Instructions to use shareit/chatbot-supervisor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shareit/chatbot-supervisor with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shareit/chatbot-supervisor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Training in progress, step 5700, 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:de7b0a3ce745f3e3d74e2e126b1ef845a5c990537cffa13753e8b5959e6dc1b7
|
| 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 sha256:2c427c8ab995b21b81a36a9e88e9a859520b07a618a27857fe12261ee221b1ed
|
| 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 sha256:8640482959cac4cd67e382f4472218bfcae7c2eeb306fc064f7bcf7f2297adf4
|
| 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.
|
| 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,
|
|
@@ -37808,6 +37808,2106 @@
|
|
| 37808 |
"learning_rate": 4.1021456044593466e-05,
|
| 37809 |
"loss": 0.6682,
|
| 37810 |
"step": 5400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37811 |
}
|
| 37812 |
],
|
| 37813 |
"logging_steps": 1,
|
|
@@ -37827,7 +39927,7 @@
|
|
| 37827 |
"attributes": {}
|
| 37828 |
}
|
| 37829 |
},
|
| 37830 |
-
"total_flos": 3.
|
| 37831 |
"train_batch_size": 8,
|
| 37832 |
"trial_name": null,
|
| 37833 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.492307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5700,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 37808 |
"learning_rate": 4.1021456044593466e-05,
|
| 37809 |
"loss": 0.6682,
|
| 37810 |
"step": 5400
|
| 37811 |
+
},
|
| 37812 |
+
{
|
| 37813 |
+
"epoch": 6.151566951566951,
|
| 37814 |
+
"grad_norm": 0.2057657539844513,
|
| 37815 |
+
"learning_rate": 4.101787910291713e-05,
|
| 37816 |
+
"loss": 0.8057,
|
| 37817 |
+
"step": 5401
|
| 37818 |
+
},
|
| 37819 |
+
{
|
| 37820 |
+
"epoch": 6.152706552706553,
|
| 37821 |
+
"grad_norm": 0.17795559763908386,
|
| 37822 |
+
"learning_rate": 4.10143016048958e-05,
|
| 37823 |
+
"loss": 0.8306,
|
| 37824 |
+
"step": 5402
|
| 37825 |
+
},
|
| 37826 |
+
{
|
| 37827 |
+
"epoch": 6.153846153846154,
|
| 37828 |
+
"grad_norm": 0.19012929499149323,
|
| 37829 |
+
"learning_rate": 4.101072355065374e-05,
|
| 37830 |
+
"loss": 0.7311,
|
| 37831 |
+
"step": 5403
|
| 37832 |
+
},
|
| 37833 |
+
{
|
| 37834 |
+
"epoch": 6.154985754985755,
|
| 37835 |
+
"grad_norm": 0.14840446412563324,
|
| 37836 |
+
"learning_rate": 4.1007144940315225e-05,
|
| 37837 |
+
"loss": 0.7818,
|
| 37838 |
+
"step": 5404
|
| 37839 |
+
},
|
| 37840 |
+
{
|
| 37841 |
+
"epoch": 6.156125356125356,
|
| 37842 |
+
"grad_norm": 0.19507408142089844,
|
| 37843 |
+
"learning_rate": 4.100356577400454e-05,
|
| 37844 |
+
"loss": 0.6246,
|
| 37845 |
+
"step": 5405
|
| 37846 |
+
},
|
| 37847 |
+
{
|
| 37848 |
+
"epoch": 6.157264957264958,
|
| 37849 |
+
"grad_norm": 0.13652437925338745,
|
| 37850 |
+
"learning_rate": 4.099998605184601e-05,
|
| 37851 |
+
"loss": 0.9509,
|
| 37852 |
+
"step": 5406
|
| 37853 |
+
},
|
| 37854 |
+
{
|
| 37855 |
+
"epoch": 6.158404558404558,
|
| 37856 |
+
"grad_norm": 0.1518937349319458,
|
| 37857 |
+
"learning_rate": 4.099640577396396e-05,
|
| 37858 |
+
"loss": 0.8777,
|
| 37859 |
+
"step": 5407
|
| 37860 |
+
},
|
| 37861 |
+
{
|
| 37862 |
+
"epoch": 6.15954415954416,
|
| 37863 |
+
"grad_norm": 0.14349329471588135,
|
| 37864 |
+
"learning_rate": 4.099282494048275e-05,
|
| 37865 |
+
"loss": 0.7823,
|
| 37866 |
+
"step": 5408
|
| 37867 |
+
},
|
| 37868 |
+
{
|
| 37869 |
+
"epoch": 6.160683760683761,
|
| 37870 |
+
"grad_norm": 0.1953577846288681,
|
| 37871 |
+
"learning_rate": 4.098924355152675e-05,
|
| 37872 |
+
"loss": 0.7073,
|
| 37873 |
+
"step": 5409
|
| 37874 |
+
},
|
| 37875 |
+
{
|
| 37876 |
+
"epoch": 6.1618233618233615,
|
| 37877 |
+
"grad_norm": 0.19672128558158875,
|
| 37878 |
+
"learning_rate": 4.098566160722035e-05,
|
| 37879 |
+
"loss": 0.7058,
|
| 37880 |
+
"step": 5410
|
| 37881 |
+
},
|
| 37882 |
+
{
|
| 37883 |
+
"epoch": 6.162962962962963,
|
| 37884 |
+
"grad_norm": 0.2700105905532837,
|
| 37885 |
+
"learning_rate": 4.0982079107687965e-05,
|
| 37886 |
+
"loss": 0.4254,
|
| 37887 |
+
"step": 5411
|
| 37888 |
+
},
|
| 37889 |
+
{
|
| 37890 |
+
"epoch": 6.164102564102564,
|
| 37891 |
+
"grad_norm": 0.22202476859092712,
|
| 37892 |
+
"learning_rate": 4.0978496053054013e-05,
|
| 37893 |
+
"loss": 0.5088,
|
| 37894 |
+
"step": 5412
|
| 37895 |
+
},
|
| 37896 |
+
{
|
| 37897 |
+
"epoch": 6.165242165242165,
|
| 37898 |
+
"grad_norm": 0.21494624018669128,
|
| 37899 |
+
"learning_rate": 4.097491244344296e-05,
|
| 37900 |
+
"loss": 0.6267,
|
| 37901 |
+
"step": 5413
|
| 37902 |
+
},
|
| 37903 |
+
{
|
| 37904 |
+
"epoch": 6.166381766381766,
|
| 37905 |
+
"grad_norm": 0.1644032895565033,
|
| 37906 |
+
"learning_rate": 4.097132827897926e-05,
|
| 37907 |
+
"loss": 0.7998,
|
| 37908 |
+
"step": 5414
|
| 37909 |
+
},
|
| 37910 |
+
{
|
| 37911 |
+
"epoch": 6.167521367521368,
|
| 37912 |
+
"grad_norm": 0.18602855503559113,
|
| 37913 |
+
"learning_rate": 4.0967743559787414e-05,
|
| 37914 |
+
"loss": 0.8451,
|
| 37915 |
+
"step": 5415
|
| 37916 |
+
},
|
| 37917 |
+
{
|
| 37918 |
+
"epoch": 6.168660968660968,
|
| 37919 |
+
"grad_norm": 0.1747872233390808,
|
| 37920 |
+
"learning_rate": 4.096415828599192e-05,
|
| 37921 |
+
"loss": 0.8646,
|
| 37922 |
+
"step": 5416
|
| 37923 |
+
},
|
| 37924 |
+
{
|
| 37925 |
+
"epoch": 6.16980056980057,
|
| 37926 |
+
"grad_norm": 0.18089835345745087,
|
| 37927 |
+
"learning_rate": 4.0960572457717305e-05,
|
| 37928 |
+
"loss": 0.7518,
|
| 37929 |
+
"step": 5417
|
| 37930 |
+
},
|
| 37931 |
+
{
|
| 37932 |
+
"epoch": 6.170940170940171,
|
| 37933 |
+
"grad_norm": 0.18630164861679077,
|
| 37934 |
+
"learning_rate": 4.0956986075088125e-05,
|
| 37935 |
+
"loss": 0.7452,
|
| 37936 |
+
"step": 5418
|
| 37937 |
+
},
|
| 37938 |
+
{
|
| 37939 |
+
"epoch": 6.172079772079772,
|
| 37940 |
+
"grad_norm": 0.1786157488822937,
|
| 37941 |
+
"learning_rate": 4.095339913822892e-05,
|
| 37942 |
+
"loss": 0.8762,
|
| 37943 |
+
"step": 5419
|
| 37944 |
+
},
|
| 37945 |
+
{
|
| 37946 |
+
"epoch": 6.173219373219373,
|
| 37947 |
+
"grad_norm": 0.17823855578899384,
|
| 37948 |
+
"learning_rate": 4.094981164726431e-05,
|
| 37949 |
+
"loss": 0.7615,
|
| 37950 |
+
"step": 5420
|
| 37951 |
+
},
|
| 37952 |
+
{
|
| 37953 |
+
"epoch": 6.174358974358975,
|
| 37954 |
+
"grad_norm": 0.18031442165374756,
|
| 37955 |
+
"learning_rate": 4.094622360231887e-05,
|
| 37956 |
+
"loss": 0.8003,
|
| 37957 |
+
"step": 5421
|
| 37958 |
+
},
|
| 37959 |
+
{
|
| 37960 |
+
"epoch": 6.175498575498575,
|
| 37961 |
+
"grad_norm": 0.19077175855636597,
|
| 37962 |
+
"learning_rate": 4.094263500351724e-05,
|
| 37963 |
+
"loss": 0.8451,
|
| 37964 |
+
"step": 5422
|
| 37965 |
+
},
|
| 37966 |
+
{
|
| 37967 |
+
"epoch": 6.176638176638177,
|
| 37968 |
+
"grad_norm": 0.20899420976638794,
|
| 37969 |
+
"learning_rate": 4.093904585098404e-05,
|
| 37970 |
+
"loss": 0.7411,
|
| 37971 |
+
"step": 5423
|
| 37972 |
+
},
|
| 37973 |
+
{
|
| 37974 |
+
"epoch": 6.177777777777778,
|
| 37975 |
+
"grad_norm": 0.1612003743648529,
|
| 37976 |
+
"learning_rate": 4.0935456144843956e-05,
|
| 37977 |
+
"loss": 0.9227,
|
| 37978 |
+
"step": 5424
|
| 37979 |
+
},
|
| 37980 |
+
{
|
| 37981 |
+
"epoch": 6.178917378917379,
|
| 37982 |
+
"grad_norm": 0.18165160715579987,
|
| 37983 |
+
"learning_rate": 4.0931865885221656e-05,
|
| 37984 |
+
"loss": 0.6729,
|
| 37985 |
+
"step": 5425
|
| 37986 |
+
},
|
| 37987 |
+
{
|
| 37988 |
+
"epoch": 6.18005698005698,
|
| 37989 |
+
"grad_norm": 0.16721685230731964,
|
| 37990 |
+
"learning_rate": 4.092827507224183e-05,
|
| 37991 |
+
"loss": 0.8923,
|
| 37992 |
+
"step": 5426
|
| 37993 |
+
},
|
| 37994 |
+
{
|
| 37995 |
+
"epoch": 6.181196581196581,
|
| 37996 |
+
"grad_norm": 0.18058645725250244,
|
| 37997 |
+
"learning_rate": 4.092468370602922e-05,
|
| 37998 |
+
"loss": 0.8386,
|
| 37999 |
+
"step": 5427
|
| 38000 |
+
},
|
| 38001 |
+
{
|
| 38002 |
+
"epoch": 6.182336182336182,
|
| 38003 |
+
"grad_norm": 0.1631706804037094,
|
| 38004 |
+
"learning_rate": 4.092109178670855e-05,
|
| 38005 |
+
"loss": 0.7912,
|
| 38006 |
+
"step": 5428
|
| 38007 |
+
},
|
| 38008 |
+
{
|
| 38009 |
+
"epoch": 6.183475783475783,
|
| 38010 |
+
"grad_norm": 0.20347100496292114,
|
| 38011 |
+
"learning_rate": 4.0917499314404576e-05,
|
| 38012 |
+
"loss": 0.6502,
|
| 38013 |
+
"step": 5429
|
| 38014 |
+
},
|
| 38015 |
+
{
|
| 38016 |
+
"epoch": 6.184615384615385,
|
| 38017 |
+
"grad_norm": 0.2409413605928421,
|
| 38018 |
+
"learning_rate": 4.091390628924208e-05,
|
| 38019 |
+
"loss": 0.6087,
|
| 38020 |
+
"step": 5430
|
| 38021 |
+
},
|
| 38022 |
+
{
|
| 38023 |
+
"epoch": 6.185754985754985,
|
| 38024 |
+
"grad_norm": 0.18910107016563416,
|
| 38025 |
+
"learning_rate": 4.091031271134586e-05,
|
| 38026 |
+
"loss": 0.6308,
|
| 38027 |
+
"step": 5431
|
| 38028 |
+
},
|
| 38029 |
+
{
|
| 38030 |
+
"epoch": 6.186894586894587,
|
| 38031 |
+
"grad_norm": 0.19836777448654175,
|
| 38032 |
+
"learning_rate": 4.0906718580840716e-05,
|
| 38033 |
+
"loss": 0.6492,
|
| 38034 |
+
"step": 5432
|
| 38035 |
+
},
|
| 38036 |
+
{
|
| 38037 |
+
"epoch": 6.188034188034188,
|
| 38038 |
+
"grad_norm": 0.14992153644561768,
|
| 38039 |
+
"learning_rate": 4.090312389785149e-05,
|
| 38040 |
+
"loss": 0.8728,
|
| 38041 |
+
"step": 5433
|
| 38042 |
+
},
|
| 38043 |
+
{
|
| 38044 |
+
"epoch": 6.189173789173789,
|
| 38045 |
+
"grad_norm": 0.17563802003860474,
|
| 38046 |
+
"learning_rate": 4.089952866250305e-05,
|
| 38047 |
+
"loss": 0.8546,
|
| 38048 |
+
"step": 5434
|
| 38049 |
+
},
|
| 38050 |
+
{
|
| 38051 |
+
"epoch": 6.19031339031339,
|
| 38052 |
+
"grad_norm": 0.228382870554924,
|
| 38053 |
+
"learning_rate": 4.089593287492024e-05,
|
| 38054 |
+
"loss": 0.5632,
|
| 38055 |
+
"step": 5435
|
| 38056 |
+
},
|
| 38057 |
+
{
|
| 38058 |
+
"epoch": 6.191452991452992,
|
| 38059 |
+
"grad_norm": 0.24549713730812073,
|
| 38060 |
+
"learning_rate": 4.089233653522798e-05,
|
| 38061 |
+
"loss": 0.8282,
|
| 38062 |
+
"step": 5436
|
| 38063 |
+
},
|
| 38064 |
+
{
|
| 38065 |
+
"epoch": 6.192592592592592,
|
| 38066 |
+
"grad_norm": 0.19304408133029938,
|
| 38067 |
+
"learning_rate": 4.0888739643551165e-05,
|
| 38068 |
+
"loss": 0.7496,
|
| 38069 |
+
"step": 5437
|
| 38070 |
+
},
|
| 38071 |
+
{
|
| 38072 |
+
"epoch": 6.193732193732194,
|
| 38073 |
+
"grad_norm": 0.19243228435516357,
|
| 38074 |
+
"learning_rate": 4.088514220001472e-05,
|
| 38075 |
+
"loss": 0.7399,
|
| 38076 |
+
"step": 5438
|
| 38077 |
+
},
|
| 38078 |
+
{
|
| 38079 |
+
"epoch": 6.194871794871795,
|
| 38080 |
+
"grad_norm": 0.21948397159576416,
|
| 38081 |
+
"learning_rate": 4.088154420474362e-05,
|
| 38082 |
+
"loss": 0.7033,
|
| 38083 |
+
"step": 5439
|
| 38084 |
+
},
|
| 38085 |
+
{
|
| 38086 |
+
"epoch": 6.196011396011396,
|
| 38087 |
+
"grad_norm": 0.19144877791404724,
|
| 38088 |
+
"learning_rate": 4.08779456578628e-05,
|
| 38089 |
+
"loss": 0.7552,
|
| 38090 |
+
"step": 5440
|
| 38091 |
+
},
|
| 38092 |
+
{
|
| 38093 |
+
"epoch": 6.197150997150997,
|
| 38094 |
+
"grad_norm": 0.1941777914762497,
|
| 38095 |
+
"learning_rate": 4.087434655949727e-05,
|
| 38096 |
+
"loss": 0.5746,
|
| 38097 |
+
"step": 5441
|
| 38098 |
+
},
|
| 38099 |
+
{
|
| 38100 |
+
"epoch": 6.1982905982905985,
|
| 38101 |
+
"grad_norm": 0.16696923971176147,
|
| 38102 |
+
"learning_rate": 4.087074690977203e-05,
|
| 38103 |
+
"loss": 0.9095,
|
| 38104 |
+
"step": 5442
|
| 38105 |
+
},
|
| 38106 |
+
{
|
| 38107 |
+
"epoch": 6.199430199430199,
|
| 38108 |
+
"grad_norm": 0.2027294635772705,
|
| 38109 |
+
"learning_rate": 4.08671467088121e-05,
|
| 38110 |
+
"loss": 0.5538,
|
| 38111 |
+
"step": 5443
|
| 38112 |
+
},
|
| 38113 |
+
{
|
| 38114 |
+
"epoch": 6.2005698005698004,
|
| 38115 |
+
"grad_norm": 0.22019366919994354,
|
| 38116 |
+
"learning_rate": 4.0863545956742534e-05,
|
| 38117 |
+
"loss": 0.5056,
|
| 38118 |
+
"step": 5444
|
| 38119 |
+
},
|
| 38120 |
+
{
|
| 38121 |
+
"epoch": 6.201709401709402,
|
| 38122 |
+
"grad_norm": 0.21672432124614716,
|
| 38123 |
+
"learning_rate": 4.0859944653688385e-05,
|
| 38124 |
+
"loss": 0.6106,
|
| 38125 |
+
"step": 5445
|
| 38126 |
+
},
|
| 38127 |
+
{
|
| 38128 |
+
"epoch": 6.202849002849002,
|
| 38129 |
+
"grad_norm": 0.1908385455608368,
|
| 38130 |
+
"learning_rate": 4.085634279977475e-05,
|
| 38131 |
+
"loss": 0.7042,
|
| 38132 |
+
"step": 5446
|
| 38133 |
+
},
|
| 38134 |
+
{
|
| 38135 |
+
"epoch": 6.203988603988604,
|
| 38136 |
+
"grad_norm": 0.17540811002254486,
|
| 38137 |
+
"learning_rate": 4.085274039512672e-05,
|
| 38138 |
+
"loss": 0.7663,
|
| 38139 |
+
"step": 5447
|
| 38140 |
+
},
|
| 38141 |
+
{
|
| 38142 |
+
"epoch": 6.205128205128205,
|
| 38143 |
+
"grad_norm": 0.22469978034496307,
|
| 38144 |
+
"learning_rate": 4.084913743986942e-05,
|
| 38145 |
+
"loss": 0.5877,
|
| 38146 |
+
"step": 5448
|
| 38147 |
+
},
|
| 38148 |
+
{
|
| 38149 |
+
"epoch": 6.206267806267807,
|
| 38150 |
+
"grad_norm": 0.1598920077085495,
|
| 38151 |
+
"learning_rate": 4.0845533934128e-05,
|
| 38152 |
+
"loss": 0.9132,
|
| 38153 |
+
"step": 5449
|
| 38154 |
+
},
|
| 38155 |
+
{
|
| 38156 |
+
"epoch": 6.207407407407407,
|
| 38157 |
+
"grad_norm": 0.18967831134796143,
|
| 38158 |
+
"learning_rate": 4.084192987802761e-05,
|
| 38159 |
+
"loss": 0.8009,
|
| 38160 |
+
"step": 5450
|
| 38161 |
+
},
|
| 38162 |
+
{
|
| 38163 |
+
"epoch": 6.208547008547009,
|
| 38164 |
+
"grad_norm": 0.18315912783145905,
|
| 38165 |
+
"learning_rate": 4.083832527169342e-05,
|
| 38166 |
+
"loss": 0.8127,
|
| 38167 |
+
"step": 5451
|
| 38168 |
+
},
|
| 38169 |
+
{
|
| 38170 |
+
"epoch": 6.20968660968661,
|
| 38171 |
+
"grad_norm": 0.15255817770957947,
|
| 38172 |
+
"learning_rate": 4.083472011525065e-05,
|
| 38173 |
+
"loss": 0.8159,
|
| 38174 |
+
"step": 5452
|
| 38175 |
+
},
|
| 38176 |
+
{
|
| 38177 |
+
"epoch": 6.210826210826211,
|
| 38178 |
+
"grad_norm": 0.16031622886657715,
|
| 38179 |
+
"learning_rate": 4.083111440882449e-05,
|
| 38180 |
+
"loss": 0.7793,
|
| 38181 |
+
"step": 5453
|
| 38182 |
+
},
|
| 38183 |
+
{
|
| 38184 |
+
"epoch": 6.211965811965812,
|
| 38185 |
+
"grad_norm": 0.1582925021648407,
|
| 38186 |
+
"learning_rate": 4.082750815254021e-05,
|
| 38187 |
+
"loss": 0.8903,
|
| 38188 |
+
"step": 5454
|
| 38189 |
+
},
|
| 38190 |
+
{
|
| 38191 |
+
"epoch": 6.2131054131054135,
|
| 38192 |
+
"grad_norm": 0.21032319962978363,
|
| 38193 |
+
"learning_rate": 4.082390134652303e-05,
|
| 38194 |
+
"loss": 0.8633,
|
| 38195 |
+
"step": 5455
|
| 38196 |
+
},
|
| 38197 |
+
{
|
| 38198 |
+
"epoch": 6.214245014245014,
|
| 38199 |
+
"grad_norm": 0.2191559225320816,
|
| 38200 |
+
"learning_rate": 4.082029399089825e-05,
|
| 38201 |
+
"loss": 0.4965,
|
| 38202 |
+
"step": 5456
|
| 38203 |
+
},
|
| 38204 |
+
{
|
| 38205 |
+
"epoch": 6.2153846153846155,
|
| 38206 |
+
"grad_norm": 0.1581375002861023,
|
| 38207 |
+
"learning_rate": 4.081668608579114e-05,
|
| 38208 |
+
"loss": 0.8054,
|
| 38209 |
+
"step": 5457
|
| 38210 |
+
},
|
| 38211 |
+
{
|
| 38212 |
+
"epoch": 6.216524216524217,
|
| 38213 |
+
"grad_norm": 0.17443591356277466,
|
| 38214 |
+
"learning_rate": 4.081307763132704e-05,
|
| 38215 |
+
"loss": 0.7814,
|
| 38216 |
+
"step": 5458
|
| 38217 |
+
},
|
| 38218 |
+
{
|
| 38219 |
+
"epoch": 6.2176638176638175,
|
| 38220 |
+
"grad_norm": 0.18770234286785126,
|
| 38221 |
+
"learning_rate": 4.080946862763126e-05,
|
| 38222 |
+
"loss": 0.8021,
|
| 38223 |
+
"step": 5459
|
| 38224 |
+
},
|
| 38225 |
+
{
|
| 38226 |
+
"epoch": 6.218803418803419,
|
| 38227 |
+
"grad_norm": 0.14728766679763794,
|
| 38228 |
+
"learning_rate": 4.0805859074829164e-05,
|
| 38229 |
+
"loss": 0.8208,
|
| 38230 |
+
"step": 5460
|
| 38231 |
+
},
|
| 38232 |
+
{
|
| 38233 |
+
"epoch": 6.21994301994302,
|
| 38234 |
+
"grad_norm": 0.17098896205425262,
|
| 38235 |
+
"learning_rate": 4.080224897304611e-05,
|
| 38236 |
+
"loss": 0.827,
|
| 38237 |
+
"step": 5461
|
| 38238 |
+
},
|
| 38239 |
+
{
|
| 38240 |
+
"epoch": 6.221082621082621,
|
| 38241 |
+
"grad_norm": 0.16605925559997559,
|
| 38242 |
+
"learning_rate": 4.07986383224075e-05,
|
| 38243 |
+
"loss": 0.777,
|
| 38244 |
+
"step": 5462
|
| 38245 |
+
},
|
| 38246 |
+
{
|
| 38247 |
+
"epoch": 6.222222222222222,
|
| 38248 |
+
"grad_norm": 0.17997348308563232,
|
| 38249 |
+
"learning_rate": 4.079502712303873e-05,
|
| 38250 |
+
"loss": 0.7636,
|
| 38251 |
+
"step": 5463
|
| 38252 |
+
},
|
| 38253 |
+
{
|
| 38254 |
+
"epoch": 6.223361823361824,
|
| 38255 |
+
"grad_norm": 0.22712866961956024,
|
| 38256 |
+
"learning_rate": 4.079141537506523e-05,
|
| 38257 |
+
"loss": 0.6999,
|
| 38258 |
+
"step": 5464
|
| 38259 |
+
},
|
| 38260 |
+
{
|
| 38261 |
+
"epoch": 6.224501424501424,
|
| 38262 |
+
"grad_norm": 0.22008147835731506,
|
| 38263 |
+
"learning_rate": 4.0787803078612455e-05,
|
| 38264 |
+
"loss": 0.7733,
|
| 38265 |
+
"step": 5465
|
| 38266 |
+
},
|
| 38267 |
+
{
|
| 38268 |
+
"epoch": 6.225641025641026,
|
| 38269 |
+
"grad_norm": 0.17507445812225342,
|
| 38270 |
+
"learning_rate": 4.0784190233805855e-05,
|
| 38271 |
+
"loss": 0.9629,
|
| 38272 |
+
"step": 5466
|
| 38273 |
+
},
|
| 38274 |
+
{
|
| 38275 |
+
"epoch": 6.226780626780627,
|
| 38276 |
+
"grad_norm": 0.20270459353923798,
|
| 38277 |
+
"learning_rate": 4.078057684077092e-05,
|
| 38278 |
+
"loss": 0.6832,
|
| 38279 |
+
"step": 5467
|
| 38280 |
+
},
|
| 38281 |
+
{
|
| 38282 |
+
"epoch": 6.227920227920228,
|
| 38283 |
+
"grad_norm": 0.1600881665945053,
|
| 38284 |
+
"learning_rate": 4.077696289963317e-05,
|
| 38285 |
+
"loss": 0.8731,
|
| 38286 |
+
"step": 5468
|
| 38287 |
+
},
|
| 38288 |
+
{
|
| 38289 |
+
"epoch": 6.229059829059829,
|
| 38290 |
+
"grad_norm": 0.2190249115228653,
|
| 38291 |
+
"learning_rate": 4.07733484105181e-05,
|
| 38292 |
+
"loss": 0.7833,
|
| 38293 |
+
"step": 5469
|
| 38294 |
+
},
|
| 38295 |
+
{
|
| 38296 |
+
"epoch": 6.230199430199431,
|
| 38297 |
+
"grad_norm": 0.16586245596408844,
|
| 38298 |
+
"learning_rate": 4.0769733373551254e-05,
|
| 38299 |
+
"loss": 0.6337,
|
| 38300 |
+
"step": 5470
|
| 38301 |
+
},
|
| 38302 |
+
{
|
| 38303 |
+
"epoch": 6.231339031339031,
|
| 38304 |
+
"grad_norm": 0.17984691262245178,
|
| 38305 |
+
"learning_rate": 4.076611778885822e-05,
|
| 38306 |
+
"loss": 0.6924,
|
| 38307 |
+
"step": 5471
|
| 38308 |
+
},
|
| 38309 |
+
{
|
| 38310 |
+
"epoch": 6.2324786324786325,
|
| 38311 |
+
"grad_norm": 0.17775210738182068,
|
| 38312 |
+
"learning_rate": 4.076250165656454e-05,
|
| 38313 |
+
"loss": 0.8526,
|
| 38314 |
+
"step": 5472
|
| 38315 |
+
},
|
| 38316 |
+
{
|
| 38317 |
+
"epoch": 6.233618233618234,
|
| 38318 |
+
"grad_norm": 0.17768071591854095,
|
| 38319 |
+
"learning_rate": 4.0758884976795843e-05,
|
| 38320 |
+
"loss": 0.6849,
|
| 38321 |
+
"step": 5473
|
| 38322 |
+
},
|
| 38323 |
+
{
|
| 38324 |
+
"epoch": 6.2347578347578345,
|
| 38325 |
+
"grad_norm": 0.17510420083999634,
|
| 38326 |
+
"learning_rate": 4.075526774967773e-05,
|
| 38327 |
+
"loss": 0.7369,
|
| 38328 |
+
"step": 5474
|
| 38329 |
+
},
|
| 38330 |
+
{
|
| 38331 |
+
"epoch": 6.235897435897436,
|
| 38332 |
+
"grad_norm": 0.17719455063343048,
|
| 38333 |
+
"learning_rate": 4.075164997533584e-05,
|
| 38334 |
+
"loss": 0.7602,
|
| 38335 |
+
"step": 5475
|
| 38336 |
+
},
|
| 38337 |
+
{
|
| 38338 |
+
"epoch": 6.237037037037037,
|
| 38339 |
+
"grad_norm": 0.1920306533575058,
|
| 38340 |
+
"learning_rate": 4.0748031653895823e-05,
|
| 38341 |
+
"loss": 0.719,
|
| 38342 |
+
"step": 5476
|
| 38343 |
+
},
|
| 38344 |
+
{
|
| 38345 |
+
"epoch": 6.238176638176638,
|
| 38346 |
+
"grad_norm": 0.1743188202381134,
|
| 38347 |
+
"learning_rate": 4.0744412785483375e-05,
|
| 38348 |
+
"loss": 0.7839,
|
| 38349 |
+
"step": 5477
|
| 38350 |
+
},
|
| 38351 |
+
{
|
| 38352 |
+
"epoch": 6.239316239316239,
|
| 38353 |
+
"grad_norm": 0.17863917350769043,
|
| 38354 |
+
"learning_rate": 4.0740793370224165e-05,
|
| 38355 |
+
"loss": 0.6877,
|
| 38356 |
+
"step": 5478
|
| 38357 |
+
},
|
| 38358 |
+
{
|
| 38359 |
+
"epoch": 6.240455840455841,
|
| 38360 |
+
"grad_norm": 0.18066370487213135,
|
| 38361 |
+
"learning_rate": 4.073717340824391e-05,
|
| 38362 |
+
"loss": 0.9225,
|
| 38363 |
+
"step": 5479
|
| 38364 |
+
},
|
| 38365 |
+
{
|
| 38366 |
+
"epoch": 6.241595441595441,
|
| 38367 |
+
"grad_norm": 0.17196287214756012,
|
| 38368 |
+
"learning_rate": 4.073355289966835e-05,
|
| 38369 |
+
"loss": 0.7665,
|
| 38370 |
+
"step": 5480
|
| 38371 |
+
},
|
| 38372 |
+
{
|
| 38373 |
+
"epoch": 6.242735042735043,
|
| 38374 |
+
"grad_norm": 0.19007204473018646,
|
| 38375 |
+
"learning_rate": 4.072993184462323e-05,
|
| 38376 |
+
"loss": 0.674,
|
| 38377 |
+
"step": 5481
|
| 38378 |
+
},
|
| 38379 |
+
{
|
| 38380 |
+
"epoch": 6.243874643874644,
|
| 38381 |
+
"grad_norm": 0.22861039638519287,
|
| 38382 |
+
"learning_rate": 4.072631024323431e-05,
|
| 38383 |
+
"loss": 0.4813,
|
| 38384 |
+
"step": 5482
|
| 38385 |
+
},
|
| 38386 |
+
{
|
| 38387 |
+
"epoch": 6.245014245014245,
|
| 38388 |
+
"grad_norm": 0.20271611213684082,
|
| 38389 |
+
"learning_rate": 4.07226880956274e-05,
|
| 38390 |
+
"loss": 0.5928,
|
| 38391 |
+
"step": 5483
|
| 38392 |
+
},
|
| 38393 |
+
{
|
| 38394 |
+
"epoch": 6.246153846153846,
|
| 38395 |
+
"grad_norm": 0.1714460551738739,
|
| 38396 |
+
"learning_rate": 4.071906540192829e-05,
|
| 38397 |
+
"loss": 0.6774,
|
| 38398 |
+
"step": 5484
|
| 38399 |
+
},
|
| 38400 |
+
{
|
| 38401 |
+
"epoch": 6.247293447293448,
|
| 38402 |
+
"grad_norm": 0.19361095130443573,
|
| 38403 |
+
"learning_rate": 4.071544216226281e-05,
|
| 38404 |
+
"loss": 0.4751,
|
| 38405 |
+
"step": 5485
|
| 38406 |
+
},
|
| 38407 |
+
{
|
| 38408 |
+
"epoch": 6.248433048433048,
|
| 38409 |
+
"grad_norm": 0.1699151247739792,
|
| 38410 |
+
"learning_rate": 4.0711818376756814e-05,
|
| 38411 |
+
"loss": 0.827,
|
| 38412 |
+
"step": 5486
|
| 38413 |
+
},
|
| 38414 |
+
{
|
| 38415 |
+
"epoch": 6.24957264957265,
|
| 38416 |
+
"grad_norm": 0.17237791419029236,
|
| 38417 |
+
"learning_rate": 4.0708194045536154e-05,
|
| 38418 |
+
"loss": 0.7743,
|
| 38419 |
+
"step": 5487
|
| 38420 |
+
},
|
| 38421 |
+
{
|
| 38422 |
+
"epoch": 6.250712250712251,
|
| 38423 |
+
"grad_norm": 0.17621074616909027,
|
| 38424 |
+
"learning_rate": 4.070456916872671e-05,
|
| 38425 |
+
"loss": 0.7688,
|
| 38426 |
+
"step": 5488
|
| 38427 |
+
},
|
| 38428 |
+
{
|
| 38429 |
+
"epoch": 6.2518518518518515,
|
| 38430 |
+
"grad_norm": 0.17917349934577942,
|
| 38431 |
+
"learning_rate": 4.07009437464544e-05,
|
| 38432 |
+
"loss": 0.7973,
|
| 38433 |
+
"step": 5489
|
| 38434 |
+
},
|
| 38435 |
+
{
|
| 38436 |
+
"epoch": 6.252991452991453,
|
| 38437 |
+
"grad_norm": 0.17991836369037628,
|
| 38438 |
+
"learning_rate": 4.069731777884512e-05,
|
| 38439 |
+
"loss": 0.8146,
|
| 38440 |
+
"step": 5490
|
| 38441 |
+
},
|
| 38442 |
+
{
|
| 38443 |
+
"epoch": 6.254131054131054,
|
| 38444 |
+
"grad_norm": 0.16662746667861938,
|
| 38445 |
+
"learning_rate": 4.069369126602485e-05,
|
| 38446 |
+
"loss": 0.886,
|
| 38447 |
+
"step": 5491
|
| 38448 |
+
},
|
| 38449 |
+
{
|
| 38450 |
+
"epoch": 6.255270655270655,
|
| 38451 |
+
"grad_norm": 0.19454513490200043,
|
| 38452 |
+
"learning_rate": 4.0690064208119505e-05,
|
| 38453 |
+
"loss": 0.7909,
|
| 38454 |
+
"step": 5492
|
| 38455 |
+
},
|
| 38456 |
+
{
|
| 38457 |
+
"epoch": 6.256410256410256,
|
| 38458 |
+
"grad_norm": 0.15574559569358826,
|
| 38459 |
+
"learning_rate": 4.068643660525509e-05,
|
| 38460 |
+
"loss": 0.7042,
|
| 38461 |
+
"step": 5493
|
| 38462 |
+
},
|
| 38463 |
+
{
|
| 38464 |
+
"epoch": 6.257549857549858,
|
| 38465 |
+
"grad_norm": 0.2107429802417755,
|
| 38466 |
+
"learning_rate": 4.0682808457557594e-05,
|
| 38467 |
+
"loss": 0.7224,
|
| 38468 |
+
"step": 5494
|
| 38469 |
+
},
|
| 38470 |
+
{
|
| 38471 |
+
"epoch": 6.258689458689458,
|
| 38472 |
+
"grad_norm": 0.18273282051086426,
|
| 38473 |
+
"learning_rate": 4.0679179765153035e-05,
|
| 38474 |
+
"loss": 0.9002,
|
| 38475 |
+
"step": 5495
|
| 38476 |
+
},
|
| 38477 |
+
{
|
| 38478 |
+
"epoch": 6.25982905982906,
|
| 38479 |
+
"grad_norm": 0.19854958355426788,
|
| 38480 |
+
"learning_rate": 4.067555052816744e-05,
|
| 38481 |
+
"loss": 0.7524,
|
| 38482 |
+
"step": 5496
|
| 38483 |
+
},
|
| 38484 |
+
{
|
| 38485 |
+
"epoch": 6.260968660968661,
|
| 38486 |
+
"grad_norm": 0.16223762929439545,
|
| 38487 |
+
"learning_rate": 4.0671920746726866e-05,
|
| 38488 |
+
"loss": 0.8428,
|
| 38489 |
+
"step": 5497
|
| 38490 |
+
},
|
| 38491 |
+
{
|
| 38492 |
+
"epoch": 6.262108262108262,
|
| 38493 |
+
"grad_norm": 0.16430439054965973,
|
| 38494 |
+
"learning_rate": 4.0668290420957395e-05,
|
| 38495 |
+
"loss": 0.8178,
|
| 38496 |
+
"step": 5498
|
| 38497 |
+
},
|
| 38498 |
+
{
|
| 38499 |
+
"epoch": 6.263247863247863,
|
| 38500 |
+
"grad_norm": 0.20250779390335083,
|
| 38501 |
+
"learning_rate": 4.0664659550985105e-05,
|
| 38502 |
+
"loss": 0.695,
|
| 38503 |
+
"step": 5499
|
| 38504 |
+
},
|
| 38505 |
+
{
|
| 38506 |
+
"epoch": 6.264387464387465,
|
| 38507 |
+
"grad_norm": 0.17243987321853638,
|
| 38508 |
+
"learning_rate": 4.066102813693611e-05,
|
| 38509 |
+
"loss": 0.7791,
|
| 38510 |
+
"step": 5500
|
| 38511 |
+
},
|
| 38512 |
+
{
|
| 38513 |
+
"epoch": 6.265527065527065,
|
| 38514 |
+
"grad_norm": 0.18005329370498657,
|
| 38515 |
+
"learning_rate": 4.0657396178936534e-05,
|
| 38516 |
+
"loss": 0.7831,
|
| 38517 |
+
"step": 5501
|
| 38518 |
+
},
|
| 38519 |
+
{
|
| 38520 |
+
"epoch": 6.266666666666667,
|
| 38521 |
+
"grad_norm": 0.20994611084461212,
|
| 38522 |
+
"learning_rate": 4.065376367711255e-05,
|
| 38523 |
+
"loss": 0.6416,
|
| 38524 |
+
"step": 5502
|
| 38525 |
+
},
|
| 38526 |
+
{
|
| 38527 |
+
"epoch": 6.267806267806268,
|
| 38528 |
+
"grad_norm": 0.18187794089317322,
|
| 38529 |
+
"learning_rate": 4.065013063159028e-05,
|
| 38530 |
+
"loss": 0.5668,
|
| 38531 |
+
"step": 5503
|
| 38532 |
+
},
|
| 38533 |
+
{
|
| 38534 |
+
"epoch": 6.268945868945869,
|
| 38535 |
+
"grad_norm": 0.20314699411392212,
|
| 38536 |
+
"learning_rate": 4.064649704249595e-05,
|
| 38537 |
+
"loss": 0.6542,
|
| 38538 |
+
"step": 5504
|
| 38539 |
+
},
|
| 38540 |
+
{
|
| 38541 |
+
"epoch": 6.27008547008547,
|
| 38542 |
+
"grad_norm": 0.20696061849594116,
|
| 38543 |
+
"learning_rate": 4.0642862909955745e-05,
|
| 38544 |
+
"loss": 0.6915,
|
| 38545 |
+
"step": 5505
|
| 38546 |
+
},
|
| 38547 |
+
{
|
| 38548 |
+
"epoch": 6.2712250712250714,
|
| 38549 |
+
"grad_norm": 0.19110968708992004,
|
| 38550 |
+
"learning_rate": 4.06392282340959e-05,
|
| 38551 |
+
"loss": 0.6842,
|
| 38552 |
+
"step": 5506
|
| 38553 |
+
},
|
| 38554 |
+
{
|
| 38555 |
+
"epoch": 6.272364672364672,
|
| 38556 |
+
"grad_norm": 0.2018856555223465,
|
| 38557 |
+
"learning_rate": 4.0635593015042636e-05,
|
| 38558 |
+
"loss": 0.7229,
|
| 38559 |
+
"step": 5507
|
| 38560 |
+
},
|
| 38561 |
+
{
|
| 38562 |
+
"epoch": 6.273504273504273,
|
| 38563 |
+
"grad_norm": 0.200718954205513,
|
| 38564 |
+
"learning_rate": 4.063195725292225e-05,
|
| 38565 |
+
"loss": 0.5362,
|
| 38566 |
+
"step": 5508
|
| 38567 |
+
},
|
| 38568 |
+
{
|
| 38569 |
+
"epoch": 6.274643874643875,
|
| 38570 |
+
"grad_norm": 0.18743805587291718,
|
| 38571 |
+
"learning_rate": 4.0628320947860985e-05,
|
| 38572 |
+
"loss": 0.8418,
|
| 38573 |
+
"step": 5509
|
| 38574 |
+
},
|
| 38575 |
+
{
|
| 38576 |
+
"epoch": 6.275783475783475,
|
| 38577 |
+
"grad_norm": 0.17090246081352234,
|
| 38578 |
+
"learning_rate": 4.062468409998515e-05,
|
| 38579 |
+
"loss": 0.7145,
|
| 38580 |
+
"step": 5510
|
| 38581 |
+
},
|
| 38582 |
+
{
|
| 38583 |
+
"epoch": 6.276923076923077,
|
| 38584 |
+
"grad_norm": 0.15754278004169464,
|
| 38585 |
+
"learning_rate": 4.062104670942108e-05,
|
| 38586 |
+
"loss": 0.7671,
|
| 38587 |
+
"step": 5511
|
| 38588 |
+
},
|
| 38589 |
+
{
|
| 38590 |
+
"epoch": 6.278062678062678,
|
| 38591 |
+
"grad_norm": 0.17991505563259125,
|
| 38592 |
+
"learning_rate": 4.06174087762951e-05,
|
| 38593 |
+
"loss": 0.776,
|
| 38594 |
+
"step": 5512
|
| 38595 |
+
},
|
| 38596 |
+
{
|
| 38597 |
+
"epoch": 6.279202279202279,
|
| 38598 |
+
"grad_norm": 0.18786561489105225,
|
| 38599 |
+
"learning_rate": 4.0613770300733565e-05,
|
| 38600 |
+
"loss": 0.718,
|
| 38601 |
+
"step": 5513
|
| 38602 |
+
},
|
| 38603 |
+
{
|
| 38604 |
+
"epoch": 6.28034188034188,
|
| 38605 |
+
"grad_norm": 0.2050205022096634,
|
| 38606 |
+
"learning_rate": 4.061013128286285e-05,
|
| 38607 |
+
"loss": 0.6767,
|
| 38608 |
+
"step": 5514
|
| 38609 |
+
},
|
| 38610 |
+
{
|
| 38611 |
+
"epoch": 6.281481481481482,
|
| 38612 |
+
"grad_norm": 0.17826548218727112,
|
| 38613 |
+
"learning_rate": 4.060649172280934e-05,
|
| 38614 |
+
"loss": 0.522,
|
| 38615 |
+
"step": 5515
|
| 38616 |
+
},
|
| 38617 |
+
{
|
| 38618 |
+
"epoch": 6.282621082621082,
|
| 38619 |
+
"grad_norm": 0.17450261116027832,
|
| 38620 |
+
"learning_rate": 4.060285162069946e-05,
|
| 38621 |
+
"loss": 0.916,
|
| 38622 |
+
"step": 5516
|
| 38623 |
+
},
|
| 38624 |
+
{
|
| 38625 |
+
"epoch": 6.283760683760684,
|
| 38626 |
+
"grad_norm": 0.2118103951215744,
|
| 38627 |
+
"learning_rate": 4.059921097665963e-05,
|
| 38628 |
+
"loss": 0.8111,
|
| 38629 |
+
"step": 5517
|
| 38630 |
+
},
|
| 38631 |
+
{
|
| 38632 |
+
"epoch": 6.284900284900285,
|
| 38633 |
+
"grad_norm": 0.16722458600997925,
|
| 38634 |
+
"learning_rate": 4.059556979081631e-05,
|
| 38635 |
+
"loss": 0.8077,
|
| 38636 |
+
"step": 5518
|
| 38637 |
+
},
|
| 38638 |
+
{
|
| 38639 |
+
"epoch": 6.286039886039886,
|
| 38640 |
+
"grad_norm": 0.18036098778247833,
|
| 38641 |
+
"learning_rate": 4.059192806329596e-05,
|
| 38642 |
+
"loss": 0.6988,
|
| 38643 |
+
"step": 5519
|
| 38644 |
+
},
|
| 38645 |
+
{
|
| 38646 |
+
"epoch": 6.287179487179487,
|
| 38647 |
+
"grad_norm": 0.20158371329307556,
|
| 38648 |
+
"learning_rate": 4.0588285794225076e-05,
|
| 38649 |
+
"loss": 0.7276,
|
| 38650 |
+
"step": 5520
|
| 38651 |
+
},
|
| 38652 |
+
{
|
| 38653 |
+
"epoch": 6.2883190883190885,
|
| 38654 |
+
"grad_norm": 0.15440712869167328,
|
| 38655 |
+
"learning_rate": 4.0584642983730146e-05,
|
| 38656 |
+
"loss": 0.8107,
|
| 38657 |
+
"step": 5521
|
| 38658 |
+
},
|
| 38659 |
+
{
|
| 38660 |
+
"epoch": 6.289458689458689,
|
| 38661 |
+
"grad_norm": 0.17782963812351227,
|
| 38662 |
+
"learning_rate": 4.058099963193772e-05,
|
| 38663 |
+
"loss": 0.84,
|
| 38664 |
+
"step": 5522
|
| 38665 |
+
},
|
| 38666 |
+
{
|
| 38667 |
+
"epoch": 6.2905982905982905,
|
| 38668 |
+
"grad_norm": 0.22440436482429504,
|
| 38669 |
+
"learning_rate": 4.0577355738974324e-05,
|
| 38670 |
+
"loss": 0.662,
|
| 38671 |
+
"step": 5523
|
| 38672 |
+
},
|
| 38673 |
+
{
|
| 38674 |
+
"epoch": 6.291737891737892,
|
| 38675 |
+
"grad_norm": 0.18663540482521057,
|
| 38676 |
+
"learning_rate": 4.057371130496652e-05,
|
| 38677 |
+
"loss": 0.7808,
|
| 38678 |
+
"step": 5524
|
| 38679 |
+
},
|
| 38680 |
+
{
|
| 38681 |
+
"epoch": 6.292877492877492,
|
| 38682 |
+
"grad_norm": 0.20182882249355316,
|
| 38683 |
+
"learning_rate": 4.0570066330040906e-05,
|
| 38684 |
+
"loss": 0.7635,
|
| 38685 |
+
"step": 5525
|
| 38686 |
+
},
|
| 38687 |
+
{
|
| 38688 |
+
"epoch": 6.294017094017094,
|
| 38689 |
+
"grad_norm": 0.16176316142082214,
|
| 38690 |
+
"learning_rate": 4.056642081432407e-05,
|
| 38691 |
+
"loss": 0.8451,
|
| 38692 |
+
"step": 5526
|
| 38693 |
+
},
|
| 38694 |
+
{
|
| 38695 |
+
"epoch": 6.295156695156695,
|
| 38696 |
+
"grad_norm": 0.1974044144153595,
|
| 38697 |
+
"learning_rate": 4.0562774757942624e-05,
|
| 38698 |
+
"loss": 0.6236,
|
| 38699 |
+
"step": 5527
|
| 38700 |
+
},
|
| 38701 |
+
{
|
| 38702 |
+
"epoch": 6.296296296296296,
|
| 38703 |
+
"grad_norm": 0.16082333028316498,
|
| 38704 |
+
"learning_rate": 4.055912816102321e-05,
|
| 38705 |
+
"loss": 0.8136,
|
| 38706 |
+
"step": 5528
|
| 38707 |
+
},
|
| 38708 |
+
{
|
| 38709 |
+
"epoch": 6.297435897435897,
|
| 38710 |
+
"grad_norm": 0.1818101704120636,
|
| 38711 |
+
"learning_rate": 4.055548102369249e-05,
|
| 38712 |
+
"loss": 0.7774,
|
| 38713 |
+
"step": 5529
|
| 38714 |
+
},
|
| 38715 |
+
{
|
| 38716 |
+
"epoch": 6.298575498575499,
|
| 38717 |
+
"grad_norm": 0.17527911067008972,
|
| 38718 |
+
"learning_rate": 4.055183334607714e-05,
|
| 38719 |
+
"loss": 0.7551,
|
| 38720 |
+
"step": 5530
|
| 38721 |
+
},
|
| 38722 |
+
{
|
| 38723 |
+
"epoch": 6.2997150997151,
|
| 38724 |
+
"grad_norm": 0.1772170513868332,
|
| 38725 |
+
"learning_rate": 4.054818512830385e-05,
|
| 38726 |
+
"loss": 0.8582,
|
| 38727 |
+
"step": 5531
|
| 38728 |
+
},
|
| 38729 |
+
{
|
| 38730 |
+
"epoch": 6.300854700854701,
|
| 38731 |
+
"grad_norm": 0.19636009633541107,
|
| 38732 |
+
"learning_rate": 4.054453637049933e-05,
|
| 38733 |
+
"loss": 0.582,
|
| 38734 |
+
"step": 5532
|
| 38735 |
+
},
|
| 38736 |
+
{
|
| 38737 |
+
"epoch": 6.301994301994302,
|
| 38738 |
+
"grad_norm": 0.1604292094707489,
|
| 38739 |
+
"learning_rate": 4.0540887072790326e-05,
|
| 38740 |
+
"loss": 0.8054,
|
| 38741 |
+
"step": 5533
|
| 38742 |
+
},
|
| 38743 |
+
{
|
| 38744 |
+
"epoch": 6.3031339031339035,
|
| 38745 |
+
"grad_norm": 0.1790705770254135,
|
| 38746 |
+
"learning_rate": 4.053723723530356e-05,
|
| 38747 |
+
"loss": 0.771,
|
| 38748 |
+
"step": 5534
|
| 38749 |
+
},
|
| 38750 |
+
{
|
| 38751 |
+
"epoch": 6.304273504273504,
|
| 38752 |
+
"grad_norm": 0.18854586780071259,
|
| 38753 |
+
"learning_rate": 4.0533586858165816e-05,
|
| 38754 |
+
"loss": 0.7078,
|
| 38755 |
+
"step": 5535
|
| 38756 |
+
},
|
| 38757 |
+
{
|
| 38758 |
+
"epoch": 6.3054131054131055,
|
| 38759 |
+
"grad_norm": 0.1725122183561325,
|
| 38760 |
+
"learning_rate": 4.0529935941503896e-05,
|
| 38761 |
+
"loss": 0.8923,
|
| 38762 |
+
"step": 5536
|
| 38763 |
+
},
|
| 38764 |
+
{
|
| 38765 |
+
"epoch": 6.306552706552707,
|
| 38766 |
+
"grad_norm": 0.18810155987739563,
|
| 38767 |
+
"learning_rate": 4.0526284485444585e-05,
|
| 38768 |
+
"loss": 0.8407,
|
| 38769 |
+
"step": 5537
|
| 38770 |
+
},
|
| 38771 |
+
{
|
| 38772 |
+
"epoch": 6.3076923076923075,
|
| 38773 |
+
"grad_norm": 0.21764864027500153,
|
| 38774 |
+
"learning_rate": 4.052263249011472e-05,
|
| 38775 |
+
"loss": 0.6224,
|
| 38776 |
+
"step": 5538
|
| 38777 |
+
},
|
| 38778 |
+
{
|
| 38779 |
+
"epoch": 6.308831908831909,
|
| 38780 |
+
"grad_norm": 0.20365047454833984,
|
| 38781 |
+
"learning_rate": 4.0518979955641144e-05,
|
| 38782 |
+
"loss": 0.7715,
|
| 38783 |
+
"step": 5539
|
| 38784 |
+
},
|
| 38785 |
+
{
|
| 38786 |
+
"epoch": 6.30997150997151,
|
| 38787 |
+
"grad_norm": 0.1990799754858017,
|
| 38788 |
+
"learning_rate": 4.051532688215071e-05,
|
| 38789 |
+
"loss": 0.6924,
|
| 38790 |
+
"step": 5540
|
| 38791 |
+
},
|
| 38792 |
+
{
|
| 38793 |
+
"epoch": 6.311111111111111,
|
| 38794 |
+
"grad_norm": 0.2261703908443451,
|
| 38795 |
+
"learning_rate": 4.0511673269770304e-05,
|
| 38796 |
+
"loss": 0.7812,
|
| 38797 |
+
"step": 5541
|
| 38798 |
+
},
|
| 38799 |
+
{
|
| 38800 |
+
"epoch": 6.312250712250712,
|
| 38801 |
+
"grad_norm": 0.1494823694229126,
|
| 38802 |
+
"learning_rate": 4.050801911862684e-05,
|
| 38803 |
+
"loss": 0.8382,
|
| 38804 |
+
"step": 5542
|
| 38805 |
+
},
|
| 38806 |
+
{
|
| 38807 |
+
"epoch": 6.313390313390314,
|
| 38808 |
+
"grad_norm": 0.19464197754859924,
|
| 38809 |
+
"learning_rate": 4.050436442884722e-05,
|
| 38810 |
+
"loss": 0.7306,
|
| 38811 |
+
"step": 5543
|
| 38812 |
+
},
|
| 38813 |
+
{
|
| 38814 |
+
"epoch": 6.314529914529914,
|
| 38815 |
+
"grad_norm": 0.20078547298908234,
|
| 38816 |
+
"learning_rate": 4.0500709200558375e-05,
|
| 38817 |
+
"loss": 0.7558,
|
| 38818 |
+
"step": 5544
|
| 38819 |
+
},
|
| 38820 |
+
{
|
| 38821 |
+
"epoch": 6.315669515669516,
|
| 38822 |
+
"grad_norm": 0.20504049956798553,
|
| 38823 |
+
"learning_rate": 4.049705343388729e-05,
|
| 38824 |
+
"loss": 0.578,
|
| 38825 |
+
"step": 5545
|
| 38826 |
+
},
|
| 38827 |
+
{
|
| 38828 |
+
"epoch": 6.316809116809117,
|
| 38829 |
+
"grad_norm": 0.2148253619670868,
|
| 38830 |
+
"learning_rate": 4.049339712896091e-05,
|
| 38831 |
+
"loss": 0.7114,
|
| 38832 |
+
"step": 5546
|
| 38833 |
+
},
|
| 38834 |
+
{
|
| 38835 |
+
"epoch": 6.317948717948718,
|
| 38836 |
+
"grad_norm": 0.1700192242860794,
|
| 38837 |
+
"learning_rate": 4.048974028590624e-05,
|
| 38838 |
+
"loss": 0.9176,
|
| 38839 |
+
"step": 5547
|
| 38840 |
+
},
|
| 38841 |
+
{
|
| 38842 |
+
"epoch": 6.319088319088319,
|
| 38843 |
+
"grad_norm": 0.18755079805850983,
|
| 38844 |
+
"learning_rate": 4.04860829048503e-05,
|
| 38845 |
+
"loss": 0.6967,
|
| 38846 |
+
"step": 5548
|
| 38847 |
+
},
|
| 38848 |
+
{
|
| 38849 |
+
"epoch": 6.320227920227921,
|
| 38850 |
+
"grad_norm": 0.15865486860275269,
|
| 38851 |
+
"learning_rate": 4.048242498592011e-05,
|
| 38852 |
+
"loss": 0.8662,
|
| 38853 |
+
"step": 5549
|
| 38854 |
+
},
|
| 38855 |
+
{
|
| 38856 |
+
"epoch": 6.321367521367521,
|
| 38857 |
+
"grad_norm": 0.17340147495269775,
|
| 38858 |
+
"learning_rate": 4.047876652924273e-05,
|
| 38859 |
+
"loss": 0.6638,
|
| 38860 |
+
"step": 5550
|
| 38861 |
+
},
|
| 38862 |
+
{
|
| 38863 |
+
"epoch": 6.3225071225071225,
|
| 38864 |
+
"grad_norm": 0.17811904847621918,
|
| 38865 |
+
"learning_rate": 4.047510753494521e-05,
|
| 38866 |
+
"loss": 0.681,
|
| 38867 |
+
"step": 5551
|
| 38868 |
+
},
|
| 38869 |
+
{
|
| 38870 |
+
"epoch": 6.323646723646724,
|
| 38871 |
+
"grad_norm": 0.16214832663536072,
|
| 38872 |
+
"learning_rate": 4.0471448003154654e-05,
|
| 38873 |
+
"loss": 0.8522,
|
| 38874 |
+
"step": 5552
|
| 38875 |
+
},
|
| 38876 |
+
{
|
| 38877 |
+
"epoch": 6.3247863247863245,
|
| 38878 |
+
"grad_norm": 0.192167729139328,
|
| 38879 |
+
"learning_rate": 4.046778793399816e-05,
|
| 38880 |
+
"loss": 0.7349,
|
| 38881 |
+
"step": 5553
|
| 38882 |
+
},
|
| 38883 |
+
{
|
| 38884 |
+
"epoch": 6.325925925925926,
|
| 38885 |
+
"grad_norm": 0.21371591091156006,
|
| 38886 |
+
"learning_rate": 4.0464127327602865e-05,
|
| 38887 |
+
"loss": 0.5996,
|
| 38888 |
+
"step": 5554
|
| 38889 |
+
},
|
| 38890 |
+
{
|
| 38891 |
+
"epoch": 6.327065527065527,
|
| 38892 |
+
"grad_norm": 0.231183260679245,
|
| 38893 |
+
"learning_rate": 4.046046618409589e-05,
|
| 38894 |
+
"loss": 0.6828,
|
| 38895 |
+
"step": 5555
|
| 38896 |
+
},
|
| 38897 |
+
{
|
| 38898 |
+
"epoch": 6.328205128205128,
|
| 38899 |
+
"grad_norm": 0.22443002462387085,
|
| 38900 |
+
"learning_rate": 4.0456804503604414e-05,
|
| 38901 |
+
"loss": 0.7126,
|
| 38902 |
+
"step": 5556
|
| 38903 |
+
},
|
| 38904 |
+
{
|
| 38905 |
+
"epoch": 6.329344729344729,
|
| 38906 |
+
"grad_norm": 0.19145648181438446,
|
| 38907 |
+
"learning_rate": 4.045314228625561e-05,
|
| 38908 |
+
"loss": 0.9129,
|
| 38909 |
+
"step": 5557
|
| 38910 |
+
},
|
| 38911 |
+
{
|
| 38912 |
+
"epoch": 6.330484330484331,
|
| 38913 |
+
"grad_norm": 0.19444787502288818,
|
| 38914 |
+
"learning_rate": 4.044947953217667e-05,
|
| 38915 |
+
"loss": 0.7147,
|
| 38916 |
+
"step": 5558
|
| 38917 |
+
},
|
| 38918 |
+
{
|
| 38919 |
+
"epoch": 6.331623931623931,
|
| 38920 |
+
"grad_norm": 0.16869063675403595,
|
| 38921 |
+
"learning_rate": 4.044581624149483e-05,
|
| 38922 |
+
"loss": 0.9214,
|
| 38923 |
+
"step": 5559
|
| 38924 |
+
},
|
| 38925 |
+
{
|
| 38926 |
+
"epoch": 6.332763532763533,
|
| 38927 |
+
"grad_norm": 0.1611240804195404,
|
| 38928 |
+
"learning_rate": 4.0442152414337305e-05,
|
| 38929 |
+
"loss": 0.8649,
|
| 38930 |
+
"step": 5560
|
| 38931 |
+
},
|
| 38932 |
+
{
|
| 38933 |
+
"epoch": 6.333903133903134,
|
| 38934 |
+
"grad_norm": 0.17310021817684174,
|
| 38935 |
+
"learning_rate": 4.043848805083137e-05,
|
| 38936 |
+
"loss": 0.7633,
|
| 38937 |
+
"step": 5561
|
| 38938 |
+
},
|
| 38939 |
+
{
|
| 38940 |
+
"epoch": 6.335042735042735,
|
| 38941 |
+
"grad_norm": 0.20856855809688568,
|
| 38942 |
+
"learning_rate": 4.043482315110429e-05,
|
| 38943 |
+
"loss": 0.707,
|
| 38944 |
+
"step": 5562
|
| 38945 |
+
},
|
| 38946 |
+
{
|
| 38947 |
+
"epoch": 6.336182336182336,
|
| 38948 |
+
"grad_norm": 0.2036934494972229,
|
| 38949 |
+
"learning_rate": 4.043115771528335e-05,
|
| 38950 |
+
"loss": 0.7533,
|
| 38951 |
+
"step": 5563
|
| 38952 |
+
},
|
| 38953 |
+
{
|
| 38954 |
+
"epoch": 6.337321937321938,
|
| 38955 |
+
"grad_norm": 0.17045928537845612,
|
| 38956 |
+
"learning_rate": 4.042749174349587e-05,
|
| 38957 |
+
"loss": 0.796,
|
| 38958 |
+
"step": 5564
|
| 38959 |
+
},
|
| 38960 |
+
{
|
| 38961 |
+
"epoch": 6.338461538461538,
|
| 38962 |
+
"grad_norm": 0.1955578476190567,
|
| 38963 |
+
"learning_rate": 4.0423825235869185e-05,
|
| 38964 |
+
"loss": 0.6873,
|
| 38965 |
+
"step": 5565
|
| 38966 |
+
},
|
| 38967 |
+
{
|
| 38968 |
+
"epoch": 6.33960113960114,
|
| 38969 |
+
"grad_norm": 0.15852148830890656,
|
| 38970 |
+
"learning_rate": 4.0420158192530624e-05,
|
| 38971 |
+
"loss": 0.8393,
|
| 38972 |
+
"step": 5566
|
| 38973 |
+
},
|
| 38974 |
+
{
|
| 38975 |
+
"epoch": 6.340740740740741,
|
| 38976 |
+
"grad_norm": 0.1966450959444046,
|
| 38977 |
+
"learning_rate": 4.041649061360756e-05,
|
| 38978 |
+
"loss": 0.6703,
|
| 38979 |
+
"step": 5567
|
| 38980 |
+
},
|
| 38981 |
+
{
|
| 38982 |
+
"epoch": 6.3418803418803416,
|
| 38983 |
+
"grad_norm": 0.16714483499526978,
|
| 38984 |
+
"learning_rate": 4.041282249922739e-05,
|
| 38985 |
+
"loss": 0.7973,
|
| 38986 |
+
"step": 5568
|
| 38987 |
+
},
|
| 38988 |
+
{
|
| 38989 |
+
"epoch": 6.343019943019943,
|
| 38990 |
+
"grad_norm": 0.18942955136299133,
|
| 38991 |
+
"learning_rate": 4.04091538495175e-05,
|
| 38992 |
+
"loss": 0.849,
|
| 38993 |
+
"step": 5569
|
| 38994 |
+
},
|
| 38995 |
+
{
|
| 38996 |
+
"epoch": 6.344159544159544,
|
| 38997 |
+
"grad_norm": 0.18266943097114563,
|
| 38998 |
+
"learning_rate": 4.040548466460533e-05,
|
| 38999 |
+
"loss": 0.7453,
|
| 39000 |
+
"step": 5570
|
| 39001 |
+
},
|
| 39002 |
+
{
|
| 39003 |
+
"epoch": 6.345299145299145,
|
| 39004 |
+
"grad_norm": 0.15580274164676666,
|
| 39005 |
+
"learning_rate": 4.040181494461831e-05,
|
| 39006 |
+
"loss": 0.8869,
|
| 39007 |
+
"step": 5571
|
| 39008 |
+
},
|
| 39009 |
+
{
|
| 39010 |
+
"epoch": 6.346438746438746,
|
| 39011 |
+
"grad_norm": 0.1870015263557434,
|
| 39012 |
+
"learning_rate": 4.0398144689683895e-05,
|
| 39013 |
+
"loss": 0.8276,
|
| 39014 |
+
"step": 5572
|
| 39015 |
+
},
|
| 39016 |
+
{
|
| 39017 |
+
"epoch": 6.347578347578348,
|
| 39018 |
+
"grad_norm": 0.16944514214992523,
|
| 39019 |
+
"learning_rate": 4.039447389992957e-05,
|
| 39020 |
+
"loss": 0.9026,
|
| 39021 |
+
"step": 5573
|
| 39022 |
+
},
|
| 39023 |
+
{
|
| 39024 |
+
"epoch": 6.348717948717948,
|
| 39025 |
+
"grad_norm": 0.19888898730278015,
|
| 39026 |
+
"learning_rate": 4.0390802575482836e-05,
|
| 39027 |
+
"loss": 0.7978,
|
| 39028 |
+
"step": 5574
|
| 39029 |
+
},
|
| 39030 |
+
{
|
| 39031 |
+
"epoch": 6.34985754985755,
|
| 39032 |
+
"grad_norm": 0.21368567645549774,
|
| 39033 |
+
"learning_rate": 4.038713071647121e-05,
|
| 39034 |
+
"loss": 0.6742,
|
| 39035 |
+
"step": 5575
|
| 39036 |
+
},
|
| 39037 |
+
{
|
| 39038 |
+
"epoch": 6.350997150997151,
|
| 39039 |
+
"grad_norm": 0.24270881712436676,
|
| 39040 |
+
"learning_rate": 4.038345832302221e-05,
|
| 39041 |
+
"loss": 0.6214,
|
| 39042 |
+
"step": 5576
|
| 39043 |
+
},
|
| 39044 |
+
{
|
| 39045 |
+
"epoch": 6.352136752136752,
|
| 39046 |
+
"grad_norm": 0.1544049084186554,
|
| 39047 |
+
"learning_rate": 4.03797853952634e-05,
|
| 39048 |
+
"loss": 0.9009,
|
| 39049 |
+
"step": 5577
|
| 39050 |
+
},
|
| 39051 |
+
{
|
| 39052 |
+
"epoch": 6.353276353276353,
|
| 39053 |
+
"grad_norm": 0.14882121980190277,
|
| 39054 |
+
"learning_rate": 4.037611193332236e-05,
|
| 39055 |
+
"loss": 0.8344,
|
| 39056 |
+
"step": 5578
|
| 39057 |
+
},
|
| 39058 |
+
{
|
| 39059 |
+
"epoch": 6.354415954415955,
|
| 39060 |
+
"grad_norm": 0.21202531456947327,
|
| 39061 |
+
"learning_rate": 4.0372437937326654e-05,
|
| 39062 |
+
"loss": 0.6494,
|
| 39063 |
+
"step": 5579
|
| 39064 |
+
},
|
| 39065 |
+
{
|
| 39066 |
+
"epoch": 6.355555555555555,
|
| 39067 |
+
"grad_norm": 0.15874454379081726,
|
| 39068 |
+
"learning_rate": 4.036876340740391e-05,
|
| 39069 |
+
"loss": 0.6908,
|
| 39070 |
+
"step": 5580
|
| 39071 |
+
},
|
| 39072 |
+
{
|
| 39073 |
+
"epoch": 6.356695156695157,
|
| 39074 |
+
"grad_norm": 0.19329917430877686,
|
| 39075 |
+
"learning_rate": 4.0365088343681746e-05,
|
| 39076 |
+
"loss": 0.7809,
|
| 39077 |
+
"step": 5581
|
| 39078 |
+
},
|
| 39079 |
+
{
|
| 39080 |
+
"epoch": 6.357834757834758,
|
| 39081 |
+
"grad_norm": 0.17928197979927063,
|
| 39082 |
+
"learning_rate": 4.0361412746287806e-05,
|
| 39083 |
+
"loss": 0.8637,
|
| 39084 |
+
"step": 5582
|
| 39085 |
+
},
|
| 39086 |
+
{
|
| 39087 |
+
"epoch": 6.358974358974359,
|
| 39088 |
+
"grad_norm": 0.23423759639263153,
|
| 39089 |
+
"learning_rate": 4.0357736615349765e-05,
|
| 39090 |
+
"loss": 0.5022,
|
| 39091 |
+
"step": 5583
|
| 39092 |
+
},
|
| 39093 |
+
{
|
| 39094 |
+
"epoch": 6.36011396011396,
|
| 39095 |
+
"grad_norm": 0.1744619607925415,
|
| 39096 |
+
"learning_rate": 4.035405995099529e-05,
|
| 39097 |
+
"loss": 0.792,
|
| 39098 |
+
"step": 5584
|
| 39099 |
+
},
|
| 39100 |
+
{
|
| 39101 |
+
"epoch": 6.3612535612535615,
|
| 39102 |
+
"grad_norm": 0.19806456565856934,
|
| 39103 |
+
"learning_rate": 4.035038275335209e-05,
|
| 39104 |
+
"loss": 0.6759,
|
| 39105 |
+
"step": 5585
|
| 39106 |
+
},
|
| 39107 |
+
{
|
| 39108 |
+
"epoch": 6.362393162393162,
|
| 39109 |
+
"grad_norm": 0.18646864593029022,
|
| 39110 |
+
"learning_rate": 4.034670502254789e-05,
|
| 39111 |
+
"loss": 0.7262,
|
| 39112 |
+
"step": 5586
|
| 39113 |
+
},
|
| 39114 |
+
{
|
| 39115 |
+
"epoch": 6.363532763532763,
|
| 39116 |
+
"grad_norm": 0.1802903264760971,
|
| 39117 |
+
"learning_rate": 4.0343026758710424e-05,
|
| 39118 |
+
"loss": 0.8121,
|
| 39119 |
+
"step": 5587
|
| 39120 |
+
},
|
| 39121 |
+
{
|
| 39122 |
+
"epoch": 6.364672364672365,
|
| 39123 |
+
"grad_norm": 0.1669279783964157,
|
| 39124 |
+
"learning_rate": 4.0339347961967434e-05,
|
| 39125 |
+
"loss": 0.7895,
|
| 39126 |
+
"step": 5588
|
| 39127 |
+
},
|
| 39128 |
+
{
|
| 39129 |
+
"epoch": 6.365811965811965,
|
| 39130 |
+
"grad_norm": 0.20458777248859406,
|
| 39131 |
+
"learning_rate": 4.033566863244671e-05,
|
| 39132 |
+
"loss": 0.7021,
|
| 39133 |
+
"step": 5589
|
| 39134 |
+
},
|
| 39135 |
+
{
|
| 39136 |
+
"epoch": 6.366951566951567,
|
| 39137 |
+
"grad_norm": 0.16863298416137695,
|
| 39138 |
+
"learning_rate": 4.033198877027604e-05,
|
| 39139 |
+
"loss": 0.8631,
|
| 39140 |
+
"step": 5590
|
| 39141 |
+
},
|
| 39142 |
+
{
|
| 39143 |
+
"epoch": 6.368091168091168,
|
| 39144 |
+
"grad_norm": 0.15161456167697906,
|
| 39145 |
+
"learning_rate": 4.032830837558324e-05,
|
| 39146 |
+
"loss": 0.8739,
|
| 39147 |
+
"step": 5591
|
| 39148 |
+
},
|
| 39149 |
+
{
|
| 39150 |
+
"epoch": 6.36923076923077,
|
| 39151 |
+
"grad_norm": 0.2144942432641983,
|
| 39152 |
+
"learning_rate": 4.032462744849613e-05,
|
| 39153 |
+
"loss": 0.811,
|
| 39154 |
+
"step": 5592
|
| 39155 |
+
},
|
| 39156 |
+
{
|
| 39157 |
+
"epoch": 6.37037037037037,
|
| 39158 |
+
"grad_norm": 0.19144073128700256,
|
| 39159 |
+
"learning_rate": 4.032094598914258e-05,
|
| 39160 |
+
"loss": 0.8182,
|
| 39161 |
+
"step": 5593
|
| 39162 |
+
},
|
| 39163 |
+
{
|
| 39164 |
+
"epoch": 6.371509971509972,
|
| 39165 |
+
"grad_norm": 0.1798471063375473,
|
| 39166 |
+
"learning_rate": 4.0317263997650435e-05,
|
| 39167 |
+
"loss": 0.8006,
|
| 39168 |
+
"step": 5594
|
| 39169 |
+
},
|
| 39170 |
+
{
|
| 39171 |
+
"epoch": 6.372649572649573,
|
| 39172 |
+
"grad_norm": 0.16783884167671204,
|
| 39173 |
+
"learning_rate": 4.0313581474147585e-05,
|
| 39174 |
+
"loss": 0.8669,
|
| 39175 |
+
"step": 5595
|
| 39176 |
+
},
|
| 39177 |
+
{
|
| 39178 |
+
"epoch": 6.373789173789174,
|
| 39179 |
+
"grad_norm": 0.26721659302711487,
|
| 39180 |
+
"learning_rate": 4.0309898418761935e-05,
|
| 39181 |
+
"loss": 0.4397,
|
| 39182 |
+
"step": 5596
|
| 39183 |
+
},
|
| 39184 |
+
{
|
| 39185 |
+
"epoch": 6.374928774928775,
|
| 39186 |
+
"grad_norm": 0.18910394608974457,
|
| 39187 |
+
"learning_rate": 4.030621483162142e-05,
|
| 39188 |
+
"loss": 0.6172,
|
| 39189 |
+
"step": 5597
|
| 39190 |
+
},
|
| 39191 |
+
{
|
| 39192 |
+
"epoch": 6.3760683760683765,
|
| 39193 |
+
"grad_norm": 0.17705880105495453,
|
| 39194 |
+
"learning_rate": 4.030253071285397e-05,
|
| 39195 |
+
"loss": 0.6707,
|
| 39196 |
+
"step": 5598
|
| 39197 |
+
},
|
| 39198 |
+
{
|
| 39199 |
+
"epoch": 6.377207977207977,
|
| 39200 |
+
"grad_norm": 0.17414258420467377,
|
| 39201 |
+
"learning_rate": 4.029884606258755e-05,
|
| 39202 |
+
"loss": 0.8989,
|
| 39203 |
+
"step": 5599
|
| 39204 |
+
},
|
| 39205 |
+
{
|
| 39206 |
+
"epoch": 6.3783475783475785,
|
| 39207 |
+
"grad_norm": 0.18619024753570557,
|
| 39208 |
+
"learning_rate": 4.029516088095012e-05,
|
| 39209 |
+
"loss": 0.8322,
|
| 39210 |
+
"step": 5600
|
| 39211 |
+
},
|
| 39212 |
+
{
|
| 39213 |
+
"epoch": 6.37948717948718,
|
| 39214 |
+
"grad_norm": 0.2084839940071106,
|
| 39215 |
+
"learning_rate": 4.0291475168069704e-05,
|
| 39216 |
+
"loss": 0.7855,
|
| 39217 |
+
"step": 5601
|
| 39218 |
+
},
|
| 39219 |
+
{
|
| 39220 |
+
"epoch": 6.3806267806267805,
|
| 39221 |
+
"grad_norm": 0.19497095048427582,
|
| 39222 |
+
"learning_rate": 4.02877889240743e-05,
|
| 39223 |
+
"loss": 0.7825,
|
| 39224 |
+
"step": 5602
|
| 39225 |
+
},
|
| 39226 |
+
{
|
| 39227 |
+
"epoch": 6.381766381766382,
|
| 39228 |
+
"grad_norm": 0.18872429430484772,
|
| 39229 |
+
"learning_rate": 4.028410214909194e-05,
|
| 39230 |
+
"loss": 0.823,
|
| 39231 |
+
"step": 5603
|
| 39232 |
+
},
|
| 39233 |
+
{
|
| 39234 |
+
"epoch": 6.382905982905983,
|
| 39235 |
+
"grad_norm": 0.16437706351280212,
|
| 39236 |
+
"learning_rate": 4.0280414843250694e-05,
|
| 39237 |
+
"loss": 0.7583,
|
| 39238 |
+
"step": 5604
|
| 39239 |
+
},
|
| 39240 |
+
{
|
| 39241 |
+
"epoch": 6.384045584045584,
|
| 39242 |
+
"grad_norm": 0.1967761516571045,
|
| 39243 |
+
"learning_rate": 4.0276727006678605e-05,
|
| 39244 |
+
"loss": 0.7592,
|
| 39245 |
+
"step": 5605
|
| 39246 |
+
},
|
| 39247 |
+
{
|
| 39248 |
+
"epoch": 6.385185185185185,
|
| 39249 |
+
"grad_norm": 0.18910476565361023,
|
| 39250 |
+
"learning_rate": 4.027303863950378e-05,
|
| 39251 |
+
"loss": 0.78,
|
| 39252 |
+
"step": 5606
|
| 39253 |
+
},
|
| 39254 |
+
{
|
| 39255 |
+
"epoch": 6.386324786324787,
|
| 39256 |
+
"grad_norm": 0.19769850373268127,
|
| 39257 |
+
"learning_rate": 4.026934974185432e-05,
|
| 39258 |
+
"loss": 0.6605,
|
| 39259 |
+
"step": 5607
|
| 39260 |
+
},
|
| 39261 |
+
{
|
| 39262 |
+
"epoch": 6.387464387464387,
|
| 39263 |
+
"grad_norm": 0.16382963955402374,
|
| 39264 |
+
"learning_rate": 4.026566031385836e-05,
|
| 39265 |
+
"loss": 0.7627,
|
| 39266 |
+
"step": 5608
|
| 39267 |
+
},
|
| 39268 |
+
{
|
| 39269 |
+
"epoch": 6.388603988603989,
|
| 39270 |
+
"grad_norm": 0.21894732117652893,
|
| 39271 |
+
"learning_rate": 4.0261970355644035e-05,
|
| 39272 |
+
"loss": 0.4727,
|
| 39273 |
+
"step": 5609
|
| 39274 |
+
},
|
| 39275 |
+
{
|
| 39276 |
+
"epoch": 6.38974358974359,
|
| 39277 |
+
"grad_norm": 0.15893937647342682,
|
| 39278 |
+
"learning_rate": 4.025827986733951e-05,
|
| 39279 |
+
"loss": 0.8326,
|
| 39280 |
+
"step": 5610
|
| 39281 |
+
},
|
| 39282 |
+
{
|
| 39283 |
+
"epoch": 6.390883190883191,
|
| 39284 |
+
"grad_norm": 0.18021126091480255,
|
| 39285 |
+
"learning_rate": 4.025458884907296e-05,
|
| 39286 |
+
"loss": 0.7186,
|
| 39287 |
+
"step": 5611
|
| 39288 |
+
},
|
| 39289 |
+
{
|
| 39290 |
+
"epoch": 6.392022792022792,
|
| 39291 |
+
"grad_norm": 0.1703164279460907,
|
| 39292 |
+
"learning_rate": 4.025089730097258e-05,
|
| 39293 |
+
"loss": 0.8183,
|
| 39294 |
+
"step": 5612
|
| 39295 |
+
},
|
| 39296 |
+
{
|
| 39297 |
+
"epoch": 6.3931623931623935,
|
| 39298 |
+
"grad_norm": 0.20678535103797913,
|
| 39299 |
+
"learning_rate": 4.024720522316661e-05,
|
| 39300 |
+
"loss": 0.7038,
|
| 39301 |
+
"step": 5613
|
| 39302 |
+
},
|
| 39303 |
+
{
|
| 39304 |
+
"epoch": 6.394301994301994,
|
| 39305 |
+
"grad_norm": 0.18387947976589203,
|
| 39306 |
+
"learning_rate": 4.024351261578328e-05,
|
| 39307 |
+
"loss": 0.8208,
|
| 39308 |
+
"step": 5614
|
| 39309 |
+
},
|
| 39310 |
+
{
|
| 39311 |
+
"epoch": 6.3954415954415955,
|
| 39312 |
+
"grad_norm": 0.17696422338485718,
|
| 39313 |
+
"learning_rate": 4.023981947895082e-05,
|
| 39314 |
+
"loss": 0.9805,
|
| 39315 |
+
"step": 5615
|
| 39316 |
+
},
|
| 39317 |
+
{
|
| 39318 |
+
"epoch": 6.396581196581197,
|
| 39319 |
+
"grad_norm": 0.1638094037771225,
|
| 39320 |
+
"learning_rate": 4.023612581279752e-05,
|
| 39321 |
+
"loss": 0.7836,
|
| 39322 |
+
"step": 5616
|
| 39323 |
+
},
|
| 39324 |
+
{
|
| 39325 |
+
"epoch": 6.3977207977207975,
|
| 39326 |
+
"grad_norm": 0.14453627169132233,
|
| 39327 |
+
"learning_rate": 4.023243161745168e-05,
|
| 39328 |
+
"loss": 0.8727,
|
| 39329 |
+
"step": 5617
|
| 39330 |
+
},
|
| 39331 |
+
{
|
| 39332 |
+
"epoch": 6.398860398860399,
|
| 39333 |
+
"grad_norm": 0.18408818542957306,
|
| 39334 |
+
"learning_rate": 4.02287368930416e-05,
|
| 39335 |
+
"loss": 0.7912,
|
| 39336 |
+
"step": 5618
|
| 39337 |
+
},
|
| 39338 |
+
{
|
| 39339 |
+
"epoch": 6.4,
|
| 39340 |
+
"grad_norm": 0.1662292629480362,
|
| 39341 |
+
"learning_rate": 4.0225041639695607e-05,
|
| 39342 |
+
"loss": 0.6997,
|
| 39343 |
+
"step": 5619
|
| 39344 |
+
},
|
| 39345 |
+
{
|
| 39346 |
+
"epoch": 6.401139601139601,
|
| 39347 |
+
"grad_norm": 0.18224625289440155,
|
| 39348 |
+
"learning_rate": 4.022134585754205e-05,
|
| 39349 |
+
"loss": 0.9088,
|
| 39350 |
+
"step": 5620
|
| 39351 |
+
},
|
| 39352 |
+
{
|
| 39353 |
+
"epoch": 6.402279202279202,
|
| 39354 |
+
"grad_norm": 0.19629694521427155,
|
| 39355 |
+
"learning_rate": 4.021764954670929e-05,
|
| 39356 |
+
"loss": 0.745,
|
| 39357 |
+
"step": 5621
|
| 39358 |
+
},
|
| 39359 |
+
{
|
| 39360 |
+
"epoch": 6.403418803418804,
|
| 39361 |
+
"grad_norm": 0.16984345018863678,
|
| 39362 |
+
"learning_rate": 4.021395270732571e-05,
|
| 39363 |
+
"loss": 0.7422,
|
| 39364 |
+
"step": 5622
|
| 39365 |
+
},
|
| 39366 |
+
{
|
| 39367 |
+
"epoch": 6.404558404558404,
|
| 39368 |
+
"grad_norm": 0.2379043996334076,
|
| 39369 |
+
"learning_rate": 4.021025533951972e-05,
|
| 39370 |
+
"loss": 0.4332,
|
| 39371 |
+
"step": 5623
|
| 39372 |
+
},
|
| 39373 |
+
{
|
| 39374 |
+
"epoch": 6.405698005698006,
|
| 39375 |
+
"grad_norm": 0.19199815392494202,
|
| 39376 |
+
"learning_rate": 4.020655744341973e-05,
|
| 39377 |
+
"loss": 0.8657,
|
| 39378 |
+
"step": 5624
|
| 39379 |
+
},
|
| 39380 |
+
{
|
| 39381 |
+
"epoch": 6.406837606837607,
|
| 39382 |
+
"grad_norm": 0.18495675921440125,
|
| 39383 |
+
"learning_rate": 4.020285901915418e-05,
|
| 39384 |
+
"loss": 0.7719,
|
| 39385 |
+
"step": 5625
|
| 39386 |
+
},
|
| 39387 |
+
{
|
| 39388 |
+
"epoch": 6.407977207977208,
|
| 39389 |
+
"grad_norm": 0.1718648225069046,
|
| 39390 |
+
"learning_rate": 4.019916006685154e-05,
|
| 39391 |
+
"loss": 0.7742,
|
| 39392 |
+
"step": 5626
|
| 39393 |
+
},
|
| 39394 |
+
{
|
| 39395 |
+
"epoch": 6.409116809116809,
|
| 39396 |
+
"grad_norm": 0.2106252759695053,
|
| 39397 |
+
"learning_rate": 4.019546058664026e-05,
|
| 39398 |
+
"loss": 0.6134,
|
| 39399 |
+
"step": 5627
|
| 39400 |
+
},
|
| 39401 |
+
{
|
| 39402 |
+
"epoch": 6.410256410256411,
|
| 39403 |
+
"grad_norm": 0.22573627531528473,
|
| 39404 |
+
"learning_rate": 4.0191760578648844e-05,
|
| 39405 |
+
"loss": 0.5967,
|
| 39406 |
+
"step": 5628
|
| 39407 |
+
},
|
| 39408 |
+
{
|
| 39409 |
+
"epoch": 6.411396011396011,
|
| 39410 |
+
"grad_norm": 0.2238600254058838,
|
| 39411 |
+
"learning_rate": 4.0188060043005814e-05,
|
| 39412 |
+
"loss": 0.6215,
|
| 39413 |
+
"step": 5629
|
| 39414 |
+
},
|
| 39415 |
+
{
|
| 39416 |
+
"epoch": 6.4125356125356126,
|
| 39417 |
+
"grad_norm": 0.15070021152496338,
|
| 39418 |
+
"learning_rate": 4.018435897983969e-05,
|
| 39419 |
+
"loss": 0.774,
|
| 39420 |
+
"step": 5630
|
| 39421 |
+
},
|
| 39422 |
+
{
|
| 39423 |
+
"epoch": 6.413675213675214,
|
| 39424 |
+
"grad_norm": 0.21966534852981567,
|
| 39425 |
+
"learning_rate": 4.018065738927902e-05,
|
| 39426 |
+
"loss": 0.7222,
|
| 39427 |
+
"step": 5631
|
| 39428 |
+
},
|
| 39429 |
+
{
|
| 39430 |
+
"epoch": 6.4148148148148145,
|
| 39431 |
+
"grad_norm": 0.2008989304304123,
|
| 39432 |
+
"learning_rate": 4.017695527145238e-05,
|
| 39433 |
+
"loss": 0.7044,
|
| 39434 |
+
"step": 5632
|
| 39435 |
+
},
|
| 39436 |
+
{
|
| 39437 |
+
"epoch": 6.415954415954416,
|
| 39438 |
+
"grad_norm": 0.16906078159809113,
|
| 39439 |
+
"learning_rate": 4.0173252626488335e-05,
|
| 39440 |
+
"loss": 0.7342,
|
| 39441 |
+
"step": 5633
|
| 39442 |
+
},
|
| 39443 |
+
{
|
| 39444 |
+
"epoch": 6.417094017094017,
|
| 39445 |
+
"grad_norm": 0.14185194671154022,
|
| 39446 |
+
"learning_rate": 4.01695494545155e-05,
|
| 39447 |
+
"loss": 0.9029,
|
| 39448 |
+
"step": 5634
|
| 39449 |
+
},
|
| 39450 |
+
{
|
| 39451 |
+
"epoch": 6.418233618233618,
|
| 39452 |
+
"grad_norm": 0.17673517763614655,
|
| 39453 |
+
"learning_rate": 4.0165845755662504e-05,
|
| 39454 |
+
"loss": 0.8179,
|
| 39455 |
+
"step": 5635
|
| 39456 |
+
},
|
| 39457 |
+
{
|
| 39458 |
+
"epoch": 6.419373219373219,
|
| 39459 |
+
"grad_norm": 0.2244737297296524,
|
| 39460 |
+
"learning_rate": 4.016214153005797e-05,
|
| 39461 |
+
"loss": 0.648,
|
| 39462 |
+
"step": 5636
|
| 39463 |
+
},
|
| 39464 |
+
{
|
| 39465 |
+
"epoch": 6.420512820512821,
|
| 39466 |
+
"grad_norm": 0.23522430658340454,
|
| 39467 |
+
"learning_rate": 4.015843677783057e-05,
|
| 39468 |
+
"loss": 0.5819,
|
| 39469 |
+
"step": 5637
|
| 39470 |
+
},
|
| 39471 |
+
{
|
| 39472 |
+
"epoch": 6.421652421652421,
|
| 39473 |
+
"grad_norm": 0.16448065638542175,
|
| 39474 |
+
"learning_rate": 4.0154731499108975e-05,
|
| 39475 |
+
"loss": 0.823,
|
| 39476 |
+
"step": 5638
|
| 39477 |
+
},
|
| 39478 |
+
{
|
| 39479 |
+
"epoch": 6.422792022792023,
|
| 39480 |
+
"grad_norm": 0.18005219101905823,
|
| 39481 |
+
"learning_rate": 4.0151025694021884e-05,
|
| 39482 |
+
"loss": 0.7005,
|
| 39483 |
+
"step": 5639
|
| 39484 |
+
},
|
| 39485 |
+
{
|
| 39486 |
+
"epoch": 6.423931623931624,
|
| 39487 |
+
"grad_norm": 0.22259432077407837,
|
| 39488 |
+
"learning_rate": 4.0147319362697997e-05,
|
| 39489 |
+
"loss": 0.5743,
|
| 39490 |
+
"step": 5640
|
| 39491 |
+
},
|
| 39492 |
+
{
|
| 39493 |
+
"epoch": 6.425071225071225,
|
| 39494 |
+
"grad_norm": 0.19946357607841492,
|
| 39495 |
+
"learning_rate": 4.0143612505266055e-05,
|
| 39496 |
+
"loss": 0.7333,
|
| 39497 |
+
"step": 5641
|
| 39498 |
+
},
|
| 39499 |
+
{
|
| 39500 |
+
"epoch": 6.426210826210826,
|
| 39501 |
+
"grad_norm": 0.2001507580280304,
|
| 39502 |
+
"learning_rate": 4.01399051218548e-05,
|
| 39503 |
+
"loss": 0.8802,
|
| 39504 |
+
"step": 5642
|
| 39505 |
+
},
|
| 39506 |
+
{
|
| 39507 |
+
"epoch": 6.427350427350428,
|
| 39508 |
+
"grad_norm": 0.1886977255344391,
|
| 39509 |
+
"learning_rate": 4.013619721259302e-05,
|
| 39510 |
+
"loss": 0.6688,
|
| 39511 |
+
"step": 5643
|
| 39512 |
+
},
|
| 39513 |
+
{
|
| 39514 |
+
"epoch": 6.428490028490028,
|
| 39515 |
+
"grad_norm": 0.19466671347618103,
|
| 39516 |
+
"learning_rate": 4.013248877760948e-05,
|
| 39517 |
+
"loss": 0.7361,
|
| 39518 |
+
"step": 5644
|
| 39519 |
+
},
|
| 39520 |
+
{
|
| 39521 |
+
"epoch": 6.42962962962963,
|
| 39522 |
+
"grad_norm": 0.19370336830615997,
|
| 39523 |
+
"learning_rate": 4.012877981703298e-05,
|
| 39524 |
+
"loss": 0.7927,
|
| 39525 |
+
"step": 5645
|
| 39526 |
+
},
|
| 39527 |
+
{
|
| 39528 |
+
"epoch": 6.430769230769231,
|
| 39529 |
+
"grad_norm": 0.17426654696464539,
|
| 39530 |
+
"learning_rate": 4.0125070330992366e-05,
|
| 39531 |
+
"loss": 0.8787,
|
| 39532 |
+
"step": 5646
|
| 39533 |
+
},
|
| 39534 |
+
{
|
| 39535 |
+
"epoch": 6.431908831908832,
|
| 39536 |
+
"grad_norm": 0.1852133572101593,
|
| 39537 |
+
"learning_rate": 4.0121360319616453e-05,
|
| 39538 |
+
"loss": 0.7635,
|
| 39539 |
+
"step": 5647
|
| 39540 |
+
},
|
| 39541 |
+
{
|
| 39542 |
+
"epoch": 6.433048433048433,
|
| 39543 |
+
"grad_norm": 0.18585824966430664,
|
| 39544 |
+
"learning_rate": 4.0117649783034124e-05,
|
| 39545 |
+
"loss": 0.8038,
|
| 39546 |
+
"step": 5648
|
| 39547 |
+
},
|
| 39548 |
+
{
|
| 39549 |
+
"epoch": 6.434188034188034,
|
| 39550 |
+
"grad_norm": 0.13975170254707336,
|
| 39551 |
+
"learning_rate": 4.011393872137424e-05,
|
| 39552 |
+
"loss": 0.9754,
|
| 39553 |
+
"step": 5649
|
| 39554 |
+
},
|
| 39555 |
+
{
|
| 39556 |
+
"epoch": 6.435327635327635,
|
| 39557 |
+
"grad_norm": 0.17845340073108673,
|
| 39558 |
+
"learning_rate": 4.01102271347657e-05,
|
| 39559 |
+
"loss": 0.6753,
|
| 39560 |
+
"step": 5650
|
| 39561 |
+
},
|
| 39562 |
+
{
|
| 39563 |
+
"epoch": 6.436467236467236,
|
| 39564 |
+
"grad_norm": 0.21644507348537445,
|
| 39565 |
+
"learning_rate": 4.010651502333742e-05,
|
| 39566 |
+
"loss": 0.5942,
|
| 39567 |
+
"step": 5651
|
| 39568 |
+
},
|
| 39569 |
+
{
|
| 39570 |
+
"epoch": 6.437606837606838,
|
| 39571 |
+
"grad_norm": 0.2078523337841034,
|
| 39572 |
+
"learning_rate": 4.0102802387218324e-05,
|
| 39573 |
+
"loss": 0.7106,
|
| 39574 |
+
"step": 5652
|
| 39575 |
+
},
|
| 39576 |
+
{
|
| 39577 |
+
"epoch": 6.438746438746438,
|
| 39578 |
+
"grad_norm": 0.2149255871772766,
|
| 39579 |
+
"learning_rate": 4.0099089226537376e-05,
|
| 39580 |
+
"loss": 0.7849,
|
| 39581 |
+
"step": 5653
|
| 39582 |
+
},
|
| 39583 |
+
{
|
| 39584 |
+
"epoch": 6.43988603988604,
|
| 39585 |
+
"grad_norm": 0.23576869070529938,
|
| 39586 |
+
"learning_rate": 4.009537554142353e-05,
|
| 39587 |
+
"loss": 0.6039,
|
| 39588 |
+
"step": 5654
|
| 39589 |
+
},
|
| 39590 |
+
{
|
| 39591 |
+
"epoch": 6.441025641025641,
|
| 39592 |
+
"grad_norm": 0.18726636469364166,
|
| 39593 |
+
"learning_rate": 4.009166133200578e-05,
|
| 39594 |
+
"loss": 0.9907,
|
| 39595 |
+
"step": 5655
|
| 39596 |
+
},
|
| 39597 |
+
{
|
| 39598 |
+
"epoch": 6.442165242165242,
|
| 39599 |
+
"grad_norm": 0.16134890913963318,
|
| 39600 |
+
"learning_rate": 4.0087946598413136e-05,
|
| 39601 |
+
"loss": 0.8894,
|
| 39602 |
+
"step": 5656
|
| 39603 |
+
},
|
| 39604 |
+
{
|
| 39605 |
+
"epoch": 6.443304843304843,
|
| 39606 |
+
"grad_norm": 0.17697754502296448,
|
| 39607 |
+
"learning_rate": 4.008423134077461e-05,
|
| 39608 |
+
"loss": 0.7024,
|
| 39609 |
+
"step": 5657
|
| 39610 |
+
},
|
| 39611 |
+
{
|
| 39612 |
+
"epoch": 6.444444444444445,
|
| 39613 |
+
"grad_norm": 0.17293867468833923,
|
| 39614 |
+
"learning_rate": 4.008051555921925e-05,
|
| 39615 |
+
"loss": 0.9143,
|
| 39616 |
+
"step": 5658
|
| 39617 |
+
},
|
| 39618 |
+
{
|
| 39619 |
+
"epoch": 6.445584045584045,
|
| 39620 |
+
"grad_norm": 0.15596815943717957,
|
| 39621 |
+
"learning_rate": 4.007679925387611e-05,
|
| 39622 |
+
"loss": 0.7836,
|
| 39623 |
+
"step": 5659
|
| 39624 |
+
},
|
| 39625 |
+
{
|
| 39626 |
+
"epoch": 6.446723646723647,
|
| 39627 |
+
"grad_norm": 0.18265388906002045,
|
| 39628 |
+
"learning_rate": 4.007308242487427e-05,
|
| 39629 |
+
"loss": 0.7222,
|
| 39630 |
+
"step": 5660
|
| 39631 |
+
},
|
| 39632 |
+
{
|
| 39633 |
+
"epoch": 6.447863247863248,
|
| 39634 |
+
"grad_norm": 0.17139224708080292,
|
| 39635 |
+
"learning_rate": 4.006936507234284e-05,
|
| 39636 |
+
"loss": 0.9408,
|
| 39637 |
+
"step": 5661
|
| 39638 |
+
},
|
| 39639 |
+
{
|
| 39640 |
+
"epoch": 6.449002849002849,
|
| 39641 |
+
"grad_norm": 0.2636291980743408,
|
| 39642 |
+
"learning_rate": 4.0065647196410894e-05,
|
| 39643 |
+
"loss": 0.5335,
|
| 39644 |
+
"step": 5662
|
| 39645 |
+
},
|
| 39646 |
+
{
|
| 39647 |
+
"epoch": 6.45014245014245,
|
| 39648 |
+
"grad_norm": 0.16780348122119904,
|
| 39649 |
+
"learning_rate": 4.006192879720761e-05,
|
| 39650 |
+
"loss": 0.7985,
|
| 39651 |
+
"step": 5663
|
| 39652 |
+
},
|
| 39653 |
+
{
|
| 39654 |
+
"epoch": 6.4512820512820515,
|
| 39655 |
+
"grad_norm": 0.17742887139320374,
|
| 39656 |
+
"learning_rate": 4.005820987486211e-05,
|
| 39657 |
+
"loss": 0.7793,
|
| 39658 |
+
"step": 5664
|
| 39659 |
+
},
|
| 39660 |
+
{
|
| 39661 |
+
"epoch": 6.452421652421652,
|
| 39662 |
+
"grad_norm": 0.18413466215133667,
|
| 39663 |
+
"learning_rate": 4.005449042950358e-05,
|
| 39664 |
+
"loss": 0.6578,
|
| 39665 |
+
"step": 5665
|
| 39666 |
+
},
|
| 39667 |
+
{
|
| 39668 |
+
"epoch": 6.453561253561253,
|
| 39669 |
+
"grad_norm": 0.19075767695903778,
|
| 39670 |
+
"learning_rate": 4.005077046126119e-05,
|
| 39671 |
+
"loss": 0.6387,
|
| 39672 |
+
"step": 5666
|
| 39673 |
+
},
|
| 39674 |
+
{
|
| 39675 |
+
"epoch": 6.454700854700855,
|
| 39676 |
+
"grad_norm": 0.15881739556789398,
|
| 39677 |
+
"learning_rate": 4.004704997026415e-05,
|
| 39678 |
+
"loss": 0.8274,
|
| 39679 |
+
"step": 5667
|
| 39680 |
+
},
|
| 39681 |
+
{
|
| 39682 |
+
"epoch": 6.455840455840455,
|
| 39683 |
+
"grad_norm": 0.15998823940753937,
|
| 39684 |
+
"learning_rate": 4.004332895664169e-05,
|
| 39685 |
+
"loss": 0.9557,
|
| 39686 |
+
"step": 5668
|
| 39687 |
+
},
|
| 39688 |
+
{
|
| 39689 |
+
"epoch": 6.456980056980057,
|
| 39690 |
+
"grad_norm": 0.17333857715129852,
|
| 39691 |
+
"learning_rate": 4.003960742052305e-05,
|
| 39692 |
+
"loss": 0.7169,
|
| 39693 |
+
"step": 5669
|
| 39694 |
+
},
|
| 39695 |
+
{
|
| 39696 |
+
"epoch": 6.458119658119658,
|
| 39697 |
+
"grad_norm": 0.23144127428531647,
|
| 39698 |
+
"learning_rate": 4.0035885362037473e-05,
|
| 39699 |
+
"loss": 0.7375,
|
| 39700 |
+
"step": 5670
|
| 39701 |
+
},
|
| 39702 |
+
{
|
| 39703 |
+
"epoch": 6.459259259259259,
|
| 39704 |
+
"grad_norm": 0.1870126575231552,
|
| 39705 |
+
"learning_rate": 4.003216278131425e-05,
|
| 39706 |
+
"loss": 0.6237,
|
| 39707 |
+
"step": 5671
|
| 39708 |
+
},
|
| 39709 |
+
{
|
| 39710 |
+
"epoch": 6.46039886039886,
|
| 39711 |
+
"grad_norm": 0.17142246663570404,
|
| 39712 |
+
"learning_rate": 4.0028439678482686e-05,
|
| 39713 |
+
"loss": 0.7533,
|
| 39714 |
+
"step": 5672
|
| 39715 |
+
},
|
| 39716 |
+
{
|
| 39717 |
+
"epoch": 6.461538461538462,
|
| 39718 |
+
"grad_norm": 0.24917946755886078,
|
| 39719 |
+
"learning_rate": 4.0024716053672074e-05,
|
| 39720 |
+
"loss": 0.4811,
|
| 39721 |
+
"step": 5673
|
| 39722 |
+
},
|
| 39723 |
+
{
|
| 39724 |
+
"epoch": 6.462678062678062,
|
| 39725 |
+
"grad_norm": 0.20272578299045563,
|
| 39726 |
+
"learning_rate": 4.002099190701176e-05,
|
| 39727 |
+
"loss": 0.8904,
|
| 39728 |
+
"step": 5674
|
| 39729 |
+
},
|
| 39730 |
+
{
|
| 39731 |
+
"epoch": 6.463817663817664,
|
| 39732 |
+
"grad_norm": 0.2139831781387329,
|
| 39733 |
+
"learning_rate": 4.001726723863109e-05,
|
| 39734 |
+
"loss": 0.7117,
|
| 39735 |
+
"step": 5675
|
| 39736 |
+
},
|
| 39737 |
+
{
|
| 39738 |
+
"epoch": 6.464957264957265,
|
| 39739 |
+
"grad_norm": 0.20929937064647675,
|
| 39740 |
+
"learning_rate": 4.001354204865943e-05,
|
| 39741 |
+
"loss": 0.6985,
|
| 39742 |
+
"step": 5676
|
| 39743 |
+
},
|
| 39744 |
+
{
|
| 39745 |
+
"epoch": 6.466096866096866,
|
| 39746 |
+
"grad_norm": 0.17709870636463165,
|
| 39747 |
+
"learning_rate": 4.0009816337226166e-05,
|
| 39748 |
+
"loss": 0.7949,
|
| 39749 |
+
"step": 5677
|
| 39750 |
+
},
|
| 39751 |
+
{
|
| 39752 |
+
"epoch": 6.467236467236467,
|
| 39753 |
+
"grad_norm": 0.19222743809223175,
|
| 39754 |
+
"learning_rate": 4.00060901044607e-05,
|
| 39755 |
+
"loss": 0.7244,
|
| 39756 |
+
"step": 5678
|
| 39757 |
+
},
|
| 39758 |
+
{
|
| 39759 |
+
"epoch": 6.4683760683760685,
|
| 39760 |
+
"grad_norm": 0.18339277803897858,
|
| 39761 |
+
"learning_rate": 4.000236335049247e-05,
|
| 39762 |
+
"loss": 0.5729,
|
| 39763 |
+
"step": 5679
|
| 39764 |
+
},
|
| 39765 |
+
{
|
| 39766 |
+
"epoch": 6.46951566951567,
|
| 39767 |
+
"grad_norm": 0.18804150819778442,
|
| 39768 |
+
"learning_rate": 3.999863607545089e-05,
|
| 39769 |
+
"loss": 0.7491,
|
| 39770 |
+
"step": 5680
|
| 39771 |
+
},
|
| 39772 |
+
{
|
| 39773 |
+
"epoch": 6.4706552706552705,
|
| 39774 |
+
"grad_norm": 0.16036182641983032,
|
| 39775 |
+
"learning_rate": 3.999490827946544e-05,
|
| 39776 |
+
"loss": 0.7275,
|
| 39777 |
+
"step": 5681
|
| 39778 |
+
},
|
| 39779 |
+
{
|
| 39780 |
+
"epoch": 6.471794871794872,
|
| 39781 |
+
"grad_norm": 0.18374961614608765,
|
| 39782 |
+
"learning_rate": 3.999117996266559e-05,
|
| 39783 |
+
"loss": 0.7085,
|
| 39784 |
+
"step": 5682
|
| 39785 |
+
},
|
| 39786 |
+
{
|
| 39787 |
+
"epoch": 6.472934472934473,
|
| 39788 |
+
"grad_norm": 0.1866759955883026,
|
| 39789 |
+
"learning_rate": 3.998745112518083e-05,
|
| 39790 |
+
"loss": 0.8317,
|
| 39791 |
+
"step": 5683
|
| 39792 |
+
},
|
| 39793 |
+
{
|
| 39794 |
+
"epoch": 6.474074074074074,
|
| 39795 |
+
"grad_norm": 0.18938614428043365,
|
| 39796 |
+
"learning_rate": 3.998372176714068e-05,
|
| 39797 |
+
"loss": 0.5777,
|
| 39798 |
+
"step": 5684
|
| 39799 |
+
},
|
| 39800 |
+
{
|
| 39801 |
+
"epoch": 6.475213675213675,
|
| 39802 |
+
"grad_norm": 0.2183467596769333,
|
| 39803 |
+
"learning_rate": 3.997999188867466e-05,
|
| 39804 |
+
"loss": 0.7164,
|
| 39805 |
+
"step": 5685
|
| 39806 |
+
},
|
| 39807 |
+
{
|
| 39808 |
+
"epoch": 6.476353276353277,
|
| 39809 |
+
"grad_norm": 0.17132146656513214,
|
| 39810 |
+
"learning_rate": 3.9976261489912336e-05,
|
| 39811 |
+
"loss": 0.8326,
|
| 39812 |
+
"step": 5686
|
| 39813 |
+
},
|
| 39814 |
+
{
|
| 39815 |
+
"epoch": 6.477492877492877,
|
| 39816 |
+
"grad_norm": 0.22032825648784637,
|
| 39817 |
+
"learning_rate": 3.997253057098327e-05,
|
| 39818 |
+
"loss": 0.6774,
|
| 39819 |
+
"step": 5687
|
| 39820 |
+
},
|
| 39821 |
+
{
|
| 39822 |
+
"epoch": 6.478632478632479,
|
| 39823 |
+
"grad_norm": 0.20137335360050201,
|
| 39824 |
+
"learning_rate": 3.996879913201703e-05,
|
| 39825 |
+
"loss": 0.7788,
|
| 39826 |
+
"step": 5688
|
| 39827 |
+
},
|
| 39828 |
+
{
|
| 39829 |
+
"epoch": 6.47977207977208,
|
| 39830 |
+
"grad_norm": 0.17918981611728668,
|
| 39831 |
+
"learning_rate": 3.9965067173143236e-05,
|
| 39832 |
+
"loss": 0.8275,
|
| 39833 |
+
"step": 5689
|
| 39834 |
+
},
|
| 39835 |
+
{
|
| 39836 |
+
"epoch": 6.480911680911681,
|
| 39837 |
+
"grad_norm": 0.2228441834449768,
|
| 39838 |
+
"learning_rate": 3.99613346944915e-05,
|
| 39839 |
+
"loss": 0.6525,
|
| 39840 |
+
"step": 5690
|
| 39841 |
+
},
|
| 39842 |
+
{
|
| 39843 |
+
"epoch": 6.482051282051282,
|
| 39844 |
+
"grad_norm": 0.19778205454349518,
|
| 39845 |
+
"learning_rate": 3.995760169619148e-05,
|
| 39846 |
+
"loss": 0.8469,
|
| 39847 |
+
"step": 5691
|
| 39848 |
+
},
|
| 39849 |
+
{
|
| 39850 |
+
"epoch": 6.4831908831908835,
|
| 39851 |
+
"grad_norm": 0.1902667135000229,
|
| 39852 |
+
"learning_rate": 3.995386817837281e-05,
|
| 39853 |
+
"loss": 0.7686,
|
| 39854 |
+
"step": 5692
|
| 39855 |
+
},
|
| 39856 |
+
{
|
| 39857 |
+
"epoch": 6.484330484330484,
|
| 39858 |
+
"grad_norm": 0.15250743925571442,
|
| 39859 |
+
"learning_rate": 3.995013414116517e-05,
|
| 39860 |
+
"loss": 0.9219,
|
| 39861 |
+
"step": 5693
|
| 39862 |
+
},
|
| 39863 |
+
{
|
| 39864 |
+
"epoch": 6.4854700854700855,
|
| 39865 |
+
"grad_norm": 0.1628999561071396,
|
| 39866 |
+
"learning_rate": 3.994639958469827e-05,
|
| 39867 |
+
"loss": 0.8197,
|
| 39868 |
+
"step": 5694
|
| 39869 |
+
},
|
| 39870 |
+
{
|
| 39871 |
+
"epoch": 6.486609686609687,
|
| 39872 |
+
"grad_norm": 0.20843957364559174,
|
| 39873 |
+
"learning_rate": 3.99426645091018e-05,
|
| 39874 |
+
"loss": 0.6886,
|
| 39875 |
+
"step": 5695
|
| 39876 |
+
},
|
| 39877 |
+
{
|
| 39878 |
+
"epoch": 6.4877492877492875,
|
| 39879 |
+
"grad_norm": 0.195245161652565,
|
| 39880 |
+
"learning_rate": 3.9938928914505506e-05,
|
| 39881 |
+
"loss": 0.7892,
|
| 39882 |
+
"step": 5696
|
| 39883 |
+
},
|
| 39884 |
+
{
|
| 39885 |
+
"epoch": 6.488888888888889,
|
| 39886 |
+
"grad_norm": 0.150603249669075,
|
| 39887 |
+
"learning_rate": 3.993519280103913e-05,
|
| 39888 |
+
"loss": 0.8768,
|
| 39889 |
+
"step": 5697
|
| 39890 |
+
},
|
| 39891 |
+
{
|
| 39892 |
+
"epoch": 6.49002849002849,
|
| 39893 |
+
"grad_norm": 0.1576722413301468,
|
| 39894 |
+
"learning_rate": 3.993145616883243e-05,
|
| 39895 |
+
"loss": 0.8517,
|
| 39896 |
+
"step": 5698
|
| 39897 |
+
},
|
| 39898 |
+
{
|
| 39899 |
+
"epoch": 6.491168091168091,
|
| 39900 |
+
"grad_norm": 0.24340248107910156,
|
| 39901 |
+
"learning_rate": 3.99277190180152e-05,
|
| 39902 |
+
"loss": 0.6631,
|
| 39903 |
+
"step": 5699
|
| 39904 |
+
},
|
| 39905 |
+
{
|
| 39906 |
+
"epoch": 6.492307692307692,
|
| 39907 |
+
"grad_norm": 0.29386258125305176,
|
| 39908 |
+
"learning_rate": 3.992398134871723e-05,
|
| 39909 |
+
"loss": 0.5602,
|
| 39910 |
+
"step": 5700
|
| 39911 |
}
|
| 39912 |
],
|
| 39913 |
"logging_steps": 1,
|
|
|
|
| 39927 |
"attributes": {}
|
| 39928 |
}
|
| 39929 |
},
|
| 39930 |
+
"total_flos": 3.187143718700802e+19,
|
| 39931 |
"train_batch_size": 8,
|
| 39932 |
"trial_name": null,
|
| 39933 |
"trial_params": null
|