851043403148651,
|
| 78121 |
+
"learning_rate": 1.578103321582133e-05,
|
| 78122 |
+
"loss": 0.6541,
|
| 78123 |
+
"step": 11159
|
| 78124 |
+
},
|
| 78125 |
+
{
|
| 78126 |
+
"epoch": 12.71111111111111,
|
| 78127 |
+
"grad_norm": 0.2115449160337448,
|
| 78128 |
+
"learning_rate": 1.57767025498112e-05,
|
| 78129 |
+
"loss": 0.6917,
|
| 78130 |
+
"step": 11160
|
| 78131 |
+
},
|
| 78132 |
+
{
|
| 78133 |
+
"epoch": 12.712250712250713,
|
| 78134 |
+
"grad_norm": 0.21514242887496948,
|
| 78135 |
+
"learning_rate": 1.5772372204151564e-05,
|
| 78136 |
+
"loss": 0.535,
|
| 78137 |
+
"step": 11161
|
| 78138 |
+
},
|
| 78139 |
+
{
|
| 78140 |
+
"epoch": 12.713390313390313,
|
| 78141 |
+
"grad_norm": 0.2880719304084778,
|
| 78142 |
+
"learning_rate": 1.576804217899282e-05,
|
| 78143 |
+
"loss": 0.6128,
|
| 78144 |
+
"step": 11162
|
| 78145 |
+
},
|
| 78146 |
+
{
|
| 78147 |
+
"epoch": 12.714529914529914,
|
| 78148 |
+
"grad_norm": 0.1779347062110901,
|
| 78149 |
+
"learning_rate": 1.5763712474485352e-05,
|
| 78150 |
+
"loss": 1.077,
|
| 78151 |
+
"step": 11163
|
| 78152 |
+
},
|
| 78153 |
+
{
|
| 78154 |
+
"epoch": 12.715669515669516,
|
| 78155 |
+
"grad_norm": 0.196516215801239,
|
| 78156 |
+
"learning_rate": 1.5759383090779557e-05,
|
| 78157 |
+
"loss": 0.7063,
|
| 78158 |
+
"step": 11164
|
| 78159 |
+
},
|
| 78160 |
+
{
|
| 78161 |
+
"epoch": 12.716809116809117,
|
| 78162 |
+
"grad_norm": 0.2461429238319397,
|
| 78163 |
+
"learning_rate": 1.5755054028025795e-05,
|
| 78164 |
+
"loss": 0.5388,
|
| 78165 |
+
"step": 11165
|
| 78166 |
+
},
|
| 78167 |
+
{
|
| 78168 |
+
"epoch": 12.717948717948717,
|
| 78169 |
+
"grad_norm": 0.19045525789260864,
|
| 78170 |
+
"learning_rate": 1.5750725286374436e-05,
|
| 78171 |
+
"loss": 0.7982,
|
| 78172 |
+
"step": 11166
|
| 78173 |
+
},
|
| 78174 |
+
{
|
| 78175 |
+
"epoch": 12.71908831908832,
|
| 78176 |
+
"grad_norm": 0.22819633781909943,
|
| 78177 |
+
"learning_rate": 1.5746396865975814e-05,
|
| 78178 |
+
"loss": 0.6243,
|
| 78179 |
+
"step": 11167
|
| 78180 |
+
},
|
| 78181 |
+
{
|
| 78182 |
+
"epoch": 12.72022792022792,
|
| 78183 |
+
"grad_norm": 0.20307184755802155,
|
| 78184 |
+
"learning_rate": 1.5742068766980282e-05,
|
| 78185 |
+
"loss": 0.5656,
|
| 78186 |
+
"step": 11168
|
| 78187 |
+
},
|
| 78188 |
+
{
|
| 78189 |
+
"epoch": 12.72136752136752,
|
| 78190 |
+
"grad_norm": 0.2208218276500702,
|
| 78191 |
+
"learning_rate": 1.573774098953816e-05,
|
| 78192 |
+
"loss": 0.6779,
|
| 78193 |
+
"step": 11169
|
| 78194 |
+
},
|
| 78195 |
+
{
|
| 78196 |
+
"epoch": 12.722507122507123,
|
| 78197 |
+
"grad_norm": 0.20758362114429474,
|
| 78198 |
+
"learning_rate": 1.5733413533799767e-05,
|
| 78199 |
+
"loss": 0.8041,
|
| 78200 |
+
"step": 11170
|
| 78201 |
+
},
|
| 78202 |
+
{
|
| 78203 |
+
"epoch": 12.723646723646723,
|
| 78204 |
+
"grad_norm": 0.17610397934913635,
|
| 78205 |
+
"learning_rate": 1.5729086399915398e-05,
|
| 78206 |
+
"loss": 0.6553,
|
| 78207 |
+
"step": 11171
|
| 78208 |
+
},
|
| 78209 |
+
{
|
| 78210 |
+
"epoch": 12.724786324786324,
|
| 78211 |
+
"grad_norm": 0.201230987906456,
|
| 78212 |
+
"learning_rate": 1.5724759588035358e-05,
|
| 78213 |
+
"loss": 0.6433,
|
| 78214 |
+
"step": 11172
|
| 78215 |
+
},
|
| 78216 |
+
{
|
| 78217 |
+
"epoch": 12.725925925925926,
|
| 78218 |
+
"grad_norm": 0.23075005412101746,
|
| 78219 |
+
"learning_rate": 1.5720433098309927e-05,
|
| 78220 |
+
"loss": 0.6756,
|
| 78221 |
+
"step": 11173
|
| 78222 |
+
},
|
| 78223 |
+
{
|
| 78224 |
+
"epoch": 12.727065527065527,
|
| 78225 |
+
"grad_norm": 0.19387048482894897,
|
| 78226 |
+
"learning_rate": 1.5716106930889368e-05,
|
| 78227 |
+
"loss": 0.6994,
|
| 78228 |
+
"step": 11174
|
| 78229 |
+
},
|
| 78230 |
+
{
|
| 78231 |
+
"epoch": 12.728205128205127,
|
| 78232 |
+
"grad_norm": 0.2190813422203064,
|
| 78233 |
+
"learning_rate": 1.5711781085923953e-05,
|
| 78234 |
+
"loss": 0.481,
|
| 78235 |
+
"step": 11175
|
| 78236 |
+
},
|
| 78237 |
+
{
|
| 78238 |
+
"epoch": 12.72934472934473,
|
| 78239 |
+
"grad_norm": 0.24127015471458435,
|
| 78240 |
+
"learning_rate": 1.5707455563563917e-05,
|
| 78241 |
+
"loss": 0.6465,
|
| 78242 |
+
"step": 11176
|
| 78243 |
+
},
|
| 78244 |
+
{
|
| 78245 |
+
"epoch": 12.73048433048433,
|
| 78246 |
+
"grad_norm": 0.25211644172668457,
|
| 78247 |
+
"learning_rate": 1.570313036395951e-05,
|
| 78248 |
+
"loss": 0.5271,
|
| 78249 |
+
"step": 11177
|
| 78250 |
+
},
|
| 78251 |
+
{
|
| 78252 |
+
"epoch": 12.73162393162393,
|
| 78253 |
+
"grad_norm": 0.2326471209526062,
|
| 78254 |
+
"learning_rate": 1.5698805487260948e-05,
|
| 78255 |
+
"loss": 0.5954,
|
| 78256 |
+
"step": 11178
|
| 78257 |
+
},
|
| 78258 |
+
{
|
| 78259 |
+
"epoch": 12.732763532763533,
|
| 78260 |
+
"grad_norm": 0.21010422706604004,
|
| 78261 |
+
"learning_rate": 1.5694480933618456e-05,
|
| 78262 |
+
"loss": 0.7784,
|
| 78263 |
+
"step": 11179
|
| 78264 |
+
},
|
| 78265 |
+
{
|
| 78266 |
+
"epoch": 12.733903133903134,
|
| 78267 |
+
"grad_norm": 0.15468095242977142,
|
| 78268 |
+
"learning_rate": 1.569015670318222e-05,
|
| 78269 |
+
"loss": 0.7947,
|
| 78270 |
+
"step": 11180
|
| 78271 |
+
},
|
| 78272 |
+
{
|
| 78273 |
+
"epoch": 12.735042735042736,
|
| 78274 |
+
"grad_norm": 0.25469398498535156,
|
| 78275 |
+
"learning_rate": 1.5685832796102458e-05,
|
| 78276 |
+
"loss": 0.4579,
|
| 78277 |
+
"step": 11181
|
| 78278 |
+
},
|
| 78279 |
+
{
|
| 78280 |
+
"epoch": 12.736182336182337,
|
| 78281 |
+
"grad_norm": 0.2417183816432953,
|
| 78282 |
+
"learning_rate": 1.5681509212529318e-05,
|
| 78283 |
+
"loss": 0.6263,
|
| 78284 |
+
"step": 11182
|
| 78285 |
+
},
|
| 78286 |
+
{
|
| 78287 |
+
"epoch": 12.737321937321937,
|
| 78288 |
+
"grad_norm": 0.2280004471540451,
|
| 78289 |
+
"learning_rate": 1.5677185952613e-05,
|
| 78290 |
+
"loss": 0.6585,
|
| 78291 |
+
"step": 11183
|
| 78292 |
+
},
|
| 78293 |
+
{
|
| 78294 |
+
"epoch": 12.73846153846154,
|
| 78295 |
+
"grad_norm": 0.20425523817539215,
|
| 78296 |
+
"learning_rate": 1.5672863016503653e-05,
|
| 78297 |
+
"loss": 0.6748,
|
| 78298 |
+
"step": 11184
|
| 78299 |
+
},
|
| 78300 |
+
{
|
| 78301 |
+
"epoch": 12.73960113960114,
|
| 78302 |
+
"grad_norm": 0.2509705424308777,
|
| 78303 |
+
"learning_rate": 1.566854040435142e-05,
|
| 78304 |
+
"loss": 0.5541,
|
| 78305 |
+
"step": 11185
|
| 78306 |
+
},
|
| 78307 |
+
{
|
| 78308 |
+
"epoch": 12.74074074074074,
|
| 78309 |
+
"grad_norm": 0.31750181317329407,
|
| 78310 |
+
"learning_rate": 1.566421811630644e-05,
|
| 78311 |
+
"loss": 0.7052,
|
| 78312 |
+
"step": 11186
|
| 78313 |
+
},
|
| 78314 |
+
{
|
| 78315 |
+
"epoch": 12.741880341880343,
|
| 78316 |
+
"grad_norm": 0.24409219622612,
|
| 78317 |
+
"learning_rate": 1.5659896152518844e-05,
|
| 78318 |
+
"loss": 0.7305,
|
| 78319 |
+
"step": 11187
|
| 78320 |
+
},
|
| 78321 |
+
{
|
| 78322 |
+
"epoch": 12.743019943019943,
|
| 78323 |
+
"grad_norm": 0.1938214898109436,
|
| 78324 |
+
"learning_rate": 1.5655574513138735e-05,
|
| 78325 |
+
"loss": 0.7939,
|
| 78326 |
+
"step": 11188
|
| 78327 |
+
},
|
| 78328 |
+
{
|
| 78329 |
+
"epoch": 12.744159544159544,
|
| 78330 |
+
"grad_norm": 0.25239941477775574,
|
| 78331 |
+
"learning_rate": 1.5651253198316222e-05,
|
| 78332 |
+
"loss": 0.6208,
|
| 78333 |
+
"step": 11189
|
| 78334 |
+
},
|
| 78335 |
+
{
|
| 78336 |
+
"epoch": 12.745299145299146,
|
| 78337 |
+
"grad_norm": 0.22138601541519165,
|
| 78338 |
+
"learning_rate": 1.5646932208201395e-05,
|
| 78339 |
+
"loss": 0.5108,
|
| 78340 |
+
"step": 11190
|
| 78341 |
+
},
|
| 78342 |
+
{
|
| 78343 |
+
"epoch": 12.746438746438747,
|
| 78344 |
+
"grad_norm": 0.18638557195663452,
|
| 78345 |
+
"learning_rate": 1.5642611542944336e-05,
|
| 78346 |
+
"loss": 0.8004,
|
| 78347 |
+
"step": 11191
|
| 78348 |
+
},
|
| 78349 |
+
{
|
| 78350 |
+
"epoch": 12.747578347578347,
|
| 78351 |
+
"grad_norm": 0.21830163896083832,
|
| 78352 |
+
"learning_rate": 1.5638291202695104e-05,
|
| 78353 |
+
"loss": 0.656,
|
| 78354 |
+
"step": 11192
|
| 78355 |
+
},
|
| 78356 |
+
{
|
| 78357 |
+
"epoch": 12.74871794871795,
|
| 78358 |
+
"grad_norm": 0.19808819890022278,
|
| 78359 |
+
"learning_rate": 1.5633971187603765e-05,
|
| 78360 |
+
"loss": 0.7945,
|
| 78361 |
+
"step": 11193
|
| 78362 |
+
},
|
| 78363 |
+
{
|
| 78364 |
+
"epoch": 12.74985754985755,
|
| 78365 |
+
"grad_norm": 0.20925697684288025,
|
| 78366 |
+
"learning_rate": 1.5629651497820365e-05,
|
| 78367 |
+
"loss": 0.6595,
|
| 78368 |
+
"step": 11194
|
| 78369 |
+
},
|
| 78370 |
+
{
|
| 78371 |
+
"epoch": 12.75099715099715,
|
| 78372 |
+
"grad_norm": 0.24728427827358246,
|
| 78373 |
+
"learning_rate": 1.5625332133494935e-05,
|
| 78374 |
+
"loss": 0.5493,
|
| 78375 |
+
"step": 11195
|
| 78376 |
+
},
|
| 78377 |
+
{
|
| 78378 |
+
"epoch": 12.752136752136753,
|
| 78379 |
+
"grad_norm": 0.2341899275779724,
|
| 78380 |
+
"learning_rate": 1.562101309477751e-05,
|
| 78381 |
+
"loss": 0.6311,
|
| 78382 |
+
"step": 11196
|
| 78383 |
+
},
|
| 78384 |
+
{
|
| 78385 |
+
"epoch": 12.753276353276354,
|
| 78386 |
+
"grad_norm": 0.20414113998413086,
|
| 78387 |
+
"learning_rate": 1.561669438181808e-05,
|
| 78388 |
+
"loss": 0.6863,
|
| 78389 |
+
"step": 11197
|
| 78390 |
+
},
|
| 78391 |
+
{
|
| 78392 |
+
"epoch": 12.754415954415954,
|
| 78393 |
+
"grad_norm": 0.21995875239372253,
|
| 78394 |
+
"learning_rate": 1.561237599476667e-05,
|
| 78395 |
+
"loss": 0.8367,
|
| 78396 |
+
"step": 11198
|
| 78397 |
+
},
|
| 78398 |
+
{
|
| 78399 |
+
"epoch": 12.755555555555556,
|
| 78400 |
+
"grad_norm": 0.1657383143901825,
|
| 78401 |
+
"learning_rate": 1.5608057933773247e-05,
|
| 78402 |
+
"loss": 0.727,
|
| 78403 |
+
"step": 11199
|
| 78404 |
+
},
|
| 78405 |
+
{
|
| 78406 |
+
"epoch": 12.756695156695157,
|
| 78407 |
+
"grad_norm": 0.23210634291172028,
|
| 78408 |
+
"learning_rate": 1.560374019898781e-05,
|
| 78409 |
+
"loss": 0.6924,
|
| 78410 |
+
"step": 11200
|
| 78411 |
+
},
|
| 78412 |
+
{
|
| 78413 |
+
"epoch": 12.757834757834758,
|
| 78414 |
+
"grad_norm": 0.19804133474826813,
|
| 78415 |
+
"learning_rate": 1.5599422790560307e-05,
|
| 78416 |
+
"loss": 0.7299,
|
| 78417 |
+
"step": 11201
|
| 78418 |
+
},
|
| 78419 |
+
{
|
| 78420 |
+
"epoch": 12.75897435897436,
|
| 78421 |
+
"grad_norm": 0.268680602312088,
|
| 78422 |
+
"learning_rate": 1.559510570864071e-05,
|
| 78423 |
+
"loss": 0.4928,
|
| 78424 |
+
"step": 11202
|
| 78425 |
+
},
|
| 78426 |
+
{
|
| 78427 |
+
"epoch": 12.76011396011396,
|
| 78428 |
+
"grad_norm": 0.21380242705345154,
|
| 78429 |
+
"learning_rate": 1.5590788953378947e-05,
|
| 78430 |
+
"loss": 0.5975,
|
| 78431 |
+
"step": 11203
|
| 78432 |
+
},
|
| 78433 |
+
{
|
| 78434 |
+
"epoch": 12.761253561253561,
|
| 78435 |
+
"grad_norm": 0.24435050785541534,
|
| 78436 |
+
"learning_rate": 1.5586472524924956e-05,
|
| 78437 |
+
"loss": 0.6826,
|
| 78438 |
+
"step": 11204
|
| 78439 |
+
},
|
| 78440 |
+
{
|
| 78441 |
+
"epoch": 12.762393162393163,
|
| 78442 |
+
"grad_norm": 0.2538256347179413,
|
| 78443 |
+
"learning_rate": 1.5582156423428675e-05,
|
| 78444 |
+
"loss": 0.5048,
|
| 78445 |
+
"step": 11205
|
| 78446 |
+
},
|
| 78447 |
+
{
|
| 78448 |
+
"epoch": 12.763532763532764,
|
| 78449 |
+
"grad_norm": 0.2266242355108261,
|
| 78450 |
+
"learning_rate": 1.557784064903999e-05,
|
| 78451 |
+
"loss": 0.6112,
|
| 78452 |
+
"step": 11206
|
| 78453 |
+
},
|
| 78454 |
+
{
|
| 78455 |
+
"epoch": 12.764672364672364,
|
| 78456 |
+
"grad_norm": 0.22259734570980072,
|
| 78457 |
+
"learning_rate": 1.5573525201908817e-05,
|
| 78458 |
+
"loss": 0.7573,
|
| 78459 |
+
"step": 11207
|
| 78460 |
+
},
|
| 78461 |
+
{
|
| 78462 |
+
"epoch": 12.765811965811967,
|
| 78463 |
+
"grad_norm": 0.24566206336021423,
|
| 78464 |
+
"learning_rate": 1.5569210082185033e-05,
|
| 78465 |
+
"loss": 0.7427,
|
| 78466 |
+
"step": 11208
|
| 78467 |
+
},
|
| 78468 |
+
{
|
| 78469 |
+
"epoch": 12.766951566951567,
|
| 78470 |
+
"grad_norm": 0.18628554046154022,
|
| 78471 |
+
"learning_rate": 1.556489529001852e-05,
|
| 78472 |
+
"loss": 0.8772,
|
| 78473 |
+
"step": 11209
|
| 78474 |
+
},
|
| 78475 |
+
{
|
| 78476 |
+
"epoch": 12.768091168091168,
|
| 78477 |
+
"grad_norm": 0.2506822645664215,
|
| 78478 |
+
"learning_rate": 1.5560580825559137e-05,
|
| 78479 |
+
"loss": 0.6094,
|
| 78480 |
+
"step": 11210
|
| 78481 |
+
},
|
| 78482 |
+
{
|
| 78483 |
+
"epoch": 12.76923076923077,
|
| 78484 |
+
"grad_norm": 0.18677690625190735,
|
| 78485 |
+
"learning_rate": 1.5556266688956744e-05,
|
| 78486 |
+
"loss": 0.6967,
|
| 78487 |
+
"step": 11211
|
| 78488 |
+
},
|
| 78489 |
+
{
|
| 78490 |
+
"epoch": 12.77037037037037,
|
| 78491 |
+
"grad_norm": 0.15620164573192596,
|
| 78492 |
+
"learning_rate": 1.5551952880361175e-05,
|
| 78493 |
+
"loss": 0.7795,
|
| 78494 |
+
"step": 11212
|
| 78495 |
+
},
|
| 78496 |
+
{
|
| 78497 |
+
"epoch": 12.771509971509971,
|
| 78498 |
+
"grad_norm": 0.21999280154705048,
|
| 78499 |
+
"learning_rate": 1.5547639399922273e-05,
|
| 78500 |
+
"loss": 0.4862,
|
| 78501 |
+
"step": 11213
|
| 78502 |
+
},
|
| 78503 |
+
{
|
| 78504 |
+
"epoch": 12.772649572649573,
|
| 78505 |
+
"grad_norm": 0.20681433379650116,
|
| 78506 |
+
"learning_rate": 1.554332624778984e-05,
|
| 78507 |
+
"loss": 0.5806,
|
| 78508 |
+
"step": 11214
|
| 78509 |
+
},
|
| 78510 |
+
{
|
| 78511 |
+
"epoch": 12.773789173789174,
|
| 78512 |
+
"grad_norm": 0.18957693874835968,
|
| 78513 |
+
"learning_rate": 1.5539013424113686e-05,
|
| 78514 |
+
"loss": 0.7632,
|
| 78515 |
+
"step": 11215
|
| 78516 |
+
},
|
| 78517 |
+
{
|
| 78518 |
+
"epoch": 12.774928774928775,
|
| 78519 |
+
"grad_norm": 0.19347313046455383,
|
| 78520 |
+
"learning_rate": 1.5534700929043628e-05,
|
| 78521 |
+
"loss": 0.7254,
|
| 78522 |
+
"step": 11216
|
| 78523 |
+
},
|
| 78524 |
+
{
|
| 78525 |
+
"epoch": 12.776068376068377,
|
| 78526 |
+
"grad_norm": 0.21261726319789886,
|
| 78527 |
+
"learning_rate": 1.5530388762729432e-05,
|
| 78528 |
+
"loss": 0.6183,
|
| 78529 |
+
"step": 11217
|
| 78530 |
+
},
|
| 78531 |
+
{
|
| 78532 |
+
"epoch": 12.777207977207977,
|
| 78533 |
+
"grad_norm": 0.2281065732240677,
|
| 78534 |
+
"learning_rate": 1.5526076925320877e-05,
|
| 78535 |
+
"loss": 0.6127,
|
| 78536 |
+
"step": 11218
|
| 78537 |
+
},
|
| 78538 |
+
{
|
| 78539 |
+
"epoch": 12.778347578347578,
|
| 78540 |
+
"grad_norm": 0.2227533459663391,
|
| 78541 |
+
"learning_rate": 1.552176541696772e-05,
|
| 78542 |
+
"loss": 0.7665,
|
| 78543 |
+
"step": 11219
|
| 78544 |
+
},
|
| 78545 |
+
{
|
| 78546 |
+
"epoch": 12.77948717948718,
|
| 78547 |
+
"grad_norm": 0.21940748393535614,
|
| 78548 |
+
"learning_rate": 1.551745423781972e-05,
|
| 78549 |
+
"loss": 0.6665,
|
| 78550 |
+
"step": 11220
|
| 78551 |
+
},
|
| 78552 |
+
{
|
| 78553 |
+
"epoch": 12.78062678062678,
|
| 78554 |
+
"grad_norm": 0.22539184987545013,
|
| 78555 |
+
"learning_rate": 1.5513143388026606e-05,
|
| 78556 |
+
"loss": 0.5846,
|
| 78557 |
+
"step": 11221
|
| 78558 |
+
},
|
| 78559 |
+
{
|
| 78560 |
+
"epoch": 12.781766381766381,
|
| 78561 |
+
"grad_norm": 0.2524380683898926,
|
| 78562 |
+
"learning_rate": 1.5508832867738116e-05,
|
| 78563 |
+
"loss": 0.5339,
|
| 78564 |
+
"step": 11222
|
| 78565 |
+
},
|
| 78566 |
+
{
|
| 78567 |
+
"epoch": 12.782905982905984,
|
| 78568 |
+
"grad_norm": 0.1836635023355484,
|
| 78569 |
+
"learning_rate": 1.550452267710396e-05,
|
| 78570 |
+
"loss": 0.7841,
|
| 78571 |
+
"step": 11223
|
| 78572 |
+
},
|
| 78573 |
+
{
|
| 78574 |
+
"epoch": 12.784045584045584,
|
| 78575 |
+
"grad_norm": 0.16528676450252533,
|
| 78576 |
+
"learning_rate": 1.5500212816273844e-05,
|
| 78577 |
+
"loss": 0.7765,
|
| 78578 |
+
"step": 11224
|
| 78579 |
+
},
|
| 78580 |
+
{
|
| 78581 |
+
"epoch": 12.785185185185185,
|
| 78582 |
+
"grad_norm": 0.1646662801504135,
|
| 78583 |
+
"learning_rate": 1.549590328539746e-05,
|
| 78584 |
+
"loss": 0.7165,
|
| 78585 |
+
"step": 11225
|
| 78586 |
+
},
|
| 78587 |
+
{
|
| 78588 |
+
"epoch": 12.786324786324787,
|
| 78589 |
+
"grad_norm": 0.16733065247535706,
|
| 78590 |
+
"learning_rate": 1.5491594084624483e-05,
|
| 78591 |
+
"loss": 0.7258,
|
| 78592 |
+
"step": 11226
|
| 78593 |
+
},
|
| 78594 |
+
{
|
| 78595 |
+
"epoch": 12.787464387464388,
|
| 78596 |
+
"grad_norm": 0.21924377977848053,
|
| 78597 |
+
"learning_rate": 1.5487285214104595e-05,
|
| 78598 |
+
"loss": 0.794,
|
| 78599 |
+
"step": 11227
|
| 78600 |
+
},
|
| 78601 |
+
{
|
| 78602 |
+
"epoch": 12.788603988603988,
|
| 78603 |
+
"grad_norm": 0.19709335267543793,
|
| 78604 |
+
"learning_rate": 1.5482976673987465e-05,
|
| 78605 |
+
"loss": 0.5388,
|
| 78606 |
+
"step": 11228
|
| 78607 |
+
},
|
| 78608 |
+
{
|
| 78609 |
+
"epoch": 12.78974358974359,
|
| 78610 |
+
"grad_norm": 0.21844550967216492,
|
| 78611 |
+
"learning_rate": 1.5478668464422717e-05,
|
| 78612 |
+
"loss": 0.8007,
|
| 78613 |
+
"step": 11229
|
| 78614 |
+
},
|
| 78615 |
+
{
|
| 78616 |
+
"epoch": 12.790883190883191,
|
| 78617 |
+
"grad_norm": 0.19894273579120636,
|
| 78618 |
+
"learning_rate": 1.5474360585559998e-05,
|
| 78619 |
+
"loss": 0.675,
|
| 78620 |
+
"step": 11230
|
| 78621 |
+
},
|
| 78622 |
+
{
|
| 78623 |
+
"epoch": 12.792022792022792,
|
| 78624 |
+
"grad_norm": 0.2822384536266327,
|
| 78625 |
+
"learning_rate": 1.547005303754893e-05,
|
| 78626 |
+
"loss": 0.4806,
|
| 78627 |
+
"step": 11231
|
| 78628 |
+
},
|
| 78629 |
+
{
|
| 78630 |
+
"epoch": 12.793162393162394,
|
| 78631 |
+
"grad_norm": 0.27862998843193054,
|
| 78632 |
+
"learning_rate": 1.5465745820539135e-05,
|
| 78633 |
+
"loss": 0.5472,
|
| 78634 |
+
"step": 11232
|
| 78635 |
+
},
|
| 78636 |
+
{
|
| 78637 |
+
"epoch": 12.794301994301994,
|
| 78638 |
+
"grad_norm": 0.21956251561641693,
|
| 78639 |
+
"learning_rate": 1.54614389346802e-05,
|
| 78640 |
+
"loss": 0.5191,
|
| 78641 |
+
"step": 11233
|
| 78642 |
+
},
|
| 78643 |
+
{
|
| 78644 |
+
"epoch": 12.795441595441595,
|
| 78645 |
+
"grad_norm": 0.19542093575000763,
|
| 78646 |
+
"learning_rate": 1.5457132380121728e-05,
|
| 78647 |
+
"loss": 0.7289,
|
| 78648 |
+
"step": 11234
|
| 78649 |
+
},
|
| 78650 |
+
{
|
| 78651 |
+
"epoch": 12.796581196581197,
|
| 78652 |
+
"grad_norm": 0.24643944203853607,
|
| 78653 |
+
"learning_rate": 1.5452826157013284e-05,
|
| 78654 |
+
"loss": 0.6039,
|
| 78655 |
+
"step": 11235
|
| 78656 |
+
},
|
| 78657 |
+
{
|
| 78658 |
+
"epoch": 12.797720797720798,
|
| 78659 |
+
"grad_norm": 0.2070317417383194,
|
| 78660 |
+
"learning_rate": 1.544852026550445e-05,
|
| 78661 |
+
"loss": 0.581,
|
| 78662 |
+
"step": 11236
|
| 78663 |
+
},
|
| 78664 |
+
{
|
| 78665 |
+
"epoch": 12.798860398860398,
|
| 78666 |
+
"grad_norm": 0.18230903148651123,
|
| 78667 |
+
"learning_rate": 1.5444214705744764e-05,
|
| 78668 |
+
"loss": 0.7172,
|
| 78669 |
+
"step": 11237
|
| 78670 |
+
},
|
| 78671 |
+
{
|
| 78672 |
+
"epoch": 12.8,
|
| 78673 |
+
"grad_norm": 0.2501848042011261,
|
| 78674 |
+
"learning_rate": 1.5439909477883784e-05,
|
| 78675 |
+
"loss": 0.643,
|
| 78676 |
+
"step": 11238
|
| 78677 |
+
},
|
| 78678 |
+
{
|
| 78679 |
+
"epoch": 12.801139601139601,
|
| 78680 |
+
"grad_norm": 0.23969808220863342,
|
| 78681 |
+
"learning_rate": 1.543560458207104e-05,
|
| 78682 |
+
"loss": 0.674,
|
| 78683 |
+
"step": 11239
|
| 78684 |
+
},
|
| 78685 |
+
{
|
| 78686 |
+
"epoch": 12.802279202279202,
|
| 78687 |
+
"grad_norm": 0.24644148349761963,
|
| 78688 |
+
"learning_rate": 1.5431300018456047e-05,
|
| 78689 |
+
"loss": 0.465,
|
| 78690 |
+
"step": 11240
|
| 78691 |
+
},
|
| 78692 |
+
{
|
| 78693 |
+
"epoch": 12.803418803418804,
|
| 78694 |
+
"grad_norm": 0.2110668420791626,
|
| 78695 |
+
"learning_rate": 1.5426995787188324e-05,
|
| 78696 |
+
"loss": 0.5697,
|
| 78697 |
+
"step": 11241
|
| 78698 |
+
},
|
| 78699 |
+
{
|
| 78700 |
+
"epoch": 12.804558404558405,
|
| 78701 |
+
"grad_norm": 0.1825806349515915,
|
| 78702 |
+
"learning_rate": 1.5422691888417364e-05,
|
| 78703 |
+
"loss": 0.7538,
|
| 78704 |
+
"step": 11242
|
| 78705 |
+
},
|
| 78706 |
+
{
|
| 78707 |
+
"epoch": 12.805698005698005,
|
| 78708 |
+
"grad_norm": 0.24073870480060577,
|
| 78709 |
+
"learning_rate": 1.541838832229265e-05,
|
| 78710 |
+
"loss": 0.612,
|
| 78711 |
+
"step": 11243
|
| 78712 |
+
},
|
| 78713 |
+
{
|
| 78714 |
+
"epoch": 12.806837606837608,
|
| 78715 |
+
"grad_norm": 0.19120050966739655,
|
| 78716 |
+
"learning_rate": 1.5414085088963658e-05,
|
| 78717 |
+
"loss": 0.638,
|
| 78718 |
+
"step": 11244
|
| 78719 |
+
},
|
| 78720 |
+
{
|
| 78721 |
+
"epoch": 12.807977207977208,
|
| 78722 |
+
"grad_norm": 0.23519383370876312,
|
| 78723 |
+
"learning_rate": 1.5409782188579855e-05,
|
| 78724 |
+
"loss": 0.5826,
|
| 78725 |
+
"step": 11245
|
| 78726 |
+
},
|
| 78727 |
+
{
|
| 78728 |
+
"epoch": 12.809116809116809,
|
| 78729 |
+
"grad_norm": 0.31809619069099426,
|
| 78730 |
+
"learning_rate": 1.5405479621290687e-05,
|
| 78731 |
+
"loss": 0.3012,
|
| 78732 |
+
"step": 11246
|
| 78733 |
+
},
|
| 78734 |
+
{
|
| 78735 |
+
"epoch": 12.810256410256411,
|
| 78736 |
+
"grad_norm": 0.21087875962257385,
|
| 78737 |
+
"learning_rate": 1.54011773872456e-05,
|
| 78738 |
+
"loss": 0.7106,
|
| 78739 |
+
"step": 11247
|
| 78740 |
+
},
|
| 78741 |
+
{
|
| 78742 |
+
"epoch": 12.811396011396011,
|
| 78743 |
+
"grad_norm": 0.2201055884361267,
|
| 78744 |
+
"learning_rate": 1.5396875486594007e-05,
|
| 78745 |
+
"loss": 0.6285,
|
| 78746 |
+
"step": 11248
|
| 78747 |
+
},
|
| 78748 |
+
{
|
| 78749 |
+
"epoch": 12.812535612535612,
|
| 78750 |
+
"grad_norm": 0.18184322118759155,
|
| 78751 |
+
"learning_rate": 1.539257391948535e-05,
|
| 78752 |
+
"loss": 0.778,
|
| 78753 |
+
"step": 11249
|
| 78754 |
+
},
|
| 78755 |
+
{
|
| 78756 |
+
"epoch": 12.813675213675214,
|
| 78757 |
+
"grad_norm": 0.21316279470920563,
|
| 78758 |
+
"learning_rate": 1.5388272686069016e-05,
|
| 78759 |
+
"loss": 0.7233,
|
| 78760 |
+
"step": 11250
|
| 78761 |
+
},
|
| 78762 |
+
{
|
| 78763 |
+
"epoch": 12.814814814814815,
|
| 78764 |
+
"grad_norm": 0.21728692948818207,
|
| 78765 |
+
"learning_rate": 1.5383971786494406e-05,
|
| 78766 |
+
"loss": 0.6832,
|
| 78767 |
+
"step": 11251
|
| 78768 |
+
},
|
| 78769 |
+
{
|
| 78770 |
+
"epoch": 12.815954415954415,
|
| 78771 |
+
"grad_norm": 0.2114868015050888,
|
| 78772 |
+
"learning_rate": 1.53796712209109e-05,
|
| 78773 |
+
"loss": 0.6524,
|
| 78774 |
+
"step": 11252
|
| 78775 |
+
},
|
| 78776 |
+
{
|
| 78777 |
+
"epoch": 12.817094017094018,
|
| 78778 |
+
"grad_norm": 0.2465014010667801,
|
| 78779 |
+
"learning_rate": 1.537537098946787e-05,
|
| 78780 |
+
"loss": 0.8676,
|
| 78781 |
+
"step": 11253
|
| 78782 |
+
},
|
| 78783 |
+
{
|
| 78784 |
+
"epoch": 12.818233618233618,
|
| 78785 |
+
"grad_norm": 0.2124163955450058,
|
| 78786 |
+
"learning_rate": 1.5371071092314672e-05,
|
| 78787 |
+
"loss": 0.7978,
|
| 78788 |
+
"step": 11254
|
| 78789 |
+
},
|
| 78790 |
+
{
|
| 78791 |
+
"epoch": 12.819373219373219,
|
| 78792 |
+
"grad_norm": 0.19976741075515747,
|
| 78793 |
+
"learning_rate": 1.5366771529600653e-05,
|
| 78794 |
+
"loss": 0.7583,
|
| 78795 |
+
"step": 11255
|
| 78796 |
+
},
|
| 78797 |
+
{
|
| 78798 |
+
"epoch": 12.820512820512821,
|
| 78799 |
+
"grad_norm": 0.19268165528774261,
|
| 78800 |
+
"learning_rate": 1.5362472301475158e-05,
|
| 78801 |
+
"loss": 0.8674,
|
| 78802 |
+
"step": 11256
|
| 78803 |
+
},
|
| 78804 |
+
{
|
| 78805 |
+
"epoch": 12.821652421652422,
|
| 78806 |
+
"grad_norm": 0.19234377145767212,
|
| 78807 |
+
"learning_rate": 1.5358173408087495e-05,
|
| 78808 |
+
"loss": 0.6675,
|
| 78809 |
+
"step": 11257
|
| 78810 |
+
},
|
| 78811 |
+
{
|
| 78812 |
+
"epoch": 12.822792022792022,
|
| 78813 |
+
"grad_norm": 0.21339838206768036,
|
| 78814 |
+
"learning_rate": 1.535387484958699e-05,
|
| 78815 |
+
"loss": 0.6563,
|
| 78816 |
+
"step": 11258
|
| 78817 |
+
},
|
| 78818 |
+
{
|
| 78819 |
+
"epoch": 12.823931623931625,
|
| 78820 |
+
"grad_norm": 0.24457897245883942,
|
| 78821 |
+
"learning_rate": 1.5349576626122923e-05,
|
| 78822 |
+
"loss": 0.6577,
|
| 78823 |
+
"step": 11259
|
| 78824 |
+
},
|
| 78825 |
+
{
|
| 78826 |
+
"epoch": 12.825071225071225,
|
| 78827 |
+
"grad_norm": 0.27925947308540344,
|
| 78828 |
+
"learning_rate": 1.5345278737844614e-05,
|
| 78829 |
+
"loss": 0.5595,
|
| 78830 |
+
"step": 11260
|
| 78831 |
+
},
|
| 78832 |
+
{
|
| 78833 |
+
"epoch": 12.826210826210826,
|
| 78834 |
+
"grad_norm": 0.1818474531173706,
|
| 78835 |
+
"learning_rate": 1.534098118490132e-05,
|
| 78836 |
+
"loss": 0.6588,
|
| 78837 |
+
"step": 11261
|
| 78838 |
+
},
|
| 78839 |
+
{
|
| 78840 |
+
"epoch": 12.827350427350428,
|
| 78841 |
+
"grad_norm": 0.16830523312091827,
|
| 78842 |
+
"learning_rate": 1.5336683967442315e-05,
|
| 78843 |
+
"loss": 0.9107,
|
| 78844 |
+
"step": 11262
|
| 78845 |
+
},
|
| 78846 |
+
{
|
| 78847 |
+
"epoch": 12.828490028490029,
|
| 78848 |
+
"grad_norm": 0.18106761574745178,
|
| 78849 |
+
"learning_rate": 1.533238708561685e-05,
|
| 78850 |
+
"loss": 0.7089,
|
| 78851 |
+
"step": 11263
|
| 78852 |
+
},
|
| 78853 |
+
{
|
| 78854 |
+
"epoch": 12.829629629629629,
|
| 78855 |
+
"grad_norm": 0.16657721996307373,
|
| 78856 |
+
"learning_rate": 1.5328090539574162e-05,
|
| 78857 |
+
"loss": 0.7726,
|
| 78858 |
+
"step": 11264
|
| 78859 |
+
},
|
| 78860 |
+
{
|
| 78861 |
+
"epoch": 12.830769230769231,
|
| 78862 |
+
"grad_norm": 0.21090742945671082,
|
| 78863 |
+
"learning_rate": 1.532379432946349e-05,
|
| 78864 |
+
"loss": 0.6567,
|
| 78865 |
+
"step": 11265
|
| 78866 |
+
},
|
| 78867 |
+
{
|
| 78868 |
+
"epoch": 12.831908831908832,
|
| 78869 |
+
"grad_norm": 0.25384172797203064,
|
| 78870 |
+
"learning_rate": 1.5319498455434057e-05,
|
| 78871 |
+
"loss": 0.4562,
|
| 78872 |
+
"step": 11266
|
| 78873 |
+
},
|
| 78874 |
+
{
|
| 78875 |
+
"epoch": 12.833048433048432,
|
| 78876 |
+
"grad_norm": 0.20707079768180847,
|
| 78877 |
+
"learning_rate": 1.531520291763506e-05,
|
| 78878 |
+
"loss": 0.8442,
|
| 78879 |
+
"step": 11267
|
| 78880 |
+
},
|
| 78881 |
+
{
|
| 78882 |
+
"epoch": 12.834188034188035,
|
| 78883 |
+
"grad_norm": 0.20802339911460876,
|
| 78884 |
+
"learning_rate": 1.53109077162157e-05,
|
| 78885 |
+
"loss": 0.6555,
|
| 78886 |
+
"step": 11268
|
| 78887 |
+
},
|
| 78888 |
+
{
|
| 78889 |
+
"epoch": 12.835327635327635,
|
| 78890 |
+
"grad_norm": 0.21156306564807892,
|
| 78891 |
+
"learning_rate": 1.5306612851325154e-05,
|
| 78892 |
+
"loss": 0.6527,
|
| 78893 |
+
"step": 11269
|
| 78894 |
+
},
|
| 78895 |
+
{
|
| 78896 |
+
"epoch": 12.836467236467236,
|
| 78897 |
+
"grad_norm": 2.3743772506713867,
|
| 78898 |
+
"learning_rate": 1.5302318323112607e-05,
|
| 78899 |
+
"loss": 0.4502,
|
| 78900 |
+
"step": 11270
|
| 78901 |
+
},
|
| 78902 |
+
{
|
| 78903 |
+
"epoch": 12.837606837606838,
|
| 78904 |
+
"grad_norm": 0.25030121207237244,
|
| 78905 |
+
"learning_rate": 1.5298024131727207e-05,
|
| 78906 |
+
"loss": 0.5459,
|
| 78907 |
+
"step": 11271
|
| 78908 |
+
},
|
| 78909 |
+
{
|
| 78910 |
+
"epoch": 12.838746438746439,
|
| 78911 |
+
"grad_norm": 0.20316855609416962,
|
| 78912 |
+
"learning_rate": 1.529373027731811e-05,
|
| 78913 |
+
"loss": 0.8273,
|
| 78914 |
+
"step": 11272
|
| 78915 |
+
},
|
| 78916 |
+
{
|
| 78917 |
+
"epoch": 12.83988603988604,
|
| 78918 |
+
"grad_norm": 0.18483185768127441,
|
| 78919 |
+
"learning_rate": 1.528943676003446e-05,
|
| 78920 |
+
"loss": 0.8948,
|
| 78921 |
+
"step": 11273
|
| 78922 |
+
},
|
| 78923 |
+
{
|
| 78924 |
+
"epoch": 12.841025641025642,
|
| 78925 |
+
"grad_norm": 0.23908449709415436,
|
| 78926 |
+
"learning_rate": 1.528514358002537e-05,
|
| 78927 |
+
"loss": 0.7057,
|
| 78928 |
+
"step": 11274
|
| 78929 |
+
},
|
| 78930 |
+
{
|
| 78931 |
+
"epoch": 12.842165242165242,
|
| 78932 |
+
"grad_norm": 0.20082879066467285,
|
| 78933 |
+
"learning_rate": 1.5280850737439967e-05,
|
| 78934 |
+
"loss": 0.7533,
|
| 78935 |
+
"step": 11275
|
| 78936 |
+
},
|
| 78937 |
+
{
|
| 78938 |
+
"epoch": 12.843304843304843,
|
| 78939 |
+
"grad_norm": 0.20539212226867676,
|
| 78940 |
+
"learning_rate": 1.5276558232427335e-05,
|
| 78941 |
+
"loss": 0.7364,
|
| 78942 |
+
"step": 11276
|
| 78943 |
+
},
|
| 78944 |
+
{
|
| 78945 |
+
"epoch": 12.844444444444445,
|
| 78946 |
+
"grad_norm": 0.23212577402591705,
|
| 78947 |
+
"learning_rate": 1.5272266065136583e-05,
|
| 78948 |
+
"loss": 0.6454,
|
| 78949 |
+
"step": 11277
|
| 78950 |
+
},
|
| 78951 |
+
{
|
| 78952 |
+
"epoch": 12.845584045584046,
|
| 78953 |
+
"grad_norm": 0.21794946491718292,
|
| 78954 |
+
"learning_rate": 1.526797423571678e-05,
|
| 78955 |
+
"loss": 0.7836,
|
| 78956 |
+
"step": 11278
|
| 78957 |
+
},
|
| 78958 |
+
{
|
| 78959 |
+
"epoch": 12.846723646723646,
|
| 78960 |
+
"grad_norm": 0.23278498649597168,
|
| 78961 |
+
"learning_rate": 1.5263682744316997e-05,
|
| 78962 |
+
"loss": 0.4949,
|
| 78963 |
+
"step": 11279
|
| 78964 |
+
},
|
| 78965 |
+
{
|
| 78966 |
+
"epoch": 12.847863247863248,
|
| 78967 |
+
"grad_norm": 0.19228476285934448,
|
| 78968 |
+
"learning_rate": 1.525939159108628e-05,
|
| 78969 |
+
"loss": 0.8375,
|
| 78970 |
+
"step": 11280
|
| 78971 |
+
},
|
| 78972 |
+
{
|
| 78973 |
+
"epoch": 12.849002849002849,
|
| 78974 |
+
"grad_norm": 0.1980063021183014,
|
| 78975 |
+
"learning_rate": 1.5255100776173688e-05,
|
| 78976 |
+
"loss": 0.7407,
|
| 78977 |
+
"step": 11281
|
| 78978 |
+
},
|
| 78979 |
+
{
|
| 78980 |
+
"epoch": 12.85014245014245,
|
| 78981 |
+
"grad_norm": 0.21237735450267792,
|
| 78982 |
+
"learning_rate": 1.5250810299728235e-05,
|
| 78983 |
+
"loss": 0.5179,
|
| 78984 |
+
"step": 11282
|
| 78985 |
+
},
|
| 78986 |
+
{
|
| 78987 |
+
"epoch": 12.851282051282052,
|
| 78988 |
+
"grad_norm": 0.25003233551979065,
|
| 78989 |
+
"learning_rate": 1.5246520161898952e-05,
|
| 78990 |
+
"loss": 0.6853,
|
| 78991 |
+
"step": 11283
|
| 78992 |
+
},
|
| 78993 |
+
{
|
| 78994 |
+
"epoch": 12.852421652421652,
|
| 78995 |
+
"grad_norm": 0.2409413456916809,
|
| 78996 |
+
"learning_rate": 1.5242230362834855e-05,
|
| 78997 |
+
"loss": 0.6818,
|
| 78998 |
+
"step": 11284
|
| 78999 |
+
},
|
| 79000 |
+
{
|
| 79001 |
+
"epoch": 12.853561253561253,
|
| 79002 |
+
"grad_norm": 0.23972086608409882,
|
| 79003 |
+
"learning_rate": 1.5237940902684924e-05,
|
| 79004 |
+
"loss": 0.5063,
|
| 79005 |
+
"step": 11285
|
| 79006 |
+
},
|
| 79007 |
+
{
|
| 79008 |
+
"epoch": 12.854700854700855,
|
| 79009 |
+
"grad_norm": 0.2771264910697937,
|
| 79010 |
+
"learning_rate": 1.5233651781598157e-05,
|
| 79011 |
+
"loss": 0.5091,
|
| 79012 |
+
"step": 11286
|
| 79013 |
+
},
|
| 79014 |
+
{
|
| 79015 |
+
"epoch": 12.855840455840456,
|
| 79016 |
+
"grad_norm": 0.23623840510845184,
|
| 79017 |
+
"learning_rate": 1.5229362999723517e-05,
|
| 79018 |
+
"loss": 0.7786,
|
| 79019 |
+
"step": 11287
|
| 79020 |
+
},
|
| 79021 |
+
{
|
| 79022 |
+
"epoch": 12.856980056980056,
|
| 79023 |
+
"grad_norm": 0.23032218217849731,
|
| 79024 |
+
"learning_rate": 1.5225074557209974e-05,
|
| 79025 |
+
"loss": 0.5387,
|
| 79026 |
+
"step": 11288
|
| 79027 |
+
},
|
| 79028 |
+
{
|
| 79029 |
+
"epoch": 12.858119658119659,
|
| 79030 |
+
"grad_norm": 0.26485055685043335,
|
| 79031 |
+
"learning_rate": 1.5220786454206468e-05,
|
| 79032 |
+
"loss": 0.5621,
|
| 79033 |
+
"step": 11289
|
| 79034 |
+
},
|
| 79035 |
+
{
|
| 79036 |
+
"epoch": 12.85925925925926,
|
| 79037 |
+
"grad_norm": 0.21657170355319977,
|
| 79038 |
+
"learning_rate": 1.5216498690861946e-05,
|
| 79039 |
+
"loss": 0.6269,
|
| 79040 |
+
"step": 11290
|
| 79041 |
+
},
|
| 79042 |
+
{
|
| 79043 |
+
"epoch": 12.86039886039886,
|
| 79044 |
+
"grad_norm": 0.367741197347641,
|
| 79045 |
+
"learning_rate": 1.5212211267325324e-05,
|
| 79046 |
+
"loss": 0.3114,
|
| 79047 |
+
"step": 11291
|
| 79048 |
+
},
|
| 79049 |
+
{
|
| 79050 |
+
"epoch": 12.861538461538462,
|
| 79051 |
+
"grad_norm": 0.24216917157173157,
|
| 79052 |
+
"learning_rate": 1.5207924183745525e-05,
|
| 79053 |
+
"loss": 0.57,
|
| 79054 |
+
"step": 11292
|
| 79055 |
+
},
|
| 79056 |
+
{
|
| 79057 |
+
"epoch": 12.862678062678063,
|
| 79058 |
+
"grad_norm": 0.24328188598155975,
|
| 79059 |
+
"learning_rate": 1.520363744027144e-05,
|
| 79060 |
+
"loss": 0.7571,
|
| 79061 |
+
"step": 11293
|
| 79062 |
+
},
|
| 79063 |
+
{
|
| 79064 |
+
"epoch": 12.863817663817663,
|
| 79065 |
+
"grad_norm": 0.17762377858161926,
|
| 79066 |
+
"learning_rate": 1.519935103705197e-05,
|
| 79067 |
+
"loss": 0.7394,
|
| 79068 |
+
"step": 11294
|
| 79069 |
+
},
|
| 79070 |
+
{
|
| 79071 |
+
"epoch": 12.864957264957265,
|
| 79072 |
+
"grad_norm": 0.2241375893354416,
|
| 79073 |
+
"learning_rate": 1.5195064974235996e-05,
|
| 79074 |
+
"loss": 0.711,
|
| 79075 |
+
"step": 11295
|
| 79076 |
+
},
|
| 79077 |
+
{
|
| 79078 |
+
"epoch": 12.866096866096866,
|
| 79079 |
+
"grad_norm": 0.3043307363986969,
|
| 79080 |
+
"learning_rate": 1.5190779251972376e-05,
|
| 79081 |
+
"loss": 0.4974,
|
| 79082 |
+
"step": 11296
|
| 79083 |
+
},
|
| 79084 |
+
{
|
| 79085 |
+
"epoch": 12.867236467236467,
|
| 79086 |
+
"grad_norm": 0.21094325184822083,
|
| 79087 |
+
"learning_rate": 1.5186493870409968e-05,
|
| 79088 |
+
"loss": 0.6314,
|
| 79089 |
+
"step": 11297
|
| 79090 |
+
},
|
| 79091 |
+
{
|
| 79092 |
+
"epoch": 12.868376068376069,
|
| 79093 |
+
"grad_norm": 0.22727924585342407,
|
| 79094 |
+
"learning_rate": 1.5182208829697614e-05,
|
| 79095 |
+
"loss": 0.7082,
|
| 79096 |
+
"step": 11298
|
| 79097 |
+
},
|
| 79098 |
+
{
|
| 79099 |
+
"epoch": 12.86951566951567,
|
| 79100 |
+
"grad_norm": 0.17573437094688416,
|
| 79101 |
+
"learning_rate": 1.517792412998415e-05,
|
| 79102 |
+
"loss": 0.8817,
|
| 79103 |
+
"step": 11299
|
| 79104 |
+
},
|
| 79105 |
+
{
|
| 79106 |
+
"epoch": 12.87065527065527,
|
| 79107 |
+
"grad_norm": 0.2225823700428009,
|
| 79108 |
+
"learning_rate": 1.5173639771418389e-05,
|
| 79109 |
+
"loss": 0.8804,
|
| 79110 |
+
"step": 11300
|
| 79111 |
+
},
|
| 79112 |
+
{
|
| 79113 |
+
"epoch": 12.871794871794872,
|
| 79114 |
+
"grad_norm": 0.21569858491420746,
|
| 79115 |
+
"learning_rate": 1.5169355754149145e-05,
|
| 79116 |
+
"loss": 0.5543,
|
| 79117 |
+
"step": 11301
|
| 79118 |
+
},
|
| 79119 |
+
{
|
| 79120 |
+
"epoch": 12.872934472934473,
|
| 79121 |
+
"grad_norm": 0.19905759394168854,
|
| 79122 |
+
"learning_rate": 1.5165072078325204e-05,
|
| 79123 |
+
"loss": 0.8759,
|
| 79124 |
+
"step": 11302
|
| 79125 |
+
},
|
| 79126 |
+
{
|
| 79127 |
+
"epoch": 12.874074074074073,
|
| 79128 |
+
"grad_norm": 0.20556959509849548,
|
| 79129 |
+
"learning_rate": 1.5160788744095362e-05,
|
| 79130 |
+
"loss": 0.6941,
|
| 79131 |
+
"step": 11303
|
| 79132 |
+
},
|
| 79133 |
+
{
|
| 79134 |
+
"epoch": 12.875213675213676,
|
| 79135 |
+
"grad_norm": 0.19223438203334808,
|
| 79136 |
+
"learning_rate": 1.5156505751608369e-05,
|
| 79137 |
+
"loss": 0.7244,
|
| 79138 |
+
"step": 11304
|
| 79139 |
+
},
|
| 79140 |
+
{
|
| 79141 |
+
"epoch": 12.876353276353276,
|
| 79142 |
+
"grad_norm": 0.18705134093761444,
|
| 79143 |
+
"learning_rate": 1.5152223101013016e-05,
|
| 79144 |
+
"loss": 0.7124,
|
| 79145 |
+
"step": 11305
|
| 79146 |
+
},
|
| 79147 |
+
{
|
| 79148 |
+
"epoch": 12.877492877492877,
|
| 79149 |
+
"grad_norm": 0.19291657209396362,
|
| 79150 |
+
"learning_rate": 1.5147940792458032e-05,
|
| 79151 |
+
"loss": 0.7488,
|
| 79152 |
+
"step": 11306
|
| 79153 |
+
},
|
| 79154 |
+
{
|
| 79155 |
+
"epoch": 12.878632478632479,
|
| 79156 |
+
"grad_norm": 0.24266314506530762,
|
| 79157 |
+
"learning_rate": 1.514365882609216e-05,
|
| 79158 |
+
"loss": 0.5949,
|
| 79159 |
+
"step": 11307
|
| 79160 |
+
},
|
| 79161 |
+
{
|
| 79162 |
+
"epoch": 12.87977207977208,
|
| 79163 |
+
"grad_norm": 0.24872809648513794,
|
| 79164 |
+
"learning_rate": 1.513937720206412e-05,
|
| 79165 |
+
"loss": 0.649,
|
| 79166 |
+
"step": 11308
|
| 79167 |
+
},
|
| 79168 |
+
{
|
| 79169 |
+
"epoch": 12.88091168091168,
|
| 79170 |
+
"grad_norm": 0.22760015726089478,
|
| 79171 |
+
"learning_rate": 1.5135095920522632e-05,
|
| 79172 |
+
"loss": 0.6703,
|
| 79173 |
+
"step": 11309
|
| 79174 |
+
},
|
| 79175 |
+
{
|
| 79176 |
+
"epoch": 12.882051282051282,
|
| 79177 |
+
"grad_norm": 0.19884894788265228,
|
| 79178 |
+
"learning_rate": 1.5130814981616383e-05,
|
| 79179 |
+
"loss": 0.7886,
|
| 79180 |
+
"step": 11310
|
| 79181 |
+
},
|
| 79182 |
+
{
|
| 79183 |
+
"epoch": 12.883190883190883,
|
| 79184 |
+
"grad_norm": 0.25892016291618347,
|
| 79185 |
+
"learning_rate": 1.5126534385494079e-05,
|
| 79186 |
+
"loss": 0.7138,
|
| 79187 |
+
"step": 11311
|
| 79188 |
+
},
|
| 79189 |
+
{
|
| 79190 |
+
"epoch": 12.884330484330484,
|
| 79191 |
+
"grad_norm": 0.3058724105358124,
|
| 79192 |
+
"learning_rate": 1.5122254132304381e-05,
|
| 79193 |
+
"loss": 0.3287,
|
| 79194 |
+
"step": 11312
|
| 79195 |
+
},
|
| 79196 |
+
{
|
| 79197 |
+
"epoch": 12.885470085470086,
|
| 79198 |
+
"grad_norm": 0.2279716581106186,
|
| 79199 |
+
"learning_rate": 1.5117974222195965e-05,
|
| 79200 |
+
"loss": 0.6315,
|
| 79201 |
+
"step": 11313
|
| 79202 |
+
},
|
| 79203 |
+
{
|
| 79204 |
+
"epoch": 12.886609686609686,
|
| 79205 |
+
"grad_norm": 0.2113867700099945,
|
| 79206 |
+
"learning_rate": 1.5113694655317476e-05,
|
| 79207 |
+
"loss": 0.5906,
|
| 79208 |
+
"step": 11314
|
| 79209 |
+
},
|
| 79210 |
+
{
|
| 79211 |
+
"epoch": 12.887749287749287,
|
| 79212 |
+
"grad_norm": 0.2106524407863617,
|
| 79213 |
+
"learning_rate": 1.5109415431817553e-05,
|
| 79214 |
+
"loss": 0.5456,
|
| 79215 |
+
"step": 11315
|
| 79216 |
+
},
|
| 79217 |
+
{
|
| 79218 |
+
"epoch": 12.88888888888889,
|
| 79219 |
+
"grad_norm": 0.21508152782917023,
|
| 79220 |
+
"learning_rate": 1.5105136551844846e-05,
|
| 79221 |
+
"loss": 0.7473,
|
| 79222 |
+
"step": 11316
|
| 79223 |
+
},
|
| 79224 |
+
{
|
| 79225 |
+
"epoch": 12.89002849002849,
|
| 79226 |
+
"grad_norm": 0.22165998816490173,
|
| 79227 |
+
"learning_rate": 1.5100858015547947e-05,
|
| 79228 |
+
"loss": 0.5849,
|
| 79229 |
+
"step": 11317
|
| 79230 |
+
},
|
| 79231 |
+
{
|
| 79232 |
+
"epoch": 12.89116809116809,
|
| 79233 |
+
"grad_norm": 0.1639089435338974,
|
| 79234 |
+
"learning_rate": 1.5096579823075479e-05,
|
| 79235 |
+
"loss": 0.6897,
|
| 79236 |
+
"step": 11318
|
| 79237 |
+
},
|
| 79238 |
+
{
|
| 79239 |
+
"epoch": 12.892307692307693,
|
| 79240 |
+
"grad_norm": 0.17655792832374573,
|
| 79241 |
+
"learning_rate": 1.5092301974576023e-05,
|
| 79242 |
+
"loss": 0.9143,
|
| 79243 |
+
"step": 11319
|
| 79244 |
+
},
|
| 79245 |
+
{
|
| 79246 |
+
"epoch": 12.893447293447293,
|
| 79247 |
+
"grad_norm": 0.22830168902873993,
|
| 79248 |
+
"learning_rate": 1.508802447019817e-05,
|
| 79249 |
+
"loss": 0.6356,
|
| 79250 |
+
"step": 11320
|
| 79251 |
+
},
|
| 79252 |
+
{
|
| 79253 |
+
"epoch": 12.894586894586894,
|
| 79254 |
+
"grad_norm": 0.2639561891555786,
|
| 79255 |
+
"learning_rate": 1.508374731009048e-05,
|
| 79256 |
+
"loss": 0.6211,
|
| 79257 |
+
"step": 11321
|
| 79258 |
+
},
|
| 79259 |
+
{
|
| 79260 |
+
"epoch": 12.895726495726496,
|
| 79261 |
+
"grad_norm": 0.24511019885540009,
|
| 79262 |
+
"learning_rate": 1.507947049440152e-05,
|
| 79263 |
+
"loss": 0.5841,
|
| 79264 |
+
"step": 11322
|
| 79265 |
+
},
|
| 79266 |
+
{
|
| 79267 |
+
"epoch": 12.896866096866097,
|
| 79268 |
+
"grad_norm": 0.23563529551029205,
|
| 79269 |
+
"learning_rate": 1.507519402327983e-05,
|
| 79270 |
+
"loss": 0.5909,
|
| 79271 |
+
"step": 11323
|
| 79272 |
+
},
|
| 79273 |
+
{
|
| 79274 |
+
"epoch": 12.898005698005697,
|
| 79275 |
+
"grad_norm": 0.2009643316268921,
|
| 79276 |
+
"learning_rate": 1.5070917896873946e-05,
|
| 79277 |
+
"loss": 0.8266,
|
| 79278 |
+
"step": 11324
|
| 79279 |
+
},
|
| 79280 |
+
{
|
| 79281 |
+
"epoch": 12.8991452991453,
|
| 79282 |
+
"grad_norm": 0.15463519096374512,
|
| 79283 |
+
"learning_rate": 1.5066642115332386e-05,
|
| 79284 |
+
"loss": 0.8298,
|
| 79285 |
+
"step": 11325
|
| 79286 |
+
},
|
| 79287 |
+
{
|
| 79288 |
+
"epoch": 12.9002849002849,
|
| 79289 |
+
"grad_norm": 0.18611261248588562,
|
| 79290 |
+
"learning_rate": 1.5062366678803654e-05,
|
| 79291 |
+
"loss": 0.6996,
|
| 79292 |
+
"step": 11326
|
| 79293 |
+
},
|
| 79294 |
+
{
|
| 79295 |
+
"epoch": 12.9014245014245,
|
| 79296 |
+
"grad_norm": 0.19349269568920135,
|
| 79297 |
+
"learning_rate": 1.5058091587436268e-05,
|
| 79298 |
+
"loss": 0.7205,
|
| 79299 |
+
"step": 11327
|
| 79300 |
+
},
|
| 79301 |
+
{
|
| 79302 |
+
"epoch": 12.902564102564103,
|
| 79303 |
+
"grad_norm": 0.22040440142154694,
|
| 79304 |
+
"learning_rate": 1.5053816841378698e-05,
|
| 79305 |
+
"loss": 0.7988,
|
| 79306 |
+
"step": 11328
|
| 79307 |
+
},
|
| 79308 |
+
{
|
| 79309 |
+
"epoch": 12.903703703703703,
|
| 79310 |
+
"grad_norm": 0.23214900493621826,
|
| 79311 |
+
"learning_rate": 1.5049542440779424e-05,
|
| 79312 |
+
"loss": 0.732,
|
| 79313 |
+
"step": 11329
|
| 79314 |
+
},
|
| 79315 |
+
{
|
| 79316 |
+
"epoch": 12.904843304843304,
|
| 79317 |
+
"grad_norm": 0.2591022551059723,
|
| 79318 |
+
"learning_rate": 1.5045268385786904e-05,
|
| 79319 |
+
"loss": 0.7225,
|
| 79320 |
+
"step": 11330
|
| 79321 |
+
},
|
| 79322 |
+
{
|
| 79323 |
+
"epoch": 12.905982905982906,
|
| 79324 |
+
"grad_norm": 0.20048879086971283,
|
| 79325 |
+
"learning_rate": 1.5040994676549588e-05,
|
| 79326 |
+
"loss": 0.8738,
|
| 79327 |
+
"step": 11331
|
| 79328 |
+
},
|
| 79329 |
+
{
|
| 79330 |
+
"epoch": 12.907122507122507,
|
| 79331 |
+
"grad_norm": 0.20053917169570923,
|
| 79332 |
+
"learning_rate": 1.5036721313215913e-05,
|
| 79333 |
+
"loss": 0.6706,
|
| 79334 |
+
"step": 11332
|
| 79335 |
+
},
|
| 79336 |
+
{
|
| 79337 |
+
"epoch": 12.908262108262107,
|
| 79338 |
+
"grad_norm": 0.22289910912513733,
|
| 79339 |
+
"learning_rate": 1.503244829593431e-05,
|
| 79340 |
+
"loss": 0.674,
|
| 79341 |
+
"step": 11333
|
| 79342 |
+
},
|
| 79343 |
+
{
|
| 79344 |
+
"epoch": 12.90940170940171,
|
| 79345 |
+
"grad_norm": 0.24713099002838135,
|
| 79346 |
+
"learning_rate": 1.502817562485318e-05,
|
| 79347 |
+
"loss": 0.6585,
|
| 79348 |
+
"step": 11334
|
| 79349 |
+
},
|
| 79350 |
+
{
|
| 79351 |
+
"epoch": 12.91054131054131,
|
| 79352 |
+
"grad_norm": 0.1970605105161667,
|
| 79353 |
+
"learning_rate": 1.5023903300120943e-05,
|
| 79354 |
+
"loss": 0.8098,
|
| 79355 |
+
"step": 11335
|
| 79356 |
+
},
|
| 79357 |
+
{
|
| 79358 |
+
"epoch": 12.91168091168091,
|
| 79359 |
+
"grad_norm": 0.18536637723445892,
|
| 79360 |
+
"learning_rate": 1.5019631321885972e-05,
|
| 79361 |
+
"loss": 0.6711,
|
| 79362 |
+
"step": 11336
|
| 79363 |
+
},
|
| 79364 |
+
{
|
| 79365 |
+
"epoch": 12.912820512820513,
|
| 79366 |
+
"grad_norm": 0.1956309825181961,
|
| 79367 |
+
"learning_rate": 1.5015359690296646e-05,
|
| 79368 |
+
"loss": 0.5207,
|
| 79369 |
+
"step": 11337
|
| 79370 |
+
},
|
| 79371 |
+
{
|
| 79372 |
+
"epoch": 12.913960113960114,
|
| 79373 |
+
"grad_norm": 0.21517540514469147,
|
| 79374 |
+
"learning_rate": 1.5011088405501345e-05,
|
| 79375 |
+
"loss": 0.7251,
|
| 79376 |
+
"step": 11338
|
| 79377 |
+
},
|
| 79378 |
+
{
|
| 79379 |
+
"epoch": 12.915099715099714,
|
| 79380 |
+
"grad_norm": 0.2148135006427765,
|
| 79381 |
+
"learning_rate": 1.500681746764841e-05,
|
| 79382 |
+
"loss": 0.6951,
|
| 79383 |
+
"step": 11339
|
| 79384 |
+
},
|
| 79385 |
+
{
|
| 79386 |
+
"epoch": 12.916239316239317,
|
| 79387 |
+
"grad_norm": 0.20857606828212738,
|
| 79388 |
+
"learning_rate": 1.5002546876886191e-05,
|
| 79389 |
+
"loss": 0.6369,
|
| 79390 |
+
"step": 11340
|
| 79391 |
+
},
|
| 79392 |
+
{
|
| 79393 |
+
"epoch": 12.917378917378917,
|
| 79394 |
+
"grad_norm": 0.2005983144044876,
|
| 79395 |
+
"learning_rate": 1.4998276633363007e-05,
|
| 79396 |
+
"loss": 0.7484,
|
| 79397 |
+
"step": 11341
|
| 79398 |
+
},
|
| 79399 |
+
{
|
| 79400 |
+
"epoch": 12.918518518518518,
|
| 79401 |
+
"grad_norm": 0.17464596033096313,
|
| 79402 |
+
"learning_rate": 1.4994006737227185e-05,
|
| 79403 |
+
"loss": 0.9722,
|
| 79404 |
+
"step": 11342
|
| 79405 |
+
},
|
| 79406 |
+
{
|
| 79407 |
+
"epoch": 12.91965811965812,
|
| 79408 |
+
"grad_norm": 0.21768459677696228,
|
| 79409 |
+
"learning_rate": 1.4989737188627018e-05,
|
| 79410 |
+
"loss": 0.6091,
|
| 79411 |
+
"step": 11343
|
| 79412 |
+
},
|
| 79413 |
+
{
|
| 79414 |
+
"epoch": 12.92079772079772,
|
| 79415 |
+
"grad_norm": 0.262990802526474,
|
| 79416 |
+
"learning_rate": 1.498546798771081e-05,
|
| 79417 |
+
"loss": 0.6419,
|
| 79418 |
+
"step": 11344
|
| 79419 |
+
},
|
| 79420 |
+
{
|
| 79421 |
+
"epoch": 12.921937321937321,
|
| 79422 |
+
"grad_norm": 0.22202444076538086,
|
| 79423 |
+
"learning_rate": 1.4981199134626841e-05,
|
| 79424 |
+
"loss": 0.764,
|
| 79425 |
+
"step": 11345
|
| 79426 |
+
},
|
| 79427 |
+
{
|
| 79428 |
+
"epoch": 12.923076923076923,
|
| 79429 |
+
"grad_norm": 0.18325243890285492,
|
| 79430 |
+
"learning_rate": 1.4976930629523375e-05,
|
| 79431 |
+
"loss": 0.6889,
|
| 79432 |
+
"step": 11346
|
| 79433 |
+
},
|
| 79434 |
+
{
|
| 79435 |
+
"epoch": 12.924216524216524,
|
| 79436 |
+
"grad_norm": 0.2587796151638031,
|
| 79437 |
+
"learning_rate": 1.4972662472548676e-05,
|
| 79438 |
+
"loss": 0.4527,
|
| 79439 |
+
"step": 11347
|
| 79440 |
+
},
|
| 79441 |
+
{
|
| 79442 |
+
"epoch": 12.925356125356124,
|
| 79443 |
+
"grad_norm": 0.2007748782634735,
|
| 79444 |
+
"learning_rate": 1.4968394663850977e-05,
|
| 79445 |
+
"loss": 0.7945,
|
| 79446 |
+
"step": 11348
|
| 79447 |
+
},
|
| 79448 |
+
{
|
| 79449 |
+
"epoch": 12.926495726495727,
|
| 79450 |
+
"grad_norm": 0.21909686923027039,
|
| 79451 |
+
"learning_rate": 1.4964127203578521e-05,
|
| 79452 |
+
"loss": 0.8434,
|
| 79453 |
+
"step": 11349
|
| 79454 |
+
},
|
| 79455 |
+
{
|
| 79456 |
+
"epoch": 12.927635327635327,
|
| 79457 |
+
"grad_norm": 0.2630300521850586,
|
| 79458 |
+
"learning_rate": 1.495986009187953e-05,
|
| 79459 |
+
"loss": 0.619,
|
| 79460 |
+
"step": 11350
|
| 79461 |
+
},
|
| 79462 |
+
{
|
| 79463 |
+
"epoch": 12.928774928774928,
|
| 79464 |
+
"grad_norm": 0.20543648302555084,
|
| 79465 |
+
"learning_rate": 1.4955593328902206e-05,
|
| 79466 |
+
"loss": 0.8312,
|
| 79467 |
+
"step": 11351
|
| 79468 |
+
},
|
| 79469 |
+
{
|
| 79470 |
+
"epoch": 12.92991452991453,
|
| 79471 |
+
"grad_norm": 0.21905991435050964,
|
| 79472 |
+
"learning_rate": 1.495132691479475e-05,
|
| 79473 |
+
"loss": 0.5108,
|
| 79474 |
+
"step": 11352
|
| 79475 |
+
},
|
| 79476 |
+
{
|
| 79477 |
+
"epoch": 12.93105413105413,
|
| 79478 |
+
"grad_norm": 0.22271057963371277,
|
| 79479 |
+
"learning_rate": 1.4947060849705341e-05,
|
| 79480 |
+
"loss": 0.4384,
|
| 79481 |
+
"step": 11353
|
| 79482 |
+
},
|
| 79483 |
+
{
|
| 79484 |
+
"epoch": 12.932193732193731,
|
| 79485 |
+
"grad_norm": 0.25240451097488403,
|
| 79486 |
+
"learning_rate": 1.494279513378216e-05,
|
| 79487 |
+
"loss": 0.685,
|
| 79488 |
+
"step": 11354
|
| 79489 |
+
},
|
| 79490 |
+
{
|
| 79491 |
+
"epoch": 12.933333333333334,
|
| 79492 |
+
"grad_norm": 0.18054066598415375,
|
| 79493 |
+
"learning_rate": 1.4938529767173357e-05,
|
| 79494 |
+
"loss": 0.8588,
|
| 79495 |
+
"step": 11355
|
| 79496 |
+
},
|
| 79497 |
+
{
|
| 79498 |
+
"epoch": 12.934472934472934,
|
| 79499 |
+
"grad_norm": 0.16919507086277008,
|
| 79500 |
+
"learning_rate": 1.4934264750027089e-05,
|
| 79501 |
+
"loss": 0.6914,
|
| 79502 |
+
"step": 11356
|
| 79503 |
+
},
|
| 79504 |
+
{
|
| 79505 |
+
"epoch": 12.935612535612536,
|
| 79506 |
+
"grad_norm": 0.22787116467952728,
|
| 79507 |
+
"learning_rate": 1.493000008249148e-05,
|
| 79508 |
+
"loss": 0.6032,
|
| 79509 |
+
"step": 11357
|
| 79510 |
+
},
|
| 79511 |
+
{
|
| 79512 |
+
"epoch": 12.936752136752137,
|
| 79513 |
+
"grad_norm": 0.24769218266010284,
|
| 79514 |
+
"learning_rate": 1.4925735764714666e-05,
|
| 79515 |
+
"loss": 0.6556,
|
| 79516 |
+
"step": 11358
|
| 79517 |
+
},
|
| 79518 |
+
{
|
| 79519 |
+
"epoch": 12.937891737891738,
|
| 79520 |
+
"grad_norm": 0.23653510212898254,
|
| 79521 |
+
"learning_rate": 1.4921471796844744e-05,
|
| 79522 |
+
"loss": 0.7298,
|
| 79523 |
+
"step": 11359
|
| 79524 |
+
},
|
| 79525 |
+
{
|
| 79526 |
+
"epoch": 12.93903133903134,
|
| 79527 |
+
"grad_norm": 0.23376649618148804,
|
| 79528 |
+
"learning_rate": 1.491720817902983e-05,
|
| 79529 |
+
"loss": 0.703,
|
| 79530 |
+
"step": 11360
|
| 79531 |
+
},
|
| 79532 |
+
{
|
| 79533 |
+
"epoch": 12.94017094017094,
|
| 79534 |
+
"grad_norm": 0.22891533374786377,
|
| 79535 |
+
"learning_rate": 1.4912944911418006e-05,
|
| 79536 |
+
"loss": 0.6003,
|
| 79537 |
+
"step": 11361
|
| 79538 |
+
},
|
| 79539 |
+
{
|
| 79540 |
+
"epoch": 12.941310541310541,
|
| 79541 |
+
"grad_norm": 0.22133411467075348,
|
| 79542 |
+
"learning_rate": 1.4908681994157339e-05,
|
| 79543 |
+
"loss": 0.6826,
|
| 79544 |
+
"step": 11362
|
| 79545 |
+
},
|
| 79546 |
+
{
|
| 79547 |
+
"epoch": 12.942450142450143,
|
| 79548 |
+
"grad_norm": 0.25973889231681824,
|
| 79549 |
+
"learning_rate": 1.4904419427395904e-05,
|
| 79550 |
+
"loss": 0.5391,
|
| 79551 |
+
"step": 11363
|
| 79552 |
+
},
|
| 79553 |
+
{
|
| 79554 |
+
"epoch": 12.943589743589744,
|
| 79555 |
+
"grad_norm": 0.18987728655338287,
|
| 79556 |
+
"learning_rate": 1.490015721128174e-05,
|
| 79557 |
+
"loss": 0.7936,
|
| 79558 |
+
"step": 11364
|
| 79559 |
+
},
|
| 79560 |
+
{
|
| 79561 |
+
"epoch": 12.944729344729344,
|
| 79562 |
+
"grad_norm": 0.20876216888427734,
|
| 79563 |
+
"learning_rate": 1.4895895345962896e-05,
|
| 79564 |
+
"loss": 0.6467,
|
| 79565 |
+
"step": 11365
|
| 79566 |
+
},
|
| 79567 |
+
{
|
| 79568 |
+
"epoch": 12.945868945868947,
|
| 79569 |
+
"grad_norm": 0.22567686438560486,
|
| 79570 |
+
"learning_rate": 1.4891633831587386e-05,
|
| 79571 |
+
"loss": 0.582,
|
| 79572 |
+
"step": 11366
|
| 79573 |
+
},
|
| 79574 |
+
{
|
| 79575 |
+
"epoch": 12.947008547008547,
|
| 79576 |
+
"grad_norm": 0.17486126720905304,
|
| 79577 |
+
"learning_rate": 1.488737266830324e-05,
|
| 79578 |
+
"loss": 0.6805,
|
| 79579 |
+
"step": 11367
|
| 79580 |
+
},
|
| 79581 |
+
{
|
| 79582 |
+
"epoch": 12.948148148148148,
|
| 79583 |
+
"grad_norm": 0.249233216047287,
|
| 79584 |
+
"learning_rate": 1.4883111856258444e-05,
|
| 79585 |
+
"loss": 0.4735,
|
| 79586 |
+
"step": 11368
|
| 79587 |
+
},
|
| 79588 |
+
{
|
| 79589 |
+
"epoch": 12.94928774928775,
|
| 79590 |
+
"grad_norm": 0.2411205917596817,
|
| 79591 |
+
"learning_rate": 1.4878851395601002e-05,
|
| 79592 |
+
"loss": 0.7448,
|
| 79593 |
+
"step": 11369
|
| 79594 |
+
},
|
| 79595 |
+
{
|
| 79596 |
+
"epoch": 12.95042735042735,
|
| 79597 |
+
"grad_norm": 0.15878437459468842,
|
| 79598 |
+
"learning_rate": 1.487459128647887e-05,
|
| 79599 |
+
"loss": 0.7648,
|
| 79600 |
+
"step": 11370
|
| 79601 |
+
},
|
| 79602 |
+
{
|
| 79603 |
+
"epoch": 12.951566951566951,
|
| 79604 |
+
"grad_norm": 0.1965569108724594,
|
| 79605 |
+
"learning_rate": 1.4870331529040032e-05,
|
| 79606 |
+
"loss": 0.7249,
|
| 79607 |
+
"step": 11371
|
| 79608 |
+
},
|
| 79609 |
+
{
|
| 79610 |
+
"epoch": 12.952706552706553,
|
| 79611 |
+
"grad_norm": 0.20828257501125336,
|
| 79612 |
+
"learning_rate": 1.4866072123432445e-05,
|
| 79613 |
+
"loss": 0.7939,
|
| 79614 |
+
"step": 11372
|
| 79615 |
+
},
|
| 79616 |
+
{
|
| 79617 |
+
"epoch": 12.953846153846154,
|
| 79618 |
+
"grad_norm": 0.2108020931482315,
|
| 79619 |
+
"learning_rate": 1.4861813069804037e-05,
|
| 79620 |
+
"loss": 0.5208,
|
| 79621 |
+
"step": 11373
|
| 79622 |
+
},
|
| 79623 |
+
{
|
| 79624 |
+
"epoch": 12.954985754985755,
|
| 79625 |
+
"grad_norm": 0.26978325843811035,
|
| 79626 |
+
"learning_rate": 1.4857554368302745e-05,
|
| 79627 |
+
"loss": 0.5179,
|
| 79628 |
+
"step": 11374
|
| 79629 |
+
},
|
| 79630 |
+
{
|
| 79631 |
+
"epoch": 12.956125356125357,
|
| 79632 |
+
"grad_norm": 0.29760831594467163,
|
| 79633 |
+
"learning_rate": 1.485329601907648e-05,
|
| 79634 |
+
"loss": 0.3318,
|
| 79635 |
+
"step": 11375
|
| 79636 |
+
},
|
| 79637 |
+
{
|
| 79638 |
+
"epoch": 12.957264957264957,
|
| 79639 |
+
"grad_norm": 0.18968529999256134,
|
| 79640 |
+
"learning_rate": 1.4849038022273148e-05,
|
| 79641 |
+
"loss": 0.5812,
|
| 79642 |
+
"step": 11376
|
| 79643 |
+
},
|
| 79644 |
+
{
|
| 79645 |
+
"epoch": 12.958404558404558,
|
| 79646 |
+
"grad_norm": 0.23169593513011932,
|
| 79647 |
+
"learning_rate": 1.4844780378040634e-05,
|
| 79648 |
+
"loss": 0.5563,
|
| 79649 |
+
"step": 11377
|
| 79650 |
+
},
|
| 79651 |
+
{
|
| 79652 |
+
"epoch": 12.95954415954416,
|
| 79653 |
+
"grad_norm": 0.17449063062667847,
|
| 79654 |
+
"learning_rate": 1.4840523086526836e-05,
|
| 79655 |
+
"loss": 0.8254,
|
| 79656 |
+
"step": 11378
|
| 79657 |
+
},
|
| 79658 |
+
{
|
| 79659 |
+
"epoch": 12.96068376068376,
|
| 79660 |
+
"grad_norm": 0.23026247322559357,
|
| 79661 |
+
"learning_rate": 1.4836266147879602e-05,
|
| 79662 |
+
"loss": 0.584,
|
| 79663 |
+
"step": 11379
|
| 79664 |
+
},
|
| 79665 |
+
{
|
| 79666 |
+
"epoch": 12.961823361823361,
|
| 79667 |
+
"grad_norm": 0.20057043433189392,
|
| 79668 |
+
"learning_rate": 1.4832009562246799e-05,
|
| 79669 |
+
"loss": 0.6018,
|
| 79670 |
+
"step": 11380
|
| 79671 |
+
},
|
| 79672 |
+
{
|
| 79673 |
+
"epoch": 12.962962962962964,
|
| 79674 |
+
"grad_norm": 0.256772518157959,
|
| 79675 |
+
"learning_rate": 1.482775332977625e-05,
|
| 79676 |
+
"loss": 0.8504,
|
| 79677 |
+
"step": 11381
|
| 79678 |
+
},
|
| 79679 |
+
{
|
| 79680 |
+
"epoch": 12.964102564102564,
|
| 79681 |
+
"grad_norm": 0.2533794939517975,
|
| 79682 |
+
"learning_rate": 1.482349745061582e-05,
|
| 79683 |
+
"loss": 0.7321,
|
| 79684 |
+
"step": 11382
|
| 79685 |
+
},
|
| 79686 |
+
{
|
| 79687 |
+
"epoch": 12.965242165242165,
|
| 79688 |
+
"grad_norm": 0.23897698521614075,
|
| 79689 |
+
"learning_rate": 1.4819241924913303e-05,
|
| 79690 |
+
"loss": 0.5534,
|
| 79691 |
+
"step": 11383
|
| 79692 |
+
},
|
| 79693 |
+
{
|
| 79694 |
+
"epoch": 12.966381766381767,
|
| 79695 |
+
"grad_norm": 0.19721534848213196,
|
| 79696 |
+
"learning_rate": 1.4814986752816512e-05,
|
| 79697 |
+
"loss": 0.7591,
|
| 79698 |
+
"step": 11384
|
| 79699 |
+
},
|
| 79700 |
+
{
|
| 79701 |
+
"epoch": 12.967521367521368,
|
| 79702 |
+
"grad_norm": 0.19526709616184235,
|
| 79703 |
+
"learning_rate": 1.4810731934473241e-05,
|
| 79704 |
+
"loss": 0.6045,
|
| 79705 |
+
"step": 11385
|
| 79706 |
+
},
|
| 79707 |
+
{
|
| 79708 |
+
"epoch": 12.968660968660968,
|
| 79709 |
+
"grad_norm": 0.15430134534835815,
|
| 79710 |
+
"learning_rate": 1.4806477470031271e-05,
|
| 79711 |
+
"loss": 0.8702,
|
| 79712 |
+
"step": 11386
|
| 79713 |
+
},
|
| 79714 |
+
{
|
| 79715 |
+
"epoch": 12.96980056980057,
|
| 79716 |
+
"grad_norm": 0.255127489566803,
|
| 79717 |
+
"learning_rate": 1.4802223359638368e-05,
|
| 79718 |
+
"loss": 0.553,
|
| 79719 |
+
"step": 11387
|
| 79720 |
+
},
|
| 79721 |
+
{
|
| 79722 |
+
"epoch": 12.970940170940171,
|
| 79723 |
+
"grad_norm": 0.26086923480033875,
|
| 79724 |
+
"learning_rate": 1.4797969603442297e-05,
|
| 79725 |
+
"loss": 0.5594,
|
| 79726 |
+
"step": 11388
|
| 79727 |
+
},
|
| 79728 |
+
{
|
| 79729 |
+
"epoch": 12.972079772079772,
|
| 79730 |
+
"grad_norm": 0.20795606076717377,
|
| 79731 |
+
"learning_rate": 1.4793716201590791e-05,
|
| 79732 |
+
"loss": 0.8878,
|
| 79733 |
+
"step": 11389
|
| 79734 |
+
},
|
| 79735 |
+
{
|
| 79736 |
+
"epoch": 12.973219373219374,
|
| 79737 |
+
"grad_norm": 0.20088131725788116,
|
| 79738 |
+
"learning_rate": 1.4789463154231598e-05,
|
| 79739 |
+
"loss": 0.7535,
|
| 79740 |
+
"step": 11390
|
| 79741 |
+
},
|
| 79742 |
+
{
|
| 79743 |
+
"epoch": 12.974358974358974,
|
| 79744 |
+
"grad_norm": 0.19947673380374908,
|
| 79745 |
+
"learning_rate": 1.4785210461512416e-05,
|
| 79746 |
+
"loss": 0.5852,
|
| 79747 |
+
"step": 11391
|
| 79748 |
+
},
|
| 79749 |
+
{
|
| 79750 |
+
"epoch": 12.975498575498575,
|
| 79751 |
+
"grad_norm": 0.19736547768115997,
|
| 79752 |
+
"learning_rate": 1.4780958123580968e-05,
|
| 79753 |
+
"loss": 0.5457,
|
| 79754 |
+
"step": 11392
|
| 79755 |
+
},
|
| 79756 |
+
{
|
| 79757 |
+
"epoch": 12.976638176638177,
|
| 79758 |
+
"grad_norm": 0.20003557205200195,
|
| 79759 |
+
"learning_rate": 1.477670614058495e-05,
|
| 79760 |
+
"loss": 0.6882,
|
| 79761 |
+
"step": 11393
|
| 79762 |
+
},
|
| 79763 |
+
{
|
| 79764 |
+
"epoch": 12.977777777777778,
|
| 79765 |
+
"grad_norm": 0.23446090519428253,
|
| 79766 |
+
"learning_rate": 1.477245451267204e-05,
|
| 79767 |
+
"loss": 0.6767,
|
| 79768 |
+
"step": 11394
|
| 79769 |
+
},
|
| 79770 |
+
{
|
| 79771 |
+
"epoch": 12.978917378917378,
|
| 79772 |
+
"grad_norm": 0.26469114422798157,
|
| 79773 |
+
"learning_rate": 1.476820323998992e-05,
|
| 79774 |
+
"loss": 0.4988,
|
| 79775 |
+
"step": 11395
|
| 79776 |
+
},
|
| 79777 |
+
{
|
| 79778 |
+
"epoch": 12.98005698005698,
|
| 79779 |
+
"grad_norm": 0.1809329390525818,
|
| 79780 |
+
"learning_rate": 1.4763952322686229e-05,
|
| 79781 |
+
"loss": 0.9165,
|
| 79782 |
+
"step": 11396
|
| 79783 |
+
},
|
| 79784 |
+
{
|
| 79785 |
+
"epoch": 12.981196581196581,
|
| 79786 |
+
"grad_norm": 0.17014767229557037,
|
| 79787 |
+
"learning_rate": 1.4759701760908629e-05,
|
| 79788 |
+
"loss": 0.766,
|
| 79789 |
+
"step": 11397
|
| 79790 |
+
},
|
| 79791 |
+
{
|
| 79792 |
+
"epoch": 12.982336182336182,
|
| 79793 |
+
"grad_norm": 0.2265402227640152,
|
| 79794 |
+
"learning_rate": 1.4755451554804745e-05,
|
| 79795 |
+
"loss": 0.6505,
|
| 79796 |
+
"step": 11398
|
| 79797 |
+
},
|
| 79798 |
+
{
|
| 79799 |
+
"epoch": 12.983475783475784,
|
| 79800 |
+
"grad_norm": 0.2196301966905594,
|
| 79801 |
+
"learning_rate": 1.4751201704522201e-05,
|
| 79802 |
+
"loss": 0.7872,
|
| 79803 |
+
"step": 11399
|
| 79804 |
+
},
|
| 79805 |
+
{
|
| 79806 |
+
"epoch": 12.984615384615385,
|
| 79807 |
+
"grad_norm": 0.26781708002090454,
|
| 79808 |
+
"learning_rate": 1.4746952210208604e-05,
|
| 79809 |
+
"loss": 0.7257,
|
| 79810 |
+
"step": 11400
|
| 79811 |
}
|
| 79812 |
],
|
| 79813 |
"logging_steps": 1,
|
|
|
|
| 79827 |
"attributes": {}
|
| 79828 |
}
|
| 79829 |
},
|
| 79830 |
+
"total_flos": 6.374253556470694e+19,
|
| 79831 |
"train_batch_size": 8,
|
| 79832 |
"trial_name": null,
|
| 79833 |
"trial_params": null
|