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 3600, 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 sha256:1d29906a893a45c963b40c0d9edc786bf43c438907f3380083349dc02b856089
|
| 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:b1203e46122dfbcf2e1a5d8123743c6fe9b32f313485e0b17cbf0ada37b68d1f
|
| 3 |
size 173247691
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54dd0a605dec457223fc713b0253cd0396085ae73c45210410bd44b75f2dcf0c
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -23108,6 +23108,2106 @@
|
|
| 23108 |
"learning_rate": 4.7130735104216584e-05,
|
| 23109 |
"loss": 0.7879,
|
| 23110 |
"step": 3300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23111 |
}
|
| 23112 |
],
|
| 23113 |
"logging_steps": 1,
|
|
@@ -23127,7 +25227,7 @@
|
|
| 23127 |
"attributes": {}
|
| 23128 |
}
|
| 23129 |
},
|
| 23130 |
-
"total_flos":
|
| 23131 |
"train_batch_size": 8,
|
| 23132 |
"trial_name": null,
|
| 23133 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.1002849002849,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 23108 |
"learning_rate": 4.7130735104216584e-05,
|
| 23109 |
"loss": 0.7879,
|
| 23110 |
"step": 3300
|
| 23111 |
+
},
|
| 23112 |
+
{
|
| 23113 |
+
"epoch": 3.7601139601139604,
|
| 23114 |
+
"grad_norm": 0.16756659746170044,
|
| 23115 |
+
"learning_rate": 4.7128567479861476e-05,
|
| 23116 |
+
"loss": 0.778,
|
| 23117 |
+
"step": 3301
|
| 23118 |
+
},
|
| 23119 |
+
{
|
| 23120 |
+
"epoch": 3.7612535612535614,
|
| 23121 |
+
"grad_norm": 0.16091838479042053,
|
| 23122 |
+
"learning_rate": 4.712639908692037e-05,
|
| 23123 |
+
"loss": 0.7816,
|
| 23124 |
+
"step": 3302
|
| 23125 |
+
},
|
| 23126 |
+
{
|
| 23127 |
+
"epoch": 3.7623931623931623,
|
| 23128 |
+
"grad_norm": 0.1462317407131195,
|
| 23129 |
+
"learning_rate": 4.712422992546857e-05,
|
| 23130 |
+
"loss": 0.7826,
|
| 23131 |
+
"step": 3303
|
| 23132 |
+
},
|
| 23133 |
+
{
|
| 23134 |
+
"epoch": 3.763532763532764,
|
| 23135 |
+
"grad_norm": 0.16462798416614532,
|
| 23136 |
+
"learning_rate": 4.712205999558143e-05,
|
| 23137 |
+
"loss": 0.9022,
|
| 23138 |
+
"step": 3304
|
| 23139 |
+
},
|
| 23140 |
+
{
|
| 23141 |
+
"epoch": 3.7646723646723648,
|
| 23142 |
+
"grad_norm": 0.16236019134521484,
|
| 23143 |
+
"learning_rate": 4.711988929733429e-05,
|
| 23144 |
+
"loss": 0.7944,
|
| 23145 |
+
"step": 3305
|
| 23146 |
+
},
|
| 23147 |
+
{
|
| 23148 |
+
"epoch": 3.7658119658119658,
|
| 23149 |
+
"grad_norm": 0.14094164967536926,
|
| 23150 |
+
"learning_rate": 4.711771783080259e-05,
|
| 23151 |
+
"loss": 0.8613,
|
| 23152 |
+
"step": 3306
|
| 23153 |
+
},
|
| 23154 |
+
{
|
| 23155 |
+
"epoch": 3.766951566951567,
|
| 23156 |
+
"grad_norm": 0.18130993843078613,
|
| 23157 |
+
"learning_rate": 4.711554559606171e-05,
|
| 23158 |
+
"loss": 0.6142,
|
| 23159 |
+
"step": 3307
|
| 23160 |
+
},
|
| 23161 |
+
{
|
| 23162 |
+
"epoch": 3.768091168091168,
|
| 23163 |
+
"grad_norm": 0.14163918793201447,
|
| 23164 |
+
"learning_rate": 4.711337259318712e-05,
|
| 23165 |
+
"loss": 1.0577,
|
| 23166 |
+
"step": 3308
|
| 23167 |
+
},
|
| 23168 |
+
{
|
| 23169 |
+
"epoch": 3.769230769230769,
|
| 23170 |
+
"grad_norm": 0.14657098054885864,
|
| 23171 |
+
"learning_rate": 4.711119882225429e-05,
|
| 23172 |
+
"loss": 0.8357,
|
| 23173 |
+
"step": 3309
|
| 23174 |
+
},
|
| 23175 |
+
{
|
| 23176 |
+
"epoch": 3.7703703703703706,
|
| 23177 |
+
"grad_norm": 0.12951062619686127,
|
| 23178 |
+
"learning_rate": 4.710902428333871e-05,
|
| 23179 |
+
"loss": 0.852,
|
| 23180 |
+
"step": 3310
|
| 23181 |
+
},
|
| 23182 |
+
{
|
| 23183 |
+
"epoch": 3.7715099715099716,
|
| 23184 |
+
"grad_norm": 0.1622898429632187,
|
| 23185 |
+
"learning_rate": 4.710684897651592e-05,
|
| 23186 |
+
"loss": 0.704,
|
| 23187 |
+
"step": 3311
|
| 23188 |
+
},
|
| 23189 |
+
{
|
| 23190 |
+
"epoch": 3.7726495726495726,
|
| 23191 |
+
"grad_norm": 0.16411170363426208,
|
| 23192 |
+
"learning_rate": 4.710467290186148e-05,
|
| 23193 |
+
"loss": 0.7952,
|
| 23194 |
+
"step": 3312
|
| 23195 |
+
},
|
| 23196 |
+
{
|
| 23197 |
+
"epoch": 3.773789173789174,
|
| 23198 |
+
"grad_norm": 0.15382306277751923,
|
| 23199 |
+
"learning_rate": 4.710249605945095e-05,
|
| 23200 |
+
"loss": 0.6917,
|
| 23201 |
+
"step": 3313
|
| 23202 |
+
},
|
| 23203 |
+
{
|
| 23204 |
+
"epoch": 3.774928774928775,
|
| 23205 |
+
"grad_norm": 0.14002524316310883,
|
| 23206 |
+
"learning_rate": 4.710031844935996e-05,
|
| 23207 |
+
"loss": 1.0518,
|
| 23208 |
+
"step": 3314
|
| 23209 |
+
},
|
| 23210 |
+
{
|
| 23211 |
+
"epoch": 3.776068376068376,
|
| 23212 |
+
"grad_norm": 0.1697578728199005,
|
| 23213 |
+
"learning_rate": 4.709814007166412e-05,
|
| 23214 |
+
"loss": 0.6775,
|
| 23215 |
+
"step": 3315
|
| 23216 |
+
},
|
| 23217 |
+
{
|
| 23218 |
+
"epoch": 3.7772079772079774,
|
| 23219 |
+
"grad_norm": 0.15462514758110046,
|
| 23220 |
+
"learning_rate": 4.709596092643912e-05,
|
| 23221 |
+
"loss": 0.8434,
|
| 23222 |
+
"step": 3316
|
| 23223 |
+
},
|
| 23224 |
+
{
|
| 23225 |
+
"epoch": 3.7783475783475784,
|
| 23226 |
+
"grad_norm": 0.19596315920352936,
|
| 23227 |
+
"learning_rate": 4.709378101376063e-05,
|
| 23228 |
+
"loss": 0.7472,
|
| 23229 |
+
"step": 3317
|
| 23230 |
+
},
|
| 23231 |
+
{
|
| 23232 |
+
"epoch": 3.7794871794871794,
|
| 23233 |
+
"grad_norm": 0.1463899463415146,
|
| 23234 |
+
"learning_rate": 4.709160033370435e-05,
|
| 23235 |
+
"loss": 0.9265,
|
| 23236 |
+
"step": 3318
|
| 23237 |
+
},
|
| 23238 |
+
{
|
| 23239 |
+
"epoch": 3.780626780626781,
|
| 23240 |
+
"grad_norm": 0.16193729639053345,
|
| 23241 |
+
"learning_rate": 4.7089418886346056e-05,
|
| 23242 |
+
"loss": 0.8363,
|
| 23243 |
+
"step": 3319
|
| 23244 |
+
},
|
| 23245 |
+
{
|
| 23246 |
+
"epoch": 3.781766381766382,
|
| 23247 |
+
"grad_norm": 0.13628825545310974,
|
| 23248 |
+
"learning_rate": 4.7087236671761506e-05,
|
| 23249 |
+
"loss": 0.8596,
|
| 23250 |
+
"step": 3320
|
| 23251 |
+
},
|
| 23252 |
+
{
|
| 23253 |
+
"epoch": 3.782905982905983,
|
| 23254 |
+
"grad_norm": 0.17029441893100739,
|
| 23255 |
+
"learning_rate": 4.708505369002647e-05,
|
| 23256 |
+
"loss": 0.8404,
|
| 23257 |
+
"step": 3321
|
| 23258 |
+
},
|
| 23259 |
+
{
|
| 23260 |
+
"epoch": 3.784045584045584,
|
| 23261 |
+
"grad_norm": 0.17348740994930267,
|
| 23262 |
+
"learning_rate": 4.708286994121679e-05,
|
| 23263 |
+
"loss": 0.6665,
|
| 23264 |
+
"step": 3322
|
| 23265 |
+
},
|
| 23266 |
+
{
|
| 23267 |
+
"epoch": 3.785185185185185,
|
| 23268 |
+
"grad_norm": 0.13818663358688354,
|
| 23269 |
+
"learning_rate": 4.708068542540831e-05,
|
| 23270 |
+
"loss": 0.8523,
|
| 23271 |
+
"step": 3323
|
| 23272 |
+
},
|
| 23273 |
+
{
|
| 23274 |
+
"epoch": 3.786324786324786,
|
| 23275 |
+
"grad_norm": 0.13160809874534607,
|
| 23276 |
+
"learning_rate": 4.707850014267689e-05,
|
| 23277 |
+
"loss": 0.9992,
|
| 23278 |
+
"step": 3324
|
| 23279 |
+
},
|
| 23280 |
+
{
|
| 23281 |
+
"epoch": 3.7874643874643876,
|
| 23282 |
+
"grad_norm": 0.14526665210723877,
|
| 23283 |
+
"learning_rate": 4.707631409309846e-05,
|
| 23284 |
+
"loss": 0.8231,
|
| 23285 |
+
"step": 3325
|
| 23286 |
+
},
|
| 23287 |
+
{
|
| 23288 |
+
"epoch": 3.7886039886039886,
|
| 23289 |
+
"grad_norm": 0.1624801754951477,
|
| 23290 |
+
"learning_rate": 4.707412727674893e-05,
|
| 23291 |
+
"loss": 0.8036,
|
| 23292 |
+
"step": 3326
|
| 23293 |
+
},
|
| 23294 |
+
{
|
| 23295 |
+
"epoch": 3.7897435897435896,
|
| 23296 |
+
"grad_norm": 0.16265356540679932,
|
| 23297 |
+
"learning_rate": 4.7071939693704255e-05,
|
| 23298 |
+
"loss": 0.9489,
|
| 23299 |
+
"step": 3327
|
| 23300 |
+
},
|
| 23301 |
+
{
|
| 23302 |
+
"epoch": 3.790883190883191,
|
| 23303 |
+
"grad_norm": 0.1629178673028946,
|
| 23304 |
+
"learning_rate": 4.7069751344040416e-05,
|
| 23305 |
+
"loss": 0.8472,
|
| 23306 |
+
"step": 3328
|
| 23307 |
+
},
|
| 23308 |
+
{
|
| 23309 |
+
"epoch": 3.792022792022792,
|
| 23310 |
+
"grad_norm": 0.16582542657852173,
|
| 23311 |
+
"learning_rate": 4.706756222783342e-05,
|
| 23312 |
+
"loss": 0.8367,
|
| 23313 |
+
"step": 3329
|
| 23314 |
+
},
|
| 23315 |
+
{
|
| 23316 |
+
"epoch": 3.793162393162393,
|
| 23317 |
+
"grad_norm": 0.15202531218528748,
|
| 23318 |
+
"learning_rate": 4.70653723451593e-05,
|
| 23319 |
+
"loss": 1.01,
|
| 23320 |
+
"step": 3330
|
| 23321 |
+
},
|
| 23322 |
+
{
|
| 23323 |
+
"epoch": 3.7943019943019944,
|
| 23324 |
+
"grad_norm": 0.13972711563110352,
|
| 23325 |
+
"learning_rate": 4.706318169609412e-05,
|
| 23326 |
+
"loss": 0.8285,
|
| 23327 |
+
"step": 3331
|
| 23328 |
+
},
|
| 23329 |
+
{
|
| 23330 |
+
"epoch": 3.7954415954415954,
|
| 23331 |
+
"grad_norm": 0.14830423891544342,
|
| 23332 |
+
"learning_rate": 4.706099028071396e-05,
|
| 23333 |
+
"loss": 0.8479,
|
| 23334 |
+
"step": 3332
|
| 23335 |
+
},
|
| 23336 |
+
{
|
| 23337 |
+
"epoch": 3.7965811965811964,
|
| 23338 |
+
"grad_norm": 0.14009328186511993,
|
| 23339 |
+
"learning_rate": 4.7058798099094946e-05,
|
| 23340 |
+
"loss": 0.9931,
|
| 23341 |
+
"step": 3333
|
| 23342 |
+
},
|
| 23343 |
+
{
|
| 23344 |
+
"epoch": 3.797720797720798,
|
| 23345 |
+
"grad_norm": 0.18037128448486328,
|
| 23346 |
+
"learning_rate": 4.705660515131321e-05,
|
| 23347 |
+
"loss": 0.7468,
|
| 23348 |
+
"step": 3334
|
| 23349 |
+
},
|
| 23350 |
+
{
|
| 23351 |
+
"epoch": 3.798860398860399,
|
| 23352 |
+
"grad_norm": 0.13112333416938782,
|
| 23353 |
+
"learning_rate": 4.7054411437444926e-05,
|
| 23354 |
+
"loss": 0.8557,
|
| 23355 |
+
"step": 3335
|
| 23356 |
+
},
|
| 23357 |
+
{
|
| 23358 |
+
"epoch": 3.8,
|
| 23359 |
+
"grad_norm": 0.1434762328863144,
|
| 23360 |
+
"learning_rate": 4.7052216957566275e-05,
|
| 23361 |
+
"loss": 0.7453,
|
| 23362 |
+
"step": 3336
|
| 23363 |
+
},
|
| 23364 |
+
{
|
| 23365 |
+
"epoch": 3.8011396011396013,
|
| 23366 |
+
"grad_norm": 0.2030930519104004,
|
| 23367 |
+
"learning_rate": 4.705002171175349e-05,
|
| 23368 |
+
"loss": 0.6288,
|
| 23369 |
+
"step": 3337
|
| 23370 |
+
},
|
| 23371 |
+
{
|
| 23372 |
+
"epoch": 3.8022792022792022,
|
| 23373 |
+
"grad_norm": 0.13329127430915833,
|
| 23374 |
+
"learning_rate": 4.704782570008281e-05,
|
| 23375 |
+
"loss": 0.8263,
|
| 23376 |
+
"step": 3338
|
| 23377 |
+
},
|
| 23378 |
+
{
|
| 23379 |
+
"epoch": 3.8034188034188032,
|
| 23380 |
+
"grad_norm": 0.16466042399406433,
|
| 23381 |
+
"learning_rate": 4.7045628922630515e-05,
|
| 23382 |
+
"loss": 0.7695,
|
| 23383 |
+
"step": 3339
|
| 23384 |
+
},
|
| 23385 |
+
{
|
| 23386 |
+
"epoch": 3.8045584045584047,
|
| 23387 |
+
"grad_norm": 0.18540437519550323,
|
| 23388 |
+
"learning_rate": 4.70434313794729e-05,
|
| 23389 |
+
"loss": 0.8276,
|
| 23390 |
+
"step": 3340
|
| 23391 |
+
},
|
| 23392 |
+
{
|
| 23393 |
+
"epoch": 3.8056980056980056,
|
| 23394 |
+
"grad_norm": 0.17809467017650604,
|
| 23395 |
+
"learning_rate": 4.704123307068629e-05,
|
| 23396 |
+
"loss": 0.7119,
|
| 23397 |
+
"step": 3341
|
| 23398 |
+
},
|
| 23399 |
+
{
|
| 23400 |
+
"epoch": 3.8068376068376066,
|
| 23401 |
+
"grad_norm": 0.14918246865272522,
|
| 23402 |
+
"learning_rate": 4.7039033996347046e-05,
|
| 23403 |
+
"loss": 0.8541,
|
| 23404 |
+
"step": 3342
|
| 23405 |
+
},
|
| 23406 |
+
{
|
| 23407 |
+
"epoch": 3.807977207977208,
|
| 23408 |
+
"grad_norm": 0.151133731007576,
|
| 23409 |
+
"learning_rate": 4.703683415653154e-05,
|
| 23410 |
+
"loss": 0.8092,
|
| 23411 |
+
"step": 3343
|
| 23412 |
+
},
|
| 23413 |
+
{
|
| 23414 |
+
"epoch": 3.809116809116809,
|
| 23415 |
+
"grad_norm": 0.15425163507461548,
|
| 23416 |
+
"learning_rate": 4.703463355131619e-05,
|
| 23417 |
+
"loss": 0.899,
|
| 23418 |
+
"step": 3344
|
| 23419 |
+
},
|
| 23420 |
+
{
|
| 23421 |
+
"epoch": 3.81025641025641,
|
| 23422 |
+
"grad_norm": 0.16399483382701874,
|
| 23423 |
+
"learning_rate": 4.703243218077742e-05,
|
| 23424 |
+
"loss": 0.823,
|
| 23425 |
+
"step": 3345
|
| 23426 |
+
},
|
| 23427 |
+
{
|
| 23428 |
+
"epoch": 3.8113960113960115,
|
| 23429 |
+
"grad_norm": 0.1537674367427826,
|
| 23430 |
+
"learning_rate": 4.7030230044991684e-05,
|
| 23431 |
+
"loss": 0.8778,
|
| 23432 |
+
"step": 3346
|
| 23433 |
+
},
|
| 23434 |
+
{
|
| 23435 |
+
"epoch": 3.8125356125356125,
|
| 23436 |
+
"grad_norm": 0.1560267060995102,
|
| 23437 |
+
"learning_rate": 4.702802714403548e-05,
|
| 23438 |
+
"loss": 0.8398,
|
| 23439 |
+
"step": 3347
|
| 23440 |
+
},
|
| 23441 |
+
{
|
| 23442 |
+
"epoch": 3.8136752136752134,
|
| 23443 |
+
"grad_norm": 0.16034267842769623,
|
| 23444 |
+
"learning_rate": 4.7025823477985316e-05,
|
| 23445 |
+
"loss": 0.7942,
|
| 23446 |
+
"step": 3348
|
| 23447 |
+
},
|
| 23448 |
+
{
|
| 23449 |
+
"epoch": 3.814814814814815,
|
| 23450 |
+
"grad_norm": 0.17743459343910217,
|
| 23451 |
+
"learning_rate": 4.702361904691773e-05,
|
| 23452 |
+
"loss": 0.807,
|
| 23453 |
+
"step": 3349
|
| 23454 |
+
},
|
| 23455 |
+
{
|
| 23456 |
+
"epoch": 3.815954415954416,
|
| 23457 |
+
"grad_norm": 0.13582278788089752,
|
| 23458 |
+
"learning_rate": 4.702141385090929e-05,
|
| 23459 |
+
"loss": 0.8062,
|
| 23460 |
+
"step": 3350
|
| 23461 |
+
},
|
| 23462 |
+
{
|
| 23463 |
+
"epoch": 3.817094017094017,
|
| 23464 |
+
"grad_norm": 0.1425933688879013,
|
| 23465 |
+
"learning_rate": 4.7019207890036584e-05,
|
| 23466 |
+
"loss": 0.8535,
|
| 23467 |
+
"step": 3351
|
| 23468 |
+
},
|
| 23469 |
+
{
|
| 23470 |
+
"epoch": 3.8182336182336183,
|
| 23471 |
+
"grad_norm": 0.145987406373024,
|
| 23472 |
+
"learning_rate": 4.701700116437624e-05,
|
| 23473 |
+
"loss": 0.9585,
|
| 23474 |
+
"step": 3352
|
| 23475 |
+
},
|
| 23476 |
+
{
|
| 23477 |
+
"epoch": 3.8193732193732193,
|
| 23478 |
+
"grad_norm": 0.16236691176891327,
|
| 23479 |
+
"learning_rate": 4.7014793674004896e-05,
|
| 23480 |
+
"loss": 0.7493,
|
| 23481 |
+
"step": 3353
|
| 23482 |
+
},
|
| 23483 |
+
{
|
| 23484 |
+
"epoch": 3.8205128205128203,
|
| 23485 |
+
"grad_norm": 0.12828007340431213,
|
| 23486 |
+
"learning_rate": 4.701258541899923e-05,
|
| 23487 |
+
"loss": 0.9837,
|
| 23488 |
+
"step": 3354
|
| 23489 |
+
},
|
| 23490 |
+
{
|
| 23491 |
+
"epoch": 3.8216524216524217,
|
| 23492 |
+
"grad_norm": 0.16995170712471008,
|
| 23493 |
+
"learning_rate": 4.701037639943594e-05,
|
| 23494 |
+
"loss": 0.6957,
|
| 23495 |
+
"step": 3355
|
| 23496 |
+
},
|
| 23497 |
+
{
|
| 23498 |
+
"epoch": 3.8227920227920227,
|
| 23499 |
+
"grad_norm": 0.1511501967906952,
|
| 23500 |
+
"learning_rate": 4.700816661539174e-05,
|
| 23501 |
+
"loss": 0.695,
|
| 23502 |
+
"step": 3356
|
| 23503 |
+
},
|
| 23504 |
+
{
|
| 23505 |
+
"epoch": 3.8239316239316237,
|
| 23506 |
+
"grad_norm": 0.16818365454673767,
|
| 23507 |
+
"learning_rate": 4.7005956066943396e-05,
|
| 23508 |
+
"loss": 0.7185,
|
| 23509 |
+
"step": 3357
|
| 23510 |
+
},
|
| 23511 |
+
{
|
| 23512 |
+
"epoch": 3.825071225071225,
|
| 23513 |
+
"grad_norm": 0.15481878817081451,
|
| 23514 |
+
"learning_rate": 4.7003744754167676e-05,
|
| 23515 |
+
"loss": 0.7676,
|
| 23516 |
+
"step": 3358
|
| 23517 |
+
},
|
| 23518 |
+
{
|
| 23519 |
+
"epoch": 3.826210826210826,
|
| 23520 |
+
"grad_norm": 0.1362566351890564,
|
| 23521 |
+
"learning_rate": 4.70015326771414e-05,
|
| 23522 |
+
"loss": 0.8843,
|
| 23523 |
+
"step": 3359
|
| 23524 |
+
},
|
| 23525 |
+
{
|
| 23526 |
+
"epoch": 3.827350427350427,
|
| 23527 |
+
"grad_norm": 0.16790726780891418,
|
| 23528 |
+
"learning_rate": 4.699931983594138e-05,
|
| 23529 |
+
"loss": 0.8681,
|
| 23530 |
+
"step": 3360
|
| 23531 |
+
},
|
| 23532 |
+
{
|
| 23533 |
+
"epoch": 3.8284900284900285,
|
| 23534 |
+
"grad_norm": 0.1538618505001068,
|
| 23535 |
+
"learning_rate": 4.69971062306445e-05,
|
| 23536 |
+
"loss": 0.6958,
|
| 23537 |
+
"step": 3361
|
| 23538 |
+
},
|
| 23539 |
+
{
|
| 23540 |
+
"epoch": 3.8296296296296295,
|
| 23541 |
+
"grad_norm": 0.14279936254024506,
|
| 23542 |
+
"learning_rate": 4.6994891861327606e-05,
|
| 23543 |
+
"loss": 0.9614,
|
| 23544 |
+
"step": 3362
|
| 23545 |
+
},
|
| 23546 |
+
{
|
| 23547 |
+
"epoch": 3.830769230769231,
|
| 23548 |
+
"grad_norm": 0.13365939259529114,
|
| 23549 |
+
"learning_rate": 4.699267672806764e-05,
|
| 23550 |
+
"loss": 1.2272,
|
| 23551 |
+
"step": 3363
|
| 23552 |
+
},
|
| 23553 |
+
{
|
| 23554 |
+
"epoch": 3.831908831908832,
|
| 23555 |
+
"grad_norm": 0.18748198449611664,
|
| 23556 |
+
"learning_rate": 4.699046083094154e-05,
|
| 23557 |
+
"loss": 0.6171,
|
| 23558 |
+
"step": 3364
|
| 23559 |
+
},
|
| 23560 |
+
{
|
| 23561 |
+
"epoch": 3.833048433048433,
|
| 23562 |
+
"grad_norm": 0.1396261751651764,
|
| 23563 |
+
"learning_rate": 4.698824417002625e-05,
|
| 23564 |
+
"loss": 0.944,
|
| 23565 |
+
"step": 3365
|
| 23566 |
+
},
|
| 23567 |
+
{
|
| 23568 |
+
"epoch": 3.8341880341880343,
|
| 23569 |
+
"grad_norm": 0.15107348561286926,
|
| 23570 |
+
"learning_rate": 4.698602674539878e-05,
|
| 23571 |
+
"loss": 0.9461,
|
| 23572 |
+
"step": 3366
|
| 23573 |
+
},
|
| 23574 |
+
{
|
| 23575 |
+
"epoch": 3.8353276353276353,
|
| 23576 |
+
"grad_norm": 0.15369813144207,
|
| 23577 |
+
"learning_rate": 4.6983808557136135e-05,
|
| 23578 |
+
"loss": 0.8081,
|
| 23579 |
+
"step": 3367
|
| 23580 |
+
},
|
| 23581 |
+
{
|
| 23582 |
+
"epoch": 3.8364672364672363,
|
| 23583 |
+
"grad_norm": 0.1463460773229599,
|
| 23584 |
+
"learning_rate": 4.698158960531536e-05,
|
| 23585 |
+
"loss": 0.8933,
|
| 23586 |
+
"step": 3368
|
| 23587 |
+
},
|
| 23588 |
+
{
|
| 23589 |
+
"epoch": 3.8376068376068377,
|
| 23590 |
+
"grad_norm": 0.1420212984085083,
|
| 23591 |
+
"learning_rate": 4.697936989001353e-05,
|
| 23592 |
+
"loss": 0.9669,
|
| 23593 |
+
"step": 3369
|
| 23594 |
+
},
|
| 23595 |
+
{
|
| 23596 |
+
"epoch": 3.8387464387464387,
|
| 23597 |
+
"grad_norm": 0.16711066663265228,
|
| 23598 |
+
"learning_rate": 4.697714941130774e-05,
|
| 23599 |
+
"loss": 0.8245,
|
| 23600 |
+
"step": 3370
|
| 23601 |
+
},
|
| 23602 |
+
{
|
| 23603 |
+
"epoch": 3.83988603988604,
|
| 23604 |
+
"grad_norm": 0.1338273137807846,
|
| 23605 |
+
"learning_rate": 4.697492816927512e-05,
|
| 23606 |
+
"loss": 0.9024,
|
| 23607 |
+
"step": 3371
|
| 23608 |
+
},
|
| 23609 |
+
{
|
| 23610 |
+
"epoch": 3.841025641025641,
|
| 23611 |
+
"grad_norm": 0.16420644521713257,
|
| 23612 |
+
"learning_rate": 4.697270616399281e-05,
|
| 23613 |
+
"loss": 0.7058,
|
| 23614 |
+
"step": 3372
|
| 23615 |
+
},
|
| 23616 |
+
{
|
| 23617 |
+
"epoch": 3.842165242165242,
|
| 23618 |
+
"grad_norm": 0.1521245837211609,
|
| 23619 |
+
"learning_rate": 4.6970483395537987e-05,
|
| 23620 |
+
"loss": 0.7781,
|
| 23621 |
+
"step": 3373
|
| 23622 |
+
},
|
| 23623 |
+
{
|
| 23624 |
+
"epoch": 3.8433048433048436,
|
| 23625 |
+
"grad_norm": 0.14421981573104858,
|
| 23626 |
+
"learning_rate": 4.696825986398786e-05,
|
| 23627 |
+
"loss": 0.7919,
|
| 23628 |
+
"step": 3374
|
| 23629 |
+
},
|
| 23630 |
+
{
|
| 23631 |
+
"epoch": 3.8444444444444446,
|
| 23632 |
+
"grad_norm": 0.16730935871601105,
|
| 23633 |
+
"learning_rate": 4.6966035569419654e-05,
|
| 23634 |
+
"loss": 0.694,
|
| 23635 |
+
"step": 3375
|
| 23636 |
+
},
|
| 23637 |
+
{
|
| 23638 |
+
"epoch": 3.8455840455840455,
|
| 23639 |
+
"grad_norm": 0.15459780395030975,
|
| 23640 |
+
"learning_rate": 4.696381051191062e-05,
|
| 23641 |
+
"loss": 0.9161,
|
| 23642 |
+
"step": 3376
|
| 23643 |
+
},
|
| 23644 |
+
{
|
| 23645 |
+
"epoch": 3.846723646723647,
|
| 23646 |
+
"grad_norm": 0.1502046287059784,
|
| 23647 |
+
"learning_rate": 4.696158469153805e-05,
|
| 23648 |
+
"loss": 0.7694,
|
| 23649 |
+
"step": 3377
|
| 23650 |
+
},
|
| 23651 |
+
{
|
| 23652 |
+
"epoch": 3.847863247863248,
|
| 23653 |
+
"grad_norm": 0.1428917646408081,
|
| 23654 |
+
"learning_rate": 4.6959358108379256e-05,
|
| 23655 |
+
"loss": 0.953,
|
| 23656 |
+
"step": 3378
|
| 23657 |
+
},
|
| 23658 |
+
{
|
| 23659 |
+
"epoch": 3.849002849002849,
|
| 23660 |
+
"grad_norm": 0.19488106667995453,
|
| 23661 |
+
"learning_rate": 4.695713076251156e-05,
|
| 23662 |
+
"loss": 0.6441,
|
| 23663 |
+
"step": 3379
|
| 23664 |
+
},
|
| 23665 |
+
{
|
| 23666 |
+
"epoch": 3.8501424501424504,
|
| 23667 |
+
"grad_norm": 0.18286015093326569,
|
| 23668 |
+
"learning_rate": 4.695490265401233e-05,
|
| 23669 |
+
"loss": 0.7315,
|
| 23670 |
+
"step": 3380
|
| 23671 |
+
},
|
| 23672 |
+
{
|
| 23673 |
+
"epoch": 3.8512820512820514,
|
| 23674 |
+
"grad_norm": 0.16389550268650055,
|
| 23675 |
+
"learning_rate": 4.695267378295896e-05,
|
| 23676 |
+
"loss": 0.667,
|
| 23677 |
+
"step": 3381
|
| 23678 |
+
},
|
| 23679 |
+
{
|
| 23680 |
+
"epoch": 3.8524216524216524,
|
| 23681 |
+
"grad_norm": 0.1413779854774475,
|
| 23682 |
+
"learning_rate": 4.6950444149428854e-05,
|
| 23683 |
+
"loss": 0.7685,
|
| 23684 |
+
"step": 3382
|
| 23685 |
+
},
|
| 23686 |
+
{
|
| 23687 |
+
"epoch": 3.853561253561254,
|
| 23688 |
+
"grad_norm": 0.1864253282546997,
|
| 23689 |
+
"learning_rate": 4.694821375349946e-05,
|
| 23690 |
+
"loss": 0.6877,
|
| 23691 |
+
"step": 3383
|
| 23692 |
+
},
|
| 23693 |
+
{
|
| 23694 |
+
"epoch": 3.8547008547008548,
|
| 23695 |
+
"grad_norm": 0.160108283162117,
|
| 23696 |
+
"learning_rate": 4.694598259524824e-05,
|
| 23697 |
+
"loss": 0.8099,
|
| 23698 |
+
"step": 3384
|
| 23699 |
+
},
|
| 23700 |
+
{
|
| 23701 |
+
"epoch": 3.8558404558404558,
|
| 23702 |
+
"grad_norm": 0.14981703460216522,
|
| 23703 |
+
"learning_rate": 4.69437506747527e-05,
|
| 23704 |
+
"loss": 0.854,
|
| 23705 |
+
"step": 3385
|
| 23706 |
+
},
|
| 23707 |
+
{
|
| 23708 |
+
"epoch": 3.856980056980057,
|
| 23709 |
+
"grad_norm": 0.1802595853805542,
|
| 23710 |
+
"learning_rate": 4.694151799209035e-05,
|
| 23711 |
+
"loss": 0.7782,
|
| 23712 |
+
"step": 3386
|
| 23713 |
+
},
|
| 23714 |
+
{
|
| 23715 |
+
"epoch": 3.858119658119658,
|
| 23716 |
+
"grad_norm": 0.13733747601509094,
|
| 23717 |
+
"learning_rate": 4.693928454733875e-05,
|
| 23718 |
+
"loss": 1.0103,
|
| 23719 |
+
"step": 3387
|
| 23720 |
+
},
|
| 23721 |
+
{
|
| 23722 |
+
"epoch": 3.859259259259259,
|
| 23723 |
+
"grad_norm": 0.1732407510280609,
|
| 23724 |
+
"learning_rate": 4.693705034057545e-05,
|
| 23725 |
+
"loss": 0.8377,
|
| 23726 |
+
"step": 3388
|
| 23727 |
+
},
|
| 23728 |
+
{
|
| 23729 |
+
"epoch": 3.8603988603988606,
|
| 23730 |
+
"grad_norm": 0.14769984781742096,
|
| 23731 |
+
"learning_rate": 4.693481537187807e-05,
|
| 23732 |
+
"loss": 0.9164,
|
| 23733 |
+
"step": 3389
|
| 23734 |
+
},
|
| 23735 |
+
{
|
| 23736 |
+
"epoch": 3.8615384615384616,
|
| 23737 |
+
"grad_norm": 0.15641845762729645,
|
| 23738 |
+
"learning_rate": 4.6932579641324234e-05,
|
| 23739 |
+
"loss": 0.9101,
|
| 23740 |
+
"step": 3390
|
| 23741 |
+
},
|
| 23742 |
+
{
|
| 23743 |
+
"epoch": 3.8626780626780626,
|
| 23744 |
+
"grad_norm": 0.144445538520813,
|
| 23745 |
+
"learning_rate": 4.693034314899159e-05,
|
| 23746 |
+
"loss": 0.877,
|
| 23747 |
+
"step": 3391
|
| 23748 |
+
},
|
| 23749 |
+
{
|
| 23750 |
+
"epoch": 3.863817663817664,
|
| 23751 |
+
"grad_norm": 0.15623387694358826,
|
| 23752 |
+
"learning_rate": 4.6928105894957816e-05,
|
| 23753 |
+
"loss": 0.8651,
|
| 23754 |
+
"step": 3392
|
| 23755 |
+
},
|
| 23756 |
+
{
|
| 23757 |
+
"epoch": 3.864957264957265,
|
| 23758 |
+
"grad_norm": 0.14462868869304657,
|
| 23759 |
+
"learning_rate": 4.692586787930063e-05,
|
| 23760 |
+
"loss": 0.8706,
|
| 23761 |
+
"step": 3393
|
| 23762 |
+
},
|
| 23763 |
+
{
|
| 23764 |
+
"epoch": 3.866096866096866,
|
| 23765 |
+
"grad_norm": 0.16158561408519745,
|
| 23766 |
+
"learning_rate": 4.692362910209775e-05,
|
| 23767 |
+
"loss": 0.8211,
|
| 23768 |
+
"step": 3394
|
| 23769 |
+
},
|
| 23770 |
+
{
|
| 23771 |
+
"epoch": 3.8672364672364674,
|
| 23772 |
+
"grad_norm": 0.14164027571678162,
|
| 23773 |
+
"learning_rate": 4.692138956342694e-05,
|
| 23774 |
+
"loss": 0.9125,
|
| 23775 |
+
"step": 3395
|
| 23776 |
+
},
|
| 23777 |
+
{
|
| 23778 |
+
"epoch": 3.8683760683760684,
|
| 23779 |
+
"grad_norm": 0.16288837790489197,
|
| 23780 |
+
"learning_rate": 4.691914926336599e-05,
|
| 23781 |
+
"loss": 0.8973,
|
| 23782 |
+
"step": 3396
|
| 23783 |
+
},
|
| 23784 |
+
{
|
| 23785 |
+
"epoch": 3.8695156695156694,
|
| 23786 |
+
"grad_norm": 0.21154040098190308,
|
| 23787 |
+
"learning_rate": 4.691690820199271e-05,
|
| 23788 |
+
"loss": 0.6815,
|
| 23789 |
+
"step": 3397
|
| 23790 |
+
},
|
| 23791 |
+
{
|
| 23792 |
+
"epoch": 3.870655270655271,
|
| 23793 |
+
"grad_norm": 0.130178302526474,
|
| 23794 |
+
"learning_rate": 4.691466637938493e-05,
|
| 23795 |
+
"loss": 0.9517,
|
| 23796 |
+
"step": 3398
|
| 23797 |
+
},
|
| 23798 |
+
{
|
| 23799 |
+
"epoch": 3.871794871794872,
|
| 23800 |
+
"grad_norm": 0.18135111033916473,
|
| 23801 |
+
"learning_rate": 4.691242379562053e-05,
|
| 23802 |
+
"loss": 0.7641,
|
| 23803 |
+
"step": 3399
|
| 23804 |
+
},
|
| 23805 |
+
{
|
| 23806 |
+
"epoch": 3.872934472934473,
|
| 23807 |
+
"grad_norm": 0.1670042723417282,
|
| 23808 |
+
"learning_rate": 4.6910180450777384e-05,
|
| 23809 |
+
"loss": 0.7716,
|
| 23810 |
+
"step": 3400
|
| 23811 |
+
},
|
| 23812 |
+
{
|
| 23813 |
+
"epoch": 3.8740740740740742,
|
| 23814 |
+
"grad_norm": 0.14281009137630463,
|
| 23815 |
+
"learning_rate": 4.690793634493342e-05,
|
| 23816 |
+
"loss": 0.9608,
|
| 23817 |
+
"step": 3401
|
| 23818 |
+
},
|
| 23819 |
+
{
|
| 23820 |
+
"epoch": 3.875213675213675,
|
| 23821 |
+
"grad_norm": 0.17043545842170715,
|
| 23822 |
+
"learning_rate": 4.690569147816658e-05,
|
| 23823 |
+
"loss": 0.7808,
|
| 23824 |
+
"step": 3402
|
| 23825 |
+
},
|
| 23826 |
+
{
|
| 23827 |
+
"epoch": 3.876353276353276,
|
| 23828 |
+
"grad_norm": 0.18869633972644806,
|
| 23829 |
+
"learning_rate": 4.690344585055484e-05,
|
| 23830 |
+
"loss": 0.7139,
|
| 23831 |
+
"step": 3403
|
| 23832 |
+
},
|
| 23833 |
+
{
|
| 23834 |
+
"epoch": 3.8774928774928776,
|
| 23835 |
+
"grad_norm": 0.13043910264968872,
|
| 23836 |
+
"learning_rate": 4.6901199462176184e-05,
|
| 23837 |
+
"loss": 1.0668,
|
| 23838 |
+
"step": 3404
|
| 23839 |
+
},
|
| 23840 |
+
{
|
| 23841 |
+
"epoch": 3.8786324786324786,
|
| 23842 |
+
"grad_norm": 0.13791286945343018,
|
| 23843 |
+
"learning_rate": 4.689895231310864e-05,
|
| 23844 |
+
"loss": 0.8447,
|
| 23845 |
+
"step": 3405
|
| 23846 |
+
},
|
| 23847 |
+
{
|
| 23848 |
+
"epoch": 3.8797720797720796,
|
| 23849 |
+
"grad_norm": 0.14306683838367462,
|
| 23850 |
+
"learning_rate": 4.6896704403430265e-05,
|
| 23851 |
+
"loss": 0.9538,
|
| 23852 |
+
"step": 3406
|
| 23853 |
+
},
|
| 23854 |
+
{
|
| 23855 |
+
"epoch": 3.880911680911681,
|
| 23856 |
+
"grad_norm": 0.16624945402145386,
|
| 23857 |
+
"learning_rate": 4.689445573321913e-05,
|
| 23858 |
+
"loss": 0.8153,
|
| 23859 |
+
"step": 3407
|
| 23860 |
+
},
|
| 23861 |
+
{
|
| 23862 |
+
"epoch": 3.882051282051282,
|
| 23863 |
+
"grad_norm": 0.16687414050102234,
|
| 23864 |
+
"learning_rate": 4.689220630255333e-05,
|
| 23865 |
+
"loss": 0.8279,
|
| 23866 |
+
"step": 3408
|
| 23867 |
+
},
|
| 23868 |
+
{
|
| 23869 |
+
"epoch": 3.883190883190883,
|
| 23870 |
+
"grad_norm": 0.16535744071006775,
|
| 23871 |
+
"learning_rate": 4.688995611151101e-05,
|
| 23872 |
+
"loss": 0.6107,
|
| 23873 |
+
"step": 3409
|
| 23874 |
+
},
|
| 23875 |
+
{
|
| 23876 |
+
"epoch": 3.8843304843304844,
|
| 23877 |
+
"grad_norm": 0.14052452147006989,
|
| 23878 |
+
"learning_rate": 4.6887705160170314e-05,
|
| 23879 |
+
"loss": 0.7906,
|
| 23880 |
+
"step": 3410
|
| 23881 |
+
},
|
| 23882 |
+
{
|
| 23883 |
+
"epoch": 3.8854700854700854,
|
| 23884 |
+
"grad_norm": 0.15893520414829254,
|
| 23885 |
+
"learning_rate": 4.688545344860943e-05,
|
| 23886 |
+
"loss": 0.72,
|
| 23887 |
+
"step": 3411
|
| 23888 |
+
},
|
| 23889 |
+
{
|
| 23890 |
+
"epoch": 3.8866096866096864,
|
| 23891 |
+
"grad_norm": 0.16928741335868835,
|
| 23892 |
+
"learning_rate": 4.6883200976906556e-05,
|
| 23893 |
+
"loss": 0.723,
|
| 23894 |
+
"step": 3412
|
| 23895 |
+
},
|
| 23896 |
+
{
|
| 23897 |
+
"epoch": 3.887749287749288,
|
| 23898 |
+
"grad_norm": 0.16943496465682983,
|
| 23899 |
+
"learning_rate": 4.6880947745139934e-05,
|
| 23900 |
+
"loss": 0.7667,
|
| 23901 |
+
"step": 3413
|
| 23902 |
+
},
|
| 23903 |
+
{
|
| 23904 |
+
"epoch": 3.888888888888889,
|
| 23905 |
+
"grad_norm": 0.15176483988761902,
|
| 23906 |
+
"learning_rate": 4.687869375338783e-05,
|
| 23907 |
+
"loss": 0.7118,
|
| 23908 |
+
"step": 3414
|
| 23909 |
+
},
|
| 23910 |
+
{
|
| 23911 |
+
"epoch": 3.89002849002849,
|
| 23912 |
+
"grad_norm": 0.17340417206287384,
|
| 23913 |
+
"learning_rate": 4.687643900172852e-05,
|
| 23914 |
+
"loss": 0.8506,
|
| 23915 |
+
"step": 3415
|
| 23916 |
+
},
|
| 23917 |
+
{
|
| 23918 |
+
"epoch": 3.8911680911680913,
|
| 23919 |
+
"grad_norm": 0.15264245867729187,
|
| 23920 |
+
"learning_rate": 4.687418349024032e-05,
|
| 23921 |
+
"loss": 0.9093,
|
| 23922 |
+
"step": 3416
|
| 23923 |
+
},
|
| 23924 |
+
{
|
| 23925 |
+
"epoch": 3.8923076923076922,
|
| 23926 |
+
"grad_norm": 0.14344799518585205,
|
| 23927 |
+
"learning_rate": 4.6871927219001576e-05,
|
| 23928 |
+
"loss": 0.8267,
|
| 23929 |
+
"step": 3417
|
| 23930 |
+
},
|
| 23931 |
+
{
|
| 23932 |
+
"epoch": 3.8934472934472932,
|
| 23933 |
+
"grad_norm": 0.16674695909023285,
|
| 23934 |
+
"learning_rate": 4.686967018809065e-05,
|
| 23935 |
+
"loss": 0.8371,
|
| 23936 |
+
"step": 3418
|
| 23937 |
+
},
|
| 23938 |
+
{
|
| 23939 |
+
"epoch": 3.8945868945868947,
|
| 23940 |
+
"grad_norm": 0.1460442692041397,
|
| 23941 |
+
"learning_rate": 4.686741239758594e-05,
|
| 23942 |
+
"loss": 1.0146,
|
| 23943 |
+
"step": 3419
|
| 23944 |
+
},
|
| 23945 |
+
{
|
| 23946 |
+
"epoch": 3.8957264957264957,
|
| 23947 |
+
"grad_norm": 0.17456045746803284,
|
| 23948 |
+
"learning_rate": 4.686515384756587e-05,
|
| 23949 |
+
"loss": 0.6636,
|
| 23950 |
+
"step": 3420
|
| 23951 |
+
},
|
| 23952 |
+
{
|
| 23953 |
+
"epoch": 3.8968660968660966,
|
| 23954 |
+
"grad_norm": 0.24361936748027802,
|
| 23955 |
+
"learning_rate": 4.686289453810886e-05,
|
| 23956 |
+
"loss": 0.4847,
|
| 23957 |
+
"step": 3421
|
| 23958 |
+
},
|
| 23959 |
+
{
|
| 23960 |
+
"epoch": 3.898005698005698,
|
| 23961 |
+
"grad_norm": 0.12225434184074402,
|
| 23962 |
+
"learning_rate": 4.686063446929341e-05,
|
| 23963 |
+
"loss": 1.0733,
|
| 23964 |
+
"step": 3422
|
| 23965 |
+
},
|
| 23966 |
+
{
|
| 23967 |
+
"epoch": 3.899145299145299,
|
| 23968 |
+
"grad_norm": 0.1633254885673523,
|
| 23969 |
+
"learning_rate": 4.6858373641198e-05,
|
| 23970 |
+
"loss": 0.8836,
|
| 23971 |
+
"step": 3423
|
| 23972 |
+
},
|
| 23973 |
+
{
|
| 23974 |
+
"epoch": 3.9002849002849,
|
| 23975 |
+
"grad_norm": 0.16331011056900024,
|
| 23976 |
+
"learning_rate": 4.685611205390117e-05,
|
| 23977 |
+
"loss": 0.8265,
|
| 23978 |
+
"step": 3424
|
| 23979 |
+
},
|
| 23980 |
+
{
|
| 23981 |
+
"epoch": 3.9014245014245015,
|
| 23982 |
+
"grad_norm": 0.13616515696048737,
|
| 23983 |
+
"learning_rate": 4.6853849707481466e-05,
|
| 23984 |
+
"loss": 0.893,
|
| 23985 |
+
"step": 3425
|
| 23986 |
+
},
|
| 23987 |
+
{
|
| 23988 |
+
"epoch": 3.9025641025641025,
|
| 23989 |
+
"grad_norm": 0.14399182796478271,
|
| 23990 |
+
"learning_rate": 4.685158660201746e-05,
|
| 23991 |
+
"loss": 0.7359,
|
| 23992 |
+
"step": 3426
|
| 23993 |
+
},
|
| 23994 |
+
{
|
| 23995 |
+
"epoch": 3.9037037037037035,
|
| 23996 |
+
"grad_norm": 0.16251274943351746,
|
| 23997 |
+
"learning_rate": 4.6849322737587765e-05,
|
| 23998 |
+
"loss": 0.8572,
|
| 23999 |
+
"step": 3427
|
| 24000 |
+
},
|
| 24001 |
+
{
|
| 24002 |
+
"epoch": 3.904843304843305,
|
| 24003 |
+
"grad_norm": 0.13758879899978638,
|
| 24004 |
+
"learning_rate": 4.684705811427099e-05,
|
| 24005 |
+
"loss": 0.9263,
|
| 24006 |
+
"step": 3428
|
| 24007 |
+
},
|
| 24008 |
+
{
|
| 24009 |
+
"epoch": 3.905982905982906,
|
| 24010 |
+
"grad_norm": 0.1321915239095688,
|
| 24011 |
+
"learning_rate": 4.684479273214582e-05,
|
| 24012 |
+
"loss": 0.8173,
|
| 24013 |
+
"step": 3429
|
| 24014 |
+
},
|
| 24015 |
+
{
|
| 24016 |
+
"epoch": 3.907122507122507,
|
| 24017 |
+
"grad_norm": 0.172994464635849,
|
| 24018 |
+
"learning_rate": 4.684252659129093e-05,
|
| 24019 |
+
"loss": 0.7523,
|
| 24020 |
+
"step": 3430
|
| 24021 |
+
},
|
| 24022 |
+
{
|
| 24023 |
+
"epoch": 3.9082621082621083,
|
| 24024 |
+
"grad_norm": 0.1446010023355484,
|
| 24025 |
+
"learning_rate": 4.684025969178501e-05,
|
| 24026 |
+
"loss": 0.9883,
|
| 24027 |
+
"step": 3431
|
| 24028 |
+
},
|
| 24029 |
+
{
|
| 24030 |
+
"epoch": 3.9094017094017093,
|
| 24031 |
+
"grad_norm": 0.15167920291423798,
|
| 24032 |
+
"learning_rate": 4.6837992033706815e-05,
|
| 24033 |
+
"loss": 0.7456,
|
| 24034 |
+
"step": 3432
|
| 24035 |
+
},
|
| 24036 |
+
{
|
| 24037 |
+
"epoch": 3.9105413105413103,
|
| 24038 |
+
"grad_norm": 0.16871385276317596,
|
| 24039 |
+
"learning_rate": 4.68357236171351e-05,
|
| 24040 |
+
"loss": 0.8245,
|
| 24041 |
+
"step": 3433
|
| 24042 |
+
},
|
| 24043 |
+
{
|
| 24044 |
+
"epoch": 3.9116809116809117,
|
| 24045 |
+
"grad_norm": 0.1432938277721405,
|
| 24046 |
+
"learning_rate": 4.683345444214866e-05,
|
| 24047 |
+
"loss": 0.9974,
|
| 24048 |
+
"step": 3434
|
| 24049 |
+
},
|
| 24050 |
+
{
|
| 24051 |
+
"epoch": 3.9128205128205127,
|
| 24052 |
+
"grad_norm": 0.16849583387374878,
|
| 24053 |
+
"learning_rate": 4.68311845088263e-05,
|
| 24054 |
+
"loss": 0.8222,
|
| 24055 |
+
"step": 3435
|
| 24056 |
+
},
|
| 24057 |
+
{
|
| 24058 |
+
"epoch": 3.913960113960114,
|
| 24059 |
+
"grad_norm": 0.1425115168094635,
|
| 24060 |
+
"learning_rate": 4.6828913817246875e-05,
|
| 24061 |
+
"loss": 0.9264,
|
| 24062 |
+
"step": 3436
|
| 24063 |
+
},
|
| 24064 |
+
{
|
| 24065 |
+
"epoch": 3.915099715099715,
|
| 24066 |
+
"grad_norm": 0.1551201045513153,
|
| 24067 |
+
"learning_rate": 4.682664236748924e-05,
|
| 24068 |
+
"loss": 0.9058,
|
| 24069 |
+
"step": 3437
|
| 24070 |
+
},
|
| 24071 |
+
{
|
| 24072 |
+
"epoch": 3.916239316239316,
|
| 24073 |
+
"grad_norm": 0.16255636513233185,
|
| 24074 |
+
"learning_rate": 4.682437015963228e-05,
|
| 24075 |
+
"loss": 0.7827,
|
| 24076 |
+
"step": 3438
|
| 24077 |
+
},
|
| 24078 |
+
{
|
| 24079 |
+
"epoch": 3.9173789173789175,
|
| 24080 |
+
"grad_norm": 0.135501891374588,
|
| 24081 |
+
"learning_rate": 4.682209719375494e-05,
|
| 24082 |
+
"loss": 0.9333,
|
| 24083 |
+
"step": 3439
|
| 24084 |
+
},
|
| 24085 |
+
{
|
| 24086 |
+
"epoch": 3.9185185185185185,
|
| 24087 |
+
"grad_norm": 0.14796842634677887,
|
| 24088 |
+
"learning_rate": 4.6819823469936154e-05,
|
| 24089 |
+
"loss": 0.8812,
|
| 24090 |
+
"step": 3440
|
| 24091 |
+
},
|
| 24092 |
+
{
|
| 24093 |
+
"epoch": 3.9196581196581195,
|
| 24094 |
+
"grad_norm": 0.17937713861465454,
|
| 24095 |
+
"learning_rate": 4.681754898825489e-05,
|
| 24096 |
+
"loss": 0.6784,
|
| 24097 |
+
"step": 3441
|
| 24098 |
+
},
|
| 24099 |
+
{
|
| 24100 |
+
"epoch": 3.920797720797721,
|
| 24101 |
+
"grad_norm": 0.19107134640216827,
|
| 24102 |
+
"learning_rate": 4.681527374879015e-05,
|
| 24103 |
+
"loss": 0.7208,
|
| 24104 |
+
"step": 3442
|
| 24105 |
+
},
|
| 24106 |
+
{
|
| 24107 |
+
"epoch": 3.921937321937322,
|
| 24108 |
+
"grad_norm": 0.12797027826309204,
|
| 24109 |
+
"learning_rate": 4.681299775162096e-05,
|
| 24110 |
+
"loss": 0.9502,
|
| 24111 |
+
"step": 3443
|
| 24112 |
+
},
|
| 24113 |
+
{
|
| 24114 |
+
"epoch": 3.9230769230769234,
|
| 24115 |
+
"grad_norm": 0.15293848514556885,
|
| 24116 |
+
"learning_rate": 4.681072099682637e-05,
|
| 24117 |
+
"loss": 0.7478,
|
| 24118 |
+
"step": 3444
|
| 24119 |
+
},
|
| 24120 |
+
{
|
| 24121 |
+
"epoch": 3.9242165242165243,
|
| 24122 |
+
"grad_norm": 0.15323732793331146,
|
| 24123 |
+
"learning_rate": 4.6808443484485466e-05,
|
| 24124 |
+
"loss": 0.967,
|
| 24125 |
+
"step": 3445
|
| 24126 |
+
},
|
| 24127 |
+
{
|
| 24128 |
+
"epoch": 3.9253561253561253,
|
| 24129 |
+
"grad_norm": 0.14220960438251495,
|
| 24130 |
+
"learning_rate": 4.6806165214677346e-05,
|
| 24131 |
+
"loss": 0.8756,
|
| 24132 |
+
"step": 3446
|
| 24133 |
+
},
|
| 24134 |
+
{
|
| 24135 |
+
"epoch": 3.9264957264957268,
|
| 24136 |
+
"grad_norm": 0.16512326896190643,
|
| 24137 |
+
"learning_rate": 4.680388618748114e-05,
|
| 24138 |
+
"loss": 0.9124,
|
| 24139 |
+
"step": 3447
|
| 24140 |
+
},
|
| 24141 |
+
{
|
| 24142 |
+
"epoch": 3.9276353276353277,
|
| 24143 |
+
"grad_norm": 0.16266563534736633,
|
| 24144 |
+
"learning_rate": 4.6801606402976005e-05,
|
| 24145 |
+
"loss": 0.8936,
|
| 24146 |
+
"step": 3448
|
| 24147 |
+
},
|
| 24148 |
+
{
|
| 24149 |
+
"epoch": 3.9287749287749287,
|
| 24150 |
+
"grad_norm": 0.15460358560085297,
|
| 24151 |
+
"learning_rate": 4.6799325861241125e-05,
|
| 24152 |
+
"loss": 0.7959,
|
| 24153 |
+
"step": 3449
|
| 24154 |
+
},
|
| 24155 |
+
{
|
| 24156 |
+
"epoch": 3.92991452991453,
|
| 24157 |
+
"grad_norm": 0.13435477018356323,
|
| 24158 |
+
"learning_rate": 4.679704456235571e-05,
|
| 24159 |
+
"loss": 1.0186,
|
| 24160 |
+
"step": 3450
|
| 24161 |
+
},
|
| 24162 |
+
{
|
| 24163 |
+
"epoch": 3.931054131054131,
|
| 24164 |
+
"grad_norm": 0.15804614126682281,
|
| 24165 |
+
"learning_rate": 4.679476250639899e-05,
|
| 24166 |
+
"loss": 0.942,
|
| 24167 |
+
"step": 3451
|
| 24168 |
+
},
|
| 24169 |
+
{
|
| 24170 |
+
"epoch": 3.932193732193732,
|
| 24171 |
+
"grad_norm": 0.17201738059520721,
|
| 24172 |
+
"learning_rate": 4.679247969345024e-05,
|
| 24173 |
+
"loss": 0.7787,
|
| 24174 |
+
"step": 3452
|
| 24175 |
+
},
|
| 24176 |
+
{
|
| 24177 |
+
"epoch": 3.9333333333333336,
|
| 24178 |
+
"grad_norm": 0.15990282595157623,
|
| 24179 |
+
"learning_rate": 4.6790196123588735e-05,
|
| 24180 |
+
"loss": 0.8476,
|
| 24181 |
+
"step": 3453
|
| 24182 |
+
},
|
| 24183 |
+
{
|
| 24184 |
+
"epoch": 3.9344729344729346,
|
| 24185 |
+
"grad_norm": 0.14648666977882385,
|
| 24186 |
+
"learning_rate": 4.6787911796893804e-05,
|
| 24187 |
+
"loss": 0.8386,
|
| 24188 |
+
"step": 3454
|
| 24189 |
+
},
|
| 24190 |
+
{
|
| 24191 |
+
"epoch": 3.9356125356125355,
|
| 24192 |
+
"grad_norm": 0.14609716832637787,
|
| 24193 |
+
"learning_rate": 4.678562671344477e-05,
|
| 24194 |
+
"loss": 0.9798,
|
| 24195 |
+
"step": 3455
|
| 24196 |
+
},
|
| 24197 |
+
{
|
| 24198 |
+
"epoch": 3.936752136752137,
|
| 24199 |
+
"grad_norm": 0.14763420820236206,
|
| 24200 |
+
"learning_rate": 4.6783340873321014e-05,
|
| 24201 |
+
"loss": 0.8774,
|
| 24202 |
+
"step": 3456
|
| 24203 |
+
},
|
| 24204 |
+
{
|
| 24205 |
+
"epoch": 3.937891737891738,
|
| 24206 |
+
"grad_norm": 0.14125679433345795,
|
| 24207 |
+
"learning_rate": 4.678105427660192e-05,
|
| 24208 |
+
"loss": 0.739,
|
| 24209 |
+
"step": 3457
|
| 24210 |
+
},
|
| 24211 |
+
{
|
| 24212 |
+
"epoch": 3.939031339031339,
|
| 24213 |
+
"grad_norm": 0.13715296983718872,
|
| 24214 |
+
"learning_rate": 4.677876692336693e-05,
|
| 24215 |
+
"loss": 0.8174,
|
| 24216 |
+
"step": 3458
|
| 24217 |
+
},
|
| 24218 |
+
{
|
| 24219 |
+
"epoch": 3.9401709401709404,
|
| 24220 |
+
"grad_norm": 0.14227436482906342,
|
| 24221 |
+
"learning_rate": 4.6776478813695446e-05,
|
| 24222 |
+
"loss": 0.8349,
|
| 24223 |
+
"step": 3459
|
| 24224 |
+
},
|
| 24225 |
+
{
|
| 24226 |
+
"epoch": 3.9413105413105414,
|
| 24227 |
+
"grad_norm": 0.15223047137260437,
|
| 24228 |
+
"learning_rate": 4.677418994766698e-05,
|
| 24229 |
+
"loss": 0.8952,
|
| 24230 |
+
"step": 3460
|
| 24231 |
+
},
|
| 24232 |
+
{
|
| 24233 |
+
"epoch": 3.9424501424501424,
|
| 24234 |
+
"grad_norm": 0.1365755945444107,
|
| 24235 |
+
"learning_rate": 4.677190032536102e-05,
|
| 24236 |
+
"loss": 0.8954,
|
| 24237 |
+
"step": 3461
|
| 24238 |
+
},
|
| 24239 |
+
{
|
| 24240 |
+
"epoch": 3.943589743589744,
|
| 24241 |
+
"grad_norm": 0.16250252723693848,
|
| 24242 |
+
"learning_rate": 4.676960994685709e-05,
|
| 24243 |
+
"loss": 0.8019,
|
| 24244 |
+
"step": 3462
|
| 24245 |
+
},
|
| 24246 |
+
{
|
| 24247 |
+
"epoch": 3.9447293447293448,
|
| 24248 |
+
"grad_norm": 0.16038726270198822,
|
| 24249 |
+
"learning_rate": 4.676731881223474e-05,
|
| 24250 |
+
"loss": 0.7893,
|
| 24251 |
+
"step": 3463
|
| 24252 |
+
},
|
| 24253 |
+
{
|
| 24254 |
+
"epoch": 3.9458689458689458,
|
| 24255 |
+
"grad_norm": 0.1472318321466446,
|
| 24256 |
+
"learning_rate": 4.676502692157354e-05,
|
| 24257 |
+
"loss": 0.8278,
|
| 24258 |
+
"step": 3464
|
| 24259 |
+
},
|
| 24260 |
+
{
|
| 24261 |
+
"epoch": 3.947008547008547,
|
| 24262 |
+
"grad_norm": 0.1726992130279541,
|
| 24263 |
+
"learning_rate": 4.676273427495311e-05,
|
| 24264 |
+
"loss": 0.7704,
|
| 24265 |
+
"step": 3465
|
| 24266 |
+
},
|
| 24267 |
+
{
|
| 24268 |
+
"epoch": 3.948148148148148,
|
| 24269 |
+
"grad_norm": 0.22516140341758728,
|
| 24270 |
+
"learning_rate": 4.676044087245306e-05,
|
| 24271 |
+
"loss": 0.8842,
|
| 24272 |
+
"step": 3466
|
| 24273 |
+
},
|
| 24274 |
+
{
|
| 24275 |
+
"epoch": 3.949287749287749,
|
| 24276 |
+
"grad_norm": 0.14022859930992126,
|
| 24277 |
+
"learning_rate": 4.675814671415307e-05,
|
| 24278 |
+
"loss": 0.7451,
|
| 24279 |
+
"step": 3467
|
| 24280 |
+
},
|
| 24281 |
+
{
|
| 24282 |
+
"epoch": 3.9504273504273506,
|
| 24283 |
+
"grad_norm": 0.18753965198993683,
|
| 24284 |
+
"learning_rate": 4.67558518001328e-05,
|
| 24285 |
+
"loss": 0.7253,
|
| 24286 |
+
"step": 3468
|
| 24287 |
+
},
|
| 24288 |
+
{
|
| 24289 |
+
"epoch": 3.9515669515669516,
|
| 24290 |
+
"grad_norm": 0.14902377128601074,
|
| 24291 |
+
"learning_rate": 4.675355613047197e-05,
|
| 24292 |
+
"loss": 0.9185,
|
| 24293 |
+
"step": 3469
|
| 24294 |
+
},
|
| 24295 |
+
{
|
| 24296 |
+
"epoch": 3.9527065527065526,
|
| 24297 |
+
"grad_norm": 0.16637928783893585,
|
| 24298 |
+
"learning_rate": 4.675125970525031e-05,
|
| 24299 |
+
"loss": 0.7003,
|
| 24300 |
+
"step": 3470
|
| 24301 |
+
},
|
| 24302 |
+
{
|
| 24303 |
+
"epoch": 3.953846153846154,
|
| 24304 |
+
"grad_norm": 0.15486907958984375,
|
| 24305 |
+
"learning_rate": 4.6748962524547594e-05,
|
| 24306 |
+
"loss": 0.8815,
|
| 24307 |
+
"step": 3471
|
| 24308 |
+
},
|
| 24309 |
+
{
|
| 24310 |
+
"epoch": 3.954985754985755,
|
| 24311 |
+
"grad_norm": 0.14602243900299072,
|
| 24312 |
+
"learning_rate": 4.674666458844359e-05,
|
| 24313 |
+
"loss": 0.6844,
|
| 24314 |
+
"step": 3472
|
| 24315 |
+
},
|
| 24316 |
+
{
|
| 24317 |
+
"epoch": 3.956125356125356,
|
| 24318 |
+
"grad_norm": 0.18017630279064178,
|
| 24319 |
+
"learning_rate": 4.674436589701813e-05,
|
| 24320 |
+
"loss": 0.7329,
|
| 24321 |
+
"step": 3473
|
| 24322 |
+
},
|
| 24323 |
+
{
|
| 24324 |
+
"epoch": 3.9572649572649574,
|
| 24325 |
+
"grad_norm": 0.15623396635055542,
|
| 24326 |
+
"learning_rate": 4.674206645035104e-05,
|
| 24327 |
+
"loss": 0.8304,
|
| 24328 |
+
"step": 3474
|
| 24329 |
+
},
|
| 24330 |
+
{
|
| 24331 |
+
"epoch": 3.9584045584045584,
|
| 24332 |
+
"grad_norm": 0.1459084302186966,
|
| 24333 |
+
"learning_rate": 4.6739766248522194e-05,
|
| 24334 |
+
"loss": 0.9101,
|
| 24335 |
+
"step": 3475
|
| 24336 |
+
},
|
| 24337 |
+
{
|
| 24338 |
+
"epoch": 3.9595441595441594,
|
| 24339 |
+
"grad_norm": 0.1555999517440796,
|
| 24340 |
+
"learning_rate": 4.6737465291611484e-05,
|
| 24341 |
+
"loss": 0.8722,
|
| 24342 |
+
"step": 3476
|
| 24343 |
+
},
|
| 24344 |
+
{
|
| 24345 |
+
"epoch": 3.960683760683761,
|
| 24346 |
+
"grad_norm": 0.166189044713974,
|
| 24347 |
+
"learning_rate": 4.673516357969882e-05,
|
| 24348 |
+
"loss": 0.7908,
|
| 24349 |
+
"step": 3477
|
| 24350 |
+
},
|
| 24351 |
+
{
|
| 24352 |
+
"epoch": 3.961823361823362,
|
| 24353 |
+
"grad_norm": 0.16147474944591522,
|
| 24354 |
+
"learning_rate": 4.673286111286415e-05,
|
| 24355 |
+
"loss": 0.8033,
|
| 24356 |
+
"step": 3478
|
| 24357 |
+
},
|
| 24358 |
+
{
|
| 24359 |
+
"epoch": 3.962962962962963,
|
| 24360 |
+
"grad_norm": 0.14976289868354797,
|
| 24361 |
+
"learning_rate": 4.673055789118745e-05,
|
| 24362 |
+
"loss": 0.7987,
|
| 24363 |
+
"step": 3479
|
| 24364 |
+
},
|
| 24365 |
+
{
|
| 24366 |
+
"epoch": 3.9641025641025642,
|
| 24367 |
+
"grad_norm": 0.1402273029088974,
|
| 24368 |
+
"learning_rate": 4.672825391474872e-05,
|
| 24369 |
+
"loss": 1.0181,
|
| 24370 |
+
"step": 3480
|
| 24371 |
+
},
|
| 24372 |
+
{
|
| 24373 |
+
"epoch": 3.965242165242165,
|
| 24374 |
+
"grad_norm": 0.15403476357460022,
|
| 24375 |
+
"learning_rate": 4.6725949183627975e-05,
|
| 24376 |
+
"loss": 0.6773,
|
| 24377 |
+
"step": 3481
|
| 24378 |
+
},
|
| 24379 |
+
{
|
| 24380 |
+
"epoch": 3.966381766381766,
|
| 24381 |
+
"grad_norm": 0.16899093985557556,
|
| 24382 |
+
"learning_rate": 4.6723643697905274e-05,
|
| 24383 |
+
"loss": 0.725,
|
| 24384 |
+
"step": 3482
|
| 24385 |
+
},
|
| 24386 |
+
{
|
| 24387 |
+
"epoch": 3.9675213675213676,
|
| 24388 |
+
"grad_norm": 0.15205314755439758,
|
| 24389 |
+
"learning_rate": 4.672133745766068e-05,
|
| 24390 |
+
"loss": 0.8625,
|
| 24391 |
+
"step": 3483
|
| 24392 |
+
},
|
| 24393 |
+
{
|
| 24394 |
+
"epoch": 3.9686609686609686,
|
| 24395 |
+
"grad_norm": 0.13682928681373596,
|
| 24396 |
+
"learning_rate": 4.6719030462974304e-05,
|
| 24397 |
+
"loss": 0.8228,
|
| 24398 |
+
"step": 3484
|
| 24399 |
+
},
|
| 24400 |
+
{
|
| 24401 |
+
"epoch": 3.9698005698005696,
|
| 24402 |
+
"grad_norm": 0.16801244020462036,
|
| 24403 |
+
"learning_rate": 4.671672271392627e-05,
|
| 24404 |
+
"loss": 0.9002,
|
| 24405 |
+
"step": 3485
|
| 24406 |
+
},
|
| 24407 |
+
{
|
| 24408 |
+
"epoch": 3.970940170940171,
|
| 24409 |
+
"grad_norm": 0.15570217370986938,
|
| 24410 |
+
"learning_rate": 4.6714414210596744e-05,
|
| 24411 |
+
"loss": 0.8369,
|
| 24412 |
+
"step": 3486
|
| 24413 |
+
},
|
| 24414 |
+
{
|
| 24415 |
+
"epoch": 3.972079772079772,
|
| 24416 |
+
"grad_norm": 0.14175504446029663,
|
| 24417 |
+
"learning_rate": 4.6712104953065894e-05,
|
| 24418 |
+
"loss": 0.932,
|
| 24419 |
+
"step": 3487
|
| 24420 |
+
},
|
| 24421 |
+
{
|
| 24422 |
+
"epoch": 3.973219373219373,
|
| 24423 |
+
"grad_norm": 0.14280645549297333,
|
| 24424 |
+
"learning_rate": 4.670979494141393e-05,
|
| 24425 |
+
"loss": 0.6716,
|
| 24426 |
+
"step": 3488
|
| 24427 |
+
},
|
| 24428 |
+
{
|
| 24429 |
+
"epoch": 3.9743589743589745,
|
| 24430 |
+
"grad_norm": 0.18303732573986053,
|
| 24431 |
+
"learning_rate": 4.670748417572108e-05,
|
| 24432 |
+
"loss": 0.6283,
|
| 24433 |
+
"step": 3489
|
| 24434 |
+
},
|
| 24435 |
+
{
|
| 24436 |
+
"epoch": 3.9754985754985754,
|
| 24437 |
+
"grad_norm": 0.1463060826063156,
|
| 24438 |
+
"learning_rate": 4.6705172656067606e-05,
|
| 24439 |
+
"loss": 0.9817,
|
| 24440 |
+
"step": 3490
|
| 24441 |
+
},
|
| 24442 |
+
{
|
| 24443 |
+
"epoch": 3.9766381766381764,
|
| 24444 |
+
"grad_norm": 0.13618658483028412,
|
| 24445 |
+
"learning_rate": 4.670286038253381e-05,
|
| 24446 |
+
"loss": 0.6886,
|
| 24447 |
+
"step": 3491
|
| 24448 |
+
},
|
| 24449 |
+
{
|
| 24450 |
+
"epoch": 3.977777777777778,
|
| 24451 |
+
"grad_norm": 0.18522575497627258,
|
| 24452 |
+
"learning_rate": 4.670054735519998e-05,
|
| 24453 |
+
"loss": 0.8265,
|
| 24454 |
+
"step": 3492
|
| 24455 |
+
},
|
| 24456 |
+
{
|
| 24457 |
+
"epoch": 3.978917378917379,
|
| 24458 |
+
"grad_norm": 0.14105400443077087,
|
| 24459 |
+
"learning_rate": 4.669823357414647e-05,
|
| 24460 |
+
"loss": 0.7428,
|
| 24461 |
+
"step": 3493
|
| 24462 |
+
},
|
| 24463 |
+
{
|
| 24464 |
+
"epoch": 3.98005698005698,
|
| 24465 |
+
"grad_norm": 0.13627874851226807,
|
| 24466 |
+
"learning_rate": 4.669591903945363e-05,
|
| 24467 |
+
"loss": 0.8517,
|
| 24468 |
+
"step": 3494
|
| 24469 |
+
},
|
| 24470 |
+
{
|
| 24471 |
+
"epoch": 3.9811965811965813,
|
| 24472 |
+
"grad_norm": 0.15071073174476624,
|
| 24473 |
+
"learning_rate": 4.669360375120187e-05,
|
| 24474 |
+
"loss": 0.9303,
|
| 24475 |
+
"step": 3495
|
| 24476 |
+
},
|
| 24477 |
+
{
|
| 24478 |
+
"epoch": 3.9823361823361823,
|
| 24479 |
+
"grad_norm": 0.14497306942939758,
|
| 24480 |
+
"learning_rate": 4.6691287709471574e-05,
|
| 24481 |
+
"loss": 0.8023,
|
| 24482 |
+
"step": 3496
|
| 24483 |
+
},
|
| 24484 |
+
{
|
| 24485 |
+
"epoch": 3.9834757834757832,
|
| 24486 |
+
"grad_norm": 0.16087129712104797,
|
| 24487 |
+
"learning_rate": 4.6688970914343224e-05,
|
| 24488 |
+
"loss": 0.7488,
|
| 24489 |
+
"step": 3497
|
| 24490 |
+
},
|
| 24491 |
+
{
|
| 24492 |
+
"epoch": 3.9846153846153847,
|
| 24493 |
+
"grad_norm": 0.11948225647211075,
|
| 24494 |
+
"learning_rate": 4.668665336589726e-05,
|
| 24495 |
+
"loss": 0.9906,
|
| 24496 |
+
"step": 3498
|
| 24497 |
+
},
|
| 24498 |
+
{
|
| 24499 |
+
"epoch": 3.9857549857549857,
|
| 24500 |
+
"grad_norm": 0.14590954780578613,
|
| 24501 |
+
"learning_rate": 4.668433506421419e-05,
|
| 24502 |
+
"loss": 0.9324,
|
| 24503 |
+
"step": 3499
|
| 24504 |
+
},
|
| 24505 |
+
{
|
| 24506 |
+
"epoch": 3.9868945868945866,
|
| 24507 |
+
"grad_norm": 0.14911605417728424,
|
| 24508 |
+
"learning_rate": 4.668201600937453e-05,
|
| 24509 |
+
"loss": 0.82,
|
| 24510 |
+
"step": 3500
|
| 24511 |
+
},
|
| 24512 |
+
{
|
| 24513 |
+
"epoch": 3.988034188034188,
|
| 24514 |
+
"grad_norm": 0.16907189786434174,
|
| 24515 |
+
"learning_rate": 4.667969620145882e-05,
|
| 24516 |
+
"loss": 0.8538,
|
| 24517 |
+
"step": 3501
|
| 24518 |
+
},
|
| 24519 |
+
{
|
| 24520 |
+
"epoch": 3.989173789173789,
|
| 24521 |
+
"grad_norm": 0.1457272469997406,
|
| 24522 |
+
"learning_rate": 4.6677375640547646e-05,
|
| 24523 |
+
"loss": 0.8234,
|
| 24524 |
+
"step": 3502
|
| 24525 |
+
},
|
| 24526 |
+
{
|
| 24527 |
+
"epoch": 3.99031339031339,
|
| 24528 |
+
"grad_norm": 0.20971538126468658,
|
| 24529 |
+
"learning_rate": 4.667505432672161e-05,
|
| 24530 |
+
"loss": 0.6387,
|
| 24531 |
+
"step": 3503
|
| 24532 |
+
},
|
| 24533 |
+
{
|
| 24534 |
+
"epoch": 3.9914529914529915,
|
| 24535 |
+
"grad_norm": 0.1684182733297348,
|
| 24536 |
+
"learning_rate": 4.6672732260061326e-05,
|
| 24537 |
+
"loss": 0.8368,
|
| 24538 |
+
"step": 3504
|
| 24539 |
+
},
|
| 24540 |
+
{
|
| 24541 |
+
"epoch": 3.9925925925925925,
|
| 24542 |
+
"grad_norm": 0.13544008135795593,
|
| 24543 |
+
"learning_rate": 4.6670409440647455e-05,
|
| 24544 |
+
"loss": 0.8769,
|
| 24545 |
+
"step": 3505
|
| 24546 |
+
},
|
| 24547 |
+
{
|
| 24548 |
+
"epoch": 3.9937321937321935,
|
| 24549 |
+
"grad_norm": 0.15714909136295319,
|
| 24550 |
+
"learning_rate": 4.666808586856066e-05,
|
| 24551 |
+
"loss": 0.7932,
|
| 24552 |
+
"step": 3506
|
| 24553 |
+
},
|
| 24554 |
+
{
|
| 24555 |
+
"epoch": 3.994871794871795,
|
| 24556 |
+
"grad_norm": 0.16212841868400574,
|
| 24557 |
+
"learning_rate": 4.666576154388166e-05,
|
| 24558 |
+
"loss": 0.8595,
|
| 24559 |
+
"step": 3507
|
| 24560 |
+
},
|
| 24561 |
+
{
|
| 24562 |
+
"epoch": 3.996011396011396,
|
| 24563 |
+
"grad_norm": 0.20602630078792572,
|
| 24564 |
+
"learning_rate": 4.666343646669118e-05,
|
| 24565 |
+
"loss": 0.8981,
|
| 24566 |
+
"step": 3508
|
| 24567 |
+
},
|
| 24568 |
+
{
|
| 24569 |
+
"epoch": 3.9971509971509973,
|
| 24570 |
+
"grad_norm": 0.15896059572696686,
|
| 24571 |
+
"learning_rate": 4.666111063706998e-05,
|
| 24572 |
+
"loss": 0.8023,
|
| 24573 |
+
"step": 3509
|
| 24574 |
+
},
|
| 24575 |
+
{
|
| 24576 |
+
"epoch": 3.9982905982905983,
|
| 24577 |
+
"grad_norm": 0.148764505982399,
|
| 24578 |
+
"learning_rate": 4.665878405509883e-05,
|
| 24579 |
+
"loss": 0.727,
|
| 24580 |
+
"step": 3510
|
| 24581 |
+
},
|
| 24582 |
+
{
|
| 24583 |
+
"epoch": 3.9994301994301993,
|
| 24584 |
+
"grad_norm": 0.16278378665447235,
|
| 24585 |
+
"learning_rate": 4.665645672085856e-05,
|
| 24586 |
+
"loss": 0.7494,
|
| 24587 |
+
"step": 3511
|
| 24588 |
+
},
|
| 24589 |
+
{
|
| 24590 |
+
"epoch": 4.0,
|
| 24591 |
+
"grad_norm": 0.3494948446750641,
|
| 24592 |
+
"learning_rate": 4.6654128634429996e-05,
|
| 24593 |
+
"loss": 0.6898,
|
| 24594 |
+
"step": 3512
|
| 24595 |
+
},
|
| 24596 |
+
{
|
| 24597 |
+
"epoch": 4.001139601139601,
|
| 24598 |
+
"grad_norm": 0.156687393784523,
|
| 24599 |
+
"learning_rate": 4.665179979589399e-05,
|
| 24600 |
+
"loss": 0.7136,
|
| 24601 |
+
"step": 3513
|
| 24602 |
+
},
|
| 24603 |
+
{
|
| 24604 |
+
"epoch": 4.002279202279202,
|
| 24605 |
+
"grad_norm": 0.16005277633666992,
|
| 24606 |
+
"learning_rate": 4.6649470205331424e-05,
|
| 24607 |
+
"loss": 0.8428,
|
| 24608 |
+
"step": 3514
|
| 24609 |
+
},
|
| 24610 |
+
{
|
| 24611 |
+
"epoch": 4.003418803418803,
|
| 24612 |
+
"grad_norm": 0.17963695526123047,
|
| 24613 |
+
"learning_rate": 4.664713986282323e-05,
|
| 24614 |
+
"loss": 0.7718,
|
| 24615 |
+
"step": 3515
|
| 24616 |
+
},
|
| 24617 |
+
{
|
| 24618 |
+
"epoch": 4.004558404558405,
|
| 24619 |
+
"grad_norm": 0.16050583124160767,
|
| 24620 |
+
"learning_rate": 4.6644808768450346e-05,
|
| 24621 |
+
"loss": 0.8189,
|
| 24622 |
+
"step": 3516
|
| 24623 |
+
},
|
| 24624 |
+
{
|
| 24625 |
+
"epoch": 4.005698005698005,
|
| 24626 |
+
"grad_norm": 0.1456081122159958,
|
| 24627 |
+
"learning_rate": 4.664247692229372e-05,
|
| 24628 |
+
"loss": 0.7237,
|
| 24629 |
+
"step": 3517
|
| 24630 |
+
},
|
| 24631 |
+
{
|
| 24632 |
+
"epoch": 4.006837606837607,
|
| 24633 |
+
"grad_norm": 0.16313639283180237,
|
| 24634 |
+
"learning_rate": 4.6640144324434355e-05,
|
| 24635 |
+
"loss": 0.8514,
|
| 24636 |
+
"step": 3518
|
| 24637 |
+
},
|
| 24638 |
+
{
|
| 24639 |
+
"epoch": 4.007977207977208,
|
| 24640 |
+
"grad_norm": 0.16933190822601318,
|
| 24641 |
+
"learning_rate": 4.663781097495327e-05,
|
| 24642 |
+
"loss": 0.8514,
|
| 24643 |
+
"step": 3519
|
| 24644 |
+
},
|
| 24645 |
+
{
|
| 24646 |
+
"epoch": 4.009116809116809,
|
| 24647 |
+
"grad_norm": 0.14906363189220428,
|
| 24648 |
+
"learning_rate": 4.66354768739315e-05,
|
| 24649 |
+
"loss": 0.935,
|
| 24650 |
+
"step": 3520
|
| 24651 |
+
},
|
| 24652 |
+
{
|
| 24653 |
+
"epoch": 4.01025641025641,
|
| 24654 |
+
"grad_norm": 0.15414398908615112,
|
| 24655 |
+
"learning_rate": 4.663314202145012e-05,
|
| 24656 |
+
"loss": 0.7571,
|
| 24657 |
+
"step": 3521
|
| 24658 |
+
},
|
| 24659 |
+
{
|
| 24660 |
+
"epoch": 4.011396011396012,
|
| 24661 |
+
"grad_norm": 0.15351127088069916,
|
| 24662 |
+
"learning_rate": 4.6630806417590235e-05,
|
| 24663 |
+
"loss": 0.8924,
|
| 24664 |
+
"step": 3522
|
| 24665 |
+
},
|
| 24666 |
+
{
|
| 24667 |
+
"epoch": 4.012535612535612,
|
| 24668 |
+
"grad_norm": 0.17059801518917084,
|
| 24669 |
+
"learning_rate": 4.662847006243295e-05,
|
| 24670 |
+
"loss": 0.5921,
|
| 24671 |
+
"step": 3523
|
| 24672 |
+
},
|
| 24673 |
+
{
|
| 24674 |
+
"epoch": 4.013675213675214,
|
| 24675 |
+
"grad_norm": 0.1579991728067398,
|
| 24676 |
+
"learning_rate": 4.662613295605942e-05,
|
| 24677 |
+
"loss": 0.6791,
|
| 24678 |
+
"step": 3524
|
| 24679 |
+
},
|
| 24680 |
+
{
|
| 24681 |
+
"epoch": 4.014814814814815,
|
| 24682 |
+
"grad_norm": 0.15408803522586823,
|
| 24683 |
+
"learning_rate": 4.6623795098550825e-05,
|
| 24684 |
+
"loss": 0.8667,
|
| 24685 |
+
"step": 3525
|
| 24686 |
+
},
|
| 24687 |
+
{
|
| 24688 |
+
"epoch": 4.015954415954416,
|
| 24689 |
+
"grad_norm": 0.15600430965423584,
|
| 24690 |
+
"learning_rate": 4.662145648998836e-05,
|
| 24691 |
+
"loss": 0.7489,
|
| 24692 |
+
"step": 3526
|
| 24693 |
+
},
|
| 24694 |
+
{
|
| 24695 |
+
"epoch": 4.017094017094017,
|
| 24696 |
+
"grad_norm": 0.13071642816066742,
|
| 24697 |
+
"learning_rate": 4.6619117130453254e-05,
|
| 24698 |
+
"loss": 0.8093,
|
| 24699 |
+
"step": 3527
|
| 24700 |
+
},
|
| 24701 |
+
{
|
| 24702 |
+
"epoch": 4.0182336182336185,
|
| 24703 |
+
"grad_norm": 0.12814581394195557,
|
| 24704 |
+
"learning_rate": 4.661677702002676e-05,
|
| 24705 |
+
"loss": 0.9089,
|
| 24706 |
+
"step": 3528
|
| 24707 |
+
},
|
| 24708 |
+
{
|
| 24709 |
+
"epoch": 4.019373219373219,
|
| 24710 |
+
"grad_norm": 0.15070417523384094,
|
| 24711 |
+
"learning_rate": 4.661443615879015e-05,
|
| 24712 |
+
"loss": 0.6987,
|
| 24713 |
+
"step": 3529
|
| 24714 |
+
},
|
| 24715 |
+
{
|
| 24716 |
+
"epoch": 4.02051282051282,
|
| 24717 |
+
"grad_norm": 0.1645977795124054,
|
| 24718 |
+
"learning_rate": 4.661209454682472e-05,
|
| 24719 |
+
"loss": 0.7235,
|
| 24720 |
+
"step": 3530
|
| 24721 |
+
},
|
| 24722 |
+
{
|
| 24723 |
+
"epoch": 4.021652421652422,
|
| 24724 |
+
"grad_norm": 0.14421582221984863,
|
| 24725 |
+
"learning_rate": 4.660975218421183e-05,
|
| 24726 |
+
"loss": 0.8332,
|
| 24727 |
+
"step": 3531
|
| 24728 |
+
},
|
| 24729 |
+
{
|
| 24730 |
+
"epoch": 4.022792022792022,
|
| 24731 |
+
"grad_norm": 0.189396470785141,
|
| 24732 |
+
"learning_rate": 4.6607409071032815e-05,
|
| 24733 |
+
"loss": 0.7734,
|
| 24734 |
+
"step": 3532
|
| 24735 |
+
},
|
| 24736 |
+
{
|
| 24737 |
+
"epoch": 4.023931623931624,
|
| 24738 |
+
"grad_norm": 0.14422671496868134,
|
| 24739 |
+
"learning_rate": 4.660506520736906e-05,
|
| 24740 |
+
"loss": 0.8768,
|
| 24741 |
+
"step": 3533
|
| 24742 |
+
},
|
| 24743 |
+
{
|
| 24744 |
+
"epoch": 4.025071225071225,
|
| 24745 |
+
"grad_norm": 0.17115554213523865,
|
| 24746 |
+
"learning_rate": 4.660272059330198e-05,
|
| 24747 |
+
"loss": 0.8174,
|
| 24748 |
+
"step": 3534
|
| 24749 |
+
},
|
| 24750 |
+
{
|
| 24751 |
+
"epoch": 4.026210826210826,
|
| 24752 |
+
"grad_norm": 0.17225325107574463,
|
| 24753 |
+
"learning_rate": 4.6600375228913e-05,
|
| 24754 |
+
"loss": 0.8584,
|
| 24755 |
+
"step": 3535
|
| 24756 |
+
},
|
| 24757 |
+
{
|
| 24758 |
+
"epoch": 4.027350427350427,
|
| 24759 |
+
"grad_norm": 0.16570670902729034,
|
| 24760 |
+
"learning_rate": 4.659802911428359e-05,
|
| 24761 |
+
"loss": 0.9189,
|
| 24762 |
+
"step": 3536
|
| 24763 |
+
},
|
| 24764 |
+
{
|
| 24765 |
+
"epoch": 4.028490028490029,
|
| 24766 |
+
"grad_norm": 0.187309131026268,
|
| 24767 |
+
"learning_rate": 4.659568224949524e-05,
|
| 24768 |
+
"loss": 0.6821,
|
| 24769 |
+
"step": 3537
|
| 24770 |
+
},
|
| 24771 |
+
{
|
| 24772 |
+
"epoch": 4.029629629629629,
|
| 24773 |
+
"grad_norm": 0.11738475412130356,
|
| 24774 |
+
"learning_rate": 4.659333463462945e-05,
|
| 24775 |
+
"loss": 0.9917,
|
| 24776 |
+
"step": 3538
|
| 24777 |
+
},
|
| 24778 |
+
{
|
| 24779 |
+
"epoch": 4.030769230769231,
|
| 24780 |
+
"grad_norm": 0.17785432934761047,
|
| 24781 |
+
"learning_rate": 4.6590986269767766e-05,
|
| 24782 |
+
"loss": 0.8195,
|
| 24783 |
+
"step": 3539
|
| 24784 |
+
},
|
| 24785 |
+
{
|
| 24786 |
+
"epoch": 4.031908831908832,
|
| 24787 |
+
"grad_norm": 0.17022278904914856,
|
| 24788 |
+
"learning_rate": 4.658863715499175e-05,
|
| 24789 |
+
"loss": 0.8277,
|
| 24790 |
+
"step": 3540
|
| 24791 |
+
},
|
| 24792 |
+
{
|
| 24793 |
+
"epoch": 4.033048433048433,
|
| 24794 |
+
"grad_norm": 0.13847829401493073,
|
| 24795 |
+
"learning_rate": 4.658628729038301e-05,
|
| 24796 |
+
"loss": 0.792,
|
| 24797 |
+
"step": 3541
|
| 24798 |
+
},
|
| 24799 |
+
{
|
| 24800 |
+
"epoch": 4.034188034188034,
|
| 24801 |
+
"grad_norm": 0.15126143395900726,
|
| 24802 |
+
"learning_rate": 4.658393667602314e-05,
|
| 24803 |
+
"loss": 0.8249,
|
| 24804 |
+
"step": 3542
|
| 24805 |
+
},
|
| 24806 |
+
{
|
| 24807 |
+
"epoch": 4.0353276353276355,
|
| 24808 |
+
"grad_norm": 0.18600907921791077,
|
| 24809 |
+
"learning_rate": 4.658158531199379e-05,
|
| 24810 |
+
"loss": 0.7253,
|
| 24811 |
+
"step": 3543
|
| 24812 |
+
},
|
| 24813 |
+
{
|
| 24814 |
+
"epoch": 4.036467236467236,
|
| 24815 |
+
"grad_norm": 0.13330426812171936,
|
| 24816 |
+
"learning_rate": 4.6579233198376634e-05,
|
| 24817 |
+
"loss": 0.896,
|
| 24818 |
+
"step": 3544
|
| 24819 |
+
},
|
| 24820 |
+
{
|
| 24821 |
+
"epoch": 4.0376068376068375,
|
| 24822 |
+
"grad_norm": 0.16327106952667236,
|
| 24823 |
+
"learning_rate": 4.6576880335253374e-05,
|
| 24824 |
+
"loss": 0.7623,
|
| 24825 |
+
"step": 3545
|
| 24826 |
+
},
|
| 24827 |
+
{
|
| 24828 |
+
"epoch": 4.038746438746439,
|
| 24829 |
+
"grad_norm": 0.2002708464860916,
|
| 24830 |
+
"learning_rate": 4.6574526722705726e-05,
|
| 24831 |
+
"loss": 0.6612,
|
| 24832 |
+
"step": 3546
|
| 24833 |
+
},
|
| 24834 |
+
{
|
| 24835 |
+
"epoch": 4.0398860398860394,
|
| 24836 |
+
"grad_norm": 0.1520686000585556,
|
| 24837 |
+
"learning_rate": 4.657217236081543e-05,
|
| 24838 |
+
"loss": 1.0156,
|
| 24839 |
+
"step": 3547
|
| 24840 |
+
},
|
| 24841 |
+
{
|
| 24842 |
+
"epoch": 4.041025641025641,
|
| 24843 |
+
"grad_norm": 0.14421986043453217,
|
| 24844 |
+
"learning_rate": 4.656981724966426e-05,
|
| 24845 |
+
"loss": 0.9037,
|
| 24846 |
+
"step": 3548
|
| 24847 |
+
},
|
| 24848 |
+
{
|
| 24849 |
+
"epoch": 4.042165242165242,
|
| 24850 |
+
"grad_norm": 0.14663898944854736,
|
| 24851 |
+
"learning_rate": 4.6567461389334016e-05,
|
| 24852 |
+
"loss": 0.9552,
|
| 24853 |
+
"step": 3549
|
| 24854 |
+
},
|
| 24855 |
+
{
|
| 24856 |
+
"epoch": 4.043304843304844,
|
| 24857 |
+
"grad_norm": 0.15126721560955048,
|
| 24858 |
+
"learning_rate": 4.656510477990653e-05,
|
| 24859 |
+
"loss": 0.8096,
|
| 24860 |
+
"step": 3550
|
| 24861 |
+
},
|
| 24862 |
+
{
|
| 24863 |
+
"epoch": 4.044444444444444,
|
| 24864 |
+
"grad_norm": 0.15986499190330505,
|
| 24865 |
+
"learning_rate": 4.6562747421463655e-05,
|
| 24866 |
+
"loss": 0.7929,
|
| 24867 |
+
"step": 3551
|
| 24868 |
+
},
|
| 24869 |
+
{
|
| 24870 |
+
"epoch": 4.045584045584046,
|
| 24871 |
+
"grad_norm": 0.17100024223327637,
|
| 24872 |
+
"learning_rate": 4.656038931408726e-05,
|
| 24873 |
+
"loss": 0.6964,
|
| 24874 |
+
"step": 3552
|
| 24875 |
+
},
|
| 24876 |
+
{
|
| 24877 |
+
"epoch": 4.046723646723647,
|
| 24878 |
+
"grad_norm": 0.14742796123027802,
|
| 24879 |
+
"learning_rate": 4.655803045785926e-05,
|
| 24880 |
+
"loss": 0.9442,
|
| 24881 |
+
"step": 3553
|
| 24882 |
+
},
|
| 24883 |
+
{
|
| 24884 |
+
"epoch": 4.047863247863248,
|
| 24885 |
+
"grad_norm": 0.15347158908843994,
|
| 24886 |
+
"learning_rate": 4.6555670852861574e-05,
|
| 24887 |
+
"loss": 0.7916,
|
| 24888 |
+
"step": 3554
|
| 24889 |
+
},
|
| 24890 |
+
{
|
| 24891 |
+
"epoch": 4.049002849002849,
|
| 24892 |
+
"grad_norm": 0.16807137429714203,
|
| 24893 |
+
"learning_rate": 4.6553310499176154e-05,
|
| 24894 |
+
"loss": 0.7506,
|
| 24895 |
+
"step": 3555
|
| 24896 |
+
},
|
| 24897 |
+
{
|
| 24898 |
+
"epoch": 4.050142450142451,
|
| 24899 |
+
"grad_norm": 0.15673980116844177,
|
| 24900 |
+
"learning_rate": 4.6550949396884995e-05,
|
| 24901 |
+
"loss": 0.8105,
|
| 24902 |
+
"step": 3556
|
| 24903 |
+
},
|
| 24904 |
+
{
|
| 24905 |
+
"epoch": 4.051282051282051,
|
| 24906 |
+
"grad_norm": 0.13703081011772156,
|
| 24907 |
+
"learning_rate": 4.65485875460701e-05,
|
| 24908 |
+
"loss": 0.9299,
|
| 24909 |
+
"step": 3557
|
| 24910 |
+
},
|
| 24911 |
+
{
|
| 24912 |
+
"epoch": 4.0524216524216525,
|
| 24913 |
+
"grad_norm": 0.14694665372371674,
|
| 24914 |
+
"learning_rate": 4.65462249468135e-05,
|
| 24915 |
+
"loss": 0.8278,
|
| 24916 |
+
"step": 3558
|
| 24917 |
+
},
|
| 24918 |
+
{
|
| 24919 |
+
"epoch": 4.053561253561254,
|
| 24920 |
+
"grad_norm": 0.15886713564395905,
|
| 24921 |
+
"learning_rate": 4.6543861599197246e-05,
|
| 24922 |
+
"loss": 0.8094,
|
| 24923 |
+
"step": 3559
|
| 24924 |
+
},
|
| 24925 |
+
{
|
| 24926 |
+
"epoch": 4.0547008547008545,
|
| 24927 |
+
"grad_norm": 0.1390674114227295,
|
| 24928 |
+
"learning_rate": 4.654149750330345e-05,
|
| 24929 |
+
"loss": 0.8836,
|
| 24930 |
+
"step": 3560
|
| 24931 |
+
},
|
| 24932 |
+
{
|
| 24933 |
+
"epoch": 4.055840455840456,
|
| 24934 |
+
"grad_norm": 0.14855355024337769,
|
| 24935 |
+
"learning_rate": 4.653913265921419e-05,
|
| 24936 |
+
"loss": 0.9287,
|
| 24937 |
+
"step": 3561
|
| 24938 |
+
},
|
| 24939 |
+
{
|
| 24940 |
+
"epoch": 4.056980056980057,
|
| 24941 |
+
"grad_norm": 0.14535707235336304,
|
| 24942 |
+
"learning_rate": 4.653676706701163e-05,
|
| 24943 |
+
"loss": 0.8883,
|
| 24944 |
+
"step": 3562
|
| 24945 |
+
},
|
| 24946 |
+
{
|
| 24947 |
+
"epoch": 4.058119658119658,
|
| 24948 |
+
"grad_norm": 0.13472265005111694,
|
| 24949 |
+
"learning_rate": 4.653440072677792e-05,
|
| 24950 |
+
"loss": 0.9482,
|
| 24951 |
+
"step": 3563
|
| 24952 |
+
},
|
| 24953 |
+
{
|
| 24954 |
+
"epoch": 4.059259259259259,
|
| 24955 |
+
"grad_norm": 0.15425075590610504,
|
| 24956 |
+
"learning_rate": 4.6532033638595254e-05,
|
| 24957 |
+
"loss": 0.8602,
|
| 24958 |
+
"step": 3564
|
| 24959 |
+
},
|
| 24960 |
+
{
|
| 24961 |
+
"epoch": 4.060398860398861,
|
| 24962 |
+
"grad_norm": 0.19460026919841766,
|
| 24963 |
+
"learning_rate": 4.652966580254584e-05,
|
| 24964 |
+
"loss": 0.7565,
|
| 24965 |
+
"step": 3565
|
| 24966 |
+
},
|
| 24967 |
+
{
|
| 24968 |
+
"epoch": 4.061538461538461,
|
| 24969 |
+
"grad_norm": 0.14792226254940033,
|
| 24970 |
+
"learning_rate": 4.6527297218711926e-05,
|
| 24971 |
+
"loss": 0.8495,
|
| 24972 |
+
"step": 3566
|
| 24973 |
+
},
|
| 24974 |
+
{
|
| 24975 |
+
"epoch": 4.062678062678063,
|
| 24976 |
+
"grad_norm": 0.16837316751480103,
|
| 24977 |
+
"learning_rate": 4.652492788717579e-05,
|
| 24978 |
+
"loss": 0.8988,
|
| 24979 |
+
"step": 3567
|
| 24980 |
+
},
|
| 24981 |
+
{
|
| 24982 |
+
"epoch": 4.063817663817664,
|
| 24983 |
+
"grad_norm": 0.15385596454143524,
|
| 24984 |
+
"learning_rate": 4.6522557808019704e-05,
|
| 24985 |
+
"loss": 0.866,
|
| 24986 |
+
"step": 3568
|
| 24987 |
+
},
|
| 24988 |
+
{
|
| 24989 |
+
"epoch": 4.064957264957265,
|
| 24990 |
+
"grad_norm": 0.17028549313545227,
|
| 24991 |
+
"learning_rate": 4.652018698132601e-05,
|
| 24992 |
+
"loss": 0.8137,
|
| 24993 |
+
"step": 3569
|
| 24994 |
+
},
|
| 24995 |
+
{
|
| 24996 |
+
"epoch": 4.066096866096866,
|
| 24997 |
+
"grad_norm": 0.14771980047225952,
|
| 24998 |
+
"learning_rate": 4.651781540717704e-05,
|
| 24999 |
+
"loss": 0.867,
|
| 25000 |
+
"step": 3570
|
| 25001 |
+
},
|
| 25002 |
+
{
|
| 25003 |
+
"epoch": 4.067236467236468,
|
| 25004 |
+
"grad_norm": 0.15428456664085388,
|
| 25005 |
+
"learning_rate": 4.651544308565515e-05,
|
| 25006 |
+
"loss": 0.784,
|
| 25007 |
+
"step": 3571
|
| 25008 |
+
},
|
| 25009 |
+
{
|
| 25010 |
+
"epoch": 4.068376068376068,
|
| 25011 |
+
"grad_norm": 0.13995905220508575,
|
| 25012 |
+
"learning_rate": 4.651307001684276e-05,
|
| 25013 |
+
"loss": 0.9278,
|
| 25014 |
+
"step": 3572
|
| 25015 |
+
},
|
| 25016 |
+
{
|
| 25017 |
+
"epoch": 4.06951566951567,
|
| 25018 |
+
"grad_norm": 0.1955014020204544,
|
| 25019 |
+
"learning_rate": 4.65106962008223e-05,
|
| 25020 |
+
"loss": 0.5831,
|
| 25021 |
+
"step": 3573
|
| 25022 |
+
},
|
| 25023 |
+
{
|
| 25024 |
+
"epoch": 4.070655270655271,
|
| 25025 |
+
"grad_norm": 0.17508552968502045,
|
| 25026 |
+
"learning_rate": 4.65083216376762e-05,
|
| 25027 |
+
"loss": 0.7284,
|
| 25028 |
+
"step": 3574
|
| 25029 |
+
},
|
| 25030 |
+
{
|
| 25031 |
+
"epoch": 4.0717948717948715,
|
| 25032 |
+
"grad_norm": 0.16214320063591003,
|
| 25033 |
+
"learning_rate": 4.6505946327486936e-05,
|
| 25034 |
+
"loss": 0.8925,
|
| 25035 |
+
"step": 3575
|
| 25036 |
+
},
|
| 25037 |
+
{
|
| 25038 |
+
"epoch": 4.072934472934473,
|
| 25039 |
+
"grad_norm": 0.1865091770887375,
|
| 25040 |
+
"learning_rate": 4.650357027033702e-05,
|
| 25041 |
+
"loss": 0.7345,
|
| 25042 |
+
"step": 3576
|
| 25043 |
+
},
|
| 25044 |
+
{
|
| 25045 |
+
"epoch": 4.074074074074074,
|
| 25046 |
+
"grad_norm": 0.19175677001476288,
|
| 25047 |
+
"learning_rate": 4.650119346630897e-05,
|
| 25048 |
+
"loss": 0.7089,
|
| 25049 |
+
"step": 3577
|
| 25050 |
+
},
|
| 25051 |
+
{
|
| 25052 |
+
"epoch": 4.075213675213675,
|
| 25053 |
+
"grad_norm": 0.1551404446363449,
|
| 25054 |
+
"learning_rate": 4.649881591548535e-05,
|
| 25055 |
+
"loss": 0.8324,
|
| 25056 |
+
"step": 3578
|
| 25057 |
+
},
|
| 25058 |
+
{
|
| 25059 |
+
"epoch": 4.076353276353276,
|
| 25060 |
+
"grad_norm": 0.14528369903564453,
|
| 25061 |
+
"learning_rate": 4.6496437617948725e-05,
|
| 25062 |
+
"loss": 0.8641,
|
| 25063 |
+
"step": 3579
|
| 25064 |
+
},
|
| 25065 |
+
{
|
| 25066 |
+
"epoch": 4.077492877492878,
|
| 25067 |
+
"grad_norm": 0.15619570016860962,
|
| 25068 |
+
"learning_rate": 4.649405857378171e-05,
|
| 25069 |
+
"loss": 0.7039,
|
| 25070 |
+
"step": 3580
|
| 25071 |
+
},
|
| 25072 |
+
{
|
| 25073 |
+
"epoch": 4.078632478632478,
|
| 25074 |
+
"grad_norm": 0.17114530503749847,
|
| 25075 |
+
"learning_rate": 4.6491678783066924e-05,
|
| 25076 |
+
"loss": 0.7716,
|
| 25077 |
+
"step": 3581
|
| 25078 |
+
},
|
| 25079 |
+
{
|
| 25080 |
+
"epoch": 4.07977207977208,
|
| 25081 |
+
"grad_norm": 0.15298311412334442,
|
| 25082 |
+
"learning_rate": 4.6489298245887034e-05,
|
| 25083 |
+
"loss": 0.7569,
|
| 25084 |
+
"step": 3582
|
| 25085 |
+
},
|
| 25086 |
+
{
|
| 25087 |
+
"epoch": 4.080911680911681,
|
| 25088 |
+
"grad_norm": 0.2157907336950302,
|
| 25089 |
+
"learning_rate": 4.6486916962324724e-05,
|
| 25090 |
+
"loss": 0.5514,
|
| 25091 |
+
"step": 3583
|
| 25092 |
+
},
|
| 25093 |
+
{
|
| 25094 |
+
"epoch": 4.082051282051282,
|
| 25095 |
+
"grad_norm": 0.1464688926935196,
|
| 25096 |
+
"learning_rate": 4.6484534932462696e-05,
|
| 25097 |
+
"loss": 0.9838,
|
| 25098 |
+
"step": 3584
|
| 25099 |
+
},
|
| 25100 |
+
{
|
| 25101 |
+
"epoch": 4.083190883190883,
|
| 25102 |
+
"grad_norm": 0.16757918894290924,
|
| 25103 |
+
"learning_rate": 4.6482152156383684e-05,
|
| 25104 |
+
"loss": 0.7074,
|
| 25105 |
+
"step": 3585
|
| 25106 |
+
},
|
| 25107 |
+
{
|
| 25108 |
+
"epoch": 4.084330484330485,
|
| 25109 |
+
"grad_norm": 0.1393502950668335,
|
| 25110 |
+
"learning_rate": 4.647976863417046e-05,
|
| 25111 |
+
"loss": 0.9847,
|
| 25112 |
+
"step": 3586
|
| 25113 |
+
},
|
| 25114 |
+
{
|
| 25115 |
+
"epoch": 4.085470085470085,
|
| 25116 |
+
"grad_norm": 0.16414041817188263,
|
| 25117 |
+
"learning_rate": 4.64773843659058e-05,
|
| 25118 |
+
"loss": 0.8177,
|
| 25119 |
+
"step": 3587
|
| 25120 |
+
},
|
| 25121 |
+
{
|
| 25122 |
+
"epoch": 4.086609686609687,
|
| 25123 |
+
"grad_norm": 0.1699393391609192,
|
| 25124 |
+
"learning_rate": 4.647499935167251e-05,
|
| 25125 |
+
"loss": 0.9266,
|
| 25126 |
+
"step": 3588
|
| 25127 |
+
},
|
| 25128 |
+
{
|
| 25129 |
+
"epoch": 4.087749287749288,
|
| 25130 |
+
"grad_norm": 0.1846645325422287,
|
| 25131 |
+
"learning_rate": 4.647261359155344e-05,
|
| 25132 |
+
"loss": 0.8353,
|
| 25133 |
+
"step": 3589
|
| 25134 |
+
},
|
| 25135 |
+
{
|
| 25136 |
+
"epoch": 4.088888888888889,
|
| 25137 |
+
"grad_norm": 0.16945374011993408,
|
| 25138 |
+
"learning_rate": 4.6470227085631455e-05,
|
| 25139 |
+
"loss": 0.8741,
|
| 25140 |
+
"step": 3590
|
| 25141 |
+
},
|
| 25142 |
+
{
|
| 25143 |
+
"epoch": 4.09002849002849,
|
| 25144 |
+
"grad_norm": 0.11592093110084534,
|
| 25145 |
+
"learning_rate": 4.6467839833989435e-05,
|
| 25146 |
+
"loss": 0.8984,
|
| 25147 |
+
"step": 3591
|
| 25148 |
+
},
|
| 25149 |
+
{
|
| 25150 |
+
"epoch": 4.091168091168091,
|
| 25151 |
+
"grad_norm": 0.19027556478977203,
|
| 25152 |
+
"learning_rate": 4.64654518367103e-05,
|
| 25153 |
+
"loss": 0.8381,
|
| 25154 |
+
"step": 3592
|
| 25155 |
+
},
|
| 25156 |
+
{
|
| 25157 |
+
"epoch": 4.092307692307692,
|
| 25158 |
+
"grad_norm": 0.17370308935642242,
|
| 25159 |
+
"learning_rate": 4.646306309387699e-05,
|
| 25160 |
+
"loss": 0.7826,
|
| 25161 |
+
"step": 3593
|
| 25162 |
+
},
|
| 25163 |
+
{
|
| 25164 |
+
"epoch": 4.093447293447293,
|
| 25165 |
+
"grad_norm": 0.17760266363620758,
|
| 25166 |
+
"learning_rate": 4.6460673605572484e-05,
|
| 25167 |
+
"loss": 0.7861,
|
| 25168 |
+
"step": 3594
|
| 25169 |
+
},
|
| 25170 |
+
{
|
| 25171 |
+
"epoch": 4.094586894586895,
|
| 25172 |
+
"grad_norm": 0.18767882883548737,
|
| 25173 |
+
"learning_rate": 4.645828337187976e-05,
|
| 25174 |
+
"loss": 0.6726,
|
| 25175 |
+
"step": 3595
|
| 25176 |
+
},
|
| 25177 |
+
{
|
| 25178 |
+
"epoch": 4.095726495726495,
|
| 25179 |
+
"grad_norm": 0.19562728703022003,
|
| 25180 |
+
"learning_rate": 4.645589239288185e-05,
|
| 25181 |
+
"loss": 0.7954,
|
| 25182 |
+
"step": 3596
|
| 25183 |
+
},
|
| 25184 |
+
{
|
| 25185 |
+
"epoch": 4.096866096866097,
|
| 25186 |
+
"grad_norm": 0.16158398985862732,
|
| 25187 |
+
"learning_rate": 4.6453500668661786e-05,
|
| 25188 |
+
"loss": 0.7515,
|
| 25189 |
+
"step": 3597
|
| 25190 |
+
},
|
| 25191 |
+
{
|
| 25192 |
+
"epoch": 4.098005698005698,
|
| 25193 |
+
"grad_norm": 0.17128139734268188,
|
| 25194 |
+
"learning_rate": 4.645110819930265e-05,
|
| 25195 |
+
"loss": 0.6846,
|
| 25196 |
+
"step": 3598
|
| 25197 |
+
},
|
| 25198 |
+
{
|
| 25199 |
+
"epoch": 4.099145299145299,
|
| 25200 |
+
"grad_norm": 0.1473407745361328,
|
| 25201 |
+
"learning_rate": 4.644871498488753e-05,
|
| 25202 |
+
"loss": 0.6415,
|
| 25203 |
+
"step": 3599
|
| 25204 |
+
},
|
| 25205 |
+
{
|
| 25206 |
+
"epoch": 4.1002849002849,
|
| 25207 |
+
"grad_norm": 0.14364983141422272,
|
| 25208 |
+
"learning_rate": 4.644632102549956e-05,
|
| 25209 |
+
"loss": 0.8383,
|
| 25210 |
+
"step": 3600
|
| 25211 |
}
|
| 25212 |
],
|
| 25213 |
"logging_steps": 1,
|
|
|
|
| 25227 |
"attributes": {}
|
| 25228 |
}
|
| 25229 |
},
|
| 25230 |
+
"total_flos": 2.0128471156601487e+19,
|
| 25231 |
"train_batch_size": 8,
|
| 25232 |
"trial_name": null,
|
| 25233 |
"trial_params": null
|