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 13200, 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 sha256:6c6ed46c413f571f197f0c5984a7d508b40e2e3721d1720037f60e1efdfbd876
|
| 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:bf386412284d142ea24874d3b51850a89ab321f3d76a1b3f665254c40594e84c
|
| 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 sha256:97f621c40c37c796d75663f728f7490ddcd9db068eaa82d92691bb9a37ff256f
|
| 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:af60437b8fcbfe37c08e284e2436c6eb6149c609f6a910e093adef85fa7f77c2
|
| 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,
|
|
@@ -90308,6 +90308,2106 @@
|
|
| 90308 |
"learning_rate": 8.853702458122149e-06,
|
| 90309 |
"loss": 0.6758,
|
| 90310 |
"step": 12900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90311 |
}
|
| 90312 |
],
|
| 90313 |
"logging_steps": 1,
|
|
@@ -90327,7 +92427,7 @@
|
|
| 90327 |
"attributes": {}
|
| 90328 |
}
|
| 90329 |
},
|
| 90330 |
-
"total_flos": 7.
|
| 90331 |
"train_batch_size": 8,
|
| 90332 |
"trial_name": null,
|
| 90333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.034188034188034,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 13200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 90308 |
"learning_rate": 8.853702458122149e-06,
|
| 90309 |
"loss": 0.6758,
|
| 90310 |
"step": 12900
|
| 90311 |
+
},
|
| 90312 |
+
{
|
| 90313 |
+
"epoch": 14.694017094017093,
|
| 90314 |
+
"grad_norm": 0.2252517193555832,
|
| 90315 |
+
"learning_rate": 8.850145627456869e-06,
|
| 90316 |
+
"loss": 0.502,
|
| 90317 |
+
"step": 12901
|
| 90318 |
+
},
|
| 90319 |
+
{
|
| 90320 |
+
"epoch": 14.695156695156696,
|
| 90321 |
+
"grad_norm": 0.24951429665088654,
|
| 90322 |
+
"learning_rate": 8.84658935772045e-06,
|
| 90323 |
+
"loss": 0.5665,
|
| 90324 |
+
"step": 12902
|
| 90325 |
+
},
|
| 90326 |
+
{
|
| 90327 |
+
"epoch": 14.696296296296296,
|
| 90328 |
+
"grad_norm": 0.24416764080524445,
|
| 90329 |
+
"learning_rate": 8.843033649036397e-06,
|
| 90330 |
+
"loss": 0.7362,
|
| 90331 |
+
"step": 12903
|
| 90332 |
+
},
|
| 90333 |
+
{
|
| 90334 |
+
"epoch": 14.697435897435897,
|
| 90335 |
+
"grad_norm": 0.21139328181743622,
|
| 90336 |
+
"learning_rate": 8.839478501528217e-06,
|
| 90337 |
+
"loss": 0.7178,
|
| 90338 |
+
"step": 12904
|
| 90339 |
+
},
|
| 90340 |
+
{
|
| 90341 |
+
"epoch": 14.698575498575499,
|
| 90342 |
+
"grad_norm": 0.2219403237104416,
|
| 90343 |
+
"learning_rate": 8.835923915319382e-06,
|
| 90344 |
+
"loss": 0.611,
|
| 90345 |
+
"step": 12905
|
| 90346 |
+
},
|
| 90347 |
+
{
|
| 90348 |
+
"epoch": 14.6997150997151,
|
| 90349 |
+
"grad_norm": 0.20910504460334778,
|
| 90350 |
+
"learning_rate": 8.832369890533379e-06,
|
| 90351 |
+
"loss": 0.5973,
|
| 90352 |
+
"step": 12906
|
| 90353 |
+
},
|
| 90354 |
+
{
|
| 90355 |
+
"epoch": 14.7008547008547,
|
| 90356 |
+
"grad_norm": 0.20052868127822876,
|
| 90357 |
+
"learning_rate": 8.82881642729362e-06,
|
| 90358 |
+
"loss": 0.6465,
|
| 90359 |
+
"step": 12907
|
| 90360 |
+
},
|
| 90361 |
+
{
|
| 90362 |
+
"epoch": 14.701994301994302,
|
| 90363 |
+
"grad_norm": 0.22043506801128387,
|
| 90364 |
+
"learning_rate": 8.82526352572354e-06,
|
| 90365 |
+
"loss": 0.5573,
|
| 90366 |
+
"step": 12908
|
| 90367 |
+
},
|
| 90368 |
+
{
|
| 90369 |
+
"epoch": 14.703133903133903,
|
| 90370 |
+
"grad_norm": 0.20473963022232056,
|
| 90371 |
+
"learning_rate": 8.821711185946538e-06,
|
| 90372 |
+
"loss": 0.4251,
|
| 90373 |
+
"step": 12909
|
| 90374 |
+
},
|
| 90375 |
+
{
|
| 90376 |
+
"epoch": 14.704273504273504,
|
| 90377 |
+
"grad_norm": 0.21355542540550232,
|
| 90378 |
+
"learning_rate": 8.818159408086004e-06,
|
| 90379 |
+
"loss": 0.4016,
|
| 90380 |
+
"step": 12910
|
| 90381 |
+
},
|
| 90382 |
+
{
|
| 90383 |
+
"epoch": 14.705413105413106,
|
| 90384 |
+
"grad_norm": 0.18627426028251648,
|
| 90385 |
+
"learning_rate": 8.814608192265287e-06,
|
| 90386 |
+
"loss": 0.6788,
|
| 90387 |
+
"step": 12911
|
| 90388 |
+
},
|
| 90389 |
+
{
|
| 90390 |
+
"epoch": 14.706552706552706,
|
| 90391 |
+
"grad_norm": 0.24863211810588837,
|
| 90392 |
+
"learning_rate": 8.811057538607736e-06,
|
| 90393 |
+
"loss": 0.4992,
|
| 90394 |
+
"step": 12912
|
| 90395 |
+
},
|
| 90396 |
+
{
|
| 90397 |
+
"epoch": 14.707692307692307,
|
| 90398 |
+
"grad_norm": 0.18860134482383728,
|
| 90399 |
+
"learning_rate": 8.80750744723668e-06,
|
| 90400 |
+
"loss": 0.6766,
|
| 90401 |
+
"step": 12913
|
| 90402 |
+
},
|
| 90403 |
+
{
|
| 90404 |
+
"epoch": 14.70883190883191,
|
| 90405 |
+
"grad_norm": 0.2076950967311859,
|
| 90406 |
+
"learning_rate": 8.803957918275425e-06,
|
| 90407 |
+
"loss": 0.4725,
|
| 90408 |
+
"step": 12914
|
| 90409 |
+
},
|
| 90410 |
+
{
|
| 90411 |
+
"epoch": 14.70997150997151,
|
| 90412 |
+
"grad_norm": 0.17382395267486572,
|
| 90413 |
+
"learning_rate": 8.800408951847242e-06,
|
| 90414 |
+
"loss": 0.7972,
|
| 90415 |
+
"step": 12915
|
| 90416 |
+
},
|
| 90417 |
+
{
|
| 90418 |
+
"epoch": 14.71111111111111,
|
| 90419 |
+
"grad_norm": 0.2199559062719345,
|
| 90420 |
+
"learning_rate": 8.796860548075397e-06,
|
| 90421 |
+
"loss": 0.6238,
|
| 90422 |
+
"step": 12916
|
| 90423 |
+
},
|
| 90424 |
+
{
|
| 90425 |
+
"epoch": 14.712250712250713,
|
| 90426 |
+
"grad_norm": 0.27296844124794006,
|
| 90427 |
+
"learning_rate": 8.793312707083162e-06,
|
| 90428 |
+
"loss": 0.512,
|
| 90429 |
+
"step": 12917
|
| 90430 |
+
},
|
| 90431 |
+
{
|
| 90432 |
+
"epoch": 14.713390313390313,
|
| 90433 |
+
"grad_norm": 0.19933409988880157,
|
| 90434 |
+
"learning_rate": 8.789765428993737e-06,
|
| 90435 |
+
"loss": 0.5875,
|
| 90436 |
+
"step": 12918
|
| 90437 |
+
},
|
| 90438 |
+
{
|
| 90439 |
+
"epoch": 14.714529914529914,
|
| 90440 |
+
"grad_norm": 0.22687682509422302,
|
| 90441 |
+
"learning_rate": 8.786218713930336e-06,
|
| 90442 |
+
"loss": 0.7143,
|
| 90443 |
+
"step": 12919
|
| 90444 |
+
},
|
| 90445 |
+
{
|
| 90446 |
+
"epoch": 14.715669515669516,
|
| 90447 |
+
"grad_norm": 0.23462781310081482,
|
| 90448 |
+
"learning_rate": 8.782672562016147e-06,
|
| 90449 |
+
"loss": 0.4709,
|
| 90450 |
+
"step": 12920
|
| 90451 |
+
},
|
| 90452 |
+
{
|
| 90453 |
+
"epoch": 14.716809116809117,
|
| 90454 |
+
"grad_norm": 0.20330078899860382,
|
| 90455 |
+
"learning_rate": 8.779126973374347e-06,
|
| 90456 |
+
"loss": 0.8525,
|
| 90457 |
+
"step": 12921
|
| 90458 |
+
},
|
| 90459 |
+
{
|
| 90460 |
+
"epoch": 14.717948717948717,
|
| 90461 |
+
"grad_norm": 0.21839894354343414,
|
| 90462 |
+
"learning_rate": 8.775581948128067e-06,
|
| 90463 |
+
"loss": 0.7413,
|
| 90464 |
+
"step": 12922
|
| 90465 |
+
},
|
| 90466 |
+
{
|
| 90467 |
+
"epoch": 14.71908831908832,
|
| 90468 |
+
"grad_norm": 0.18619459867477417,
|
| 90469 |
+
"learning_rate": 8.772037486400441e-06,
|
| 90470 |
+
"loss": 0.775,
|
| 90471 |
+
"step": 12923
|
| 90472 |
+
},
|
| 90473 |
+
{
|
| 90474 |
+
"epoch": 14.72022792022792,
|
| 90475 |
+
"grad_norm": 0.27662035822868347,
|
| 90476 |
+
"learning_rate": 8.76849358831458e-06,
|
| 90477 |
+
"loss": 0.4355,
|
| 90478 |
+
"step": 12924
|
| 90479 |
+
},
|
| 90480 |
+
{
|
| 90481 |
+
"epoch": 14.72136752136752,
|
| 90482 |
+
"grad_norm": 0.21078123152256012,
|
| 90483 |
+
"learning_rate": 8.764950253993585e-06,
|
| 90484 |
+
"loss": 0.5978,
|
| 90485 |
+
"step": 12925
|
| 90486 |
+
},
|
| 90487 |
+
{
|
| 90488 |
+
"epoch": 14.722507122507123,
|
| 90489 |
+
"grad_norm": 0.2041301131248474,
|
| 90490 |
+
"learning_rate": 8.761407483560504e-06,
|
| 90491 |
+
"loss": 0.6782,
|
| 90492 |
+
"step": 12926
|
| 90493 |
+
},
|
| 90494 |
+
{
|
| 90495 |
+
"epoch": 14.723646723646723,
|
| 90496 |
+
"grad_norm": 0.203069269657135,
|
| 90497 |
+
"learning_rate": 8.757865277138388e-06,
|
| 90498 |
+
"loss": 0.5123,
|
| 90499 |
+
"step": 12927
|
| 90500 |
+
},
|
| 90501 |
+
{
|
| 90502 |
+
"epoch": 14.724786324786324,
|
| 90503 |
+
"grad_norm": 0.20172251760959625,
|
| 90504 |
+
"learning_rate": 8.754323634850294e-06,
|
| 90505 |
+
"loss": 0.588,
|
| 90506 |
+
"step": 12928
|
| 90507 |
+
},
|
| 90508 |
+
{
|
| 90509 |
+
"epoch": 14.725925925925926,
|
| 90510 |
+
"grad_norm": 0.22396618127822876,
|
| 90511 |
+
"learning_rate": 8.750782556819209e-06,
|
| 90512 |
+
"loss": 0.6283,
|
| 90513 |
+
"step": 12929
|
| 90514 |
+
},
|
| 90515 |
+
{
|
| 90516 |
+
"epoch": 14.727065527065527,
|
| 90517 |
+
"grad_norm": 0.208025723695755,
|
| 90518 |
+
"learning_rate": 8.747242043168133e-06,
|
| 90519 |
+
"loss": 0.8028,
|
| 90520 |
+
"step": 12930
|
| 90521 |
+
},
|
| 90522 |
+
{
|
| 90523 |
+
"epoch": 14.728205128205127,
|
| 90524 |
+
"grad_norm": 0.21255724132061005,
|
| 90525 |
+
"learning_rate": 8.743702094020035e-06,
|
| 90526 |
+
"loss": 0.7828,
|
| 90527 |
+
"step": 12931
|
| 90528 |
+
},
|
| 90529 |
+
{
|
| 90530 |
+
"epoch": 14.72934472934473,
|
| 90531 |
+
"grad_norm": 0.21702732145786285,
|
| 90532 |
+
"learning_rate": 8.740162709497874e-06,
|
| 90533 |
+
"loss": 0.4972,
|
| 90534 |
+
"step": 12932
|
| 90535 |
+
},
|
| 90536 |
+
{
|
| 90537 |
+
"epoch": 14.73048433048433,
|
| 90538 |
+
"grad_norm": 0.1985195428133011,
|
| 90539 |
+
"learning_rate": 8.736623889724572e-06,
|
| 90540 |
+
"loss": 0.5624,
|
| 90541 |
+
"step": 12933
|
| 90542 |
+
},
|
| 90543 |
+
{
|
| 90544 |
+
"epoch": 14.73162393162393,
|
| 90545 |
+
"grad_norm": 0.19873084127902985,
|
| 90546 |
+
"learning_rate": 8.733085634823044e-06,
|
| 90547 |
+
"loss": 0.6781,
|
| 90548 |
+
"step": 12934
|
| 90549 |
+
},
|
| 90550 |
+
{
|
| 90551 |
+
"epoch": 14.732763532763533,
|
| 90552 |
+
"grad_norm": 0.256135493516922,
|
| 90553 |
+
"learning_rate": 8.729547944916187e-06,
|
| 90554 |
+
"loss": 0.5671,
|
| 90555 |
+
"step": 12935
|
| 90556 |
+
},
|
| 90557 |
+
{
|
| 90558 |
+
"epoch": 14.733903133903134,
|
| 90559 |
+
"grad_norm": 0.2034204751253128,
|
| 90560 |
+
"learning_rate": 8.726010820126881e-06,
|
| 90561 |
+
"loss": 0.6488,
|
| 90562 |
+
"step": 12936
|
| 90563 |
+
},
|
| 90564 |
+
{
|
| 90565 |
+
"epoch": 14.735042735042736,
|
| 90566 |
+
"grad_norm": 0.17327383160591125,
|
| 90567 |
+
"learning_rate": 8.722474260577965e-06,
|
| 90568 |
+
"loss": 0.807,
|
| 90569 |
+
"step": 12937
|
| 90570 |
+
},
|
| 90571 |
+
{
|
| 90572 |
+
"epoch": 14.736182336182337,
|
| 90573 |
+
"grad_norm": 0.2585669159889221,
|
| 90574 |
+
"learning_rate": 8.718938266392281e-06,
|
| 90575 |
+
"loss": 0.4724,
|
| 90576 |
+
"step": 12938
|
| 90577 |
+
},
|
| 90578 |
+
{
|
| 90579 |
+
"epoch": 14.737321937321937,
|
| 90580 |
+
"grad_norm": 0.23301592469215393,
|
| 90581 |
+
"learning_rate": 8.715402837692646e-06,
|
| 90582 |
+
"loss": 0.7433,
|
| 90583 |
+
"step": 12939
|
| 90584 |
+
},
|
| 90585 |
+
{
|
| 90586 |
+
"epoch": 14.73846153846154,
|
| 90587 |
+
"grad_norm": 0.2916012406349182,
|
| 90588 |
+
"learning_rate": 8.71186797460185e-06,
|
| 90589 |
+
"loss": 0.5879,
|
| 90590 |
+
"step": 12940
|
| 90591 |
+
},
|
| 90592 |
+
{
|
| 90593 |
+
"epoch": 14.73960113960114,
|
| 90594 |
+
"grad_norm": 0.19250716269016266,
|
| 90595 |
+
"learning_rate": 8.708333677242675e-06,
|
| 90596 |
+
"loss": 0.6382,
|
| 90597 |
+
"step": 12941
|
| 90598 |
+
},
|
| 90599 |
+
{
|
| 90600 |
+
"epoch": 14.74074074074074,
|
| 90601 |
+
"grad_norm": 0.2200244516134262,
|
| 90602 |
+
"learning_rate": 8.704799945737873e-06,
|
| 90603 |
+
"loss": 0.599,
|
| 90604 |
+
"step": 12942
|
| 90605 |
+
},
|
| 90606 |
+
{
|
| 90607 |
+
"epoch": 14.741880341880343,
|
| 90608 |
+
"grad_norm": 0.18007096648216248,
|
| 90609 |
+
"learning_rate": 8.701266780210187e-06,
|
| 90610 |
+
"loss": 0.5975,
|
| 90611 |
+
"step": 12943
|
| 90612 |
+
},
|
| 90613 |
+
{
|
| 90614 |
+
"epoch": 14.743019943019943,
|
| 90615 |
+
"grad_norm": 0.2152889370918274,
|
| 90616 |
+
"learning_rate": 8.697734180782321e-06,
|
| 90617 |
+
"loss": 0.8369,
|
| 90618 |
+
"step": 12944
|
| 90619 |
+
},
|
| 90620 |
+
{
|
| 90621 |
+
"epoch": 14.744159544159544,
|
| 90622 |
+
"grad_norm": 0.22600147128105164,
|
| 90623 |
+
"learning_rate": 8.69420214757698e-06,
|
| 90624 |
+
"loss": 0.6026,
|
| 90625 |
+
"step": 12945
|
| 90626 |
+
},
|
| 90627 |
+
{
|
| 90628 |
+
"epoch": 14.745299145299146,
|
| 90629 |
+
"grad_norm": 0.208087757229805,
|
| 90630 |
+
"learning_rate": 8.690670680716836e-06,
|
| 90631 |
+
"loss": 0.7278,
|
| 90632 |
+
"step": 12946
|
| 90633 |
+
},
|
| 90634 |
+
{
|
| 90635 |
+
"epoch": 14.746438746438747,
|
| 90636 |
+
"grad_norm": 0.2290181815624237,
|
| 90637 |
+
"learning_rate": 8.687139780324563e-06,
|
| 90638 |
+
"loss": 0.6925,
|
| 90639 |
+
"step": 12947
|
| 90640 |
+
},
|
| 90641 |
+
{
|
| 90642 |
+
"epoch": 14.747578347578347,
|
| 90643 |
+
"grad_norm": 0.22713790833950043,
|
| 90644 |
+
"learning_rate": 8.683609446522772e-06,
|
| 90645 |
+
"loss": 0.7047,
|
| 90646 |
+
"step": 12948
|
| 90647 |
+
},
|
| 90648 |
+
{
|
| 90649 |
+
"epoch": 14.74871794871795,
|
| 90650 |
+
"grad_norm": 0.244438037276268,
|
| 90651 |
+
"learning_rate": 8.6800796794341e-06,
|
| 90652 |
+
"loss": 0.6606,
|
| 90653 |
+
"step": 12949
|
| 90654 |
+
},
|
| 90655 |
+
{
|
| 90656 |
+
"epoch": 14.74985754985755,
|
| 90657 |
+
"grad_norm": 0.2058820128440857,
|
| 90658 |
+
"learning_rate": 8.67655047918113e-06,
|
| 90659 |
+
"loss": 0.6525,
|
| 90660 |
+
"step": 12950
|
| 90661 |
+
},
|
| 90662 |
+
{
|
| 90663 |
+
"epoch": 14.75099715099715,
|
| 90664 |
+
"grad_norm": 0.22019192576408386,
|
| 90665 |
+
"learning_rate": 8.673021845886467e-06,
|
| 90666 |
+
"loss": 0.6703,
|
| 90667 |
+
"step": 12951
|
| 90668 |
+
},
|
| 90669 |
+
{
|
| 90670 |
+
"epoch": 14.752136752136753,
|
| 90671 |
+
"grad_norm": 0.19387786090373993,
|
| 90672 |
+
"learning_rate": 8.66949377967265e-06,
|
| 90673 |
+
"loss": 0.5103,
|
| 90674 |
+
"step": 12952
|
| 90675 |
+
},
|
| 90676 |
+
{
|
| 90677 |
+
"epoch": 14.753276353276354,
|
| 90678 |
+
"grad_norm": 0.2757326662540436,
|
| 90679 |
+
"learning_rate": 8.665966280662219e-06,
|
| 90680 |
+
"loss": 0.7082,
|
| 90681 |
+
"step": 12953
|
| 90682 |
+
},
|
| 90683 |
+
{
|
| 90684 |
+
"epoch": 14.754415954415954,
|
| 90685 |
+
"grad_norm": 0.17531627416610718,
|
| 90686 |
+
"learning_rate": 8.6624393489777e-06,
|
| 90687 |
+
"loss": 0.7196,
|
| 90688 |
+
"step": 12954
|
| 90689 |
+
},
|
| 90690 |
+
{
|
| 90691 |
+
"epoch": 14.755555555555556,
|
| 90692 |
+
"grad_norm": 0.2704463303089142,
|
| 90693 |
+
"learning_rate": 8.6589129847416e-06,
|
| 90694 |
+
"loss": 0.5077,
|
| 90695 |
+
"step": 12955
|
| 90696 |
+
},
|
| 90697 |
+
{
|
| 90698 |
+
"epoch": 14.756695156695157,
|
| 90699 |
+
"grad_norm": 0.2233131229877472,
|
| 90700 |
+
"learning_rate": 8.655387188076381e-06,
|
| 90701 |
+
"loss": 0.7694,
|
| 90702 |
+
"step": 12956
|
| 90703 |
+
},
|
| 90704 |
+
{
|
| 90705 |
+
"epoch": 14.757834757834758,
|
| 90706 |
+
"grad_norm": 0.19787319004535675,
|
| 90707 |
+
"learning_rate": 8.651861959104513e-06,
|
| 90708 |
+
"loss": 0.7725,
|
| 90709 |
+
"step": 12957
|
| 90710 |
+
},
|
| 90711 |
+
{
|
| 90712 |
+
"epoch": 14.75897435897436,
|
| 90713 |
+
"grad_norm": 0.19262279570102692,
|
| 90714 |
+
"learning_rate": 8.648337297948436e-06,
|
| 90715 |
+
"loss": 0.8371,
|
| 90716 |
+
"step": 12958
|
| 90717 |
+
},
|
| 90718 |
+
{
|
| 90719 |
+
"epoch": 14.76011396011396,
|
| 90720 |
+
"grad_norm": 0.17423337697982788,
|
| 90721 |
+
"learning_rate": 8.644813204730578e-06,
|
| 90722 |
+
"loss": 0.7347,
|
| 90723 |
+
"step": 12959
|
| 90724 |
+
},
|
| 90725 |
+
{
|
| 90726 |
+
"epoch": 14.761253561253561,
|
| 90727 |
+
"grad_norm": 0.24191370606422424,
|
| 90728 |
+
"learning_rate": 8.64128967957333e-06,
|
| 90729 |
+
"loss": 0.6996,
|
| 90730 |
+
"step": 12960
|
| 90731 |
+
},
|
| 90732 |
+
{
|
| 90733 |
+
"epoch": 14.762393162393163,
|
| 90734 |
+
"grad_norm": 0.19753214716911316,
|
| 90735 |
+
"learning_rate": 8.63776672259907e-06,
|
| 90736 |
+
"loss": 0.6602,
|
| 90737 |
+
"step": 12961
|
| 90738 |
+
},
|
| 90739 |
+
{
|
| 90740 |
+
"epoch": 14.763532763532764,
|
| 90741 |
+
"grad_norm": 0.19329145550727844,
|
| 90742 |
+
"learning_rate": 8.634244333930181e-06,
|
| 90743 |
+
"loss": 0.7179,
|
| 90744 |
+
"step": 12962
|
| 90745 |
+
},
|
| 90746 |
+
{
|
| 90747 |
+
"epoch": 14.764672364672364,
|
| 90748 |
+
"grad_norm": 0.2344941645860672,
|
| 90749 |
+
"learning_rate": 8.630722513688986e-06,
|
| 90750 |
+
"loss": 0.6992,
|
| 90751 |
+
"step": 12963
|
| 90752 |
+
},
|
| 90753 |
+
{
|
| 90754 |
+
"epoch": 14.765811965811967,
|
| 90755 |
+
"grad_norm": 0.1706835776567459,
|
| 90756 |
+
"learning_rate": 8.627201261997815e-06,
|
| 90757 |
+
"loss": 0.7616,
|
| 90758 |
+
"step": 12964
|
| 90759 |
+
},
|
| 90760 |
+
{
|
| 90761 |
+
"epoch": 14.766951566951567,
|
| 90762 |
+
"grad_norm": 0.19436347484588623,
|
| 90763 |
+
"learning_rate": 8.623680578978968e-06,
|
| 90764 |
+
"loss": 0.6385,
|
| 90765 |
+
"step": 12965
|
| 90766 |
+
},
|
| 90767 |
+
{
|
| 90768 |
+
"epoch": 14.768091168091168,
|
| 90769 |
+
"grad_norm": 0.1849130392074585,
|
| 90770 |
+
"learning_rate": 8.620160464754737e-06,
|
| 90771 |
+
"loss": 0.8438,
|
| 90772 |
+
"step": 12966
|
| 90773 |
+
},
|
| 90774 |
+
{
|
| 90775 |
+
"epoch": 14.76923076923077,
|
| 90776 |
+
"grad_norm": 0.20800837874412537,
|
| 90777 |
+
"learning_rate": 8.616640919447372e-06,
|
| 90778 |
+
"loss": 0.6825,
|
| 90779 |
+
"step": 12967
|
| 90780 |
+
},
|
| 90781 |
+
{
|
| 90782 |
+
"epoch": 14.77037037037037,
|
| 90783 |
+
"grad_norm": 0.17224492132663727,
|
| 90784 |
+
"learning_rate": 8.61312194317912e-06,
|
| 90785 |
+
"loss": 0.7496,
|
| 90786 |
+
"step": 12968
|
| 90787 |
+
},
|
| 90788 |
+
{
|
| 90789 |
+
"epoch": 14.771509971509971,
|
| 90790 |
+
"grad_norm": 0.20169848203659058,
|
| 90791 |
+
"learning_rate": 8.609603536072209e-06,
|
| 90792 |
+
"loss": 0.6928,
|
| 90793 |
+
"step": 12969
|
| 90794 |
+
},
|
| 90795 |
+
{
|
| 90796 |
+
"epoch": 14.772649572649573,
|
| 90797 |
+
"grad_norm": 0.18767385184764862,
|
| 90798 |
+
"learning_rate": 8.606085698248848e-06,
|
| 90799 |
+
"loss": 0.6698,
|
| 90800 |
+
"step": 12970
|
| 90801 |
+
},
|
| 90802 |
+
{
|
| 90803 |
+
"epoch": 14.773789173789174,
|
| 90804 |
+
"grad_norm": 0.18218882381916046,
|
| 90805 |
+
"learning_rate": 8.602568429831203e-06,
|
| 90806 |
+
"loss": 0.8292,
|
| 90807 |
+
"step": 12971
|
| 90808 |
+
},
|
| 90809 |
+
{
|
| 90810 |
+
"epoch": 14.774928774928775,
|
| 90811 |
+
"grad_norm": 0.21513763070106506,
|
| 90812 |
+
"learning_rate": 8.599051730941445e-06,
|
| 90813 |
+
"loss": 0.4836,
|
| 90814 |
+
"step": 12972
|
| 90815 |
+
},
|
| 90816 |
+
{
|
| 90817 |
+
"epoch": 14.776068376068377,
|
| 90818 |
+
"grad_norm": 0.29810693860054016,
|
| 90819 |
+
"learning_rate": 8.59553560170174e-06,
|
| 90820 |
+
"loss": 0.2674,
|
| 90821 |
+
"step": 12973
|
| 90822 |
+
},
|
| 90823 |
+
{
|
| 90824 |
+
"epoch": 14.777207977207977,
|
| 90825 |
+
"grad_norm": 0.20459535717964172,
|
| 90826 |
+
"learning_rate": 8.592020042234186e-06,
|
| 90827 |
+
"loss": 0.702,
|
| 90828 |
+
"step": 12974
|
| 90829 |
+
},
|
| 90830 |
+
{
|
| 90831 |
+
"epoch": 14.778347578347578,
|
| 90832 |
+
"grad_norm": 0.2290467917919159,
|
| 90833 |
+
"learning_rate": 8.5885050526609e-06,
|
| 90834 |
+
"loss": 0.5831,
|
| 90835 |
+
"step": 12975
|
| 90836 |
+
},
|
| 90837 |
+
{
|
| 90838 |
+
"epoch": 14.77948717948718,
|
| 90839 |
+
"grad_norm": 0.19999980926513672,
|
| 90840 |
+
"learning_rate": 8.584990633103962e-06,
|
| 90841 |
+
"loss": 0.6615,
|
| 90842 |
+
"step": 12976
|
| 90843 |
+
},
|
| 90844 |
+
{
|
| 90845 |
+
"epoch": 14.78062678062678,
|
| 90846 |
+
"grad_norm": 0.2327142059803009,
|
| 90847 |
+
"learning_rate": 8.581476783685452e-06,
|
| 90848 |
+
"loss": 0.7061,
|
| 90849 |
+
"step": 12977
|
| 90850 |
+
},
|
| 90851 |
+
{
|
| 90852 |
+
"epoch": 14.781766381766381,
|
| 90853 |
+
"grad_norm": 0.19669906795024872,
|
| 90854 |
+
"learning_rate": 8.577963504527395e-06,
|
| 90855 |
+
"loss": 0.842,
|
| 90856 |
+
"step": 12978
|
| 90857 |
+
},
|
| 90858 |
+
{
|
| 90859 |
+
"epoch": 14.782905982905984,
|
| 90860 |
+
"grad_norm": 0.2074698507785797,
|
| 90861 |
+
"learning_rate": 8.574450795751827e-06,
|
| 90862 |
+
"loss": 0.7923,
|
| 90863 |
+
"step": 12979
|
| 90864 |
+
},
|
| 90865 |
+
{
|
| 90866 |
+
"epoch": 14.784045584045584,
|
| 90867 |
+
"grad_norm": 0.21502606570720673,
|
| 90868 |
+
"learning_rate": 8.570938657480753e-06,
|
| 90869 |
+
"loss": 0.6886,
|
| 90870 |
+
"step": 12980
|
| 90871 |
+
},
|
| 90872 |
+
{
|
| 90873 |
+
"epoch": 14.785185185185185,
|
| 90874 |
+
"grad_norm": 0.18325702846050262,
|
| 90875 |
+
"learning_rate": 8.567427089836166e-06,
|
| 90876 |
+
"loss": 0.552,
|
| 90877 |
+
"step": 12981
|
| 90878 |
+
},
|
| 90879 |
+
{
|
| 90880 |
+
"epoch": 14.786324786324787,
|
| 90881 |
+
"grad_norm": 0.19786466658115387,
|
| 90882 |
+
"learning_rate": 8.563916092940023e-06,
|
| 90883 |
+
"loss": 0.7887,
|
| 90884 |
+
"step": 12982
|
| 90885 |
+
},
|
| 90886 |
+
{
|
| 90887 |
+
"epoch": 14.787464387464388,
|
| 90888 |
+
"grad_norm": 0.20122556388378143,
|
| 90889 |
+
"learning_rate": 8.56040566691426e-06,
|
| 90890 |
+
"loss": 0.8217,
|
| 90891 |
+
"step": 12983
|
| 90892 |
+
},
|
| 90893 |
+
{
|
| 90894 |
+
"epoch": 14.788603988603988,
|
| 90895 |
+
"grad_norm": 0.23256726562976837,
|
| 90896 |
+
"learning_rate": 8.556895811880827e-06,
|
| 90897 |
+
"loss": 0.7266,
|
| 90898 |
+
"step": 12984
|
| 90899 |
+
},
|
| 90900 |
+
{
|
| 90901 |
+
"epoch": 14.78974358974359,
|
| 90902 |
+
"grad_norm": 0.22507259249687195,
|
| 90903 |
+
"learning_rate": 8.55338652796163e-06,
|
| 90904 |
+
"loss": 0.6712,
|
| 90905 |
+
"step": 12985
|
| 90906 |
+
},
|
| 90907 |
+
{
|
| 90908 |
+
"epoch": 14.790883190883191,
|
| 90909 |
+
"grad_norm": 0.2573149502277374,
|
| 90910 |
+
"learning_rate": 8.549877815278537e-06,
|
| 90911 |
+
"loss": 0.6409,
|
| 90912 |
+
"step": 12986
|
| 90913 |
+
},
|
| 90914 |
+
{
|
| 90915 |
+
"epoch": 14.792022792022792,
|
| 90916 |
+
"grad_norm": 0.2129795402288437,
|
| 90917 |
+
"learning_rate": 8.546369673953428e-06,
|
| 90918 |
+
"loss": 0.6501,
|
| 90919 |
+
"step": 12987
|
| 90920 |
+
},
|
| 90921 |
+
{
|
| 90922 |
+
"epoch": 14.793162393162394,
|
| 90923 |
+
"grad_norm": 0.22979819774627686,
|
| 90924 |
+
"learning_rate": 8.542862104108146e-06,
|
| 90925 |
+
"loss": 0.525,
|
| 90926 |
+
"step": 12988
|
| 90927 |
+
},
|
| 90928 |
+
{
|
| 90929 |
+
"epoch": 14.794301994301994,
|
| 90930 |
+
"grad_norm": 0.23122137784957886,
|
| 90931 |
+
"learning_rate": 8.53935510586453e-06,
|
| 90932 |
+
"loss": 0.527,
|
| 90933 |
+
"step": 12989
|
| 90934 |
+
},
|
| 90935 |
+
{
|
| 90936 |
+
"epoch": 14.795441595441595,
|
| 90937 |
+
"grad_norm": 0.2197915017604828,
|
| 90938 |
+
"learning_rate": 8.53584867934437e-06,
|
| 90939 |
+
"loss": 0.507,
|
| 90940 |
+
"step": 12990
|
| 90941 |
+
},
|
| 90942 |
+
{
|
| 90943 |
+
"epoch": 14.796581196581197,
|
| 90944 |
+
"grad_norm": 0.22086749970912933,
|
| 90945 |
+
"learning_rate": 8.53234282466946e-06,
|
| 90946 |
+
"loss": 0.4494,
|
| 90947 |
+
"step": 12991
|
| 90948 |
+
},
|
| 90949 |
+
{
|
| 90950 |
+
"epoch": 14.797720797720798,
|
| 90951 |
+
"grad_norm": 0.24085772037506104,
|
| 90952 |
+
"learning_rate": 8.528837541961571e-06,
|
| 90953 |
+
"loss": 0.6806,
|
| 90954 |
+
"step": 12992
|
| 90955 |
+
},
|
| 90956 |
+
{
|
| 90957 |
+
"epoch": 14.798860398860398,
|
| 90958 |
+
"grad_norm": 0.2377721071243286,
|
| 90959 |
+
"learning_rate": 8.525332831342459e-06,
|
| 90960 |
+
"loss": 0.4843,
|
| 90961 |
+
"step": 12993
|
| 90962 |
+
},
|
| 90963 |
+
{
|
| 90964 |
+
"epoch": 14.8,
|
| 90965 |
+
"grad_norm": 0.19742220640182495,
|
| 90966 |
+
"learning_rate": 8.521828692933826e-06,
|
| 90967 |
+
"loss": 0.659,
|
| 90968 |
+
"step": 12994
|
| 90969 |
+
},
|
| 90970 |
+
{
|
| 90971 |
+
"epoch": 14.801139601139601,
|
| 90972 |
+
"grad_norm": 0.19149692356586456,
|
| 90973 |
+
"learning_rate": 8.518325126857405e-06,
|
| 90974 |
+
"loss": 0.4287,
|
| 90975 |
+
"step": 12995
|
| 90976 |
+
},
|
| 90977 |
+
{
|
| 90978 |
+
"epoch": 14.802279202279202,
|
| 90979 |
+
"grad_norm": 0.21423348784446716,
|
| 90980 |
+
"learning_rate": 8.514822133234886e-06,
|
| 90981 |
+
"loss": 0.7736,
|
| 90982 |
+
"step": 12996
|
| 90983 |
+
},
|
| 90984 |
+
{
|
| 90985 |
+
"epoch": 14.803418803418804,
|
| 90986 |
+
"grad_norm": 0.25497955083847046,
|
| 90987 |
+
"learning_rate": 8.511319712187924e-06,
|
| 90988 |
+
"loss": 0.6745,
|
| 90989 |
+
"step": 12997
|
| 90990 |
+
},
|
| 90991 |
+
{
|
| 90992 |
+
"epoch": 14.804558404558405,
|
| 90993 |
+
"grad_norm": 0.2030903548002243,
|
| 90994 |
+
"learning_rate": 8.507817863838166e-06,
|
| 90995 |
+
"loss": 0.7302,
|
| 90996 |
+
"step": 12998
|
| 90997 |
+
},
|
| 90998 |
+
{
|
| 90999 |
+
"epoch": 14.805698005698005,
|
| 91000 |
+
"grad_norm": 0.22430749237537384,
|
| 91001 |
+
"learning_rate": 8.504316588307252e-06,
|
| 91002 |
+
"loss": 0.6879,
|
| 91003 |
+
"step": 12999
|
| 91004 |
+
},
|
| 91005 |
+
{
|
| 91006 |
+
"epoch": 14.806837606837608,
|
| 91007 |
+
"grad_norm": 0.22423458099365234,
|
| 91008 |
+
"learning_rate": 8.500815885716792e-06,
|
| 91009 |
+
"loss": 0.5246,
|
| 91010 |
+
"step": 13000
|
| 91011 |
+
},
|
| 91012 |
+
{
|
| 91013 |
+
"epoch": 14.807977207977208,
|
| 91014 |
+
"grad_norm": 0.2193293273448944,
|
| 91015 |
+
"learning_rate": 8.497315756188366e-06,
|
| 91016 |
+
"loss": 0.5874,
|
| 91017 |
+
"step": 13001
|
| 91018 |
+
},
|
| 91019 |
+
{
|
| 91020 |
+
"epoch": 14.809116809116809,
|
| 91021 |
+
"grad_norm": 0.23553064465522766,
|
| 91022 |
+
"learning_rate": 8.493816199843541e-06,
|
| 91023 |
+
"loss": 0.639,
|
| 91024 |
+
"step": 13002
|
| 91025 |
+
},
|
| 91026 |
+
{
|
| 91027 |
+
"epoch": 14.810256410256411,
|
| 91028 |
+
"grad_norm": 0.19212353229522705,
|
| 91029 |
+
"learning_rate": 8.490317216803872e-06,
|
| 91030 |
+
"loss": 0.5617,
|
| 91031 |
+
"step": 13003
|
| 91032 |
+
},
|
| 91033 |
+
{
|
| 91034 |
+
"epoch": 14.811396011396011,
|
| 91035 |
+
"grad_norm": 0.2506997883319855,
|
| 91036 |
+
"learning_rate": 8.486818807190897e-06,
|
| 91037 |
+
"loss": 0.4465,
|
| 91038 |
+
"step": 13004
|
| 91039 |
+
},
|
| 91040 |
+
{
|
| 91041 |
+
"epoch": 14.812535612535612,
|
| 91042 |
+
"grad_norm": 0.2890404462814331,
|
| 91043 |
+
"learning_rate": 8.483320971126098e-06,
|
| 91044 |
+
"loss": 0.2299,
|
| 91045 |
+
"step": 13005
|
| 91046 |
+
},
|
| 91047 |
+
{
|
| 91048 |
+
"epoch": 14.813675213675214,
|
| 91049 |
+
"grad_norm": 0.2695049047470093,
|
| 91050 |
+
"learning_rate": 8.479823708730994e-06,
|
| 91051 |
+
"loss": 0.4743,
|
| 91052 |
+
"step": 13006
|
| 91053 |
+
},
|
| 91054 |
+
{
|
| 91055 |
+
"epoch": 14.814814814814815,
|
| 91056 |
+
"grad_norm": 0.24549205601215363,
|
| 91057 |
+
"learning_rate": 8.47632702012705e-06,
|
| 91058 |
+
"loss": 0.6416,
|
| 91059 |
+
"step": 13007
|
| 91060 |
+
},
|
| 91061 |
+
{
|
| 91062 |
+
"epoch": 14.815954415954415,
|
| 91063 |
+
"grad_norm": 0.19436125457286835,
|
| 91064 |
+
"learning_rate": 8.472830905435703e-06,
|
| 91065 |
+
"loss": 0.6691,
|
| 91066 |
+
"step": 13008
|
| 91067 |
+
},
|
| 91068 |
+
{
|
| 91069 |
+
"epoch": 14.817094017094018,
|
| 91070 |
+
"grad_norm": 0.27004918456077576,
|
| 91071 |
+
"learning_rate": 8.469335364778385e-06,
|
| 91072 |
+
"loss": 0.619,
|
| 91073 |
+
"step": 13009
|
| 91074 |
+
},
|
| 91075 |
+
{
|
| 91076 |
+
"epoch": 14.818233618233618,
|
| 91077 |
+
"grad_norm": 0.22013430297374725,
|
| 91078 |
+
"learning_rate": 8.465840398276512e-06,
|
| 91079 |
+
"loss": 0.6623,
|
| 91080 |
+
"step": 13010
|
| 91081 |
+
},
|
| 91082 |
+
{
|
| 91083 |
+
"epoch": 14.819373219373219,
|
| 91084 |
+
"grad_norm": 0.21185335516929626,
|
| 91085 |
+
"learning_rate": 8.462346006051477e-06,
|
| 91086 |
+
"loss": 0.72,
|
| 91087 |
+
"step": 13011
|
| 91088 |
+
},
|
| 91089 |
+
{
|
| 91090 |
+
"epoch": 14.820512820512821,
|
| 91091 |
+
"grad_norm": 0.2211286723613739,
|
| 91092 |
+
"learning_rate": 8.458852188224636e-06,
|
| 91093 |
+
"loss": 0.7469,
|
| 91094 |
+
"step": 13012
|
| 91095 |
+
},
|
| 91096 |
+
{
|
| 91097 |
+
"epoch": 14.821652421652422,
|
| 91098 |
+
"grad_norm": 0.3561602234840393,
|
| 91099 |
+
"learning_rate": 8.455358944917349e-06,
|
| 91100 |
+
"loss": 0.563,
|
| 91101 |
+
"step": 13013
|
| 91102 |
+
},
|
| 91103 |
+
{
|
| 91104 |
+
"epoch": 14.822792022792022,
|
| 91105 |
+
"grad_norm": 0.28517386317253113,
|
| 91106 |
+
"learning_rate": 8.45186627625094e-06,
|
| 91107 |
+
"loss": 0.7062,
|
| 91108 |
+
"step": 13014
|
| 91109 |
+
},
|
| 91110 |
+
{
|
| 91111 |
+
"epoch": 14.823931623931625,
|
| 91112 |
+
"grad_norm": 0.20802541077136993,
|
| 91113 |
+
"learning_rate": 8.448374182346735e-06,
|
| 91114 |
+
"loss": 0.5973,
|
| 91115 |
+
"step": 13015
|
| 91116 |
+
},
|
| 91117 |
+
{
|
| 91118 |
+
"epoch": 14.825071225071225,
|
| 91119 |
+
"grad_norm": 0.23817268013954163,
|
| 91120 |
+
"learning_rate": 8.444882663325996e-06,
|
| 91121 |
+
"loss": 0.5042,
|
| 91122 |
+
"step": 13016
|
| 91123 |
+
},
|
| 91124 |
+
{
|
| 91125 |
+
"epoch": 14.826210826210826,
|
| 91126 |
+
"grad_norm": 0.20003987848758698,
|
| 91127 |
+
"learning_rate": 8.441391719310014e-06,
|
| 91128 |
+
"loss": 0.8336,
|
| 91129 |
+
"step": 13017
|
| 91130 |
+
},
|
| 91131 |
+
{
|
| 91132 |
+
"epoch": 14.827350427350428,
|
| 91133 |
+
"grad_norm": 0.21644364297389984,
|
| 91134 |
+
"learning_rate": 8.437901350420045e-06,
|
| 91135 |
+
"loss": 0.5737,
|
| 91136 |
+
"step": 13018
|
| 91137 |
+
},
|
| 91138 |
+
{
|
| 91139 |
+
"epoch": 14.828490028490029,
|
| 91140 |
+
"grad_norm": 0.20241820812225342,
|
| 91141 |
+
"learning_rate": 8.434411556777294e-06,
|
| 91142 |
+
"loss": 0.828,
|
| 91143 |
+
"step": 13019
|
| 91144 |
+
},
|
| 91145 |
+
{
|
| 91146 |
+
"epoch": 14.829629629629629,
|
| 91147 |
+
"grad_norm": 0.21604406833648682,
|
| 91148 |
+
"learning_rate": 8.430922338502991e-06,
|
| 91149 |
+
"loss": 0.5363,
|
| 91150 |
+
"step": 13020
|
| 91151 |
+
},
|
| 91152 |
+
{
|
| 91153 |
+
"epoch": 14.830769230769231,
|
| 91154 |
+
"grad_norm": 0.19081199169158936,
|
| 91155 |
+
"learning_rate": 8.427433695718318e-06,
|
| 91156 |
+
"loss": 0.5969,
|
| 91157 |
+
"step": 13021
|
| 91158 |
+
},
|
| 91159 |
+
{
|
| 91160 |
+
"epoch": 14.831908831908832,
|
| 91161 |
+
"grad_norm": 0.22546574473381042,
|
| 91162 |
+
"learning_rate": 8.423945628544455e-06,
|
| 91163 |
+
"loss": 0.427,
|
| 91164 |
+
"step": 13022
|
| 91165 |
+
},
|
| 91166 |
+
{
|
| 91167 |
+
"epoch": 14.833048433048432,
|
| 91168 |
+
"grad_norm": 0.25194093585014343,
|
| 91169 |
+
"learning_rate": 8.420458137102539e-06,
|
| 91170 |
+
"loss": 0.3672,
|
| 91171 |
+
"step": 13023
|
| 91172 |
+
},
|
| 91173 |
+
{
|
| 91174 |
+
"epoch": 14.834188034188035,
|
| 91175 |
+
"grad_norm": 0.19357764720916748,
|
| 91176 |
+
"learning_rate": 8.416971221513703e-06,
|
| 91177 |
+
"loss": 0.6002,
|
| 91178 |
+
"step": 13024
|
| 91179 |
+
},
|
| 91180 |
+
{
|
| 91181 |
+
"epoch": 14.835327635327635,
|
| 91182 |
+
"grad_norm": 0.20514234900474548,
|
| 91183 |
+
"learning_rate": 8.41348488189906e-06,
|
| 91184 |
+
"loss": 0.6676,
|
| 91185 |
+
"step": 13025
|
| 91186 |
+
},
|
| 91187 |
+
{
|
| 91188 |
+
"epoch": 14.836467236467236,
|
| 91189 |
+
"grad_norm": 0.24507999420166016,
|
| 91190 |
+
"learning_rate": 8.40999911837971e-06,
|
| 91191 |
+
"loss": 0.6282,
|
| 91192 |
+
"step": 13026
|
| 91193 |
+
},
|
| 91194 |
+
{
|
| 91195 |
+
"epoch": 14.837606837606838,
|
| 91196 |
+
"grad_norm": 0.2528490126132965,
|
| 91197 |
+
"learning_rate": 8.406513931076699e-06,
|
| 91198 |
+
"loss": 0.6174,
|
| 91199 |
+
"step": 13027
|
| 91200 |
+
},
|
| 91201 |
+
{
|
| 91202 |
+
"epoch": 14.838746438746439,
|
| 91203 |
+
"grad_norm": 0.19692501425743103,
|
| 91204 |
+
"learning_rate": 8.403029320111096e-06,
|
| 91205 |
+
"loss": 0.7863,
|
| 91206 |
+
"step": 13028
|
| 91207 |
+
},
|
| 91208 |
+
{
|
| 91209 |
+
"epoch": 14.83988603988604,
|
| 91210 |
+
"grad_norm": 0.21329069137573242,
|
| 91211 |
+
"learning_rate": 8.399545285603927e-06,
|
| 91212 |
+
"loss": 0.7401,
|
| 91213 |
+
"step": 13029
|
| 91214 |
+
},
|
| 91215 |
+
{
|
| 91216 |
+
"epoch": 14.841025641025642,
|
| 91217 |
+
"grad_norm": 0.2121441662311554,
|
| 91218 |
+
"learning_rate": 8.39606182767621e-06,
|
| 91219 |
+
"loss": 0.7027,
|
| 91220 |
+
"step": 13030
|
| 91221 |
+
},
|
| 91222 |
+
{
|
| 91223 |
+
"epoch": 14.842165242165242,
|
| 91224 |
+
"grad_norm": 0.19697655737400055,
|
| 91225 |
+
"learning_rate": 8.39257894644892e-06,
|
| 91226 |
+
"loss": 0.6129,
|
| 91227 |
+
"step": 13031
|
| 91228 |
+
},
|
| 91229 |
+
{
|
| 91230 |
+
"epoch": 14.843304843304843,
|
| 91231 |
+
"grad_norm": 0.22422295808792114,
|
| 91232 |
+
"learning_rate": 8.389096642043034e-06,
|
| 91233 |
+
"loss": 0.6316,
|
| 91234 |
+
"step": 13032
|
| 91235 |
+
},
|
| 91236 |
+
{
|
| 91237 |
+
"epoch": 14.844444444444445,
|
| 91238 |
+
"grad_norm": 0.19399236142635345,
|
| 91239 |
+
"learning_rate": 8.385614914579501e-06,
|
| 91240 |
+
"loss": 0.715,
|
| 91241 |
+
"step": 13033
|
| 91242 |
+
},
|
| 91243 |
+
{
|
| 91244 |
+
"epoch": 14.845584045584046,
|
| 91245 |
+
"grad_norm": 0.22976943850517273,
|
| 91246 |
+
"learning_rate": 8.382133764179258e-06,
|
| 91247 |
+
"loss": 0.6337,
|
| 91248 |
+
"step": 13034
|
| 91249 |
+
},
|
| 91250 |
+
{
|
| 91251 |
+
"epoch": 14.846723646723646,
|
| 91252 |
+
"grad_norm": 0.22685664892196655,
|
| 91253 |
+
"learning_rate": 8.378653190963203e-06,
|
| 91254 |
+
"loss": 0.8493,
|
| 91255 |
+
"step": 13035
|
| 91256 |
+
},
|
| 91257 |
+
{
|
| 91258 |
+
"epoch": 14.847863247863248,
|
| 91259 |
+
"grad_norm": 0.21823418140411377,
|
| 91260 |
+
"learning_rate": 8.37517319505223e-06,
|
| 91261 |
+
"loss": 0.598,
|
| 91262 |
+
"step": 13036
|
| 91263 |
+
},
|
| 91264 |
+
{
|
| 91265 |
+
"epoch": 14.849002849002849,
|
| 91266 |
+
"grad_norm": 0.18279263377189636,
|
| 91267 |
+
"learning_rate": 8.37169377656721e-06,
|
| 91268 |
+
"loss": 0.7885,
|
| 91269 |
+
"step": 13037
|
| 91270 |
+
},
|
| 91271 |
+
{
|
| 91272 |
+
"epoch": 14.85014245014245,
|
| 91273 |
+
"grad_norm": 0.17645741999149323,
|
| 91274 |
+
"learning_rate": 8.368214935628996e-06,
|
| 91275 |
+
"loss": 0.6113,
|
| 91276 |
+
"step": 13038
|
| 91277 |
+
},
|
| 91278 |
+
{
|
| 91279 |
+
"epoch": 14.851282051282052,
|
| 91280 |
+
"grad_norm": 0.20534776151180267,
|
| 91281 |
+
"learning_rate": 8.36473667235841e-06,
|
| 91282 |
+
"loss": 0.5682,
|
| 91283 |
+
"step": 13039
|
| 91284 |
+
},
|
| 91285 |
+
{
|
| 91286 |
+
"epoch": 14.852421652421652,
|
| 91287 |
+
"grad_norm": 0.21249881386756897,
|
| 91288 |
+
"learning_rate": 8.361258986876272e-06,
|
| 91289 |
+
"loss": 0.6571,
|
| 91290 |
+
"step": 13040
|
| 91291 |
+
},
|
| 91292 |
+
{
|
| 91293 |
+
"epoch": 14.853561253561253,
|
| 91294 |
+
"grad_norm": 0.2308804839849472,
|
| 91295 |
+
"learning_rate": 8.357781879303372e-06,
|
| 91296 |
+
"loss": 0.6684,
|
| 91297 |
+
"step": 13041
|
| 91298 |
+
},
|
| 91299 |
+
{
|
| 91300 |
+
"epoch": 14.854700854700855,
|
| 91301 |
+
"grad_norm": 0.20016048848628998,
|
| 91302 |
+
"learning_rate": 8.354305349760466e-06,
|
| 91303 |
+
"loss": 0.7256,
|
| 91304 |
+
"step": 13042
|
| 91305 |
+
},
|
| 91306 |
+
{
|
| 91307 |
+
"epoch": 14.855840455840456,
|
| 91308 |
+
"grad_norm": 0.19493573904037476,
|
| 91309 |
+
"learning_rate": 8.35082939836831e-06,
|
| 91310 |
+
"loss": 0.8461,
|
| 91311 |
+
"step": 13043
|
| 91312 |
+
},
|
| 91313 |
+
{
|
| 91314 |
+
"epoch": 14.856980056980056,
|
| 91315 |
+
"grad_norm": 0.19311264157295227,
|
| 91316 |
+
"learning_rate": 8.347354025247633e-06,
|
| 91317 |
+
"loss": 0.6911,
|
| 91318 |
+
"step": 13044
|
| 91319 |
+
},
|
| 91320 |
+
{
|
| 91321 |
+
"epoch": 14.858119658119659,
|
| 91322 |
+
"grad_norm": 0.2238873988389969,
|
| 91323 |
+
"learning_rate": 8.343879230519158e-06,
|
| 91324 |
+
"loss": 0.4791,
|
| 91325 |
+
"step": 13045
|
| 91326 |
+
},
|
| 91327 |
+
{
|
| 91328 |
+
"epoch": 14.85925925925926,
|
| 91329 |
+
"grad_norm": 0.1901557743549347,
|
| 91330 |
+
"learning_rate": 8.340405014303552e-06,
|
| 91331 |
+
"loss": 0.5558,
|
| 91332 |
+
"step": 13046
|
| 91333 |
+
},
|
| 91334 |
+
{
|
| 91335 |
+
"epoch": 14.86039886039886,
|
| 91336 |
+
"grad_norm": 0.20459187030792236,
|
| 91337 |
+
"learning_rate": 8.336931376721491e-06,
|
| 91338 |
+
"loss": 0.6601,
|
| 91339 |
+
"step": 13047
|
| 91340 |
+
},
|
| 91341 |
+
{
|
| 91342 |
+
"epoch": 14.861538461538462,
|
| 91343 |
+
"grad_norm": 0.21996235847473145,
|
| 91344 |
+
"learning_rate": 8.333458317893631e-06,
|
| 91345 |
+
"loss": 0.5077,
|
| 91346 |
+
"step": 13048
|
| 91347 |
+
},
|
| 91348 |
+
{
|
| 91349 |
+
"epoch": 14.862678062678063,
|
| 91350 |
+
"grad_norm": 0.18952824175357819,
|
| 91351 |
+
"learning_rate": 8.329985837940593e-06,
|
| 91352 |
+
"loss": 0.5322,
|
| 91353 |
+
"step": 13049
|
| 91354 |
+
},
|
| 91355 |
+
{
|
| 91356 |
+
"epoch": 14.863817663817663,
|
| 91357 |
+
"grad_norm": 0.1865224987268448,
|
| 91358 |
+
"learning_rate": 8.32651393698299e-06,
|
| 91359 |
+
"loss": 0.6469,
|
| 91360 |
+
"step": 13050
|
| 91361 |
+
},
|
| 91362 |
+
{
|
| 91363 |
+
"epoch": 14.864957264957265,
|
| 91364 |
+
"grad_norm": 0.18879809975624084,
|
| 91365 |
+
"learning_rate": 8.323042615141413e-06,
|
| 91366 |
+
"loss": 0.731,
|
| 91367 |
+
"step": 13051
|
| 91368 |
+
},
|
| 91369 |
+
{
|
| 91370 |
+
"epoch": 14.866096866096866,
|
| 91371 |
+
"grad_norm": 0.18550975620746613,
|
| 91372 |
+
"learning_rate": 8.319571872536437e-06,
|
| 91373 |
+
"loss": 0.5353,
|
| 91374 |
+
"step": 13052
|
| 91375 |
+
},
|
| 91376 |
+
{
|
| 91377 |
+
"epoch": 14.867236467236467,
|
| 91378 |
+
"grad_norm": 0.17426526546478271,
|
| 91379 |
+
"learning_rate": 8.316101709288588e-06,
|
| 91380 |
+
"loss": 0.8389,
|
| 91381 |
+
"step": 13053
|
| 91382 |
+
},
|
| 91383 |
+
{
|
| 91384 |
+
"epoch": 14.868376068376069,
|
| 91385 |
+
"grad_norm": 0.18053342401981354,
|
| 91386 |
+
"learning_rate": 8.31263212551841e-06,
|
| 91387 |
+
"loss": 0.8319,
|
| 91388 |
+
"step": 13054
|
| 91389 |
+
},
|
| 91390 |
+
{
|
| 91391 |
+
"epoch": 14.86951566951567,
|
| 91392 |
+
"grad_norm": 0.23310673236846924,
|
| 91393 |
+
"learning_rate": 8.309163121346408e-06,
|
| 91394 |
+
"loss": 0.5109,
|
| 91395 |
+
"step": 13055
|
| 91396 |
+
},
|
| 91397 |
+
{
|
| 91398 |
+
"epoch": 14.87065527065527,
|
| 91399 |
+
"grad_norm": 0.16054700314998627,
|
| 91400 |
+
"learning_rate": 8.305694696893082e-06,
|
| 91401 |
+
"loss": 0.7403,
|
| 91402 |
+
"step": 13056
|
| 91403 |
+
},
|
| 91404 |
+
{
|
| 91405 |
+
"epoch": 14.871794871794872,
|
| 91406 |
+
"grad_norm": 0.20461927354335785,
|
| 91407 |
+
"learning_rate": 8.302226852278877e-06,
|
| 91408 |
+
"loss": 0.7519,
|
| 91409 |
+
"step": 13057
|
| 91410 |
+
},
|
| 91411 |
+
{
|
| 91412 |
+
"epoch": 14.872934472934473,
|
| 91413 |
+
"grad_norm": 0.2121797502040863,
|
| 91414 |
+
"learning_rate": 8.298759587624256e-06,
|
| 91415 |
+
"loss": 0.7163,
|
| 91416 |
+
"step": 13058
|
| 91417 |
+
},
|
| 91418 |
+
{
|
| 91419 |
+
"epoch": 14.874074074074073,
|
| 91420 |
+
"grad_norm": 0.2598489224910736,
|
| 91421 |
+
"learning_rate": 8.29529290304964e-06,
|
| 91422 |
+
"loss": 0.6562,
|
| 91423 |
+
"step": 13059
|
| 91424 |
+
},
|
| 91425 |
+
{
|
| 91426 |
+
"epoch": 14.875213675213676,
|
| 91427 |
+
"grad_norm": 0.22083567082881927,
|
| 91428 |
+
"learning_rate": 8.29182679867544e-06,
|
| 91429 |
+
"loss": 0.6853,
|
| 91430 |
+
"step": 13060
|
| 91431 |
+
},
|
| 91432 |
+
{
|
| 91433 |
+
"epoch": 14.876353276353276,
|
| 91434 |
+
"grad_norm": 0.19808152318000793,
|
| 91435 |
+
"learning_rate": 8.288361274622042e-06,
|
| 91436 |
+
"loss": 0.6148,
|
| 91437 |
+
"step": 13061
|
| 91438 |
+
},
|
| 91439 |
+
{
|
| 91440 |
+
"epoch": 14.877492877492877,
|
| 91441 |
+
"grad_norm": 0.19256912171840668,
|
| 91442 |
+
"learning_rate": 8.284896331009817e-06,
|
| 91443 |
+
"loss": 0.5713,
|
| 91444 |
+
"step": 13062
|
| 91445 |
+
},
|
| 91446 |
+
{
|
| 91447 |
+
"epoch": 14.878632478632479,
|
| 91448 |
+
"grad_norm": 0.18643289804458618,
|
| 91449 |
+
"learning_rate": 8.281431967959108e-06,
|
| 91450 |
+
"loss": 0.8897,
|
| 91451 |
+
"step": 13063
|
| 91452 |
+
},
|
| 91453 |
+
{
|
| 91454 |
+
"epoch": 14.87977207977208,
|
| 91455 |
+
"grad_norm": 0.2128099799156189,
|
| 91456 |
+
"learning_rate": 8.277968185590252e-06,
|
| 91457 |
+
"loss": 0.7361,
|
| 91458 |
+
"step": 13064
|
| 91459 |
+
},
|
| 91460 |
+
{
|
| 91461 |
+
"epoch": 14.88091168091168,
|
| 91462 |
+
"grad_norm": 0.18543875217437744,
|
| 91463 |
+
"learning_rate": 8.274504984023534e-06,
|
| 91464 |
+
"loss": 0.7431,
|
| 91465 |
+
"step": 13065
|
| 91466 |
+
},
|
| 91467 |
+
{
|
| 91468 |
+
"epoch": 14.882051282051282,
|
| 91469 |
+
"grad_norm": 0.2094191014766693,
|
| 91470 |
+
"learning_rate": 8.271042363379258e-06,
|
| 91471 |
+
"loss": 0.6611,
|
| 91472 |
+
"step": 13066
|
| 91473 |
+
},
|
| 91474 |
+
{
|
| 91475 |
+
"epoch": 14.883190883190883,
|
| 91476 |
+
"grad_norm": 0.22779624164104462,
|
| 91477 |
+
"learning_rate": 8.267580323777686e-06,
|
| 91478 |
+
"loss": 0.6232,
|
| 91479 |
+
"step": 13067
|
| 91480 |
+
},
|
| 91481 |
+
{
|
| 91482 |
+
"epoch": 14.884330484330484,
|
| 91483 |
+
"grad_norm": 0.1786550134420395,
|
| 91484 |
+
"learning_rate": 8.264118865339068e-06,
|
| 91485 |
+
"loss": 0.7023,
|
| 91486 |
+
"step": 13068
|
| 91487 |
+
},
|
| 91488 |
+
{
|
| 91489 |
+
"epoch": 14.885470085470086,
|
| 91490 |
+
"grad_norm": 0.20286069810390472,
|
| 91491 |
+
"learning_rate": 8.26065798818362e-06,
|
| 91492 |
+
"loss": 0.7334,
|
| 91493 |
+
"step": 13069
|
| 91494 |
+
},
|
| 91495 |
+
{
|
| 91496 |
+
"epoch": 14.886609686609686,
|
| 91497 |
+
"grad_norm": 0.23107458651065826,
|
| 91498 |
+
"learning_rate": 8.257197692431553e-06,
|
| 91499 |
+
"loss": 0.5261,
|
| 91500 |
+
"step": 13070
|
| 91501 |
+
},
|
| 91502 |
+
{
|
| 91503 |
+
"epoch": 14.887749287749287,
|
| 91504 |
+
"grad_norm": 0.2501099705696106,
|
| 91505 |
+
"learning_rate": 8.253737978203051e-06,
|
| 91506 |
+
"loss": 0.6518,
|
| 91507 |
+
"step": 13071
|
| 91508 |
+
},
|
| 91509 |
+
{
|
| 91510 |
+
"epoch": 14.88888888888889,
|
| 91511 |
+
"grad_norm": 0.26554644107818604,
|
| 91512 |
+
"learning_rate": 8.250278845618283e-06,
|
| 91513 |
+
"loss": 0.5686,
|
| 91514 |
+
"step": 13072
|
| 91515 |
+
},
|
| 91516 |
+
{
|
| 91517 |
+
"epoch": 14.89002849002849,
|
| 91518 |
+
"grad_norm": 0.20167513191699982,
|
| 91519 |
+
"learning_rate": 8.246820294797395e-06,
|
| 91520 |
+
"loss": 0.7667,
|
| 91521 |
+
"step": 13073
|
| 91522 |
+
},
|
| 91523 |
+
{
|
| 91524 |
+
"epoch": 14.89116809116809,
|
| 91525 |
+
"grad_norm": 0.2177019864320755,
|
| 91526 |
+
"learning_rate": 8.243362325860508e-06,
|
| 91527 |
+
"loss": 0.7147,
|
| 91528 |
+
"step": 13074
|
| 91529 |
+
},
|
| 91530 |
+
{
|
| 91531 |
+
"epoch": 14.892307692307693,
|
| 91532 |
+
"grad_norm": 0.19998271763324738,
|
| 91533 |
+
"learning_rate": 8.239904938927736e-06,
|
| 91534 |
+
"loss": 0.8471,
|
| 91535 |
+
"step": 13075
|
| 91536 |
+
},
|
| 91537 |
+
{
|
| 91538 |
+
"epoch": 14.893447293447293,
|
| 91539 |
+
"grad_norm": 0.23724326491355896,
|
| 91540 |
+
"learning_rate": 8.236448134119149e-06,
|
| 91541 |
+
"loss": 0.6115,
|
| 91542 |
+
"step": 13076
|
| 91543 |
+
},
|
| 91544 |
+
{
|
| 91545 |
+
"epoch": 14.894586894586894,
|
| 91546 |
+
"grad_norm": 0.19616632163524628,
|
| 91547 |
+
"learning_rate": 8.232991911554816e-06,
|
| 91548 |
+
"loss": 0.6234,
|
| 91549 |
+
"step": 13077
|
| 91550 |
+
},
|
| 91551 |
+
{
|
| 91552 |
+
"epoch": 14.895726495726496,
|
| 91553 |
+
"grad_norm": 0.2279236912727356,
|
| 91554 |
+
"learning_rate": 8.229536271354785e-06,
|
| 91555 |
+
"loss": 0.6154,
|
| 91556 |
+
"step": 13078
|
| 91557 |
+
},
|
| 91558 |
+
{
|
| 91559 |
+
"epoch": 14.896866096866097,
|
| 91560 |
+
"grad_norm": 0.2267291247844696,
|
| 91561 |
+
"learning_rate": 8.226081213639084e-06,
|
| 91562 |
+
"loss": 0.8262,
|
| 91563 |
+
"step": 13079
|
| 91564 |
+
},
|
| 91565 |
+
{
|
| 91566 |
+
"epoch": 14.898005698005697,
|
| 91567 |
+
"grad_norm": 0.1714223027229309,
|
| 91568 |
+
"learning_rate": 8.222626738527706e-06,
|
| 91569 |
+
"loss": 0.5915,
|
| 91570 |
+
"step": 13080
|
| 91571 |
+
},
|
| 91572 |
+
{
|
| 91573 |
+
"epoch": 14.8991452991453,
|
| 91574 |
+
"grad_norm": 0.1930173635482788,
|
| 91575 |
+
"learning_rate": 8.219172846140638e-06,
|
| 91576 |
+
"loss": 0.5572,
|
| 91577 |
+
"step": 13081
|
| 91578 |
+
},
|
| 91579 |
+
{
|
| 91580 |
+
"epoch": 14.9002849002849,
|
| 91581 |
+
"grad_norm": 0.25991231203079224,
|
| 91582 |
+
"learning_rate": 8.215719536597844e-06,
|
| 91583 |
+
"loss": 0.6455,
|
| 91584 |
+
"step": 13082
|
| 91585 |
+
},
|
| 91586 |
+
{
|
| 91587 |
+
"epoch": 14.9014245014245,
|
| 91588 |
+
"grad_norm": 0.18016129732131958,
|
| 91589 |
+
"learning_rate": 8.212266810019267e-06,
|
| 91590 |
+
"loss": 0.6232,
|
| 91591 |
+
"step": 13083
|
| 91592 |
+
},
|
| 91593 |
+
{
|
| 91594 |
+
"epoch": 14.902564102564103,
|
| 91595 |
+
"grad_norm": 0.22624294459819794,
|
| 91596 |
+
"learning_rate": 8.20881466652483e-06,
|
| 91597 |
+
"loss": 0.6423,
|
| 91598 |
+
"step": 13084
|
| 91599 |
+
},
|
| 91600 |
+
{
|
| 91601 |
+
"epoch": 14.903703703703703,
|
| 91602 |
+
"grad_norm": 0.19937890768051147,
|
| 91603 |
+
"learning_rate": 8.205363106234437e-06,
|
| 91604 |
+
"loss": 0.7158,
|
| 91605 |
+
"step": 13085
|
| 91606 |
+
},
|
| 91607 |
+
{
|
| 91608 |
+
"epoch": 14.904843304843304,
|
| 91609 |
+
"grad_norm": 0.26309749484062195,
|
| 91610 |
+
"learning_rate": 8.201912129267978e-06,
|
| 91611 |
+
"loss": 0.5991,
|
| 91612 |
+
"step": 13086
|
| 91613 |
+
},
|
| 91614 |
+
{
|
| 91615 |
+
"epoch": 14.905982905982906,
|
| 91616 |
+
"grad_norm": 0.23269060254096985,
|
| 91617 |
+
"learning_rate": 8.198461735745294e-06,
|
| 91618 |
+
"loss": 0.7014,
|
| 91619 |
+
"step": 13087
|
| 91620 |
+
},
|
| 91621 |
+
{
|
| 91622 |
+
"epoch": 14.907122507122507,
|
| 91623 |
+
"grad_norm": 0.19453437626361847,
|
| 91624 |
+
"learning_rate": 8.195011925786243e-06,
|
| 91625 |
+
"loss": 0.8058,
|
| 91626 |
+
"step": 13088
|
| 91627 |
+
},
|
| 91628 |
+
{
|
| 91629 |
+
"epoch": 14.908262108262107,
|
| 91630 |
+
"grad_norm": 0.2564391493797302,
|
| 91631 |
+
"learning_rate": 8.191562699510639e-06,
|
| 91632 |
+
"loss": 0.537,
|
| 91633 |
+
"step": 13089
|
| 91634 |
+
},
|
| 91635 |
+
{
|
| 91636 |
+
"epoch": 14.90940170940171,
|
| 91637 |
+
"grad_norm": 0.19253656268119812,
|
| 91638 |
+
"learning_rate": 8.188114057038293e-06,
|
| 91639 |
+
"loss": 0.5394,
|
| 91640 |
+
"step": 13090
|
| 91641 |
+
},
|
| 91642 |
+
{
|
| 91643 |
+
"epoch": 14.91054131054131,
|
| 91644 |
+
"grad_norm": 0.17925649881362915,
|
| 91645 |
+
"learning_rate": 8.184665998488971e-06,
|
| 91646 |
+
"loss": 0.817,
|
| 91647 |
+
"step": 13091
|
| 91648 |
+
},
|
| 91649 |
+
{
|
| 91650 |
+
"epoch": 14.91168091168091,
|
| 91651 |
+
"grad_norm": 0.23220553994178772,
|
| 91652 |
+
"learning_rate": 8.181218523982443e-06,
|
| 91653 |
+
"loss": 0.6122,
|
| 91654 |
+
"step": 13092
|
| 91655 |
+
},
|
| 91656 |
+
{
|
| 91657 |
+
"epoch": 14.912820512820513,
|
| 91658 |
+
"grad_norm": 0.2346821129322052,
|
| 91659 |
+
"learning_rate": 8.177771633638445e-06,
|
| 91660 |
+
"loss": 0.6432,
|
| 91661 |
+
"step": 13093
|
| 91662 |
+
},
|
| 91663 |
+
{
|
| 91664 |
+
"epoch": 14.913960113960114,
|
| 91665 |
+
"grad_norm": 0.2243751585483551,
|
| 91666 |
+
"learning_rate": 8.174325327576701e-06,
|
| 91667 |
+
"loss": 0.6897,
|
| 91668 |
+
"step": 13094
|
| 91669 |
+
},
|
| 91670 |
+
{
|
| 91671 |
+
"epoch": 14.915099715099714,
|
| 91672 |
+
"grad_norm": 0.1665022224187851,
|
| 91673 |
+
"learning_rate": 8.170879605916909e-06,
|
| 91674 |
+
"loss": 0.9448,
|
| 91675 |
+
"step": 13095
|
| 91676 |
+
},
|
| 91677 |
+
{
|
| 91678 |
+
"epoch": 14.916239316239317,
|
| 91679 |
+
"grad_norm": 0.21701228618621826,
|
| 91680 |
+
"learning_rate": 8.167434468778749e-06,
|
| 91681 |
+
"loss": 0.59,
|
| 91682 |
+
"step": 13096
|
| 91683 |
+
},
|
| 91684 |
+
{
|
| 91685 |
+
"epoch": 14.917378917378917,
|
| 91686 |
+
"grad_norm": 0.20046526193618774,
|
| 91687 |
+
"learning_rate": 8.163989916281885e-06,
|
| 91688 |
+
"loss": 0.5072,
|
| 91689 |
+
"step": 13097
|
| 91690 |
+
},
|
| 91691 |
+
{
|
| 91692 |
+
"epoch": 14.918518518518518,
|
| 91693 |
+
"grad_norm": 0.2463109791278839,
|
| 91694 |
+
"learning_rate": 8.160545948545945e-06,
|
| 91695 |
+
"loss": 0.4702,
|
| 91696 |
+
"step": 13098
|
| 91697 |
+
},
|
| 91698 |
+
{
|
| 91699 |
+
"epoch": 14.91965811965812,
|
| 91700 |
+
"grad_norm": 0.19561436772346497,
|
| 91701 |
+
"learning_rate": 8.157102565690553e-06,
|
| 91702 |
+
"loss": 0.5023,
|
| 91703 |
+
"step": 13099
|
| 91704 |
+
},
|
| 91705 |
+
{
|
| 91706 |
+
"epoch": 14.92079772079772,
|
| 91707 |
+
"grad_norm": 0.21838906407356262,
|
| 91708 |
+
"learning_rate": 8.153659767835306e-06,
|
| 91709 |
+
"loss": 0.6128,
|
| 91710 |
+
"step": 13100
|
| 91711 |
+
},
|
| 91712 |
+
{
|
| 91713 |
+
"epoch": 14.921937321937321,
|
| 91714 |
+
"grad_norm": 0.2385895699262619,
|
| 91715 |
+
"learning_rate": 8.15021755509979e-06,
|
| 91716 |
+
"loss": 0.6217,
|
| 91717 |
+
"step": 13101
|
| 91718 |
+
},
|
| 91719 |
+
{
|
| 91720 |
+
"epoch": 14.923076923076923,
|
| 91721 |
+
"grad_norm": 0.1635356992483139,
|
| 91722 |
+
"learning_rate": 8.146775927603551e-06,
|
| 91723 |
+
"loss": 0.7619,
|
| 91724 |
+
"step": 13102
|
| 91725 |
+
},
|
| 91726 |
+
{
|
| 91727 |
+
"epoch": 14.924216524216524,
|
| 91728 |
+
"grad_norm": 0.20667387545108795,
|
| 91729 |
+
"learning_rate": 8.143334885466127e-06,
|
| 91730 |
+
"loss": 0.7719,
|
| 91731 |
+
"step": 13103
|
| 91732 |
+
},
|
| 91733 |
+
{
|
| 91734 |
+
"epoch": 14.925356125356124,
|
| 91735 |
+
"grad_norm": 0.19133946299552917,
|
| 91736 |
+
"learning_rate": 8.139894428807033e-06,
|
| 91737 |
+
"loss": 0.7622,
|
| 91738 |
+
"step": 13104
|
| 91739 |
+
},
|
| 91740 |
+
{
|
| 91741 |
+
"epoch": 14.926495726495727,
|
| 91742 |
+
"grad_norm": 0.5747365355491638,
|
| 91743 |
+
"learning_rate": 8.136454557745785e-06,
|
| 91744 |
+
"loss": 0.8878,
|
| 91745 |
+
"step": 13105
|
| 91746 |
+
},
|
| 91747 |
+
{
|
| 91748 |
+
"epoch": 14.927635327635327,
|
| 91749 |
+
"grad_norm": 0.24037352204322815,
|
| 91750 |
+
"learning_rate": 8.133015272401836e-06,
|
| 91751 |
+
"loss": 0.5662,
|
| 91752 |
+
"step": 13106
|
| 91753 |
+
},
|
| 91754 |
+
{
|
| 91755 |
+
"epoch": 14.928774928774928,
|
| 91756 |
+
"grad_norm": 0.2153923362493515,
|
| 91757 |
+
"learning_rate": 8.129576572894654e-06,
|
| 91758 |
+
"loss": 0.644,
|
| 91759 |
+
"step": 13107
|
| 91760 |
+
},
|
| 91761 |
+
{
|
| 91762 |
+
"epoch": 14.92991452991453,
|
| 91763 |
+
"grad_norm": 0.23597195744514465,
|
| 91764 |
+
"learning_rate": 8.126138459343669e-06,
|
| 91765 |
+
"loss": 0.6726,
|
| 91766 |
+
"step": 13108
|
| 91767 |
+
},
|
| 91768 |
+
{
|
| 91769 |
+
"epoch": 14.93105413105413,
|
| 91770 |
+
"grad_norm": 0.23389115929603577,
|
| 91771 |
+
"learning_rate": 8.122700931868307e-06,
|
| 91772 |
+
"loss": 0.7252,
|
| 91773 |
+
"step": 13109
|
| 91774 |
+
},
|
| 91775 |
+
{
|
| 91776 |
+
"epoch": 14.932193732193731,
|
| 91777 |
+
"grad_norm": 0.18410557508468628,
|
| 91778 |
+
"learning_rate": 8.11926399058795e-06,
|
| 91779 |
+
"loss": 0.8647,
|
| 91780 |
+
"step": 13110
|
| 91781 |
+
},
|
| 91782 |
+
{
|
| 91783 |
+
"epoch": 14.933333333333334,
|
| 91784 |
+
"grad_norm": 0.16643090546131134,
|
| 91785 |
+
"learning_rate": 8.115827635621972e-06,
|
| 91786 |
+
"loss": 0.6601,
|
| 91787 |
+
"step": 13111
|
| 91788 |
+
},
|
| 91789 |
+
{
|
| 91790 |
+
"epoch": 14.934472934472934,
|
| 91791 |
+
"grad_norm": 0.25036999583244324,
|
| 91792 |
+
"learning_rate": 8.112391867089733e-06,
|
| 91793 |
+
"loss": 0.7001,
|
| 91794 |
+
"step": 13112
|
| 91795 |
+
},
|
| 91796 |
+
{
|
| 91797 |
+
"epoch": 14.935612535612536,
|
| 91798 |
+
"grad_norm": 0.24862360954284668,
|
| 91799 |
+
"learning_rate": 8.108956685110574e-06,
|
| 91800 |
+
"loss": 0.5775,
|
| 91801 |
+
"step": 13113
|
| 91802 |
+
},
|
| 91803 |
+
{
|
| 91804 |
+
"epoch": 14.936752136752137,
|
| 91805 |
+
"grad_norm": 0.22571787238121033,
|
| 91806 |
+
"learning_rate": 8.105522089803794e-06,
|
| 91807 |
+
"loss": 0.8268,
|
| 91808 |
+
"step": 13114
|
| 91809 |
+
},
|
| 91810 |
+
{
|
| 91811 |
+
"epoch": 14.937891737891738,
|
| 91812 |
+
"grad_norm": 0.1795872151851654,
|
| 91813 |
+
"learning_rate": 8.10208808128868e-06,
|
| 91814 |
+
"loss": 0.884,
|
| 91815 |
+
"step": 13115
|
| 91816 |
+
},
|
| 91817 |
+
{
|
| 91818 |
+
"epoch": 14.93903133903134,
|
| 91819 |
+
"grad_norm": 0.24070943892002106,
|
| 91820 |
+
"learning_rate": 8.098654659684538e-06,
|
| 91821 |
+
"loss": 0.7474,
|
| 91822 |
+
"step": 13116
|
| 91823 |
+
},
|
| 91824 |
+
{
|
| 91825 |
+
"epoch": 14.94017094017094,
|
| 91826 |
+
"grad_norm": 0.3789416551589966,
|
| 91827 |
+
"learning_rate": 8.095221825110585e-06,
|
| 91828 |
+
"loss": 0.7326,
|
| 91829 |
+
"step": 13117
|
| 91830 |
+
},
|
| 91831 |
+
{
|
| 91832 |
+
"epoch": 14.941310541310541,
|
| 91833 |
+
"grad_norm": 0.3040759563446045,
|
| 91834 |
+
"learning_rate": 8.091789577686068e-06,
|
| 91835 |
+
"loss": 0.36,
|
| 91836 |
+
"step": 13118
|
| 91837 |
+
},
|
| 91838 |
+
{
|
| 91839 |
+
"epoch": 14.942450142450143,
|
| 91840 |
+
"grad_norm": 0.20012761652469635,
|
| 91841 |
+
"learning_rate": 8.088357917530198e-06,
|
| 91842 |
+
"loss": 0.5821,
|
| 91843 |
+
"step": 13119
|
| 91844 |
+
},
|
| 91845 |
+
{
|
| 91846 |
+
"epoch": 14.943589743589744,
|
| 91847 |
+
"grad_norm": 0.2004968374967575,
|
| 91848 |
+
"learning_rate": 8.084926844762173e-06,
|
| 91849 |
+
"loss": 0.7867,
|
| 91850 |
+
"step": 13120
|
| 91851 |
+
},
|
| 91852 |
+
{
|
| 91853 |
+
"epoch": 14.944729344729344,
|
| 91854 |
+
"grad_norm": 0.24345803260803223,
|
| 91855 |
+
"learning_rate": 8.081496359501145e-06,
|
| 91856 |
+
"loss": 0.6358,
|
| 91857 |
+
"step": 13121
|
| 91858 |
+
},
|
| 91859 |
+
{
|
| 91860 |
+
"epoch": 14.945868945868947,
|
| 91861 |
+
"grad_norm": 0.22192974388599396,
|
| 91862 |
+
"learning_rate": 8.078066461866277e-06,
|
| 91863 |
+
"loss": 0.6239,
|
| 91864 |
+
"step": 13122
|
| 91865 |
+
},
|
| 91866 |
+
{
|
| 91867 |
+
"epoch": 14.947008547008547,
|
| 91868 |
+
"grad_norm": 0.19137127697467804,
|
| 91869 |
+
"learning_rate": 8.074637151976695e-06,
|
| 91870 |
+
"loss": 0.7225,
|
| 91871 |
+
"step": 13123
|
| 91872 |
+
},
|
| 91873 |
+
{
|
| 91874 |
+
"epoch": 14.948148148148148,
|
| 91875 |
+
"grad_norm": 0.20317646861076355,
|
| 91876 |
+
"learning_rate": 8.071208429951515e-06,
|
| 91877 |
+
"loss": 0.7814,
|
| 91878 |
+
"step": 13124
|
| 91879 |
+
},
|
| 91880 |
+
{
|
| 91881 |
+
"epoch": 14.94928774928775,
|
| 91882 |
+
"grad_norm": 0.21901699900627136,
|
| 91883 |
+
"learning_rate": 8.067780295909816e-06,
|
| 91884 |
+
"loss": 0.5427,
|
| 91885 |
+
"step": 13125
|
| 91886 |
+
},
|
| 91887 |
+
{
|
| 91888 |
+
"epoch": 14.95042735042735,
|
| 91889 |
+
"grad_norm": 0.21417075395584106,
|
| 91890 |
+
"learning_rate": 8.064352749970663e-06,
|
| 91891 |
+
"loss": 0.7064,
|
| 91892 |
+
"step": 13126
|
| 91893 |
+
},
|
| 91894 |
+
{
|
| 91895 |
+
"epoch": 14.951566951566951,
|
| 91896 |
+
"grad_norm": 0.1974361389875412,
|
| 91897 |
+
"learning_rate": 8.060925792253127e-06,
|
| 91898 |
+
"loss": 0.9247,
|
| 91899 |
+
"step": 13127
|
| 91900 |
+
},
|
| 91901 |
+
{
|
| 91902 |
+
"epoch": 14.952706552706553,
|
| 91903 |
+
"grad_norm": 0.20048248767852783,
|
| 91904 |
+
"learning_rate": 8.057499422876214e-06,
|
| 91905 |
+
"loss": 0.6776,
|
| 91906 |
+
"step": 13128
|
| 91907 |
+
},
|
| 91908 |
+
{
|
| 91909 |
+
"epoch": 14.953846153846154,
|
| 91910 |
+
"grad_norm": 0.2453715205192566,
|
| 91911 |
+
"learning_rate": 8.054073641958936e-06,
|
| 91912 |
+
"loss": 0.5454,
|
| 91913 |
+
"step": 13129
|
| 91914 |
+
},
|
| 91915 |
+
{
|
| 91916 |
+
"epoch": 14.954985754985755,
|
| 91917 |
+
"grad_norm": 0.21314768493175507,
|
| 91918 |
+
"learning_rate": 8.050648449620284e-06,
|
| 91919 |
+
"loss": 0.6296,
|
| 91920 |
+
"step": 13130
|
| 91921 |
+
},
|
| 91922 |
+
{
|
| 91923 |
+
"epoch": 14.956125356125357,
|
| 91924 |
+
"grad_norm": 0.21752789616584778,
|
| 91925 |
+
"learning_rate": 8.04722384597923e-06,
|
| 91926 |
+
"loss": 0.6996,
|
| 91927 |
+
"step": 13131
|
| 91928 |
+
},
|
| 91929 |
+
{
|
| 91930 |
+
"epoch": 14.957264957264957,
|
| 91931 |
+
"grad_norm": 0.17562344670295715,
|
| 91932 |
+
"learning_rate": 8.043799831154703e-06,
|
| 91933 |
+
"loss": 0.7061,
|
| 91934 |
+
"step": 13132
|
| 91935 |
+
},
|
| 91936 |
+
{
|
| 91937 |
+
"epoch": 14.958404558404558,
|
| 91938 |
+
"grad_norm": 0.21547521650791168,
|
| 91939 |
+
"learning_rate": 8.040376405265637e-06,
|
| 91940 |
+
"loss": 0.5766,
|
| 91941 |
+
"step": 13133
|
| 91942 |
+
},
|
| 91943 |
+
{
|
| 91944 |
+
"epoch": 14.95954415954416,
|
| 91945 |
+
"grad_norm": 0.18879757821559906,
|
| 91946 |
+
"learning_rate": 8.03695356843094e-06,
|
| 91947 |
+
"loss": 0.7277,
|
| 91948 |
+
"step": 13134
|
| 91949 |
+
},
|
| 91950 |
+
{
|
| 91951 |
+
"epoch": 14.96068376068376,
|
| 91952 |
+
"grad_norm": 0.16375558078289032,
|
| 91953 |
+
"learning_rate": 8.033531320769502e-06,
|
| 91954 |
+
"loss": 0.5537,
|
| 91955 |
+
"step": 13135
|
| 91956 |
+
},
|
| 91957 |
+
{
|
| 91958 |
+
"epoch": 14.961823361823361,
|
| 91959 |
+
"grad_norm": 0.2281581610441208,
|
| 91960 |
+
"learning_rate": 8.03010966240017e-06,
|
| 91961 |
+
"loss": 0.3687,
|
| 91962 |
+
"step": 13136
|
| 91963 |
+
},
|
| 91964 |
+
{
|
| 91965 |
+
"epoch": 14.962962962962964,
|
| 91966 |
+
"grad_norm": 0.19088397920131683,
|
| 91967 |
+
"learning_rate": 8.026688593441789e-06,
|
| 91968 |
+
"loss": 0.9433,
|
| 91969 |
+
"step": 13137
|
| 91970 |
+
},
|
| 91971 |
+
{
|
| 91972 |
+
"epoch": 14.964102564102564,
|
| 91973 |
+
"grad_norm": 0.2279069423675537,
|
| 91974 |
+
"learning_rate": 8.023268114013205e-06,
|
| 91975 |
+
"loss": 0.6148,
|
| 91976 |
+
"step": 13138
|
| 91977 |
+
},
|
| 91978 |
+
{
|
| 91979 |
+
"epoch": 14.965242165242165,
|
| 91980 |
+
"grad_norm": 0.2353031039237976,
|
| 91981 |
+
"learning_rate": 8.019848224233198e-06,
|
| 91982 |
+
"loss": 0.4261,
|
| 91983 |
+
"step": 13139
|
| 91984 |
+
},
|
| 91985 |
+
{
|
| 91986 |
+
"epoch": 14.966381766381767,
|
| 91987 |
+
"grad_norm": 0.21128053963184357,
|
| 91988 |
+
"learning_rate": 8.01642892422056e-06,
|
| 91989 |
+
"loss": 0.6382,
|
| 91990 |
+
"step": 13140
|
| 91991 |
+
},
|
| 91992 |
+
{
|
| 91993 |
+
"epoch": 14.967521367521368,
|
| 91994 |
+
"grad_norm": 0.1791439950466156,
|
| 91995 |
+
"learning_rate": 8.013010214094047e-06,
|
| 91996 |
+
"loss": 0.716,
|
| 91997 |
+
"step": 13141
|
| 91998 |
+
},
|
| 91999 |
+
{
|
| 92000 |
+
"epoch": 14.968660968660968,
|
| 92001 |
+
"grad_norm": 0.2184140533208847,
|
| 92002 |
+
"learning_rate": 8.009592093972407e-06,
|
| 92003 |
+
"loss": 0.5625,
|
| 92004 |
+
"step": 13142
|
| 92005 |
+
},
|
| 92006 |
+
{
|
| 92007 |
+
"epoch": 14.96980056980057,
|
| 92008 |
+
"grad_norm": 0.2042216658592224,
|
| 92009 |
+
"learning_rate": 8.006174563974364e-06,
|
| 92010 |
+
"loss": 0.5908,
|
| 92011 |
+
"step": 13143
|
| 92012 |
+
},
|
| 92013 |
+
{
|
| 92014 |
+
"epoch": 14.970940170940171,
|
| 92015 |
+
"grad_norm": 0.18341132998466492,
|
| 92016 |
+
"learning_rate": 8.002757624218601e-06,
|
| 92017 |
+
"loss": 0.7578,
|
| 92018 |
+
"step": 13144
|
| 92019 |
+
},
|
| 92020 |
+
{
|
| 92021 |
+
"epoch": 14.972079772079772,
|
| 92022 |
+
"grad_norm": 0.1882096379995346,
|
| 92023 |
+
"learning_rate": 7.999341274823813e-06,
|
| 92024 |
+
"loss": 0.7151,
|
| 92025 |
+
"step": 13145
|
| 92026 |
+
},
|
| 92027 |
+
{
|
| 92028 |
+
"epoch": 14.973219373219374,
|
| 92029 |
+
"grad_norm": 0.22262947261333466,
|
| 92030 |
+
"learning_rate": 7.99592551590865e-06,
|
| 92031 |
+
"loss": 0.7037,
|
| 92032 |
+
"step": 13146
|
| 92033 |
+
},
|
| 92034 |
+
{
|
| 92035 |
+
"epoch": 14.974358974358974,
|
| 92036 |
+
"grad_norm": 0.16954749822616577,
|
| 92037 |
+
"learning_rate": 7.992510347591767e-06,
|
| 92038 |
+
"loss": 0.8455,
|
| 92039 |
+
"step": 13147
|
| 92040 |
+
},
|
| 92041 |
+
{
|
| 92042 |
+
"epoch": 14.975498575498575,
|
| 92043 |
+
"grad_norm": 0.19645527005195618,
|
| 92044 |
+
"learning_rate": 7.989095769991752e-06,
|
| 92045 |
+
"loss": 0.5582,
|
| 92046 |
+
"step": 13148
|
| 92047 |
+
},
|
| 92048 |
+
{
|
| 92049 |
+
"epoch": 14.976638176638177,
|
| 92050 |
+
"grad_norm": 0.21293814480304718,
|
| 92051 |
+
"learning_rate": 7.985681783227231e-06,
|
| 92052 |
+
"loss": 0.816,
|
| 92053 |
+
"step": 13149
|
| 92054 |
+
},
|
| 92055 |
+
{
|
| 92056 |
+
"epoch": 14.977777777777778,
|
| 92057 |
+
"grad_norm": 0.20369470119476318,
|
| 92058 |
+
"learning_rate": 7.982268387416777e-06,
|
| 92059 |
+
"loss": 0.6565,
|
| 92060 |
+
"step": 13150
|
| 92061 |
+
},
|
| 92062 |
+
{
|
| 92063 |
+
"epoch": 14.978917378917378,
|
| 92064 |
+
"grad_norm": 0.21613477170467377,
|
| 92065 |
+
"learning_rate": 7.978855582678934e-06,
|
| 92066 |
+
"loss": 0.8284,
|
| 92067 |
+
"step": 13151
|
| 92068 |
+
},
|
| 92069 |
+
{
|
| 92070 |
+
"epoch": 14.98005698005698,
|
| 92071 |
+
"grad_norm": 0.1987038254737854,
|
| 92072 |
+
"learning_rate": 7.975443369132246e-06,
|
| 92073 |
+
"loss": 0.6989,
|
| 92074 |
+
"step": 13152
|
| 92075 |
+
},
|
| 92076 |
+
{
|
| 92077 |
+
"epoch": 14.981196581196581,
|
| 92078 |
+
"grad_norm": 0.2501388490200043,
|
| 92079 |
+
"learning_rate": 7.972031746895226e-06,
|
| 92080 |
+
"loss": 0.3936,
|
| 92081 |
+
"step": 13153
|
| 92082 |
+
},
|
| 92083 |
+
{
|
| 92084 |
+
"epoch": 14.982336182336182,
|
| 92085 |
+
"grad_norm": 0.2502672076225281,
|
| 92086 |
+
"learning_rate": 7.968620716086378e-06,
|
| 92087 |
+
"loss": 0.64,
|
| 92088 |
+
"step": 13154
|
| 92089 |
+
},
|
| 92090 |
+
{
|
| 92091 |
+
"epoch": 14.983475783475784,
|
| 92092 |
+
"grad_norm": 0.21978996694087982,
|
| 92093 |
+
"learning_rate": 7.965210276824162e-06,
|
| 92094 |
+
"loss": 0.6249,
|
| 92095 |
+
"step": 13155
|
| 92096 |
+
},
|
| 92097 |
+
{
|
| 92098 |
+
"epoch": 14.984615384615385,
|
| 92099 |
+
"grad_norm": 0.22645944356918335,
|
| 92100 |
+
"learning_rate": 7.96180042922704e-06,
|
| 92101 |
+
"loss": 0.7684,
|
| 92102 |
+
"step": 13156
|
| 92103 |
+
},
|
| 92104 |
+
{
|
| 92105 |
+
"epoch": 14.985754985754985,
|
| 92106 |
+
"grad_norm": 0.170969158411026,
|
| 92107 |
+
"learning_rate": 7.958391173413444e-06,
|
| 92108 |
+
"loss": 0.9267,
|
| 92109 |
+
"step": 13157
|
| 92110 |
+
},
|
| 92111 |
+
{
|
| 92112 |
+
"epoch": 14.986894586894588,
|
| 92113 |
+
"grad_norm": 0.24624089896678925,
|
| 92114 |
+
"learning_rate": 7.954982509501793e-06,
|
| 92115 |
+
"loss": 0.5439,
|
| 92116 |
+
"step": 13158
|
| 92117 |
+
},
|
| 92118 |
+
{
|
| 92119 |
+
"epoch": 14.988034188034188,
|
| 92120 |
+
"grad_norm": 0.16725294291973114,
|
| 92121 |
+
"learning_rate": 7.951574437610459e-06,
|
| 92122 |
+
"loss": 0.6938,
|
| 92123 |
+
"step": 13159
|
| 92124 |
+
},
|
| 92125 |
+
{
|
| 92126 |
+
"epoch": 14.989173789173789,
|
| 92127 |
+
"grad_norm": 0.20970317721366882,
|
| 92128 |
+
"learning_rate": 7.948166957857837e-06,
|
| 92129 |
+
"loss": 0.6518,
|
| 92130 |
+
"step": 13160
|
| 92131 |
+
},
|
| 92132 |
+
{
|
| 92133 |
+
"epoch": 14.990313390313391,
|
| 92134 |
+
"grad_norm": 0.1861695647239685,
|
| 92135 |
+
"learning_rate": 7.944760070362276e-06,
|
| 92136 |
+
"loss": 0.8329,
|
| 92137 |
+
"step": 13161
|
| 92138 |
+
},
|
| 92139 |
+
{
|
| 92140 |
+
"epoch": 14.991452991452991,
|
| 92141 |
+
"grad_norm": 0.22031596302986145,
|
| 92142 |
+
"learning_rate": 7.941353775242092e-06,
|
| 92143 |
+
"loss": 0.8112,
|
| 92144 |
+
"step": 13162
|
| 92145 |
+
},
|
| 92146 |
+
{
|
| 92147 |
+
"epoch": 14.992592592592592,
|
| 92148 |
+
"grad_norm": 0.2391941398382187,
|
| 92149 |
+
"learning_rate": 7.937948072615603e-06,
|
| 92150 |
+
"loss": 0.3122,
|
| 92151 |
+
"step": 13163
|
| 92152 |
+
},
|
| 92153 |
+
{
|
| 92154 |
+
"epoch": 14.993732193732194,
|
| 92155 |
+
"grad_norm": 0.2180904746055603,
|
| 92156 |
+
"learning_rate": 7.934542962601096e-06,
|
| 92157 |
+
"loss": 0.6465,
|
| 92158 |
+
"step": 13164
|
| 92159 |
+
},
|
| 92160 |
+
{
|
| 92161 |
+
"epoch": 14.994871794871795,
|
| 92162 |
+
"grad_norm": 0.19434095919132233,
|
| 92163 |
+
"learning_rate": 7.931138445316855e-06,
|
| 92164 |
+
"loss": 0.5411,
|
| 92165 |
+
"step": 13165
|
| 92166 |
+
},
|
| 92167 |
+
{
|
| 92168 |
+
"epoch": 14.996011396011395,
|
| 92169 |
+
"grad_norm": 0.1636805236339569,
|
| 92170 |
+
"learning_rate": 7.927734520881103e-06,
|
| 92171 |
+
"loss": 0.7147,
|
| 92172 |
+
"step": 13166
|
| 92173 |
+
},
|
| 92174 |
+
{
|
| 92175 |
+
"epoch": 14.997150997150998,
|
| 92176 |
+
"grad_norm": 0.20240598917007446,
|
| 92177 |
+
"learning_rate": 7.924331189412082e-06,
|
| 92178 |
+
"loss": 0.5211,
|
| 92179 |
+
"step": 13167
|
| 92180 |
+
},
|
| 92181 |
+
{
|
| 92182 |
+
"epoch": 14.998290598290598,
|
| 92183 |
+
"grad_norm": 0.22989417612552643,
|
| 92184 |
+
"learning_rate": 7.920928451027996e-06,
|
| 92185 |
+
"loss": 0.4583,
|
| 92186 |
+
"step": 13168
|
| 92187 |
+
},
|
| 92188 |
+
{
|
| 92189 |
+
"epoch": 14.999430199430199,
|
| 92190 |
+
"grad_norm": 0.21044647693634033,
|
| 92191 |
+
"learning_rate": 7.917526305847042e-06,
|
| 92192 |
+
"loss": 0.6731,
|
| 92193 |
+
"step": 13169
|
| 92194 |
+
},
|
| 92195 |
+
{
|
| 92196 |
+
"epoch": 15.0,
|
| 92197 |
+
"grad_norm": 0.4262370467185974,
|
| 92198 |
+
"learning_rate": 7.914124753987367e-06,
|
| 92199 |
+
"loss": 0.5881,
|
| 92200 |
+
"step": 13170
|
| 92201 |
+
},
|
| 92202 |
+
{
|
| 92203 |
+
"epoch": 15.0011396011396,
|
| 92204 |
+
"grad_norm": 0.17920657992362976,
|
| 92205 |
+
"learning_rate": 7.910723795567119e-06,
|
| 92206 |
+
"loss": 0.8095,
|
| 92207 |
+
"step": 13171
|
| 92208 |
+
},
|
| 92209 |
+
{
|
| 92210 |
+
"epoch": 15.002279202279203,
|
| 92211 |
+
"grad_norm": 0.17844052612781525,
|
| 92212 |
+
"learning_rate": 7.907323430704444e-06,
|
| 92213 |
+
"loss": 0.5271,
|
| 92214 |
+
"step": 13172
|
| 92215 |
+
},
|
| 92216 |
+
{
|
| 92217 |
+
"epoch": 15.003418803418803,
|
| 92218 |
+
"grad_norm": 0.21409167349338531,
|
| 92219 |
+
"learning_rate": 7.903923659517424e-06,
|
| 92220 |
+
"loss": 0.6292,
|
| 92221 |
+
"step": 13173
|
| 92222 |
+
},
|
| 92223 |
+
{
|
| 92224 |
+
"epoch": 15.004558404558404,
|
| 92225 |
+
"grad_norm": 0.2429785132408142,
|
| 92226 |
+
"learning_rate": 7.90052448212415e-06,
|
| 92227 |
+
"loss": 0.5617,
|
| 92228 |
+
"step": 13174
|
| 92229 |
+
},
|
| 92230 |
+
{
|
| 92231 |
+
"epoch": 15.005698005698006,
|
| 92232 |
+
"grad_norm": 0.2211749106645584,
|
| 92233 |
+
"learning_rate": 7.897125898642683e-06,
|
| 92234 |
+
"loss": 0.4085,
|
| 92235 |
+
"step": 13175
|
| 92236 |
+
},
|
| 92237 |
+
{
|
| 92238 |
+
"epoch": 15.006837606837607,
|
| 92239 |
+
"grad_norm": 0.17734220623970032,
|
| 92240 |
+
"learning_rate": 7.893727909191075e-06,
|
| 92241 |
+
"loss": 0.6562,
|
| 92242 |
+
"step": 13176
|
| 92243 |
+
},
|
| 92244 |
+
{
|
| 92245 |
+
"epoch": 15.007977207977207,
|
| 92246 |
+
"grad_norm": 0.2056671530008316,
|
| 92247 |
+
"learning_rate": 7.890330513887332e-06,
|
| 92248 |
+
"loss": 0.6359,
|
| 92249 |
+
"step": 13177
|
| 92250 |
+
},
|
| 92251 |
+
{
|
| 92252 |
+
"epoch": 15.00911680911681,
|
| 92253 |
+
"grad_norm": 0.174454003572464,
|
| 92254 |
+
"learning_rate": 7.886933712849462e-06,
|
| 92255 |
+
"loss": 0.8016,
|
| 92256 |
+
"step": 13178
|
| 92257 |
+
},
|
| 92258 |
+
{
|
| 92259 |
+
"epoch": 15.01025641025641,
|
| 92260 |
+
"grad_norm": 0.2390289008617401,
|
| 92261 |
+
"learning_rate": 7.883537506195446e-06,
|
| 92262 |
+
"loss": 0.495,
|
| 92263 |
+
"step": 13179
|
| 92264 |
+
},
|
| 92265 |
+
{
|
| 92266 |
+
"epoch": 15.01139601139601,
|
| 92267 |
+
"grad_norm": 0.23715642094612122,
|
| 92268 |
+
"learning_rate": 7.88014189404325e-06,
|
| 92269 |
+
"loss": 0.555,
|
| 92270 |
+
"step": 13180
|
| 92271 |
+
},
|
| 92272 |
+
{
|
| 92273 |
+
"epoch": 15.012535612535613,
|
| 92274 |
+
"grad_norm": 0.1833748072385788,
|
| 92275 |
+
"learning_rate": 7.876746876510796e-06,
|
| 92276 |
+
"loss": 0.7993,
|
| 92277 |
+
"step": 13181
|
| 92278 |
+
},
|
| 92279 |
+
{
|
| 92280 |
+
"epoch": 15.013675213675214,
|
| 92281 |
+
"grad_norm": 0.17663298547267914,
|
| 92282 |
+
"learning_rate": 7.873352453716007e-06,
|
| 92283 |
+
"loss": 0.9667,
|
| 92284 |
+
"step": 13182
|
| 92285 |
+
},
|
| 92286 |
+
{
|
| 92287 |
+
"epoch": 15.014814814814814,
|
| 92288 |
+
"grad_norm": 0.19699348509311676,
|
| 92289 |
+
"learning_rate": 7.86995862577679e-06,
|
| 92290 |
+
"loss": 0.7184,
|
| 92291 |
+
"step": 13183
|
| 92292 |
+
},
|
| 92293 |
+
{
|
| 92294 |
+
"epoch": 15.015954415954416,
|
| 92295 |
+
"grad_norm": 0.20095711946487427,
|
| 92296 |
+
"learning_rate": 7.866565392811029e-06,
|
| 92297 |
+
"loss": 0.7508,
|
| 92298 |
+
"step": 13184
|
| 92299 |
+
},
|
| 92300 |
+
{
|
| 92301 |
+
"epoch": 15.017094017094017,
|
| 92302 |
+
"grad_norm": 0.17907115817070007,
|
| 92303 |
+
"learning_rate": 7.863172754936562e-06,
|
| 92304 |
+
"loss": 0.6666,
|
| 92305 |
+
"step": 13185
|
| 92306 |
+
},
|
| 92307 |
+
{
|
| 92308 |
+
"epoch": 15.018233618233618,
|
| 92309 |
+
"grad_norm": 0.19085030257701874,
|
| 92310 |
+
"learning_rate": 7.859780712271228e-06,
|
| 92311 |
+
"loss": 0.6368,
|
| 92312 |
+
"step": 13186
|
| 92313 |
+
},
|
| 92314 |
+
{
|
| 92315 |
+
"epoch": 15.01937321937322,
|
| 92316 |
+
"grad_norm": 0.20784366130828857,
|
| 92317 |
+
"learning_rate": 7.856389264932847e-06,
|
| 92318 |
+
"loss": 0.5504,
|
| 92319 |
+
"step": 13187
|
| 92320 |
+
},
|
| 92321 |
+
{
|
| 92322 |
+
"epoch": 15.02051282051282,
|
| 92323 |
+
"grad_norm": 0.1735832691192627,
|
| 92324 |
+
"learning_rate": 7.852998413039222e-06,
|
| 92325 |
+
"loss": 0.6713,
|
| 92326 |
+
"step": 13188
|
| 92327 |
+
},
|
| 92328 |
+
{
|
| 92329 |
+
"epoch": 15.021652421652421,
|
| 92330 |
+
"grad_norm": 0.1971295177936554,
|
| 92331 |
+
"learning_rate": 7.849608156708107e-06,
|
| 92332 |
+
"loss": 0.5978,
|
| 92333 |
+
"step": 13189
|
| 92334 |
+
},
|
| 92335 |
+
{
|
| 92336 |
+
"epoch": 15.022792022792023,
|
| 92337 |
+
"grad_norm": 0.17829209566116333,
|
| 92338 |
+
"learning_rate": 7.846218496057265e-06,
|
| 92339 |
+
"loss": 0.6386,
|
| 92340 |
+
"step": 13190
|
| 92341 |
+
},
|
| 92342 |
+
{
|
| 92343 |
+
"epoch": 15.023931623931624,
|
| 92344 |
+
"grad_norm": 0.19698618352413177,
|
| 92345 |
+
"learning_rate": 7.842829431204426e-06,
|
| 92346 |
+
"loss": 0.6467,
|
| 92347 |
+
"step": 13191
|
| 92348 |
+
},
|
| 92349 |
+
{
|
| 92350 |
+
"epoch": 15.025071225071224,
|
| 92351 |
+
"grad_norm": 0.2385060340166092,
|
| 92352 |
+
"learning_rate": 7.839440962267313e-06,
|
| 92353 |
+
"loss": 0.4415,
|
| 92354 |
+
"step": 13192
|
| 92355 |
+
},
|
| 92356 |
+
{
|
| 92357 |
+
"epoch": 15.026210826210827,
|
| 92358 |
+
"grad_norm": 0.19427725672721863,
|
| 92359 |
+
"learning_rate": 7.83605308936359e-06,
|
| 92360 |
+
"loss": 0.6364,
|
| 92361 |
+
"step": 13193
|
| 92362 |
+
},
|
| 92363 |
+
{
|
| 92364 |
+
"epoch": 15.027350427350427,
|
| 92365 |
+
"grad_norm": 0.18198898434638977,
|
| 92366 |
+
"learning_rate": 7.832665812610954e-06,
|
| 92367 |
+
"loss": 0.5802,
|
| 92368 |
+
"step": 13194
|
| 92369 |
+
},
|
| 92370 |
+
{
|
| 92371 |
+
"epoch": 15.028490028490028,
|
| 92372 |
+
"grad_norm": 0.21146386861801147,
|
| 92373 |
+
"learning_rate": 7.829279132127052e-06,
|
| 92374 |
+
"loss": 0.6762,
|
| 92375 |
+
"step": 13195
|
| 92376 |
+
},
|
| 92377 |
+
{
|
| 92378 |
+
"epoch": 15.02962962962963,
|
| 92379 |
+
"grad_norm": 0.22080320119857788,
|
| 92380 |
+
"learning_rate": 7.825893048029497e-06,
|
| 92381 |
+
"loss": 0.7275,
|
| 92382 |
+
"step": 13196
|
| 92383 |
+
},
|
| 92384 |
+
{
|
| 92385 |
+
"epoch": 15.03076923076923,
|
| 92386 |
+
"grad_norm": 0.1955811232328415,
|
| 92387 |
+
"learning_rate": 7.822507560435905e-06,
|
| 92388 |
+
"loss": 0.6227,
|
| 92389 |
+
"step": 13197
|
| 92390 |
+
},
|
| 92391 |
+
{
|
| 92392 |
+
"epoch": 15.031908831908831,
|
| 92393 |
+
"grad_norm": 0.14774277806282043,
|
| 92394 |
+
"learning_rate": 7.819122669463865e-06,
|
| 92395 |
+
"loss": 0.6414,
|
| 92396 |
+
"step": 13198
|
| 92397 |
+
},
|
| 92398 |
+
{
|
| 92399 |
+
"epoch": 15.033048433048434,
|
| 92400 |
+
"grad_norm": 0.17973187565803528,
|
| 92401 |
+
"learning_rate": 7.81573837523095e-06,
|
| 92402 |
+
"loss": 0.5757,
|
| 92403 |
+
"step": 13199
|
| 92404 |
+
},
|
| 92405 |
+
{
|
| 92406 |
+
"epoch": 15.034188034188034,
|
| 92407 |
+
"grad_norm": 0.23686793446540833,
|
| 92408 |
+
"learning_rate": 7.812354677854688e-06,
|
| 92409 |
+
"loss": 0.4224,
|
| 92410 |
+
"step": 13200
|
| 92411 |
}
|
| 92412 |
],
|
| 92413 |
"logging_steps": 1,
|
|
|
|
| 92427 |
"attributes": {}
|
| 92428 |
}
|
| 92429 |
},
|
| 92430 |
+
"total_flos": 7.380283043553952e+19,
|
| 92431 |
"train_batch_size": 8,
|
| 92432 |
"trial_name": null,
|
| 92433 |
"trial_params": null
|