Instructions to use shareit/chatbot-supervisor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shareit/chatbot-supervisor with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shareit/chatbot-supervisor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Training in progress, step 12300, 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 sha256:356e3fe02e14a05457eeb39e647559c6e51247b42a3e95ab97997c731bd84fc1
|
| 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 sha256:784e29779e23e64a830cfe8cf1dd6a03cd83dead5bc0a1bead0e153d467ec011
|
| 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 sha256:4801416a03beb0f63c300670679d3fb6cca48da8259362e9be9e6ffae0c5ffd0
|
| 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 sha256:03fafc6da7da4b83fb0c55f0954dc238ba908ca129fb64820fba0eec14845dec
|
| 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,
|
|
@@ -84008,6 +84008,2106 @@
|
|
| 84008 |
"learning_rate": 1.226670659146217e-05,
|
| 84009 |
"loss": 0.5978,
|
| 84010 |
"step": 12000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84011 |
}
|
| 84012 |
],
|
| 84013 |
"logging_steps": 1,
|
|
@@ -84027,7 +86127,7 @@
|
|
| 84027 |
"attributes": {}
|
| 84028 |
}
|
| 84029 |
},
|
| 84030 |
-
"total_flos": 6.
|
| 84031 |
"train_batch_size": 8,
|
| 84032 |
"trial_name": null,
|
| 84033 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.00911680911681,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 12300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 84008 |
"learning_rate": 1.226670659146217e-05,
|
| 84009 |
"loss": 0.5978,
|
| 84010 |
"step": 12000
|
| 84011 |
+
},
|
| 84012 |
+
{
|
| 84013 |
+
"epoch": 13.668945868945869,
|
| 84014 |
+
"grad_norm": 0.21521274745464325,
|
| 84015 |
+
"learning_rate": 1.2262697259871538e-05,
|
| 84016 |
+
"loss": 0.6199,
|
| 84017 |
+
"step": 12001
|
| 84018 |
+
},
|
| 84019 |
+
{
|
| 84020 |
+
"epoch": 13.67008547008547,
|
| 84021 |
+
"grad_norm": 0.1693134307861328,
|
| 84022 |
+
"learning_rate": 1.2258688370682459e-05,
|
| 84023 |
+
"loss": 0.6558,
|
| 84024 |
+
"step": 12002
|
| 84025 |
+
},
|
| 84026 |
+
{
|
| 84027 |
+
"epoch": 13.671225071225072,
|
| 84028 |
+
"grad_norm": 0.21319220960140228,
|
| 84029 |
+
"learning_rate": 1.2254679924034169e-05,
|
| 84030 |
+
"loss": 0.6246,
|
| 84031 |
+
"step": 12003
|
| 84032 |
+
},
|
| 84033 |
+
{
|
| 84034 |
+
"epoch": 13.672364672364672,
|
| 84035 |
+
"grad_norm": 0.23365657031536102,
|
| 84036 |
+
"learning_rate": 1.2250671920065903e-05,
|
| 84037 |
+
"loss": 0.5943,
|
| 84038 |
+
"step": 12004
|
| 84039 |
+
},
|
| 84040 |
+
{
|
| 84041 |
+
"epoch": 13.673504273504273,
|
| 84042 |
+
"grad_norm": 0.2138364464044571,
|
| 84043 |
+
"learning_rate": 1.2246664358916856e-05,
|
| 84044 |
+
"loss": 0.6211,
|
| 84045 |
+
"step": 12005
|
| 84046 |
+
},
|
| 84047 |
+
{
|
| 84048 |
+
"epoch": 13.674643874643875,
|
| 84049 |
+
"grad_norm": 0.1780523955821991,
|
| 84050 |
+
"learning_rate": 1.2242657240726226e-05,
|
| 84051 |
+
"loss": 0.7917,
|
| 84052 |
+
"step": 12006
|
| 84053 |
+
},
|
| 84054 |
+
{
|
| 84055 |
+
"epoch": 13.675783475783476,
|
| 84056 |
+
"grad_norm": 0.2242337018251419,
|
| 84057 |
+
"learning_rate": 1.2238650565633195e-05,
|
| 84058 |
+
"loss": 0.6403,
|
| 84059 |
+
"step": 12007
|
| 84060 |
+
},
|
| 84061 |
+
{
|
| 84062 |
+
"epoch": 13.676923076923076,
|
| 84063 |
+
"grad_norm": 0.2050691395998001,
|
| 84064 |
+
"learning_rate": 1.2234644333776931e-05,
|
| 84065 |
+
"loss": 0.5379,
|
| 84066 |
+
"step": 12008
|
| 84067 |
+
},
|
| 84068 |
+
{
|
| 84069 |
+
"epoch": 13.678062678062679,
|
| 84070 |
+
"grad_norm": 0.20676282048225403,
|
| 84071 |
+
"learning_rate": 1.2230638545296566e-05,
|
| 84072 |
+
"loss": 0.8157,
|
| 84073 |
+
"step": 12009
|
| 84074 |
+
},
|
| 84075 |
+
{
|
| 84076 |
+
"epoch": 13.67920227920228,
|
| 84077 |
+
"grad_norm": 0.23082448542118073,
|
| 84078 |
+
"learning_rate": 1.2226633200331238e-05,
|
| 84079 |
+
"loss": 0.707,
|
| 84080 |
+
"step": 12010
|
| 84081 |
+
},
|
| 84082 |
+
{
|
| 84083 |
+
"epoch": 13.68034188034188,
|
| 84084 |
+
"grad_norm": 0.20839092135429382,
|
| 84085 |
+
"learning_rate": 1.222262829902006e-05,
|
| 84086 |
+
"loss": 0.6023,
|
| 84087 |
+
"step": 12011
|
| 84088 |
+
},
|
| 84089 |
+
{
|
| 84090 |
+
"epoch": 13.681481481481482,
|
| 84091 |
+
"grad_norm": 0.1955326348543167,
|
| 84092 |
+
"learning_rate": 1.2218623841502156e-05,
|
| 84093 |
+
"loss": 0.7687,
|
| 84094 |
+
"step": 12012
|
| 84095 |
+
},
|
| 84096 |
+
{
|
| 84097 |
+
"epoch": 13.682621082621083,
|
| 84098 |
+
"grad_norm": 0.22524051368236542,
|
| 84099 |
+
"learning_rate": 1.2214619827916584e-05,
|
| 84100 |
+
"loss": 0.5829,
|
| 84101 |
+
"step": 12013
|
| 84102 |
+
},
|
| 84103 |
+
{
|
| 84104 |
+
"epoch": 13.683760683760683,
|
| 84105 |
+
"grad_norm": 0.1810995638370514,
|
| 84106 |
+
"learning_rate": 1.2210616258402427e-05,
|
| 84107 |
+
"loss": 0.7893,
|
| 84108 |
+
"step": 12014
|
| 84109 |
+
},
|
| 84110 |
+
{
|
| 84111 |
+
"epoch": 13.684900284900285,
|
| 84112 |
+
"grad_norm": 0.18191368877887726,
|
| 84113 |
+
"learning_rate": 1.2206613133098737e-05,
|
| 84114 |
+
"loss": 0.7852,
|
| 84115 |
+
"step": 12015
|
| 84116 |
+
},
|
| 84117 |
+
{
|
| 84118 |
+
"epoch": 13.686039886039886,
|
| 84119 |
+
"grad_norm": 0.2552942931652069,
|
| 84120 |
+
"learning_rate": 1.2202610452144564e-05,
|
| 84121 |
+
"loss": 0.6092,
|
| 84122 |
+
"step": 12016
|
| 84123 |
+
},
|
| 84124 |
+
{
|
| 84125 |
+
"epoch": 13.687179487179487,
|
| 84126 |
+
"grad_norm": 0.2494039535522461,
|
| 84127 |
+
"learning_rate": 1.2198608215678917e-05,
|
| 84128 |
+
"loss": 0.5332,
|
| 84129 |
+
"step": 12017
|
| 84130 |
+
},
|
| 84131 |
+
{
|
| 84132 |
+
"epoch": 13.688319088319089,
|
| 84133 |
+
"grad_norm": 0.1996004283428192,
|
| 84134 |
+
"learning_rate": 1.2194606423840807e-05,
|
| 84135 |
+
"loss": 0.6962,
|
| 84136 |
+
"step": 12018
|
| 84137 |
+
},
|
| 84138 |
+
{
|
| 84139 |
+
"epoch": 13.68945868945869,
|
| 84140 |
+
"grad_norm": 0.197572261095047,
|
| 84141 |
+
"learning_rate": 1.2190605076769232e-05,
|
| 84142 |
+
"loss": 0.7313,
|
| 84143 |
+
"step": 12019
|
| 84144 |
+
},
|
| 84145 |
+
{
|
| 84146 |
+
"epoch": 13.69059829059829,
|
| 84147 |
+
"grad_norm": 0.2840818762779236,
|
| 84148 |
+
"learning_rate": 1.2186604174603178e-05,
|
| 84149 |
+
"loss": 0.4424,
|
| 84150 |
+
"step": 12020
|
| 84151 |
+
},
|
| 84152 |
+
{
|
| 84153 |
+
"epoch": 13.691737891737892,
|
| 84154 |
+
"grad_norm": 0.22129279375076294,
|
| 84155 |
+
"learning_rate": 1.2182603717481588e-05,
|
| 84156 |
+
"loss": 0.7447,
|
| 84157 |
+
"step": 12021
|
| 84158 |
+
},
|
| 84159 |
+
{
|
| 84160 |
+
"epoch": 13.692877492877493,
|
| 84161 |
+
"grad_norm": 0.18007630109786987,
|
| 84162 |
+
"learning_rate": 1.2178603705543412e-05,
|
| 84163 |
+
"loss": 0.8695,
|
| 84164 |
+
"step": 12022
|
| 84165 |
+
},
|
| 84166 |
+
{
|
| 84167 |
+
"epoch": 13.694017094017093,
|
| 84168 |
+
"grad_norm": 0.19652818143367767,
|
| 84169 |
+
"learning_rate": 1.2174604138927603e-05,
|
| 84170 |
+
"loss": 0.6182,
|
| 84171 |
+
"step": 12023
|
| 84172 |
+
},
|
| 84173 |
+
{
|
| 84174 |
+
"epoch": 13.695156695156696,
|
| 84175 |
+
"grad_norm": 0.23077695071697235,
|
| 84176 |
+
"learning_rate": 1.2170605017773057e-05,
|
| 84177 |
+
"loss": 0.5186,
|
| 84178 |
+
"step": 12024
|
| 84179 |
+
},
|
| 84180 |
+
{
|
| 84181 |
+
"epoch": 13.696296296296296,
|
| 84182 |
+
"grad_norm": 0.16277217864990234,
|
| 84183 |
+
"learning_rate": 1.2166606342218678e-05,
|
| 84184 |
+
"loss": 0.7847,
|
| 84185 |
+
"step": 12025
|
| 84186 |
+
},
|
| 84187 |
+
{
|
| 84188 |
+
"epoch": 13.697435897435897,
|
| 84189 |
+
"grad_norm": 0.20688322186470032,
|
| 84190 |
+
"learning_rate": 1.216260811240335e-05,
|
| 84191 |
+
"loss": 0.6436,
|
| 84192 |
+
"step": 12026
|
| 84193 |
+
},
|
| 84194 |
+
{
|
| 84195 |
+
"epoch": 13.698575498575499,
|
| 84196 |
+
"grad_norm": 0.19791574776172638,
|
| 84197 |
+
"learning_rate": 1.2158610328465958e-05,
|
| 84198 |
+
"loss": 0.7555,
|
| 84199 |
+
"step": 12027
|
| 84200 |
+
},
|
| 84201 |
+
{
|
| 84202 |
+
"epoch": 13.6997150997151,
|
| 84203 |
+
"grad_norm": 0.21570193767547607,
|
| 84204 |
+
"learning_rate": 1.2154612990545333e-05,
|
| 84205 |
+
"loss": 0.534,
|
| 84206 |
+
"step": 12028
|
| 84207 |
+
},
|
| 84208 |
+
{
|
| 84209 |
+
"epoch": 13.7008547008547,
|
| 84210 |
+
"grad_norm": 0.17073188722133636,
|
| 84211 |
+
"learning_rate": 1.2150616098780326e-05,
|
| 84212 |
+
"loss": 0.8929,
|
| 84213 |
+
"step": 12029
|
| 84214 |
+
},
|
| 84215 |
+
{
|
| 84216 |
+
"epoch": 13.701994301994302,
|
| 84217 |
+
"grad_norm": 0.17871499061584473,
|
| 84218 |
+
"learning_rate": 1.2146619653309755e-05,
|
| 84219 |
+
"loss": 0.5669,
|
| 84220 |
+
"step": 12030
|
| 84221 |
+
},
|
| 84222 |
+
{
|
| 84223 |
+
"epoch": 13.703133903133903,
|
| 84224 |
+
"grad_norm": 0.19358180463314056,
|
| 84225 |
+
"learning_rate": 1.2142623654272439e-05,
|
| 84226 |
+
"loss": 0.4399,
|
| 84227 |
+
"step": 12031
|
| 84228 |
+
},
|
| 84229 |
+
{
|
| 84230 |
+
"epoch": 13.704273504273504,
|
| 84231 |
+
"grad_norm": 0.19818490743637085,
|
| 84232 |
+
"learning_rate": 1.2138628101807154e-05,
|
| 84233 |
+
"loss": 0.6763,
|
| 84234 |
+
"step": 12032
|
| 84235 |
+
},
|
| 84236 |
+
{
|
| 84237 |
+
"epoch": 13.705413105413106,
|
| 84238 |
+
"grad_norm": 0.2800033688545227,
|
| 84239 |
+
"learning_rate": 1.2134632996052675e-05,
|
| 84240 |
+
"loss": 0.4403,
|
| 84241 |
+
"step": 12033
|
| 84242 |
+
},
|
| 84243 |
+
{
|
| 84244 |
+
"epoch": 13.706552706552706,
|
| 84245 |
+
"grad_norm": 0.2268080711364746,
|
| 84246 |
+
"learning_rate": 1.213063833714779e-05,
|
| 84247 |
+
"loss": 0.6589,
|
| 84248 |
+
"step": 12034
|
| 84249 |
+
},
|
| 84250 |
+
{
|
| 84251 |
+
"epoch": 13.707692307692307,
|
| 84252 |
+
"grad_norm": 0.22550585865974426,
|
| 84253 |
+
"learning_rate": 1.2126644125231215e-05,
|
| 84254 |
+
"loss": 0.6582,
|
| 84255 |
+
"step": 12035
|
| 84256 |
+
},
|
| 84257 |
+
{
|
| 84258 |
+
"epoch": 13.70883190883191,
|
| 84259 |
+
"grad_norm": 0.22792108356952667,
|
| 84260 |
+
"learning_rate": 1.2122650360441696e-05,
|
| 84261 |
+
"loss": 0.6455,
|
| 84262 |
+
"step": 12036
|
| 84263 |
+
},
|
| 84264 |
+
{
|
| 84265 |
+
"epoch": 13.70997150997151,
|
| 84266 |
+
"grad_norm": 0.15592224895954132,
|
| 84267 |
+
"learning_rate": 1.2118657042917938e-05,
|
| 84268 |
+
"loss": 0.7888,
|
| 84269 |
+
"step": 12037
|
| 84270 |
+
},
|
| 84271 |
+
{
|
| 84272 |
+
"epoch": 13.71111111111111,
|
| 84273 |
+
"grad_norm": 0.18949413299560547,
|
| 84274 |
+
"learning_rate": 1.2114664172798656e-05,
|
| 84275 |
+
"loss": 0.6035,
|
| 84276 |
+
"step": 12038
|
| 84277 |
+
},
|
| 84278 |
+
{
|
| 84279 |
+
"epoch": 13.712250712250713,
|
| 84280 |
+
"grad_norm": 0.23782742023468018,
|
| 84281 |
+
"learning_rate": 1.2110671750222512e-05,
|
| 84282 |
+
"loss": 0.5429,
|
| 84283 |
+
"step": 12039
|
| 84284 |
+
},
|
| 84285 |
+
{
|
| 84286 |
+
"epoch": 13.713390313390313,
|
| 84287 |
+
"grad_norm": 0.19856585562229156,
|
| 84288 |
+
"learning_rate": 1.2106679775328186e-05,
|
| 84289 |
+
"loss": 0.7701,
|
| 84290 |
+
"step": 12040
|
| 84291 |
+
},
|
| 84292 |
+
{
|
| 84293 |
+
"epoch": 13.714529914529914,
|
| 84294 |
+
"grad_norm": 0.22010724246501923,
|
| 84295 |
+
"learning_rate": 1.2102688248254326e-05,
|
| 84296 |
+
"loss": 0.6433,
|
| 84297 |
+
"step": 12041
|
| 84298 |
+
},
|
| 84299 |
+
{
|
| 84300 |
+
"epoch": 13.715669515669516,
|
| 84301 |
+
"grad_norm": 0.2371382713317871,
|
| 84302 |
+
"learning_rate": 1.2098697169139581e-05,
|
| 84303 |
+
"loss": 0.5825,
|
| 84304 |
+
"step": 12042
|
| 84305 |
+
},
|
| 84306 |
+
{
|
| 84307 |
+
"epoch": 13.716809116809117,
|
| 84308 |
+
"grad_norm": 0.2550557255744934,
|
| 84309 |
+
"learning_rate": 1.2094706538122551e-05,
|
| 84310 |
+
"loss": 0.4836,
|
| 84311 |
+
"step": 12043
|
| 84312 |
+
},
|
| 84313 |
+
{
|
| 84314 |
+
"epoch": 13.717948717948717,
|
| 84315 |
+
"grad_norm": 0.29449477791786194,
|
| 84316 |
+
"learning_rate": 1.2090716355341848e-05,
|
| 84317 |
+
"loss": 0.6653,
|
| 84318 |
+
"step": 12044
|
| 84319 |
+
},
|
| 84320 |
+
{
|
| 84321 |
+
"epoch": 13.71908831908832,
|
| 84322 |
+
"grad_norm": 0.1919989287853241,
|
| 84323 |
+
"learning_rate": 1.2086726620936072e-05,
|
| 84324 |
+
"loss": 0.6437,
|
| 84325 |
+
"step": 12045
|
| 84326 |
+
},
|
| 84327 |
+
{
|
| 84328 |
+
"epoch": 13.72022792022792,
|
| 84329 |
+
"grad_norm": 0.20676428079605103,
|
| 84330 |
+
"learning_rate": 1.2082737335043803e-05,
|
| 84331 |
+
"loss": 0.7867,
|
| 84332 |
+
"step": 12046
|
| 84333 |
+
},
|
| 84334 |
+
{
|
| 84335 |
+
"epoch": 13.72136752136752,
|
| 84336 |
+
"grad_norm": 0.2550913095474243,
|
| 84337 |
+
"learning_rate": 1.207874849780358e-05,
|
| 84338 |
+
"loss": 0.7347,
|
| 84339 |
+
"step": 12047
|
| 84340 |
+
},
|
| 84341 |
+
{
|
| 84342 |
+
"epoch": 13.722507122507123,
|
| 84343 |
+
"grad_norm": 0.2725510895252228,
|
| 84344 |
+
"learning_rate": 1.2074760109353953e-05,
|
| 84345 |
+
"loss": 0.5768,
|
| 84346 |
+
"step": 12048
|
| 84347 |
+
},
|
| 84348 |
+
{
|
| 84349 |
+
"epoch": 13.723646723646723,
|
| 84350 |
+
"grad_norm": 0.242890864610672,
|
| 84351 |
+
"learning_rate": 1.2070772169833453e-05,
|
| 84352 |
+
"loss": 0.6288,
|
| 84353 |
+
"step": 12049
|
| 84354 |
+
},
|
| 84355 |
+
{
|
| 84356 |
+
"epoch": 13.724786324786324,
|
| 84357 |
+
"grad_norm": 0.21027885377407074,
|
| 84358 |
+
"learning_rate": 1.2066784679380603e-05,
|
| 84359 |
+
"loss": 0.6246,
|
| 84360 |
+
"step": 12050
|
| 84361 |
+
},
|
| 84362 |
+
{
|
| 84363 |
+
"epoch": 13.725925925925926,
|
| 84364 |
+
"grad_norm": 0.2023586928844452,
|
| 84365 |
+
"learning_rate": 1.2062797638133874e-05,
|
| 84366 |
+
"loss": 0.7381,
|
| 84367 |
+
"step": 12051
|
| 84368 |
+
},
|
| 84369 |
+
{
|
| 84370 |
+
"epoch": 13.727065527065527,
|
| 84371 |
+
"grad_norm": 0.18032431602478027,
|
| 84372 |
+
"learning_rate": 1.2058811046231764e-05,
|
| 84373 |
+
"loss": 0.6457,
|
| 84374 |
+
"step": 12052
|
| 84375 |
+
},
|
| 84376 |
+
{
|
| 84377 |
+
"epoch": 13.728205128205127,
|
| 84378 |
+
"grad_norm": 0.2373048961162567,
|
| 84379 |
+
"learning_rate": 1.2054824903812731e-05,
|
| 84380 |
+
"loss": 0.56,
|
| 84381 |
+
"step": 12053
|
| 84382 |
+
},
|
| 84383 |
+
{
|
| 84384 |
+
"epoch": 13.72934472934473,
|
| 84385 |
+
"grad_norm": 0.32662925124168396,
|
| 84386 |
+
"learning_rate": 1.2050839211015241e-05,
|
| 84387 |
+
"loss": 0.4491,
|
| 84388 |
+
"step": 12054
|
| 84389 |
+
},
|
| 84390 |
+
{
|
| 84391 |
+
"epoch": 13.73048433048433,
|
| 84392 |
+
"grad_norm": 0.21573962271213531,
|
| 84393 |
+
"learning_rate": 1.2046853967977695e-05,
|
| 84394 |
+
"loss": 0.7075,
|
| 84395 |
+
"step": 12055
|
| 84396 |
+
},
|
| 84397 |
+
{
|
| 84398 |
+
"epoch": 13.73162393162393,
|
| 84399 |
+
"grad_norm": 0.18163876235485077,
|
| 84400 |
+
"learning_rate": 1.2042869174838542e-05,
|
| 84401 |
+
"loss": 0.7223,
|
| 84402 |
+
"step": 12056
|
| 84403 |
+
},
|
| 84404 |
+
{
|
| 84405 |
+
"epoch": 13.732763532763533,
|
| 84406 |
+
"grad_norm": 0.20618174970149994,
|
| 84407 |
+
"learning_rate": 1.2038884831736187e-05,
|
| 84408 |
+
"loss": 0.6681,
|
| 84409 |
+
"step": 12057
|
| 84410 |
+
},
|
| 84411 |
+
{
|
| 84412 |
+
"epoch": 13.733903133903134,
|
| 84413 |
+
"grad_norm": 0.24440184235572815,
|
| 84414 |
+
"learning_rate": 1.2034900938808991e-05,
|
| 84415 |
+
"loss": 0.6618,
|
| 84416 |
+
"step": 12058
|
| 84417 |
+
},
|
| 84418 |
+
{
|
| 84419 |
+
"epoch": 13.735042735042736,
|
| 84420 |
+
"grad_norm": 0.1526571363210678,
|
| 84421 |
+
"learning_rate": 1.2030917496195343e-05,
|
| 84422 |
+
"loss": 0.8562,
|
| 84423 |
+
"step": 12059
|
| 84424 |
+
},
|
| 84425 |
+
{
|
| 84426 |
+
"epoch": 13.736182336182337,
|
| 84427 |
+
"grad_norm": 0.21257290244102478,
|
| 84428 |
+
"learning_rate": 1.2026934504033594e-05,
|
| 84429 |
+
"loss": 0.7117,
|
| 84430 |
+
"step": 12060
|
| 84431 |
+
},
|
| 84432 |
+
{
|
| 84433 |
+
"epoch": 13.737321937321937,
|
| 84434 |
+
"grad_norm": 0.22210821509361267,
|
| 84435 |
+
"learning_rate": 1.2022951962462095e-05,
|
| 84436 |
+
"loss": 0.6232,
|
| 84437 |
+
"step": 12061
|
| 84438 |
+
},
|
| 84439 |
+
{
|
| 84440 |
+
"epoch": 13.73846153846154,
|
| 84441 |
+
"grad_norm": 0.2265629917383194,
|
| 84442 |
+
"learning_rate": 1.201896987161915e-05,
|
| 84443 |
+
"loss": 0.764,
|
| 84444 |
+
"step": 12062
|
| 84445 |
+
},
|
| 84446 |
+
{
|
| 84447 |
+
"epoch": 13.73960113960114,
|
| 84448 |
+
"grad_norm": 0.18448157608509064,
|
| 84449 |
+
"learning_rate": 1.2014988231643082e-05,
|
| 84450 |
+
"loss": 0.928,
|
| 84451 |
+
"step": 12063
|
| 84452 |
+
},
|
| 84453 |
+
{
|
| 84454 |
+
"epoch": 13.74074074074074,
|
| 84455 |
+
"grad_norm": 0.19953051209449768,
|
| 84456 |
+
"learning_rate": 1.2011007042672181e-05,
|
| 84457 |
+
"loss": 0.626,
|
| 84458 |
+
"step": 12064
|
| 84459 |
+
},
|
| 84460 |
+
{
|
| 84461 |
+
"epoch": 13.741880341880343,
|
| 84462 |
+
"grad_norm": 0.19707120954990387,
|
| 84463 |
+
"learning_rate": 1.2007026304844735e-05,
|
| 84464 |
+
"loss": 0.8638,
|
| 84465 |
+
"step": 12065
|
| 84466 |
+
},
|
| 84467 |
+
{
|
| 84468 |
+
"epoch": 13.743019943019943,
|
| 84469 |
+
"grad_norm": 0.21861234307289124,
|
| 84470 |
+
"learning_rate": 1.2003046018298977e-05,
|
| 84471 |
+
"loss": 0.6904,
|
| 84472 |
+
"step": 12066
|
| 84473 |
+
},
|
| 84474 |
+
{
|
| 84475 |
+
"epoch": 13.744159544159544,
|
| 84476 |
+
"grad_norm": 0.20723873376846313,
|
| 84477 |
+
"learning_rate": 1.1999066183173183e-05,
|
| 84478 |
+
"loss": 0.9858,
|
| 84479 |
+
"step": 12067
|
| 84480 |
+
},
|
| 84481 |
+
{
|
| 84482 |
+
"epoch": 13.745299145299146,
|
| 84483 |
+
"grad_norm": 0.2597009539604187,
|
| 84484 |
+
"learning_rate": 1.1995086799605582e-05,
|
| 84485 |
+
"loss": 0.3995,
|
| 84486 |
+
"step": 12068
|
| 84487 |
+
},
|
| 84488 |
+
{
|
| 84489 |
+
"epoch": 13.746438746438747,
|
| 84490 |
+
"grad_norm": 0.23442518711090088,
|
| 84491 |
+
"learning_rate": 1.1991107867734368e-05,
|
| 84492 |
+
"loss": 0.781,
|
| 84493 |
+
"step": 12069
|
| 84494 |
+
},
|
| 84495 |
+
{
|
| 84496 |
+
"epoch": 13.747578347578347,
|
| 84497 |
+
"grad_norm": 0.22636261582374573,
|
| 84498 |
+
"learning_rate": 1.1987129387697758e-05,
|
| 84499 |
+
"loss": 0.6951,
|
| 84500 |
+
"step": 12070
|
| 84501 |
+
},
|
| 84502 |
+
{
|
| 84503 |
+
"epoch": 13.74871794871795,
|
| 84504 |
+
"grad_norm": 0.26419615745544434,
|
| 84505 |
+
"learning_rate": 1.1983151359633923e-05,
|
| 84506 |
+
"loss": 0.5102,
|
| 84507 |
+
"step": 12071
|
| 84508 |
+
},
|
| 84509 |
+
{
|
| 84510 |
+
"epoch": 13.74985754985755,
|
| 84511 |
+
"grad_norm": 0.21060913801193237,
|
| 84512 |
+
"learning_rate": 1.1979173783681052e-05,
|
| 84513 |
+
"loss": 0.6206,
|
| 84514 |
+
"step": 12072
|
| 84515 |
+
},
|
| 84516 |
+
{
|
| 84517 |
+
"epoch": 13.75099715099715,
|
| 84518 |
+
"grad_norm": 0.26317015290260315,
|
| 84519 |
+
"learning_rate": 1.1975196659977272e-05,
|
| 84520 |
+
"loss": 0.4829,
|
| 84521 |
+
"step": 12073
|
| 84522 |
+
},
|
| 84523 |
+
{
|
| 84524 |
+
"epoch": 13.752136752136753,
|
| 84525 |
+
"grad_norm": 0.19388261437416077,
|
| 84526 |
+
"learning_rate": 1.197121998866073e-05,
|
| 84527 |
+
"loss": 0.4855,
|
| 84528 |
+
"step": 12074
|
| 84529 |
+
},
|
| 84530 |
+
{
|
| 84531 |
+
"epoch": 13.753276353276354,
|
| 84532 |
+
"grad_norm": 0.1724197119474411,
|
| 84533 |
+
"learning_rate": 1.1967243769869549e-05,
|
| 84534 |
+
"loss": 0.6627,
|
| 84535 |
+
"step": 12075
|
| 84536 |
+
},
|
| 84537 |
+
{
|
| 84538 |
+
"epoch": 13.754415954415954,
|
| 84539 |
+
"grad_norm": 0.19934606552124023,
|
| 84540 |
+
"learning_rate": 1.196326800374184e-05,
|
| 84541 |
+
"loss": 0.8031,
|
| 84542 |
+
"step": 12076
|
| 84543 |
+
},
|
| 84544 |
+
{
|
| 84545 |
+
"epoch": 13.755555555555556,
|
| 84546 |
+
"grad_norm": 0.19647754728794098,
|
| 84547 |
+
"learning_rate": 1.1959292690415667e-05,
|
| 84548 |
+
"loss": 0.7513,
|
| 84549 |
+
"step": 12077
|
| 84550 |
+
},
|
| 84551 |
+
{
|
| 84552 |
+
"epoch": 13.756695156695157,
|
| 84553 |
+
"grad_norm": 0.1899164766073227,
|
| 84554 |
+
"learning_rate": 1.1955317830029127e-05,
|
| 84555 |
+
"loss": 0.8108,
|
| 84556 |
+
"step": 12078
|
| 84557 |
+
},
|
| 84558 |
+
{
|
| 84559 |
+
"epoch": 13.757834757834758,
|
| 84560 |
+
"grad_norm": 0.2037467658519745,
|
| 84561 |
+
"learning_rate": 1.1951343422720284e-05,
|
| 84562 |
+
"loss": 0.7484,
|
| 84563 |
+
"step": 12079
|
| 84564 |
+
},
|
| 84565 |
+
{
|
| 84566 |
+
"epoch": 13.75897435897436,
|
| 84567 |
+
"grad_norm": 0.20733106136322021,
|
| 84568 |
+
"learning_rate": 1.1947369468627158e-05,
|
| 84569 |
+
"loss": 0.6196,
|
| 84570 |
+
"step": 12080
|
| 84571 |
+
},
|
| 84572 |
+
{
|
| 84573 |
+
"epoch": 13.76011396011396,
|
| 84574 |
+
"grad_norm": 0.18393978476524353,
|
| 84575 |
+
"learning_rate": 1.1943395967887786e-05,
|
| 84576 |
+
"loss": 0.7818,
|
| 84577 |
+
"step": 12081
|
| 84578 |
+
},
|
| 84579 |
+
{
|
| 84580 |
+
"epoch": 13.761253561253561,
|
| 84581 |
+
"grad_norm": 0.17892445623874664,
|
| 84582 |
+
"learning_rate": 1.1939422920640174e-05,
|
| 84583 |
+
"loss": 0.9429,
|
| 84584 |
+
"step": 12082
|
| 84585 |
+
},
|
| 84586 |
+
{
|
| 84587 |
+
"epoch": 13.762393162393163,
|
| 84588 |
+
"grad_norm": 0.199140265583992,
|
| 84589 |
+
"learning_rate": 1.1935450327022336e-05,
|
| 84590 |
+
"loss": 0.9958,
|
| 84591 |
+
"step": 12083
|
| 84592 |
+
},
|
| 84593 |
+
{
|
| 84594 |
+
"epoch": 13.763532763532764,
|
| 84595 |
+
"grad_norm": 0.239736407995224,
|
| 84596 |
+
"learning_rate": 1.1931478187172224e-05,
|
| 84597 |
+
"loss": 0.6854,
|
| 84598 |
+
"step": 12084
|
| 84599 |
+
},
|
| 84600 |
+
{
|
| 84601 |
+
"epoch": 13.764672364672364,
|
| 84602 |
+
"grad_norm": 0.20002266764640808,
|
| 84603 |
+
"learning_rate": 1.1927506501227812e-05,
|
| 84604 |
+
"loss": 0.6576,
|
| 84605 |
+
"step": 12085
|
| 84606 |
+
},
|
| 84607 |
+
{
|
| 84608 |
+
"epoch": 13.765811965811967,
|
| 84609 |
+
"grad_norm": 0.21758271753787994,
|
| 84610 |
+
"learning_rate": 1.1923535269327049e-05,
|
| 84611 |
+
"loss": 0.6983,
|
| 84612 |
+
"step": 12086
|
| 84613 |
+
},
|
| 84614 |
+
{
|
| 84615 |
+
"epoch": 13.766951566951567,
|
| 84616 |
+
"grad_norm": 0.22153815627098083,
|
| 84617 |
+
"learning_rate": 1.1919564491607877e-05,
|
| 84618 |
+
"loss": 0.638,
|
| 84619 |
+
"step": 12087
|
| 84620 |
+
},
|
| 84621 |
+
{
|
| 84622 |
+
"epoch": 13.768091168091168,
|
| 84623 |
+
"grad_norm": 0.23503264784812927,
|
| 84624 |
+
"learning_rate": 1.191559416820818e-05,
|
| 84625 |
+
"loss": 0.8276,
|
| 84626 |
+
"step": 12088
|
| 84627 |
+
},
|
| 84628 |
+
{
|
| 84629 |
+
"epoch": 13.76923076923077,
|
| 84630 |
+
"grad_norm": 0.20020806789398193,
|
| 84631 |
+
"learning_rate": 1.1911624299265892e-05,
|
| 84632 |
+
"loss": 0.6884,
|
| 84633 |
+
"step": 12089
|
| 84634 |
+
},
|
| 84635 |
+
{
|
| 84636 |
+
"epoch": 13.77037037037037,
|
| 84637 |
+
"grad_norm": 0.20131689310073853,
|
| 84638 |
+
"learning_rate": 1.1907654884918885e-05,
|
| 84639 |
+
"loss": 0.5925,
|
| 84640 |
+
"step": 12090
|
| 84641 |
+
},
|
| 84642 |
+
{
|
| 84643 |
+
"epoch": 13.771509971509971,
|
| 84644 |
+
"grad_norm": 0.19345976412296295,
|
| 84645 |
+
"learning_rate": 1.1903685925305036e-05,
|
| 84646 |
+
"loss": 0.7759,
|
| 84647 |
+
"step": 12091
|
| 84648 |
+
},
|
| 84649 |
+
{
|
| 84650 |
+
"epoch": 13.772649572649573,
|
| 84651 |
+
"grad_norm": 0.16225802898406982,
|
| 84652 |
+
"learning_rate": 1.1899717420562179e-05,
|
| 84653 |
+
"loss": 0.7014,
|
| 84654 |
+
"step": 12092
|
| 84655 |
+
},
|
| 84656 |
+
{
|
| 84657 |
+
"epoch": 13.773789173789174,
|
| 84658 |
+
"grad_norm": 0.19633789360523224,
|
| 84659 |
+
"learning_rate": 1.1895749370828166e-05,
|
| 84660 |
+
"loss": 0.7085,
|
| 84661 |
+
"step": 12093
|
| 84662 |
+
},
|
| 84663 |
+
{
|
| 84664 |
+
"epoch": 13.774928774928775,
|
| 84665 |
+
"grad_norm": 0.20979763567447662,
|
| 84666 |
+
"learning_rate": 1.189178177624081e-05,
|
| 84667 |
+
"loss": 0.7952,
|
| 84668 |
+
"step": 12094
|
| 84669 |
+
},
|
| 84670 |
+
{
|
| 84671 |
+
"epoch": 13.776068376068377,
|
| 84672 |
+
"grad_norm": 0.17385949194431305,
|
| 84673 |
+
"learning_rate": 1.1887814636937932e-05,
|
| 84674 |
+
"loss": 0.937,
|
| 84675 |
+
"step": 12095
|
| 84676 |
+
},
|
| 84677 |
+
{
|
| 84678 |
+
"epoch": 13.777207977207977,
|
| 84679 |
+
"grad_norm": 0.21739883720874786,
|
| 84680 |
+
"learning_rate": 1.1883847953057303e-05,
|
| 84681 |
+
"loss": 0.8762,
|
| 84682 |
+
"step": 12096
|
| 84683 |
+
},
|
| 84684 |
+
{
|
| 84685 |
+
"epoch": 13.778347578347578,
|
| 84686 |
+
"grad_norm": 0.19551996886730194,
|
| 84687 |
+
"learning_rate": 1.1879881724736702e-05,
|
| 84688 |
+
"loss": 0.7889,
|
| 84689 |
+
"step": 12097
|
| 84690 |
+
},
|
| 84691 |
+
{
|
| 84692 |
+
"epoch": 13.77948717948718,
|
| 84693 |
+
"grad_norm": 0.25265413522720337,
|
| 84694 |
+
"learning_rate": 1.187591595211389e-05,
|
| 84695 |
+
"loss": 0.6491,
|
| 84696 |
+
"step": 12098
|
| 84697 |
+
},
|
| 84698 |
+
{
|
| 84699 |
+
"epoch": 13.78062678062678,
|
| 84700 |
+
"grad_norm": 0.18349041044712067,
|
| 84701 |
+
"learning_rate": 1.1871950635326606e-05,
|
| 84702 |
+
"loss": 0.7704,
|
| 84703 |
+
"step": 12099
|
| 84704 |
+
},
|
| 84705 |
+
{
|
| 84706 |
+
"epoch": 13.781766381766381,
|
| 84707 |
+
"grad_norm": 0.20760832726955414,
|
| 84708 |
+
"learning_rate": 1.186798577451258e-05,
|
| 84709 |
+
"loss": 0.8489,
|
| 84710 |
+
"step": 12100
|
| 84711 |
+
},
|
| 84712 |
+
{
|
| 84713 |
+
"epoch": 13.782905982905984,
|
| 84714 |
+
"grad_norm": 0.2054699957370758,
|
| 84715 |
+
"learning_rate": 1.1864021369809522e-05,
|
| 84716 |
+
"loss": 0.547,
|
| 84717 |
+
"step": 12101
|
| 84718 |
+
},
|
| 84719 |
+
{
|
| 84720 |
+
"epoch": 13.784045584045584,
|
| 84721 |
+
"grad_norm": 0.32506656646728516,
|
| 84722 |
+
"learning_rate": 1.1860057421355136e-05,
|
| 84723 |
+
"loss": 0.6203,
|
| 84724 |
+
"step": 12102
|
| 84725 |
+
},
|
| 84726 |
+
{
|
| 84727 |
+
"epoch": 13.785185185185185,
|
| 84728 |
+
"grad_norm": 0.1898188441991806,
|
| 84729 |
+
"learning_rate": 1.1856093929287079e-05,
|
| 84730 |
+
"loss": 0.8057,
|
| 84731 |
+
"step": 12103
|
| 84732 |
+
},
|
| 84733 |
+
{
|
| 84734 |
+
"epoch": 13.786324786324787,
|
| 84735 |
+
"grad_norm": 0.21240024268627167,
|
| 84736 |
+
"learning_rate": 1.1852130893743026e-05,
|
| 84737 |
+
"loss": 0.6552,
|
| 84738 |
+
"step": 12104
|
| 84739 |
+
},
|
| 84740 |
+
{
|
| 84741 |
+
"epoch": 13.787464387464388,
|
| 84742 |
+
"grad_norm": 0.21144267916679382,
|
| 84743 |
+
"learning_rate": 1.1848168314860627e-05,
|
| 84744 |
+
"loss": 0.5596,
|
| 84745 |
+
"step": 12105
|
| 84746 |
+
},
|
| 84747 |
+
{
|
| 84748 |
+
"epoch": 13.788603988603988,
|
| 84749 |
+
"grad_norm": 0.15825605392456055,
|
| 84750 |
+
"learning_rate": 1.1844206192777515e-05,
|
| 84751 |
+
"loss": 0.9469,
|
| 84752 |
+
"step": 12106
|
| 84753 |
+
},
|
| 84754 |
+
{
|
| 84755 |
+
"epoch": 13.78974358974359,
|
| 84756 |
+
"grad_norm": 0.1907399445772171,
|
| 84757 |
+
"learning_rate": 1.1840244527631295e-05,
|
| 84758 |
+
"loss": 0.8039,
|
| 84759 |
+
"step": 12107
|
| 84760 |
+
},
|
| 84761 |
+
{
|
| 84762 |
+
"epoch": 13.790883190883191,
|
| 84763 |
+
"grad_norm": 0.20638875663280487,
|
| 84764 |
+
"learning_rate": 1.1836283319559572e-05,
|
| 84765 |
+
"loss": 0.6795,
|
| 84766 |
+
"step": 12108
|
| 84767 |
+
},
|
| 84768 |
+
{
|
| 84769 |
+
"epoch": 13.792022792022792,
|
| 84770 |
+
"grad_norm": 0.2701677680015564,
|
| 84771 |
+
"learning_rate": 1.1832322568699927e-05,
|
| 84772 |
+
"loss": 0.603,
|
| 84773 |
+
"step": 12109
|
| 84774 |
+
},
|
| 84775 |
+
{
|
| 84776 |
+
"epoch": 13.793162393162394,
|
| 84777 |
+
"grad_norm": 1.2137209177017212,
|
| 84778 |
+
"learning_rate": 1.182836227518993e-05,
|
| 84779 |
+
"loss": 0.5928,
|
| 84780 |
+
"step": 12110
|
| 84781 |
+
},
|
| 84782 |
+
{
|
| 84783 |
+
"epoch": 13.794301994301994,
|
| 84784 |
+
"grad_norm": 0.26294225454330444,
|
| 84785 |
+
"learning_rate": 1.1824402439167137e-05,
|
| 84786 |
+
"loss": 0.7734,
|
| 84787 |
+
"step": 12111
|
| 84788 |
+
},
|
| 84789 |
+
{
|
| 84790 |
+
"epoch": 13.795441595441595,
|
| 84791 |
+
"grad_norm": 0.21291710436344147,
|
| 84792 |
+
"learning_rate": 1.1820443060769077e-05,
|
| 84793 |
+
"loss": 0.6986,
|
| 84794 |
+
"step": 12112
|
| 84795 |
+
},
|
| 84796 |
+
{
|
| 84797 |
+
"epoch": 13.796581196581197,
|
| 84798 |
+
"grad_norm": 0.20568042993545532,
|
| 84799 |
+
"learning_rate": 1.1816484140133286e-05,
|
| 84800 |
+
"loss": 0.7356,
|
| 84801 |
+
"step": 12113
|
| 84802 |
+
},
|
| 84803 |
+
{
|
| 84804 |
+
"epoch": 13.797720797720798,
|
| 84805 |
+
"grad_norm": 0.23887597024440765,
|
| 84806 |
+
"learning_rate": 1.1812525677397243e-05,
|
| 84807 |
+
"loss": 0.4924,
|
| 84808 |
+
"step": 12114
|
| 84809 |
+
},
|
| 84810 |
+
{
|
| 84811 |
+
"epoch": 13.798860398860398,
|
| 84812 |
+
"grad_norm": 0.1845303177833557,
|
| 84813 |
+
"learning_rate": 1.1808567672698451e-05,
|
| 84814 |
+
"loss": 0.7989,
|
| 84815 |
+
"step": 12115
|
| 84816 |
+
},
|
| 84817 |
+
{
|
| 84818 |
+
"epoch": 13.8,
|
| 84819 |
+
"grad_norm": 0.216530442237854,
|
| 84820 |
+
"learning_rate": 1.1804610126174378e-05,
|
| 84821 |
+
"loss": 0.7151,
|
| 84822 |
+
"step": 12116
|
| 84823 |
+
},
|
| 84824 |
+
{
|
| 84825 |
+
"epoch": 13.801139601139601,
|
| 84826 |
+
"grad_norm": 0.19970011711120605,
|
| 84827 |
+
"learning_rate": 1.1800653037962494e-05,
|
| 84828 |
+
"loss": 0.5739,
|
| 84829 |
+
"step": 12117
|
| 84830 |
+
},
|
| 84831 |
+
{
|
| 84832 |
+
"epoch": 13.802279202279202,
|
| 84833 |
+
"grad_norm": 0.24037083983421326,
|
| 84834 |
+
"learning_rate": 1.179669640820022e-05,
|
| 84835 |
+
"loss": 0.6529,
|
| 84836 |
+
"step": 12118
|
| 84837 |
+
},
|
| 84838 |
+
{
|
| 84839 |
+
"epoch": 13.803418803418804,
|
| 84840 |
+
"grad_norm": 0.19288606941699982,
|
| 84841 |
+
"learning_rate": 1.1792740237024988e-05,
|
| 84842 |
+
"loss": 0.8498,
|
| 84843 |
+
"step": 12119
|
| 84844 |
+
},
|
| 84845 |
+
{
|
| 84846 |
+
"epoch": 13.804558404558405,
|
| 84847 |
+
"grad_norm": 0.24818424880504608,
|
| 84848 |
+
"learning_rate": 1.1788784524574207e-05,
|
| 84849 |
+
"loss": 0.6215,
|
| 84850 |
+
"step": 12120
|
| 84851 |
+
},
|
| 84852 |
+
{
|
| 84853 |
+
"epoch": 13.805698005698005,
|
| 84854 |
+
"grad_norm": 0.1914277821779251,
|
| 84855 |
+
"learning_rate": 1.1784829270985271e-05,
|
| 84856 |
+
"loss": 0.6896,
|
| 84857 |
+
"step": 12121
|
| 84858 |
+
},
|
| 84859 |
+
{
|
| 84860 |
+
"epoch": 13.806837606837608,
|
| 84861 |
+
"grad_norm": 0.2206151932477951,
|
| 84862 |
+
"learning_rate": 1.1780874476395553e-05,
|
| 84863 |
+
"loss": 0.774,
|
| 84864 |
+
"step": 12122
|
| 84865 |
+
},
|
| 84866 |
+
{
|
| 84867 |
+
"epoch": 13.807977207977208,
|
| 84868 |
+
"grad_norm": 0.21806097030639648,
|
| 84869 |
+
"learning_rate": 1.1776920140942422e-05,
|
| 84870 |
+
"loss": 0.6167,
|
| 84871 |
+
"step": 12123
|
| 84872 |
+
},
|
| 84873 |
+
{
|
| 84874 |
+
"epoch": 13.809116809116809,
|
| 84875 |
+
"grad_norm": 0.16567018628120422,
|
| 84876 |
+
"learning_rate": 1.1772966264763217e-05,
|
| 84877 |
+
"loss": 0.6197,
|
| 84878 |
+
"step": 12124
|
| 84879 |
+
},
|
| 84880 |
+
{
|
| 84881 |
+
"epoch": 13.810256410256411,
|
| 84882 |
+
"grad_norm": 0.21184101700782776,
|
| 84883 |
+
"learning_rate": 1.1769012847995275e-05,
|
| 84884 |
+
"loss": 0.6112,
|
| 84885 |
+
"step": 12125
|
| 84886 |
+
},
|
| 84887 |
+
{
|
| 84888 |
+
"epoch": 13.811396011396011,
|
| 84889 |
+
"grad_norm": 0.25883615016937256,
|
| 84890 |
+
"learning_rate": 1.1765059890775895e-05,
|
| 84891 |
+
"loss": 0.6972,
|
| 84892 |
+
"step": 12126
|
| 84893 |
+
},
|
| 84894 |
+
{
|
| 84895 |
+
"epoch": 13.812535612535612,
|
| 84896 |
+
"grad_norm": 0.21643269062042236,
|
| 84897 |
+
"learning_rate": 1.1761107393242382e-05,
|
| 84898 |
+
"loss": 0.7196,
|
| 84899 |
+
"step": 12127
|
| 84900 |
+
},
|
| 84901 |
+
{
|
| 84902 |
+
"epoch": 13.813675213675214,
|
| 84903 |
+
"grad_norm": 0.20388276875019073,
|
| 84904 |
+
"learning_rate": 1.1757155355532015e-05,
|
| 84905 |
+
"loss": 0.6601,
|
| 84906 |
+
"step": 12128
|
| 84907 |
+
},
|
| 84908 |
+
{
|
| 84909 |
+
"epoch": 13.814814814814815,
|
| 84910 |
+
"grad_norm": 0.207803875207901,
|
| 84911 |
+
"learning_rate": 1.1753203777782067e-05,
|
| 84912 |
+
"loss": 0.5011,
|
| 84913 |
+
"step": 12129
|
| 84914 |
+
},
|
| 84915 |
+
{
|
| 84916 |
+
"epoch": 13.815954415954415,
|
| 84917 |
+
"grad_norm": 0.2117311656475067,
|
| 84918 |
+
"learning_rate": 1.1749252660129776e-05,
|
| 84919 |
+
"loss": 0.7493,
|
| 84920 |
+
"step": 12130
|
| 84921 |
+
},
|
| 84922 |
+
{
|
| 84923 |
+
"epoch": 13.817094017094018,
|
| 84924 |
+
"grad_norm": 0.22393865883350372,
|
| 84925 |
+
"learning_rate": 1.1745302002712377e-05,
|
| 84926 |
+
"loss": 0.6495,
|
| 84927 |
+
"step": 12131
|
| 84928 |
+
},
|
| 84929 |
+
{
|
| 84930 |
+
"epoch": 13.818233618233618,
|
| 84931 |
+
"grad_norm": 0.23343952000141144,
|
| 84932 |
+
"learning_rate": 1.1741351805667092e-05,
|
| 84933 |
+
"loss": 0.6071,
|
| 84934 |
+
"step": 12132
|
| 84935 |
+
},
|
| 84936 |
+
{
|
| 84937 |
+
"epoch": 13.819373219373219,
|
| 84938 |
+
"grad_norm": 0.22656363248825073,
|
| 84939 |
+
"learning_rate": 1.173740206913112e-05,
|
| 84940 |
+
"loss": 0.7191,
|
| 84941 |
+
"step": 12133
|
| 84942 |
+
},
|
| 84943 |
+
{
|
| 84944 |
+
"epoch": 13.820512820512821,
|
| 84945 |
+
"grad_norm": 0.15526340901851654,
|
| 84946 |
+
"learning_rate": 1.1733452793241645e-05,
|
| 84947 |
+
"loss": 0.6953,
|
| 84948 |
+
"step": 12134
|
| 84949 |
+
},
|
| 84950 |
+
{
|
| 84951 |
+
"epoch": 13.821652421652422,
|
| 84952 |
+
"grad_norm": 0.2617109715938568,
|
| 84953 |
+
"learning_rate": 1.172950397813584e-05,
|
| 84954 |
+
"loss": 0.604,
|
| 84955 |
+
"step": 12135
|
| 84956 |
+
},
|
| 84957 |
+
{
|
| 84958 |
+
"epoch": 13.822792022792022,
|
| 84959 |
+
"grad_norm": 0.20950858294963837,
|
| 84960 |
+
"learning_rate": 1.1725555623950863e-05,
|
| 84961 |
+
"loss": 0.6931,
|
| 84962 |
+
"step": 12136
|
| 84963 |
+
},
|
| 84964 |
+
{
|
| 84965 |
+
"epoch": 13.823931623931625,
|
| 84966 |
+
"grad_norm": 0.22320875525474548,
|
| 84967 |
+
"learning_rate": 1.1721607730823832e-05,
|
| 84968 |
+
"loss": 0.5865,
|
| 84969 |
+
"step": 12137
|
| 84970 |
+
},
|
| 84971 |
+
{
|
| 84972 |
+
"epoch": 13.825071225071225,
|
| 84973 |
+
"grad_norm": 0.27012088894844055,
|
| 84974 |
+
"learning_rate": 1.1717660298891886e-05,
|
| 84975 |
+
"loss": 0.4476,
|
| 84976 |
+
"step": 12138
|
| 84977 |
+
},
|
| 84978 |
+
{
|
| 84979 |
+
"epoch": 13.826210826210826,
|
| 84980 |
+
"grad_norm": 0.248300701379776,
|
| 84981 |
+
"learning_rate": 1.1713713328292122e-05,
|
| 84982 |
+
"loss": 0.4039,
|
| 84983 |
+
"step": 12139
|
| 84984 |
+
},
|
| 84985 |
+
{
|
| 84986 |
+
"epoch": 13.827350427350428,
|
| 84987 |
+
"grad_norm": 0.20293055474758148,
|
| 84988 |
+
"learning_rate": 1.1709766819161641e-05,
|
| 84989 |
+
"loss": 0.7534,
|
| 84990 |
+
"step": 12140
|
| 84991 |
+
},
|
| 84992 |
+
{
|
| 84993 |
+
"epoch": 13.828490028490029,
|
| 84994 |
+
"grad_norm": 0.19899849593639374,
|
| 84995 |
+
"learning_rate": 1.1705820771637496e-05,
|
| 84996 |
+
"loss": 0.7671,
|
| 84997 |
+
"step": 12141
|
| 84998 |
+
},
|
| 84999 |
+
{
|
| 85000 |
+
"epoch": 13.829629629629629,
|
| 85001 |
+
"grad_norm": 0.20491692423820496,
|
| 85002 |
+
"learning_rate": 1.1701875185856756e-05,
|
| 85003 |
+
"loss": 0.6022,
|
| 85004 |
+
"step": 12142
|
| 85005 |
+
},
|
| 85006 |
+
{
|
| 85007 |
+
"epoch": 13.830769230769231,
|
| 85008 |
+
"grad_norm": 0.24299074709415436,
|
| 85009 |
+
"learning_rate": 1.1697930061956461e-05,
|
| 85010 |
+
"loss": 0.5729,
|
| 85011 |
+
"step": 12143
|
| 85012 |
+
},
|
| 85013 |
+
{
|
| 85014 |
+
"epoch": 13.831908831908832,
|
| 85015 |
+
"grad_norm": 0.19051791727542877,
|
| 85016 |
+
"learning_rate": 1.1693985400073635e-05,
|
| 85017 |
+
"loss": 0.8498,
|
| 85018 |
+
"step": 12144
|
| 85019 |
+
},
|
| 85020 |
+
{
|
| 85021 |
+
"epoch": 13.833048433048432,
|
| 85022 |
+
"grad_norm": 0.2350401133298874,
|
| 85023 |
+
"learning_rate": 1.1690041200345286e-05,
|
| 85024 |
+
"loss": 0.372,
|
| 85025 |
+
"step": 12145
|
| 85026 |
+
},
|
| 85027 |
+
{
|
| 85028 |
+
"epoch": 13.834188034188035,
|
| 85029 |
+
"grad_norm": 0.23774166405200958,
|
| 85030 |
+
"learning_rate": 1.1686097462908413e-05,
|
| 85031 |
+
"loss": 0.5306,
|
| 85032 |
+
"step": 12146
|
| 85033 |
+
},
|
| 85034 |
+
{
|
| 85035 |
+
"epoch": 13.835327635327635,
|
| 85036 |
+
"grad_norm": 0.21102823317050934,
|
| 85037 |
+
"learning_rate": 1.1682154187899994e-05,
|
| 85038 |
+
"loss": 0.7034,
|
| 85039 |
+
"step": 12147
|
| 85040 |
+
},
|
| 85041 |
+
{
|
| 85042 |
+
"epoch": 13.836467236467236,
|
| 85043 |
+
"grad_norm": 0.20242071151733398,
|
| 85044 |
+
"learning_rate": 1.1678211375456977e-05,
|
| 85045 |
+
"loss": 0.627,
|
| 85046 |
+
"step": 12148
|
| 85047 |
+
},
|
| 85048 |
+
{
|
| 85049 |
+
"epoch": 13.837606837606838,
|
| 85050 |
+
"grad_norm": 0.21489715576171875,
|
| 85051 |
+
"learning_rate": 1.1674269025716315e-05,
|
| 85052 |
+
"loss": 0.8146,
|
| 85053 |
+
"step": 12149
|
| 85054 |
+
},
|
| 85055 |
+
{
|
| 85056 |
+
"epoch": 13.838746438746439,
|
| 85057 |
+
"grad_norm": 0.17829488217830658,
|
| 85058 |
+
"learning_rate": 1.1670327138814932e-05,
|
| 85059 |
+
"loss": 0.6618,
|
| 85060 |
+
"step": 12150
|
| 85061 |
+
},
|
| 85062 |
+
{
|
| 85063 |
+
"epoch": 13.83988603988604,
|
| 85064 |
+
"grad_norm": 0.24720202386379242,
|
| 85065 |
+
"learning_rate": 1.1666385714889754e-05,
|
| 85066 |
+
"loss": 0.678,
|
| 85067 |
+
"step": 12151
|
| 85068 |
+
},
|
| 85069 |
+
{
|
| 85070 |
+
"epoch": 13.841025641025642,
|
| 85071 |
+
"grad_norm": 0.19597914814949036,
|
| 85072 |
+
"learning_rate": 1.1662444754077662e-05,
|
| 85073 |
+
"loss": 0.6746,
|
| 85074 |
+
"step": 12152
|
| 85075 |
+
},
|
| 85076 |
+
{
|
| 85077 |
+
"epoch": 13.842165242165242,
|
| 85078 |
+
"grad_norm": 0.2212129533290863,
|
| 85079 |
+
"learning_rate": 1.165850425651554e-05,
|
| 85080 |
+
"loss": 0.712,
|
| 85081 |
+
"step": 12153
|
| 85082 |
+
},
|
| 85083 |
+
{
|
| 85084 |
+
"epoch": 13.843304843304843,
|
| 85085 |
+
"grad_norm": 0.21502304077148438,
|
| 85086 |
+
"learning_rate": 1.1654564222340255e-05,
|
| 85087 |
+
"loss": 0.6935,
|
| 85088 |
+
"step": 12154
|
| 85089 |
+
},
|
| 85090 |
+
{
|
| 85091 |
+
"epoch": 13.844444444444445,
|
| 85092 |
+
"grad_norm": 0.2452617734670639,
|
| 85093 |
+
"learning_rate": 1.1650624651688654e-05,
|
| 85094 |
+
"loss": 0.7074,
|
| 85095 |
+
"step": 12155
|
| 85096 |
+
},
|
| 85097 |
+
{
|
| 85098 |
+
"epoch": 13.845584045584046,
|
| 85099 |
+
"grad_norm": 0.20556528866291046,
|
| 85100 |
+
"learning_rate": 1.164668554469757e-05,
|
| 85101 |
+
"loss": 0.5669,
|
| 85102 |
+
"step": 12156
|
| 85103 |
+
},
|
| 85104 |
+
{
|
| 85105 |
+
"epoch": 13.846723646723646,
|
| 85106 |
+
"grad_norm": 0.2439274787902832,
|
| 85107 |
+
"learning_rate": 1.1642746901503817e-05,
|
| 85108 |
+
"loss": 0.597,
|
| 85109 |
+
"step": 12157
|
| 85110 |
+
},
|
| 85111 |
+
{
|
| 85112 |
+
"epoch": 13.847863247863248,
|
| 85113 |
+
"grad_norm": 0.19938474893569946,
|
| 85114 |
+
"learning_rate": 1.163880872224421e-05,
|
| 85115 |
+
"loss": 0.591,
|
| 85116 |
+
"step": 12158
|
| 85117 |
+
},
|
| 85118 |
+
{
|
| 85119 |
+
"epoch": 13.849002849002849,
|
| 85120 |
+
"grad_norm": 0.20182687044143677,
|
| 85121 |
+
"learning_rate": 1.1634871007055507e-05,
|
| 85122 |
+
"loss": 0.9088,
|
| 85123 |
+
"step": 12159
|
| 85124 |
+
},
|
| 85125 |
+
{
|
| 85126 |
+
"epoch": 13.85014245014245,
|
| 85127 |
+
"grad_norm": 0.20904295146465302,
|
| 85128 |
+
"learning_rate": 1.1630933756074488e-05,
|
| 85129 |
+
"loss": 0.6043,
|
| 85130 |
+
"step": 12160
|
| 85131 |
+
},
|
| 85132 |
+
{
|
| 85133 |
+
"epoch": 13.851282051282052,
|
| 85134 |
+
"grad_norm": 0.18662971258163452,
|
| 85135 |
+
"learning_rate": 1.1626996969437907e-05,
|
| 85136 |
+
"loss": 0.8019,
|
| 85137 |
+
"step": 12161
|
| 85138 |
+
},
|
| 85139 |
+
{
|
| 85140 |
+
"epoch": 13.852421652421652,
|
| 85141 |
+
"grad_norm": 0.27858710289001465,
|
| 85142 |
+
"learning_rate": 1.1623060647282505e-05,
|
| 85143 |
+
"loss": 0.5142,
|
| 85144 |
+
"step": 12162
|
| 85145 |
+
},
|
| 85146 |
+
{
|
| 85147 |
+
"epoch": 13.853561253561253,
|
| 85148 |
+
"grad_norm": 0.21194970607757568,
|
| 85149 |
+
"learning_rate": 1.1619124789744984e-05,
|
| 85150 |
+
"loss": 0.5959,
|
| 85151 |
+
"step": 12163
|
| 85152 |
+
},
|
| 85153 |
+
{
|
| 85154 |
+
"epoch": 13.854700854700855,
|
| 85155 |
+
"grad_norm": 0.19565068185329437,
|
| 85156 |
+
"learning_rate": 1.1615189396962057e-05,
|
| 85157 |
+
"loss": 0.7064,
|
| 85158 |
+
"step": 12164
|
| 85159 |
+
},
|
| 85160 |
+
{
|
| 85161 |
+
"epoch": 13.855840455840456,
|
| 85162 |
+
"grad_norm": 0.29635757207870483,
|
| 85163 |
+
"learning_rate": 1.1611254469070401e-05,
|
| 85164 |
+
"loss": 0.5085,
|
| 85165 |
+
"step": 12165
|
| 85166 |
+
},
|
| 85167 |
+
{
|
| 85168 |
+
"epoch": 13.856980056980056,
|
| 85169 |
+
"grad_norm": 0.2134222537279129,
|
| 85170 |
+
"learning_rate": 1.1607320006206715e-05,
|
| 85171 |
+
"loss": 0.5913,
|
| 85172 |
+
"step": 12166
|
| 85173 |
+
},
|
| 85174 |
+
{
|
| 85175 |
+
"epoch": 13.858119658119659,
|
| 85176 |
+
"grad_norm": 0.2340858280658722,
|
| 85177 |
+
"learning_rate": 1.1603386008507627e-05,
|
| 85178 |
+
"loss": 0.5986,
|
| 85179 |
+
"step": 12167
|
| 85180 |
+
},
|
| 85181 |
+
{
|
| 85182 |
+
"epoch": 13.85925925925926,
|
| 85183 |
+
"grad_norm": 0.20966479182243347,
|
| 85184 |
+
"learning_rate": 1.1599452476109784e-05,
|
| 85185 |
+
"loss": 0.647,
|
| 85186 |
+
"step": 12168
|
| 85187 |
+
},
|
| 85188 |
+
{
|
| 85189 |
+
"epoch": 13.86039886039886,
|
| 85190 |
+
"grad_norm": 0.1754055917263031,
|
| 85191 |
+
"learning_rate": 1.1595519409149807e-05,
|
| 85192 |
+
"loss": 0.6645,
|
| 85193 |
+
"step": 12169
|
| 85194 |
+
},
|
| 85195 |
+
{
|
| 85196 |
+
"epoch": 13.861538461538462,
|
| 85197 |
+
"grad_norm": 0.20462289452552795,
|
| 85198 |
+
"learning_rate": 1.1591586807764313e-05,
|
| 85199 |
+
"loss": 0.6546,
|
| 85200 |
+
"step": 12170
|
| 85201 |
+
},
|
| 85202 |
+
{
|
| 85203 |
+
"epoch": 13.862678062678063,
|
| 85204 |
+
"grad_norm": 0.17154642939567566,
|
| 85205 |
+
"learning_rate": 1.1587654672089873e-05,
|
| 85206 |
+
"loss": 0.6322,
|
| 85207 |
+
"step": 12171
|
| 85208 |
+
},
|
| 85209 |
+
{
|
| 85210 |
+
"epoch": 13.863817663817663,
|
| 85211 |
+
"grad_norm": 0.24959947168827057,
|
| 85212 |
+
"learning_rate": 1.1583723002263069e-05,
|
| 85213 |
+
"loss": 0.5293,
|
| 85214 |
+
"step": 12172
|
| 85215 |
+
},
|
| 85216 |
+
{
|
| 85217 |
+
"epoch": 13.864957264957265,
|
| 85218 |
+
"grad_norm": 0.18102394044399261,
|
| 85219 |
+
"learning_rate": 1.1579791798420462e-05,
|
| 85220 |
+
"loss": 0.7882,
|
| 85221 |
+
"step": 12173
|
| 85222 |
+
},
|
| 85223 |
+
{
|
| 85224 |
+
"epoch": 13.866096866096866,
|
| 85225 |
+
"grad_norm": 0.25361573696136475,
|
| 85226 |
+
"learning_rate": 1.15758610606986e-05,
|
| 85227 |
+
"loss": 0.4804,
|
| 85228 |
+
"step": 12174
|
| 85229 |
+
},
|
| 85230 |
+
{
|
| 85231 |
+
"epoch": 13.867236467236467,
|
| 85232 |
+
"grad_norm": 0.1994975209236145,
|
| 85233 |
+
"learning_rate": 1.1571930789233993e-05,
|
| 85234 |
+
"loss": 0.7014,
|
| 85235 |
+
"step": 12175
|
| 85236 |
+
},
|
| 85237 |
+
{
|
| 85238 |
+
"epoch": 13.868376068376069,
|
| 85239 |
+
"grad_norm": 0.1708739995956421,
|
| 85240 |
+
"learning_rate": 1.1568000984163143e-05,
|
| 85241 |
+
"loss": 0.7404,
|
| 85242 |
+
"step": 12176
|
| 85243 |
+
},
|
| 85244 |
+
{
|
| 85245 |
+
"epoch": 13.86951566951567,
|
| 85246 |
+
"grad_norm": 0.24408669769763947,
|
| 85247 |
+
"learning_rate": 1.1564071645622579e-05,
|
| 85248 |
+
"loss": 0.4335,
|
| 85249 |
+
"step": 12177
|
| 85250 |
+
},
|
| 85251 |
+
{
|
| 85252 |
+
"epoch": 13.87065527065527,
|
| 85253 |
+
"grad_norm": 0.2690698206424713,
|
| 85254 |
+
"learning_rate": 1.1560142773748744e-05,
|
| 85255 |
+
"loss": 0.6219,
|
| 85256 |
+
"step": 12178
|
| 85257 |
+
},
|
| 85258 |
+
{
|
| 85259 |
+
"epoch": 13.871794871794872,
|
| 85260 |
+
"grad_norm": 0.3402236998081207,
|
| 85261 |
+
"learning_rate": 1.1556214368678112e-05,
|
| 85262 |
+
"loss": 0.4422,
|
| 85263 |
+
"step": 12179
|
| 85264 |
+
},
|
| 85265 |
+
{
|
| 85266 |
+
"epoch": 13.872934472934473,
|
| 85267 |
+
"grad_norm": 0.23265834152698517,
|
| 85268 |
+
"learning_rate": 1.1552286430547126e-05,
|
| 85269 |
+
"loss": 0.6945,
|
| 85270 |
+
"step": 12180
|
| 85271 |
+
},
|
| 85272 |
+
{
|
| 85273 |
+
"epoch": 13.874074074074073,
|
| 85274 |
+
"grad_norm": 0.18340229988098145,
|
| 85275 |
+
"learning_rate": 1.1548358959492222e-05,
|
| 85276 |
+
"loss": 0.7958,
|
| 85277 |
+
"step": 12181
|
| 85278 |
+
},
|
| 85279 |
+
{
|
| 85280 |
+
"epoch": 13.875213675213676,
|
| 85281 |
+
"grad_norm": 0.2880589962005615,
|
| 85282 |
+
"learning_rate": 1.1544431955649795e-05,
|
| 85283 |
+
"loss": 0.4759,
|
| 85284 |
+
"step": 12182
|
| 85285 |
+
},
|
| 85286 |
+
{
|
| 85287 |
+
"epoch": 13.876353276353276,
|
| 85288 |
+
"grad_norm": 0.192237988114357,
|
| 85289 |
+
"learning_rate": 1.1540505419156247e-05,
|
| 85290 |
+
"loss": 0.6922,
|
| 85291 |
+
"step": 12183
|
| 85292 |
+
},
|
| 85293 |
+
{
|
| 85294 |
+
"epoch": 13.877492877492877,
|
| 85295 |
+
"grad_norm": 0.22548675537109375,
|
| 85296 |
+
"learning_rate": 1.1536579350147964e-05,
|
| 85297 |
+
"loss": 0.6792,
|
| 85298 |
+
"step": 12184
|
| 85299 |
+
},
|
| 85300 |
+
{
|
| 85301 |
+
"epoch": 13.878632478632479,
|
| 85302 |
+
"grad_norm": 0.23923629522323608,
|
| 85303 |
+
"learning_rate": 1.153265374876131e-05,
|
| 85304 |
+
"loss": 0.5638,
|
| 85305 |
+
"step": 12185
|
| 85306 |
+
},
|
| 85307 |
+
{
|
| 85308 |
+
"epoch": 13.87977207977208,
|
| 85309 |
+
"grad_norm": 0.18484920263290405,
|
| 85310 |
+
"learning_rate": 1.1528728615132616e-05,
|
| 85311 |
+
"loss": 0.6905,
|
| 85312 |
+
"step": 12186
|
| 85313 |
+
},
|
| 85314 |
+
{
|
| 85315 |
+
"epoch": 13.88091168091168,
|
| 85316 |
+
"grad_norm": 0.20133459568023682,
|
| 85317 |
+
"learning_rate": 1.1524803949398219e-05,
|
| 85318 |
+
"loss": 0.7755,
|
| 85319 |
+
"step": 12187
|
| 85320 |
+
},
|
| 85321 |
+
{
|
| 85322 |
+
"epoch": 13.882051282051282,
|
| 85323 |
+
"grad_norm": 0.17119839787483215,
|
| 85324 |
+
"learning_rate": 1.1520879751694452e-05,
|
| 85325 |
+
"loss": 0.4494,
|
| 85326 |
+
"step": 12188
|
| 85327 |
+
},
|
| 85328 |
+
{
|
| 85329 |
+
"epoch": 13.883190883190883,
|
| 85330 |
+
"grad_norm": 0.2637351453304291,
|
| 85331 |
+
"learning_rate": 1.1516956022157594e-05,
|
| 85332 |
+
"loss": 0.6105,
|
| 85333 |
+
"step": 12189
|
| 85334 |
+
},
|
| 85335 |
+
{
|
| 85336 |
+
"epoch": 13.884330484330484,
|
| 85337 |
+
"grad_norm": 0.2123945653438568,
|
| 85338 |
+
"learning_rate": 1.1513032760923927e-05,
|
| 85339 |
+
"loss": 0.5973,
|
| 85340 |
+
"step": 12190
|
| 85341 |
+
},
|
| 85342 |
+
{
|
| 85343 |
+
"epoch": 13.885470085470086,
|
| 85344 |
+
"grad_norm": 0.2376355677843094,
|
| 85345 |
+
"learning_rate": 1.1509109968129725e-05,
|
| 85346 |
+
"loss": 0.6014,
|
| 85347 |
+
"step": 12191
|
| 85348 |
+
},
|
| 85349 |
+
{
|
| 85350 |
+
"epoch": 13.886609686609686,
|
| 85351 |
+
"grad_norm": 0.2171904295682907,
|
| 85352 |
+
"learning_rate": 1.1505187643911242e-05,
|
| 85353 |
+
"loss": 0.7104,
|
| 85354 |
+
"step": 12192
|
| 85355 |
+
},
|
| 85356 |
+
{
|
| 85357 |
+
"epoch": 13.887749287749287,
|
| 85358 |
+
"grad_norm": 0.2625115215778351,
|
| 85359 |
+
"learning_rate": 1.1501265788404695e-05,
|
| 85360 |
+
"loss": 0.5782,
|
| 85361 |
+
"step": 12193
|
| 85362 |
+
},
|
| 85363 |
+
{
|
| 85364 |
+
"epoch": 13.88888888888889,
|
| 85365 |
+
"grad_norm": 0.20339708030223846,
|
| 85366 |
+
"learning_rate": 1.1497344401746307e-05,
|
| 85367 |
+
"loss": 0.7304,
|
| 85368 |
+
"step": 12194
|
| 85369 |
+
},
|
| 85370 |
+
{
|
| 85371 |
+
"epoch": 13.89002849002849,
|
| 85372 |
+
"grad_norm": 0.20857179164886475,
|
| 85373 |
+
"learning_rate": 1.149342348407228e-05,
|
| 85374 |
+
"loss": 0.7868,
|
| 85375 |
+
"step": 12195
|
| 85376 |
+
},
|
| 85377 |
+
{
|
| 85378 |
+
"epoch": 13.89116809116809,
|
| 85379 |
+
"grad_norm": 0.23755505681037903,
|
| 85380 |
+
"learning_rate": 1.148950303551881e-05,
|
| 85381 |
+
"loss": 0.7817,
|
| 85382 |
+
"step": 12196
|
| 85383 |
+
},
|
| 85384 |
+
{
|
| 85385 |
+
"epoch": 13.892307692307693,
|
| 85386 |
+
"grad_norm": 0.2457745224237442,
|
| 85387 |
+
"learning_rate": 1.1485583056222043e-05,
|
| 85388 |
+
"loss": 0.7278,
|
| 85389 |
+
"step": 12197
|
| 85390 |
+
},
|
| 85391 |
+
{
|
| 85392 |
+
"epoch": 13.893447293447293,
|
| 85393 |
+
"grad_norm": 0.18069693446159363,
|
| 85394 |
+
"learning_rate": 1.148166354631813e-05,
|
| 85395 |
+
"loss": 0.6967,
|
| 85396 |
+
"step": 12198
|
| 85397 |
+
},
|
| 85398 |
+
{
|
| 85399 |
+
"epoch": 13.894586894586894,
|
| 85400 |
+
"grad_norm": 0.20564036071300507,
|
| 85401 |
+
"learning_rate": 1.147774450594324e-05,
|
| 85402 |
+
"loss": 0.707,
|
| 85403 |
+
"step": 12199
|
| 85404 |
+
},
|
| 85405 |
+
{
|
| 85406 |
+
"epoch": 13.895726495726496,
|
| 85407 |
+
"grad_norm": 0.22701707482337952,
|
| 85408 |
+
"learning_rate": 1.147382593523346e-05,
|
| 85409 |
+
"loss": 0.6321,
|
| 85410 |
+
"step": 12200
|
| 85411 |
+
},
|
| 85412 |
+
{
|
| 85413 |
+
"epoch": 13.896866096866097,
|
| 85414 |
+
"grad_norm": 0.1899927258491516,
|
| 85415 |
+
"learning_rate": 1.14699078343249e-05,
|
| 85416 |
+
"loss": 0.7092,
|
| 85417 |
+
"step": 12201
|
| 85418 |
+
},
|
| 85419 |
+
{
|
| 85420 |
+
"epoch": 13.898005698005697,
|
| 85421 |
+
"grad_norm": 0.1906367838382721,
|
| 85422 |
+
"learning_rate": 1.146599020335365e-05,
|
| 85423 |
+
"loss": 0.6838,
|
| 85424 |
+
"step": 12202
|
| 85425 |
+
},
|
| 85426 |
+
{
|
| 85427 |
+
"epoch": 13.8991452991453,
|
| 85428 |
+
"grad_norm": 0.24131150543689728,
|
| 85429 |
+
"learning_rate": 1.146207304245578e-05,
|
| 85430 |
+
"loss": 0.7082,
|
| 85431 |
+
"step": 12203
|
| 85432 |
+
},
|
| 85433 |
+
{
|
| 85434 |
+
"epoch": 13.9002849002849,
|
| 85435 |
+
"grad_norm": 0.21252180635929108,
|
| 85436 |
+
"learning_rate": 1.145815635176735e-05,
|
| 85437 |
+
"loss": 0.6188,
|
| 85438 |
+
"step": 12204
|
| 85439 |
+
},
|
| 85440 |
+
{
|
| 85441 |
+
"epoch": 13.9014245014245,
|
| 85442 |
+
"grad_norm": 0.20956584811210632,
|
| 85443 |
+
"learning_rate": 1.1454240131424379e-05,
|
| 85444 |
+
"loss": 0.7428,
|
| 85445 |
+
"step": 12205
|
| 85446 |
+
},
|
| 85447 |
+
{
|
| 85448 |
+
"epoch": 13.902564102564103,
|
| 85449 |
+
"grad_norm": 0.1799883395433426,
|
| 85450 |
+
"learning_rate": 1.1450324381562901e-05,
|
| 85451 |
+
"loss": 0.6578,
|
| 85452 |
+
"step": 12206
|
| 85453 |
+
},
|
| 85454 |
+
{
|
| 85455 |
+
"epoch": 13.903703703703703,
|
| 85456 |
+
"grad_norm": 0.1994655728340149,
|
| 85457 |
+
"learning_rate": 1.1446409102318923e-05,
|
| 85458 |
+
"loss": 0.7279,
|
| 85459 |
+
"step": 12207
|
| 85460 |
+
},
|
| 85461 |
+
{
|
| 85462 |
+
"epoch": 13.904843304843304,
|
| 85463 |
+
"grad_norm": 0.20460699498653412,
|
| 85464 |
+
"learning_rate": 1.1442494293828434e-05,
|
| 85465 |
+
"loss": 0.6784,
|
| 85466 |
+
"step": 12208
|
| 85467 |
+
},
|
| 85468 |
+
{
|
| 85469 |
+
"epoch": 13.905982905982906,
|
| 85470 |
+
"grad_norm": 0.17750096321105957,
|
| 85471 |
+
"learning_rate": 1.1438579956227385e-05,
|
| 85472 |
+
"loss": 0.6321,
|
| 85473 |
+
"step": 12209
|
| 85474 |
+
},
|
| 85475 |
+
{
|
| 85476 |
+
"epoch": 13.907122507122507,
|
| 85477 |
+
"grad_norm": 0.1773277223110199,
|
| 85478 |
+
"learning_rate": 1.1434666089651757e-05,
|
| 85479 |
+
"loss": 0.7894,
|
| 85480 |
+
"step": 12210
|
| 85481 |
+
},
|
| 85482 |
+
{
|
| 85483 |
+
"epoch": 13.908262108262107,
|
| 85484 |
+
"grad_norm": 0.22248679399490356,
|
| 85485 |
+
"learning_rate": 1.143075269423749e-05,
|
| 85486 |
+
"loss": 0.86,
|
| 85487 |
+
"step": 12211
|
| 85488 |
+
},
|
| 85489 |
+
{
|
| 85490 |
+
"epoch": 13.90940170940171,
|
| 85491 |
+
"grad_norm": 0.1918819546699524,
|
| 85492 |
+
"learning_rate": 1.1426839770120488e-05,
|
| 85493 |
+
"loss": 0.8217,
|
| 85494 |
+
"step": 12212
|
| 85495 |
+
},
|
| 85496 |
+
{
|
| 85497 |
+
"epoch": 13.91054131054131,
|
| 85498 |
+
"grad_norm": 0.19866570830345154,
|
| 85499 |
+
"learning_rate": 1.1422927317436665e-05,
|
| 85500 |
+
"loss": 0.663,
|
| 85501 |
+
"step": 12213
|
| 85502 |
+
},
|
| 85503 |
+
{
|
| 85504 |
+
"epoch": 13.91168091168091,
|
| 85505 |
+
"grad_norm": 0.21274980902671814,
|
| 85506 |
+
"learning_rate": 1.1419015336321917e-05,
|
| 85507 |
+
"loss": 0.6106,
|
| 85508 |
+
"step": 12214
|
| 85509 |
+
},
|
| 85510 |
+
{
|
| 85511 |
+
"epoch": 13.912820512820513,
|
| 85512 |
+
"grad_norm": 0.21307888627052307,
|
| 85513 |
+
"learning_rate": 1.1415103826912122e-05,
|
| 85514 |
+
"loss": 0.6648,
|
| 85515 |
+
"step": 12215
|
| 85516 |
+
},
|
| 85517 |
+
{
|
| 85518 |
+
"epoch": 13.913960113960114,
|
| 85519 |
+
"grad_norm": 0.16856104135513306,
|
| 85520 |
+
"learning_rate": 1.141119278934312e-05,
|
| 85521 |
+
"loss": 0.8613,
|
| 85522 |
+
"step": 12216
|
| 85523 |
+
},
|
| 85524 |
+
{
|
| 85525 |
+
"epoch": 13.915099715099714,
|
| 85526 |
+
"grad_norm": 0.19490613043308258,
|
| 85527 |
+
"learning_rate": 1.1407282223750762e-05,
|
| 85528 |
+
"loss": 0.6325,
|
| 85529 |
+
"step": 12217
|
| 85530 |
+
},
|
| 85531 |
+
{
|
| 85532 |
+
"epoch": 13.916239316239317,
|
| 85533 |
+
"grad_norm": 0.24189704656600952,
|
| 85534 |
+
"learning_rate": 1.1403372130270872e-05,
|
| 85535 |
+
"loss": 0.8264,
|
| 85536 |
+
"step": 12218
|
| 85537 |
+
},
|
| 85538 |
+
{
|
| 85539 |
+
"epoch": 13.917378917378917,
|
| 85540 |
+
"grad_norm": 0.2483488917350769,
|
| 85541 |
+
"learning_rate": 1.1399462509039269e-05,
|
| 85542 |
+
"loss": 0.5555,
|
| 85543 |
+
"step": 12219
|
| 85544 |
+
},
|
| 85545 |
+
{
|
| 85546 |
+
"epoch": 13.918518518518518,
|
| 85547 |
+
"grad_norm": 0.21185415983200073,
|
| 85548 |
+
"learning_rate": 1.1395553360191724e-05,
|
| 85549 |
+
"loss": 0.7399,
|
| 85550 |
+
"step": 12220
|
| 85551 |
+
},
|
| 85552 |
+
{
|
| 85553 |
+
"epoch": 13.91965811965812,
|
| 85554 |
+
"grad_norm": 0.2353629320859909,
|
| 85555 |
+
"learning_rate": 1.1391644683864013e-05,
|
| 85556 |
+
"loss": 0.7179,
|
| 85557 |
+
"step": 12221
|
| 85558 |
+
},
|
| 85559 |
+
{
|
| 85560 |
+
"epoch": 13.92079772079772,
|
| 85561 |
+
"grad_norm": 0.19837498664855957,
|
| 85562 |
+
"learning_rate": 1.1387736480191927e-05,
|
| 85563 |
+
"loss": 0.749,
|
| 85564 |
+
"step": 12222
|
| 85565 |
+
},
|
| 85566 |
+
{
|
| 85567 |
+
"epoch": 13.921937321937321,
|
| 85568 |
+
"grad_norm": 0.19528906047344208,
|
| 85569 |
+
"learning_rate": 1.1383828749311176e-05,
|
| 85570 |
+
"loss": 0.7444,
|
| 85571 |
+
"step": 12223
|
| 85572 |
+
},
|
| 85573 |
+
{
|
| 85574 |
+
"epoch": 13.923076923076923,
|
| 85575 |
+
"grad_norm": 0.191130131483078,
|
| 85576 |
+
"learning_rate": 1.1379921491357497e-05,
|
| 85577 |
+
"loss": 0.6976,
|
| 85578 |
+
"step": 12224
|
| 85579 |
+
},
|
| 85580 |
+
{
|
| 85581 |
+
"epoch": 13.924216524216524,
|
| 85582 |
+
"grad_norm": 0.21918609738349915,
|
| 85583 |
+
"learning_rate": 1.1376014706466604e-05,
|
| 85584 |
+
"loss": 0.6714,
|
| 85585 |
+
"step": 12225
|
| 85586 |
+
},
|
| 85587 |
+
{
|
| 85588 |
+
"epoch": 13.925356125356124,
|
| 85589 |
+
"grad_norm": 0.2387215793132782,
|
| 85590 |
+
"learning_rate": 1.1372108394774189e-05,
|
| 85591 |
+
"loss": 0.4853,
|
| 85592 |
+
"step": 12226
|
| 85593 |
+
},
|
| 85594 |
+
{
|
| 85595 |
+
"epoch": 13.926495726495727,
|
| 85596 |
+
"grad_norm": 0.20336930453777313,
|
| 85597 |
+
"learning_rate": 1.1368202556415922e-05,
|
| 85598 |
+
"loss": 0.5817,
|
| 85599 |
+
"step": 12227
|
| 85600 |
+
},
|
| 85601 |
+
{
|
| 85602 |
+
"epoch": 13.927635327635327,
|
| 85603 |
+
"grad_norm": 0.21663232147693634,
|
| 85604 |
+
"learning_rate": 1.1364297191527465e-05,
|
| 85605 |
+
"loss": 0.5624,
|
| 85606 |
+
"step": 12228
|
| 85607 |
+
},
|
| 85608 |
+
{
|
| 85609 |
+
"epoch": 13.928774928774928,
|
| 85610 |
+
"grad_norm": 0.22602929174900055,
|
| 85611 |
+
"learning_rate": 1.1360392300244466e-05,
|
| 85612 |
+
"loss": 0.5956,
|
| 85613 |
+
"step": 12229
|
| 85614 |
+
},
|
| 85615 |
+
{
|
| 85616 |
+
"epoch": 13.92991452991453,
|
| 85617 |
+
"grad_norm": 0.2190379500389099,
|
| 85618 |
+
"learning_rate": 1.135648788270256e-05,
|
| 85619 |
+
"loss": 0.6329,
|
| 85620 |
+
"step": 12230
|
| 85621 |
+
},
|
| 85622 |
+
{
|
| 85623 |
+
"epoch": 13.93105413105413,
|
| 85624 |
+
"grad_norm": 0.2415732592344284,
|
| 85625 |
+
"learning_rate": 1.1352583939037343e-05,
|
| 85626 |
+
"loss": 0.5511,
|
| 85627 |
+
"step": 12231
|
| 85628 |
+
},
|
| 85629 |
+
{
|
| 85630 |
+
"epoch": 13.932193732193731,
|
| 85631 |
+
"grad_norm": 0.2015382945537567,
|
| 85632 |
+
"learning_rate": 1.1348680469384404e-05,
|
| 85633 |
+
"loss": 0.7696,
|
| 85634 |
+
"step": 12232
|
| 85635 |
+
},
|
| 85636 |
+
{
|
| 85637 |
+
"epoch": 13.933333333333334,
|
| 85638 |
+
"grad_norm": 0.18540619313716888,
|
| 85639 |
+
"learning_rate": 1.1344777473879352e-05,
|
| 85640 |
+
"loss": 0.7944,
|
| 85641 |
+
"step": 12233
|
| 85642 |
+
},
|
| 85643 |
+
{
|
| 85644 |
+
"epoch": 13.934472934472934,
|
| 85645 |
+
"grad_norm": 0.17577524483203888,
|
| 85646 |
+
"learning_rate": 1.1340874952657723e-05,
|
| 85647 |
+
"loss": 0.7502,
|
| 85648 |
+
"step": 12234
|
| 85649 |
+
},
|
| 85650 |
+
{
|
| 85651 |
+
"epoch": 13.935612535612536,
|
| 85652 |
+
"grad_norm": 0.1959916353225708,
|
| 85653 |
+
"learning_rate": 1.1336972905855067e-05,
|
| 85654 |
+
"loss": 0.8664,
|
| 85655 |
+
"step": 12235
|
| 85656 |
+
},
|
| 85657 |
+
{
|
| 85658 |
+
"epoch": 13.936752136752137,
|
| 85659 |
+
"grad_norm": 0.24582608044147491,
|
| 85660 |
+
"learning_rate": 1.1333071333606917e-05,
|
| 85661 |
+
"loss": 0.6266,
|
| 85662 |
+
"step": 12236
|
| 85663 |
+
},
|
| 85664 |
+
{
|
| 85665 |
+
"epoch": 13.937891737891738,
|
| 85666 |
+
"grad_norm": 0.19905447959899902,
|
| 85667 |
+
"learning_rate": 1.1329170236048795e-05,
|
| 85668 |
+
"loss": 0.8772,
|
| 85669 |
+
"step": 12237
|
| 85670 |
+
},
|
| 85671 |
+
{
|
| 85672 |
+
"epoch": 13.93903133903134,
|
| 85673 |
+
"grad_norm": 0.25572627782821655,
|
| 85674 |
+
"learning_rate": 1.1325269613316176e-05,
|
| 85675 |
+
"loss": 0.5735,
|
| 85676 |
+
"step": 12238
|
| 85677 |
+
},
|
| 85678 |
+
{
|
| 85679 |
+
"epoch": 13.94017094017094,
|
| 85680 |
+
"grad_norm": 0.2504177987575531,
|
| 85681 |
+
"learning_rate": 1.1321369465544546e-05,
|
| 85682 |
+
"loss": 0.6384,
|
| 85683 |
+
"step": 12239
|
| 85684 |
+
},
|
| 85685 |
+
{
|
| 85686 |
+
"epoch": 13.941310541310541,
|
| 85687 |
+
"grad_norm": 0.19246777892112732,
|
| 85688 |
+
"learning_rate": 1.1317469792869373e-05,
|
| 85689 |
+
"loss": 0.6691,
|
| 85690 |
+
"step": 12240
|
| 85691 |
+
},
|
| 85692 |
+
{
|
| 85693 |
+
"epoch": 13.942450142450143,
|
| 85694 |
+
"grad_norm": 0.25398629903793335,
|
| 85695 |
+
"learning_rate": 1.1313570595426109e-05,
|
| 85696 |
+
"loss": 0.6658,
|
| 85697 |
+
"step": 12241
|
| 85698 |
+
},
|
| 85699 |
+
{
|
| 85700 |
+
"epoch": 13.943589743589744,
|
| 85701 |
+
"grad_norm": 0.24399836361408234,
|
| 85702 |
+
"learning_rate": 1.1309671873350166e-05,
|
| 85703 |
+
"loss": 0.6095,
|
| 85704 |
+
"step": 12242
|
| 85705 |
+
},
|
| 85706 |
+
{
|
| 85707 |
+
"epoch": 13.944729344729344,
|
| 85708 |
+
"grad_norm": 0.2465384304523468,
|
| 85709 |
+
"learning_rate": 1.1305773626776961e-05,
|
| 85710 |
+
"loss": 0.5077,
|
| 85711 |
+
"step": 12243
|
| 85712 |
+
},
|
| 85713 |
+
{
|
| 85714 |
+
"epoch": 13.945868945868947,
|
| 85715 |
+
"grad_norm": 0.22829167544841766,
|
| 85716 |
+
"learning_rate": 1.1301875855841906e-05,
|
| 85717 |
+
"loss": 0.7855,
|
| 85718 |
+
"step": 12244
|
| 85719 |
+
},
|
| 85720 |
+
{
|
| 85721 |
+
"epoch": 13.947008547008547,
|
| 85722 |
+
"grad_norm": 0.23919540643692017,
|
| 85723 |
+
"learning_rate": 1.129797856068038e-05,
|
| 85724 |
+
"loss": 0.8215,
|
| 85725 |
+
"step": 12245
|
| 85726 |
+
},
|
| 85727 |
+
{
|
| 85728 |
+
"epoch": 13.948148148148148,
|
| 85729 |
+
"grad_norm": 0.19917504489421844,
|
| 85730 |
+
"learning_rate": 1.1294081741427731e-05,
|
| 85731 |
+
"loss": 0.7939,
|
| 85732 |
+
"step": 12246
|
| 85733 |
+
},
|
| 85734 |
+
{
|
| 85735 |
+
"epoch": 13.94928774928775,
|
| 85736 |
+
"grad_norm": 0.22689618170261383,
|
| 85737 |
+
"learning_rate": 1.1290185398219316e-05,
|
| 85738 |
+
"loss": 0.6322,
|
| 85739 |
+
"step": 12247
|
| 85740 |
+
},
|
| 85741 |
+
{
|
| 85742 |
+
"epoch": 13.95042735042735,
|
| 85743 |
+
"grad_norm": 0.2108716517686844,
|
| 85744 |
+
"learning_rate": 1.1286289531190464e-05,
|
| 85745 |
+
"loss": 0.6106,
|
| 85746 |
+
"step": 12248
|
| 85747 |
+
},
|
| 85748 |
+
{
|
| 85749 |
+
"epoch": 13.951566951566951,
|
| 85750 |
+
"grad_norm": 0.2141427993774414,
|
| 85751 |
+
"learning_rate": 1.1282394140476497e-05,
|
| 85752 |
+
"loss": 0.6067,
|
| 85753 |
+
"step": 12249
|
| 85754 |
+
},
|
| 85755 |
+
{
|
| 85756 |
+
"epoch": 13.952706552706553,
|
| 85757 |
+
"grad_norm": 0.22058185935020447,
|
| 85758 |
+
"learning_rate": 1.1278499226212696e-05,
|
| 85759 |
+
"loss": 0.7014,
|
| 85760 |
+
"step": 12250
|
| 85761 |
+
},
|
| 85762 |
+
{
|
| 85763 |
+
"epoch": 13.953846153846154,
|
| 85764 |
+
"grad_norm": 0.25046995282173157,
|
| 85765 |
+
"learning_rate": 1.1274604788534351e-05,
|
| 85766 |
+
"loss": 0.7122,
|
| 85767 |
+
"step": 12251
|
| 85768 |
+
},
|
| 85769 |
+
{
|
| 85770 |
+
"epoch": 13.954985754985755,
|
| 85771 |
+
"grad_norm": 0.22530826926231384,
|
| 85772 |
+
"learning_rate": 1.1270710827576727e-05,
|
| 85773 |
+
"loss": 0.4146,
|
| 85774 |
+
"step": 12252
|
| 85775 |
+
},
|
| 85776 |
+
{
|
| 85777 |
+
"epoch": 13.956125356125357,
|
| 85778 |
+
"grad_norm": 0.20750823616981506,
|
| 85779 |
+
"learning_rate": 1.126681734347508e-05,
|
| 85780 |
+
"loss": 0.8046,
|
| 85781 |
+
"step": 12253
|
| 85782 |
+
},
|
| 85783 |
+
{
|
| 85784 |
+
"epoch": 13.957264957264957,
|
| 85785 |
+
"grad_norm": 0.2138403207063675,
|
| 85786 |
+
"learning_rate": 1.1262924336364616e-05,
|
| 85787 |
+
"loss": 0.6614,
|
| 85788 |
+
"step": 12254
|
| 85789 |
+
},
|
| 85790 |
+
{
|
| 85791 |
+
"epoch": 13.958404558404558,
|
| 85792 |
+
"grad_norm": 0.2613039016723633,
|
| 85793 |
+
"learning_rate": 1.1259031806380577e-05,
|
| 85794 |
+
"loss": 0.5876,
|
| 85795 |
+
"step": 12255
|
| 85796 |
+
},
|
| 85797 |
+
{
|
| 85798 |
+
"epoch": 13.95954415954416,
|
| 85799 |
+
"grad_norm": 0.24097444117069244,
|
| 85800 |
+
"learning_rate": 1.125513975365816e-05,
|
| 85801 |
+
"loss": 0.5653,
|
| 85802 |
+
"step": 12256
|
| 85803 |
+
},
|
| 85804 |
+
{
|
| 85805 |
+
"epoch": 13.96068376068376,
|
| 85806 |
+
"grad_norm": 0.2530354857444763,
|
| 85807 |
+
"learning_rate": 1.1251248178332527e-05,
|
| 85808 |
+
"loss": 0.5816,
|
| 85809 |
+
"step": 12257
|
| 85810 |
+
},
|
| 85811 |
+
{
|
| 85812 |
+
"epoch": 13.961823361823361,
|
| 85813 |
+
"grad_norm": 0.2310188114643097,
|
| 85814 |
+
"learning_rate": 1.1247357080538853e-05,
|
| 85815 |
+
"loss": 0.6506,
|
| 85816 |
+
"step": 12258
|
| 85817 |
+
},
|
| 85818 |
+
{
|
| 85819 |
+
"epoch": 13.962962962962964,
|
| 85820 |
+
"grad_norm": 0.17745593190193176,
|
| 85821 |
+
"learning_rate": 1.124346646041229e-05,
|
| 85822 |
+
"loss": 0.8187,
|
| 85823 |
+
"step": 12259
|
| 85824 |
+
},
|
| 85825 |
+
{
|
| 85826 |
+
"epoch": 13.964102564102564,
|
| 85827 |
+
"grad_norm": 0.20546174049377441,
|
| 85828 |
+
"learning_rate": 1.1239576318087978e-05,
|
| 85829 |
+
"loss": 0.6235,
|
| 85830 |
+
"step": 12260
|
| 85831 |
+
},
|
| 85832 |
+
{
|
| 85833 |
+
"epoch": 13.965242165242165,
|
| 85834 |
+
"grad_norm": 0.20018534362316132,
|
| 85835 |
+
"learning_rate": 1.1235686653701011e-05,
|
| 85836 |
+
"loss": 0.7786,
|
| 85837 |
+
"step": 12261
|
| 85838 |
+
},
|
| 85839 |
+
{
|
| 85840 |
+
"epoch": 13.966381766381767,
|
| 85841 |
+
"grad_norm": 0.2011246532201767,
|
| 85842 |
+
"learning_rate": 1.1231797467386495e-05,
|
| 85843 |
+
"loss": 0.5827,
|
| 85844 |
+
"step": 12262
|
| 85845 |
+
},
|
| 85846 |
+
{
|
| 85847 |
+
"epoch": 13.967521367521368,
|
| 85848 |
+
"grad_norm": 0.1913696825504303,
|
| 85849 |
+
"learning_rate": 1.122790875927952e-05,
|
| 85850 |
+
"loss": 0.6169,
|
| 85851 |
+
"step": 12263
|
| 85852 |
+
},
|
| 85853 |
+
{
|
| 85854 |
+
"epoch": 13.968660968660968,
|
| 85855 |
+
"grad_norm": 0.23348921537399292,
|
| 85856 |
+
"learning_rate": 1.1224020529515155e-05,
|
| 85857 |
+
"loss": 0.6982,
|
| 85858 |
+
"step": 12264
|
| 85859 |
+
},
|
| 85860 |
+
{
|
| 85861 |
+
"epoch": 13.96980056980057,
|
| 85862 |
+
"grad_norm": 0.16664430499076843,
|
| 85863 |
+
"learning_rate": 1.1220132778228422e-05,
|
| 85864 |
+
"loss": 0.5185,
|
| 85865 |
+
"step": 12265
|
| 85866 |
+
},
|
| 85867 |
+
{
|
| 85868 |
+
"epoch": 13.970940170940171,
|
| 85869 |
+
"grad_norm": 0.309536337852478,
|
| 85870 |
+
"learning_rate": 1.1216245505554385e-05,
|
| 85871 |
+
"loss": 0.3365,
|
| 85872 |
+
"step": 12266
|
| 85873 |
+
},
|
| 85874 |
+
{
|
| 85875 |
+
"epoch": 13.972079772079772,
|
| 85876 |
+
"grad_norm": 0.1737096905708313,
|
| 85877 |
+
"learning_rate": 1.1212358711628052e-05,
|
| 85878 |
+
"loss": 0.6641,
|
| 85879 |
+
"step": 12267
|
| 85880 |
+
},
|
| 85881 |
+
{
|
| 85882 |
+
"epoch": 13.973219373219374,
|
| 85883 |
+
"grad_norm": 0.1941920965909958,
|
| 85884 |
+
"learning_rate": 1.120847239658441e-05,
|
| 85885 |
+
"loss": 0.6955,
|
| 85886 |
+
"step": 12268
|
| 85887 |
+
},
|
| 85888 |
+
{
|
| 85889 |
+
"epoch": 13.974358974358974,
|
| 85890 |
+
"grad_norm": 0.1931382566690445,
|
| 85891 |
+
"learning_rate": 1.1204586560558447e-05,
|
| 85892 |
+
"loss": 0.4182,
|
| 85893 |
+
"step": 12269
|
| 85894 |
+
},
|
| 85895 |
+
{
|
| 85896 |
+
"epoch": 13.975498575498575,
|
| 85897 |
+
"grad_norm": 0.26583507657051086,
|
| 85898 |
+
"learning_rate": 1.1200701203685132e-05,
|
| 85899 |
+
"loss": 0.5278,
|
| 85900 |
+
"step": 12270
|
| 85901 |
+
},
|
| 85902 |
+
{
|
| 85903 |
+
"epoch": 13.976638176638177,
|
| 85904 |
+
"grad_norm": 0.20485515892505646,
|
| 85905 |
+
"learning_rate": 1.119681632609942e-05,
|
| 85906 |
+
"loss": 0.7461,
|
| 85907 |
+
"step": 12271
|
| 85908 |
+
},
|
| 85909 |
+
{
|
| 85910 |
+
"epoch": 13.977777777777778,
|
| 85911 |
+
"grad_norm": 0.22491665184497833,
|
| 85912 |
+
"learning_rate": 1.119293192793623e-05,
|
| 85913 |
+
"loss": 0.7647,
|
| 85914 |
+
"step": 12272
|
| 85915 |
+
},
|
| 85916 |
+
{
|
| 85917 |
+
"epoch": 13.978917378917378,
|
| 85918 |
+
"grad_norm": 0.20172721147537231,
|
| 85919 |
+
"learning_rate": 1.118904800933048e-05,
|
| 85920 |
+
"loss": 0.5171,
|
| 85921 |
+
"step": 12273
|
| 85922 |
+
},
|
| 85923 |
+
{
|
| 85924 |
+
"epoch": 13.98005698005698,
|
| 85925 |
+
"grad_norm": 0.2544950842857361,
|
| 85926 |
+
"learning_rate": 1.1185164570417075e-05,
|
| 85927 |
+
"loss": 0.646,
|
| 85928 |
+
"step": 12274
|
| 85929 |
+
},
|
| 85930 |
+
{
|
| 85931 |
+
"epoch": 13.981196581196581,
|
| 85932 |
+
"grad_norm": 0.24959351122379303,
|
| 85933 |
+
"learning_rate": 1.1181281611330904e-05,
|
| 85934 |
+
"loss": 0.4714,
|
| 85935 |
+
"step": 12275
|
| 85936 |
+
},
|
| 85937 |
+
{
|
| 85938 |
+
"epoch": 13.982336182336182,
|
| 85939 |
+
"grad_norm": 0.227168008685112,
|
| 85940 |
+
"learning_rate": 1.1177399132206806e-05,
|
| 85941 |
+
"loss": 0.6064,
|
| 85942 |
+
"step": 12276
|
| 85943 |
+
},
|
| 85944 |
+
{
|
| 85945 |
+
"epoch": 13.983475783475784,
|
| 85946 |
+
"grad_norm": 0.21360209584236145,
|
| 85947 |
+
"learning_rate": 1.1173517133179657e-05,
|
| 85948 |
+
"loss": 0.6167,
|
| 85949 |
+
"step": 12277
|
| 85950 |
+
},
|
| 85951 |
+
{
|
| 85952 |
+
"epoch": 13.984615384615385,
|
| 85953 |
+
"grad_norm": 0.22920553386211395,
|
| 85954 |
+
"learning_rate": 1.116963561438429e-05,
|
| 85955 |
+
"loss": 0.6415,
|
| 85956 |
+
"step": 12278
|
| 85957 |
+
},
|
| 85958 |
+
{
|
| 85959 |
+
"epoch": 13.985754985754985,
|
| 85960 |
+
"grad_norm": 0.192453071475029,
|
| 85961 |
+
"learning_rate": 1.1165754575955504e-05,
|
| 85962 |
+
"loss": 0.5319,
|
| 85963 |
+
"step": 12279
|
| 85964 |
+
},
|
| 85965 |
+
{
|
| 85966 |
+
"epoch": 13.986894586894588,
|
| 85967 |
+
"grad_norm": 0.18710856139659882,
|
| 85968 |
+
"learning_rate": 1.1161874018028105e-05,
|
| 85969 |
+
"loss": 0.7048,
|
| 85970 |
+
"step": 12280
|
| 85971 |
+
},
|
| 85972 |
+
{
|
| 85973 |
+
"epoch": 13.988034188034188,
|
| 85974 |
+
"grad_norm": 0.19711796939373016,
|
| 85975 |
+
"learning_rate": 1.1157993940736877e-05,
|
| 85976 |
+
"loss": 0.7385,
|
| 85977 |
+
"step": 12281
|
| 85978 |
+
},
|
| 85979 |
+
{
|
| 85980 |
+
"epoch": 13.989173789173789,
|
| 85981 |
+
"grad_norm": 0.20384639501571655,
|
| 85982 |
+
"learning_rate": 1.1154114344216584e-05,
|
| 85983 |
+
"loss": 0.544,
|
| 85984 |
+
"step": 12282
|
| 85985 |
+
},
|
| 85986 |
+
{
|
| 85987 |
+
"epoch": 13.990313390313391,
|
| 85988 |
+
"grad_norm": 0.19997817277908325,
|
| 85989 |
+
"learning_rate": 1.1150235228601984e-05,
|
| 85990 |
+
"loss": 0.7785,
|
| 85991 |
+
"step": 12283
|
| 85992 |
+
},
|
| 85993 |
+
{
|
| 85994 |
+
"epoch": 13.991452991452991,
|
| 85995 |
+
"grad_norm": 0.21891017258167267,
|
| 85996 |
+
"learning_rate": 1.1146356594027796e-05,
|
| 85997 |
+
"loss": 0.6466,
|
| 85998 |
+
"step": 12284
|
| 85999 |
+
},
|
| 86000 |
+
{
|
| 86001 |
+
"epoch": 13.992592592592592,
|
| 86002 |
+
"grad_norm": 0.2607383728027344,
|
| 86003 |
+
"learning_rate": 1.114247844062874e-05,
|
| 86004 |
+
"loss": 0.4933,
|
| 86005 |
+
"step": 12285
|
| 86006 |
+
},
|
| 86007 |
+
{
|
| 86008 |
+
"epoch": 13.993732193732194,
|
| 86009 |
+
"grad_norm": 0.16678480803966522,
|
| 86010 |
+
"learning_rate": 1.1138600768539514e-05,
|
| 86011 |
+
"loss": 0.7185,
|
| 86012 |
+
"step": 12286
|
| 86013 |
+
},
|
| 86014 |
+
{
|
| 86015 |
+
"epoch": 13.994871794871795,
|
| 86016 |
+
"grad_norm": 0.287775456905365,
|
| 86017 |
+
"learning_rate": 1.1134723577894805e-05,
|
| 86018 |
+
"loss": 0.4988,
|
| 86019 |
+
"step": 12287
|
| 86020 |
+
},
|
| 86021 |
+
{
|
| 86022 |
+
"epoch": 13.996011396011395,
|
| 86023 |
+
"grad_norm": 0.19296123087406158,
|
| 86024 |
+
"learning_rate": 1.1130846868829273e-05,
|
| 86025 |
+
"loss": 0.6281,
|
| 86026 |
+
"step": 12288
|
| 86027 |
+
},
|
| 86028 |
+
{
|
| 86029 |
+
"epoch": 13.997150997150998,
|
| 86030 |
+
"grad_norm": 0.23793011903762817,
|
| 86031 |
+
"learning_rate": 1.1126970641477572e-05,
|
| 86032 |
+
"loss": 0.7806,
|
| 86033 |
+
"step": 12289
|
| 86034 |
+
},
|
| 86035 |
+
{
|
| 86036 |
+
"epoch": 13.998290598290598,
|
| 86037 |
+
"grad_norm": 0.19576086103916168,
|
| 86038 |
+
"learning_rate": 1.112309489597434e-05,
|
| 86039 |
+
"loss": 0.5895,
|
| 86040 |
+
"step": 12290
|
| 86041 |
+
},
|
| 86042 |
+
{
|
| 86043 |
+
"epoch": 13.999430199430199,
|
| 86044 |
+
"grad_norm": 0.21129938960075378,
|
| 86045 |
+
"learning_rate": 1.1119219632454176e-05,
|
| 86046 |
+
"loss": 0.6374,
|
| 86047 |
+
"step": 12291
|
| 86048 |
+
},
|
| 86049 |
+
{
|
| 86050 |
+
"epoch": 14.0,
|
| 86051 |
+
"grad_norm": 0.2696366012096405,
|
| 86052 |
+
"learning_rate": 1.1115344851051684e-05,
|
| 86053 |
+
"loss": 0.7114,
|
| 86054 |
+
"step": 12292
|
| 86055 |
+
},
|
| 86056 |
+
{
|
| 86057 |
+
"epoch": 14.0011396011396,
|
| 86058 |
+
"grad_norm": 0.2190292775630951,
|
| 86059 |
+
"learning_rate": 1.1111470551901449e-05,
|
| 86060 |
+
"loss": 0.6586,
|
| 86061 |
+
"step": 12293
|
| 86062 |
+
},
|
| 86063 |
+
{
|
| 86064 |
+
"epoch": 14.002279202279203,
|
| 86065 |
+
"grad_norm": 0.1721022129058838,
|
| 86066 |
+
"learning_rate": 1.1107596735138046e-05,
|
| 86067 |
+
"loss": 0.7334,
|
| 86068 |
+
"step": 12294
|
| 86069 |
+
},
|
| 86070 |
+
{
|
| 86071 |
+
"epoch": 14.003418803418803,
|
| 86072 |
+
"grad_norm": 0.18997089564800262,
|
| 86073 |
+
"learning_rate": 1.1103723400896001e-05,
|
| 86074 |
+
"loss": 0.8499,
|
| 86075 |
+
"step": 12295
|
| 86076 |
+
},
|
| 86077 |
+
{
|
| 86078 |
+
"epoch": 14.004558404558404,
|
| 86079 |
+
"grad_norm": 0.16700685024261475,
|
| 86080 |
+
"learning_rate": 1.1099850549309859e-05,
|
| 86081 |
+
"loss": 0.7764,
|
| 86082 |
+
"step": 12296
|
| 86083 |
+
},
|
| 86084 |
+
{
|
| 86085 |
+
"epoch": 14.005698005698006,
|
| 86086 |
+
"grad_norm": 0.19448800384998322,
|
| 86087 |
+
"learning_rate": 1.1095978180514132e-05,
|
| 86088 |
+
"loss": 0.7613,
|
| 86089 |
+
"step": 12297
|
| 86090 |
+
},
|
| 86091 |
+
{
|
| 86092 |
+
"epoch": 14.006837606837607,
|
| 86093 |
+
"grad_norm": 0.22701026499271393,
|
| 86094 |
+
"learning_rate": 1.1092106294643321e-05,
|
| 86095 |
+
"loss": 0.6202,
|
| 86096 |
+
"step": 12298
|
| 86097 |
+
},
|
| 86098 |
+
{
|
| 86099 |
+
"epoch": 14.007977207977207,
|
| 86100 |
+
"grad_norm": 0.20509253442287445,
|
| 86101 |
+
"learning_rate": 1.1088234891831903e-05,
|
| 86102 |
+
"loss": 0.5375,
|
| 86103 |
+
"step": 12299
|
| 86104 |
+
},
|
| 86105 |
+
{
|
| 86106 |
+
"epoch": 14.00911680911681,
|
| 86107 |
+
"grad_norm": 0.20297500491142273,
|
| 86108 |
+
"learning_rate": 1.1084363972214346e-05,
|
| 86109 |
+
"loss": 0.6547,
|
| 86110 |
+
"step": 12300
|
| 86111 |
}
|
| 86112 |
],
|
| 86113 |
"logging_steps": 1,
|
|
|
|
| 86127 |
"attributes": {}
|
| 86128 |
}
|
| 86129 |
},
|
| 86130 |
+
"total_flos": 6.8770770366926684e+19,
|
| 86131 |
"train_batch_size": 8,
|
| 86132 |
"trial_name": null,
|
| 86133 |
"trial_params": null
|